From b1576fec7f4dd4657694fefc97fda4cf28ec68e9 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:04:35 +1100 Subject: powerpc: No need to use dot symbols when branching to a function binutils is smart enough to know that a branch to a function descriptor is actually a branch to the functions text address. Alan tells me that binutils has been doing this for 9 years. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/cpu_setup_fsl_booke.S | 28 +++--- arch/powerpc/kernel/entry_64.S | 86 +++++++++--------- arch/powerpc/kernel/exceptions-64e.S | 128 +++++++++++++-------------- arch/powerpc/kernel/exceptions-64s.S | 140 +++++++++++++++--------------- arch/powerpc/kernel/head_64.S | 66 +++++++------- arch/powerpc/kernel/idle_book3e.S | 2 +- arch/powerpc/kernel/idle_power4.S | 2 +- arch/powerpc/kernel/idle_power7.S | 4 +- arch/powerpc/kernel/misc_64.S | 10 +-- 9 files changed, 233 insertions(+), 233 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index cc2d8962e090..4f1393d20079 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -94,12 +94,12 @@ _GLOBAL(setup_altivec_idle) _GLOBAL(__setup_cpu_e6500) mflr r6 #ifdef CONFIG_PPC64 - bl .setup_altivec_ivors + bl setup_altivec_ivors /* Touch IVOR42 only if the CPU supports E.HV category */ mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_lrat_ivor + bl setup_lrat_ivor 1: #endif bl setup_pw20_idle @@ -164,15 +164,15 @@ _GLOBAL(__setup_cpu_e5500) #ifdef CONFIG_PPC_BOOK3E_64 _GLOBAL(__restore_cpu_e6500) mflr r5 - bl .setup_altivec_ivors + bl setup_altivec_ivors /* Touch IVOR42 only if the CPU supports E.HV category */ mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_lrat_ivor + bl setup_lrat_ivor 1: - bl .setup_pw20_idle - bl .setup_altivec_idle + bl setup_pw20_idle + bl setup_altivec_idle bl __restore_cpu_e5500 mtlr r5 blr @@ -181,9 +181,9 @@ _GLOBAL(__restore_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -192,7 +192,7 @@ _GLOBAL(__restore_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors 1: mtlr r4 blr @@ -201,9 +201,9 @@ _GLOBAL(__setup_cpu_e5500) mflr r5 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -212,7 +212,7 @@ _GLOBAL(__setup_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors b 2f 1: ld r10,CPU_SPEC_FEATURES(r4) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 662c6dd98072..b629198b072c 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -106,7 +106,7 @@ BEGIN_FW_FTR_SECTION LDX_BE r10,0,r10 /* get log write index */ cmpd cr1,r11,r10 beq+ cr1,33f - bl .accumulate_stolen_time + bl accumulate_stolen_time REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -143,7 +143,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) std r10,SOFTE(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall + bl do_show_syscall REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -181,7 +181,7 @@ system_call: /* label this so stack traces look sane */ syscall_exit: std r3,RESULT(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall_exit + bl do_show_syscall_exit ld r3,RESULT(r1) #endif CURRENT_THREAD_INFO(r12, r1) @@ -248,9 +248,9 @@ syscall_error: /* Traced system call support */ syscall_dotrace: - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_enter + bl do_syscall_trace_enter /* * Restore argument registers possibly just changed. * We use the return value of do_syscall_trace_enter @@ -308,7 +308,7 @@ syscall_exit_work: 4: /* Anything else left to do? */ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) - beq .ret_from_except_lite + beq ret_from_except_lite /* Re-enable interrupts */ #ifdef CONFIG_PPC_BOOK3E @@ -319,10 +319,10 @@ syscall_exit_work: mtmsrd r10,1 #endif /* CONFIG_PPC_BOOK3E */ - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_leave - b .ret_from_except + bl do_syscall_trace_leave + b ret_from_except /* Save non-volatile GPRs, if not already saved. */ _GLOBAL(save_nvgprs) @@ -345,38 +345,38 @@ _GLOBAL(save_nvgprs) */ _GLOBAL(ppc_fork) - bl .save_nvgprs - bl .sys_fork + bl save_nvgprs + bl sys_fork b syscall_exit _GLOBAL(ppc_vfork) - bl .save_nvgprs - bl .sys_vfork + bl save_nvgprs + bl sys_vfork b syscall_exit _GLOBAL(ppc_clone) - bl .save_nvgprs - bl .sys_clone + bl save_nvgprs + bl sys_clone b syscall_exit _GLOBAL(ppc32_swapcontext) - bl .save_nvgprs - bl .compat_sys_swapcontext + bl save_nvgprs + bl compat_sys_swapcontext b syscall_exit _GLOBAL(ppc64_swapcontext) - bl .save_nvgprs - bl .sys_swapcontext + bl save_nvgprs + bl sys_swapcontext b syscall_exit _GLOBAL(ret_from_fork) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) li r3,0 b syscall_exit _GLOBAL(ret_from_kernel_thread) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) ld r14, 0(r14) mtlr r14 @@ -611,7 +611,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR) _GLOBAL(ret_from_except) ld r11,_TRAP(r1) andi. r0,r11,1 - bne .ret_from_except_lite + bne ret_from_except_lite REST_NVGPRS(r1) _GLOBAL(ret_from_except_lite) @@ -661,23 +661,23 @@ _GLOBAL(ret_from_except_lite) #endif 1: andi. r0,r4,_TIF_NEED_RESCHED beq 2f - bl .restore_interrupts + bl restore_interrupts SCHEDULE_USER - b .ret_from_except_lite + b ret_from_except_lite 2: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM bne 3f /* only restore TM if nothing else to do */ addi r3,r1,STACK_FRAME_OVERHEAD - bl .restore_tm_state + bl restore_tm_state b restore 3: #endif - bl .save_nvgprs - bl .restore_interrupts + bl save_nvgprs + bl restore_interrupts addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except + bl do_notify_resume + b ret_from_except resume_kernel: /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ @@ -730,7 +730,7 @@ resume_kernel: * sure we are soft-disabled first and reconcile irq state. */ RECONCILE_IRQ_STATE(r3,r4) -1: bl .preempt_schedule_irq +1: bl preempt_schedule_irq /* Re-test flags and eventually loop */ CURRENT_THREAD_INFO(r9, r1) @@ -792,7 +792,7 @@ restore_no_replay: */ do_restore: #ifdef CONFIG_PPC_BOOK3E - b .exception_return_book3e + b exception_return_book3e #else /* * Clear the reservation. If we know the CPU tracks the address of @@ -907,7 +907,7 @@ restore_check_irq_replay: * * Still, this might be useful for things like hash_page */ - bl .__check_irq_replay + bl __check_irq_replay cmpwi cr0,r3,0 beq restore_no_replay @@ -928,13 +928,13 @@ restore_check_irq_replay: cmpwi cr0,r3,0x500 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .do_IRQ - b .ret_from_except + bl do_IRQ + b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .timer_interrupt - b .ret_from_except + bl timer_interrupt + b ret_from_except #ifdef CONFIG_PPC_DOORBELL 1: #ifdef CONFIG_PPC_BOOK3E @@ -948,14 +948,14 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .doorbell_exception - b .ret_from_except + bl doorbell_exception + b ret_from_except #endif /* CONFIG_PPC_DOORBELL */ -1: b .ret_from_except /* What else to do here ? */ +1: b ret_from_except /* What else to do here ? */ unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b unrecov_restore #ifdef CONFIG_PPC_RTAS @@ -1238,7 +1238,7 @@ _GLOBAL(ftrace_graph_caller) ld r11, 112(r1) addi r3, r11, 16 - bl .prepare_ftrace_return + bl prepare_ftrace_return nop ld r0, 128(r1) @@ -1254,7 +1254,7 @@ _GLOBAL(return_to_handler) mr r31, r1 stdu r1, -112(r1) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ @@ -1284,7 +1284,7 @@ _GLOBAL(mod_return_to_handler) */ ld r2, PACATOC(r13) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index c1bee3ce9d1f..5e37338c2e5c 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -499,7 +499,7 @@ exc_##n##_bad_stack: \ CHECK_NAPPING(); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ - b .ret_from_except_lite; + b ret_from_except_lite; /* This value is used to mark exception frames on the stack. */ .section ".toc","aw" @@ -550,11 +550,11 @@ interrupt_end_book3e: CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x100) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* Machine Check Interrupt */ @@ -562,11 +562,11 @@ interrupt_end_book3e: MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_MC(0x000) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception + bl machine_check_exception b ret_from_mc_except /* Data Storage Interrupt */ @@ -612,9 +612,9 @@ interrupt_end_book3e: std r14,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) - bl .save_nvgprs - bl .program_check_exception - b .ret_from_except + bl save_nvgprs + bl program_check_exception + b ret_from_except /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); @@ -625,13 +625,13 @@ interrupt_end_book3e: ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_fpu + bl load_up_fpu b fast_exception_return 1: INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception - b .ret_from_except + bl kernel_fp_unavailable_exception + b ret_from_except /* Altivec Unavailable Interrupt */ START_EXCEPTION(altivec_unavailable); @@ -644,16 +644,16 @@ BEGIN_FTR_SECTION ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_altivec + bl load_up_altivec b fast_exception_return 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except /* AltiVec Assist */ START_EXCEPTION(altivec_assist); @@ -662,16 +662,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x220) INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION - bl .altivec_assist_exception + bl altivec_assist_exception END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #else - bl .unknown_exception + bl unknown_exception #endif - b .ret_from_except + b ret_from_except /* Decrementer Interrupt */ @@ -687,14 +687,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x9f0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_BOOKE_WDT - bl .WatchdogException + bl WatchdogException #else - bl .unknown_exception + bl unknown_exception #endif b ret_from_crit_except @@ -712,10 +712,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0xf20) INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); @@ -774,9 +774,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mr r4,r14 ld r14,PACA_EXCRIT+EX_R14(r13) ld r15,PACA_EXCRIT+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except kernel_dbg_exc: b . /* NYI */ @@ -839,9 +839,9 @@ kernel_dbg_exc: mr r4,r14 ld r14,PACA_EXDBG+EX_R14(r13) ld r15,PACA_EXDBG+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except START_EXCEPTION(perfmon); NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, @@ -850,8 +850,8 @@ kernel_dbg_exc: INTS_DISABLE CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD - bl .performance_monitor_exception - b .ret_from_except_lite + bl performance_monitor_exception + b ret_from_except_lite /* Doorbell interrupt */ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, @@ -862,11 +862,11 @@ kernel_dbg_exc: CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x2a0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* @@ -878,21 +878,21 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x2c0) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x2e0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* Hypervisor call */ @@ -901,10 +901,10 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x310) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); @@ -912,10 +912,10 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x320) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* LRAT Error interrupt */ START_EXCEPTION(lrat_error); @@ -1014,16 +1014,16 @@ storage_fault_common: mr r5,r15 ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .do_page_fault + bl do_page_fault cmpdi r3,0 bne- 1f - b .ret_from_except_lite -1: bl .save_nvgprs + b ret_from_except_lite +1: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* * Alignment exception doesn't fit entirely in the 0x100 bytes so it @@ -1035,10 +1035,10 @@ alignment_more: addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except /* * We branch here from entry_64.S for the last stage of the exception @@ -1172,7 +1172,7 @@ bad_stack_book3e: std r12,0(r11) ld r2,PACATOC(r13) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1521,13 +1521,13 @@ _GLOBAL(start_initialization_book3e) * and always use AS 0, so we just set it up to match our link * address and never use 0 based addresses. */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* Init global core bits */ - bl .init_core_book3e + bl init_core_book3e /* Init per-thread bits */ - bl .init_thread_book3e + bl init_thread_book3e /* Return to common init code */ tovirt(r28,r28) @@ -1548,7 +1548,7 @@ _GLOBAL(start_initialization_book3e) */ _GLOBAL(book3e_secondary_core_init_tlb_set) li r4,1 - b .generic_secondary_smp_init + b generic_secondary_smp_init _GLOBAL(book3e_secondary_core_init) mflr r28 @@ -1558,18 +1558,18 @@ _GLOBAL(book3e_secondary_core_init) bne 2f /* Setup TLB for this core */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* We can return from the above running at a different * address, so recalculate r2 (TOC) */ - bl .relative_toc + bl relative_toc /* Init global core bits */ -2: bl .init_core_book3e +2: bl init_core_book3e /* Init per-thread bits */ -3: bl .init_thread_book3e +3: bl init_thread_book3e /* Return to common init code at proper virtual address. * diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3afd3915921a..28391e048120 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -132,12 +132,12 @@ BEGIN_FTR_SECTION #endif beq cr1,2f - b .power7_wakeup_noloss -2: b .power7_wakeup_loss + b power7_wakeup_noloss +2: b power7_wakeup_loss /* Fast Sleep wakeup on PowerNV */ 8: GET_PACA(r13) - b .power7_wakeup_tb_loss + b power7_wakeup_tb_loss 9: END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) @@ -211,7 +211,7 @@ data_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* * We can't just use a direct branch to .slb_miss_realmode @@ -243,7 +243,7 @@ instruction_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) @@ -829,7 +829,7 @@ data_access_slb_relon_pSeries: mfspr r3,SPRN_DAR mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* * We can't just use a direct branch to .slb_miss_realmode @@ -854,7 +854,7 @@ instruction_access_slb_relon_pSeries: mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) @@ -966,7 +966,7 @@ system_call_entry: b system_call_common ppc64_runlatch_on_trampoline: - b .__ppc64_runlatch_on + b __ppc64_runlatch_on /* * Here we have detected that the kernel stack pointer is bad. @@ -1025,7 +1025,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) std r12,RESULT(r1) std r11,STACK_FRAME_OVERHEAD-16(r1) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1046,7 +1046,7 @@ data_access_common: ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) li r5,0x300 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ .align 7 .globl h_data_storage_common @@ -1056,11 +1056,11 @@ h_data_storage_common: mfspr r10,SPRN_HDSISR stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except .align 7 .globl instruction_access_common @@ -1071,7 +1071,7 @@ instruction_access_common: ld r3,_NIP(r1) andis. r4,r12,0x5820 li r5,0x400 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) @@ -1088,7 +1088,7 @@ slb_miss_user_common: stw r9,PACA_EXGEN+EX_CCR(r13) std r10,PACA_EXGEN+EX_LR(r13) std r11,PACA_EXGEN+EX_SRR0(r13) - bl .slb_allocate_user + bl slb_allocate_user ld r10,PACA_EXGEN+EX_LR(r13) ld r3,PACA_EXGEN+EX_R3(r13) @@ -1131,9 +1131,9 @@ slb_miss_fault: unrecov_user_slb: EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b #endif /* __DISABLED__ */ @@ -1158,10 +1158,10 @@ machine_check_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except + bl machine_check_exception + b ret_from_except .align 7 .globl alignment_common @@ -1175,31 +1175,31 @@ alignment_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except .align 7 .globl program_check_common program_check_common: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .program_check_exception - b .ret_from_except + bl program_check_exception + b ret_from_except .align 7 .globl fp_unavailable_common fp_unavailable_common: EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) bne 1f /* if from user, just load it up */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception + bl kernel_fp_unavailable_exception BUG_OPCODE 1: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -1211,15 +1211,15 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - bl .load_up_fpu + bl load_up_fpu b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .fp_unavailable_tm - b .ret_from_except + bl fp_unavailable_tm + b ret_from_except #endif .align 7 .globl altivec_unavailable_common @@ -1237,24 +1237,24 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - bl .load_up_altivec + bl load_up_altivec b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_tm - b .ret_from_except + bl altivec_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except .align 7 .globl vsx_unavailable_common @@ -1272,23 +1272,23 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - b .load_up_vsx + b load_up_vsx #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_tm - b .ret_from_except + bl vsx_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_exception - b .ret_from_except + bl vsx_unavailable_exception + b ret_from_except STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception) STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception) @@ -1386,9 +1386,9 @@ _GLOBAL(opal_mc_secondary_handler) machine_check_handle_early: std r0,GPR0(r1) /* Save r0 */ EXCEPTION_PROLOG_COMMON_3(0x200) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_early + bl machine_check_early ld r12,_MSR(r1) #ifdef CONFIG_PPC_P7_NAP /* @@ -1408,11 +1408,11 @@ machine_check_handle_early: /* Supervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) -3: bl .machine_check_queue_event +3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - b .power7_enter_nap_mode + b power7_enter_nap_mode 4: #endif /* @@ -1444,7 +1444,7 @@ machine_check_handle_early: andi. r11,r12,MSR_RI bne 2f 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b 2: /* @@ -1452,7 +1452,7 @@ machine_check_handle_early: * Queue up the MCE event so that we can log it later, while * returning from kernel or opal call. */ - bl .machine_check_queue_event + bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP rfid 9: @@ -1477,7 +1477,7 @@ _GLOBAL(slb_miss_realmode) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - bl .slb_allocate_realmode + bl slb_allocate_realmode /* All done -- return from exception. */ @@ -1517,9 +1517,9 @@ _GLOBAL(slb_miss_realmode) unrecov_slb: EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b @@ -1573,7 +1573,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) * * at return r3 = 0 for success, 1 for page fault, negative for error */ - bl .hash_page /* build HPTE if possible */ + bl hash_page /* build HPTE if possible */ cmpdi r3,0 /* see if hash_page succeeded */ /* Success */ @@ -1587,35 +1587,35 @@ handle_page_fault: 11: ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_page_fault + bl do_page_fault cmpdi r3,0 beq+ 12f - bl .save_nvgprs + bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD lwz r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* We have a data breakpoint exception - handle it */ handle_dabr_fault: - bl .save_nvgprs + bl save_nvgprs ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_break -12: b .ret_from_except_lite + bl do_break +12: b ret_from_except_lite /* We have a page fault that hash_page could handle but HV refused * the PTE insertion */ -13: bl .save_nvgprs +13: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .low_hash_fault - b .ret_from_except + bl low_hash_fault + b ret_from_except /* * We come here as a result of a DSI at a point where we don't want @@ -1624,16 +1624,16 @@ handle_dabr_fault: * were soft-disabled. We want to invoke the exception handler for * the access, or panic if there isn't a handler. */ -77: bl .save_nvgprs +77: bl save_nvgprs mr r4,r3 addi r3,r1,STACK_FRAME_OVERHEAD li r5,SIGSEGV - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* here we have a segment miss */ do_ste_alloc: - bl .ste_allocate /* try to insert stab entry */ + bl ste_allocate /* try to insert stab entry */ cmpdi r3,0 bne- handle_page_fault b fast_exception_return diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b7363bd42452..afcfd631bf7f 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -70,7 +70,7 @@ _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION FIXUP_ENDIAN - b .__start_initialization_multiplatform + b __start_initialization_multiplatform END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ @@ -186,16 +186,16 @@ _GLOBAL(generic_secondary_thread_init) mr r24,r3 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 - bl .book3e_secondary_thread_init + bl book3e_secondary_thread_init #endif b generic_secondary_common_init @@ -214,17 +214,17 @@ _GLOBAL(generic_secondary_smp_init) mr r25,r4 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 mr r4,r25 - bl .book3e_secondary_core_init + bl book3e_secondary_core_init #endif generic_secondary_common_init: @@ -236,7 +236,7 @@ generic_secondary_common_init: ld r13,0(r13) /* Get base vaddr of paca array */ #ifndef CONFIG_SMP addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ - b .kexec_wait /* wait for next kernel if !SMP */ + b kexec_wait /* wait for next kernel if !SMP */ #else LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ @@ -250,7 +250,7 @@ generic_secondary_common_init: blt 1b mr r3,r24 /* not found, copy phys to r3 */ - b .kexec_wait /* next kernel might do better */ + b kexec_wait /* next kernel might do better */ 2: SET_PACA(r13) #ifdef CONFIG_PPC_BOOK3E @@ -326,10 +326,10 @@ _STATIC(__mmu_off) */ _GLOBAL(__start_initialization_multiplatform) /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode + bl enable_64b_mode /* Get TOC pointer (current runtime address) */ - bl .relative_toc + bl relative_toc /* find out where we are now */ bcl 20,31,$+4 @@ -342,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform) */ cmpldi cr0,r5,0 beq 1f - b .__boot_from_prom /* yes -> prom */ + b __boot_from_prom /* yes -> prom */ 1: /* Save parameters */ mr r31,r3 @@ -354,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform) #endif #ifdef CONFIG_PPC_BOOK3E - bl .start_initialization_book3e - b .__after_prom_start + bl start_initialization_book3e + b __after_prom_start #else /* Setup some critical 970 SPRs before switching MMU off */ mfspr r0,SPRN_PVR @@ -368,12 +368,12 @@ _GLOBAL(__start_initialization_multiplatform) beq 1f cmpwi r0,0x45 /* 970GX */ bne 2f -1: bl .__cpu_preinit_ppc970 +1: bl __cpu_preinit_ppc970 2: /* Switch off MMU if not already off */ - bl .__mmu_off - b .__after_prom_start + bl __mmu_off + b __after_prom_start #endif /* CONFIG_PPC_BOOK3E */ _INIT_STATIC(__boot_from_prom) @@ -395,7 +395,7 @@ _INIT_STATIC(__boot_from_prom) #ifdef CONFIG_RELOCATABLE /* Relocate code for where we are now */ mr r3,r26 - bl .relocate + bl relocate #endif /* Restore parameters */ @@ -407,7 +407,7 @@ _INIT_STATIC(__boot_from_prom) /* Do all of the interaction with OF client interface */ mr r8,r26 - bl .prom_init + bl prom_init #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */ /* We never return. We also hit that trap if trying to boot @@ -424,7 +424,7 @@ _STATIC(__after_prom_start) bne 1f add r25,r25,r26 1: mr r3,r25 - bl .relocate + bl relocate #endif /* @@ -464,7 +464,7 @@ _STATIC(__after_prom_start) lis r5,(copy_to_here - _stext)@ha addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ - bl .copy_and_flush /* copy the first n bytes */ + bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ @@ -478,9 +478,9 @@ p_end: .llong _end - _stext 4: /* Now copy the rest of the kernel up to _end */ addis r5,r26,(p_end - _stext)@ha ld r5,(p_end - _stext)@l(r5) /* get _end */ -5: bl .copy_and_flush /* copy the rest */ +5: bl copy_and_flush /* copy the rest */ -9: b .start_here_multiplatform +9: b start_here_multiplatform /* * Copy routine used to copy the kernel to start at physical address 0 @@ -544,7 +544,7 @@ __secondary_start_pmac_0: _GLOBAL(pmac_secondary_start) /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode li r0,0 mfspr r3,SPRN_HID4 @@ -556,11 +556,11 @@ _GLOBAL(pmac_secondary_start) slbia /* get TOC pointer (real address) */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_ppc970 + bl __restore_cpu_ppc970 /* pSeries do that early though I don't think we really need it */ mfmsr r3 @@ -619,7 +619,7 @@ __secondary_start: std r14,PACAKSAVE(r13) /* Do early setup for that CPU (stab, slb, hash table pointer) */ - bl .early_setup_secondary + bl early_setup_secondary /* * setup the new stack pointer, but *don't* use this until @@ -656,7 +656,7 @@ _GLOBAL(start_secondary_prolog) ld r2,PACATOC(r13) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . /* * Reset stack pointer and call start_secondary @@ -667,7 +667,7 @@ _GLOBAL(start_secondary_resume) ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . #endif @@ -717,7 +717,7 @@ p_toc: .llong __toc_start + 0x8000 - 0b */ _INIT_STATIC(start_here_multiplatform) /* set up the TOC */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Clear out the BSS. It may have been done in prom_init, @@ -776,7 +776,7 @@ _INIT_STATIC(start_here_multiplatform) /* Restore parameters passed from prom_init/kexec */ mr r3,r31 - bl .early_setup /* also sets r13 and SPRG_PACA */ + bl early_setup /* also sets r13 and SPRG_PACA */ LOAD_REG_ADDR(r3, .start_here_common) ld r4,PACAKMSR(r13) @@ -794,7 +794,7 @@ _INIT_GLOBAL(start_here_common) ld r2,PACATOC(r13) /* Do more system initializations in virtual mode */ - bl .setup_system + bl setup_system /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) @@ -805,7 +805,7 @@ _INIT_GLOBAL(start_here_common) stb r0,PACAIRQHAPPENED(r13) /* Generic kernel entry */ - bl .start_kernel + bl start_kernel /* Not reached */ BUG_OPCODE diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index bfb73cc209ce..48c21acef915 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -43,7 +43,7 @@ _GLOBAL(\name) */ #ifdef CONFIG_TRACE_IRQFLAGS stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 #endif li r0,1 diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index e3edaa189911..f57a19348bdd 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) mflr r0 std r0,16(r1) stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index c3ab86975614..dca6e16c2436 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -58,7 +58,7 @@ _GLOBAL(power7_powersave_common) /* Make sure FPU, VSX etc... are flushed as we may lose * state when going to nap mode */ - bl .discard_lazy_cpu_state + bl discard_lazy_cpu_state #endif /* CONFIG_SMP */ /* Hard disable interrupts */ @@ -168,7 +168,7 @@ _GLOBAL(power7_wakeup_loss) _GLOBAL(power7_wakeup_noloss) lbz r0,PACA_NAPSTATELOST(r13) cmpwi r0,0 - bne .power7_wakeup_loss + bne power7_wakeup_loss ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 3d0249599d52..b39cf4afad4b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -34,7 +34,7 @@ _GLOBAL(call_do_softirq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3) mr r1,r3 - bl .__do_softirq + bl __do_softirq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -45,7 +45,7 @@ _GLOBAL(call_do_irq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 - bl .__do_irq + bl __do_irq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -506,7 +506,7 @@ _GLOBAL(kexec_smp_wait) stb r4,PACAKEXECSTATE(r13) SYNC - b .kexec_wait + b kexec_wait /* * switch to real mode (turn mmu off) @@ -576,7 +576,7 @@ _GLOBAL(kexec_sequence) /* copy dest pages, flush whole dest image */ mr r3,r29 - bl .kexec_copy_flush /* (image) */ + bl kexec_copy_flush /* (image) */ /* turn off mmu */ bl real_mode @@ -586,7 +586,7 @@ _GLOBAL(kexec_sequence) mr r4,r30 /* start, aka phys mem offset */ li r5,0x100 li r6,0 - bl .copy_and_flush /* (dest, src, copy limit, start offset) */ + bl copy_and_flush /* (dest, src, copy limit, start offset) */ 1: /* assume normal blr return */ /* release other cpus to the new kernel secondary start at 0x60 */ -- cgit v1.2.3 From ad0289e4acf2bd6989e745cff3b4f0781a919e30 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:04:52 +1100 Subject: powerpc: Remove superflous function descriptors in assembly only code We have a number of places where we load the text address of a local function and indirectly branch to it in assembly. Since it is an indirect branch binutils will not know to use the function text address, so that trick wont work. There is no need for these functions to have a function descriptor so we can replace it with a label and remove the dot symbol. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/entry_64.S | 10 +++++----- arch/powerpc/kernel/exceptions-64s.S | 18 +++++++++--------- arch/powerpc/kernel/head_64.S | 9 +++++---- arch/powerpc/platforms/powernv/opal-wrappers.S | 4 ++-- 4 files changed, 21 insertions(+), 20 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b629198b072c..2d92eeb08b76 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1021,7 +1021,7 @@ _GLOBAL(enter_rtas) std r6,PACASAVEDMSR(r13) /* Setup our real return addr */ - LOAD_REG_ADDR(r4,.rtas_return_loc) + LOAD_REG_ADDR(r4,rtas_return_loc) clrldi r4,r4,2 /* convert to realmode address */ mtlr r4 @@ -1045,7 +1045,7 @@ _GLOBAL(enter_rtas) rfid b . /* prevent speculative execution */ -_STATIC(rtas_return_loc) +rtas_return_loc: FIXUP_ENDIAN /* relocation is off at this point */ @@ -1054,7 +1054,7 @@ _STATIC(rtas_return_loc) bcl 20,31,$+4 0: mflr r3 - ld r3,(1f-0b)(r3) /* get &.rtas_restore_regs */ + ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ mfmsr r6 li r0,MSR_RI @@ -1071,9 +1071,9 @@ _STATIC(rtas_return_loc) b . /* prevent speculative execution */ .align 3 -1: .llong .rtas_restore_regs +1: .llong rtas_restore_regs -_STATIC(rtas_restore_regs) +rtas_restore_regs: /* relocation is on at this point */ REST_GPR(2, r1) /* Restore the TOC */ REST_GPR(13, r1) /* Restore paca */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 28391e048120..f2f9d6144ae1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -214,13 +214,13 @@ data_access_slb_pSeries: b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -247,7 +247,7 @@ instruction_access_slb_pSeries: #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -524,7 +524,7 @@ do_stab_bolted_pSeries: std r12,PACA_EXSLB+EX_R12(r13) GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) + EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -832,13 +832,13 @@ data_access_slb_relon_pSeries: b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -858,7 +858,7 @@ instruction_access_slb_relon_pSeries: #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -1468,7 +1468,7 @@ machine_check_handle_early: * r3 is saved in paca->slb_r3 * We assume we aren't going to take any exceptions during this procedure. */ -_GLOBAL(slb_miss_realmode) +slb_miss_realmode: mflr r10 #ifdef CONFIG_RELOCATABLE mtctr r11 @@ -1646,7 +1646,7 @@ do_ste_alloc: * We assume (DAR >> 60) == 0xc. */ .align 7 -_GLOBAL(do_stab_bolted) +do_stab_bolted: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ mfspr r11,SPRN_DAR /* ea */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index afcfd631bf7f..8d7c868e5a43 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -639,7 +639,7 @@ __secondary_start: stb r0,PACAIRQHAPPENED(r13) /* enable MMU and jump to start_secondary */ - LOAD_REG_ADDR(r3, .start_secondary_prolog) + LOAD_REG_ADDR(r3, start_secondary_prolog) LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) mtspr SPRN_SRR0,r3 @@ -652,7 +652,7 @@ __secondary_start: * zero the stack back-chain pointer and get the TOC virtual address * before going into C code. */ -_GLOBAL(start_secondary_prolog) +start_secondary_prolog: ld r2,PACATOC(r13) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ @@ -778,7 +778,7 @@ _INIT_STATIC(start_here_multiplatform) mr r3,r31 bl early_setup /* also sets r13 and SPRG_PACA */ - LOAD_REG_ADDR(r3, .start_here_common) + LOAD_REG_ADDR(r3, start_here_common) ld r4,PACAKMSR(r13) mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 @@ -786,7 +786,8 @@ _INIT_STATIC(start_here_multiplatform) b . /* prevent speculative execution */ /* This is where all platforms converge execution */ -_INIT_GLOBAL(start_here_common) + +start_here_common: /* relocation is on at this point */ std r1,PACAKSAVE(r13) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index f531ffe35b3e..b5ebc545a373 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -32,7 +32,7 @@ std r12,PACASAVEDMSR(r13); \ andc r12,r12,r0; \ mtmsrd r12,1; \ - LOAD_REG_ADDR(r0,.opal_return); \ + LOAD_REG_ADDR(r0,opal_return); \ mtlr r0; \ li r0,MSR_DR|MSR_IR|MSR_LE;\ andc r12,r12,r0; \ @@ -44,7 +44,7 @@ mtspr SPRN_HSRR0,r12; \ hrfid -_STATIC(opal_return) +opal_return: /* * Fixup endian on OPAL return... we should be able to simplify * this by instead converting the below trampoline to a set of -- cgit v1.2.3 From c857c43b34ecbfd686d860d4e85281d3750e3b47 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:05:53 +1100 Subject: powerpc: Don't use a function descriptor for system call table There is no need to create a function descriptor for the system call table. By using one we force the system call table into the text section and it really belongs in the rodata section. This also removes another use of dot symbols. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/entry_64.S | 6 +++--- arch/powerpc/kernel/systbl.S | 6 +++++- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 2d92eeb08b76..2662f02ba6cf 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -39,8 +39,8 @@ * System calls. */ .section ".toc","aw" -.SYS_CALL_TABLE: - .tc .sys_call_table[TC],.sys_call_table +SYS_CALL_TABLE: + .tc sys_call_table[TC],sys_call_table /* This value is used to mark exception frames on the stack. */ exception_marker: @@ -162,7 +162,7 @@ system_call: /* label this so stack traces look sane */ * Need to vector to 32 Bit or default sys_call_table here, * based on caller's run-mode / personality. */ - ld r11,.SYS_CALL_TABLE@toc(2) + ld r11,SYS_CALL_TABLE@toc(2) andi. r10,r10,_TIF_32BIT beq 15f addi r11,r11,8 /* use 32-bit syscall entries */ diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 93219c34af32..75822f97bfea 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -36,6 +36,8 @@ #define PPC_SYS_SPU(func) PPC_SYS(func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) +.section .rodata,"a" + #ifdef CONFIG_PPC64 #define sys_sigpending sys_ni_syscall #define sys_old_getrlimit sys_ni_syscall @@ -43,5 +45,7 @@ .p2align 3 #endif -_GLOBAL(sys_call_table) +.globl sys_call_table +sys_call_table: + #include -- cgit v1.2.3 From 6a3bab90cf78bc579638525cb76ac240f8253803 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:06:11 +1100 Subject: powerpc: Remove some unnecessary uses of _GLOBAL() and _STATIC() There is no need to create a function descriptor for functions called locally out of assembly. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/exceptions-64e.S | 4 ++-- arch/powerpc/kernel/exceptions-64s.S | 2 +- arch/powerpc/kernel/head_64.S | 12 ++++++------ 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 5e37338c2e5c..c8ac8a09b0f8 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -1596,14 +1596,14 @@ _GLOBAL(book3e_secondary_thread_init) mflr r28 b 3b -_STATIC(init_core_book3e) +init_core_book3e: /* Establish the interrupt vector base */ LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e) mtspr SPRN_IVPR,r3 sync blr -_STATIC(init_thread_book3e) +init_thread_book3e: lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h mtspr SPRN_EPCR,r3 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f2f9d6144ae1..a0741b65f658 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1536,7 +1536,7 @@ power4_fixup_nap: * Hash table stuff */ .align 7 -_STATIC(do_hash_page) +do_hash_page: std r3,_DAR(r1) std r4,_DSISR(r1) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 8d7c868e5a43..82841242dc26 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -299,7 +299,7 @@ generic_secondary_common_init: * Assumes we're mapped EA == RA if the MMU is on. */ #ifdef CONFIG_PPC_BOOK3S -_STATIC(__mmu_off) +__mmu_off: mfmsr r3 andi. r0,r3,MSR_IR|MSR_DR beqlr @@ -324,7 +324,7 @@ _STATIC(__mmu_off) * DT block, r4 is a physical pointer to the kernel itself * */ -_GLOBAL(__start_initialization_multiplatform) +__start_initialization_multiplatform: /* Make sure we are running in 64 bits mode */ bl enable_64b_mode @@ -376,7 +376,7 @@ _GLOBAL(__start_initialization_multiplatform) b __after_prom_start #endif /* CONFIG_PPC_BOOK3E */ -_INIT_STATIC(__boot_from_prom) +__boot_from_prom: #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE /* Save parameters */ mr r31,r3 @@ -414,7 +414,7 @@ _INIT_STATIC(__boot_from_prom) * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */ trap -_STATIC(__after_prom_start) +__after_prom_start: #ifdef CONFIG_RELOCATABLE /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ @@ -674,7 +674,7 @@ _GLOBAL(start_secondary_resume) /* * This subroutine clobbers r11 and r12 */ -_GLOBAL(enable_64b_mode) +enable_64b_mode: mfmsr r11 /* grab the current MSR */ #ifdef CONFIG_PPC_BOOK3E oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ @@ -715,7 +715,7 @@ p_toc: .llong __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ -_INIT_STATIC(start_here_multiplatform) +start_here_multiplatform: /* set up the TOC */ bl relative_toc tovirt(r2,r2) -- cgit v1.2.3 From 354255014a9042b9204e5bed22704110326d5ecf Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:06:46 +1100 Subject: powerpc: Remove dot symbol usage in exception macros STD_EXCEPTION_COMMON, STD_EXCEPTION_COMMON_ASYNC and MASKABLE_EXCEPTION branch to the handler, so we can remove the explicit dot symbol and binutils will do the right thing. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/exceptions-64e.S | 8 +++---- arch/powerpc/kernel/exceptions-64s.S | 46 ++++++++++++++++++------------------ 2 files changed, 27 insertions(+), 27 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index c8ac8a09b0f8..771b4e92e5d9 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -591,7 +591,7 @@ interrupt_end_book3e: /* External Input Interrupt */ MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, - external_input, .do_IRQ, ACK_NONE) + external_input, do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); @@ -676,11 +676,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) /* Decrementer Interrupt */ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, - decrementer, .timer_interrupt, ACK_DEC) + decrementer, timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, - fixed_interval, .unknown_exception, ACK_FIT) + fixed_interval, unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); @@ -855,7 +855,7 @@ kernel_dbg_exc: /* Doorbell interrupt */ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, - doorbell, .doorbell_exception, ACK_NONE) + doorbell, doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a0741b65f658..20f11eb4dff7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -769,38 +769,38 @@ kvmppc_skip_Hinterrupt: /*** Common interrupt handlers ***/ - STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) + STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception) STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) - STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) + STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt) + STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception) #endif - STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt) - STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) + STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception) + STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) + STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) + STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) + STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) #endif - STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception) - STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) - STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception) + STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception) + STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception) #ifdef CONFIG_ALTIVEC - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception) #else - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) #endif #ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception) + STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) + STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) + STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) #endif /* CONFIG_CBE_RAS */ /* @@ -1073,7 +1073,7 @@ instruction_access_common: li r5,0x400 b do_hash_page /* Try to handle as hpte fault */ - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) /* * Here is the common SLB miss user that is used when going to virtual @@ -1290,8 +1290,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) bl vsx_unavailable_exception b ret_from_except - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) .align 7 .globl __end_handlers -- cgit v1.2.3 From c1fb019477c27bfe309be282d178a08e56f05249 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:07:01 +1100 Subject: powerpc: Create DOTSYM to wrap dot symbol usage There are a few places we have to use dot symbols with the current ABI - the syscall table and the kvm hcall table. Wrap both of these with a new macro called DOTSYM so it will be easy to transition away from dot symbols in a future ABI. Signed-off-by: Anton Blanchard --- arch/powerpc/include/asm/ppc_asm.h | 2 ++ arch/powerpc/include/asm/systbl.h | 6 +++--- arch/powerpc/kernel/systbl.S | 12 ++++++------ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 28 ++++++++++++++-------------- 4 files changed, 25 insertions(+), 23 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 35b23a6584cb..61992d8f99df 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -223,6 +223,8 @@ name: \ .type GLUE(.,name),@function; \ GLUE(.,name): +#define DOTSYM(a) GLUE(.,a) + #else /* 32-bit */ #define _ENTRY(n) \ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 3ddf70276706..ac062f504736 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -62,7 +62,7 @@ COMPAT_SYS_SPU(fcntl) SYSCALL(ni_syscall) SYSCALL_SPU(setpgid) SYSCALL(ni_syscall) -SYSX(sys_ni_syscall,sys_olduname, sys_olduname) +SYSX(sys_ni_syscall,sys_olduname,sys_olduname) SYSCALL_SPU(umask) SYSCALL_SPU(chroot) COMPAT_SYS(ustat) @@ -258,7 +258,7 @@ SYSCALL_SPU(tgkill) COMPAT_SYS_SPU(utimes) COMPAT_SYS_SPU(statfs64) COMPAT_SYS_SPU(fstatfs64) -SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64) +SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64) PPC_SYS_SPU(rtas) OLDSYS(debug_setcontext) SYSCALL(ni_syscall) @@ -295,7 +295,7 @@ SYSCALL_SPU(mkdirat) SYSCALL_SPU(mknodat) SYSCALL_SPU(fchownat) COMPAT_SYS_SPU(futimesat) -SYSX_SPU(sys_newfstatat, sys_fstatat64, sys_fstatat64) +SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64) SYSCALL_SPU(unlinkat) SYSCALL_SPU(renameat) SYSCALL_SPU(linkat) diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 75822f97bfea..895c50ca943c 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -17,12 +17,12 @@ #include #ifdef CONFIG_PPC64 -#define SYSCALL(func) .llong .sys_##func,.sys_##func -#define COMPAT_SYS(func) .llong .sys_##func,.compat_sys_##func -#define PPC_SYS(func) .llong .ppc_##func,.ppc_##func -#define OLDSYS(func) .llong .sys_ni_syscall,.sys_ni_syscall -#define SYS32ONLY(func) .llong .sys_ni_syscall,.compat_sys_##func -#define SYSX(f, f3264, f32) .llong .f,.f3264 +#define SYSCALL(func) .llong DOTSYM(sys_##func),DOTSYM(sys_##func) +#define COMPAT_SYS(func) .llong DOTSYM(sys_##func),DOTSYM(compat_sys_##func) +#define PPC_SYS(func) .llong DOTSYM(ppc_##func),DOTSYM(ppc_##func) +#define OLDSYS(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) +#define SYS32ONLY(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) +#define SYSX(f, f3264, f32) .llong DOTSYM(f),DOTSYM(f3264) #else #define SYSCALL(func) .long sys_##func #define COMPAT_SYS(func) .long sys_##func diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 7cfabe3881d8..e9593f58a501 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1795,16 +1795,16 @@ hcall_real_fallback: .globl hcall_real_table hcall_real_table: .long 0 /* 0 - unused */ - .long .kvmppc_h_remove - hcall_real_table - .long .kvmppc_h_enter - hcall_real_table - .long .kvmppc_h_read - hcall_real_table + .long DOTSYM(kvmppc_h_remove) - hcall_real_table + .long DOTSYM(kvmppc_h_enter) - hcall_real_table + .long DOTSYM(kvmppc_h_read) - hcall_real_table .long 0 /* 0x10 - H_CLEAR_MOD */ .long 0 /* 0x14 - H_CLEAR_REF */ - .long .kvmppc_h_protect - hcall_real_table - .long .kvmppc_h_get_tce - hcall_real_table - .long .kvmppc_h_put_tce - hcall_real_table + .long DOTSYM(kvmppc_h_protect) - hcall_real_table + .long DOTSYM(kvmppc_h_get_tce) - hcall_real_table + .long DOTSYM(kvmppc_h_put_tce) - hcall_real_table .long 0 /* 0x24 - H_SET_SPRG0 */ - .long .kvmppc_h_set_dabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_dabr) - hcall_real_table .long 0 /* 0x2c */ .long 0 /* 0x30 */ .long 0 /* 0x34 */ @@ -1820,11 +1820,11 @@ hcall_real_table: .long 0 /* 0x5c */ .long 0 /* 0x60 */ #ifdef CONFIG_KVM_XICS - .long .kvmppc_rm_h_eoi - hcall_real_table - .long .kvmppc_rm_h_cppr - hcall_real_table - .long .kvmppc_rm_h_ipi - hcall_real_table + .long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table .long 0 /* 0x70 - H_IPOLL */ - .long .kvmppc_rm_h_xirr - hcall_real_table + .long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table #else .long 0 /* 0x64 - H_EOI */ .long 0 /* 0x68 - H_CPPR */ @@ -1858,7 +1858,7 @@ hcall_real_table: .long 0 /* 0xd4 */ .long 0 /* 0xd8 */ .long 0 /* 0xdc */ - .long .kvmppc_h_cede - hcall_real_table + .long DOTSYM(kvmppc_h_cede) - hcall_real_table .long 0 /* 0xe4 */ .long 0 /* 0xe8 */ .long 0 /* 0xec */ @@ -1875,11 +1875,11 @@ hcall_real_table: .long 0 /* 0x118 */ .long 0 /* 0x11c */ .long 0 /* 0x120 */ - .long .kvmppc_h_bulk_remove - hcall_real_table + .long DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table .long 0 /* 0x128 */ .long 0 /* 0x12c */ .long 0 /* 0x130 */ - .long .kvmppc_h_set_xdabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table hcall_real_table_end: ignore_hdec: -- cgit v1.2.3 From cc7efbf91933a4b59c20e60115c336b26dfc1195 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:07:47 +1100 Subject: powerpc: ABIv2 function calls must place target address in r12 To establish addressability quickly, ABIv2 requires the target address of the function being called to be in r12. Fix a number of places in assembly code that we do indirect function calls. We need to avoid function descriptors on ABIv2 too. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/entry_64.S | 4 ++-- arch/powerpc/kernel/head_64.S | 20 +++++++++++--------- arch/powerpc/kernel/misc_64.S | 8 ++++++-- 3 files changed, 19 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 2662f02ba6cf..d23d7526d37a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -174,8 +174,8 @@ system_call: /* label this so stack traces look sane */ clrldi r8,r8,32 15: slwi r0,r0,4 - ldx r10,r11,r0 /* Fetch system call handler [ptr] */ - mtctr r10 + ldx r12,r11,r0 /* Fetch system call handler [ptr] */ + mtctr r12 bctrl /* Call handler */ syscall_exit: diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 82841242dc26..97329a19c76b 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -140,16 +140,18 @@ __secondary_hold: tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r4,__secondary_hold_spinloop-_stext(r26) - cmpdi 0,r4,0 +100: ld r12,__secondary_hold_spinloop-_stext(r26) + cmpdi 0,r12,0 beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) #ifdef CONFIG_PPC_BOOK3E - tovirt(r4,r4) + tovirt(r12,r12) #endif - ld r4,0(r4) /* deref function descriptor */ - mtctr r4 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r12) /* deref function descriptor */ +#endif + mtctr r12 mr r3,r24 /* * it may be the case that other platforms have r4 right to @@ -267,8 +269,8 @@ generic_secondary_common_init: ld r23,CPU_SPEC_RESTORE(r23) cmpdi 0,r23,0 beq 3f - ld r23,0(r23) - mtctr r23 + ld r12,0(r23) + mtctr r12 bctrl 3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */ @@ -468,8 +470,8 @@ __after_prom_start: /* this includes the code being */ /* executed here. */ addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ - addi r8,r8,(4f - _stext)@l /* that we just made */ - mtctr r8 + addi r12,r8,(4f - _stext)@l /* that we just made */ + mtctr r12 bctr .balign 8 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index b39cf4afad4b..bda85a193abf 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -595,8 +595,12 @@ _GLOBAL(kexec_sequence) stw r6,kexec_flag-1b(5) /* clear out hardware hash page table and tlb */ - ld r5,0(r27) /* deref function descriptor */ - mtctr r5 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r27) /* deref function descriptor */ +#else + mr r12,r27 +#endif + mtctr r12 bctrl /* ppc_md.hpte_clear_all(void); */ /* -- cgit v1.2.3 From 814e4cd98f777c7fa3b42e0468030cd341fb8b6b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:08:02 +1100 Subject: powerpc: Ignore .TOC. relocations The linker fixes up .TOC. relocations, so prom_init_check.sh should ignore them. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/prom_init_check.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index b0c263da219a..77aa1e95e904 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -23,7 +23,7 @@ strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 reloc_got2 kernstart_addr memstart_addr linux_banner _stext opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry boot_command_line __prom_init_toc_start __prom_init_toc_end -btext_setup_display" +btext_setup_display TOC." NM="$1" OBJ="$2" -- cgit v1.2.3 From 7cedd6014bfe353d4b552ed8d54d63f6e06e26ba Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 4 Feb 2014 16:08:51 +1100 Subject: powerpc: Fix kernel thread creation on ABIv2 Change how we setup registers for ret_from_kernel_thread. In ABIv1, instead of passing a function descriptor in, dereference it and pass the target in directly. Use ppc_global_function_entry to get it right on both ABIv1 and ABIv2. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/entry_64.S | 4 +++- arch/powerpc/kernel/process.c | 17 +++++------------ 2 files changed, 8 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d23d7526d37a..cf4f6e693437 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -378,9 +378,11 @@ _GLOBAL(ret_from_fork) _GLOBAL(ret_from_kernel_thread) bl schedule_tail REST_NVGPRS(r1) - ld r14, 0(r14) mtlr r14 mr r3,r15 +#if defined(_CALL_ELF) && _CALL_ELF == 2 + mr r12,r14 +#endif blrl li r3,0 b syscall_exit diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 31d021506d21..2ae1b99166c6 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -54,6 +54,7 @@ #ifdef CONFIG_PPC64 #include #endif +#include #include #include @@ -1108,7 +1109,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); - childregs->gpr[14] = usp; /* function */ + /* function */ + if (usp) + childregs->gpr[14] = ppc_function_entry((void *)usp); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = 1; @@ -1187,17 +1190,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (cpu_has_feature(CPU_FTR_HAS_PPR)) p->thread.ppr = INIT_PPR; #endif - /* - * The PPC64 ABI makes use of a TOC to contain function - * pointers. The function (ret_from_except) is actually a pointer - * to the TOC entry. The first entry is a pointer to the actual - * function. - */ -#ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)f); -#else - kregs->nip = (unsigned long)f; -#endif + kregs->nip = ppc_function_entry(f); return 0; } -- cgit v1.2.3 From c2e31bdc120d992a90b75d94c7fa403fea362e43 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 10 Mar 2014 10:48:44 +1100 Subject: powerpc/tm: Use STK_PARAM Get rid of the tm specific STACK_PARAM and use STK_PARAM Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/tm.S | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 03567c05950a..27aad248c002 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -41,7 +41,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ /* Stack frame offsets for local variables. */ #define TM_FRAME_L0 TM_FRAME_SIZE-16 #define TM_FRAME_L1 TM_FRAME_SIZE-8 -#define STACK_PARAM(x) (48+((x)*8)) /* In order to access the TM SPRs, TM must be enabled. So, do so: */ @@ -113,7 +112,7 @@ _GLOBAL(tm_reclaim) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ - std r3, STACK_PARAM(0)(r1) + std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) /* We need to setup MSR for VSX register save instructions. Here we @@ -202,7 +201,7 @@ dont_backup_fp: /* Now get some more GPRS free */ std r7, GPR7(r1) /* Temporary stash */ std r12, GPR12(r1) /* '' '' '' */ - ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */ + ld r12, STK_PARAM(R3)(r1) /* Param 0, thread_struct * */ std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */ -- cgit v1.2.3 From 6403105bfda4d6934b39aeb85ff818b185b42de8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 10 Mar 2014 10:52:17 +1100 Subject: powerpc/tm: Fix GOT save offset for ABIv2 The r2 TOC/GOT save offset is 40 on ABIv1 and 24 on ABIv2. Signed-off-by: Anton Blanchard --- arch/powerpc/include/asm/ppc_asm.h | 2 ++ arch/powerpc/kernel/tm.S | 8 ++++---- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 3185d11b6691..2cc2511ff076 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -190,8 +190,10 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define STK_REG(i) __STK_REG(__REG_##i) #if defined(_CALL_ELF) && _CALL_ELF == 2 +#define STK_GOT 24 #define __STK_PARAM(i) (32 + ((i)-3)*8) #else +#define STK_GOT 40 #define __STK_PARAM(i) (48 + ((i)-3)*8) #endif #define STK_PARAM(i) __STK_PARAM(__REG_##i) diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 27aad248c002..cf1027efca30 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -107,7 +107,7 @@ _GLOBAL(tm_reclaim) mflr r0 stw r6, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ @@ -288,7 +288,7 @@ dont_backup_fp: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) /* Load system default DSCR */ ld r4, DSCR_DEFAULT@toc(r2) @@ -311,7 +311,7 @@ _GLOBAL(__tm_recheckpoint) mflr r0 stw r5, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. @@ -447,7 +447,7 @@ restore_gprs: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) /* Load system default DSCR */ ld r4, DSCR_DEFAULT@toc(r2) -- cgit v1.2.3 From 2751b628c97e66e61f482935ca59148751972941 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 11 Mar 2014 11:54:06 +1100 Subject: powerpc: Fix SMP issues with ppc64le ABIv2 There is no need to put a function descriptor in __secondary_hold_spinloop. Use ppc_function_entry to get the instruction address and put it in __secondary_hold_spinloop instead. Also fix an issue where we assumed cur_cpu_spec held a function descriptor. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/head_64.S | 18 ++++++++---------- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/85xx/smp.c | 3 ++- arch/powerpc/platforms/cell/smp.c | 5 +++-- arch/powerpc/platforms/powernv/smp.c | 5 +++-- arch/powerpc/platforms/pseries/smp.c | 5 +++-- arch/powerpc/platforms/wsp/scom_smp.c | 3 ++- 7 files changed, 22 insertions(+), 19 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 97329a19c76b..a95145d7f61b 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -76,10 +76,9 @@ END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ trap - /* Secondary processors spin on this value until it becomes nonzero. - * When it does it contains the real address of the descriptor - * of the function that the cpu should jump to to continue - * initialization. + /* Secondary processors spin on this value until it becomes non-zero. + * When non-zero, it contains the real address of the function the cpu + * should jump to. */ .balign 8 .globl __secondary_hold_spinloop @@ -147,9 +146,6 @@ __secondary_hold: #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) #ifdef CONFIG_PPC_BOOK3E tovirt(r12,r12) -#endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 - ld r12,0(r12) /* deref function descriptor */ #endif mtctr r12 mr r3,r24 @@ -266,10 +262,12 @@ generic_secondary_common_init: /* See if we need to call a cpu state restore handler */ LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) - ld r23,CPU_SPEC_RESTORE(r23) - cmpdi 0,r23,0 + ld r12,CPU_SPEC_RESTORE(r23) + cmpdi 0,r12,0 beq 3f - ld r12,0(r23) +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r12) +#endif mtctr r12 bctrl diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index fbe24377eda3..90b532ace0d5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -341,7 +341,7 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); - *ptr = __pa(generic_secondary_smp_init); + *ptr = ppc_function_entry(generic_secondary_smp_init); /* And wait a bit for them to catch up */ for (i = 0; i < 100000; i++) { diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 6382098d6f8d..ba093f553678 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -267,7 +268,7 @@ out: flush_spin_table(spin_table); out_be32(&spin_table->pir, hw_cpu); out_be64((u64 *)(&spin_table->addr_h), - __pa((u64)*((unsigned long long *)generic_secondary_smp_init))); + __pa(ppc_function_entry(generic_secondary_smp_init))); flush_spin_table(spin_table); #endif diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index 90745eaa45fe..c8017a7bcabd 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -40,6 +40,7 @@ #include #include #include +#include #include "interrupt.h" #include @@ -70,8 +71,8 @@ static cpumask_t of_spin_map; static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 908672bdcea6..b370b86263a6 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "powernv.h" @@ -49,8 +50,8 @@ static void pnv_smp_setup_cpu(int cpu) int pnv_smp_kick_cpu(int nr) { unsigned int pcpu = get_hard_smp_processor_id(nr); - unsigned long start_here = __pa(*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; BUG_ON(nr < 0 || nr >= NR_CPUS); diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 24f58cb0a543..a3555b10c1a5 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "pseries.h" #include "offline_states.h" @@ -96,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu) static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c index 268bc899c1f7..8c79ce016cf1 100644 --- a/arch/powerpc/platforms/wsp/scom_smp.c +++ b/arch/powerpc/platforms/wsp/scom_smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "wsp.h" @@ -405,7 +406,7 @@ int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np) goto fail; } - start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init + start_here = ppc_function_entry(core_setup ? generic_secondary_smp_init : generic_secondary_thread_init); pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here); -- cgit v1.2.3 From 0e60e46e2aa318c92bb224de29b68b6296bb0fde Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 17:35:28 +1030 Subject: powerpc: make module stub code endian independent By representing them as words, rather than chars, we can avoid endian ifdefs. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 42 +++++++++++------------------------------ 1 file changed, 11 insertions(+), 31 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 12664c130d73..7c16b2eefd95 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -47,8 +47,8 @@ struct ppc64_stub_entry { /* 28 byte jump instruction sequence (7 instructions) */ - unsigned char jump[28]; - unsigned char unused[4]; + u32 jump[7]; + u32 unused; /* Data for the above code */ struct ppc64_opd_entry opd; }; @@ -61,25 +61,14 @@ struct ppc64_stub_entry r2) into the stub. */ static struct ppc64_stub_entry ppc64_stub = { .jump = { -#ifdef __LITTLE_ENDIAN__ - 0x00, 0x00, 0x82, 0x3d, /* addis r12,r2, */ - 0x00, 0x00, 0x8c, 0x39, /* addi r12,r12, */ + 0x3d820000, /* addis r12,r2, */ + 0x398c0000, /* addi r12,r12, */ /* Save current r2 value in magic place on the stack. */ - 0x28, 0x00, 0x41, 0xf8, /* std r2,40(r1) */ - 0x20, 0x00, 0x6c, 0xe9, /* ld r11,32(r12) */ - 0x28, 0x00, 0x4c, 0xe8, /* ld r2,40(r12) */ - 0xa6, 0x03, 0x69, 0x7d, /* mtctr r11 */ - 0x20, 0x04, 0x80, 0x4e /* bctr */ -#else - 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, */ - 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, */ - /* Save current r2 value in magic place on the stack. */ - 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */ - 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */ - 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ - 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ - 0x4e, 0x80, 0x04, 0x20 /* bctr */ -#endif + 0xf8410028, /* std r2,40(r1) */ + 0xe96c0020, /* ld r11,32(r12) */ + 0xe84c0028, /* ld r2,40(r12) */ + 0x7d6903a6, /* mtctr r11 */ + 0x4e800420 /* bctr */ } }; /* Count how many different 24-bit relocations (different symbol, @@ -274,19 +263,10 @@ static inline int create_stub(Elf64_Shdr *sechdrs, struct ppc64_opd_entry *opd, struct module *me) { - Elf64_Half *loc1, *loc2; long reladdr; *entry = ppc64_stub; -#ifdef __LITTLE_ENDIAN__ - loc1 = (Elf64_Half *)&entry->jump[0]; - loc2 = (Elf64_Half *)&entry->jump[4]; -#else - loc1 = (Elf64_Half *)&entry->jump[2]; - loc2 = (Elf64_Half *)&entry->jump[6]; -#endif - /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { @@ -296,8 +276,8 @@ static inline int create_stub(Elf64_Shdr *sechdrs, } DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr); - *loc1 = PPC_HA(reladdr); - *loc2 = PPC_LO(reladdr); + entry->jump[0] |= PPC_HA(reladdr); + entry->jump[1] |= PPC_LO(reladdr); entry->opd.funcaddr = opd->funcaddr; entry->opd.r2 = opd->r2; return 1; -- cgit v1.2.3 From d247da0a8ebcc4ebb4c766487de6af5df560adac Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 17:36:28 +1030 Subject: powerpc: modules implement R_PPC64_TOCSAVE relocation. Signed-off-by: Rusty Russell --- arch/powerpc/include/uapi/asm/elf.h | 5 ++++- arch/powerpc/kernel/module_64.c | 8 ++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 7e39c9146a71..0341109e4395 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -291,9 +291,12 @@ do { \ #define R_PPC64_DTPREL16_HIGHERA 104 /* half16 (sym+add)@dtprel@highera */ #define R_PPC64_DTPREL16_HIGHEST 105 /* half16 (sym+add)@dtprel@highest */ #define R_PPC64_DTPREL16_HIGHESTA 106 /* half16 (sym+add)@dtprel@highesta */ +#define R_PPC64_TLSGD 107 +#define R_PPC64_TLSLD 108 +#define R_PPC64_TOCSAVE 109 /* Keep this the last entry. */ -#define R_PPC64_NUM 107 +#define R_PPC64_NUM 110 /* There's actually a third entry here, but it's unused */ struct ppc64_opd_entry diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 7c16b2eefd95..a8694d462079 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -454,6 +454,14 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *location = value - (unsigned long)location; break; + case R_PPC64_TOCSAVE: + /* + * Marker reloc indicates we don't have to save r2. + * That would only save us one instruction, so ignore + * it. + */ + break; + default: printk("%s: Unknown ADD relocation: %lu\n", me->name, -- cgit v1.2.3 From 9baeaef64095eab00c232f55df2e7c2d8e89845d Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 17:37:28 +1030 Subject: powerpc: EXPORT_SYMBOL(.TOC.) For the ELFv2 ABI, powerpc introduces a magic symbol ".TOC.". depmod then complains that this doesn't resolve (so does modpost, but we could easily fix that). To export this, we need to use asm. modpost and depmod both strip "." from symbols for the old PPC64 ELFv1 ABI, so we actually export a "TOC.". Signed-off-by: Rusty Russell --- arch/powerpc/kernel/misc_64.S | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index bda85a193abf..b80fafbfab2f 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -634,3 +634,22 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ + +#ifdef CONFIG_MODULES +#if defined(_CALL_ELF) && _CALL_ELF == 2 +/* + * Export a fake .TOC. since both modpost and depmod will complain otherwise. + * Both modpost and depmod strip the leading . so we do the same here. + */ +.section "__ksymtab_strings","a" +__kstrtab_TOC.: + .asciz "TOC." + +.section "___ksymtab+TOC.","a" +/* This symbol name is important: it's used by modpost to find exported syms */ +.globl __ksymtab_TOC. +__ksymtab_TOC.: + .llong 0 /* .value */ + .llong __kstrtab_TOC. +#endif /* ELFv2 */ +#endif /* MODULES */ -- cgit v1.2.3 From 71ec7c55ed91e2352c00d51d171fccaa7cef5a00 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 19:59:11 +1030 Subject: powerpc: module: handle MODVERSION for .TOC. For the ELFv2 ABI, powerpc introduces a magic symbol ".TOC.". If we don't create a CRC for it (minus the leading ".", since we strip that) we get a modpost warning about missing CRC and the CRC array seems to be displaced by 1 so other CRCs mismatch too. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/misc_64.S | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index b80fafbfab2f..4e314b90c75d 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -637,6 +637,15 @@ _GLOBAL(kexec_sequence) #ifdef CONFIG_MODULES #if defined(_CALL_ELF) && _CALL_ELF == 2 + +#ifdef CONFIG_MODVERSIONS +.weak __crc_TOC. +.section "___kcrctab+TOC.","a" +.globl __kcrctab_TOC. +__kcrctab_TOC.: + .llong __crc_TOC. +#endif + /* * Export a fake .TOC. since both modpost and depmod will complain otherwise. * Both modpost and depmod strip the leading . so we do the same here. -- cgit v1.2.3 From 4edebbeae3085e71f75584b6582495459e2e6cb2 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 19:59:26 +1030 Subject: powerpc: Fix up TOC. for modules. The kernel resolved the '.TOC.' to a fake symbol, so we need to fix it up to point to our .toc section plus 0x8000. Signed-off-by: Rusty Russell --- arch/powerpc/include/asm/module.h | 1 + arch/powerpc/kernel/module_64.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 49fa55bfbac4..c9c7aaaf95f5 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -35,6 +35,7 @@ struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ + bool toc_fixed; /* Have we fixed up .TOC.? */ #ifdef CONFIG_DYNAMIC_FTRACE unsigned long toc; unsigned long tramp; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index a8694d462079..f6544d7071d6 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -196,6 +196,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) } } +static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex) +{ + unsigned int i, numsyms; + Elf64_Sym *syms; + + syms = (Elf64_Sym *)sechdrs[symindex].sh_addr; + numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); + + for (i = 1; i < numsyms; i++) { + if (syms[i].st_shndx == SHN_UNDEF + && strcmp(strtab + syms[i].st_name, ".TOC.") == 0) + return &syms[i]; + } + return NULL; +} + int module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs, char *secstrings, @@ -337,6 +355,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, DEBUGP("Applying ADD relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + + /* First time we're called, we can fix up .TOC. */ + if (!me->arch.toc_fixed) { + sym = find_dot_toc(sechdrs, strtab, symindex); + /* It's theoretically possible that a module doesn't want a + * .TOC. so don't fail it just for that. */ + if (sym) + sym->st_value = my_r2(sechdrs, me); + me->arch.toc_fixed = true; + } + for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr -- cgit v1.2.3 From 0906584a0a4b689f6e80307f699247621321670a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 19:59:27 +1030 Subject: powerpc: Handle new ELFv2 module relocations The new ELF ABI tends to use R_PPC64_REL16_LO and R_PPC64_REL16_HA relocations (PC-relative), so implement them. Signed-off-by: Rusty Russell --- arch/powerpc/include/uapi/asm/elf.h | 7 ++++++- arch/powerpc/kernel/module_64.c | 17 +++++++++++++++++ 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 0341109e4395..59dad113897b 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,8 +295,13 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_REL16 249 +#define R_PPC64_REL16_LO 250 +#define R_PPC64_REL16_HI 251 +#define R_PPC64_REL16_HA 252 + /* Keep this the last entry. */ -#define R_PPC64_NUM 110 +#define R_PPC64_NUM 253 /* There's actually a third entry here, but it's unused */ struct ppc64_opd_entry diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index f6544d7071d6..34ba326ccc30 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -491,6 +491,23 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_REL16_HA: + /* Subtract location pointer */ + value -= (unsigned long)location; + value = ((value + 0x8000) >> 16); + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_REL16_LO: + /* Subtract location pointer */ + value -= (unsigned long)location; + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + default: printk("%s: Unknown ADD relocation: %lu\n", me->name, -- cgit v1.2.3 From 5b12c5c69415b184aadb930660a47a8af4c6deb5 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 20:11:28 +1030 Subject: powerpc: modules: comment about de-dotifying symbols when using the ELFv2 ABI. ELFv2 doesn't use function descriptors, so we don't expect symbols to start with ".". But because depmod and modpost strip ".", and we have the special symbol ".TOC.", we still need to do it. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 34ba326ccc30..05b27a5efc7e 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -172,6 +172,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, return relocs * sizeof(struct ppc64_stub_entry); } +/* Still needed for ELFv2, for .TOC. */ static void dedotify_versions(struct modversion_info *vers, unsigned long size) { @@ -182,7 +183,7 @@ static void dedotify_versions(struct modversion_info *vers, memmove(vers->name, vers->name+1, strlen(vers->name)); } -/* Undefined symbols which refer to .funcname, hack to funcname */ +/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; -- cgit v1.2.3 From d2fae548039987e0c64957ede44822305fdafb66 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 20:12:44 +1030 Subject: powerpc: modules: change r2 save/restore offset for ELFv2 ABI. ELFv2 uses a different stack offset (24 vs 40) to save r2. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 05b27a5efc7e..8bfcf1b8b6d4 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -41,6 +41,12 @@ #define DEBUGP(fmt , ...) #endif +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define R2_STACK_OFFSET 24 +#else +#define R2_STACK_OFFSET 40 +#endif + /* Like PPC32, we need little trampolines to do > 24-bit jumps (into the kernel itself). But on PPC64, these need to be used for every jump, actually, to reset r2 (TOC+0x8000). */ @@ -61,14 +67,14 @@ struct ppc64_stub_entry r2) into the stub. */ static struct ppc64_stub_entry ppc64_stub = { .jump = { - 0x3d820000, /* addis r12,r2, */ - 0x398c0000, /* addi r12,r12, */ + 0x3d820000, /* addis r12,r2, */ + 0x398c0000, /* addi r12,r12, */ /* Save current r2 value in magic place on the stack. */ - 0xf8410028, /* std r2,40(r1) */ - 0xe96c0020, /* ld r11,32(r12) */ - 0xe84c0028, /* ld r2,40(r12) */ - 0x7d6903a6, /* mtctr r11 */ - 0x4e800420 /* bctr */ + 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ + 0xe96c0020, /* ld r11,32(r12) */ + 0xe84c0028, /* ld r2,40(r12) */ + 0x7d6903a6, /* mtctr r11 */ + 0x4e800420 /* bctr */ } }; /* Count how many different 24-bit relocations (different symbol, @@ -338,7 +344,8 @@ static int restore_r2(u32 *instruction, struct module *me) me->name, *instruction); return 0; } - *instruction = 0xe8410028; /* ld r2,40(r1) */ + /* ld r2,R2_STACK_OFFSET(r1) */ + *instruction = 0xe8410000 | R2_STACK_OFFSET; return 1; } -- cgit v1.2.3 From b1ce369e820aaca3d91e9d9bbaaf860794d9ab01 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 20:12:59 +1030 Subject: powerpc: modules: use r12 for stub jump address. In ELFv2, r12 is supposed to equal to PC on entry to a function. Our stubs use r11, so change swap that with r12. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 8bfcf1b8b6d4..f8b6d28784ef 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -67,13 +67,13 @@ struct ppc64_stub_entry r2) into the stub. */ static struct ppc64_stub_entry ppc64_stub = { .jump = { - 0x3d820000, /* addis r12,r2, */ - 0x398c0000, /* addi r12,r12, */ + 0x3d620000, /* addis r11,r2, */ + 0x396b0000, /* addi r11,r11, */ /* Save current r2 value in magic place on the stack. */ 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ - 0xe96c0020, /* ld r11,32(r12) */ - 0xe84c0028, /* ld r2,40(r12) */ - 0x7d6903a6, /* mtctr r11 */ + 0xe98b0020, /* ld r12,32(r11) */ + 0xe84b0026, /* ld r2,40(r11) */ + 0x7d8903a6, /* mtctr r12 */ 0x4e800420 /* bctr */ } }; -- cgit v1.2.3 From 5c729a115e4727fd71308e4d68846f64fa460ead Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 18 Mar 2014 20:13:03 +1030 Subject: powerpc: modules: skip r2 setup for ELFv2 ELFv2 doesn't need to set up r2 when calling a function. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index f8b6d28784ef..d7222495e24c 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -59,12 +59,19 @@ struct ppc64_stub_entry struct ppc64_opd_entry opd; }; -/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external) - function which may be more than 24-bits away. We could simply - patch the new r2 value and function pointer into the stub, but it's - significantly shorter to put these values at the end of the stub - code, and patch the stub address (32-bits relative to the TOC ptr, - r2) into the stub. */ +/* + * PPC64 uses 24 bit jumps, but we need to jump into other modules or + * the kernel which may be further. So we jump to a stub. + * + * For ELFv1 we need to use this to set up the new r2 value (aka TOC + * pointer). For ELFv2 it's the callee's responsibility to set up the + * new r2, but for both we need to save the old r2. + * + * We could simply patch the new r2 value and function pointer into + * the stub, but it's significantly shorter to put these values at the + * end of the stub code, and patch the stub address (32-bits relative + * to the TOC ptr, r2) into the stub. + */ static struct ppc64_stub_entry ppc64_stub = { .jump = { 0x3d620000, /* addis r11,r2, */ @@ -72,7 +79,10 @@ static struct ppc64_stub_entry ppc64_stub = /* Save current r2 value in magic place on the stack. */ 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ 0xe98b0020, /* ld r12,32(r11) */ +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + /* Set up new r2 from function descriptor */ 0xe84b0026, /* ld r2,40(r11) */ +#endif 0x7d8903a6, /* mtctr r12 */ 0x4e800420 /* bctr */ } }; -- cgit v1.2.3 From 008d7a914efee6ee5afe59bcc46d3d6b60657598 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 19 Mar 2014 10:42:22 +1030 Subject: powerpc: modules: implement stubs for ELFv2 ABI. ELFv2 doesn't use function descriptors, because it doesn't need to load a new r2 when calling into a function. On the other hand, you're supposed to use a local entry point for R_PPC_REL24 branches. Signed-off-by: Rusty Russell --- arch/powerpc/kernel/module_64.c | 73 ++++++++++++++++++++++++++++++++++------- 1 file changed, 61 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index d7222495e24c..042360135260 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -43,8 +43,58 @@ #if defined(_CALL_ELF) && _CALL_ELF == 2 #define R2_STACK_OFFSET 24 + +/* An address is simply the address of the function. */ +typedef unsigned long func_desc_t; + +static func_desc_t func_desc(unsigned long addr) +{ + return addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return addr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func; +} + +/* PowerPC64 specific values for the Elf64_Sym st_other field. */ +#define STO_PPC64_LOCAL_BIT 5 +#define STO_PPC64_LOCAL_MASK (7 << STO_PPC64_LOCAL_BIT) +#define PPC64_LOCAL_ENTRY_OFFSET(other) \ + (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2) + +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + /* sym->st_other indicates offset to local entry point + * (otherwise it will assume r12 is the address of the start + * of function and try to derive r2 from it). */ + return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other); +} #else #define R2_STACK_OFFSET 40 + +/* An address is address of the OPD entry, which contains address of fn. */ +typedef struct ppc64_opd_entry func_desc_t; + +static func_desc_t func_desc(unsigned long addr) +{ + return *(struct ppc64_opd_entry *)addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return func_desc(addr).funcaddr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func.funcaddr; +} +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + return 0; +} #endif /* Like PPC32, we need little trampolines to do > 24-bit jumps (into @@ -56,7 +106,7 @@ struct ppc64_stub_entry u32 jump[7]; u32 unused; /* Data for the above code */ - struct ppc64_opd_entry opd; + func_desc_t funcdata; }; /* @@ -225,7 +275,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, for (i = 1; i < numsyms; i++) { if (syms[i].st_shndx == SHN_UNDEF - && strcmp(strtab + syms[i].st_name, ".TOC.") == 0) + && strcmp(strtab + syms[i].st_name, "TOC.") == 0) return &syms[i]; } return NULL; @@ -295,7 +345,7 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) /* Patch stub to reference function and correct r2 value. */ static inline int create_stub(Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, - struct ppc64_opd_entry *opd, + unsigned long addr, struct module *me) { long reladdr; @@ -313,33 +363,31 @@ static inline int create_stub(Elf64_Shdr *sechdrs, entry->jump[0] |= PPC_HA(reladdr); entry->jump[1] |= PPC_LO(reladdr); - entry->opd.funcaddr = opd->funcaddr; - entry->opd.r2 = opd->r2; + entry->funcdata = func_desc(addr); return 1; } -/* Create stub to jump to function described in this OPD: we need the +/* Create stub to jump to function described in this OPD/ptr: we need the stub to set up the TOC ptr (r2) for the function. */ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, - unsigned long opdaddr, + unsigned long addr, struct module *me) { struct ppc64_stub_entry *stubs; - struct ppc64_opd_entry *opd = (void *)opdaddr; unsigned int i, num_stubs; num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs); /* Find this stub, or if that fails, the next avail. entry */ stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stubs[i].opd.funcaddr; i++) { + for (i = 0; stub_func_addr(stubs[i].funcdata); i++) { BUG_ON(i >= num_stubs); - if (stubs[i].opd.funcaddr == opd->funcaddr) + if (stub_func_addr(stubs[i].funcdata) == func_addr(addr)) return (unsigned long)&stubs[i]; } - if (!create_stub(sechdrs, &stubs[i], opd, me)) + if (!create_stub(sechdrs, &stubs[i], addr, me)) return 0; return (unsigned long)&stubs[i]; @@ -480,7 +528,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return -ENOENT; if (!restore_r2((u32 *)location + 1, me)) return -ENOEXEC; - } + } else + value += local_entry_offset(sym); /* Convert value to relative */ value -= (unsigned long)location; -- cgit v1.2.3 From 5e66684fe4c71e4d62d6a5d313057185ac0890cc Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 4 Apr 2014 09:06:33 +1100 Subject: powerpc: ftrace_caller, _mcount is exported to modules so needs _GLOBAL_TOC() When testing the ftrace function tracer, I realised that ftrace_caller and mcount are called from modules and they both call into C, therefore they need the ABIv2 global entry point to establish r2. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/entry_64.S | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index cf4f6e693437..9fde8a1bf1e1 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1175,7 +1175,7 @@ _GLOBAL(mcount) _GLOBAL(_mcount) blr -_GLOBAL(ftrace_caller) +_GLOBAL_TOC(ftrace_caller) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -1199,10 +1199,7 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr #else -_GLOBAL(mcount) - blr - -_GLOBAL(_mcount) +_GLOBAL_TOC(_mcount) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) -- cgit v1.2.3 From 83775b85668a85036973c71264a959236e7becbd Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 3 Apr 2014 20:00:43 +1100 Subject: powerpc/modules: Create is_module_trampoline() ftrace has way too much knowledge of our kernel module trampoline layout hidden inside it. Create is_module_trampoline() that can abstract this away inside the module loader code. Signed-off-by: Anton Blanchard --- arch/powerpc/include/asm/module.h | 1 + arch/powerpc/kernel/module_64.c | 51 +++++++++++++++++++++++++++++++++++---- 2 files changed, 47 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index c9c7aaaf95f5..f2711f0eb873 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -78,6 +78,7 @@ struct mod_arch_specific { # endif /* MODULE */ #endif +bool is_module_trampoline(u32 *insns); struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 042360135260..4db5ecdc06e6 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -102,7 +103,9 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) jump, actually, to reset r2 (TOC+0x8000). */ struct ppc64_stub_entry { - /* 28 byte jump instruction sequence (7 instructions) */ + /* 28 byte jump instruction sequence (7 instructions). We only + * need 6 instructions on ABIv2 but we always allocate 7 so + * so we don't have to modify the trampoline load instruction. */ u32 jump[7]; u32 unused; /* Data for the above code */ @@ -122,8 +125,8 @@ struct ppc64_stub_entry * end of the stub code, and patch the stub address (32-bits relative * to the TOC ptr, r2) into the stub. */ -static struct ppc64_stub_entry ppc64_stub = -{ .jump = { + +static u32 ppc64_stub_insns[] = { 0x3d620000, /* addis r11,r2, */ 0x396b0000, /* addi r11,r11, */ /* Save current r2 value in magic place on the stack. */ @@ -135,7 +138,45 @@ static struct ppc64_stub_entry ppc64_stub = #endif 0x7d8903a6, /* mtctr r12 */ 0x4e800420 /* bctr */ -} }; +}; + +#ifdef CONFIG_DYNAMIC_FTRACE + +static u32 ppc64_stub_mask[] = { + 0xffff0000, + 0xffff0000, + 0xffffffff, + 0xffffffff, +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + 0xffffffff, +#endif + 0xffffffff, + 0xffffffff +}; + +bool is_module_trampoline(u32 *p) +{ + unsigned int i; + u32 insns[ARRAY_SIZE(ppc64_stub_insns)]; + + BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask)); + + if (probe_kernel_read(insns, p, sizeof(insns))) + return -EFAULT; + + for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { + u32 insna = insns[i]; + u32 insnb = ppc64_stub_insns[i]; + u32 mask = ppc64_stub_mask[i]; + + if ((insna & mask) != (insnb & mask)) + return false; + } + + return true; +} + +#endif /* Count how many different 24-bit relocations (different symbol, different addend) */ @@ -350,7 +391,7 @@ static inline int create_stub(Elf64_Shdr *sechdrs, { long reladdr; - *entry = ppc64_stub; + memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns)); /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); -- cgit v1.2.3 From dd9fa162505c07e1917c96a1a12ca117b1afe55a Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 4 Apr 2014 15:58:42 +1100 Subject: powerpc/modules: Create module_trampoline_target() ftrace has way too much knowledge of our kernel module trampoline layout hidden inside it. Create module_trampoline_target() that gives the target address of a kernel module trampoline. Signed-off-by: Anton Blanchard --- arch/powerpc/include/asm/module.h | 2 ++ arch/powerpc/kernel/module_64.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index f2711f0eb873..dcfcad139bcc 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -79,6 +79,8 @@ struct mod_arch_specific { #endif bool is_module_trampoline(u32 *insns); +int module_trampoline_target(struct module *mod, u32 *trampoline, + unsigned long *target); struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 4db5ecdc06e6..ef349d077129 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -176,6 +176,35 @@ bool is_module_trampoline(u32 *p) return true; } +int module_trampoline_target(struct module *mod, u32 *trampoline, + unsigned long *target) +{ + u32 buf[2]; + u16 upper, lower; + long offset; + void *toc_entry; + + if (probe_kernel_read(buf, trampoline, sizeof(buf))) + return -EFAULT; + + upper = buf[0] & 0xffff; + lower = buf[1] & 0xffff; + + /* perform the addis/addi, both signed */ + offset = ((short)upper << 16) + (short)lower; + + /* + * Now get the address this trampoline jumps to. This + * is always 32 bytes into our trampoline stub. + */ + toc_entry = (void *)mod->arch.toc + offset + 32; + + if (probe_kernel_read(target, toc_entry, sizeof(*target))) + return -EFAULT; + + return 0; +} + #endif /* Count how many different 24-bit relocations (different symbol, -- cgit v1.2.3 From 62c9da6a8b394eb9336a255fc23457202d6b9755 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 4 Apr 2014 16:52:58 +1100 Subject: powerpc/ftrace: Use module loader helpers to parse trampolines Now we have is_module_trampoline() and module_trampoline_target() we can remove a bunch of intimate kernel module trampoline knowledge from ftrace. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/ftrace.c | 97 +++++++++----------------------------------- 1 file changed, 20 insertions(+), 77 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 6a014c763cc7..78cdd7fbecd0 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -105,11 +105,9 @@ __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned int op; - unsigned int jmp[5]; unsigned long ptr; unsigned long ip = rec->ip; - unsigned long tramp; - int offset; + void *tramp; /* read where this goes */ if (probe_kernel_read(&op, (void *)ip, sizeof(int))) @@ -122,96 +120,41 @@ __ftrace_make_nop(struct module *mod, } /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - - /* - * On PPC64 the trampoline looks like: - * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, - * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, - * Where the bytes 2,3,6 and 7 make up the 32bit offset - * to the TOC that holds the pointer. - * to jump to. - * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) - * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) - * The actually address is 32 bytes from the offset - * into the TOC. - * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) - */ + tramp = (void *)find_bl_target(ip, op); - pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); + pr_devel("ip:%lx jumps to %p", ip, tramp); - /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { - printk(KERN_ERR "Failed to read %lx\n", tramp); - return -EFAULT; - } - - pr_devel(" %08x %08x", jmp[0], jmp[1]); - - /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d820000) || - ((jmp[1] & 0xffff0000) != 0x398c0000) || - (jmp[2] != 0xf8410028) || - (jmp[3] != 0xe96c0020) || - (jmp[4] != 0xe84c0028)) { + if (!is_module_trampoline(tramp)) { printk(KERN_ERR "Not a trampoline\n"); return -EINVAL; } - /* The bottom half is signed extended */ - offset = ((unsigned)((unsigned short)jmp[0]) << 16) + - (int)((short)jmp[1]); - - pr_devel(" %x ", offset); - - /* get the address this jumps too */ - tramp = mod->arch.toc + offset + 32; - pr_devel("toc: %lx", tramp); - - if (probe_kernel_read(jmp, (void *)tramp, 8)) { - printk(KERN_ERR "Failed to read %lx\n", tramp); + if (module_trampoline_target(mod, tramp, &ptr)) { + printk(KERN_ERR "Failed to get trampoline target\n"); return -EFAULT; } - pr_devel(" %08x %08x\n", jmp[0], jmp[1]); - -#ifdef __LITTLE_ENDIAN__ - ptr = ((unsigned long)jmp[1] << 32) + jmp[0]; -#else - ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; -#endif + pr_devel("trampoline target %lx", ptr); /* This should match what was called */ if (ptr != ppc_function_entry((void *)addr)) { - printk(KERN_ERR "addr does not match %lx\n", ptr); + printk(KERN_ERR "addr %lx does not match expected %lx\n", + ptr, ppc_function_entry((void *)addr)); return -EINVAL; } /* - * We want to nop the line, but the next line is - * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) - * This needs to be turned to a nop too. - */ - if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) - return -EFAULT; - - if (op != 0xe8410028) { - printk(KERN_ERR "Next line is not ld! (%08x)\n", op); - return -EINVAL; - } - - /* - * Milton Miller pointed out that we can not blindly do nops. - * If a task was preempted when calling a trace function, - * the nops will remove the way to restore the TOC in r2 - * and the r2 TOC will get corrupted. - */ - - /* - * Replace: - * bl <==== will be replaced with "b 1f" - * ld r2,40(r1) - * 1: + * Our original call site looks like: + * + * bl + * ld r2,XX(r1) + * + * Milton Miller pointed out that we can not simply nop the branch. + * If a task was preempted when calling a trace function, the nops + * will remove the way to restore the TOC in r2 and the r2 TOC will + * get corrupted. + * + * Use a b +8 to jump over the load. */ op = 0x48000008; /* b +8 */ -- cgit v1.2.3 From 24a1bdc358bf3c533f7d575202e92aaca0f91761 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 4 Apr 2014 16:54:04 +1100 Subject: powerpc/ftrace: Fix ABIv2 issues with __ftrace_make_call __ftrace_make_call assumed ABIv1 TOC stack offsets, so it broke on ABIv2. While we are here, we can simplify the instruction modification code. Since we always update one instruction there is no need to probe_kernel_write and flush_icache_range, just use patch_branch. Signed-off-by: Anton Blanchard --- arch/powerpc/kernel/ftrace.c | 40 +++++++++++++++++++--------------------- 1 file changed, 19 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 78cdd7fbecd0..f202d0731b06 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -292,19 +292,24 @@ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; - unsigned long ip = rec->ip; + void *ip = (void *)rec->ip; /* read where this goes */ - if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) + if (probe_kernel_read(op, ip, sizeof(op))) return -EFAULT; /* - * It should be pointing to two nops or - * b +8; ld r2,40(r1) + * We expect to see: + * + * b +8 + * ld r2,XX(r1) + * + * The load offset is different depending on the ABI. For simplicity + * just mask it out when doing the compare. */ - if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) && - ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) { - printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + if ((op[0] != 0x48000008) || ((op[1] & 0xffff00000) != 0xe8410000)) { + printk(KERN_ERR "Unexpected call sequence: %x %x\n", + op[0], op[1]); return -EINVAL; } @@ -314,23 +319,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EINVAL; } - /* create the branch to the trampoline */ - op[0] = create_branch((unsigned int *)ip, - rec->arch.mod->arch.tramp, BRANCH_SET_LINK); - if (!op[0]) { - printk(KERN_ERR "REL24 out of range!\n"); + /* Ensure branch is within 24 bits */ + if (create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + printk(KERN_ERR "Branch out of range"); return -EINVAL; } - /* ld r2,40(r1) */ - op[1] = 0xe8410028; - - pr_devel("write to %lx\n", rec->ip); - - if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) - return -EPERM; - - flush_icache_range(ip, ip + 8); + if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + printk(KERN_ERR "REL24 out of range!\n"); + return -EINVAL; + } return 0; } -- cgit v1.2.3 From 9e0493756076692a8b6095fbee9c4f8dcbbe597a Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:07 +1000 Subject: powerpc/eeh: Remove EEH_PE_PHB_DEAD The PE state (for eeh_pe instance) EEH_PE_PHB_DEAD is duplicate to EEH_PE_ISOLATED. Originally, those PHBs (PHB PE) with EEH_PE_PHB_DEAD would be removed from the system. However, it's safe to replace that with EEH_PE_ISOLATED. The patch also clear EEH_PE_RECOVERING after fenced PHB has been handled, either failure or success. It makes the PHB PE state consistent with: PHB functions normally NONE PHB has been removed EEH_PE_ISOLATED PHB fenced, recovery in progress EEH_PE_ISOLATED | RECOVERING Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 1 - arch/powerpc/kernel/eeh.c | 10 ++-------- arch/powerpc/kernel/eeh_driver.c | 10 +++++----- 3 files changed, 7 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d4dd41fb951b..a61b06f86d80 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -53,7 +53,6 @@ struct device_node; #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ -#define EEH_PE_PHB_DEAD (1 << 2) /* Dead PHB */ #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e7b76a6bf150..f1676762f6de 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -232,7 +232,6 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) { size_t loglen = 0; struct eeh_dev *edev, *tmp; - bool valid_cfg_log = true; /* * When the PHB is fenced or dead, it's pointless to collect @@ -240,12 +239,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) * 0xFF's. For ER, we still retrieve the data from the PCI * config space. */ - if (eeh_probe_mode_dev() && - (pe->type & EEH_PE_PHB) && - (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD))) - valid_cfg_log = false; - - if (valid_cfg_log) { + if (!(pe->type & EEH_PE_PHB)) { eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -309,7 +303,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* If the PHB has been in problematic state */ eeh_serialize_lock(&flags); - if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) { + if (phb_pe->state & EEH_PE_ISOLATED) { ret = 0; goto out; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index bb61ca58ca6d..1ddc046c69cf 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -682,8 +682,7 @@ static void eeh_handle_special_event(void) phb_pe = eeh_phb_pe_get(hose); if (!phb_pe) continue; - eeh_pe_state_mark(phb_pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED); } eeh_serialize_unlock(flags); @@ -699,8 +698,7 @@ static void eeh_handle_special_event(void) eeh_remove_event(pe); if (rc == EEH_NEXT_ERR_DEAD_PHB) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); else eeh_pe_state_mark(pe, EEH_PE_ISOLATED | EEH_PE_RECOVERING); @@ -724,12 +722,14 @@ static void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { eeh_handle_normal_event(pe); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); if (!phb_pe || - !(phb_pe->state & EEH_PE_PHB_DEAD)) + !(phb_pe->state & EEH_PE_ISOLATED) || + (phb_pe->state & EEH_PE_RECOVERING)) continue; /* Notify all devices to be down */ -- cgit v1.2.3 From 7b401850a1c9b64b010b3d107321df4e7d066995 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:11 +1000 Subject: powerpc/eeh: EEH_PE_ISOLATED not reflect HW state When doing PE reset, EEH_PE_ISOLATED is cleared unconditionally. However, We should remove that if the PE reset has cleared the frozen state successfully. Otherwise, the flag should be kept. The patch fixes the issue. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f1676762f6de..cc728e8c6ee6 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -612,12 +612,6 @@ static void eeh_reset_pe_once(struct eeh_pe *pe) #define PCI_BUS_RST_HOLD_TIME_MSEC 250 msleep(PCI_BUS_RST_HOLD_TIME_MSEC); - /* We might get hit with another EEH freeze as soon as the - * pci slot reset line is dropped. Make sure we don't miss - * these, and clear the flag now. - */ - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); /* After a PCI slot has been reset, the PCI Express spec requires @@ -646,8 +640,10 @@ int eeh_reset_pe(struct eeh_pe *pe) eeh_reset_pe_once(pe); rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if ((rc & flags) == flags) + if ((rc & flags) == flags) { + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); return 0; + } if (rc < 0) { pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x", -- cgit v1.2.3 From d0914f503f7ba2cd078b123983562be8951296d3 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:12 +1000 Subject: powerpc/eeh: Block PCI-CFG access during PE reset We've observed multiple PE reset failures because of PCI-CFG access during that period. Potentially, some device drivers can't support EEH very well and they can't put the device to motionless state before PE reset. So those device drivers might produce PCI-CFG accesses during PE reset. Also, we could have PCI-CFG access from user space (e.g. "lspci"). Since access to frozen PE should return 0xFF's, we can block PCI-CFG access during the period of PE reset so that we won't get recrusive EEH errors. The patch adds flag EEH_PE_RESET, which is kept during PE reset. The PowerNV/pSeries PCI-CFG accessors reuse the flag to block PCI-CFG accordingly. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/kernel/eeh_driver.c | 13 ++++- arch/powerpc/kernel/rtas_pci.c | 66 +++++++++++++++++------ arch/powerpc/platforms/powernv/pci.c | 100 ++++++++++++++++++++++------------- 4 files changed, 126 insertions(+), 54 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index a61b06f86d80..fa32d8dbf1cd 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -53,6 +53,7 @@ struct device_node; #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ +#define EEH_PE_RESET (1 << 2) /* PE reset in progress */ #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 1ddc046c69cf..6d91b51a5ddb 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -451,19 +451,28 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); } - /* Reset the pci controller. (Asserts RST#; resets config space). + /* + * Reset the pci controller. (Asserts RST#; resets config space). * Reconfigure bridges and devices. Don't try to bring the system * up if the reset failed for some reason. + * + * During the reset, it's very dangerous to have uncontrolled PCI + * config accesses. So we prefer to block them. However, controlled + * PCI config accesses initiated from EEH itself are allowed. */ + eeh_pe_state_mark(pe, EEH_PE_RESET); rc = eeh_reset_pe(pe); - if (rc) + if (rc) { + eeh_pe_state_clear(pe, EEH_PE_RESET); return rc; + } pci_lock_rescan_remove(); /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); + eeh_pe_state_clear(pe, EEH_PE_RESET); /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 7d4c7172f38e..c168337aef9d 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -80,10 +80,6 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) if (ret) return PCIBIOS_DEVICE_NOT_FOUND; - if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) - return PCIBIOS_DEVICE_NOT_FOUND; - return PCIBIOS_SUCCESSFUL; } @@ -92,18 +88,39 @@ static int rtas_pci_read_config(struct pci_bus *bus, int where, int size, u32 *val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + *val = 0xFFFFFFFF; + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_read_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && edev->pe->state & EEH_PE_RESET) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + + ret = rtas_read_config(pdn, where, size, val); + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + return ret; } int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) @@ -136,17 +153,34 @@ static int rtas_pci_write_config(struct pci_bus *bus, int where, int size, u32 val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_write_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET)) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + ret = rtas_write_config(pdn, where, size, val); + + return ret; } static struct pci_ops rtas_pci_ops = { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 2de283d2076c..f98cf99c9f8c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -373,9 +373,6 @@ int pnv_pci_cfg_read(struct device_node *dn, struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; -#ifdef CONFIG_EEH - struct eeh_pe *phb_pe = NULL; -#endif s64 rc; switch (size) { @@ -401,31 +398,9 @@ int pnv_pci_cfg_read(struct device_node *dn, default: return PCIBIOS_FUNC_NOT_SUPPORTED; } + cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n", __func__, pdn->busno, pdn->devfn, where, size, *val); - - /* - * Check if the specified PE has been put into frozen - * state. On the other hand, we needn't do that while - * the PHB has been put into frozen state because of - * PHB-fatal errors. - */ -#ifdef CONFIG_EEH - phb_pe = eeh_phb_pe_get(pdn->phb); - if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED)) - return PCIBIOS_SUCCESSFUL; - - if (phb->flags & PNV_PHB_FLAG_EEH) { - if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) - return PCIBIOS_DEVICE_NOT_FOUND; - } else { - pnv_pci_config_check_eeh(phb, dn); - } -#else - pnv_pci_config_check_eeh(phb, dn); -#endif - return PCIBIOS_SUCCESSFUL; } @@ -452,12 +427,35 @@ int pnv_pci_cfg_write(struct device_node *dn, return PCIBIOS_FUNC_NOT_SUPPORTED; } - /* Check if the PHB got frozen due to an error (no response) */ + return PCIBIOS_SUCCESSFUL; +} + +#if CONFIG_EEH +static bool pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + struct eeh_dev *edev = NULL; + struct pnv_phb *phb = hose->private_data; + + /* EEH not enabled ? */ if (!(phb->flags & PNV_PHB_FLAG_EEH)) - pnv_pci_config_check_eeh(phb, dn); + return true; - return PCIBIOS_SUCCESSFUL; + /* PE reset ? */ + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && + (edev->pe->state & EEH_PE_RESET)) + return false; + + return true; +} +#else +static inline pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + return true; } +#endif /* CONFIG_EEH */ static int pnv_pci_read_config(struct pci_bus *bus, unsigned int devfn, @@ -465,16 +463,33 @@ static int pnv_pci_read_config(struct pci_bus *bus, { struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; + struct pnv_phb *phb; + bool found = false; + int ret; + *val = 0xFFFFFFFF; for (dn = busdn->child; dn; dn = dn->sibling) { pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) - return pnv_pci_cfg_read(dn, where, size, val); + if (pdn && pdn->devfn == devfn) { + phb = pdn->phb->private_data; + found = true; + break; + } } - *val = 0xFFFFFFFF; - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + ret = pnv_pci_cfg_read(dn, where, size, val); + if (phb->flags & PNV_PHB_FLAG_EEH) { + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + } else { + pnv_pci_config_check_eeh(phb, dn); + } + + return ret; } static int pnv_pci_write_config(struct pci_bus *bus, @@ -483,14 +498,27 @@ static int pnv_pci_write_config(struct pci_bus *bus, { struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; + struct pnv_phb *phb; + bool found = false; + int ret; for (dn = busdn->child; dn; dn = dn->sibling) { pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) - return pnv_pci_cfg_write(dn, where, size, val); + if (pdn && pdn->devfn == devfn) { + phb = pdn->phb->private_data; + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + ret = pnv_pci_cfg_write(dn, where, size, val); + if (!(phb->flags & PNV_PHB_FLAG_EEH)) + pnv_pci_config_check_eeh(phb, dn); + + return ret; } struct pci_ops pnv_pci_ops = { -- cgit v1.2.3 From 78954700631f54c3caae22647eb1f544fc4240d4 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:14 +1000 Subject: powerpc/eeh: Avoid I/O access during PE reset We have suffered recrusive frozen PE a lot, which was caused by IO accesses during the PE reset. Ben came up with the good idea to keep frozen PE until recovery (BAR restore) gets done. With that, IO accesses during PE reset are dropped by hardware and wouldn't incur the recrusive frozen PE any more. The patch implements the idea. We don't clear the frozen state until PE reset is done completely. During the period, the EEH core expects unfrozen state from backend to keep going. So we have to reuse EEH_PE_RESET flag, which has been set during PE reset, to return normal state from backend. The side effect is we have to clear frozen state for towice (PE reset and clear it explicitly), but that's harmless. We have some limitations on pHyp. pHyp doesn't allow to enable IO or DMA for unfrozen PE. So we don't enable them on unfrozen PE in eeh_pci_enable(). We have to enable IO before grabbing logs on pHyp. Otherwise, 0xFF's is always returned from PCI config space. Also, we had wrong return value from eeh_pci_enable() for EEH_OPT_THAW_DMA case. The patch fixes it too. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 50 ++++++++++++++---- arch/powerpc/kernel/eeh_driver.c | 35 +++++++++++++ arch/powerpc/platforms/powernv/eeh-ioda.c | 84 +++++++++---------------------- 3 files changed, 99 insertions(+), 70 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index cc728e8c6ee6..25f37532093d 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -238,9 +238,13 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) * the data from PCI config space because it should return * 0xFF's. For ER, we still retrieve the data from the PCI * config space. + * + * For pHyp, we have to enable IO for log retrieval. Otherwise, + * 0xFF's is always returned from PCI config space. */ if (!(pe->type & EEH_PE_PHB)) { - eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (eeh_probe_mode_devtree()) + eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -509,16 +513,42 @@ EXPORT_SYMBOL(eeh_check_failure); */ int eeh_pci_enable(struct eeh_pe *pe, int function) { - int rc; + int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + + /* + * pHyp doesn't allow to enable IO or DMA on unfrozen PE. + * Also, it's pointless to enable them on unfrozen PE. So + * we have the check here. + */ + if (function == EEH_OPT_THAW_MMIO || + function == EEH_OPT_THAW_DMA) { + rc = eeh_ops->get_state(pe, NULL); + if (rc < 0) + return rc; + + /* Needn't to enable or already enabled */ + if ((rc == EEH_STATE_NOT_SUPPORT) || + ((rc & flags) == flags)) + return 0; + } rc = eeh_ops->set_option(pe, function); if (rc) - pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n", - __func__, function, pe->phb->global_number, pe->addr, rc); + pr_warn("%s: Unexpected state change %d on " + "PHB#%d-PE#%x, err=%d\n", + __func__, function, pe->phb->global_number, + pe->addr, rc); rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && - (function == EEH_OPT_THAW_MMIO)) + if (rc <= 0) + return rc; + + if ((function == EEH_OPT_THAW_MMIO) && + (rc & EEH_STATE_MMIO_ENABLED)) + return 0; + + if ((function == EEH_OPT_THAW_DMA) && + (rc & EEH_STATE_DMA_ENABLED)) return 0; return rc; @@ -639,11 +669,13 @@ int eeh_reset_pe(struct eeh_pe *pe) for (i=0; i<3; i++) { eeh_reset_pe_once(pe); + /* + * EEH_PE_ISOLATED is expected to be removed after + * BAR restore. + */ rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if ((rc & flags) == flags) { - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + if ((rc & flags) == flags) return 0; - } if (rc < 0) { pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x", diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 6d91b51a5ddb..1f1e2cc045a9 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -417,6 +417,36 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) return NULL; } +/* + * Explicitly clear PE's frozen state for PowerNV where + * we have frozen PE until BAR restore is completed. It's + * harmless to clear it for pSeries. To be consistent with + * PE reset (for 3 times), we try to clear the frozen state + * for 3 times as well. + */ +static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) +{ + int i, rc; + + for (i = 0; i < 3; i++) { + rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (rc) + continue; + rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); + if (!rc) + break; + } + + /* The PE has been isolated, clear it */ + if (rc) + pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, rc); + else + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + + return rc; +} + /** * eeh_reset_device - Perform actual reset of a pci slot * @pe: EEH PE @@ -474,6 +504,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_pe_restore_bars(pe); eeh_pe_state_clear(pe, EEH_PE_RESET); + /* Clear frozen state */ + rc = eeh_clear_pe_frozen_state(pe); + if (rc) + return rc; + /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, * this is a hack, but if we don't do this, and try to bring diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index ed6c68634c9c..6bdae8d84463 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -268,6 +268,21 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) return EEH_STATE_NOT_SUPPORT; } + /* + * If we're in middle of PE reset, return normal + * state to keep EEH core going. For PHB reset, we + * still expect to have fenced PHB cleared with + * PHB reset. + */ + if (!(pe->type & EEH_PE_PHB) && + (pe->state & EEH_PE_RESET)) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + /* Retrieve PE status through OPAL */ pe_no = pe->addr; ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, @@ -347,52 +362,6 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) return result; } -static int ioda_eeh_pe_clear(struct eeh_pe *pe) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - u32 pe_no; - u8 fstate; - u16 pcierr; - s64 ret; - - pe_no = pe->addr; - hose = pe->phb; - phb = pe->phb->private_data; - - /* Clear the EEH error on the PE */ - ret = opal_pci_eeh_freeze_clear(phb->opal_id, - pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); - if (ret) { - pr_err("%s: Failed to clear EEH error for " - "PHB#%x-PE#%x, err=%lld\n", - __func__, hose->global_number, pe_no, ret); - return -EIO; - } - - /* - * Read the PE state back and verify that the frozen - * state has been removed. - */ - ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, - &fstate, &pcierr, NULL); - if (ret) { - pr_err("%s: Failed to get EEH status on " - "PHB#%x-PE#%x\n, err=%lld\n", - __func__, hose->global_number, pe_no, ret); - return -EIO; - } - - if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) { - pr_err("%s: Frozen state not cleared on " - "PHB#%x-PE#%x, sts=%x\n", - __func__, hose->global_number, pe_no, fstate); - return -EIO; - } - - return 0; -} - static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) { s64 rc = OPAL_HARDWARE; @@ -523,21 +492,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) struct pci_bus *bus; int ret; - /* - * Anyway, we have to clear the problematic state for the - * corresponding PE. However, we needn't do it if the PE - * is PHB associated. That means the PHB is having fatal - * errors and it needs reset. Further more, the AIB interface - * isn't reliable any more. - */ - if (!(pe->type & EEH_PE_PHB) && - (option == EEH_RESET_HOT || - option == EEH_RESET_FUNDAMENTAL)) { - ret = ioda_eeh_pe_clear(pe); - if (ret) - return -EIO; - } - /* * The rules applied to reset, either fundamental or hot reset: * @@ -545,6 +499,14 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) * direct upstream bridge isn't root bridge, we always take hot * reset no matter what option (fundamental or hot) is. Otherwise, * we should do the reset according to the required option. + * + * Here, we have different design to pHyp, which always clear the + * frozen state during PE reset. However, the good idea here from + * benh is to keep frozen state before we get PE reset done completely + * (until BAR restore). With the frozen state, HW drops illegal IO + * or MMIO access, which can incur recrusive frozen PE during PE + * reset. The side effect is that EEH core has to clear the frozen + * state explicitly after BAR restore. */ if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); -- cgit v1.2.3 From 2d86c385a15452bdc5b7d09d6881c35746af0ee6 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:15 +1000 Subject: powerpc/eeh: Cleanup eeh_gather_pci_data() The patch replaces printk(KERN_WARNING ...) with pr_warn() in the function eeh_gather_pci_data(). Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 25f37532093d..c6d8f7e6888a 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -151,18 +151,18 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) int n = 0; n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); - printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name); + pr_warn("EEH: of node=%s\n", dn->full_name); eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); - printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg); + pr_warn("EEH: PCI device/vendor: %08x\n", cfg); eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg); + pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); if (!dev) { - printk(KERN_WARNING "EEH: no PCI device for this of node\n"); + pr_warn("EEH: no PCI device for this of node\n"); return n; } @@ -170,11 +170,11 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg); + pr_warn("EEH: Bridge secondary status: %04x\n", cfg); eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg); + pr_warn("EEH: Bridge control: %04x\n", cfg); } /* Dump out the PCI-X command and status regs */ @@ -182,35 +182,34 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) if (cap) { eeh_ops->read_config(dn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg); + pr_warn("EEH: PCI-X cmd: %08x\n", cfg); eeh_ops->read_config(dn, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg); + pr_warn("EEH: PCI-X status: %08x\n", cfg); } /* If PCI-E capable, dump PCI-E cap 10, and the AER */ if (pci_is_pcie(dev)) { n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); - printk(KERN_WARNING - "EEH: PCI-E capabilities and status follow:\n"); + pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); + pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg); } cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); if (cap) { n += scnprintf(buf+n, len-n, "pci-e AER:\n"); - printk(KERN_WARNING - "EEH: PCI-E AER capability register set follows:\n"); + pr_warn("EEH: PCI-E AER capability register " + "set follows:\n"); for (i=0; i<14; i++) { eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg); + pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); } } } -- cgit v1.2.3 From 2a18dfc6ee2ea00bba767f6968f1a107fdd8e687 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:16 +1000 Subject: powerpc/eeh: Use cached capability for log dump When calling into eeh_gather_pci_data() on pSeries platform, we possiblly don't have pci_dev instance yet, but eeh_dev is always ready. So we use cached capability from eeh_dev instead of pci_dev for log dump there. In order to keep things unified, we also cache PCI capability positions to eeh_dev for PowerNV as well. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 4 ++- arch/powerpc/kernel/eeh.c | 39 ++++++++++++---------------- arch/powerpc/platforms/powernv/eeh-powernv.c | 4 +++ arch/powerpc/platforms/pseries/eeh_pseries.c | 32 +++++++++++++++++++++++ 4 files changed, 56 insertions(+), 23 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index fa32d8dbf1cd..f0183e36f610 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -99,7 +99,9 @@ struct eeh_dev { int config_addr; /* Config address */ int pe_config_addr; /* PE config address */ u32 config_space[16]; /* Saved PCI config space */ - u8 pcie_cap; /* Saved PCIe capability */ + int pcix_cap; /* Saved PCIx capability */ + int pcie_cap; /* Saved PCIe capability */ + int aer_cap; /* Saved AER capability */ struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ struct pci_controller *phb; /* Associated PHB */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c6d8f7e6888a..69df8985fc8b 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -145,7 +145,6 @@ static struct eeh_stats eeh_stats; static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) { struct device_node *dn = eeh_dev_to_of_node(edev); - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); u32 cfg; int cap, i; int n = 0; @@ -161,13 +160,8 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); - if (!dev) { - pr_warn("EEH: no PCI device for this of node\n"); - return n; - } - /* Gather bridge-specific registers */ - if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { + if (edev->mode & EEH_DEV_BRIDGE) { eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); pr_warn("EEH: Bridge secondary status: %04x\n", cfg); @@ -178,7 +172,7 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) } /* Dump out the PCI-X command and status regs */ - cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); + cap = edev->pcix_cap; if (cap) { eeh_ops->read_config(dn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); @@ -189,28 +183,29 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) pr_warn("EEH: PCI-X status: %08x\n", cfg); } - /* If PCI-E capable, dump PCI-E cap 10, and the AER */ - if (pci_is_pcie(dev)) { + /* If PCI-E capable, dump PCI-E cap 10 */ + cap = edev->pcie_cap; + if (cap) { n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg); } + } - cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (cap) { - n += scnprintf(buf+n, len-n, "pci-e AER:\n"); - pr_warn("EEH: PCI-E AER capability register " - "set follows:\n"); - - for (i=0; i<14; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); - n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); - } + /* If AER capable, dump it */ + cap = edev->aer_cap; + if (cap) { + n += scnprintf(buf+n, len-n, "pci-e AER:\n"); + pr_warn("EEH: PCI-E AER capability register set follows:\n"); + + for (i=0; i<14; i++) { + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); + pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); } } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a59788e83b8b..56a206f32f77 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -126,6 +126,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) edev->mode &= 0xFFFFFF00; if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) edev->mode |= EEH_DEV_BRIDGE; + edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (pci_is_pcie(dev)) { edev->pcie_cap = pci_pcie_cap(dev); @@ -133,6 +134,9 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) edev->mode |= EEH_DEV_ROOT_PORT; else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) edev->mode |= EEH_DEV_DS_PORT; + + edev->aer_cap = pci_find_ext_capability(dev, + PCI_EXT_CAP_ID_ERR); } edev->config_addr = ((dev->bus->number << 8) | dev->devfn); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 8a8f0472d98f..9d58a53548f2 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -175,6 +175,36 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } +static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + u32 header; + int pos = 256; + int ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + return 0; + else if (!header) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < 256) + break; + + if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** * pseries_eeh_of_probe - EEH probe on the given device * @dn: OF node @@ -220,7 +250,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) * or PCIe switch downstream port. */ edev->class_code = class_code; + edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; -- cgit v1.2.3 From 8a5ad35686fa81da7d8d07e9dd7041ac4a2ac0d7 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:17 +1000 Subject: powerpc/eeh: Cleanup EEH subsystem variables There're 2 EEH subsystem variables: eeh_subsystem_enabled and eeh_probe_mode. We needn't maintain 2 variables and we can just have one variable and introduce different flags. The patch also introduces additional flag EEH_FORCE_DISABLE, which will be used to disable EEH subsystem via boot parameter ("eeh=off") in future. Besides, the patch also introduces flag EEH_ENABLED, which is changed to disable or enable EEH functionality on the fly through debugfs entry in future. With the patch applied, the creteria to check the enabled EEH functionality is changed to: !EEH_FORCE_DISABLED && EEH_ENABLED : Enabled Other cases : Disabled Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 29 +++++++++++++++++++---------- arch/powerpc/kernel/eeh.c | 31 +++++++++++++++---------------- 2 files changed, 34 insertions(+), 26 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index f0183e36f610..f4a93218fbcb 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -32,6 +32,12 @@ struct device_node; #ifdef CONFIG_EEH +/* EEH subsystem flags */ +#define EEH_ENABLED 0x1 /* EEH enabled */ +#define EEH_FORCE_DISABLED 0x2 /* EEH disabled */ +#define EEH_PROBE_MODE_DEV 0x4 /* From PCI device */ +#define EEH_PROBE_MODE_DEVTREE 0x8 /* From device tree */ + /* * The struct is used to trace PE related EEH functionality. * In theory, there will have one instance of the struct to @@ -173,37 +179,40 @@ struct eeh_ops { int (*restore_config)(struct device_node *dn); }; +extern int eeh_subsystem_flags; extern struct eeh_ops *eeh_ops; -extern bool eeh_subsystem_enabled; extern raw_spinlock_t confirm_error_lock; -extern int eeh_probe_mode; static inline bool eeh_enabled(void) { - return eeh_subsystem_enabled; + if ((eeh_subsystem_flags & EEH_FORCE_DISABLED) || + !(eeh_subsystem_flags & EEH_ENABLED)) + return false; + + return true; } static inline void eeh_set_enable(bool mode) { - eeh_subsystem_enabled = mode; + if (mode) + eeh_subsystem_flags |= EEH_ENABLED; + else + eeh_subsystem_flags &= ~EEH_ENABLED; } -#define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ -#define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ - static inline void eeh_probe_mode_set(int flag) { - eeh_probe_mode = flag; + eeh_subsystem_flags |= flag; } static inline int eeh_probe_mode_devtree(void) { - return (eeh_probe_mode == EEH_PROBE_MODE_DEVTREE); + return (eeh_subsystem_flags & EEH_PROBE_MODE_DEVTREE); } static inline int eeh_probe_mode_dev(void) { - return (eeh_probe_mode == EEH_PROBE_MODE_DEV); + return (eeh_subsystem_flags & EEH_PROBE_MODE_DEV); } static inline void eeh_serialize_lock(unsigned long *flags) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 69df8985fc8b..06d2b7c6b661 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -87,22 +87,21 @@ /* Time to wait for a PCI slot to report status, in milliseconds */ #define PCI_BUS_RESET_WAIT_MSEC (5*60*1000) -/* Platform dependent EEH operations */ -struct eeh_ops *eeh_ops = NULL; - -bool eeh_subsystem_enabled = false; -EXPORT_SYMBOL(eeh_subsystem_enabled); - /* - * EEH probe mode support. The intention is to support multiple - * platforms for EEH. Some platforms like pSeries do PCI emunation - * based on device tree. However, other platforms like powernv probe - * PCI devices from hardware. The flag is used to distinguish that. - * In addition, struct eeh_ops::probe would be invoked for particular - * OF node or PCI device so that the corresponding PE would be created - * there. + * EEH probe mode support, which is part of the flags, + * is to support multiple platforms for EEH. Some platforms + * like pSeries do PCI emunation based on device tree. + * However, other platforms like powernv probe PCI devices + * from hardware. The flag is used to distinguish that. + * In addition, struct eeh_ops::probe would be invoked for + * particular OF node or PCI device so that the corresponding + * PE would be created there. */ -int eeh_probe_mode; +int eeh_subsystem_flags; +EXPORT_SYMBOL(eeh_subsystem_flags); + +/* Platform dependent EEH operations */ +struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); @@ -842,8 +841,8 @@ int eeh_init(void) &hose_list, list_node) pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL); } else { - pr_warning("%s: Invalid probe mode %d\n", - __func__, eeh_probe_mode); + pr_warn("%s: Invalid probe mode %x", + __func__, eeh_subsystem_flags); return -EINVAL; } -- cgit v1.2.3 From 7f52a526f64c69c913f0027fbf43821ff0b3a7d7 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:18 +1000 Subject: powerpc/eeh: Allow to disable EEH The patch introduces bootarg "eeh=off" to disable EEH functinality. Also, it creates /sys/kerenl/debug/powerpc/eeh_enable to disable or enable EEH functionality. By default, we have the functionality enabled. For PowerNV platform, we will restore to have the conventional mechanism of clearing frozen PE during PCI config access if we're going to disable EEH functionality. Conversely, we will rely on EEH for error recovery. The patch also fixes the issue that we missed to cover the case of disabled EEH functionality in function ioda_eeh_event(). Those events driven by interrupt should be cleared to avoid endless reporting. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 47 ++++++++++++++++++++++++++++++- arch/powerpc/platforms/powernv/eeh-ioda.c | 29 +++++++++++++++---- arch/powerpc/platforms/powernv/pci.h | 1 + 3 files changed, 70 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 06d2b7c6b661..1e409a2ff88b 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -22,6 +22,7 @@ */ #include +#include #include #include #include @@ -132,6 +133,15 @@ static struct eeh_stats eeh_stats; #define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) +static int __init eeh_setup(char *str) +{ + if (!strcmp(str, "off")) + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + return 1; +} +__setup("eeh=", eeh_setup); + /** * eeh_gather_pci_data - Copy assorted PCI config space registers to buff * @edev: device to report data for @@ -1117,10 +1127,45 @@ static const struct file_operations proc_eeh_operations = { .release = single_release, }; +#ifdef CONFIG_DEBUG_FS +static int eeh_enable_dbgfs_set(void *data, u64 val) +{ + if (val) + eeh_subsystem_flags &= ~EEH_FORCE_DISABLED; + else + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + /* Notify the backend */ + if (eeh_ops->post_init) + eeh_ops->post_init(); + + return 0; +} + +static int eeh_enable_dbgfs_get(void *data, u64 *val) +{ + if (eeh_enabled()) + *val = 0x1ul; + else + *val = 0x0ul; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, + eeh_enable_dbgfs_set, "0x%llx\n"); +#endif + static int __init eeh_init_proc(void) { - if (machine_is(pseries) || machine_is(powernv)) + if (machine_is(pseries) || machine_is(powernv)) { proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations); +#ifdef CONFIG_DEBUG_FS + debugfs_create_file("eeh_enable", 0600, + powerpc_debugfs_root, NULL, + &eeh_enable_dbgfs_ops); +#endif + } + return 0; } __initcall(eeh_init_proc); diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 6bdae8d84463..35ec394f784f 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -42,11 +42,19 @@ static int ioda_eeh_event(struct notifier_block *nb, { uint64_t changed_evts = (uint64_t)change; - /* We simply send special EEH event */ - if ((changed_evts & OPAL_EVENT_PCI_ERROR) && - (events & OPAL_EVENT_PCI_ERROR) && - eeh_enabled()) + /* + * We simply send special EEH event if EEH has + * been enabled, or clear pending events in + * case that we enable EEH soon + */ + if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || + !(events & OPAL_EVENT_PCI_ERROR)) + return 0; + + if (eeh_enabled()) eeh_send_failure_event(NULL); + else + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); return 0; } @@ -141,7 +149,9 @@ static int ioda_eeh_post_init(struct pci_controller *hose) } #ifdef CONFIG_DEBUG_FS - if (phb->dbgfs) { + if (!phb->has_dbgfs && phb->dbgfs) { + phb->has_dbgfs = 1; + debugfs_create_file("err_injct_outbound", 0600, phb->dbgfs, hose, &ioda_eeh_outb_dbgfs_ops); @@ -154,7 +164,14 @@ static int ioda_eeh_post_init(struct pci_controller *hose) } #endif - phb->flags |= PNV_PHB_FLAG_EEH; + /* If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; return 0; } diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 94e3495b7f2b..39ec6978e809 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -101,6 +101,7 @@ struct pnv_phb { #endif #ifdef CONFIG_DEBUG_FS + int has_dbgfs; struct dentry *dbgfs; #endif -- cgit v1.2.3 From d2b0f6f77ee525811b6efe864efa6a4eb82eea73 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:19 +1000 Subject: powerpc/eeh: No hotplug on permanently removed dev The issue was detected in a bit complicated test case where we have multiple hierarchical PEs shown as following figure: +-----------------+ | PE#3 p2p#0 | | p2p#1 | +-----------------+ | +-----------------+ | PE#4 pdev#0 | | pdev#1 | +-----------------+ PE#4 (have 2 PCI devices) is the child of PE#3, which has 2 p2p bridges. We accidentally had less-known scenario: PE#4 was removed permanently from the system because of permanent failure (e.g. exceeding the max allowd failure times in last hour), then we detects EEH errors on PE#3 and tried to recover it. However, eeh_dev instances for pdev#0/1 were not detached from PE#4, which was still connected to PE#3. All of that was because of the fact that we rely on count-based pcibios_release_device(), which isn't reliable enough. When doing recovery for PE#3, we still apply hotplug on PE#4 and pdev#0/1, which are not valid any more. Eventually, we run into kernel crash. The patch fixes above issue from two aspects. For unplug, we simply skip those permanently removed PE, whose state is (EEH_PE_STATE_ISOLATED && !EEH_PE_STATE_RECOVERING) and its frozen count should be greater than EEH_MAX_ALLOWED_FREEZES. For plug, we marked all permanently removed EEH devices with EEH_DEV_REMOVED and return 0xFF's on read its PCI config so that PCI core will omit them. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/include/asm/ppc-pci.h | 1 + arch/powerpc/kernel/eeh_driver.c | 48 ++++++++++++++++++++++++++++++------ arch/powerpc/kernel/eeh_pe.c | 47 +++++++++++++++++++++++++++++------ arch/powerpc/kernel/pci_of_scan.c | 9 +++++++ arch/powerpc/platforms/powernv/pci.c | 13 +++++++--- 6 files changed, 100 insertions(+), 19 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index f4a93218fbcb..2841ecac4c47 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -98,6 +98,7 @@ struct eeh_pe { #define EEH_DEV_NO_HANDLER (1 << 8) /* No error handler */ #define EEH_DEV_SYSFS (1 << 9) /* Sysfs created */ +#define EEH_DEV_REMOVED (1 << 10) /* Removed permanently */ struct eeh_dev { int mode; /* EEH mode */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index ed57fa7920c8..db1e2b8eff3c 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -58,6 +58,7 @@ int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); void eeh_pe_state_mark(struct eeh_pe *pe, int state); void eeh_pe_state_clear(struct eeh_pe *pe, int state); +void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 1f1e2cc045a9..f99ba9b76322 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -171,6 +171,15 @@ static void eeh_enable_irq(struct pci_dev *dev) } } +static bool eeh_dev_removed(struct eeh_dev *edev) +{ + /* EEH device removed ? */ + if (!edev || (edev->mode & EEH_DEV_REMOVED)) + return true; + + return false; +} + /** * eeh_report_error - Report pci error to each device driver * @data: eeh device @@ -187,10 +196,8 @@ static void *eeh_report_error(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - /* We might not have the associated PCI device, - * then we should continue for next one. - */ - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_frozen; driver = eeh_pcid_get(dev); @@ -230,6 +237,9 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; + if (!dev || eeh_dev_removed(edev)) + return NULL; + driver = eeh_pcid_get(dev); if (!driver) return NULL; @@ -267,7 +277,8 @@ static void *eeh_report_reset(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -307,7 +318,8 @@ static void *eeh_report_resume(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -343,7 +355,8 @@ static void *eeh_report_failure(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_perm_failure; driver = eeh_pcid_get(dev); @@ -380,6 +393,16 @@ static void *eeh_rmv_device(void *data, void *userdata) if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; + /* + * We rely on count-based pcibios_release_device() to + * detach permanently offlined PEs. Unfortunately, that's + * not reliable enough. We might have the permanently + * offlined PEs attached, but we needn't take care of + * them and their child devices. + */ + if (eeh_dev_removed(edev)) + return NULL; + driver = eeh_pcid_get(dev); if (driver) { eeh_pcid_put(dev); @@ -694,8 +717,17 @@ perm_error: /* Notify all devices that they're about to go down. */ eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - /* Shut down the device drivers for good. */ + /* Mark the PE to be removed permanently */ + pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1; + + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ if (frozen_bus) { + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); pci_unlock_rescan_remove(); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f0c353fa655a..995c2a284630 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -503,13 +503,17 @@ static void *__eeh_pe_state_mark(void *data, void *flag) struct eeh_dev *edev, *tmp; struct pci_dev *pdev; - /* - * Mark the PE with the indicated state. Also, - * the associated PCI device will be put into - * I/O frozen state to avoid I/O accesses from - * the PCI device driver. - */ + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING))) + return NULL; + pe->state |= state; + + /* Offline PCI devices if applicable */ + if (state != EEH_PE_ISOLATED) + return NULL; + eeh_pe_for_each_dev(pe, edev, tmp) { pdev = eeh_dev_to_pci_dev(edev); if (pdev) @@ -532,6 +536,27 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); } +static void *__eeh_pe_dev_mode_mark(void *data, void *flag) +{ + struct eeh_dev *edev = data; + int mode = *((int *)flag); + + edev->mode |= mode; + + return NULL; +} + +/** + * eeh_pe_dev_state_mark - Mark state for all device under the PE + * @pe: EEH PE + * + * Mark specific state for all child devices of the PE. + */ +void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode) +{ + eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode); +} + /** * __eeh_pe_state_clear - Clear state for the PE * @data: EEH PE @@ -546,8 +571,16 @@ static void *__eeh_pe_state_clear(void *data, void *flag) struct eeh_pe *pe = (struct eeh_pe *)data; int state = *((int *)flag); + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & EEH_PE_ISOLATED)) + return NULL; + pe->state &= ~state; - pe->check_count = 0; + + /* Clear check count since last isolation */ + if (state & EEH_PE_ISOLATED) + pe->check_count = 0; return NULL; } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 83c26d829991..ea6470c21f4e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -304,6 +304,9 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, struct pci_dev *dev = NULL; const __be32 *reg; int reglen, devfn; +#ifdef CONFIG_EEH + struct eeh_dev *edev = of_node_to_eeh_dev(dn); +#endif pr_debug(" * %s\n", dn->full_name); if (!of_device_is_available(dn)) @@ -321,6 +324,12 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, return dev; } + /* Device removed permanently ? */ +#ifdef CONFIG_EEH + if (edev && (edev->mode & EEH_DEV_REMOVED)) + return NULL; +#endif + /* create a new pci_dev for this device */ dev = of_create_pci_dev(dn, bus, devfn); if (!dev) diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f98cf99c9f8c..eefbfcc3fd8c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -441,11 +441,16 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose, if (!(phb->flags & PNV_PHB_FLAG_EEH)) return true; - /* PE reset ? */ + /* PE reset or device removed ? */ edev = of_node_to_eeh_dev(dn); - if (edev && edev->pe && - (edev->pe->state & EEH_PE_RESET)) - return false; + if (edev) { + if (edev->pe && + (edev->pe->state & EEH_PE_RESET)) + return false; + + if (edev->mode & EEH_DEV_REMOVED) + return false; + } return true; } -- cgit v1.2.3 From 26833a5029b710b12f00607fa255ce86909836ad Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:23 +1000 Subject: powerpc/eeh: Make the delay for PE reset unified Basically, we have 3 types of resets to fulfil PE reset: fundamental, hot and PHB reset. For the later 2 cases, we need PCI bus reset hold and settlement delay as specified by PCI spec. PowerNV and pSeries platforms are running on top of different firmware and some of the delays have been covered by underly firmware (PowerNV). The patch makes the delays unified to be done in backend, instead of EEH core. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 10 ++++++++++ arch/powerpc/kernel/eeh.c | 13 ------------- arch/powerpc/platforms/powernv/eeh-ioda.c | 12 +++++++++++- arch/powerpc/platforms/pseries/eeh_pseries.c | 10 +++++++++- 4 files changed, 30 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 2841ecac4c47..b76f58c124ca 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -38,6 +38,16 @@ struct device_node; #define EEH_PROBE_MODE_DEV 0x4 /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE 0x8 /* From device tree */ +/* + * Delay for PE reset, all in ms + * + * PCI specification has reset hold time of 100 milliseconds. + * We have 250 milliseconds here. The PCI bus settlement time + * is specified as 1.5 seconds and we have 1.8 seconds. + */ +#define EEH_PE_RST_HOLD_TIME 250 +#define EEH_PE_RST_SETTLE_TIME 1800 + /* * The struct is used to trace PE related EEH functionality. * In theory, there will have one instance of the struct to diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 1e409a2ff88b..3764fb788d6c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -639,20 +639,7 @@ static void eeh_reset_pe_once(struct eeh_pe *pe) else eeh_ops->reset(pe, EEH_RESET_HOT); - /* The PCI bus requires that the reset be held high for at least - * a 100 milliseconds. We wait a bit longer 'just in case'. - */ -#define PCI_BUS_RST_HOLD_TIME_MSEC 250 - msleep(PCI_BUS_RST_HOLD_TIME_MSEC); - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - - /* After a PCI slot has been reset, the PCI Express spec requires - * a 1.5 second idle time for the bus to stabilize, before starting - * up traffic. - */ -#define PCI_BUS_SETTLE_TIME_MSEC 1800 - msleep(PCI_BUS_SETTLE_TIME_MSEC); } /** diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 0844e00ccdd8..268cd46af8f1 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -417,9 +417,13 @@ static int ioda_eeh_phb_reset(struct pci_controller *hose, int option) /* * Poll state of the PHB until the request is done - * successfully. + * successfully. The PHB reset is usually PHB complete + * reset followed by hot reset on root bus. So we also + * need the PCI bus settlement delay. */ rc = ioda_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); out: if (rc != OPAL_SUCCESS) return -EIO; @@ -457,6 +461,8 @@ static int ioda_eeh_root_reset(struct pci_controller *hose, int option) /* Poll state of the PHB until the request is done */ rc = ioda_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); out: if (rc != OPAL_SUCCESS) return -EIO; @@ -480,11 +486,15 @@ static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl |= PCI_BRIDGE_CTL_BUS_RESET; eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_HOLD_TIME); break; case EEH_RESET_DEACTIVATE: eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_SETTLE_TIME); break; } diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 2f1ba64fc831..0bec0c02c5e7 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -532,11 +532,19 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) /* If fundamental-reset not supported, try hot-reset */ if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { + option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), EEH_RESET_HOT); + BUID_LO(pe->phb->buid), option); } + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + return ret; } -- cgit v1.2.3 From d92a208d086063ecc785b4588f74ab42268cbc4b Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:24 +1000 Subject: powerpc/pci: Mask linkDown on resetting PCI bus The problem was initially reported by Wendy who tried pass through IPR adapter, which was connected to PHB root port directly, to KVM based guest. When doing that, pci_reset_bridge_secondary_bus() was called by VFIO driver and linkDown was detected by the root port. That caused all PEs to be frozen. The patch fixes the issue by routing the reset for the secondary bus of root port to underly firmware. For that, one more weak function pci_reset_secondary_bus() is introduced so that the individual platforms can override that and do specific reset for bridge's secondary bus. Reported-by: Wendy Xiong Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/machdep.h | 3 +++ arch/powerpc/kernel/pci-common.c | 20 ++++++++++++++++ arch/powerpc/platforms/powernv/eeh-ioda.c | 38 +++++++++++++++++++++++++++++-- arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci.h | 1 + drivers/pci/pci.c | 21 ++++++++++------- 6 files changed, 74 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 5b6c03f1058f..240b137ce0cf 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -241,6 +241,9 @@ struct machdep_calls { /* Called during PCI resource reassignment */ resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); + /* Reset the secondary bus of bridge */ + void (*pcibios_reset_secondary_bus)(struct pci_dev *dev); + /* Called to shutdown machine specific hardware not already controlled * by other drivers. */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index d9476c1fc959..f9ca5091840c 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -120,6 +121,25 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, return 1; } +void pcibios_reset_secondary_bus(struct pci_dev *dev) +{ + u16 ctrl; + + if (ppc_md.pcibios_reset_secondary_bus) { + ppc_md.pcibios_reset_secondary_bus(dev); + return; + } + + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + msleep(2); + + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + ssleep(1); +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 268cd46af8f1..58ef80987eed 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -474,6 +474,8 @@ static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) { struct device_node *dn = pci_device_to_OF_node(dev); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + int aer = edev ? edev->aer_cap : 0; u32 ctrl; pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", @@ -483,24 +485,56 @@ static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) switch (option) { case EEH_RESET_FUNDAMENTAL: case EEH_RESET_HOT: + /* Don't report linkDown event */ + if (aer) { + eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl |= PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl |= PCI_BRIDGE_CTL_BUS_RESET; eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_HOLD_TIME); + break; case EEH_RESET_DEACTIVATE: eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_SETTLE_TIME); + + /* Continue reporting linkDown event */ + if (aer) { + eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl &= ~PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + break; } return 0; } +void pnv_pci_reset_secondary_bus(struct pci_dev *dev) +{ + struct pci_controller *hose; + + if (pci_is_root_bus(dev->bus)) { + hose = pci_bus_to_host(dev->bus); + ioda_eeh_root_reset(hose, EEH_RESET_HOT); + ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); + } else { + ioda_eeh_bridge_reset(dev, EEH_RESET_HOT); + ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); + } +} + /** * ioda_eeh_reset - Reset the indicated PE * @pe: EEH PE diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 98824aa99173..a179ff00be3e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1386,6 +1386,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; + ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus; pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 39ec6978e809..34a09740aad3 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -204,5 +204,6 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); +extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); #endif /* __POWERNV_PCI_H */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7325d43bf030..633382d227f4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3167,14 +3167,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return 0; } -/** - * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. - * @dev: Bridge device - * - * Use the bridge control register to assert reset on the secondary bus. - * Devices on the secondary bus are left in power-on state. - */ -void pci_reset_bridge_secondary_bus(struct pci_dev *dev) +void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; @@ -3199,6 +3192,18 @@ void pci_reset_bridge_secondary_bus(struct pci_dev *dev) */ ssleep(1); } + +/** + * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. + * @dev: Bridge device + * + * Use the bridge control register to assert reset on the secondary bus. + * Devices on the secondary bus are left in power-on state. + */ +void pci_reset_bridge_secondary_bus(struct pci_dev *dev) +{ + pcibios_reset_secondary_bus(dev); +} EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) -- cgit v1.2.3 From 35845a7826a27eb1c16ee5b0c5a0307159c1d1c4 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:26 +1000 Subject: powerpc/eeh: Can't recover from non-PE-reset case When PCI_ERS_RESULT_CAN_RECOVER returned from device drivers, the EEH core should enable I/O and DMA for the affected PE. However, it was missed to have DMA enabled in eeh_handle_normal_event(). Besides, the frozen state of the affected PE should be cleared after successful recovery, but we didn't. The patch fixes both of the issues as above. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh_driver.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index f99ba9b76322..7100a5b96e70 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -640,7 +640,6 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) result = PCI_ERS_RESULT_NEED_RESET; } else { pr_info("EEH: Notify device drivers to resume I/O\n"); - result = PCI_ERS_RESULT_NONE; eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); } } @@ -652,10 +651,17 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) if (rc < 0) goto hard_fail; - if (rc) + if (rc) { result = PCI_ERS_RESULT_NEED_RESET; - else + } else { + /* + * We didn't do PE reset for the case. The PE + * is still in frozen state. Clear it before + * resuming the PE. + */ + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); result = PCI_ERS_RESULT_RECOVERED; + } } /* If any device has a hard failure, then shut off everything. */ -- cgit v1.2.3 From a7d0431774cf4b9970cf49da5b5cdd2f1aa71b25 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 24 Apr 2014 18:00:31 +1000 Subject: powerpc/prom: Stop scanning dev-tree for fdump early Function early_init_dt_scan_fw_dump() is called to scan the device tree for fdump properties under node "rtas". Any one of them is invalid, we can stop scanning the device tree early by returning "1". It would save a bit time during boot. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/fadump.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 2230fd0ca3e4..02667744fbb5 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -69,7 +69,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, */ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL); if (!token) - return 0; + return 1; fw_dump.fadump_supported = 1; fw_dump.ibm_configure_kernel_dump = *token; @@ -92,7 +92,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, &size); if (!sections) - return 0; + return 1; num_sections = size / (3 * sizeof(u32)); @@ -110,6 +110,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, break; } } + return 1; } -- cgit v1.2.3 From 13ae40370f62cd73f90aca34feb44bac83f41075 Mon Sep 17 00:00:00 2001 From: Stephen Chivers Date: Sun, 20 Apr 2014 09:43:10 +1000 Subject: powerpc/legacy_serial: Support MVME5100 UARTS with shifted registers This patch adds support to legacy serial for UARTS with shifted registers. The MVME5100 Single Board Computer is a PowerPC platform that has 16550 style UARTS with register addresses that are 16 bytes apart (shifted by 4). Commit 309257484cc1a592e8ac5fbdd8cd661be2b80bf8 "powerpc: Cleanup udbg_16550 and add support for LPC PIO-only UARTs" added support to udbg_16550 for shifted registers by adding a "stride" parameter to the initialisation operations for Programmed IO and Memory Mapped IO. As a consequence it is now possible to use the services of legacy serial to provide early serial console messages for the MVME5100. An added benefit of this is that the serial console will always be "ttyS0" irrespective of whether the computer is fitted with extra PCI 8250 interface boards or not. I have tested this patch using the four PowerPC platforms available to me: MVME5100 - shifted registers, SAM440EP - unshifted registers, MPC8349 - unshifted registers, MVME4100 - unshifted registers. Signed-off-by: Stephen Chivers Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/legacy_serial.c | 21 +++++++++++++++------ arch/powerpc/platforms/embedded6xx/Kconfig | 1 + 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 40bd7bd4e19a..85fb16e64cef 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -71,8 +71,9 @@ static int __init add_legacy_port(struct device_node *np, int want_index, phys_addr_t taddr, unsigned long irq, upf_t flags, int irq_check_parent) { - const __be32 *clk, *spd; + const __be32 *clk, *spd, *rs; u32 clock = BASE_BAUD * 16; + u32 shift = 0; int index; /* get clock freq. if present */ @@ -83,6 +84,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, /* get default speed if present */ spd = of_get_property(np, "current-speed", NULL); + /* get register shift if present */ + rs = of_get_property(np, "reg-shift", NULL); + if (rs && *rs) + shift = be32_to_cpup(rs); + /* If we have a location index, then try to use it */ if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS) index = want_index; @@ -126,6 +132,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].uartclk = clock; legacy_serial_ports[index].irq = irq; legacy_serial_ports[index].flags = flags; + legacy_serial_ports[index].regshift = shift; legacy_serial_infos[index].taddr = taddr; legacy_serial_infos[index].np = of_node_get(np); legacy_serial_infos[index].clock = clock; @@ -163,9 +170,8 @@ static int __init add_legacy_soc_port(struct device_node *np, if (of_get_property(np, "clock-frequency", NULL) == NULL) return -1; - /* if reg-shift or offset, don't try to use it */ - if ((of_get_property(np, "reg-shift", NULL) != NULL) || - (of_get_property(np, "reg-offset", NULL) != NULL)) + /* if reg-offset don't try to use it */ + if ((of_get_property(np, "reg-offset", NULL) != NULL)) return -1; /* if rtas uses this device, don't try to use it as well */ @@ -315,17 +321,20 @@ static void __init setup_legacy_serial_console(int console) struct legacy_serial_info *info = &legacy_serial_infos[console]; struct plat_serial8250_port *port = &legacy_serial_ports[console]; void __iomem *addr; + unsigned int stride; + + stride = 1 << port->regshift; /* Check if a translated MMIO address has been found */ if (info->taddr) { addr = ioremap(info->taddr, 0x1000); if (addr == NULL) return; - udbg_uart_init_mmio(addr, 1); + udbg_uart_init_mmio(addr, stride); } else { /* Check if it's PIO and we support untranslated PIO */ if (port->iotype == UPIO_PORT && isa_io_special) - udbg_uart_init_pio(port->iobase, 1); + udbg_uart_init_pio(port->iobase, stride); else return; } diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 2a7024d8d8b1..a25f496c2ef9 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -65,6 +65,7 @@ config MVME5100 select PPC_INDIRECT_PCI select PPC_I8259 select PPC_NATIVE + select PPC_UDBG_16550 help This option enables support for the Motorola (now Emerson) MVME5100 board. -- cgit v1.2.3 From 654837e8fe8d1d302803458e3a100aa78e0d90de Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Tue, 25 Feb 2014 06:32:11 +0000 Subject: powerpc/pci: Use of_pci_range_parser helper in pci_process_bridge_OF_ranges This patch updates the implementation of pci_process_bridge_OF_ranges to use the of_pci_range_parser helpers. Signed-off-by: Andrew Murray Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/pci-common.c | 88 +++++++++++++--------------------------- 1 file changed, 29 insertions(+), 59 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f9ca5091840c..add166aa806a 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -686,60 +686,36 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, void pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int primary) { - const __be32 *ranges; - int rlen; - int pna = of_n_addr_cells(dev); - int np = pna + 5; int memno = 0; - u32 pci_space; - unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size; struct resource *res; + struct of_pci_range range; + struct of_pci_range_parser parser; printk(KERN_INFO "PCI host bridge %s %s ranges:\n", dev->full_name, primary ? "(primary)" : ""); - /* Get ranges property */ - ranges = of_get_property(dev, "ranges", &rlen); - if (ranges == NULL) + /* Check for ranges property */ + if (of_pci_range_parser_init(&parser, dev)) return; /* Parse it */ - while ((rlen -= np * 4) >= 0) { - /* Read next ranges element */ - pci_space = of_read_number(ranges, 1); - pci_addr = of_read_number(ranges + 1, 2); - cpu_addr = of_translate_address(dev, ranges + 3); - size = of_read_number(ranges + pna + 3, 2); - ranges += np; - + for_each_of_pci_range(&parser, &range) { /* If we failed translation or got a zero-sized region * (some FW try to feed us with non sensical zero sized regions * such as power3 which look like some kind of attempt at exposing * the VGA memory hole) */ - if (cpu_addr == OF_BAD_ADDR || size == 0) + if (range.cpu_addr == OF_BAD_ADDR || range.size == 0) continue; - /* Now consume following elements while they are contiguous */ - for (; rlen >= np * sizeof(u32); - ranges += np, rlen -= np * 4) { - if (of_read_number(ranges, 1) != pci_space) - break; - pci_next = of_read_number(ranges + 1, 2); - cpu_next = of_translate_address(dev, ranges + 3); - if (pci_next != pci_addr + size || - cpu_next != cpu_addr + size) - break; - size += of_read_number(ranges + pna + 3, 2); - } - /* Act based on address space type */ res = NULL; - switch ((pci_space >> 24) & 0x3) { - case 1: /* PCI IO space */ + switch (range.flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_IO: printk(KERN_INFO " IO 0x%016llx..0x%016llx -> 0x%016llx\n", - cpu_addr, cpu_addr + size - 1, pci_addr); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr); /* We support only one IO range */ if (hose->pci_io_size) { @@ -749,11 +725,12 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, } #ifdef CONFIG_PPC32 /* On 32 bits, limit I/O space to 16MB */ - if (size > 0x01000000) - size = 0x01000000; + if (range.size > 0x01000000) + range.size = 0x01000000; /* 32 bits needs to map IOs here */ - hose->io_base_virt = ioremap(cpu_addr, size); + hose->io_base_virt = ioremap(range.cpu_addr, + range.size); /* Expect trouble if pci_addr is not 0 */ if (primary) @@ -763,20 +740,20 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* pci_io_size and io_base_phys always represent IO * space starting at 0 so we factor in pci_addr */ - hose->pci_io_size = pci_addr + size; - hose->io_base_phys = cpu_addr - pci_addr; + hose->pci_io_size = range.pci_addr + range.size; + hose->io_base_phys = range.cpu_addr - range.pci_addr; /* Build resource */ res = &hose->io_resource; - res->flags = IORESOURCE_IO; - res->start = pci_addr; + range.cpu_addr = range.pci_addr; break; - case 2: /* PCI Memory space */ - case 3: /* PCI 64 bits Memory space */ + case IORESOURCE_MEM: printk(KERN_INFO " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n", - cpu_addr, cpu_addr + size - 1, pci_addr, - (pci_space & 0x40000000) ? "Prefetch" : ""); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr, + (range.pci_space & 0x40000000) ? + "Prefetch" : ""); /* We support only 3 memory ranges */ if (memno >= 3) { @@ -785,28 +762,21 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, continue; } /* Handles ISA memory hole space here */ - if (pci_addr == 0) { + if (range.pci_addr == 0) { if (primary || isa_mem_base == 0) - isa_mem_base = cpu_addr; - hose->isa_mem_phys = cpu_addr; - hose->isa_mem_size = size; + isa_mem_base = range.cpu_addr; + hose->isa_mem_phys = range.cpu_addr; + hose->isa_mem_size = range.size; } /* Build resource */ - hose->mem_offset[memno] = cpu_addr - pci_addr; + hose->mem_offset[memno] = range.cpu_addr - + range.pci_addr; res = &hose->mem_resources[memno++]; - res->flags = IORESOURCE_MEM; - if (pci_space & 0x40000000) - res->flags |= IORESOURCE_PREFETCH; - res->start = cpu_addr; break; } if (res != NULL) { - res->name = dev->full_name; - res->end = res->start + size - 1; - res->parent = NULL; - res->sibling = NULL; - res->child = NULL; + of_pci_range_to_resource(&range, dev, res); } } } -- cgit v1.2.3 From 2299d03a632c7586403ab43a11b418ee1ae47f1a Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Tue, 11 Mar 2014 17:01:18 +0530 Subject: powerpc: powernv: Framework to show the correct clock in /proc/cpuinfo Currently, the code in setup-common.c for powerpc assumes that all clock rates are same in a smp system. This value is cached in the variable named ppc_proc_freq and is the value that is reported in /proc/cpuinfo. However on the PowerNV platform, the clock rate is same only across the threads of the same core. Hence the value that is reported in /proc/cpuinfo is incorrect on PowerNV platforms. We need a better way to query and report the correct value of the processor clock in /proc/cpuinfo. The patch achieves this by creating a machdep_call named get_proc_freq() which is expected to returns the frequency in Hz. The code in show_cpuinfo() can invoke this method to display the correct clock rate on platforms that have implemented this method. On the other powerpc platforms it can use the value cached in ppc_proc_freq. Signed-off-by: Gautham R. Shenoy Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/machdep.h | 2 ++ arch/powerpc/kernel/setup-common.c | 16 ++++++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 240b137ce0cf..374abc2e41d7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -113,6 +113,8 @@ struct machdep_calls { /* Optional, may be NULL. */ void (*show_cpuinfo)(struct seq_file *m); void (*show_percpuinfo)(struct seq_file *m, int i); + /* Returns the current operating frequency of "cpu" in Hz */ + unsigned long (*get_proc_freq)(unsigned int cpu); void (*init_IRQ)(void); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 79b7612ac6fa..3cf25c89469d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -212,6 +212,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; unsigned int pvr; + unsigned long proc_freq; unsigned short maj; unsigned short min; @@ -263,12 +264,19 @@ static int show_cpuinfo(struct seq_file *m, void *v) #endif /* CONFIG_TAU */ /* - * Assume here that all clock rates are the same in a - * smp system. -- Cort + * Platforms that have variable clock rates, should implement + * the method ppc_md.get_proc_freq() that reports the clock + * rate of a given cpu. The rest can use ppc_proc_freq to + * report the clock rate that is same across all cpus. */ - if (ppc_proc_freq) + if (ppc_md.get_proc_freq) + proc_freq = ppc_md.get_proc_freq(cpu_id); + else + proc_freq = ppc_proc_freq; + + if (proc_freq) seq_printf(m, "clock\t\t: %lu.%06luMHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); + proc_freq / 1000000, proc_freq % 1000000); if (ppc_md.show_percpuinfo != NULL) ppc_md.show_percpuinfo(m, cpu_id); -- cgit v1.2.3 From ce0ac1fc326b6a4116728be933ff46d75269baa1 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 28 Mar 2014 16:40:33 +1100 Subject: powerpc/tm: Remove unnecessary r1 save We save r1 to the scratch SPR and restore it from there after the trechkpt so saving r1 to the paca is not needed. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/tm.S | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 03567c05950a..0535c7fdd12c 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -320,8 +320,6 @@ _GLOBAL(__tm_recheckpoint) */ SAVE_NVGPRS(r1) - std r1, PACAR1(r13) - /* Load complete register state from ts_ckpt* registers */ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */ -- cgit v1.2.3 From 7f06f21d40a638e1ca759ceda0f21cd81082607e Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 28 Mar 2014 16:40:34 +1100 Subject: powerpc/tm: Add checking to treclaim/trechkpt If we do a treclaim and we are not in TM suspend mode, it results in a TM bad thing (ie. a 0x700 program check). Similarly if we do a trechkpt and we have an active transaction or TEXASR Failure Summary (FS) is not set, we also take a TM bad thing. This should never happen, but if it does (ie. a kernel bug), the cause is almost impossible to debug as the GPR state is mostly userspace and hence we don't get a call chain. This adds some checks in these cases case a BUG_ON() (in asm) in case we ever hit these cases. It moves the register saving around to preserve r1 till later also. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/kernel/tm.S | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 36 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e5d2e0bc7e03..29de0152878f 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -215,6 +215,7 @@ #define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */ #define TEXASR_FS __MASK(63-36) /* Transaction Failure Summary */ #define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */ +#define TEXASR_FS __MASK(63-36) /* TEXASR Failure Summary */ #define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */ #define SPRN_CTRLF 0x088 #define SPRN_CTRLT 0x098 diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 0535c7fdd12c..508c54b92fa6 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -10,6 +10,7 @@ #include #include #include +#include #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -175,6 +176,13 @@ dont_backup_vec: stfd fr0,FPSTATE_FPSCR(r7) dont_backup_fp: + /* Do sanity check on MSR to make sure we are suspended */ + li r7, (MSR_TS_S)@higher + srdi r6, r14, 32 + and r6, r6, r7 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + /* The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. @@ -383,12 +391,10 @@ restore_gprs: /* ******************** CR,LR,CCR,MSR ********** */ ld r4, _CTR(r7) ld r5, _LINK(r7) - ld r6, _CCR(r7) ld r8, _XER(r7) mtctr r4 mtlr r5 - mtcr r6 mtxer r8 /* ******************** TAR ******************** */ @@ -404,7 +410,8 @@ restore_gprs: li r4, 0 mtmsrd r4, 1 - REST_4GPRS(0, r7) /* GPR0-3 */ + REST_GPR(0, r7) /* GPR0 */ + REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ REST_4GPRS(8, r7) /* GPR8-11 */ REST_2GPRS(12, r7) /* GPR12-13 */ @@ -416,6 +423,31 @@ restore_gprs: mtspr SPRN_DSCR, r5 mtspr SPRN_PPR, r6 + /* Do final sanity check on TEXASR to make sure FS is set. Do this + * here before we load up the userspace r1 so any bugs we hit will get + * a call chain */ + mfspr r5, SPRN_TEXASR + srdi r5, r5, 16 + li r6, (TEXASR_FS)@h + and r6, r6, r5 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Do final sanity check on MSR to make sure we are not transactional + * or suspended + */ + mfmsr r6 + li r5, (MSR_TS_MASK)@higher + srdi r6, r6, 32 + and r6, r6, r5 +1: tdnei r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Restore CR */ + ld r6, _CCR(r7) + mtcr r6 + + REST_GPR(1, r7) /* GPR1 */ REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) ld r7, GPR7(r7) -- cgit v1.2.3 From 00f554fadebb96877ad449758dc90303a9826afe Mon Sep 17 00:00:00 2001 From: Philippe Bergheaud Date: Wed, 30 Apr 2014 09:12:01 +1000 Subject: powerpc: memcpy optimization for 64bit LE Unaligned stores take alignment exceptions on POWER7 running in little-endian. This is a dumb little-endian base memcpy that prevents unaligned stores. Once booted the feature fixup code switches over to the VMX copy loops (which are already endian safe). The question is what we do before that switch over. The base 64bit memcpy takes alignment exceptions on POWER7 so we can't use it as is. Fixing the causes of alignment exception would slow it down, because we'd need to ensure all loads and stores are aligned either through rotate tricks or bytewise loads and stores. Either would be bad for all other 64bit platforms. [ I simplified the loop a bit - Anton ] Signed-off-by: Philippe Bergheaud Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/string.h | 4 ---- arch/powerpc/kernel/ppc_ksyms.c | 2 -- arch/powerpc/lib/Makefile | 2 -- arch/powerpc/lib/memcpy_64.S | 16 ++++++++++++++++ 4 files changed, 16 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index 0dffad6bcc84..e40010abcaf1 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -10,9 +10,7 @@ #define __HAVE_ARCH_STRNCMP #define __HAVE_ARCH_STRCAT #define __HAVE_ARCH_MEMSET -#ifdef __BIG_ENDIAN__ #define __HAVE_ARCH_MEMCPY -#endif #define __HAVE_ARCH_MEMMOVE #define __HAVE_ARCH_MEMCMP #define __HAVE_ARCH_MEMCHR @@ -24,9 +22,7 @@ extern int strcmp(const char *,const char *); extern int strncmp(const char *, const char *, __kernel_size_t); extern char * strcat(char *, const char *); extern void * memset(void *,int,__kernel_size_t); -#ifdef __BIG_ENDIAN__ extern void * memcpy(void *,const void *,__kernel_size_t); -#endif extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 450850a49dce..48d17d6fca5b 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -155,9 +155,7 @@ EXPORT_SYMBOL(__cmpdi2); #endif long long __bswapdi2(long long); EXPORT_SYMBOL(__bswapdi2); -#ifdef __BIG_ENDIAN__ EXPORT_SYMBOL(memcpy); -#endif EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcmp); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 95a20e17dbff..59fa2de9546d 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -23,9 +23,7 @@ obj-y += checksum_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC64) += checksum_wrappers_64.o endif -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),) obj-$(CONFIG_PPC64) += memcpy_power7.o memcpy_64.o -endif obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 72ad055168a3..dc4ba7953b92 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -12,12 +12,27 @@ .align 7 _GLOBAL(memcpy) BEGIN_FTR_SECTION +#ifdef __LITTLE_ENDIAN__ + cmpdi cr7,r5,0 +#else std r3,48(r1) /* save destination pointer for return value */ +#endif FTR_SECTION_ELSE #ifndef SELFTEST b memcpy_power7 #endif ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) +#ifdef __LITTLE_ENDIAN__ + /* dumb little-endian memcpy that will get replaced at runtime */ + addi r9,r3,-1 + addi r4,r4,-1 + beqlr cr7 + mtctr r5 +1: lbzu r10,1(r4) + stbu r10,1(r9) + bdnz 1b + blr +#else PPC_MTOCRF(0x01,r5) cmpldi cr1,r5,16 neg r6,r3 # LS 3 bits = # bytes to 8-byte dest bdry @@ -203,3 +218,4 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) stb r0,0(r3) 4: ld r3,48(r1) /* return dest pointer */ blr +#endif -- cgit v1.2.3 From 1e54b9383cf7e1cbc004b3ccc4c4eaadecce9d95 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Mon, 5 May 2014 12:09:05 +1000 Subject: powerpc/eeh: Fix build error for celleb Commit 7f52a526f ("powerpc/eeh: Allow to disable EEH") caused following build error with "celleb_defconfig" as being catched by Mikey on linux-next. arch/powerpc/kernel/eeh.c: In function 'eeh_init_proc': arch/powerpc/kernel/eeh.c:1173:37: error: 'powerpc_debugfs_root' \ undeclared (first use in this function) arch/powerpc/kernel/eeh.c:1173:37: note: each undeclared identifier \ is reported only once for each function it appears in Reported-by: Michael Neuling Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 3764fb788d6c..7051ea3101b9 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -36,6 +36,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 04c32a516806ec74b62048baf4cddcbb840927db Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Tue, 29 Apr 2014 15:25:16 -0400 Subject: powerpc: Drop return value from set_breakpoint as it is unused None of the callers check the return value, so it might as well not have one at all. Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/debug.h | 2 +- arch/powerpc/kernel/process.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index d2516308ed1e..1d7f966d3b18 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -46,7 +46,7 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -int set_breakpoint(struct arch_hw_breakpoint *brk); +void set_breakpoint(struct arch_hw_breakpoint *brk); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int signal_code, int brkpt); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 2ae1b99166c6..f895a5062287 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -496,14 +496,14 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) return 0; } -int set_breakpoint(struct arch_hw_breakpoint *brk) +void set_breakpoint(struct arch_hw_breakpoint *brk) { __get_cpu_var(current_brk) = *brk; if (cpu_has_feature(CPU_FTR_DAWR)) - return set_dawr(brk); - - return set_dabr(brk); + set_dawr(brk); + else + set_dabr(brk); } #ifdef CONFIG_PPC64 -- cgit v1.2.3 From 21f585073d6347651f2262da187606fa1c4ee16d Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Tue, 29 Apr 2014 15:25:17 -0400 Subject: powerpc: Fix smp_processor_id() in preemptible splat in set_breakpoint Currently, on 8641D, which doesn't set CONFIG_HAVE_HW_BREAKPOINT we get the following splat: BUG: using smp_processor_id() in preemptible [00000000] code: login/1382 caller is set_breakpoint+0x1c/0xa0 CPU: 0 PID: 1382 Comm: login Not tainted 3.15.0-rc3-00041-g2aafe1a4d451 #1 Call Trace: [decd5d80] [c0008dc4] show_stack+0x50/0x158 (unreliable) [decd5dc0] [c03c6fa0] dump_stack+0x7c/0xdc [decd5de0] [c01f8818] check_preemption_disabled+0xf4/0x104 [decd5e00] [c00086b8] set_breakpoint+0x1c/0xa0 [decd5e10] [c00d4530] flush_old_exec+0x2bc/0x588 [decd5e40] [c011c468] load_elf_binary+0x2ac/0x1164 [decd5ec0] [c00d35f8] search_binary_handler+0xc4/0x1f8 [decd5ef0] [c00d4ee8] do_execve+0x3d8/0x4b8 [decd5f40] [c001185c] ret_from_syscall+0x0/0x38 --- Exception: c01 at 0xfeee554 LR = 0xfeee7d4 The call path in this case is: flush_thread --> set_debug_reg_defaults --> set_breakpoint --> __get_cpu_var Since preemption is enabled in the cleanup of flush thread, and there is no need to disable it, introduce the distinction between set_breakpoint and __set_breakpoint, leaving only the flush_thread instance as the current user of set_breakpoint. Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/debug.h | 1 + arch/powerpc/include/asm/hw_breakpoint.h | 2 +- arch/powerpc/kernel/hw_breakpoint.c | 8 ++++---- arch/powerpc/kernel/process.c | 11 +++++++++-- arch/powerpc/kernel/signal.c | 2 +- arch/powerpc/xmon/xmon.c | 2 +- 6 files changed, 17 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 1d7f966d3b18..a954e4975049 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -47,6 +47,7 @@ static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif void set_breakpoint(struct arch_hw_breakpoint *brk); +void __set_breakpoint(struct arch_hw_breakpoint *brk); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int signal_code, int brkpt); diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index eb0f4ac75c4c..ac6432d9be46 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -79,7 +79,7 @@ static inline void hw_breakpoint_disable(void) brk.address = 0; brk.type = 0; brk.len = 0; - set_breakpoint(&brk); + __set_breakpoint(&brk); } extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index b0a1792279bb..0bb5918faaaf 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -72,7 +72,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_breakpoint(info); + __set_breakpoint(info); return 0; } @@ -198,7 +198,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_breakpoint(info); + __set_breakpoint(info); tsk->thread.last_hit_ubp = NULL; } @@ -284,7 +284,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); out: rcu_read_unlock(); return rc; @@ -316,7 +316,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index f895a5062287..8a1edbe26b8f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -496,7 +496,7 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) return 0; } -void set_breakpoint(struct arch_hw_breakpoint *brk) +void __set_breakpoint(struct arch_hw_breakpoint *brk) { __get_cpu_var(current_brk) = *brk; @@ -506,6 +506,13 @@ void set_breakpoint(struct arch_hw_breakpoint *brk) set_dabr(brk); } +void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); +} + #ifdef CONFIG_PPC64 DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); #endif @@ -835,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) - set_breakpoint(&new->thread.hw_brk); + __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 8fc4177ed65a..1c794cef2883 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -134,7 +134,7 @@ static int do_signal(struct pt_regs *regs) */ if (current->thread.hw_brk.address && current->thread.hw_brk.type) - set_breakpoint(¤t->thread.hw_brk); + __set_breakpoint(¤t->thread.hw_brk); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 08504e75b2c7..d3759b7a5535 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -759,7 +759,7 @@ static void insert_cpu_bpts(void) brk.address = dabr.address; brk.type = (dabr.enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; - set_breakpoint(&brk); + __set_breakpoint(&brk); } if (iabr && cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, iabr->address -- cgit v1.2.3 From 872aa779bcdd26bbe2d538c36e2c2072b3f03c8c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 12 May 2014 17:15:02 +0930 Subject: powerpc/module: Fix stubs for BE A simple patch which was supposed to swap r12 and r11 also inexplicably changed the offset by two bytes. This instruction (to load r2) isn't used in LE, so it wasn't noticed. Fixes: b1ce369e82 ("powerpc: modules: use r12 for stub jump address.) Reported-by: Alistair Popple Signed-off-by: Rusty Russell Tested-by: Alistair Popple Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/module_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index ef349d077129..077d2ce6c5a7 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -134,7 +134,7 @@ static u32 ppc64_stub_insns[] = { 0xe98b0020, /* ld r12,32(r11) */ #if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Set up new r2 from function descriptor */ - 0xe84b0026, /* ld r2,40(r11) */ + 0xe84b0028, /* ld r2,40(r11) */ #endif 0x7d8903a6, /* mtctr r12 */ 0x4e800420 /* bctr */ -- cgit v1.2.3 From 83e267d797e0e69d0ac5741f5dc88a2df3ebb3a0 Mon Sep 17 00:00:00 2001 From: Stuart Yoder Date: Wed, 30 Apr 2014 18:34:23 -0500 Subject: powerpc: move epapr paravirt init of power_save to an initcall some restructuring of epapr paravirt init resulted in ppc_md.power_save being set, and then overwritten to NULL during machine_init. This patch splits the initialization of ppc_md.power_save out into a postcore init call. Signed-off-by: Stuart Yoder Signed-off-by: Scott Wood --- arch/powerpc/kernel/epapr_paravirt.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index 7898be90f2dc..8a7a62c85604 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -30,6 +30,7 @@ extern u32 epapr_ev_idle_start[]; #endif bool epapr_paravirt_enabled; +static bool epapr_has_idle; static int __init early_init_dt_scan_epapr(unsigned long node, const char *uname, @@ -55,7 +56,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node, #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (of_get_flat_dt_prop(node, "has-idle", NULL)) - ppc_md.power_save = epapr_ev_idle; + epapr_has_idle = true; #endif epapr_paravirt_enabled = true; @@ -70,3 +71,12 @@ int __init epapr_paravirt_early_init(void) return 0; } +static int __init epapr_idle_init(void) +{ + if (epapr_has_idle) + ppc_md.power_save = epapr_ev_idle; + + return 0; +} + +postcore_initcall(epapr_idle_init); -- cgit v1.2.3 From 440d74d1caf7b38f727553bc54de09c1e29e7741 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Mon, 12 May 2014 10:05:19 -0500 Subject: powerpc: fix build of epapr_paravirt on 64-bit book3s This fixes an allyesconfig build break introduced by commit 7762b1ed7aaee223230793fcee80672e2e3aa7a8 "powerpc: move epapr paravirt init of power_save to an initcall". Signed-off-by: Scott Wood Cc: Stuart Yoder --- arch/powerpc/kernel/epapr_paravirt.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index 8a7a62c85604..eab2f2a05e5f 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -73,8 +73,10 @@ int __init epapr_paravirt_early_init(void) static int __init epapr_idle_init(void) { +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (epapr_has_idle) ppc_md.power_save = epapr_ev_idle; +#endif return 0; } -- cgit v1.2.3 From 8067bd8a12b4978e495dcbe25533ab90d24c1f83 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 15 May 2014 11:28:26 -0500 Subject: powerpc: Fix unused variable warning for epapr_has_idle This warning can be seen in allyesconfig, and was introduced by commit f9eb581c63b2acce827570e105205c0789360650 "powerpc: fix build of epapr_paravirt on 64-bit book3s". Signed-off-by: Scott Wood --- arch/powerpc/kernel/epapr_paravirt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index eab2f2a05e5f..c47fed009163 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -30,7 +30,7 @@ extern u32 epapr_ev_idle_start[]; #endif bool epapr_paravirt_enabled; -static bool epapr_has_idle; +static bool __maybe_unused epapr_has_idle; static int __init early_init_dt_scan_epapr(unsigned long node, const char *uname, -- cgit v1.2.3 From 8cb59788b342903f2912ecef0df4aaadd12e5843 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 15 May 2014 14:35:19 +0200 Subject: PPC: ePAPR: Fix hypercall on LE guest We get an array of instructions from the hypervisor via device tree that we write into a buffer that gets executed whenever we want to make an ePAPR compliant hypercall. However, the hypervisor passes us these instructions in BE order which we have to manually convert to LE when we want to run them in LE mode. With this fixup in place, I can successfully run LE kernels with KVM PV enabled on PR KVM. Signed-off-by: Alexander Graf Signed-off-by: Scott Wood --- arch/powerpc/kernel/epapr_paravirt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index c47fed009163..2d7eeae5b4d0 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -48,9 +48,10 @@ static int __init early_init_dt_scan_epapr(unsigned long node, return -1; for (i = 0; i < (len / 4); i++) { - patch_instruction(epapr_hypercall_start + i, insts[i]); + u32 inst = be32_to_cpu(insts[i]); + patch_instruction(epapr_hypercall_start + i, inst); #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) - patch_instruction(epapr_ev_idle_start + i, insts[i]); + patch_instruction(epapr_ev_idle_start + i, inst); #endif } -- cgit v1.2.3 From 8c272261194dfda11cc046fbe808e052f6f284eb Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 19 May 2014 11:14:23 -0700 Subject: powerpc/numa: Enable USE_PERCPU_NUMA_NODE_ID Based off 3bccd996 for ia64, convert powerpc to use the generic per-CPU topology tracking, specifically: initialize per cpu numa_node entry in start_secondary remove the powerpc cpu_to_node() define CONFIG_USE_PERCPU_NUMA_NODE_ID if NUMA Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 4 ++++ arch/powerpc/include/asm/topology.h | 13 ------------- arch/powerpc/kernel/smp.c | 6 ++++++ 3 files changed, 10 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e0998997943b..9125964af409 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -453,6 +453,10 @@ config NODES_SHIFT default "4" depends on NEED_MULTIPLE_NODES +config USE_PERCPU_NUMA_NODE_ID + def_bool y + depends on NUMA + config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c9202151079f..5ecf7ea52ad8 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -20,19 +20,6 @@ struct device_node; #include -static inline int cpu_to_node(int cpu) -{ - int nid; - - nid = numa_cpu_lookup_table[cpu]; - - /* - * During early boot, the numa-cpu lookup table might not have been - * setup for all CPUs yet. In such cases, default to node 0. - */ - return (nid < 0) ? 0 : nid; -} - #define parent_node(node) (node) #define cpumask_of_node(node) ((node) == -1 ? \ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e2a4232c5871..d7252adea759 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -390,6 +390,7 @@ void smp_prepare_boot_cpu(void) #ifdef CONFIG_PPC64 paca[boot_cpuid].__current = current; #endif + set_numa_node(numa_cpu_lookup_table[boot_cpuid]); current_set[boot_cpuid] = task_thread_info(current); } @@ -750,6 +751,11 @@ void start_secondary(void *unused) } traverse_core_siblings(cpu, true); + /* + * numa_node_id() works after this. + */ + set_numa_node(numa_cpu_lookup_table[cpu]); + smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); -- cgit v1.2.3 From 64bb80d87f01ec01c76863b61b457e0904387f2f Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Fri, 16 May 2014 16:41:20 -0700 Subject: powerpc/numa: Enable CONFIG_HAVE_MEMORYLESS_NODES Based off fd1197f1 for ia64, enable CONFIG_HAVE_MEMORYLESS_NODES if NUMA. Initialize the local memory node in start_secondary. With this commit and the preceding to enable CONFIG_USER_PERCPU_NUMA_NODE_ID, which is a prerequisite, in a PowerKVM guest with the following topology: numactl --hardware available: 3 nodes (0-2) node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 node 0 size: 1998 MB node 0 free: 521 MB node 1 cpus: 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 node 1 size: 0 MB node 1 free: 0 MB node 2 cpus: node 2 size: 2039 MB node 2 free: 1739 MB node distances: node 0 1 2 0: 10 40 40 1: 40 10 40 2: 40 40 10 the unreclaimable slab is reduced by close to 130M: Before: Slab: 418176 kB SReclaimable: 26624 kB SUnreclaim: 391552 kB After: Slab: 298944 kB SReclaimable: 31744 kB SUnreclaim: 267200 kB Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 4 ++++ arch/powerpc/kernel/smp.c | 1 + 2 files changed, 5 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9125964af409..bd6dd6ed3a9f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -457,6 +457,10 @@ config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA +config HAVE_MEMORYLESS_NODES + def_bool y + depends on NUMA + config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index d7252adea759..4863ea14f270 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -755,6 +755,7 @@ void start_secondary(void *unused) * numa_node_id() works after this. */ set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); smp_wmb(); notify_cpu_starting(cpu); -- cgit v1.2.3 From 441c19c8a290f5f1e1b263691641124c84232b6e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 23 May 2014 18:15:25 +1000 Subject: powerpc/kvm/book3s_hv: Rework the secondary inhibit code As part of the support for split core on POWER8, we want to be able to block splitting of the core while KVM VMs are active. The logic to do that would be exactly the same as the code we currently have for inhibiting onlining of secondaries. Instead of adding an identical mechanism to block split core, rework the secondary inhibit code to be a "HV KVM is active" check. We can then use that in both the cpu hotplug code and the upcoming split core code. Signed-off-by: Michael Ellerman Signed-off-by: Michael Neuling Acked-by: Alexander Graf Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/kvm_ppc.h | 7 +++++++ arch/powerpc/include/asm/smp.h | 8 -------- arch/powerpc/kernel/smp.c | 34 +++------------------------------- arch/powerpc/kvm/book3s_hv.c | 8 ++++---- arch/powerpc/kvm/book3s_hv_builtin.c | 31 +++++++++++++++++++++++++++++++ 5 files changed, 45 insertions(+), 43 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 4096f16502a9..2c8e39951ab5 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -337,6 +337,10 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu); } +extern void kvm_hv_vm_activated(void); +extern void kvm_hv_vm_deactivated(void); +extern bool kvm_hv_mode_active(void); + #else static inline void __init kvm_cma_reserve(void) {} @@ -356,6 +360,9 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) { kvm_vcpu_kick(vcpu); } + +static inline bool kvm_hv_mode_active(void) { return false; } + #endif #ifdef CONFIG_KVM_XICS diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ff51046b6466..5a6614a7f0b2 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -68,14 +68,6 @@ void generic_mach_cpu_die(void); void generic_set_cpu_dead(unsigned int cpu); void generic_set_cpu_up(unsigned int cpu); int generic_check_cpu_restart(unsigned int cpu); - -extern void inhibit_secondary_onlining(void); -extern void uninhibit_secondary_onlining(void); - -#else /* HOTPLUG_CPU */ -static inline void inhibit_secondary_onlining(void) {} -static inline void uninhibit_secondary_onlining(void) {} - #endif #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 4863ea14f270..5cdd9eb3b24c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -458,38 +459,9 @@ int generic_check_cpu_restart(unsigned int cpu) return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; } -static atomic_t secondary_inhibit_count; - -/* - * Don't allow secondary CPU threads to come online - */ -void inhibit_secondary_onlining(void) -{ - /* - * This makes secondary_inhibit_count stable during cpu - * online/offline operations. - */ - get_online_cpus(); - - atomic_inc(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(inhibit_secondary_onlining); - -/* - * Allow secondary CPU threads to come online again - */ -void uninhibit_secondary_onlining(void) -{ - get_online_cpus(); - atomic_dec(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining); - -static int secondaries_inhibited(void) +static bool secondaries_inhibited(void) { - return atomic_read(&secondary_inhibit_count); + return kvm_hv_mode_active(); } #else /* HOTPLUG_CPU */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 8227dba5af0f..d7b74f888ad8 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2317,10 +2317,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) spin_lock_init(&kvm->arch.slot_phys_lock); /* - * Don't allow secondary CPU threads to come online - * while any KVM VMs exist. + * Track that we now have a HV mode VM active. This blocks secondary + * CPU threads from coming online. */ - inhibit_secondary_onlining(); + kvm_hv_vm_activated(); return 0; } @@ -2336,7 +2336,7 @@ static void kvmppc_free_vcores(struct kvm *kvm) static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { - uninhibit_secondary_onlining(); + kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); if (kvm->arch.rma) { diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 8cd0daebb82d..7cde8a665205 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include #include #include #include @@ -181,3 +182,33 @@ void __init kvm_cma_reserve(void) kvm_cma_declare_contiguous(selected_size, align_size); } } + +/* + * When running HV mode KVM we need to block certain operations while KVM VMs + * exist in the system. We use a counter of VMs to track this. + * + * One of the operations we need to block is onlining of secondaries, so we + * protect hv_vm_count with get/put_online_cpus(). + */ +static atomic_t hv_vm_count; + +void kvm_hv_vm_activated(void) +{ + get_online_cpus(); + atomic_inc(&hv_vm_count); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(kvm_hv_vm_activated); + +void kvm_hv_vm_deactivated(void) +{ + get_online_cpus(); + atomic_dec(&hv_vm_count); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated); + +bool kvm_hv_mode_active(void) +{ + return atomic_read(&hv_vm_count) != 0; +} -- cgit v1.2.3 From 8d6f7c5aa3db6f3e5e43d09f8a0166c7d96f33f3 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 23 May 2014 18:15:26 +1000 Subject: powerpc/powernv: Make it possible to skip the IRQHAPPENED check in power7_nap() To support split core we need to be able to force all secondaries into nap, so the core can detect they are idle and do an unsplit. Currently power7_nap() will return without napping if there is an irq pending. We want to ignore the pending irq and nap anyway, we will deal with the interrupt later. Signed-off-by: Michael Ellerman Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/processor.h | 2 +- arch/powerpc/kernel/idle_power7.S | 9 +++++++++ arch/powerpc/platforms/powernv/smp.c | 2 +- 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index d660dc36831a..6d59072e13a7 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -449,7 +449,7 @@ extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ -extern void power7_nap(void); +extern void power7_nap(int check_irq); extern void power7_sleep(void); extern void flush_instruction_cache(void); extern void hard_reset_now(void); diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index dca6e16c2436..2480256272d4 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -39,6 +39,10 @@ * Pass requested state in r3: * 0 - nap * 1 - sleep + * + * To check IRQ_HAPPENED in r4 + * 0 - don't check + * 1 - check */ _GLOBAL(power7_powersave_common) /* Use r3 to pass state nap/sleep/winkle */ @@ -71,6 +75,8 @@ _GLOBAL(power7_powersave_common) lbz r0,PACAIRQHAPPENED(r13) cmpwi cr0,r0,0 beq 1f + cmpwi cr0,r4,0 + beq 1f addi r1,r1,INT_FRAME_SIZE ld r0,16(r1) mtlr r0 @@ -114,15 +120,18 @@ _GLOBAL(power7_idle) lwz r4,ADDROFF(powersave_nap)(r3) cmpwi 0,r4,0 beqlr + li r3, 1 /* fall through */ _GLOBAL(power7_nap) + mr r4,r3 li r3,0 b power7_powersave_common /* No return */ _GLOBAL(power7_sleep) li r3,1 + li r4,0 b power7_powersave_common /* No return */ diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 1601a1ea02c4..65faf998fe2c 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -159,7 +159,7 @@ static void pnv_smp_cpu_kill_self(void) mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { ppc64_runlatch_off(); - power7_nap(); + power7_nap(1); ppc64_runlatch_on(); if (!generic_check_cpu_restart(cpu)) { DBG("CPU%d Unexpected exit while offline !\n", cpu); -- cgit v1.2.3 From 5853aef1ac5c5d83076203e840ca463857a7515d Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 23 May 2014 18:15:27 +1000 Subject: powerpc: Add threads_per_subcore On POWER8 we have a new concept of a subcore. This is what happens when you take a regular core and split it. A subcore is a grouping of two or four SMT threads, as well as a handfull of SPRs which allows the subcore to appear as if it were a core from the point of view of a guest. Unlike threads_per_core which is fixed at boot, threads_per_subcore can change while the system is running. Most code will not want to use threads_per_subcore. Signed-off-by: Michael Ellerman Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputhreads.h | 7 +++++++ arch/powerpc/kernel/setup-common.c | 4 +++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index ac3eedb9b74a..2bf8e9307be9 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -18,10 +18,12 @@ #ifdef CONFIG_SMP extern int threads_per_core; +extern int threads_per_subcore; extern int threads_shift; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 +#define threads_per_subcore 1 #define threads_shift 0 #define threads_core_mask (CPU_MASK_CPU0) #endif @@ -74,6 +76,11 @@ static inline int cpu_thread_in_core(int cpu) return cpu & (threads_per_core - 1); } +static inline int cpu_thread_in_subcore(int cpu) +{ + return cpu & (threads_per_subcore - 1); +} + static inline int cpu_first_thread_sibling(int cpu) { return cpu & ~(threads_per_core - 1); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 3cf25c89469d..aa0f5edd8570 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -390,9 +390,10 @@ void __init check_for_initrd(void) #ifdef CONFIG_SMP -int threads_per_core, threads_shift; +int threads_per_core, threads_per_subcore, threads_shift; cpumask_t threads_core_mask; EXPORT_SYMBOL_GPL(threads_per_core); +EXPORT_SYMBOL_GPL(threads_per_subcore); EXPORT_SYMBOL_GPL(threads_shift); EXPORT_SYMBOL_GPL(threads_core_mask); @@ -401,6 +402,7 @@ static void __init cpu_init_thread_core_maps(int tpc) int i; threads_per_core = tpc; + threads_per_subcore = tpc; cpumask_clear(&threads_core_mask); /* This implementation only supports power of 2 number of threads -- cgit v1.2.3 From 6f5e40a3001d2497a134386a173e3ec3fdf2ad0b Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 23 May 2014 18:15:28 +1000 Subject: powerpc: Check cpu_thread_in_subcore() in __cpu_up() To support split core we need to change the check in __cpu_up() that determines if a cpu is allowed to come online. Currently we refuse to online cpus which are not the primary thread within their core. On POWER8 with split core support this check needs to instead refuse to online cpus which are not the primary thread within their *sub* core. On POWER7 and other systems that do not support split core, threads_per_subcore == threads_per_core and so the check is equivalent. Signed-off-by: Michael Ellerman Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5cdd9eb3b24c..6af946e9a984 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -490,7 +490,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Don't allow secondary threads to come online if inhibited */ if (threads_per_core > 1 && secondaries_inhibited() && - cpu % threads_per_core != 0) + cpu_thread_in_subcore(cpu)) return -EBUSY; if (smp_ops == NULL || -- cgit v1.2.3 From b717d98543d90c50f398ddfe9665483d09adca7a Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Fri, 23 May 2014 00:03:16 +0200 Subject: arch: powerpc/fadump: Cleaning up inconsistent NULL checks Cleaning up inconsistent NULL checks. There is otherwise a risk of a possible null pointer dereference. Was largely found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/fadump.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 02667744fbb5..d55e8986730a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -646,7 +646,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } /* Lower 4 bytes of reg_value contains logical cpu id */ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK; - if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { + if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; } @@ -663,9 +663,11 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } fadump_final_note(note_buf); - pr_debug("Updating elfcore header (%llx) with cpu notes\n", + if (fdh) { + pr_debug("Updating elfcore header (%llx) with cpu notes\n", fdh->elfcorehdr_addr); - fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + } return 0; error_out: -- cgit v1.2.3 From 39a360ef7234942333436709fd6cf641d5c51b7b Mon Sep 17 00:00:00 2001 From: Sam bobroff Date: Wed, 21 May 2014 16:32:37 +1000 Subject: powerpc: Split __SYSFS_SPRSETUP macro Split the __SYSFS_SPRSETUP macro into two parts so that registers requiring custom read and write functions can use common code for their show and store functions. Signed-off-by: Sam Bobroff Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/sysfs.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index d90d4b7810d6..e2a1d6fb3297 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -404,7 +404,7 @@ void ppc_enable_pmcs(void) } EXPORT_SYMBOL(ppc_enable_pmcs); -#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \ +#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \ static void read_##NAME(void *val) \ { \ *(unsigned long *)val = mfspr(ADDRESS); \ @@ -413,7 +413,9 @@ static void write_##NAME(void *val) \ { \ EXTRA; \ mtspr(ADDRESS, *(unsigned long *)val); \ -} \ +} + +#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \ static ssize_t show_##NAME(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ @@ -436,10 +438,15 @@ static ssize_t __used \ return count; \ } -#define SYSFS_PMCSETUP(NAME, ADDRESS) \ - __SYSFS_SPRSETUP(NAME, ADDRESS, ppc_enable_pmcs()) -#define SYSFS_SPRSETUP(NAME, ADDRESS) \ - __SYSFS_SPRSETUP(NAME, ADDRESS, ) +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) +#define SYSFS_SPRSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) + +#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) /* Let's define all possible registers, we'll only hook up the ones * that are implemented on the current processor -- cgit v1.2.3 From 1739ea9e13e636590dd56c2f4ca85e783da512e7 Mon Sep 17 00:00:00 2001 From: Sam bobroff Date: Wed, 21 May 2014 16:32:38 +1000 Subject: powerpc: Fix regression of per-CPU DSCR setting Since commit "efcac65 powerpc: Per process DSCR + some fixes (try#4)" it is no longer possible to set the DSCR on a per-CPU basis. The old behaviour was to minipulate the DSCR SPR directly but this is no longer sufficient: the value is quickly overwritten by context switching. This patch stores the per-CPU DSCR value in a kernel variable rather than directly in the SPR and it is used whenever a process has not set the DSCR itself. The sysfs interface (/sys/devices/system/cpu/cpuN/dscr) is unchanged. Writes to the old global default (/sys/devices/system/cpu/dscr_default) now set all of the per-CPU values and reads return the last written value. The new per-CPU default is added to the paca_struct and is used everywhere outside of sysfs.c instead of the old global default. Signed-off-by: Sam Bobroff Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/paca.h | 3 +++ arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/entry_64.S | 9 +-------- arch/powerpc/kernel/sysfs.c | 32 +++++++++++++++++++------------- arch/powerpc/kernel/tm.S | 16 ++++------------ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 3 +-- 6 files changed, 29 insertions(+), 35 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 8e956a0b6e85..bb0bd25f20d0 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -92,7 +92,10 @@ struct paca_struct { struct slb_shadow *slb_shadow_ptr; struct dtl_entry *dispatch_log; struct dtl_entry *dispatch_log_end; +#endif /* CONFIG_PPC_STD_MMU_64 */ + u64 dscr_default; /* per-CPU default DSCR */ +#ifdef CONFIG_PPC_STD_MMU_64 /* * Now, starting in cacheline 2, the exception save areas */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index dba8140ebc20..cba2697406b7 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -247,6 +247,7 @@ int main(void) #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); + DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default)); DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 9fde8a1bf1e1..911d45366f59 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -387,12 +387,6 @@ _GLOBAL(ret_from_kernel_thread) li r3,0 b syscall_exit - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -577,11 +571,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #ifdef CONFIG_PPC64 BEGIN_FTR_SECTION lwz r6,THREAD_DSCR_INHERIT(r4) - ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) cmpwi r6,0 bne 1f - ld r0,0(r7) + ld r0,PACA_DSCR(r13) 1: BEGIN_FTR_SECTION_NESTED(70) mfspr r8, SPRN_FSCR diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index e2a1d6fb3297..67fd2fd2620a 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -484,7 +484,6 @@ SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_SPRSETUP(purr, SPRN_PURR); SYSFS_SPRSETUP(spurr, SPRN_SPURR); -SYSFS_SPRSETUP(dscr, SPRN_DSCR); SYSFS_SPRSETUP(pir, SPRN_PIR); /* @@ -494,12 +493,27 @@ SYSFS_SPRSETUP(pir, SPRN_PIR); */ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); -static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static DEVICE_ATTR(purr, 0400, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); -unsigned long dscr_default = 0; -EXPORT_SYMBOL(dscr_default); +static unsigned long dscr_default; + +static void read_dscr(void *val) +{ + *(unsigned long *)val = get_paca()->dscr_default; +} + +static void write_dscr(void *val) +{ + get_paca()->dscr_default = *(unsigned long *)val; + if (!current->thread.dscr_inherit) { + current->thread.dscr = *(unsigned long *)val; + mtspr(SPRN_DSCR, *(unsigned long *)val); + } +} + +SYSFS_SPRSETUP_SHOW_STORE(dscr); +static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static void add_write_permission_dev_attr(struct device_attribute *attr) { @@ -512,14 +526,6 @@ static ssize_t show_dscr_default(struct device *dev, return sprintf(buf, "%lx\n", dscr_default); } -static void update_dscr(void *dummy) -{ - if (!current->thread.dscr_inherit) { - current->thread.dscr = dscr_default; - mtspr(SPRN_DSCR, dscr_default); - } -} - static ssize_t __used store_dscr_default(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -532,7 +538,7 @@ static ssize_t __used store_dscr_default(struct device *dev, return -EINVAL; dscr_default = val; - on_each_cpu(update_dscr, NULL, 1); + on_each_cpu(write_dscr, &val, 1); return count; } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index ee061c3715de..2a324f4cb1b9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -78,12 +78,6 @@ _GLOBAL(tm_abort) TABORT(R3) blr - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* void tm_reclaim(struct thread_struct *thread, * unsigned long orig_msr, * uint8_t cause) @@ -298,9 +292,8 @@ dont_backup_fp: mtlr r0 ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr @@ -479,9 +472,8 @@ restore_gprs: mtlr r0 ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 9f0ad718e476..12f4ce5b4f78 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -286,8 +286,7 @@ kvm_start_guest: beq kvm_no_guest /* Set HSTATE_DSCR(r13) to something sensible */ - LOAD_REG_ADDR(r6, dscr_default) - ld r6, 0(r6) + ld r6, PACA_DSCR(r13) std r6, HSTATE_DSCR(r13) bl kvmppc_hv_entry -- cgit v1.2.3 From c4cad90f9e9dcb85afc5e75a02ae3522ed077296 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 3 Jun 2014 17:33:41 +1000 Subject: powerpc/serial: Use saner flags when creating legacy ports We had a mix & match of flags used when creating legacy ports depending on where we found them in the device-tree. Among others we were missing UPF_SKIP_TEST for some kind of ISA ports which is a problem as quite a few UARTs out there don't support the loopback test (such as a lot of BMCs). Let's pick the set of flags used by the SoC code and generalize it which means autoconf, no loopback test, irq maybe shared and fixed port. Sending to stable as the lack of UPF_SKIP_TEST is breaking serial on some machines so I want this back into distros Signed-off-by: Benjamin Herrenschmidt CC: stable@vger.kernel.org --- arch/powerpc/kernel/legacy_serial.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 85fb16e64cef..936258881c98 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | + UPF_SHARE_IRQ | UPF_FIXED_PORT; + static unsigned int tsi_serial_in(struct uart_port *p, int offset) { unsigned int tmp; @@ -160,8 +163,6 @@ static int __init add_legacy_soc_port(struct device_node *np, { u64 addr; const __be32 *addrp; - upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ - | UPF_FIXED_PORT; struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly @@ -191,9 +192,11 @@ static int __init add_legacy_soc_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) - return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, + NO_IRQ, legacy_port_flags, 0); else - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, + NO_IRQ, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -239,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0); + taddr, NO_IRQ, legacy_port_flags, 0); } @@ -312,7 +315,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, - UPF_BOOT_AUTOCONF, np != pci_dev); + legacy_port_flags, np != pci_dev); } #endif -- cgit v1.2.3 From 2213fb142f1fff1ac28868d196294ca4423659af Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 4 Jun 2014 09:49:17 +0800 Subject: powerpc/eeh: Skip eeh sysfs when eeh is disabled When eeh is not enabled, and hotplug two pci devices on the same bus, eeh related sysfs would be added twice for the first added pci device. Since the eeh_dev is not created when eeh is not enabled. This patch adds the check, if eeh is not enabled, eeh sysfs will not be created. After applying this patch, following warnings are reduced: sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_mode' sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_config_addr' sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_pe_config_addr' Signed-off-by: Wei Yang Acked-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh_sysfs.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 5d753d4f2c75..e2595ba4b720 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -59,6 +59,9 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); int rc=0; + if (!eeh_enabled()) + return; + if (edev && (edev->mode & EEH_DEV_SYSFS)) return; -- cgit v1.2.3 From a5d862576a64cb3e0c22dc9cc2170e4d750714f9 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 4 Jun 2014 17:50:47 +1000 Subject: powerpc: Allow ppc_md platform hook to override memory_block_size_bytes The pseries platform code unconditionally overrides memory_block_size_bytes regardless of the running platform. Create a ppc_md hook that so each platform can choose to do what it wants. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/machdep.h | 3 +++ arch/powerpc/kernel/setup_64.c | 10 ++++++++++ arch/powerpc/platforms/pseries/hotplug-memory.c | 17 +++-------------- arch/powerpc/platforms/pseries/pseries.h | 2 ++ arch/powerpc/platforms/pseries/setup.c | 3 +++ 5 files changed, 21 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 374abc2e41d7..f92b0b54e921 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -98,6 +98,9 @@ struct machdep_calls { void (*iommu_save)(void); void (*iommu_restore)(void); #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + unsigned long (*memory_block_size)(void); +#endif #endif /* CONFIG_PPC64 */ void (*pci_dma_dev_setup)(struct pci_dev *dev); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 90b532ace0d5..ee082d771178 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -780,6 +781,15 @@ void __init setup_per_cpu_areas(void) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +unsigned long memory_block_size_bytes(void) +{ + if (ppc_md.memory_block_size) + return ppc_md.memory_block_size(); + + return MIN_MEMORY_BLOCK_SIZE; +} +#endif #if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO) struct ppc_pci_io ppc_pci_io; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 7f75c94af822..7995135170a3 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -21,7 +21,7 @@ #include #include -static unsigned long get_memblock_size(void) +unsigned long pseries_memory_block_size(void) { struct device_node *np; unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; @@ -64,17 +64,6 @@ static unsigned long get_memblock_size(void) return memblock_size; } -/* WARNING: This is going to override the generic definition whenever - * pseries is built-in regardless of what platform is active at boot - * time. This is fine for now as this is the only "option" and it - * should work everywhere. If not, we'll have to turn this into a - * ppc_md. callback - */ -unsigned long memory_block_size_bytes(void) -{ - return get_memblock_size(); -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memory(u64 start, u64 size) { @@ -105,7 +94,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz if (!pfn_valid(start_pfn)) goto out; - block_sz = memory_block_size_bytes(); + block_sz = pseries_memory_block_size(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; nid = memory_add_physaddr_to_nid(base); @@ -201,7 +190,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) u32 *p; int i, rc = -EINVAL; - memblock_size = get_memblock_size(); + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 99219530ea4a..361add62abf1 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -64,4 +64,6 @@ extern int dlpar_detach_node(struct device_node *); struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +unsigned long pseries_memory_block_size(void); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 215c3c269617..adc21a0e3410 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -810,4 +810,7 @@ define_machine(pseries) { #ifdef CONFIG_KEXEC .machine_kexec = pSeries_machine_kexec, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pseries_memory_block_size, +#endif }; -- cgit v1.2.3