From: Russell King Date: Wed, 2 Jan 2019 10:37:05 +0000 (+0000) Subject: Merge branches 'misc', 'sa1100-for-next' and 'spectre' into for-linus X-Git-Tag: microblaze-v5.1-rc1~37^2~1 X-Git-Url: http://git.monstr.eu/?a=commitdiff_plain;h=97b6f89f7269b746b68e7985c16d2354c688d29a;hp=039bc3b7f29f79a27155182865be538ce367aae0;p=linux-2.6-microblaze.git Merge branches 'misc', 'sa1100-for-next' and 'spectre' into for-linus --- diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 91be74d8df65..a37ee58c6cf3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -27,14 +27,14 @@ config ARM select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT if MMU select CLONE_BACKWARDS - select CPU_PM if (SUSPEND || CPU_IDLE) + select CPU_PM if SUSPEND || CPU_IDLE select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS select DMA_DIRECT_OPS if !MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB select GENERIC_ALLOCATOR select GENERIC_ARCH_TOPOLOGY if ARM_CPU_TOPOLOGY - select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI) + select GENERIC_ATOMIC64 if CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP @@ -49,12 +49,12 @@ config ARM select GENERIC_STRNLEN_USER select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND - select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_MMAP_RND_BITS if MMU - select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARM_SMCCC if CPU_V7 @@ -63,16 +63,16 @@ config ARM select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU - select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU + select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD - select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) - select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL) - select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) + select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL + select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL + select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_GCC_PLUGINS select HAVE_GENERIC_DMA_COHERENT - select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)) + select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7) select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_GZIP @@ -81,15 +81,15 @@ config ARM select HAVE_KERNEL_LZO select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M - select HAVE_KRETPROBES if (HAVE_KPROBES) + select HAVE_KRETPROBES if HAVE_KPROBES select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select HAVE_OPROFILE if (HAVE_PERF_EVENTS) + select HAVE_OPROFILE if HAVE_PERF_EVENTS select HAVE_OPTPROBES if !THUMB2_KERNEL select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ select HAVE_STACKPROTECTOR @@ -1783,7 +1783,6 @@ config PARAVIRT config PARAVIRT_TIME_ACCOUNTING bool "Paravirtual steal time accounting" select PARAVIRT - default n help Select this option to enable fine granularity task steal time accounting. Time spent executing other tasks in parallel with diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 41fa7316c52b..330cd3c2eae5 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -98,6 +98,24 @@ static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline) setprop_string(fdt, "/chosen", "bootargs", cmdline); } +static void hex_str(char *out, uint32_t value) +{ + uint32_t digit; + int idx; + + for (idx = 7; idx >= 0; idx--) { + digit = value >> 28; + value <<= 4; + digit &= 0xf; + if (digit < 10) + digit += '0'; + else + digit += 'A'-10; + *out++ = digit; + } + *out = '\0'; +} + /* * Convert and fold provided ATAGs into the provided FDT. * @@ -180,6 +198,11 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space) initrd_start); setprop_cell(fdt, "/chosen", "linux,initrd-end", initrd_start + initrd_size); + } else if (atag->hdr.tag == ATAG_SERIAL) { + char serno[16+2]; + hex_str(serno, atag->u.serialnr.high); + hex_str(serno+8, atag->u.serialnr.low); + setprop_string(fdt, "/", "serial-number", serno); } } diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 88286dd483ff..28a48e0d4cca 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -243,13 +243,15 @@ .endm #endif -#define USER(x...) \ +#define USERL(l, x...) \ 9999: x; \ .pushsection __ex_table,"a"; \ .align 3; \ - .long 9999b,9001f; \ + .long 9999b,l; \ .popsection +#define USER(x...) USERL(9001f, x) + #ifdef CONFIG_SMP #define ALT_SMP(instr...) \ 9998: instr diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 0d289240b6ca..775cac3c02bb 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -111,6 +111,7 @@ #include extern unsigned int processor_id; +struct proc_info_list *lookup_processor(u32 midr); #ifdef CONFIG_CPU_CP15 #define read_cpuid(reg) \ diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h index e25f4392e1b2..e1b6f280ab08 100644 --- a/arch/arm/include/asm/proc-fns.h +++ b/arch/arm/include/asm/proc-fns.h @@ -23,7 +23,7 @@ struct mm_struct; /* * Don't change this structure - ASM code relies on it. */ -extern struct processor { +struct processor { /* MISC * get data abort address/flags */ @@ -79,9 +79,13 @@ extern struct processor { unsigned int suspend_size; void (*do_suspend)(void *); void (*do_resume)(void *); -} processor; +}; #ifndef MULTI_CPU +static inline void init_proc_vtable(const struct processor *p) +{ +} + extern void cpu_proc_init(void); extern void cpu_proc_fin(void); extern int cpu_do_idle(void); @@ -98,17 +102,50 @@ extern void cpu_reset(unsigned long addr, bool hvc) __attribute__((noreturn)); extern void cpu_do_suspend(void *); extern void cpu_do_resume(void *); #else -#define cpu_proc_init processor._proc_init -#define cpu_proc_fin processor._proc_fin -#define cpu_reset processor.reset -#define cpu_do_idle processor._do_idle -#define cpu_dcache_clean_area processor.dcache_clean_area -#define cpu_set_pte_ext processor.set_pte_ext -#define cpu_do_switch_mm processor.switch_mm -/* These three are private to arch/arm/kernel/suspend.c */ -#define cpu_do_suspend processor.do_suspend -#define cpu_do_resume processor.do_resume +extern struct processor processor; +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +#include +/* + * This can't be a per-cpu variable because we need to access it before + * per-cpu has been initialised. We have a couple of functions that are + * called in a pre-emptible context, and so can't use smp_processor_id() + * there, hence PROC_TABLE(). We insist in init_proc_vtable() that the + * function pointers for these are identical across all CPUs. + */ +extern struct processor *cpu_vtable[]; +#define PROC_VTABLE(f) cpu_vtable[smp_processor_id()]->f +#define PROC_TABLE(f) cpu_vtable[0]->f +static inline void init_proc_vtable(const struct processor *p) +{ + unsigned int cpu = smp_processor_id(); + *cpu_vtable[cpu] = *p; + WARN_ON_ONCE(cpu_vtable[cpu]->dcache_clean_area != + cpu_vtable[0]->dcache_clean_area); + WARN_ON_ONCE(cpu_vtable[cpu]->set_pte_ext != + cpu_vtable[0]->set_pte_ext); +} +#else +#define PROC_VTABLE(f) processor.f +#define PROC_TABLE(f) processor.f +static inline void init_proc_vtable(const struct processor *p) +{ + processor = *p; +} +#endif + +#define cpu_proc_init PROC_VTABLE(_proc_init) +#define cpu_check_bugs PROC_VTABLE(check_bugs) +#define cpu_proc_fin PROC_VTABLE(_proc_fin) +#define cpu_reset PROC_VTABLE(reset) +#define cpu_do_idle PROC_VTABLE(_do_idle) +#define cpu_dcache_clean_area PROC_TABLE(dcache_clean_area) +#define cpu_set_pte_ext PROC_TABLE(set_pte_ext) +#define cpu_do_switch_mm PROC_VTABLE(switch_mm) + +/* These two are private to arch/arm/kernel/suspend.c */ +#define cpu_do_suspend PROC_VTABLE(do_suspend) +#define cpu_do_resume PROC_VTABLE(do_resume) #endif extern void cpu_resume(void); diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index c136eef8f690..6390a40f16e7 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -349,6 +349,13 @@ do { \ #define __get_user_asm_byte(x, addr, err) \ __get_user_asm(x, addr, err, ldrb) +#if __LINUX_ARM_ARCH__ >= 6 + +#define __get_user_asm_half(x, addr, err) \ + __get_user_asm(x, addr, err, ldrh) + +#else + #ifndef __ARMEB__ #define __get_user_asm_half(x, __gu_addr, err) \ ({ \ @@ -367,6 +374,8 @@ do { \ }) #endif +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + #define __get_user_asm_word(x, addr, err) \ __get_user_asm(x, addr, err, ldr) #endif @@ -442,6 +451,13 @@ do { \ #define __put_user_asm_byte(x, __pu_addr, err) \ __put_user_asm(x, __pu_addr, err, strb) +#if __LINUX_ARM_ARCH__ >= 6 + +#define __put_user_asm_half(x, __pu_addr, err) \ + __put_user_asm(x, __pu_addr, err, strh) + +#else + #ifndef __ARMEB__ #define __put_user_asm_half(x, __pu_addr, err) \ ({ \ @@ -458,6 +474,8 @@ do { \ }) #endif +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + #define __put_user_asm_word(x, __pu_addr, err) \ __put_user_asm(x, __pu_addr, err, str) diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 7be511310191..d41d3598e5e5 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -6,8 +6,8 @@ void check_other_bugs(void) { #ifdef MULTI_CPU - if (processor.check_bugs) - processor.check_bugs(); + if (cpu_check_bugs) + cpu_check_bugs(); #endif } diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 6e0375e7db05..997b02302c31 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -145,6 +145,9 @@ __mmap_switched_data: #endif .size __mmap_switched_data, . - __mmap_switched_data + __FINIT + .text + /* * This provides a C-API version of __lookup_processor_type */ @@ -156,9 +159,6 @@ ENTRY(lookup_processor_type) ldmfd sp!, {r4 - r6, r9, pc} ENDPROC(lookup_processor_type) - __FINIT - .text - /* * Read processor ID register (CP#15, CR0), and look up in the linker-built * supported processor list. Note that we can't use the absolute addresses diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 6b1148cafffd..4485d0404514 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -398,7 +398,7 @@ ENTRY(secondary_startup) ldmia r4, {r5, r7, r12} @ address to jump to after sub lr, r4, r5 @ mmu has been enabled add r3, r7, lr - ldrd r4, [r3, #0] @ get secondary_data.pgdir + ldrd r4, r5, [r3, #0] @ get secondary_data.pgdir ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps ARM_BE8(eor r4, r4, r5) @ without using a temp reg. diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ac7e08886863..375b13f7e780 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -114,6 +114,11 @@ EXPORT_SYMBOL(elf_hwcap2); #ifdef MULTI_CPU struct processor processor __ro_after_init; +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +struct processor *cpu_vtable[NR_CPUS] = { + [0] = &processor, +}; +#endif #endif #ifdef MULTI_TLB struct cpu_tlb_fns cpu_tlb __ro_after_init; @@ -666,28 +671,33 @@ static void __init smp_build_mpidr_hash(void) } #endif -static void __init setup_processor(void) +/* + * locate processor in the list of supported processor types. The linker + * builds this table for us from the entries in arch/arm/mm/proc-*.S + */ +struct proc_info_list *lookup_processor(u32 midr) { - struct proc_info_list *list; + struct proc_info_list *list = lookup_processor_type(midr); - /* - * locate processor in the list of supported processor - * types. The linker builds this table for us from the - * entries in arch/arm/mm/proc-*.S - */ - list = lookup_processor_type(read_cpuid_id()); if (!list) { - pr_err("CPU configuration botched (ID %08x), unable to continue.\n", - read_cpuid_id()); - while (1); + pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n", + smp_processor_id(), midr); + while (1) + /* can't use cpu_relax() here as it may require MMU setup */; } + return list; +} + +static void __init setup_processor(void) +{ + unsigned int midr = read_cpuid_id(); + struct proc_info_list *list = lookup_processor(midr); + cpu_name = list->cpu_name; __cpu_architecture = __get_cpu_architecture(); -#ifdef MULTI_CPU - processor = *list->proc; -#endif + init_proc_vtable(list->proc); #ifdef MULTI_TLB cpu_tlb = *list->tlb; #endif @@ -699,7 +709,7 @@ static void __init setup_processor(void) #endif pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", - cpu_name, read_cpuid_id(), read_cpuid_id() & 15, + list->cpu_name, midr, midr & 15, proc_arch[cpu_architecture()], get_cr()); snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c", diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 0978282d5fc2..3bf82232b1be 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -102,6 +103,30 @@ static unsigned long get_arch_pgd(pgd_t *pgd) #endif } +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +static int secondary_biglittle_prepare(unsigned int cpu) +{ + if (!cpu_vtable[cpu]) + cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL); + + return cpu_vtable[cpu] ? 0 : -ENOMEM; +} + +static void secondary_biglittle_init(void) +{ + init_proc_vtable(lookup_processor(read_cpuid_id())->proc); +} +#else +static int secondary_biglittle_prepare(unsigned int cpu) +{ + return 0; +} + +static void secondary_biglittle_init(void) +{ +} +#endif + int __cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; @@ -109,6 +134,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) if (!smp_ops.smp_boot_secondary) return -ENOSYS; + ret = secondary_biglittle_prepare(cpu); + if (ret) + return ret; + /* * We need to tell the secondary core where to find * its stack and the page tables. @@ -359,6 +388,8 @@ asmlinkage void secondary_start_kernel(void) struct mm_struct *mm = &init_mm; unsigned int cpu; + secondary_biglittle_init(); + /* * The identity mapping is uncached (strongly ordered), so * switch away from it before attempting any exclusive accesses. @@ -693,6 +724,21 @@ void smp_send_stop(void) pr_warn("SMP: failed to stop secondary CPUs\n"); } +/* In case panic() and panic() called at the same time on CPU1 and CPU2, + * and CPU 1 calls panic_smp_self_stop() before crash_smp_send_stop() + * CPU1 can't receive the ipi irqs from CPU2, CPU1 will be always online, + * kdump fails. So split out the panic_smp_self_stop() and add + * set_cpu_online(smp_processor_id(), false). + */ +void panic_smp_self_stop(void) +{ + pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n", + smp_processor_id()); + set_cpu_online(smp_processor_id(), false); + while (1) + cpu_relax(); +} + /* * not supported here */ diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 6709a8d33963..0d4c189c7f4f 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -34,12 +34,13 @@ * Number of bytes NOT copied. */ +#ifdef CONFIG_CPU_USE_DOMAINS + #ifndef CONFIG_THUMB2_KERNEL #define LDR1W_SHIFT 0 #else #define LDR1W_SHIFT 1 #endif -#define STR1W_SHIFT 0 .macro ldr1w ptr reg abort ldrusr \reg, \ptr, 4, abort=\abort @@ -57,10 +58,30 @@ ldr4w \ptr, \reg5, \reg6, \reg7, \reg8, \abort .endm +#else + +#define LDR1W_SHIFT 0 + + .macro ldr1w ptr reg abort + USERL(\abort, W(ldr) \reg, [\ptr], #4) + .endm + + .macro ldr4w ptr reg1 reg2 reg3 reg4 abort + USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4}) + .endm + + .macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}) + .endm + +#endif /* CONFIG_CPU_USE_DOMAINS */ + .macro ldr1b ptr reg cond=al abort ldrusr \reg, \ptr, 1, \cond, abort=\abort .endm +#define STR1W_SHIFT 0 + .macro str1w ptr reg abort W(str) \reg, [\ptr], #4 .endm diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S index 970abe521197..97a6ff4b7e3c 100644 --- a/arch/arm/lib/copy_to_user.S +++ b/arch/arm/lib/copy_to_user.S @@ -35,11 +35,6 @@ */ #define LDR1W_SHIFT 0 -#ifndef CONFIG_THUMB2_KERNEL -#define STR1W_SHIFT 0 -#else -#define STR1W_SHIFT 1 -#endif .macro ldr1w ptr reg abort W(ldr) \reg, [\ptr], #4 @@ -57,6 +52,14 @@ ldr\cond\()b \reg, [\ptr], #1 .endm +#ifdef CONFIG_CPU_USE_DOMAINS + +#ifndef CONFIG_THUMB2_KERNEL +#define STR1W_SHIFT 0 +#else +#define STR1W_SHIFT 1 +#endif + .macro str1w ptr reg abort strusr \reg, \ptr, 4, abort=\abort .endm @@ -72,6 +75,20 @@ str1w \ptr, \reg8, \abort .endm +#else + +#define STR1W_SHIFT 0 + + .macro str1w ptr reg abort + USERL(\abort, W(str) \reg, [\ptr], #4) + .endm + + .macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + USERL(\abort, stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}) + .endm + +#endif /* CONFIG_CPU_USE_DOMAINS */ + .macro str1b ptr reg cond=al abort strusr \reg, \ptr, 1, \cond, abort=\abort .endm diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 746e7801dcdf..b2e4bc3a635e 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -42,6 +42,12 @@ _ASM_NOKPROBE(__get_user_1) ENTRY(__get_user_2) check_uaccess r0, 2, r1, r2, __get_user_bad +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(ldrh) r2, [r0] + +#else + #ifdef CONFIG_CPU_USE_DOMAINS rb .req ip 2: ldrbt r2, [r0], #1 @@ -56,6 +62,9 @@ rb .req r0 #else orr r2, rb, r2, lsl #8 #endif + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + mov r0, #0 ret lr ENDPROC(__get_user_2) @@ -145,7 +154,9 @@ _ASM_NOKPROBE(__get_user_bad8) .pushsection __ex_table, "a" .long 1b, __get_user_bad .long 2b, __get_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __get_user_bad +#endif .long 4b, __get_user_bad .long 5b, __get_user_bad8 .long 6b, __get_user_bad8 diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S index 38d660d3705f..515eeaa9975c 100644 --- a/arch/arm/lib/putuser.S +++ b/arch/arm/lib/putuser.S @@ -41,16 +41,13 @@ ENDPROC(__put_user_1) ENTRY(__put_user_2) check_uaccess r0, 2, r1, ip, __put_user_bad - mov ip, r2, lsr #8 -#ifdef CONFIG_THUMB2_KERNEL -#ifndef __ARMEB__ -2: TUSER(strb) r2, [r0] -3: TUSER(strb) ip, [r0, #1] +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(strh) r2, [r0] + #else -2: TUSER(strb) ip, [r0] -3: TUSER(strb) r2, [r0, #1] -#endif -#else /* !CONFIG_THUMB2_KERNEL */ + + mov ip, r2, lsr #8 #ifndef __ARMEB__ 2: TUSER(strb) r2, [r0], #1 3: TUSER(strb) ip, [r0] @@ -58,7 +55,8 @@ ENTRY(__put_user_2) 2: TUSER(strb) ip, [r0], #1 3: TUSER(strb) r2, [r0] #endif -#endif /* CONFIG_THUMB2_KERNEL */ + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ mov r0, #0 ret lr ENDPROC(__put_user_2) @@ -91,7 +89,9 @@ ENDPROC(__put_user_bad) .pushsection __ex_table, "a" .long 1b, __put_user_bad .long 2b, __put_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __put_user_bad +#endif .long 4b, __put_user_bad .long 5b, __put_user_bad .long 6b, __put_user_bad diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 9f27b486a536..5e33d1a90664 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -223,7 +223,6 @@ config MACH_NOKIA_N8X0 config OMAP3_SDRC_AC_TIMING bool "Enable SDRC AC timing register changes" depends on ARCH_OMAP3 - default n help If you know that none of your system initiators will attempt to access SDRAM during CORE DVFS, select Y here. This should boost diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index fd724a71c2e1..7298d07a9f71 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -552,7 +552,6 @@ config TOSA_BT config TOSA_USE_EXT_KEYCODES bool "Tosa keyboard: use extended keycodes" depends on MACH_TOSA - default n help Say Y here to enable the tosa keyboard driver to generate extended (>= 127) keycodes. Be aware, that they can't be correctly interpreted diff --git a/arch/arm/mm/copypage-fa.c b/arch/arm/mm/copypage-fa.c index d130a5ece5d5..bf24690ec83a 100644 --- a/arch/arm/mm/copypage-fa.c +++ b/arch/arm/mm/copypage-fa.c @@ -17,26 +17,25 @@ /* * Faraday optimised copy_user_page */ -static void __naked -fa_copy_user_page(void *kto, const void *kfrom) +static void fa_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ -1: ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - subs r2, r2, #1 @ 1\n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + subs %2, %2, #1 @ 1\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "I" (PAGE_SIZE / 32)); + mcr p15, 0, %2, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 32) + : "r3", "r4", "ip", "lr"); } void fa_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c index 49ee0c1a7209..cc819732d9b8 100644 --- a/arch/arm/mm/copypage-feroceon.c +++ b/arch/arm/mm/copypage-feroceon.c @@ -13,58 +13,56 @@ #include #include -static void __naked -feroceon_copy_user_page(void *kto, const void *kfrom) +static void feroceon_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4-r9, lr} \n\ - mov ip, %2 \n\ -1: mov lr, r1 \n\ - ldmia r1!, {r2 - r9} \n\ - pld [lr, #32] \n\ - pld [lr, #64] \n\ - pld [lr, #96] \n\ - pld [lr, #128] \n\ - pld [lr, #160] \n\ - pld [lr, #192] \n\ - pld [lr, #224] \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - subs ip, ip, #(32 * 8) \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r2 - r7, ip, lr} \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ + pld [%1, #128] \n\ + pld [%1, #160] \n\ + pld [%1, #192] \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + subs %2, %2, #(32 * 8) \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ bne 1b \n\ - mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\ - ldmfd sp!, {r4-r9, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE)); + mcr p15, 0, %2, c7, c10, 4 @ drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE) + : "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr"); } void feroceon_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index 0224416cba3c..b03202cddddb 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -40,12 +40,11 @@ static DEFINE_RAW_SPINLOCK(minicache_lock); * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { - asm volatile( - "stmfd sp!, {r4, lr} @ 2\n\ - mov r4, %2 @ 1\n\ + int tmp; + + asm volatile ("\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ 1: mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ @@ -55,13 +54,13 @@ mc_copy_user_page(void *from, void *to) mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ - subs r4, r4, #1 @ 1\n\ + subs %2, %2, #1 @ 1\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmneia %0!, {r2, r3, ip, lr} @ 4\n\ - bne 1b @ 1\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64)); + bne 1b @ " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r2", "r3", "ip", "lr"); } void v4_mc_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c index 067d0fdd630c..cd3e165afeed 100644 --- a/arch/arm/mm/copypage-v4wb.c +++ b/arch/arm/mm/copypage-v4wb.c @@ -22,29 +22,28 @@ * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -v4wb_copy_user_page(void *kto, const void *kfrom) +static void v4wb_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %1, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); } void v4wb_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c index b85c5da2e510..8614572e1296 100644 --- a/arch/arm/mm/copypage-v4wt.c +++ b/arch/arm/mm/copypage-v4wt.c @@ -20,27 +20,26 @@ * dirty data in the cache. However, we do have to ensure that * subsequent reads are up to date. */ -static void __naked -v4wt_copy_user_page(void *kto, const void *kfrom) +static void v4wt_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c7, 0 @ flush ID cache\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %2, c7, c7, 0 @ flush ID cache" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); } void v4wt_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c index 03a2042aced5..a08158241ad1 100644 --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -21,53 +21,46 @@ /* * XSC3 optimised copy_user_highpage - * r0 = destination - * r1 = source * * The source page may have some clean entries in the cache already, but we * can safely ignore them - break_cow() will flush them out of the cache * if we eventually end up using our copied page. * */ -static void __naked -xsc3_mc_copy_user_page(void *kto, const void *kfrom) +static void xsc3_mc_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r1, #64] \n\ - pld [r1, #96] \n\ + int tmp; + + asm volatile ("\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%1, #64] \n\ + pld [%1, #96] \n\ \n\ -2: ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - subs lr, lr, #1 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ +2: ldrd r2, r3, [%1], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, r3, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, r3, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + subs %2, %2, #1 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r4, r5, [%0], #8 \n\ bgt 1b \n\ - beq 2b \n\ - \n\ - ldmfd sp!, {r4, r5, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5"); } void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, @@ -85,8 +78,6 @@ void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, /* * XScale optimised clear_user_page - * r0 = destination - * r1 = virtual user address of ultimate destination page */ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) { @@ -96,10 +87,10 @@ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) mov r2, #0 \n\ mov r3, #0 \n\ 1: mcr p15, 0, %0, c7, c6, 1 @ invalidate line\n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ subs r1, r1, #1 \n\ bne 1b" : "=r" (ptr) diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 97972379f4d6..63b921936754 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -36,52 +36,51 @@ static DEFINE_RAW_SPINLOCK(minicache_lock); * Dcache aliasing issue. The writes will be forwarded to the write buffer, * and merged as appropriate. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { + int tmp; + /* * Strangely enough, best performance is achieved * when prefetching destination as well. (NP) */ - asm volatile( - "stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - pld [r0, #0] \n\ - pld [r0, #32] \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r0, #64] \n\ - pld [r0, #96] \n\ - pld [r1, #64] \n\ - pld [r1, #96] \n\ -2: ldrd r2, [r0], #8 \n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + asm volatile ("\ + pld [%0, #0] \n\ + pld [%0, #32] \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%0, #64] \n\ + pld [%0, #96] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ +2: ldrd r2, r3, [%0], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, r3, [%1], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ + strd r4, r5, [%1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + strd r2, r3, [%1], #8 \n\ + strd r4, r5, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - ldrd r2, [r0], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, r3, [%1], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ + strd r4, r5, [%1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + strd r2, r3, [%1], #8 \n\ + strd r4, r5, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - subs lr, lr, #1 \n\ + subs %2, %2, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ bgt 1b \n\ - beq 2b \n\ - ldmfd sp!, {r4, r5, pc} " - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5", "ip"); } void xscale_mc_copy_user_highpage(struct page *to, struct page *from, @@ -115,10 +114,10 @@ xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr) mov r2, #0 \n\ mov r3, #0 \n\ 1: mov ip, %0 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ subs r1, r1, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index f4ea4c62c613..58f69fa07df9 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -173,6 +173,12 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr, show_regs(regs); } #endif +#ifndef CONFIG_KUSER_HELPERS + if ((sig == SIGSEGV) && ((addr & PAGE_MASK) == 0xffff0000)) + printk_ratelimited(KERN_DEBUG + "%s: CONFIG_KUSER_HELPERS disabled at 0x%08lx\n", + tsk->comm, addr); +#endif tsk->thread.address = addr; tsk->thread.error_code = fsr; diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 81d0efb055c6..5461d589a1e2 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -274,6 +274,13 @@ .endm .macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0, bugs=0 +/* + * If we are building for big.Little with branch predictor hardening, + * we need the processor function tables to remain available after boot. + */ +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) + .section ".rodata" +#endif .type \name\()_processor_functions, #object .align 2 ENTRY(\name\()_processor_functions) @@ -309,6 +316,9 @@ ENTRY(\name\()_processor_functions) .endif .size \name\()_processor_functions, . - \name\()_processor_functions +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) + .previous +#endif .endm .macro define_cache_functions name:req diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 5544b82a2e7a..9a07916af8dd 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -52,8 +52,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - if (processor.switch_mm != cpu_v7_bpiall_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_bpiall; spectre_v2_method = "BPIALL"; @@ -61,8 +59,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - if (processor.switch_mm != cpu_v7_iciallu_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_iciallu; spectre_v2_method = "ICIALLU"; @@ -88,11 +84,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_hvc_arch_workaround_1; - processor.switch_mm = cpu_v7_hvc_switch_mm; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; spectre_v2_method = "hypervisor"; break; @@ -101,11 +95,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_smc_arch_workaround_1; - processor.switch_mm = cpu_v7_smc_switch_mm; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; spectre_v2_method = "firmware"; break; @@ -119,11 +111,6 @@ static void cpu_v7_spectre_init(void) if (spectre_v2_method) pr_info("CPU%u: Spectre v2: using %s workaround\n", smp_processor_id(), spectre_v2_method); - return; - -bl_error: - pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n", - cpu); } #else static void cpu_v7_spectre_init(void) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6fe52819e014..339eb17c9808 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -112,7 +112,7 @@ ENTRY(cpu_v7_hvc_switch_mm) hvc #0 ldmfd sp!, {r0 - r3} b cpu_v7_switch_mm -ENDPROC(cpu_v7_smc_switch_mm) +ENDPROC(cpu_v7_hvc_switch_mm) #endif ENTRY(cpu_v7_iciallu_switch_mm) mov r3, #0 diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S index 1867f3e43016..fd2ff9034d17 100644 --- a/arch/arm/mm/pv-fixup-asm.S +++ b/arch/arm/mm/pv-fixup-asm.S @@ -33,10 +33,10 @@ ENTRY(lpae_pgtables_remap_asm) add r7, r2, #0x1000 add r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER add r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER) -1: ldrd r4, [r7] +1: ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L2_ORDER + strd r4, r5, [r7], #1 << L2_ORDER cmp r7, r6 bls 1b @@ -44,22 +44,22 @@ ENTRY(lpae_pgtables_remap_asm) add r7, r2, #0x1000 add r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER bic r7, r7, #(1 << L2_ORDER) - 1 - ldrd r4, [r7] + ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L2_ORDER - ldrd r4, [r7] + strd r4, r5, [r7], #1 << L2_ORDER + ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7] + strd r4, r5, [r7] /* Update level 1 entries */ mov r6, #4 mov r7, r2 -2: ldrd r4, [r7] +2: ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L1_ORDER + strd r4, r5, [r7], #1 << L1_ORDER subs r6, r6, #1 bne 2b diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index c0a242cae79a..93fd7fc537cf 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -92,7 +92,6 @@ config OMAP_32K_TIMER config OMAP3_L2_AUX_SECURE_SAVE_RESTORE bool "OMAP3 HS/EMU save and restore for L2 AUX control register" depends on ARCH_OMAP3 && PM - default n help Without this option, L2 Auxiliary control register contents are lost during off-mode entry on HS/EMU devices. This feature diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index aff6e6eadc70..ee7b07938dd5 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -573,7 +573,7 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp *ufp, */ ufp_exc->fpexc = hwstate->fpexc; ufp_exc->fpinst = hwstate->fpinst; - ufp_exc->fpinst2 = ufp_exc->fpinst2; + ufp_exc->fpinst2 = hwstate->fpinst2; /* Ensure that VFP is disabled. */ vfp_flush_hwstate(thread);