March 2019 - Linux-stable-mirror

[PATCH stable v4.14 00/32] powerpc spectre backports for 4.14

by Michael Ellerman

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hi Greg, Please queue up these powerpc patches for 4.14 if you have no objections. cheers Christophe Leroy (1): powerpc/fsl: Fix the flush of branch predictor. Diana Craciun (16): powerpc/64: Disable the speculation barrier from the command line powerpc/64: Make stf barrier PPC_BOOK3S_64 specific. powerpc/64: Make meltdown reporting Book3S 64 specific powerpc/fsl: Add barrier_nospec implementation for NXP PowerPC Book3E powerpc/fsl: Sanitize the syscall table for NXP PowerPC 32 bit platforms powerpc/fsl: Add infrastructure to fixup branch predictor flush powerpc/fsl: Add macro to flush the branch predictor powerpc/fsl: Fix spectre_v2 mitigations reporting powerpc/fsl: Emulate SPRN_BUCSR register powerpc/fsl: Add nospectre_v2 command line argument powerpc/fsl: Flush the branch predictor at each kernel entry (64bit) powerpc/fsl: Flush the branch predictor at each kernel entry (32 bit) powerpc/fsl: Flush branch predictor when entering KVM powerpc/fsl: Enable runtime patching if nospectre_v2 boot arg is used powerpc/fsl: Update Spectre v2 reporting powerpc/fsl: Fixed warning: orphan section `__btb_flush_fixup' Michael Ellerman (11): powerpc: Use barrier_nospec in copy_from_user() powerpc/64: Use barrier_nospec in syscall entry powerpc64s: Show ori31 availability in spectre_v1 sysfs file not v2 powerpc/64: Add CONFIG_PPC_BARRIER_NOSPEC powerpc/64: Call setup_barrier_nospec() from setup_arch() powerpc/asm: Add a patch_site macro & helpers for patching instructions powerpc/64s: Add new security feature flags for count cache flush powerpc/64s: Add support for software count cache flush powerpc/pseries: Query hypervisor for count cache flush settings powerpc/powernv: Query firmware for count cache flush settings powerpc/security: Fix spectre_v2 reporting Michal Suchanek (4): powerpc/64s: Add support for ori barrier_nospec patching powerpc/64s: Patch barrier_nospec in modules powerpc/64s: Enable barrier_nospec based on firmware settings powerpc/64s: Enhance the information in cpu_show_spectre_v1() arch/powerpc/Kconfig | 7 +- arch/powerpc/include/asm/asm-prototypes.h | 6 + arch/powerpc/include/asm/barrier.h | 12 +- arch/powerpc/include/asm/code-patching-asm.h | 18 ++ arch/powerpc/include/asm/code-patching.h | 2 + arch/powerpc/include/asm/feature-fixups.h | 21 ++ arch/powerpc/include/asm/hvcall.h | 2 + arch/powerpc/include/asm/ppc_asm.h | 10 + arch/powerpc/include/asm/security_features.h | 7 + arch/powerpc/include/asm/setup.h | 20 ++ arch/powerpc/include/asm/uaccess.h | 11 +- arch/powerpc/kernel/Makefile | 3 +- arch/powerpc/kernel/entry_32.S | 10 + arch/powerpc/kernel/entry_64.S | 69 ++++++ arch/powerpc/kernel/exceptions-64e.S | 27 ++- arch/powerpc/kernel/head_booke.h | 12 ++ arch/powerpc/kernel/head_fsl_booke.S | 15 ++ arch/powerpc/kernel/module.c | 10 +- arch/powerpc/kernel/security.c | 215 ++++++++++++++++++- arch/powerpc/kernel/setup-common.c | 3 + arch/powerpc/kernel/vmlinux.lds.S | 19 +- arch/powerpc/kvm/bookehv_interrupts.S | 4 + arch/powerpc/kvm/e500_emulate.c | 7 + arch/powerpc/lib/code-patching.c | 16 ++ arch/powerpc/lib/feature-fixups.c | 93 ++++++++ arch/powerpc/mm/tlb_low_64e.S | 7 + arch/powerpc/platforms/powernv/setup.c | 7 + arch/powerpc/platforms/pseries/setup.c | 7 + 28 files changed, 622 insertions(+), 18 deletions(-) create mode 100644 arch/powerpc/include/asm/code-patching-asm.h diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fe418226df7f..de3b07c7be30 100644 - --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,7 +164,7 @@ config PPC select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE - - select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 + select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_SMP_IDLE_THREAD @@ -236,6 +236,11 @@ config PPC # Please keep this list sorted alphabetically. # +config PPC_BARRIER_NOSPEC + bool + default y + depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E + config GENERIC_CSUM def_bool n diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 7330150bfe34..ba4c75062d49 100644 - --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -126,4 +126,10 @@ extern int __ucmpdi2(u64, u64); void _mcount(void); unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); +/* Patch sites */ +extern s32 patch__call_flush_count_cache; +extern s32 patch__flush_count_cache_return; + +extern long flush_count_cache; + #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index e582d2c88092..449474f667c4 100644 - --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -77,19 +77,25 @@ do { \ }) #ifdef CONFIG_PPC_BOOK3S_64 +#define NOSPEC_BARRIER_SLOT nop +#elif defined(CONFIG_PPC_FSL_BOOK3E) +#define NOSPEC_BARRIER_SLOT nop; nop +#endif + +#ifdef CONFIG_PPC_BARRIER_NOSPEC /* * Prevent execution of subsequent instructions until preceding branches have * been fully resolved and are no longer executing speculatively. */ - -#define barrier_nospec_asm ori 31,31,0 +#define barrier_nospec_asm NOSPEC_BARRIER_FIXUP_SECTION; NOSPEC_BARRIER_SLOT // This also acts as a compiler barrier due to the memory clobber. #define barrier_nospec() asm (stringify_in_c(barrier_nospec_asm) ::: "memory") - -#else /* !CONFIG_PPC_BOOK3S_64 */ +#else /* !CONFIG_PPC_BARRIER_NOSPEC */ #define barrier_nospec_asm #define barrier_nospec() - -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ #include <asm-generic/barrier.h> diff --git a/arch/powerpc/include/asm/code-patching-asm.h b/arch/powerpc/include/asm/code-patching-asm.h new file mode 100644 index 000000000000..ed7b1448493a - --- /dev/null +++ b/arch/powerpc/include/asm/code-patching-asm.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018, Michael Ellerman, IBM Corporation. + */ +#ifndef _ASM_POWERPC_CODE_PATCHING_ASM_H +#define _ASM_POWERPC_CODE_PATCHING_ASM_H + +/* Define a "site" that can be patched */ +.macro patch_site label name + .pushsection ".rodata" + .balign 4 + .global \name +\name: + .4byte \label - . + .popsection +.endm + +#endif /* _ASM_POWERPC_CODE_PATCHING_ASM_H */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 812535f40124..b2051234ada8 100644 - --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -32,6 +32,8 @@ unsigned int create_cond_branch(const unsigned int *addr, int patch_branch(unsigned int *addr, unsigned long target, int flags); int patch_instruction(unsigned int *addr, unsigned int instr); int raw_patch_instruction(unsigned int *addr, unsigned int instr); +int patch_instruction_site(s32 *addr, unsigned int instr); +int patch_branch_site(s32 *site, unsigned long target, int flags); int instr_is_relative_branch(unsigned int instr); int instr_is_relative_link_branch(unsigned int instr); diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index a9b64df34e2a..b1d478acbaec 100644 - --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -211,6 +211,25 @@ label##3: \ FTR_ENTRY_OFFSET 951b-952b; \ .popsection; +#define NOSPEC_BARRIER_FIXUP_SECTION \ +953: \ + .pushsection __barrier_nospec_fixup,"a"; \ + .align 2; \ +954: \ + FTR_ENTRY_OFFSET 953b-954b; \ + .popsection; + +#define START_BTB_FLUSH_SECTION \ +955: \ + +#define END_BTB_FLUSH_SECTION \ +956: \ + .pushsection __btb_flush_fixup,"a"; \ + .align 2; \ +957: \ + FTR_ENTRY_OFFSET 955b-957b; \ + FTR_ENTRY_OFFSET 956b-957b; \ + .popsection; #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -219,6 +238,8 @@ extern long stf_barrier_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; +extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; +extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; void apply_feature_fixups(void); void setup_feature_keys(void); diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 5a740feb7bd7..15cef59092c7 100644 - --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -340,10 +340,12 @@ #define H_CPU_CHAR_BRANCH_HINTS_HONORED (1ull << 58) // IBM bit 5 #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 +#define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9 #define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 +#define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5 /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 36f3e41c9fbe..3e1b8de72776 100644 - --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -802,4 +802,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) stringify_in_c(.long (_target) - . ;) \ stringify_in_c(.previous) +#ifdef CONFIG_PPC_FSL_BOOK3E +#define BTB_FLUSH(reg) \ + lis reg,BUCSR_INIT@h; \ + ori reg,reg,BUCSR_INIT@l; \ + mtspr SPRN_BUCSR,reg; \ + isync; +#else +#define BTB_FLUSH(reg) +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 44989b22383c..759597bf0fd8 100644 - --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -22,6 +22,7 @@ enum stf_barrier_type { void setup_stf_barrier(void); void do_stf_barrier_fixups(enum stf_barrier_type types); +void setup_count_cache_flush(void); static inline void security_ftr_set(unsigned long feature) { @@ -59,6 +60,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Indirect branch prediction cache disabled #define SEC_FTR_COUNT_CACHE_DISABLED 0x0000000000000020ull +// bcctr 2,0,0 triggers a hardware assisted count cache flush +#define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull + // Features indicating need for Spectre/Meltdown mitigations @@ -74,6 +78,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Firmware configuration indicates user favours security over performance #define SEC_FTR_FAVOUR_SECURITY 0x0000000000000200ull +// Software required to flush count cache on context switch +#define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index a5e919e34c42..5ceab440ecb9 100644 - --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,6 +52,26 @@ enum l1d_flush_type { void setup_rfi_flush(enum l1d_flush_type, bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); +#ifdef CONFIG_PPC_BARRIER_NOSPEC +void setup_barrier_nospec(void); +#else +static inline void setup_barrier_nospec(void) { }; +#endif +void do_barrier_nospec_fixups(bool enable); +extern bool barrier_nospec_enabled; + +#ifdef CONFIG_PPC_BARRIER_NOSPEC +void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); +#else +static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; +#endif + +#ifdef CONFIG_PPC_FSL_BOOK3E +void setup_spectre_v2(void); +#else +static inline void setup_spectre_v2(void) {}; +#endif +void do_btb_flush_fixups(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index cf26e62b268d..bd6d0fb5be9f 100644 - --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -238,6 +238,7 @@ do { \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__typeof__(*(ptr)))__gu_val; \ __gu_err; \ @@ -249,8 +250,10 @@ do { \ __long_type(*(ptr)) __gu_val = 0; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ - - if (access_ok(VERIFY_READ, __gu_addr, (size))) \ + if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) @@ -261,6 +264,7 @@ do { \ __long_type(*(ptr)) __gu_val; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ @@ -288,15 +292,19 @@ static inline unsigned long raw_copy_from_user(void *to, switch (n) { case 1: + barrier_nospec(); __get_user_size(*(u8 *)to, from, 1, ret); break; case 2: + barrier_nospec(); __get_user_size(*(u16 *)to, from, 2, ret); break; case 4: + barrier_nospec(); __get_user_size(*(u32 *)to, from, 4, ret); break; case 8: + barrier_nospec(); __get_user_size(*(u64 *)to, from, 8, ret); break; } @@ -304,6 +312,7 @@ static inline unsigned long raw_copy_from_user(void *to, return 0; } + barrier_nospec(); return __copy_tofrom_user((__force void __user *)to, from, n); } diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index a1089c9a9aa5..142b08d40642 100644 - --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -45,9 +45,10 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o - -obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o security.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 4ae464b9d490..a2999cd73a82 100644 - --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -33,6 +33,7 @@ #include <asm/unistd.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/barrier.h> /* * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE. @@ -358,6 +359,15 @@ _GLOBAL(DoSyscall) ori r10,r10,sys_call_table@l slwi r0,r0,2 bge- 66f + + barrier_nospec_asm + /* + * Prevent the load of the handler below (based on the user-passed + * system call number) being speculatively executed until the test + * against NR_syscalls and branch to .66f above has + * committed. + */ + lwzx r10,r10,r0 /* Fetch system call handler [ptr] */ mtlr r10 addi r9,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index c194f4c8e66b..12395895b9aa 100644 - --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -25,6 +25,7 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/thread_info.h> +#include <asm/code-patching-asm.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/cputable.h> @@ -36,6 +37,7 @@ #include <asm/context_tracking.h> #include <asm/tm.h> #include <asm/ppc-opcode.h> +#include <asm/barrier.h> #include <asm/export.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/exception-64s.h> @@ -76,6 +78,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) std r0,GPR0(r1) std r10,GPR1(r1) beq 2f /* if from kernel mode */ +#ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION +#endif ACCOUNT_CPU_USER_ENTRY(r13, r10, r11) 2: std r2,GPR2(r1) std r3,GPR3(r1) @@ -179,6 +186,15 @@ system_call: /* label this so stack traces look sane */ clrldi r8,r8,32 15: slwi r0,r0,4 + + barrier_nospec_asm + /* + * Prevent the load of the handler below (based on the user-passed + * system call number) being speculatively executed until the test + * against NR_syscalls and branch to .Lsyscall_enosys above has + * committed. + */ + ldx r12,r11,r0 /* Fetch system call handler [ptr] */ mtctr r12 bctrl /* Call handler */ @@ -487,6 +503,57 @@ _GLOBAL(ret_from_kernel_thread) li r3,0 b .Lsyscall_exit +#ifdef CONFIG_PPC_BOOK3S_64 + +#define FLUSH_COUNT_CACHE \ +1: nop; \ + patch_site 1b, patch__call_flush_count_cache + + +#define BCCTR_FLUSH .long 0x4c400420 + +.macro nops number + .rept \number + nop + .endr +.endm + +.balign 32 +.global flush_count_cache +flush_count_cache: + /* Save LR into r9 */ + mflr r9 + + .rept 64 + bl .+4 + .endr + b 1f + nops 6 + + .balign 32 + /* Restore LR */ +1: mtlr r9 + li r9,0x7fff + mtctr r9 + + BCCTR_FLUSH + +2: nop + patch_site 2b patch__flush_count_cache_return + + nops 3 + + .rept 278 + .balign 32 + BCCTR_FLUSH + nops 7 + .endr + + blr +#else +#define FLUSH_COUNT_CACHE +#endif /* CONFIG_PPC_BOOK3S_64 */ + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -518,6 +585,8 @@ _GLOBAL(_switch) std r23,_CCR(r1) std r1,KSP(r3) /* Set old stack pointer */ + FLUSH_COUNT_CACHE + /* * On SMP kernels, care must be taken because a task may be * scheduled off CPUx and on to CPUy. Memory ordering must be diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index acd8ca76233e..2edc1b7b34cc 100644 - --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -295,7 +295,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ ld r1,PACAKSAVE(r13); /* get kernel stack coming from usr */\ - -1: cmpdi cr1,r1,0; /* check if SP makes sense */ \ +1: type##_BTB_FLUSH \ + cmpdi cr1,r1,0; /* check if SP makes sense */ \ bge- cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \ mfspr r10,SPRN_##type##_SRR0; /* read SRR0 before touching stack */ @@ -327,6 +328,30 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 +#ifdef CONFIG_PPC_FSL_BOOK3E +#define GEN_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + beq 1f; \ + BTB_FLUSH(r10) \ + 1: \ + END_BTB_FLUSH_SECTION + +#define CRIT_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r10) \ + END_BTB_FLUSH_SECTION + +#define DBG_BTB_FLUSH CRIT_BTB_FLUSH +#define MC_BTB_FLUSH CRIT_BTB_FLUSH +#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH +#else +#define GEN_BTB_FLUSH +#define CRIT_BTB_FLUSH +#define DBG_BTB_FLUSH +#define MC_BTB_FLUSH +#define GDBELL_BTB_FLUSH +#endif + #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index d0862a100d29..306e26c073a0 100644 - --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -32,6 +32,16 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) +#ifdef CONFIG_PPC_FSL_BOOK3E +#define BOOKE_CLEAR_BTB(reg) \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(reg) \ +END_BTB_FLUSH_SECTION +#else +#define BOOKE_CLEAR_BTB(reg) +#endif + + #define NORMAL_EXCEPTION_PROLOG(intno) \ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ mfspr r10, SPRN_SPRG_THREAD; \ @@ -43,6 +53,7 @@ andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ + BOOKE_CLEAR_BTB(r11) \ /* if from user, start at top of this thread's kernel stack */ \ lwz r11, THREAD_INFO-THREAD(r10); \ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ @@ -128,6 +139,7 @@ stw r9,_CCR(r8); /* save CR on stack */\ mfspr r11,exc_level_srr1; /* check whether user or kernel */\ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ + BOOKE_CLEAR_BTB(r10) \ andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index bf4c6021515f..60a0aeefc4a7 100644 - --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -452,6 +452,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION mfspr r10, SPRN_DEAR /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -546,6 +553,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_SRR0 /* Get faulting address */ /* If we are faulting a kernel address, we have to use the diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 3f7ba0f5bf29..77371c9ef3d8 100644 - --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -72,7 +72,15 @@ int module_finalize(const Elf_Ehdr *hdr, do_feature_fixups(powerpc_firmware_features, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); - -#endif +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_PPC_BARRIER_NOSPEC + sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); + if (sect != NULL) + do_barrier_nospec_fixups_range(barrier_nospec_enabled, + (void *)sect->sh_addr, + (void *)sect->sh_addr + sect->sh_size); +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ sect = find_section(hdr, sechdrs, "__lwsync_fixup"); if (sect != NULL) diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index b98a722da915..48b50fb8dc4b 100644 - --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -9,11 +9,120 @@ #include <linux/seq_buf.h> #include <asm/debugfs.h> +#include <asm/asm-prototypes.h> +#include <asm/code-patching.h> #include <asm/security_features.h> +#include <asm/setup.h> unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; +enum count_cache_flush_type { + COUNT_CACHE_FLUSH_NONE = 0x1, + COUNT_CACHE_FLUSH_SW = 0x2, + COUNT_CACHE_FLUSH_HW = 0x4, +}; +static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + +bool barrier_nospec_enabled; +static bool no_nospec; +static bool btb_flush_enabled; +#ifdef CONFIG_PPC_FSL_BOOK3E +static bool no_spectrev2; +#endif + +static void enable_barrier_nospec(bool enable) +{ + barrier_nospec_enabled = enable; + do_barrier_nospec_fixups(enable); +} + +void setup_barrier_nospec(void) +{ + bool enable; + + /* + * It would make sense to check SEC_FTR_SPEC_BAR_ORI31 below as well. + * But there's a good reason not to. The two flags we check below are + * both are enabled by default in the kernel, so if the hcall is not + * functional they will be enabled. + * On a system where the host firmware has been updated (so the ori + * functions as a barrier), but on which the hypervisor (KVM/Qemu) has + * not been updated, we would like to enable the barrier. Dropping the + * check for SEC_FTR_SPEC_BAR_ORI31 achieves that. The only downside is + * we potentially enable the barrier on systems where the host firmware + * is not updated, but that's harmless as it's a no-op. + */ + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); + + if (!no_nospec) + enable_barrier_nospec(enable); +} + +static int __init handle_nospectre_v1(char *p) +{ + no_nospec = true; + + return 0; +} +early_param("nospectre_v1", handle_nospectre_v1); + +#ifdef CONFIG_DEBUG_FS +static int barrier_nospec_set(void *data, u64 val) +{ + switch (val) { + case 0: + case 1: + break; + default: + return -EINVAL; + } + + if (!!val == !!barrier_nospec_enabled) + return 0; + + enable_barrier_nospec(!!val); + + return 0; +} + +static int barrier_nospec_get(void *data, u64 *val) +{ + *val = barrier_nospec_enabled ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_barrier_nospec, + barrier_nospec_get, barrier_nospec_set, "%llu\n"); + +static __init int barrier_nospec_debugfs_init(void) +{ + debugfs_create_file("barrier_nospec", 0600, powerpc_debugfs_root, NULL, + &fops_barrier_nospec); + return 0; +} +device_initcall(barrier_nospec_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ + +#ifdef CONFIG_PPC_FSL_BOOK3E +static int __init handle_nospectre_v2(char *p) +{ + no_spectrev2 = true; + + return 0; +} +early_param("nospectre_v2", handle_nospectre_v2); +void setup_spectre_v2(void) +{ + if (no_spectrev2) + do_btb_flush_fixups(); + else + btb_flush_enabled = true; +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ + +#ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { bool thread_priv; @@ -46,25 +155,39 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha return sprintf(buf, "Vulnerable\n"); } +#endif ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - - if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) - - return sprintf(buf, "Not affected\n"); + struct seq_buf s; - - return sprintf(buf, "Vulnerable\n"); + seq_buf_init(&s, buf, PAGE_SIZE - 1); + + if (security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) { + if (barrier_nospec_enabled) + seq_buf_printf(&s, "Mitigation: __user pointer sanitization"); + else + seq_buf_printf(&s, "Vulnerable"); + + if (security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31)) + seq_buf_printf(&s, ", ori31 speculation barrier enabled"); + + seq_buf_printf(&s, "\n"); + } else + seq_buf_printf(&s, "Not affected\n"); + + return s.len; } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - - bool bcs, ccd, ori; struct seq_buf s; + bool bcs, ccd; seq_buf_init(&s, buf, PAGE_SIZE - 1); bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED); ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED); - - ori = security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31); if (bcs || ccd) { seq_buf_printf(&s, "Mitigation: "); @@ -77,17 +200,23 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); - - } else + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { + seq_buf_printf(&s, "Mitigation: Software count cache flush"); + + if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) + seq_buf_printf(&s, " (hardware accelerated)"); + } else if (btb_flush_enabled) { + seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); + } else { seq_buf_printf(&s, "Vulnerable"); - - - - if (ori) - - seq_buf_printf(&s, ", ori31 speculation barrier enabled"); + } seq_buf_printf(&s, "\n"); return s.len; } +#ifdef CONFIG_PPC_BOOK3S_64 /* * Store-forwarding barrier support. */ @@ -235,3 +364,71 @@ static __init int stf_barrier_debugfs_init(void) } device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ + +static void toggle_count_cache_flush(bool enable) +{ + if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); + return; + } + + patch_branch_site(&patch__call_flush_count_cache, + (u64)&flush_count_cache, BRANCH_SET_LINK); + + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { + count_cache_flush_type = COUNT_CACHE_FLUSH_SW; + pr_info("count-cache-flush: full software flush sequence enabled.\n"); + return; + } + + patch_instruction_site(&patch__flush_count_cache_return, PPC_INST_BLR); + count_cache_flush_type = COUNT_CACHE_FLUSH_HW; + pr_info("count-cache-flush: hardware assisted flush sequence enabled\n"); +} + +void setup_count_cache_flush(void) +{ + toggle_count_cache_flush(true); +} + +#ifdef CONFIG_DEBUG_FS +static int count_cache_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + toggle_count_cache_flush(enable); + + return 0; +} + +static int count_cache_flush_get(void *data, u64 *val) +{ + if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE) + *val = 0; + else + *val = 1; + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, + count_cache_flush_set, "%llu\n"); + +static __init int count_cache_flush_debugfs_init(void) +{ + debugfs_create_file("count_cache_flush", 0600, powerpc_debugfs_root, + NULL, &fops_count_cache_flush); + return 0; +} +device_initcall(count_cache_flush_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ +#endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 008447664643..c58364c74dad 100644 - --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -937,6 +937,9 @@ void __init setup_arch(char **cmdline_p) if (ppc_md.setup_arch) ppc_md.setup_arch(); + setup_barrier_nospec(); + setup_spectre_v2(); + paging_init(); /* Initialize the MMU context management stuff. */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index c89ffb88fa3b..b0cf4af7ba84 100644 - --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -153,8 +153,25 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } - -#endif +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_PPC_BARRIER_NOSPEC + . = ALIGN(8); + __spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) { + __start___barrier_nospec_fixup = .; + *(__barrier_nospec_fixup) + __stop___barrier_nospec_fixup = .; + } +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ +#ifdef CONFIG_PPC_FSL_BOOK3E + . = ALIGN(8); + __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { + __start__btb_flush_fixup = .; + *(__btb_flush_fixup) + __stop__btb_flush_fixup = .; + } +#endif EXCEPTION_TABLE(0) NOTES :kernel :notes diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index 81bd8a07aa51..612b7f6a887f 100644 - --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -75,6 +75,10 @@ PPC_LL r1, VCPU_HOST_STACK(r4) PPC_LL r2, HOST_R2(r1) +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_PID lwz r8, VCPU_HOST_PID(r4) PPC_LL r11, VCPU_SHARED(r4) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 990db69a1d0b..fa88f641ac03 100644 - --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -277,6 +277,13 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va vcpu->arch.pwrmgtcr0 = spr_val; break; + case SPRN_BUCSR: + /* + * If we are here, it means that we have already flushed the + * branch predictor, so just return to guest. + */ + break; + /* extra exceptions */ #ifdef CONFIG_SPE_POSSIBLE case SPRN_IVOR32: diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 130405158afa..c5154817178b 100644 - --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -206,6 +206,22 @@ int patch_branch(unsigned int *addr, unsigned long target, int flags) return patch_instruction(addr, create_branch(addr, target, flags)); } +int patch_branch_site(s32 *site, unsigned long target, int flags) +{ + unsigned int *addr; + + addr = (unsigned int *)((unsigned long)site + *site); + return patch_instruction(addr, create_branch(addr, target, flags)); +} + +int patch_instruction_site(s32 *site, unsigned int instr) +{ + unsigned int *addr; + + addr = (unsigned int *)((unsigned long)site + *site); + return patch_instruction(addr, instr); +} + bool is_offset_in_branch_range(long offset) { /* diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index e1bcdc32a851..de7861e09b41 100644 - --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -277,8 +277,101 @@ void do_rfi_flush_fixups(enum l1d_flush_type types) (types & L1D_FLUSH_MTTRIG) ? "mttrig type" : "unknown"); } + +void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) +{ + unsigned int instr, *dest; + long *start, *end; + int i; + + start = fixup_start; + end = fixup_end; + + instr = 0x60000000; /* nop */ + + if (enable) { + pr_info("barrier-nospec: using ORI speculation barrier\n"); + instr = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + } + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + patch_instruction(dest, instr); + } + + printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); +} + #endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_PPC_BARRIER_NOSPEC +void do_barrier_nospec_fixups(bool enable) +{ + void *start, *end; + + start = PTRRELOC(&__start___barrier_nospec_fixup), + end = PTRRELOC(&__stop___barrier_nospec_fixup); + + do_barrier_nospec_fixups_range(enable, start, end); +} +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ + +#ifdef CONFIG_PPC_FSL_BOOK3E +void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) +{ + unsigned int instr[2], *dest; + long *start, *end; + int i; + + start = fixup_start; + end = fixup_end; + + instr[0] = PPC_INST_NOP; + instr[1] = PPC_INST_NOP; + + if (enable) { + pr_info("barrier-nospec: using isync; sync as speculation barrier\n"); + instr[0] = PPC_INST_ISYNC; + instr[1] = PPC_INST_SYNC; + } + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + patch_instruction(dest, instr[0]); + patch_instruction(dest + 1, instr[1]); + } + + printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); +} + +static void patch_btb_flush_section(long *curr) +{ + unsigned int *start, *end; + + start = (void *)curr + *curr; + end = (void *)curr + *(curr + 1); + for (; start < end; start++) { + pr_devel("patching dest %lx\n", (unsigned long)start); + patch_instruction(start, PPC_INST_NOP); + } +} + +void do_btb_flush_fixups(void) +{ + long *start, *end; + + start = PTRRELOC(&__start__btb_flush_fixup); + end = PTRRELOC(&__stop__btb_flush_fixup); + + for (; start < end; start += 2) + patch_btb_flush_section(start); +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ + void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { long *start, *end; diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index eb82d787d99a..b7e9c09dfe19 100644 - --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -69,6 +69,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) std r15,EX_TLB_R15(r12) std r10,EX_TLB_CR(r12) #ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION std r7,EX_TLB_R7(r12) #endif TLB_MISS_PROLOG_STATS diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index fd143c934768..888aa9584e94 100644 - --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -77,6 +77,12 @@ static void init_fw_feat_flags(struct device_node *np) if (fw_feature_is("enabled", "fw-count-cache-disabled", np)) security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED); + if (fw_feature_is("enabled", "fw-count-cache-flush-bcctr2,0,0", np)) + security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + + if (fw_feature_is("enabled", "needs-count-cache-flush-on-context-switch", np)) + security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. @@ -123,6 +129,7 @@ static void pnv_setup_rfi_flush(void) security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); + setup_count_cache_flush(); } static void __init pnv_setup_arch(void) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 45f814041448..6a0ad56e89b9 100644 - --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -484,6 +484,12 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) if (result->character & H_CPU_CHAR_COUNT_CACHE_DISABLED) security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED); + if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) + security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + + if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE) + security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. @@ -534,6 +540,7 @@ void pseries_setup_rfi_flush(void) security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR); setup_rfi_flush(types, enable); + setup_count_cache_flush(); } static void __init pSeries_setup_arch(void) - -- 2.20.1 -----BEGIN PGP SIGNATURE----- iQIcBAEBAgAGBQJcngBeAAoJEFHr6jzI4aWAEAcP/jR1tS4sWnyzjbNPPDb49qWi ZFUERlA7UYuGn2ikJNavmUfVLze5NMzI73g7dgS1JF3DiiV2/gqHsUYtDvODoR0f 6H1KUYo2Z+eU2OtBvcauPuFTMcWGqT/YQUt5RJ5vV2yf/YJIBkXxbLl4Z64zOHyF K094Hq/oWXdl2Oj8Jsdb2MOg7wq6YJCYQ3BA3MN1Vr6SfKwoU265dNxR+bM0mFxd 9g9Hx7/Kh0q7PL+BkjH/nt+czZ92NC5k3TKv+E1UAQO4BGJys+gHFHUgvrWarl/H 2hvaw9FQbLHhBuIWTJaTGbiWL2LcV7j8KK1+SjjMTBkl3DlLhkpgXw2f0F1SaSaT KxekFNxz5GaIG2d07HybvCRWhEoUf2LC/ey34Hu60hjxRWiZayeZZuAztIhS22u1 95MFUkJykjfztOzSfW/FFuzxun/3ZkY4mDClGtGGRYJ72UC6fSW4pxVinwQeZn91 HTIPCF/URYNh5F3CMSN6kP6Z6npp+C6vs6inEW1n6y98YXKl8U0cXg9vpsKkSQ2/ Puh1wQXFIa3zQkZTsZZIBYnPxLKaavnyfRzkRcGpdX/7EZUzQs9Am3WXgL5wPtfb S4irV1qBsd2wnMLop00yVXoiZXUH/llFOFWwYfjkgcjebJdZ++hmfGH69K1F5eKI XZNhnxpR9ykE5QkhlybW =QXu0 -----END PGP SIGNATURE-----

5 years, 1 month

4
42
0 0

[PATCH v2] writeback: use exact memcg dirty counts

by Greg Thelen

Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") memcg dirty and writeback counters are managed as: 1) per-memcg per-cpu values in range of [-32..32] 2) per-memcg atomic counter When a per-cpu counter cannot fit in [-32..32] it's flushed to the atomic. Stat readers only check the atomic. Thus readers such as balance_dirty_pages() may see a nontrivial error margin: 32 pages per cpu. Assuming 100 cpus: 4k x86 page_size: 13 MiB error per memcg 64k ppc page_size: 200 MiB error per memcg Considering that dirty+writeback are used together for some decisions the errors double. This inaccuracy can lead to undeserved oom kills. One nasty case is when all per-cpu counters hold positive values offsetting an atomic negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32). balance_dirty_pages() only consults the atomic and does not consider throttling the next n_cpu*32 dirty pages. If the file_lru is in the 13..200 MiB range then there's absolutely no dirty throttling, which burdens vmscan with only dirty+writeback pages thus resorting to oom kill. It could be argued that tiny containers are not supported, but it's more subtle. It's the amount the space available for file lru that matters. If a container has memory.max-200MiB of non reclaimable memory, then it will also suffer such oom kills on a 100 cpu machine. The following test reliably ooms without this patch. This patch avoids oom kills. $ cat test mount -t cgroup2 none /dev/cgroup cd /dev/cgroup echo +io +memory > cgroup.subtree_control mkdir test cd test echo 10M > memory.max (echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo) (echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100) $ cat memcg-writeback-stress.c /* * Dirty pages from all but one cpu. * Clean pages from the non dirtying cpu. * This is to stress per cpu counter imbalance. * On a 100 cpu machine: * - per memcg per cpu dirty count is 32 pages for each of 99 cpus * - per memcg atomic is -99*32 pages * - thus the complete dirty limit: sum of all counters 0 * - balance_dirty_pages() only sees atomic count -99*32 pages, which * it max()s to 0. * - So a workload can dirty -99*32 pages before balance_dirty_pages() * cares. */ #define _GNU_SOURCE #include <err.h> #include <fcntl.h> #include <sched.h> #include <stdlib.h> #include <stdio.h> #include <sys/stat.h> #include <sys/sysinfo.h> #include <sys/types.h> #include <unistd.h> static char *buf; static int bufSize; static void set_affinity(int cpu) { cpu_set_t affinity; CPU_ZERO(&affinity); CPU_SET(cpu, &affinity); if (sched_setaffinity(0, sizeof(affinity), &affinity)) err(1, "sched_setaffinity"); } static void dirty_on(int output_fd, int cpu) { int i, wrote; set_affinity(cpu); for (i = 0; i < 32; i++) { for (wrote = 0; wrote < bufSize; ) { int ret = write(output_fd, buf+wrote, bufSize-wrote); if (ret == -1) err(1, "write"); wrote += ret; } } } int main(int argc, char **argv) { int cpu, flush_cpu = 1, output_fd; const char *output; if (argc != 2) errx(1, "usage: output_file"); output = argv[1]; bufSize = getpagesize(); buf = malloc(getpagesize()); if (buf == NULL) errx(1, "malloc failed"); output_fd = open(output, O_CREAT|O_RDWR); if (output_fd == -1) err(1, "open(%s)", output); for (cpu = 0; cpu < get_nprocs(); cpu++) { if (cpu != flush_cpu) dirty_on(output_fd, cpu); } set_affinity(flush_cpu); if (fsync(output_fd)) err(1, "fsync(%s)", output); if (close(output_fd)) err(1, "close(%s)", output); free(buf); } Make balance_dirty_pages() and wb_over_bg_thresh() work harder to collect exact per memcg counters. This avoids the aforementioned oom kills. This does not affect the overhead of memory.stat, which still reads the single atomic counter. Why not use percpu_counter? memcg already handles cpus going offline, so no need for that overhead from percpu_counter. And the percpu_counter spinlocks are more heavyweight than is required. It probably also makes sense to use exact dirty and writeback counters in memcg oom reports. But that is saved for later. Cc: stable(a)vger.kernel.org # v4.16+ Signed-off-by: Greg Thelen <gthelen(a)google.com> --- Changelog since v1: - Move memcg_exact_page_state() into memcontrol.c. - Unconditionally gather exact (per cpu) counters in mem_cgroup_wb_stats(), it's not called in performance sensitive paths. - Unconditionally check for underflow regardless of CONFIG_SMP. It's just easier this way. This isn't performance sensitive. - Add stable tag. include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1f3d880b7ca1..dbb6118370c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); -/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 532e0e2a4817..81a0d3914ec9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) return &memcg->cgwb_domain; } +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX; -- 2.21.0.392.gf8f6787159e-goog

5 years, 1 month

4
4
0 0

[RFC/RFT PATCH 08/18] crypto: ccm - fix incompatibility between "ccm" and "ccm_base"

by Eric Biggers

From: Eric Biggers <ebiggers(a)google.com> [This is essentially the same as the corresponding patch to GCM.] CCM instances can be created by either the "ccm" template, which only allows choosing the block cipher, e.g. "ccm(aes)"; or by "ccm_base", which allows choosing the ctr and cbcmac implementations, e.g. "ccm_base(ctr(aes-generic),cbcmac(aes-generic))". However, a "ccm_base" instance prevents a "ccm" instance from being registered using the same implementations. Nor will the instance be found by lookups of "ccm". This can be used as a denial of service. Moreover, "ccm_base" instances are never tested by the crypto self-tests, even if there are compatible "ccm" tests. The root cause of these problems is that instances of the two templates use different cra_names. Therefore, fix these problems by making "ccm_base" instances set the same cra_name as "ccm" instances, e.g. "ccm(aes)" instead of "ccm_base(ctr(aes-generic),cbcmac(aes-generic))". This requires extracting the block cipher name from the name of the ctr algorithm, which means starting to require that the stream cipher really be ctr and not something else. But it would be pretty bizarre if anyone was actually relying on being able to use a non-ctr stream cipher here. Fixes: 4a49b499dfa0 ("[CRYPTO] ccm: Added CCM mode") Cc: stable(a)vger.kernel.org Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- crypto/ccm.c | 38 ++++++++++++-------------------------- 1 file changed, 12 insertions(+), 26 deletions(-) diff --git a/crypto/ccm.c b/crypto/ccm.c index 50df8f001c1c9..3bb49776450b7 100644 --- a/crypto/ccm.c +++ b/crypto/ccm.c @@ -458,7 +458,6 @@ static void crypto_ccm_free(struct aead_instance *inst) static int crypto_ccm_create_common(struct crypto_template *tmpl, struct rtattr **tb, - const char *full_name, const char *ctr_name, const char *mac_name) { @@ -509,23 +508,22 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl, ctr = crypto_spawn_skcipher_alg(&ictx->ctr); - /* Not a stream cipher? */ + /* Must be CTR mode with 16-byte blocks. */ err = -EINVAL; - if (ctr->base.cra_blocksize != 1) + if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 || + crypto_skcipher_alg_ivsize(ctr) != 16) goto err_drop_ctr; - /* We want the real thing! */ - if (crypto_skcipher_alg_ivsize(ctr) != 16) + err = -ENAMETOOLONG; + if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, + "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME) goto err_drop_ctr; - err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)", ctr->base.cra_driver_name, mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_drop_ctr; - memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME); - inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC; inst->alg.base.cra_priority = (mac->base.cra_priority + ctr->base.cra_priority) / 2; @@ -567,7 +565,6 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb) const char *cipher_name; char ctr_name[CRYPTO_MAX_ALG_NAME]; char mac_name[CRYPTO_MAX_ALG_NAME]; - char full_name[CRYPTO_MAX_ALG_NAME]; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) @@ -581,35 +578,24 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb) cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; - if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm(%s)", cipher_name) >= - CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; - - return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name, - mac_name); + return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_ccm_base_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *ctr_name; - const char *cipher_name; - char full_name[CRYPTO_MAX_ALG_NAME]; + const char *mac_name; ctr_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(ctr_name)) return PTR_ERR(ctr_name); - cipher_name = crypto_attr_alg_name(tb[2]); - if (IS_ERR(cipher_name)) - return PTR_ERR(cipher_name); - - if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)", - ctr_name, cipher_name) >= CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; + mac_name = crypto_attr_alg_name(tb[2]); + if (IS_ERR(mac_name)) + return PTR_ERR(mac_name); - return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name, - cipher_name); + return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_rfc4309_setkey(struct crypto_aead *parent, const u8 *key, -- 2.21.0

5 years, 1 month

2
1
0 0

[PATCH stable only] nvmet: set loop queue's segment boundary mask as PAGE_SIZE - 1

by Ming Lei

NVMe target only accepts single-page sg list, either file or block device backed target code follows this assumption. However, loop target is one exception, given the sg list is from the host queue directly. This patch sets loop queue's segment boundary mask as PAGE_SIZE - 1 for following NVMe target assumption. Reported-by: Yi Zhang <yi.zhang(a)redhat.com> Fixes: 3a85a5de29ea ("nvme-loop: add a NVMe loopback host driver") Cc: Yi Zhang <yi.zhang(a)redhat.com> Cc: Sagi Grimberg <sagi(a)grimberg.me> Cc: Chaitanya Kulkarni <chaitanya.kulkarni(a)wdc.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> --- drivers/nvme/target/loop.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index b9f623ab01f3..7194f86b9dac 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -549,6 +549,9 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) if (ret) goto out_cleanup_connect_q; + /* target only accepts single-page sg list */ + blk_queue_segment_boundary(ctrl->ctrl.connect_q, PAGE_SIZE - 1); + return 0; out_cleanup_connect_q: -- 2.9.5

5 years, 1 month

3
4
0 0

[PATCH] cifs: a smb2_validate_and_copy_iov failure does not mean the handle is invalid.

by Ronnie Sahlberg

It only means that we do not have a valid cached value for the file_all_info structure. CC: Stable <stable(a)vger.kernel.org> Signed-off-by: Ronnie Sahlberg <lsahlber(a)redhat.com> --- fs/cifs/smb2ops.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7cfafac255aa..728437f8c45d 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -733,14 +733,12 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) goto oshr_exit; - rc = smb2_validate_and_copy_iov( + if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), &rsp_iov[1], sizeof(struct smb2_file_all_info), - (char *)&tcon->crfid.file_all_info); - if (rc) - goto oshr_exit; - tcon->crfid.file_all_info_is_valid = 1; + (char *)&tcon->crfid.file_all_info)) + tcon->crfid.file_all_info_is_valid = 1; oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); -- 2.13.6

5 years, 1 month

2
1
0 0

[RFC/RFT PATCH 07/18] crypto: gcm - fix incompatibility between "gcm" and "gcm_base"

by Eric Biggers

From: Eric Biggers <ebiggers(a)google.com> GCM instances can be created by either the "gcm" template, which only allows choosing the block cipher, e.g. "gcm(aes)"; or by "gcm_base", which allows choosing the ctr and ghash implementations, e.g. "gcm_base(ctr(aes-generic),ghash-generic)". However, a "gcm_base" instance prevents a "gcm" instance from being registered using the same implementations. Nor will the instance be found by lookups of "gcm". This can be used as a denial of service. Moreover, "gcm_base" instances are never tested by the crypto self-tests, even if there are compatible "gcm" tests. The root cause of these problems is that instances of the two templates use different cra_names. Therefore, fix these problems by making "gcm_base" instances set the same cra_name as "gcm" instances, e.g. "gcm(aes)" instead of "gcm_base(ctr(aes-generic),ghash-generic)". This requires extracting the block cipher name from the name of the ctr algorithm, which means starting to require that the stream cipher really be ctr and not something else. But it would be pretty bizarre if anyone was actually relying on being able to use a non-ctr stream cipher here. Fixes: d00aa19b507b ("[CRYPTO] gcm: Allow block cipher parameter") Cc: stable(a)vger.kernel.org Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- crypto/gcm.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) diff --git a/crypto/gcm.c b/crypto/gcm.c index e1a11f529d257..12ff5ed569272 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -597,7 +597,6 @@ static void crypto_gcm_free(struct aead_instance *inst) static int crypto_gcm_create_common(struct crypto_template *tmpl, struct rtattr **tb, - const char *full_name, const char *ctr_name, const char *ghash_name) { @@ -650,24 +649,23 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl, ctr = crypto_spawn_skcipher_alg(&ctx->ctr); - /* We only support 16-byte blocks. */ + /* Must be CTR mode with 16-byte blocks. */ err = -EINVAL; - if (crypto_skcipher_alg_ivsize(ctr) != 16) + if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 || + crypto_skcipher_alg_ivsize(ctr) != 16) goto out_put_ctr; - /* Not a stream cipher? */ - if (ctr->base.cra_blocksize != 1) + err = -ENAMETOOLONG; + if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, + "gcm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME) goto out_put_ctr; - err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)", ctr->base.cra_driver_name, ghash_alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto out_put_ctr; - memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME); - inst->alg.base.cra_flags = (ghash->base.cra_flags | ctr->base.cra_flags) & CRYPTO_ALG_ASYNC; inst->alg.base.cra_priority = (ghash->base.cra_priority + @@ -709,7 +707,6 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *cipher_name; char ctr_name[CRYPTO_MAX_ALG_NAME]; - char full_name[CRYPTO_MAX_ALG_NAME]; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) @@ -719,12 +716,7 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb) CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; - if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >= - CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; - - return crypto_gcm_create_common(tmpl, tb, full_name, - ctr_name, "ghash"); + return crypto_gcm_create_common(tmpl, tb, ctr_name, "ghash"); } static int crypto_gcm_base_create(struct crypto_template *tmpl, @@ -732,7 +724,6 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl, { const char *ctr_name; const char *ghash_name; - char full_name[CRYPTO_MAX_ALG_NAME]; ctr_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(ctr_name)) @@ -742,12 +733,7 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl, if (IS_ERR(ghash_name)) return PTR_ERR(ghash_name); - if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)", - ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME) - return -ENAMETOOLONG; - - return crypto_gcm_create_common(tmpl, tb, full_name, - ctr_name, ghash_name); + return crypto_gcm_create_common(tmpl, tb, ctr_name, ghash_name); } static int crypto_rfc4106_setkey(struct crypto_aead *parent, const u8 *key, -- 2.21.0

5 years, 1 month

1
1
0 0

[STABLE candidates] backport candidates from Allwinner kernels

by Arnd Bergmann

These are from https://github.com/BPI-SINOVOIP/BPI-M2P-bsp-4.4 They contain a bunch of things from an older Android kernel that looks like it would still make sense for normal stable kernels as well, very little here is allwinner specific: 0905f04eb21f sched/fair: Fix new task's load avg removed from source CPU in wake_up_new_task() 382c55f88ffe mmc: block: Allow more than 8 partitions per card b9b7aebb42d1 arm64: fix COMPAT_SHMLBA definition for large pages b523e185bba3 efi: stub: define DISABLE_BRANCH_PROFILING for all architectures 6c044fecdf78 ARM: 8458/1: bL_switcher: add GIC dependency ad84f56bf6d6 ARM: 8494/1: mm: Enable PXN when running non-LPAE kernel on LPAE processor 2010b93e9317 net: tcp: deal with listen sockets properly in tcp_abort. 699f68556943 android: unconditionally remove callbacks in sync_fence_free() 0eb77e988032 vmstat: make vmstat_updater deferrable again and shut down on idle 8d43b49e7e00 hid-sensor-hub.c: fix wrong do_div() usage 75feee3d9d51 arm64: hide __efistub_ aliases from kallsyms 728dabd6d175 Eliminate the .eh_frame sections from the aarch64 vmlinux and kernel modules 45c815f06b80 perf: Synchronously free aux pages in case of allocation failure 7c1306723ee9 net: diag: support v4mapped sockets in inet_diag_find_one_icsk() a5ebb87db843 Revert "mmc: block: don't use parameter prefix if built as module" 3d65ae4634ed writeback: initialize inode members that track writeback history 5ef11c35ce86 mm: ASLR: use get_random_long() 0d9c51a6e1df block: partition: add partition specific uevent callbacks for partition info a9ddc71f5840 coresight: fixing lockdep error fae54158792a coresight: coresight_unregister() function cleanup f2dfab3568fc coresight: release reference taken by 'bus_find_device()' ad725aee070c coresight: remove csdev's link from topology b15f0fb657e0 coresight: removing bind/unbind options from sysfs 4a2e2b19f96a stm class: Hide STM-specific options if STM is disabled 4c127fd16e6b stm class: Fix locking in unbinding policy path c74f7e8281ad stm class: Fix link list locking f08b18266c71 stm class: Prevent user-controllable allocations 59be422e4ce1 stm class: Support devices with multiple instances 1810f2c44817 stm class: Fix unlocking braino in the error path cde4ad836884 stm class: Guard output assignment against concurrency f7c81c7176c7 stm class: Fix unbalanced module/device refcounting b4ca34aaf78e stm class: Fix a race in unlinking bf16e5b8cdea coresight: "DEVICE_ATTR_RO" should defined as static. 61390593f723 coresight: etm4x: Check every parameter used by dma_xx_coherent. 3694bd76781b asm-generic: Fix local variable shadow in __set_fixmap_offset 18e77054de74 staging: ashmem: Avoid deadlock with mmap/shrink 90a2f171383b staging: ashmem: Add missing include 1328d8efef17 staging: ion: Set minimum carveout heap allocation order to PAGE_SHIFT 4532150762ce staging: goldfish: audio: fix compiliation on arm 1b9bdf5c1661 ARM: 8510/1: rework ARM_CPU_SUSPEND dependencies b660950c60a7 arm64/kernel: fix incorrect EL0 check in inv_entry macro b4201cc4fc6e mac80211: fix "warning: ‘target_metric’ may be used uninitialized" dcb10a967ce8 perf/ring_buffer: Refuse to begin AUX transaction after rb->aux_mmap_count drops 812264550dcb arm64: kernel: Include _AC definition in page.h f6cf0545ec69 PM / Hibernate: Call flush_icache_range() on pages restored in-place cbe4a61d1ddc stm class: Do not leak the chrdev in error path 389b6699a2aa stm class: Fix stm device initialization order bbb1681ee365 arm64: mm: mark fault_info table const 5014e904681d coresight: Handle build path error dcb94b88c09c ipv6: fix endianness error in icmpv6_err cee51c33f52e usb: gadget: configfs: add mutex lock before unregister gadget 207707d8fd48 usb: gadget: rndis: free response queue during REMOTE_NDIS_RESET_MSG 7b996243fab4 tun: fix transmit timestamp support 01b411590665 cpu/hotplug: Handle unbalanced hotplug enable/disable 359be67862c5 dma mapping : export caller to vmallocinfo ace6033ec5c3 video: fbdev: Set pixclock = 0 in goldfishfb These are from https://github.com/BPI-SINOVOIP/BPI-M64-bsp-4.4: 91d372117695 s390: add DEBUG_RODATA support 99a507771fa5 arm64: kconfig: drop CONFIG_RTC_LIB dependency 38b850a73034 arm64: spinlock: order spin_{is_locked,unlock_wait} against local locks 987aa5f80596 mmc: mmc: fix switch timeout issue caused by jiffies precision 4ef8c1c93f84 cfg80211: size various nl80211 messages correctly c88215d7050f cfg80211: Fix documentation for connect result 5c2a625937ba arm64: support keyctl() system call in 32-bit mode And finally, one from https://github.com/BPI-SINOVOIP/BPI-Mainline-kernel/tree/master/linux-4.14: a830405ee452 stmmac: copy unicast mac address to MAC registers I can post them as patches as well if that helps. Overall, my script found 380, 80 and 55 patches backported from mainline here, respectively, but most of them are clearly not stable candidates. Arnd

5 years, 1 month

2
3
0 0

[PATCH v4.19.x] usb: typec: class: Don't use port parent for getting mux handles

by Heikki Krogerus

commit 23481121c81d984193edf1532f5e123637e50903 upstream. It is not possible to use the parent of the port device when requesting mux handles as the parent may be a multiport USB Type-C or PD controller. The muxes must be assigned to the ports, not the controllers. This will also move the requesting of the muxes after the port device is initialized. [ heikki: This patch fixes an issue where port->id was used uninitialized. ] Cc: <stable(a)vger.kernel.org> # 4.19.x: cd7753d: drivers: base: Helpers for adding device connection descriptions Cc: <stable(a)vger.kernel.org> # 4.19.x: 140a4ec: platform: x86: intel_cht_int33fe: Register all connections at once Cc: <stable(a)vger.kernel.org> # 4.19.x: 78d2b54: platform: x86: intel_cht_int33fe: Add connection for the DP alt mode Cc: <stable(a)vger.kernel.org> # 4.19.x: 495965a: platform: x86: intel_cht_int33fe: Add connections for the USB Type-C port Cc: <stable(a)vger.kernel.org> # 4.19.x Cc: <stable(a)vger.kernel.org> # 4.19.x: 148b0aa: platform: x86: intel_cht_int33fe: Remove the old connections for the muxes Fixes: bdecb33af34f ("usb: typec: API for controlling USB Type-C Multiplexers") Acked-by: Hans de Goede <hdegoede(a)redhat.com> Tested-by: Hans de Goede <hdegoede(a)redhat.com> Signed-off-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> --- Hi, This is a request to backport commit 23481121c81d984193edf1532f5e123637e50903 It was not marked as a fix, but it does fix an issue where a variable "port->id" was used in function typec_register_port() without initializing it. The patch has additional prerequisites which are listed in the sign-off area. Please note that there is also one patch listed there after this one. thanks, heikki --- drivers/usb/typec/class.c | 38 +++++++++++++++----------------------- 1 file changed, 15 insertions(+), 23 deletions(-) diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index e61dffb27a0c..00141e05bc72 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1500,7 +1500,7 @@ typec_port_register_altmode(struct typec_port *port, sprintf(id, "id%04xm%02x", desc->svid, desc->mode); - mux = typec_mux_get(port->dev.parent, id); + mux = typec_mux_get(&port->dev, id); if (IS_ERR(mux)) return ERR_CAST(mux); @@ -1540,18 +1540,6 @@ struct typec_port *typec_register_port(struct device *parent, return ERR_PTR(id); } - port->sw = typec_switch_get(cap->fwnode ? &port->dev : parent); - if (IS_ERR(port->sw)) { - ret = PTR_ERR(port->sw); - goto err_switch; - } - - port->mux = typec_mux_get(parent, "typec-mux"); - if (IS_ERR(port->mux)) { - ret = PTR_ERR(port->mux); - goto err_mux; - } - switch (cap->type) { case TYPEC_PORT_SRC: port->pwr_role = TYPEC_SOURCE; @@ -1592,13 +1580,26 @@ struct typec_port *typec_register_port(struct device *parent, port->port_type = cap->type; port->prefer_role = cap->prefer_role; + device_initialize(&port->dev); port->dev.class = typec_class; port->dev.parent = parent; port->dev.fwnode = cap->fwnode; port->dev.type = &typec_port_dev_type; dev_set_name(&port->dev, "port%d", id); - ret = device_register(&port->dev); + port->sw = typec_switch_get(&port->dev); + if (IS_ERR(port->sw)) { + put_device(&port->dev); + return ERR_CAST(port->sw); + } + + port->mux = typec_mux_get(&port->dev, "typec-mux"); + if (IS_ERR(port->mux)) { + put_device(&port->dev); + return ERR_CAST(port->mux); + } + + ret = device_add(&port->dev); if (ret) { dev_err(parent, "failed to register port (%d)\n", ret); put_device(&port->dev); @@ -1606,15 +1607,6 @@ struct typec_port *typec_register_port(struct device *parent, } return port; - -err_mux: - typec_switch_put(port->sw); - -err_switch: - ida_simple_remove(&typec_index_ida, port->id); - kfree(port); - - return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(typec_register_port); -- 2.20.1

5 years, 1 month

2
1
0 0

[PATCH v2 1/2] dmaengine: sh: rcar-dmac: With cyclic DMA residue 0 is valid

by Dirk Behme

Having a cyclic DMA, a residue 0 is not an indication of a completed DMA. In case of cyclic DMA make sure that dma_set_residue() is called and with this a residue of 0 is forwarded correctly to the caller. Fixes: 3544d2878817 ("dmaengine: rcar-dmac: use result of updated get_residue in tx_status") Signed-off-by: Dirk Behme <dirk.behme(a)de.bosch.com> Signed-off-by: Achim Dahlhoff <Achim.Dahlhoff(a)de.bosch.com> Signed-off-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx(a)renesas.com> Cc: <stable(a)vger.kernel.org> # v4.8+ --- Note: Patch done against mainline v5.0 Changes in v2: None drivers/dma/sh/rcar-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 2b4f25698169..2ea59229d7f5 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1378,7 +1378,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan, spin_unlock_irqrestore(&rchan->lock, flags); /* if there's no residue, the cookie is complete */ - if (!residue) + if (!residue && !rchan->desc.running->cyclic) return DMA_COMPLETE; dma_set_residue(txstate, residue); -- 2.20.0

5 years, 1 month

1
2
0 0

[PATCH 4.20, 5.0] mt76x02u: use usb_bulk_msg to upload firmware

by Stanislaw Gruszka

commit 5de4db8fcb6d6fc7d9064c22841211790c0ab81b upstream. We don't need to send firmware data asynchronously, much simpler is just use synchronous usb_bulk_msg(). [ stable note: this patch was originally developed as cleanup, but it remove incorrect usage of page_frag_alloc(): alloc more than PAGE_SIZE and create not ARCH_DMA_MINALIGN dma buffers needed at least for performance reason. Was tested on 5.0 and 4.20, see https://bugzilla.kernel.org/show_bug.cgi?id=202673 and https://bugzilla.kernel.org/show_bug.cgi?id=202241 ] Tested-by: Lorenzo Bianconi <lorenzo.bianconi(a)redhat.com> Signed-off-by: Felix Fietkau <nbd(a)nbd.name> Signed-off-by: Stanislaw Gruszka <sgruszka(a)redhat.com> --- drivers/net/wireless/mediatek/mt76/mt76.h | 13 ++++++ .../net/wireless/mediatek/mt76/mt76x02_usb_mcu.c | 52 +++++++--------------- drivers/net/wireless/mediatek/mt76/usb.c | 1 - 3 files changed, 29 insertions(+), 37 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 5cd508a68609..6d29ba4046c3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -713,6 +713,19 @@ static inline bool mt76u_check_sg(struct mt76_dev *dev) udev->speed == USB_SPEED_WIRELESS)); } +static inline int +mt76u_bulk_msg(struct mt76_dev *dev, void *data, int len, int timeout) +{ + struct usb_interface *intf = to_usb_interface(dev->dev); + struct usb_device *udev = interface_to_usbdev(intf); + struct mt76_usb *usb = &dev->usb; + unsigned int pipe; + int sent; + + pipe = usb_sndbulkpipe(udev, usb->out_ep[MT_EP_OUT_INBAND_CMD]); + return usb_bulk_msg(udev, pipe, data, len, &sent, timeout); +} + int mt76u_vendor_request(struct mt76_dev *dev, u8 req, u8 req_type, u16 val, u16 offset, void *buf, size_t len); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c index 6db789f90269..2ca393e267af 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c @@ -121,18 +121,14 @@ static int __mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb, int cmd, bool wait_resp) { - struct usb_interface *intf = to_usb_interface(dev->dev); - struct usb_device *udev = interface_to_usbdev(intf); struct mt76_usb *usb = &dev->usb; - unsigned int pipe; - int ret, sent; + int ret; u8 seq = 0; u32 info; if (test_bit(MT76_REMOVED, &dev->state)) return 0; - pipe = usb_sndbulkpipe(udev, usb->out_ep[MT_EP_OUT_INBAND_CMD]); if (wait_resp) { seq = ++usb->mcu.msg_seq & 0xf; if (!seq) @@ -146,7 +142,7 @@ __mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb, if (ret) return ret; - ret = usb_bulk_msg(udev, pipe, skb->data, skb->len, &sent, 500); + ret = mt76u_bulk_msg(dev, skb->data, skb->len, 500); if (ret) return ret; @@ -268,14 +264,12 @@ void mt76x02u_mcu_fw_reset(struct mt76x02_dev *dev) EXPORT_SYMBOL_GPL(mt76x02u_mcu_fw_reset); static int -__mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, struct mt76u_buf *buf, +__mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, u8 *data, const void *fw_data, int len, u32 dst_addr) { - u8 *data = sg_virt(&buf->urb->sg[0]); - DECLARE_COMPLETION_ONSTACK(cmpl); __le32 info; u32 val; - int err; + int err, data_len; info = cpu_to_le32(FIELD_PREP(MT_MCU_MSG_PORT, CPU_TX_PORT) | FIELD_PREP(MT_MCU_MSG_LEN, len) | @@ -291,25 +285,12 @@ __mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, struct mt76u_buf *buf, mt76u_single_wr(&dev->mt76, MT_VEND_WRITE_FCE, MT_FCE_DMA_LEN, len << 16); - buf->len = MT_CMD_HDR_LEN + len + sizeof(info); - err = mt76u_submit_buf(&dev->mt76, USB_DIR_OUT, - MT_EP_OUT_INBAND_CMD, - buf, GFP_KERNEL, - mt76u_mcu_complete_urb, &cmpl); - if (err < 0) - return err; - - if (!wait_for_completion_timeout(&cmpl, - msecs_to_jiffies(1000))) { - dev_err(dev->mt76.dev, "firmware upload timed out\n"); - usb_kill_urb(buf->urb); - return -ETIMEDOUT; - } + data_len = MT_CMD_HDR_LEN + len + sizeof(info); - if (mt76u_urb_error(buf->urb)) { - dev_err(dev->mt76.dev, "firmware upload failed: %d\n", - buf->urb->status); - return buf->urb->status; + err = mt76u_bulk_msg(&dev->mt76, data, data_len, 1000); + if (err) { + dev_err(dev->mt76.dev, "firmware upload failed: %d\n", err); + return err; } val = mt76_rr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX); @@ -322,17 +303,16 @@ __mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, struct mt76u_buf *buf, int mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, const void *data, int data_len, u32 max_payload, u32 offset) { - int err, len, pos = 0, max_len = max_payload - 8; - struct mt76u_buf buf; + int len, err = 0, pos = 0, max_len = max_payload - 8; + u8 *buf; - err = mt76u_buf_alloc(&dev->mt76, &buf, 1, max_payload, max_payload, - GFP_KERNEL); - if (err < 0) - return err; + buf = kmalloc(max_payload, GFP_KERNEL); + if (!buf) + return -ENOMEM; while (data_len > 0) { len = min_t(int, data_len, max_len); - err = __mt76x02u_mcu_fw_send_data(dev, &buf, data + pos, + err = __mt76x02u_mcu_fw_send_data(dev, buf, data + pos, len, offset + pos); if (err < 0) break; @@ -341,7 +321,7 @@ int mt76x02u_mcu_fw_send_data(struct mt76x02_dev *dev, const void *data, pos += len; usleep_range(5000, 10000); } - mt76u_buf_free(&buf); + kfree(buf); return err; } diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index b061263453d4..09923cedd039 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -326,7 +326,6 @@ int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf, return mt76u_fill_rx_sg(dev, buf, nsgs, len, sglen); } -EXPORT_SYMBOL_GPL(mt76u_buf_alloc); void mt76u_buf_free(struct mt76u_buf *buf) { -- 2.7.5

5 years, 1 month

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2019