diff options
Diffstat (limited to 'arch/arm/kernel')
46 files changed, 1136 insertions, 1453 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 040619c32d68..38ddd9f83d0e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o obj-$(CONFIG_SMP) += smp.o ifdef CONFIG_MMU obj-$(CONFIG_SMP) += smp_tlb.o diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 85598b5d1efd..713e807621d2 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -182,13 +182,13 @@ 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/atags_parse.c b/arch/arm/kernel/atags_parse.c index 8c14de8180c0..7807ef58a2ab 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/root_dev.h> #include <linux/screen_info.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/system_info.h> @@ -222,10 +223,10 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) } if (mdesc->fixup) - mdesc->fixup(tags, &from, &meminfo); + mdesc->fixup(tags, &from); if (tags->hdr.tag == ATAG_CORE) { - if (meminfo.nr_banks != 0) + if (memblock_phys_mem_size()) squash_mem_tags(tags); save_atags(tags); parse_tags(tags); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 16d43cd45619..17a26c17f7f5 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -545,6 +545,18 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw) */ pci_bus_add_devices(bus); } + + list_for_each_entry(sys, &head, node) { + struct pci_bus *bus = sys->bus; + + /* Configure PCI Express settings */ + if (bus && !pci_has_flag(PCI_PROBE_ONLY)) { + struct pci_bus *child; + + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); + } + } } #ifndef CONFIG_PCI_HOST_ITE8152 diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 8f51bdcdacbb..9f899d8fdcca 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -392,6 +392,9 @@ /* 380 */ CALL(sys_sched_setattr) CALL(sys_sched_getattr) CALL(sys_renameat2) + CALL(sys_seccomp) + CALL(sys_getrandom) +/* 385 */ CALL(sys_memfd_create) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index 14f7c3b14632..78c91b5f97d4 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -90,7 +90,7 @@ ENTRY(printascii) ldrneb r1, [r0], #1 teqne r1, #0 bne 1b - mov pc, lr + ret lr ENDPROC(printascii) ENTRY(printch) @@ -105,7 +105,7 @@ ENTRY(debug_ll_addr) addruart r2, r3, ip str r2, [r0] str r3, [r1] - mov pc, lr + ret lr ENDPROC(debug_ll_addr) #endif @@ -116,7 +116,7 @@ ENTRY(printascii) mov r0, #0x04 @ SYS_WRITE0 ARM( svc #0x123456 ) THUMB( svc #0xab ) - mov pc, lr + ret lr ENDPROC(printascii) ENTRY(printch) @@ -125,14 +125,14 @@ ENTRY(printch) mov r0, #0x03 @ SYS_WRITEC ARM( svc #0x123456 ) THUMB( svc #0xab ) - mov pc, lr + ret lr ENDPROC(printch) ENTRY(debug_ll_addr) mov r2, #0 str r2, [r0] str r2, [r1] - mov pc, lr + ret lr ENDPROC(debug_ll_addr) #endif diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index c7419a585ddc..11c54de9f8cf 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -27,56 +27,23 @@ #include <asm/mach/arch.h> #include <asm/mach-types.h> -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - arm_add_memory(base, size); -} - -void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) -{ - return memblock_virt_alloc(size, align); -} - -void __init arm_dt_memblock_reserve(void) -{ - u64 *reserve_map, base, size; - - if (!initial_boot_params) - return; - /* Reserve the dtb region */ - memblock_reserve(virt_to_phys(initial_boot_params), - be32_to_cpu(initial_boot_params->totalsize)); +#ifdef CONFIG_SMP +extern struct of_cpu_method __cpu_method_of_table[]; - /* - * Process the reserve map. This will probably overlap the initrd - * and dtb locations which are already reserved, but overlaping - * doesn't hurt anything - */ - reserve_map = ((void*)initial_boot_params) + - be32_to_cpu(initial_boot_params->off_mem_rsvmap); - while (1) { - base = be64_to_cpup(reserve_map++); - size = be64_to_cpup(reserve_map++); - if (!size) - break; - memblock_reserve(base, size); - } -} +static const struct of_cpu_method __cpu_method_of_table_sentinel + __used __section(__cpu_method_of_table_end); -#ifdef CONFIG_SMP -extern struct of_cpu_method __cpu_method_of_table_begin[]; -extern struct of_cpu_method __cpu_method_of_table_end[]; static int __init set_smp_ops_by_method(struct device_node *node) { const char *method; - struct of_cpu_method *m = __cpu_method_of_table_begin; + struct of_cpu_method *m = __cpu_method_of_table; if (of_property_read_string(node, "enable-method", &method)) return 0; - for (; m < __cpu_method_of_table_end; m++) + for (; m->method; m++) if (!strcmp(m->method, method)) { smp_set_ops(m->ops); return 1; @@ -245,14 +212,14 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) mdesc_best = &__mach_desc_GENERIC_DT; #endif - if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) + if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys))) return NULL; mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach); if (!mdesc) { const char *prop; - long size; + int size; unsigned long dt_root; early_print("\nError: unrecognized/unsupported " @@ -270,6 +237,12 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) dump_machine_table(); /* does not return */ } + /* We really don't want to do this, but sometimes firmware provides buggy data */ + if (mdesc->dt_fixup) + mdesc->dt_fixup(); + + early_init_dt_scan_nodes(); + /* Change machine number to match the mdesc we're using */ __machine_arch_type = mdesc->nr; diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 1879e8dd2acc..36276cdccfbc 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -224,7 +224,7 @@ svc_preempt: 1: bl preempt_schedule_irq @ irq en/disable is done inside ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS tst r0, #_TIF_NEED_RESCHED - moveq pc, r8 @ go again + reteq r8 @ go again b 1b #endif @@ -344,7 +344,7 @@ ENDPROC(__pabt_svc) @ @ Enable the alignment trap while in kernel mode @ - alignment_trap r0 + alignment_trap r0, .LCcralign @ @ Clear FP to mark the first stack frame @@ -413,6 +413,11 @@ __und_usr: @ adr r9, BSYM(ret_from_exception) + @ IRQs must be enabled before attempting to read the instruction from + @ user space since that could cause a page/translation fault if the + @ page table was modified by another CPU. + enable_irq + tst r3, #PSR_T_BIT @ Thumb mode? bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 @@ -484,7 +489,8 @@ ENDPROC(__und_usr) */ .pushsection .fixup, "ax" .align 2 -4: mov pc, r9 +4: str r4, [sp, #S_PC] @ retry current instruction + ret r9 .popsection .pushsection __ex_table,"a" .long 1b, 4b @@ -517,7 +523,7 @@ ENDPROC(__und_usr) * r9 = normal "successful" return address * r10 = this threads thread_info structure * lr = unrecognised instruction return address - * IRQs disabled, FIQs enabled. + * IRQs enabled, FIQs enabled. */ @ @ Fall-through from Thumb-2 __und_usr @@ -546,7 +552,7 @@ call_fpe: #endif tst r0, #0x08000000 @ only CDP/CPRT/LDC/STC have bit 27 tstne r0, #0x04000000 @ bit 26 set on both ARM and Thumb-2 - moveq pc, lr + reteq lr and r8, r0, #0x00000f00 @ mask out CP number THUMB( lsr r8, r8, #8 ) mov r7, #1 @@ -565,33 +571,33 @@ call_fpe: THUMB( add pc, r8 ) nop - movw_pc lr @ CP#0 + ret.w lr @ CP#0 W(b) do_fpe @ CP#1 (FPE) W(b) do_fpe @ CP#2 (FPE) - movw_pc lr @ CP#3 + ret.w lr @ CP#3 #ifdef CONFIG_CRUNCH b crunch_task_enable @ CP#4 (MaverickCrunch) b crunch_task_enable @ CP#5 (MaverickCrunch) b crunch_task_enable @ CP#6 (MaverickCrunch) #else - movw_pc lr @ CP#4 - movw_pc lr @ CP#5 - movw_pc lr @ CP#6 + ret.w lr @ CP#4 + ret.w lr @ CP#5 + ret.w lr @ CP#6 #endif - movw_pc lr @ CP#7 - movw_pc lr @ CP#8 - movw_pc lr @ CP#9 + ret.w lr @ CP#7 + ret.w lr @ CP#8 + ret.w lr @ CP#9 #ifdef CONFIG_VFP W(b) do_vfp @ CP#10 (VFP) W(b) do_vfp @ CP#11 (VFP) #else - movw_pc lr @ CP#10 (VFP) - movw_pc lr @ CP#11 (VFP) + ret.w lr @ CP#10 (VFP) + ret.w lr @ CP#11 (VFP) #endif - movw_pc lr @ CP#12 - movw_pc lr @ CP#13 - movw_pc lr @ CP#14 (Debug) - movw_pc lr @ CP#15 (Control) + ret.w lr @ CP#12 + ret.w lr @ CP#13 + ret.w lr @ CP#14 (Debug) + ret.w lr @ CP#15 (Control) #ifdef NEED_CPU_ARCHITECTURE .align 2 @@ -624,7 +630,6 @@ call_fpe: #endif do_fpe: - enable_irq ldr r4, .LCfp add r10, r10, #TI_FPSTATE @ r10 = workspace ldr pc, [r4] @ Call FP module USR entry point @@ -644,7 +649,7 @@ ENTRY(fp_enter) .popsection ENTRY(no_fp) - mov pc, lr + ret lr ENDPROC(no_fp) __und_usr_fault_32: @@ -652,8 +657,7 @@ __und_usr_fault_32: b 1f __und_usr_fault_16: mov r1, #2 -1: enable_irq - mov r0, sp +1: mov r0, sp adr lr, BSYM(ret_from_exception) b __und_fault ENDPROC(__und_usr_fault_32) @@ -741,7 +745,7 @@ ENDPROC(__switch_to) #ifdef CONFIG_ARM_THUMB bx \reg #else - mov pc, \reg + ret \reg #endif .endm @@ -833,7 +837,7 @@ kuser_cmpxchg64_fixup: #if __LINUX_ARM_ARCH__ < 6 bcc kuser_cmpxchg32_fixup #endif - mov pc, lr + ret lr .previous #else @@ -901,7 +905,7 @@ kuser_cmpxchg32_fixup: subs r8, r4, r7 rsbcss r8, r8, #(2b - 1b) strcs r7, [sp, #S_PC] - mov pc, lr + ret lr .previous #else @@ -1143,11 +1147,8 @@ __vectors_start: .data .globl cr_alignment - .globl cr_no_alignment cr_alignment: .space 4 -cr_no_alignment: - .space 4 #ifdef CONFIG_MULTI_IRQ_HANDLER .globl handle_arch_irq diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index a2dcafdf1bc8..e52fe5a2d843 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ +#include <asm/assembler.h> #include <asm/unistd.h> #include <asm/ftrace.h> #include <asm/unwind.h> @@ -88,7 +89,7 @@ ENTRY(ret_from_fork) cmp r5, #0 movne r0, r4 adrne lr, BSYM(1f) - movne pc, r5 + retne r5 1: get_thread_info tsk b ret_slow_syscall ENDPROC(ret_from_fork) @@ -290,7 +291,7 @@ ENDPROC(ftrace_graph_caller_old) .macro mcount_exit ldmia sp!, {r0-r3, ip, lr} - mov pc, ip + ret ip .endm ENTRY(__gnu_mcount_nc) @@ -298,7 +299,7 @@ UNWIND(.fnstart) #ifdef CONFIG_DYNAMIC_FTRACE mov ip, lr ldmia sp!, {lr} - mov pc, ip + ret ip #else __mcount #endif @@ -333,12 +334,12 @@ return_to_handler: bl ftrace_return_to_handler mov lr, r0 @ r0 has real ret addr ldmia sp!, {r0-r3} - mov pc, lr + ret lr #endif ENTRY(ftrace_stub) .Lftrace_stub: - mov pc, lr + ret lr ENDPROC(ftrace_stub) #endif /* CONFIG_FUNCTION_TRACER */ @@ -365,13 +366,7 @@ ENTRY(vector_swi) str r0, [sp, #S_OLD_R0] @ Save OLD_R0 #endif zero_fp - -#ifdef CONFIG_ALIGNMENT_TRAP - ldr ip, __cr_alignment - ldr ip, [ip] - mcr p15, 0, ip, c1, c0 @ update control register -#endif - + alignment_trap ip, __cr_alignment enable_irq ct_user_exit get_thread_info tsk @@ -567,7 +562,7 @@ sys_mmap2: streq r5, [sp, #4] beq sys_mmap_pgoff mov r0, #-EINVAL - mov pc, lr + ret lr #else str r5, [sp, #4] b sys_mmap_pgoff diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 1420725142ca..8db307d0954b 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -37,9 +37,9 @@ #endif .endm - .macro alignment_trap, rtemp + .macro alignment_trap, rtemp, label #ifdef CONFIG_ALIGNMENT_TRAP - ldr \rtemp, .LCcralign + ldr \rtemp, \label ldr \rtemp, [\rtemp] mcr p15, 0, \rtemp, c1, c0 #endif @@ -132,6 +132,10 @@ orrne r5, V7M_xPSR_FRAMEPTRALIGN biceq r5, V7M_xPSR_FRAMEPTRALIGN + @ ensure bit 0 is cleared in the PC, otherwise behaviour is + @ unpredictable + bic r4, #1 + @ write basic exception frame stmdb r2!, {r1, r3-r5} ldmia sp, {r1, r3-r5} @@ -236,12 +240,6 @@ movs pc, lr @ return & move spsr_svc into cpsr .endm - @ - @ 32-bit wide "mov pc, reg" - @ - .macro movw_pc, reg - mov pc, \reg - .endm #else /* CONFIG_THUMB2_KERNEL */ .macro svc_exit, rpsr, irq = 0 .if \irq != 0 @@ -300,14 +298,6 @@ movs pc, lr @ return & move spsr_svc into cpsr .endm #endif /* ifdef CONFIG_CPU_V7M / else */ - - @ - @ 32-bit wide "mov pc, reg" - @ - .macro movw_pc, reg - mov pc, \reg - nop - .endm #endif /* !CONFIG_THUMB2_KERNEL */ /* diff --git a/arch/arm/kernel/fiqasm.S b/arch/arm/kernel/fiqasm.S index 207f9d652010..8dd26e1a9bd6 100644 --- a/arch/arm/kernel/fiqasm.S +++ b/arch/arm/kernel/fiqasm.S @@ -32,7 +32,7 @@ ENTRY(__set_fiq_regs) ldr lr, [r0] msr cpsr_c, r1 @ return to SVC mode mov r0, r0 @ avoid hazard prior to ARMv4 - mov pc, lr + ret lr ENDPROC(__set_fiq_regs) ENTRY(__get_fiq_regs) @@ -45,5 +45,5 @@ ENTRY(__get_fiq_regs) str lr, [r0] msr cpsr_c, r1 @ return to SVC mode mov r0, r0 @ avoid hazard prior to ARMv4 - mov pc, lr + ret lr ENDPROC(__get_fiq_regs) diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index c108ddcb9ba4..af9a8a927a4e 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -14,6 +14,7 @@ #include <linux/ftrace.h> #include <linux/uaccess.h> +#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/opcodes.h> @@ -63,6 +64,18 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr) } #endif +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr) { return arm_gen_branch_link(pc, addr); diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index c96ecacb2021..8733012d231f 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -10,6 +10,7 @@ * published by the Free Software Foundation. * */ +#include <asm/assembler.h> #define ATAG_CORE 0x54410001 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2) @@ -61,10 +62,10 @@ __vet_atags: cmp r5, r6 bne 1f -2: mov pc, lr @ atag/dtb pointer is ok +2: ret lr @ atag/dtb pointer is ok 1: mov r2, #0 - mov pc, lr + ret lr ENDPROC(__vet_atags) /* @@ -99,8 +100,7 @@ __mmap_switched: str r1, [r5] @ Save machine type str r2, [r6] @ Save atags pointer cmp r7, #0 - bicne r4, r0, #CR_A @ Clear 'A' bit - stmneia r7, {r0, r4} @ Save control register values + strne r0, [r7] @ Save control register values b start_kernel ENDPROC(__mmap_switched) @@ -163,7 +163,7 @@ __lookup_processor_type: cmp r5, r6 blo 1b mov r5, #0 @ unknown processor -2: mov pc, lr +2: ret lr ENDPROC(__lookup_processor_type) /* diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 716249cc2ee1..cc176b67c134 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -82,7 +82,7 @@ ENTRY(stext) adr lr, BSYM(1f) @ return (PIC) address ARM( add pc, r10, #PROCINFO_INITFUNC ) THUMB( add r12, r10, #PROCINFO_INITFUNC ) - THUMB( mov pc, r12 ) + THUMB( ret r12 ) 1: b __after_proc_init ENDPROC(stext) @@ -119,7 +119,7 @@ ENTRY(secondary_startup) mov r13, r12 @ __secondary_switched address ARM( add pc, r10, #PROCINFO_INITFUNC ) THUMB( add r12, r10, #PROCINFO_INITFUNC ) - THUMB( mov pc, r12 ) + THUMB( ret r12 ) ENDPROC(secondary_startup) ENTRY(__secondary_switched) @@ -164,7 +164,7 @@ __after_proc_init: #endif mcr p15, 0, r0, c1, c0, 0 @ write control reg #endif /* CONFIG_CPU_CP15 */ - mov pc, r13 + ret r13 ENDPROC(__after_proc_init) .ltorg @@ -254,7 +254,7 @@ ENTRY(__setup_mpu) orr r0, r0, #CR_M @ Set SCTRL.M (MPU on) mcr p15, 0, r0, c1, c0, 0 @ Enable MPU isb - mov pc,lr + ret lr ENDPROC(__setup_mpu) #endif #include "head-common.S" diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 591d6e4a6492..664eee8c4a26 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -140,7 +140,7 @@ ENTRY(stext) mov r8, r4 @ set TTBR1 to swapper_pg_dir ARM( add pc, r10, #PROCINFO_INITFUNC ) THUMB( add r12, r10, #PROCINFO_INITFUNC ) - THUMB( mov pc, r12 ) + THUMB( ret r12 ) 1: b __enable_mmu ENDPROC(stext) .ltorg @@ -335,7 +335,7 @@ __create_page_tables: sub r4, r4, #0x1000 @ point to the PGD table mov r4, r4, lsr #ARCH_PGD_SHIFT #endif - mov pc, lr + ret lr ENDPROC(__create_page_tables) .ltorg .align @@ -383,7 +383,7 @@ ENTRY(secondary_startup) ARM( add pc, r10, #PROCINFO_INITFUNC ) @ initialise processor @ (return control reg) THUMB( add r12, r10, #PROCINFO_INITFUNC ) - THUMB( mov pc, r12 ) + THUMB( ret r12 ) ENDPROC(secondary_startup) /* @@ -468,14 +468,14 @@ ENTRY(__turn_mmu_on) instr_sync mov r3, r3 mov r3, r13 - mov pc, r3 + ret r3 __turn_mmu_on_end: ENDPROC(__turn_mmu_on) .popsection #ifdef CONFIG_SMP_ON_UP - __INIT + __HEAD __fixup_smp: and r3, r9, #0x000f0000 @ architecture version teq r3, #0x000f0000 @ CPU ID supported? @@ -487,7 +487,7 @@ __fixup_smp: orr r4, r4, #0x0000b000 orr r4, r4, #0x00000020 @ val 0x4100b020 teq r3, r4 @ ARM 11MPCore? - moveq pc, lr @ yes, assume SMP + reteq lr @ yes, assume SMP mrc p15, 0, r0, c0, c0, 5 @ read MPIDR and r0, r0, #0xc0000000 @ multiprocessing extensions and @@ -500,7 +500,7 @@ __fixup_smp: orr r4, r4, #0x0000c000 orr r4, r4, #0x00000090 teq r3, r4 @ Check for ARM Cortex-A9 - movne pc, lr @ Not ARM Cortex-A9, + retne lr @ Not ARM Cortex-A9, @ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the @ below address check will need to be #ifdef'd or equivalent @@ -512,7 +512,7 @@ __fixup_smp: ARM_BE8(rev r0, r0) @ byteswap if big endian and r0, r0, #0x3 @ number of CPUs teq r0, #0x0 @ is 1? - movne pc, lr + retne lr __fixup_smp_on_up: adr r0, 1f @@ -539,7 +539,7 @@ smp_on_up: .text __do_fixup_smp_on_up: cmp r4, r5 - movhs pc, lr + reths lr ldmia r4!, {r0, r6} ARM( str r6, [r0, r3] ) THUMB( add r0, r0, r3 ) @@ -672,7 +672,7 @@ ARM_BE8(rev16 ip, ip) 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot bcc 1b - mov pc, lr + ret lr #endif ENDPROC(__fixup_a_pv_table) diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c new file mode 100644 index 000000000000..bb8b79648643 --- /dev/null +++ b/arch/arm/kernel/hibernate.c @@ -0,0 +1,107 @@ +/* + * Hibernation support specific for ARM + * + * Derived from work on ARM hibernation support by: + * + * Ubuntu project, hibernation support for mach-dove + * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu) + * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.) + * https://lkml.org/lkml/2010/6/18/4 + * https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html + * https://patchwork.kernel.org/patch/96442/ + * + * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> + * + * License terms: GNU General Public License (GPL) version 2 + */ + +#include <linux/mm.h> +#include <linux/suspend.h> +#include <asm/system_misc.h> +#include <asm/idmap.h> +#include <asm/suspend.h> +#include <asm/memory.h> + +extern const void __nosave_begin, __nosave_end; + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); + + return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); +} + +void notrace save_processor_state(void) +{ + WARN_ON(num_online_cpus() != 1); + local_fiq_disable(); +} + +void notrace restore_processor_state(void) +{ + local_fiq_enable(); +} + +/* + * Snapshot kernel memory and reset the system. + * + * swsusp_save() is executed in the suspend finisher so that the CPU + * context pointer and memory are part of the saved image, which is + * required by the resume kernel image to restart execution from + * swsusp_arch_suspend(). + * + * soft_restart is not technically needed, but is used to get success + * returned from cpu_suspend. + * + * When soft reboot completes, the hibernation snapshot is written out. + */ +static int notrace arch_save_image(unsigned long unused) +{ + int ret; + + ret = swsusp_save(); + if (ret == 0) + soft_restart(virt_to_phys(cpu_resume)); + return ret; +} + +/* + * Save the current CPU state before suspend / poweroff. + */ +int notrace swsusp_arch_suspend(void) +{ + return cpu_suspend(0, arch_save_image); +} + +/* + * Restore page contents for physical pages that were in use during loading + * hibernation image. Switch to idmap_pgd so the physical page tables + * are overwritten with the same contents. + */ +static void notrace arch_restore_image(void *unused) +{ + struct pbe *pbe; + + cpu_switch_mm(idmap_pgd, &init_mm); + for (pbe = restore_pblist; pbe; pbe = pbe->next) + copy_page(pbe->orig_address, pbe->address); + + soft_restart(virt_to_phys(cpu_resume)); +} + +static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; + +/* + * Resume from the hibernation image. + * Due to the kernel heap / data restore, stack contents change underneath + * and that would make function calls impossible; switch to a temporary + * stack within the nosave region to avoid that problem. + */ +int swsusp_arch_resume(void) +{ + extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); + call_with_stack(arch_restore_image, 0, + resume_stack + ARRAY_SIZE(resume_stack)); + return 0; +} diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 797b1a6a4906..2a55373f49bf 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -99,7 +99,7 @@ ENTRY(__hyp_stub_install_secondary) * immediately. */ compare_cpu_mode_with_primary r4, r5, r6, r7 - movne pc, lr + retne lr /* * Once we have given up on one CPU, we do not try to install the @@ -111,7 +111,7 @@ ENTRY(__hyp_stub_install_secondary) */ cmp r4, #HYP_MODE - movne pc, lr @ give up if the CPU is not in HYP mode + retne lr @ give up if the CPU is not in HYP mode /* * Configure HSCTLR to set correct exception endianness/instruction set @@ -134,9 +134,7 @@ ENTRY(__hyp_stub_install_secondary) mcr p15, 4, r7, c1, c1, 3 @ HSTR THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE -#ifdef CONFIG_CPU_BIG_ENDIAN - orr r7, #(1 << 9) @ HSCTLR.EE -#endif +ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE mcr p15, 4, r7, c1, c0, 0 @ HSCTLR mrc p15, 4, r7, c1, c1, 1 @ HDCR @@ -201,7 +199,7 @@ ENDPROC(__hyp_get_vectors) @ fall through ENTRY(__hyp_set_vectors) __HVC(0) - mov pc, lr + ret lr ENDPROC(__hyp_set_vectors) #ifndef ZIMAGE diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17b8f38..2c4257604513 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -37,6 +37,7 @@ #include <linux/proc_fs.h> #include <linux/export.h> +#include <asm/hardware/cache-l2x0.h> #include <asm/exception.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> @@ -115,10 +116,21 @@ EXPORT_SYMBOL_GPL(set_irq_flags); void __init init_IRQ(void) { + int ret; + if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq) irqchip_init(); else machine_desc->init_irq(); + + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) && + (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) { + outer_cache.write_sec = machine_desc->l2c_write_sec; + ret = l2x0_of_init(machine_desc->l2c_aux_val, + machine_desc->l2c_aux_mask); + if (ret) + pr_err("L2C: failed to init: %d\n", ret); + } } #ifdef CONFIG_MULTI_IRQ_HANDLER diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 346485910732..9d1cf7156895 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -20,7 +20,7 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; -static ctl_table ctl_isa_vars[4] = { +static struct ctl_table ctl_isa_vars[4] = { { .procname = "membase", .data = &isa_membase, @@ -44,7 +44,7 @@ static ctl_table ctl_isa_vars[4] = { static struct ctl_table_header *isa_sysctl_header; -static ctl_table ctl_isa[2] = { +static struct ctl_table ctl_isa[2] = { { .procname = "isa", .mode = 0555, @@ -52,7 +52,7 @@ static ctl_table ctl_isa[2] = { }, {} }; -static ctl_table ctl_bus[2] = { +static struct ctl_table ctl_bus[2] = { { .procname = "bus", .mode = 0555, diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index 2452dd1bef53..ad58e565fe98 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -18,6 +18,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/assembler.h> #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) #define PJ4(code...) code @@ -65,17 +66,18 @@ * r9 = ret_from_exception * lr = undefined instr exit * - * called from prefetch exception handler with interrupts disabled + * called from prefetch exception handler with interrupts enabled */ ENTRY(iwmmxt_task_enable) + inc_preempt_count r10, r3 XSC(mrc p15, 0, r2, c15, c1, 0) PJ4(mrc p15, 0, r2, c1, c0, 2) @ CP0 and CP1 accessible? XSC(tst r2, #0x3) PJ4(tst r2, #0xf) - movne pc, lr @ if so no business here + bne 4f @ if so no business here @ enable access to CP0 and CP1 XSC(orr r2, r2, #0x3) XSC(mcr p15, 0, r2, c15, c1, 0) @@ -92,13 +94,19 @@ ENTRY(iwmmxt_task_enable) mrc p15, 0, r2, c2, c0, 0 mov r2, r2 @ cpwait + bl concan_save - teq r1, #0 @ test for last ownership - mov lr, r9 @ normal exit from exception - beq concan_load @ no owner, skip save +#ifdef CONFIG_PREEMPT_COUNT + get_thread_info r10 +#endif +4: dec_preempt_count r10, r3 + ret r9 @ normal exit from exception concan_save: + teq r1, #0 @ test for last ownership + beq concan_load @ no owner, skip save + tmrc r2, wCon @ CUP? wCx @@ -136,7 +144,7 @@ concan_dump: wstrd wR15, [r1, #MMX_WR15] 2: teq r0, #0 @ anything to load? - moveq pc, lr + reteq lr @ if not, return concan_load: @@ -169,9 +177,10 @@ concan_load: @ clear CUP/MUP (only if r1 != 0) teq r1, #0 mov r2, #0 - moveq pc, lr + reteq lr + tmcr wCon, r2 - mov pc, lr + ret lr /* * Back up Concan regs to save area and disable access to them @@ -257,7 +266,7 @@ ENTRY(iwmmxt_task_copy) mov r3, lr @ preserve return address bl concan_dump msr cpsr_c, ip @ restore interrupt mode - mov pc, r3 + ret r3 /* * Restore Concan state from given memory address @@ -293,7 +302,7 @@ ENTRY(iwmmxt_task_restore) mov r3, lr @ preserve return address bl concan_load msr cpsr_c, ip @ restore interrupt mode - mov pc, r3 + ret r3 /* * Concan handling on task switch @@ -315,7 +324,7 @@ ENTRY(iwmmxt_task_switch) add r3, r0, #TI_IWMMXT_STATE @ get next task Concan save area ldr r2, [r2] @ get current Concan owner teq r2, r3 @ next task owns it? - movne pc, lr @ no: leave Concan disabled + retne lr @ no: leave Concan disabled 1: @ flip Concan access XSC(eor r1, r1, #0x3) @@ -342,7 +351,7 @@ ENTRY(iwmmxt_task_release) eors r0, r0, r1 @ if equal... streq r0, [r3] @ then clear ownership msr cpsr_c, r2 @ restore interrupts - mov pc, lr + ret lr .data concan_owner: diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 778c2f7024ff..a74b53c1b7df 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -160,12 +160,16 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr) static struct undef_hook kgdb_brkpt_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_BREAKINST, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, .fn = kgdb_brk_fn }; static struct undef_hook kgdb_compiled_brkpt_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_COMPILED_BREAK, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, .fn = kgdb_compiled_brk_fn }; diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c index 9db4b659d03e..cb1424240ff6 100644 --- a/arch/arm/kernel/kprobes-test-arm.c +++ b/arch/arm/kernel/kprobes-test-arm.c @@ -74,8 +74,6 @@ void kprobe_arm_test_cases(void) TEST_RRR( op "lt" s " r11, r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")\ TEST_RR( op "gt" s " r12, r13" ", r",14,val, ", ror r",14,7,"")\ TEST_RR( op "le" s " r14, r",0, val, ", r13" ", lsl r",14,8,"")\ - TEST_RR( op s " r12, pc" ", r",14,val, ", ror r",14,7,"")\ - TEST_RR( op s " r14, r",0, val, ", pc" ", lsl r",14,8,"")\ TEST_R( op "eq" s " r0, r",11,VAL1,", #0xf5") \ TEST_R( op "ne" s " r11, r",0, VAL1,", #0xf5000000") \ TEST_R( op s " r7, r",8, VAL2,", #0x000af000") \ @@ -103,8 +101,6 @@ void kprobe_arm_test_cases(void) TEST_RRR( op "ge r",11,VAL1,", r",14,N(val),", asr r",7, 6,"") \ TEST_RR( op "le r13" ", r",14,val, ", ror r",14,7,"") \ TEST_RR( op "gt r",0, val, ", r13" ", lsl r",14,8,"") \ - TEST_RR( op " pc" ", r",14,val, ", ror r",14,7,"") \ - TEST_RR( op " r",0, val, ", pc" ", lsl r",14,8,"") \ TEST_R( op "eq r",11,VAL1,", #0xf5") \ TEST_R( op "ne r",0, VAL1,", #0xf5000000") \ TEST_R( op " r",8, VAL2,", #0x000af000") @@ -125,7 +121,6 @@ void kprobe_arm_test_cases(void) TEST_RR( op "ge" s " r11, r",11,N(val),", asr r",7, 6,"") \ TEST_RR( op "lt" s " r12, r",11,val, ", ror r",14,7,"") \ TEST_R( op "gt" s " r14, r13" ", lsl r",14,8,"") \ - TEST_R( op "le" s " r14, pc" ", lsl r",14,8,"") \ TEST( op "eq" s " r0, #0xf5") \ TEST( op "ne" s " r11, #0xf5000000") \ TEST( op s " r7, #0x000af000") \ @@ -159,12 +154,19 @@ void kprobe_arm_test_cases(void) TEST_SUPPORTED("cmp pc, #0x1000"); TEST_SUPPORTED("cmp sp, #0x1000"); - /* Data-processing with PC as shift*/ + /* Data-processing with PC and a shift count in a register */ TEST_UNSUPPORTED(__inst_arm(0xe15c0f1e) " @ cmp r12, r14, asl pc") TEST_UNSUPPORTED(__inst_arm(0xe1a0cf1e) " @ mov r12, r14, asl pc") TEST_UNSUPPORTED(__inst_arm(0xe08caf1e) " @ add r10, r12, r14, asl pc") - - /* Data-processing with PC as shift*/ + TEST_UNSUPPORTED(__inst_arm(0xe151021f) " @ cmp r1, pc, lsl r2") + TEST_UNSUPPORTED(__inst_arm(0xe17f0211) " @ cmn pc, r1, lsl r2") + TEST_UNSUPPORTED(__inst_arm(0xe1a0121f) " @ mov r1, pc, lsl r2") + TEST_UNSUPPORTED(__inst_arm(0xe1a0f211) " @ mov pc, r1, lsl r2") + TEST_UNSUPPORTED(__inst_arm(0xe042131f) " @ sub r1, r2, pc, lsl r3") + TEST_UNSUPPORTED(__inst_arm(0xe1cf1312) " @ bic r1, pc, r2, lsl r3") + TEST_UNSUPPORTED(__inst_arm(0xe081f312) " @ add pc, r1, r2, lsl r3") + + /* Data-processing with PC as a target and status registers updated */ TEST_UNSUPPORTED("movs pc, r1") TEST_UNSUPPORTED("movs pc, r1, lsl r2") TEST_UNSUPPORTED("movs pc, #0x10000") @@ -187,14 +189,14 @@ void kprobe_arm_test_cases(void) TEST_BF_R ("add pc, pc, r",14,2f-1f-8,"") TEST_BF_R ("add pc, r",14,2f-1f-8,", pc") TEST_BF_R ("mov pc, r",0,2f,"") - TEST_BF_RR("mov pc, r",0,2f,", asl r",1,0,"") + TEST_BF_R ("add pc, pc, r",14,(2f-1f-8)*2,", asr #1") TEST_BB( "sub pc, pc, #1b-2b+8") #if __LINUX_ARM_ARCH__ == 6 && !defined(CONFIG_CPU_V7) TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before and after ARMv6 */ #endif TEST_BB_R( "sub pc, pc, r",14, 1f-2f+8,"") TEST_BB_R( "rsb pc, r",14,1f-2f+8,", pc") - TEST_RR( "add pc, pc, r",10,-2,", asl r",11,1,"") + TEST_R( "add pc, pc, r",10,-2,", asl #1") #ifdef CONFIG_THUMB2_KERNEL TEST_ARM_TO_THUMB_INTERWORK_R("add pc, pc, r",0,3f-1f-8+1,"") TEST_ARM_TO_THUMB_INTERWORK_R("sub pc, r",0,3f+8+1,", #8") @@ -216,6 +218,7 @@ void kprobe_arm_test_cases(void) TEST_BB_R("bx r",7,2f,"") TEST_BF_R("bxeq r",14,2f,"") +#if __LINUX_ARM_ARCH__ >= 5 TEST_R("clz r0, r",0, 0x0,"") TEST_R("clzeq r7, r",14,0x1,"") TEST_R("clz lr, r",7, 0xffffffff,"") @@ -337,6 +340,7 @@ void kprobe_arm_test_cases(void) TEST_UNSUPPORTED(__inst_arm(0xe16f02e1) " @ smultt pc, r1, r2") TEST_UNSUPPORTED(__inst_arm(0xe16002ef) " @ smultt r0, pc, r2") TEST_UNSUPPORTED(__inst_arm(0xe1600fe1) " @ smultt r0, r1, pc") +#endif TEST_GROUP("Multiply and multiply-accumulate") @@ -559,6 +563,7 @@ void kprobe_arm_test_cases(void) TEST_UNSUPPORTED("ldrsht r1, [r2], #48") #endif +#if __LINUX_ARM_ARCH__ >= 5 TEST_RPR( "strd r",0, VAL1,", [r",1, 48,", -r",2,24,"]") TEST_RPR( "strccd r",8, VAL2,", [r",13,0, ", r",12,48,"]") TEST_RPR( "strd r",4, VAL1,", [r",2, 24,", r",3, 48,"]!") @@ -595,6 +600,7 @@ void kprobe_arm_test_cases(void) TEST_UNSUPPORTED(__inst_arm(0xe1efc3d0) " @ ldrd r12, [pc, #48]!") TEST_UNSUPPORTED(__inst_arm(0xe0c9f3d0) " @ ldrd pc, [r9], #48") TEST_UNSUPPORTED(__inst_arm(0xe0c9e3d0) " @ ldrd lr, [r9], #48") +#endif TEST_GROUP("Miscellaneous") @@ -1227,7 +1233,9 @@ void kprobe_arm_test_cases(void) TEST_COPROCESSOR( "mrc"two" 0, 0, r0, cr0, cr0, 0") COPROCESSOR_INSTRUCTIONS_ST_LD("",e) +#if __LINUX_ARM_ARCH__ >= 5 COPROCESSOR_INSTRUCTIONS_MC_MR("",e) +#endif TEST_UNSUPPORTED("svc 0") TEST_UNSUPPORTED("svc 0xffffff") @@ -1287,7 +1295,9 @@ void kprobe_arm_test_cases(void) TEST( "blx __dummy_thumb_subroutine_odd") #endif /* __LINUX_ARM_ARCH__ >= 6 */ +#if __LINUX_ARM_ARCH__ >= 5 COPROCESSOR_INSTRUCTIONS_ST_LD("2",f) +#endif #if __LINUX_ARM_ARCH__ >= 6 COPROCESSOR_INSTRUCTIONS_MC_MR("2",f) #endif diff --git a/arch/arm/kernel/kprobes-test.c b/arch/arm/kernel/kprobes-test.c index 379639998d5a..08d731294bcd 100644 --- a/arch/arm/kernel/kprobes-test.c +++ b/arch/arm/kernel/kprobes-test.c @@ -225,6 +225,7 @@ static int pre_handler_called; static int post_handler_called; static int jprobe_func_called; static int kretprobe_handler_called; +static int tests_failed; #define FUNC_ARG1 0x12345678 #define FUNC_ARG2 0xabcdef @@ -461,6 +462,13 @@ static int run_api_tests(long (*func)(long, long)) pr_info(" jprobe\n"); ret = test_jprobe(func); +#if defined(CONFIG_THUMB2_KERNEL) && !defined(MODULE) + if (ret == -EINVAL) { + pr_err("FAIL: Known longtime bug with jprobe on Thumb kernels\n"); + tests_failed = ret; + ret = 0; + } +#endif if (ret < 0) return ret; @@ -1672,6 +1680,8 @@ static int __init run_all_tests(void) out: if (ret == 0) + ret = tests_failed; + if (ret == 0) pr_info("Finished kprobe tests OK\n"); else pr_err("kprobe tests failed\n"); diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index a6bc431cde70..266cba46db3e 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -410,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event) */ hwc->config_base |= (unsigned long)mapping; - if (!hwc->sample_period) { + if (!is_sampling_event(event)) { /* * For non-sampling runs, limit the sample_period to half * of the counter width. That way, the new counter value @@ -560,11 +560,16 @@ user_backtrace(struct frame_tail __user *tail, struct perf_callchain_entry *entry) { struct frame_tail buftail; + unsigned long err; - /* Also check accessibility of one struct frame_tail beyond */ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) return NULL; - if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail))) + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) return NULL; perf_callchain_store(entry, buftail.lr); @@ -590,6 +595,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) } perf_callchain_store(entry, regs->ARM_pc); + + if (!current->mm) + return; + tail = (struct frame_tail __user *)regs->ARM_fp - 1; while ((entry->nr < PERF_MAX_STACK_DEPTH) && @@ -621,10 +630,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } - fr.fp = regs->ARM_fp; - fr.sp = regs->ARM_sp; - fr.lr = regs->ARM_lr; - fr.pc = regs->ARM_pc; + arm_get_current_stackframe(regs, &fr); walk_stackframe(&fr, callchain_trace, entry); } diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 51798d7854ac..e6a6edbec613 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -126,8 +126,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) irqs = min(pmu_device->num_resources, num_possible_cpus()); if (irqs < 1) { - pr_err("no irqs for PMUs defined\n"); - return -ENODEV; + printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n"); + return 0; } irq = platform_get_irq(pmu_device, 0); @@ -191,6 +191,10 @@ 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); + + /* If no interrupts available, set the corresponding capability flag */ + if (!platform_get_irq(cpu_pmu->plat_device, 0)) + cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } /* @@ -221,6 +225,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = { * PMU platform driver and devicetree bindings. */ static struct of_device_id cpu_pmu_of_device_ids[] = { + {.compatible = "arm,cortex-a17-pmu", .data = armv7_a17_pmu_init}, {.compatible = "arm,cortex-a15-pmu", .data = armv7_a15_pmu_init}, {.compatible = "arm,cortex-a12-pmu", .data = armv7_a12_pmu_init}, {.compatible = "arm,cortex-a9-pmu", .data = armv7_a9_pmu_init}, @@ -228,14 +233,17 @@ static struct of_device_id cpu_pmu_of_device_ids[] = { {.compatible = "arm,cortex-a7-pmu", .data = armv7_a7_pmu_init}, {.compatible = "arm,cortex-a5-pmu", .data = armv7_a5_pmu_init}, {.compatible = "arm,arm11mpcore-pmu", .data = armv6mpcore_pmu_init}, - {.compatible = "arm,arm1176-pmu", .data = armv6pmu_init}, - {.compatible = "arm,arm1136-pmu", .data = armv6pmu_init}, + {.compatible = "arm,arm1176-pmu", .data = armv6_1176_pmu_init}, + {.compatible = "arm,arm1136-pmu", .data = armv6_1136_pmu_init}, {.compatible = "qcom,krait-pmu", .data = krait_pmu_init}, {}, }; static struct platform_device_id cpu_pmu_plat_device_ids[] = { {.name = "arm-pmu"}, + {.name = "armv6-pmu"}, + {.name = "armv7-pmu"}, + {.name = "xscale-pmu"}, {}, }; @@ -245,40 +253,43 @@ 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; - } - /* 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: + ret = armv6_1136_pmu_init(pmu); + break; + case ARM_CPU_PART_ARM1156: + ret = armv6_1156_pmu_init(pmu); + break; + case ARM_CPU_PART_ARM1176: + ret = armv6_1176_pmu_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; } put_cpu(); diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index 03664b0e8fa4..abfeb04f3213 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -65,13 +65,11 @@ enum armv6_counters { * accesses/misses in hardware. */ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC, - [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6_PERFCTR_IBUF_STALL, [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6_PERFCTR_LSU_FULL_STALL, }; @@ -79,116 +77,31 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = { static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - /* - * The performance counters don't differentiate between read - * and write accesses/misses so this isn't strictly correct, - * but it's the best we can do. Writes and reads get - * combined. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - /* - * The ARM performance counters can count micro DTLB misses, - * micro ITLB misses and main TLB misses. There isn't an event - * for TLB misses, so use the micro misses here and if users - * want the main TLB misses they can use a raw counter. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS, + + /* + * The ARM performance counters can count micro DTLB misses, micro ITLB + * misses and main TLB misses. There isn't an event for TLB misses, so + * use the micro misses here and if users want the main TLB misses they + * can use a raw counter. + */ + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, }; enum armv6mpcore_perf_types { @@ -220,13 +133,11 @@ enum armv6mpcore_perf_types { * accesses/misses in hardware. */ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC, - [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6MPCORE_PERFCTR_IBUF_STALL, [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6MPCORE_PERFCTR_LSU_FULL_STALL, }; @@ -234,114 +145,26 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = { static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = - ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS, - [C(RESULT_MISS)] = - ARMV6MPCORE_PERFCTR_DCACHE_RDMISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = - ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS, - [C(RESULT_MISS)] = - ARMV6MPCORE_PERFCTR_DCACHE_WRMISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - /* - * The ARM performance counters can count micro DTLB misses, - * micro ITLB misses and main TLB misses. There isn't an event - * for TLB misses, so use the micro misses here and if users - * want the main TLB misses they can use a raw counter. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDMISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRMISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS, + + /* + * The ARM performance counters can count micro DTLB misses, micro ITLB + * misses and main TLB misses. There isn't an event for TLB misses, so + * use the micro misses here and if users want the main TLB misses they + * can use a raw counter. + */ + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, }; static inline unsigned long @@ -653,9 +476,8 @@ static int armv6_map_event(struct perf_event *event) &armv6_perf_cache_map, 0xFF); } -static int armv6pmu_init(struct arm_pmu *cpu_pmu) +static void armv6pmu_init(struct arm_pmu *cpu_pmu) { - cpu_pmu->name = "v6"; cpu_pmu->handle_irq = armv6pmu_handle_irq; cpu_pmu->enable = armv6pmu_enable_event; cpu_pmu->disable = armv6pmu_disable_event; @@ -667,7 +489,26 @@ static int armv6pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->map_event = armv6_map_event; cpu_pmu->num_events = 3; cpu_pmu->max_period = (1LLU << 32) - 1; +} + +static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1136"; + return 0; +} +static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1156"; + return 0; +} + +static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1176"; return 0; } @@ -687,7 +528,7 @@ static int armv6mpcore_map_event(struct perf_event *event) static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu) { - cpu_pmu->name = "v6mpcore"; + cpu_pmu->name = "armv6_11mpcore"; cpu_pmu->handle_irq = armv6pmu_handle_irq; cpu_pmu->enable = armv6pmu_enable_event; cpu_pmu->disable = armv6mpcore_pmu_disable_event; @@ -703,7 +544,17 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu) return 0; } #else -static int armv6pmu_init(struct arm_pmu *cpu_pmu) +static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) +{ + return -ENODEV; +} + +static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu) +{ + return -ENODEV; +} + +static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu) { return -ENODEV; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index f4ef3981ed02..116758b77f93 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -148,137 +148,62 @@ enum krait_perf_types { * accesses/misses in hardware. */ static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV7_A8_PERFCTR_STALL_ISIDE, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - /* - * The performance counters don't differentiate between read - * and write accesses/misses so this isn't strictly correct, - * but it's the best we can do. Writes and reads get - * combined. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Cortex-A9 HW events mapping */ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_A9_PERFCTR_INSTR_CORE_RENAME, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV7_A9_PERFCTR_STALL_ICACHE, [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV7_A9_PERFCTR_STALL_DISPATCH, }; @@ -286,238 +211,83 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - /* - * The performance counters don't differentiate between read - * and write accesses/misses so this isn't strictly correct, - * but it's the best we can do. Writes and reads get - * combined. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Cortex-A5 HW events mapping */ static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, - [C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - /* - * The prefetch counters don't differentiate between the I - * side and the D side. - */ - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, - [C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, + [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + /* + * The prefetch counters don't differentiate between the I side and the + * D side. + */ + [C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, + [C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Cortex-A15 HW events mapping */ static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, @@ -525,123 +295,48 @@ static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_A15_PERFCTR_PC_WRITE_SPEC, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - /* - * Not all performance counters differentiate between read - * and write accesses/misses so we're not always strictly - * correct, but it's the best we can do. Writes and reads get - * combined in these cases. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE, + + /* + * Not all performance counters differentiate between read and write + * accesses/misses so we're not always strictly correct, but it's the + * best we can do. Writes and reads get combined in these cases. + */ + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Cortex-A7 HW events mapping */ static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, @@ -649,123 +344,48 @@ static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - /* - * The performance counters don't differentiate between read - * and write accesses/misses so this isn't strictly correct, - * but it's the best we can do. Writes and reads get - * combined. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Cortex-A12 HW events mapping */ static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, @@ -773,138 +393,60 @@ static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_A12_PERFCTR_PC_WRITE_SPEC, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - /* - * Not all performance counters differentiate between read - * and write accesses/misses so we're not always strictly - * correct, but it's the best we can do. Writes and reads get - * combined in these cases. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_A12_PERFCTR_PF_TLB_REFILL, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + /* + * Not all performance counters differentiate between read and write + * accesses/misses so we're not always strictly correct, but it's the + * best we can do. Writes and reads get combined in these cases. + */ + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A12_PERFCTR_PF_TLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* * Krait HW events mapping */ static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, - [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, }; static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, - [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, }; @@ -912,110 +454,31 @@ static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = { static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - /* - * The performance counters don't differentiate between read - * and write accesses/misses so this isn't strictly correct, - * but it's the best we can do. Writes and reads get - * combined. - */ - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ICACHE_ACCESS, - [C(RESULT_MISS)] = KRAIT_PERFCTR_L1_ICACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = KRAIT_PERFCTR_L1_ICACHE_MISS, + + [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, + + [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; /* @@ -1545,7 +1008,7 @@ 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; @@ -1554,7 +1017,7 @@ 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; @@ -1563,7 +1026,7 @@ 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; @@ -1572,7 +1035,7 @@ 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; @@ -1582,7 +1045,7 @@ 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; @@ -1592,13 +1055,20 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A12"; + cpu_pmu->name = "armv7_cortex_a12"; cpu_pmu->map_event = armv7_a12_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; return 0; } +static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7_a12_pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a17"; + return 0; +} + /* * Krait Performance Monitor Region Event Selection Register (PMRESRn) * @@ -1816,6 +1286,7 @@ static void krait_pmu_disable_event(struct perf_event *event) unsigned long flags; struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct pmu_hw_events *events = cpu_pmu->get_hw_events(); /* Disable counter and interrupt */ @@ -1841,6 +1312,7 @@ static void krait_pmu_enable_event(struct perf_event *event) unsigned long flags; struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct pmu_hw_events *events = cpu_pmu->get_hw_events(); /* @@ -1917,7 +1389,7 @@ static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc, struct perf_event *event) { int idx; - int bit; + int bit = -1; unsigned int prefix; unsigned int region; unsigned int code; @@ -1946,7 +1418,7 @@ static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc, } idx = armv7pmu_get_event_idx(cpuc, event); - if (idx < 0 && krait_event) + if (idx < 0 && bit >= 0) clear_bit(bit, cpuc->used_mask); return idx; @@ -1974,7 +1446,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc, static int krait_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Krait"; + cpu_pmu->name = "armv7_krait"; /* Some early versions of Krait don't support PC write events */ if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node, "qcom,no-pc-write")) @@ -2021,6 +1493,11 @@ static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) return -ENODEV; } +static inline int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) +{ + return -ENODEV; +} + static inline int krait_pmu_init(struct arm_pmu *cpu_pmu) { return -ENODEV; diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 63990c42fac9..08da0af550b7 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -48,118 +48,31 @@ enum xscale_counters { }; static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT, [PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION, - [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH, [PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = XSCALE_PERFCTR_ICACHE_NO_DELIVER, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, }; static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, - [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, - [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, }; #define XSCALE_PMU_ENABLE 0x001 @@ -442,7 +355,7 @@ static int xscale_map_event(struct perf_event *event) static int xscale1pmu_init(struct arm_pmu *cpu_pmu) { - cpu_pmu->name = "xscale1"; + cpu_pmu->name = "armv5_xscale1"; cpu_pmu->handle_irq = xscale1pmu_handle_irq; cpu_pmu->enable = xscale1pmu_enable_event; cpu_pmu->disable = xscale1pmu_disable_event; @@ -812,7 +725,7 @@ static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val) static int xscale2pmu_init(struct arm_pmu *cpu_pmu) { - cpu_pmu->name = "xscale2"; + cpu_pmu->name = "armv5_xscale2"; cpu_pmu->handle_irq = xscale2pmu_handle_irq; cpu_pmu->enable = xscale2pmu_enable_event; cpu_pmu->disable = xscale2pmu_disable_event; diff --git a/arch/arm/kernel/probes-arm.c b/arch/arm/kernel/probes-arm.c index 51a13a027989..8eaef81d8344 100644 --- a/arch/arm/kernel/probes-arm.c +++ b/arch/arm/kernel/probes-arm.c @@ -341,12 +341,12 @@ static const union decode_item arm_cccc_000x_table[] = { /* CMP (reg-shift reg) cccc 0001 0101 xxxx xxxx xxxx 0xx1 xxxx */ /* CMN (reg-shift reg) cccc 0001 0111 xxxx xxxx xxxx 0xx1 xxxx */ DECODE_EMULATEX (0x0f900090, 0x01100010, PROBES_DATA_PROCESSING_REG, - REGS(ANY, 0, NOPC, 0, ANY)), + REGS(NOPC, 0, NOPC, 0, NOPC)), /* MOV (reg-shift reg) cccc 0001 101x xxxx xxxx xxxx 0xx1 xxxx */ /* MVN (reg-shift reg) cccc 0001 111x xxxx xxxx xxxx 0xx1 xxxx */ DECODE_EMULATEX (0x0fa00090, 0x01a00010, PROBES_DATA_PROCESSING_REG, - REGS(0, ANY, NOPC, 0, ANY)), + REGS(0, NOPC, NOPC, 0, NOPC)), /* AND (reg-shift reg) cccc 0000 000x xxxx xxxx xxxx 0xx1 xxxx */ /* EOR (reg-shift reg) cccc 0000 001x xxxx xxxx xxxx 0xx1 xxxx */ @@ -359,7 +359,7 @@ static const union decode_item arm_cccc_000x_table[] = { /* ORR (reg-shift reg) cccc 0001 100x xxxx xxxx xxxx 0xx1 xxxx */ /* BIC (reg-shift reg) cccc 0001 110x xxxx xxxx xxxx 0xx1 xxxx */ DECODE_EMULATEX (0x0e000090, 0x00000010, PROBES_DATA_PROCESSING_REG, - REGS(ANY, ANY, NOPC, 0, ANY)), + REGS(NOPC, NOPC, NOPC, 0, NOPC)), DECODE_END }; diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c index 46931880093d..f73891b6b730 100644 --- a/arch/arm/kernel/psci.c +++ b/arch/arm/kernel/psci.c @@ -17,63 +17,58 @@ #include <linux/init.h> #include <linux/of.h> +#include <linux/reboot.h> +#include <linux/pm.h> +#include <uapi/linux/psci.h> #include <asm/compiler.h> #include <asm/errno.h> #include <asm/opcodes-sec.h> #include <asm/opcodes-virt.h> #include <asm/psci.h> +#include <asm/system_misc.h> struct psci_operations psci_ops; static int (*invoke_psci_fn)(u32, u32, u32, u32); +typedef int (*psci_initcall_t)(const struct device_node *); enum psci_function { PSCI_FN_CPU_SUSPEND, PSCI_FN_CPU_ON, PSCI_FN_CPU_OFF, PSCI_FN_MIGRATE, + PSCI_FN_AFFINITY_INFO, + PSCI_FN_MIGRATE_INFO_TYPE, PSCI_FN_MAX, }; static u32 psci_function_id[PSCI_FN_MAX]; -#define PSCI_RET_SUCCESS 0 -#define PSCI_RET_EOPNOTSUPP -1 -#define PSCI_RET_EINVAL -2 -#define PSCI_RET_EPERM -3 - static int psci_to_linux_errno(int errno) { switch (errno) { case PSCI_RET_SUCCESS: return 0; - case PSCI_RET_EOPNOTSUPP: + case PSCI_RET_NOT_SUPPORTED: return -EOPNOTSUPP; - case PSCI_RET_EINVAL: + case PSCI_RET_INVALID_PARAMS: return -EINVAL; - case PSCI_RET_EPERM: + case PSCI_RET_DENIED: return -EPERM; }; return -EINVAL; } -#define PSCI_POWER_STATE_ID_MASK 0xffff -#define PSCI_POWER_STATE_ID_SHIFT 0 -#define PSCI_POWER_STATE_TYPE_MASK 0x1 -#define PSCI_POWER_STATE_TYPE_SHIFT 16 -#define PSCI_POWER_STATE_AFFL_MASK 0x3 -#define PSCI_POWER_STATE_AFFL_SHIFT 24 - static u32 psci_power_state_pack(struct psci_power_state state) { - return ((state.id & PSCI_POWER_STATE_ID_MASK) - << PSCI_POWER_STATE_ID_SHIFT) | - ((state.type & PSCI_POWER_STATE_TYPE_MASK) - << PSCI_POWER_STATE_TYPE_SHIFT) | - ((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK) - << PSCI_POWER_STATE_AFFL_SHIFT); + return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT) + & PSCI_0_2_POWER_STATE_ID_MASK) | + ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT) + & PSCI_0_2_POWER_STATE_TYPE_MASK) | + ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT) + & PSCI_0_2_POWER_STATE_AFFL_MASK); } /* @@ -110,6 +105,14 @@ static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, return function_id; } +static int psci_get_version(void) +{ + int err; + + err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0); + return err; +} + static int psci_cpu_suspend(struct psci_power_state state, unsigned long entry_point) { @@ -153,26 +156,36 @@ static int psci_migrate(unsigned long cpuid) return psci_to_linux_errno(err); } -static const struct of_device_id psci_of_match[] __initconst = { - { .compatible = "arm,psci", }, - {}, -}; +static int psci_affinity_info(unsigned long target_affinity, + unsigned long lowest_affinity_level) +{ + int err; + u32 fn; + + fn = psci_function_id[PSCI_FN_AFFINITY_INFO]; + err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0); + return err; +} -void __init psci_init(void) +static int psci_migrate_info_type(void) { - struct device_node *np; - const char *method; - u32 id; + int err; + u32 fn; - np = of_find_matching_node(NULL, psci_of_match); - if (!np) - return; + fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE]; + err = invoke_psci_fn(fn, 0, 0, 0); + return err; +} + +static int get_set_conduit_method(struct device_node *np) +{ + const char *method; - pr_info("probing function IDs from device-tree\n"); + pr_info("probing for conduit method from DT.\n"); if (of_property_read_string(np, "method", &method)) { - pr_warning("missing \"method\" property\n"); - goto out_put_node; + pr_warn("missing \"method\" property\n"); + return -ENXIO; } if (!strcmp("hvc", method)) { @@ -180,10 +193,99 @@ void __init psci_init(void) } else if (!strcmp("smc", method)) { invoke_psci_fn = __invoke_psci_fn_smc; } else { - pr_warning("invalid \"method\" property: %s\n", method); + pr_warn("invalid \"method\" property: %s\n", method); + return -EINVAL; + } + return 0; +} + +static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd) +{ + invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0); +} + +static void psci_sys_poweroff(void) +{ + invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); +} + +/* + * PSCI Function IDs for v0.2+ are well defined so use + * standard values. + */ +static int psci_0_2_init(struct device_node *np) +{ + int err, ver; + + err = get_set_conduit_method(np); + + if (err) + goto out_put_node; + + ver = psci_get_version(); + + if (ver == PSCI_RET_NOT_SUPPORTED) { + /* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */ + pr_err("PSCI firmware does not comply with the v0.2 spec.\n"); + err = -EOPNOTSUPP; goto out_put_node; + } else { + pr_info("PSCIv%d.%d detected in firmware.\n", + PSCI_VERSION_MAJOR(ver), + PSCI_VERSION_MINOR(ver)); + + if (PSCI_VERSION_MAJOR(ver) == 0 && + PSCI_VERSION_MINOR(ver) < 2) { + err = -EINVAL; + pr_err("Conflicting PSCI version detected.\n"); + goto out_put_node; + } } + pr_info("Using standard PSCI v0.2 function IDs\n"); + psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND; + psci_ops.cpu_suspend = psci_cpu_suspend; + + psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF; + psci_ops.cpu_off = psci_cpu_off; + + psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON; + psci_ops.cpu_on = psci_cpu_on; + + psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE; + psci_ops.migrate = psci_migrate; + + psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO; + psci_ops.affinity_info = psci_affinity_info; + + psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] = + PSCI_0_2_FN_MIGRATE_INFO_TYPE; + psci_ops.migrate_info_type = psci_migrate_info_type; + + arm_pm_restart = psci_sys_reset; + + pm_power_off = psci_sys_poweroff; + +out_put_node: + of_node_put(np); + return err; +} + +/* + * PSCI < v0.2 get PSCI Function IDs via DT. + */ +static int psci_0_1_init(struct device_node *np) +{ + u32 id; + int err; + + err = get_set_conduit_method(np); + + if (err) + goto out_put_node; + + pr_info("Using PSCI v0.1 Function IDs from DT\n"); + if (!of_property_read_u32(np, "cpu_suspend", &id)) { psci_function_id[PSCI_FN_CPU_SUSPEND] = id; psci_ops.cpu_suspend = psci_cpu_suspend; @@ -206,5 +308,25 @@ void __init psci_init(void) out_put_node: of_node_put(np); - return; + return err; +} + +static const struct of_device_id psci_of_match[] __initconst = { + { .compatible = "arm,psci", .data = psci_0_1_init}, + { .compatible = "arm,psci-0.2", .data = psci_0_2_init}, + {}, +}; + +int __init psci_init(void) +{ + struct device_node *np; + const struct of_device_id *matched_np; + psci_initcall_t init_fn; + + np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np); + if (!np) + return -ENODEV; + + init_fn = (psci_initcall_t)matched_np->data; + return init_fn(np); } diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c index 570a48cc3d64..28a1db4da704 100644 --- a/arch/arm/kernel/psci_smp.c +++ b/arch/arm/kernel/psci_smp.c @@ -16,6 +16,8 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/of.h> +#include <linux/delay.h> +#include <uapi/linux/psci.h> #include <asm/psci.h> #include <asm/smp_plat.h> @@ -66,6 +68,36 @@ void __ref psci_cpu_die(unsigned int cpu) /* We should never return */ panic("psci: cpu %d failed to shutdown\n", cpu); } + +int __ref psci_cpu_kill(unsigned int cpu) +{ + int err, i; + + if (!psci_ops.affinity_info) + return 1; + /* + * cpu_kill could race with cpu_die and we can + * potentially end up declaring this cpu undead + * while it is dying. So, try again a few times. + */ + + for (i = 0; i < 10; i++) { + err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); + if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { + pr_info("CPU%d killed.\n", cpu); + return 1; + } + + msleep(10); + pr_info("Retrying again to check for CPU kill\n"); + } + + pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", + cpu, err); + /* Make platform_cpu_kill() fail. */ + return 0; +} + #endif bool __init psci_smp_available(void) @@ -78,5 +110,6 @@ struct smp_operations __initdata psci_smp_ops = { .smp_boot_secondary = psci_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = psci_cpu_die, + .cpu_kill = psci_cpu_kill, #endif }; diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 0dd3b79b15c3..0c27ed6f3f23 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -908,7 +908,7 @@ enum ptrace_syscall_dir { PTRACE_SYSCALL_EXIT, }; -static int tracehook_report_syscall(struct pt_regs *regs, +static void tracehook_report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) { unsigned long ip; @@ -926,7 +926,6 @@ static int tracehook_report_syscall(struct pt_regs *regs, current_thread_info()->syscall = -1; regs->ARM_ip = ip; - return current_thread_info()->syscall; } asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno) @@ -938,7 +937,9 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno) return -1; if (test_thread_flag(TIF_SYSCALL_TRACE)) - scno = tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + + scno = current_thread_info()->syscall; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, scno); diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index 95858966d84e..35e72585ec1d 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -3,6 +3,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/kexec.h> .align 3 /* not needed for this code, but keeps fncpy() happy */ @@ -59,7 +60,7 @@ ENTRY(relocate_new_kernel) mov r0,#0 ldr r1,kexec_mach_type ldr r2,kexec_boot_atags - ARM( mov pc, lr ) + ARM( ret lr ) THUMB( bx lr ) .align diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 50e198c1e9c8..84db893dedc2 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -72,6 +72,7 @@ static int __init fpe_setup(char *line) __setup("fpe=", fpe_setup); #endif +extern void init_default_cache_policy(unsigned long); extern void paging_init(const struct machine_desc *desc); extern void early_paging_init(const struct machine_desc *, struct proc_info_list *); @@ -392,19 +393,34 @@ static void __init cpuid_init_hwcaps(void) elf_hwcap |= HWCAP_LPAE; } -static void __init feat_v6_fixup(void) +static void __init elf_hwcap_fixup(void) { - int id = read_cpuid_id(); - - if ((id & 0xff0f0000) != 0x41070000) - return; + unsigned id = read_cpuid_id(); + unsigned sync_prim; /* * HWCAP_TLS is available only on 1136 r1p0 and later, * see also kuser_get_tls_init. */ - if ((((id >> 4) & 0xfff) == 0xb36) && (((id >> 20) & 3) == 0)) + if (read_cpuid_part() == ARM_CPU_PART_ARM1136 && + ((id >> 20) & 3) == 0) { elf_hwcap &= ~HWCAP_TLS; + return; + } + + /* Verify if CPUID scheme is implemented */ + if ((id & 0x000f0000) != 0x000f0000) + return; + + /* + * If the CPU supports LDREX/STREX and LDREXB/STREXB, + * avoid advertising SWP; it may not be atomic with + * multiprocessing cores. + */ + sync_prim = ((read_cpuid_ext(CPUID_EXT_ISAR3) >> 8) & 0xf0) | + ((read_cpuid_ext(CPUID_EXT_ISAR4) >> 20) & 0x0f); + if (sync_prim >= 0x13) + elf_hwcap &= ~HWCAP_SWP; } /* @@ -590,7 +606,7 @@ static void __init setup_processor(void) pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", cpu_name, read_cpuid_id(), read_cpuid_id() & 15, - proc_arch[cpu_architecture()], cr_alignment); + proc_arch[cpu_architecture()], get_cr()); snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c", list->arch_name, ENDIANNESS); @@ -603,10 +619,12 @@ static void __init setup_processor(void) #ifndef CONFIG_ARM_THUMB elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif - +#ifdef CONFIG_MMU + init_default_cache_policy(list->__cpu_mm_mmu_flags); +#endif erratum_a15_798181_init(); - feat_v6_fixup(); + elf_hwcap_fixup(); cacheid_init(); cpu_init(); @@ -628,15 +646,8 @@ void __init dump_machine_table(void) int __init arm_add_memory(u64 start, u64 size) { - struct membank *bank = &meminfo.bank[meminfo.nr_banks]; u64 aligned_start; - if (meminfo.nr_banks >= NR_BANKS) { - pr_crit("NR_BANKS too low, ignoring memory at 0x%08llx\n", - (long long)start); - return -EINVAL; - } - /* * Ensure that start/size are aligned to a page boundary. * Size is appropriately rounded down, start is rounded up. @@ -677,17 +688,17 @@ int __init arm_add_memory(u64 start, u64 size) aligned_start = PHYS_OFFSET; } - bank->start = aligned_start; - bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); + start = aligned_start; + size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* * Check whether this memory region has non-zero size or * invalid node number. */ - if (bank->size == 0) + if (size == 0) return -EINVAL; - meminfo.nr_banks++; + memblock_add(start, size); return 0; } @@ -695,6 +706,7 @@ int __init arm_add_memory(u64 start, u64 size) * Pick out the memory size. We look for mem=size@start, * where start and size are "size[KkMm]" */ + static int __init early_mem(char *p) { static int usermem __initdata = 0; @@ -709,7 +721,8 @@ static int __init early_mem(char *p) */ if (usermem == 0) { usermem = 1; - meminfo.nr_banks = 0; + memblock_remove(memblock_start_of_DRAM(), + memblock_end_of_DRAM() - memblock_start_of_DRAM()); } start = PHYS_OFFSET; @@ -854,13 +867,6 @@ static void __init reserve_crashkernel(void) static inline void reserve_crashkernel(void) {} #endif /* CONFIG_KEXEC */ -static int __init meminfo_cmp(const void *_a, const void *_b) -{ - const struct membank *a = _a, *b = _b; - long cmp = bank_pfn_start(a) - bank_pfn_start(b); - return cmp < 0 ? -1 : cmp > 0 ? 1 : 0; -} - void __init hyp_mode_check(void) { #ifdef CONFIG_ARM_VIRT_EXT @@ -903,12 +909,10 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - early_paging_init(mdesc, lookup_processor_type(read_cpuid_id())); setup_dma_zone(mdesc); sanity_check_meminfo(); - arm_memblock_init(&meminfo, mdesc); + arm_memblock_init(mdesc); paging_init(mdesc); request_standard_resources(mdesc); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index b907d9b790ab..e1e60e5a7a27 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -107,7 +107,7 @@ ENTRY(cpu_resume_mmu) instr_sync mov r0, r0 mov r0, r0 - mov pc, r3 @ jump to virtual address + ret r3 @ jump to virtual address ENDPROC(cpu_resume_mmu) .popsection cpu_resume_after_mmu: @@ -127,6 +127,10 @@ ENDPROC(cpu_resume_after_mmu) .align ENTRY(cpu_resume) ARM_BE8(setend be) @ ensure we are in BE mode +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r1 mov r1, #0 ALT_SMP(mrc p15, 0, r0, c0, c0, 5) ALT_UP_B(1f) @@ -144,7 +148,6 @@ ARM_BE8(setend be) @ ensure we are in BE mode ldr r0, [r0, #SLEEP_SAVE_SP_PHYS] ldr r0, [r0, r1, lsl #2] - setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off @ load phys pgd, stack, resume fn ARM( ldmia r0!, {r1, sp, pc} ) THUMB( ldmia r0!, {r1, r2, r3} ) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 7c4fada440f0..9388a3d479e1 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -47,6 +47,9 @@ #include <asm/mach/arch.h> #include <asm/mpu.h> +#define CREATE_TRACE_POINTS +#include <trace/events/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 @@ -430,38 +433,15 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } } -static void (*smp_cross_call)(const struct cpumask *, unsigned int); +static void (*__smp_cross_call)(const struct cpumask *, unsigned int); void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int)) { - if (!smp_cross_call) - smp_cross_call = fn; -} - -void arch_send_call_function_ipi_mask(const struct cpumask *mask) -{ - smp_cross_call(mask, IPI_CALL_FUNC); -} - -void arch_send_wakeup_ipi_mask(const struct cpumask *mask) -{ - smp_cross_call(mask, IPI_WAKEUP); -} - -void arch_send_call_function_single_ipi(int cpu) -{ - smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); + if (!__smp_cross_call) + __smp_cross_call = fn; } -#ifdef CONFIG_IRQ_WORK -void arch_irq_work_raise(void) -{ - if (is_smp()) - smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); -} -#endif - -static const char *ipi_types[NR_IPI] = { +static const char *ipi_types[NR_IPI] __tracepoint_string = { #define S(x,s) [x] = s S(IPI_WAKEUP, "CPU wakeup interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), @@ -473,6 +453,12 @@ static const char *ipi_types[NR_IPI] = { S(IPI_COMPLETION, "completion interrupts"), }; +static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) +{ + trace_ipi_raise(target, ipi_types[ipinr]); + __smp_cross_call(target, ipinr); +} + void show_ipi_list(struct seq_file *p, int prec) { unsigned int cpu, i; @@ -499,6 +485,29 @@ u64 smp_irq_stat_cpu(unsigned int cpu) return sum; } +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_CALL_FUNC); +} + +void arch_send_wakeup_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_WAKEUP); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); +} + +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + if (is_smp()) + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); +} +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST void tick_broadcast(const struct cpumask *mask) { @@ -556,8 +565,10 @@ void handle_IPI(int ipinr, struct pt_regs *regs) unsigned int cpu = smp_processor_id(); struct pt_regs *old_regs = set_irq_regs(regs); - if (ipinr < NR_IPI) + if ((unsigned)ipinr < NR_IPI) { + trace_ipi_entry(ipi_types[ipinr]); __inc_irq_stat(cpu, ipi_irqs[ipinr]); + } switch (ipinr) { case IPI_WAKEUP: @@ -612,6 +623,9 @@ void handle_IPI(int ipinr, struct pt_regs *regs) cpu, ipinr); break; } + + if ((unsigned)ipinr < NR_IPI) + trace_ipi_exit(ipi_types[ipinr]); set_irq_regs(old_regs); } diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 1aafa0d785eb..72f9241ad5db 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -17,6 +17,8 @@ #include <asm/cputype.h> #define SCU_CTRL 0x00 +#define SCU_ENABLE (1 << 0) +#define SCU_STANDBY_ENABLE (1 << 5) #define SCU_CONFIG 0x04 #define SCU_CPU_STATUS 0x08 #define SCU_INVALIDATE 0x0c @@ -50,10 +52,16 @@ void scu_enable(void __iomem *scu_base) scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); /* already enabled? */ - if (scu_ctrl & 1) + if (scu_ctrl & SCU_ENABLE) return; - scu_ctrl |= 1; + scu_ctrl |= SCU_ENABLE; + + /* Cortex-A9 earlier than r2p0 has no standby bit in SCU */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090 && + (read_cpuid_id() & 0x00f0000f) >= 0x00200000) + scu_ctrl |= SCU_STANDBY_ENABLE; + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); /* diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 95d063620b76..2e72be4f623e 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -92,15 +92,19 @@ void erratum_a15_798181_init(void) unsigned int midr = read_cpuid_id(); unsigned int revidr = read_cpuid(CPUID_REVIDR); - /* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */ - if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 || - (revidr & 0x210) == 0x210) { - return; - } - if (revidr & 0x10) - erratum_a15_798181_handler = erratum_a15_798181_partial; - else + /* Brahma-B15 r0p0..r0p2 affected + * Cortex-A15 r0p0..r3p2 w/o ECO fix affected */ + if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2) erratum_a15_798181_handler = erratum_a15_798181_broadcast; + else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr <= 0x413fc0f2 && + (revidr & 0x210) != 0x210) { + if (revidr & 0x10) + erratum_a15_798181_handler = + erratum_a15_798181_partial; + else + erratum_a15_798181_handler = + erratum_a15_798181_broadcast; + } } #endif diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index af4e8c8a5422..f065eb05d254 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -3,6 +3,7 @@ #include <linux/stacktrace.h> #include <asm/stacktrace.h> +#include <asm/traps.h> #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) /* @@ -61,6 +62,7 @@ EXPORT_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { struct stack_trace *trace; + unsigned long last_pc; unsigned int no_sched_functions; unsigned int skip; }; @@ -69,6 +71,7 @@ static int save_trace(struct stackframe *frame, void *d) { struct stack_trace_data *data = d; struct stack_trace *trace = data->trace; + struct pt_regs *regs; unsigned long addr = frame->pc; if (data->no_sched_functions && in_sched_functions(addr)) @@ -80,16 +83,39 @@ static int save_trace(struct stackframe *frame, void *d) trace->entries[trace->nr_entries++] = addr; + if (trace->nr_entries >= trace->max_entries) + return 1; + + /* + * in_exception_text() is designed to test if the PC is one of + * the functions which has an exception stack above it, but + * unfortunately what is in frame->pc is the return LR value, + * not the saved PC value. So, we need to track the previous + * frame PC value when doing this. + */ + addr = data->last_pc; + data->last_pc = frame->pc; + if (!in_exception_text(addr)) + return 0; + + regs = (struct pt_regs *)frame->sp; + + trace->entries[trace->nr_entries++] = regs->ARM_pc; + 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.last_pc = ULONG_MAX; data.skip = trace->skip; + data.no_sched_functions = nosched; if (tsk != current) { #ifdef CONFIG_SMP @@ -102,7 +128,6 @@ 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 +136,12 @@ 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 +149,33 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + struct stack_trace_data data; + struct stackframe frame; + + data.trace = trace; + data.skip = trace->skip; + data.no_sched_functions = 0; + + frame.fp = regs->ARM_fp; + frame.sp = regs->ARM_sp; + frame.lr = regs->ARM_lr; + frame.pc = regs->ARM_pc; + + walk_stackframe(&frame, save_trace, &data); + if (trace->nr_entries < trace->max_entries) + 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/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index b1b89882b113..67ca8578c6d8 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -27,6 +27,7 @@ #include <linux/perf_event.h> #include <asm/opcodes.h> +#include <asm/system_info.h> #include <asm/traps.h> #include <asm/uaccess.h> @@ -266,6 +267,9 @@ static struct undef_hook swp_hook = { */ static int __init swp_emulation_init(void) { + if (cpu_architecture() < CPU_ARCH_ARMv7) + return 0; + #ifdef CONFIG_PROC_FS if (!proc_create("cpu/swp_emulation", S_IRUGO, NULL, &proc_status_fops)) return -ENOMEM; diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 829a96d4a179..0cc7e58c47cc 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -50,10 +50,7 @@ unsigned long profile_pc(struct pt_regs *regs) if (!in_lock_functions(regs->ARM_pc)) return regs->ARM_pc; - frame.fp = regs->ARM_fp; - frame.sp = regs->ARM_sp; - frame.lr = regs->ARM_lr; - frame.pc = regs->ARM_pc; + arm_get_current_stackframe(regs, &frame); do { int ret = unwind_frame(&frame); if (ret < 0) diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 0bc94b1fd1ae..e35d880f9773 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -26,30 +26,30 @@ #include <asm/topology.h> /* - * cpu power scale management + * cpu capacity scale management */ /* - * cpu power table + * cpu capacity table * This per cpu data structure describes the relative capacity of each core. * On a heteregenous system, cores don't have the same computation capacity - * and we reflect that difference in the cpu_power field so the scheduler can - * take this difference into account during load balance. A per cpu structure - * is preferred because each CPU updates its own cpu_power field during the - * load balance except for idle cores. One idle core is selected to run the - * rebalance_domains for all idle cores and the cpu_power can be updated - * during this sequence. + * and we reflect that difference in the cpu_capacity field so the scheduler + * can take this difference into account during load balance. A per cpu + * structure is preferred because each CPU updates its own cpu_capacity field + * during the load balance except for idle cores. One idle core is selected + * to run the rebalance_domains for all idle cores and the cpu_capacity can be + * updated during this sequence. */ static DEFINE_PER_CPU(unsigned long, cpu_scale); -unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { return per_cpu(cpu_scale, cpu); } -static void set_power_scale(unsigned int cpu, unsigned long power) +static void set_capacity_scale(unsigned int cpu, unsigned long capacity) { - per_cpu(cpu_scale, cpu) = power; + per_cpu(cpu_scale, cpu) = capacity; } #ifdef CONFIG_OF @@ -62,11 +62,11 @@ struct cpu_efficiency { * Table of relative efficiency of each processors * The efficiency value must fit in 20bit and the final * cpu_scale value must be in the range - * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * 0 < cpu_scale < 3*SCHED_CAPACITY_SCALE/2 * in order to return at most 1 when DIV_ROUND_CLOSEST * is used to compute the capacity of a CPU. * Processors that are not defined in the table, - * use the default SCHED_POWER_SCALE value for cpu_scale. + * use the default SCHED_CAPACITY_SCALE value for cpu_scale. */ static const struct cpu_efficiency table_efficiency[] = { {"arm,cortex-a15", 3891}, @@ -83,21 +83,21 @@ static unsigned long middle_capacity = 1; * Iterate all CPUs' descriptor in DT and compute the efficiency * (as per table_efficiency). Also calculate a middle efficiency * as close as possible to (max{eff_i} - min{eff_i}) / 2 - * This is later used to scale the cpu_power field such that an - * 'average' CPU is of middle power. Also see the comments near - * table_efficiency[] and update_cpu_power(). + * This is later used to scale the cpu_capacity field such that an + * 'average' CPU is of middle capacity. Also see the comments near + * table_efficiency[] and update_cpu_capacity(). */ static void __init parse_dt_topology(void) { const struct cpu_efficiency *cpu_eff; struct device_node *cn = NULL; - unsigned long min_capacity = (unsigned long)(-1); + unsigned long min_capacity = ULONG_MAX; unsigned long max_capacity = 0; unsigned long capacity = 0; - int alloc_size, cpu = 0; + int cpu = 0; - alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); - __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT); + __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity), + GFP_NOWAIT); for_each_possible_cpu(cpu) { const u32 *rate; @@ -141,15 +141,15 @@ static void __init parse_dt_topology(void) * cpu_scale because all CPUs have the same capacity. Otherwise, we * compute a middle_capacity factor that will ensure that the capacity * of an 'average' CPU of the system will be as close as possible to - * SCHED_POWER_SCALE, which is the default value, but with the + * SCHED_CAPACITY_SCALE, which is the default value, but with the * constraint explained near table_efficiency[]. */ if (4*max_capacity < (3*(max_capacity + min_capacity))) middle_capacity = (min_capacity + max_capacity) - >> (SCHED_POWER_SHIFT+1); + >> (SCHED_CAPACITY_SHIFT+1); else middle_capacity = ((max_capacity / 3) - >> (SCHED_POWER_SHIFT-1)) + 1; + >> (SCHED_CAPACITY_SHIFT-1)) + 1; } @@ -158,20 +158,20 @@ static void __init parse_dt_topology(void) * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the * function returns directly for SMP system. */ -static void update_cpu_power(unsigned int cpu) +static void update_cpu_capacity(unsigned int cpu) { if (!cpu_capacity(cpu)) return; - set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); - printk(KERN_INFO "CPU%u: update cpu_power %lu\n", - cpu, arch_scale_freq_power(NULL, cpu)); + printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n", + cpu, arch_scale_freq_capacity(NULL, cpu)); } #else static inline void parse_dt_topology(void) {} -static inline void update_cpu_power(unsigned int cpuid) {} +static inline void update_cpu_capacity(unsigned int cpuid) {} #endif /* @@ -185,6 +185,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return &cpu_topology[cpu].core_sibling; } +/* + * The current assumption is that we can power gate each core independently. + * This will be superseded by DT binding once available. + */ +const struct cpumask *cpu_corepower_mask(int cpu) +{ + return &cpu_topology[cpu].thread_sibling; +} + static void update_siblings_masks(unsigned int cpuid) { struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -258,7 +267,7 @@ void store_cpu_topology(unsigned int cpuid) update_siblings_masks(cpuid); - update_cpu_power(cpuid); + update_cpu_capacity(cpuid); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -266,6 +275,20 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } +static inline int cpu_corepower_flags(void) +{ + return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN; +} + +static struct sched_domain_topology_level arm_topology[] = { +#ifdef CONFIG_SCHED_MC + { cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) }, + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array @@ -274,7 +297,7 @@ void __init init_cpu_topology(void) { unsigned int cpu; - /* init core mask and power*/ + /* init core mask and capacity */ for_each_possible_cpu(cpu) { struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); @@ -284,9 +307,12 @@ void __init init_cpu_topology(void) cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); - set_power_scale(cpu, SCHED_POWER_SCALE); + set_capacity_scale(cpu, SCHED_CAPACITY_SCALE); } smp_wmb(); parse_dt_topology(); + + /* Set scheduler topology descriptor */ + set_sched_topology(arm_topology); } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index abd2fc067736..c8e4bb714944 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -31,11 +31,13 @@ #include <asm/exception.h> #include <asm/unistd.h> #include <asm/traps.h> +#include <asm/ptrace.h> #include <asm/unwind.h> #include <asm/tls.h> #include <asm/system_misc.h> #include <asm/opcodes.h> + static const char *handler[]= { "prefetch abort", "data abort", @@ -184,7 +186,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) tsk = current; if (regs) { - fp = regs->ARM_fp; + fp = frame_pointer(regs); mode = processor_mode(regs); } else if (tsk != current) { fp = thread_saved_fp(tsk); @@ -719,7 +721,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) dump_instr("", regs); if (user_mode(regs)) { __show_regs(regs); - c_backtrace(regs->ARM_fp, processor_mode(regs)); + c_backtrace(frame_pointer(regs), processor_mode(regs)); } } #endif diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index 3c217694ebec..a61a1dfbb0db 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -31,7 +31,7 @@ #warning Your compiler does not have EABI support. #warning ARM unwind is known to compile only with EABI compilers. #warning Change compiler or disable ARM_UNWIND option. -#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) +#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) && !defined(__clang__) #warning Your compiler is too buggy; it is known to not compile ARM unwind support. #warning Change compiler or disable ARM_UNWIND option. #endif @@ -285,7 +285,7 @@ static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl, if (unwind_pop_register(ctrl, &vsp, reg)) return -URC_FAILURE; - if (insn & 0x80) + if (insn & 0x8) if (unwind_pop_register(ctrl, &vsp, 14)) return -URC_FAILURE; @@ -479,12 +479,10 @@ void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk) tsk = current; if (regs) { - frame.fp = regs->ARM_fp; - frame.sp = regs->ARM_sp; - frame.lr = regs->ARM_lr; + arm_get_current_stackframe(regs, &frame); /* PC might be corrupted, use LR in that case. */ - frame.pc = kernel_text_address(regs->ARM_pc) - ? regs->ARM_pc : regs->ARM_lr; + if (!kernel_text_address(regs->ARM_pc)) + frame.pc = regs->ARM_lr; } else if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; diff --git a/arch/arm/kernel/uprobes.c b/arch/arm/kernel/uprobes.c index f9bacee973bf..56adf9c1fde0 100644 --- a/arch/arm/kernel/uprobes.c +++ b/arch/arm/kernel/uprobes.c @@ -113,6 +113,26 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, return 0; } +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + void *xol_page_kaddr = kmap_atomic(page); + void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK); + + preempt_disable(); + + /* Initialize the slot */ + memcpy(dst, src, len); + + /* flush caches (dcache/icache) */ + flush_uprobe_xol_access(page, vaddr, dst, len); + + preempt_enable(); + + kunmap_atomic(xol_page_kaddr); +} + + int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 7bcee5c9b604..6f57cb94367f 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -318,7 +318,6 @@ SECTIONS _end = .; STABS_DEBUG - .comment 0 : { *(.comment) } } /* |