- Linux-stable-mirror - lists.linaro.org

[Linux-stable-mirror] Patch "x86/retpoline: Fill return stack buffer on vmexit" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline: Fill return stack buffer on vmexit to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-fill-return-stack-buffer-on-vmexit.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 117cc7a908c83697b0b737d15ae1eb5943afe35b Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Fri, 12 Jan 2018 11:11:27 +0000 Subject: x86/retpoline: Fill return stack buffer on vmexit From: David Woodhouse <dwmw(a)amazon.co.uk> commit 117cc7a908c83697b0b737d15ae1eb5943afe35b upstream. In accordance with the Intel and AMD documentation, we need to overwrite all entries in the RSB on exiting a guest, to prevent malicious branch target predictions from affecting the host kernel. This is needed both for retpoline and for IBRS. [ak: numbers again for the RSB stuffing labels] Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: Rik van Riel <riel(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: thomas.lendacky(a)amd.com Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Kees Cook <keescook(a)google.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1515755487-8524-1-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/nospec-branch.h | 76 ++++++++++++++++++++++++++++++++++- arch/x86/kvm/svm.c | 4 + arch/x86/kvm/vmx.c | 4 + 3 files changed, 83 insertions(+), 1 deletion(-) --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -7,6 +7,48 @@ #include <asm/alternative-asm.h> #include <asm/cpufeature.h> +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + #ifdef __ASSEMBLY__ /* @@ -61,6 +103,19 @@ #endif .endm + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: +#endif +.endm + #else /* __ASSEMBLY__ */ #if defined(CONFIG_X86_64) && defined(RETPOLINE) @@ -97,7 +152,7 @@ X86_FEATURE_RETPOLINE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) -#else /* No retpoline */ +#else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif @@ -112,5 +167,24 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +/* + * On VMEXIT we must ensure that no RSB predictions learned in the guest + * can be followed in the host, by overwriting the RSB completely. Both + * retpoline and IBRS mitigations for Spectre v2 need this; only on future + * CPUs with IBRS_ATT *might* it be avoided. + */ +static inline void vmexit_fill_RSB(void) +{ +#ifdef CONFIG_RETPOLINE + unsigned long loops = RSB_CLEAR_LOOPS / 2; + + asm volatile (ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=&r" (loops), ASM_CALL_CONSTRAINT + : "r" (loops) : "memory" ); +#endif +} #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,6 +37,7 @@ #include <asm/desc.h> #include <asm/debugreg.h> #include <asm/kvm_para.h> +#include <asm/nospec-branch.h> #include <asm/virtext.h> #include "trace.h" @@ -3904,6 +3905,9 @@ static void svm_vcpu_run(struct kvm_vcpu #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -47,6 +47,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include "trace.h" #include "pmu.h" @@ -8701,6 +8702,9 @@ static void __noclone vmx_vcpu_run(struc #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.4/x86-spectre-add-boot-time-option-to-select-spectre-v2-mitigation.patch queue-4.4/x86-retpoline-irq32-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-hyperv-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-retpoline-ftrace-convert-ftrace-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-xen-convert-xen-hypercall-indirect-jumps.patch queue-4.4/x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-retpoline-fill-return-stack-buffer-on-vmexit.patch queue-4.4/x86-retpoline-remove-compile-time-warning.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch queue-4.4/x86-retpoline-add-initial-retpoline-support.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline/entry: Convert entry assembler indirect jumps" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline/entry: Convert entry assembler indirect jumps to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 2641f08bb7fc63a636a2b18173221d7040a3512e Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 11 Jan 2018 21:46:28 +0000 Subject: x86/retpoline/entry: Convert entry assembler indirect jumps From: David Woodhouse <dwmw(a)amazon.co.uk> commit 2641f08bb7fc63a636a2b18173221d7040a3512e upstream. Convert indirect jumps in core 32/64bit entry assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled. Don't use CALL_NOSPEC in entry_SYSCALL_64_fastpath because the return address after the 'call' instruction must be *precisely* at the .Lentry_SYSCALL_64_after_fastpath label for stub_ptregs_64 to work, and the use of alternatives will mess that up unless we play horrid games to prepend with NOPs and make the variants the same length. It's not worth it; in the case where we ALTERNATIVE out the retpoline, the first instruction at __x86.indirect_thunk.rax is going to be a bare jmp *%rax anyway. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Ingo Molnar <mingo(a)kernel.org> Acked-by: Arjan van de Ven <arjan(a)linux.intel.com> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: Rik van Riel <riel(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: thomas.lendacky(a)amd.com Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Kees Cook <keescook(a)google.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1515707194-20531-7-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_32.S | 5 +++-- arch/x86/entry/entry_64.S | 14 +++++++++++++- 2 files changed, 16 insertions(+), 3 deletions(-) --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> .section .entry.text, "ax" @@ -226,7 +227,7 @@ ENTRY(ret_from_kernel_thread) pushl $0x0202 # Reset kernel eflags popfl movl PT_EBP(%esp), %eax - call *PT_EBX(%esp) + CALL_NOSPEC PT_EBX(%esp) movl $0, PT_EAX(%esp) /* @@ -938,7 +939,7 @@ error_code: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(page_fault) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,6 +36,7 @@ #include <asm/smap.h> #include <asm/pgtable_types.h> #include <asm/kaiser.h> +#include <asm/nospec-branch.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -184,7 +185,13 @@ entry_SYSCALL_64_fastpath: #endif ja 1f /* return -ENOSYS (already in pt_regs->ax) */ movq %r10, %rcx +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif + movq %rax, RAX(%rsp) 1: /* @@ -276,7 +283,12 @@ tracesys_phase2: #endif ja 1f /* return -ENOSYS (already in pt_regs->ax) */ movq %r10, %rcx /* fixup for C */ +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif movq %rax, RAX(%rsp) 1: /* Use IRET because user could have changed pt_regs->foo */ @@ -491,7 +503,7 @@ ENTRY(ret_from_fork) * nb: we depend on RESTORE_EXTRA_REGS above */ movq %rbp, %rdi - call *%rbx + CALL_NOSPEC %rbx movl $0, RAX(%rsp) RESTORE_EXTRA_REGS jmp int_ret_from_sys_call Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.4/x86-spectre-add-boot-time-option-to-select-spectre-v2-mitigation.patch queue-4.4/x86-retpoline-irq32-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-hyperv-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-retpoline-ftrace-convert-ftrace-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-xen-convert-xen-hypercall-indirect-jumps.patch queue-4.4/x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-retpoline-fill-return-stack-buffer-on-vmexit.patch queue-4.4/x86-retpoline-remove-compile-time-warning.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch queue-4.4/x86-retpoline-add-initial-retpoline-support.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline/crypto: Convert crypto assembler indirect jumps" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline/crypto: Convert crypto assembler indirect jumps to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 9697fa39efd3fc3692f2949d4045f393ec58450b Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 11 Jan 2018 21:46:27 +0000 Subject: x86/retpoline/crypto: Convert crypto assembler indirect jumps From: David Woodhouse <dwmw(a)amazon.co.uk> commit 9697fa39efd3fc3692f2949d4045f393ec58450b upstream. Convert all indirect jumps in crypto assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Arjan van de Ven <arjan(a)linux.intel.com> Acked-by: Ingo Molnar <mingo(a)kernel.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: Rik van Riel <riel(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: thomas.lendacky(a)amd.com Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Kees Cook <keescook(a)google.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1515707194-20531-6-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/crypto/aesni-intel_asm.S | 5 +++-- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 3 ++- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 3 ++- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 3 ++- 4 files changed, 9 insertions(+), 5 deletions(-) --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -31,6 +31,7 @@ #include <linux/linkage.h> #include <asm/inst.h> +#include <asm/nospec-branch.h> /* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2714,7 +2715,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2759,7 +2760,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x40(OUTP), INC pxor INC, STATE1 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -16,6 +16,7 @@ */ #include <linux/linkage.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1210,7 +1211,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 16), %rsp; --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -11,6 +11,7 @@ */ #include <linux/linkage.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1323,7 +1324,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 32), %rsp; --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@ #include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h> ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction @@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len offset=crc_array-jump_table lea offset(bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp ################################################################ ## 2a) PROCESS FULL BLOCKS: Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.4/x86-spectre-add-boot-time-option-to-select-spectre-v2-mitigation.patch queue-4.4/x86-retpoline-irq32-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-hyperv-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-retpoline-ftrace-convert-ftrace-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-xen-convert-xen-hypercall-indirect-jumps.patch queue-4.4/x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-retpoline-fill-return-stack-buffer-on-vmexit.patch queue-4.4/x86-retpoline-remove-compile-time-warning.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch queue-4.4/x86-retpoline-add-initial-retpoline-support.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline/checksum32: Convert assembler indirect jumps" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline/checksum32: Convert assembler indirect jumps to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5096732f6f695001fa2d6f1335a2680b37912c69 Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 11 Jan 2018 21:46:32 +0000 Subject: x86/retpoline/checksum32: Convert assembler indirect jumps From: David Woodhouse <dwmw(a)amazon.co.uk> commit 5096732f6f695001fa2d6f1335a2680b37912c69 upstream. Convert all indirect jumps in 32bit checksum assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Arjan van de Ven <arjan(a)linux.intel.com> Acked-by: Ingo Molnar <mingo(a)kernel.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: Rik van Riel <riel(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: thomas.lendacky(a)amd.com Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Kees Cook <keescook(a)google.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1515707194-20531-11-git-send-email-dwmw@amazon.co… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/lib/checksum_32.S | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -28,7 +28,8 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/asm.h> - +#include <asm/nospec-branch.h> + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -155,7 +156,7 @@ 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 @@ -437,7 +438,7 @@ 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) Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.4/x86-spectre-add-boot-time-option-to-select-spectre-v2-mitigation.patch queue-4.4/x86-retpoline-irq32-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-hyperv-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-retpoline-ftrace-convert-ftrace-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-xen-convert-xen-hypercall-indirect-jumps.patch queue-4.4/x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-retpoline-fill-return-stack-buffer-on-vmexit.patch queue-4.4/x86-retpoline-remove-compile-time-warning.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch queue-4.4/x86-retpoline-add-initial-retpoline-support.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline: Add initial retpoline support" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline: Add initial retpoline support to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-add-initial-retpoline-support.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 76b043848fd22dbf7f8bf3a1452f8c70d557b860 Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 11 Jan 2018 21:46:25 +0000 Subject: x86/retpoline: Add initial retpoline support From: David Woodhouse <dwmw(a)amazon.co.uk> commit 76b043848fd22dbf7f8bf3a1452f8c70d557b860 upstream. 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 <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Arjan van de Ven <arjan(a)linux.intel.com> Acked-by: Ingo Molnar <mingo(a)kernel.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: Rik van Riel <riel(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: thomas.lendacky(a)amd.com Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Kees Cook <keescook(a)google.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1515707194-20531-4-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> [ 4.4 backport: removed objtool annotation since there is no objtool ] Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/Kconfig | 13 ++++ arch/x86/Makefile | 10 +++ arch/x86/include/asm/asm-prototypes.h | 25 ++++++++ arch/x86/include/asm/cpufeature.h | 2 arch/x86/include/asm/nospec-branch.h | 106 ++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 4 + arch/x86/lib/Makefile | 1 arch/x86/lib/retpoline.S | 48 +++++++++++++++ 8 files changed, 209 insertions(+) create mode 100644 arch/x86/include/asm/nospec-branch.h create mode 100644 arch/x86/lib/retpoline.S --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -379,6 +379,19 @@ 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. + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -189,6 +189,16 @@ KBUILD_CFLAGS += -fno-asynchronous-unwin KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) +# 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 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -10,7 +10,32 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h> #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 */ --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -200,6 +200,8 @@ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +#define X86_FEATURE_RETPOLINE ( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeature.h> + +#ifdef __ASSEMBLY__ + +/* + * 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 + 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 + 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__ */ + +#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 \ + 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 $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -837,6 +837,10 @@ static void __init early_identify_cpu(st setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); +#ifdef CONFIG_RETPOLINE + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); +#endif + fpu__init_system(c); #ifdef CONFIG_X86_32 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -21,6 +21,7 @@ lib-y += usercopy_$(BITS).o usercopy.o g lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o +lib-$(CONFIG_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> +#include <asm-generic/export.h> +#include <asm/nospec-branch.h> + +.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 Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.4/x86-spectre-add-boot-time-option-to-select-spectre-v2-mitigation.patch queue-4.4/x86-retpoline-irq32-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-hyperv-convert-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-entry-convert-entry-assembler-indirect-jumps.patch queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-retpoline-ftrace-convert-ftrace-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-crypto-convert-crypto-assembler-indirect-jumps.patch queue-4.4/x86-retpoline-xen-convert-xen-hypercall-indirect-jumps.patch queue-4.4/x86-retpoline-checksum32-convert-assembler-indirect-jumps.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-retpoline-fill-return-stack-buffer-on-vmexit.patch queue-4.4/x86-retpoline-remove-compile-time-warning.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch queue-4.4/x86-retpoline-add-initial-retpoline-support.patch

7 years, 5 months

1
0
0 0

Re: [Linux-stable-mirror] Linux 3.18.92

by Greg KH

On Wed, Jan 17, 2018 at 10:38:30AM +0000, Harsh Shandilya wrote: > On Wed 17 Jan, 2018, 3:11 PM Greg KH, <gregkh(a)linuxfoundation.org> wrote: > > > I'm announcing the release of the 3.18.92 kernel. > > > > All users of the 3.18 kernel series must upgrade. > > > > The updated 3.18.y git tree can be found at: > > git:// > > git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git > > linux-3.18.y > > and can be browsed at the normal kernel.org git web browser: > > > > http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary > > > > thanks, > > > > greg k-h > > > > Builds and boots on the OnePlus 3T, no regressions noticed in general usage. Great, thanks for testing and letting me know. greg k-h

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From b8b7abaed7a49b350f8ba659ddc264b04931d581 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski <luto(a)kernel.org> Date: Sun, 17 Sep 2017 09:03:50 -0700 Subject: x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier From: Andy Lutomirski <luto(a)kernel.org> commit b8b7abaed7a49b350f8ba659ddc264b04931d581 upstream. Otherwise we might have the PCID feature bit set during cpu_init(). This is just for robustness. I haven't seen any actual bugs here. Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bpetkov(a)suse.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Fixes: cba4671af755 ("x86/mm: Disable PCID on 32-bit kernels") Link: http://lkml.kernel.org/r/b16dae9d6b0db5d9801ddbebbfd83384097c61f3.150566353… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 8 -------- arch/x86/kernel/cpu/common.c | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -22,14 +22,6 @@ void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -838,6 +838,14 @@ static void __init early_identify_cpu(st setup_force_cpu_bug(X86_BUG_SPECTRE_V2); fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) Patches currently in stable-queue which might be from luto(a)kernel.org are queue-4.4/x86-asm-use-register-variable-to-get-stack-pointer-value.patch queue-4.4/x86-mm-32-move-setup_clear_cpu_cap-x86_feature_pcid-earlier.patch queue-4.4/x86-asm-make-asm-alternative.h-safe-from-assembly.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/kbuild: enable modversions for symbols exported from asm" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/kbuild: enable modversions for symbols exported from asm to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-kbuild-enable-modversions-for-symbols-exported-from-asm.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 334bb773876403eae3457d81be0b8ea70f8e4ccc Mon Sep 17 00:00:00 2001 From: Adam Borowski <kilobyte(a)angband.pl> Date: Sun, 11 Dec 2016 02:09:18 +0100 Subject: x86/kbuild: enable modversions for symbols exported from asm From: Adam Borowski <kilobyte(a)angband.pl> commit 334bb773876403eae3457d81be0b8ea70f8e4ccc upstream. Commit 4efca4ed ("kbuild: modversions for EXPORT_SYMBOL() for asm") adds modversion support for symbols exported from asm files. Architectures must include C-style declarations for those symbols in asm/asm-prototypes.h in order for them to be versioned. Add these declarations for x86, and an architecture-independent file that can be used for common symbols. With f27c2f6 reverting 8ab2ae6 ("default exported asm symbols to zero") we produce a scary warning on x86, this commit fixes that. Signed-off-by: Adam Borowski <kilobyte(a)angband.pl> Tested-by: Kalle Valo <kvalo(a)codeaurora.org> Acked-by: Nicholas Piggin <npiggin(a)gmail.com> Tested-by: Peter Wu <peter(a)lekensteyn.nl> Tested-by: Oliver Hartkopp <socketcan(a)hartkopp.net> Signed-off-by: Michal Marek <mmarek(a)suse.com> Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/asm-prototypes.h | 16 ++++++++++++++++ include/asm-generic/asm-prototypes.h | 7 +++++++ 2 files changed, 23 insertions(+) --- /dev/null +++ b/arch/x86/include/asm/asm-prototypes.h @@ -0,0 +1,16 @@ +#include <asm/ftrace.h> +#include <asm/uaccess.h> +#include <asm/string.h> +#include <asm/page.h> +#include <asm/checksum.h> + +#include <asm-generic/asm-prototypes.h> + +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/special_insns.h> +#include <asm/preempt.h> + +#ifndef CONFIG_X86_CMPXCHG64 +extern void cmpxchg8b_emu(void); +#endif --- /dev/null +++ b/include/asm-generic/asm-prototypes.h @@ -0,0 +1,7 @@ +#include <linux/bitops.h> +extern void *__memset(void *, int, __kernel_size_t); +extern void *__memcpy(void *, const void *, __kernel_size_t); +extern void *__memmove(void *, const void *, __kernel_size_t); +extern void *memset(void *, int, __kernel_size_t); +extern void *memcpy(void *, const void *, __kernel_size_t); +extern void *memmove(void *, const void *, __kernel_size_t); Patches currently in stable-queue which might be from kilobyte(a)angband.pl are queue-4.4/x86-kbuild-enable-modversions-for-symbols-exported-from-asm.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpu/AMD: Make LFENCE a serializing instruction" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpu/AMD: Make LFENCE a serializing instruction to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpu-amd-make-lfence-a-serializing-instruction.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From e4d0e84e490790798691aaa0f2e598637f1867ec Mon Sep 17 00:00:00 2001 From: Tom Lendacky <thomas.lendacky(a)amd.com> Date: Mon, 8 Jan 2018 16:09:21 -0600 Subject: x86/cpu/AMD: Make LFENCE a serializing instruction From: Tom Lendacky <thomas.lendacky(a)amd.com> commit e4d0e84e490790798691aaa0f2e598637f1867ec upstream. To aid in speculation control, make LFENCE a serializing instruction since it has less overhead than MFENCE. This is done by setting bit 1 of MSR 0xc0011029 (DE_CFG). Some families that support LFENCE do not have this MSR. For these families, the LFENCE instruction is already serializing. Signed-off-by: Tom Lendacky <thomas.lendacky(a)amd.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Reviewed-by: Borislav Petkov <bp(a)suse.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/20180108220921.12580.71694.stgit@tlendack-t1.amdo… Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/msr-index.h | 2 ++ arch/x86/kernel/cpu/amd.c | 10 ++++++++++ 2 files changed, 12 insertions(+) --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -330,6 +330,8 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -746,6 +746,16 @@ static void init_amd(struct cpuinfo_x86 set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + /* MFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } Patches currently in stable-queue which might be from thomas.lendacky(a)amd.com are queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch

7 years, 5 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 9c6a73c75864ad9fa49e5fa6513e4c4071c0e29f Mon Sep 17 00:00:00 2001 From: Tom Lendacky <thomas.lendacky(a)amd.com> Date: Mon, 8 Jan 2018 16:09:32 -0600 Subject: x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC From: Tom Lendacky <thomas.lendacky(a)amd.com> commit 9c6a73c75864ad9fa49e5fa6513e4c4071c0e29f upstream. With LFENCE now a serializing instruction, use LFENCE_RDTSC in preference to MFENCE_RDTSC. However, since the kernel could be running under a hypervisor that does not support writing that MSR, read the MSR back and verify that the bit has been set successfully. If the MSR can be read and the bit is set, then set the LFENCE_RDTSC feature, otherwise set the MFENCE_RDTSC feature. Signed-off-by: Tom Lendacky <thomas.lendacky(a)amd.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Reviewed-by: Borislav Petkov <bp(a)suse.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/20180108220932.12580.52458.stgit@tlendack-t1.amdo… Signed-off-by: Razvan Ghitulete <rga(a)amazon.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/amd.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -332,6 +332,7 @@ #define MSR_FAM10H_NODE_ID 0xc001100c #define MSR_F10H_DECFG 0xc0011029 #define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -746,6 +746,9 @@ static void init_amd(struct cpuinfo_x86 set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { + unsigned long long val; + int ret; + /* * A serializing LFENCE has less overhead than MFENCE, so * use it for execution serialization. On families which @@ -756,8 +759,19 @@ static void init_amd(struct cpuinfo_x86 msr_set_bit(MSR_F10H_DECFG, MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* Patches currently in stable-queue which might be from thomas.lendacky(a)amd.com are queue-4.4/x86-cpu-amd-make-lfence-a-serializing-instruction.patch queue-4.4/x86-cpu-amd-use-lfence_rdtsc-in-preference-to-mfence_rdtsc.patch

7 years, 5 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror