1
0
Fork 0
alistair23-linux/arch/powerpc/include/asm/perf_event_server.h

168 lines
6.4 KiB
C
Raw Normal View History

/*
* Performance event support - PowerPC classic/server specific definitions.
*
* 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/types.h>
#include <asm/hw_irq.h>
#include <linux/device.h>
#include <uapi/asm/perf_event.h>
/* Update perf_event_print_debug() if this changes */
#define MAX_HWEVENTS 8
#define MAX_EVENT_ALTERNATIVES 8
#define MAX_LIMITED_HWCOUNTERS 2
struct perf_event;
/*
* This struct provides the constants and functions needed to
* describe the PMU on a particular POWER-family CPU.
*/
struct power_pmu {
const char *name;
int n_counter;
int max_alternatives;
unsigned long add_fields;
unsigned long test_adder;
int (*compute_mmcr)(u64 events[], int n_ev,
unsigned int hwc[], unsigned long mmcr[],
struct perf_event *pevents[]);
int (*get_constraint)(u64 event_id, unsigned long *mskp,
unsigned long *valp);
int (*get_alternatives)(u64 event_id, unsigned int flags,
u64 alt[]);
void (*get_mem_data_src)(union perf_mem_data_src *dsrc,
u32 flags, struct pt_regs *regs);
void (*get_mem_weight)(u64 *weight);
powerpc/perf: Add constraints for power9 l2/l3 bus events In previous generation processors, both bus events and direct events of performance monitoring unit can be individually programmabled and monitored in PMCs. But in Power9, L2/L3 bus events are always available as a "bank" of 4 events. To obtain the counts for any of the l2/l3 bus events in a given bank, the user will have to program PMC4 with corresponding l2/l3 bus event for that bank. Patch enforce two contraints incase of L2/L3 bus events. 1)Any L2/L3 event when programmed is also expected to program corresponding PMC4 event from that group. 2)PMC4 event should always been programmed first due to group constraint logic limitation For ex. consider these L3 bus events PM_L3_PF_ON_CHIP_MEM (0x460A0), PM_L3_PF_MISS_L3 (0x160A0), PM_L3_CO_MEM (0x260A0), PM_L3_PF_ON_CHIP_CACHE (0x360A0), 1) This is an INVALID group for L3 Bus event monitoring, since it is missing PMC4 event. perf stat -e "{r160A0,r260A0,r360A0}" < > And this is a VALID group for L3 Bus events: perf stat -e "{r460A0,r160A0,r260A0,r360A0}" < > 2) This is an INVALID group for L3 Bus event monitoring, since it is missing PMC4 event. perf stat -e "{r260A0,r360A0}" < > And this is a VALID group for L3 Bus events: perf stat -e "{r460A0,r260A0,r360A0}" < > 3) This is an INVALID group for L3 Bus event monitoring, since it is missing PMC4 event. perf stat -e "{r360A0}" < > And this is a VALID group for L3 Bus events: perf stat -e "{r460A0,r360A0}" < > Patch here implements group constraint logic suggested by Michael Ellerman. Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-10 08:27:01 -06:00
unsigned long group_constraint_mask;
unsigned long group_constraint_val;
u64 (*bhrb_filter_map)(u64 branch_sample_type);
void (*config_bhrb)(u64 pmu_bhrb_filter);
void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
int (*limited_pmc_event)(u64 event_id);
u32 flags;
const struct attribute_group **attr_groups;
int n_generic;
int *generic_events;
int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
int n_blacklist_ev;
int *blacklist_ev;
/* BHRB entries in the PMU */
int bhrb_nr;
};
/*
* Values for power_pmu.flags
*/
#define PPMU_LIMITED_PMC5_6 0x00000001 /* PMC5/6 have limited function */
#define PPMU_ALT_SIPR 0x00000002 /* uses alternate posn for SIPR/HV */
#define PPMU_NO_SIPR 0x00000004 /* no SIPR/HV in MMCRA at all */
#define PPMU_NO_CONT_SAMPLING 0x00000008 /* no continuous sampling */
#define PPMU_SIAR_VALID 0x00000010 /* Processor has SIAR Valid bit */
#define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */
#define PPMU_HAS_SIER 0x00000040 /* Has SIER */
#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */
#define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */
/*
* Values for flags to get_alternatives()
*/
#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */
#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */
#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */
extern int register_power_pmu(struct power_pmu *);
struct pt_regs;
extern unsigned long perf_misc_flags(struct pt_regs *regs);
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long int read_bhrb(int n);
/*
* Only override the default definitions in include/linux/perf_event.h
* if we have hardware PMU support.
*/
#ifdef CONFIG_PPC_PERF_CTRS
#define perf_misc_flags(regs) perf_misc_flags(regs)
#endif
/*
* The power_pmu.get_constraint function returns a 32/64-bit value and
* a 32/64-bit mask that express the constraints between this event_id and
* other events.
*
* The value and mask are divided up into (non-overlapping) bitfields
* of three different types:
*
* Select field: this expresses the constraint that some set of bits
* in MMCR* needs to be set to a specific value for this event_id. For a
* select field, the mask contains 1s in every bit of the field, and
* the value contains a unique value for each possible setting of the
* MMCR* bits. The constraint checking code will ensure that two events
* that set the same field in their masks have the same value in their
* value dwords.
*
* Add field: this expresses the constraint that there can be at most
* N events in a particular class. A field of k bits can be used for
* N <= 2^(k-1) - 1. The mask has the most significant bit of the field
* set (and the other bits 0), and the value has only the least significant
* bit of the field set. In addition, the 'add_fields' and 'test_adder'
* in the struct power_pmu for this processor come into play. The
* add_fields value contains 1 in the LSB of the field, and the
* test_adder contains 2^(k-1) - 1 - N in the field.
*
* NAND field: this expresses the constraint that you may not have events
* in all of a set of classes. (For example, on PPC970, you can't select
* events from the FPU, ISU and IDU simultaneously, although any two are
* possible.) For N classes, the field is N+1 bits wide, and each class
* is assigned one bit from the least-significant N bits. The mask has
* only the most-significant bit set, and the value has only the bit
* for the event_id's class set. The test_adder has the least significant
* bit set in the field.
*
* If an event_id is not subject to the constraint expressed by a particular
* field, then it will have 0 in both the mask and value for that field.
*/
extern ssize_t power_events_sysfs_show(struct device *dev,
struct device_attribute *attr, char *page);
/*
* EVENT_VAR() is same as PMU_EVENT_VAR with a suffix.
*
* Having a suffix allows us to have aliases in sysfs - eg: the generic
* event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and
* 'PM_CYC' where the latter is the name by which the event is known in
* POWER CPU specification.
*
* Similarly, some hardware and cache events use the same event code. Eg.
* on POWER8, both "cache-references" and "L1-dcache-loads" events refer
* to the same event, PM_LD_REF_L1. The suffix, allows us to have two
* sysfs objects for the same event and thus two entries/aliases in sysfs.
*/
#define EVENT_VAR(_id, _suffix) event_attr_##_id##_suffix
#define EVENT_PTR(_id, _suffix) &EVENT_VAR(_id, _suffix).attr.attr
#define EVENT_ATTR(_name, _id, _suffix) \
PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), _id, \
power_events_sysfs_show)
#define GENERIC_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _g)
#define GENERIC_EVENT_PTR(_id) EVENT_PTR(_id, _g)
#define CACHE_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _c)
#define CACHE_EVENT_PTR(_id) EVENT_PTR(_id, _c)
perf tools: Make Power7 events available for perf Power7 supports over 530 different perf events but only a small subset of these can be specified by name, for the remaining events, we must specify them by their raw code: perf stat -e r2003c <application> This patch makes all the POWER7 events available in sysfs. So we can instead specify these as: perf stat -e 'cpu/PM_CMPLU_STALL_DFU/' <application> where PM_CMPLU_STALL_DFU is the r2003c in previous example. Before this patch is applied, the size of power7-pmu.o is: $ size arch/powerpc/perf/power7-pmu.o text data bss dec hex filename 3073 2720 0 5793 16a1 arch/powerpc/perf/power7-pmu.o and after the patch is applied, it is: $ size arch/powerpc/perf/power7-pmu.o text data bss dec hex filename 15950 31112 0 47062 b7d6 arch/powerpc/perf/power7-pmu.o For the run time overhead, I use two scripts, one is "event_name.sh", which contains 50 event names, it looks like: # ./perf record -e 'cpu/PM_CMPLU_STALL_DFU/' -e ..... /bin/sleep 1 the other one is named "event_code.sh" which use corresponding events raw code instead of events names, it looks like: # ./perf record -e r2003c -e ...... /bin/sleep 1 below is the result. Using events name: [root@localhost perf]# time ./event_name.sh [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (~102 samples) ] real 0m1.192s user 0m0.028s sys 0m0.106s Using events raw code: [root@localhost perf]# time ./event_code.sh [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.003 MB perf.data (~112 samples) ] real 0m1.198s user 0m0.028s sys 0m0.105s Signed-off-by: Runzhen Wang <runzhen@linux.vnet.ibm.com> Acked-by: Michael Ellerman <michael@ellerman.id.au> Cc: icycoder@gmail.com Cc: linuxppc-dev@lists.ozlabs.org Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Runzhen Wang <runzhew@clemson.edu> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1372407297-6996-3-git-send-email-runzhen@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-06-28 02:14:57 -06:00
#define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _p)
#define POWER_EVENT_PTR(_id) EVENT_PTR(_id, _p)