Merge remote-tracking branch 'scott/next' into next
Freescale updates from Scott. Mostly support for critical
and machine check exceptions on 64-bit BookE, some new
PCI suspend/resume work and misc bits.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 3c1cc24..7b40a3c 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -57,6 +57,523 @@
/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
Date: 2013/01/08
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
new file mode 100644
index 0000000..e78ee79
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -0,0 +1,23 @@
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Provides access to the binary "24x7 catalog" provided by the
+ hypervisor on POWER7 and 8 systems. This catalog lists events
+ avaliable from the powerpc "hv_24x7" pmu. Its format is
+ documented here:
+ https://raw.githubusercontent.com/jmesmon/catalog-24x7/master/hv-24x7-catalog.h
+
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog_length
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number equal to the length in bytes of the catalog. This is
+ also extractable from the provided binary "catalog" sysfs entry.
+
+What: /sys/bus/event_source/devices/hv_24x7/interface/catalog_version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ Exposes the "version" field of the 24x7 catalog. This is also
+ extractable from the provided binary "catalog" sysfs entry.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
new file mode 100644
index 0000000..3fa58c2
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
@@ -0,0 +1,43 @@
+What: /sys/bus/event_source/devices/hv_gpci/interface/collect_privileged
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ '0' if the hypervisor is configured to forbid access to event
+ counters being accumulated by other guests and to physical
+ domain event counters.
+ '1' if that access is allowed.
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/ga
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "GA" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/expanded
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "EXPANDED" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/lab
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ 0 or 1. Indicates whether we have access to "LAB" events (listed
+ in arch/powerpc/perf/hv-gpci.h).
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number indicating the version of the gpci interface that the
+ hypervisor reports supporting.
+
+What: /sys/bus/event_source/devices/hv_gpci/interface/kernel_version
+Date: February 2014
+Contact: Cody P Schafer <cody@linux.vnet.ibm.com>
+Description:
+ A number indicating the latest version of the gpci interface
+ that the kernel is aware of.
diff --git a/MAINTAINERS b/MAINTAINERS
index b2cf5cf..27030d5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5216,11 +5216,10 @@
F: arch/powerpc/platforms/52xx/
LINUX FOR POWERPC EMBEDDED PPC4XX
-M: Josh Boyer <jwboyer@gmail.com>
+M: Alistair Popple <alistair@popple.id.au>
M: Matt Porter <mporter@kernel.crashing.org>
W: http://www.penguinppc.org/
L: linuxppc-dev@lists.ozlabs.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwboyer/powerpc-4xx.git
S: Maintained
F: arch/powerpc/platforms/40x/
F: arch/powerpc/platforms/44x/
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index e015896..f26b267 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -73,74 +73,8 @@
CONFIG_INET_IPCOMP=m
# CONFIG_IPV6 is not set
CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CONNTRACK_AMANDA=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_H323=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_NETBIOS_NS=m
-CONFIG_NF_CONNTRACK_PPTP=m
-CONFIG_NF_CONNTRACK_SIP=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_BRIDGE=m
CONFIG_BPF_JIT=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index f627fda..438e813 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -48,74 +48,8 @@
CONFIG_INET_IPCOMP=m
# CONFIG_IPV6 is not set
CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CONNTRACK_AMANDA=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_H323=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_NETBIOS_NS=m
-CONFIG_NF_CONNTRACK_PPTP=m
-CONFIG_NF_CONNTRACK_SIP=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_BRIDGE=m
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index e9a8b4e..9ea8342b 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -65,57 +65,8 @@
CONFIG_INET_IPCOMP=m
# CONFIG_IPV6 is not set
CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_UDPLITE=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_BRIDGE=m
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
@@ -353,3 +304,5 @@
CONFIG_VIRTUALIZATION=y
CONFIG_KVM_BOOK3S_64=m
CONFIG_KVM_BOOK3S_64_HV=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
diff --git a/arch/powerpc/configs/pseries_le_defconfig b/arch/powerpc/configs/pseries_le_defconfig
index 62771e0..3c84f9d 100644
--- a/arch/powerpc/configs/pseries_le_defconfig
+++ b/arch/powerpc/configs/pseries_le_defconfig
@@ -67,57 +67,8 @@
CONFIG_INET_IPCOMP=m
# CONFIG_IPV6 is not set
CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_UDPLITE=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_BRIDGE=m
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index a613d2c..b142b8e 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
#include <linux/sched.h>
#define COMPAT_USER_HZ 100
+#ifdef __BIG_ENDIAN__
#define COMPAT_UTS_MACHINE "ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE "ppcle\0\0"
+#endif
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 617cc76..bc23477 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -189,6 +189,7 @@
#define CPU_FTR_HAS_PPR LONG_ASM_CONST(0x0200000000000000)
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
+#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
#ifndef __ASSEMBLY__
@@ -445,6 +446,7 @@
CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
+#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
#define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -466,8 +468,8 @@
#define CPU_FTRS_POSSIBLE \
(CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 | \
CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 | \
- CPU_FTRS_POWER7 | CPU_FTRS_POWER8 | CPU_FTRS_CELL | \
- CPU_FTRS_PA6T | CPU_FTR_VSX)
+ CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
+ CPU_FTRS_CELL | CPU_FTRS_PA6T | CPU_FTR_VSX)
#endif
#else
enum {
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 6683061..aeaa56c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -147,6 +147,14 @@
END_FTR_SECTION_NESTED(ftr,ftr,943)
/*
+ * Set an SPR from a register if the CPU has the given feature
+ */
+#define OPT_SET_SPR(ra, spr, ftr) \
+BEGIN_FTR_SECTION_NESTED(943) \
+ mtspr spr,ra; \
+END_FTR_SECTION_NESTED(ftr,ftr,943)
+
+/*
* Save a register to the PACA if the CPU has the given feature
*/
#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index d8b600b..5dbbb29 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -274,6 +274,11 @@
/* Platform specific hcalls, used by KVM */
#define H_RTAS 0xf000
+/* "Platform specific hcalls", provided by PHYP */
+#define H_GET_24X7_CATALOG_PAGE 0xF078
+#define H_GET_24X7_DATA 0xF07C
+#define H_GET_PERF_COUNTER_INFO 0xF080
+
#ifndef __ASSEMBLY__
/**
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 2636acf..ffafab0 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -83,6 +83,8 @@
#define OPAL_INTERNAL_ERROR -11
#define OPAL_BUSY_EVENT -12
#define OPAL_HARDWARE_FROZEN -13
+#define OPAL_WRONG_STATE -14
+#define OPAL_ASYNC_COMPLETION -15
/* API Tokens (in r0) */
#define OPAL_CONSOLE_WRITE 1
@@ -165,8 +167,11 @@
#define OPAL_DUMP_ACK 84
#define OPAL_GET_MSG 85
#define OPAL_CHECK_ASYNC_COMPLETION 86
-#define OPAL_DUMP_RESEND 91
#define OPAL_SYNC_HOST_REBOOT 87
+#define OPAL_SENSOR_READ 88
+#define OPAL_GET_PARAM 89
+#define OPAL_SET_PARAM 90
+#define OPAL_DUMP_RESEND 91
#define OPAL_DUMP_INFO2 94
#ifndef __ASSEMBLY__
@@ -253,7 +258,9 @@
};
enum OpalMessageType {
- OPAL_MSG_ASYNC_COMP = 0,
+ OPAL_MSG_ASYNC_COMP = 0, /* params[0] = token, params[1] = rc,
+ * additional params function-specific
+ */
OPAL_MSG_MEM_ERR,
OPAL_MSG_EPOW,
OPAL_MSG_SHUTDOWN,
@@ -406,6 +413,13 @@
OPAL_LPC_FW = 2,
};
+/* System parameter permission */
+enum OpalSysparamPerm {
+ OPAL_SYSPARAM_READ = 0x1,
+ OPAL_SYSPARAM_WRITE = 0x2,
+ OPAL_SYSPARAM_RW = (OPAL_SYSPARAM_READ | OPAL_SYSPARAM_WRITE),
+};
+
struct opal_msg {
uint32_t msg_type;
uint32_t reserved;
@@ -855,6 +869,12 @@
int64_t opal_get_msg(uint64_t buffer, size_t size);
int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token);
int64_t opal_sync_host_reboot(void);
+int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer,
+ size_t length);
+int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer,
+ size_t length);
+int64_t opal_sensor_read(uint32_t sensor_hndl, int token,
+ uint32_t *sensor_data);
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
@@ -880,6 +900,13 @@
extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
+extern int __opal_async_get_token(void);
+extern int opal_async_get_token_interruptible(void);
+extern int __opal_async_release_token(int token);
+extern int opal_async_release_token(int token);
+extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg);
+extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data);
+
extern void hvc_opal_init_early(void);
struct rtc_time;
@@ -890,6 +917,7 @@
extern void opal_flash_init(void);
extern int opal_elog_init(void);
extern void opal_platform_dump_init(void);
+extern void opal_sys_param_init(void);
extern int opal_machine_check(struct pt_regs *regs);
extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 3fd2f1b6..9ed73714 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -14,6 +14,7 @@
#include <linux/device.h>
#include <uapi/asm/perf_event.h>
+/* Update perf_event_print_debug() if this changes */
#define MAX_HWEVENTS 8
#define MAX_EVENT_ALTERNATIVES 8
#define MAX_LIMITED_HWCOUNTERS 2
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f7251c2..1a36b8e 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -668,12 +668,14 @@
#define MMCR0_PMXE 0x04000000UL /* performance monitor exception enable */
#define MMCR0_FCECE 0x02000000UL /* freeze ctrs on enabled cond or event */
#define MMCR0_TBEE 0x00400000UL /* time base exception enable */
+#define MMCR0_BHRBA 0x00200000UL /* BHRB Access allowed in userspace */
#define MMCR0_EBE 0x00100000UL /* Event based branch enable */
#define MMCR0_PMCC 0x000c0000UL /* PMC control */
#define MMCR0_PMCC_U6 0x00080000UL /* PMC1-6 are R/W by user (PR) */
#define MMCR0_PMC1CE 0x00008000UL /* PMC1 count enable*/
#define MMCR0_PMCjCE 0x00004000UL /* PMCj count enable*/
#define MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */
+#define MMCR0_PMAO_SYNC 0x00000800UL /* PMU interrupt is synchronous */
#define MMCR0_PMAO 0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
#define MMCR0_SHRFC 0x00000040UL /* SHRre freeze conditions between threads */
#define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */
@@ -707,6 +709,7 @@
#define SPRN_EBBHR 804 /* Event based branch handler register */
#define SPRN_EBBRR 805 /* Event based branch return register */
#define SPRN_BESCR 806 /* Branch event status and control register */
+#define BESCR_GE 0x8000000000000000ULL /* Global Enable */
#define SPRN_WORT 895 /* Workload optimization register - thread */
#define SPRN_PMC1 787
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 6c8dd5d..c1faade 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -510,7 +510,7 @@
.pvr_mask = 0xffff0000,
.pvr_value = 0x004b0000,
.cpu_name = "POWER8E (raw)",
- .cpu_features = CPU_FTRS_POWER8,
+ .cpu_features = CPU_FTRS_POWER8E,
.cpu_user_features = COMMON_USER_POWER8,
.cpu_user_features2 = COMMON_USER2_POWER8,
.mmu_features = MMU_FTRS_POWER8,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 38d5073..4c34c3c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -164,13 +164,18 @@
*/
mfspr r13,SPRN_SRR1
rlwinm. r13,r13,47-31,30,31
+ OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
beq 9f
+ mfspr r13,SPRN_SRR1
+ rlwinm. r13,r13,47-31,30,31
/* waking up from powersave (nap) state */
cmpwi cr1,r13,2
/* Total loss of HV state is fatal. let's just stay stuck here */
+ OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
bgt cr1,.
9:
+ OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif /* CONFIG_PPC_P7_NAP */
EXCEPTION_PROLOG_0(PACA_EXMC)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 4cf674d..f386296 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1013,12 +1013,13 @@
return NULL;
}
+/* We assume to be passed big endian arguments */
asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
{
struct rtas_args args;
unsigned long flags;
char *buff_copy, *errbuf = NULL;
- int nargs;
+ int nargs, nret, token;
int rc;
if (!capable(CAP_SYS_ADMIN))
@@ -1027,10 +1028,13 @@
if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0)
return -EFAULT;
- nargs = args.nargs;
+ nargs = be32_to_cpu(args.nargs);
+ nret = be32_to_cpu(args.nret);
+ token = be32_to_cpu(args.token);
+
if (nargs > ARRAY_SIZE(args.args)
- || args.nret > ARRAY_SIZE(args.args)
- || nargs + args.nret > ARRAY_SIZE(args.args))
+ || nret > ARRAY_SIZE(args.args)
+ || nargs + nret > ARRAY_SIZE(args.args))
return -EINVAL;
/* Copy in args. */
@@ -1038,14 +1042,14 @@
nargs * sizeof(rtas_arg_t)) != 0)
return -EFAULT;
- if (args.token == RTAS_UNKNOWN_SERVICE)
+ if (token == RTAS_UNKNOWN_SERVICE)
return -EINVAL;
args.rets = &args.args[nargs];
- memset(args.rets, 0, args.nret * sizeof(rtas_arg_t));
+ memset(args.rets, 0, nret * sizeof(rtas_arg_t));
/* Need to handle ibm,suspend_me call specially */
- if (args.token == ibm_suspend_me_token) {
+ if (token == ibm_suspend_me_token) {
rc = rtas_ibm_suspend_me(&args);
if (rc)
return rc;
@@ -1062,7 +1066,7 @@
/* A -1 return code indicates that the last command couldn't
be completed due to a hardware error. */
- if (args.rets[0] == -1)
+ if (be32_to_cpu(args.rets[0]) == -1)
errbuf = __fetch_rtas_last_error(buff_copy);
unlock_rtas(flags);
@@ -1077,7 +1081,7 @@
/* Copy out args. */
if (copy_to_user(uargs->args + nargs,
args.args + nargs,
- args.nret * sizeof(rtas_arg_t)) != 0)
+ nret * sizeof(rtas_arg_t)) != 0)
return -EFAULT;
return 0;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 33cd7a0..df86f0c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1379,8 +1379,9 @@
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
- pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
- hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
+ pr_err_ratelimited(
+ "%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
+ hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
if (user_mode(regs)) {
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 62bf5e8..f6ce1f1 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -647,6 +647,11 @@
if (old & _PAGE_HASHPTE)
hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
}
+ /*
+ * This ensures that generic code that rely on IRQ disabling
+ * to prevent a parallel THP split work as expected.
+ */
+ kick_all_cpus_sync();
}
/*
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 60d71ee..f9c083a 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -11,5 +11,7 @@
obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
+obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 67cf220..4520c93 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -78,6 +78,7 @@
#define MMCR0_FC56 0
#define MMCR0_PMAO 0
#define MMCR0_EBE 0
+#define MMCR0_BHRBA 0
#define MMCR0_PMCC 0
#define MMCR0_PMCC_U6 0
@@ -120,6 +121,7 @@
static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
void power_pmu_flush_branch_stack(void) {}
static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
+static void pmao_restore_workaround(bool ebb) { }
#endif /* CONFIG_PPC32 */
static bool regs_use_siar(struct pt_regs *regs)
@@ -502,8 +504,11 @@
if (!leader->attr.pinned || !leader->attr.exclusive)
return -EINVAL;
- if (event->attr.inherit || event->attr.sample_period ||
- event->attr.enable_on_exec || event->attr.freq)
+ if (event->attr.freq ||
+ event->attr.inherit ||
+ event->attr.sample_type ||
+ event->attr.sample_period ||
+ event->attr.enable_on_exec)
return -EINVAL;
}
@@ -542,13 +547,21 @@
if (!ebb)
goto out;
- /* Enable EBB and read/write to all 6 PMCs for userspace */
- mmcr0 |= MMCR0_EBE | MMCR0_PMCC_U6;
+ /* Enable EBB and read/write to all 6 PMCs and BHRB for userspace */
+ mmcr0 |= MMCR0_EBE | MMCR0_BHRBA | MMCR0_PMCC_U6;
- /* Add any bits from the user reg, FC or PMAO */
+ /*
+ * Add any bits from the user MMCR0, FC or PMAO. This is compatible
+ * with pmao_restore_workaround() because we may add PMAO but we never
+ * clear it here.
+ */
mmcr0 |= current->thread.mmcr0;
- /* Be careful not to set PMXE if userspace had it cleared */
+ /*
+ * Be careful not to set PMXE if userspace had it cleared. This is also
+ * compatible with pmao_restore_workaround() because it has already
+ * cleared PMXE and we leave PMAO alone.
+ */
if (!(current->thread.mmcr0 & MMCR0_PMXE))
mmcr0 &= ~MMCR0_PMXE;
@@ -559,14 +572,95 @@
out:
return mmcr0;
}
+
+static void pmao_restore_workaround(bool ebb)
+{
+ unsigned pmcs[6];
+
+ if (!cpu_has_feature(CPU_FTR_PMAO_BUG))
+ return;
+
+ /*
+ * On POWER8E there is a hardware defect which affects the PMU context
+ * switch logic, ie. power_pmu_disable/enable().
+ *
+ * When a counter overflows PMXE is cleared and FC/PMAO is set in MMCR0
+ * by the hardware. Sometime later the actual PMU exception is
+ * delivered.
+ *
+ * If we context switch, or simply disable/enable, the PMU prior to the
+ * exception arriving, the exception will be lost when we clear PMAO.
+ *
+ * When we reenable the PMU, we will write the saved MMCR0 with PMAO
+ * set, and this _should_ generate an exception. However because of the
+ * defect no exception is generated when we write PMAO, and we get
+ * stuck with no counters counting but no exception delivered.
+ *
+ * The workaround is to detect this case and tweak the hardware to
+ * create another pending PMU exception.
+ *
+ * We do that by setting up PMC6 (cycles) for an imminent overflow and
+ * enabling the PMU. That causes a new exception to be generated in the
+ * chip, but we don't take it yet because we have interrupts hard
+ * disabled. We then write back the PMU state as we want it to be seen
+ * by the exception handler. When we reenable interrupts the exception
+ * handler will be called and see the correct state.
+ *
+ * The logic is the same for EBB, except that the exception is gated by
+ * us having interrupts hard disabled as well as the fact that we are
+ * not in userspace. The exception is finally delivered when we return
+ * to userspace.
+ */
+
+ /* Only if PMAO is set and PMAO_SYNC is clear */
+ if ((current->thread.mmcr0 & (MMCR0_PMAO | MMCR0_PMAO_SYNC)) != MMCR0_PMAO)
+ return;
+
+ /* If we're doing EBB, only if BESCR[GE] is set */
+ if (ebb && !(current->thread.bescr & BESCR_GE))
+ return;
+
+ /*
+ * We are already soft-disabled in power_pmu_enable(). We need to hard
+ * enable to actually prevent the PMU exception from firing.
+ */
+ hard_irq_disable();
+
+ /*
+ * This is a bit gross, but we know we're on POWER8E and have 6 PMCs.
+ * Using read/write_pmc() in a for loop adds 12 function calls and
+ * almost doubles our code size.
+ */
+ pmcs[0] = mfspr(SPRN_PMC1);
+ pmcs[1] = mfspr(SPRN_PMC2);
+ pmcs[2] = mfspr(SPRN_PMC3);
+ pmcs[3] = mfspr(SPRN_PMC4);
+ pmcs[4] = mfspr(SPRN_PMC5);
+ pmcs[5] = mfspr(SPRN_PMC6);
+
+ /* Ensure all freeze bits are unset */
+ mtspr(SPRN_MMCR2, 0);
+
+ /* Set up PMC6 to overflow in one cycle */
+ mtspr(SPRN_PMC6, 0x7FFFFFFE);
+
+ /* Enable exceptions and unfreeze PMC6 */
+ mtspr(SPRN_MMCR0, MMCR0_PMXE | MMCR0_PMCjCE | MMCR0_PMAO);
+
+ /* Now we need to refreeze and restore the PMCs */
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMAO);
+
+ mtspr(SPRN_PMC1, pmcs[0]);
+ mtspr(SPRN_PMC2, pmcs[1]);
+ mtspr(SPRN_PMC3, pmcs[2]);
+ mtspr(SPRN_PMC4, pmcs[3]);
+ mtspr(SPRN_PMC5, pmcs[4]);
+ mtspr(SPRN_PMC6, pmcs[5]);
+}
#endif /* CONFIG_PPC64 */
static void perf_event_interrupt(struct pt_regs *regs);
-void perf_event_print_debug(void)
-{
-}
-
/*
* Read one performance monitor counter (PMC).
*/
@@ -645,6 +739,57 @@
}
}
+/* Called from sysrq_handle_showregs() */
+void perf_event_print_debug(void)
+{
+ unsigned long sdar, sier, flags;
+ u32 pmcs[MAX_HWEVENTS];
+ int i;
+
+ if (!ppmu->n_counter)
+ return;
+
+ local_irq_save(flags);
+
+ pr_info("CPU: %d PMU registers, ppmu = %s n_counters = %d",
+ smp_processor_id(), ppmu->name, ppmu->n_counter);
+
+ for (i = 0; i < ppmu->n_counter; i++)
+ pmcs[i] = read_pmc(i + 1);
+
+ for (; i < MAX_HWEVENTS; i++)
+ pmcs[i] = 0xdeadbeef;
+
+ pr_info("PMC1: %08x PMC2: %08x PMC3: %08x PMC4: %08x\n",
+ pmcs[0], pmcs[1], pmcs[2], pmcs[3]);
+
+ if (ppmu->n_counter > 4)
+ pr_info("PMC5: %08x PMC6: %08x PMC7: %08x PMC8: %08x\n",
+ pmcs[4], pmcs[5], pmcs[6], pmcs[7]);
+
+ pr_info("MMCR0: %016lx MMCR1: %016lx MMCRA: %016lx\n",
+ mfspr(SPRN_MMCR0), mfspr(SPRN_MMCR1), mfspr(SPRN_MMCRA));
+
+ sdar = sier = 0;
+#ifdef CONFIG_PPC64
+ sdar = mfspr(SPRN_SDAR);
+
+ if (ppmu->flags & PPMU_HAS_SIER)
+ sier = mfspr(SPRN_SIER);
+
+ if (ppmu->flags & PPMU_EBB) {
+ pr_info("MMCR2: %016lx EBBHR: %016lx\n",
+ mfspr(SPRN_MMCR2), mfspr(SPRN_EBBHR));
+ pr_info("EBBRR: %016lx BESCR: %016lx\n",
+ mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR));
+ }
+#endif
+ pr_info("SIAR: %016lx SDAR: %016lx SIER: %016lx\n",
+ mfspr(SPRN_SIAR), sdar, sier);
+
+ local_irq_restore(flags);
+}
+
/*
* Check if a set of events can all go on the PMU at once.
* If they can't, this will look at alternative codes for the events
@@ -973,11 +1118,12 @@
}
/*
- * Set the 'freeze counters' bit, clear EBE/PMCC/PMAO/FC56.
+ * Set the 'freeze counters' bit, clear EBE/BHRBA/PMCC/PMAO/FC56
*/
val = mmcr0 = mfspr(SPRN_MMCR0);
val |= MMCR0_FC;
- val &= ~(MMCR0_EBE | MMCR0_PMCC | MMCR0_PMAO | MMCR0_FC56);
+ val &= ~(MMCR0_EBE | MMCR0_BHRBA | MMCR0_PMCC | MMCR0_PMAO |
+ MMCR0_FC56);
/*
* The barrier is to make sure the mtspr has been
@@ -1144,6 +1290,8 @@
cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
out_enable:
+ pmao_restore_workaround(ebb);
+
mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
mb();
diff --git a/arch/powerpc/perf/hv-24x7-catalog.h b/arch/powerpc/perf/hv-24x7-catalog.h
new file mode 100644
index 0000000..21b19dd
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7-catalog.h
@@ -0,0 +1,33 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+#define LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+
+#include <linux/types.h>
+
+/* From document "24x7 Event and Group Catalog Formats Proposal" v0.15 */
+
+struct hv_24x7_catalog_page_0 {
+#define HV_24X7_CATALOG_MAGIC 0x32347837 /* "24x7" in ASCII */
+ __be32 magic;
+ __be32 length; /* In 4096 byte pages */
+ __be64 version; /* XXX: arbitrary? what's the meaning/useage/purpose? */
+ __u8 build_time_stamp[16]; /* "YYYYMMDDHHMMSS\0\0" */
+ __u8 reserved2[32];
+ __be16 schema_data_offs; /* in 4096 byte pages */
+ __be16 schema_data_len; /* in 4096 byte pages */
+ __be16 schema_entry_count;
+ __u8 reserved3[2];
+ __be16 event_data_offs;
+ __be16 event_data_len;
+ __be16 event_entry_count;
+ __u8 reserved4[2];
+ __be16 group_data_offs; /* in 4096 byte pages */
+ __be16 group_data_len; /* in 4096 byte pages */
+ __be16 group_entry_count;
+ __u8 reserved5[2];
+ __be16 formula_data_offs; /* in 4096 byte pages */
+ __be16 formula_data_len; /* in 4096 byte pages */
+ __be16 formula_entry_count;
+ __u8 reserved6[2];
+} __packed;
+
+#endif
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
new file mode 100644
index 0000000..297c9105
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -0,0 +1,510 @@
+/*
+ * Hypervisor supplied "24x7" performance counter support
+ *
+ * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
+ * Copyright 2014 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.
+ */
+
+#define pr_fmt(fmt) "hv-24x7: " fmt
+
+#include <linux/perf_event.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/io.h>
+
+#include "hv-24x7.h"
+#include "hv-24x7-catalog.h"
+#include "hv-common.h"
+
+/*
+ * TODO: Merging events:
+ * - Think of the hcall as an interface to a 4d array of counters:
+ * - x = domains
+ * - y = indexes in the domain (core, chip, vcpu, node, etc)
+ * - z = offset into the counter space
+ * - w = lpars (guest vms, "logical partitions")
+ * - A single request is: x,y,y_last,z,z_last,w,w_last
+ * - this means we can retrieve a rectangle of counters in y,z for a single x.
+ *
+ * - Things to consider (ignoring w):
+ * - input cost_per_request = 16
+ * - output cost_per_result(ys,zs) = 8 + 8 * ys + ys * zs
+ * - limited number of requests per hcall (must fit into 4K bytes)
+ * - 4k = 16 [buffer header] - 16 [request size] * request_count
+ * - 255 requests per hcall
+ * - sometimes it will be more efficient to read extra data and discard
+ */
+
+/*
+ * Example usage:
+ * perf stat -e 'hv_24x7/domain=2,offset=8,starting_index=0,lpar=0xffffffff/'
+ */
+
+/* u3 0-6, one of HV_24X7_PERF_DOMAIN */
+EVENT_DEFINE_RANGE_FORMAT(domain, config, 0, 3);
+/* u16 */
+EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 16, 31);
+/* u32, see "data_offset" */
+EVENT_DEFINE_RANGE_FORMAT(offset, config, 32, 63);
+/* u16 */
+EVENT_DEFINE_RANGE_FORMAT(lpar, config1, 0, 15);
+
+EVENT_DEFINE_RANGE(reserved1, config, 4, 15);
+EVENT_DEFINE_RANGE(reserved2, config1, 16, 63);
+EVENT_DEFINE_RANGE(reserved3, config2, 0, 63);
+
+static struct attribute *format_attrs[] = {
+ &format_attr_domain.attr,
+ &format_attr_offset.attr,
+ &format_attr_starting_index.attr,
+ &format_attr_lpar.attr,
+ NULL,
+};
+
+static struct attribute_group format_group = {
+ .name = "format",
+ .attrs = format_attrs,
+};
+
+static struct kmem_cache *hv_page_cache;
+
+/*
+ * read_offset_data - copy data from one buffer to another while treating the
+ * source buffer as a small view on the total avaliable
+ * source data.
+ *
+ * @dest: buffer to copy into
+ * @dest_len: length of @dest in bytes
+ * @requested_offset: the offset within the source data we want. Must be > 0
+ * @src: buffer to copy data from
+ * @src_len: length of @src in bytes
+ * @source_offset: the offset in the sorce data that (src,src_len) refers to.
+ * Must be > 0
+ *
+ * returns the number of bytes copied.
+ *
+ * The following ascii art shows the various buffer possitioning we need to
+ * handle, assigns some arbitrary varibles to points on the buffer, and then
+ * shows how we fiddle with those values to get things we care about (copy
+ * start in src and copy len)
+ *
+ * s = @src buffer
+ * d = @dest buffer
+ * '.' areas in d are written to.
+ *
+ * u
+ * x w v z
+ * d |.........|
+ * s |----------------------|
+ *
+ * u
+ * x w z v
+ * d |........------|
+ * s |------------------|
+ *
+ * x w u,z,v
+ * d |........|
+ * s |------------------|
+ *
+ * x,w u,v,z
+ * d |..................|
+ * s |------------------|
+ *
+ * x u
+ * w v z
+ * d |........|
+ * s |------------------|
+ *
+ * x z w v
+ * d |------|
+ * s |------|
+ *
+ * x = source_offset
+ * w = requested_offset
+ * z = source_offset + src_len
+ * v = requested_offset + dest_len
+ *
+ * w_offset_in_s = w - x = requested_offset - source_offset
+ * z_offset_in_s = z - x = src_len
+ * v_offset_in_s = v - x = request_offset + dest_len - src_len
+ */
+static ssize_t read_offset_data(void *dest, size_t dest_len,
+ loff_t requested_offset, void *src,
+ size_t src_len, loff_t source_offset)
+{
+ size_t w_offset_in_s = requested_offset - source_offset;
+ size_t z_offset_in_s = src_len;
+ size_t v_offset_in_s = requested_offset + dest_len - src_len;
+ size_t u_offset_in_s = min(z_offset_in_s, v_offset_in_s);
+ size_t copy_len = u_offset_in_s - w_offset_in_s;
+
+ if (requested_offset < 0 || source_offset < 0)
+ return -EINVAL;
+
+ if (z_offset_in_s <= w_offset_in_s)
+ return 0;
+
+ memcpy(dest, src + w_offset_in_s, copy_len);
+ return copy_len;
+}
+
+static unsigned long h_get_24x7_catalog_page(char page[static 4096],
+ u32 version, u32 index)
+{
+ WARN_ON(!IS_ALIGNED((unsigned long)page, 4096));
+ return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE,
+ virt_to_phys(page),
+ version,
+ index);
+}
+
+static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf,
+ loff_t offset, size_t count)
+{
+ unsigned long hret;
+ ssize_t ret = 0;
+ size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
+ loff_t page_offset = 0;
+ uint32_t catalog_version_num = 0;
+ void *page = kmem_cache_alloc(hv_page_cache, GFP_USER);
+ struct hv_24x7_catalog_page_0 *page_0 = page;
+ if (!page)
+ return -ENOMEM;
+
+ hret = h_get_24x7_catalog_page(page, 0, 0);
+ if (hret) {
+ ret = -EIO;
+ goto e_free;
+ }
+
+ catalog_version_num = be32_to_cpu(page_0->version);
+ catalog_page_len = be32_to_cpu(page_0->length);
+ catalog_len = catalog_page_len * 4096;
+
+ page_offset = offset / 4096;
+ page_count = count / 4096;
+
+ if (page_offset >= catalog_page_len)
+ goto e_free;
+
+ if (page_offset != 0) {
+ hret = h_get_24x7_catalog_page(page, catalog_version_num,
+ page_offset);
+ if (hret) {
+ ret = -EIO;
+ goto e_free;
+ }
+ }
+
+ ret = read_offset_data(buf, count, offset,
+ page, 4096, page_offset * 4096);
+e_free:
+ if (hret)
+ pr_err("h_get_24x7_catalog_page(ver=%d, page=%lld) failed: rc=%ld\n",
+ catalog_version_num, page_offset, hret);
+ kfree(page);
+
+ pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n",
+ offset, page_offset, count, page_count, catalog_len,
+ catalog_page_len, ret);
+
+ return ret;
+}
+
+#define PAGE_0_ATTR(_name, _fmt, _expr) \
+static ssize_t _name##_show(struct device *dev, \
+ struct device_attribute *dev_attr, \
+ char *buf) \
+{ \
+ unsigned long hret; \
+ ssize_t ret = 0; \
+ void *page = kmem_cache_alloc(hv_page_cache, GFP_USER); \
+ struct hv_24x7_catalog_page_0 *page_0 = page; \
+ if (!page) \
+ return -ENOMEM; \
+ hret = h_get_24x7_catalog_page(page, 0, 0); \
+ if (hret) { \
+ ret = -EIO; \
+ goto e_free; \
+ } \
+ ret = sprintf(buf, _fmt, _expr); \
+e_free: \
+ kfree(page); \
+ return ret; \
+} \
+static DEVICE_ATTR_RO(_name)
+
+PAGE_0_ATTR(catalog_version, "%lld\n",
+ (unsigned long long)be32_to_cpu(page_0->version));
+PAGE_0_ATTR(catalog_len, "%lld\n",
+ (unsigned long long)be32_to_cpu(page_0->length) * 4096);
+static BIN_ATTR_RO(catalog, 0/* real length varies */);
+
+static struct bin_attribute *if_bin_attrs[] = {
+ &bin_attr_catalog,
+ NULL,
+};
+
+static struct attribute *if_attrs[] = {
+ &dev_attr_catalog_len.attr,
+ &dev_attr_catalog_version.attr,
+ NULL,
+};
+
+static struct attribute_group if_group = {
+ .name = "interface",
+ .bin_attrs = if_bin_attrs,
+ .attrs = if_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+ &format_group,
+ &if_group,
+ NULL,
+};
+
+static bool is_physical_domain(int domain)
+{
+ return domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP ||
+ domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
+}
+
+static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
+ u16 lpar, u64 *res,
+ bool success_expected)
+{
+ unsigned long ret;
+
+ /*
+ * request_buffer and result_buffer are not required to be 4k aligned,
+ * but are not allowed to cross any 4k boundary. Aligning them to 4k is
+ * the simplest way to ensure that.
+ */
+ struct reqb {
+ struct hv_24x7_request_buffer buf;
+ struct hv_24x7_request req;
+ } __packed __aligned(4096) request_buffer = {
+ .buf = {
+ .interface_version = HV_24X7_IF_VERSION_CURRENT,
+ .num_requests = 1,
+ },
+ .req = {
+ .performance_domain = domain,
+ .data_size = cpu_to_be16(8),
+ .data_offset = cpu_to_be32(offset),
+ .starting_lpar_ix = cpu_to_be16(lpar),
+ .max_num_lpars = cpu_to_be16(1),
+ .starting_ix = cpu_to_be16(ix),
+ .max_ix = cpu_to_be16(1),
+ }
+ };
+
+ struct resb {
+ struct hv_24x7_data_result_buffer buf;
+ struct hv_24x7_result res;
+ struct hv_24x7_result_element elem;
+ __be64 result;
+ } __packed __aligned(4096) result_buffer = {};
+
+ ret = plpar_hcall_norets(H_GET_24X7_DATA,
+ virt_to_phys(&request_buffer), sizeof(request_buffer),
+ virt_to_phys(&result_buffer), sizeof(result_buffer));
+
+ if (ret) {
+ if (success_expected)
+ pr_err_ratelimited("hcall failed: %d %#x %#x %d => 0x%lx (%ld) detail=0x%x failing ix=%x\n",
+ domain, offset, ix, lpar,
+ ret, ret,
+ result_buffer.buf.detailed_rc,
+ result_buffer.buf.failing_request_ix);
+ return ret;
+ }
+
+ *res = be64_to_cpu(result_buffer.result);
+ return ret;
+}
+
+static unsigned long event_24x7_request(struct perf_event *event, u64 *res,
+ bool success_expected)
+{
+ return single_24x7_request(event_get_domain(event),
+ event_get_offset(event),
+ event_get_starting_index(event),
+ event_get_lpar(event),
+ res,
+ success_expected);
+}
+
+static int h_24x7_event_init(struct perf_event *event)
+{
+ struct hv_perf_caps caps;
+ unsigned domain;
+ unsigned long hret;
+ u64 ct;
+
+ /* Not our event */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* Unused areas must be 0 */
+ if (event_get_reserved1(event) ||
+ event_get_reserved2(event) ||
+ event_get_reserved3(event)) {
+ pr_devel("reserved set when forbidden 0x%llx(0x%llx) 0x%llx(0x%llx) 0x%llx(0x%llx)\n",
+ event->attr.config,
+ event_get_reserved1(event),
+ event->attr.config1,
+ event_get_reserved2(event),
+ event->attr.config2,
+ event_get_reserved3(event));
+ return -EINVAL;
+ }
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ is_sampling_event(event)) /* no sampling */
+ return -EINVAL;
+
+ /* no branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ /* offset must be 8 byte aligned */
+ if (event_get_offset(event) % 8) {
+ pr_devel("bad alignment\n");
+ return -EINVAL;
+ }
+
+ /* Domains above 6 are invalid */
+ domain = event_get_domain(event);
+ if (domain > 6) {
+ pr_devel("invalid domain %d\n", domain);
+ return -EINVAL;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_devel("could not get capabilities: rc=%ld\n", hret);
+ return -EIO;
+ }
+
+ /* PHYSICAL domains & other lpars require extra capabilities */
+ if (!caps.collect_privileged && (is_physical_domain(domain) ||
+ (event_get_lpar(event) != event_get_lpar_max()))) {
+ pr_devel("hv permisions disallow: is_physical_domain:%d, lpar=0x%llx\n",
+ is_physical_domain(domain),
+ event_get_lpar(event));
+ return -EACCES;
+ }
+
+ /* see if the event complains */
+ if (event_24x7_request(event, &ct, false)) {
+ pr_devel("test hcall failed\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static u64 h_24x7_get_value(struct perf_event *event)
+{
+ unsigned long ret;
+ u64 ct;
+ ret = event_24x7_request(event, &ct, true);
+ if (ret)
+ /* We checked this in event init, shouldn't fail here... */
+ return 0;
+
+ return ct;
+}
+
+static void h_24x7_event_update(struct perf_event *event)
+{
+ s64 prev;
+ u64 now;
+ now = h_24x7_get_value(event);
+ prev = local64_xchg(&event->hw.prev_count, now);
+ local64_add(now - prev, &event->count);
+}
+
+static void h_24x7_event_start(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_RELOAD)
+ local64_set(&event->hw.prev_count, h_24x7_get_value(event));
+}
+
+static void h_24x7_event_stop(struct perf_event *event, int flags)
+{
+ h_24x7_event_update(event);
+}
+
+static int h_24x7_event_add(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_START)
+ h_24x7_event_start(event, flags);
+
+ return 0;
+}
+
+static int h_24x7_event_idx(struct perf_event *event)
+{
+ return 0;
+}
+
+static struct pmu h_24x7_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+
+ .name = "hv_24x7",
+ .attr_groups = attr_groups,
+ .event_init = h_24x7_event_init,
+ .add = h_24x7_event_add,
+ .del = h_24x7_event_stop,
+ .start = h_24x7_event_start,
+ .stop = h_24x7_event_stop,
+ .read = h_24x7_event_update,
+ .event_idx = h_24x7_event_idx,
+};
+
+static int hv_24x7_init(void)
+{
+ int r;
+ unsigned long hret;
+ struct hv_perf_caps caps;
+
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ pr_info("not a virtualized system, not enabling\n");
+ return -ENODEV;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+ hret);
+ return -ENODEV;
+ }
+
+ hv_page_cache = kmem_cache_create("hv-page-4096", 4096, 4096, 0, NULL);
+ if (!hv_page_cache)
+ return -ENOMEM;
+
+ r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+device_initcall(hv_24x7_init);
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
new file mode 100644
index 0000000..720ebce
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -0,0 +1,109 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_H_
+#define LINUX_POWERPC_PERF_HV_24X7_H_
+
+#include <linux/types.h>
+
+struct hv_24x7_request {
+ /* PHYSICAL domains require enabling via phyp/hmc. */
+#define HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP 0x01
+#define HV_24X7_PERF_DOMAIN_PHYSICAL_CORE 0x02
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CORE 0x03
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CHIP 0x04
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_NODE 0x05
+#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_REMOTE_NODE 0x06
+ __u8 performance_domain;
+ __u8 reserved[0x1];
+
+ /* bytes to read starting at @data_offset. must be a multiple of 8 */
+ __be16 data_size;
+
+ /*
+ * byte offset within the perf domain to read from. must be 8 byte
+ * aligned
+ */
+ __be32 data_offset;
+
+ /*
+ * only valid for VIRTUAL_PROCESSOR domains, ignored for others.
+ * -1 means "current partition only"
+ * Enabling via phyp/hmc required for non-"-1" values. 0 forbidden
+ * unless requestor is 0.
+ */
+ __be16 starting_lpar_ix;
+
+ /*
+ * Ignored when @starting_lpar_ix == -1
+ * Ignored when @performance_domain is not VIRTUAL_PROCESSOR_*
+ * -1 means "infinite" or all
+ */
+ __be16 max_num_lpars;
+
+ /* chip, core, or virtual processor based on @performance_domain */
+ __be16 starting_ix;
+ __be16 max_ix;
+} __packed;
+
+struct hv_24x7_request_buffer {
+ /* 0 - ? */
+ /* 1 - ? */
+#define HV_24X7_IF_VERSION_CURRENT 0x01
+ __u8 interface_version;
+ __u8 num_requests;
+ __u8 reserved[0xE];
+ struct hv_24x7_request requests[];
+} __packed;
+
+struct hv_24x7_result_element {
+ __be16 lpar_ix;
+
+ /*
+ * represents the core, chip, or virtual processor based on the
+ * request's @performance_domain
+ */
+ __be16 domain_ix;
+
+ /* -1 if @performance_domain does not refer to a virtual processor */
+ __be32 lpar_cfg_instance_id;
+
+ /* size = @result_element_data_size of cointaining result. */
+ __u8 element_data[];
+} __packed;
+
+struct hv_24x7_result {
+ __u8 result_ix;
+
+ /*
+ * 0 = not all result elements fit into the buffer, additional requests
+ * required
+ * 1 = all result elements were returned
+ */
+ __u8 results_complete;
+ __be16 num_elements_returned;
+
+ /* This is a copy of @data_size from the coresponding hv_24x7_request */
+ __be16 result_element_data_size;
+ __u8 reserved[0x2];
+
+ /* WARNING: only valid for first result element due to variable sizes
+ * of result elements */
+ /* struct hv_24x7_result_element[@num_elements_returned] */
+ struct hv_24x7_result_element elements[];
+} __packed;
+
+struct hv_24x7_data_result_buffer {
+ /* See versioning for request buffer */
+ __u8 interface_version;
+
+ __u8 num_results;
+ __u8 reserved[0x1];
+ __u8 failing_request_ix;
+ __be32 detailed_rc;
+ __be64 cec_cfg_instance_id;
+ __be64 catalog_version_num;
+ __u8 reserved2[0x8];
+ /* WARNING: only valid for the first result due to variable sizes of
+ * results */
+ struct hv_24x7_result results[]; /* [@num_results] */
+} __packed;
+
+#endif
diff --git a/arch/powerpc/perf/hv-common.c b/arch/powerpc/perf/hv-common.c
new file mode 100644
index 0000000..47e02b3
--- /dev/null
+++ b/arch/powerpc/perf/hv-common.c
@@ -0,0 +1,39 @@
+#include <asm/io.h>
+#include <asm/hvcall.h>
+
+#include "hv-gpci.h"
+#include "hv-common.h"
+
+unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
+{
+ unsigned long r;
+ struct p {
+ struct hv_get_perf_counter_info_params params;
+ struct cv_system_performance_capabilities caps;
+ } __packed __aligned(sizeof(uint64_t));
+
+ struct p arg = {
+ .params = {
+ .counter_request = cpu_to_be32(
+ CIR_SYSTEM_PERFORMANCE_CAPABILITIES),
+ .starting_index = cpu_to_be32(-1),
+ .counter_info_version_in = 0,
+ }
+ };
+
+ r = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+ virt_to_phys(&arg), sizeof(arg));
+
+ if (r)
+ return r;
+
+ pr_devel("capability_mask: 0x%x\n", arg.caps.capability_mask);
+
+ caps->version = arg.params.counter_info_version_out;
+ caps->collect_privileged = !!arg.caps.perf_collect_privileged;
+ caps->ga = !!(arg.caps.capability_mask & CV_CM_GA);
+ caps->expanded = !!(arg.caps.capability_mask & CV_CM_EXPANDED);
+ caps->lab = !!(arg.caps.capability_mask & CV_CM_LAB);
+
+ return r;
+}
diff --git a/arch/powerpc/perf/hv-common.h b/arch/powerpc/perf/hv-common.h
new file mode 100644
index 0000000..5d79cec
--- /dev/null
+++ b/arch/powerpc/perf/hv-common.h
@@ -0,0 +1,36 @@
+#ifndef LINUX_POWERPC_PERF_HV_COMMON_H_
+#define LINUX_POWERPC_PERF_HV_COMMON_H_
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+struct hv_perf_caps {
+ u16 version;
+ u16 collect_privileged:1,
+ ga:1,
+ expanded:1,
+ lab:1,
+ unused:12;
+};
+
+unsigned long hv_perf_caps_get(struct hv_perf_caps *caps);
+
+
+#define EVENT_DEFINE_RANGE_FORMAT(name, attr_var, bit_start, bit_end) \
+PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end); \
+EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end)
+
+#define EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end) \
+static u64 event_get_##name##_max(void) \
+{ \
+ BUILD_BUG_ON((bit_start > bit_end) \
+ || (bit_end >= (sizeof(1ull) * 8))); \
+ return (((1ull << (bit_end - bit_start)) - 1) << 1) + 1; \
+} \
+static u64 event_get_##name(struct perf_event *event) \
+{ \
+ return (event->attr.attr_var >> (bit_start)) & \
+ event_get_##name##_max(); \
+}
+
+#endif
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
new file mode 100644
index 0000000..278ba7b
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -0,0 +1,294 @@
+/*
+ * Hypervisor supplied "gpci" ("get performance counter info") performance
+ * counter support
+ *
+ * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
+ * Copyright 2014 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.
+ */
+
+#define pr_fmt(fmt) "hv-gpci: " fmt
+
+#include <linux/init.h>
+#include <linux/perf_event.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/io.h>
+
+#include "hv-gpci.h"
+#include "hv-common.h"
+
+/*
+ * Example usage:
+ * perf stat -e 'hv_gpci/counter_info_version=3,offset=0,length=8,
+ * secondary_index=0,starting_index=0xffffffff,request=0x10/' ...
+ */
+
+/* u32 */
+EVENT_DEFINE_RANGE_FORMAT(request, config, 0, 31);
+/* u32 */
+EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 32, 63);
+/* u16 */
+EVENT_DEFINE_RANGE_FORMAT(secondary_index, config1, 0, 15);
+/* u8 */
+EVENT_DEFINE_RANGE_FORMAT(counter_info_version, config1, 16, 23);
+/* u8, bytes of data (1-8) */
+EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31);
+/* u32, byte offset */
+EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
+
+static struct attribute *format_attrs[] = {
+ &format_attr_request.attr,
+ &format_attr_starting_index.attr,
+ &format_attr_secondary_index.attr,
+ &format_attr_counter_info_version.attr,
+
+ &format_attr_offset.attr,
+ &format_attr_length.attr,
+ NULL,
+};
+
+static struct attribute_group format_group = {
+ .name = "format",
+ .attrs = format_attrs,
+};
+
+#define HV_CAPS_ATTR(_name, _format) \
+static ssize_t _name##_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *page) \
+{ \
+ struct hv_perf_caps caps; \
+ unsigned long hret = hv_perf_caps_get(&caps); \
+ if (hret) \
+ return -EIO; \
+ \
+ return sprintf(page, _format, caps._name); \
+} \
+static struct device_attribute hv_caps_attr_##_name = __ATTR_RO(_name)
+
+static ssize_t kernel_version_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
+}
+
+DEVICE_ATTR_RO(kernel_version);
+HV_CAPS_ATTR(version, "0x%x\n");
+HV_CAPS_ATTR(ga, "%d\n");
+HV_CAPS_ATTR(expanded, "%d\n");
+HV_CAPS_ATTR(lab, "%d\n");
+HV_CAPS_ATTR(collect_privileged, "%d\n");
+
+static struct attribute *interface_attrs[] = {
+ &dev_attr_kernel_version.attr,
+ &hv_caps_attr_version.attr,
+ &hv_caps_attr_ga.attr,
+ &hv_caps_attr_expanded.attr,
+ &hv_caps_attr_lab.attr,
+ &hv_caps_attr_collect_privileged.attr,
+ NULL,
+};
+
+static struct attribute_group interface_group = {
+ .name = "interface",
+ .attrs = interface_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+ &format_group,
+ &interface_group,
+ NULL,
+};
+
+#define GPCI_MAX_DATA_BYTES \
+ (1024 - sizeof(struct hv_get_perf_counter_info_params))
+
+static unsigned long single_gpci_request(u32 req, u32 starting_index,
+ u16 secondary_index, u8 version_in, u32 offset, u8 length,
+ u64 *value)
+{
+ unsigned long ret;
+ size_t i;
+ u64 count;
+
+ struct {
+ struct hv_get_perf_counter_info_params params;
+ uint8_t bytes[GPCI_MAX_DATA_BYTES];
+ } __packed __aligned(sizeof(uint64_t)) arg = {
+ .params = {
+ .counter_request = cpu_to_be32(req),
+ .starting_index = cpu_to_be32(starting_index),
+ .secondary_index = cpu_to_be16(secondary_index),
+ .counter_info_version_in = version_in,
+ }
+ };
+
+ ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+ virt_to_phys(&arg), sizeof(arg));
+ if (ret) {
+ pr_devel("hcall failed: 0x%lx\n", ret);
+ return ret;
+ }
+
+ /*
+ * we verify offset and length are within the zeroed buffer at event
+ * init.
+ */
+ count = 0;
+ for (i = offset; i < offset + length; i++)
+ count |= arg.bytes[i] << (i - offset);
+
+ *value = count;
+ return ret;
+}
+
+static u64 h_gpci_get_value(struct perf_event *event)
+{
+ u64 count;
+ unsigned long ret = single_gpci_request(event_get_request(event),
+ event_get_starting_index(event),
+ event_get_secondary_index(event),
+ event_get_counter_info_version(event),
+ event_get_offset(event),
+ event_get_length(event),
+ &count);
+ if (ret)
+ return 0;
+ return count;
+}
+
+static void h_gpci_event_update(struct perf_event *event)
+{
+ s64 prev;
+ u64 now = h_gpci_get_value(event);
+ prev = local64_xchg(&event->hw.prev_count, now);
+ local64_add(now - prev, &event->count);
+}
+
+static void h_gpci_event_start(struct perf_event *event, int flags)
+{
+ local64_set(&event->hw.prev_count, h_gpci_get_value(event));
+}
+
+static void h_gpci_event_stop(struct perf_event *event, int flags)
+{
+ h_gpci_event_update(event);
+}
+
+static int h_gpci_event_add(struct perf_event *event, int flags)
+{
+ if (flags & PERF_EF_START)
+ h_gpci_event_start(event, flags);
+
+ return 0;
+}
+
+static int h_gpci_event_init(struct perf_event *event)
+{
+ u64 count;
+ u8 length;
+
+ /* Not our event */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* config2 is unused */
+ if (event->attr.config2) {
+ pr_devel("config2 set when reserved\n");
+ return -EINVAL;
+ }
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ is_sampling_event(event)) /* no sampling */
+ return -EINVAL;
+
+ /* no branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ length = event_get_length(event);
+ if (length < 1 || length > 8) {
+ pr_devel("length invalid\n");
+ return -EINVAL;
+ }
+
+ /* last byte within the buffer? */
+ if ((event_get_offset(event) + length) > GPCI_MAX_DATA_BYTES) {
+ pr_devel("request outside of buffer: %zu > %zu\n",
+ (size_t)event_get_offset(event) + length,
+ GPCI_MAX_DATA_BYTES);
+ return -EINVAL;
+ }
+
+ /* check if the request works... */
+ if (single_gpci_request(event_get_request(event),
+ event_get_starting_index(event),
+ event_get_secondary_index(event),
+ event_get_counter_info_version(event),
+ event_get_offset(event),
+ length,
+ &count)) {
+ pr_devel("gpci hcall failed\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int h_gpci_event_idx(struct perf_event *event)
+{
+ return 0;
+}
+
+static struct pmu h_gpci_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+
+ .name = "hv_gpci",
+ .attr_groups = attr_groups,
+ .event_init = h_gpci_event_init,
+ .add = h_gpci_event_add,
+ .del = h_gpci_event_stop,
+ .start = h_gpci_event_start,
+ .stop = h_gpci_event_stop,
+ .read = h_gpci_event_update,
+ .event_idx = h_gpci_event_idx,
+};
+
+static int hv_gpci_init(void)
+{
+ int r;
+ unsigned long hret;
+ struct hv_perf_caps caps;
+
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ pr_info("not a virtualized system, not enabling\n");
+ return -ENODEV;
+ }
+
+ hret = hv_perf_caps_get(&caps);
+ if (hret) {
+ pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+ hret);
+ return -ENODEV;
+ }
+
+ r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+device_initcall(hv_gpci_init);
diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h
new file mode 100644
index 0000000..b25f460
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci.h
@@ -0,0 +1,73 @@
+#ifndef LINUX_POWERPC_PERF_HV_GPCI_H_
+#define LINUX_POWERPC_PERF_HV_GPCI_H_
+
+#include <linux/types.h>
+
+/* From the document "H_GetPerformanceCounterInfo Interface" v1.07 */
+
+/* H_GET_PERF_COUNTER_INFO argument */
+struct hv_get_perf_counter_info_params {
+ __be32 counter_request; /* I */
+ __be32 starting_index; /* IO */
+ __be16 secondary_index; /* IO */
+ __be16 returned_values; /* O */
+ __be32 detail_rc; /* O, only needed when called via *_norets() */
+
+ /*
+ * O, size each of counter_value element in bytes, only set for version
+ * >= 0x3
+ */
+ __be16 cv_element_size;
+
+ /* I, 0 (zero) for versions < 0x3 */
+ __u8 counter_info_version_in;
+
+ /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */
+ __u8 counter_info_version_out;
+ __u8 reserved[0xC];
+ __u8 counter_value[];
+} __packed;
+
+/*
+ * counter info version => fw version/reference (spec version)
+ *
+ * 8 => power8 (1.07)
+ * [7 is skipped by spec 1.07]
+ * 6 => TLBIE (1.07)
+ * 5 => v7r7m0.phyp (1.05)
+ * [4 skipped]
+ * 3 => v7r6m0.phyp (?)
+ * [1,2 skipped]
+ * 0 => v7r{2,3,4}m0.phyp (?)
+ */
+#define COUNTER_INFO_VERSION_CURRENT 0x8
+
+/*
+ * These determine the counter_value[] layout and the meaning of starting_index
+ * and secondary_index.
+ *
+ * Unless otherwise noted, @secondary_index is unused and ignored.
+ */
+enum counter_info_requests {
+
+ /* GENERAL */
+
+ /* @starting_index: must be -1 (to refer to the current partition)
+ */
+ CIR_SYSTEM_PERFORMANCE_CAPABILITIES = 0X40,
+};
+
+struct cv_system_performance_capabilities {
+ /* If != 0, allowed to collect data from other partitions */
+ __u8 perf_collect_privileged;
+
+ /* These following are only valid if counter_info_version >= 0x3 */
+#define CV_CM_GA (1 << 7)
+#define CV_CM_EXPANDED (1 << 6)
+#define CV_CM_LAB (1 << 5)
+ /* remaining bits are reserved */
+ __u8 capability_mask;
+ __u8 reserved[0xE];
+} __packed;
+
+#endif
diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h
index 687790a..64f13d9 100644
--- a/arch/powerpc/perf/power7-events-list.h
+++ b/arch/powerpc/perf/power7-events-list.h
@@ -546,3 +546,13 @@
EVENT(PM_DTLB_MISS_16M, 0x4c05e)
EVENT(PM_LSU1_LMQ_LHR_MERGE, 0x0d09a)
EVENT(PM_IFU_FIN, 0x40066)
+EVENT(PM_1THRD_CON_RUN_INSTR, 0x30062)
+EVENT(PM_CMPLU_STALL_COUNT, 0x4000B)
+EVENT(PM_MEM0_PB_RD_CL, 0x30083)
+EVENT(PM_THRD_1_RUN_CYC, 0x10060)
+EVENT(PM_THRD_2_CONC_RUN_INSTR, 0x40062)
+EVENT(PM_THRD_2_RUN_CYC, 0x20060)
+EVENT(PM_THRD_3_CONC_RUN_INST, 0x10062)
+EVENT(PM_THRD_3_RUN_CYC, 0x30060)
+EVENT(PM_THRD_4_CONC_RUN_INST, 0x20062)
+EVENT(PM_THRD_4_RUN_CYC, 0x40060)
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 96cee20..fe2763b 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -10,6 +10,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) "power8-pmu: " fmt
+
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <asm/firmware.h>
@@ -62,9 +64,11 @@
*
* 60 56 52 48 44 40 36 32
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * | [ thresh_cmp ] [ thresh_ctl ]
- * | |
- * *- EBB (Linux) thresh start/stop OR FAB match -*
+ * | | [ ] [ thresh_cmp ] [ thresh_ctl ]
+ * | | | |
+ * | | *- IFM (Linux) thresh start/stop OR FAB match -*
+ * | *- BHRB (Linux)
+ * *- EBB (Linux)
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
@@ -114,9 +118,18 @@
* MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG)
* MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE)
*
+ * if EBB and BHRB:
+ * MMCRA[32:33] = IFM
+ *
*/
#define EVENT_EBB_MASK 1ull
+#define EVENT_EBB_SHIFT PERF_EVENT_CONFIG_EBB_SHIFT
+#define EVENT_BHRB_MASK 1ull
+#define EVENT_BHRB_SHIFT 62
+#define EVENT_WANTS_BHRB (EVENT_BHRB_MASK << EVENT_BHRB_SHIFT)
+#define EVENT_IFM_MASK 3ull
+#define EVENT_IFM_SHIFT 60
#define EVENT_THR_CMP_SHIFT 40 /* Threshold CMP value */
#define EVENT_THR_CMP_MASK 0x3ff
#define EVENT_THR_CTL_SHIFT 32 /* Threshold control value (start/stop) */
@@ -141,6 +154,12 @@
#define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
#define EVENT_PSEL_MASK 0xff /* PMCxSEL value */
+/* Bits defined by Linux */
+#define EVENT_LINUX_MASK \
+ ((EVENT_EBB_MASK << EVENT_EBB_SHIFT) | \
+ (EVENT_BHRB_MASK << EVENT_BHRB_SHIFT) | \
+ (EVENT_IFM_MASK << EVENT_IFM_SHIFT))
+
#define EVENT_VALID_MASK \
((EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \
(EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \
@@ -149,7 +168,7 @@
(EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \
(EVENT_COMBINE_MASK << EVENT_COMBINE_SHIFT) | \
(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
- (EVENT_EBB_MASK << PERF_EVENT_CONFIG_EBB_SHIFT) | \
+ EVENT_LINUX_MASK | \
EVENT_PSEL_MASK)
/* MMCRA IFM bits - POWER8 */
@@ -173,10 +192,11 @@
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * | [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1]
- * EBB -* | |
- * | | Count of events for each PMC.
- * L1 I/D qualifier -* | p1, p2, p3, p4, p5, p6.
+ * [ ] | [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1]
+ * | | | |
+ * BHRB IFM -* | | | Count of events for each PMC.
+ * EBB -* | | p1, p2, p3, p4, p5, p6.
+ * L1 I/D qualifier -* |
* nc - number of counters -*
*
* The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
@@ -195,6 +215,9 @@
#define CNST_EBB_VAL(v) (((v) & EVENT_EBB_MASK) << 24)
#define CNST_EBB_MASK CNST_EBB_VAL(EVENT_EBB_MASK)
+#define CNST_IFM_VAL(v) (((v) & EVENT_IFM_MASK) << 25)
+#define CNST_IFM_MASK CNST_IFM_VAL(EVENT_IFM_MASK)
+
#define CNST_L1_QUAL_VAL(v) (((v) & 3) << 22)
#define CNST_L1_QUAL_MASK CNST_L1_QUAL_VAL(3)
@@ -241,6 +264,7 @@
#define MMCRA_THR_SEL_SHIFT 16
#define MMCRA_THR_CMP_SHIFT 32
#define MMCRA_SDAR_MODE_TLB (1ull << 42)
+#define MMCRA_IFM_SHIFT 30
static inline bool event_is_fab_match(u64 event)
@@ -265,20 +289,22 @@
pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
- ebb = (event >> PERF_EVENT_CONFIG_EBB_SHIFT) & EVENT_EBB_MASK;
-
- /* Clear the EBB bit in the event, so event checks work below */
- event &= ~(EVENT_EBB_MASK << PERF_EVENT_CONFIG_EBB_SHIFT);
+ ebb = (event >> EVENT_EBB_SHIFT) & EVENT_EBB_MASK;
if (pmc) {
+ u64 base_event;
+
if (pmc > 6)
return -1;
+ /* Ignore Linux defined bits when checking event below */
+ base_event = event & ~EVENT_LINUX_MASK;
+
+ if (pmc >= 5 && base_event != 0x500fa && base_event != 0x600f4)
+ return -1;
+
mask |= CNST_PMC_MASK(pmc);
value |= CNST_PMC_VAL(pmc);
-
- if (pmc >= 5 && event != 0x500fa && event != 0x600f4)
- return -1;
}
if (pmc <= 4) {
@@ -299,9 +325,10 @@
* HV writable, and there is no API for guest kernels to modify
* it. The solution is for the hypervisor to initialise the
* field to zeroes, and for us to only ever allow events that
- * have a cache selector of zero.
+ * have a cache selector of zero. The bank selector (bit 3) is
+ * irrelevant, as long as the rest of the value is 0.
*/
- if (cache)
+ if (cache & 0x7)
return -1;
} else if (event & EVENT_IS_L1) {
@@ -342,6 +369,15 @@
/* EBB events must specify the PMC */
return -1;
+ if (event & EVENT_WANTS_BHRB) {
+ if (!ebb)
+ /* Only EBB events can request BHRB */
+ return -1;
+
+ mask |= CNST_IFM_MASK;
+ value |= CNST_IFM_VAL(event >> EVENT_IFM_SHIFT);
+ }
+
/*
* All events must agree on EBB, either all request it or none.
* EBB events are pinned & exclusive, so this should never actually
@@ -431,6 +467,11 @@
mmcra |= val << MMCRA_THR_CMP_SHIFT;
}
+ if (event[i] & EVENT_WANTS_BHRB) {
+ val = (event[i] >> EVENT_IFM_SHIFT) & EVENT_IFM_MASK;
+ mmcra |= val << MMCRA_IFM_SHIFT;
+ }
+
hwc[i] = pmc - 1;
}
@@ -774,6 +815,9 @@
/* Tell userspace that EBB is supported */
cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+ if (cpu_has_feature(CPU_FTR_PMAO_BUG))
+ pr_info("PMAO restore workaround active.\n");
+
return 0;
}
early_initcall(init_power8_pmu);
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 5125cae..f324ea0 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,6 +1,6 @@
-obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o
+obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o
obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
-obj-y += rng.o opal-elog.o opal-dump.o
+obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
new file mode 100644
index 0000000..cd0c135
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -0,0 +1,203 @@
+/*
+ * PowerNV OPAL asynchronous completion interfaces
+ *
+ * Copyright 2013 IBM Corp.
+ *
+ * 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.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/gfp.h>
+#include <linux/of.h>
+#include <asm/opal.h>
+
+#define N_ASYNC_COMPLETIONS 64
+
+static DECLARE_BITMAP(opal_async_complete_map, N_ASYNC_COMPLETIONS) = {~0UL};
+static DECLARE_BITMAP(opal_async_token_map, N_ASYNC_COMPLETIONS);
+static DECLARE_WAIT_QUEUE_HEAD(opal_async_wait);
+static DEFINE_SPINLOCK(opal_async_comp_lock);
+static struct semaphore opal_async_sem;
+static struct opal_msg *opal_async_responses;
+static unsigned int opal_max_async_tokens;
+
+int __opal_async_get_token(void)
+{
+ unsigned long flags;
+ int token;
+
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ token = find_first_bit(opal_async_complete_map, opal_max_async_tokens);
+ if (token >= opal_max_async_tokens) {
+ token = -EBUSY;
+ goto out;
+ }
+
+ if (__test_and_set_bit(token, opal_async_token_map)) {
+ token = -EBUSY;
+ goto out;
+ }
+
+ __clear_bit(token, opal_async_complete_map);
+
+out:
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+ return token;
+}
+
+int opal_async_get_token_interruptible(void)
+{
+ int token;
+
+ /* Wait until a token is available */
+ if (down_interruptible(&opal_async_sem))
+ return -ERESTARTSYS;
+
+ token = __opal_async_get_token();
+ if (token < 0)
+ up(&opal_async_sem);
+
+ return token;
+}
+
+int __opal_async_release_token(int token)
+{
+ unsigned long flags;
+
+ if (token < 0 || token >= opal_max_async_tokens) {
+ pr_err("%s: Passed token is out of range, token %d\n",
+ __func__, token);
+ return -EINVAL;
+ }
+
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ __set_bit(token, opal_async_complete_map);
+ __clear_bit(token, opal_async_token_map);
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+
+ return 0;
+}
+
+int opal_async_release_token(int token)
+{
+ int ret;
+
+ ret = __opal_async_release_token(token);
+ if (ret)
+ return ret;
+
+ up(&opal_async_sem);
+
+ return 0;
+}
+
+int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
+{
+ if (token >= opal_max_async_tokens) {
+ pr_err("%s: Invalid token passed\n", __func__);
+ return -EINVAL;
+ }
+
+ if (!msg) {
+ pr_err("%s: Invalid message pointer passed\n", __func__);
+ return -EINVAL;
+ }
+
+ wait_event(opal_async_wait, test_bit(token, opal_async_complete_map));
+ memcpy(msg, &opal_async_responses[token], sizeof(*msg));
+
+ return 0;
+}
+
+static int opal_async_comp_event(struct notifier_block *nb,
+ unsigned long msg_type, void *msg)
+{
+ struct opal_msg *comp_msg = msg;
+ unsigned long flags;
+
+ if (msg_type != OPAL_MSG_ASYNC_COMP)
+ return 0;
+
+ memcpy(&opal_async_responses[comp_msg->params[0]], comp_msg,
+ sizeof(*comp_msg));
+ spin_lock_irqsave(&opal_async_comp_lock, flags);
+ __set_bit(comp_msg->params[0], opal_async_complete_map);
+ spin_unlock_irqrestore(&opal_async_comp_lock, flags);
+
+ wake_up(&opal_async_wait);
+
+ return 0;
+}
+
+static struct notifier_block opal_async_comp_nb = {
+ .notifier_call = opal_async_comp_event,
+ .next = NULL,
+ .priority = 0,
+};
+
+static int __init opal_async_comp_init(void)
+{
+ struct device_node *opal_node;
+ const __be32 *async;
+ int err;
+
+ opal_node = of_find_node_by_path("/ibm,opal");
+ if (!opal_node) {
+ pr_err("%s: Opal node not found\n", __func__);
+ err = -ENOENT;
+ goto out;
+ }
+
+ async = of_get_property(opal_node, "opal-msg-async-num", NULL);
+ if (!async) {
+ pr_err("%s: %s has no opal-msg-async-num\n",
+ __func__, opal_node->full_name);
+ err = -ENOENT;
+ goto out_opal_node;
+ }
+
+ opal_max_async_tokens = be32_to_cpup(async);
+ if (opal_max_async_tokens > N_ASYNC_COMPLETIONS)
+ opal_max_async_tokens = N_ASYNC_COMPLETIONS;
+
+ err = opal_message_notifier_register(OPAL_MSG_ASYNC_COMP,
+ &opal_async_comp_nb);
+ if (err) {
+ pr_err("%s: Can't register OPAL event notifier (%d)\n",
+ __func__, err);
+ goto out_opal_node;
+ }
+
+ opal_async_responses = kzalloc(
+ sizeof(*opal_async_responses) * opal_max_async_tokens,
+ GFP_KERNEL);
+ if (!opal_async_responses) {
+ pr_err("%s: Out of memory, failed to do asynchronous "
+ "completion init\n", __func__);
+ err = -ENOMEM;
+ goto out_opal_node;
+ }
+
+ /* Initialize to 1 less than the maximum tokens available, as we may
+ * require to pop one during emergency through synchronous call to
+ * __opal_async_get_token()
+ */
+ sema_init(&opal_async_sem, opal_max_async_tokens - 1);
+
+out_opal_node:
+ of_node_put(opal_node);
+out:
+ return err;
+}
+subsys_initcall(opal_async_comp_init);
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
new file mode 100644
index 0000000..663cc9c
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -0,0 +1,64 @@
+/*
+ * PowerNV sensor code
+ *
+ * Copyright (C) 2013 IBM
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <asm/opal.h>
+
+static DEFINE_MUTEX(opal_sensor_mutex);
+
+/*
+ * This will return sensor information to driver based on the requested sensor
+ * handle. A handle is an opaque id for the powernv, read by the driver from the
+ * device tree..
+ */
+int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
+{
+ int ret, token;
+ struct opal_msg msg;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ pr_err("%s: Couldn't get the token, returning\n", __func__);
+ ret = token;
+ goto out;
+ }
+
+ mutex_lock(&opal_sensor_mutex);
+ ret = opal_sensor_read(sensor_hndl, token, sensor_data);
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ mutex_unlock(&opal_sensor_mutex);
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(opal_get_sensor_data);
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
new file mode 100644
index 0000000..0bd249a
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -0,0 +1,290 @@
+/*
+ * PowerNV system parameter code
+ *
+ * Copyright (C) 2013 IBM
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/gfp.h>
+#include <linux/stat.h>
+#include <asm/opal.h>
+
+#define MAX_PARAM_DATA_LEN 64
+
+static DEFINE_MUTEX(opal_sysparam_mutex);
+static struct kobject *sysparam_kobj;
+static void *param_data_buf;
+
+struct param_attr {
+ struct list_head list;
+ u32 param_id;
+ u32 param_size;
+ struct kobj_attribute kobj_attr;
+};
+
+static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
+{
+ struct opal_msg msg;
+ int ret, token;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ if (token != -ERESTARTSYS)
+ pr_err("%s: Couldn't get the token, returning\n",
+ __func__);
+ ret = token;
+ goto out;
+ }
+
+ ret = opal_get_param(token, param_id, (u64)buffer, length);
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+
+static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
+{
+ struct opal_msg msg;
+ int ret, token;
+
+ token = opal_async_get_token_interruptible();
+ if (token < 0) {
+ if (token != -ERESTARTSYS)
+ pr_err("%s: Couldn't get the token, returning\n",
+ __func__);
+ ret = token;
+ goto out;
+ }
+
+ ret = opal_set_param(token, param_id, (u64)buffer, length);
+
+ if (ret != OPAL_ASYNC_COMPLETION)
+ goto out_token;
+
+ ret = opal_async_wait_response(token, &msg);
+ if (ret) {
+ pr_err("%s: Failed to wait for the async response, %d\n",
+ __func__, ret);
+ goto out_token;
+ }
+
+ ret = msg.params[1];
+
+out_token:
+ opal_async_release_token(token);
+out:
+ return ret;
+}
+
+static ssize_t sys_param_show(struct kobject *kobj,
+ struct kobj_attribute *kobj_attr, char *buf)
+{
+ struct param_attr *attr = container_of(kobj_attr, struct param_attr,
+ kobj_attr);
+ int ret;
+
+ mutex_lock(&opal_sysparam_mutex);
+ ret = opal_get_sys_param(attr->param_id, attr->param_size,
+ param_data_buf);
+ if (ret)
+ goto out;
+
+ memcpy(buf, param_data_buf, attr->param_size);
+
+out:
+ mutex_unlock(&opal_sysparam_mutex);
+ return ret ? ret : attr->param_size;
+}
+
+static ssize_t sys_param_store(struct kobject *kobj,
+ struct kobj_attribute *kobj_attr, const char *buf, size_t count)
+{
+ struct param_attr *attr = container_of(kobj_attr, struct param_attr,
+ kobj_attr);
+ int ret;
+
+ mutex_lock(&opal_sysparam_mutex);
+ memcpy(param_data_buf, buf, count);
+ ret = opal_set_sys_param(attr->param_id, attr->param_size,
+ param_data_buf);
+ mutex_unlock(&opal_sysparam_mutex);
+ return ret ? ret : count;
+}
+
+void __init opal_sys_param_init(void)
+{
+ struct device_node *sysparam;
+ struct param_attr *attr;
+ u32 *id, *size;
+ int count, i;
+ u8 *perm;
+
+ if (!opal_kobj) {
+ pr_warn("SYSPARAM: opal kobject is not available\n");
+ goto out;
+ }
+
+ sysparam_kobj = kobject_create_and_add("sysparams", opal_kobj);
+ if (!sysparam_kobj) {
+ pr_err("SYSPARAM: Failed to create sysparam kobject\n");
+ goto out;
+ }
+
+ /* Allocate big enough buffer for any get/set transactions */
+ param_data_buf = kzalloc(MAX_PARAM_DATA_LEN, GFP_KERNEL);
+ if (!param_data_buf) {
+ pr_err("SYSPARAM: Failed to allocate memory for param data "
+ "buf\n");
+ goto out_kobj_put;
+ }
+
+ sysparam = of_find_node_by_path("/ibm,opal/sysparams");
+ if (!sysparam) {
+ pr_err("SYSPARAM: Opal sysparam node not found\n");
+ goto out_param_buf;
+ }
+
+ if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
+ pr_err("SYSPARAM: Opal sysparam node not compatible\n");
+ goto out_node_put;
+ }
+
+ /* Number of parameters exposed through DT */
+ count = of_property_count_strings(sysparam, "param-name");
+ if (count < 0) {
+ pr_err("SYSPARAM: No string found of property param-name in "
+ "the node %s\n", sysparam->name);
+ goto out_node_put;
+ }
+
+ id = kzalloc(sizeof(*id) * count, GFP_KERNEL);
+ if (!id) {
+ pr_err("SYSPARAM: Failed to allocate memory to read parameter "
+ "id\n");
+ goto out_node_put;
+ }
+
+ size = kzalloc(sizeof(*size) * count, GFP_KERNEL);
+ if (!size) {
+ pr_err("SYSPARAM: Failed to allocate memory to read parameter "
+ "size\n");
+ goto out_free_id;
+ }
+
+ perm = kzalloc(sizeof(*perm) * count, GFP_KERNEL);
+ if (!perm) {
+ pr_err("SYSPARAM: Failed to allocate memory to read supported "
+ "action on the parameter");
+ goto out_free_size;
+ }
+
+ if (of_property_read_u32_array(sysparam, "param-id", id, count)) {
+ pr_err("SYSPARAM: Missing property param-id in the DT\n");
+ goto out_free_perm;
+ }
+
+ if (of_property_read_u32_array(sysparam, "param-len", size, count)) {
+ pr_err("SYSPARAM: Missing propery param-len in the DT\n");
+ goto out_free_perm;
+ }
+
+
+ if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) {
+ pr_err("SYSPARAM: Missing propery param-perm in the DT\n");
+ goto out_free_perm;
+ }
+
+ attr = kzalloc(sizeof(*attr) * count, GFP_KERNEL);
+ if (!attr) {
+ pr_err("SYSPARAM: Failed to allocate memory for parameter "
+ "attributes\n");
+ goto out_free_perm;
+ }
+
+ /* For each of the parameters, populate the parameter attributes */
+ for (i = 0; i < count; i++) {
+ sysfs_attr_init(&attr[i].kobj_attr.attr);
+ attr[i].param_id = id[i];
+ attr[i].param_size = size[i];
+ if (of_property_read_string_index(sysparam, "param-name", i,
+ &attr[i].kobj_attr.attr.name))
+ continue;
+
+ /* If the parameter is read-only or read-write */
+ switch (perm[i] & 3) {
+ case OPAL_SYSPARAM_READ:
+ attr[i].kobj_attr.attr.mode = S_IRUGO;
+ break;
+ case OPAL_SYSPARAM_WRITE:
+ attr[i].kobj_attr.attr.mode = S_IWUGO;
+ break;
+ case OPAL_SYSPARAM_RW:
+ attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUGO;
+ break;
+ default:
+ break;
+ }
+
+ attr[i].kobj_attr.show = sys_param_show;
+ attr[i].kobj_attr.store = sys_param_store;
+
+ if (sysfs_create_file(sysparam_kobj, &attr[i].kobj_attr.attr)) {
+ pr_err("SYSPARAM: Failed to create sysfs file %s\n",
+ attr[i].kobj_attr.attr.name);
+ goto out_free_attr;
+ }
+ }
+
+ kfree(perm);
+ kfree(size);
+ kfree(id);
+ of_node_put(sysparam);
+ return;
+
+out_free_attr:
+ kfree(attr);
+out_free_perm:
+ kfree(perm);
+out_free_size:
+ kfree(size);
+out_free_id:
+ kfree(id);
+out_node_put:
+ of_node_put(sysparam);
+out_param_buf:
+ kfree(param_data_buf);
+out_kobj_put:
+ kobject_put(sysparam_kobj);
+out:
+ return;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 47ec3f7..75c89df 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -140,3 +140,6 @@
OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION);
OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND);
OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT);
+OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ);
+OPAL_CALL(opal_get_param, OPAL_GET_PARAM);
+OPAL_CALL(opal_set_param, OPAL_SET_PARAM);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2e269c2..e92f2f6 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -572,6 +572,8 @@
opal_flash_init();
/* Setup platform dump extract interface */
opal_platform_dump_init();
+ /* Setup system parameters interface */
+ opal_sys_param_init();
}
return 0;
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 80b1d57..2cb8b77 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -111,6 +111,18 @@
will be reused for other LPARs. The interface allows firmware to
balance memory across many LPARs.
+config HV_PERF_CTRS
+ bool "Hypervisor supplied PMU events (24x7 & GPCI)"
+ default y
+ depends on PERF_EVENTS && PPC_PSERIES
+ help
+ Enable access to hypervisor supplied counters in perf. Currently,
+ this enables code that uses the hcall GetPerfCounterInfo and 24x7
+ interfaces to retrieve counters. GPCI exists on Power 6 and later
+ systems. 24x7 is available on Power 8 systems.
+
+ If unsure, select Y.
+
config DTL
bool "Dispatch Trace Log"
depends on PPC_SPLPAR && DEBUG_FS
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 5ce43d8..ad4cdcb 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -557,6 +557,14 @@
This driver can also be built as a module. If so, the module
will be called ibmpex.
+config SENSORS_IBMPOWERNV
+ tristate "IBM PowerNv Platform temperature/power/fan sensor"
+ depends on PPC_POWERNV
+ default y
+ help
+ If you say yes here you get support for the temperature/fan/power
+ sensors on your platform.
+
config SENSORS_IIO_HWMON
tristate "Hwmon driver that uses channels specified via iio maps"
depends on IIO
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index ec7cde0..807e172 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -70,6 +70,7 @@
obj-$(CONFIG_SENSORS_I5K_AMB) += i5k_amb.o
obj-$(CONFIG_SENSORS_IBMAEM) += ibmaem.o
obj-$(CONFIG_SENSORS_IBMPEX) += ibmpex.o
+obj-$(CONFIG_SENSORS_IBMPOWERNV)+= ibmpowernv.o
obj-$(CONFIG_SENSORS_IIO_HWMON) += iio_hwmon.o
obj-$(CONFIG_SENSORS_INA209) += ina209.o
obj-$(CONFIG_SENSORS_INA2XX) += ina2xx.o
diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c
new file mode 100644
index 0000000..b7b1297
--- /dev/null
+++ b/drivers/hwmon/ibmpowernv.c
@@ -0,0 +1,529 @@
+/*
+ * hwmon driver for temperature/power/fan on IBM PowerNV platform
+ * Copyright (C) 2013 IBM
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include <linux/jiffies.h>
+#include <linux/platform_device.h>
+#include <asm/opal.h>
+#include <linux/err.h>
+
+MODULE_DESCRIPTION("IBM PowerNV Platform power/temp/fan sensor hwmon module");
+MODULE_LICENSE("GPL");
+
+#define MAX_ATTR_LENGTH 32
+
+/* Device tree sensor name prefixes. The device tree has the names in the
+ * format "cooling-fan#2-faulted" where the "cooling-fan" is the sensor type,
+ * 2 is the sensor count, and "faulted" is the sensor data attribute type.
+ */
+#define DT_FAULT_ATTR_SUFFIX "faulted"
+#define DT_DATA_ATTR_SUFFIX "data"
+#define DT_THRESHOLD_ATTR_SUFFIX "thrs"
+
+enum sensors {
+ FAN,
+ TEMPERATURE,
+ POWERSUPPLY,
+ POWER,
+ MAX_SENSOR_TYPE,
+};
+
+enum attributes {
+ INPUT,
+ MINIMUM,
+ MAXIMUM,
+ FAULT,
+ MAX_ATTR_TYPES
+};
+
+static struct sensor_name {
+ char *name;
+ char *compaible;
+} sensor_names[] = {
+ {"fan-sensor", "ibm,opal-sensor-cooling-fan"},
+ {"amb-temp-sensor", "ibm,opal-sensor-amb-temp"},
+ {"power-sensor", "ibm,opal-sensor-power-supply"},
+ {"power", "ibm,opal-sensor-power"}
+};
+
+static const char * const attribute_type_table[] = {
+ "input",
+ "min",
+ "max",
+ "fault",
+ NULL
+};
+
+struct pdev_entry {
+ struct list_head list;
+ struct platform_device *pdev;
+ enum sensors type;
+};
+
+static LIST_HEAD(pdev_list);
+
+/* The sensors are categorised on type.
+ *
+ * The sensors of same type are categorised under a common platform device.
+ * So, The pdev is shared by all sensors of same type.
+ * Ex : temp1_input, temp1_max, temp2_input,temp2_max all share same platform
+ * device.
+ *
+ * "sensor_data" is the Platform device specific data.
+ * There is one hwmon_device instance for all the sensors of same type.
+ * This also holds the list of all sensors with same type but different
+ * attribute and index.
+ */
+struct sensor_specific_data {
+ u32 sensor_id; /* The hex value as in the device tree */
+ u32 sensor_index; /* The sensor instance index */
+ struct sensor_device_attribute sd_attr;
+ enum attributes attr_type;
+ char attr_name[64];
+};
+
+struct sensor_data {
+ struct device *hwmon_dev;
+ struct list_head sensor_list;
+ struct device_attribute name_attr;
+};
+
+struct sensor_entry {
+ struct list_head list;
+ struct sensor_specific_data *sensor_data;
+};
+
+static struct platform_device *powernv_sensor_get_pdev(enum sensors type)
+{
+ struct pdev_entry *p;
+ list_for_each_entry(p, &pdev_list, list)
+ if (p->type == type)
+ return p->pdev;
+
+ return NULL;
+}
+
+static struct sensor_specific_data *powernv_sensor_get_sensor_data(
+ struct sensor_data *pdata,
+ int index, enum attributes attr_type)
+{
+ struct sensor_entry *p;
+ list_for_each_entry(p, &pdata->sensor_list, list)
+ if ((p->sensor_data->sensor_index == index) &&
+ (attr_type == p->sensor_data->attr_type))
+ return p->sensor_data;
+
+ return NULL;
+}
+
+static ssize_t show_name(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+
+ return sprintf(buf, "%s\n", pdev->name);
+}
+
+/* Note: Data from the sensors for each sensor type needs to be converted to
+ * the dimension appropriate.
+ */
+static ssize_t show_sensor(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ struct sensor_device_attribute *sd_attr = to_sensor_dev_attr(devattr);
+ struct platform_device *pdev = to_platform_device(dev);
+ struct sensor_data *pdata = platform_get_drvdata(pdev);
+ struct sensor_specific_data *tdata = NULL;
+ enum sensors sensor_type = pdev->id;
+ u32 x = -1;
+ int ret;
+
+ if (sd_attr && sd_attr->dev_attr.attr.name) {
+ char *pos = strchr(sd_attr->dev_attr.attr.name, '_');
+ int i;
+
+ for (i = 0; i < MAX_ATTR_TYPES; i++) {
+ if (strcmp(pos+1, attribute_type_table[i]) == 0) {
+ tdata = powernv_sensor_get_sensor_data(pdata,
+ sd_attr->index, i);
+ break;
+ }
+ }
+ }
+
+ if (tdata) {
+ ret = opal_get_sensor_data(tdata->sensor_id, &x);
+ if (ret)
+ x = -1;
+ }
+
+ if (sensor_type == TEMPERATURE && x > 0) {
+ /* Temperature comes in Degrees and convert it to
+ * milli-degrees.
+ */
+ x = x*1000;
+ } else if (sensor_type == POWER && x > 0) {
+ /* Power value comes in watts, convert to micro-watts */
+ x = x * 1000000;
+ }
+
+ return sprintf(buf, "%d\n", x);
+}
+
+static u32 get_sensor_index_from_name(const char *name)
+{
+ char *hash_position = strchr(name, '#');
+ u32 index = 0, copy_length;
+ char newbuf[8];
+
+ if (hash_position) {
+ copy_length = strchr(hash_position, '-') - hash_position - 1;
+ if (copy_length < sizeof(newbuf)) {
+ strncpy(newbuf, hash_position + 1, copy_length);
+ sscanf(newbuf, "%d", &index);
+ }
+ }
+
+ return index;
+}
+
+static inline void get_sensor_suffix_from_name(const char *name, char *suffix)
+{
+ char *dash_position = strrchr(name, '-');
+ if (dash_position)
+ strncpy(suffix, dash_position+1, MAX_ATTR_LENGTH);
+ else
+ strcpy(suffix,"");
+}
+
+static int get_sensor_attr_properties(const char *sensor_name,
+ enum sensors sensor_type, enum attributes *attr_type,
+ u32 *sensor_index)
+{
+ char suffix[MAX_ATTR_LENGTH];
+
+ *attr_type = MAX_ATTR_TYPES;
+ *sensor_index = get_sensor_index_from_name(sensor_name);
+ if (*sensor_index == 0)
+ return -EINVAL;
+
+ get_sensor_suffix_from_name(sensor_name, suffix);
+ if (strcmp(suffix, "") == 0)
+ return -EINVAL;
+
+ if (strcmp(suffix, DT_FAULT_ATTR_SUFFIX) == 0)
+ *attr_type = FAULT;
+ else if (strcmp(suffix, DT_DATA_ATTR_SUFFIX) == 0)
+ *attr_type = INPUT;
+ else if ((sensor_type == TEMPERATURE) &&
+ (strcmp(suffix, DT_THRESHOLD_ATTR_SUFFIX) == 0))
+ *attr_type = MAXIMUM;
+ else if ((sensor_type == FAN) &&
+ (strcmp(suffix, DT_THRESHOLD_ATTR_SUFFIX) == 0))
+ *attr_type = MINIMUM;
+ else
+ return -ENOENT;
+
+ if (((sensor_type == FAN) && ((*attr_type == INPUT) ||
+ (*attr_type == MINIMUM)))
+ || ((sensor_type == TEMPERATURE) && ((*attr_type == INPUT) ||
+ (*attr_type == MAXIMUM)))
+ || ((sensor_type == POWER) && ((*attr_type == INPUT))))
+ return 0;
+
+ return -ENOENT;
+}
+
+static int create_sensor_attr(struct sensor_specific_data *tdata,
+ struct device *dev, enum sensors sensor_type,
+ enum attributes attr_type)
+{
+ int err = 0;
+ char temp_file_prefix[50];
+ static const char *const file_name_format = "%s%d_%s";
+
+ tdata->attr_type = attr_type;
+
+ if (sensor_type == FAN)
+ strcpy(temp_file_prefix, "fan");
+ else if (sensor_type == TEMPERATURE)
+ strcpy(temp_file_prefix, "temp");
+ else if (sensor_type == POWERSUPPLY)
+ strcpy(temp_file_prefix, "powersupply");
+ else if (sensor_type == POWER)
+ strcpy(temp_file_prefix, "power");
+
+ snprintf(tdata->attr_name, sizeof(tdata->attr_name), file_name_format,
+ temp_file_prefix, tdata->sensor_index,
+ attribute_type_table[tdata->attr_type]);
+
+ sysfs_attr_init(&tdata->sd_attr.dev_attr.attr);
+ tdata->sd_attr.dev_attr.attr.name = tdata->attr_name;
+ tdata->sd_attr.dev_attr.attr.mode = S_IRUGO;
+ tdata->sd_attr.dev_attr.show = show_sensor;
+
+ tdata->sd_attr.index = tdata->sensor_index;
+ err = device_create_file(dev, &tdata->sd_attr.dev_attr);
+
+ return err;
+}
+
+static int create_name_attr(struct sensor_data *pdata,
+ struct device *dev)
+{
+ sysfs_attr_init(&pdata->name_attr.attr);
+ pdata->name_attr.attr.name = "name";
+ pdata->name_attr.attr.mode = S_IRUGO;
+ pdata->name_attr.show = show_name;
+ return device_create_file(dev, &pdata->name_attr);
+}
+
+static int create_platform_device(enum sensors sensor_type,
+ struct platform_device **pdev)
+{
+ struct pdev_entry *pdev_entry = NULL;
+ int err;
+
+ *pdev = platform_device_alloc(sensor_names[sensor_type].name,
+ sensor_type);
+ if (!*pdev) {
+ pr_err("Device allocation failed\n");
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ pdev_entry = kzalloc(sizeof(struct pdev_entry), GFP_KERNEL);
+ if (!pdev_entry) {
+ pr_err("Device allocation failed\n");
+ err = -ENOMEM;
+ goto exit_device_put;
+ }
+
+ err = platform_device_add(*pdev);
+ if (err) {
+ pr_err("Device addition failed (%d)\n", err);
+ goto exit_device_free;
+ }
+
+ pdev_entry->pdev = *pdev;
+ pdev_entry->type = (*pdev)->id;
+
+ list_add_tail(&pdev_entry->list, &pdev_list);
+
+ return 0;
+exit_device_free:
+ kfree(pdev_entry);
+exit_device_put:
+ platform_device_put(*pdev);
+exit:
+ return err;
+}
+
+static int create_sensor_data(struct platform_device *pdev)
+{
+ struct sensor_data *pdata = NULL;
+ int err = 0;
+
+ pdata = kzalloc(sizeof(struct sensor_data), GFP_KERNEL);
+ if (!pdata) {
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ err = create_name_attr(pdata, &pdev->dev);
+ if (err)
+ goto exit_free;
+
+ pdata->hwmon_dev = hwmon_device_register(&pdev->dev);
+ if (IS_ERR(pdata->hwmon_dev)) {
+ err = PTR_ERR(pdata->hwmon_dev);
+ dev_err(&pdev->dev, "Class registration failed (%d)\n",
+ err);
+ goto exit_name;
+ }
+
+ INIT_LIST_HEAD(&pdata->sensor_list);
+ platform_set_drvdata(pdev, pdata);
+
+ return 0;
+
+exit_name:
+ device_remove_file(&pdev->dev, &pdata->name_attr);
+exit_free:
+ kfree(pdata);
+exit:
+ return err;
+}
+
+static void delete_sensor_attr(struct sensor_data *pdata)
+{
+ struct sensor_entry *s, *l;
+
+ list_for_each_entry_safe(s, l, &pdata->sensor_list, list) {
+ struct sensor_specific_data *tdata = s->sensor_data;
+ kfree(tdata);
+ list_del(&s->list);
+ kfree(s);
+ }
+}
+
+static int powernv_sensor_init(u32 sensor_id, const struct device_node *np,
+ enum sensors sensor_type, enum attributes attr_type,
+ u32 sensor_index)
+{
+ struct platform_device *pdev = powernv_sensor_get_pdev(sensor_type);
+ struct sensor_specific_data *tdata;
+ struct sensor_entry *sensor_entry;
+ struct sensor_data *pdata;
+ int err = 0;
+
+ if (!pdev) {
+ err = create_platform_device(sensor_type, &pdev);
+ if (err)
+ goto exit;
+
+ err = create_sensor_data(pdev);
+ if (err)
+ goto exit;
+ }
+
+ pdata = platform_get_drvdata(pdev);
+ if (!pdata) {
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ tdata = kzalloc(sizeof(struct sensor_specific_data), GFP_KERNEL);
+ if (!tdata) {
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ tdata->sensor_id = sensor_id;
+ tdata->sensor_index = sensor_index;
+
+ err = create_sensor_attr(tdata, &pdev->dev, sensor_type, attr_type);
+ if (err)
+ goto exit_free;
+
+ sensor_entry = kzalloc(sizeof(struct sensor_entry), GFP_KERNEL);
+ if (!sensor_entry) {
+ err = -ENOMEM;
+ goto exit_attr;
+ }
+
+ sensor_entry->sensor_data = tdata;
+
+ list_add_tail(&sensor_entry->list, &pdata->sensor_list);
+
+ return 0;
+exit_attr:
+ device_remove_file(&pdev->dev, &tdata->sd_attr.dev_attr);
+exit_free:
+ kfree(tdata);
+exit:
+ return err;
+}
+
+static void delete_unregister_sensors(void)
+{
+ struct pdev_entry *p, *n;
+
+ list_for_each_entry_safe(p, n, &pdev_list, list) {
+ struct sensor_data *pdata = platform_get_drvdata(p->pdev);
+ if (pdata) {
+ delete_sensor_attr(pdata);
+
+ hwmon_device_unregister(pdata->hwmon_dev);
+ kfree(pdata);
+ }
+ platform_device_unregister(p->pdev);
+ list_del(&p->list);
+ kfree(p);
+ }
+}
+
+static int __init powernv_hwmon_init(void)
+{
+ struct device_node *opal, *np = NULL;
+ enum attributes attr_type;
+ enum sensors type;
+ const u32 *sensor_id;
+ u32 sensor_index;
+ int err;
+
+ opal = of_find_node_by_path("/ibm,opal/sensors");
+ if (!opal) {
+ pr_err("%s: Opal 'sensors' node not found\n", __func__);
+ return -ENXIO;
+ }
+
+ for_each_child_of_node(opal, np) {
+ if (np->name == NULL)
+ continue;
+
+ for (type = 0; type < MAX_SENSOR_TYPE; type++)
+ if (of_device_is_compatible(np,
+ sensor_names[type].compaible))
+ break;
+
+ if (type == MAX_SENSOR_TYPE)
+ continue;
+
+ if (get_sensor_attr_properties(np->name, type, &attr_type,
+ &sensor_index))
+ continue;
+
+ sensor_id = of_get_property(np, "sensor-id", NULL);
+ if (!sensor_id) {
+ pr_info("%s: %s doesn't have sensor-id\n", __func__,
+ np->name);
+ continue;
+ }
+
+ err = powernv_sensor_init(*sensor_id, np, type, attr_type,
+ sensor_index);
+ if (err) {
+ of_node_put(opal);
+ goto exit;
+ }
+ }
+ of_node_put(opal);
+
+ return 0;
+exit:
+ delete_unregister_sensors();
+ return err;
+
+}
+
+static void powernv_hwmon_exit(void)
+{
+ delete_unregister_sensors();
+}
+
+module_init(powernv_hwmon_init);
+module_exit(powernv_hwmon_exit);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 6b57938..aa04068 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -70,8 +70,11 @@
if (grp->bin_attrs) {
for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) {
if (update)
- sysfs_remove_bin_file(kobj, *bin_attr);
- error = sysfs_create_bin_file(kobj, *bin_attr);
+ kernfs_remove_by_name(parent,
+ (*bin_attr)->attr.name);
+ error = sysfs_add_file_mode_ns(parent,
+ &(*bin_attr)->attr, true,
+ (*bin_attr)->attr.mode, NULL);
if (error)
break;
}