diff options
Diffstat (limited to 'arch/arm/kernel')
43 files changed, 883 insertions, 1446 deletions
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index f7b450f97e68..a88671cfe1ff 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -98,6 +98,14 @@ EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); +EXPORT_SYMBOL(__get_user_8); + +#ifdef __ARMEB__ +EXPORT_SYMBOL(__get_user_64t_1); +EXPORT_SYMBOL(__get_user_64t_2); +EXPORT_SYMBOL(__get_user_64t_4); +EXPORT_SYMBOL(__get_user_32t_8); +#endif EXPORT_SYMBOL(__put_user_1); EXPORT_SYMBOL(__put_user_2); 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 7807ef58a2ab..528f8af2addb 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -130,7 +130,7 @@ static int __init parse_tag_cmdline(const struct tag *tag) strlcat(default_command_line, tag->u.cmdline.cmdline, COMMAND_LINE_SIZE); #elif defined(CONFIG_CMDLINE_FORCE) - pr_warning("Ignoring tag cmdline (using the default kernel command line)\n"); + pr_warn("Ignoring tag cmdline (using the default kernel command line)\n"); #else strlcpy(default_command_line, tag->u.cmdline.cmdline, COMMAND_LINE_SIZE); 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/entry-armv.S b/arch/arm/kernel/entry-armv.S index 52a949a8077d..2f5555d307b3 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -146,7 +146,7 @@ ENDPROC(__und_invalid) #define SPFIX(code...) #endif - .macro svc_entry, stack_hole=0 + .macro svc_entry, stack_hole=0, trace=1 UNWIND(.fnstart ) UNWIND(.save {r0 - pc} ) sub sp, sp, #(S_FRAME_SIZE + \stack_hole - 4) @@ -182,9 +182,11 @@ ENDPROC(__und_invalid) @ stmia r7, {r2 - r6} + .if \trace #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif + .endif .endm .align 5 @@ -224,7 +226,7 @@ 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 @@ -295,6 +297,15 @@ __pabt_svc: ENDPROC(__pabt_svc) .align 5 +__fiq_svc: + svc_entry trace=0 + mov r0, sp @ struct pt_regs *regs + bl handle_fiq_as_nmi + svc_exit_via_fiq + UNWIND(.fnend ) +ENDPROC(__fiq_svc) + + .align 5 .LCcralign: .word cr_alignment #ifdef MULTI_DABORT @@ -305,6 +316,46 @@ ENDPROC(__pabt_svc) .word fp_enter /* + * Abort mode handlers + */ + +@ +@ Taking a FIQ in abort mode is similar to taking a FIQ in SVC mode +@ and reuses the same macros. However in abort mode we must also +@ save/restore lr_abt and spsr_abt to make nested aborts safe. +@ + .align 5 +__fiq_abt: + svc_entry trace=0 + + ARM( msr cpsr_c, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + mov r1, lr @ Save lr_abt + mrs r2, spsr @ Save spsr_abt, abort is now safe + ARM( msr cpsr_c, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + stmfd sp!, {r1 - r2} + + add r0, sp, #8 @ struct pt_regs *regs + bl handle_fiq_as_nmi + + ldmfd sp!, {r1 - r2} + ARM( msr cpsr_c, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + mov lr, r1 @ Restore lr_abt, abort is unsafe + msr spsr_cxsf, r2 @ Restore spsr_abt + ARM( msr cpsr_c, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + + svc_exit_via_fiq + UNWIND(.fnend ) +ENDPROC(__fiq_abt) + +/* * User mode handlers * * EABI note: sp_svc is always 64-bit aligned here, so should S_FRAME_SIZE @@ -314,13 +365,16 @@ ENDPROC(__pabt_svc) #error "sizeof(struct pt_regs) must be a multiple of 8" #endif - .macro usr_entry + .macro usr_entry, trace=1 UNWIND(.fnstart ) UNWIND(.cantunwind ) @ don't unwind the user space sub sp, sp, #S_FRAME_SIZE ARM( stmib sp, {r1 - r12} ) THUMB( stmia sp, {r0 - r12} ) + ATRAP( mrc p15, 0, r7, c1, c0, 0) + ATRAP( ldr r8, .LCcralign) + ldmia r0, {r3 - r5} add r0, sp, #S_PC @ here for interlock avoidance mov r6, #-1 @ "" "" "" "" @@ -328,6 +382,8 @@ ENDPROC(__pabt_svc) str r3, [sp] @ save the "real" r0 copied @ from the exception stack + ATRAP( ldr r8, [r8, #0]) + @ @ We are now ready to fill in the remaining blanks on the stack: @ @@ -341,20 +397,21 @@ ENDPROC(__pabt_svc) ARM( stmdb r0, {sp, lr}^ ) THUMB( store_user_sp_lr r0, r1, S_SP - S_PC ) - @ @ Enable the alignment trap while in kernel mode - @ - alignment_trap r0, .LCcralign + ATRAP( teq r8, r7) + ATRAP( mcrne p15, 0, r8, c1, c0, 0) @ @ Clear FP to mark the first stack frame @ zero_fp + .if \trace #ifdef CONFIG_IRQSOFF_TRACER bl trace_hardirqs_off #endif ct_user_exit save = 0 + .endif .endm .macro kuser_cmpxchg_check @@ -490,7 +547,7 @@ ENDPROC(__und_usr) .pushsection .fixup, "ax" .align 2 4: str r4, [sp, #S_PC] @ retry current instruction - mov pc, r9 + ret r9 .popsection .pushsection __ex_table,"a" .long 1b, 4b @@ -552,7 +609,7 @@ 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 @@ -571,33 +628,33 @@ 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 @@ -649,7 +706,7 @@ ENTRY(fp_enter) .popsection ENTRY(no_fp) - mov pc, lr + ret lr ENDPROC(no_fp) __und_usr_fault_32: @@ -683,6 +740,17 @@ ENTRY(ret_from_exception) ENDPROC(__pabt_usr) ENDPROC(ret_from_exception) + .align 5 +__fiq_usr: + usr_entry trace=0 + kuser_cmpxchg_check + mov r0, sp @ struct pt_regs *regs + bl handle_fiq_as_nmi + get_thread_info tsk + restore_user_regs fast = 0, offset = 0 + UNWIND(.fnend ) +ENDPROC(__fiq_usr) + /* * Register switch for ARMv3 and ARMv4 processors * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info @@ -745,7 +813,7 @@ ENDPROC(__switch_to) #ifdef CONFIG_ARM_THUMB bx \reg #else - mov pc, \reg + ret \reg #endif .endm @@ -837,7 +905,7 @@ kuser_cmpxchg64_fixup: #if __LINUX_ARM_ARCH__ < 6 bcc kuser_cmpxchg32_fixup #endif - mov pc, lr + ret lr .previous #else @@ -905,7 +973,7 @@ kuser_cmpxchg32_fixup: subs r8, r4, r7 rsbcss r8, r8, #(2b - 1b) strcs r7, [sp, #S_PC] - mov pc, lr + ret lr .previous #else @@ -1118,17 +1186,29 @@ vector_addrexcptn: b vector_addrexcptn /*============================================================================= - * Undefined FIQs + * FIQ "NMI" handler *----------------------------------------------------------------------------- - * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC - * MUST PRESERVE SVC SPSR, but need to switch to SVC mode to show our msg. - * Basically to switch modes, we *HAVE* to clobber one register... brain - * damage alert! I don't think that we can execute any code in here in any - * other mode than FIQ... Ok you can switch to another mode, but you can't - * get out of that mode without clobbering one register. + * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86 + * systems. */ -vector_fiq: - subs pc, lr, #4 + vector_stub fiq, FIQ_MODE, 4 + + .long __fiq_usr @ 0 (USR_26 / USR_32) + .long __fiq_svc @ 1 (FIQ_26 / FIQ_32) + .long __fiq_svc @ 2 (IRQ_26 / IRQ_32) + .long __fiq_svc @ 3 (SVC_26 / SVC_32) + .long __fiq_svc @ 4 + .long __fiq_svc @ 5 + .long __fiq_svc @ 6 + .long __fiq_abt @ 7 + .long __fiq_svc @ 8 + .long __fiq_svc @ 9 + .long __fiq_svc @ a + .long __fiq_svc @ b + .long __fiq_svc @ c + .long __fiq_svc @ d + .long __fiq_svc @ e + .long __fiq_svc @ f .globl vector_fiq_offset .equ vector_fiq_offset, vector_fiq diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 7139d4a7dea7..6bb09d4abdea 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 */ @@ -365,7 +366,7 @@ ENTRY(vector_swi) str r0, [sp, #S_OLD_R0] @ Save OLD_R0 #endif zero_fp - alignment_trap ip, __cr_alignment + alignment_trap r10, ip, __cr_alignment enable_irq ct_user_exit get_thread_info tsk @@ -561,7 +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 5d702f8900b1..4176df721bf0 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -37,11 +37,19 @@ #endif .endm - .macro alignment_trap, rtemp, label #ifdef CONFIG_ALIGNMENT_TRAP - ldr \rtemp, \label - ldr \rtemp, [\rtemp] - mcr p15, 0, \rtemp, c1, c0 +#define ATRAP(x...) x +#else +#define ATRAP(x...) +#endif + + .macro alignment_trap, rtmp1, rtmp2, label +#ifdef CONFIG_ALIGNMENT_TRAP + mrc p15, 0, \rtmp2, c1, c0, 0 + ldr \rtmp1, \label + ldr \rtmp1, [\rtmp1] + teq \rtmp1, \rtmp2 + mcrne p15, 0, \rtmp1, c1, c0, 0 #endif .endm @@ -208,26 +216,49 @@ #endif .endif msr spsr_cxsf, \rpsr -#if defined(CONFIG_CPU_V6) - ldr r0, [sp] - strex r1, r2, [sp] @ clear the exclusive monitor - ldmib sp, {r1 - pc}^ @ load r1 - pc, cpsr -#elif defined(CONFIG_CPU_32v6K) - clrex @ clear the exclusive monitor - ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr -#else - ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) + @ We must avoid clrex due to Cortex-A15 erratum #830321 + sub r0, sp, #4 @ uninhabited address + strex r1, r2, [r0] @ clear the exclusive monitor #endif + ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr + .endm + + @ + @ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit + @ + @ This macro acts in a similar manner to svc_exit but switches to FIQ + @ mode to restore the final part of the register state. + @ + @ We cannot use the normal svc_exit procedure because that would + @ clobber spsr_svc (FIQ could be delivered during the first few + @ instructions of vector_swi meaning its contents have not been + @ saved anywhere). + @ + @ Note that, unlike svc_exit, this macro also does not allow a caller + @ supplied rpsr. This is because the FIQ exceptions are not re-entrant + @ and the handlers cannot call into the scheduler (meaning the value + @ on the stack remains correct). + @ + .macro svc_exit_via_fiq + mov r0, sp + ldmib r0, {r1 - r14} @ abort is deadly from here onward (it will + @ clobber state restored below) + msr cpsr_c, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT + add r8, r0, #S_PC + ldr r9, [r0, #S_PSR] + msr spsr_cxsf, r9 + ldr r0, [r0, #S_R0] + ldmia r8, {pc}^ .endm .macro restore_user_regs, fast = 0, offset = 0 ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr ldr lr, [sp, #\offset + S_PC]! @ get pc msr spsr_cxsf, r1 @ save in spsr_svc -#if defined(CONFIG_CPU_V6) +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) + @ We must avoid clrex due to Cortex-A15 erratum #830321 strex r1, r2, [sp] @ clear the exclusive monitor -#elif defined(CONFIG_CPU_32v6K) - clrex @ clear the exclusive monitor #endif .if \fast ldmdb sp, {r1 - lr}^ @ get calling r1 - lr @@ -240,12 +271,6 @@ 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 @@ -267,7 +292,10 @@ .endif ldr lr, [sp, #S_SP] @ top of the stack ldrd r0, r1, [sp, #S_LR] @ calling lr and pc - clrex @ clear the exclusive monitor + + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor + stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context ldmia sp, {r0 - r12} mov sp, lr @@ -275,6 +303,25 @@ rfeia sp! .endm + @ + @ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit + @ + @ For full details see non-Thumb implementation above. + @ + .macro svc_exit_via_fiq + add r0, sp, #S_R2 + ldr lr, [sp, #S_LR] + ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will + @ clobber state restored below) + ldmia r0, {r2 - r12} + mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT + msr cpsr_c, r1 + sub r0, #S_R2 + add r8, r0, #S_PC + ldmia r0, {r0 - r1} + rfeia r8 + .endm + #ifdef CONFIG_CPU_V7M /* * Note we don't need to do clrex here as clearing the local monitor is @@ -288,13 +335,16 @@ .endm #else /* ifdef CONFIG_CPU_V7M */ .macro restore_user_regs, fast = 0, offset = 0 - clrex @ clear the exclusive monitor mov r2, sp load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr ldr lr, [sp, #\offset + S_PC] @ get pc add sp, sp, #\offset + S_SP msr spsr_cxsf, r1 @ save in spsr_svc + + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r1, r2, [sp] @ clear the exclusive monitor + .if \fast ldmdb sp, {r1 - r12} @ get calling r1 - r12 .else @@ -304,14 +354,6 @@ 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/fiq.c b/arch/arm/kernel/fiq.c index 918875d96d5d..b37752a96652 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -52,7 +52,8 @@ (unsigned)&vector_fiq_offset; \ }) -static unsigned long no_fiq_insn; +static unsigned long dfl_fiq_insn; +static struct pt_regs dfl_fiq_regs; /* Default reacquire function * - we always relinquish FIQ control @@ -60,8 +61,15 @@ static unsigned long no_fiq_insn; */ static int fiq_def_op(void *ref, int relinquish) { - if (!relinquish) - set_fiq_handler(&no_fiq_insn, sizeof(no_fiq_insn)); + if (!relinquish) { + /* Restore default handler and registers */ + local_fiq_disable(); + set_fiq_regs(&dfl_fiq_regs); + set_fiq_handler(&dfl_fiq_insn, sizeof(dfl_fiq_insn)); + local_fiq_enable(); + + /* FIXME: notify irq controller to standard enable FIQs */ + } return 0; } @@ -150,6 +158,7 @@ EXPORT_SYMBOL(disable_fiq); void __init init_FIQ(int start) { unsigned offset = FIQ_OFFSET; - no_fiq_insn = *(unsigned long *)(0xffff0000 + offset); + dfl_fiq_insn = *(unsigned long *)(0xffff0000 + offset); + get_fiq_regs(&dfl_fiq_regs); fiq_start = start; } 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/head-common.S b/arch/arm/kernel/head-common.S index 572a38335c96..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) /* @@ -162,7 +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 2c35f0ff2fdc..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) /* @@ -468,7 +468,7 @@ 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 @@ -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 index bb8b79648643..c4cc50e58c13 100644 --- a/arch/arm/kernel/hibernate.c +++ b/arch/arm/kernel/hibernate.c @@ -21,8 +21,7 @@ #include <asm/idmap.h> #include <asm/suspend.h> #include <asm/memory.h> - -extern const void __nosave_begin, __nosave_end; +#include <asm/sections.h> int pfn_is_nosave(unsigned long pfn) { diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 4d963fb66e3f..b5b452f90f76 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -113,8 +113,8 @@ static u32 read_wb_reg(int n) GEN_READ_WB_REG_CASES(ARM_OP2_WVR, val); GEN_READ_WB_REG_CASES(ARM_OP2_WCR, val); default: - pr_warning("attempt to read from unknown breakpoint " - "register %d\n", n); + pr_warn("attempt to read from unknown breakpoint register %d\n", + n); } return val; @@ -128,8 +128,8 @@ static void write_wb_reg(int n, u32 val) GEN_WRITE_WB_REG_CASES(ARM_OP2_WVR, val); GEN_WRITE_WB_REG_CASES(ARM_OP2_WCR, val); default: - pr_warning("attempt to write to unknown breakpoint " - "register %d\n", n); + pr_warn("attempt to write to unknown breakpoint register %d\n", + n); } isb(); } @@ -292,7 +292,7 @@ int hw_breakpoint_slots(int type) case TYPE_DATA: return get_num_wrps(); default: - pr_warning("unknown slot type: %d\n", type); + pr_warn("unknown slot type: %d\n", type); return 0; } } @@ -365,7 +365,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) } if (i == max_slots) { - pr_warning("Can't find any breakpoint slot\n"); + pr_warn("Can't find any breakpoint slot\n"); return -EBUSY; } @@ -417,7 +417,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) } if (i == max_slots) { - pr_warning("Can't find any breakpoint slot\n"); + pr_warn("Can't find any breakpoint slot\n"); return; } @@ -894,8 +894,8 @@ static int debug_reg_trap(struct pt_regs *regs, unsigned int instr) { int cpu = smp_processor_id(); - pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n", - instr, cpu); + pr_warn("Debug register access (0x%x) caused undefined instruction on CPU %d\n", + instr, cpu); /* Set the error flag for this CPU and skip the faulting instruction. */ cpumask_set_cpu(cpu, &debug_err_mask); 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 2c4257604513..7c81ec428b9b 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -65,24 +65,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) */ void handle_IRQ(unsigned int irq, struct pt_regs *regs) { - struct pt_regs *old_regs = set_irq_regs(regs); - - irq_enter(); - - /* - * Some hardware gives randomly wrong interrupts. Rather - * than crashing, do something sensible. - */ - if (unlikely(irq >= nr_irqs)) { - if (printk_ratelimit()) - printk(KERN_WARNING "Bad IRQ%u\n", irq); - ack_bad_irq(irq); - } else { - generic_handle_irq(irq); - } - - irq_exit(); - set_irq_regs(old_regs); + __handle_domain_irq(NULL, irq, false, regs); } /* @@ -175,7 +158,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; @@ -205,8 +188,8 @@ void migrate_irqs(void) raw_spin_unlock(&desc->lock); if (affinity_broken && printk_ratelimit()) - pr_warning("IRQ%u no longer affine to CPU%u\n", i, - smp_processor_id()); + pr_warn("IRQ%u no longer affine to CPU%u\n", + i, smp_processor_id()); } local_irq_restore(flags); diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index 2b32978ae905..ad58e565fe98 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -100,7 +100,7 @@ ENTRY(iwmmxt_task_enable) get_thread_info r10 #endif 4: dec_preempt_count r10, r3 - mov pc, r9 @ normal exit from exception + ret r9 @ normal exit from exception concan_save: @@ -144,7 +144,7 @@ concan_dump: wstrd wR15, [r1, #MMX_WR15] 2: teq r0, #0 @ anything to load? - moveq pc, lr @ if not, return + reteq lr @ if not, return concan_load: @@ -177,10 +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 @@ -266,7 +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 @@ -302,7 +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 @@ -324,7 +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) @@ -351,7 +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/kprobes-test.c b/arch/arm/kernel/kprobes-test.c index 08d731294bcd..b206d7790c77 100644 --- a/arch/arm/kernel/kprobes-test.c +++ b/arch/arm/kernel/kprobes-test.c @@ -110,10 +110,13 @@ * * @ TESTCASE_START * bl __kprobes_test_case_start - * @ start of inline data... + * .pushsection .rodata + * "10: * .ascii "mov r0, r7" @ text title for test case * .byte 0 - * .align 2, 0 + * .popsection + * @ start of inline data... + * .word 10b @ pointer to title in .rodata section * * @ TEST_ARG_REG * .byte ARG_TYPE_REG @@ -971,7 +974,7 @@ void __naked __kprobes_test_case_start(void) __asm__ __volatile__ ( "stmdb sp!, {r4-r11} \n\t" "sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" - "bic r0, lr, #1 @ r0 = inline title string \n\t" + "bic r0, lr, #1 @ r0 = inline data \n\t" "mov r1, sp \n\t" "bl kprobes_test_case_start \n\t" "bx r0 \n\t" @@ -1349,15 +1352,14 @@ static unsigned long next_instruction(unsigned long pc) return pc + 4; } -static uintptr_t __used kprobes_test_case_start(const char *title, void *stack) +static uintptr_t __used kprobes_test_case_start(const char **title, void *stack) { struct test_arg *args; struct test_arg_end *end_arg; unsigned long test_code; - args = (struct test_arg *)PTR_ALIGN(title + strlen(title) + 1, 4); - - current_title = title; + current_title = *title++; + args = (struct test_arg *)title; current_args = args; current_stack = stack; diff --git a/arch/arm/kernel/kprobes-test.h b/arch/arm/kernel/kprobes-test.h index eecc90a0fd91..4430990e90e7 100644 --- a/arch/arm/kernel/kprobes-test.h +++ b/arch/arm/kernel/kprobes-test.h @@ -111,11 +111,14 @@ struct test_arg_end { #define TESTCASE_START(title) \ __asm__ __volatile__ ( \ "bl __kprobes_test_case_start \n\t" \ + ".pushsection .rodata \n\t" \ + "10: \n\t" \ /* don't use .asciz here as 'title' may be */ \ /* multiple strings to be concatenated. */ \ ".ascii "#title" \n\t" \ ".byte 0 \n\t" \ - ".align 2, 0 \n\t" + ".popsection \n\t" \ + ".word 10b \n\t" #define TEST_ARG_REG(reg, val) \ ".byte "__stringify(ARG_TYPE_REG)" \n\t" \ diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 45e478157278..6a4dffefd357 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -91,6 +91,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, break; case R_ARM_ABS32: + case R_ARM_TARGET1: *(u32 *)loc += sym->st_value; break; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 4238bcba9d60..266cba46db3e 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -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 af9e35e8836f..eb2c4d55666b 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -76,21 +76,15 @@ static struct pmu_hw_events *cpu_pmu_get_cpu_events(void) static void cpu_pmu_enable_percpu_irq(void *data) { - struct arm_pmu *cpu_pmu = data; - struct platform_device *pmu_device = cpu_pmu->plat_device; - int irq = platform_get_irq(pmu_device, 0); + int irq = *(int *)data; enable_percpu_irq(irq, IRQ_TYPE_NONE); - cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs); } static void cpu_pmu_disable_percpu_irq(void *data) { - struct arm_pmu *cpu_pmu = data; - struct platform_device *pmu_device = cpu_pmu->plat_device; - int irq = platform_get_irq(pmu_device, 0); + int irq = *(int *)data; - cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs); disable_percpu_irq(irq); } @@ -103,7 +97,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) irq = platform_get_irq(pmu_device, 0); if (irq >= 0 && irq_is_percpu(irq)) { - on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1); + on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1); free_percpu_irq(irq, &percpu_pmu); } else { for (i = 0; i < irqs; ++i) { @@ -138,7 +132,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) irq); return err; } - on_each_cpu(cpu_pmu_enable_percpu_irq, cpu_pmu, 1); + on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1); } else { for (i = 0; i < irqs; ++i) { err = 0; @@ -152,8 +146,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) * continue. Otherwise, continue without this interrupt. */ if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) { - pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", - irq, i); + pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n", + irq, i); continue; } @@ -233,14 +227,17 @@ 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"}, {}, }; @@ -250,40 +247,43 @@ 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 1d37568c547a..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; @@ -1592,7 +1055,7 @@ 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; @@ -1602,7 +1065,7 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) { armv7_a12_pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A17"; + cpu_pmu->name = "armv7_cortex_a17"; return 0; } @@ -1823,6 +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 */ @@ -1848,6 +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(); /* @@ -1981,7 +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")) 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/process.c b/arch/arm/kernel/process.c index 81ef686a91ca..fe972a2f3df3 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -114,18 +114,13 @@ void soft_restart(unsigned long addr) BUG(); } -static void null_restart(enum reboot_mode reboot_mode, const char *cmd) -{ -} - /* * Function pointers to optional machine specific functions */ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd) = null_restart; -EXPORT_SYMBOL_GPL(arm_pm_restart); +void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); /* * This is our default idle handler. @@ -230,7 +225,10 @@ void machine_restart(char *cmd) local_irq_disable(); smp_send_stop(); - arm_pm_restart(reboot_mode, cmd); + if (arm_pm_restart) + arm_pm_restart(reboot_mode, cmd); + else + do_kernel_restart(cmd); /* Give a grace period for failure to restart of 1s */ mdelay(1000); @@ -306,7 +304,6 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs * regs) { - printk("\n"); __show_regs(regs); dump_stack(); } @@ -334,6 +331,8 @@ void flush_thread(void) memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); memset(&thread->fpstate, 0, sizeof(union fp_state)); + flush_tls(); + thread_notify(THREAD_NOTIFY_FLUSH, thread); } @@ -472,19 +471,57 @@ int in_gate_area_no_mm(unsigned long addr) const char *arch_vma_name(struct vm_area_struct *vma) { - return is_gate_vma(vma) ? "[vectors]" : - (vma->vm_mm && vma->vm_start == vma->vm_mm->context.sigpage) ? - "[sigpage]" : NULL; + return is_gate_vma(vma) ? "[vectors]" : NULL; +} + +/* If possible, provide a placement hint at a random offset from the + * stack for the signal page. + */ +static unsigned long sigpage_addr(const struct mm_struct *mm, + unsigned int npages) +{ + unsigned long offset; + unsigned long first; + unsigned long last; + unsigned long addr; + unsigned int slots; + + first = PAGE_ALIGN(mm->start_stack); + + last = TASK_SIZE - (npages << PAGE_SHIFT); + + /* No room after stack? */ + if (first > last) + return 0; + + /* Just enough room? */ + if (first == last) + return first; + + slots = ((last - first) >> PAGE_SHIFT) + 1; + + offset = get_random_int() % slots; + + addr = first + (offset << PAGE_SHIFT); + + return addr; } static struct page *signal_page; extern struct page *get_signal_page(void); +static const struct vm_special_mapping sigpage_mapping = { + .name = "[sigpage]", + .pages = &signal_page, +}; + int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; unsigned long addr; - int ret; + unsigned long hint; + int ret = 0; if (!signal_page) signal_page = get_signal_page(); @@ -492,18 +529,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return -ENOMEM; down_write(&mm->mmap_sem); - addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0); + hint = sigpage_addr(mm, 1); + addr = get_unmapped_area(NULL, hint, PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } - ret = install_special_mapping(mm, addr, PAGE_SIZE, + vma = _install_special_mapping(mm, addr, PAGE_SIZE, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, - &signal_page); + &sigpage_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } - if (ret == 0) - mm->context.sigpage = addr; + mm->context.sigpage = addr; up_fail: up_write(&mm->mmap_sem); diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 6af95986fbf7..ef9119f7462e 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -933,8 +933,13 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno) current_thread_info()->syscall = scno; /* Do the secure computing check first; failures should be fast. */ - if (secure_computing(scno) == -1) +#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER + if (secure_computing() == -1) return -1; +#else + /* XXX: remove this once OABI gets fixed */ + secure_computing_strict(scno); +#endif if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); 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/return_address.c b/arch/arm/kernel/return_address.c index fafedd86885d..98ea4b7eb406 100644 --- a/arch/arm/kernel/return_address.c +++ b/arch/arm/kernel/return_address.c @@ -59,15 +59,6 @@ void *return_address(unsigned int level) #else /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */ -#if defined(CONFIG_ARM_UNWIND) -#warning "TODO: return_address should use unwind tables" -#endif - -void *return_address(unsigned int level) -{ - return NULL; -} - #endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) / else */ EXPORT_SYMBOL_GPL(return_address); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 8a16ee5d8a95..c03106378b49 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -133,6 +133,7 @@ struct stack { u32 irq[3]; u32 abt[3]; u32 und[3]; + u32 fiq[3]; } ____cacheline_aligned; #ifndef CONFIG_CPU_V7M @@ -393,19 +394,34 @@ 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; } /* @@ -455,7 +471,10 @@ void notrace cpu_init(void) "msr cpsr_c, %5\n\t" "add r14, %0, %6\n\t" "mov sp, r14\n\t" - "msr cpsr_c, %7" + "msr cpsr_c, %7\n\t" + "add r14, %0, %8\n\t" + "mov sp, r14\n\t" + "msr cpsr_c, %9" : : "r" (stk), PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), @@ -464,6 +483,8 @@ void notrace cpu_init(void) "I" (offsetof(struct stack, abt[0])), PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE), "I" (offsetof(struct stack, und[0])), + PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), + "I" (offsetof(struct stack, fiq[0])), PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE) : "r14"); #endif @@ -609,7 +630,7 @@ static void __init setup_processor(void) #endif erratum_a15_798181_init(); - feat_v6_fixup(); + elf_hwcap_fixup(); cacheid_init(); cpu_init(); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 1b880db2a033..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: diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 7c4fada440f0..13396d3d600e 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 @@ -92,6 +95,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; + if (!smp_ops.smp_boot_secondary) + return -ENOSYS; + /* * We need to tell the secondary core where to find * its stack and the page tables. @@ -110,7 +116,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) /* * Now bring the CPU into our world. */ - ret = boot_secondary(cpu, idle); + ret = smp_ops.smp_boot_secondary(cpu, idle); if (ret == 0) { /* * CPU was successfully started, wait for it @@ -139,13 +145,6 @@ void __init smp_init_cpus(void) smp_ops.smp_init_cpus(); } -int boot_secondary(unsigned int cpu, struct task_struct *idle) -{ - if (smp_ops.smp_boot_secondary) - return smp_ops.smp_boot_secondary(cpu, idle); - return -ENOSYS; -} - int platform_can_cpu_hotplug(void) { #ifdef CONFIG_HOTPLUG_CPU @@ -430,38 +429,15 @@ 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); + if (!__smp_cross_call) + __smp_cross_call = fn; } -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 - -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 +449,12 @@ 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 +481,29 @@ 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 (arch_irq_work_has_interrupt()) + 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 +561,10 @@ 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 +619,9 @@ 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); } @@ -636,7 +646,7 @@ void smp_send_stop(void) udelay(1); if (num_online_cpus() > 1) - pr_warning("SMP: failed to stop secondary CPUs\n"); + pr_warn("SMP: failed to stop secondary CPUs\n"); } /* 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/smp_twd.c b/arch/arm/kernel/smp_twd.c index dfc32130bc44..93090213c71c 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -92,7 +92,7 @@ static int twd_timer_ack(void) static void twd_timer_stop(void) { - struct clock_event_device *clk = __this_cpu_ptr(twd_evt); + struct clock_event_device *clk = raw_cpu_ptr(twd_evt); twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk); disable_percpu_irq(clk->irq); @@ -108,7 +108,7 @@ static void twd_update_frequency(void *new_rate) { twd_timer_rate = *((unsigned long *) new_rate); - clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate); + clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate); } static int twd_rate_change(struct notifier_block *nb, @@ -134,7 +134,7 @@ static struct notifier_block twd_clk_nb = { static int twd_clk_init(void) { - if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) + if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) return clk_notifier_register(twd_clk, &twd_clk_nb); return 0; @@ -153,7 +153,7 @@ static void twd_update_frequency(void *data) { twd_timer_rate = clk_get_rate(twd_clk); - clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate); + clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate); } static int twd_cpufreq_transition(struct notifier_block *nb, @@ -179,7 +179,7 @@ static struct notifier_block twd_cpufreq_nb = { static int twd_cpufreq_init(void) { - if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) + if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) return cpufreq_register_notifier(&twd_cpufreq_nb, CPUFREQ_TRANSITION_NOTIFIER); @@ -269,7 +269,7 @@ static void twd_get_clock(struct device_node *np) */ static void twd_timer_setup(void) { - struct clock_event_device *clk = __this_cpu_ptr(twd_evt); + struct clock_event_device *clk = raw_cpu_ptr(twd_evt); int cpu = smp_processor_id(); /* diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index b1b89882b113..587fdfe1a72c 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> @@ -141,14 +142,6 @@ static int emulate_swpX(unsigned int address, unsigned int *data, while (1) { unsigned long temp; - /* - * Barrier required between accessing protected resource and - * releasing a lock for it. Legacy code might not have done - * this, and we cannot determine that this is not the case - * being emulated, so insert always. - */ - smp_mb(); - if (type == TYPE_SWPB) __user_swpb_asm(*data, address, res, temp); else @@ -161,13 +154,6 @@ static int emulate_swpX(unsigned int address, unsigned int *data, } if (res == 0) { - /* - * Barrier also required between acquiring a lock for a - * protected resource and accessing the resource. Inserted for - * same reason as above. - */ - smp_mb(); - if (type == TYPE_SWPB) swpbcounter++; else @@ -266,6 +252,9 @@ 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/thumbee.c b/arch/arm/kernel/thumbee.c index 7b8403b76666..80f0d69205e7 100644 --- a/arch/arm/kernel/thumbee.c +++ b/arch/arm/kernel/thumbee.c @@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void switch (cmd) { case THREAD_NOTIFY_FLUSH: - thread->thumbee_state = 0; + teehbr_write(0); break; case THREAD_NOTIFY_SWITCH: current_thread_info()->thumbee_state = teehbr_read(); 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 e35d880f9773..89cfdd6e50cb 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -42,7 +42,7 @@ */ static DEFINE_PER_CPU(unsigned long, cpu_scale); -unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) +unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) { return per_cpu(cpu_scale, cpu); } @@ -166,7 +166,7 @@ static void update_cpu_capacity(unsigned int cpu) set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n", - cpu, arch_scale_freq_capacity(NULL, cpu)); + cpu, arch_scale_cpu_capacity(NULL, cpu)); } #else diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index abd2fc067736..0c8b10801d36 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -25,17 +25,20 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/irq.h> #include <linux/atomic.h> #include <asm/cacheflush.h> #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 +187,7 @@ 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); @@ -458,10 +461,29 @@ die_sig: arm_notify_die("Oops - undefined instruction", regs, &info, 0, 6); } -asmlinkage void do_unexp_fiq (struct pt_regs *regs) +/* + * Handle FIQ similarly to NMI on x86 systems. + * + * The runtime environment for NMIs is extremely restrictive + * (NMIs can pre-empt critical sections meaning almost all locking is + * forbidden) meaning this default FIQ handling must only be used in + * circumstances where non-maskability improves robustness, such as + * watchdog or debug logic. + * + * This handler is not appropriate for general purpose use in drivers + * platform code and can be overrideen using set_fiq_handler. + */ +asmlinkage void __exception_irq_entry handle_fiq_as_nmi(struct pt_regs *regs) { - printk("Hmm. Unexpected FIQ received, but trying to continue\n"); - printk("You may have a hardware problem...\n"); + struct pt_regs *old_regs = set_irq_regs(regs); + + nmi_enter(); + + /* nop. FIQ handlers for special arch/arm features can be added here. */ + + nmi_exit(); + + set_irq_regs(old_regs); } /* @@ -579,7 +601,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags) #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE) asmlinkage int arm_syscall(int no, struct pt_regs *regs) { - struct thread_info *thread = current_thread_info(); siginfo_t info; if ((no >> 16) != (__ARM_NR_BASE>> 16)) @@ -630,21 +651,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) return regs->ARM_r0; case NR(set_tls): - thread->tp_value[0] = regs->ARM_r0; - if (tls_emu) - return 0; - if (has_tls_reg) { - asm ("mcr p15, 0, %0, c13, c0, 3" - : : "r" (regs->ARM_r0)); - } else { - /* - * User space must never try to access this directly. - * Expect your app to break eventually if you do so. - * The user helper at 0xffff0fe0 must be used instead. - * (see entry-armv.S for details) - */ - *((unsigned int *)0xffff0ff0) = regs->ARM_r0; - } + set_tls(regs->ARM_r0); return 0; #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG @@ -719,7 +726,7 @@ 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 e67682f02cb2..cbb85c5fabf9 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -157,7 +157,7 @@ static const struct unwind_idx *search_index(unsigned long addr, if (likely(start->addr_offset <= addr_prel31)) return start; else { - pr_warning("unwind: Unknown symbol address %08lx\n", addr); + pr_warn("unwind: Unknown symbol address %08lx\n", addr); return NULL; } } @@ -225,7 +225,7 @@ static unsigned long unwind_get_byte(struct unwind_ctrl_block *ctrl) unsigned long ret; if (ctrl->entries <= 0) { - pr_warning("unwind: Corrupt unwind table\n"); + pr_warn("unwind: Corrupt unwind table\n"); return 0; } @@ -333,8 +333,8 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) insn = (insn << 8) | unwind_get_byte(ctrl); mask = insn & 0x0fff; if (mask == 0) { - pr_warning("unwind: 'Refuse to unwind' instruction %04lx\n", - insn); + pr_warn("unwind: 'Refuse to unwind' instruction %04lx\n", + insn); return -URC_FAILURE; } @@ -357,8 +357,8 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) unsigned long mask = unwind_get_byte(ctrl); if (mask == 0 || mask & 0xf0) { - pr_warning("unwind: Spare encoding %04lx\n", - (insn << 8) | mask); + pr_warn("unwind: Spare encoding %04lx\n", + (insn << 8) | mask); return -URC_FAILURE; } @@ -370,7 +370,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) ctrl->vrs[SP] += 0x204 + (uleb128 << 2); } else { - pr_warning("unwind: Unhandled instruction %02lx\n", insn); + pr_warn("unwind: Unhandled instruction %02lx\n", insn); return -URC_FAILURE; } @@ -403,7 +403,7 @@ int unwind_frame(struct stackframe *frame) idx = unwind_find_idx(frame->pc); if (!idx) { - pr_warning("unwind: Index not found %08lx\n", frame->pc); + pr_warn("unwind: Index not found %08lx\n", frame->pc); return -URC_FAILURE; } @@ -422,8 +422,8 @@ int unwind_frame(struct stackframe *frame) /* only personality routine 0 supported in the index */ ctrl.insn = &idx->insn; else { - pr_warning("unwind: Unsupported personality routine %08lx in the index at %p\n", - idx->insn, idx); + pr_warn("unwind: Unsupported personality routine %08lx in the index at %p\n", + idx->insn, idx); return -URC_FAILURE; } @@ -435,8 +435,8 @@ int unwind_frame(struct stackframe *frame) ctrl.byte = 1; ctrl.entries = 1 + ((*ctrl.insn & 0x00ff0000) >> 16); } else { - pr_warning("unwind: Unsupported personality routine %08lx at %p\n", - *ctrl.insn, ctrl.insn); + pr_warn("unwind: Unsupported personality routine %08lx at %p\n", + *ctrl.insn, ctrl.insn); 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/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 7bcee5c9b604..8e95aa47457a 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -219,8 +219,8 @@ SECTIONS __data_loc = ALIGN(4); /* location in binary */ . = PAGE_OFFSET + TEXT_OFFSET; #else - __init_end = .; . = ALIGN(THREAD_SIZE); + __init_end = .; __data_loc = .; #endif @@ -318,7 +318,6 @@ SECTIONS _end = .; STABS_DEBUG - .comment 0 : { *(.comment) } } /* |