diff options
Diffstat (limited to 'arch/powerpc/kernel')
26 files changed, 1209 insertions, 346 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 612b0c4dc26..b73396b9390 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -4,6 +4,8 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' +subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror + ifeq ($(CONFIG_PPC64),y) CFLAGS_prom_init.o += -mno-minimal-toc endif @@ -95,9 +97,10 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o -obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \ - power5-pmu.o power5+-pmu.o power6-pmu.o \ - power7-pmu.o +obj-$(CONFIG_PPC_PERF_CTRS) += perf_counter.o +obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ + power5+-pmu.o power6-pmu.o power7-pmu.o +obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o @@ -106,6 +109,7 @@ obj-y += iomap.o endif obj-$(CONFIG_PPC64) += $(obj64-y) +obj-$(CONFIG_PPC32) += $(obj32-y) ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) obj-y += ppc_save_regs.o diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index 54f767e31a1..1e9949e6885 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -239,6 +239,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR) ori r11,r11,HID0_SGE | HID0_FOLD | HID0_BHTE ori r11,r11,HID0_LRSTK | HID0_BTIC oris r11,r11,HID0_DPM@h +BEGIN_MMU_FTR_SECTION + oris r11,r11,HID0_HIGH_BAT@h +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) BEGIN_FTR_SECTION xori r11,r11,HID0_BTIC END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC) diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index eb4b9adcedb..0adb50ad803 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -17,6 +17,40 @@ #include <asm/cputable.h> #include <asm/ppc_asm.h> +_GLOBAL(__e500_icache_setup) + mfspr r0, SPRN_L1CSR1 + andi. r3, r0, L1CSR1_ICE + bnelr /* Already enabled */ + oris r0, r0, L1CSR1_CPE@h + ori r0, r0, (L1CSR1_ICFI | L1CSR1_ICLFR | L1CSR1_ICE) + mtspr SPRN_L1CSR1, r0 /* Enable I-Cache */ + isync + blr + +_GLOBAL(__e500_dcache_setup) + mfspr r0, SPRN_L1CSR0 + andi. r3, r0, L1CSR0_DCE + bnelr /* Already enabled */ + msync + isync + li r0, 0 + mtspr SPRN_L1CSR0, r0 /* Disable */ + msync + isync + li r0, (L1CSR0_DCFI | L1CSR0_CLFC) + mtspr SPRN_L1CSR0, r0 /* Invalidate */ + isync +1: mfspr r0, SPRN_L1CSR0 + andi. r3, r0, L1CSR0_CLFC + bne+ 1b /* Wait for lock bits reset */ + oris r0, r0, L1CSR0_CPE@h + ori r0, r0, L1CSR0_DCE + msync + isync + mtspr SPRN_L1CSR0, r0 /* Enable */ + isync + blr + _GLOBAL(__setup_cpu_e200) /* enable dedicated debug exception handling resources (Debug APU) */ mfspr r3,SPRN_HID0 @@ -25,7 +59,16 @@ _GLOBAL(__setup_cpu_e200) b __setup_e200_ivors _GLOBAL(__setup_cpu_e500v1) _GLOBAL(__setup_cpu_e500v2) - b __setup_e500_ivors + mflr r4 + bl __e500_icache_setup + bl __e500_dcache_setup + bl __setup_e500_ivors + mtlr r4 + blr _GLOBAL(__setup_cpu_e500mc) - b __setup_e500mc_ivors - + mflr r4 + bl __e500_icache_setup + bl __e500_dcache_setup + bl __setup_e500mc_ivors + mtlr r4 + blr diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 20a60d661ba..ccf129d47d8 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -7,6 +7,7 @@ #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/lmb.h> #include <asm/bug.h> #include <asm/abs_addr.h> @@ -90,11 +91,10 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, static int dma_direct_dma_supported(struct device *dev, u64 mask) { #ifdef CONFIG_PPC64 - /* Could be improved to check for memory though it better be - * done via some global so platforms can set the limit in case + /* Could be improved so platforms can set the limit in case * they have limited DMA windows */ - return mask >= DMA_BIT_MASK(32); + return mask >= (lmb_end_of_DRAM() - 1); #else return 1; #endif diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 4dd38f12915..3cadba60a4b 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -191,11 +191,49 @@ transfer_to_handler_cont: mflr r9 lwz r11,0(r9) /* virtual address of handler */ lwz r9,4(r9) /* where to go when done */ +#ifdef CONFIG_TRACE_IRQFLAGS + lis r12,reenable_mmu@h + ori r12,r12,reenable_mmu@l + mtspr SPRN_SRR0,r12 + mtspr SPRN_SRR1,r10 + SYNC + RFI +reenable_mmu: /* re-enable mmu so we can */ + mfmsr r10 + lwz r12,_MSR(r1) + xor r10,r10,r12 + andi. r10,r10,MSR_EE /* Did EE change? */ + beq 1f + + /* Save handler and return address into the 2 unused words + * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything + * else can be recovered from the pt_regs except r3 which for + * normal interrupts has been set to pt_regs and for syscalls + * is an argument, so we temporarily use ORIG_GPR3 to save it + */ + stw r9,8(r1) + stw r11,12(r1) + stw r3,ORIG_GPR3(r1) + bl trace_hardirqs_off + lwz r0,GPR0(r1) + lwz r3,ORIG_GPR3(r1) + lwz r4,GPR4(r1) + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + lwz r9,8(r1) + lwz r11,12(r1) +1: mtctr r11 + mtlr r9 + bctr /* jump to handler */ +#else /* CONFIG_TRACE_IRQFLAGS */ mtspr SPRN_SRR0,r11 mtspr SPRN_SRR1,r10 mtlr r9 SYNC RFI /* jump to handler, enable MMU */ +#endif /* CONFIG_TRACE_IRQFLAGS */ #if defined (CONFIG_6xx) || defined(CONFIG_E500) 4: rlwinm r12,r12,0,~_TLF_NAPPING @@ -251,6 +289,31 @@ _GLOBAL(DoSyscall) #ifdef SHOW_SYSCALLS bl do_show_syscall #endif /* SHOW_SYSCALLS */ +#ifdef CONFIG_TRACE_IRQFLAGS + /* Return from syscalls can (and generally will) hard enable + * interrupts. You aren't supposed to call a syscall with + * interrupts disabled in the first place. However, to ensure + * that we get it right vs. lockdep if it happens, we force + * that hard enable here with appropriate tracing if we see + * that we have been called with interrupts off + */ + mfmsr r11 + andi. r12,r11,MSR_EE + bne+ 1f + /* We came in with interrupts disabled, we enable them now */ + bl trace_hardirqs_on + mfmsr r11 + lwz r0,GPR0(r1) + lwz r3,GPR3(r1) + lwz r4,GPR4(r1) + ori r11,r11,MSR_EE + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + mtmsr r11 +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ lwz r11,TI_FLAGS(r10) andi. r11,r11,_TIF_SYSCALL_T_OR_A @@ -275,6 +338,7 @@ ret_from_syscall: rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ /* disable interrupts so current_thread_info()->flags can't change */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ + /* Note: We don't bother telling lockdep about it */ SYNC MTMSRD(r10) lwz r9,TI_FLAGS(r12) @@ -288,6 +352,19 @@ ret_from_syscall: oris r11,r11,0x1000 /* Set SO bit in CR */ stw r11,_CCR(r1) syscall_exit_cont: + lwz r8,_MSR(r1) +#ifdef CONFIG_TRACE_IRQFLAGS + /* If we are going to return from the syscall with interrupts + * off, we trace that here. It shouldn't happen though but we + * want to catch the bugger if it does right ? + */ + andi. r10,r8,MSR_EE + bne+ 1f + stw r3,GPR3(r1) + bl trace_hardirqs_off + lwz r3,GPR3(r1) +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) /* If the process has its own DBCR0 value, load it up. The internal debug mode bit tells us that dbcr0 should be loaded. */ @@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) mtlr r4 mtcr r5 lwz r7,_NIP(r1) - lwz r8,_MSR(r1) FIX_SRR1(r8, r0) lwz r2,GPR2(r1) lwz r1,GPR1(r1) @@ -394,7 +470,9 @@ syscall_exit_work: andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq ret_from_except - /* Re-enable interrupts */ + /* Re-enable interrupts. There is no need to trace that with + * lockdep as we are supposed to have IRQs on at this point + */ ori r10,r10,MSR_EE SYNC MTMSRD(r10) @@ -705,6 +783,7 @@ ret_from_except: /* Hard-disable interrupts so that current_thread_info()->flags * can't change between when we test it and when we return * from the interrupt. */ + /* Note: We don't bother telling lockdep about it */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) SYNC /* Some chip revs have problems here... */ MTMSRD(r10) /* disable interrupts */ @@ -744,11 +823,24 @@ resume_kernel: beq+ restore andi. r0,r3,MSR_EE /* interrupts off? */ beq restore /* don't schedule if so */ +#ifdef CONFIG_TRACE_IRQFLAGS + /* Lockdep thinks irqs are enabled, we need to call + * preempt_schedule_irq with IRQs off, so we inform lockdep + * now that we -did- turn them off already + */ + bl trace_hardirqs_off +#endif 1: bl preempt_schedule_irq rlwinm r9,r1,0,0,(31-THREAD_SHIFT) lwz r3,TI_FLAGS(r9) andi. r0,r3,_TIF_NEED_RESCHED bne- 1b +#ifdef CONFIG_TRACE_IRQFLAGS + /* And now, to properly rebalance the above, we tell lockdep they + * are being turned back on, which will happen when we return + */ + bl trace_hardirqs_on +#endif #else resume_kernel: #endif /* CONFIG_PREEMPT */ @@ -765,6 +857,28 @@ restore: stw r6,icache_44x_need_flush@l(r4) 1: #endif /* CONFIG_44x */ + + lwz r9,_MSR(r1) +#ifdef CONFIG_TRACE_IRQFLAGS + /* Lockdep doesn't know about the fact that IRQs are temporarily turned + * off in this assembly code while peeking at TI_FLAGS() and such. However + * we need to inform it if the exception turned interrupts off, and we + * are about to trun them back on. + * + * The problem here sadly is that we don't know whether the exceptions was + * one that turned interrupts off or not. So we always tell lockdep about + * turning them on here when we go back to wherever we came from with EE + * on, even if that may meen some redudant calls being tracked. Maybe later + * we could encode what the exception did somewhere or test the exception + * type in the pt_regs but that sounds overkill + */ + andi. r10,r9,MSR_EE + beq 1f + bl trace_hardirqs_on + lwz r9,_MSR(r1) +1: +#endif /* CONFIG_TRACE_IRQFLAGS */ + lwz r0,GPR0(r1) lwz r2,GPR2(r1) REST_4GPRS(3, r1) @@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) - lwz r9,_MSR(r1) andi. r10,r9,MSR_RI /* check if this exception occurred */ beql nonrecoverable /* at a bad place (MSR:RI = 0) */ @@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) MTMSRD(r10) /* clear the RI bit */ .globl exc_exit_restart exc_exit_restart: - lwz r9,_MSR(r1) lwz r12,_NIP(r1) FIX_SRR1(r9,r10) mtspr SPRN_SRR0,r12 @@ -1035,11 +1147,18 @@ do_work: /* r10 contains MSR_KERNEL here */ beq do_user_signal do_resched: /* r10 contains MSR_KERNEL here */ + /* Note: We don't need to inform lockdep that we are enabling + * interrupts here. As far as it knows, they are already enabled + */ ori r10,r10,MSR_EE SYNC MTMSRD(r10) /* hard-enable interrupts */ bl schedule recheck: + /* Note: And we don't tell it we are disabling them again + * neither. Those disable/enable cycles used to peek at + * TI_FLAGS aren't advertised. + */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) SYNC MTMSRD(r10) /* disable interrupts */ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 1b12696cca0..ce1f3e44c24 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -586,7 +586,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) { *parent = old; return; } diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 48469463f89..fc213294275 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -1124,9 +1124,8 @@ mmu_off: RFI /* - * Use the first pair of BAT registers to map the 1st 16MB - * of RAM to PAGE_OFFSET. From this point on we can't safely - * call OF any more. + * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET + * (we keep one for debugging) and on others, we use one 256M BAT. */ initial_bats: lis r11,PAGE_OFFSET@h @@ -1136,12 +1135,16 @@ initial_bats: bne 4f ori r11,r11,4 /* set up BAT registers for 601 */ li r8,0x7f /* valid, block length = 8MB */ - oris r9,r11,0x800000@h /* set up BAT reg for 2nd 8M */ - oris r10,r8,0x800000@h /* set up BAT reg for 2nd 8M */ mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ mtspr SPRN_IBAT0L,r8 /* lower BAT register */ - mtspr SPRN_IBAT1U,r9 - mtspr SPRN_IBAT1L,r10 + addis r11,r11,0x800000@h + addis r8,r8,0x800000@h + mtspr SPRN_IBAT1U,r11 + mtspr SPRN_IBAT1L,r8 + addis r11,r11,0x800000@h + addis r8,r8,0x800000@h + mtspr SPRN_IBAT2U,r11 + mtspr SPRN_IBAT2L,r8 isync blr diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c new file mode 100644 index 00000000000..cc466d039af --- /dev/null +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -0,0 +1,417 @@ +/* + * Performance counter support for MPC7450-family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/string.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> +#include <asm/cputable.h> + +#define N_COUNTER 6 /* Number of hardware counters */ +#define MAX_ALT 3 /* Maximum number of event alternative codes */ + +/* + * Bits in event code for MPC7450 family + */ +#define PM_THRMULT_MSKS 0x40000 +#define PM_THRESH_SH 12 +#define PM_THRESH_MSK 0x3f +#define PM_PMC_SH 8 +#define PM_PMC_MSK 7 +#define PM_PMCSEL_MSK 0x7f + +/* + * Classify events according to how specific their PMC requirements are. + * Result is: + * 0: can go on any PMC + * 1: can go on PMCs 1-4 + * 2: can go on PMCs 1,2,4 + * 3: can go on PMCs 1 or 2 + * 4: can only go on one PMC + * -1: event code is invalid + */ +#define N_CLASSES 5 + +static int mpc7450_classify_event(u32 event) +{ + int pmc; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > N_COUNTER) + return -1; + return 4; + } + event &= PM_PMCSEL_MSK; + if (event <= 1) + return 0; + if (event <= 7) + return 1; + if (event <= 13) + return 2; + if (event <= 22) + return 3; + return -1; +} + +/* + * Events using threshold and possible threshold scale: + * code scale? name + * 11e N PM_INSTQ_EXCEED_CYC + * 11f N PM_ALTV_IQ_EXCEED_CYC + * 128 Y PM_DTLB_SEARCH_EXCEED_CYC + * 12b Y PM_LD_MISS_EXCEED_L1_CYC + * 220 N PM_CQ_EXCEED_CYC + * 30c N PM_GPR_RB_EXCEED_CYC + * 30d ? PM_FPR_IQ_EXCEED_CYC ? + * 311 Y PM_ITLB_SEARCH_EXCEED + * 410 N PM_GPR_IQ_EXCEED_CYC + */ + +/* + * Return use of threshold and threshold scale bits: + * 0 = uses neither, 1 = uses threshold, 2 = uses both + */ +static int mpc7450_threshold_use(u32 event) +{ + int pmc, sel; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + sel = event & PM_PMCSEL_MSK; + switch (pmc) { + case 1: + if (sel == 0x1e || sel == 0x1f) + return 1; + if (sel == 0x28 || sel == 0x2b) + return 2; + break; + case 2: + if (sel == 0x20) + return 1; + break; + case 3: + if (sel == 0xc || sel == 0xd) + return 1; + if (sel == 0x11) + return 2; + break; + case 4: + if (sel == 0x10) + return 1; + break; + } + return 0; +} + +/* + * Layout of constraint bits: + * 33222222222211111111110000000000 + * 10987654321098765432109876543210 + * |< >< > < > < ><><><><><><> + * TS TV G4 G3 G2P6P5P4P3P2P1 + * + * P1 - P6 + * 0 - 11: Count of events needing PMC1 .. PMC6 + * + * G2 + * 12 - 14: Count of events needing PMC1 or PMC2 + * + * G3 + * 16 - 18: Count of events needing PMC1, PMC2 or PMC4 + * + * G4 + * 20 - 23: Count of events needing PMC1, PMC2, PMC3 or PMC4 + * + * TV + * 24 - 29: Threshold value requested + * + * TS + * 30: Threshold scale value requested + */ + +static u32 pmcbits[N_COUNTER][2] = { + { 0x00844002, 0x00111001 }, /* PMC1 mask, value: P1,G2,G3,G4 */ + { 0x00844008, 0x00111004 }, /* PMC2: P2,G2,G3,G4 */ + { 0x00800020, 0x00100010 }, /* PMC3: P3,G4 */ + { 0x00840080, 0x00110040 }, /* PMC4: P4,G3,G4 */ + { 0x00000200, 0x00000100 }, /* PMC5: P5 */ + { 0x00000800, 0x00000400 } /* PMC6: P6 */ +}; + +static u32 classbits[N_CLASSES - 1][2] = { + { 0x00000000, 0x00000000 }, /* class 0: no constraint */ + { 0x00800000, 0x00100000 }, /* class 1: G4 */ + { 0x00040000, 0x00010000 }, /* class 2: G3 */ + { 0x00004000, 0x00001000 }, /* class 3: G2 */ +}; + +static int mpc7450_get_constraint(u64 event, unsigned long *maskp, + unsigned long *valp) +{ + int pmc, class; + u32 mask, value; + int thresh, tuse; + + class = mpc7450_classify_event(event); + if (class < 0) + return -1; + if (class == 4) { + pmc = ((unsigned int)event >> PM_PMC_SH) & PM_PMC_MSK; + mask = pmcbits[pmc - 1][0]; + value = pmcbits[pmc - 1][1]; + } else { + mask = classbits[class][0]; + value = classbits[class][1]; + } + + tuse = mpc7450_threshold_use(event); + if (tuse) { + thresh = ((unsigned int)event >> PM_THRESH_SH) & PM_THRESH_MSK; + mask |= 0x3f << 24; + value |= thresh << 24; + if (tuse == 2) { + mask |= 0x40000000; + if ((unsigned int)event & PM_THRMULT_MSKS) + value |= 0x40000000; + } + } + + *maskp = mask; + *valp = value; + return 0; +} + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x217, 0x317 }, /* PM_L1_DCACHE_MISS */ + { 0x418, 0x50f, 0x60f }, /* PM_SNOOP_RETRY */ + { 0x502, 0x602 }, /* PM_L2_HIT */ + { 0x503, 0x603 }, /* PM_L3_HIT */ + { 0x504, 0x604 }, /* PM_L2_ICACHE_MISS */ + { 0x505, 0x605 }, /* PM_L3_ICACHE_MISS */ + { 0x506, 0x606 }, /* PM_L2_DCACHE_MISS */ + { 0x507, 0x607 }, /* PM_L3_DCACHE_MISS */ + { 0x50a, 0x623 }, /* PM_LD_HIT_L3 */ + { 0x50b, 0x624 }, /* PM_ST_HIT_L3 */ + { 0x50d, 0x60d }, /* PM_L2_TOUCH_HIT */ + { 0x50e, 0x60e }, /* PM_L3_TOUCH_HIT */ + { 0x512, 0x612 }, /* PM_INT_LOCAL */ + { 0x513, 0x61d }, /* PM_L2_MISS */ + { 0x514, 0x61e }, /* PM_L3_MISS */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u32 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static int mpc7450_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + u32 ae; + + alt[0] = event; + nalt = 1; + i = find_alternative((u32)event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != (u32)event) + alt[nalt++] = ae; + } + } + return nalt; +} + +/* + * Bitmaps of which PMCs each class can use for classes 0 - 3. + * Bit i is set if PMC i+1 is usable. + */ +static const u8 classmap[N_CLASSES] = { + 0x3f, 0x0f, 0x0b, 0x03, 0 +}; + +/* Bit position and width of each PMCSEL field */ +static const int pmcsel_shift[N_COUNTER] = { + 6, 0, 27, 22, 17, 11 +}; +static const u32 pmcsel_mask[N_COUNTER] = { + 0x7f, 0x3f, 0x1f, 0x1f, 0x1f, 0x3f +}; + +/* + * Compute MMCR0/1/2 values for a set of events. + */ +static int mpc7450_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], unsigned long mmcr[]) +{ + u8 event_index[N_CLASSES][N_COUNTER]; + int n_classevent[N_CLASSES]; + int i, j, class, tuse; + u32 pmc_inuse = 0, pmc_avail; + u32 mmcr0 = 0, mmcr1 = 0, mmcr2 = 0; + u32 ev, pmc, thresh; + + if (n_ev > N_COUNTER) + return -1; + + /* First pass: count usage in each class */ + for (i = 0; i < N_CLASSES; ++i) + n_classevent[i] = 0; + for (i = 0; i < n_ev; ++i) { + class = mpc7450_classify_event(event[i]); + if (class < 0) + return -1; + j = n_classevent[class]++; + event_index[class][j] = i; + } + + /* Second pass: allocate PMCs from most specific event to least */ + for (class = N_CLASSES - 1; class >= 0; --class) { + for (i = 0; i < n_classevent[class]; ++i) { + ev = event[event_index[class][i]]; + if (class == 4) { + pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + } else { + /* Find a suitable PMC */ + pmc_avail = classmap[class] & ~pmc_inuse; + if (!pmc_avail) + return -1; + pmc = ffs(pmc_avail); + } + pmc_inuse |= 1 << (pmc - 1); + + tuse = mpc7450_threshold_use(ev); + if (tuse) { + thresh = (ev >> PM_THRESH_SH) & PM_THRESH_MSK; + mmcr0 |= thresh << 16; + if (tuse == 2 && (ev & PM_THRMULT_MSKS)) + mmcr2 = 0x80000000; + } + ev &= pmcsel_mask[pmc - 1]; + ev <<= pmcsel_shift[pmc - 1]; + if (pmc <= 2) + mmcr0 |= ev; + else + mmcr1 |= ev; + hwc[event_index[class][i]] = pmc - 1; + } + } + + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr0 |= MMCR0_PMCnCE; + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcr2; + return 0; +} + +/* + * Disable counting by a PMC. + * Note that the pmc argument is 0-based here, not 1-based. + */ +static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +{ + if (pmc <= 1) + mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); + else + mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); +} + +static int mpc7450_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 1, + [PERF_COUNT_HW_INSTRUCTIONS] = 2, + [PERF_COUNT_HW_CACHE_MISSES] = 0x217, /* PM_L1_DCACHE_MISS */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x122, /* PM_BR_CMPL */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x41c, /* PM_BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x225 }, + [C(OP_WRITE)] = { 0, 0x227 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x129, 0x115 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0x634, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x312 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x223 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x122, 0x41c }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu mpc7450_pmu = { + .name = "MPC7450 family", + .n_counter = N_COUNTER, + .max_alternatives = MAX_ALT, + .add_fields = 0x00111555ul, + .test_adder = 0x00301000ul, + .compute_mmcr = mpc7450_compute_mmcr, + .get_constraint = mpc7450_get_constraint, + .get_alternatives = mpc7450_get_alternatives, + .disable_pmc = mpc7450_disable_pmc, + .n_generic = ARRAY_SIZE(mpc7450_generic_events), + .generic_events = mpc7450_generic_events, + .cache_events = &mpc7450_cache_events, +}; + +static int init_mpc7450_pmu(void) +{ + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450")) + return -ENODEV; + + return register_power_pmu(&mpc7450_pmu); +} + +arch_initcall(init_mpc7450_pmu); diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index fa983a59c4c..a359cb08e90 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np, dev->dev.archdata.of_node = np; if (bus_id) - dev_set_name(&dev->dev, bus_id); + dev_set_name(&dev->dev, "%s", bus_id); else of_device_make_bus_id(dev); diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c index bb202388170..70e1f57f7dd 100644 --- a/arch/powerpc/kernel/perf_counter.c +++ b/arch/powerpc/kernel/perf_counter.c @@ -29,7 +29,7 @@ struct cpu_hw_counters { struct perf_counter *counter[MAX_HWCOUNTERS]; u64 events[MAX_HWCOUNTERS]; unsigned int flags[MAX_HWCOUNTERS]; - u64 mmcr[3]; + unsigned long mmcr[3]; struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS]; u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS]; }; @@ -46,6 +46,115 @@ struct power_pmu *ppmu; */ static unsigned int freeze_counters_kernel = MMCR0_FCS; +/* + * 32-bit doesn't have MMCRA but does have an MMCR2, + * and a few other names are different. + */ +#ifdef CONFIG_PPC32 + +#define MMCR0_FCHV 0 +#define MMCR0_PMCjCE MMCR0_PMCnCE + +#define SPRN_MMCRA SPRN_MMCR2 +#define MMCRA_SAMPLE_ENABLE 0 + +static inline unsigned long perf_ip_adjust(struct pt_regs *regs) +{ + return 0; +} +static inline void perf_set_pmu_inuse(int inuse) { } +static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { } +static inline u32 perf_get_misc_flags(struct pt_regs *regs) +{ + return 0; +} +static inline void perf_read_regs(struct pt_regs *regs) { } +static inline int perf_intr_is_nmi(struct pt_regs *regs) +{ + return 0; +} + +#endif /* CONFIG_PPC32 */ + +/* + * Things that are specific to 64-bit implementations. + */ +#ifdef CONFIG_PPC64 + +static inline unsigned long perf_ip_adjust(struct pt_regs *regs) +{ + unsigned long mmcra = regs->dsisr; + + if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; + if (slot > 1) + return 4 * (slot - 1); + } + return 0; +} + +static inline void perf_set_pmu_inuse(int inuse) +{ + get_lppaca()->pmcregs_in_use = inuse; +} + +/* + * The user wants a data address recorded. + * If we're not doing instruction sampling, give them the SDAR + * (sampled data address). If we are doing instruction sampling, then + * only give them the SDAR if it corresponds to the instruction + * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC + * bit in MMCRA. + */ +static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) +{ + unsigned long m |