Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 User visible changes:

  * Add a visual cue for toggle zeroing of samples in 'perf top' (Taeung Song)

  * Fix for double free in 'perf stat' when using some specific invalid
    command line combo (Yasser Shalabi)

 Infrastructure changes:

  * Add option to copy events when queuing for sorting across cpu buffers
    and enable it for 'perf kvm stat live', to avoid having events left
    in the queue pointing to the ring buffer be rewritten in high volume
    sessions.  (Alexander Yarygin, improving work done by David Ahern):

  * Document sysfs events/ interfaces (Cody P Schafer)

  * Add support to new style format of kernel PMU event. (Kan Liang)

  * Fix typos in perf/Documentation (Masanari Iida)

  * Improve callchains when using libunwind (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

31 files changed, 460 insertions, 669 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 7b40a3cbc26a..20979f8b3edb 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -27,575 +27,62 @@ Description:	Generic performance monitoring events
 		"basename".
 
 
-What: 		/sys/devices/cpu/events/PM_1PLUS_PPC_CMPL
-		/sys/devices/cpu/events/PM_BRU_FIN
-		/sys/devices/cpu/events/PM_BR_MPRED
-		/sys/devices/cpu/events/PM_CMPLU_STALL
-		/sys/devices/cpu/events/PM_CMPLU_STALL_BRU
-		/sys/devices/cpu/events/PM_CMPLU_STALL_DCACHE_MISS
-		/sys/devices/cpu/events/PM_CMPLU_STALL_DFU
-		/sys/devices/cpu/events/PM_CMPLU_STALL_DIV
-		/sys/devices/cpu/events/PM_CMPLU_STALL_ERAT_MISS
-		/sys/devices/cpu/events/PM_CMPLU_STALL_FXU
-		/sys/devices/cpu/events/PM_CMPLU_STALL_IFU
-		/sys/devices/cpu/events/PM_CMPLU_STALL_LSU
-		/sys/devices/cpu/events/PM_CMPLU_STALL_REJECT
-		/sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR
-		/sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR_LONG
-		/sys/devices/cpu/events/PM_CMPLU_STALL_STORE
-		/sys/devices/cpu/events/PM_CMPLU_STALL_THRD
-		/sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR
-		/sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR_LONG
-		/sys/devices/cpu/events/PM_CYC
-		/sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED
-		/sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED_IC_MISS
-		/sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
-		/sys/devices/cpu/events/PM_GCT_NOSLOT_IC_MISS
-		/sys/devices/cpu/events/PM_GRP_CMPL
-		/sys/devices/cpu/events/PM_INST_CMPL
-		/sys/devices/cpu/events/PM_LD_MISS_L1
-		/sys/devices/cpu/events/PM_LD_REF_L1
-		/sys/devices/cpu/events/PM_RUN_CYC
-		/sys/devices/cpu/events/PM_RUN_INST_CMPL
-		/sys/devices/cpu/events/PM_IC_DEMAND_L2_BR_ALL
-		/sys/devices/cpu/events/PM_GCT_UTIL_7_TO_10_SLOTS
-		/sys/devices/cpu/events/PM_PMC2_SAVED
-		/sys/devices/cpu/events/PM_VSU0_16FLOP
-		/sys/devices/cpu/events/PM_MRK_LSU_DERAT_MISS
-		/sys/devices/cpu/events/PM_MRK_ST_CMPL
-		/sys/devices/cpu/events/PM_NEST_PAIR3_ADD
-		/sys/devices/cpu/events/PM_L2_ST_DISP
-		/sys/devices/cpu/events/PM_L2_CASTOUT_MOD
-		/sys/devices/cpu/events/PM_ISEG
-		/sys/devices/cpu/events/PM_MRK_INST_TIMEO
-		/sys/devices/cpu/events/PM_L2_RCST_DISP_FAIL_ADDR
-		/sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_CONFIRM
-		/sys/devices/cpu/events/PM_IERAT_WR_64K
-		/sys/devices/cpu/events/PM_MRK_DTLB_MISS_16M
-		/sys/devices/cpu/events/PM_IERAT_MISS
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_LMEM
-		/sys/devices/cpu/events/PM_FLOP
-		/sys/devices/cpu/events/PM_THRD_PRIO_4_5_CYC
-		/sys/devices/cpu/events/PM_BR_PRED_TA
-		/sys/devices/cpu/events/PM_EXT_INT
-		/sys/devices/cpu/events/PM_VSU_FSQRT_FDIV
-		/sys/devices/cpu/events/PM_MRK_LD_MISS_EXPOSED_CYC
-		/sys/devices/cpu/events/PM_LSU1_LDF
-		/sys/devices/cpu/events/PM_IC_WRITE_ALL
-		/sys/devices/cpu/events/PM_LSU0_SRQ_STFWD
-		/sys/devices/cpu/events/PM_PTEG_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_DATA_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_VSU1_SCAL_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_VSU0_8FLOP
-		/sys/devices/cpu/events/PM_POWER_EVENT1
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD_BAL
-		/sys/devices/cpu/events/PM_VSU1_2FLOP
-		/sys/devices/cpu/events/PM_LWSYNC_HELD
-		/sys/devices/cpu/events/PM_PTEG_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_INST_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_IERAT_XLATE_WR_16MPLUS
-		/sys/devices/cpu/events/PM_IC_REQ_ALL
-		/sys/devices/cpu/events/PM_DSLB_MISS
-		/sys/devices/cpu/events/PM_L3_MISS
-		/sys/devices/cpu/events/PM_LSU0_L1_PREF
-		/sys/devices/cpu/events/PM_VSU_SCALAR_SINGLE_ISSUED
-		/sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE
-		/sys/devices/cpu/events/PM_L2_INST
-		/sys/devices/cpu/events/PM_VSU0_FRSP
-		/sys/devices/cpu/events/PM_FLUSH_DISP
-		/sys/devices/cpu/events/PM_PTEG_FROM_L2MISS
-		/sys/devices/cpu/events/PM_VSU1_DQ_ISSUED
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DMEM
-		/sys/devices/cpu/events/PM_LSU_FLUSH_ULD
-		/sys/devices/cpu/events/PM_PTEG_FROM_LMEM
-		/sys/devices/cpu/events/PM_MRK_DERAT_MISS_16M
-		/sys/devices/cpu/events/PM_THRD_ALL_RUN_CYC
-		/sys/devices/cpu/events/PM_MEM0_PREFETCH_DISP
-		/sys/devices/cpu/events/PM_MRK_STALL_CMPLU_CYC_COUNT
-		/sys/devices/cpu/events/PM_DATA_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_VSU_FRSP
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_PMC1_OVERFLOW
-		/sys/devices/cpu/events/PM_VSU0_SINGLE
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L3MISS
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_VSU0_VECTOR_SP_ISSUED
-		/sys/devices/cpu/events/PM_VSU1_FEST
-		/sys/devices/cpu/events/PM_MRK_INST_DISP
-		/sys/devices/cpu/events/PM_VSU0_COMPLEX_ISSUED
-		/sys/devices/cpu/events/PM_LSU1_FLUSH_UST
-		/sys/devices/cpu/events/PM_FXU_IDLE
-		/sys/devices/cpu/events/PM_LSU0_FLUSH_ULD
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC
-		/sys/devices/cpu/events/PM_LSU1_REJECT_LMQ_FULL
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_INST_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_SHL_CREATED
-		/sys/devices/cpu/events/PM_L2_ST_HIT
-		/sys/devices/cpu/events/PM_DATA_FROM_DMEM
-		/sys/devices/cpu/events/PM_L3_LD_MISS
-		/sys/devices/cpu/events/PM_FXU1_BUSY_FXU0_IDLE
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD_RES
-		/sys/devices/cpu/events/PM_L2_SN_SX_I_DONE
-		/sys/devices/cpu/events/PM_STCX_CMPL
-		/sys/devices/cpu/events/PM_VSU0_2FLOP
-		/sys/devices/cpu/events/PM_L3_PREF_MISS
-		/sys/devices/cpu/events/PM_LSU_SRQ_SYNC_CYC
-		/sys/devices/cpu/events/PM_LSU_REJECT_ERAT_MISS
-		/sys/devices/cpu/events/PM_L1_ICACHE_MISS
-		/sys/devices/cpu/events/PM_LSU1_FLUSH_SRQ
-		/sys/devices/cpu/events/PM_LD_REF_L1_LSU0
-		/sys/devices/cpu/events/PM_VSU0_FEST
-		/sys/devices/cpu/events/PM_VSU_VECTOR_SINGLE_ISSUED
-		/sys/devices/cpu/events/PM_FREQ_UP
-		/sys/devices/cpu/events/PM_DATA_FROM_LMEM
-		/sys/devices/cpu/events/PM_LSU1_LDX
-		/sys/devices/cpu/events/PM_PMC3_OVERFLOW
-		/sys/devices/cpu/events/PM_MRK_BR_MPRED
-		/sys/devices/cpu/events/PM_SHL_MATCH
-		/sys/devices/cpu/events/PM_MRK_BR_TAKEN
-		/sys/devices/cpu/events/PM_ISLB_MISS
-		/sys/devices/cpu/events/PM_DISP_HELD_THERMAL
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_LSU1_SRQ_STFWD
-		/sys/devices/cpu/events/PM_PTEG_FROM_DMEM
-		/sys/devices/cpu/events/PM_VSU_2FLOP
-		/sys/devices/cpu/events/PM_GCT_FULL_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L3_CYC
-		/sys/devices/cpu/events/PM_LSU_SRQ_S0_ALLOC
-		/sys/devices/cpu/events/PM_MRK_DERAT_MISS_4K
-		/sys/devices/cpu/events/PM_BR_MPRED_TA
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L2MISS
-		/sys/devices/cpu/events/PM_DPU_HELD_POWER
-		/sys/devices/cpu/events/PM_MRK_VSU_FIN
-		/sys/devices/cpu/events/PM_LSU_SRQ_S0_VALID
-		/sys/devices/cpu/events/PM_GCT_EMPTY_CYC
-		/sys/devices/cpu/events/PM_IOPS_DISP
-		/sys/devices/cpu/events/PM_RUN_SPURR
-		/sys/devices/cpu/events/PM_PTEG_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_VSU0_1FLOP
-		/sys/devices/cpu/events/PM_SNOOP_TLBIE
-		/sys/devices/cpu/events/PM_DATA_FROM_L3MISS
-		/sys/devices/cpu/events/PM_VSU_SINGLE
-		/sys/devices/cpu/events/PM_DTLB_MISS_16G
-		/sys/devices/cpu/events/PM_FLUSH
-		/sys/devices/cpu/events/PM_L2_LD_HIT
-		/sys/devices/cpu/events/PM_NEST_PAIR2_AND
-		/sys/devices/cpu/events/PM_VSU1_1FLOP
-		/sys/devices/cpu/events/PM_IC_PREF_REQ
-		/sys/devices/cpu/events/PM_L3_LD_HIT
-		/sys/devices/cpu/events/PM_DISP_HELD
-		/sys/devices/cpu/events/PM_L2_LD
-		/sys/devices/cpu/events/PM_LSU_FLUSH_SRQ
-		/sys/devices/cpu/events/PM_BC_PLUS_8_CONV
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_MOD_CYC
-		/sys/devices/cpu/events/PM_L2_RCST_BUSY_RC_FULL
-		/sys/devices/cpu/events/PM_TB_BIT_TRANS
-		/sys/devices/cpu/events/PM_THERMAL_MAX
-		/sys/devices/cpu/events/PM_LSU1_FLUSH_ULD
-		/sys/devices/cpu/events/PM_LSU1_REJECT_LHS
-		/sys/devices/cpu/events/PM_LSU_LRQ_S0_ALLOC
-		/sys/devices/cpu/events/PM_L3_CO_L31
-		/sys/devices/cpu/events/PM_POWER_EVENT4
-		/sys/devices/cpu/events/PM_DATA_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_BR_UNCOND
-		/sys/devices/cpu/events/PM_LSU1_DC_PREF_STREAM_ALLOC
-		/sys/devices/cpu/events/PM_PMC4_REWIND
-		/sys/devices/cpu/events/PM_L2_RCLD_DISP
-		/sys/devices/cpu/events/PM_THRD_PRIO_2_3_CYC
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L2MISS
-		/sys/devices/cpu/events/PM_IC_DEMAND_L2_BHT_REDIRECT
-		/sys/devices/cpu/events/PM_DATA_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_IC_PREF_CANCEL_L2
-		/sys/devices/cpu/events/PM_MRK_FIN_STALL_CYC_COUNT
-		/sys/devices/cpu/events/PM_BR_PRED_CCACHE
-		/sys/devices/cpu/events/PM_GCT_UTIL_1_TO_2_SLOTS
-		/sys/devices/cpu/events/PM_MRK_ST_CMPL_INT
-		/sys/devices/cpu/events/PM_LSU_TWO_TABLEWALK_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L3MISS
-		/sys/devices/cpu/events/PM_LSU_SET_MPRED
-		/sys/devices/cpu/events/PM_FLUSH_DISP_TLBIE
-		/sys/devices/cpu/events/PM_VSU1_FCONV
-		/sys/devices/cpu/events/PM_DERAT_MISS_16G
-		/sys/devices/cpu/events/PM_INST_FROM_LMEM
-		/sys/devices/cpu/events/PM_IC_DEMAND_L2_BR_REDIRECT
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L2
-		/sys/devices/cpu/events/PM_PTEG_FROM_L2
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_SHR_CYC
-		/sys/devices/cpu/events/PM_MRK_DTLB_MISS_4K
-		/sys/devices/cpu/events/PM_VSU0_FPSCR
-		/sys/devices/cpu/events/PM_VSU1_VECT_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_MEM0_RQ_DISP
-		/sys/devices/cpu/events/PM_L2_LD_MISS
-		/sys/devices/cpu/events/PM_VMX_RESULT_SAT_1
-		/sys/devices/cpu/events/PM_L1_PREF
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_LMEM_CYC
-		/sys/devices/cpu/events/PM_GRP_IC_MISS_NONSPEC
-		/sys/devices/cpu/events/PM_PB_NODE_PUMP
-		/sys/devices/cpu/events/PM_SHL_MERGED
-		/sys/devices/cpu/events/PM_NEST_PAIR1_ADD
-		/sys/devices/cpu/events/PM_DATA_FROM_L3
-		/sys/devices/cpu/events/PM_LSU_FLUSH
-		/sys/devices/cpu/events/PM_LSU_SRQ_SYNC_COUNT
-		/sys/devices/cpu/events/PM_PMC2_OVERFLOW
-		/sys/devices/cpu/events/PM_LSU_LDF
-		/sys/devices/cpu/events/PM_POWER_EVENT3
-		/sys/devices/cpu/events/PM_DISP_WT
-		/sys/devices/cpu/events/PM_IC_BANK_CONFLICT
-		/sys/devices/cpu/events/PM_BR_MPRED_CR_TA
-		/sys/devices/cpu/events/PM_L2_INST_MISS
-		/sys/devices/cpu/events/PM_NEST_PAIR2_ADD
-		/sys/devices/cpu/events/PM_MRK_LSU_FLUSH
-		/sys/devices/cpu/events/PM_L2_LDST
-		/sys/devices/cpu/events/PM_INST_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_VSU0_FIN
-		/sys/devices/cpu/events/PM_VSU1_FCONV
-		/sys/devices/cpu/events/PM_INST_FROM_RMEM
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD_TLBIE
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DMEM_CYC
-		/sys/devices/cpu/events/PM_BR_PRED_CR
-		/sys/devices/cpu/events/PM_LSU_REJECT
-		/sys/devices/cpu/events/PM_GCT_UTIL_3_TO_6_SLOTS
-		/sys/devices/cpu/events/PM_CMPLU_STALL_END_GCT_NOSLOT
-		/sys/devices/cpu/events/PM_LSU0_REJECT_LMQ_FULL
-		/sys/devices/cpu/events/PM_VSU_FEST
-		/sys/devices/cpu/events/PM_NEST_PAIR0_AND
-		/sys/devices/cpu/events/PM_PTEG_FROM_L3
-		/sys/devices/cpu/events/PM_POWER_EVENT2
-		/sys/devices/cpu/events/PM_IC_PREF_CANCEL_PAGE
-		/sys/devices/cpu/events/PM_VSU0_FSQRT_FDIV
-		/sys/devices/cpu/events/PM_MRK_GRP_CMPL
-		/sys/devices/cpu/events/PM_VSU0_SCAL_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_GRP_DISP
-		/sys/devices/cpu/events/PM_LSU0_LDX
-		/sys/devices/cpu/events/PM_DATA_FROM_L2
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_VSU0_VECT_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_VSU1_2FLOP_DOUBLE
-		/sys/devices/cpu/events/PM_THRD_PRIO_6_7_CYC
-		/sys/devices/cpu/events/PM_BC_PLUS_8_RSLV_TAKEN
-		/sys/devices/cpu/events/PM_BR_MPRED_CR
-		/sys/devices/cpu/events/PM_L3_CO_MEM
-		/sys/devices/cpu/events/PM_DATA_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_LSU_SRQ_FULL_CYC
-		/sys/devices/cpu/events/PM_TABLEWALK_CYC
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_RMEM
-		/sys/devices/cpu/events/PM_LSU_SRQ_STFWD
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_RMEM
-		/sys/devices/cpu/events/PM_FXU0_FIN
-		/sys/devices/cpu/events/PM_LSU1_L1_SW_PREF
-		/sys/devices/cpu/events/PM_PTEG_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_PMC5_OVERFLOW
-		/sys/devices/cpu/events/PM_LD_REF_L1_LSU1
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_DATA_FROM_RMEM
-		/sys/devices/cpu/events/PM_VSU0_SCAL_SINGLE_ISSUED
-		/sys/devices/cpu/events/PM_BR_MPRED_LSTACK
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_MOD_CYC
-		/sys/devices/cpu/events/PM_LSU0_FLUSH_UST
-		/sys/devices/cpu/events/PM_LSU_NCST
-		/sys/devices/cpu/events/PM_BR_TAKEN
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_LMEM
-		/sys/devices/cpu/events/PM_DTLB_MISS_4K
-		/sys/devices/cpu/events/PM_PMC4_SAVED
-		/sys/devices/cpu/events/PM_VSU1_PERMUTE_ISSUED
-		/sys/devices/cpu/events/PM_SLB_MISS
-		/sys/devices/cpu/events/PM_LSU1_FLUSH_LRQ
-		/sys/devices/cpu/events/PM_DTLB_MISS
-		/sys/devices/cpu/events/PM_VSU1_FRSP
-		/sys/devices/cpu/events/PM_VSU_VECTOR_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_L2_CASTOUT_SHR
-		/sys/devices/cpu/events/PM_DATA_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_VSU1_STF
-		/sys/devices/cpu/events/PM_ST_FIN
-		/sys/devices/cpu/events/PM_PTEG_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_L2_LOC_GUESS_WRONG
-		/sys/devices/cpu/events/PM_MRK_STCX_FAIL
-		/sys/devices/cpu/events/PM_LSU0_REJECT_LHS
-		/sys/devices/cpu/events/PM_IC_PREF_CANCEL_HIT
-		/sys/devices/cpu/events/PM_L3_PREF_BUSY
-		/sys/devices/cpu/events/PM_MRK_BRU_FIN
-		/sys/devices/cpu/events/PM_LSU1_NCLD
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_LSU_NCLD
-		/sys/devices/cpu/events/PM_LSU_LDX
-		/sys/devices/cpu/events/PM_L2_LOC_GUESS_CORRECT
-		/sys/devices/cpu/events/PM_THRESH_TIMEO
-		/sys/devices/cpu/events/PM_L3_PREF_ST
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD_SYNC
-		/sys/devices/cpu/events/PM_VSU_SIMPLE_ISSUED
-		/sys/devices/cpu/events/PM_VSU1_SINGLE
-		/sys/devices/cpu/events/PM_DATA_TABLEWALK_CYC
-		/sys/devices/cpu/events/PM_L2_RC_ST_DONE
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L21_MOD
-		/sys/devices/cpu/events/PM_LARX_LSU1
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RMEM
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD
-		/sys/devices/cpu/events/PM_DERAT_MISS_4K
-		/sys/devices/cpu/events/PM_L2_RCLD_DISP_FAIL_ADDR
-		/sys/devices/cpu/events/PM_SEG_EXCEPTION
-		/sys/devices/cpu/events/PM_FLUSH_DISP_SB
-		/sys/devices/cpu/events/PM_L2_DC_INV
-		/sys/devices/cpu/events/PM_PTEG_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_DSEG
-		/sys/devices/cpu/events/PM_BR_PRED_LSTACK
-		/sys/devices/cpu/events/PM_VSU0_STF
-		/sys/devices/cpu/events/PM_LSU_FX_FIN
-		/sys/devices/cpu/events/PM_DERAT_MISS_16M
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_GCT_UTIL_11_PLUS_SLOTS
-		/sys/devices/cpu/events/PM_INST_FROM_L3
-		/sys/devices/cpu/events/PM_MRK_IFU_FIN
-		/sys/devices/cpu/events/PM_ITLB_MISS
-		/sys/devices/cpu/events/PM_VSU_STF
-		/sys/devices/cpu/events/PM_LSU_FLUSH_UST
-		/sys/devices/cpu/events/PM_L2_LDST_MISS
-		/sys/devices/cpu/events/PM_FXU1_FIN
-		/sys/devices/cpu/events/PM_SHL_DEALLOCATED
-		/sys/devices/cpu/events/PM_L2_SN_M_WR_DONE
-		/sys/devices/cpu/events/PM_LSU_REJECT_SET_MPRED
-		/sys/devices/cpu/events/PM_L3_PREF_LD
-		/sys/devices/cpu/events/PM_L2_SN_M_RD_DONE
-		/sys/devices/cpu/events/PM_MRK_DERAT_MISS_16G
-		/sys/devices/cpu/events/PM_VSU_FCONV
-		/sys/devices/cpu/events/PM_ANY_THRD_RUN_CYC
-		/sys/devices/cpu/events/PM_LSU_LMQ_FULL_CYC
-		/sys/devices/cpu/events/PM_MRK_LSU_REJECT_LHS
-		/sys/devices/cpu/events/PM_MRK_LD_MISS_L1_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L2_CYC
-		/sys/devices/cpu/events/PM_INST_IMC_MATCH_DISP
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RMEM_CYC
-		/sys/devices/cpu/events/PM_VSU0_SIMPLE_ISSUED
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_VSU_FMA_DOUBLE
-		/sys/devices/cpu/events/PM_VSU_4FLOP
-		/sys/devices/cpu/events/PM_VSU1_FIN
-		/sys/devices/cpu/events/PM_NEST_PAIR1_AND
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_RL2L3_MOD
-		/sys/devices/cpu/events/PM_PTEG_FROM_RMEM
-		/sys/devices/cpu/events/PM_LSU_LRQ_S0_VALID
-		/sys/devices/cpu/events/PM_LSU0_LDF
-		/sys/devices/cpu/events/PM_FLUSH_COMPLETION
-		/sys/devices/cpu/events/PM_ST_MISS_L1
-		/sys/devices/cpu/events/PM_L2_NODE_PUMP
-		/sys/devices/cpu/events/PM_INST_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_MRK_STALL_CMPLU_CYC
-		/sys/devices/cpu/events/PM_VSU1_DENORM
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_SHR_CYC
-		/sys/devices/cpu/events/PM_NEST_PAIR0_ADD
-		/sys/devices/cpu/events/PM_INST_FROM_L3MISS
-		/sys/devices/cpu/events/PM_EE_OFF_EXT_INT
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_DMEM
-		/sys/devices/cpu/events/PM_INST_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_PMC6_OVERFLOW
-		/sys/devices/cpu/events/PM_VSU_2FLOP_DOUBLE
-		/sys/devices/cpu/events/PM_TLB_MISS
-		/sys/devices/cpu/events/PM_FXU_BUSY
-		/sys/devices/cpu/events/PM_L2_RCLD_DISP_FAIL_OTHER
-		/sys/devices/cpu/events/PM_LSU_REJECT_LMQ_FULL
-		/sys/devices/cpu/events/PM_IC_RELOAD_SHR
-		/sys/devices/cpu/events/PM_GRP_MRK
-		/sys/devices/cpu/events/PM_MRK_ST_NEST
-		/sys/devices/cpu/events/PM_VSU1_FSQRT_FDIV
-		/sys/devices/cpu/events/PM_LSU0_FLUSH_LRQ
-		/sys/devices/cpu/events/PM_LARX_LSU0
-		/sys/devices/cpu/events/PM_IBUF_FULL_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_SHR_CYC
-		/sys/devices/cpu/events/PM_LSU_DC_PREF_STREAM_ALLOC
-		/sys/devices/cpu/events/PM_GRP_MRK_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_SHR_CYC
-		/sys/devices/cpu/events/PM_L2_GLOB_GUESS_CORRECT
-		/sys/devices/cpu/events/PM_LSU_REJECT_LHS
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_LMEM
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L3
-		/sys/devices/cpu/events/PM_FREQ_DOWN
-		/sys/devices/cpu/events/PM_PB_RETRY_NODE_PUMP
-		/sys/devices/cpu/events/PM_INST_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_MRK_INST_ISSUED
-		/sys/devices/cpu/events/PM_PTEG_FROM_L3MISS
-		/sys/devices/cpu/events/PM_RUN_PURR
-		/sys/devices/cpu/events/PM_MRK_GRP_IC_MISS
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L3
-		/sys/devices/cpu/events/PM_PTEG_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_LSU_FLUSH_LRQ
-		/sys/devices/cpu/events/PM_MRK_DERAT_MISS_64K
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_DL2L3_MOD
-		/sys/devices/cpu/events/PM_L2_ST_MISS
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_LWSYNC
-		/sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE
-		/sys/devices/cpu/events/PM_MRK_LSU_FLUSH_LRQ
-		/sys/devices/cpu/events/PM_INST_IMC_MATCH_CMPL
-		/sys/devices/cpu/events/PM_NEST_PAIR3_AND
-		/sys/devices/cpu/events/PM_PB_RETRY_SYS_PUMP
-		/sys/devices/cpu/events/PM_MRK_INST_FIN
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_INST_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_MRK_DTLB_MISS_64K
-		/sys/devices/cpu/events/PM_LSU_FIN
-		/sys/devices/cpu/events/PM_MRK_LSU_REJECT
-		/sys/devices/cpu/events/PM_L2_CO_FAIL_BUSY
-		/sys/devices/cpu/events/PM_MEM0_WQ_DISP
-		/sys/devices/cpu/events/PM_DATA_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_THERMAL_WARN
-		/sys/devices/cpu/events/PM_VSU0_4FLOP
-		/sys/devices/cpu/events/PM_BR_MPRED_CCACHE
-		/sys/devices/cpu/events/PM_L1_DEMAND_WRITE
-		/sys/devices/cpu/events/PM_FLUSH_BR_MPRED
-		/sys/devices/cpu/events/PM_MRK_DTLB_MISS_16G
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_DMEM
-		/sys/devices/cpu/events/PM_L2_RCST_DISP
-		/sys/devices/cpu/events/PM_LSU_PARTIAL_CDF
-		/sys/devices/cpu/events/PM_DISP_CLB_HELD_SB
-		/sys/devices/cpu/events/PM_VSU0_FMA_DOUBLE
-		/sys/devices/cpu/events/PM_FXU0_BUSY_FXU1_IDLE
-		/sys/devices/cpu/events/PM_IC_DEMAND_CYC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_MRK_LSU_FLUSH_UST
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L3MISS
-		/sys/devices/cpu/events/PM_VSU_DENORM
-		/sys/devices/cpu/events/PM_MRK_LSU_PARTIAL_CDF
-		/sys/devices/cpu/events/PM_INST_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_IC_PREF_WRITE
-		/sys/devices/cpu/events/PM_BR_PRED
-		/sys/devices/cpu/events/PM_INST_FROM_DMEM
-		/sys/devices/cpu/events/PM_IC_PREF_CANCEL_ALL
-		/sys/devices/cpu/events/PM_LSU_DC_PREF_STREAM_CONFIRM
-		/sys/devices/cpu/events/PM_MRK_LSU_FLUSH_SRQ
-		/sys/devices/cpu/events/PM_MRK_FIN_STALL_CYC
-		/sys/devices/cpu/events/PM_L2_RCST_DISP_FAIL_OTHER
-		/sys/devices/cpu/events/PM_VSU1_DD_ISSUED
-		/sys/devices/cpu/events/PM_PTEG_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_DATA_FROM_L21_SHR
-		/sys/devices/cpu/events/PM_LSU0_NCLD
-		/sys/devices/cpu/events/PM_VSU1_4FLOP
-		/sys/devices/cpu/events/PM_VSU1_8FLOP
-		/sys/devices/cpu/events/PM_VSU_8FLOP
-		/sys/devices/cpu/events/PM_LSU_LMQ_SRQ_EMPTY_CYC
-		/sys/devices/cpu/events/PM_DTLB_MISS_64K
-		/sys/devices/cpu/events/PM_THRD_CONC_RUN_INST
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L2
-		/sys/devices/cpu/events/PM_PB_SYS_PUMP
-		/sys/devices/cpu/events/PM_VSU_FIN
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_THRD_PRIO_0_1_CYC
-		/sys/devices/cpu/events/PM_DERAT_MISS_64K
-		/sys/devices/cpu/events/PM_PMC2_REWIND
-		/sys/devices/cpu/events/PM_INST_FROM_L2
-		/sys/devices/cpu/events/PM_GRP_BR_MPRED_NONSPEC
-		/sys/devices/cpu/events/PM_INST_DISP
-		/sys/devices/cpu/events/PM_MEM0_RD_CANCEL_TOTAL
-		/sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_CONFIRM
-		/sys/devices/cpu/events/PM_L1_DCACHE_RELOAD_VALID
-		/sys/devices/cpu/events/PM_VSU_SCALAR_DOUBLE_ISSUED
-		/sys/devices/cpu/events/PM_L3_PREF_HIT
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L31_MOD
-		/sys/devices/cpu/events/PM_MRK_FXU_FIN
-		/sys/devices/cpu/events/PM_PMC4_OVERFLOW
-		/sys/devices/cpu/events/PM_MRK_PTEG_FROM_L3
-		/sys/devices/cpu/events/PM_LSU0_LMQ_LHR_MERGE
-		/sys/devices/cpu/events/PM_BTAC_HIT
-		/sys/devices/cpu/events/PM_L3_RD_BUSY
-		/sys/devices/cpu/events/PM_LSU0_L1_SW_PREF
-		/sys/devices/cpu/events/PM_INST_FROM_L2MISS
-		/sys/devices/cpu/events/PM_LSU0_DC_PREF_STREAM_ALLOC
-		/sys/devices/cpu/events/PM_L2_ST
-		/sys/devices/cpu/events/PM_VSU0_DENORM
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_BR_PRED_CR_TA
-		/sys/devices/cpu/events/PM_VSU0_FCONV
-		/sys/devices/cpu/events/PM_MRK_LSU_FLUSH_ULD
-		/sys/devices/cpu/events/PM_BTAC_MISS
-		/sys/devices/cpu/events/PM_MRK_LD_MISS_EXPOSED_CYC_COUNT
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L2
-		/sys/devices/cpu/events/PM_LSU_DCACHE_RELOAD_VALID
-		/sys/devices/cpu/events/PM_VSU_FMA
-		/sys/devices/cpu/events/PM_LSU0_FLUSH_SRQ
-		/sys/devices/cpu/events/PM_LSU1_L1_PREF
-		/sys/devices/cpu/events/PM_IOPS_CMPL
-		/sys/devices/cpu/events/PM_L2_SYS_PUMP
-		/sys/devices/cpu/events/PM_L2_RCLD_BUSY_RC_FULL
-		/sys/devices/cpu/events/PM_LSU_LMQ_S0_ALLOC
-		/sys/devices/cpu/events/PM_FLUSH_DISP_SYNC
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_DL2L3_MOD_CYC
-		/sys/devices/cpu/events/PM_L2_IC_INV
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L21_MOD_CYC
-		/sys/devices/cpu/events/PM_L3_PREF_LDST
-		/sys/devices/cpu/events/PM_LSU_SRQ_EMPTY_CYC
-		/sys/devices/cpu/events/PM_LSU_LMQ_S0_VALID
-		/sys/devices/cpu/events/PM_FLUSH_PARTIAL
-		/sys/devices/cpu/events/PM_VSU1_FMA_DOUBLE
-		/sys/devices/cpu/events/PM_1PLUS_PPC_DISP
-		/sys/devices/cpu/events/PM_DATA_FROM_L2MISS
-		/sys/devices/cpu/events/PM_SUSPENDED
-		/sys/devices/cpu/events/PM_VSU0_FMA
-		/sys/devices/cpu/events/PM_STCX_FAIL
-		/sys/devices/cpu/events/PM_VSU0_FSQRT_FDIV_DOUBLE
-		/sys/devices/cpu/events/PM_DC_PREF_DST
-		/sys/devices/cpu/events/PM_VSU1_SCAL_SINGLE_ISSUED
-		/sys/devices/cpu/events/PM_L3_HIT
-		/sys/devices/cpu/events/PM_L2_GLOB_GUESS_WRONG
-		/sys/devices/cpu/events/PM_MRK_DFU_FIN
-		/sys/devices/cpu/events/PM_INST_FROM_L1
-		/sys/devices/cpu/events/PM_IC_DEMAND_REQ
-		/sys/devices/cpu/events/PM_VSU1_FSQRT_FDIV_DOUBLE
-		/sys/devices/cpu/events/PM_VSU1_FMA
-		/sys/devices/cpu/events/PM_MRK_LD_MISS_L1
-		/sys/devices/cpu/events/PM_VSU0_2FLOP_DOUBLE
-		/sys/devices/cpu/events/PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_L31_SHR
-		/sys/devices/cpu/events/PM_MRK_LSU_REJECT_ERAT_MISS
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_L2MISS
-		/sys/devices/cpu/events/PM_DATA_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_INST_FROM_PREF
-		/sys/devices/cpu/events/PM_VSU1_SQ
-		/sys/devices/cpu/events/PM_L2_LD_DISP
-		/sys/devices/cpu/events/PM_L2_DISP_ALL
-		/sys/devices/cpu/events/PM_THRD_GRP_CMPL_BOTH_CYC
-		/sys/devices/cpu/events/PM_VSU_FSQRT_FDIV_DOUBLE
-		/sys/devices/cpu/events/PM_INST_PTEG_FROM_DL2L3_SHR
-		/sys/devices/cpu/events/PM_VSU_1FLOP
-		/sys/devices/cpu/events/PM_HV_CYC
-		/sys/devices/cpu/events/PM_MRK_LSU_FIN
-		/sys/devices/cpu/events/PM_MRK_DATA_FROM_RL2L3_SHR
-		/sys/devices/cpu/events/PM_DTLB_MISS_16M
-		/sys/devices/cpu/events/PM_LSU1_LMQ_LHR_MERGE
-		/sys/devices/cpu/events/PM_IFU_FIN
-		/sys/devices/cpu/events/PM_1THRD_CON_RUN_INSTR
-		/sys/devices/cpu/events/PM_CMPLU_STALL_COUNT
-		/sys/devices/cpu/events/PM_MEM0_PB_RD_CL
-		/sys/devices/cpu/events/PM_THRD_1_RUN_CYC
-		/sys/devices/cpu/events/PM_THRD_2_CONC_RUN_INSTR
-		/sys/devices/cpu/events/PM_THRD_2_RUN_CYC
-		/sys/devices/cpu/events/PM_THRD_3_CONC_RUN_INST
-		/sys/devices/cpu/events/PM_THRD_3_RUN_CYC
-		/sys/devices/cpu/events/PM_THRD_4_CONC_RUN_INST
-		/sys/devices/cpu/events/PM_THRD_4_RUN_CYC
+What: /sys/bus/event_source/devices/<pmu>/events/<event>
+Date: 2014/02/24
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Per-pmu performance monitoring events specific to the running system
 
-Date:		2013/01/08
+		Each file (except for some of those with a '.' in them, '.unit'
+		and '.scale') in the 'events' directory describes a single
+		performance monitoring event supported by the <pmu>. The name
+		of the file is the name of the event.
+
+		File contents:
+
+			<term>[=<value>][,<term>[=<value>]]...
+
+		Where <term> is one of the terms listed under
+		/sys/bus/event_source/devices/<pmu>/format/ and <value> is
+		a number is base-16 format with a '0x' prefix (lowercase only).
+		If a <term> is specified alone (without an assigned value), it
+		is implied that 0x1 is assigned to that <term>.
 
+		Examples (each of these lines would be in a seperate file):
+
+			event=0x2abc
+			event=0x423,inv,cmask=0x3
+			domain=0x1,offset=0x8,starting_index=0xffff
+
+		Each of the assignments indicates a value to be assigned to a
+		particular set of bits (as defined by the format file
+		corresponding to the <term>) in the perf_event structure passed
+		to the perf_open syscall.
+
+What: /sys/bus/event_source/devices/<pmu>/events/<event>.unit
+Date: 2014/02/24
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
-		Linux Powerpc mailing list <linuxppc-dev@ozlabs.org>
+Description:	Perf event units
 
-Description:	POWER-systems specific performance monitoring events
+		A string specifying the English plural numerical unit that <event>
+		(once multiplied by <event>.scale) represents.
 
-		A collection of performance monitoring events that may be
-		supported by the POWER CPU. These events can be monitored
-		using the 'perf(1)' tool.
+		Example:
 
-		These events may not be supported by other CPUs.
+			Joules
 
-		The contents of each file would look like:
+What: /sys/bus/event_source/devices/<pmu>/events/<event>.scale
+Date: 2014/02/24
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Perf event scaling factors
 
-			event=0xNNNN
+		A string representing a floating point value expressed in
+		scientific notation to be multiplied by the event count
+		recieved from the kernel to match the unit specified in the
+		<event>.unit file.
 
-		where 'N' is a hex digit and the number '0xNNNN' shows the
-		"raw code" for the perf event identified by the file's
-		"basename".
+		Example:
+
+			2.3283064365386962890625e-10
 
-		Further, multiple terms like 'event=0xNNNN' can be specified
-		and separated with comma. All available terms are defined in
-		the /sys/bus/event_source/devices/<dev>/format file.
+		This is provided to avoid performing floating point arithmetic
+		in the kernel.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index b3b8abae62b8..e463caa3eb49 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -196,10 +196,10 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
   - period being the hist entry period value
 
-  - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+  - WEIGHT-A/WEIGHT-B being user supplied weights in the the '-c' option
     behind ':' separator like '-c wdiff:1,2'.
-    - WIEGHT-A being the weight of the data file
-    - WIEGHT-B being the weight of the baseline data file
+    - WEIGHT-A being the weight of the data file
+    - WEIGHT-B being the weight of the baseline data file
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6e689dc89a2f..6252e776009c 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -100,7 +100,7 @@ OPTIONS
 STAT REPORT OPTIONS
 -------------------
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 --event=<value>::
        event to be analyzed. Possible values: vmexit, mmio (x86 only),
@@ -134,7 +134,7 @@ STAT LIVE OPTIONS
     Analyze events only for given process ID(s) (comma separated list).
 
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 
 --event=<value>::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 6fce6a622206..cbb4f743d921 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -19,7 +19,7 @@ various perf commands with the -e option.
 EVENT MODIFIERS
 ---------------
 
-Events can optionally have a modifer by appending a colon and one or
+Events can optionally have a modifier by appending a colon and one or
 more modifiers. Modifiers allow the user to restrict the events to be
 counted. The following modifiers exist:
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d460049cae8e..398f8d53bd6d 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -146,7 +146,7 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
 -N::
 --no-buildid-cache::
-Do not update the builid cache. This saves some overhead in situations
+Do not update the buildid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
 is sufficient.
 
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index d00bef231340..dfbb506d2c34 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -181,8 +181,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name
-  symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name
+  flag_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the flag field $field_name of event $event_name
+  symbol_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the symbolic field $field_name of event $event_name
 
 Perf::Trace::Context Module
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 9f1f054b8432..54acba221558 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -263,7 +263,7 @@ and having the counts we've tallied as values.
 
 The print_syscall_totals() function iterates over the entries in the
 dictionary and displays a line for each entry containing the syscall
-name (the dictonary keys contain the syscall ids, which are passed to
+name (the dictionary keys contain the syscall ids, which are passed to
 the Util function syscall_name(), which translates the raw syscall
 numbers to the corresponding syscall name strings).  The output is
 displayed after all the events in the trace have been processed, by
@@ -576,8 +576,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
-  symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
+  flag_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the flag field field_name of event event_name
+  symbol_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the symbolic field field_name of event event_name
 
 The *autodict* function returns a special kind of Python
 dictionary that implements Perl's 'autovivifying' hashes in Python
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 05f9a0a6784c..5a0160d359a1 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -140,7 +140,7 @@ OPTIONS
     
 		"Overriding previous field request for all events."
     
-	Alternativey, consider the order:
+	Alternatively, consider the order:
     
 		-f comm,tid,time,ip,sym -f trace:
     
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index d1d3e5121f89..31a5c3ea7f74 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -25,7 +25,7 @@ OPTIONS
 -------
 -s::
 --skip::
-	Tests to skip (comma separater numeric list).
+	Tests to skip (comma separated numeric list).
 
 -v::
 --verbose::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 02aac831bdd9..7e1b1f2bb83c 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -20,7 +20,7 @@ scheduling events, etc.
 This is a live mode tool in addition to working with perf.data files like
 the other perf tools. Files can be generated using the 'perf record' command
 but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
-Alernatively, the 'perf trace record' can be used as a shortcut to
+Alternatively, 'perf trace record' can be used as a shortcut to
 automatically include the raw_syscalls events when writing events to a file.
 
 The following options apply to perf trace; options to perf trace record are
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 460a4ce9c044..b65eb0507b38 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -376,7 +376,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 					  struct perf_sample *sample)
 {
 	/* Only kvm_entry records vcpu id. */
-	if (!thread->priv && kvm_entry_event(evsel)) {
+	if (!thread__priv(thread) && kvm_entry_event(evsel)) {
 		struct vcpu_event_record *vcpu_record;
 
 		vcpu_record = zalloc(sizeof(*vcpu_record));
@@ -386,10 +386,10 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 		}
 
 		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
-		thread->priv = vcpu_record;
+		thread__set_priv(thread, vcpu_record);
 	}
 
-	return thread->priv;
+	return thread__priv(thread);
 }
 
 static bool handle_kvm_event(struct perf_kvm_stat *kvm,
@@ -1358,6 +1358,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	}
 	kvm->session->evlist = kvm->evlist;
 	perf_session__set_id_hdr_size(kvm->session);
+	ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
 	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
 				    kvm->evlist->threads, false);
 	err = kvm_live_open_events(kvm);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2cfc4b93991f..140a6cd88351 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -257,6 +257,13 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
+		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
+		    (sample_type & PERF_SAMPLE_STACK_USER))
+			callchain_param.record_mode = CALLCHAIN_DWARF;
+		else
+			callchain_param.record_mode = CALLCHAIN_FP;
+	}
 	return 0;
 }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 09bcf2393910..fb126459b134 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1189,13 +1189,13 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 	if (thread == NULL)
 		goto fail;
 
-	if (thread->priv == NULL)
-		thread->priv = thread_trace__new();
+	if (thread__priv(thread) == NULL)
+		thread__set_priv(thread, thread_trace__new());
 		
-	if (thread->priv == NULL)
+	if (thread__priv(thread) == NULL)
 		goto fail;
 
-	ttrace = thread->priv;
+	ttrace = thread__priv(thread);
 	++ttrace->nr_events;
 
 	return ttrace;
@@ -1248,7 +1248,7 @@ struct trace {
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
 {
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 
 	if (fd > ttrace->paths.max) {
 		char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
@@ -1301,7 +1301,7 @@ static int thread__read_fd_path(struct thread *thread, int fd)
 static const char *thread__fd_path(struct thread *thread, int fd,
 				   struct trace *trace)
 {
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 
 	if (ttrace == NULL)
 		return NULL;
@@ -1338,7 +1338,7 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 {
 	int fd = arg->val;
 	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
-	struct thread_trace *ttrace = arg->thread->priv;
+	struct thread_trace *ttrace = thread__priv(arg->thread);
 
 	if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
 		zfree(&ttrace->paths.table[fd]);
@@ -2381,7 +2381,7 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	FILE *fp = data->fp;
 	size_t printed = data->printed;
 	struct trace *trace = data->trace;
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 	double ratio;
 
 	if (ttrace == NULL)
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 96adb730b744..fc25e57f4a5d 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -9,6 +9,7 @@
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
+#include "callchain.h"
 
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
@@ -120,6 +121,8 @@ int test__dwarf_unwind(void)
 		return -1;
 	}
 
+	callchain_param.record_mode = CALLCHAIN_DWARF;
+
 	if (init_live_machine(machine)) {
 		pr_err("Could not init machine\n");
 		goto out;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 5941927a4b7f..7f2f51f93619 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -457,6 +457,36 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist)
 	return 0;
 }
 
+
+static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	/* pmu-event:u */
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	/* cpu/pmu-event/u*/
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
 static int test__checkterms_simple(struct list_head *terms)
 {
 	struct parse_events_term *term;
@@ -1554,6 +1584,12 @@ static int test_pmu_events(void)
 		e.check = test__checkevent_pmu_events;
 
 		ret = test_event(&e);
+		if (ret)
+			break;
+		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		e.name  = name;
+		e.check = test__checkevent_pmu_events_mix;
+		ret = test_event(&e);
 #undef MAX_NAME
 	}
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 68eab9ea1634..cfb976b3de3a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -35,7 +35,9 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size);
+static int hists__browser_title(struct hists *hists,
+				struct hist_browser_timer *hbt,
+				char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -390,7 +392,7 @@ static int hist_browser__run(struct hist_browser *browser,
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hists__browser_title(browser->hists, title, sizeof(title));
+	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title,
 			     "Press '?' for help on key bindings") < 0)
@@ -417,7 +419,8 @@ static int hist_browser__run(struct hist_browser *browser,
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists, title, sizeof(title));
+			hists__browser_title(browser->hists,
+					     hbt, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -1204,7 +1207,15 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size)
+/* Check whether the browser is for 'top' or 'report' */
+static inline bool is_report_browser(void *timer)
+{
+	return timer == NULL;
+}
+
+static int hists__browser_title(struct hists *hists,
+				struct hist_browser_timer *hbt,
+				char *bf, size_t size)
 {
 	char unit;
 	int printed;
@@ -1258,6 +1269,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
+	if (!is_report_browser(hbt)) {
+		struct perf_top *top = hbt->arg;
+
+		if (top->zero)
+			printed += scnprintf(bf + printed, size - printed, " [z]");
+	}
+
 	return printed;
 }
 
@@ -1269,12 +1287,6 @@ static inline void free_popup_options(char **options, int n)
 		zfree(&options[i]);
 }
 
-/* Check whether the browser is for 'top' or 'report' */
-static inline bool is_report_browser(void *timer)
-{
-	return timer == NULL;
-}
-
 /*
  * Only runtime switching of perf data file will make "input_name" point
  * to a malloced buffer. So add "is_input_name_malloced" flag to decide
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b4b54d84e9b0..3c9e77d6b4c2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1003,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 
 out_delete_threads:
 	thread_map__delete(evlist->threads);
+	evlist->threads = NULL;
 	return -1;
 }
 
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 97a800738226..6f19c548ecc0 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,4 +1,3 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
-int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 706ce1a66169..fd4be94125fb 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -1,5 +1,6 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
 #include "ordered-events.h"
 #include "evlist.h"
 #include "session.h"
@@ -57,11 +58,45 @@ static void queue_event(struct ordered_events *oe, struct ordered_event *new)
 	}
 }
 
+static union perf_event *__dup_event(struct ordered_events *oe,
+				     union perf_event *event)
+{
+	union perf_event *new_event = NULL;
+
+	if (oe->cur_alloc_size < oe->max_alloc_size) {
+		new_event = memdup(event, event->header.size);
+		if (new_event)
+			oe->cur_alloc_size += event->header.size;
+	}
+
+	return new_event;
+}
+
+static union perf_event *dup_event(struct ordered_events *oe,
+				   union perf_event *event)
+{
+	return oe->copy_on_queue ? __dup_event(oe, event) : event;
+}
+
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue) {
+		oe->cur_alloc_size -= event->header.size;
+		free(event);
+	}
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
-static struct ordered_event *alloc_event(struct ordered_events *oe)
+static struct ordered_event *alloc_event(struct ordered_events *oe,
+					 union perf_event *event)
 {
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
+	union perf_event *new_event;
+
+	new_event = dup_event(oe, event);
+	if (!new_event)
+		return NULL;
 
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
@@ -74,8 +109,10 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
 
 		oe->buffer = malloc(size);
-		if (!oe->buffer)
+		if (!oe->buffer) {
+			free_dup_event(oe, new_event);
 			return NULL;
+		}
 
 		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
 		   oe->cur_alloc_size, size, oe->max_alloc_size);
@@ -90,15 +127,17 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
 	}
 
+	new->event = new_event;
 	return new;
 }
 
 struct ordered_event *
-ordered_events__new(struct ordered_events *oe, u64 timestamp)
+ordered_events__new(struct ordered_events *oe, u64 timestamp,
+		    union perf_event *event)
 {
 	struct ordered_event *new;
 
-	new = alloc_event(oe);
+	new = alloc_event(oe, event);
 	if (new) {
 		new->timestamp = timestamp;
 		queue_event(oe, new);
@@ -111,6 +150,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 {
 	list_move(&event->list, &oe->cache);
 	oe->nr_events--;
+	free_dup_event(oe, event->event);
 }
 
 static int __ordered_events__flush(struct perf_session *s,
@@ -240,6 +280,7 @@ void ordered_events__free(struct ordered_events *oe)
 
 		event = list_entry(oe->to_free.next, struct ordered_event, list);
 		list_del(&event->list);
+		free_dup_event(oe, event->event);
 		free(event);
 	}
 }
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 3b2f20542a01..7b8f9b011f38 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -34,9 +34,11 @@ struct ordered_events {
 	int			buffer_idx;
 	unsigned int		nr_events;
 	enum oe_flush		last_flush_type;
+	bool                    copy_on_queue;
 };
 
-struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp,
+					  union perf_event *event);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 			  enum oe_flush how);
@@ -48,4 +50,10 @@ void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
 {
 	oe->max_alloc_size = size;
 }
+
+static inline
+void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy)
+{
+	oe->copy_on_queue = copy;
+}
 #endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d76aa30cb1fb..c659a3ca1283 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,7 +6,7 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "linux/string.h"
+#include "string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -30,6 +30,15 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
+static struct perf_pmu_event_symbol *perf_pmu_events_list;
+/*
+ * The variable indicates the number of supported pmu event symbols.
+ * 0 means not initialized and ready to init
+ * -1 means failed to init, don't try anymore
+ * >0 is the number of supported pmu event symbols
+ */
+static int perf_pmu_events_list_num;
+
 static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
@@ -863,30 +872,111 @@ int parse_events_name(struct list_head *list, char *name)
 	return 0;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token);
+static int
+comp_pmu(const void *p1, const void *p2)
+{
+	struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1;
+	struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2;
 
-static int parse_events_fixup(int ret, const char *str, void *data,
-			      int start_token)
+	return strcmp(pmu1->symbol, pmu2->symbol);
+}
+
+static void perf_pmu__parse_cleanup(void)
 {
-	char *o = strdup(str);
-	char *s = NULL;
-	char *t = o;
-	char *p;
+	if (perf_pmu_events_list_num > 0) {
+		struct perf_pmu_event_symbol *p;
+		int i;
+
+		for (i = 0; i < perf_pmu_events_list_num; i++) {
+			p = perf_pmu_events_list + i;
+			free(p->symbol);
+		}
+		free(perf_pmu_events_list);
+		perf_pmu_events_list = NULL;
+		perf_pmu_events_list_num = 0;
+	}
+}
+
+#define SET_SYMBOL(str, stype)		\
+do {					\
+	p->symbol = str;		\
+	if (!p->symbol)			\
+		goto err;		\
+	p->type = stype;		\
+} while (0)
+
+/*
+ * Read the pmu events list from sysfs
+ * Save it into perf_pmu_events_list
+ */
+static void perf_pmu__parse_init(void)
+{
+
+	struct perf_pmu *pmu = NULL;
+	struct perf_pmu_alias *alias;
 	int len = 0;
 
-	if (!o)
-		return ret;
-	while ((p = strsep(&t, ",")) != NULL) {
-		if (s)
-			str_append(&s, &len, ",");
-		str_append(&s, &len, "cpu/");
-		str_append(&s, &len, p);
-		str_append(&s, &len, "/");
+	pmu = perf_pmu__find("cpu");
+	if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+		perf_pmu_events_list_num = -1;
+		return;
 	}
-	free(o);
-	if (!s)
-		return -ENOMEM;
-	return parse_events__scanner(s, data, start_token);
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (strchr(alias->name, '-'))
+			len++;
+		len++;
+	}
+	perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
+	if (!perf_pmu_events_list)
+		return;
+	perf_pmu_events_list_num = len;
+
+	len = 0;
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+		char *tmp = strchr(alias->name, '-');
+
+		if (tmp != NULL) {
+			SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+					PMU_EVENT_SYMBOL_PREFIX);
+			p++;
+			SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+			len += 2;
+		} else {
+			SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+			len++;
+		}
+	}
+	qsort(perf_pmu_events_list, len,
+		sizeof(struct perf_pmu_event_symbol), comp_pmu);
+
+	return;
+err:
+	perf_pmu__parse_cleanup();
+}
+
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name)
+{
+	struct perf_pmu_event_symbol p, *r;
+
+	/* scan kernel pmu events from sysfs if needed */
+	if (perf_pmu_events_list_num == 0)
+		perf_pmu__parse_init();
+	/*
+	 * name "cpu" could be prefix of cpu-cycles or cpu// events.
+	 * cpu-cycles has been handled by hardcode.
+	 * So it must be cpu// events, not kernel pmu event.
+	 */
+	if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu"))
+		return PMU_EVENT_SYMBOL_ERR;
+
+	p.symbol = strdup(name);
+	r = bsearch(&p, perf_pmu_events_list,
+			(size_t) perf_pmu_events_list_num,
+			sizeof(struct perf_pmu_event_symbol), comp_pmu);
+	free(p.symbol);
+	return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
 static int parse_events__scanner(const char *str, void *data, int start_token)
@@ -909,8 +999,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 	parse_events__flush_buffer(buffer, scanner);
 	parse_events__delete_buffer(buffer, scanner);
 	parse_events_lex_destroy(scanner);
-	if (ret && !strchr(str, '/'))
-		ret = parse_events_fixup(ret, str, data, start_token);
 	return ret;
 }
 
@@ -945,6 +1033,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	int ret;
 
 	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+	perf_pmu__parse_cleanup();
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index df094b4ed5ed..db2cf78ff0f3 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum perf_pmu_event_symbol_type {
+	PMU_EVENT_SYMBOL_ERR,		/* not a PMU EVENT */
+	PMU_EVENT_SYMBOL,		/* normal style PMU event */
+	PMU_EVENT_SYMBOL_PREFIX,	/* prefix of pre-suf style event */
+	PMU_EVENT_SYMBOL_SUFFIX,	/* suffix of pre-suf style event */
+};
+
+struct perf_pmu_event_symbol {
+	char	*symbol;
+	enum perf_pmu_event_symbol_type	type;
+};
+
 enum {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
@@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type);
 int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 343299575b30..906630bbf8eb 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+static int pmu_str_check(yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	yylval->str = strdup(text);
+	switch (perf_pmu__parse_check(text)) {
+		case PMU_EVENT_SYMBOL_PREFIX:
+			return PE_PMU_EVENT_PRE;
+		case PMU_EVENT_SYMBOL_SUFFIX:
+			return PE_PMU_EVENT_SUF;
+		case PMU_EVENT_SYMBOL:
+			return PE_KERNEL_PMU_EVENT;
+		default:
+			return PE_NAME;
+	}
+}
+
 static int sym(yyscan_t scanner, int type, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -178,6 +196,16 @@ alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 
+	/*
+	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
+	 * Because the prefix cycles is mixed up with cpu-cycles.
+	 * loads and stores are mixed up with cache event
+	 */
+cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
 LLC|L2					|
@@ -199,7 +227,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{name}			{ return str(yyscanner, PE_NAME); }
+{name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 55fab6ad609a..93c4c9fbc922 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -47,6 +47,7 @@ static inc_group_count(struct list_head *list,
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
+%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -58,6 +59,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
+%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
 %type <term> event_term
@@ -220,6 +222,44 @@ PE_NAME '/' '/'
 	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
 	$$ = list;
 }
+|
+PE_KERNEL_PMU_EVENT sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
+|
+PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+	char pmu_name[128];
+	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					&pmu_name, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 93a41ca96b8e..e243ad962a4d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -12,16 +12,6 @@
 #include "parse-events.h"
 #include "cpumap.h"
 
-#define UNIT_MAX_LEN	31 /* max length for event unit name */
-
-struct perf_pmu_alias {
-	char *name;
-	struct list_head terms; /* HEAD struct parse_events_term -> list */
-	struct list_head list;  /* ELEM */
-	char unit[UNIT_MAX_LEN+1];
-	double scale;
-};
-
 struct perf_pmu_format {
 	char *name;
 	int value;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe90a012c003..fe9dfbee8eed 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -30,6 +30,16 @@ struct perf_pmu_info {
 	double scale;
 };
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+struct perf_pmu_alias {
+	char *name;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
+};
+
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 896bac73ea08..6702ac28754b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -532,17 +532,16 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 			return -EINVAL;
 	}
 
-	new = ordered_events__new(oe, timestamp);
+	new = ordered_events__new(oe, timestamp, event);
 	if (!new) {
 		ordered_events__flush(s, tool, OE_FLUSH__HALF);
-		new = ordered_events__new(oe, timestamp);
+		new = ordered_events__new(oe, timestamp, event);
 	}
 
 	if (!new)
 		return -ENOMEM;
 
 	new->file_offset = file_offset;
-	new->event = event;
 	return 0;
 }
 
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d87767f76903..6afd6106ceb5 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -357,27 +357,3 @@ void *memdup(const void *src, size_t len)
 
 	return p;
 }
-
-/**
- * str_append - reallocate string and append another
- * @s: pointer to string pointer
- * @len: pointer to len (initialized)
- * @a: string to append.
- */
-int str_append(char **s, int *len, const char *a)
-{
-	int olen = *s ? strlen(*s) : 0;
-	int nlen = olen + strlen(a) + 1;
-	if (*len < nlen) {
-		*len = *len * 2;
-		if (*len < nlen)
-			*len = nlen;
-		*s = realloc(*s, *len);
-		if (!*s)
-			return -ENOMEM;
-		if (olen == 0)
-			**s = 0;
-	}
-	strcat(*s, a);
-	return 0;
-}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index a9df7f2c6dc9..2b7b2d91c016 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
+#include "unwind.h"
 
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
@@ -37,6 +38,9 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
+		if (unwind__prepare_access(thread) < 0)
+			goto err_thread;
+
 		comm_str = malloc(32);
 		if (!comm_str)
 			goto err_thread;
@@ -48,6 +52,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
+
 	}
 
 	return thread;
@@ -69,6 +74,7 @@ void thread__delete(struct thread *thread)
 		list_del(&comm->list);
 		comm__free(comm);
 	}
+	unwind__finish_access(thread);
 
 	free(thread);
 }
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 92b56db52471..e060386165c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
+#include "callchain.h"
 #include "thread.h"
 #include "session.h"
 #include "perf_regs.h"
@@ -525,12 +526,12 @@ static unw_accessors_t accessors = {
 	.get_proc_name		= get_proc_name,
 };
 
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-		       void *arg, int max_stack)
+int unwind__prepare_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;
-	unw_cursor_t c;
-	int ret;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return 0;
 
 	addr_space = unw_create_addr_space(&accessors, 0);
 	if (!addr_space) {
@@ -538,6 +539,33 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		return -ENOMEM;
 	}
 
+	thread__set_priv(thread, addr_space);
+
+	return 0;
+}
+
+void unwind__finish_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_destroy_addr_space(addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+		       void *arg, int max_stack)
+{
+	unw_addr_space_t addr_space;
+	unw_cursor_t c;
+	int ret;
+
+	addr_space = thread__priv(ui->thread);
+	if (addr_space == NULL)
+		return -1;
+
 	ret = unw_init_remote(&c, addr_space, ui);
 	if (ret)
 		display_error(ret);
@@ -549,7 +577,6 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
 	}
 
-	unw_destroy_addr_space(addr_space);
 	return ret;
 }
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f03061260b4e..c17c4855bdbc 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "symbol.h"
+#include "thread.h"
 
 struct unwind_entry {
 	struct map	*map;
@@ -21,6 +22,15 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
+int unwind__prepare_access(struct thread *thread);
+void unwind__finish_access(struct thread *thread);
+#else
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -33,5 +43,12 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 {
 	return 0;
 }
+
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */