This patch set adds generic events, specific events, and format attribute
for the e6500 pmu to sysfs. This makes perf more convenient to use on the
e6500 by allowing the users to see all supported events and specify
events using meaningful names instead of raw event codes.
This patchset includes similar features in the following commits:
- 1c53a270724d
("perf/POWER7: Make generic event translations available in sysfs").
- 886c3b2d677f
("perf/POWER7: Make some POWER7 events available in sysfs")
- cfe0d8ba14a1
("perf tools: Make Power7 events available for perf")
- 3bf7b07ece6e
("perf/POWER7: Create a sysfs format entry for Power7 events").
This patchset also update tool/perf/design.txt to account for the changes
in commit a21ca2cac582 ("perf_counter: Separate out attr->type from
attr->config").
Attached patches:
1/3 perf/e6500: Make event translations available in sysfs
2/3 perf/e6500: Create a sysfs format entry for e6500 events
3/3 perf/doc: Update perf_event_attr struct
arch/powerpc/include/asm/perf_event_fsl_emb.h | 20 +-
arch/powerpc/perf/core-fsl-emb.c | 12 ++
arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
arch/powerpc/perf/e6500-pmu.c | 63 +++++-
tools/perf/design.txt | 159 ++++++++++----
5 files changed, 491 insertions(+), 52 deletions(-)
create mode 100644 arch/powerpc/perf/e6500-events-list.h
--
1.9.1
Make the perf events in e6500 available via sysfs.
$ ls /sys/devices/cpu/events/
branch-instructions
branch-misses
cache-misses
cpu-cycles
instructions
FSL_0_INST_CMPL
FSL_1_INST_CMPL
...
$ cat /sys/devices/cpu/events/cpu-cycles
event=0x01
Similar to the following commits:
- 1c53a270724d ("perf/POWER7: Make generic event translations
available in sysfs").
- 886c3b2d677f ("perf/POWER7: Make some POWER7 events available
in sysfs")
- cfe0d8ba14a1 ("perf tools: Make Power7 events available for perf")
Signed-off-by: Tom Huynh <[email protected]>
---
arch/powerpc/include/asm/perf_event_fsl_emb.h | 20 +-
arch/powerpc/perf/core-fsl-emb.c | 12 ++
arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
arch/powerpc/perf/e6500-pmu.c | 50 ++++-
4 files changed, 365 insertions(+), 6 deletions(-)
create mode 100644 arch/powerpc/perf/e6500-events-list.h
diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h
index a581654..d76124f 100644
--- a/arch/powerpc/include/asm/perf_event_fsl_emb.h
+++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h
@@ -11,6 +11,7 @@
*/
#include <linux/types.h>
+#include <linux/device.h>
#include <asm/hw_irq.h>
#define MAX_HWEVENTS 6
@@ -39,7 +40,7 @@ struct fsl_emb_pmu {
/* Returns event flags and PMLCb (FSL_EMB_EVENT_*) */
u64 (*xlate_event)(u64 event_id);
-
+ const struct attribute_group **attr_groups;
int n_generic;
int *generic_events;
int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
@@ -48,3 +49,20 @@ struct fsl_emb_pmu {
};
int register_fsl_emb_pmu(struct fsl_emb_pmu *);
+
+extern ssize_t fsl_emb_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page);
+
+#define EVENT_VAR(_id, _suffix) event_attr_##_id##_suffix
+#define EVENT_PTR(_id, _suffix) (&event_attr_##_id##_suffix.attr.attr)
+
+#define EVENT_ATTR(_name, _id, _suffix) \
+ PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id, \
+ fsl_emb_events_sysfs_show)
+
+#define GENERIC_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _g)
+#define GENERIC_EVENT_PTR(_id) EVENT_PTR(_id, _g)
+
+#define FSL_EMB_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _p)
+#define FSL_EMB_EVENT_PTR(_id) EVENT_PTR(_id, _p)
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 4acaea0..d4af2f3 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -581,6 +581,16 @@ static int fsl_emb_pmu_event_init(struct perf_event *event)
return err;
}
+ssize_t fsl_emb_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+ return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
static struct pmu fsl_emb_pmu = {
.pmu_enable = fsl_emb_pmu_enable,
.pmu_disable = fsl_emb_pmu_disable,
@@ -711,6 +721,8 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
pr_info("%s performance monitor hardware support registered\n",
pmu->name);
+ fsl_emb_pmu.attr_groups = ppmu->attr_groups;
+
perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW);
return 0;
diff --git a/arch/powerpc/perf/e6500-events-list.h b/arch/powerpc/perf/e6500-events-list.h
new file mode 100644
index 0000000..27be38a
--- /dev/null
+++ b/arch/powerpc/perf/e6500-events-list.h
@@ -0,0 +1,289 @@
+/*
+ * Performance counter support for e6500 family processors.
+ *
+ * Copyright 2015 Freescale Semiconductor, Inc.
+ *
+ * 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.
+ */
+EVENT(FSL_CYC, 1)
+EVENT(FSL_INST_CMPL, 2)
+EVENT(FSL_UOPS_CMPL, 3)
+EVENT(FSL_UOPS_DECODED, 5)
+EVENT(FSL_PM_EV_TRANS, 6)
+EVENT(FSL_PM_EV_CYC, 7)
+EVENT(FSL_BR_CMPL, 8)
+EVENT(FSL_BR_TKN, 67)
+EVENT(FSL_BLR_TKN, 68)
+EVENT(FSL_NUM_CQ_REDIR, 11)
+EVENT(FSL_LD_UOPS_CMPL, 9)
+EVENT(FSL_ST_UOPS_CMPL, 10)
+EVENT(FSL_LSU_UOPS_CMPL, 181)
+EVENT(FSL_GPR_LD_CMPL, 182)
+EVENT(FSL_GPR_ST_CMPL, 183)
+EVENT(FSL_CACHE_OPS_CMPL, 184)
+EVENT(FSL_MEM_BAR_CMPL, 185)
+EVENT(FSL_SFX_UOPS_CMPL, 186)
+EVENT(FSL_SFX_SINGLE_CYC_UOPS_CMPL, 187)
+EVENT(FSL_SFX_DOUBLE_CYC_UOPS_CMPL, 188)
+EVENT(FSL_CFX_INST_CMPL, 190)
+EVENT(FSL_SFX_CFX_INST_CMPL, 191)
+EVENT(FSL_FPU_INST_CMPL, 192)
+EVENT(FSL_FPR_LD_CMPL, 193)
+EVENT(FSL_FPR_ST_CMPL, 194)
+EVENT(FSL_FPR_LD_ST_CMPL, 195)
+EVENT(FSL_FPR_SINGLE_PRE_LD_ST_CMPL, 196)
+EVENT(FSL_FPR_DOUBLE_PRE_LD_ST_CMPL, 197)
+EVENT(FSL_ALTIV_INST_CMPL, 198)
+EVENT(FSL_ALTIV_VSFX_INST_CMPL, 199)
+EVENT(FSL_ALTIV_VCFX_INST_CMPL, 200)
+EVENT(FSL_ALTIV_VPU_INST_CMPL, 201)
+EVENT(FSL_ALTIV_VFPU_INST_CMPL, 202)
+EVENT(FSL_VR_LD_CMPL, 203)
+EVENT(FSL_VR_ST_CMPL, 204)
+EVENT(FSL_VSCR_SAT_SET, 205)
+EVENT(FSL_BR_FIN, 12)
+EVENT(FSL_TKN_BR_FIN, 13)
+EVENT(FSL_UNCON_BR_NO_BTB_FIN, 14)
+EVENT(FSL_BR_MPRED, 15)
+EVENT(FSL_BR_BTB_DIR_MPRED, 16)
+EVENT(FSL_TARGET_MPRED_BTB, 69)
+EVENT(FSL_TARGET_MPRED_LINK_STACK, 70)
+EVENT(FSL_BTB_ALLOC, 71)
+EVENT(FSL_BTB_HIT_PHANTOM_BR, 72)
+EVENT(FSL_BTB_HIT_PSEUDO_HIT, 17)
+/* Pipelne Stalls */
+EVENT(FSL_DECODE_STALL, 18)
+EVENT(FSL_SFX_CFX_STALL, 19)
+EVENT(FSL_LSU_STALL, 110)
+EVENT(FSL_BR_STALL, 20)
+EVENT(FSL_FPU_STALL, 111)
+EVENT(FSL_ALTIV_STALL, 112)
+EVENT(FSL_SFX0_SCHED_STALL, 21)
+EVENT(FSL_SFX1_SCHED_STALL, 22)
+EVENT(FSL_CFX_SCHED_STALL, 23)
+EVENT(FSL_LSU_SCHED_STALL, 24)
+EVENT(FSL_BU_SCHED_STALL, 25)
+EVENT(FSL_FPU_SCHED_STALL, 113)
+EVENT(FSL_VPERM_SCHED_STALL, 114)
+EVENT(FSL_VGEN_SCHED_STALL, 115)
+EVENT(FSL_VPU_INST_WAIT_OPD, 116)
+EVENT(FSL_VFPU_INST_WAIT_OPD, 117)
+EVENT(FSL_VSFX_INST_WAIT_OPD, 118)
+EVENT(FSL_VCFX_INST_WAIT_OPD, 119)
+EVENT(FSL_IB_EMPTY, 122)
+EVENT(FSL_IB_FULL, 123)
+EVENT(FSL_CB_EMPTY, 124)
+EVENT(FSL_CB_FULL, 125)
+EVENT(FSL_0_INST_CMPL, 127)
+EVENT(FSL_1_INST_CMPL, 128)
+EVENT(FSL_2_INST_CMPL, 129)
+/* Execution Unit Idle Events */
+EVENT(FSL_SFX0_IDL, 210)
+EVENT(FSL_SFX1_IDL, 211)
+EVENT(FSL_CFX_IDL, 212)
+EVENT(FSL_LSU_IDL, 213)
+EVENT(FSL_BU_IDL, 214)
+EVENT(FSL_FPU_IDL, 215)
+EVENT(FSL_VPU_IDL, 216)
+EVENT(FSL_VFPU_IDL, 217)
+EVENT(FSL_VSFX_IDL, 218)
+EVENT(FSL_VCFX_IDL, 219)
+/* Load/Store and Data Cache Events */
+EVENT(FSL_TOTL_TRANS, 26)
+EVENT(FSL_LD_TRANS, 27)
+EVENT(FSL_ST_TRANS, 28)
+EVENT(FSL_TOUCH_TRANS, 29)
+EVENT(FSL_CACHE_OPS_TRANS, 30)
+EVENT(FSL_CACHE_INHIB_TRANS, 31)
+EVENT(FSL_GUARD_LD_TRANS, 32)
+EVENT(FSL_WR_TH_ST_TRANS, 33)
+EVENT(FSL_MISALIGN_LD_ST_TRANS, 34)
+EVENT(FSL_L1D_MIS, 221)
+EVENT(FSL_L1D_LD_MIS, 222)
+EVENT(FSL_L1D_ST_MIS, 223)
+EVENT(FSL_L1D_RELD, 41)
+EVENT(FSL_LD_ALLOC_LMQ, 224)
+EVENT(FSL_LD_THRD_MIS_COLL, 225)
+EVENT(FSL_INTER_THRD_STAT_ARY_COLL, 226)
+EVENT(FSL_SGB_ALLOC, 227)
+EVENT(FSL_SGB_GATHER, 228)
+EVENT(FSL_SGB_OV, 229)
+EVENT(FSL_SGB_PROMO, 230)
+EVENT(FSL_SGB_IN_ORD_PROMO, 231)
+EVENT(FSL_SGB_OUT_ORD_PROMO, 232)
+EVENT(FSL_SGB_HI_PRI_PROMO, 233)
+EVENT(FSL_SGB_MISO_PROMO, 234)
+EVENT(FSL_SGB_WTMRK_PROMO, 235)
+EVENT(FSL_SGB_OV_PROMO, 236)
+EVENT(FSL_DLAQ_FUL_CYC, 237)
+EVENT(FSL_DLAQ_FUL_TIME, 238)
+EVENT(FSL_LRSAQ_FUL_CYC, 239)
+EVENT(FSL_LRSAQ_FUL_TIME, 240)
+EVENT(FSL_FWDAQ_FUL_CYC, 241)
+EVENT(FSL_FWDAQ_FUL_TIME, 242)
+EVENT(FSL_LD_MIS_LD_Q_FUL, 44)
+EVENT(FSL_LD_GUARD_MIS_TIME, 45)
+EVENT(FSL_TRANS_ST_FUL_ST_Q, 46)
+EVENT(FSL_LD_ON_ST_TIME, 47)
+EVENT(FSL_STQ_COLL_FWD, 243)
+EVENT(FSL_STQ_COLL_FWD_DATA_RDY, 244)
+EVENT(FSL_STQ_COLL_FW_TIME, 242)
+EVENT(FSL_STQ_COLL_FWD_TIME_DATA_NOT_RDY, 245)
+EVENT(FSL_STQ_COLL_NOT_FWD_TIME, 246)
+EVENT(FSL_STQ_COLL_FWD_CYC, 247)
+EVENT(FSL_STQ_COLL_FWD_CYC_DATA_RDY, 248)
+EVENT(FSL_STQ_COLL_FWD_CYC_DATA_NOT_RDY, 249)
+EVENT(FSL_STQ_COLL_NOT_FWD_CYC, 250)
+EVENT(FSL_FALSE_LD_ON_ST_COLL, 251)
+EVENT(FSL_DTLB_MIS_TIME, 48)
+EVENT(FSL_DTLB_BUSY_TIME, 49)
+EVENT(FSL_2ND_MISALIGN_1ST_MIS_TIME, 50)
+EVENT(FSL_LD_MIS_LD_Q_FULL, 52)
+EVENT(FSL_LD_GUARD_MIS_CYC, 53)
+EVENT(FSL_LS0_BUS_COLL, 252)
+EVENT(FSL_INTER_THRD_DB_WD_BANK_COLL, 253)
+EVENT(FSL_TRANS_ST_ST_Q_FULL_CYC, 54)
+EVENT(FSL_LD_ON_ST_CYC, 55)
+EVENT(FSL_DTLB_MIS_CYC, 56)
+EVENT(FSL_DTLB_BUSY_CYC, 57)
+EVENT(FSL_2ND_MISALIGN_1ST_MIS_CYC, 58)
+/* Fetch and Instruction Cache Events */
+EVENT(FSL_L1I_MIS, 254)
+EVENT(FSL_L1I_RELD, 60)
+EVENT(FSL_L1I_FET, 61)
+EVENT(FSL_FET_2X4_HIT, 35)
+EVENT(FSL_FET_HIT_ON_PREFET, 36)
+EVENT(FSL_FET_PREFET_GEN, 37)
+/* Instruction MMU, Data MMU and L2 MMU Events */
+EVENT(FSL_IMMU_TLB_4K_RELD, 62)
+EVENT(FSL_IMMU_VSP_RELD, 63)
+EVENT(FSL_IMMU_MIS, 256)
+EVENT(FSL_IMMU_TLB_4K_HIT, 257)
+EVENT(FSL_IMMU_VSP_HIT, 258)
+EVENT(FSL_IMMU_CYC_HW_TB_WALK, 259)
+EVENT(FSL_DMMU_TLB_4K_RELD, 64)
+EVENT(FSL_DMMU_VSP_RELD, 65)
+EVENT(FSL_DMMU_MIS, 260)
+EVENT(FSL_DMMU_TLB_4K_HIT, 261)
+EVENT(FSL_DMMU_VSO_HIT, 262)
+EVENT(FSL_DMMU_CYC_HW_TB_WALK, 263)
+EVENT(FSL_L2MMU_MIS, 264)
+EVENT(FSL_L2MMU_HIT_L2MMU_4K, 265)
+EVENT(FSL_L2MMU_HIT_L2MMU_VSP, 266)
+EVENT(FSL_L2MMU_ERR_MIS, 66)
+EVENT(FSL_L2MMU_INDIR_MIS, 267)
+EVENT(FSL_L2MMU_INDIR_VALID_MIS, 268)
+EVENT(FSL_LRAT_MIS, 269)
+/* Chaining Events */
+EVENT(FSL_PMC0_OV, 82)
+EVENT(FSL_PMC1_OV, 83)
+EVENT(FSL_PMC2_OV, 84)
+EVENT(FSL_PMC3_OV, 85)
+EVENT(FSL_PMC4_OV, 91)
+EVENT(FSL_PMC5_OV, 92)
+/* Interrupt Events */
+EVENT(FSL_INT_TKN, 86)
+EVENT(FSL_EXT_IN_INT_TKN, 87)
+EVENT(FSL_CRI_IN_INT_TKN, 88)
+EVENT(FSL_SYSCAL_TRAP_INT, 89)
+/* Misc Events */
+EVENT(FSL_TRANS_TBL_PMGC0_TBSEL, 90)
+/* L1 Stashing Events */
+EVENT(FSL_STASH_HIT_L1D, 97)
+EVENT(FSL_STASH_REQ_L1D, 99)
+/* Thread Events */
+EVENT(FSL_LSU_THRD_PRI_SWITCH_TIME, 100)
+EVENT(FSL_THRD_FPU_REQ_DENY_CYC, 101)
+EVENT(FSL_THRD_VPERM_REQ_DENY_CYC, 102)
+EVENT(FSL_THRD_VGEN_REQ_DENY_CYC, 103)
+EVENT(FSL_THRD_CFX_REQ_DENY_CYC, 104)
+EVENT(FSL_THRD_FET_REQ_DENY_CYC, 105)
+/* IAC and DAQ Events */
+EVENT(FSL_IAC1, 140)
+EVENT(FSL_IAC2, 141)
+EVENT(FSL_IAC3, 142)
+EVENT(FSL_IAC4, 143)
+EVENT(FSL_IAC5, 136)
+EVENT(FSL_IAC6, 137)
+EVENT(FSL_IAC7, 138)
+EVENT(FSL_IAC8, 139)
+EVENT(FSL_DAC1, 144)
+EVENT(FSL_DAC2, 145)
+/* DVT Events */
+EVENT(FSL_DVT0, 148)
+EVENT(FSL_DVT1, 149)
+EVENT(FSL_DVT2, 150)
+EVENT(FSL_DVT3, 151)
+EVENT(FSL_DVT4, 152)
+EVENT(FSL_DVT5, 153)
+EVENT(FSL_DVT6, 154)
+EVENT(FSL_DVT7, 155)
+EVENT(FSL_CMPL_CYC_STALL_NEXUS, 156)
+/* FPU Events */
+EVENT(FSL_FPU_FIN, 161)
+EVENT(FSL_FPU_DIV_CYC, 162)
+EVENT(FSL_FPU_DENORM_IN, 163)
+EVENT(FSL_FPU_DENORM_OUT, 164)
+EVENT(FSL_FPU_FPSCR_FULL_STALL, 165)
+EVENT(FSL_FPU_PIPE_SYNC_STALL, 166)
+EVENT(FSL_FPU_IN_DATA_STALL, 167)
+EVENT(FSL_INST_GEN_FLAG, 168)
+/* Power Management Events */
+EVENT(FSL_PW20, 172)
+/* Extended Load Store Events */
+EVENT(FSL_DECOR_LD, 176)
+EVENT(FSL_DECOR_ST, 177)
+EVENT(FSL_STCX_SUCCESS, 179)
+EVENT(FSL_STCX_NOT_SUCCESS, 180)
+EVENT(FSL_CYC_LMQ_LOSE_DLINK_ARB_SGB, 272)
+EVENT(FSL_CYC_SGB_LOSE_DLINK_ARB_LMQ, 273)
+EVENT(FSL_CYC_THRD_LOSE_DLINK_ARB_OTHER_THRD, 274)
+/* eLink Events */
+EVENT(FSL_DLINK_REQ, 443)
+EVENT(FSL_ILINK_REQ, 444)
+EVENT(FSL_RLINK_REQ, 445)
+EVENT(FSL_BLINK_REQ, 446)
+EVENT(FSL_CLINK_REQ, 447)
+/* Shared L2 Events */
+EVENT(FSL_L2_HIT, 456)
+EVENT(FSL_L2_MIS, 457)
+EVENT(FSL_L2_DEMAND_ACCESS, 458)
+EVENT(FSL_L2_ACCESS, 459)
+EVENT(FSL_L2_ST_ALLOC, 460)
+EVENT(FSL_L2I_ACCESS, 461)
+EVENT(FSL_L2D_ACCESS, 462)
+EVENT(FSL_L2I_MIS, 463)
+EVENT(FSL_L2D_MIS, 464)
+EVENT(FSL_L2_HIT_PER_THRD, 465)
+EVENT(FSL_L2_MIS_PER_THRD, 466)
+EVENT(FSL_L2_DEMAND_ACCESS_PER_THRD, 467)
+EVENT(FSL_L2_ST_ALLOC_PER_THRD, 468)
+EVENT(FSL_L2I_ACCESS_PER_THRD, 469)
+EVENT(FSL_L2D_ACCESS_PER_THRD, 470)
+EVENT(FSL_L2I_MIS_PER_THRD, 471)
+EVENT(FSL_L2D_MIS_PER_THRD, 472)
+EVENT(FSL_L2_RELD_CORENET, 473)
+EVENT(FSL_L2_STASH_REQ, 474)
+EVENT(FSL_L2_STASH_REQ_TO_SNOOP, 475)
+EVENT(FSL_L2_SNOOP_HIT, 476)
+EVENT(FSL_L2_SNOOP_MINT, 477)
+EVENT(FSL_L2_SNOOP_SINT, 478)
+EVENT(FSL_L2_SNOOP_PUSH, 479)
+EVENT(FSL_STALL_BIB_CYC, 480)
+EVENT(FSL_STALL_RLT_CYC, 482)
+EVENT(FSL_STALL_RLFQ_CYC, 484)
+EVENT(FSL_STALL_DTQ_CYC, 486)
+EVENT(FSL_STALL_COB_CYC, 488)
+EVENT(FSL_STALL_WDB_490, 490)
+EVENT(FSL_STALL_RLDB_CYC, 492)
+EVENT(FSL_STALL_SNPQ, 494)
+/* BIU Events */
+EVENT(FSL_BIU_MASTER_REQ, 506)
+EVENT(FSL_BIU_MASTER_GLOBAL_REQ, 507)
+EVENT(FSL_BIU_MASTER_DATA_REQ, 508)
+EVENT(FSL_BIU_MASTER_INST_REQ, 509)
+EVENT(FSL_STASH_REQ, 510)
+EVENT(FSL_SNOOP_REQ, 511)
diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c
index 3d877aa..abaa6d7 100644
--- a/arch/powerpc/perf/e6500-pmu.c
+++ b/arch/powerpc/perf/e6500-pmu.c
@@ -17,16 +17,23 @@
#include <asm/reg.h>
#include <asm/cputable.h>
+#define EVENT(_name, _code) \
+ PME_##_name = _code,
+enum {
+#include "e6500-events-list.h"
+};
+#undef EVENT
+
/*
* Map of generic hardware event types to hardware events
* Zero if unsupported
*/
static int e6500_generic_events[] = {
- [PERF_COUNT_HW_CPU_CYCLES] = 1,
- [PERF_COUNT_HW_INSTRUCTIONS] = 2,
- [PERF_COUNT_HW_CACHE_MISSES] = 221,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
- [PERF_COUNT_HW_BRANCH_MISSES] = 15,
+ [PERF_COUNT_HW_CPU_CYCLES] = PME_FSL_CYC,
+ [PERF_COUNT_HW_INSTRUCTIONS] = PME_FSL_INST_CMPL,
+ [PERF_COUNT_HW_CACHE_MISSES] = PME_FSL_L1D_MIS,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PME_FSL_BR_FIN,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PME_FSL_BR_MPRED,
};
#define C(x) PERF_COUNT_HW_CACHE_##x
@@ -99,11 +106,44 @@ static u64 e6500_xlate_event(u64 event_id)
return FSL_EMB_EVENT_VALID;
}
+GENERIC_EVENT_ATTR(cycles, FSL_CYC);
+GENERIC_EVENT_ATTR(instructions, FSL_INST_CMPL);
+GENERIC_EVENT_ATTR(cache-misses, FSL_L1D_MIS);
+GENERIC_EVENT_ATTR(branch-instructions, FSL_BR_FIN);
+GENERIC_EVENT_ATTR(branch-misses, FSL_BR_MPRED);
+#define EVENT(_name, _code) FSL_EMB_EVENT_ATTR(_name, _name);
+#include "e6500-events-list.h"
+#undef EVENT
+
+#define EVENT(_name, _code) FSL_EMB_EVENT_PTR(_name),
+
+static struct attribute *e6500_events_attr[] = {
+ GENERIC_EVENT_PTR(FSL_CYC),
+ GENERIC_EVENT_PTR(FSL_INST_CMPL),
+ GENERIC_EVENT_PTR(FSL_L1D_MIS),
+ GENERIC_EVENT_PTR(FSL_BR_FIN),
+ GENERIC_EVENT_PTR(FSL_BR_MPRED),
+ #include "e6500-events-list.h"
+ #undef EVENT
+ NULL,
+};
+
+static struct attribute_group e6500_pmu_events_group = {
+ .name = "events",
+ .attrs = e6500_events_attr,
+};
+
+static const struct attribute_group *e6500_pmu_attr_groups[] = {
+ &e6500_pmu_events_group,
+ NULL,
+};
+
static struct fsl_emb_pmu e6500_pmu = {
.name = "e6500 family",
.n_counter = 6,
.n_restricted = 0,
.xlate_event = e6500_xlate_event,
+ .attr_groups = e6500_pmu_attr_groups,
.n_generic = ARRAY_SIZE(e6500_generic_events),
.generic_events = e6500_generic_events,
.cache_events = &e6500_cache_events,
--
1.9.1
Create a sysfs entry, '/sys/bus/event_source/devices/cpu/format/event'
which describes the format of the e6500 PMU events. e6500 has <= 512
events, so use the 9 lsb to specify the raw event code.
$ cat /sys/devices/cpu/format/event
config:0-8
Similar to commit 3bf7b07ece6e ("perf/POWER7: Create a sysfs format
entry for Power7 events").
Signed-off-by: Kim Phillips <[email protected]>
Signed-off-by: Tom Huynh <[email protected]>
---
arch/powerpc/perf/e6500-pmu.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c
index abaa6d7..4bbdbb0 100644
--- a/arch/powerpc/perf/e6500-pmu.c
+++ b/arch/powerpc/perf/e6500-pmu.c
@@ -133,7 +133,20 @@ static struct attribute_group e6500_pmu_events_group = {
.attrs = e6500_events_attr,
};
+PMU_FORMAT_ATTR(event, "config:0-8");
+
+static struct attribute *e6500_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+struct attribute_group e6500_pmu_format_group = {
+ .name = "format",
+ .attrs = e6500_pmu_format_attr,
+};
+
static const struct attribute_group *e6500_pmu_attr_groups[] = {
+ &e6500_pmu_format_group,
&e6500_pmu_events_group,
NULL,
};
--
1.9.1
Update the fields in perf_event_attr as currently seen in
include/uapi/linux/perf_event.h
Remove outdated comments on the config field
The doc has not account for commit a21ca2cac582 ("perf_counter:
Separate out attr->type from attr->config").
Signed-off-by: Tom Huynh <[email protected]>
---
tools/perf/design.txt | 159 +++++++++++++++++++++++++++++++++++---------------
1 file changed, 113 insertions(+), 46 deletions(-)
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index a28dca2..96bd261 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -32,60 +32,127 @@ can be used to set the blocking mode, etc.
Multiple counters can be kept open at a time, and the counters
can be poll()ed.
-When creating a new counter fd, 'perf_event_attr' is:
+When creating a new counter fd, 'perf_event_attr' is defined in
+include/linux/uapi/perf_event.h as:
struct perf_event_attr {
- /*
- * The MSB of the config word signifies if the rest contains cpu
- * specific (raw) counter configuration data, if unset, the next
- * 7 bits are an event type and the rest of the bits are the event
- * identifier.
- */
- __u64 config;
-
- __u64 irq_period;
- __u32 record_type;
- __u32 read_format;
-
- __u64 disabled : 1, /* off by default */
- inherit : 1, /* children inherit it */
- pinned : 1, /* must always be on PMU */
- exclusive : 1, /* only group on PMU */
- exclude_user : 1, /* don't count user */
- exclude_kernel : 1, /* ditto kernel */
- exclude_hv : 1, /* ditto hypervisor */
- exclude_idle : 1, /* don't count when idle */
- mmap : 1, /* include mmap data */
- munmap : 1, /* include munmap data */
- comm : 1, /* include comm data */
-
- __reserved_1 : 52;
-
- __u32 extra_config_len;
- __u32 wakeup_events; /* wakeup every n events */
-
- __u64 __reserved_2;
- __u64 __reserved_3;
-};
-The 'config' field specifies what the counter should count. It
-is divided into 3 bit-fields:
+ /*
+ * Major type: hardware/software/tracepoint/etc.
+ */
+ __u32 type;
+
+ /*
+ * Size of the attr structure, for fwd/bwd compat.
+ */
+ __u32 size;
+
+ /*
+ * Type specific configuration information.
+ */
+ __u64 config;
+
+ union {
+ __u64 sample_period;
+ __u64 sample_freq;
+ };
+
+ __u64 sample_type;
+ __u64 read_format;
+
+ __u64 disabled : 1, /* off by default */
+ inherit : 1, /* children inherit it */
+ pinned : 1, /* must always be on PMU */
+ exclusive : 1, /* only group on PMU */
+ exclude_user : 1, /* don't count user */
+ exclude_kernel : 1, /* ditto kernel */
+ exclude_hv : 1, /* ditto hypervisor */
+ exclude_idle : 1, /* don't count when idle */
+ mmap : 1, /* include mmap data */
+ comm : 1, /* include comm data */
+ freq : 1, /* use freq, not period */
+ inherit_stat : 1, /* per task counts */
+ enable_on_exec : 1, /* next exec enables */
+ task : 1, /* trace fork/exit */
+ watermark : 1, /* wakeup_watermark */
+ /*
+ * precise_ip:
+ *
+ * 0 - SAMPLE_IP can have arbitrary skid
+ * 1 - SAMPLE_IP must have constant skid
+ * 2 - SAMPLE_IP requested to have 0 skid
+ * 3 - SAMPLE_IP must have 0 skid
+ *
+ * See also PERF_RECORD_MISC_EXACT_IP
+ */
+ precise_ip : 2, /* skid constraint */
+ mmap_data : 1, /* non-exec mmap data */
+ sample_id_all : 1, /* sample_type all events */
+
+ exclude_host : 1, /* don't count in host */
+ exclude_guest : 1, /* don't count in guest */
+
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+ mmap2 : 1, /* include mmap with inode data */
+ comm_exec : 1, /* flag comm events that are due to an exec */
+ __reserved_1 : 39;
+
+ union {
+ __u32 wakeup_events; /* wakeup every n events */
+ __u32 wakeup_watermark; /* bytes before wakeup */
+ };
+
+ __u32 bp_type;
+ union {
+ __u64 bp_addr;
+ __u64 config1; /* extension of config */
+ };
+ union {
+ __u64 bp_len;
+ __u64 config2; /* extension of config1 */
+ };
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
-raw_type: 1 bit (most significant bit) 0x8000_0000_0000_0000
-type: 7 bits (next most significant) 0x7f00_0000_0000_0000
-event_id: 56 bits (least significant) 0x00ff_ffff_ffff_ffff
+ /* Align to u64. */
+ __u32 __reserved_2;
+ /*
+ * Defines set of regs to dump for each sample
+ * state captured on:
+ * - precise = 0: PMU interrupt
+ * - precise > 0: sampled instruction
+ *
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_intr;
+};
-If 'raw_type' is 1, then the counter will count a hardware event
-specified by the remaining 63 bits of event_config. The encoding is
-machine-specific.
+The 'config' field specifies what the counter should count. The counter will
+count a hardware event specified by the 64 bits of event_config. The encoding
+is machine-specific.
-If 'raw_type' is 0, then the 'type' field says what kind of counter
-this is, with the following encoding:
+The 'type' field says what kind of counter this is, with the following encoding:
enum perf_type_id {
- PERF_TYPE_HARDWARE = 0,
- PERF_TYPE_SOFTWARE = 1,
- PERF_TYPE_TRACEPOINT = 2,
+ PERF_TYPE_HARDWARE = 0,
+ PERF_TYPE_SOFTWARE = 1,
+ PERF_TYPE_TRACEPOINT = 2,
+ PERF_TYPE_HW_CACHE = 3,
+ PERF_TYPE_RAW = 4,
+ PERF_TYPE_BREAKPOINT = 5,
+
+ PERF_TYPE_MAX, /* non-ABI */
};
A counter of PERF_TYPE_HARDWARE will count the hardware event
--
1.9.1
On Fri, Feb 06, 2015 at 04:43:54PM -0600, Tom Huynh wrote:
> arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
That's a lot of events to stuff in the kernel, would a userspace list
not be more convenient?
ISTR there being various discussions on providing support for that in
tools/perf, Jiri?
* Peter Zijlstra <[email protected]> wrote:
> On Fri, Feb 06, 2015 at 04:43:54PM -0600, Tom Huynh wrote:
> > arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
>
> That's a lot of events to stuff in the kernel, would a
> userspace list not be more convenient?
>
> ISTR there being various discussions on providing support
> for that in tools/perf, Jiri?
As long as it's in a single well organized place in tools/,
I'd be fine with that solution as well.
What doesn't work very well is disjunct, disorganized,
inconsistent event descriptions all across the tooling and
platform landscape - putting static tables into sysfs is a
marked improvement over that, despite its memory usage.
Thanks,
Ingo
On Mon, Feb 09, 2015 at 11:07:38AM +0100, Ingo Molnar wrote:
>
> * Peter Zijlstra <[email protected]> wrote:
>
> > On Fri, Feb 06, 2015 at 04:43:54PM -0600, Tom Huynh wrote:
> > > arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
> >
> > That's a lot of events to stuff in the kernel, would a
> > userspace list not be more convenient?
> >
> > ISTR there being various discussions on providing support
> > for that in tools/perf, Jiri?
>
> As long as it's in a single well organized place in tools/,
> I'd be fine with that solution as well.
>
> What doesn't work very well is disjunct, disorganized,
> inconsistent event descriptions all across the tooling and
> platform landscape - putting static tables into sysfs is a
> marked improvement over that, despite its memory usage.
the last version is in here:
http://marc.info/?l=linux-kernel&m=140676269017820&w=2
AFAIK Andi is setting up the download area as discussed
in the thread and should repost at some point
jirka
* Jiri Olsa <[email protected]> wrote:
> On Mon, Feb 09, 2015 at 11:07:38AM +0100, Ingo Molnar wrote:
> >
> > * Peter Zijlstra <[email protected]> wrote:
> >
> > > On Fri, Feb 06, 2015 at 04:43:54PM -0600, Tom Huynh wrote:
> > > > arch/powerpc/perf/e6500-events-list.h | 289 ++++++++++++++++++++++++++
> > >
> > > That's a lot of events to stuff in the kernel, would a
> > > userspace list not be more convenient?
> > >
> > > ISTR there being various discussions on providing support
> > > for that in tools/perf, Jiri?
> >
> > As long as it's in a single well organized place in tools/,
> > I'd be fine with that solution as well.
> >
> > What doesn't work very well is disjunct, disorganized,
> > inconsistent event descriptions all across the tooling and
> > platform landscape - putting static tables into sysfs is a
> > marked improvement over that, despite its memory usage.
>
> the last version is in here:
> http://marc.info/?l=linux-kernel&m=140676269017820&w=2
>
> AFAIK Andi is setting up the download area as discussed
> in the thread and should repost at some point
I'll NAK any external 'download area' (and I told that Andi
before): tools/perf/event-tables/ or so is a good enough
'download area' with fast enough update cycles.
If any 'update' of event descriptions is needed it can
happen through the distro package mechanism, or via a
simple 'git pull' if it's compiled directly.
Lets not overengineer this with any dependence on an
external site and with a separate update mechanism - lets
just get the tables into tools/ and see it from there...
Thanks,
Ingo
> I'll NAK any external 'download area' (and I told that Andi
> before): tools/perf/event-tables/ or so is a good enough
> 'download area' with fast enough update cycles.
The proposal was to put it on kernel.org, similar to how
external firmware blobs are distributed. CPU event lists
are data sheets, so are like firmware. They do not
follow the normal kernel code licenses. They are not
source code. They cannot be reviewed in the normal way.
> If any 'update' of event descriptions is needed it can
> happen through the distro package mechanism, or via a
> simple 'git pull' if it's compiled directly.
>
> Lets not overengineer this with any dependence on an
> external site and with a separate update mechanism - lets
> just get the tables into tools/ and see it from there...
That experiment has been already done for oprofile,
didn't work very well.
-Andi
--
[email protected] -- Speaking for myself only.
On Mon, 2015-02-09 at 21:40 +0100, Andi Kleen wrote:
> > I'll NAK any external 'download area' (and I told that Andi
> > before): tools/perf/event-tables/ or so is a good enough
> > 'download area' with fast enough update cycles.
>
> The proposal was to put it on kernel.org, similar to how
> external firmware blobs are distributed. CPU event lists
> are data sheets, so are like firmware. They do not
> follow the normal kernel code licenses. They are not
> source code. They cannot be reviewed in the normal way.
How is it different from describing registers and bits in driver header
files? What does it mean to talk about a license on information, rather
than the expression of information?
-Scott
On Mon, Feb 09, 2015 at 09:40:19PM +0100, Andi Kleen wrote:
> > I'll NAK any external 'download area' (and I told that Andi
> > before): tools/perf/event-tables/ or so is a good enough
> > 'download area' with fast enough update cycles.
>
> The proposal was to put it on kernel.org, similar to how
> external firmware blobs are distributed. CPU event lists
> are data sheets, so are like firmware. They do not
> follow the normal kernel code licenses. They are not
> source code. They cannot be reviewed in the normal way.
Could you provide more details about the license and review
concern? How are the event list files different from hardware-
specific information (e.g. reg mapping) in header files?
> > If any 'update' of event descriptions is needed it can
> > happen through the distro package mechanism, or via a
> > simple 'git pull' if it's compiled directly.
> >
> > Lets not overengineer this with any dependence on an
> > external site and with a separate update mechanism - lets
> > just get the tables into tools/ and see it from there...
>
> That experiment has been already done for oprofile,
> didn't work very well.
Please excuse my ignorance, could you say exactly what didn't
work well for oprofile?
Ingo's suggestion seems good to me because these event files
will be transparent to the users, and it's just more
convenient not having to go to a website to look for
the event file that matches the machine to download.
The distro package or the perf make mechanism can put these
files into the appropriate directory. The users who are not
perf developers won't need to know about these files.
- Tom
* Scott Wood <[email protected]> wrote:
> On Mon, 2015-02-09 at 21:40 +0100, Andi Kleen wrote:
> > > I'll NAK any external 'download area' (and I told that Andi
> > > before): tools/perf/event-tables/ or so is a good enough
> > > 'download area' with fast enough update cycles.
> >
> > The proposal was to put it on kernel.org, similar to how
> > external firmware blobs are distributed. [...]
Fortunately perf is not an external firmware blob ...
> > [...] CPU event lists are data sheets, so are like
> > firmware. [...]
What an absolute, idiotic, nonsense argument!
CPU event lists are human readable descriptions for events.
If they aren't then they have no place in tooling.
Treating them like firmware is as backwards as it gets.
> > [...] They do not follow the normal kernel code
> > licenses. They are not source code. They cannot be
> > reviewed in the normal way.
>
> How is it different from describing registers and bits in
> driver header files? What does it mean to talk about a
> license on information, rather than the expression of
> information?
Andi is making idiotic arguments, instead of implementing
the technically sane solution.
Thanks,
Ingo
Well I'm tired of discussing this. I don't think what you
proposed makes sense, putting 3.4MB[1] of changing blob into perf.
I'll resubmit the JSON parser without the downloader. Then users
have the option to get their own events and use that.
If you don't like that, standard perf just has to stay with limited
events and rXXXX as before, with users having to use external
tools or libraries for names for more events[2][3].
-Andi
[1] Current size of https://download.01.org/perfmon/
[2] ocperf in https://github.com/andikleen/pmu-tools
[3] http://perfmon2.sourceforge.net/
--
[email protected] -- Speaking for myself only.