4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tom Lendacky thomas.lendacky@amd.com

commit e4d0e84e490790798691aaa0f2e598637f1867ec upstream.

To aid in speculation control, make LFENCE a serializing instruction since it has less overhead than MFENCE. This is done by setting bit 1 of MSR 0xc0011029 (DE_CFG). Some families that support LFENCE do not have this MSR. For these families, the LFENCE instruction is already serializing.

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Reviewed-by: Borislav Petkov bp@suse.de Cc: Peter Zijlstra peterz@infradead.org Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Dave Hansen dave.hansen@intel.com Cc: Borislav Petkov bp@alien8.de Cc: Dan Williams dan.j.williams@intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: David Woodhouse dwmw@amazon.co.uk Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/20180108220921.12580.71694.stgit@tlendack-t1.amdof... Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/msr-index.h | 2 ++ arch/x86/kernel/cpu/amd.c | 10 ++++++++++ 2 files changed, 12 insertions(+)

--- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -330,6 +330,8 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1

/* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -746,6 +746,16 @@ static void init_amd(struct cpuinfo_x86 set_cpu_cap(c, X86_FEATURE_K8);

if (cpu_has_xmm2) { + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + /* MFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski luto@kernel.org

commit b8b7abaed7a49b350f8ba659ddc264b04931d581 upstream.

Otherwise we might have the PCID feature bit set during cpu_init().

This is just for robustness. I haven't seen any actual bugs here.

Signed-off-by: Andy Lutomirski luto@kernel.org Cc: Borislav Petkov bpetkov@suse.de Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Fixes: cba4671af755 ("x86/mm: Disable PCID on 32-bit kernels") Link: http://lkml.kernel.org/r/b16dae9d6b0db5d9801ddbebbfd83384097c61f3.1505663533... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/cpu/bugs.c | 8 -------- arch/x86/kernel/cpu/common.c | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -22,14 +22,6 @@

void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu();

if (!IS_ENABLED(CONFIG_SMP)) { --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -838,6 +838,14 @@ static void __init early_identify_cpu(st setup_force_cpu_bug(X86_BUG_SPECTRE_V2);

fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif }

void __init early_cpu_init(void)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adam Borowski kilobyte@angband.pl

commit 334bb773876403eae3457d81be0b8ea70f8e4ccc upstream.

Commit 4efca4ed ("kbuild: modversions for EXPORT_SYMBOL() for asm") adds modversion support for symbols exported from asm files. Architectures must include C-style declarations for those symbols in asm/asm-prototypes.h in order for them to be versioned.

Add these declarations for x86, and an architecture-independent file that can be used for common symbols.

With f27c2f6 reverting 8ab2ae6 ("default exported asm symbols to zero") we produce a scary warning on x86, this commit fixes that.

Signed-off-by: Adam Borowski kilobyte@angband.pl Tested-by: Kalle Valo kvalo@codeaurora.org Acked-by: Nicholas Piggin npiggin@gmail.com Tested-by: Peter Wu peter@lekensteyn.nl Tested-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Michal Marek mmarek@suse.com Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/asm-prototypes.h | 16 ++++++++++++++++ include/asm-generic/asm-prototypes.h | 7 +++++++ 2 files changed, 23 insertions(+)

--- /dev/null +++ b/arch/x86/include/asm/asm-prototypes.h @@ -0,0 +1,16 @@ +#include <asm/ftrace.h> +#include <asm/uaccess.h> +#include <asm/string.h> +#include <asm/page.h> +#include <asm/checksum.h> + +#include <asm-generic/asm-prototypes.h> + +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/special_insns.h> +#include <asm/preempt.h> + +#ifndef CONFIG_X86_CMPXCHG64 +extern void cmpxchg8b_emu(void); +#endif --- /dev/null +++ b/include/asm-generic/asm-prototypes.h @@ -0,0 +1,7 @@ +#include <linux/bitops.h> +extern void *__memset(void *, int, __kernel_size_t); +extern void *__memcpy(void *, const void *, __kernel_size_t); +extern void *__memmove(void *, const void *, __kernel_size_t); +extern void *memset(void *, int, __kernel_size_t); +extern void *memcpy(void *, const void *, __kernel_size_t); +extern void *memmove(void *, const void *, __kernel_size_t);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro viro@zeniv.linux.org.uk

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 <asm/export.h> from assembler. The rest needs to have their <asm/export.h> define everal macros and then explicitly include <asm-generic/export.h>

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 viro@zeniv.linux.org.uk Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/asm-generic/export.h | 94 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+)

--- /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 <linux/kconfig.h> +#include <generated/autoksyms.h> + +#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

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Woodhouse dwmw@amazon.co.uk

commit 76b043848fd22dbf7f8bf3a1452f8c70d557b860 upstream.

Enable the use of -mindirect-branch=thunk-extern in newer GCC, and provide the corresponding thunks. Provide assembler macros for invoking the thunks in the same way that GCC does, from native and inline assembler.

This adds X86_FEATURE_RETPOLINE and sets it by default on all CPUs. In some circumstances, IBRS microcode features may be used instead, and the retpoline can be disabled.

On AMD CPUs if lfence is serialising, the retpoline can be dramatically simplified to a simple "lfence; jmp *\reg". A future patch, after it has been verified that lfence really is serialising in all circumstances, can enable this by setting the X86_FEATURE_RETPOLINE_AMD feature bit in addition to X86_FEATURE_RETPOLINE.

Do not align the retpoline in the altinstr section, because there is no guarantee that it stays aligned when it's copied over the oldinstr during alternative patching.

[ Andi Kleen: Rename the macros, add CONFIG_RETPOLINE option, export thunks] [ tglx: Put actual function CALL/JMP in front of the macros, convert to symbolic labels ] [ dwmw2: Convert back to numeric labels, merge objtool fixes ]

Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Arjan van de Ven arjan@linux.intel.com Acked-by: Ingo Molnar mingo@kernel.org Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/1515707194-20531-4-git-send-email-dwmw@amazon.co.u... Signed-off-by: David Woodhouse dwmw@amazon.co.uk [ 4.4 backport: removed objtool annotation since there is no objtool ] Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/Kconfig | 13 ++++ arch/x86/Makefile | 10 +++ arch/x86/include/asm/asm-prototypes.h | 25 ++++++++ arch/x86/include/asm/cpufeature.h | 2 arch/x86/include/asm/nospec-branch.h | 106 ++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 4 + arch/x86/lib/Makefile | 1 arch/x86/lib/retpoline.S | 48 +++++++++++++++ 8 files changed, 209 insertions(+) create mode 100644 arch/x86/include/asm/nospec-branch.h create mode 100644 arch/x86/lib/retpoline.S

--- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -379,6 +379,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH

+config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + default y + ---help--- + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -189,6 +189,16 @@ KBUILD_CFLAGS += -fno-asynchronous-unwin KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y)

+# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + else + $(warning CONFIG_RETPOLINE=y, but not supported by the compiler. Toolchain update recommended.) + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs

--- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -10,7 +10,32 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h>

#ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +INDIRECT_THUNK(sp) +#endif /* CONFIG_RETPOLINE */ --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -200,6 +200,8 @@ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */

+#define X86_FEATURE_RETPOLINE ( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */

--- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeature.h> + +#ifdef __ASSEMBLY__ + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_@ +.Lspec_trap_@: + pause + jmp .Lspec_trap_@ +.Ldo_rop_@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_@ +.Ldo_retpoline_jmp_@: + RETPOLINE_JMP \reg +.Ldo_call_@: + call .Ldo_retpoline_jmp_@ +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -837,6 +837,10 @@ static void __init early_identify_cpu(st setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2);

+#ifdef CONFIG_RETPOLINE + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); +#endif + fpu__init_system(c);

#ifdef CONFIG_X86_32 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -21,6 +21,7 @@ lib-y += usercopy_$(BITS).o usercopy.o g lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o +lib-$(CONFIG_RETPOLINE) += retpoline.o

obj-y += msr.o msr-reg.o msr-reg-export.o

--- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> +#include <asm-generic/export.h> +#include <asm/nospec-branch.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk.\reg + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +GENERATE_THUNK(_ASM_SP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Woodhouse dwmw@amazon.co.uk

commit 9697fa39efd3fc3692f2949d4045f393ec58450b upstream.

Convert all indirect jumps in crypto assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Arjan van de Ven arjan@linux.intel.com Acked-by: Ingo Molnar mingo@kernel.org Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/1515707194-20531-6-git-send-email-dwmw@amazon.co.u... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/crypto/aesni-intel_asm.S | 5 +++-- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 3 ++- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 3 ++- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 3 ++- 4 files changed, 9 insertions(+), 5 deletions(-)

--- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -31,6 +31,7 @@

#include <linux/linkage.h> #include <asm/inst.h> +#include <asm/nospec-branch.h>

/* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2714,7 +2715,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP)

- call *%r11 + CALL_NOSPEC %r11

movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2759,7 +2760,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP)

- call *%r11 + CALL_NOSPEC %r11

movdqu 0x40(OUTP), INC pxor INC, STATE1 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -16,6 +16,7 @@ */

#include <linux/linkage.h> +#include <asm/nospec-branch.h>

#define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1210,7 +1211,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15;

- call *%r9; + CALL_NOSPEC %r9;

addq $(16 * 16), %rsp;

--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -11,6 +11,7 @@ */

#include <linux/linkage.h> +#include <asm/nospec-branch.h>

#define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1323,7 +1324,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15;

- call *%r9; + CALL_NOSPEC %r9;

addq $(16 * 32), %rsp;

--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@

#include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h>

## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction

@@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len offset=crc_array-jump_table lea offset(bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp

################################################################ ## 2a) PROCESS FULL BLOCKS:

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Woodhouse dwmw@amazon.co.uk

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 dwmw@amazon.co.uk Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Arjan van de Ven arjan@linux.intel.com Acked-by: Ingo Molnar mingo@kernel.org Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/1515707194-20531-8-git-send-email-dwmw@amazon.co.u... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/entry/entry_32.S | 5 +++-- arch/x86/kernel/mcount_64.S | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-)

--- 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 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -7,7 +7,7 @@ #include <linux/linkage.h> #include <asm/ptrace.h> #include <asm/ftrace.h> - +#include <asm/nospec-branch.h>

.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

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Woodhouse dwmw@amazon.co.uk

commit ea08816d5b185ab3d09e95e393f265af54560350 upstream.

Convert indirect call in Xen hypercall to use non-speculative sequence, when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Arjan van de Ven arjan@linux.intel.com Acked-by: Ingo Molnar mingo@kernel.org Reviewed-by: Juergen Gross jgross@suse.com Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/1515707194-20531-10-git-send-email-dwmw@amazon.co.... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/xen/hypercall.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/smap.h> +#include <asm/nospec-branch.h>

#include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -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();

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 7614e913db1f40fff819b36216484dc3808995d4 upstream.

Convert all indirect jumps in 32bit irq inline asm code to use non speculative sequences.

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Arjan van de Ven arjan@linux.intel.com Acked-by: Ingo Molnar mingo@kernel.org Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Paul Turner pjt@google.com Link: https://lkml.kernel.org/r/1515707194-20531-12-git-send-email-dwmw@amazon.co.... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Razvan Ghitulete rga@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/irq_32.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -20,6 +20,7 @@ #include <linux/mm.h>

#include <asm/apic.h> +#include <asm/nospec-branch.h>

#ifdef CONFIG_DEBUG_STACKOVERFLOW

@@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softi 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(i 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; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

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 torvalds@linux-foundation.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: David Woodhouse dwmw@amazon.co.uk Cc: Peter Zijlstra (Intel) peterz@infradead.org Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: thomas.lendacky@amd.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jiri Kosina jikos@kernel.org Cc: Andy Lutomirski luto@amacapital.net Cc: Dave Hansen dave.hansen@intel.com Cc: Kees Cook keescook@google.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Link: https://lkml.kernel.org/r/CA+55aFzWgquv4i6Mab6bASqYXg3ErV3XDFEYf=GEcCDQg5uAt... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/Makefile | 2 -- 1 file changed, 2 deletions(-)

--- 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

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Li Jinyue lijinyue@huawei.com

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 lijinyue@huawei.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: peterz@infradead.org Cc: dvhart@infradead.org Link: https://lkml.kernel.org/r/1513242294-31786-1-git-send-email-lijinyue@huawei.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/futex.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1621,6 +1621,9 @@ static int futex_requeue(u32 __user *uad 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

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai tiwai@suse.de

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... Reported-and-tested-by: Francisco G. frangio.1@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- 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 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),

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers ebiggers@google.com

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 <linux/pfkeyv2.h> #include <sys/socket.h> #include <unistd.h>

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 glider@google.com Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/key/af_key.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -401,6 +401,11 @@ static int verify_address_len(const void #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));

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tomas Henzl thenzl@redhat.com

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 thenzl@redhat.com Acked-by: Don Brace don.brace@microsemi.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Cc: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/hpsa.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3638,6 +3638,7 @@ static int hpsa_update_device_info(struc 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,

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tom Lendacky thomas.lendacky@amd.com

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 thomas.lendacky@amd.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov bp@alien8.de Acked-by: David Woodhouse dwmw@amazon.co.uk Acked-by: Arjan van de Ven arjan@linux.intel.com Cc: Rik van Riel riel@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Paul Turner pjt@google.com Cc: Peter Zijlstra peterz@infradead.org Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Jiri Kosina jikos@kernel.org Cc: Dave Hansen dave.hansen@intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Dan Williams dan.j.williams@intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Cc: Kees Cook keescook@google.com Link: https://lkml.kernel.org/r/20180113232730.31060.36287.stgit@tlendack-t1.amdof... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/nospec-branch.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- 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" \

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joe Lawrence joe.lawrence@redhat.com

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@redh... Signed-off-by: Joe Lawrence joe.lawrence@redhat.com Reported-by: Mikulas Patocka mpatocka@redhat.com Reviewed-by: Mikulas Patocka mpatocka@redhat.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Jens Axboe axboe@kernel.dk Cc: Michael Kerrisk mtk.manpages@gmail.com Cc: Randy Dunlap rdunlap@infradead.org Cc: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Dong Jinguang dongjinguang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/pipe.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)

--- a/fs/pipe.c +++ b/fs/pipe.c @@ -1001,6 +1001,9 @@ static long pipe_set_size(struct pipe_in { 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_in

/* * 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_si 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; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: H. Nikolaus Schaller hns@goldelico.com

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 hns@goldelico.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/misc/twl6040-vibra.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/input/misc/twl6040-vibra.c +++ b/drivers/input/misc/twl6040-vibra.c @@ -262,6 +262,7 @@ static int twl6040_vibra_probe(struct pl 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) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johan Hovold johan@kernel.org

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 johan@kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/misc/twl4030-vibra.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- 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_p 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;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann arnd@arndb.de

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 balbi@kernel.org Cc: Eric Anholt eric@anholt.net Tested-by: Stefan Wahren stefan.wahren@i2se.com Acked-by: Rob Herring robh@kernel.org Tested-by: Hans Verkuil hans.verkuil@cisco.com Acked-by: Kishon Vijay Abraham I kishon@ti.com Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/phy/phy-core.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -365,6 +365,10 @@ static struct phy *_of_phy_get(struct de 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)) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephane Grosjean s.grosjean@peak-system.com

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 s.grosjean@peak-system.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)

--- 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 p 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 p }

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 p }

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; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joe Thornber thornber@redhat.com

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-...

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 monty_pavel@sina.com Signed-off-by: Joe Thornber thornber@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/persistent-data/dm-btree.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-)

--- 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 sh 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; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier marc.zyngier@arm.com

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 marc.zyngier@arm.com Signed-off-by: Christoffer Dall christoffer.dall@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/kvm/handle_exit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- 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 *v

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 *v

static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicholas Piggin npiggin@gmail.com

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 npiggin@gmail.com Signed-off-by: Michal Marek mmarek@suse.com [jkosina@suse.cz: folded cc6acc11cad1 fixup in as well ] Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/Makefile.build | 87 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 80 insertions(+), 7 deletions(-)

--- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -158,7 +158,8 @@ cmd_cc_i_c = $(CPP) $(c_flags) - $(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 $(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 <linux/kernel.h>" ; \ + echo "#include <asm/asm-prototypes.h>" ; \ + $(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)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Hiramatsu mhiramat@kernel.org

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 mhiramat@kernel.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: David Woodhouse dwmw@amazon.co.uk Cc: Andi Kleen ak@linux.intel.com Cc: Peter Zijlstra peterz@infradead.org Cc: Ananth N Mavinakayanahalli ananth@linux.vnet.ibm.com Cc: Arjan van de Ven arjan@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Link: https://lkml.kernel.org/r/151629206178.10241.6828804696410044771.stgit@devbo... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- 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(-)

--- 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 --- 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 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,7 +9,7 @@ #include <asm/nospec-branch.h>

.macro THUNK reg - .section .text.__x86.indirect_thunk.\reg + .section .text.__x86.indirect_thunk

ENTRY(__x86_indirect_thunk_\reg) CFI_STARTPROC

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Hiramatsu mhiramat@kernel.org

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 mhiramat@kernel.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: David Woodhouse dwmw@amazon.co.uk Cc: Andi Kleen ak@linux.intel.com Cc: Peter Zijlstra peterz@infradead.org Cc: Ananth N Mavinakayanahalli ananth@linux.vnet.ibm.com Cc: Arjan van de Ven arjan@linux.intel.com Cc: Greg Kroah-Hartman gregkh@linux-foundation.org Link: https://lkml.kernel.org/r/151629212062.10241.6991266100233002273.stgit@devbo... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/kprobes/opt.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-)

--- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -36,6 +36,7 @@ #include <asm/alternative.h> #include <asm/insn.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h>

#include "common.h"

@@ -191,7 +192,7 @@ static int copy_optimized_instructions(u }

/* 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 i 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) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

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 ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: David Woodhouse dwmw@amazon.co.uk 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 gregkh@linuxfoundation.org

--- arch/x86/include/asm/nospec-branch.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- 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__ */