diff options
Diffstat (limited to 'arch')
-rw-r--r-- | arch/powerpc/include/asm/perf_event_server.h | 4 | ||||
-rw-r--r-- | arch/powerpc/perf/power7-events-list.h | 548 | ||||
-rw-r--r-- | arch/powerpc/perf/power7-pmu.c | 148 | ||||
-rw-r--r-- | arch/x86/Kconfig | 5 | ||||
-rw-r--r-- | arch/x86/include/asm/alternative.h | 14 | ||||
-rw-r--r-- | arch/x86/include/asm/tsc.h | 1 | ||||
-rw-r--r-- | arch/x86/kernel/alternative.c | 155 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.h | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_amd.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 180 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_ds.c | 32 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.c | 254 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.h | 10 | ||||
-rw-r--r-- | arch/x86/kernel/jump_label.c | 16 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/common.h | 5 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/core.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/opt.c | 110 | ||||
-rw-r--r-- | arch/x86/kernel/traps.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/tsc.c | 6 |
20 files changed, 1111 insertions, 394 deletions
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 8b2492644754..3fd2f1b6f906 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -138,11 +138,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev, #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), PME_PM_##_id, \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_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 POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(PM_##_name, _id, _p) +#define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _p) #define POWER_EVENT_PTR(_id) EVENT_PTR(_id, _p) diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h new file mode 100644 index 000000000000..687790a2c0b8 --- /dev/null +++ b/arch/powerpc/perf/power7-events-list.h @@ -0,0 +1,548 @@ +/* + * Performance counter support for POWER7 processors. + * + * Copyright 2013 Runzhen Wang, 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. + */ + +EVENT(PM_IC_DEMAND_L2_BR_ALL, 0x04898) +EVENT(PM_GCT_UTIL_7_TO_10_SLOTS, 0x020a0) +EVENT(PM_PMC2_SAVED, 0x10022) +EVENT(PM_CMPLU_STALL_DFU, 0x2003c) +EVENT(PM_VSU0_16FLOP, 0x0a0a4) +EVENT(PM_MRK_LSU_DERAT_MISS, 0x3d05a) +EVENT(PM_MRK_ST_CMPL, 0x10034) +EVENT(PM_NEST_PAIR3_ADD, 0x40881) +EVENT(PM_L2_ST_DISP, 0x46180) +EVENT(PM_L2_CASTOUT_MOD, 0x16180) +EVENT(PM_ISEG, 0x020a4) +EVENT(PM_MRK_INST_TIMEO, 0x40034) +EVENT(PM_L2_RCST_DISP_FAIL_ADDR, 0x36282) +EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM, 0x0d0b6) +EVENT(PM_IERAT_WR_64K, 0x040be) +EVENT(PM_MRK_DTLB_MISS_16M, 0x4d05e) +EVENT(PM_IERAT_MISS, 0x100f6) +EVENT(PM_MRK_PTEG_FROM_LMEM, 0x4d052) +EVENT(PM_FLOP, 0x100f4) +EVENT(PM_THRD_PRIO_4_5_CYC, 0x040b4) +EVENT(PM_BR_PRED_TA, 0x040aa) +EVENT(PM_CMPLU_STALL_FXU, 0x20014) +EVENT(PM_EXT_INT, 0x200f8) +EVENT(PM_VSU_FSQRT_FDIV, 0x0a888) +EVENT(PM_MRK_LD_MISS_EXPOSED_CYC, 0x1003e) +EVENT(PM_LSU1_LDF, 0x0c086) +EVENT(PM_IC_WRITE_ALL, 0x0488c) +EVENT(PM_LSU0_SRQ_STFWD, 0x0c0a0) +EVENT(PM_PTEG_FROM_RL2L3_MOD, 0x1c052) +EVENT(PM_MRK_DATA_FROM_L31_SHR, 0x1d04e) +EVENT(PM_DATA_FROM_L21_MOD, 0x3c046) +EVENT(PM_VSU1_SCAL_DOUBLE_ISSUED, 0x0b08a) +EVENT(PM_VSU0_8FLOP, 0x0a0a0) +EVENT(PM_POWER_EVENT1, 0x1006e) +EVENT(PM_DISP_CLB_HELD_BAL, 0x02092) +EVENT(PM_VSU1_2FLOP, 0x0a09a) +EVENT(PM_LWSYNC_HELD, 0x0209a) +EVENT(PM_PTEG_FROM_DL2L3_SHR, 0x3c054) +EVENT(PM_INST_FROM_L21_MOD, 0x34046) +EVENT(PM_IERAT_XLATE_WR_16MPLUS, 0x040bc) +EVENT(PM_IC_REQ_ALL, 0x04888) +EVENT(PM_DSLB_MISS, 0x0d090) +EVENT(PM_L3_MISS, 0x1f082) +EVENT(PM_LSU0_L1_PREF, 0x0d0b8) +EVENT(PM_VSU_SCALAR_SINGLE_ISSUED, 0x0b884) +EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE, 0x0d0be) +EVENT(PM_L2_INST, 0x36080) +EVENT(PM_VSU0_FRSP, 0x0a0b4) +EVENT(PM_FLUSH_DISP, 0x02082) +EVENT(PM_PTEG_FROM_L2MISS, 0x4c058) +EVENT(PM_VSU1_DQ_ISSUED, 0x0b09a) +EVENT(PM_CMPLU_STALL_LSU, 0x20012) +EVENT(PM_MRK_DATA_FROM_DMEM, 0x1d04a) +EVENT(PM_LSU_FLUSH_ULD, 0x0c8b0) +EVENT(PM_PTEG_FROM_LMEM, 0x4c052) +EVENT(PM_MRK_DERAT_MISS_16M, 0x3d05c) +EVENT(PM_THRD_ALL_RUN_CYC, 0x2000c) +EVENT(PM_MEM0_PREFETCH_DISP, 0x20083) +EVENT(PM_MRK_STALL_CMPLU_CYC_COUNT, 0x3003f) +EVENT(PM_DATA_FROM_DL2L3_MOD, 0x3c04c) +EVENT(PM_VSU_FRSP, 0x0a8b4) +EVENT(PM_MRK_DATA_FROM_L21_MOD, 0x3d046) +EVENT(PM_PMC1_OVERFLOW, 0x20010) +EVENT(PM_VSU0_SINGLE, 0x0a0a8) +EVENT(PM_MRK_PTEG_FROM_L3MISS, 0x2d058) +EVENT(PM_MRK_PTEG_FROM_L31_SHR, 0x2d056) +EVENT(PM_VSU0_VECTOR_SP_ISSUED, 0x0b090) +EVENT(PM_VSU1_FEST, 0x0a0ba) +EVENT(PM_MRK_INST_DISP, 0x20030) +EVENT(PM_VSU0_COMPLEX_ISSUED, 0x0b096) +EVENT(PM_LSU1_FLUSH_UST, 0x0c0b6) +EVENT(PM_INST_CMPL, 0x00002) +EVENT(PM_FXU_IDLE, 0x1000e) +EVENT(PM_LSU0_FLUSH_ULD, 0x0c0b0) +EVENT(PM_MRK_DATA_FROM_DL2L3_MOD, 0x3d04c) +EVENT(PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC, 0x3001c) +EVENT(PM_LSU1_REJECT_LMQ_FULL, 0x0c0a6) +EVENT(PM_INST_PTEG_FROM_L21_MOD, 0x3e056) +EVENT(PM_INST_FROM_RL2L3_MOD, 0x14042) +EVENT(PM_SHL_CREATED, 0x05082) +EVENT(PM_L2_ST_HIT, 0x46182) +EVENT(PM_DATA_FROM_DMEM, 0x1c04a) +EVENT(PM_L3_LD_MISS, 0x2f082) +EVENT(PM_FXU1_BUSY_FXU0_IDLE, 0x4000e) +EVENT(PM_DISP_CLB_HELD_RES, 0x02094) +EVENT(PM_L2_SN_SX_I_DONE, 0x36382) +EVENT(PM_GRP_CMPL, 0x30004) +EVENT(PM_STCX_CMPL, 0x0c098) +EVENT(PM_VSU0_2FLOP, 0x0a098) +EVENT(PM_L3_PREF_MISS, 0x3f082) +EVENT(PM_LSU_SRQ_SYNC_CYC, 0x0d096) +EVENT(PM_LSU_REJECT_ERAT_MISS, 0x20064) +EVENT(PM_L1_ICACHE_MISS, 0x200fc) +EVENT(PM_LSU1_FLUSH_SRQ, 0x0c0be) +EVENT(PM_LD_REF_L1_LSU0, 0x0c080) +EVENT(PM_VSU0_FEST, 0x0a0b8) +EVENT(PM_VSU_VECTOR_SINGLE_ISSUED, 0x0b890) +EVENT(PM_FREQ_UP, 0x4000c) +EVENT(PM_DATA_FROM_LMEM, 0x3c04a) +EVENT(PM_LSU1_LDX, 0x0c08a) +EVENT(PM_PMC3_OVERFLOW, 0x40010) +EVENT(PM_MRK_BR_MPRED, 0x30036) +EVENT(PM_SHL_MATCH, 0x05086) +EVENT(PM_MRK_BR_TAKEN, 0x10036) +EVENT(PM_CMPLU_STALL_BRU, 0x4004e) +EVENT(PM_ISLB_MISS, 0x0d092) +EVENT(PM_CYC, 0x0001e) +EVENT(PM_DISP_HELD_THERMAL, 0x30006) +EVENT(PM_INST_PTEG_FROM_RL2L3_SHR, 0x2e054) +EVENT(PM_LSU1_SRQ_STFWD, 0x0c0a2) +EVENT(PM_GCT_NOSLOT_BR_MPRED, 0x4001a) +EVENT(PM_1PLUS_PPC_CMPL, 0x100f2) +EVENT(PM_PTEG_FROM_DMEM, 0x2c052) +EVENT(PM_VSU_2FLOP, 0x0a898) +EVENT(PM_GCT_FULL_CYC, 0x04086) +EVENT(PM_MRK_DATA_FROM_L3_CYC, 0x40020) +EVENT(PM_LSU_SRQ_S0_ALLOC, 0x0d09d) +EVENT(PM_MRK_DERAT_MISS_4K, 0x1d05c) +EVENT(PM_BR_MPRED_TA, 0x040ae) +EVENT(PM_INST_PTEG_FROM_L2MISS, 0x4e058) +EVENT(PM_DPU_HELD_POWER, 0x20006) +EVENT(PM_RUN_INST_CMPL, 0x400fa) +EVENT(PM_MRK_VSU_FIN, 0x30032) +EVENT(PM_LSU_SRQ_S0_VALID, 0x0d09c) +EVENT(PM_GCT_EMPTY_CYC, 0x20008) +EVENT(PM_IOPS_DISP, 0x30014) +EVENT(PM_RUN_SPURR, 0x10008) +EVENT(PM_PTEG_FROM_L21_MOD, 0x3c056) +EVENT(PM_VSU0_1FLOP, 0x0a080) +EVENT(PM_SNOOP_TLBIE, 0x0d0b2) +EVENT(PM_DATA_FROM_L3MISS, 0x2c048) +EVENT(PM_VSU_SINGLE, 0x0a8a8) +EVENT(PM_DTLB_MISS_16G, 0x1c05e) +EVENT(PM_CMPLU_STALL_VECTOR, 0x2001c) +EVENT(PM_FLUSH, 0x400f8) +EVENT(PM_L2_LD_HIT, 0x36182) +EVENT(PM_NEST_PAIR2_AND, 0x30883) +EVENT(PM_VSU1_1FLOP, 0x0a082) +EVENT(PM_IC_PREF_REQ, 0x0408a) +EVENT(PM_L3_LD_HIT, 0x2f080) +EVENT(PM_GCT_NOSLOT_IC_MISS, 0x2001a) +EVENT(PM_DISP_HELD, 0x10006) +EVENT(PM_L2_LD, 0x16080) +EVENT(PM_LSU_FLUSH_SRQ, 0x0c8bc) +EVENT(PM_BC_PLUS_8_CONV, 0x040b8) +EVENT(PM_MRK_DATA_FROM_L31_MOD_CYC, 0x40026) +EVENT(PM_CMPLU_STALL_VECTOR_LONG, 0x4004a) +EVENT(PM_L2_RCST_BUSY_RC_FULL, 0x26282) +EVENT(PM_TB_BIT_TRANS, 0x300f8) +EVENT(PM_THERMAL_MAX, 0x40006) +EVENT(PM_LSU1_FLUSH_ULD, 0x0c0b2) +EVENT(PM_LSU1_REJECT_LHS, 0x0c0ae) +EVENT(PM_LSU_LRQ_S0_ALLOC, 0x0d09f) +EVENT(PM_L3_CO_L31, 0x4f080) +EVENT(PM_POWER_EVENT4, 0x4006e) +EVENT(PM_DATA_FROM_L31_SHR, 0x1c04e) +EVENT(PM_BR_UNCOND, 0x0409e) +EVENT(PM_LSU1_DC_PREF_STREAM_ALLOC, 0x0d0aa) +EVENT(PM_PMC4_REWIND, 0x10020) +EVENT(PM_L2_RCLD_DISP, 0x16280) +EVENT(PM_THRD_PRIO_2_3_CYC, 0x040b2) +EVENT(PM_MRK_PTEG_FROM_L2MISS, 0x4d058) +EVENT(PM_IC_DEMAND_L2_BHT_REDIRECT, 0x04098) +EVENT(PM_LSU_DERAT_MISS, 0x200f6) +EVENT(PM_IC_PREF_CANCEL_L2, 0x04094) +EVENT(PM_MRK_FIN_STALL_CYC_COUNT, 0x1003d) +EVENT(PM_BR_PRED_CCACHE, 0x040a0) +EVENT(PM_GCT_UTIL_1_TO_2_SLOTS, 0x0209c) +EVENT(PM_MRK_ST_CMPL_INT, 0x30034) +EVENT(PM_LSU_TWO_TABLEWALK_CYC, 0x0d0a6) +EVENT(PM_MRK_DATA_FROM_L3MISS, 0x2d048) +EVENT(PM_GCT_NOSLOT_CYC, 0x100f8) +EVENT(PM_LSU_SET_MPRED, 0x0c0a8) +EVENT(PM_FLUSH_DISP_TLBIE, 0x0208a) +EVENT(PM_VSU1_FCONV, 0x0a0b2) +EVENT(PM_DERAT_MISS_16G, 0x4c05c) +EVENT(PM_INST_FROM_LMEM, 0x3404a) +EVENT(PM_IC_DEMAND_L2_BR_REDIRECT, 0x0409a) +EVENT(PM_CMPLU_STALL_SCALAR_LONG, 0x20018) +EVENT(PM_INST_PTEG_FROM_L2, 0x1e050) +EVENT(PM_PTEG_FROM_L2, 0x1c050) +EVENT(PM_MRK_DATA_FROM_L21_SHR_CYC, 0x20024) +EVENT(PM_MRK_DTLB_MISS_4K, 0x2d05a) +EVENT(PM_VSU0_FPSCR, 0x0b09c) +EVENT(PM_VSU1_VECT_DOUBLE_ISSUED, 0x0b082) +EVENT(PM_MRK_PTEG_FROM_RL2L3_MOD, 0x1d052) +EVENT(PM_MEM0_RQ_DISP, 0x10083) +EVENT(PM_L2_LD_MISS, 0x26080) +EVENT(PM_VMX_RESULT_SAT_1, 0x0b0a0) +EVENT(PM_L1_PREF, 0x0d8b8) +EVENT(PM_MRK_DATA_FROM_LMEM_CYC, 0x2002c) +EVENT(PM_GRP_IC_MISS_NONSPEC, 0x1000c) +EVENT(PM_PB_NODE_PUMP, 0x10081) +EVENT(PM_SHL_MERGED, 0x05084) +EVENT(PM_NEST_PAIR1_ADD, 0x20881) +EVENT(PM_DATA_FROM_L3, 0x1c048) +EVENT(PM_LSU_FLUSH, 0x0208e) +EVENT(PM_LSU_SRQ_SYNC_COUNT, 0x0d097) +EVENT(PM_PMC2_OVERFLOW, 0x30010) +EVENT(PM_LSU_LDF, 0x0c884) +EVENT(PM_POWER_EVENT3, 0x3006e) +EVENT(PM_DISP_WT, 0x30008) +EVENT(PM_CMPLU_STALL_REJECT, 0x40016) +EVENT(PM_IC_BANK_CONFLICT, 0x04082) +EVENT(PM_BR_MPRED_CR_TA, 0x048ae) +EVENT(PM_L2_INST_MISS, 0x36082) +EVENT(PM_CMPLU_STALL_ERAT_MISS, 0x40018) +EVENT(PM_NEST_PAIR2_ADD, 0x30881) +EVENT(PM_MRK_LSU_FLUSH, 0x0d08c) +EVENT(PM_L2_LDST, 0x16880) +EVENT(PM_INST_FROM_L31_SHR, 0x1404e) +EVENT(PM_VSU0_FIN, 0x0a0bc) +EVENT(PM_LARX_LSU, 0x0c894) +EVENT(PM_INST_FROM_RMEM, 0x34042) +EVENT(PM_DISP_CLB_HELD_TLBIE, 0x02096) +EVENT(PM_MRK_DATA_FROM_DMEM_CYC, 0x2002e) +EVENT(PM_BR_PRED_CR, 0x040a8) +EVENT(PM_LSU_REJECT, 0x10064) +EVENT(PM_GCT_UTIL_3_TO_6_SLOTS, 0x0209e) +EVENT(PM_CMPLU_STALL_END_GCT_NOSLOT, 0x10028) +EVENT(PM_LSU0_REJECT_LMQ_FULL, 0x0c0a4) +EVENT(PM_VSU_FEST, 0x0a8b8) +EVENT(PM_NEST_PAIR0_AND, 0x10883) +EVENT(PM_PTEG_FROM_L3, 0x2c050) +EVENT(PM_POWER_EVENT2, 0x2006e) +EVENT(PM_IC_PREF_CANCEL_PAGE, 0x04090) +EVENT(PM_VSU0_FSQRT_FDIV, 0x0a088) +EVENT(PM_MRK_GRP_CMPL, 0x40030) +EVENT(PM_VSU0_SCAL_DOUBLE_ISSUED, 0x0b088) +EVENT(PM_GRP_DISP, 0x3000a) +EVENT(PM_LSU0_LDX, 0x0c088) +EVENT(PM_DATA_FROM_L2, 0x1c040) +EVENT(PM_MRK_DATA_FROM_RL2L3_MOD, 0x1d042) +EVENT(PM_LD_REF_L1, 0x0c880) +EVENT(PM_VSU0_VECT_DOUBLE_ISSUED, 0x0b080) +EVENT(PM_VSU1_2FLOP_DOUBLE, 0x0a08e) +EVENT(PM_THRD_PRIO_6_7_CYC, 0x040b6) +EVENT(PM_BC_PLUS_8_RSLV_TAKEN, 0x040ba) +EVENT(PM_BR_MPRED_CR, 0x040ac) +EVENT(PM_L3_CO_MEM, 0x4f082) +EVENT(PM_LD_MISS_L1, 0x400f0) +EVENT(PM_DATA_FROM_RL2L3_MOD, 0x1c042) +EVENT(PM_LSU_SRQ_FULL_CYC, 0x1001a) +EVENT(PM_TABLEWALK_CYC, 0x10026) +EVENT(PM_MRK_PTEG_FROM_RMEM, 0x3d052) +EVENT(PM_LSU_SRQ_STFWD, 0x0c8a0) +EVENT(PM_INST_PTEG_FROM_RMEM, 0x3e052) +EVENT(PM_FXU0_FIN, 0x10004) +EVENT(PM_LSU1_L1_SW_PREF, 0x0c09e) +EVENT(PM_PTEG_FROM_L31_MOD, 0x1c054) +EVENT(PM_PMC5_OVERFLOW, 0x10024) +EVENT(PM_LD_REF_L1_LSU1, 0x0c082) +EVENT(PM_INST_PTEG_FROM_L21_SHR, 0x4e056) +EVENT(PM_CMPLU_STALL_THRD, 0x1001c) +EVENT(PM_DATA_FROM_RMEM, 0x3c042) +EVENT(PM_VSU0_SCAL_SINGLE_ISSUED, 0x0b084) +EVENT(PM_BR_MPRED_LSTACK, 0x040a6) +EVENT(PM_MRK_DATA_FROM_RL2L3_MOD_CYC, 0x40028) +EVENT(PM_LSU0_FLUSH_UST, 0x0c0b4) +EVENT(PM_LSU_NCST, 0x0c090) +EVENT(PM_BR_TAKEN, 0x20004) +EVENT(PM_INST_PTEG_FROM_LMEM, 0x4e052) +EVENT(PM_GCT_NOSLOT_BR_MPRED_IC_MISS, 0x4001c) +EVENT(PM_DTLB_MISS_4K, 0x2c05a) +EVENT(PM_PMC4_SAVED, 0x30022) +EVENT(PM_VSU1_PERMUTE_ISSUED, 0x0b092) +EVENT(PM_SLB_MISS, 0x0d890) +EVENT(PM_LSU1_FLUSH_LRQ, 0x0c0ba) +EVENT(PM_DTLB_MISS, 0x300fc) +EVENT(PM_VSU1_FRSP, 0x0a0b6) +EVENT(PM_VSU_VECTOR_DOUBLE_ISSUED, 0x0b880) +EVENT(PM_L2_CASTOUT_SHR, 0x16182) +EVENT(PM_DATA_FROM_DL2L3_SHR, 0x3c044) +EVENT(PM_VSU1_STF, 0x0b08e) +EVENT(PM_ST_FIN, 0x200f0) +EVENT(PM_PTEG_FROM_L21_SHR, 0x4c056) +EVENT(PM_L2_LOC_GUESS_WRONG, 0x26480) +EVENT(PM_MRK_STCX_FAIL, 0x0d08e) +EVENT(PM_LSU0_REJECT_LHS, 0x0c0ac) +EVENT(PM_IC_PREF_CANCEL_HIT, 0x04092) +EVENT(PM_L3_PREF_BUSY, 0x4f080) +EVENT(PM_MRK_BRU_FIN, 0x2003a) +EVENT(PM_LSU1_NCLD, 0x0c08e) +EVENT(PM_INST_PTEG_FROM_L31_MOD, 0x1e054) +EVENT(PM_LSU_NCLD, 0x0c88c) +EVENT(PM_LSU_LDX, 0x0c888) +EVENT(PM_L2_LOC_GUESS_CORRECT, 0x16480) +EVENT(PM_THRESH_TIMEO, 0x10038) +EVENT(PM_L3_PREF_ST, 0x0d0ae) +EVENT(PM_DISP_CLB_HELD_SYNC, 0x02098) +EVENT(PM_VSU_SIMPLE_ISSUED, 0x0b894) +EVENT(PM_VSU1_SINGLE, 0x0a0aa) +EVENT(PM_DATA_TABLEWALK_CYC, 0x3001a) +EVENT(PM_L2_RC_ST_DONE, 0x36380) +EVENT(PM_MRK_PTEG_FROM_L21_MOD, 0x3d056) +EVENT(PM_LARX_LSU1, 0x0c096) +EVENT(PM_MRK_DATA_FROM_RMEM, 0x3d042) +EVENT(PM_DISP_CLB_HELD, 0x02090) +EVENT(PM_DERAT_MISS_4K, 0x1c05c) +EVENT(PM_L2_RCLD_DISP_FAIL_ADDR, 0x16282) +EVENT(PM_SEG_EXCEPTION, 0x028a4) +EVENT(PM_FLUSH_DISP_SB, 0x0208c) +EVENT(PM_L2_DC_INV, 0x26182) +EVENT(PM_PTEG_FROM_DL2L3_MOD, 0x4c054) +EVENT(PM_DSEG, 0x020a6) +EVENT(PM_BR_PRED_LSTACK, 0x040a2) +EVENT(PM_VSU0_STF, 0x0b08c) +EVENT(PM_LSU_FX_FIN, 0x10066) +EVENT(PM_DERAT_MISS_16M, 0x3c05c) +EVENT(PM_MRK_PTEG_FROM_DL2L3_MOD, 0x4d054) +EVENT(PM_GCT_UTIL_11_PLUS_SLOTS, 0x020a2) +EVENT(PM_INST_FROM_L3, 0x14048) +EVENT(PM_MRK_IFU_FIN, 0x3003a) +EVENT(PM_ITLB_MISS, 0x400fc) +EVENT(PM_VSU_STF, 0x0b88c) +EVENT(PM_LSU_FLUSH_UST, 0x0c8b4) +EVENT(PM_L2_LDST_MISS, 0x26880) +EVENT(PM_FXU1_FIN, 0x40004) +EVENT(PM_SHL_DEALLOCATED, 0x05080) +EVENT(PM_L2_SN_M_WR_DONE, 0x46382) +EVENT(PM_LSU_REJECT_SET_MPRED, 0x0c8a8) +EVENT(PM_L3_PREF_LD, 0x0d0ac) +EVENT(PM_L2_SN_M_RD_DONE, 0x46380) +EVENT(PM_MRK_DERAT_MISS_16G, 0x4d05c) +EVENT(PM_VSU_FCONV, 0x0a8b0) +EVENT(PM_ANY_THRD_RUN_CYC, 0x100fa) +EVENT(PM_LSU_LMQ_FULL_CYC, 0x0d0a4) +EVENT(PM_MRK_LSU_REJECT_LHS, 0x0d082) +EVENT(PM_MRK_LD_MISS_L1_CYC, 0x4003e) +EVENT(PM_MRK_DATA_FROM_L2_CYC, 0x20020) +EVENT(PM_INST_IMC_MATCH_DISP, 0x30016) +EVENT(PM_MRK_DATA_FROM_RMEM_CYC, 0x4002c) +EVENT(PM_VSU0_SIMPLE_ISSUED, 0x0b094) +EVENT(PM_CMPLU_STALL_DIV, 0x40014) +EVENT(PM_MRK_PTEG_FROM_RL2L3_SHR, 0x2d054) +EVENT(PM_VSU_FMA_DOUBLE, 0x0a890) +EVENT(PM_VSU_4FLOP, 0x0a89c) +EVENT(PM_VSU1_FIN, 0x0a0be) +EVENT(PM_NEST_PAIR1_AND, 0x20883) +EVENT(PM_INST_PTEG_FROM_RL2L3_MOD, 0x1e052) +EVENT(PM_RUN_CYC, 0x200f4) +EVENT(PM_PTEG_FROM_RMEM, 0x3c052) +EVENT(PM_LSU_LRQ_S0_VALID, 0x0d09e) +EVENT(PM_LSU0_LDF, 0x0c084) +EVENT(PM_FLUSH_COMPLETION, 0x30012) +EVENT(PM_ST_MISS_L1, 0x300f0) +EVENT(PM_L2_NODE_PUMP, 0x36480) +EVENT(PM_INST_FROM_DL2L3_SHR, 0x34044) +EVENT(PM_MRK_STALL_CMPLU_CYC, 0x3003e) +EVENT(PM_VSU1_DENORM, 0x0a0ae) +EVENT(PM_MRK_DATA_FROM_L31_SHR_CYC, 0x20026) +EVENT(PM_NEST_PAIR0_ADD, 0x10881) +EVENT(PM_INST_FROM_L3MISS, 0x24048) +EVENT(PM_EE_OFF_EXT_INT, 0x02080) +EVENT(PM_INST_PTEG_FROM_DMEM, 0x2e052) +EVENT(PM_INST_FROM_DL2L3_MOD, 0x3404c) +EVENT(PM_PMC6_OVERFLOW, 0x30024) +EVENT(PM_VSU_2FLOP_DOUBLE, 0x0a88c) +EVENT(PM_TLB_MISS, 0x20066) +EVENT(PM_FXU_BUSY, 0x2000e) +EVENT(PM_L2_RCLD_DISP_FAIL_OTHER, 0x26280) +EVENT(PM_LSU_REJECT_LMQ_FULL, 0x0c8a4) +EVENT(PM_IC_RELOAD_SHR, 0x04096) +EVENT(PM_GRP_MRK, 0x10031) +EVENT(PM_MRK_ST_NEST, 0x20034) +EVENT(PM_VSU1_FSQRT_FDIV, 0x0a08a) +EVENT(PM_LSU0_FLUSH_LRQ, 0x0c0b8) +EVENT(PM_LARX_LSU0, 0x0c094) +EVENT(PM_IBUF_FULL_CYC, 0x04084) +EVENT(PM_MRK_DATA_FROM_DL2L3_SHR_CYC, 0x2002a) +EVENT(PM_LSU_DC_PREF_STREAM_ALLOC, 0x0d8a8) +EVENT(PM_GRP_MRK_CYC, 0x10030) +EVENT(PM_MRK_DATA_FROM_RL2L3_SHR_CYC, 0x20028) +EVENT(PM_L2_GLOB_GUESS_CORRECT, 0x16482) +EVENT(PM_LSU_REJECT_LHS, 0x0c8ac) +EVENT(PM_MRK_DATA_FROM_LMEM, 0x3d04a) +EVENT(PM_INST_PTEG_FROM_L3, 0x2e050) +EVENT(PM_FREQ_DOWN, 0x3000c) +EVENT(PM_PB_RETRY_NODE_PUMP, 0x30081) +EVENT(PM_INST_FROM_RL2L3_SHR, 0x1404c) +EVENT(PM_MRK_INST_ISSUED, 0x10032) +EVENT(PM_PTEG_FROM_L3MISS, 0x2c058) +EVENT(PM_RUN_PURR, 0x400f4) +EVENT(PM_MRK_GRP_IC_MISS, 0x40038) +EVENT(PM_MRK_DATA_FROM_L3, 0x1d048) +EVENT(PM_CMPLU_STALL_DCACHE_MISS, 0x20016) +EVENT(PM_PTEG_FROM_RL2L3_SHR, 0x2c054) +EVENT(PM_LSU_FLUSH_LRQ, 0x0c8b8) +EVENT(PM_MRK_DERAT_MISS_64K, 0x2d05c) +EVENT(PM_INST_PTEG_FROM_DL2L3_MOD, 0x4e054) +EVENT(PM_L2_ST_MISS, 0x26082) +EVENT(PM_MRK_PTEG_FROM_L21_SHR, 0x4d056) +EVENT(PM_LWSYNC, 0x0d094) +EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE, 0x0d0bc) +EVENT(PM_MRK_LSU_FLUSH_LRQ, 0x0d088) +EVENT(PM_INST_IMC_MATCH_CMPL, 0x100f0) +EVENT(PM_NEST_PAIR3_AND, 0x40883) +EVENT(PM_PB_RETRY_SYS_PUMP, 0x40081) +EVENT(PM_MRK_INST_FIN, 0x30030) +EVENT(PM_MRK_PTEG_FROM_DL2L3_SHR, 0x3d054) +EVENT(PM_INST_FROM_L31_MOD, 0x14044) +EVENT(PM_MRK_DTLB_MISS_64K, 0x3d05e) +EVENT(PM_LSU_FIN, 0x30066) +EVENT(PM_MRK_LSU_REJECT, 0x40064) +EVENT(PM_L2_CO_FAIL_BUSY, 0x16382) +EVENT(PM_MEM0_WQ_DISP, 0x40083) +EVENT(PM_DATA_FROM_L31_MOD, 0x1c044) +EVENT(PM_THERMAL_WARN, 0x10016) +EVENT(PM_VSU0_4FLOP, 0x0a09c) +EVENT(PM_BR_MPRED_CCACHE, 0x040a4) +EVENT(PM_CMPLU_STALL_IFU, 0x4004c) +EVENT(PM_L1_DEMAND_WRITE, 0x0408c) +EVENT(PM_FLUSH_BR_MPRED, 0x02084) +EVENT(PM_MRK_DTLB_MISS_16G, 0x1d05e) +EVENT(PM_MRK_PTEG_FROM_DMEM, 0x2d052) +EVENT(PM_L2_RCST_DISP, 0x36280) +EVENT(PM_CMPLU_STALL, 0x4000a) +EVENT(PM_LSU_PARTIAL_CDF, 0x0c0aa) +EVENT(PM_DISP_CLB_HELD_SB, 0x020a8) +EVENT(PM_VSU0_FMA_DOUBLE, 0x0a090) +EVENT(PM_FXU0_BUSY_FXU1_IDLE, 0x3000e) +EVENT(PM_IC_DEMAND_CYC, 0x10018) +EVENT(PM_MRK_DATA_FROM_L21_SHR, 0x3d04e) +EVENT(PM_MRK_LSU_FLUSH_UST, 0x0d086) +EVENT(PM_INST_PTEG_FROM_L3MISS, 0x2e058) +EVENT(PM_VSU_DENORM, 0x0a8ac) +EVENT(PM_MRK_LSU_PARTIAL_CDF, 0x0d080) +EVENT(PM_INST_FROM_L21_SHR, 0x3404e) +EVENT(PM_IC_PREF_WRITE, 0x0408e) +EVENT(PM_BR_PRED, 0x0409c) +EVENT(PM_INST_FROM_DMEM, 0x1404a) +EVENT(PM_IC_PREF_CANCEL_ALL, 0x04890) +EVENT(PM_LSU_DC_PREF_STREAM_CONFIRM, 0x0d8b4) +EVENT(PM_MRK_LSU_FLUSH_SRQ, 0x0d08a) +EVENT(PM_MRK_FIN_STALL_CYC, 0x1003c) +EVENT(PM_L2_RCST_DISP_FAIL_OTHER, 0x46280) +EVENT(PM_VSU1_DD_ISSUED, 0x0b098) +EVENT(PM_PTEG_FROM_L31_SHR, 0x2c056) +EVENT(PM_DATA_FROM_L21_SHR, 0x3c04e) +EVENT(PM_LSU0_NCLD, 0x0c08c) +EVENT(PM_VSU1_4FLOP, 0x0a09e) +EVENT(PM_VSU1_8FLOP, 0x0a0a2) +EVENT(PM_VSU_8FLOP, 0x0a8a0) +EVENT(PM_LSU_LMQ_SRQ_EMPTY_CYC, 0x2003e) +EVENT(PM_DTLB_MISS_64K, 0x3c05e) +EVENT(PM_THRD_CONC_RUN_INST, 0x300f4) +EVENT(PM_MRK_PTEG_FROM_L2, 0x1d050) +EVENT(PM_PB_SYS_PUMP, 0x20081) +EVENT(PM_VSU_FIN, 0x0a8bc) +EVENT(PM_MRK_DATA_FROM_L31_MOD, 0x1d044) +EVENT(PM_THRD_PRIO_0_1_CYC, 0x040b0) +EVENT(PM_DERAT_MISS_64K, 0x2c05c) +EVENT(PM_PMC2_REWIND, 0x30020) +EVENT(PM_INST_FROM_L2, 0x14040) +EVENT(PM_GRP_BR_MPRED_NONSPEC, 0x1000a) +EVENT(PM_INST_DISP, 0x200f2) +EVENT(PM_MEM0_RD_CANCEL_TOTAL, 0x30083) +EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM, 0x0d0b4) +EVENT(PM_L1_DCACHE_RELOAD_VALID, 0x300f6) +EVENT(PM_VSU_SCALAR_DOUBLE_ISSUED, 0x0b888) +EVENT(PM_L3_PREF_HIT, 0x3f080) +EVENT(PM_MRK_PTEG_FROM_L31_MOD, 0x1d054) +EVENT(PM_CMPLU_STALL_STORE, 0x2004a) +EVENT(PM_MRK_FXU_FIN, 0x20038) +EVENT(PM_PMC4_OVERFLOW, 0x10010) +EVENT(PM_MRK_PTEG_FROM_L3, 0x2d050) +EVENT(PM_LSU0_LMQ_LHR_MERGE, 0x0d098) +EVENT(PM_BTAC_HIT, 0x0508a) +EVENT(PM_L3_RD_BUSY, 0x4f082) +EVENT(PM_LSU0_L1_SW_PREF, 0x0c09c) +EVENT(PM_INST_FROM_L2MISS, 0x44048) +EVENT(PM_LSU0_DC_PREF_STREAM_ALLOC, 0x0d0a8) +EVENT(PM_L2_ST, 0x16082) +EVENT(PM_VSU0_DENORM, 0x0a0ac) +EVENT(PM_MRK_DATA_FROM_DL2L3_SHR, 0x3d044) +EVENT(PM_BR_PRED_CR_TA, 0x048aa) +EVENT(PM_VSU0_FCONV, 0x0a0b0) +EVENT(PM_MRK_LSU_FLUSH_ULD, 0x0d084) +EVENT(PM_BTAC_MISS, 0x05088) +EVENT(PM_MRK_LD_MISS_EXPOSED_CYC_COUNT, 0x1003f) +EVENT(PM_MRK_DATA_FROM_L2, 0x1d040) +EVENT(PM_LSU_DCACHE_RELOAD_VALID, 0x0d0a2) +EVENT(PM_VSU_FMA, 0x0a884) +EVENT(PM_LSU0_FLUSH_SRQ, 0x0c0bc) +EVENT(PM_LSU1_L1_PREF, 0x0d0ba) +EVENT(PM_IOPS_CMPL, 0x10014) +EVENT(PM_L2_SYS_PUMP, 0x36482) +EVENT(PM_L2_RCLD_BUSY_RC_FULL, 0x46282) +EVENT(PM_LSU_LMQ_S0_ALLOC, 0x0d0a1) +EVENT(PM_FLUSH_DISP_SYNC, 0x02088) +EVENT(PM_MRK_DATA_FROM_DL2L3_MOD_CYC, 0x4002a) +EVENT(PM_L2_IC_INV, 0x26180) +EVENT(PM_MRK_DATA_FROM_L21_MOD_CYC, 0x40024) +EVENT(PM_L3_PREF_LDST, 0x0d8ac) +EVENT(PM_LSU_SRQ_EMPTY_CYC, 0x40008) +EVENT(PM_LSU_LMQ_S0_VALID, 0x0d0a0) +EVENT(PM_FLUSH_PARTIAL, 0x02086) +EVENT(PM_VSU1_FMA_DOUBLE, 0x0a092) +EVENT(PM_1PLUS_PPC_DISP, 0x400f2) +EVENT(PM_DATA_FROM_L2MISS, 0x200fe) +EVENT(PM_SUSPENDED, 0x00000) +EVENT(PM_VSU0_FMA, 0x0a084) +EVENT(PM_CMPLU_STALL_SCALAR, 0x40012) +EVENT(PM_STCX_FAIL, 0x0c09a) +EVENT(PM_VSU0_FSQRT_FDIV_DOUBLE, 0x0a094) +EVENT(PM_DC_PREF_DST, 0x0d0b0) +EVENT(PM_VSU1_SCAL_SINGLE_ISSUED, 0x0b086) +EVENT(PM_L3_HIT, 0x1f080) +EVENT(PM_L2_GLOB_GUESS_WRONG, 0x26482) +EVENT(PM_MRK_DFU_FIN, 0x20032) +EVENT(PM_INST_FROM_L1, 0x04080) +EVENT(PM_BRU_FIN, 0x10068) +EVENT(PM_IC_DEMAND_REQ, 0x04088) +EVENT(PM_VSU1_FSQRT_FDIV_DOUBLE, 0x0a096) +EVENT(PM_VSU1_FMA, 0x0a086) +EVENT(PM_MRK_LD_MISS_L1, 0x20036) +EVENT(PM_VSU0_2FLOP_DOUBLE, 0x0a08c) +EVENT(PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM, 0x0d8bc) +EVENT(PM_INST_PTEG_FROM_L31_SHR, 0x2e056) +EVENT(PM_MRK_LSU_REJECT_ERAT_MISS, 0x30064) +EVENT(PM_MRK_DATA_FROM_L2MISS, 0x4d048) +EVENT(PM_DATA_FROM_RL2L3_SHR, 0x1c04c) +EVENT(PM_INST_FROM_PREF, 0x14046) +EVENT(PM_VSU1_SQ, 0x0b09e) +EVENT(PM_L2_LD_DISP, 0x36180) +EVENT(PM_L2_DISP_ALL, 0x46080) +EVENT(PM_THRD_GRP_CMPL_BOTH_CYC, 0x10012) +EVENT(PM_VSU_FSQRT_FDIV_DOUBLE, 0x0a894) +EVENT(PM_BR_MPRED, 0x400f6) +EVENT(PM_INST_PTEG_FROM_DL2L3_SHR, 0x3e054) +EVENT(PM_VSU_1FLOP, 0x0a880) +EVENT(PM_HV_CYC, 0x2000a) +EVENT(PM_MRK_LSU_FIN, 0x40032) +EVENT(PM_MRK_DATA_FROM_RL2L3_SHR, 0x1d04c) +EVENT(PM_DTLB_MISS_16M, 0x4c05e) +EVENT(PM_LSU1_LMQ_LHR_MERGE, 0x0d09a) +EVENT(PM_IFU_FIN, 0x40066) diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index d1821b8bbc4c..56c67bca2f75 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -53,37 +53,13 @@ /* * Power7 event codes. */ -#define PME_PM_CYC 0x1e -#define PME_PM_GCT_NOSLOT_CYC 0x100f8 -#define PME_PM_CMPLU_STALL 0x4000a -#define PME_PM_INST_CMPL 0x2 -#define PME_PM_LD_REF_L1 0xc880 -#define PME_PM_LD_MISS_L1 0x400f0 -#define PME_PM_BRU_FIN 0x10068 -#define PME_PM_BR_MPRED 0x400f6 - -#define PME_PM_CMPLU_STALL_FXU 0x20014 -#define PME_PM_CMPLU_STALL_DIV 0x40014 -#define PME_PM_CMPLU_STALL_SCALAR 0x40012 -#define PME_PM_CMPLU_STALL_SCALAR_LONG 0x20018 -#define PME_PM_CMPLU_STALL_VECTOR 0x2001c -#define PME_PM_CMPLU_STALL_VECTOR_LONG 0x4004a -#define PME_PM_CMPLU_STALL_LSU 0x20012 -#define PME_PM_CMPLU_STALL_REJECT 0x40016 -#define PME_PM_CMPLU_STALL_ERAT_MISS 0x40018 -#define PME_PM_CMPLU_STALL_DCACHE_MISS 0x20016 -#define PME_PM_CMPLU_STALL_STORE 0x2004a -#define PME_PM_CMPLU_STALL_THRD 0x1001c -#define PME_PM_CMPLU_STALL_IFU 0x4004c -#define PME_PM_CMPLU_STALL_BRU 0x4004e -#define PME_PM_GCT_NOSLOT_IC_MISS 0x2001a -#define PME_PM_GCT_NOSLOT_BR_MPRED 0x4001a -#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS 0x4001c -#define PME_PM_GRP_CMPL 0x30004 -#define PME_PM_1PLUS_PPC_CMPL 0x100f2 -#define PME_PM_CMPLU_STALL_DFU 0x2003c -#define PME_PM_RUN_CYC 0x200f4 -#define PME_PM_RUN_INST_CMPL 0x400fa +#define EVENT(_name, _code) \ + PME_##_name = _code, + +enum { +#include "power7-events-list.h" +}; +#undef EVENT /* * Layout of constraint bits: @@ -398,96 +374,36 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { }; -GENERIC_EVENT_ATTR(cpu-cycles, CYC); -GENERIC_EVENT_ATTR(stalled-cycles-frontend, GCT_NOSLOT_CYC); -GENERIC_EVENT_ATTR(stalled-cycles-backend, CMPLU_STALL); -GENERIC_EVENT_ATTR(instructions, INST_CMPL); -GENERIC_EVENT_ATTR(cache-references, LD_REF_L1); -GENERIC_EVENT_ATTR(cache-misses, LD_MISS_L1); -GENERIC_EVENT_ATTR(branch-instructions, BRU_FIN); -GENERIC_EVENT_ATTR(branch-misses, BR_MPRED); - -POWER_EVENT_ATTR(CYC, CYC); -POWER_EVENT_ATTR(GCT_NOSLOT_CYC, GCT_NOSLOT_CYC); -POWER_EVENT_ATTR(CMPLU_STALL, CMPLU_STALL); -POWER_EVENT_ATTR(INST_CMPL, INST_CMPL); -POWER_EVENT_ATTR(LD_REF_L1, LD_REF_L1); -POWER_EVENT_ATTR(LD_MISS_L1, LD_MISS_L1); -POWER_EVENT_ATTR(BRU_FIN, BRU_FIN) -POWER_EVENT_ATTR(BR_MPRED, BR_MPRED); - -POWER_EVENT_ATTR(CMPLU_STALL_FXU, CMPLU_STALL_FXU); -POWER_EVENT_ATTR(CMPLU_STALL_DIV, CMPLU_STALL_DIV); -POWER_EVENT_ATTR(CMPLU_STALL_SCALAR, CMPLU_STALL_SCALAR); -POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG, CMPLU_STALL_SCALAR_LONG); -POWER_EVENT_ATTR(CMPLU_STALL_VECTOR, CMPLU_STALL_VECTOR); -POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG, CMPLU_STALL_VECTOR_LONG); -POWER_EVENT_ATTR(CMPLU_STALL_LSU, CMPLU_STALL_LSU); -POWER_EVENT_ATTR(CMPLU_STALL_REJECT, CMPLU_STALL_REJECT); - -POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS, CMPLU_STALL_ERAT_MISS); -POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS, CMPLU_STALL_DCACHE_MISS); -POWER_EVENT_ATTR(CMPLU_STALL_STORE, CMPLU_STALL_STORE); -POWER_EVENT_ATTR(CMPLU_STALL_THRD, CMPLU_STALL_THRD); -POWER_EVENT_ATTR(CMPLU_STALL_IFU, CMPLU_STALL_IFU); -POWER_EVENT_ATTR(CMPLU_STALL_BRU, CMPLU_STALL_BRU); -POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS, GCT_NOSLOT_IC_MISS); - -POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED, GCT_NOSLOT_BR_MPRED); -POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS, GCT_NOSLOT_BR_MPRED_IC_MISS); -POWER_EVENT_ATTR(GRP_CMPL, GRP_CMPL); -POWER_EVENT_ATTR(1PLUS_PPC_CMPL, 1PLUS_PPC_CMPL); -POWER_EVENT_ATTR(CMPLU_STALL_DFU, CMPLU_STALL_DFU); -POWER_EVENT_ATTR(RUN_CYC, RUN_CYC); -POWER_EVENT_ATTR(RUN_INST_CMPL, RUN_INST_CMPL); +GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_GCT_NOSLOT_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL); +GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); +GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); +GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1); +GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN); +GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED); + +#define EVENT(_name, _code) POWER_EVENT_ATTR(_name, _name); +#include "power7-events-list.h" +#undef EVENT + +#define EVENT(_name, _code) POWER_EVENT_PTR(_name), static struct attribute *power7_events_attr[] = { - GENERIC_EVENT_PTR(CYC), - GENERIC_EVENT_PTR(GCT_NOSLOT_CYC), - GENERIC_EVENT_PTR(CMPLU_STALL), - GENERIC_EVENT_PTR(INST_CMPL), - GENERIC_EVENT_PTR(LD_REF_L1), - GENERIC_EVENT_PTR(LD_MISS_L1), - GENERIC_EVENT_PTR(BRU_FIN), - GENERIC_EVENT_PTR(BR_MPRED), - - POWER_EVENT_PTR(CYC), - POWER_EVENT_PTR(GCT_NOSLOT_CYC), - POWER_EVENT_PTR(CMPLU_STALL), - POWER_EVENT_PTR(INST_CMPL), - POWER_EVENT_PTR(LD_REF_L1), - POWER_EVENT_PTR(LD_MISS_L1), - POWER_EVENT_PTR(BRU_FIN), - POWER_EVENT_PTR(BR_MPRED), - - POWER_EVENT_PTR(CMPLU_STALL_FXU), - POWER_EVENT_PTR(CMPLU_STALL_DIV), - POWER_EVENT_PTR(CMPLU_STALL_SCALAR), - POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG), - POWER_EVENT_PTR(CMPLU_STALL_VECTOR), - POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG), - POWER_EVENT_PTR(CMPLU_STALL_LSU), - POWER_EVENT_PTR(CMPLU_STALL_REJECT), - - POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS), - POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS), - POWER_EVENT_PTR(CMPLU_STALL_STORE), - POWER_EVENT_PTR(CMPLU_STALL_THRD), - POWER_EVENT_PTR(CMPLU_STALL_IFU), - POWER_EVENT_PTR(CMPLU_STALL_BRU), - POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS), - POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED), - - POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS), - POWER_EVENT_PTR(GRP_CMPL), - POWER_EVENT_PTR(1PLUS_PPC_CMPL), - POWER_EVENT_PTR(CMPLU_STALL_DFU), - POWER_EVENT_PTR(RUN_CYC), - POWER_EVENT_PTR(RUN_INST_CMPL), + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC), + GENERIC_EVENT_PTR(PM_CMPLU_STALL), + GENERIC_EVENT_PTR(PM_INST_CMPL), + GENERIC_EVENT_PTR(PM_LD_REF_L1), + GENERIC_EVENT_PTR(PM_LD_MISS_L1), + GENERIC_EVENT_PTR(PM_BRU_FIN), + GENERIC_EVENT_PTR(PM_BR_MPRED), + + #include "power7-events-list.h" + #undef EVENT NULL }; - static struct attribute_group power7_pmu_events_group = { .name = "events", .attrs = power7_events_attr, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 27457379bbd5..f16fc34e6608 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -82,7 +82,6 @@ config X86 select HAVE_USER_RETURN_NOTIFIER select ARCH_BINFMT_ELF_RANDOMIZE_PIE select HAVE_ARCH_JUMP_LABEL - select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select SPARSE_IRQ @@ -2333,10 +2332,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -config HAVE_TEXT_POKE_SMP - bool - select STOP_MACHINE if SMP - config X86_DEV_DMA_OPS bool depends on X86_64 || STA2X11 diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 58ed6d96a6ac..0a3f9c9f98d5 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -5,6 +5,7 @@ #include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h> +#include <asm/ptrace.h> /* * Alternative inline assembly for SMP. @@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * no thread can be preempted in the instructions being modified (no iret to an * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. - * More care must be taken when modifying code in the SMP case because of - * Intel's errata. text_poke_smp() takes care that errata, but still - * doesn't support NMI/MCE handler code modifying. * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ -struct text_poke_param { - void *addr; - const void *opcode; - size_t len; -}; - extern void *text_poke(void *addr, const void *opcode, size_t len); -extern void *text_poke_smp(void *addr, const void *opcode, size_t len); -extern void text_poke_smp_batch(struct text_poke_param *params, int n); +extern int poke_int3_handler(struct pt_regs *regs); +extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index c91e8b9d588b..235be70d5bb4 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -49,6 +49,7 @@ extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); +extern int check_tsc_disabled(void); extern unsigned long native_calibrate_tsc(void); extern int tsc_clocksource_reliable; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c15cf9a25e27..15e8563e5c24 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/memory.h> #include <linux/stop_machine.h> #include <linux/slab.h> +#include <linux/kdebug.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) return addr; } -/* - * Cross-modifying kernel text with stop_machine(). - * This code originally comes from immediate value. - */ -static atomic_t stop_machine_first; -static int wrote_text; +static void do_sync_core(void *info) +{ + sync_core(); +} -struct text_poke_params { - struct text_poke_param *params; - int nparams; -}; +static bool bp_patching_in_progress; +static void *bp_int3_handler, *bp_int3_addr; -static int __kprobes stop_machine_text_poke(void *data) +int poke_int3_handler(struct pt_regs *regs) { - struct text_poke_params *tpp = data; - struct text_poke_param *p; - int i; + /* bp_patching_in_progress */ + smp_rmb(); - if (atomic_xchg(&stop_machine_first, 0)) { - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - text_poke(p->addr, p->opcode, p->len); - } - smp_wmb(); /* Make sure other cpus see that this has run */ - wrote_text = 1; - } else { - while (!wrote_text) - cpu_relax(); - smp_mb(); /* Load wrote_text before following execution */ - } + if (likely(!bp_patching_in_progress)) + return 0; - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - flush_icache_range((unsigned long)p->addr, - (unsigned long)p->addr + p->len); - } - /* - * Intel Archiecture Software Developer's Manual section 7.1.3 specifies - * that a core serializing instruction such as "cpuid" should be - * executed on _each_ core before the new instruction is made visible. - */ - sync_core(); - return 0; -} + if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + return 0; + + /* set up the specified breakpoint handler */ + regs->ip = (unsigned long) bp_int3_handler; + + return 1; -/** - * text_poke_smp - Update instructions on a live kernel on SMP - * @addr: address to modify - * @opcode: source of the copy - * @len: length to copy - * - * Modify multi-byte instruction by using stop_machine() on SMP. This allows - * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying - * should be allowed, since stop_machine() does _not_ protect code against - * NMI and MCE. - * - * Note: Must be called under get_online_cpus() and text_mutex. - */ -void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) -{ - struct text_poke_params tpp; - struct text_poke_param p; - - p.addr = addr; - p.opcode = opcode; - p.len = len; - tpp.params = &p; - tpp.nparams = 1; - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - /* Use __stop_machine() because the caller already got online_cpus. */ - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); - return addr; } /** - * text_poke_smp_batch - Update instructions on a live kernel on SMP - * @params: an array of text_poke parameters - * @n: the number of elements in params. + * text_poke_bp() -- update instructions on live kernel on SMP + * @addr: address to patch + * @opcode: opcode of new instruction + * @len: length to copy + * @handler: address to jump to when the temporary breakpoint is hit * - * Modify multi-byte instruction by using stop_machine() on SMP. Since the - * stop_machine() is heavy task, it is better to aggregate text_poke requests - * and do it once if possible. + * Modify multi-byte instruction by using int3 breakpoint on SMP. + * We completely avoid stop_machine() here, and achieve the + * synchronization using int3 breakpoint. * - * Note: Must be called under get_online_cpus() and text_mutex. + * The way it is done: + * - add a int3 trap to the address that will be patched + * - sync cores + * - update all but the first byte of the patched range + * - sync cores + * - replace the first byte (int3) by the first byte of + * replacing opcode + * - sync cores + * + * Note: must be called under text_mutex. */ -void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { - struct text_poke_params tpp = {.params = params, .nparams = n}; + unsigned char int3 = 0xcc; + + bp_int3_handler = handler; + bp_int3_addr = (u8 *)addr + sizeof(int3); + bp_patching_in_progress = true; + /* + * Corresponding read barrier in int3 notifier for + * making sure the in_progress flags is correctly ordered wrt. + * patching + */ + smp_wmb(); + + text_poke(addr, &int3, sizeof(int3)); - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); + on_each_cpu(do_sync_core, NULL, 1); + + if (len - sizeof(int3) > 0) { + /* patch all but the first byte */ + text_poke((char *)addr + sizeof(int3), + (const char *) opcode + sizeof(int3), + len - sizeof(int3)); + /* + * According to Intel, this core syncing is very likely + * not necessary and we'd be safe even without it. But + * better safe than sorry (plus there's not only Intel). + */ + on_each_cpu(do_sync_core, NULL, 1); + } + + /* patch the first byte */ + text_poke(addr, opcode, sizeof(int3)); + + on_each_cpu(do_sync_core, NULL, 1); + + bp_patching_in_progress = false; + smp_wmb(); + + return addr; } + diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index a7c7305030cc..8355c84b9729 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1884,6 +1884,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { userpg->cap_usr_time = 0; + userpg->cap_usr_time_zero = 0; userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; @@ -1897,6 +1898,11 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + + if (sched_clock_stable && !check_tsc_disabled()) { + userpg->cap_usr_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); + } } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 97e557bc4c91..cc16faae0538 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -641,6 +641,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; +extern struct event_constraint intel_slm_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 4cbe03287b08..beeb7cc07044 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu) struct amd_nb *nb; int i; - nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO, - cpu_to_node(cpu)); + nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu)); if (!nb) return NULL; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index a45d8d4ace10..0abf6742a8b0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -81,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -143,8 +144,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -162,16 +164,27 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_slm_event_constraints[] __read_mostly = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */ + EVENT_CONSTRAINT_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; @@ -882,6 +895,140 @@ static __initconst const u64 atom_hw_cache_event_ids }, }; +static struct extra_reg intel_slm_extra_regs[] __read_mostly = +{ + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1), + EVENT_EXTRA_END +}; + +#define SLM_DMND_READ SNB_DMND_DATA_RD +#define SLM_DMND_WRITE SNB_DMND_RFO +#define SLM_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) + +#define SLM_SNP_ANY (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM) +#define SLM_LLC_ACCESS SNB_RESP_ANY +#define SLM_LLC_MISS (SLM_SNP_ANY|SNB_NON_DRAM) + +static __initconst const u64 slm_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_WRITE|SLM_LLC_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_PREFETCH|SLM_LLC_MISS, + }, + }, +}; + +static __initconst const u64 slm_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0104, /* LD_DCU_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */ + [ C(RESULT_MISS) ] = 0x0280, /* ICACGE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0804, /* LD_DTLB_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ + [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) { /* user explicitly requested branch sampling */ @@ -1301,11 +1448,11 @@ static void intel_fixup_er(struct perf_event *event, int idx) if (idx == EXTRA_REG_RSP_0) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01b7; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0; } else if (idx == EXTRA_REG_RSP_1) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01bb; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1; } } @@ -2176,6 +2323,21 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; + case 55: /* Atom 22nm "Silvermont" */ + memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_atom(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_slm_extra_regs; + x86_pmu.er_flags |= ERF_HAS_RSP_1; + pr_cont("Silvermont events, "); + break; + case 37: /* 32 nm nehalem, "Clarkdale" */ case 44: /* 32 nm nehalem, "Gulftown" */ case 47: /* 32 nm Xeon E7 */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 3065c57a63c1..63438aad177f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -224,7 +224,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -262,7 +262,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -295,7 +295,7 @@ static int alloc_ds_buffer(int cpu) int node = cpu_to_node(cpu); struct debug_store *ds; - ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node); + ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); if (unlikely(!ds)) return -ENOMEM; @@ -517,6 +517,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_slm_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ + INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 1fb6c72717bd..fd8011ed4dcd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore; /* pci bus to socket mapping */ static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; + static DEFINE_RAW_SPINLOCK(uncore_box_lock); /* mask of cpus that collect uncore events */ @@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { @@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = { }; static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event.attr, + &format_attr_event_ext.attr, &format_attr_occ_sel.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = { &format_attr_edge.attr, &format_attr_inv.attr, &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, NULL, }; @@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = { SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), }; +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + static struct intel_uncore_ops snbep_uncore_pci_ops = { - .init_box = snbep_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ }; static struct event_constraint snbep_uncore_cbox_constraints[] = { @@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = { NULL, }; +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; + WARN_ON_ONCE(!filter_pdev); + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + #define SNBEP_UNCORE_PCI_COMMON_INIT() \ .perf_ctr = SNBEP_PCI_PMON_CTR0, \ .event_ctl = SNBEP_PCI_PMON_CTL0, \ @@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = { }; static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &snbep_uncore_pci_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, }; @@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { { /* Home Agent */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = SNBEP_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), }, { /* MC Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), }, { /* MC Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), }, { /* MC Channel 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), }, { /* MC Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), }, { /* QPI Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), }, { /* QPI Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = SNBEP_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* end: all zeroes */ } }; @@ -1256,71 +1363,71 @@ static struct intel_uncore_type *ivt_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { { /* Home Agent 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), }, { /* Home Agent 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), }, { /* MC0 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), }, { /* MC0 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), }, { /* MC0 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), }, { /* MC1 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), }, { /* MC1 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), }, { /* MC1 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), }, { /* MC1 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), }, { /* QPI0 Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), }, { /* QPI0 Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), }, { /* QPI1 Port 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = IVT_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI0 Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI0 Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), }, { /* R3QPI1 Link 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), }, { /* end: all zeroes */ } }; @@ -2606,7 +2713,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (!box) return NULL; @@ -3167,16 +3274,24 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) +static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, phys_id; + struct intel_uncore_type *type; + int phys_id; phys_id = pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { + extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + pci_set_drvdata(pdev, NULL); + return 0; + } + + type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; box = uncore_alloc_box(type, 0); if (!box) return -ENOMEM; @@ -3185,21 +3300,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) * for performance monitoring unit with multiple boxes, * each box has a different function id. */ - for (i = 0; i < type->num_boxes; i++) { - pmu = &type->pmus[i]; - if (pmu->func_id == pdev->devfn) - break; - if (pmu->func_id < 0) { - pmu->func_id = pdev->devfn; - break; - } - pmu = NULL; - } - - if (!pmu) { - kfree(box); - return -EINVAL; - } + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + if (pmu->func_id < 0) + pmu->func_id = pdev->devfn; + else + WARN_ON_ONCE(pmu->func_id != pdev->devfn); box->phys_id = phys_id; box->pci_dev = pdev; @@ -3217,9 +3322,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); - struct intel_uncore_pmu *pmu = box->pmu; - int cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + struct intel_uncore_pmu *pmu; + int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + box = pci_get_drvdata(pdev); + if (!box) { + for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { + if (extra_pci_dev[phys_id][i] == pdev) { + extra_pci_dev[phys_id][i] = NULL; + break; + } + } + WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); + return; + } + + pmu = box->pmu; if (WARN_ON_ONCE(phys_id != box->phys_id)) return; @@ -3240,12 +3358,6 @@ static void uncore_pci_remove(struct pci_dev *pdev) kfree(box); } -static int uncore_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) -{ - return uncore_pci_add(pci_uncores[id->driver_data], pdev); -} - static int __init uncore_pci_init(void) { int ret; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 47b3d00c9d89..a80ab71a883d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -12,6 +12,15 @@ #define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC #define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) +#define UNCORE_PCI_DEV_DATA(type, idx) ((type << 8) | idx) +#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) +#define UNCORE_PCI_DEV_IDX(data) (data & 0xff) +#define UNCORE_EXTRA_PCI_DEV 0xff +#define UNCORE_EXTRA_PCI_DEV_MAX 2 + +/* support up to 8 sockets */ +#define UNCORE_SOCKET_MAX 8 + #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) /* SNB event control */ @@ -108,6 +117,7 @@ (SNBEP_PMON_CTL_EV_SEL_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ SNBEP_PMON_CTL_INVERT | \ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 2889b3d43882..460f5d9ceebb 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -37,7 +37,19 @@ static void __jump_label_transform(struct jump_entry *entry, } else memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + /* + * Make text_poke_bp() a default fallback poker. + * + * At the time the change is being done, just ignore whether we + * are doing nop -> jump or jump -> nop transition, and assume + * always nop being the 'currently valid' instruction + * + */ + if (poker) + (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + else + text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE, + (void *)entry->code + JUMP_LABEL_NOP_SIZE); } void arch_jump_label_transform(struct jump_entry *entry, @@ -45,7 +57,7 @@ void arch_jump_label_transform(struct jump_entry *entry, { get_online_cpus(); mutex_lock(&text_mutex); - __jump_label_transform(entry, type, text_poke_smp); + __jump_label_transform(entry, type, NULL); mutex_unlock(&text_mutex); put_online_cpus(); } diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 2e9d4b5af036..c6ee63f927ab 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to); extern void synthesize_relcall(void *from, void *to); #ifdef CONFIG_OPTPROBES -extern int arch_init_optprobes(void); extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); #else /* !CONFIG_OPTPROBES */ -static inline int arch_init_optprobes(void) -{ - return 0; -} static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { return 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 211bce445522..cd49b2c96d32 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) int __init arch_init_kprobes(void) { - return arch_init_optprobes(); + return 0; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 76dc6f095724..d71e99439376 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -371,31 +371,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - /* * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. @@ -403,37 +378,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, void __kprobes arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - int c = 0; + u8 insn_buf[RELATIVEJUMP_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); + list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); } -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) { + u8 insn_buf[RELATIVEJUMP_SIZE]; + /* Set int3 to first byte for kprobes */ insn_buf[0] = BREAKPOINT_INSTRUCTION; memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); } /* @@ -444,34 +420,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list) { struct optimized_kprobe *op, *tmp; - int c = 0; list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + arch_unoptimize_kprobe(op); list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); } int __kprobes @@ -491,22 +444,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } - -int __kprobes arch_init_optprobes(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1b23a1c92746..8c8093b146ca 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,6 +58,7 @@ #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> +#include <asm/alternative.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + if (poke_int3_handler(regs)) + return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6ff49247edf8..930e5d48f560 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -89,6 +89,12 @@ int check_tsc_unstable(void) } EXPORT_SYMBOL_GPL(check_tsc_unstable); +int check_tsc_disabled(void) +{ + return tsc_disabled; +} +EXPORT_SYMBOL_GPL(check_tsc_disabled); + #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { |