From 81cd5ae303e88a1e9d3a3e0f1fe8abd100edde16 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 27 Oct 2009 18:31:29 +0000 Subject: powerpc: perf_event: Enable SDAR in continous sample mode In continuous sampling mode we want the SDAR to update. While we can select between dcache misses and ERAT (L1-TLB) misses, a decent default is to enable both. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/reg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 6315edc205d..bc8dd53f718 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -489,6 +489,8 @@ #define SPRN_MMCR1 798 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ +#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL +#define MMCRA_SDAR_ERAT_MISS 0x20000000UL #define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */ #define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ -- cgit v1.2.3-70-g09d2 From eecff81d1fcda22cd0029d11fe2a71dceed11dad Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 27 Oct 2009 18:46:55 +0000 Subject: powerpc: Create PPC_WARN_ALIGNMENT to match PPC_WARN_EMULATED perf_event wants a separate event for alignment and emulation faults, so create another emulation event. This will make it easy to hook in perf_event at one spot. We pass in regs which will be required for these events. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/emulated_ops.h | 7 +++++-- arch/powerpc/kernel/align.c | 12 ++++++------ arch/powerpc/kernel/traps.c | 18 +++++++++--------- 3 files changed, 20 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 9154e852673..640c4e456aa 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -57,7 +57,7 @@ extern u32 ppc_warn_emulated; extern void ppc_warn_emulated_print(const char *type); -#define PPC_WARN_EMULATED(type) \ +#define __PPC_WARN_EMULATED(type) \ do { \ atomic_inc(&ppc_emulated.type.val); \ if (ppc_warn_emulated) \ @@ -66,8 +66,11 @@ extern void ppc_warn_emulated_print(const char *type); #else /* !CONFIG_PPC_EMULATED_STATS */ -#define PPC_WARN_EMULATED(type) do { } while (0) +#define __PPC_WARN_EMULATED(type) do { } while (0) #endif /* !CONFIG_PPC_EMULATED_STATS */ +#define PPC_WARN_EMULATED(type, regs) __PPC_WARN_EMULATED(type) +#define PPC_WARN_ALIGNMENT(type, regs) __PPC_WARN_EMULATED(type) + #endif /* _ASM_POWERPC_EMULATED_OPS_H */ diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index a5b632e52fa..3839839f83c 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -732,7 +732,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_SPE if ((instr >> 26) == 0x4) { - PPC_WARN_EMULATED(spe); + PPC_WARN_ALIGNMENT(spe, regs); return emulate_spe(regs, reg, instr); } #endif @@ -786,7 +786,7 @@ int fix_alignment(struct pt_regs *regs) flags |= SPLT; nb = 8; } - PPC_WARN_EMULATED(vsx); + PPC_WARN_ALIGNMENT(vsx, regs); return emulate_vsx(addr, reg, areg, regs, flags, nb); } #endif @@ -794,7 +794,7 @@ int fix_alignment(struct pt_regs *regs) * the exception of DCBZ which is handled as a special case here */ if (instr == DCBZ) { - PPC_WARN_EMULATED(dcbz); + PPC_WARN_ALIGNMENT(dcbz, regs); return emulate_dcbz(regs, addr); } if (unlikely(nb == 0)) @@ -804,7 +804,7 @@ int fix_alignment(struct pt_regs *regs) * function */ if (flags & M) { - PPC_WARN_EMULATED(multiple); + PPC_WARN_ALIGNMENT(multiple, regs); return emulate_multiple(regs, addr, reg, nb, flags, instr, swiz); } @@ -825,11 +825,11 @@ int fix_alignment(struct pt_regs *regs) /* Special case for 16-byte FP loads and stores */ if (nb == 16) { - PPC_WARN_EMULATED(fp_pair); + PPC_WARN_ALIGNMENT(fp_pair, regs); return emulate_fp_pair(addr, reg, flags); } - PPC_WARN_EMULATED(unaligned); + PPC_WARN_ALIGNMENT(unaligned, regs); /* If we are loading, get the data from user space, else * get it from register values diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6f0ae1a9bfa..9d1f9354d6c 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -759,7 +759,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate the mfspr rD, PVR. */ if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) { - PPC_WARN_EMULATED(mfpvr); + PPC_WARN_EMULATED(mfpvr, regs); rd = (instword >> 21) & 0x1f; regs->gpr[rd] = mfspr(SPRN_PVR); return 0; @@ -767,7 +767,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulating the dcba insn is just a no-op. */ if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) { - PPC_WARN_EMULATED(dcba); + PPC_WARN_EMULATED(dcba, regs); return 0; } @@ -776,7 +776,7 @@ static int emulate_instruction(struct pt_regs *regs) int shift = (instword >> 21) & 0x1c; unsigned long msk = 0xf0000000UL >> shift; - PPC_WARN_EMULATED(mcrxr); + PPC_WARN_EMULATED(mcrxr, regs); regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk); regs->xer &= ~0xf0000000UL; return 0; @@ -784,19 +784,19 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate load/store string insn. */ if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) { - PPC_WARN_EMULATED(string); + PPC_WARN_EMULATED(string, regs); return emulate_string_inst(regs, instword); } /* Emulate the popcntb (Population Count Bytes) instruction. */ if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) { - PPC_WARN_EMULATED(popcntb); + PPC_WARN_EMULATED(popcntb, regs); return emulate_popcntb_inst(regs, instword); } /* Emulate isel (Integer Select) instruction */ if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) { - PPC_WARN_EMULATED(isel); + PPC_WARN_EMULATED(isel, regs); return emulate_isel(regs, instword); } @@ -995,7 +995,7 @@ void SoftwareEmulation(struct pt_regs *regs) #ifdef CONFIG_MATH_EMULATION errcode = do_mathemu(regs); if (errcode >= 0) - PPC_WARN_EMULATED(math); + PPC_WARN_EMULATED(math, regs); switch (errcode) { case 0: @@ -1018,7 +1018,7 @@ void SoftwareEmulation(struct pt_regs *regs) #elif defined(CONFIG_8XX_MINIMAL_FPEMU) errcode = Soft_emulate_8xx(regs); if (errcode >= 0) - PPC_WARN_EMULATED(8xx); + PPC_WARN_EMULATED(8xx, regs); switch (errcode) { case 0: @@ -1129,7 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs) flush_altivec_to_thread(current); - PPC_WARN_EMULATED(altivec); + PPC_WARN_EMULATED(altivec, regs); err = emulate_altivec(regs); if (err == 0) { regs->nip += 4; /* skip emulated instruction */ -- cgit v1.2.3-70-g09d2 From 196f02bf900c5eb6f85d889c4f70e7cc11fda7e8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 01:13:00 +0000 Subject: powerpc: perf_event: Add alignment-faults and emulation-faults software events Hook up the alignment-faults and emulation-faults events for powerpc. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/emulated_ops.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 640c4e456aa..f0fb4fc1f6e 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -19,6 +19,7 @@ #define _ASM_POWERPC_EMULATED_OPS_H #include +#include #ifdef CONFIG_PPC_EMULATED_STATS @@ -70,7 +71,18 @@ extern void ppc_warn_emulated_print(const char *type); #endif /* !CONFIG_PPC_EMULATED_STATS */ -#define PPC_WARN_EMULATED(type, regs) __PPC_WARN_EMULATED(type) -#define PPC_WARN_ALIGNMENT(type, regs) __PPC_WARN_EMULATED(type) +#define PPC_WARN_EMULATED(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, \ + 1, 0, regs, 0); \ + __PPC_WARN_EMULATED(type); \ + } while (0) + +#define PPC_WARN_ALIGNMENT(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, \ + 1, 0, regs, regs->dar); \ + __PPC_WARN_EMULATED(type); \ + } while (0) #endif /* _ASM_POWERPC_EMULATED_OPS_H */ -- cgit v1.2.3-70-g09d2 From 1bf4af165050d90ea6659ffb2536ec8ca783aab5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:47:42 +0000 Subject: powerpc: tracing: Add powerpc tracepoints for interrupt entry and exit This adds powerpc-specific tracepoints for interrupt entry and exit. While we already have generic irq_handler_entry and irq_handler_exit tracepoints there are cases on our virtualised powerpc machines where an interrupt is presented to the OS, but subsequently handled by the hypervisor. This means no OS interrupt handler is invoked. Here is an example on a POWER6 machine with the patch below applied: -0 [006] 3243.949840744: irq_entry: pt_regs=c0000000ce31fb10 -0 [006] 3243.949850520: irq_exit: pt_regs=c0000000ce31fb10 -0 [007] 3243.950218208: irq_entry: pt_regs=c0000000ce323b10 -0 [007] 3243.950224080: irq_exit: pt_regs=c0000000ce323b10 -0 [000] 3244.021879320: irq_entry: pt_regs=c000000000a63aa0 -0 [000] 3244.021883616: irq_handler_entry: irq=87 handler=eth0 -0 [000] 3244.021887328: irq_handler_exit: irq=87 return=handled -0 [000] 3244.021897408: irq_exit: pt_regs=c000000000a63aa0 Here we see two phantom interrupts (no handler was invoked), followed by a real interrupt for eth0. Without the tracepoints in this patch we would have missed the phantom interrupts. Signed-off-by: Anton Blanchard Acked-by: Steven Rostedt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 53 ++++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/irq.c | 6 +++++ 2 files changed, 59 insertions(+) create mode 100644 arch/powerpc/include/asm/trace.h (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h new file mode 100644 index 00000000000..187696da5ae --- /dev/null +++ b/arch/powerpc/include/asm/trace.h @@ -0,0 +1,53 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM powerpc + +#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_POWERPC_H + +#include + +struct pt_regs; + +TRACE_EVENT(irq_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(irq_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +#endif /* _TRACE_POWERPC_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH asm +#define TRACE_INCLUDE_FILE trace + +#include diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index e5d12117798..02a334662cc 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -70,6 +70,8 @@ #include #include #endif +#define CREATE_TRACE_POINTS +#include int __irq_offset_value; static int ppc_spurious_interrupts; @@ -325,6 +327,8 @@ void do_IRQ(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); unsigned int irq; + trace_irq_entry(regs); + irq_enter(); check_stack_overflow(); @@ -348,6 +352,8 @@ void do_IRQ(struct pt_regs *regs) timer_interrupt(regs); } #endif + + trace_irq_exit(regs); } void __init init_IRQ(void) -- cgit v1.2.3-70-g09d2 From 6795b85c6a4f690e61e7be31aa150d945c723fb5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:49:14 +0000 Subject: powerpc: tracing: Add powerpc tracepoints for timer entry and exit We can monitor the effectiveness of our power management of both the kernel and hypervisor by probing the timer interrupt. For example, on this box we see 10.37s timer interrupts on an idle core: -0 [010] 3900.671297: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3900.671302: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 -0 [010] 3911.042963: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3911.042968: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 -0 [010] 3921.414630: timer_interrupt_entry: pt_regs=c0000000ce1e7b10 -0 [010] 3921.414635: timer_interrupt_exit: pt_regs=c0000000ce1e7b10 Since we have a 207MHz decrementer it will go negative and fire every 10.37s even if Linux is completely idle. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 34 ++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/time.c | 6 ++++++ 2 files changed, 40 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 187696da5ae..b558c31d409 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -42,6 +42,40 @@ TRACE_EVENT(irq_exit, TP_printk("pt_regs=%p", __entry->regs) ); +TRACE_EVENT(timer_interrupt_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(timer_interrupt_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + #endif /* _TRACE_POWERPC_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 92dc844299b..d6e88df4630 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs) struct clock_event_device *evt = &decrementer->event; u64 now; + trace_timer_interrupt_entry(regs); + /* Ensure a positive value is written to the decrementer, or else * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); @@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs) now = decrementer->next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + trace_timer_interrupt_exit(regs); return; } old_regs = set_irq_regs(regs); @@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs) irq_exit(); set_irq_regs(old_regs); + + trace_timer_interrupt_exit(regs); } void wakeup_decrementer(void) -- cgit v1.2.3-70-g09d2 From c8cd093a6e9f96ea6b871576fd4e46d7c818bb89 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:50:29 +0000 Subject: powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig.debug | 2 +- arch/powerpc/include/asm/hvcall.h | 2 + arch/powerpc/include/asm/trace.h | 45 ++++++++++++ arch/powerpc/platforms/pseries/hvCall.S | 101 +++++++++++++++------------ arch/powerpc/platforms/pseries/hvCall_inst.c | 37 ++++++++++ arch/powerpc/platforms/pseries/lpar.c | 32 +++++++++ 6 files changed, 175 insertions(+), 44 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 3b100518539..bf3382f1904 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE config HCALL_STATS bool "Hypervisor call instrumentation" - depends on PPC_PSERIES && DEBUG_FS + depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS help Adds code to keep track of the number of hypervisor calls made and the amount of time spent in hypervisor calls. Wall time spent in diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 6251a4b10be..c27caac47ad 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -274,6 +274,8 @@ struct hcall_stats { unsigned long num_calls; /* number of calls (on this CPU) */ unsigned long tb_total; /* total wall time (mftb) of calls. */ unsigned long purr_total; /* total cpu time (PURR) of calls. */ + unsigned long tb_start; + unsigned long purr_start; }; #define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1) diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index b558c31d409..9b01c0e43b5 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -76,6 +76,51 @@ TRACE_EVENT(timer_interrupt_exit, TP_printk("pt_regs=%p", __entry->regs) ); +#ifdef CONFIG_PPC_PSERIES +extern void hcall_tracepoint_regfunc(void); +extern void hcall_tracepoint_unregfunc(void); + +TRACE_EVENT_FN(hcall_entry, + + TP_PROTO(unsigned long opcode), + + TP_ARGS(opcode), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + ), + + TP_fast_assign( + __entry->opcode = opcode; + ), + + TP_printk("opcode=%lu", __entry->opcode), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); + +TRACE_EVENT_FN(hcall_exit, + + TP_PROTO(unsigned long opcode, unsigned long retval), + + TP_ARGS(opcode, retval), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + __field(unsigned long, retval) + ), + + TP_fast_assign( + __entry->opcode = opcode; + __entry->retval = retval; + ), + + TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); +#endif + #endif /* _TRACE_POWERPC_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index c1427b3634e..01e95ab18d3 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -14,20 +14,54 @@ #define STK_PARM(i) (48 + ((i)-3)*8) -#ifdef CONFIG_HCALL_STATS +#ifdef CONFIG_TRACEPOINTS + + .section ".toc","aw" + + .globl hcall_tracepoint_refcount +hcall_tracepoint_refcount: + .llong 0 + + .section ".text" + /* * precall must preserve all registers. use unused STK_PARM() - * areas to save snapshots and opcode. + * areas to save snapshots and opcode. We branch around this + * in early init (eg when populating the MMU hashtable) by using an + * unconditional cpu feature. */ #define HCALL_INST_PRECALL \ - std r3,STK_PARM(r3)(r1); /* save opcode */ \ - mftb r0; /* get timebase and */ \ - std r0,STK_PARM(r5)(r1); /* save for later */ \ BEGIN_FTR_SECTION; \ - mfspr r0,SPRN_PURR; /* get PURR and */ \ - std r0,STK_PARM(r6)(r1); /* save for later */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); - + b 1f; \ +END_FTR_SECTION(0, 1); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + std r3,STK_PARM(r3)(r1); \ + std r4,STK_PARM(r4)(r1); \ + std r5,STK_PARM(r5)(r1); \ + std r6,STK_PARM(r6)(r1); \ + std r7,STK_PARM(r7)(r1); \ + std r8,STK_PARM(r8)(r1); \ + std r9,STK_PARM(r9)(r1); \ + std r10,STK_PARM(r10)(r1); \ + std r0,16(r1); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_entry; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + ld r4,STK_PARM(r4)(r1); \ + ld r5,STK_PARM(r5)(r1); \ + ld r6,STK_PARM(r6)(r1); \ + ld r7,STK_PARM(r7)(r1); \ + ld r8,STK_PARM(r8)(r1); \ + ld r9,STK_PARM(r9)(r1); \ + ld r10,STK_PARM(r10)(r1); \ + mtlr r0; \ +1: + /* * postcall is performed immediately before function return which * allows liberal use of volatile registers. We branch around this @@ -38,40 +72,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_PURR); BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ - ld r4,STK_PARM(r3)(r1); /* validate opcode */ \ - cmpldi cr7,r4,MAX_HCALL_OPCODE; \ - bgt- cr7,1f; \ - \ - /* get time and PURR snapshots after hcall */ \ - mftb r7; /* timebase after */ \ -BEGIN_FTR_SECTION; \ - mfspr r8,SPRN_PURR; /* PURR after */ \ - ld r6,STK_PARM(r6)(r1); /* PURR before */ \ - subf r6,r6,r8; /* delta */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ - ld r5,STK_PARM(r5)(r1); /* timebase before */ \ - subf r5,r5,r7; /* time delta */ \ - \ - /* calculate address of stat structure r4 = opcode */ \ - srdi r4,r4,2; /* index into array */ \ - mulli r4,r4,HCALL_STAT_SIZE; \ - LOAD_REG_ADDR(r7, per_cpu__hcall_stats); \ - add r4,r4,r7; \ - ld r7,PACA_DATA_OFFSET(r13); /* per cpu offset */ \ - add r4,r4,r7; \ - \ - /* update stats */ \ - ld r7,HCALL_STAT_CALLS(r4); /* count */ \ - addi r7,r7,1; \ - std r7,HCALL_STAT_CALLS(r4); \ - ld r7,HCALL_STAT_TB(r4); /* timebase */ \ - add r7,r7,r5; \ - std r7,HCALL_STAT_TB(r4); \ -BEGIN_FTR_SECTION; \ - ld r7,HCALL_STAT_PURR(r4); /* PURR */ \ - add r7,r7,r6; \ - std r7,HCALL_STAT_PURR(r4); \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + ld r6,STK_PARM(r3)(r1); \ + std r3,STK_PARM(r3)(r1); \ + mr r4,r3; \ + mr r3,r6; \ + std r0,16(r1); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_exit; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + mtlr r0; \ 1: #else #define HCALL_INST_PRECALL diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 3631a4f277e..e44e1035f13 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -26,6 +26,7 @@ #include #include #include +#include DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats); @@ -100,6 +101,34 @@ static const struct file_operations hcall_inst_seq_fops = { #define HCALL_ROOT_DIR "hcall_inst" #define CPU_NAME_BUF_SIZE 32 + +static void probe_hcall_entry(unsigned long opcode) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &get_cpu_var(hcall_stats)[opcode / 4]; + h->tb_start = mftb(); + h->purr_start = mfspr(SPRN_PURR); +} + +static void probe_hcall_exit(unsigned long opcode, unsigned long retval) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &__get_cpu_var(hcall_stats)[opcode / 4]; + h->num_calls++; + h->tb_total = mftb() - h->tb_start; + h->purr_total = mfspr(SPRN_PURR) - h->purr_start; + + put_cpu_var(hcall_stats); +} + static int __init hcall_inst_init(void) { struct dentry *hcall_root; @@ -110,6 +139,14 @@ static int __init hcall_inst_init(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) return 0; + if (register_trace_hcall_entry(probe_hcall_entry)) + return -EINVAL; + + if (register_trace_hcall_exit(probe_hcall_exit)) { + unregister_trace_hcall_entry(probe_hcall_entry); + return -EINVAL; + } + hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL); if (!hcall_root) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 903eb9eec68..4b7b6e8e32d 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "plpar_wrappers.h" #include "pseries.h" @@ -661,3 +662,34 @@ void arch_free_page(struct page *page, int order) EXPORT_SYMBOL(arch_free_page); #endif + +#ifdef CONFIG_TRACEPOINTS +/* + * We optimise our hcall path by placing hcall_tracepoint_refcount + * directly in the TOC so we can check if the hcall tracepoints are + * enabled via a single load. + */ + +/* NB: reg/unreg are called while guarded with the tracepoints_mutex */ +extern long hcall_tracepoint_refcount; + +void hcall_tracepoint_regfunc(void) +{ + hcall_tracepoint_refcount++; +} + +void hcall_tracepoint_unregfunc(void) +{ + hcall_tracepoint_refcount--; +} + +void __trace_hcall_entry(unsigned long opcode) +{ + trace_hcall_entry(opcode); +} + +void __trace_hcall_exit(long opcode, unsigned long retval) +{ + trace_hcall_exit(opcode, retval); +} +#endif -- cgit v1.2.3-70-g09d2 From 6f26353ca29e96475208bce673efb6a2c58b73f2 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 26 Oct 2009 18:51:09 +0000 Subject: powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/trace.h | 9 ++++---- arch/powerpc/platforms/pseries/hvCall.S | 31 +++++++++++++++++++--------- arch/powerpc/platforms/pseries/hvCall_inst.c | 5 +++-- arch/powerpc/platforms/pseries/lpar.c | 9 ++++---- 4 files changed, 34 insertions(+), 20 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 9b01c0e43b5..cbe2297d68b 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -82,9 +82,9 @@ extern void hcall_tracepoint_unregfunc(void); TRACE_EVENT_FN(hcall_entry, - TP_PROTO(unsigned long opcode), + TP_PROTO(unsigned long opcode, unsigned long *args), - TP_ARGS(opcode), + TP_ARGS(opcode, args), TP_STRUCT__entry( __field(unsigned long, opcode) @@ -101,9 +101,10 @@ TRACE_EVENT_FN(hcall_entry, TRACE_EVENT_FN(hcall_exit, - TP_PROTO(unsigned long opcode, unsigned long retval), + TP_PROTO(unsigned long opcode, unsigned long retval, + unsigned long *retbuf), - TP_ARGS(opcode, retval), + TP_ARGS(opcode, retval, retbuf), TP_STRUCT__entry( __field(unsigned long, opcode) diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 01e95ab18d3..383a5d0e981 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -30,7 +30,7 @@ hcall_tracepoint_refcount: * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. */ -#define HCALL_INST_PRECALL \ +#define HCALL_INST_PRECALL(FIRST_REG) \ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ @@ -47,6 +47,7 @@ END_FTR_SECTION(0, 1); \ std r9,STK_PARM(r9)(r1); \ std r10,STK_PARM(r10)(r1); \ std r0,16(r1); \ + addi r4,r1,STK_PARM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ bl .__trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ @@ -68,7 +69,7 @@ END_FTR_SECTION(0, 1); \ * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. */ -#define HCALL_INST_POSTCALL \ +#define __HCALL_INST_POSTCALL \ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ @@ -88,9 +89,19 @@ END_FTR_SECTION(0, 1); \ ld r3,STK_PARM(r3)(r1); \ mtlr r0; \ 1: + +#define HCALL_INST_POSTCALL_NORETS \ + li r5,0; \ + __HCALL_INST_POSTCALL + +#define HCALL_INST_POSTCALL(BUFREG) \ + mr r5,BUFREG; \ + __HCALL_INST_POSTCALL + #else -#define HCALL_INST_PRECALL -#define HCALL_INST_POSTCALL +#define HCALL_INST_PRECALL(FIRST_ARG) +#define HCALL_INST_POSTCALL_NORETS +#define HCALL_INST_POSTCALL(BUFREG) #endif .text @@ -101,11 +112,11 @@ _GLOBAL(plpar_hcall_norets) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r4) HVSC /* invoke the hypervisor */ - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL_NORETS lwz r0,8(r1) mtcrf 0xff,r0 @@ -117,7 +128,7 @@ _GLOBAL(plpar_hcall) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -136,7 +147,7 @@ _GLOBAL(plpar_hcall) std r6, 16(r12) std r7, 24(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 @@ -183,7 +194,7 @@ _GLOBAL(plpar_hcall9) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -211,7 +222,7 @@ _GLOBAL(plpar_hcall9) std r11,56(r12) std r0, 64(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index e44e1035f13..2f58c71b725 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -102,7 +102,7 @@ static const struct file_operations hcall_inst_seq_fops = { #define CPU_NAME_BUF_SIZE 32 -static void probe_hcall_entry(unsigned long opcode) +static void probe_hcall_entry(unsigned long opcode, unsigned long *args) { struct hcall_stats *h; @@ -114,7 +114,8 @@ static void probe_hcall_entry(unsigned long opcode) h->purr_start = mfspr(SPRN_PURR); } -static void probe_hcall_exit(unsigned long opcode, unsigned long retval) +static void probe_hcall_exit(unsigned long opcode, unsigned long retval, + unsigned long *retbuf) { struct hcall_stats *h; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4b7b6e8e32d..0707653612b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -683,13 +683,14 @@ void hcall_tracepoint_unregfunc(void) hcall_tracepoint_refcount--; } -void __trace_hcall_entry(unsigned long opcode) +void __trace_hcall_entry(unsigned long opcode, unsigned long *args) { - trace_hcall_entry(opcode); + trace_hcall_entry(opcode, args); } -void __trace_hcall_exit(long opcode, unsigned long retval) +void __trace_hcall_exit(long opcode, unsigned long retval, + unsigned long *retbuf) { - trace_hcall_exit(opcode, retval); + trace_hcall_exit(opcode, retval, retbuf); } #endif -- cgit v1.2.3-70-g09d2