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/platforms/pseries/hvCall.S | 101 +++++++++++++++------------ arch/powerpc/platforms/pseries/hvCall_inst.c | 37 ++++++++++ arch/powerpc/platforms/pseries/lpar.c | 32 +++++++++ 3 files changed, 127 insertions(+), 43 deletions(-) (limited to 'arch/powerpc/platforms/pseries') 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 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/platforms/pseries/hvCall.S | 31 +++++++++++++++++++--------- arch/powerpc/platforms/pseries/hvCall_inst.c | 5 +++-- arch/powerpc/platforms/pseries/lpar.c | 9 ++++---- 3 files changed, 29 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/platforms/pseries') 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