From e6c591e7a430197777a6456a3cd2db38fffd7647 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 25 Apr 2016 17:35:29 +0200 Subject: [PATCH 01/55] gcov: disable for COMPILE_TEST commit cc622420798c4bcf093785d872525087a7798db9 upstream. Enabling gcov is counterproductive to compile testing: it significantly increases the kernel image size, compile time, and it produces lots of false positive "may be used uninitialized" warnings as the result of missed optimizations. This is in line with how UBSAN_SANITIZE_ALL and PROFILE_ALL_BRANCHES work, both of which have similar problems. With an ARM allmodconfig kernel, I see the build time drop from 283 minutes CPU time to 225 minutes, and the vmlinux size drops from 43MB to 26MB. Signed-off-by: Arnd Bergmann Acked-by: Peter Oberparleiter Signed-off-by: Michal Marek Signed-off-by: Greg Kroah-Hartman --- kernel/gcov/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index c92e44855ddd..1276aabaab55 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL config GCOV_PROFILE_ALL bool "Profile entire Kernel" + depends on !COMPILE_TEST depends on GCOV_KERNEL depends on ARCH_HAS_GCOV_PROFILE_ALL default n From 20c28c04a6bc2ebd60fa20e5c3a6bf3bfa736d81 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 8 Jan 2018 16:09:21 -0600 Subject: [PATCH 02/55] x86/cpu/AMD: Make LFENCE a serializing instruction 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 Signed-off-by: Thomas Gleixner Reviewed-by: Reviewed-by: Borislav Petkov Cc: Peter Zijlstra Cc: Tim Chen Cc: Dave Hansen Cc: Borislav Petkov Cc: Dan Williams Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: David Woodhouse Cc: Paul Turner Link: https://lkml.kernel.org/r/20180108220921.12580.71694.stgit@tlendack-t1.amdoffice.net Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/msr-index.h | 2 ++ arch/x86/kernel/cpu/amd.c | 10 ++++++++++ 2 files changed, 12 insertions(+) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 37db36fddc88..f00dfff81370 100644 --- 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 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e2defc7593a4..7f2e9c6ff239 100644 --- 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 *c) 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); } From 642ce1bb5ea64b1d036dff04a005d9bbe28ab5b4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 8 Jan 2018 16:09:32 -0600 Subject: [PATCH 03/55] x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC 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 Signed-off-by: Thomas Gleixner Reviewed-by: Reviewed-by: Borislav Petkov Cc: Peter Zijlstra Cc: Tim Chen Cc: Dave Hansen Cc: Borislav Petkov Cc: Dan Williams Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: David Woodhouse Cc: Paul Turner Link: https://lkml.kernel.org/r/20180108220932.12580.52458.stgit@tlendack-t1.amdoffice.net Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/amd.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f00dfff81370..b8911aecf035 100644 --- 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 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7f2e9c6ff239..4bf9e77f3e05 100644 --- 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 *c) 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 *c) 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); + } } /* From 416f66509fce36e128ea2d9e62739a21f1a1d04d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 17 Sep 2017 09:03:50 -0700 Subject: [PATCH 04/55] x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier 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 Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: cba4671af755 ("x86/mm: Disable PCID on 32-bit kernels") Link: http://lkml.kernel.org/r/b16dae9d6b0db5d9801ddbebbfd83384097c61f3.1505663533.git.luto@kernel.org Signed-off-by: Ingo Molnar Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 8 -------- arch/x86/kernel/cpu/common.c | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cd46f9039119..cb6b4f9d0b7a 100644 --- 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)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dc4dfad66a70..0531c1707b40 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -838,6 +838,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) 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) From cfc8c1d61e46fd3c60a34a5b1962eeeb03222a3d Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 29 Sep 2017 17:15:36 +0300 Subject: [PATCH 05/55] x86/asm: Use register variable to get stack pointer value commit 196bd485ee4f03ce4c690bfcf38138abfcd0a4bc upstream. Currently we use current_stack_pointer() function to get the value of the stack pointer register. Since commit: f5caf621ee35 ("x86/asm: Fix inline asm call constraints for Clang") ... we have a stack register variable declared. It can be used instead of current_stack_pointer() function which allows to optimize away some excessive "mov %rsp, %" instructions: -mov %rsp,%rdx -sub %rdx,%rax -cmp $0x3fff,%rax -ja ffffffff810722fd +sub %rsp,%rax +cmp $0x3fff,%rax +ja ffffffff810722fa Remove current_stack_pointer(), rename __asm_call_sp to current_stack_pointer and use it instead of the removed function. Signed-off-by: Andrey Ryabinin Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170929141537.29167-1-aryabinin@virtuozzo.com Signed-off-by: Ingo Molnar [dwmw2: We want ASM_CALL_CONSTRAINT for retpoline] Signed-off-by: David Woodhouse Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/asm.h | 11 +++++++++++ arch/x86/include/asm/thread_info.h | 11 ----------- arch/x86/kernel/irq_32.c | 6 +++--- arch/x86/kernel/traps.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 189679aba703..b9c6c7a6f5a6 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -105,4 +105,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif +#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c7b551028740..9b028204685d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -166,17 +166,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); } -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 38da8f29a9c8..647089c64d13 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -65,7 +65,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -89,7 +89,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -142,7 +142,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 679302c312f8..22b81f35c500 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -166,7 +166,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } From b76ac90af34dc08f057da15aa34584a0a3d381b5 Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Sun, 11 Dec 2016 02:09:18 +0100 Subject: [PATCH 06/55] x86/kbuild: enable modversions for symbols exported from asm 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 Tested-by: Kalle Valo Acked-by: Nicholas Piggin Tested-by: Peter Wu Tested-by: Oliver Hartkopp Signed-off-by: Michal Marek Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/asm-prototypes.h | 16 ++++++++++++++++ include/asm-generic/asm-prototypes.h | 7 +++++++ 2 files changed, 23 insertions(+) create mode 100644 arch/x86/include/asm/asm-prototypes.h create mode 100644 include/asm-generic/asm-prototypes.h diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..44b8762fa0c7 --- /dev/null +++ b/arch/x86/include/asm/asm-prototypes.h @@ -0,0 +1,16 @@ +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include + +#ifndef CONFIG_X86_CMPXCHG64 +extern void cmpxchg8b_emu(void); +#endif diff --git a/include/asm-generic/asm-prototypes.h b/include/asm-generic/asm-prototypes.h new file mode 100644 index 000000000000..df13637e4017 --- /dev/null +++ b/include/asm-generic/asm-prototypes.h @@ -0,0 +1,7 @@ +#include +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); From b8e7a489b51810992ba3266bfd9e043709e07267 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 26 Apr 2016 12:23:25 -0700 Subject: [PATCH 07/55] x86/asm: Make asm/alternative.h safe from assembly commit f005f5d860e0231fe212cfda8c1a3148b99609f4 upstream. asm/alternative.h isn't directly useful from assembly, but it shouldn't break the build. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/e5b693fcef99fe6e80341c9e97a002fb23871e91.1461698311.git.luto@kernel.org Signed-off-by: Ingo Molnar Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/alternative.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index d1cf17173b1b..215ea9214215 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H +#ifndef __ASSEMBLY__ + #include #include #include @@ -271,4 +273,6 @@ extern void *text_poke(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_ALTERNATIVE_H */ From a88693d006986b8fc9ae5036852ac0156106de2a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 11 Jan 2016 10:54:54 -0500 Subject: [PATCH 08/55] EXPORT_SYMBOL() for asm commit 22823ab419d8ed884195cfa75483fd3a99bb1462 upstream. Add asm-usable variants of EXPORT_SYMBOL/EXPORT_SYMBOL_GPL. This commit just adds the default implementation; most of the architectures can simply add export.h to asm/Kbuild and start using from assembler. The rest needs to have their define everal macros and then explicitly include One area where the things might diverge from default is the alignment; normally it's 8 bytes on 64bit targets and 4 on 32bit ones, both for unsigned long and for struct kernel_symbol. Unfortunately, amd64 and m68k are unusual - m68k aligns to 2 bytes (for both) and amd64 aligns struct kernel_symbol to 16 bytes. For those we'll need asm/export.h to override the constants used by generic version - KSYM_ALIGN and KCRC_ALIGN for kernel_symbol and unsigned long resp. And no, __alignof__ would not do the trick - on amd64 __alignof__ of struct kernel_symbol is 8, not 16. More serious source of unpleasantness is treatment of function descriptors on architectures that have those. Things like ppc64, parisc, ia64, etc. need more than the address of the first insn to call an arbitrary function. As the result, their representation of pointers to functions is not the typical "address of the entry point" - it's an address of a small static structure containing all the required information (including the entry point, of course). Sadly, the asm-side conventions differ in what the function name refers to - entry point or the function descriptor. On ppc64 we do the latter; bar: .quad foo is what void (*bar)(void) = foo; turns into and the rare places where we need to explicitly work with the label of entry point are dealt with as DOTSYM(foo). For our purposes it's ideal - generic macros are usable. However, parisc would have foo and P%foo used for label of entry point and address of the function descriptor and bar: .long P%foo woudl be used instead. ia64 goes similar to parisc in that respect, except that there it's @fptr(foo) rather than P%foo. Such architectures need to define KSYM_FUNC that would turn a function name into whatever is needed to refer to function descriptor. What's more, on such architectures we need to know whether we are exporting a function or an object - in assembler we have to tell that explicitly, to decide whether we want EXPORT_SYMBOL(foo) produce e.g. __ksymtab_foo: .quad foo or __ksymtab_foo: .quad @fptr(foo) For that reason we introduce EXPORT_DATA_SYMBOL{,_GPL}(), to be used for exports of data objects. On normal architectures it's the same thing as EXPORT_SYMBOL{,_GPL}(), but on parisc-like ones they differ and the right one needs to be used. Most of the exports are functions, so we keep EXPORT_SYMBOL for those... Signed-off-by: Al Viro Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/export.h | 94 ++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 include/asm-generic/export.h diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h new file mode 100644 index 000000000000..43199a049da5 --- /dev/null +++ b/include/asm-generic/export.h @@ -0,0 +1,94 @@ +#ifndef __ASM_GENERIC_EXPORT_H +#define __ASM_GENERIC_EXPORT_H + +#ifndef KSYM_FUNC +#define KSYM_FUNC(x) x +#endif +#ifdef CONFIG_64BIT +#define __put .quad +#ifndef KSYM_ALIGN +#define KSYM_ALIGN 8 +#endif +#ifndef KCRC_ALIGN +#define KCRC_ALIGN 8 +#endif +#else +#define __put .long +#ifndef KSYM_ALIGN +#define KSYM_ALIGN 4 +#endif +#ifndef KCRC_ALIGN +#define KCRC_ALIGN 4 +#endif +#endif + +#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX +#define KSYM(name) _##name +#else +#define KSYM(name) name +#endif + +/* + * note on .section use: @progbits vs %progbits nastiness doesn't matter, + * since we immediately emit into those sections anyway. + */ +.macro ___EXPORT_SYMBOL name,val,sec +#ifdef CONFIG_MODULES + .globl KSYM(__ksymtab_\name) + .section ___ksymtab\sec+\name,"a" + .balign KSYM_ALIGN +KSYM(__ksymtab_\name): + __put \val, KSYM(__kstrtab_\name) + .previous + .section __ksymtab_strings,"a" +KSYM(__kstrtab_\name): +#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX + .asciz "_\name" +#else + .asciz "\name" +#endif + .previous +#ifdef CONFIG_MODVERSIONS + .section ___kcrctab\sec+\name,"a" + .balign KCRC_ALIGN +KSYM(__kcrctab_\name): + __put KSYM(__crc_\name) + .weak KSYM(__crc_\name) + .previous +#endif +#endif +.endm +#undef __put + +#if defined(__KSYM_DEPS__) + +#define __EXPORT_SYMBOL(sym, val, sec) === __KSYM_##sym === + +#elif defined(CONFIG_TRIM_UNUSED_KSYMS) + +#include +#include + +#define __EXPORT_SYMBOL(sym, val, sec) \ + __cond_export_sym(sym, val, sec, config_enabled(__KSYM_##sym)) +#define __cond_export_sym(sym, val, sec, conf) \ + ___cond_export_sym(sym, val, sec, conf) +#define ___cond_export_sym(sym, val, sec, enabled) \ + __cond_export_sym_##enabled(sym, val, sec) +#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec +#define __cond_export_sym_0(sym, val, sec) /* nothing */ + +#else +#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec +#endif + +#define EXPORT_SYMBOL(name) \ + __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),) +#define EXPORT_SYMBOL_GPL(name) \ + __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl) +#define EXPORT_DATA_SYMBOL(name) \ + __EXPORT_SYMBOL(name, KSYM(name),) +#define EXPORT_DATA_SYMBOL_GPL(name) \ + __EXPORT_SYMBOL(name, KSYM(name),_gpl) + +#endif From 675901851fd2a00c7a70bcf327303efba3b81e2f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:54 +0900 Subject: [PATCH 09/55] kconfig.h: use __is_defined() to check if MODULE is defined commit 4f920843d248946545415c1bf6120942048708ed upstream. The macro MODULE is not a config option, it is a per-file build option. So, config_enabled(MODULE) is not sensible. (There is another case in include/linux/export.h, where config_enabled() is used against a non-config option.) This commit renames some macros in include/linux/kconfig.h for the use for non-config macros and replaces config_enabled(MODULE) with __is_defined(MODULE). I am keeping config_enabled() because it is still referenced from some places, but I expect it would be deprecated in the future. Signed-off-by: Masahiro Yamada Signed-off-by: Michal Marek Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- include/linux/kconfig.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index b33c7797eb57..a94b5bf57f51 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -17,10 +17,11 @@ * the last step cherry picks the 2nd arg, we get a zero. */ #define __ARG_PLACEHOLDER_1 0, -#define config_enabled(cfg) _config_enabled(cfg) -#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value) -#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0) -#define ___config_enabled(__ignored, val, ...) val +#define config_enabled(cfg) ___is_defined(cfg) +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) +#define __take_second_arg(__ignored, val, ...) val /* * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 @@ -42,7 +43,7 @@ * built-in code when CONFIG_FOO is set to 'm'. */ #define IS_REACHABLE(option) (config_enabled(option) || \ - (config_enabled(option##_MODULE) && config_enabled(MODULE))) + (config_enabled(option##_MODULE) && __is_defined(MODULE))) /* * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', From 3c5e10905263dbe9fbc621d1889b85e9c867da25 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:25 +0000 Subject: [PATCH 10/55] x86/retpoline: Add initial retpoline support 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 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 Signed-off-by: David Woodhouse [ 4.4 backport: removed objtool annotation since there is no objtool ] Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- 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 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0ef2cdd11616..75d0053b495a 100644 --- 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" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4086abca0b32..34fdac520edb 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -189,6 +189,16 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables 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 diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 44b8762fa0c7..b15aa4083dfd 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -10,7 +10,32 @@ #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/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 142028afd049..0fbc98568018 100644 --- 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 */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..5763548fb30b --- /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 +#include +#include + +#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 $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0531c1707b40..5b3a6e888bc5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -837,6 +837,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); +#ifdef CONFIG_RETPOLINE + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); +#endif + fpu__init_system(c); #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2587888d987..12a34d15b648 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -21,6 +21,7 @@ lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o 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 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..019a03599bb0 --- /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 From 9f789bc5711bcacb5df003594b992f0c1cc19df4 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:26 +0000 Subject: [PATCH 11/55] x86/spectre: Add boot time option to select Spectre v2 mitigation commit da285121560e769cc31797bba6422eea71d473e0 upstream. Add a spectre_v2= option to select the mitigation used for the indirect branch speculation vulnerability. Currently, the only option available is retpoline, in its various forms. This will be expanded to cover the new IBRS/IBPB microcode features. The RETPOLINE_AMD feature relies on a serializing LFENCE for speculation control. For AMD hardware, only set RETPOLINE_AMD if LFENCE is a serializing instruction, which is indicated by the LFENCE_RDTSC feature. [ tglx: Folded back the LFENCE/AMD fixes and reworked it so IBRS integration becomes simple ] Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner 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/1515707194-20531-5-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 28 +++++ arch/x86/include/asm/nospec-branch.h | 10 ++ arch/x86/kernel/cpu/bugs.c | 158 ++++++++++++++++++++++++++- arch/x86/kernel/cpu/common.c | 4 - 4 files changed, 195 insertions(+), 5 deletions(-) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 39280b72f27a..22a4688dc0c8 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2452,6 +2452,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nohugeiomap [KNL,x86] Disable kernel huge I/O mappings. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 + (indirect branch prediction) vulnerability. System may + allow data leaks with this option, which is equivalent + to spectre_v2=off. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. @@ -3594,6 +3599,29 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/laptops/sonypi.txt + spectre_v2= [X86] Control mitigation of Spectre variant 2 + (indirect branch speculation) vulnerability. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable + + Selecting 'on' will, and 'auto' may, choose a + mitigation method at run time according to the + CPU, the available microcode, the setting of the + CONFIG_RETPOLINE configuration option, and the + compiler with which the kernel was built. + + Specific mitigations can also be selected manually: + + retpoline - replace indirect branches + retpoline,generic - google's original retpoline + retpoline,amd - AMD-specific minimal thunk + + Not specifying this option is equivalent to + spectre_v2=auto. + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 5763548fb30b..fe48aeee79d1 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -102,5 +102,15 @@ # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE_MINIMAL, + SPECTRE_V2_RETPOLINE_MINIMAL_AMD, + SPECTRE_V2_RETPOLINE_GENERIC, + SPECTRE_V2_RETPOLINE_AMD, + SPECTRE_V2_IBRS, +}; + #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cb6b4f9d0b7a..49d25ddf0e9f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,9 @@ #include #include #include + +#include +#include #include #include #include @@ -20,6 +23,8 @@ #include #include +static void __init spectre_v2_select_mitigation(void); + void __init check_bugs(void) { identify_boot_cpu(); @@ -29,6 +34,9 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -61,6 +69,153 @@ void __init check_bugs(void) #endif } +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret; + + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret > 0) { + if (match_option(arg, ret, "off")) { + goto disable; + } else if (match_option(arg, ret, "on")) { + spec2_print_if_secure("force enabled on command line."); + return SPECTRE_V2_CMD_FORCE; + } else if (match_option(arg, ret, "retpoline")) { + spec2_print_if_insecure("retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE; + } else if (match_option(arg, ret, "retpoline,amd")) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + spec2_print_if_insecure("AMD retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_AMD; + } else if (match_option(arg, ret, "retpoline,generic")) { + spec2_print_if_insecure("generic retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_GENERIC; + } else if (match_option(arg, ret, "auto")) { + return SPECTRE_V2_CMD_AUTO; + } + } + + if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_AUTO; +disable: + spec2_print_if_insecure("disabled on command line."); + return SPECTRE_V2_CMD_NONE; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + /* FALLTRHU */ + case SPECTRE_V2_CMD_AUTO: + goto retpoline_auto; + + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); +} + +#undef pr_fmt + #ifdef CONFIG_SYSFS ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -85,6 +240,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + + return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5b3a6e888bc5..0531c1707b40 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -837,10 +837,6 @@ 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 From 9fe55976f0c8acfd7408bf693b6d171587b62129 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:27 +0000 Subject: [PATCH 12/55] x86/retpoline/crypto: Convert crypto assembler indirect jumps 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 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/1515707194-20531-6-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- 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(-) diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 6bd2c6c95373..3f93dedb5a4d 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -31,6 +31,7 @@ #include #include +#include /* * 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 diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index ce71f9212409..5881756f78a2 100644 --- 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 +#include #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; diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 0e0b8863a34b..0d45b04b490a 100644 --- 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 +#include #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; diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 4fe27e074194..48767520cbe0 100644 --- 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 #include +#include ## 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: From 028083cb02db69237e73950576bc81ac579693dc Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:28 +0000 Subject: [PATCH 13/55] x86/retpoline/entry: Convert entry assembler indirect jumps 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 Signed-off-by: Thomas Gleixner Acked-by: Ingo Molnar Acked-by: Arjan van de Ven 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/1515707194-20531-7-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_32.S | 6 ++++-- arch/x86/entry/entry_64.S | 14 +++++++++++++- 2 files changed, 17 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ae678ad128a9..adbbd4f538e9 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include #include #include +#include .section .entry.text, "ax" @@ -226,7 +227,8 @@ ENTRY(ret_from_kernel_thread) pushl $0x0202 # Reset kernel eflags popfl movl PT_EBP(%esp), %eax - call *PT_EBX(%esp) + movl PT_EBX(%esp), %edx + CALL_NOSPEC %edx movl $0, PT_EAX(%esp) /* @@ -938,7 +940,7 @@ 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) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 952b23b5d4e9..81b1cd533965 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,6 +36,7 @@ #include #include #include +#include #include /* Avoid __ASSEMBLER__'ifying 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 From 7153a6d5ff050050555066f58ac3458c5efc699b Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:29 +0000 Subject: [PATCH 14/55] x86/retpoline/ftrace: Convert ftrace assembler indirect jumps commit 9351803bd803cdbeb9b5a7850b7b6f464806e3db upstream. Convert all indirect jumps in ftrace 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/1515707194-20531-8-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_32.S | 5 +++-- arch/x86/kernel/mcount_64.S | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index adbbd4f538e9..d437f3871e53 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -863,7 +863,8 @@ trace: movl 0x4(%ebp), %edx subl $MCOUNT_INSN_SIZE, %eax - call *ftrace_trace_function + movl ftrace_trace_function, %ecx + CALL_NOSPEC %ecx popl %edx popl %ecx @@ -898,7 +899,7 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - jmp *%ecx + JMP_NOSPEC %ecx #endif #ifdef CONFIG_TRACING diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 5d9afbcb6074..09284cfab86f 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -7,7 +7,7 @@ #include #include #include - +#include .code64 .section .entry.text, "ax" @@ -285,8 +285,9 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function + movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs jmp fgraph_trace @@ -329,5 +330,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif From d2beed45635e3c430bc6d84ff8e6c6e8cb2e10b4 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:30 +0000 Subject: [PATCH 15/55] x86/retpoline/hyperv: Convert assembler indirect jumps commit e70e5892b28c18f517f29ab6e83bd57705104b31 upstream. Convert all indirect jumps in hyperv inline asm 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/1515707194-20531-9-git-send-email-dwmw@amazon.co.uk [ backport to 4.4, hopefully correct, not tested... - gregkh ] Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hv.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 8ce1f2e22912..d415a804fd26 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "hyperv_vmbus.h" /* The one and only */ @@ -103,9 +104,10 @@ static u64 do_hypercall(u64 control, void *input, void *output) return (u64)ULLONG_MAX; __asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8"); - __asm__ __volatile__("call *%3" : "=a" (hv_status) : + __asm__ __volatile__(CALL_NOSPEC : + "=a" (hv_status) : "c" (control), "d" (input_address), - "m" (hypercall_page)); + THUNK_TARGET(hypercall_page)); return hv_status; @@ -123,11 +125,12 @@ static u64 do_hypercall(u64 control, void *input, void *output) if (!hypercall_page) return (u64)ULLONG_MAX; - __asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi), + __asm__ __volatile__ (CALL_NOSPEC : "=d"(hv_status_hi), "=a"(hv_status_lo) : "d" (control_hi), "a" (control_lo), "b" (input_address_hi), "c" (input_address_lo), "D"(output_address_hi), - "S"(output_address_lo), "m" (hypercall_page)); + "S"(output_address_lo), + THUNK_TARGET(hypercall_page)); return hv_status_lo | ((u64)hv_status_hi << 32); #endif /* !x86_64 */ From 6b222e7483af4fd8f632efbf3b91025c2359b10a Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:31 +0000 Subject: [PATCH 16/55] x86/retpoline/xen: Convert Xen hypercall indirect jumps commit ea08816d5b185ab3d09e95e393f265af54560350 upstream. Convert indirect call in Xen hypercall to use non-speculative sequence, 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 Reviewed-by: Juergen Gross 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/1515707194-20531-10-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/xen/hypercall.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 85133b2b8e99..0977e7607046 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -215,9 +216,9 @@ privcmd_call(unsigned call, __HYPERCALL_5ARG(a1, a2, a3, a4, a5); stac(); - asm volatile("call *%[call]" + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM - : [call] "a" (&hypercall_page[call]) + : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); clac(); From 7e5bb301bd2fdd62cbee7b26a8234cccb6731849 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:32 +0000 Subject: [PATCH 17/55] x86/retpoline/checksum32: Convert assembler indirect jumps 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 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 Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/checksum_32.S | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index c1e623209853..90353a26ed95 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -28,7 +28,8 @@ #include #include #include - +#include + /* * 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) From f72655b837eb4320a1ffebbd0e0ebe92ce1e5314 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 11 Jan 2018 21:46:33 +0000 Subject: [PATCH 18/55] x86/retpoline/irq32: Convert assembler indirect jumps commit 7614e913db1f40fff819b36216484dc3808995d4 upstream. Convert all indirect jumps in 32bit irq inline asm code to use non speculative sequences. Signed-off-by: Andi Kleen 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: 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/1515707194-20531-12-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/irq_32.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 647089c64d13..528b7aa1780d 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -20,6 +20,7 @@ #include #include +#include #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); } @@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) call_on_stack(print_stack_overflow, isp); asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } From eebc3f8adee0a6f43a4789ef0bf5c5b35de8cfe4 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 12 Jan 2018 11:11:27 +0000 Subject: [PATCH 19/55] x86/retpoline: Fill return stack buffer on vmexit 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 Signed-off-by: Thomas Gleixner Tested-by: Peter Zijlstra (Intel) Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel Cc: Andi Kleen Cc: Josh Poimboeuf Cc: thomas.lendacky@amd.com 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/1515755487-8524-1-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse Signed-off-by: Razvan Ghitulete Signed-off-by: Greg Kroah-Hartman --- 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(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index fe48aeee79d1..1afd04eb5fb7 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -7,6 +7,48 @@ #include #include +/* + * 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 ") 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__ /* @@ -59,6 +101,19 @@ #else call *\reg #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__ */ @@ -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__ */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 900ffb6c28b5..2038e5bacce6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include "trace.h" @@ -3904,6 +3905,9 @@ static void svm_vcpu_run(struct kvm_vcpu *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 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c26255f19603..75d60e40c389 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -47,6 +47,7 @@ #include #include #include +#include #include "trace.h" #include "pmu.h" @@ -8701,6 +8702,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #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); From 451725c3e785dfc3ede6c65184b96c213181995a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 14 Jan 2018 22:13:29 +0100 Subject: [PATCH 20/55] x86/retpoline: Remove compile time warning commit b8b9ce4b5aec8de9e23cabb0a26b78641f9ab1d6 upstream. Remove the compile time warning when CONFIG_RETPOLINE=y and the compiler does not have retpoline support. Linus rationale for this is: It's wrong because it will just make people turn off RETPOLINE, and the asm updates - and return stack clearing - that are independent of the compiler are likely the most important parts because they are likely the ones easiest to target. And it's annoying because most people won't be able to do anything about it. The number of people building their own compiler? Very small. So if their distro hasn't got a compiler yet (and pretty much nobody does), the warning is just annoying crap. It is already properly reported as part of the sysfs interface. The compile-time warning only encourages bad things. Fixes: 76b043848fd2 ("x86/retpoline: Add initial retpoline support") Requested-by: Linus Torvalds Signed-off-by: Thomas Gleixner Cc: David Woodhouse Cc: Peter Zijlstra (Intel) Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel Cc: Andi Kleen Cc: Josh Poimboeuf Cc: thomas.lendacky@amd.com Cc: Linus Torvalds Cc: Jiri Kosina Cc: Andy Lutomirski Cc: Dave Hansen Cc: Kees Cook Cc: Tim Chen Cc: Greg Kroah-Hartman Link: https://lkml.kernel.org/r/CA+55aFzWgquv4i6Mab6bASqYXg3ErV3XDFEYf=GEcCDQg5uAtw@mail.gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/Makefile | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 34fdac520edb..1f9caa041bf7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -194,8 +194,6 @@ 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 From f1fcb9d2926c378e39adf42ef3446e08b2d63895 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 7 Apr 2017 09:34:12 +0200 Subject: [PATCH 21/55] scsi: sg: disable SET_FORCE_LOW_DMA commit 745dfa0d8ec26b24f3304459ff6e9eacc5c8351b upstream. The ioctl SET_FORCE_LOW_DMA has never worked since the initial git check-in, and the respective setting is nowadays handled correctly. So disable it entirely. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Tested-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/sg.c | 30 +++++++++--------------------- include/scsi/sg.h | 1 - 2 files changed, 9 insertions(+), 22 deletions(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 38f77e127349..0f0ff75755e0 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -160,7 +160,6 @@ typedef struct sg_fd { /* holds the state of a file descriptor */ struct list_head rq_list; /* head of request list */ struct fasync_struct *async_qp; /* used by asynchronous notification */ Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */ - char low_dma; /* as in parent but possibly overridden to 1 */ char force_packid; /* 1 -> pack_id input to read(), 0 -> ignored */ char cmd_q; /* 1 -> allow command queuing, 0 -> don't */ unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */ @@ -932,24 +931,14 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) /* strange ..., for backward compatibility */ return sfp->timeout_user; case SG_SET_FORCE_LOW_DMA: - result = get_user(val, ip); - if (result) - return result; - if (val) { - sfp->low_dma = 1; - if ((0 == sfp->low_dma) && !sfp->res_in_use) { - val = (int) sfp->reserve.bufflen; - sg_remove_scat(sfp, &sfp->reserve); - sg_build_reserve(sfp, val); - } - } else { - if (atomic_read(&sdp->detaching)) - return -ENODEV; - sfp->low_dma = sdp->device->host->unchecked_isa_dma; - } + /* + * N.B. This ioctl never worked properly, but failed to + * return an error value. So returning '0' to keep compability + * with legacy applications. + */ return 0; case SG_GET_LOW_DMA: - return put_user((int) sfp->low_dma, ip); + return put_user((int) sdp->device->host->unchecked_isa_dma, ip); case SG_GET_SCSI_ID: if (!access_ok(VERIFY_WRITE, p, sizeof (sg_scsi_id_t))) return -EFAULT; @@ -1870,6 +1859,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size) int sg_tablesize = sfp->parentdp->sg_tablesize; int blk_size = buff_size, order; gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN; + struct sg_device *sdp = sfp->parentdp; if (blk_size < 0) return -EFAULT; @@ -1895,7 +1885,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size) scatter_elem_sz_prev = num; } - if (sfp->low_dma) + if (sdp->device->host->unchecked_isa_dma) gfp_mask |= GFP_DMA; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) @@ -2158,8 +2148,6 @@ sg_add_sfp(Sg_device * sdp) sfp->timeout = SG_DEFAULT_TIMEOUT; sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER; sfp->force_packid = SG_DEF_FORCE_PACK_ID; - sfp->low_dma = (SG_DEF_FORCE_LOW_DMA == 0) ? - sdp->device->host->unchecked_isa_dma : 1; sfp->cmd_q = SG_DEF_COMMAND_Q; sfp->keep_orphan = SG_DEF_KEEP_ORPHAN; sfp->parentdp = sdp; @@ -2618,7 +2606,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) jiffies_to_msecs(fp->timeout), fp->reserve.bufflen, (int) fp->reserve.k_use_sg, - (int) fp->low_dma); + (int) sdp->device->host->unchecked_isa_dma); seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=0\n", (int) fp->cmd_q, (int) fp->force_packid, (int) fp->keep_orphan); diff --git a/include/scsi/sg.h b/include/scsi/sg.h index 3afec7032448..20bc71c3e0b8 100644 --- a/include/scsi/sg.h +++ b/include/scsi/sg.h @@ -197,7 +197,6 @@ typedef struct sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ #define SG_DEFAULT_RETRIES 0 /* Defaults, commented if they differ from original sg driver */ -#define SG_DEF_FORCE_LOW_DMA 0 /* was 1 -> memory below 16MB on i386 */ #define SG_DEF_FORCE_PACK_ID 0 #define SG_DEF_KEEP_ORPHAN 0 #define SG_DEF_RESERVED_SIZE SG_SCATTER_SZ /* load time option */ From 58c82be944f58561e77eb9db5039a4b0eca96ac5 Mon Sep 17 00:00:00 2001 From: Li Jinyue Date: Thu, 14 Dec 2017 17:04:54 +0800 Subject: [PATCH 22/55] futex: Prevent overflow by strengthen input validation commit fbe0e839d1e22d88810f3ee3e2f1479be4c0aa4a upstream. UBSAN reports signed integer overflow in kernel/futex.c: UBSAN: Undefined behaviour in kernel/futex.c:2041:18 signed integer overflow: 0 - -2147483648 cannot be represented in type 'int' Add a sanity check to catch negative values of nr_wake and nr_requeue. Signed-off-by: Li Jinyue Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: dvhart@infradead.org Link: https://lkml.kernel.org/r/1513242294-31786-1-git-send-email-lijinyue@huawei.com Signed-off-by: Greg Kroah-Hartman --- kernel/futex.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/futex.c b/kernel/futex.c index fc68462801de..1fce19fc824c 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1621,6 +1621,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_q *this, *next; WAKE_Q(wake_q); + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; + if (requeue_pi) { /* * Requeue PI only works on two distinct uaddrs. This From 80547bb6154d02279e446526a7d3daf7d5aa15db Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 10 Jan 2018 23:48:05 +0100 Subject: [PATCH 23/55] ALSA: pcm: Remove yet superfluous WARN_ON() commit 23b19b7b50fe1867da8d431eea9cd3e4b6328c2c upstream. muldiv32() contains a snd_BUG_ON() (which is morphed as WARN_ON() with debug option) for checking the case of 0 / 0. This would be helpful if this happens only as a logical error; however, since the hw refine is performed with any data set provided by user, the inconsistent values that can trigger such a condition might be passed easily. Actually, syzbot caught this by passing some zero'ed old hw_params ioctl. So, having snd_BUG_ON() there is simply superfluous and rather harmful to give unnecessary confusions. Let's get rid of it. Reported-by: syzbot+7e6ee55011deeebce15d@syzkaller.appspotmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_lib.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 7b805766306e..4c145d6bccd4 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -578,7 +578,6 @@ static inline unsigned int muldiv32(unsigned int a, unsigned int b, { u_int64_t n = (u_int64_t) a * b; if (c == 0) { - snd_BUG_ON(!n); *r = 0; return UINT_MAX; } From a4d7639d5fb65070e43f679493341f1ec4212e6e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 10 Jan 2018 08:34:28 +0100 Subject: [PATCH 24/55] ALSA: hda - Apply headphone noise quirk for another Dell XPS 13 variant commit e4c9fd10eb21376f44723c40ad12395089251c28 upstream. There is another Dell XPS 13 variant (SSID 1028:082a) that requires the existing fixup for reducing the headphone noise. This patch adds the quirk entry for that. BugLink: http://lkml.kernel.org/r/CAHXyb9ZCZJzVisuBARa+UORcjRERV8yokez=DP1_5O5isTz0ZA@mail.gmail.com Reported-and-tested-by: Francisco G. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5875a08d555e..f14c1f288443 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5600,6 +5600,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), + SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From 478a7fa82ff78be3b7aa94a9994fe0544b931f53 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 10 Jan 2018 10:53:18 +0100 Subject: [PATCH 25/55] ALSA: hda - Apply the existing quirk to iMac 14,1 commit 031f335cda879450095873003abb03ae8ed3b74a upstream. iMac 14,1 requires the same quirk as iMac 12,2, using GPIO 2 and 3 for headphone and speaker output amps. Add the codec SSID quirk entry (106b:0600) accordingly. BugLink: http://lkml.kernel.org/r/CAEw6Zyteav09VGHRfD5QwsfuWv5a43r0tFBNbfcHXoNrxVz7ew@mail.gmail.com Reported-by: Freaky Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_cirrus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 80bbadc83721..d6e079f4ec09 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -408,6 +408,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { /*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/ /* codec SSID */ + SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), From 48907f2535aa4b5951a0863b8bc7526402388c8d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 29 Dec 2017 18:13:05 -0600 Subject: [PATCH 26/55] af_key: fix buffer overread in verify_address_len() commit 06b335cb51af018d5feeff5dd4fd53847ddb675a upstream. If a message sent to a PF_KEY socket ended with one of the extensions that takes a 'struct sadb_address' but there were not enough bytes remaining in the message for the ->sa_family member of the 'struct sockaddr' which is supposed to follow, then verify_address_len() read past the end of the message, into uninitialized memory. Fix it by returning -EINVAL in this case. This bug was found using syzkaller with KMSAN. Reproducer: #include #include #include int main() { int sock = socket(PF_KEY, SOCK_RAW, PF_KEY_V2); char buf[24] = { 0 }; struct sadb_msg *msg = (void *)buf; struct sadb_address *addr = (void *)(msg + 1); msg->sadb_msg_version = PF_KEY_V2; msg->sadb_msg_type = SADB_DELETE; msg->sadb_msg_len = 3; addr->sadb_address_len = 1; addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; write(sock, buf, 24); } Reported-by: Alexander Potapenko Signed-off-by: Eric Biggers Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman --- net/key/af_key.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/key/af_key.c b/net/key/af_key.c index 94bf810ad242..ea81a58a4ff6 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -401,6 +401,11 @@ static int verify_address_len(const void *p) #endif int len; + if (sp->sadb_address_len < + DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), + sizeof(uint64_t))) + return -EINVAL; + switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); From b78f2d36e7378f43ba849e90e1f9dbfedd09eaf9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 29 Dec 2017 18:15:23 -0600 Subject: [PATCH 27/55] af_key: fix buffer overread in parse_exthdrs() commit 4e765b4972af7b07adcb1feb16e7a525ce1f6b28 upstream. If a message sent to a PF_KEY socket ended with an incomplete extension header (fewer than 4 bytes remaining), then parse_exthdrs() read past the end of the message, into uninitialized memory. Fix it by returning -EINVAL in this case. Reproducer: #include #include #include int main() { int sock = socket(PF_KEY, SOCK_RAW, PF_KEY_V2); char buf[17] = { 0 }; struct sadb_msg *msg = (void *)buf; msg->sadb_msg_version = PF_KEY_V2; msg->sadb_msg_type = SADB_DELETE; msg->sadb_msg_len = 2; write(sock, buf, 17); } Signed-off-by: Eric Biggers Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman --- net/key/af_key.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/key/af_key.c b/net/key/af_key.c index ea81a58a4ff6..6482b001f19a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -516,6 +516,9 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * uint16_t ext_type; int ext_len; + if (len < sizeof(*ehdr)) + return -EINVAL; + ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; From ec7a002d7796a1831d171159366d71fbcc8bf049 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Mon, 20 Mar 2017 16:42:48 +0100 Subject: [PATCH 28/55] scsi: hpsa: fix volume offline state commit eb94588dabec82e012281608949a860f64752914 upstream. In a previous patch a hpsa_scsi_dev_t.volume_offline update line has been removed, so let us put it back.. Fixes: 85b29008d8 (hpsa: update check for logical volume status) Signed-off-by: Tomas Henzl Acked-by: Don Brace Signed-off-by: Martin K. Petersen Cc: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/hpsa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 0c87f341fed4..910b795fc5eb 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3638,6 +3638,7 @@ static int hpsa_update_device_info(struct ctlr_info *h, if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC) hpsa_get_ioaccel_status(h, scsi3addr, this_device); volume_offline = hpsa_volume_offline(h, scsi3addr); + this_device->volume_offline = volume_offline; if (volume_offline == HPSA_LV_FAILED) { rc = HPSA_LV_FAILED; dev_err(&h->pdev->dev, From 8bd58b61d2faacdacd05287a3bbb32ad226b5428 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 10 May 2017 21:03:37 +0800 Subject: [PATCH 29/55] sched/deadline: Zero out positive runtime after throttling constrained tasks commit ae83b56a56f8d9643dedbee86b457fa1c5d42f59 upstream. When a contrained task is throttled by dl_check_constrained_dl(), it may carry the remaining positive runtime, as a result when dl_task_timer() fires and calls replenish_dl_entity(), it will not be replenished correctly due to the positive dl_se->runtime. This patch assigns its runtime to 0 if positive after throttling. Signed-off-by: Xunlei Pang Signed-off-by: Peter Zijlstra (Intel) Acked-by: Daniel Bristot de Oliveira Cc: Juri Lelli Cc: Linus Torvalds Cc: Luca Abeni Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Fixes: df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline) Link: http://lkml.kernel.org/r/1494421417-27550-1-git-send-email-xlpang@redhat.com Signed-off-by: Ingo Molnar Cc: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- kernel/sched/deadline.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a996f7356216..6be2afd9bfd6 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -732,6 +732,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; + if (dl_se->runtime > 0) + dl_se->runtime = 0; } } From fba063e6dfb413e06b9daa5d45b164761172f5ed Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Sat, 13 Jan 2018 17:27:30 -0600 Subject: [PATCH 30/55] x86/retpoline: Add LFENCE to the retpoline/RSB filling RSB macros commit 28d437d550e1e39f805d99f9f8ac399c778827b7 upstream. The PAUSE instruction is currently used in the retpoline and RSB filling macros as a speculation trap. The use of PAUSE was originally suggested because it showed a very, very small difference in the amount of cycles/time used to execute the retpoline as compared to LFENCE. On AMD, the PAUSE instruction is not a serializing instruction, so the pause/jmp loop will use excess power as it is speculated over waiting for return to mispredict to the correct target. The RSB filling macro is applicable to AMD, and, if software is unable to verify that LFENCE is serializing on AMD (possible when running under a hypervisor), the generic retpoline support will be used and, so, is also applicable to AMD. Keep the current usage of PAUSE for Intel, but add an LFENCE instruction to the speculation trap for AMD. The same sequence has been adopted by GCC for the GCC generated retpolines. Signed-off-by: Tom Lendacky Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Acked-by: David Woodhouse Acked-by: Arjan van de Ven Cc: Rik van Riel Cc: Andi Kleen Cc: Paul Turner Cc: Peter Zijlstra Cc: Tim Chen Cc: Jiri Kosina Cc: Dave Hansen Cc: Andy Lutomirski Cc: Josh Poimboeuf Cc: Dan Williams Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: Kees Cook Link: https://lkml.kernel.org/r/20180113232730.31060.36287.stgit@tlendack-t1.amdoffice.net Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 1afd04eb5fb7..e28a9ff1246c 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,7 +11,7 @@ * 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. + * infinite 'pause; lfence; 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 @@ -38,11 +38,13 @@ call 772f; \ 773: /* speculation trap */ \ pause; \ + lfence; \ jmp 773b; \ 772: \ call 774f; \ 775: /* speculation trap */ \ pause; \ + lfence; \ jmp 775b; \ 774: \ dec reg; \ @@ -60,6 +62,7 @@ call .Ldo_rop_\@ .Lspec_trap_\@: pause + lfence jmp .Lspec_trap_\@ .Ldo_rop_\@: mov \reg, (%_ASM_SP) @@ -142,6 +145,7 @@ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ + " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: addl $4, %%esp;\n" \ From 1782af2835fe6fbff6265a53fb85847fb9c58137 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 16 Jan 2018 12:52:28 -0800 Subject: [PATCH 31/55] module: Add retpoline tag to VERMAGIC commit 6cfb521ac0d5b97470883ff9b7facae264b7ab12 upstream. Add a marker for retpoline to the module VERMAGIC. This catches the case when a non RETPOLINE compiled module gets loaded into a retpoline kernel, making it insecure. It doesn't handle the case when retpoline has been runtime disabled. Even in this case the match of the retcompile status will be enforced. This implies that even with retpoline run time disabled all modules loaded need to be recompiled. Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Acked-by: David Woodhouse Cc: rusty@rustcorp.com.au Cc: arjan.van.de.ven@intel.com Cc: jeyu@kernel.org Cc: torvalds@linux-foundation.org Link: https://lkml.kernel.org/r/20180116205228.4890-1-andi@firstfloor.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vermagic.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 6f8fbcf10dfb..a3d04934aa96 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -24,10 +24,16 @@ #ifndef MODULE_ARCH_VERMAGIC #define MODULE_ARCH_VERMAGIC "" #endif +#ifdef RETPOLINE +#define MODULE_VERMAGIC_RETPOLINE "retpoline " +#else +#define MODULE_VERMAGIC_RETPOLINE "" +#endif #define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ - MODULE_ARCH_VERMAGIC + MODULE_ARCH_VERMAGIC \ + MODULE_VERMAGIC_RETPOLINE From aa041f13f8c6761ba985a4aab42c0dab49ec4202 Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Fri, 17 Nov 2017 15:29:21 -0800 Subject: [PATCH 32/55] pipe: avoid round_pipe_size() nr_pages overflow on 32-bit commit d3f14c485867cfb2e0c48aa88c41d0ef4bf5209c upstream. round_pipe_size() contains a right-bit-shift expression which may overflow, which would cause undefined results in a subsequent roundup_pow_of_two() call. static inline unsigned int round_pipe_size(unsigned int size) { unsigned long nr_pages; nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; } PAGE_SIZE is defined as (1UL << PAGE_SHIFT), so: - 4 bytes wide on 32-bit (0 to 0xffffffff) - 8 bytes wide on 64-bit (0 to 0xffffffffffffffff) That means that 32-bit round_pipe_size(), nr_pages may overflow to 0: size=0x00000000 nr_pages=0x0 size=0x00000001 nr_pages=0x1 size=0xfffff000 nr_pages=0xfffff size=0xfffff001 nr_pages=0x0 << ! size=0xffffffff nr_pages=0x0 << ! This is bad because roundup_pow_of_two(n) is undefined when n == 0! 64-bit is not a problem as the unsigned int size is 4 bytes wide (similar to 32-bit) and the larger, 8 byte wide unsigned long, is sufficient to handle the largest value of the bit shift expression: size=0xffffffff nr_pages=100000 Modify round_pipe_size() to return 0 if n == 0 and updates its callers to handle accordingly. Link: http://lkml.kernel.org/r/1507658689-11669-3-git-send-email-joe.lawrence@redhat.com Signed-off-by: Joe Lawrence Reported-by: Mikulas Patocka Reviewed-by: Mikulas Patocka Cc: Al Viro Cc: Jens Axboe Cc: Michael Kerrisk Cc: Randy Dunlap Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Dong Jinguang Signed-off-by: Greg Kroah-Hartman --- fs/pipe.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index ab8dad3ccb6a..39eff9a67253 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1001,6 +1001,9 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) { struct pipe_buffer *bufs; + if (!nr_pages) + return -EINVAL; + /* * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't * expect a lot of shrink+grow operations, just free and allocate @@ -1045,13 +1048,19 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) /* * Currently we rely on the pipe array holding a power-of-2 number - * of pages. + * of pages. Returns 0 on error. */ static inline unsigned int round_pipe_size(unsigned int size) { unsigned long nr_pages; + if (size < pipe_min_size) + size = pipe_min_size; + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (nr_pages == 0) + return 0; + return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; } @@ -1062,13 +1071,18 @@ static inline unsigned int round_pipe_size(unsigned int size) int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, size_t *lenp, loff_t *ppos) { + unsigned int rounded_pipe_max_size; int ret; ret = proc_dointvec_minmax(table, write, buf, lenp, ppos); if (ret < 0 || !write) return ret; - pipe_max_size = round_pipe_size(pipe_max_size); + rounded_pipe_max_size = round_pipe_size(pipe_max_size); + if (rounded_pipe_max_size == 0) + return -EINVAL; + + pipe_max_size = rounded_pipe_max_size; return ret; } From 7fd1335392891188b022f5fa518201710d5be3ac Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 16 Jan 2018 12:20:18 +0100 Subject: [PATCH 33/55] x86/apic/vector: Fix off by one in error path commit 45d55e7bac4028af93f5fa324e69958a0b868e96 upstream. Keith reported the following warning: WARNING: CPU: 28 PID: 1420 at kernel/irq/matrix.c:222 irq_matrix_remove_managed+0x10f/0x120 x86_vector_free_irqs+0xa1/0x180 x86_vector_alloc_irqs+0x1e4/0x3a0 msi_domain_alloc+0x62/0x130 The reason for this is that if the vector allocation fails the error handling code tries to free the failed vector as well, which causes the above imbalance warning to trigger. Adjust the error path to handle this correctly. Fixes: b5dc8e6c21e7 ("x86/irq: Use hierarchical irqdomain to manage CPU interrupt vectors") Reported-by: Keith Busch Signed-off-by: Thomas Gleixner Tested-by: Keith Busch Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1801161217300.1823@nanos Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/apic/vector.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 0988e204f1e3..a41e523536a2 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -359,14 +359,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; irq_data->hwirq = virq + i; err = assign_irq_vector_policy(virq + i, node, data, info); - if (err) + if (err) { + irq_data->chip_data = NULL; + free_apic_chip_data(data); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } From 47970b4ea09c7dc4bb610825a1e72915abb63aca Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 8 Jan 2018 17:20:18 -0800 Subject: [PATCH 34/55] Input: 88pm860x-ts - fix child-node lookup commit 906bf7daa0618d0ef39f4872ca42218c29a3631f upstream. Fix child node-lookup during probe, which ended up searching the whole device tree depth-first starting at parent rather than just matching on its children. To make things worse, the parent node was prematurely freed, while the child node was leaked. Fixes: 2e57d56747e6 ("mfd: 88pm860x: Device tree support") Signed-off-by: Johan Hovold Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/touchscreen/88pm860x-ts.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c index 251ff2aa0633..7a0dbce4dae9 100644 --- a/drivers/input/touchscreen/88pm860x-ts.c +++ b/drivers/input/touchscreen/88pm860x-ts.c @@ -126,7 +126,7 @@ static int pm860x_touch_dt_init(struct platform_device *pdev, int data, n, ret; if (!np) return -ENODEV; - np = of_find_node_by_name(np, "touch"); + np = of_get_child_by_name(np, "touch"); if (!np) { dev_err(&pdev->dev, "Can't find touch node\n"); return -EINVAL; @@ -144,13 +144,13 @@ static int pm860x_touch_dt_init(struct platform_device *pdev, if (data) { ret = pm860x_reg_write(i2c, PM8607_GPADC_MISC1, data); if (ret < 0) - return -EINVAL; + goto err_put_node; } /* set tsi prebias time */ if (!of_property_read_u32(np, "marvell,88pm860x-tsi-prebias", &data)) { ret = pm860x_reg_write(i2c, PM8607_TSI_PREBIAS, data); if (ret < 0) - return -EINVAL; + goto err_put_node; } /* set prebias & prechg time of pen detect */ data = 0; @@ -161,10 +161,18 @@ static int pm860x_touch_dt_init(struct platform_device *pdev, if (data) { ret = pm860x_reg_write(i2c, PM8607_PD_PREBIAS, data); if (ret < 0) - return -EINVAL; + goto err_put_node; } of_property_read_u32(np, "marvell,88pm860x-resistor-X", res_x); + + of_node_put(np); + return 0; + +err_put_node: + of_node_put(np); + + return -EINVAL; } #else #define pm860x_touch_dt_init(x, y, z) (-1) From 8e70d4862271b9c7a8300273a3bb895a5c9dbc97 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Mon, 9 May 2016 17:01:01 -0700 Subject: [PATCH 35/55] Input: twl6040-vibra - fix DT node memory management commit c52c545ead97fcc2f4f8ea38f1ae3c23211e09a8 upstream. commit e7ec014a47e4 ("Input: twl6040-vibra - update for device tree support") made the separate vibra DT node to a subnode of the twl6040. It now calls of_find_node_by_name() to locate the "vibra" subnode. This function has a side effect to call of_node_put on() for the twl6040 parent node passed in as a parameter. This causes trouble later on. Solution: we must call of_node_get() before of_find_node_by_name() Signed-off-by: H. Nikolaus Schaller Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/misc/twl6040-vibra.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c index ea63fad48de6..7221a00168bd 100644 --- a/drivers/input/misc/twl6040-vibra.c +++ b/drivers/input/misc/twl6040-vibra.c @@ -262,6 +262,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev) int vddvibr_uV = 0; int error; + of_node_get(twl6040_core_dev->of_node); twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node, "vibra"); if (!twl6040_core_node) { From a89e1ac9b0da065fa95ddd33030dcd38231f2b27 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 8 Jan 2018 17:17:48 -0800 Subject: [PATCH 36/55] Input: twl6040-vibra - fix child-node lookup commit dcaf12a8b0bbdbfcfa2be8dff2c4948d9844b4ad upstream. Fix child-node lookup during probe, which ended up searching the whole device tree depth-first starting at parent rather than just matching on its children. Later sanity checks on node properties (which would likely be missing) should prevent this from causing much trouble however, especially as the original premature free of the parent node has already been fixed separately (but that "fix" was apparently never backported to stable). Fixes: e7ec014a47e4 ("Input: twl6040-vibra - update for device tree support") Fixes: c52c545ead97 ("Input: twl6040-vibra - fix DT node memory management") Signed-off-by: Johan Hovold Acked-by: Peter Ujfalusi Tested-by: H. Nikolaus Schaller (on Pyra OMAP5 hardware) Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/misc/twl6040-vibra.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c index 7221a00168bd..1e968ae37f60 100644 --- a/drivers/input/misc/twl6040-vibra.c +++ b/drivers/input/misc/twl6040-vibra.c @@ -262,8 +262,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev) int vddvibr_uV = 0; int error; - of_node_get(twl6040_core_dev->of_node); - twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node, + twl6040_core_node = of_get_child_by_name(twl6040_core_dev->of_node, "vibra"); if (!twl6040_core_node) { dev_err(&pdev->dev, "parent of node is missing?\n"); From b6306f3fdcaa21b1544433de50004d13ce59042b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 8 Jan 2018 17:15:06 -0800 Subject: [PATCH 37/55] Input: twl4030-vibra - fix sibling-node lookup commit 5b189201993ab03001a398de731045bfea90c689 upstream. A helper purported to look up a child node based on its name was using the wrong of-helper and ended up prematurely freeing the parent of-node while searching the whole device tree depth-first starting at the parent node. Fixes: 64b9e4d803b1 ("input: twl4030-vibra: Support for DT booted kernel") Fixes: e661d0a04462 ("Input: twl4030-vibra - fix ERROR: Bad of_node_put() warning") Signed-off-by: Johan Hovold Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/misc/twl4030-vibra.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c index 10c4e3d462f1..7233db002588 100644 --- a/drivers/input/misc/twl4030-vibra.c +++ b/drivers/input/misc/twl4030-vibra.c @@ -178,12 +178,14 @@ static SIMPLE_DEV_PM_OPS(twl4030_vibra_pm_ops, twl4030_vibra_suspend, twl4030_vibra_resume); static bool twl4030_vibra_check_coexist(struct twl4030_vibra_data *pdata, - struct device_node *node) + struct device_node *parent) { + struct device_node *node; + if (pdata && pdata->coexist) return true; - node = of_find_node_by_name(node, "codec"); + node = of_get_child_by_name(parent, "codec"); if (node) { of_node_put(node); return true; From cf3625004e6c9093dcaa233c6f553b7eba269b50 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 18 Jan 2018 15:53:10 -0500 Subject: [PATCH 38/55] tracing: Fix converting enum's from the map in trace_event_eval_update() commit 1ebe1eaf2f02784921759992ae1fde1a9bec8fd0 upstream. Since enums do not get converted by the TRACE_EVENT macro into their values, the event format displaces the enum name and not the value. This breaks tools like perf and trace-cmd that need to interpret the raw binary data. To solve this, an enum map was created to convert these enums into their actual numbers on boot up. This is done by TRACE_EVENTS() adding a TRACE_DEFINE_ENUM() macro. Some enums were not being converted. This was caused by an optization that had a bug in it. All calls get checked against this enum map to see if it should be converted or not, and it compares the call's system to the system that the enum map was created under. If they match, then they call is processed. To cut down on the number of iterations needed to find the maps with a matching system, since calls and maps are grouped by system, when a match is made, the index into the map array is saved, so that the next call, if it belongs to the same system as the previous call, could start right at that array index and not have to scan all the previous arrays. The problem was, the saved index was used as the variable to know if this is a call in a new system or not. If the index was zero, it was assumed that the call is in a new system and would keep incrementing the saved index until it found a matching system. The issue arises when the first matching system was at index zero. The next map, if it belonged to the same system, would then think it was the first match and increment the index to one. If the next call belong to the same system, it would begin its search of the maps off by one, and miss the first enum that should be converted. This left a single enum not converted properly. Also add a comment to describe exactly what that index was for. It took me a bit too long to figure out what I was thinking when debugging this issue. Link: http://lkml.kernel.org/r/717BE572-2070-4C1E-9902-9F2E0FEDA4F8@oracle.com Fixes: 0c564a538aa93 ("tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values") Reported-by: Chuck Lever Teste-by: Chuck Lever Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 996f0fd34312..ba5392807912 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2300,6 +2300,7 @@ void trace_event_enum_update(struct trace_enum_map **map, int len) { struct trace_event_call *call, *p; const char *last_system = NULL; + bool first = false; int last_i; int i; @@ -2307,15 +2308,28 @@ void trace_event_enum_update(struct trace_enum_map **map, int len) list_for_each_entry_safe(call, p, &ftrace_events, list) { /* events are usually grouped together with systems */ if (!last_system || call->class->system != last_system) { + first = true; last_i = 0; last_system = call->class->system; } + /* + * Since calls are grouped by systems, the likelyhood that the + * next call in the iteration belongs to the same system as the + * previous call is high. As an optimization, we skip seaching + * for a map[] that matches the call's system if the last call + * was from the same system. That's what last_i is for. If the + * call has the same system as the previous call, then last_i + * will be the index of the first map[] that has a matching + * system. + */ for (i = last_i; i < len; i++) { if (call->class->system == map[i]->system) { /* Save the first system if need be */ - if (!last_i) + if (first) { last_i = i; + first = false; + } update_event_printk(call, map[i]); } } From d5276c0137137dfa89402c52eceeb406f4950404 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Jan 2018 11:12:05 +0100 Subject: [PATCH 39/55] phy: work around 'phys' references to usb-nop-xceiv devices commit b7563e2796f8b23c98afcfea7363194227fa089d upstream. Stefan Wahren reports a problem with a warning fix that was merged for v4.15: we had lots of device nodes with a 'phys' property pointing to a device node that is not compliant with the binding documented in Documentation/devicetree/bindings/phy/phy-bindings.txt This generally works because USB HCD drivers that support both the generic phy subsystem and the older usb-phy subsystem ignore most errors from phy_get() and related calls and then use the usb-phy driver instead. However, it turns out that making the usb-nop-xceiv device compatible with the generic-phy binding changes the phy_get() return code from -EINVAL to -EPROBE_DEFER, and the dwc2 usb controller driver for bcm2835 now returns -EPROBE_DEFER from its probe function rather than ignoring the failure, breaking all USB support on raspberry-pi when CONFIG_GENERIC_PHY is enabled. The same code is used in the dwc3 driver and the usb_add_hcd() function, so a reasonable assumption would be that many other platforms are affected as well. I have reviewed all the related patches and concluded that "usb-nop-xceiv" is the only USB phy that is affected by the change, and since it is by far the most commonly referenced phy, all the other USB phy drivers appear to be used in ways that are are either safe in DT (they don't use the 'phys' property), or in the driver (they already ignore -EPROBE_DEFER from generic-phy when usb-phy is available). To work around the problem, this adds a special case to _of_phy_get() so we ignore any PHY node that is compatible with "usb-nop-xceiv", as we know that this can never load no matter how much we defer. In the future, we might implement a generic-phy driver for "usb-nop-xceiv" and then remove this workaround. Since we generally want older kernels to also want to work with the fixed devicetree files, it would be good to backport the patch into stable kernels as well (3.13+ are possibly affected), even though they don't contain any of the patches that may have caused regressions. Fixes: 014d6da6cb25 ARM: dts: bcm283x: Fix DTC warnings about missing phy-cells Fixes: c5bbf358b790 arm: dts: nspire: Add missing #phy-cells to usb-nop-xceiv Fixes: 44e5dced2ef6 arm: dts: marvell: Add missing #phy-cells to usb-nop-xceiv Fixes: f568f6f554b8 ARM: dts: omap: Add missing #phy-cells to usb-nop-xceiv Fixes: d745d5f277bf ARM: dts: imx51-zii-rdu1: Add missing #phy-cells to usb-nop-xceiv Fixes: 915fbe59cbf2 ARM: dts: imx: Add missing #phy-cells to usb-nop-xceiv Link: https://marc.info/?l=linux-usb&m=151518314314753&w=2 Link: https://patchwork.kernel.org/patch/10158145/ Cc: Felipe Balbi Cc: Eric Anholt Tested-by: Stefan Wahren Acked-by: Rob Herring Tested-by: Hans Verkuil Acked-by: Kishon Vijay Abraham I Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- drivers/phy/phy-core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index e7e574dc667a..be1f0276ab23 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -365,6 +365,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index) if (ret) return ERR_PTR(-ENODEV); + /* This phy type handled by the usb-phy subsystem for now */ + if (of_device_is_compatible(args.np, "usb-nop-xceiv")) + return ERR_PTR(-ENODEV); + mutex_lock(&phy_provider_mutex); phy_provider = of_phy_provider_lookup(args.np); if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) { From 2d5523bf47b4326ff1279613bfe69982bc4675c1 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 4 Jan 2018 17:53:12 +0100 Subject: [PATCH 40/55] ARM: dts: kirkwood: fix pin-muxing of MPP7 on OpenBlocks A7 commit 56aeb07c914a616ab84357d34f8414a69b140cdf upstream. MPP7 is currently muxed as "gpio", but this function doesn't exist for MPP7, only "gpo" is available. This causes the following error: kirkwood-pinctrl f1010000.pin-controller: unsupported function gpio on pin mpp7 pinctrl core: failed to register map default (6): invalid type given kirkwood-pinctrl f1010000.pin-controller: error claiming hogs: -22 kirkwood-pinctrl f1010000.pin-controller: could not claim hogs: -22 kirkwood-pinctrl f1010000.pin-controller: unable to register pinctrl driver kirkwood-pinctrl: probe of f1010000.pin-controller failed with error -22 So the pinctrl driver is not probed, all device drivers (including the UART driver) do a -EPROBE_DEFER, and therefore the system doesn't really boot (well, it boots, but with no UART, and no devices that require pin-muxing). Back when the Device Tree file for this board was introduced, the definition was already wrong. The pinctrl driver also always described as "gpo" this function for MPP7. However, between Linux 4.10 and 4.11, a hog pin failing to be muxed was turned from a simple warning to a hard error that caused the entire pinctrl driver probe to bail out. This is probably the result of commit 6118714275f0a ("pinctrl: core: Fix pinctrl_register_and_init() with pinctrl_enable()"). This commit fixes the Device Tree to use the proper "gpo" function for MPP7, which fixes the boot of OpenBlocks A7, which was broken since Linux 4.11. Fixes: f24b56cbcd9d ("ARM: kirkwood: add support for OpenBlocks A7 platform") Signed-off-by: Thomas Petazzoni Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/kirkwood-openblocks_a7.dts | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts index d5e3bc518968..d57f48543f76 100644 --- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts +++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts @@ -53,7 +53,8 @@ }; pinctrl: pin-controller@10000 { - pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>; + pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header + &pmx_gpio_header_gpo>; pinctrl-names = "default"; pmx_uart0: pmx-uart0 { @@ -85,11 +86,16 @@ * ground. */ pmx_gpio_header: pmx-gpio-header { - marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28", + marvell,pins = "mpp17", "mpp29", "mpp28", "mpp35", "mpp34", "mpp40"; marvell,function = "gpio"; }; + pmx_gpio_header_gpo: pxm-gpio-header-gpo { + marvell,pins = "mpp7"; + marvell,function = "gpo"; + }; + pmx_gpio_init: pmx-init { marvell,pins = "mpp38"; marvell,function = "gpio"; From 082dfe6141f3a8adab45c7def0d1b1da17545f7c Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Mon, 15 Jan 2018 16:31:19 +0100 Subject: [PATCH 41/55] can: peak: fix potential bug in packet fragmentation commit d8a243af1a68395e07ac85384a2740d4134c67f4 upstream. In some rare conditions when running one PEAK USB-FD interface over a non high-speed USB controller, one useless USB fragment might be sent. This patch fixes the way a USB command is fragmented when its length is greater than 64 bytes and when the underlying USB controller is not a high-speed one. Signed-off-by: Stephane Grosjean Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index ce44a033f63b..64cc86a82b2d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -184,7 +184,7 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) void *cmd_head = pcan_usb_fd_cmd_buffer(dev); int err = 0; u8 *packet_ptr; - int i, n = 1, packet_len; + int packet_len; ptrdiff_t cmd_len; /* usb device unregistered? */ @@ -201,17 +201,13 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) } packet_ptr = cmd_head; + packet_len = cmd_len; /* firmware is not able to re-assemble 512 bytes buffer in full-speed */ - if ((dev->udev->speed != USB_SPEED_HIGH) && - (cmd_len > PCAN_UFD_LOSPD_PKT_SIZE)) { - packet_len = PCAN_UFD_LOSPD_PKT_SIZE; - n += cmd_len / packet_len; - } else { - packet_len = cmd_len; - } + if (unlikely(dev->udev->speed != USB_SPEED_HIGH)) + packet_len = min(packet_len, PCAN_UFD_LOSPD_PKT_SIZE); - for (i = 0; i < n; i++) { + do { err = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, PCAN_USBPRO_EP_CMDOUT), @@ -224,7 +220,12 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) } packet_ptr += packet_len; - } + cmd_len -= packet_len; + + if (cmd_len < PCAN_UFD_LOSPD_PKT_SIZE) + packet_len = cmd_len; + + } while (packet_len > 0); return err; } From b7bd013a3fe033280bcc58903c51f087e4989229 Mon Sep 17 00:00:00 2001 From: Xinyu Lin Date: Sun, 17 Dec 2017 20:13:39 +0800 Subject: [PATCH 42/55] libata: apply MAX_SEC_1024 to all LITEON EP1 series devices commit db5ff909798ef0099004ad50a0ff5fde92426fd1 upstream. LITEON EP1 has the same timeout issues as CX1 series devices. Revert max_sectors to the value of 1024. Fixes: e0edc8c54646 ("libata: apply MAX_SEC_1024 to all CX1-JB*-HP devices") Signed-off-by: Xinyu Lin Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b0b77b61c40c..69ec1c5d7152 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4143,6 +4143,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + { "LITEON EP1-*", NULL, ATA_HORKAGE_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ From 9c7755af771ac1b4ef1fc0e552749aa80d23af32 Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Wed, 20 Dec 2017 09:56:06 +0000 Subject: [PATCH 43/55] dm btree: fix serious bug in btree_split_beneath() commit bc68d0a43560e950850fc69b58f0f8254b28f6d6 upstream. When inserting a new key/value pair into a btree we walk down the spine of btree nodes performing the following 2 operations: i) space for a new entry ii) adjusting the first key entry if the new key is lower than any in the node. If the _root_ node is full, the function btree_split_beneath() allocates 2 new nodes, and redistibutes the root nodes entries between them. The root node is left with 2 entries corresponding to the 2 new nodes. btree_split_beneath() then adjusts the spine to point to one of the two new children. This means the first key is never adjusted if the new key was lower, ie. operation (ii) gets missed out. This can result in the new key being 'lost' for a period; until another low valued key is inserted that will uncover it. This is a serious bug, and quite hard to make trigger in normal use. A reproducing test case ("thin create devices-in-reverse-order") is available as part of the thin-provision-tools project: https://github.com/jthornber/thin-provisioning-tools/blob/master/functional-tests/device-mapper/dm-tests.scm#L593 Fix the issue by changing btree_split_beneath() so it no longer adjusts the spine. Instead it unlocks both the new nodes, and lets the main loop in btree_insert_raw() relock the appropriate one and make any neccessary adjustments. Reported-by: Monty Pavel Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/persistent-data/dm-btree.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index a1a68209bd36..880b7dee9c52 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -671,23 +671,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) pn->keys[1] = rn->keys[0]; memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64)); - /* - * rejig the spine. This is ugly, since it knows too - * much about the spine - */ - if (s->nodes[0] != new_parent) { - unlock_block(s->info, s->nodes[0]); - s->nodes[0] = new_parent; - } - if (key < le64_to_cpu(rn->keys[0])) { - unlock_block(s->info, right); - s->nodes[1] = left; - } else { - unlock_block(s->info, left); - s->nodes[1] = right; - } - s->count = 2; - + unlock_block(s->info, left); + unlock_block(s->info, right); return 0; } From 7e7b086ef2fec6b1bca061a3082fc1c2701999d5 Mon Sep 17 00:00:00 2001 From: Dennis Yang Date: Tue, 12 Dec 2017 18:21:40 +0800 Subject: [PATCH 44/55] dm thin metadata: THIN_MAX_CONCURRENT_LOCKS should be 6 commit 490ae017f54e55bde382d45ea24bddfb6d1a0aaf upstream. For btree removal, there is a corner case that a single thread could takes 6 locks which is more than THIN_MAX_CONCURRENT_LOCKS(5) and leads to deadlock. A btree removal might eventually call rebalance_children()->rebalance3() to rebalance entries of three neighbor child nodes when shadow_spine has already acquired two write locks. In rebalance3(), it tries to shadow and acquire the write locks of all three child nodes. However, shadowing a child node requires acquiring a read lock of the original child node and a write lock of the new block. Although the read lock will be released after block shadowing, shadowing the third child node in rebalance3() could still take the sixth lock. (2 write locks for shadow_spine + 2 write locks for the first two child nodes's shadow + 1 write lock for the last child node's shadow + 1 read lock for the last child node) Signed-off-by: Dennis Yang Acked-by: Joe Thornber Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin-metadata.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 3b67afda430b..e339f4288e8f 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -81,10 +81,14 @@ #define SECTOR_TO_BLOCK_SHIFT 3 /* + * For btree insert: * 3 for btree insert + * 2 for btree lookup used within space map + * For btree remove: + * 2 for shadow spine + + * 4 for rebalance 3 child node */ -#define THIN_MAX_CONCURRENT_LOCKS 5 +#define THIN_MAX_CONCURRENT_LOCKS 6 /* This should be plenty */ #define SPACE_MAP_ROOT_SIZE 128 From 5ecd5c8388f060a02a6b97d9b99d9ea885903568 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Jan 2018 10:23:47 +0000 Subject: [PATCH 45/55] arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls commit acfb3b883f6d6a4b5d27ad7fdded11f6a09ae6dd upstream. KVM doesn't follow the SMCCC when it comes to unimplemented calls, and inject an UNDEF instead of returning an error. Since firmware calls are now used for security mitigation, they are becoming more common, and the undef is counter productive. Instead, let's follow the SMCCC which states that -1 must be returned to the caller when getting an unknown function number. Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/handle_exit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index ba93a09eb536..5295aef7c8f0 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -42,7 +42,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_psci_call(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -51,7 +51,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } From 6b1c99e275c034e4650044a7bb1a0bc274e1eb45 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 26 Dec 2017 23:43:54 -0600 Subject: [PATCH 46/55] x86/cpu, x86/pti: Do not enable PTI on AMD processors commit 694d99d40972f12e59a3696effee8a376b79d7c8 upstream. AMD processors are not subject to the types of attacks that the kernel page table isolation feature protects against. The AMD microarchitecture does not allow memory references, including speculative references, that access higher privileged data when running in a lesser privileged mode when that access would result in a page fault. Disable page table isolation by default on AMD processors by not setting the X86_BUG_CPU_INSECURE feature, which controls whether X86_FEATURE_PTI is set. Signed-off-by: Tom Lendacky Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Dave Hansen Cc: Andy Lutomirski Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20171227054354.20369.94587.stgit@tlendack-t1.amdoffice.net Cc: Nick Lowe Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0531c1707b40..f7f2ad3687ee 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -831,8 +831,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - /* Assume for now that ALL x86 CPUs are insecure */ - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + if (c->x86_vendor != X86_VENDOR_AMD) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); From ff535919c1366b0218113f95c447d92c3aac0c1f Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 1 Nov 2016 12:46:19 +1100 Subject: [PATCH 47/55] kbuild: modversions for EXPORT_SYMBOL() for asm commit 4efca4ed05cbdfd13ec3e8cb623fb77d6e4ab187 upstream. Allow architectures to create asm/asm-prototypes.h file that provides C prototypes for exported asm functions, which enables proper CRC versions to be generated for them. Signed-off-by: Nicholas Piggin Signed-off-by: Michal Marek [jkosina@suse.cz: folded cc6acc11cad1 fixup in as well ] Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- scripts/Makefile.build | 87 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 80 insertions(+), 7 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 01df30af4d4a..18209917e379 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -158,7 +158,8 @@ cmd_cc_i_c = $(CPP) $(c_flags) -o $@ $< $(obj)/%.i: $(src)/%.c FORCE $(call if_changed_dep,cc_i_c) -cmd_gensymtypes = \ +# These mirror gensymtypes_S and co below, keep them in synch. +cmd_gensymtypes_c = \ $(CPP) -D__GENKSYMS__ $(c_flags) $< | \ $(GENKSYMS) $(if $(1), -T $(2)) \ $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ @@ -168,7 +169,7 @@ cmd_gensymtypes = \ quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@ cmd_cc_symtypes_c = \ set -e; \ - $(call cmd_gensymtypes,true,$@) >/dev/null; \ + $(call cmd_gensymtypes_c,true,$@) >/dev/null; \ test -s $@ || rm -f $@ $(obj)/%.symtypes : $(src)/%.c FORCE @@ -197,9 +198,10 @@ else # the actual value of the checksum generated by genksyms cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $< -cmd_modversions = \ + +cmd_modversions_c = \ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ - $(call cmd_gensymtypes,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ > $(@D)/.tmp_$(@F:.o=.ver); \ \ $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ @@ -244,7 +246,7 @@ endif define rule_cc_o_c $(call echo-cmd,checksrc) $(cmd_checksrc) \ $(call echo-cmd,cc_o_c) $(cmd_cc_o_c); \ - $(cmd_modversions) \ + $(cmd_modversions_c) \ $(call echo-cmd,record_mcount) \ $(cmd_record_mcount) \ scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' > \ @@ -253,6 +255,15 @@ define rule_cc_o_c mv -f $(dot-target).tmp $(dot-target).cmd endef +define rule_as_o_S + $(call echo-cmd,as_o_S) $(cmd_as_o_S); \ + scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,as_o_S)' > \ + $(dot-target).tmp; \ + $(cmd_modversions_S) \ + rm -f $(depfile); \ + mv -f $(dot-target).tmp $(dot-target).cmd +endef + # Built-in and composite module parts $(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE $(call cmd,force_checksrc) @@ -281,6 +292,38 @@ modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(real-objs-m) : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) $(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) +# .S file exports must have their C prototypes defined in asm/asm-prototypes.h +# or a file that it includes, in order to get versioned symbols. We build a +# dummy C file that includes asm-prototypes and the EXPORT_SYMBOL lines from +# the .S file (with trailing ';'), and run genksyms on that, to extract vers. +# +# This is convoluted. The .S file must first be preprocessed to run guards and +# expand names, then the resulting exports must be constructed into plain +# EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed +# to make the genksyms input. +# +# These mirror gensymtypes_c and co above, keep them in synch. +cmd_gensymtypes_S = \ + (echo "\#include " ; \ + echo "\#include " ; \ + $(CPP) $(a_flags) $< | \ + grep "\<___EXPORT_SYMBOL\>" | \ + sed 's/.*___EXPORT_SYMBOL[[:space:]]*\([a-zA-Z0-9_]*\)[[:space:]]*,.*/EXPORT_SYMBOL(\1);/' ) | \ + $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | \ + $(GENKSYMS) $(if $(1), -T $(2)) \ + $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ + $(if $(KBUILD_PRESERVE),-p) \ + -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null)) + +quiet_cmd_cc_symtypes_S = SYM $(quiet_modtag) $@ +cmd_cc_symtypes_S = \ + set -e; \ + $(call cmd_gensymtypes_S,true,$@) >/dev/null; \ + test -s $@ || rm -f $@ + +$(obj)/%.symtypes : $(src)/%.S FORCE + $(call cmd,cc_symtypes_S) + quiet_cmd_as_s_S = CPP $(quiet_modtag) $@ cmd_as_s_S = $(CPP) $(a_flags) -o $@ $< @@ -288,10 +331,40 @@ $(obj)/%.s: $(src)/%.S FORCE $(call if_changed_dep,as_s_S) quiet_cmd_as_o_S = AS $(quiet_modtag) $@ -cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +ifndef CONFIG_MODVERSIONS +cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +else + +ASM_PROTOTYPES := $(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/asm-prototypes.h) + +ifeq ($(ASM_PROTOTYPES),) +cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +else + +# versioning matches the C process described above, with difference that +# we parse asm-prototypes.h C header to get function definitions. + +cmd_as_o_S = $(CC) $(a_flags) -c -o $(@D)/.tmp_$(@F) $< + +cmd_modversions_S = \ + if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ + $(call cmd_gensymtypes_S,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + > $(@D)/.tmp_$(@F:.o=.ver); \ + \ + $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ + -T $(@D)/.tmp_$(@F:.o=.ver); \ + rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver); \ + else \ + mv -f $(@D)/.tmp_$(@F) $@; \ + fi; +endif +endif $(obj)/%.o: $(src)/%.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) targets += $(real-objs-y) $(real-objs-m) $(lib-y) targets += $(extra-y) $(MAKECMDGOALS) $(always) From f59e7ce17ba327245c8feb312d447b09d3b98eba Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 18 Jan 2018 16:28:26 +0100 Subject: [PATCH 48/55] x86/mce: Make machine check speculation protected commit 6f41c34d69eb005e7848716bbcafc979b35037d5 upstream. The machine check idtentry uses an indirect branch directly from the low level code. This evades the speculation protection. Replace it by a direct call into C code and issue the indirect call there so the compiler can apply the proper speculation protection. Signed-off-by: Thomas Gleixner Reviewed-by:Borislav Petkov Reviewed-by: David Woodhouse Niced-by: Peter Zijlstra Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1801181626290.1847@nanos Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/traps.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 5 +++++ 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 81b1cd533965..a03b22c615d9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1031,7 +1031,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index c3496619740a..156959ca49ce 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -92,6 +92,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif +dotraplinkage void do_mce(struct pt_regs *, long); static inline int get_si_code(unsigned long condition) { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7e8a736d09db..364fbad72e60 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1672,6 +1672,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: From 799dc737680a8074a0c7c2d3426b85f4c439377f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 19 Jan 2018 01:14:21 +0900 Subject: [PATCH 49/55] retpoline: Introduce start/end markers of indirect thunk commit 736e80a4213e9bbce40a7c050337047128b472ac upstream. Introduce start/end markers of __x86_indirect_thunk_* functions. To make it easy, consolidate .text.__x86.indirect_thunk.* sections to one .text.__x86.indirect_thunk section and put it in the end of kernel text section and adds __indirect_thunk_start/end so that other subsystem (e.g. kprobes) can identify it. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Acked-by: David Woodhouse Cc: Andi Kleen Cc: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: Arjan van de Ven Cc: Greg Kroah-Hartman Link: https://lkml.kernel.org/r/151629206178.10241.6828804696410044771.stgit@devbox Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 3 +++ arch/x86/kernel/vmlinux.lds.S | 7 +++++++ arch/x86/lib/retpoline.S | 2 +- 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e28a9ff1246c..4f7a5d3fed91 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -171,6 +171,9 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +extern char __indirect_thunk_start[]; +extern char __indirect_thunk_end[]; + /* * 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 diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 74e4bf11f562..e065065a4dfb 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -104,6 +104,13 @@ SECTIONS IRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 019a03599bb0..8a8093e9cf01 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,7 +9,7 @@ #include .macro THUNK reg - .section .text.__x86.indirect_thunk.\reg + .section .text.__x86.indirect_thunk ENTRY(__x86_indirect_thunk_\reg) CFI_STARTPROC From 9b8bd0d3586842716f5673e7a0922a9c9e1fcbfd Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 19 Jan 2018 01:14:51 +0900 Subject: [PATCH 50/55] kprobes/x86: Blacklist indirect thunk functions for kprobes commit c1804a236894ecc942da7dc6c5abe209e56cba93 upstream. Mark __x86_indirect_thunk_* functions as blacklist for kprobes because those functions can be called from anywhere in the kernel including blacklist functions of kprobes. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Acked-by: David Woodhouse Cc: Andi Kleen Cc: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: Arjan van de Ven Cc: Greg Kroah-Hartman Link: https://lkml.kernel.org/r/151629209111.10241.5444852823378068683.stgit@devbox Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 8a8093e9cf01..e611a124c442 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -25,7 +25,8 @@ ENDPROC(__x86_indirect_thunk_\reg) * 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 __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) GENERATE_THUNK(_ASM_AX) From 6cb73eb8045157ea280f0a047777ea1f56547375 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 19 Jan 2018 01:15:20 +0900 Subject: [PATCH 51/55] kprobes/x86: Disable optimizing on the function jumps to indirect thunk commit c86a32c09f8ced67971a2310e3b0dda4d1749007 upstream. Since indirect jump instructions will be replaced by jump to __x86_indirect_thunk_*, those jmp instruction must be treated as an indirect jump. Since optprobe prohibits to optimize probes in the function which uses an indirect jump, it also needs to find out the function which jump to __x86_indirect_thunk_* and disable optimization. Add a check that the jump target address is between the __indirect_thunk_start/end when optimizing kprobe. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Acked-by: David Woodhouse Cc: Andi Kleen Cc: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: Arjan van de Ven Cc: Greg Kroah-Hartman Link: https://lkml.kernel.org/r/151629212062.10241.6991266100233002273.stgit@devbox Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/kprobes/opt.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index c9d488f3e4cd..ea8e2b846101 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "common.h" @@ -191,7 +192,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -225,6 +226,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { From 58f96ac5dba6b66d9fb4e0072e0e01df0360a43f Mon Sep 17 00:00:00 2001 From: "zhenwei.pi" Date: Thu, 18 Jan 2018 09:04:52 +0800 Subject: [PATCH 52/55] x86/pti: Document fix wrong index commit 98f0fceec7f84d80bc053e49e596088573086421 upstream. In section <2. Runtime Cost>, fix wrong index. Signed-off-by: zhenwei.pi Signed-off-by: Thomas Gleixner Cc: dave.hansen@linux.intel.com Link: https://lkml.kernel.org/r/1516237492-27739-1-git-send-email-zhenwei.pi@youruncloud.com Signed-off-by: Greg Kroah-Hartman --- Documentation/x86/pti.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt index d11eff61fc9a..5cd58439ad2d 100644 --- a/Documentation/x86/pti.txt +++ b/Documentation/x86/pti.txt @@ -78,7 +78,7 @@ this protection comes at a cost: non-PTI SYSCALL entry code, so requires mapping fewer things into the userspace page tables. The downside is that stacks must be switched at entry time. - d. Global pages are disabled for all kernel structures not + c. Global pages are disabled for all kernel structures not mapped into both kernel and userspace page tables. This feature of the MMU allows different processes to share TLB entries mapping the kernel. Losing the feature means more From 11e619414b69b7f1e47baac72c5be589d86e5393 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 17 Jan 2018 14:53:28 -0800 Subject: [PATCH 53/55] x86/retpoline: Optimize inline assembler for vmexit_fill_RSB commit 3f7d875566d8e79c5e0b2c9a413e91b2c29e0854 upstream. The generated assembler for the C fill RSB inline asm operations has several issues: - The C code sets up the loop register, which is then immediately overwritten in __FILL_RETURN_BUFFER with the same value again. - The C code also passes in the iteration count in another register, which is not used at all. Remove these two unnecessary operations. Just rely on the single constant passed to the macro for the iterations. Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Acked-by: David Woodhouse Cc: dave.hansen@intel.com Cc: gregkh@linuxfoundation.org Cc: torvalds@linux-foundation.org Cc: arjan@linux.intel.com Link: https://lkml.kernel.org/r/20180117225328.15414-1-andi@firstfloor.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4f7a5d3fed91..492370b9b35b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -183,15 +183,16 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops = RSB_CLEAR_LOOPS / 2; + unsigned long loops; 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" ); + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } + #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ From 38bc402237f8cb68c5f3ab0292c6d5537af38847 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 29 Oct 2017 16:27:21 +0100 Subject: [PATCH 54/55] MIPS: AR7: ensure the port type's FCR value is used commit 0a5191efe06b5103909206e4fbcff81d30283f8e upstream. Since commit aef9a7bd9b67 ("serial/uart/8250: Add tunable RX interrupt trigger I/F of FIFO buffers"), the port's default FCR value isn't used in serial8250_do_set_termios anymore, but copied over once in serial8250_config_port and then modified as needed. Unfortunately, serial8250_config_port will never be called if the port is shared between kernel and userspace, and the port's flag doesn't have UPF_BOOT_AUTOCONF, which would trigger a serial8250_config_port as well. This causes garbled output from userspace: [ 5.220000] random: procd urandom read with 49 bits of entropy available ers [kee Fix this by forcing it to be configured on boot, resulting in the expected output: [ 5.250000] random: procd urandom read with 50 bits of entropy available Press the [f] key and hit [enter] to enter failsafe mode Press the [1], [2], [3] or [4] key and hit [enter] to select the debug level Fixes: aef9a7bd9b67 ("serial/uart/8250: Add tunable RX interrupt trigger I/F of FIFO buffers") Signed-off-by: Jonas Gorski Cc: Greg Kroah-Hartman Cc: Yoshihiro YUNOMAE Cc: Florian Fainelli Cc: Nicolas Schichan Cc: linux-mips@linux-mips.org Cc: linux-serial@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/17544/ Signed-off-by: Ralf Baechle Cc: James Hogan Signed-off-by: Greg Kroah-Hartman --- arch/mips/ar7/platform.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 3446b6fb3acb..9da4e2292fc7 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -576,7 +576,7 @@ static int __init ar7_register_uarts(void) uart_port.type = PORT_AR7; uart_port.uartclk = clk_get_rate(bus_clk) / 2; uart_port.iotype = UPIO_MEM32; - uart_port.flags = UPF_FIXED_TYPE; + uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF; uart_port.regshift = 2; uart_port.line = 0; From f0d0a93b0e81278e86c7d81c25a54ac4f4b739d2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 23 Jan 2018 19:50:18 +0100 Subject: [PATCH 55/55] Linux 4.4.113 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 07070a1e6292..39019c9d205c 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 112 +SUBLEVEL = 113 EXTRAVERSION = NAME = Blurry Fish Butt