diff options
Diffstat (limited to 'arch/arm/kernel')
38 files changed, 1085 insertions, 1021 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 5f3338eacad2..65160d5fe850 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -17,13 +17,13 @@ CFLAGS_REMOVE_return_address.o = -pg obj-y := elf.o entry-armv.o entry-common.o irq.o opcodes.o \ process.o ptrace.o return_address.o sched_clock.o \ - setup.o signal.o stacktrace.o sys_arm.o time.o traps.o + setup.o signal.o sigreturn_codes.o \ + stacktrace.o sys_arm.o time.o traps.o obj-$(CONFIG_ATAGS) += atags_parse.o obj-$(CONFIG_ATAGS_PROC) += atags_proc.o obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o -obj-$(CONFIG_OC_ETM) += etm.o obj-$(CONFIG_CPU_IDLE) += cpuidle.o obj-$(CONFIG_ISA_DMA_API) += dma.o obj-$(CONFIG_FIQ) += fiq.o fiqasm.o @@ -82,6 +82,9 @@ obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o -obj-$(CONFIG_ARM_PSCI) += psci.o +ifeq ($(CONFIG_ARM_PSCI),y) +obj-y += psci.o +obj-$(CONFIG_SMP) += psci_smp.o +endif extra-y := $(head-y) vmlinux.lds diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index ee68cce6b48e..776d9186e9c1 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -168,6 +168,7 @@ int main(void) DEFINE(VCPU_FIQ_REGS, offsetof(struct kvm_vcpu, arch.regs.fiq_regs)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc)); DEFINE(VCPU_CPSR, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr)); + DEFINE(VCPU_HCR, offsetof(struct kvm_vcpu, arch.hcr)); DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.fault.hsr)); DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); @@ -175,13 +176,13 @@ int main(void) DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); #ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); - DEFINE(VGIC_CPU_HCR, offsetof(struct vgic_cpu, vgic_hcr)); - DEFINE(VGIC_CPU_VMCR, offsetof(struct vgic_cpu, vgic_vmcr)); - DEFINE(VGIC_CPU_MISR, offsetof(struct vgic_cpu, vgic_misr)); - DEFINE(VGIC_CPU_EISR, offsetof(struct vgic_cpu, vgic_eisr)); - DEFINE(VGIC_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_elrsr)); - DEFINE(VGIC_CPU_APR, offsetof(struct vgic_cpu, vgic_apr)); - DEFINE(VGIC_CPU_LR, offsetof(struct vgic_cpu, vgic_lr)); + DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); + DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); + DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr)); + DEFINE(VGIC_V2_CPU_EISR, offsetof(struct vgic_cpu, vgic_v2.vgic_eisr)); + DEFINE(VGIC_V2_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr)); + DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr)); + DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr)); DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); #ifdef CONFIG_KVM_ARM_TIMER DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c index 90c50d4b43f7..5d1286d51154 100644 --- a/arch/arm/kernel/crash_dump.c +++ b/arch/arm/kernel/crash_dump.c @@ -39,7 +39,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!csize) return 0; - vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE); if (!vaddr) return -ENOMEM; diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 5859c8bc727c..a44e7d11ab02 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -212,7 +212,7 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) } if (!mdesc_best) { const char *prop; - long size; + int size; early_print("\nError: unrecognized/unsupported " "device tree compatible list:\n[ "); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 582b405befc5..45a68d6bb2a3 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -192,6 +192,7 @@ __dabt_svc: svc_entry mov r2, sp dabt_helper + THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) @@ -415,9 +416,8 @@ __und_usr: bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 1: ldrt r0, [r4] -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r0, r0 @ little endian instruction -#endif + ARM_BE8(rev r0, r0) @ little endian instruction + @ r0 = 32-bit ARM instruction which caused the exception @ r2 = PC value for the following instruction (:= regs->ARM_pc) @ r4 = PC value for the faulting instruction @@ -741,6 +741,18 @@ ENDPROC(__switch_to) #endif .endm + .macro kuser_pad, sym, size + .if (. - \sym) & 3 + .rept 4 - (. - \sym) & 3 + .byte 0 + .endr + .endif + .rept (\size - (. - \sym)) / 4 + .word 0xe7fddef1 + .endr + .endm + +#ifdef CONFIG_KUSER_HELPERS .align 5 .globl __kuser_helper_start __kuser_helper_start: @@ -831,18 +843,13 @@ kuser_cmpxchg64_fixup: #error "incoherent kernel configuration" #endif - /* pad to next slot */ - .rept (16 - (. - __kuser_cmpxchg64)/4) - .word 0 - .endr - - .align 5 + kuser_pad __kuser_cmpxchg64, 64 __kuser_memory_barrier: @ 0xffff0fa0 smp_dmb arm usr_ret lr - .align 5 + kuser_pad __kuser_memory_barrier, 32 __kuser_cmpxchg: @ 0xffff0fc0 @@ -915,13 +922,14 @@ kuser_cmpxchg32_fixup: #endif - .align 5 + kuser_pad __kuser_cmpxchg, 32 __kuser_get_tls: @ 0xffff0fe0 ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init usr_ret lr mrc p15, 0, r0, c13, c0, 3 @ 0xffff0fe8 hardware TLS code - .rep 4 + kuser_pad __kuser_get_tls, 16 + .rep 3 .word 0 @ 0xffff0ff0 software TLS value, then .endr @ pad up to __kuser_helper_version @@ -931,14 +939,16 @@ __kuser_helper_version: @ 0xffff0ffc .globl __kuser_helper_end __kuser_helper_end: +#endif + THUMB( .thumb ) /* * Vector stubs. * - * This code is copied to 0xffff0200 so we can use branches in the - * vectors, rather than ldr's. Note that this code must not - * exceed 0x300 bytes. + * This code is copied to 0xffff1000 so we can use branches in the + * vectors, rather than ldr's. Note that this code must not exceed + * a page size. * * Common stub entry macro: * Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC @@ -985,8 +995,17 @@ ENDPROC(vector_\name) 1: .endm - .globl __stubs_start + .section .stubs, "ax", %progbits __stubs_start: + @ This must be the first word + .word vector_swi + +vector_rst: + ARM( swi SYS_ERROR0 ) + THUMB( svc #0 ) + THUMB( nop ) + b vector_und + /* * Interrupt dispatcher */ @@ -1081,6 +1100,16 @@ __stubs_start: .align 5 /*============================================================================= + * Address exception handler + *----------------------------------------------------------------------------- + * These aren't too critical. + * (they're not supposed to happen, and won't happen in 32-bit data mode). + */ + +vector_addrexcptn: + b vector_addrexcptn + +/*============================================================================= * Undefined FIQs *----------------------------------------------------------------------------- * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC @@ -1093,45 +1122,19 @@ __stubs_start: vector_fiq: subs pc, lr, #4 -/*============================================================================= - * Address exception handler - *----------------------------------------------------------------------------- - * These aren't too critical. - * (they're not supposed to happen, and won't happen in 32-bit data mode). - */ + .globl vector_fiq_offset + .equ vector_fiq_offset, vector_fiq -vector_addrexcptn: - b vector_addrexcptn - -/* - * We group all the following data together to optimise - * for CPUs with separate I & D caches. - */ - .align 5 - -.LCvswi: - .word vector_swi - - .globl __stubs_end -__stubs_end: - - .equ stubs_offset, __vectors_start + 0x200 - __stubs_start - - .globl __vectors_start + .section .vectors, "ax", %progbits __vectors_start: - ARM( swi SYS_ERROR0 ) - THUMB( svc #0 ) - THUMB( nop ) - W(b) vector_und + stubs_offset - W(ldr) pc, .LCvswi + stubs_offset - W(b) vector_pabt + stubs_offset - W(b) vector_dabt + stubs_offset - W(b) vector_addrexcptn + stubs_offset - W(b) vector_irq + stubs_offset - W(b) vector_fiq + stubs_offset - - .globl __vectors_end -__vectors_end: + W(b) vector_rst + W(b) vector_und + W(ldr) pc, __vectors_start + 0x1000 + W(b) vector_pabt + W(b) vector_dabt + W(b) vector_addrexcptn + W(b) vector_irq + W(b) vector_fiq .data diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bc5bc0a97131..11d68917d3b1 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -362,6 +362,16 @@ ENTRY(vector_swi) str r0, [sp, #S_OLD_R0] @ Save OLD_R0 zero_fp +#ifdef CONFIG_ALIGNMENT_TRAP + ldr ip, __cr_alignment + ldr ip, [ip] + mcr p15, 0, ip, c1, c0 @ update control register +#endif + + enable_irq + ct_user_exit + get_thread_info tsk + /* * Get the system call number. */ @@ -375,13 +385,11 @@ ENTRY(vector_swi) #ifdef CONFIG_ARM_THUMB tst r8, #PSR_T_BIT movne r10, #0 @ no thumb OABI emulation - ldreq r10, [lr, #-4] @ get SWI instruction + USER( ldreq r10, [lr, #-4] ) @ get SWI instruction #else - ldr r10, [lr, #-4] @ get SWI instruction -#endif -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r10, r10 @ little endian instruction + USER( ldr r10, [lr, #-4] ) @ get SWI instruction #endif + ARM_BE8(rev r10, r10) @ little endian instruction #elif defined(CONFIG_AEABI) @@ -392,22 +400,13 @@ ENTRY(vector_swi) /* Legacy ABI only, possibly thumb mode. */ tst r8, #PSR_T_BIT @ this is SPSR from save_user_regs addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in - ldreq scno, [lr, #-4] + USER( ldreq scno, [lr, #-4] ) #else /* Legacy ABI only. */ - ldr scno, [lr, #-4] @ get SWI instruction -#endif - -#ifdef CONFIG_ALIGNMENT_TRAP - ldr ip, __cr_alignment - ldr ip, [ip] - mcr p15, 0, ip, c1, c0 @ update control register + USER( ldr scno, [lr, #-4] ) @ get SWI instruction #endif - enable_irq - ct_user_exit - get_thread_info tsk adr tbl, sys_call_table @ load syscall table pointer #if defined(CONFIG_OABI_COMPAT) @@ -442,6 +441,21 @@ local_restart: eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back bcs arm_syscall b sys_ni_syscall @ not private func + +#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI) + /* + * We failed to handle a fault trying to access the page + * containing the swi instruction, but we're not really in a + * position to return -EFAULT. Instead, return back to the + * instruction and re-enter the user fault handling path trying + * to page it in. This will likely result in sending SEGV to the + * current task. + */ +9001: + sub lr, lr, #4 + str lr, [sp, #S_PC] + b ret_fast_syscall +#endif ENDPROC(vector_swi) /* diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c deleted file mode 100644 index 8ff0ecdc637f..000000000000 --- a/arch/arm/kernel/etm.c +++ /dev/null @@ -1,660 +0,0 @@ -/* - * linux/arch/arm/kernel/etm.c - * - * Driver for ARM's Embedded Trace Macrocell and Embedded Trace Buffer. - * - * Copyright (C) 2009 Nokia Corporation. - * Alexander Shishkin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/io.h> -#include <linux/sysrq.h> -#include <linux/device.h> -#include <linux/clk.h> -#include <linux/amba/bus.h> -#include <linux/fs.h> -#include <linux/uaccess.h> -#include <linux/miscdevice.h> -#include <linux/vmalloc.h> -#include <linux/mutex.h> -#include <linux/module.h> -#include <asm/hardware/coresight.h> -#include <asm/sections.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Alexander Shishkin"); - -/* - * ETM tracer state - */ -struct tracectx { - unsigned int etb_bufsz; - void __iomem *etb_regs; - void __iomem *etm_regs; - unsigned long flags; - int ncmppairs; - int etm_portsz; - struct device *dev; - struct clk *emu_clk; - struct mutex mutex; -}; - -static struct tracectx tracer; - -static inline bool trace_isrunning(struct tracectx *t) -{ - return !!(t->flags & TRACER_RUNNING); -} - -static int etm_setup_address_range(struct tracectx *t, int n, - unsigned long start, unsigned long end, int exclude, int data) -{ - u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \ - ETMAAT_NOVALCMP; - - if (n < 1 || n > t->ncmppairs) - return -EINVAL; - - /* comparators and ranges are numbered starting with 1 as opposed - * to bits in a word */ - n--; - - if (data) - flags |= ETMAAT_DLOADSTORE; - else - flags |= ETMAAT_IEXEC; - - /* first comparator for the range */ - etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2)); - etm_writel(t, start, ETMR_COMP_VAL(n * 2)); - - /* second comparator is right next to it */ - etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1)); - etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1)); - - flags = exclude ? ETMTE_INCLEXCL : 0; - etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL); - - return 0; -} - -static int trace_start(struct tracectx *t) -{ - u32 v; - unsigned long timeout = TRACER_TIMEOUT; - - etb_unlock(t); - - etb_writel(t, 0, ETBR_FORMATTERCTRL); - etb_writel(t, 1, ETBR_CTRL); - - etb_lock(t); - - /* configure etm */ - v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz); - - if (t->flags & TRACER_CYCLE_ACC) - v |= ETMCTRL_CYCLEACCURATE; - - etm_unlock(t); - - etm_writel(t, v, ETMR_CTRL); - - while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to assert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_setup_address_range(t, 1, (unsigned long)_stext, - (unsigned long)_etext, 0, 0); - etm_writel(t, 0, ETMR_TRACEENCTRL2); - etm_writel(t, 0, ETMR_TRACESSCTRL); - etm_writel(t, 0x6f, ETMR_TRACEENEVT); - - v &= ~ETMCTRL_PROGRAM; - v |= ETMCTRL_PORTSEL; - - etm_writel(t, v, ETMR_CTRL); - - timeout = TRACER_TIMEOUT; - while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_lock(t); - - t->flags |= TRACER_RUNNING; - - return 0; -} - -static int trace_stop(struct tracectx *t) -{ - unsigned long timeout = TRACER_TIMEOUT; - - etm_unlock(t); - - etm_writel(t, 0x440, ETMR_CTRL); - while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to assert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_lock(t); - - etb_unlock(t); - etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL); - - timeout = TRACER_TIMEOUT; - while (etb_readl(t, ETBR_FORMATTERCTRL) & - ETBFF_MANUAL_FLUSH && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for formatter flush to commence " - "timed out\n"); - etb_lock(t); - return -EFAULT; - } - - etb_writel(t, 0, ETBR_CTRL); - - etb_lock(t); - - t->flags &= ~TRACER_RUNNING; - - return 0; -} - -static int etb_getdatalen(struct tracectx *t) -{ - u32 v; - int rp, wp; - - v = etb_readl(t, ETBR_STATUS); - - if (v & 1) - return t->etb_bufsz; - - rp = etb_readl(t, ETBR_READADDR); - wp = etb_readl(t, ETBR_WRITEADDR); - - if (rp > wp) { - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_WRITEADDR); - - return 0; - } - - return wp - rp; -} - -/* sysrq+v will always stop the running trace and leave it at that */ -static void etm_dump(void) -{ - struct tracectx *t = &tracer; - u32 first = 0; - int length; - - if (!t->etb_regs) { - printk(KERN_INFO "No tracing hardware found\n"); - return; - } - - if (trace_isrunning(t)) - trace_stop(t); - - etb_unlock(t); - - length = etb_getdatalen(t); - - if (length == t->etb_bufsz) - first = etb_readl(t, ETBR_WRITEADDR); - - etb_writel(t, first, ETBR_READADDR); - - printk(KERN_INFO "Trace buffer contents length: %d\n", length); - printk(KERN_INFO "--- ETB buffer begin ---\n"); - for (; length; length--) - printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM))); - printk(KERN_INFO "\n--- ETB buffer end ---\n"); - - /* deassert the overflow bit */ - etb_writel(t, 1, ETBR_CTRL); - etb_writel(t, 0, ETBR_CTRL); - - etb_writel(t, 0, ETBR_TRIGGERCOUNT); - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_WRITEADDR); - - etb_lock(t); -} - -static void sysrq_etm_dump(int key) -{ - dev_dbg(tracer.dev, "Dumping ETB buffer\n"); - etm_dump(); -} - -static struct sysrq_key_op sysrq_etm_op = { - .handler = sysrq_etm_dump, - .help_msg = "etm-buffer-dump(v)", - .action_msg = "etm", -}; - -static int etb_open(struct inode *inode, struct file *file) -{ - if (!tracer.etb_regs) - return -ENODEV; - - file->private_data = &tracer; - - return nonseekable_open(inode, file); -} - -static ssize_t etb_read(struct file *file, char __user *data, - size_t len, loff_t *ppos) -{ - int total, i; - long length; - struct tracectx *t = file->private_data; - u32 first = 0; - u32 *buf; - - mutex_lock(&t->mutex); - - if (trace_isrunning(t)) { - length = 0; - goto out; - } - - etb_unlock(t); - - total = etb_getdatalen(t); - if (total == t->etb_bufsz) - first = etb_readl(t, ETBR_WRITEADDR); - - etb_writel(t, first, ETBR_READADDR); - - length = min(total * 4, (int)len); - buf = vmalloc(length); - - dev_dbg(t->dev, "ETB buffer length: %d\n", total); - dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS)); - for (i = 0; i < length / 4; i++) - buf[i] = etb_readl(t, ETBR_READMEM); - - /* the only way to deassert overflow bit in ETB status is this */ - etb_writel(t, 1, ETBR_CTRL); - etb_writel(t, 0, ETBR_CTRL); - - etb_writel(t, 0, ETBR_WRITEADDR); - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_TRIGGERCOUNT); - - etb_lock(t); - - length -= copy_to_user(data, buf, length); - vfree(buf); - -out: - mutex_unlock(&t->mutex); - - return length; -} - -static int etb_release(struct inode *inode, struct file *file) -{ - /* there's nothing to do here, actually */ - return 0; -} - -static const struct file_operations etb_fops = { - .owner = THIS_MODULE, - .read = etb_read, - .open = etb_open, - .release = etb_release, - .llseek = no_llseek, -}; - -static struct miscdevice etb_miscdev = { - .name = "tracebuf", - .minor = 0, - .fops = &etb_fops, -}; - -static int etb_probe(struct amba_device *dev, const struct amba_id *id) -{ - struct tracectx *t = &tracer; - int ret = 0; - - ret = amba_request_regions(dev, NULL); - if (ret) - goto out; - - t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res)); - if (!t->etb_regs) { - ret = -ENOMEM; - goto out_release; - } - - amba_set_drvdata(dev, t); - - etb_miscdev.parent = &dev->dev; - - ret = misc_register(&etb_miscdev); - if (ret) - goto out_unmap; - - t->emu_clk = clk_get(&dev->dev, "emu_src_ck"); - if (IS_ERR(t->emu_clk)) { - dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n"); - return -EFAULT; - } - - clk_enable(t->emu_clk); - - etb_unlock(t); - t->etb_bufsz = etb_readl(t, ETBR_DEPTH); - dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz); - - /* make sure trace capture is disabled */ - etb_writel(t, 0, ETBR_CTRL); - etb_writel(t, 0x1000, ETBR_FORMATTERCTRL); - etb_lock(t); - - dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n"); - -out: - return ret; - -out_unmap: - amba_set_drvdata(dev, NULL); - iounmap(t->etb_regs); - -out_release: - amba_release_regions(dev); - - return ret; -} - -static int etb_remove(struct amba_device *dev) -{ - struct tracectx *t = amba_get_drvdata(dev); - - amba_set_drvdata(dev, NULL); - - iounmap(t->etb_regs); - t->etb_regs = NULL; - - clk_disable(t->emu_clk); - clk_put(t->emu_clk); - - amba_release_regions(dev); - - return 0; -} - -static struct amba_id etb_ids[] = { - { - .id = 0x0003b907, - .mask = 0x0007ffff, - }, - { 0, 0 }, -}; - -static struct amba_driver etb_driver = { - .drv = { - .name = "etb", - .owner = THIS_MODULE, - }, - .probe = etb_probe, - .remove = etb_remove, - .id_table = etb_ids, -}; - -/* use a sysfs file "trace_running" to start/stop tracing */ -static ssize_t trace_running_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%x\n", trace_isrunning(&tracer)); -} - -static ssize_t trace_running_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t n) -{ - unsigned int value; - int ret; - - if (sscanf(buf, "%u", &value) != 1) - return -EINVAL; - - mutex_lock(&tracer.mutex); - ret = value ? trace_start(&tracer) : trace_stop(&tracer); - mutex_unlock(&tracer.mutex); - - return ret ? : n; -} - -static struct kobj_attribute trace_running_attr = - __ATTR(trace_running, 0644, trace_running_show, trace_running_store); - -static ssize_t trace_info_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st; - int datalen; - - etb_unlock(&tracer); - datalen = etb_getdatalen(&tracer); - etb_wa = etb_readl(&tracer, ETBR_WRITEADDR); - etb_ra = etb_readl(&tracer, ETBR_READADDR); - etb_st = etb_readl(&tracer, ETBR_STATUS); - etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL); - etb_lock(&tracer); - - etm_unlock(&tracer); - etm_ctrl = etm_readl(&tracer, ETMR_CTRL); - etm_st = etm_readl(&tracer, ETMR_STATUS); - etm_lock(&tracer); - - return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n" - "ETBR_WRITEADDR:\t%08x\n" - "ETBR_READADDR:\t%08x\n" - "ETBR_STATUS:\t%08x\n" - "ETBR_FORMATTERCTRL:\t%08x\n" - "ETMR_CTRL:\t%08x\n" - "ETMR_STATUS:\t%08x\n", - datalen, - tracer.ncmppairs, - etb_wa, - etb_ra, - etb_st, - etb_fc, - etm_ctrl, - etm_st - ); -} - -static struct kobj_attribute trace_info_attr = - __ATTR(trace_info, 0444, trace_info_show, NULL); - -static ssize_t trace_mode_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%d %d\n", - !!(tracer.flags & TRACER_CYCLE_ACC), - tracer.etm_portsz); -} - -static ssize_t trace_mode_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t n) -{ - unsigned int cycacc, portsz; - - if (sscanf(buf, "%u %u", &cycacc, &portsz) != 2) - return -EINVAL; - - mutex_lock(&tracer.mutex); - if (cycacc) - tracer.flags |= TRACER_CYCLE_ACC; - else - tracer.flags &= ~TRACER_CYCLE_ACC; - - tracer.etm_portsz = portsz & 0x0f; - mutex_unlock(&tracer.mutex); - - return n; -} - -static struct kobj_attribute trace_mode_attr = - __ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store); - -static int etm_probe(struct amba_device *dev, const struct amba_id *id) -{ - struct tracectx *t = &tracer; - int ret = 0; - - if (t->etm_regs) { - dev_dbg(&dev->dev, "ETM already initialized\n"); - ret = -EBUSY; - goto out; - } - - ret = amba_request_regions(dev, NULL); - if (ret) - goto out; - - t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res)); - if (!t->etm_regs) { - ret = -ENOMEM; - goto out_release; - } - - amba_set_drvdata(dev, t); - - mutex_init(&t->mutex); - t->dev = &dev->dev; - t->flags = TRACER_CYCLE_ACC; - t->etm_portsz = 1; - - etm_unlock(t); - (void)etm_readl(t, ETMMR_PDSR); - /* dummy first read */ - (void)etm_readl(&tracer, ETMMR_OSSRR); - - t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf; - etm_writel(t, 0x440, ETMR_CTRL); - etm_lock(t); - - ret = sysfs_create_file(&dev->dev.kobj, - &trace_running_attr.attr); - if (ret) - goto out_unmap; - - /* failing to create any of these two is not fatal */ - ret = sysfs_create_file(&dev->dev.kobj, &trace_info_attr.attr); - if (ret) - dev_dbg(&dev->dev, "Failed to create trace_info in sysfs\n"); - - ret = sysfs_create_file(&dev->dev.kobj, &trace_mode_attr.attr); - if (ret) - dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n"); - - dev_dbg(t->dev, "ETM AMBA driver initialized.\n"); - -out: - return ret; - -out_unmap: - amba_set_drvdata(dev, NULL); - iounmap(t->etm_regs); - -out_release: - amba_release_regions(dev); - - return ret; -} - -static int etm_remove(struct amba_device *dev) -{ - struct tracectx *t = amba_get_drvdata(dev); - - amba_set_drvdata(dev, NULL); - - iounmap(t->etm_regs); - t->etm_regs = NULL; - - amba_release_regions(dev); - - sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr); - sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr); - sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr); - - return 0; -} - -static struct amba_id etm_ids[] = { - { - .id = 0x0003b921, - .mask = 0x0007ffff, - }, - { 0, 0 }, -}; - -static struct amba_driver etm_driver = { - .drv = { - .name = "etm", - .owner = THIS_MODULE, - }, - .probe = etm_probe, - .remove = etm_remove, - .id_table = etm_ids, -}; - -static int __init etm_init(void) -{ - int retval; - - retval = amba_driver_register(&etb_driver); - if (retval) { - printk(KERN_ERR "Failed to register etb\n"); - return retval; - } - - retval = amba_driver_register(&etm_driver); - if (retval) { - amba_driver_unregister(&etb_driver); - printk(KERN_ERR "Failed to probe etm\n"); - return retval; - } - - /* not being able to install this handler is not fatal */ - (void)register_sysrq_key('v', &sysrq_etm_op); - - return 0; -} - -device_initcall(etm_init); - diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index 2adda11f712f..25442f451148 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -47,6 +47,11 @@ #include <asm/irq.h> #include <asm/traps.h> +#define FIQ_OFFSET ({ \ + extern void *vector_fiq_offset; \ + (unsigned)&vector_fiq_offset; \ + }) + static unsigned long no_fiq_insn; /* Default reacquire function @@ -80,13 +85,16 @@ int show_fiq_list(struct seq_file *p, int prec) void set_fiq_handler(void *start, unsigned int length) { #if defined(CONFIG_CPU_USE_DOMAINS) - memcpy((void *)0xffff001c, start, length); + void *base = (void *)0xffff0000; #else - memcpy(vectors_page + 0x1c, start, length); + void *base = vectors_page; #endif - flush_icache_range(0xffff001c, 0xffff001c + length); + unsigned offset = FIQ_OFFSET; + + memcpy(base + offset, start, length); + flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length); if (!vectors_high()) - flush_icache_range(0x1c, 0x1c + length); + flush_icache_range(offset, offset + length); } int claim_fiq(struct fiq_handler *f) @@ -144,6 +152,7 @@ EXPORT_SYMBOL(disable_fiq); void __init init_FIQ(int start) { - no_fiq_insn = *(unsigned long *)0xffff001c; + unsigned offset = FIQ_OFFSET; + no_fiq_insn = *(unsigned long *)(0xffff0000 + offset); fiq_start = start; } diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 8bac553fe213..2d1bf8c6353d 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -77,6 +77,7 @@ __HEAD ENTRY(stext) + ARM_BE8(setend be ) @ ensure we are in BE8 mode THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, @@ -109,7 +110,7 @@ ENTRY(stext) sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET) add r8, r8, r4 @ PHYS_OFFSET #else - ldr r8, =PHYS_OFFSET @ always constant in this case + ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case #endif /* @@ -342,7 +343,6 @@ __turn_mmu_on_loc: .long __turn_mmu_on_end #if defined(CONFIG_SMP) - __CPUINIT ENTRY(secondary_startup) /* * Common entry point for secondary CPUs. @@ -351,6 +351,9 @@ ENTRY(secondary_startup) * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ + + ARM_BE8(setend be) @ ensure we are in BE8 mode + #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install_secondary #endif @@ -584,8 +587,10 @@ __fixup_a_pv_table: b 2f 1: add r7, r3 ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) and ip, 0x8f00 orr ip, r6 @ mask in offset bits 31-24 +ARM_BE8(rev16 ip, ip) strh ip, [r7, #2] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot @@ -594,8 +599,14 @@ __fixup_a_pv_table: #else b 2f 1: ldr ip, [r7, r3] +#ifdef CONFIG_CPU_ENDIAN_BE8 + @ in BE8, we load data in BE, but instructions still in LE + bic ip, ip, #0xff000000 + orr ip, ip, r6, lsl#24 +#else bic ip, ip, #0x000000ff orr ip, ip, r6 @ mask in offset bits 31-24 +#endif str ip, [r7, r3] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 1fd749ee4a1b..7eee611b6ee5 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -29,6 +29,7 @@ #include <linux/hw_breakpoint.h> #include <linux/smp.h> #include <linux/cpu_pm.h> +#include <linux/coresight.h> #include <asm/cacheflush.h> #include <asm/cputype.h> @@ -36,7 +37,6 @@ #include <asm/hw_breakpoint.h> #include <asm/kdebug.h> #include <asm/traps.h> -#include <asm/hardware/coresight.h> /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); @@ -975,7 +975,7 @@ static void reset_ctrl_regs(void *unused) * Unconditionally clear the OS lock by writing a value * other than CS_LAR_KEY to the access register. */ - ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY); + ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK); isb(); /* @@ -1049,7 +1049,8 @@ static struct notifier_block dbg_cpu_pm_nb = { static void __init pm_init(void) { - cpu_pm_register_notifier(&dbg_cpu_pm_nb); + if (has_ossr) + cpu_pm_register_notifier(&dbg_cpu_pm_nb); } #else static inline void pm_init(void) diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 1315c4ccfa56..dbe21107945a 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -153,6 +153,8 @@ THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL orr r7, r7, #3 @ PL1PCEN | PL1PCTEN mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL + mov r7, #0 + mcrr p15, 4, r7, r7, c14 @ CNTVOFF 1: #endif diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17b8f38..1e782bdeee49 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 18a76282970e..380c20fb9c85 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> #include <asm/system_info.h> +#include <asm/opcodes.h> #include "kprobes.h" @@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) if (handler) { /* We can emulate the instruction in (possibly) modified form */ - asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist; + asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) | + (rn << 16) | reglist); asi->insn_handler = handler; return INSN_GOOD; } @@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, #ifdef CONFIG_THUMB2_KERNEL if (thumb) { u16 *thumb_insn = (u16 *)asi->insn; - thumb_insn[1] = 0x4770; /* Thumb bx lr */ - thumb_insn[2] = 0x4770; /* Thumb bx lr */ + /* Thumb bx lr */ + thumb_insn[1] = __opcode_to_mem_thumb16(0x4770); + thumb_insn[2] = __opcode_to_mem_thumb16(0x4770); return insn; } - asi->insn[1] = 0xe12fff1e; /* ARM bx lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */ #else - asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */ #endif /* Make an ARM instruction unconditional */ if (insn < 0xe0000000) @@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, if (thumb) { u16 *ip = (u16 *)asi->insn; if (is_wide_instruction(insn)) - *ip++ = insn >> 16; - *ip++ = insn; + *ip++ = __opcode_to_mem_thumb16(insn >> 16); + *ip++ = __opcode_to_mem_thumb16(insn); return; } #endif - asi->insn[0] = insn; + asi->insn[0] = __opcode_to_mem_arm(insn); } /* diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 6123daf397a7..b82e798983c4 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -163,9 +163,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi); /* Fixup modified instruction to have halfwords in correct order...*/ - insn = asi->insn[0]; - ((u16 *)asi->insn)[0] = insn >> 16; - ((u16 *)asi->insn)[1] = insn & 0xffff; + insn = __mem_to_opcode_arm(asi->insn[0]); + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16); + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff); return ret; } @@ -1153,7 +1153,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) { insn &= ~0x00ff; insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */ - ((u16 *)asi->insn)[0] = insn; + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn); asi->insn_handler = t16_emulate_hiregs; return INSN_GOOD; } @@ -1182,8 +1182,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and LR in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half STMDB R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = t16_emulate_push; return INSN_GOOD; } @@ -1232,8 +1234,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and PC in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half LDMIA R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc : t16_emulate_pop_nopc; return INSN_GOOD; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 170e9f34003f..1c6ece51781c 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -26,6 +26,7 @@ #include <linux/stop_machine.h> #include <linux/stringify.h> #include <asm/traps.h> +#include <asm/opcodes.h> #include <asm/cacheflush.h> #include "kprobes.h" @@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) #ifdef CONFIG_THUMB2_KERNEL thumb = true; addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ - insn = ((u16 *)addr)[0]; + insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]); if (is_wide_instruction(insn)) { - insn <<= 16; - insn |= ((u16 *)addr)[1]; + u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]); + insn = __opcode_thumb32_compose(insn, inst2); decode_insn = thumb32_kprobe_decode_insn; } else decode_insn = thumb16_kprobe_decode_insn; @@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) thumb = false; if (addr & 0x3) return -EINVAL; - insn = *p->addr; + insn = __mem_to_opcode_arm(*p->addr); decode_insn = arm_kprobe_decode_insn; #endif diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 4fb074c446bf..70ae735dec53 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -14,10 +14,11 @@ #include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> +#include <asm/fncpy.h> #include <asm/mach-types.h> #include <asm/system_misc.h> -extern const unsigned char relocate_new_kernel[]; +extern void relocate_new_kernel(void); extern const unsigned int relocate_new_kernel_size; extern unsigned long kexec_start_address; @@ -73,6 +74,7 @@ void machine_crash_nonpanic_core(void *unused) crash_save_cpu(®s, smp_processor_id()); flush_cache_all(); + set_cpu_online(smp_processor_id(), false); atomic_dec(&waiting_for_crash_ipi); while (1) cpu_relax(); @@ -132,6 +134,8 @@ void machine_kexec(struct kimage *image) { unsigned long page_list; unsigned long reboot_code_buffer_phys; + unsigned long reboot_entry = (unsigned long)relocate_new_kernel; + unsigned long reboot_entry_phys; void *reboot_code_buffer; if (num_online_cpus() > 1) { @@ -155,16 +159,23 @@ void machine_kexec(struct kimage *image) /* copy our kernel relocation code to the control code page */ - memcpy(reboot_code_buffer, - relocate_new_kernel, relocate_new_kernel_size); + reboot_entry = fncpy(reboot_code_buffer, + reboot_entry, + relocate_new_kernel_size); + reboot_entry_phys = (unsigned long)reboot_entry + + (reboot_code_buffer_phys - (unsigned long)reboot_code_buffer); - - flush_icache_range((unsigned long) reboot_code_buffer, - (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); printk(KERN_INFO "Bye!\n"); if (kexec_reinit) kexec_reinit(); - soft_restart(reboot_code_buffer_phys); + soft_restart(reboot_entry_phys); +} + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_ARM_LPAE + VMCOREINFO_CONFIG(ARM_LPAE); +#endif } diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 1e9be5d25e56..1705ee80d097 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -24,6 +24,7 @@ #include <asm/sections.h> #include <asm/smp_plat.h> #include <asm/unwind.h> +#include <asm/opcodes.h> #ifdef CONFIG_XIP_KERNEL /* @@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, Elf32_Sym *sym; const char *symname; s32 offset; + u32 tmp; #ifdef CONFIG_THUMB2_KERNEL u32 upper, lower, sign, j1, j2; #endif @@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - offset = (*(u32 *)loc & 0x00ffffff) << 2; + offset = __mem_to_opcode_arm(*(u32 *)loc); + offset = (offset & 0x00ffffff) << 2; if (offset & 0x02000000) offset -= 0x04000000; @@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, } offset >>= 2; + offset &= 0x00ffffff; - *(u32 *)loc &= 0xff000000; - *(u32 *)loc |= offset & 0x00ffffff; + *(u32 *)loc &= __opcode_to_mem_arm(0xff000000); + *(u32 *)loc |= __opcode_to_mem_arm(offset); break; case R_ARM_V4BX: @@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, * other bits to re-code instruction as * MOV PC,Rm. */ - *(u32 *)loc &= 0xf000000f; - *(u32 *)loc |= 0x01a0f000; + *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f); + *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000); break; case R_ARM_PREL31: @@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - offset = *(u32 *)loc; + offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); offset = (offset ^ 0x8000) - 0x8000; @@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS) offset >>= 16; - *(u32 *)loc &= 0xfff0f000; - *(u32 *)loc |= ((offset & 0xf000) << 4) | - (offset & 0x0fff); + tmp &= 0xfff0f000; + tmp |= ((offset & 0xf000) << 4) | + (offset & 0x0fff); + + *(u32 *)loc = __opcode_to_mem_arm(tmp); break; #ifdef CONFIG_THUMB2_KERNEL case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * 25 bit signed address range (Thumb-2 BL and B.W @@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, sign = (offset >> 24) & 1; j1 = sign ^ (~(offset >> 23) & 1); j2 = sign ^ (~(offset >> 22) & 1); - *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) | + upper = (u16)((upper & 0xf800) | (sign << 10) | ((offset >> 12) & 0x03ff)); - *(u16 *)(loc + 2) = (u16)((lower & 0xd000) | - (j1 << 13) | (j2 << 11) | - ((offset >> 1) & 0x07ff)); + lower = (u16)((lower & 0xd000) | + (j1 << 13) | (j2 << 11) | + ((offset >> 1) & 0x07ff)); + + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * MOVT/MOVW instructions encoding in Thumb-2: @@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS) offset >>= 16; - *(u16 *)loc = (u16)((upper & 0xfbf0) | - ((offset & 0xf000) >> 12) | - ((offset & 0x0800) >> 1)); - *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) | - ((offset & 0x0700) << 4) | - (offset & 0x00ff)); + upper = (u16)((upper & 0xfbf0) | + ((offset & 0xf000) >> 12) | + ((offset & 0x0800) >> 1)); + lower = (u16)((lower & 0x8f00) | + ((offset & 0x0700) << 4) | + (offset & 0x00ff)); + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; #endif @@ -296,6 +307,10 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, maps[ARM_SEC_EXIT].unw_sec = s; else if (strcmp(".ARM.exidx.devexit.text", secname) == 0) maps[ARM_SEC_DEVEXIT].unw_sec = s; + else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0) + maps[ARM_SEC_UNLIKELY].unw_sec = s; + else if (strcmp(".ARM.exidx.text.hot", secname) == 0) + maps[ARM_SEC_HOT].unw_sec = s; else if (strcmp(".init.text", secname) == 0) maps[ARM_SEC_INIT].txt_sec = s; else if (strcmp(".devinit.text", secname) == 0) @@ -306,6 +321,10 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, maps[ARM_SEC_EXIT].txt_sec = s; else if (strcmp(".devexit.text", secname) == 0) maps[ARM_SEC_DEVEXIT].txt_sec = s; + else if (strcmp(".text.unlikely", secname) == 0) + maps[ARM_SEC_UNLIKELY].txt_sec = s; + else if (strcmp(".text.hot", secname) == 0) + maps[ARM_SEC_HOT].txt_sec = s; } for (i = 0; i < ARM_SEC_MAX; i++) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 8c3094d0f7b7..b41749fe56dc 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -12,6 +12,7 @@ */ #define pr_fmt(fmt) "hw perfevents: " fmt +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -53,7 +54,12 @@ armpmu_map_cache_event(const unsigned (*cache_map) static int armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*event_map)[config]; + int mapping; + + if (config >= PERF_COUNT_HW_MAX) + return -ENOENT; + + mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } @@ -81,6 +87,9 @@ armpmu_map_event(struct perf_event *event, return armpmu_map_cache_event(cache_map, config); case PERF_TYPE_RAW: return armpmu_map_raw_event(raw_event_mask, config); + default: + if (event->attr.type >= PERF_TYPE_MAX) + return armpmu_map_raw_event(raw_event_mask, config); } return -ENOENT; @@ -158,6 +167,8 @@ armpmu_stop(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to update the counter, so ignore * PERF_EF_UPDATE, see comments in armpmu_start(). @@ -174,6 +185,8 @@ static void armpmu_start(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to reprogram the period, so ignore * PERF_EF_RELOAD, see the comment below. @@ -201,6 +214,9 @@ armpmu_del(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; + armpmu_stop(event, PERF_EF_UPDATE); hw_events->events[idx] = NULL; clear_bit(idx, hw_events->used_mask); @@ -217,6 +233,10 @@ armpmu_add(struct perf_event *event, int flags) int idx; int err = 0; + /* An event following a process won't be stopped earlier */ + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return 0; + perf_pmu_disable(event->pmu); /* If we don't have a space for the counter then finish early. */ @@ -253,6 +273,9 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; + if (is_software_event(event)) + return 1; + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) return 1; @@ -295,11 +318,18 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev) struct arm_pmu *armpmu = (struct arm_pmu *) dev; struct platform_device *plat_device = armpmu->plat_device; struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev); + int ret; + u64 start_clock, finish_clock; + start_clock = sched_clock(); if (plat && plat->handle_irq) - return plat->handle_irq(irq, dev, armpmu->handle_irq); + ret = plat->handle_irq(irq, dev, armpmu->handle_irq); else - return armpmu->handle_irq(irq, dev); + ret = armpmu->handle_irq(irq, dev); + finish_clock = sched_clock(); + + perf_sample_event_took(finish_clock - start_clock); + return ret; } static void @@ -416,6 +446,10 @@ static int armpmu_event_init(struct perf_event *event) int err = 0; atomic_t *active_events = &armpmu->active_events; + if (event->cpu != -1 && + !cpumask_test_cpu(event->cpu, &armpmu->valid_cpus)) + return -ENOENT; + /* does not support taken branch sampling */ if (has_branch_stack(event)) return -EOPNOTSUPP; @@ -569,6 +603,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + perf_callchain_store(entry, regs->ARM_pc); tail = (struct frame_tail __user *)regs->ARM_fp - 1; while ((entry->nr < PERF_MAX_STACK_DEPTH) && diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 1f2740e3dbc0..e0665b871f5b 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) "CPU PMU: " fmt #include <linux/bitmap.h> +#include <linux/cpu_pm.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/of.h> @@ -31,33 +32,36 @@ #include <asm/pmu.h> /* Set at runtime when we know what CPU type we are. */ -static struct arm_pmu *cpu_pmu; +static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu); static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events); static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask); static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); +static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs); + /* * Despite the names, these two functions are CPU-specific and are used * by the OProfile/perf code. */ const char *perf_pmu_name(void) { - if (!cpu_pmu) + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); + if (!pmu) return NULL; - return cpu_pmu->name; + return pmu->name; } EXPORT_SYMBOL_GPL(perf_pmu_name); int perf_num_counters(void) { - int max_events = 0; + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); - if (cpu_pmu != NULL) - max_events = cpu_pmu->num_events; + if (!pmu) + return 0; - return max_events; + return pmu->num_events; } EXPORT_SYMBOL_GPL(perf_num_counters); @@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) { int i, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; irqs = min(pmu_device->num_resources, num_possible_cpus()); for (i = 0; i < irqs; ++i) { - if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs)) + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); + if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs)) continue; irq = platform_get_irq(pmu_device, i); if (irq >= 0) @@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) { int i, err, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; if (!pmu_device) return -ENODEV; @@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) for (i = 0; i < irqs; ++i) { err = 0; + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); irq = platform_get_irq(pmu_device, i); if (irq < 0) continue; @@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) * assume that we're running on a uniprocessor machine and * continue. Otherwise, continue without this interrupt. */ - if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) { + if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) { pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", irq, i); continue; @@ -126,7 +134,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return err; } - cpumask_set_cpu(i, &cpu_pmu->active_irqs); + cpumask_set_cpu(cpu, &cpu_pmu->active_irqs); } return 0; @@ -135,7 +143,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) static void cpu_pmu_init(struct arm_pmu *cpu_pmu) { int cpu; - for_each_possible_cpu(cpu) { + for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) { struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu); events->events = per_cpu(hw_events, cpu); events->used_mask = per_cpu(used_mask, cpu); @@ -148,7 +156,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) /* Ensure the PMU has sane values out of reset. */ if (cpu_pmu->reset) - on_each_cpu(cpu_pmu->reset, cpu_pmu, 1); + on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1); } /* @@ -160,21 +168,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) static int __cpuinit cpu_pmu_notify(struct notifier_block *b, unsigned long action, void *hcpu) { + struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu); + if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING) return NOTIFY_DONE; - if (cpu_pmu && cpu_pmu->reset) - cpu_pmu->reset(cpu_pmu); + if (pmu && pmu->reset) + pmu->reset(pmu); else return NOTIFY_DONE; return NOTIFY_OK; } +static int cpu_pmu_pm_notify(struct notifier_block *b, + unsigned long action, void *hcpu) +{ + int cpu = smp_processor_id(); + struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu); + struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu); + + if (!pmu) + return NOTIFY_DONE; + + if (action == CPU_PM_ENTER && pmu->save_regs) { + pmu->save_regs(pmu, pmuregs); + } else if (action == CPU_PM_EXIT && pmu->restore_regs) { + pmu->restore_regs(pmu, pmuregs); + } + + return NOTIFY_OK; +} + static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = { .notifier_call = cpu_pmu_notify, }; +static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = { + .notifier_call = cpu_pmu_pm_notify, +}; + /* * PMU platform driver and devicetree bindings. */ @@ -201,51 +234,44 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = { static int probe_current_pmu(struct arm_pmu *pmu) { int cpu = get_cpu(); - unsigned long implementor = read_cpuid_implementor(); - unsigned long part_number = read_cpuid_part_number(); int ret = -ENODEV; pr_info("probing PMU on CPU %d\n", cpu); + switch (read_cpuid_part()) { /* ARM Ltd CPUs. */ - if (implementor == ARM_CPU_IMP_ARM) { - switch (part_number) { - case ARM_CPU_PART_ARM1136: - case ARM_CPU_PART_ARM1156: - case ARM_CPU_PART_ARM1176: - ret = armv6pmu_init(pmu); - break; - case ARM_CPU_PART_ARM11MPCORE: - ret = armv6mpcore_pmu_init(pmu); - break; - case ARM_CPU_PART_CORTEX_A8: - ret = armv7_a8_pmu_init(pmu); - break; - case ARM_CPU_PART_CORTEX_A9: - ret = armv7_a9_pmu_init(pmu); - break; - case ARM_CPU_PART_CORTEX_A5: - ret = armv7_a5_pmu_init(pmu); - break; - case ARM_CPU_PART_CORTEX_A15: - ret = armv7_a15_pmu_init(pmu); - break; - case ARM_CPU_PART_CORTEX_A7: - ret = armv7_a7_pmu_init(pmu); - break; - } - /* Intel CPUs [xscale]. */ - } else if (implementor == ARM_CPU_IMP_INTEL) { - switch (xscale_cpu_arch_version()) { - case ARM_CPU_XSCALE_ARCH_V1: - ret = xscale1pmu_init(pmu); - break; - case ARM_CPU_XSCALE_ARCH_V2: - ret = xscale2pmu_init(pmu); - break; + case ARM_CPU_PART_ARM1136: + case ARM_CPU_PART_ARM1156: + case ARM_CPU_PART_ARM1176: + ret = armv6pmu_init(pmu); + break; + case ARM_CPU_PART_ARM11MPCORE: + ret = armv6mpcore_pmu_init(pmu); + break; + case ARM_CPU_PART_CORTEX_A8: + ret = armv7_a8_pmu_init(pmu); + break; + case ARM_CPU_PART_CORTEX_A9: + ret = armv7_a9_pmu_init(pmu); + break; + + default: + if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) { + switch (xscale_cpu_arch_version()) { + case ARM_CPU_XSCALE_ARCH_V1: + ret = xscale1pmu_init(pmu); + break; + case ARM_CPU_XSCALE_ARCH_V2: + ret = xscale2pmu_init(pmu); + break; + } } + break; } + /* assume PMU support all the CPUs in this case */ + cpumask_setall(&pmu->valid_cpus); + put_cpu(); return ret; } @@ -253,15 +279,10 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int cpu_pmu_device_probe(struct platform_device *pdev) { const struct of_device_id *of_id; - int (*init_fn)(struct arm_pmu *); struct device_node *node = pdev->dev.of_node; struct arm_pmu *pmu; - int ret = -ENODEV; - - if (cpu_pmu) { - pr_info("attempt to register multiple PMU devices!"); - return -ENOSPC; - } + int ret = 0; + int cpu; pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL); if (!pmu) { @@ -270,8 +291,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) } if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) { - init_fn = of_id->data; - ret = init_fn(pmu); + smp_call_func_t init_fn = (smp_call_func_t)of_id->data; + struct device_node *ncluster; + int cluster = -1; + cpumask_t sibling_mask; + + ncluster = of_parse_phandle(node, "cluster", 0); + if (ncluster) { + int len; + const u32 *hwid; + hwid = of_get_property(ncluster, "reg", &len); + if (hwid && len == 4) + cluster = be32_to_cpup(hwid); + } + /* set sibling mask to all cpu mask if socket is not specified */ + if (cluster == -1 || + cluster_to_logical_mask(cluster, &sibling_mask)) + cpumask_setall(&sibling_mask); + + smp_call_function_any(&sibling_mask, init_fn, pmu, 1); + + /* now set the valid_cpus after init */ + cpumask_copy(&pmu->valid_cpus, &sibling_mask); } else { ret = probe_current_pmu(pmu); } @@ -281,10 +322,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) goto out_free; } - cpu_pmu = pmu; - cpu_pmu->plat_device = pdev; - cpu_pmu_init(cpu_pmu); - ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW); + for_each_cpu_mask(cpu, pmu->valid_cpus) + per_cpu(cpu_pmu, cpu) = pmu; + + pmu->plat_device = pdev; + cpu_pmu_init(pmu); + ret = armpmu_register(pmu, -1); if (!ret) return 0; @@ -313,9 +356,17 @@ static int __init register_pmu_driver(void) if (err) return err; + err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier); + if (err) { + unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + return err; + } + err = platform_driver_register(&cpu_pmu_driver); - if (err) + if (err) { + cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier); unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + } return err; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 039cffb053a7..654db5030c31 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) } #endif +static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc)); + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset)); + asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren)); + asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset)); + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mrc p15, 0, %0, c9, c13, 1" + : "=r"(regs->pmxevttype[cnt])); + asm volatile("mrc p15, 0, %0, c9, c13, 2" + : "=r"(regs->pmxevtcnt[cnt])); + } + return; +} + +static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset)); + asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren)); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset)); + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mcr p15, 0, %0, c9, c13, 1" + : : "r"(regs->pmxevttype[cnt])); + asm volatile("mcr p15, 0, %0, c9, c13, 2" + : : "r"(regs->pmxevtcnt[cnt])); + } + asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc)); +} + static void armv7pmu_enable_event(struct perf_event *event) { unsigned long flags; @@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv7pmu_start; cpu_pmu->stop = armv7pmu_stop; cpu_pmu->reset = armv7pmu_reset; + cpu_pmu->save_regs = armv7pmu_save_regs; + cpu_pmu->restore_regs = armv7pmu_restore_regs; cpu_pmu->max_period = (1LLU << 32) - 1; }; @@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void) static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A8"; + cpu_pmu->name = "ARMv7_Cortex_A8"; cpu_pmu->map_event = armv7_a8_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A9"; + cpu_pmu->name = "ARMv7_Cortex_A9"; cpu_pmu->map_event = armv7_a9_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A5"; + cpu_pmu->name = "ARMv7_Cortex_A5"; cpu_pmu->map_event = armv7_a5_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A15"; + cpu_pmu->name = "ARMv7_Cortex_A15"; cpu_pmu->map_event = armv7_a15_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; @@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A7"; + cpu_pmu->name = "ARMv7_Cortex_A7"; cpu_pmu->map_event = armv7_a7_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 6e8931ccf13e..ac4c2e5e17e4 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -408,6 +408,7 @@ EXPORT_SYMBOL(dump_fpu); unsigned long get_wchan(struct task_struct *p) { struct stackframe frame; + unsigned long stack_page; int count = 0; if (!p || p == current || p->state == TASK_RUNNING) return 0; @@ -416,9 +417,11 @@ unsigned long get_wchan(struct task_struct *p) frame.sp = thread_saved_sp(p); frame.lr = 0; /* recovered from the stack */ frame.pc = thread_saved_pc(p); + stack_page = (unsigned long)task_stack_page(p); do { - int ret = unwind_frame(&frame); - if (ret < 0) + if (frame.sp < stack_page || + frame.sp >= stack_page + THREAD_SIZE || + unwind_frame(&frame) < 0) return 0; if (!in_sched_functions(frame.pc)) return frame.pc; @@ -433,10 +436,11 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } #ifdef CONFIG_MMU +#ifdef CONFIG_KUSER_HELPERS /* * The vectors page is always readable from user space for the - * atomic helpers and the signal restart code. Insert it into the - * gate_vma so that it is visible through ptrace and /proc/<pid>/mem. + * atomic helpers. Insert it into the gate_vma so that it is visible + * through ptrace and /proc/<pid>/mem. */ static struct vm_area_struct gate_vma = { .vm_start = 0xffff0000, @@ -465,9 +469,48 @@ int in_gate_area_no_mm(unsigned long addr) { return in_gate_area(NULL, addr); } +#define is_gate_vma(vma) ((vma) == &gate_vma) +#else +#define is_gate_vma(vma) 0 +#endif const char *arch_vma_name(struct vm_area_struct *vma) { - return (vma == &gate_vma) ? "[vectors]" : NULL; + return is_gate_vma(vma) ? "[vectors]" : + (vma->vm_mm && vma->vm_start == vma->vm_mm->context.sigpage) ? + "[sigpage]" : NULL; +} + +static struct page *signal_page; +extern struct page *get_signal_page(void); + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + struct mm_struct *mm = current->mm; + unsigned long addr; + int ret; + + if (!signal_page) + signal_page = get_signal_page(); + if (!signal_page) + return -ENOMEM; + + down_write(&mm->mmap_sem); + addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0); + if (IS_ERR_VALUE(addr)) { + ret = addr; + goto up_fail; + } + + ret = install_special_mapping(mm, addr, PAGE_SIZE, + VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + &signal_page); + + if (ret == 0) + mm->context.sigpage = addr; + + up_fail: + up_write(&mm->mmap_sem); + return ret; } #endif diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c index 36531643cc2c..0daf4f252284 100644 --- a/arch/arm/kernel/psci.c +++ b/arch/arm/kernel/psci.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/of.h> +#include <linux/string.h> #include <asm/compiler.h> #include <asm/errno.h> @@ -26,6 +27,11 @@ struct psci_operations psci_ops; +/* Type of psci support. Currently can only be enabled or disabled */ +#define PSCI_SUP_DISABLED 0 +#define PSCI_SUP_ENABLED 1 + +static unsigned int psci; static int (*invoke_psci_fn)(u32, u32, u32, u32); enum psci_function { @@ -42,6 +48,7 @@ static u32 psci_function_id[PSCI_FN_MAX]; #define PSCI_RET_EOPNOTSUPP -1 #define PSCI_RET_EINVAL -2 #define PSCI_RET_EPERM -3 +#define PSCI_RET_EALREADYON -4 static int psci_to_linux_errno(int errno) { @@ -54,6 +61,8 @@ static int psci_to_linux_errno(int errno) return -EINVAL; case PSCI_RET_EPERM: return -EPERM; + case PSCI_RET_EALREADYON: + return -EAGAIN; }; return -EINVAL; @@ -158,15 +167,18 @@ static const struct of_device_id psci_of_match[] __initconst = { {}, }; -static int __init psci_init(void) +void __init psci_init(void) { struct device_node *np; const char *method; u32 id; + if (psci == PSCI_SUP_DISABLED) + return; + np = of_find_matching_node(NULL, psci_of_match); if (!np) - return 0; + return; pr_info("probing function IDs from device-tree\n"); @@ -206,6 +218,35 @@ static int __init psci_init(void) out_put_node: of_node_put(np); - return 0; + return; +} + +int __init psci_probe(void) +{ + struct device_node *np; + int ret = -ENODEV; + + if (psci == PSCI_SUP_ENABLED) { + np = of_find_matching_node(NULL, psci_of_match); + if (np) + ret = 0; + } + + of_node_put(np); + return ret; +} + +static int __init early_psci(char *val) +{ + int ret = 0; + + if (strcmp(val, "enable") == 0) + psci = PSCI_SUP_ENABLED; + else if (strcmp(val, "disable") == 0) + psci = PSCI_SUP_DISABLED; + else + ret = -EINVAL; + + return ret; } -early_initcall(psci_init); +early_param("psci", early_psci); diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c new file mode 100644 index 000000000000..23a11424c568 --- /dev/null +++ b/arch/arm/kernel/psci_smp.c @@ -0,0 +1,84 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2012 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/init.h> +#include <linux/irqchip/arm-gic.h> +#include <linux/smp.h> +#include <linux/of.h> + +#include <asm/psci.h> +#include <asm/smp_plat.h> + +/* + * psci_smp assumes that the following is true about PSCI: + * + * cpu_suspend Suspend the execution on a CPU + * @state we don't currently describe affinity levels, so just pass 0. + * @entry_point the first instruction to be executed on return + * returns 0 success, < 0 on failure + * + * cpu_off Power down a CPU + * @state we don't currently describe affinity levels, so just pass 0. + * no return on successful call + * + * cpu_on Power up a CPU + * @cpuid cpuid of target CPU, as from MPIDR + * @entry_point the first instruction to be executed on return + * returns 0 success, < 0 on failure + * + * migrate Migrate the context to a different CPU + * @cpuid cpuid of target CPU, as from MPIDR + * returns 0 success, < 0 on failure + * + */ + +extern void secondary_startup(void); + +static int __cpuinit psci_boot_secondary(unsigned int cpu, + struct task_struct *idle) +{ + if (psci_ops.cpu_on) + return psci_ops.cpu_on(cpu_logical_map(cpu), + __pa(secondary_startup)); + return -ENODEV; +} + +#ifdef CONFIG_HOTPLUG_CPU +void __ref psci_cpu_die(unsigned int cpu) +{ + const struct psci_power_state ps = { + .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, + }; + + if (psci_ops.cpu_off) + psci_ops.cpu_off(ps); + + /* We should never return */ + panic("psci: cpu %d failed to shutdown\n", cpu); +} +#else +#define psci_cpu_die NULL +#endif + +bool __init psci_smp_available(void) +{ + /* is cpu_on available at least? */ + return (psci_ops.cpu_on != NULL); +} + +struct smp_operations __initdata psci_smp_ops = { + .smp_boot_secondary = psci_boot_secondary, + .cpu_die = psci_cpu_die, +}; diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index d0cdedf4864d..95858966d84e 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -2,10 +2,12 @@ * relocate_kernel.S - put the kernel image in place to boot */ +#include <linux/linkage.h> #include <asm/kexec.h> - .globl relocate_new_kernel -relocate_new_kernel: + .align 3 /* not needed for this code, but keeps fncpy() happy */ + +ENTRY(relocate_new_kernel) ldr r0,kexec_indirection_page ldr r1,kexec_start_address @@ -79,6 +81,8 @@ kexec_mach_type: kexec_boot_atags: .long 0x0 +ENDPROC(relocate_new_kernel) + relocate_new_kernel_end: .globl relocate_new_kernel_size diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index e8edcaa0e432..a57cc5d33540 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -51,10 +51,11 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) return (cyc * mult) >> shift; } -static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace sched_clock_32(void) { u64 epoch_ns; u32 epoch_cyc; + u32 cyc; if (cd.suspended) return cd.epoch_ns; @@ -73,7 +74,9 @@ static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) smp_rmb(); } while (epoch_cyc != cd.epoch_cyc_copy); - return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift); + cyc = read_sched_clock(); + cyc = (cyc - epoch_cyc) & sched_clock_mask; + return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift); } /* @@ -165,12 +168,6 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) pr_debug("Registered %pF as sched_clock source\n", read); } -static unsigned long long notrace sched_clock_32(void) -{ - u32 cyc = read_sched_clock(); - return cyc_to_sched_clock(cyc, sched_clock_mask); -} - unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32; unsigned long long notrace sched_clock(void) diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index b4b1d397592b..29beb8c76560 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -37,6 +37,7 @@ #include <asm/cputype.h> #include <asm/elf.h> #include <asm/procinfo.h> +#include <asm/psci.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp_plat.h> @@ -261,6 +262,19 @@ static int cpu_has_aliasing_icache(unsigned int arch) int aliasing_icache; unsigned int id_reg, num_sets, line_size; +#ifdef CONFIG_BIG_LITTLE + /* + * We expect a combination of Cortex-A15 and Cortex-A7 cores. + * A7 = VIPT aliasing I-cache + * A15 = PIPT (non-aliasing) I-cache + * To cater for this discrepancy, let's assume aliasing I-cache + * all the time. This means unneeded extra work on the A15 but + * only ptrace is affected which is not performance critical. + */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0) + return 1; +#endif + /* PIPT caches never alias. */ if (icache_is_pipt()) return 0; @@ -530,6 +544,7 @@ void __init dump_machine_table(void) int __init arm_add_memory(phys_addr_t start, phys_addr_t size) { struct membank *bank = &meminfo.bank[meminfo.nr_banks]; + u64 aligned_start; if (meminfo.nr_banks >= NR_BANKS) { printk(KERN_CRIT "NR_BANKS too low, " @@ -542,10 +557,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * Size is appropriately rounded down, start is rounded up. */ size -= start & ~PAGE_MASK; - bank->start = PAGE_ALIGN(start); + aligned_start = PAGE_ALIGN(start); + +#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT + if (aligned_start > ULONG_MAX) { + printk(KERN_CRIT "Ignoring memory at 0x%08llx outside " + "32-bit physical address space\n", (long long)start); + return -EINVAL; + } -#ifndef CONFIG_ARM_LPAE - if (bank->start + size < bank->start) { + if (aligned_start + size > ULONG_MAX) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); /* @@ -553,10 +574,25 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB. * This means we lose a page after masking. */ - size = ULONG_MAX - bank->start; + size = ULONG_MAX - aligned_start; } #endif + if (aligned_start < PHYS_OFFSET) { + if (aligned_start + size <= PHYS_OFFSET) { + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, aligned_start + size); + return -EINVAL; + } + + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, (u64)PHYS_OFFSET); + + size -= PHYS_OFFSET - aligned_start; + aligned_start = PHYS_OFFSET; + } + + bank->start = aligned_start; bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* @@ -796,9 +832,15 @@ void __init setup_arch(char **cmdline_p) unflatten_device_tree(); arm_dt_init_cpu_maps(); + psci_init(); #ifdef CONFIG_SMP if (is_smp()) { - smp_set_ops(mdesc->smp); + if (!mdesc->smp_init || !mdesc->smp_init()) { + if (psci_smp_available()) + smp_set_ops(&psci_smp_ops); + else if (mdesc->smp) + smp_set_ops(mdesc->smp); + } smp_init_cpus(); } #endif @@ -872,6 +914,9 @@ static const char *hwcap_str[] = { "vfpv4", "idiva", "idivt", + "vfpd32", + "lpae", + "evtstrm", NULL }; diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 296786bdbb73..3c23086dc8e2 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ #include <linux/errno.h> +#include <linux/random.h> #include <linux/signal.h> #include <linux/personality.h> #include <linux/uaccess.h> @@ -15,35 +16,14 @@ #include <asm/elf.h> #include <asm/cacheflush.h> +#include <asm/traps.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/vfp.h> -#include "signal.h" +extern const unsigned long sigreturn_codes[7]; -/* - * For ARM syscalls, we encode the syscall number into the instruction. - */ -#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) -#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) - -/* - * With EABI, the syscall number has to be loaded into r7. - */ -#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -/* - * For Thumb syscalls, we pass the syscall number via r7. We therefore - * need two 16-bit instructions. - */ -#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -const unsigned long sigreturn_codes[7] = { - MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN, - MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN, -}; +static unsigned long signal_return_offset; #ifdef CONFIG_CRUNCH static int preserve_crunch_context(struct crunch_sigframe __user *frame) @@ -396,13 +376,19 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig, __put_user(sigreturn_codes[idx+1], rc+1)) return 1; +#ifdef CONFIG_MMU if (cpsr & MODE32_BIT) { + struct mm_struct *mm = current->mm; /* - * 32-bit code can use the new high-page - * signal return code support. + * 32-bit code can use the signal return page + * except when the MPU has protected the vectors + * page from PL0 */ - retcode = KERN_SIGRETURN_CODE + (idx << 2) + thumb; - } else { + retcode = mm->context.sigpage + signal_return_offset + + (idx << 2) + thumb; + } else +#endif + { /* * Ensure that the instruction cache sees * the return code written onto the stack. @@ -603,3 +589,33 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } while (thread_flags & _TIF_WORK_MASK); return 0; } + +struct page *get_signal_page(void) +{ + unsigned long ptr; + unsigned offset; + struct page *page; + void *addr; + + page = alloc_pages(GFP_KERNEL, 0); + + if (!page) + return NULL; + + addr = page_address(page); + + /* Give the signal return code some randomness */ + offset = 0x200 + (get_random_int() & 0x7fc); + signal_return_offset = offset; + + /* + * Copy signal return handlers into the vector page, and + * set sigreturn to be a pointer to these. + */ + memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); + + ptr = (unsigned long)addr + offset; + flush_icache_range(ptr, ptr + sizeof(sigreturn_codes)); + + return page; +} diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h deleted file mode 100644 index 5ff067b7c752..000000000000 --- a/arch/arm/kernel/signal.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * linux/arch/arm/kernel/signal.h - * - * Copyright (C) 2005-2009 Russell King. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define KERN_SIGRETURN_CODE (CONFIG_VECTORS_BASE + 0x00000500) - -extern const unsigned long sigreturn_codes[7]; diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S new file mode 100644 index 000000000000..3c5d0f2170fd --- /dev/null +++ b/arch/arm/kernel/sigreturn_codes.S @@ -0,0 +1,80 @@ +/* + * sigreturn_codes.S - code sinpets for sigreturn syscalls + * + * Created by: Victor Kamensky, 2013-08-13 + * Copyright: (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <asm/unistd.h> + +/* + * For ARM syscalls, we encode the syscall number into the instruction. + * With EABI, the syscall number has to be loaded into r7. As result + * ARM syscall sequence snippet will have move and svc in .arm encoding + * + * For Thumb syscalls, we pass the syscall number via r7. We therefore + * need two 16-bit instructions in .thumb encoding + * + * Please note sigreturn_codes code are not executed in place. Instead + * they just copied by kernel into appropriate places. Code inside of + * arch/arm/kernel/signal.c is very sensitive to layout of these code + * snippets. + */ + +#if __LINUX_ARM_ARCH__ <= 4 + /* + * Note we manually set minimally required arch that supports + * required thumb opcodes for early arch versions. It is OK + * for this file to be used in combination with other + * lower arch variants, since these code snippets are only + * used as input data. + */ + .arch armv4t +#endif + + .section .rodata + .global sigreturn_codes + .type sigreturn_codes, #object + + .arm + +sigreturn_codes: + + /* ARM sigreturn syscall code snippet */ + mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn syscall code snippet */ + .thumb + movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn_rt syscall code snippet */ + .arm + mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn_rt syscall code snippet */ + .thumb + movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* + * Note on addtional space: setup_return in signal.c + * algorithm uses two words copy regardless whether + * it is thumb case or not, so we need additional + * word after real last entry. + */ + .arm + .space 4 + + .size sigreturn_codes, . - sigreturn_codes diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 987dcf33415c..baf4d28213a5 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -4,6 +4,7 @@ #include <asm/assembler.h> #include <asm/glue-cache.h> #include <asm/glue-proc.h> +#include "entry-header.S" .text /* @@ -30,9 +31,8 @@ ENTRY(__cpu_suspend) mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp #ifdef CONFIG_SMP - ALT_SMP(mrc p15, 0, lr, c0, c0, 5) - ALT_UP(mov lr, #0) - and lr, lr, #15 + get_thread_info r5 + ldr lr, [r5, #TI_CPU] @ cpu logical index add r3, r3, lr, lsl #2 #endif bl __cpu_suspend_save @@ -81,11 +81,15 @@ ENDPROC(cpu_resume_after_mmu) .data .align ENTRY(cpu_resume) +ARM_BE8(setend be) @ ensure we are in BE mode #ifdef CONFIG_SMP + mov r1, #0 @ fall-back logical index for UP + ALT_SMP(mrc p15, 0, r0, c0, c0, 5) + ALT_UP_B(1f) + bic r0, #0xff000000 + bl cpu_logical_index @ return logical index in r1 +1: adr r0, sleep_save_sp - ALT_SMP(mrc p15, 0, r1, c0, c0, 5) - ALT_UP(mov r1, #0) - and r1, r1, #15 ldr r0, [r0, r1, lsl #2] @ stack phys addr #else ldr r0, sleep_save_sp @ stack phys addr @@ -102,3 +106,20 @@ sleep_save_sp: .rept CONFIG_NR_CPUS .long 0 @ preserve stack phys ptr here .endr + +#ifdef CONFIG_SMP +cpu_logical_index: + adr r3, cpu_map_ptr + ldr r2, [r3] + add r3, r3, r2 @ virt_to_phys(__cpu_logical_map) + mov r1, #0 +1: + ldr r2, [r3, r1, lsl #2] + cmp r2, r0 + moveq pc, lr + add r1, r1, #1 + b 1b + +cpu_map_ptr: + .long __cpu_logical_map - . +#endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 5919eb451bb9..d6e3d1ca4ddf 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -46,6 +46,9 @@ #include <asm/virt.h> #include <asm/mach/arch.h> +#define CREATE_TRACE_POINTS +#include <trace/events/arm-ipi.h> + /* * as from 2.5, kernels no longer have an init_tasks structure * so we need some other way of telling a new secondary core @@ -57,7 +60,7 @@ struct secondary_data secondary_data; * control for which core is the next to come out of the secondary * boot "holding pen" */ -volatile int __cpuinitdata pen_release = -1; +volatile int pen_release = -1; enum ipi_msg_type { IPI_WAKEUP, @@ -66,6 +69,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_COMPLETION, }; static DECLARE_COMPLETION(cpu_running); @@ -87,8 +91,8 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle) * its stack and the page tables. */ secondary_data.stack = task_stack_page(idle) + THREAD_START_SP; - secondary_data.pgdir = virt_to_phys(idmap_pgd); - secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir); + secondary_data.pgdir = virt_to_idmap(idmap_pgd); + secondary_data.swapper_pg_dir = virt_to_idmap(swapper_pg_dir); __cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data)); outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1)); @@ -463,6 +467,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_COMPLETION, "completion interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -588,6 +593,19 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +static DEFINE_PER_CPU(struct completion *, cpu_completion); + +int register_ipi_completion(struct completion *completion, int cpu) +{ + per_cpu(cpu_completion, cpu) = completion; + return IPI_COMPLETION; +} + +static void ipi_complete(unsigned int cpu) +{ + complete(per_cpu(cpu_completion, cpu)); +} + /* * Main handler for inter-processor interrupts */ @@ -604,6 +622,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) if (ipinr < NR_IPI) __inc_irq_stat(cpu, ipi_irqs[ipinr]); + trace_arm_ipi_entry(ipinr); switch (ipinr) { case IPI_WAKEUP: break; @@ -638,11 +657,18 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_COMPLETION: + irq_enter(); + ipi_complete(cpu); + irq_exit(); + break; + default: printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; } + trace_arm_ipi_exit(ipinr); set_irq_regs(old_regs); } diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 5bc1a63284e3..1aafa0d785eb 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -28,7 +28,7 @@ */ unsigned int __init scu_get_core_count(void __iomem *scu_base) { - unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG); + unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG); return (ncores & 0x03) + 1; } @@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { - scu_ctrl = __raw_readl(scu_base + 0x30); + scu_ctrl = readl_relaxed(scu_base + 0x30); if (!(scu_ctrl & 1)) - __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30); } #endif - scu_ctrl = __raw_readl(scu_base + SCU_CTRL); + scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) return; scu_ctrl |= 1; - __raw_writel(scu_ctrl, scu_base + SCU_CTRL); + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); /* * Ensure that the data accessed by CPU0 before the SCU was @@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode) if (mode > 3 || mode == 1 || cpu > 3) return -EINVAL; - val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; val |= mode; - __raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu); + writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu); return 0; } diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 9a52a07aa40e..a98b62dca2fa 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -103,7 +103,7 @@ static void broadcast_tlb_a15_erratum(void) static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) { - int cpu, this_cpu; + int this_cpu; cpumask_t mask = { CPU_BITS_NONE }; if (!erratum_a15_798181()) @@ -111,21 +111,7 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) dummy_flush_tlb_a15_erratum(); this_cpu = get_cpu(); - for_each_online_cpu(cpu) { - if (cpu == this_cpu) - continue; - /* - * We only need to send an IPI if the other CPUs are running - * the same ASID as the one being invalidated. There is no - * need for locking around the active_asids check since the - * switch_mm() function has at least one dmb() (as required by - * this workaround) in case a context switch happens on - * another CPU after the condition below. - */ - if (atomic64_read(&mm->context.id) == - atomic64_read(&per_cpu(active_asids, cpu))) - cpumask_set_cpu(cpu, &mask); - } + a15_erratum_get_cpumask(this_cpu, mm, &mask); smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); put_cpu(); } diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 90525d9d290b..4971ccf012ca 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_PERIODIC: ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_PERIODIC; - __raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), + writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), twd_base + TWD_TIMER_LOAD); break; case CLOCK_EVT_MODE_ONESHOT: @@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode, ctrl = 0; } - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); } static int twd_set_next_event(unsigned long evt, struct clock_event_device *unused) { - unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL); + unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL); ctrl |= TWD_TIMER_CONTROL_ENABLE; - __raw_writel(evt, twd_base + TWD_TIMER_COUNTER); - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); return 0; } @@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt, */ static int twd_timer_ack(void) { - if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) { - __raw_writel(1, twd_base + TWD_TIMER_INTSTAT); + if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) { + writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT); return 1; } @@ -120,7 +120,7 @@ static int twd_rate_change(struct notifier_block *nb, * changing cpu. */ if (flags == POST_RATE_CHANGE) - smp_call_function(twd_update_frequency, + on_each_cpu(twd_update_frequency, (void *)&cnd->new_rate, 1); return NOTIFY_OK; @@ -209,15 +209,15 @@ static void __cpuinit twd_calibrate_rate(void) waitjiffies += 5; /* enable, no interrupt or reload */ - __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL); /* maximum value */ - __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); while (get_jiffies_64() < waitjiffies) udelay(10); - count = __raw_readl(twd_base + TWD_TIMER_COUNTER); + count = readl_relaxed(twd_base + TWD_TIMER_COUNTER); twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); @@ -275,7 +275,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk) * bother with the below. */ if (per_cpu(percpu_setup_called, cpu)) { - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clockevents_register_device(*__this_cpu_ptr(twd_evt)); enable_percpu_irq(clk->irq, 0); return 0; @@ -288,7 +288,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk) * The following is done once per CPU the first time .setup() is * called. */ - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clk->name = "local_timer"; clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT | diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index 00f79e59985b..6582c4adc182 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -31,7 +31,7 @@ int notrace unwind_frame(struct stackframe *frame) high = ALIGN(low, THREAD_SIZE); /* check current frame pointer is within bounds */ - if (fp < (low + 12) || fp + 4 >= high) + if (fp < low + 12 || fp > high - 4) return -EINVAL; /* restore the registers from the stack frame */ @@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d) return trace->nr_entries >= trace->max_entries; } -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +/* This must be noinline to so that our skip calculation works correctly */ +static noinline void __save_stack_trace(struct task_struct *tsk, + struct stack_trace *trace, unsigned int nosched) { struct stack_trace_data data; struct stackframe frame; data.trace = trace; data.skip = trace->skip; + data.no_sched_functions = nosched; if (tsk != current) { #ifdef CONFIG_SMP @@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; return; #else - data.no_sched_functions = 1; frame.fp = thread_saved_fp(tsk); frame.sp = thread_saved_sp(tsk); frame.lr = 0; /* recovered from the stack */ @@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) } else { register unsigned long current_sp asm ("sp"); - data.no_sched_functions = 0; + /* We don't want this function nor the caller */ + data.skip += 2; frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; frame.lr = (unsigned long)__builtin_return_address(0); - frame.pc = (unsigned long)save_stack_trace_tsk; + frame.pc = (unsigned long)__save_stack_trace; } walk_stackframe(&frame, save_trace, &data); @@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace, 1); +} + void save_stack_trace(struct stack_trace *trace) { - save_stack_trace_tsk(current, trace); + __save_stack_trace(current, trace, 0); } EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index c5a59546a256..677da58d9e88 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <asm/cputype.h> +#include <asm/smp_plat.h> #include <asm/topology.h> /* @@ -289,6 +290,140 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } + +#ifdef CONFIG_SCHED_HMP + +static const char * const little_cores[] = { + "arm,cortex-a7", + NULL, +}; + +static bool is_little_cpu(struct device_node *cn) +{ + const char * const *lc; + for (lc = little_cores; *lc; lc++) + if (of_device_is_compatible(cn, *lc)) + return true; + return false; +} + +void __init arch_get_fast_and_slow_cpus(struct cpumask *fast, + struct cpumask *slow) +{ + struct device_node *cn = NULL; + int cpu; + + cpumask_clear(fast); + cpumask_clear(slow); + + /* + * Use the config options if they are given. This helps testing + * HMP scheduling on systems without a big.LITTLE architecture. + */ + if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) { + if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast)) + WARN(1, "Failed to parse HMP fast cpu mask!\n"); + if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow)) + WARN(1, "Failed to parse HMP slow cpu mask!\n"); + return; + } + + /* + * Else, parse device tree for little cores. + */ + while ((cn = of_find_node_by_type(cn, "cpu"))) { + + const u32 *mpidr; + int len; + + mpidr = of_get_property(cn, "reg", &len); + if (!mpidr || len != 4) { + pr_err("* %s missing reg property\n", cn->full_name); + continue; + } + + cpu = get_logical_index(be32_to_cpup(mpidr)); + if (cpu == -EINVAL) { + pr_err("couldn't get logical index for mpidr %x\n", + be32_to_cpup(mpidr)); + break; + } + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + } + + if (!cpumask_empty(fast) && !cpumask_empty(slow)) + return; + + /* + * We didn't find both big and little cores so let's call all cores + * fast as this will keep the system running, with all cores being + * treated equal. + */ + cpumask_setall(fast); + cpumask_clear(slow); +} + +struct cpumask hmp_slow_cpu_mask; + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct hmp_domain *domain; + + arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask); + + /* + * Initialize hmp_domains + * Must be ordered with respect to compute capacity. + * Fastest domain at head of list. + */ + if(!cpumask_empty(&hmp_slow_cpu_mask)) { + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); +} +#endif /* CONFIG_SCHED_HMP */ + + +/* + * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster + * @socket_id: cluster HW identifier + * @cluster_mask: the cpumask location to be initialized, modified by the + * function only if return value == 0 + * + * Return: + * + * 0 on success + * -EINVAL if cluster_mask is NULL or there is no record matching socket_id + */ +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask) +{ + int cpu; + + if (!cluster_mask) + return -EINVAL; + + for_each_online_cpu(cpu) + if (socket_id == topology_physical_package_id(cpu)) { + cpumask_copy(cluster_mask, topology_core_cpumask(cpu)); + return 0; + } + + return -EINVAL; +} + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 18b32e8e4497..b4fd850c34b2 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -34,10 +34,15 @@ #include <asm/unwind.h> #include <asm/tls.h> #include <asm/system_misc.h> - -#include "signal.h" - -static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" }; +#include <asm/opcodes.h> + +static const char *handler[]= { + "prefetch abort", + "data abort", + "address exception", + "interrupt", + "undefined instruction", +}; void *vectors_page; @@ -343,15 +348,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs, int is_valid_bugaddr(unsigned long pc) { #ifdef CONFIG_THUMB2_KERNEL - unsigned short bkpt; + u16 bkpt; + u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE); #else - unsigned long bkpt; + u32 bkpt; + u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif if (probe_kernel_address((unsigned *)pc, bkpt)) return 0; - return bkpt == BUG_INSTR_VALUE; + return bkpt == insn; } #endif @@ -404,25 +411,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (processor_mode(regs) == SVC_MODE) { #ifdef CONFIG_THUMB2_KERNEL if (thumb_mode(regs)) { - instr = ((u16 *)pc)[0]; + instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]); if (is_wide_instruction(instr)) { - instr <<= 16; - instr |= ((u16 *)pc)[1]; + u16 inst2; + inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]); + instr = __opcode_thumb32_compose(instr, inst2); } } else #endif - instr = *(u32 *) pc; + instr = __mem_to_opcode_arm(*(u32 *) pc); } else if (thumb_mode(regs)) { if (get_user(instr, (u16 __user *)pc)) goto die_sig; + instr = __mem_to_opcode_thumb16(instr); if (is_wide_instruction(instr)) { unsigned int instr2; if (get_user(instr2, (u16 __user *)pc+1)) goto die_sig; - instr <<= 16; - instr |= instr2; + instr2 = __mem_to_opcode_thumb16(instr2); + instr = __opcode_thumb32_compose(instr, instr2); } } else if (get_user(instr, (u32 __user *)pc)) { + instr = __mem_to_opcode_arm(instr); goto die_sig; } @@ -800,47 +810,55 @@ void __init trap_init(void) return; } -static void __init kuser_get_tls_init(unsigned long vectors) +#ifdef CONFIG_KUSER_HELPERS +static void __init kuser_init(void *vectors) { + extern char __kuser_helper_start[], __kuser_helper_end[]; + int kuser_sz = __kuser_helper_end - __kuser_helper_start; + + memcpy(vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz); + /* * vectors + 0xfe0 = __kuser_get_tls * vectors + 0xfe8 = hardware TLS instruction at 0xffff0fe8 */ if (tls_emu || has_tls_reg) - memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4); + memcpy(vectors + 0xfe0, vectors + 0xfe8, 4); } +#else +static void __init kuser_init(void *vectors) +{ +} +#endif void __init early_trap_init(void *vectors_base) { unsigned long vectors = (unsigned long)vectors_base; extern char __stubs_start[], __stubs_end[]; extern char __vectors_start[], __vectors_end[]; - extern char __kuser_helper_start[], __kuser_helper_end[]; - int kuser_sz = __kuser_helper_end - __kuser_helper_start; + unsigned i; vectors_page = vectors_base; /* + * Poison the vectors page with an undefined instruction. This + * instruction is chosen to be undefined for both ARM and Thumb + * ISAs. The Thumb version is an undefined instruction with a + * branch back to the undefined instruction. + */ + for (i = 0; i < PAGE_SIZE / sizeof(u32); i++) + ((u32 *)vectors_base)[i] = 0xe7fddef1; + + /* * Copy the vectors, stubs and kuser helpers (in entry-armv.S) * into the vector page, mapped at 0xffff0000, and ensure these * are visible to the instruction stream. */ memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start); - memcpy((void *)vectors + 0x200, __stubs_start, __stubs_end - __stubs_start); - memcpy((void *)vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz); + memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start); - /* - * Do processor specific fixups for the kuser helpers - */ - kuser_get_tls_init(vectors); - - /* - * Copy signal return handlers into the vector page, and - * set sigreturn to be a pointer to these. - */ - memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE), - sigreturn_codes, sizeof(sigreturn_codes)); + kuser_init(vectors_base); - flush_icache_range(vectors, vectors + PAGE_SIZE); + flush_icache_range(vectors, vectors + PAGE_SIZE * 2); modify_domain(DOMAIN_USER, DOMAIN_CLIENT); } diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index a871b8e00fca..33f2ea32f5a0 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -152,6 +152,23 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_begin = .; #endif + /* + * The vectors and stubs are relocatable code, and the + * only thing that matters is their relative offsets + */ + __vectors_start = .; + .vectors 0 : AT(__vectors_start) { + *(.vectors) + } + . = __vectors_start + SIZEOF(.vectors); + __vectors_end = .; + + __stubs_start = .; + .stubs 0x1000 : AT(__stubs_start) { + *(.stubs) + } + . = __stubs_start + SIZEOF(.stubs); + __stubs_end = .; INIT_TEXT_SECTION(8) .exit.text : { |