diff options
| author | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2009-06-12 16:53:38 +1000 |
|---|---|---|
| committer | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2009-06-12 16:53:38 +1000 |
| commit | bc47ab0241c7c86da4f5e5f82fbca7d45387c18d (patch) | |
| tree | b9c33ae8b6de43e44cc5fcbaa3e4a15f18a5ed42 /arch/powerpc | |
| parent | 37f9ef553bed630957e025504cdcbc76f5de49d5 (diff) | |
| parent | 8ebf975608aaebd7feb33d77f07ba21a6380e086 (diff) | |
| download | kernel_samsung_crespo-bc47ab0241c7c86da4f5e5f82fbca7d45387c18d.zip kernel_samsung_crespo-bc47ab0241c7c86da4f5e5f82fbca7d45387c18d.tar.gz kernel_samsung_crespo-bc47ab0241c7c86da4f5e5f82fbca7d45387c18d.tar.bz2 | |
Merge commit 'origin/master' into next
Manual merge of:
arch/powerpc/kernel/asm-offsets.c
Diffstat (limited to 'arch/powerpc')
25 files changed, 4895 insertions, 93 deletions
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 5339bb4..ea8870a 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc3 -# Tue Nov 11 19:36:51 2008 +# Linux kernel version: 2.6.30-rc7 +# Mon May 25 14:53:25 2009 # # CONFIG_PPC64 is not set @@ -14,6 +14,7 @@ CONFIG_6xx=y # CONFIG_40x is not set # CONFIG_44x is not set # CONFIG_E200 is not set +CONFIG_PPC_BOOK3S=y CONFIG_PPC_FPU=y CONFIG_ALTIVEC=y CONFIG_PPC_STD_MMU=y @@ -43,7 +44,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y CONFIG_PPC=y CONFIG_EARLY_PRINTK=y CONFIG_GENERIC_NVRAM=y -CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y +CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_PPC_OF=y CONFIG_OF=y @@ -52,12 +53,14 @@ CONFIG_OF=y CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y +CONFIG_DTC=y # CONFIG_DEFAULT_UIMAGE is not set CONFIG_HIBERNATE_32=y CONFIG_ARCH_HIBERNATION_POSSIBLE=y CONFIG_ARCH_SUSPEND_POSSIBLE=y # CONFIG_PPC_DCR_NATIVE is not set # CONFIG_PPC_DCR_MMIO is not set +CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -72,14 +75,24 @@ CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_CGROUPS is not set # CONFIG_GROUP_SCHED is not set +# CONFIG_CGROUPS is not set CONFIG_SYSFS_DEPRECATED=y CONFIG_SYSFS_DEPRECATED_V2=y # CONFIG_RELAY is not set @@ -88,23 +101,27 @@ CONFIG_NAMESPACES=y # CONFIG_IPC_NS is not set # CONFIG_USER_NS is not set # CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_SYSCTL=y +CONFIG_ANON_INODES=y # CONFIG_EMBEDDED is not set CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y # CONFIG_KALLSYMS_EXTRA_PASS is not set +# CONFIG_STRIP_ASM_SYMS is not set CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y -# CONFIG_COMPAT_BRK is not set CONFIG_BASE_FULL=y CONFIG_FUTEX=y -CONFIG_ANON_INODES=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y CONFIG_TIMERFD=y @@ -114,10 +131,12 @@ CONFIG_AIO=y CONFIG_VM_EVENT_COUNTERS=y CONFIG_PCI_QUIRKS=y CONFIG_SLUB_DEBUG=y +# CONFIG_COMPAT_BRK is not set # CONFIG_SLAB is not set CONFIG_SLUB=y # CONFIG_SLOB is not set CONFIG_PROFILING=y +CONFIG_TRACEPOINTS=y # CONFIG_MARKERS is not set CONFIG_OPROFILE=y CONFIG_HAVE_OPROFILE=y @@ -127,10 +146,10 @@ CONFIG_HAVE_IOREMAP_PROT=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_ARCH_TRACEHOOK=y +# CONFIG_SLOW_WORK is not set # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y -# CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 CONFIG_MODULES=y # CONFIG_MODULE_FORCE_LOAD is not set @@ -138,11 +157,8 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y CONFIG_BLOCK=y CONFIG_LBD=y -# CONFIG_BLK_DEV_IO_TRACE is not set -CONFIG_LSF=y CONFIG_BLK_DEV_BSG=y # CONFIG_BLK_DEV_INTEGRITY is not set @@ -158,14 +174,11 @@ CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="anticipatory" -CONFIG_CLASSIC_RCU=y CONFIG_FREEZER=y # # Platform support # -CONFIG_PPC_MULTIPLATFORM=y -CONFIG_CLASSIC32=y # CONFIG_PPC_CHRP is not set # CONFIG_MPC5121_ADS is not set # CONFIG_MPC5121_GENERIC is not set @@ -178,7 +191,9 @@ CONFIG_PPC_PMAC=y # CONFIG_PPC_83xx is not set # CONFIG_PPC_86xx is not set # CONFIG_EMBEDDED6xx is not set +# CONFIG_AMIGAONE is not set CONFIG_PPC_NATIVE=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y # CONFIG_IPIC is not set CONFIG_MPIC=y # CONFIG_MPIC_WEIRD is not set @@ -212,11 +227,12 @@ CONFIG_CPU_FREQ_PMAC=y CONFIG_PPC601_SYNC_FIX=y # CONFIG_TAU is not set # CONFIG_FSL_ULI1575 is not set +# CONFIG_SIMPLE_GPIO is not set # # Kernel options # -# CONFIG_HIGHMEM is not set +CONFIG_HIGHMEM=y CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -239,6 +255,7 @@ CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y CONFIG_ARCH_HAS_WALK_MEMORY=y CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y # CONFIG_KEXEC is not set +# CONFIG_CRASH_DUMP is not set CONFIG_ARCH_FLATMEM_ENABLE=y CONFIG_ARCH_POPULATES_NODE_MAP=y CONFIG_SELECT_MEMORY_MODEL=y @@ -250,12 +267,17 @@ CONFIG_FLAT_NODE_MEM_MAP=y CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 # CONFIG_MIGRATION is not set -# CONFIG_RESOURCES_64BIT is not set # CONFIG_PHYS_ADDR_T_64BIT is not set CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y CONFIG_UNEVICTABLE_LRU=y +CONFIG_HAVE_MLOCK=y +CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_PPC_4K_PAGES=y +# CONFIG_PPC_16K_PAGES is not set +# CONFIG_PPC_64K_PAGES is not set +# CONFIG_PPC_256K_PAGES is not set CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set @@ -288,6 +310,8 @@ CONFIG_ARCH_SUPPORTS_MSI=y # CONFIG_PCI_MSI is not set # CONFIG_PCI_LEGACY is not set # CONFIG_PCI_DEBUG is not set +# CONFIG_PCI_STUB is not set +# CONFIG_PCI_IOV is not set CONFIG_PCCARD=m # CONFIG_PCMCIA_DEBUG is not set CONFIG_PCMCIA=m @@ -397,6 +421,8 @@ CONFIG_NETFILTER_XTABLES=m CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m # CONFIG_NETFILTER_XT_TARGET_CONNMARK is not set # CONFIG_NETFILTER_XT_TARGET_DSCP is not set +CONFIG_NETFILTER_XT_TARGET_HL=m +# CONFIG_NETFILTER_XT_TARGET_LED is not set CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m @@ -405,6 +431,7 @@ CONFIG_NETFILTER_XT_TARGET_RATEEST=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m +# CONFIG_NETFILTER_XT_MATCH_CLUSTER is not set CONFIG_NETFILTER_XT_MATCH_COMMENT=m # CONFIG_NETFILTER_XT_MATCH_CONNBYTES is not set CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m @@ -415,6 +442,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m # CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_HL=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_LIMIT=m @@ -478,17 +506,15 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_IP_DCCP=m CONFIG_INET_DCCP_DIAG=m -CONFIG_IP_DCCP_ACKVEC=y # # DCCP CCIDs Configuration (EXPERIMENTAL) # -CONFIG_IP_DCCP_CCID2=m # CONFIG_IP_DCCP_CCID2_DEBUG is not set -CONFIG_IP_DCCP_CCID3=m +CONFIG_IP_DCCP_CCID3=y # CONFIG_IP_DCCP_CCID3_DEBUG is not set CONFIG_IP_DCCP_CCID3_RTO=100 -CONFIG_IP_DCCP_TFRC_LIB=m +CONFIG_IP_DCCP_TFRC_LIB=y # # DCCP Kernel Hacking @@ -508,13 +534,16 @@ CONFIG_IP_DCCP_TFRC_LIB=m # CONFIG_LAPB is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set +# CONFIG_PHONET is not set # CONFIG_NET_SCHED is not set CONFIG_NET_CLS_ROUTE=y +# CONFIG_DCB is not set # # Network testing # # CONFIG_NET_PKTGEN is not set +# CONFIG_NET_DROP_MONITOR is not set # CONFIG_HAMRADIO is not set # CONFIG_CAN is not set CONFIG_IRDA=m @@ -577,8 +606,6 @@ CONFIG_BT_HIDP=m # # Bluetooth device drivers # -CONFIG_BT_HCIUSB=m -# CONFIG_BT_HCIUSB_SCO is not set # CONFIG_BT_HCIBTUSB is not set # CONFIG_BT_HCIUART is not set CONFIG_BT_HCIBCM203X=m @@ -590,31 +617,27 @@ CONFIG_BT_HCIBFUSB=m # CONFIG_BT_HCIBTUART is not set # CONFIG_BT_HCIVHCI is not set # CONFIG_AF_RXRPC is not set -# CONFIG_PHONET is not set CONFIG_WIRELESS=y CONFIG_CFG80211=m -CONFIG_NL80211=y +# CONFIG_CFG80211_REG_DEBUG is not set CONFIG_WIRELESS_OLD_REGULATORY=y CONFIG_WIRELESS_EXT=y CONFIG_WIRELESS_EXT_SYSFS=y +# CONFIG_LIB80211 is not set CONFIG_MAC80211=m # # Rate control algorithm selection # -CONFIG_MAC80211_RC_PID=y -# CONFIG_MAC80211_RC_MINSTREL is not set -CONFIG_MAC80211_RC_DEFAULT_PID=y -# CONFIG_MAC80211_RC_DEFAULT_MINSTREL is not set -CONFIG_MAC80211_RC_DEFAULT="pid" +CONFIG_MAC80211_RC_MINSTREL=y +# CONFIG_MAC80211_RC_DEFAULT_PID is not set +CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y +CONFIG_MAC80211_RC_DEFAULT="minstrel" # CONFIG_MAC80211_MESH is not set CONFIG_MAC80211_LEDS=y +# CONFIG_MAC80211_DEBUGFS is not set # CONFIG_MAC80211_DEBUG_MENU is not set -CONFIG_IEEE80211=m -# CONFIG_IEEE80211_DEBUG is not set -CONFIG_IEEE80211_CRYPT_WEP=m -CONFIG_IEEE80211_CRYPT_CCMP=m -CONFIG_IEEE80211_CRYPT_TKIP=m +# CONFIG_WIMAX is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -662,17 +685,27 @@ CONFIG_BLK_DEV_RAM_SIZE=4096 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_PHANTOM is not set -# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set +# CONFIG_ISL29003 is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y CONFIG_IDE=y # # Please see Documentation/ide/ide.txt for help/info on IDE drives # +CONFIG_IDE_XFER_MODE=y CONFIG_IDE_TIMINGS=y CONFIG_IDE_ATAPI=y # CONFIG_BLK_DEV_IDE_SATA is not set @@ -684,7 +717,6 @@ CONFIG_BLK_DEV_IDECS=m CONFIG_BLK_DEV_IDECD=y CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y # CONFIG_BLK_DEV_IDETAPE is not set -CONFIG_BLK_DEV_IDESCSI=y # CONFIG_IDE_TASK_IOCTL is not set CONFIG_IDE_PROC_FS=y @@ -714,6 +746,7 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y # CONFIG_BLK_DEV_JMICRON is not set # CONFIG_BLK_DEV_SC1200 is not set # CONFIG_BLK_DEV_PIIX is not set +# CONFIG_BLK_DEV_IT8172 is not set # CONFIG_BLK_DEV_IT8213 is not set # CONFIG_BLK_DEV_IT821X is not set # CONFIG_BLK_DEV_NS87415 is not set @@ -728,7 +761,6 @@ CONFIG_BLK_DEV_SL82C105=y # CONFIG_BLK_DEV_TC86C001 is not set CONFIG_BLK_DEV_IDE_PMAC=y CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y -CONFIG_BLK_DEV_IDEDMA_PMAC=y CONFIG_BLK_DEV_IDEDMA=y # @@ -772,6 +804,7 @@ CONFIG_SCSI_FC_ATTRS=y # CONFIG_SCSI_SRP_ATTRS is not set CONFIG_SCSI_LOWLEVEL=y # CONFIG_ISCSI_TCP is not set +# CONFIG_SCSI_CXGB3_ISCSI is not set # CONFIG_BLK_DEV_3W_XXXX_RAID is not set # CONFIG_SCSI_3W_9XXX is not set # CONFIG_SCSI_ACARD is not set @@ -791,8 +824,12 @@ CONFIG_SCSI_AIC7XXX_OLD=m # CONFIG_MEGARAID_NEWGEN is not set # CONFIG_MEGARAID_LEGACY is not set # CONFIG_MEGARAID_SAS is not set +# CONFIG_SCSI_MPT2SAS is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set +# CONFIG_LIBFC is not set +# CONFIG_LIBFCOE is not set +# CONFIG_FCOE is not set # CONFIG_SCSI_DMX3191D is not set # CONFIG_SCSI_EATA is not set # CONFIG_SCSI_FUTURE_DOMAIN is not set @@ -822,6 +859,7 @@ CONFIG_SCSI_MAC53C94=y # CONFIG_SCSI_SRP is not set # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set # CONFIG_SCSI_DH is not set +# CONFIG_SCSI_OSD_INITIATOR is not set # CONFIG_ATA is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=m @@ -881,6 +919,7 @@ CONFIG_THERM_ADT746X=m # CONFIG_ANSLCD is not set CONFIG_PMAC_RACKMETER=m CONFIG_NETDEVICES=y +CONFIG_COMPAT_NET_DEV_OPS=y CONFIG_DUMMY=m # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set @@ -898,6 +937,8 @@ CONFIG_BMAC=y CONFIG_SUNGEM=y # CONFIG_CASSINI is not set # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_ETHOC is not set +# CONFIG_DNET is not set # CONFIG_NET_TULIP is not set # CONFIG_HP100 is not set # CONFIG_IBM_NEW_EMAC_ZMII is not set @@ -913,7 +954,6 @@ CONFIG_PCNET32=y # CONFIG_ADAPTEC_STARFIRE is not set # CONFIG_B44 is not set # CONFIG_FORCEDETH is not set -# CONFIG_EEPRO100 is not set # CONFIG_E100 is not set # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set @@ -923,6 +963,7 @@ CONFIG_PCNET32=y # CONFIG_R6040 is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set +# CONFIG_SMSC9420 is not set # CONFIG_SUNDANCE is not set # CONFIG_TLAN is not set # CONFIG_VIA_RHINE is not set @@ -935,6 +976,7 @@ CONFIG_NETDEV_1000=y # CONFIG_E1000E is not set # CONFIG_IP1000 is not set # CONFIG_IGB is not set +# CONFIG_IGBVF is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set @@ -945,18 +987,20 @@ CONFIG_NETDEV_1000=y # CONFIG_VIA_VELOCITY is not set # CONFIG_TIGON3 is not set # CONFIG_BNX2 is not set -# CONFIG_MV643XX_ETH is not set # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set # CONFIG_ATL1E is not set +# CONFIG_ATL1C is not set # CONFIG_JME is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set +CONFIG_CHELSIO_T3_DEPENDS=y # CONFIG_CHELSIO_T3 is not set # CONFIG_ENIC is not set # CONFIG_IXGBE is not set # CONFIG_IXGB is not set # CONFIG_S2IO is not set +# CONFIG_VXGE is not set # CONFIG_MYRI10GE is not set # CONFIG_NETXEN_NIC is not set # CONFIG_NIU is not set @@ -966,6 +1010,7 @@ CONFIG_NETDEV_10000=y # CONFIG_BNX2X is not set # CONFIG_QLGE is not set # CONFIG_SFC is not set +# CONFIG_BE2NET is not set # CONFIG_TR is not set # @@ -974,20 +1019,11 @@ CONFIG_NETDEV_10000=y # CONFIG_WLAN_PRE80211 is not set CONFIG_WLAN_80211=y # CONFIG_PCMCIA_RAYCS is not set -# CONFIG_IPW2100 is not set -# CONFIG_IPW2200 is not set # CONFIG_LIBERTAS is not set # CONFIG_LIBERTAS_THINFIRM is not set # CONFIG_AIRO is not set -CONFIG_HERMES=m -CONFIG_APPLE_AIRPORT=m -# CONFIG_PLX_HERMES is not set -# CONFIG_TMD_HERMES is not set -# CONFIG_NORTEL_HERMES is not set -CONFIG_PCI_HERMES=m -CONFIG_PCMCIA_HERMES=m -# CONFIG_PCMCIA_SPECTRUM is not set # CONFIG_ATMEL is not set +# CONFIG_AT76C50X_USB is not set # CONFIG_AIRO_CS is not set # CONFIG_PCMCIA_WL3501 is not set CONFIG_PRISM54=m @@ -997,15 +1033,17 @@ CONFIG_PRISM54=m # CONFIG_RTL8187 is not set # CONFIG_ADM8211 is not set # CONFIG_MAC80211_HWSIM is not set +# CONFIG_MWL8K is not set CONFIG_P54_COMMON=m # CONFIG_P54_USB is not set # CONFIG_P54_PCI is not set +CONFIG_P54_LEDS=y # CONFIG_ATH5K is not set # CONFIG_ATH9K is not set -# CONFIG_IWLCORE is not set -# CONFIG_IWLWIFI_LEDS is not set -# CONFIG_IWLAGN is not set -# CONFIG_IWL3945 is not set +# CONFIG_AR9170_USB is not set +# CONFIG_IPW2100 is not set +# CONFIG_IPW2200 is not set +# CONFIG_IWLWIFI is not set # CONFIG_HOSTAP is not set CONFIG_B43=m CONFIG_B43_PCI_AUTOSELECT=y @@ -1025,6 +1063,19 @@ CONFIG_B43LEGACY_DMA_AND_PIO_MODE=y # CONFIG_B43LEGACY_PIO_MODE is not set # CONFIG_ZD1211RW is not set # CONFIG_RT2X00 is not set +CONFIG_HERMES=m +CONFIG_HERMES_CACHE_FW_ON_INIT=y +CONFIG_APPLE_AIRPORT=m +# CONFIG_PLX_HERMES is not set +# CONFIG_TMD_HERMES is not set +# CONFIG_NORTEL_HERMES is not set +CONFIG_PCI_HERMES=m +CONFIG_PCMCIA_HERMES=m +# CONFIG_PCMCIA_SPECTRUM is not set + +# +# Enable WiMAX (Networking options) to see the WiMAX drivers +# # # USB Network Adapters @@ -1036,6 +1087,7 @@ CONFIG_B43LEGACY_DMA_AND_PIO_MODE=y CONFIG_USB_USBNET=m CONFIG_USB_NET_AX8817X=m CONFIG_USB_NET_CDCETHER=m +# CONFIG_USB_NET_CDC_EEM is not set # CONFIG_USB_NET_DM9601 is not set # CONFIG_USB_NET_SMSC95XX is not set # CONFIG_USB_NET_GL620A is not set @@ -1099,7 +1151,7 @@ CONFIG_INPUT_KEYBOARD=y CONFIG_INPUT_MOUSE=y # CONFIG_MOUSE_PS2 is not set # CONFIG_MOUSE_SERIAL is not set -# CONFIG_MOUSE_APPLETOUCH is not set +CONFIG_MOUSE_APPLETOUCH=y # CONFIG_MOUSE_BCM5974 is not set # CONFIG_MOUSE_VSXXXAA is not set # CONFIG_INPUT_JOYSTICK is not set @@ -1150,10 +1202,13 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y # CONFIG_SERIAL_JSM is not set # CONFIG_SERIAL_OF_PLATFORM is not set CONFIG_UNIX98_PTYS=y +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_HVC_UDBG is not set # CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=m +# CONFIG_HW_RANDOM_TIMERIOMEM is not set CONFIG_NVRAM=y CONFIG_GEN_RTC=y # CONFIG_GEN_RTC_X is not set @@ -1232,12 +1287,9 @@ CONFIG_I2C_POWERMAC=y # Miscellaneous I2C Chip support # # CONFIG_DS1682 is not set -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_PCF8591 is not set # CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set @@ -1259,11 +1311,11 @@ CONFIG_BATTERY_PMU=y # CONFIG_THERMAL is not set # CONFIG_THERMAL_HWMON is not set # CONFIG_WATCHDOG is not set +CONFIG_SSB_POSSIBLE=y # # Sonics Silicon Backplane # -CONFIG_SSB_POSSIBLE=y CONFIG_SSB=m CONFIG_SSB_SPROM=y CONFIG_SSB_PCIHOST_POSSIBLE=y @@ -1281,18 +1333,13 @@ CONFIG_SSB_DRIVER_PCICORE=y # CONFIG_MFD_CORE is not set # CONFIG_MFD_SM501 is not set # CONFIG_HTC_PASIC3 is not set +# CONFIG_TWL4030_CORE is not set # CONFIG_MFD_TMIO is not set # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set - -# -# Voltage and Current regulators -# +# CONFIG_MFD_PCF50633 is not set # CONFIG_REGULATOR is not set -# CONFIG_REGULATOR_FIXED_VOLTAGE is not set -# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set -# CONFIG_REGULATOR_BQ24022 is not set # # Multimedia devices @@ -1390,6 +1437,7 @@ CONFIG_FB_ATY_BACKLIGHT=y # CONFIG_FB_KYRO is not set CONFIG_FB_3DFX=y # CONFIG_FB_3DFX_ACCEL is not set +CONFIG_FB_3DFX_I2C=y # CONFIG_FB_VOODOO1 is not set # CONFIG_FB_VT8623 is not set # CONFIG_FB_TRIDENT is not set @@ -1399,12 +1447,14 @@ CONFIG_FB_3DFX=y # CONFIG_FB_IBM_GXT4500 is not set # CONFIG_FB_VIRTUAL is not set # CONFIG_FB_METRONOME is not set +# CONFIG_FB_MB862XX is not set +# CONFIG_FB_BROADSHEET is not set CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_LCD_CLASS_DEVICE=m # CONFIG_LCD_ILI9320 is not set # CONFIG_LCD_PLATFORM is not set CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_BACKLIGHT_CORGI is not set +CONFIG_BACKLIGHT_GENERIC=y # # Display device support @@ -1444,11 +1494,13 @@ CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m CONFIG_SND_PCM_OSS_PLUGINS=y CONFIG_SND_SEQUENCER_OSS=y +# CONFIG_SND_HRTIMER is not set # CONFIG_SND_DYNAMIC_MINORS is not set CONFIG_SND_SUPPORT_OLD_API=y CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_VERBOSE_PRINTK is not set # CONFIG_SND_DEBUG is not set +CONFIG_SND_VMASTER=y CONFIG_SND_DRIVERS=y CONFIG_SND_DUMMY=m # CONFIG_SND_VIRMIDI is not set @@ -1486,6 +1538,8 @@ CONFIG_SND_PCI=y # CONFIG_SND_INDIGO is not set # CONFIG_SND_INDIGOIO is not set # CONFIG_SND_INDIGODJ is not set +# CONFIG_SND_INDIGOIOX is not set +# CONFIG_SND_INDIGODJX is not set # CONFIG_SND_EMU10K1 is not set # CONFIG_SND_EMU10K1X is not set # CONFIG_SND_ENS1370 is not set @@ -1551,28 +1605,31 @@ CONFIG_USB_HID=y # # Special HID drivers # -CONFIG_HID_COMPAT=y CONFIG_HID_A4TECH=y CONFIG_HID_APPLE=y CONFIG_HID_BELKIN=y -CONFIG_HID_BRIGHT=y CONFIG_HID_CHERRY=y CONFIG_HID_CHICONY=y CONFIG_HID_CYPRESS=y -CONFIG_HID_DELL=y +# CONFIG_DRAGONRISE_FF is not set CONFIG_HID_EZKEY=y +CONFIG_HID_KYE=y CONFIG_HID_GYRATION=y +CONFIG_HID_KENSINGTON=y CONFIG_HID_LOGITECH=y # CONFIG_LOGITECH_FF is not set # CONFIG_LOGIRUMBLEPAD2_FF is not set CONFIG_HID_MICROSOFT=y CONFIG_HID_MONTEREY=y +CONFIG_HID_NTRIG=y CONFIG_HID_PANTHERLORD=y # CONFIG_PANTHERLORD_FF is not set CONFIG_HID_PETALYNX=y CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y +# CONFIG_GREENASIA_FF is not set +CONFIG_HID_TOPSEED=y # CONFIG_THRUSTMASTER_FF is not set # CONFIG_ZEROPLUS_FF is not set CONFIG_USB_SUPPORT=y @@ -1603,6 +1660,7 @@ CONFIG_USB_EHCI_HCD=m CONFIG_USB_EHCI_ROOT_HUB_TT=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set # CONFIG_USB_EHCI_HCD_PPC_OF is not set +# CONFIG_USB_OXU210HP_HCD is not set # CONFIG_USB_ISP116X_HCD is not set # CONFIG_USB_ISP1760_HCD is not set CONFIG_USB_OHCI_HCD=y @@ -1625,24 +1683,23 @@ CONFIG_USB_PRINTER=m # CONFIG_USB_TMC is not set # -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' +# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may # # -# may also be needed; see USB_STORAGE Help for more information +# also be needed; see USB_STORAGE Help for more info # CONFIG_USB_STORAGE=m # CONFIG_USB_STORAGE_DEBUG is not set # CONFIG_USB_STORAGE_DATAFAB is not set # CONFIG_USB_STORAGE_FREECOM is not set # CONFIG_USB_STORAGE_ISD200 is not set -# CONFIG_USB_STORAGE_DPCM is not set # CONFIG_USB_STORAGE_USBAT is not set # CONFIG_USB_STORAGE_SDDR09 is not set # CONFIG_USB_STORAGE_SDDR55 is not set # CONFIG_USB_STORAGE_JUMPSHOT is not set # CONFIG_USB_STORAGE_ALAUDA is not set -CONFIG_USB_STORAGE_ONETOUCH=y +CONFIG_USB_STORAGE_ONETOUCH=m # CONFIG_USB_STORAGE_KARMA is not set # CONFIG_USB_STORAGE_CYPRESS_ATACB is not set # CONFIG_USB_LIBUSUAL is not set @@ -1665,7 +1722,7 @@ CONFIG_USB_EZUSB=y # CONFIG_USB_SERIAL_CH341 is not set # CONFIG_USB_SERIAL_WHITEHEAT is not set # CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set -# CONFIG_USB_SERIAL_CP2101 is not set +# CONFIG_USB_SERIAL_CP210X is not set # CONFIG_USB_SERIAL_CYPRESS_M8 is not set # CONFIG_USB_SERIAL_EMPEG is not set # CONFIG_USB_SERIAL_FTDI_SIO is not set @@ -1701,15 +1758,19 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y # CONFIG_USB_SERIAL_NAVMAN is not set # CONFIG_USB_SERIAL_PL2303 is not set # CONFIG_USB_SERIAL_OTI6858 is not set +# CONFIG_USB_SERIAL_QUALCOMM is not set # CONFIG_USB_SERIAL_SPCP8X5 is not set # CONFIG_USB_SERIAL_HP4X is not set # CONFIG_USB_SERIAL_SAFE is not set +# CONFIG_USB_SERIAL_SIEMENS_MPI is not set # CONFIG_USB_SERIAL_SIERRAWIRELESS is not set +# CONFIG_USB_SERIAL_SYMBOL is not set # CONFIG_USB_SERIAL_TI is not set # CONFIG_USB_SERIAL_CYBERJACK is not set # CONFIG_USB_SERIAL_XIRCOM is not set # CONFIG_USB_SERIAL_OPTION is not set # CONFIG_USB_SERIAL_OMNINET is not set +# CONFIG_USB_SERIAL_OPTICON is not set # CONFIG_USB_SERIAL_DEBUG is not set # @@ -1726,7 +1787,6 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y # CONFIG_USB_LED is not set # CONFIG_USB_CYPRESS_CY7C63 is not set # CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGET is not set # CONFIG_USB_IDMOUSE is not set # CONFIG_USB_FTDI_ELAN is not set CONFIG_USB_APPLEDISPLAY=m @@ -1738,6 +1798,11 @@ CONFIG_USB_APPLEDISPLAY=m # CONFIG_USB_ISIGHTFW is not set # CONFIG_USB_VST is not set # CONFIG_USB_GADGET is not set + +# +# OTG and related infrastructure +# +# CONFIG_NOP_USB_XCEIV is not set # CONFIG_UWB is not set # CONFIG_MMC is not set # CONFIG_MEMSTICK is not set @@ -1748,7 +1813,9 @@ CONFIG_LEDS_CLASS=y # LED drivers # # CONFIG_LEDS_PCA9532 is not set +# CONFIG_LEDS_LP5521 is not set # CONFIG_LEDS_PCA955X is not set +# CONFIG_LEDS_BD2802 is not set # # LED Triggers @@ -1759,11 +1826,16 @@ CONFIG_LEDS_TRIGGER_IDE_DISK=y # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set CONFIG_LEDS_TRIGGER_DEFAULT_ON=y + +# +# iptables trigger is under Netfilter config (LED target) +# # CONFIG_ACCESSIBILITY is not set # CONFIG_INFINIBAND is not set # CONFIG_EDAC is not set # CONFIG_RTC_CLASS is not set # CONFIG_DMADEVICES is not set +# CONFIG_AUXDISPLAY is not set # CONFIG_UIO is not set # CONFIG_STAGING is not set @@ -1774,6 +1846,7 @@ CONFIG_EXT2_FS=y # CONFIG_EXT2_FS_XATTR is not set # CONFIG_EXT2_FS_XIP is not set CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y # CONFIG_EXT3_FS_SECURITY is not set @@ -1783,7 +1856,9 @@ CONFIG_EXT4_FS_XATTR=y # CONFIG_EXT4_FS_POSIX_ACL is not set # CONFIG_EXT4_FS_SECURITY is not set CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set CONFIG_JBD2=y +# CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set @@ -1792,6 +1867,7 @@ CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y @@ -1801,6 +1877,11 @@ CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m # +# Caches +# +# CONFIG_FSCACHE is not set + +# # CD-ROM/DVD Filesystems # CONFIG_ISO9660_FS=y @@ -1831,10 +1912,7 @@ CONFIG_TMPFS=y # CONFIG_TMPFS_POSIX_ACL is not set # CONFIG_HUGETLB_PAGE is not set # CONFIG_CONFIGFS_FS is not set - -# -# Miscellaneous filesystems -# +CONFIG_MISC_FILESYSTEMS=y # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set CONFIG_HFS_FS=m @@ -1843,6 +1921,7 @@ CONFIG_HFSPLUS_FS=m # CONFIG_BFS_FS is not set # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set +# CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_OMFS_FS is not set @@ -1851,6 +1930,7 @@ CONFIG_HFSPLUS_FS=m # CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set +# CONFIG_NILFS2_FS is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y @@ -1868,7 +1948,6 @@ CONFIG_NFS_ACL_SUPPORT=y CONFIG_NFS_COMMON=y CONFIG_SUNRPC=y CONFIG_SUNRPC_GSS=y -# CONFIG_SUNRPC_REGISTER_V4 is not set CONFIG_RPCSEC_GSS_KRB5=y # CONFIG_RPCSEC_GSS_SPKM3 is not set CONFIG_SMB_FS=m @@ -1940,11 +2019,13 @@ CONFIG_NLS_ISO8859_1=m # CONFIG_NLS_KOI8_U is not set CONFIG_NLS_UTF8=m # CONFIG_DLM is not set +CONFIG_BINARY_PRINTF=y # # Library routines # CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_LAST_BIT=y CONFIG_CRC_CCITT=y CONFIG_CRC16=y CONFIG_CRC_T10DIF=y @@ -1954,15 +2035,18 @@ CONFIG_CRC32=y CONFIG_LIBCRC32C=m CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y +CONFIG_DECOMPRESS_GZIP=y +CONFIG_DECOMPRESS_BZIP2=y +CONFIG_DECOMPRESS_LZMA=y CONFIG_TEXTSEARCH=y CONFIG_TEXTSEARCH_KMP=m CONFIG_TEXTSEARCH_BM=m CONFIG_TEXTSEARCH_FSM=m -CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y CONFIG_HAVE_LMB=y +CONFIG_NLATTR=y # # Kernel hacking @@ -1973,13 +2057,16 @@ CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set -# CONFIG_DEBUG_FS is not set +CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set CONFIG_DETECT_SOFTLOCKUP=y # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +CONFIG_DETECT_HUNG_TASK=y +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 CONFIG_SCHED_DEBUG=y CONFIG_SCHEDSTATS=y # CONFIG_TIMER_STATS is not set @@ -1994,6 +2081,7 @@ CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set CONFIG_STACKTRACE=y # CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set @@ -2001,6 +2089,7 @@ CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set # CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_CPU_STALL_DETECTOR is not set @@ -2009,7 +2098,14 @@ CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_FAULT_INJECTION is not set CONFIG_LATENCYTOP=y CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_NOP_TRACER=y CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y +CONFIG_RING_BUFFER=y +CONFIG_TRACING=y +CONFIG_TRACING_SUPPORT=y # # Tracers @@ -2017,12 +2113,19 @@ CONFIG_HAVE_FUNCTION_TRACER=y # CONFIG_FUNCTION_TRACER is not set # CONFIG_SCHED_TRACER is not set # CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_EVENT_TRACER is not set # CONFIG_BOOT_TRACER is not set +# CONFIG_TRACE_BRANCH_PROFILING is not set # CONFIG_STACK_TRACER is not set -# CONFIG_DYNAMIC_PRINTK_DEBUG is not set +# CONFIG_KMEMTRACE is not set +# CONFIG_WORKQUEUE_TRACER is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_FTRACE_STARTUP_TEST is not set +# CONFIG_DYNAMIC_DEBUG is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set +CONFIG_PRINT_STACK_DEPTH=64 # CONFIG_DEBUG_STACKOVERFLOW is not set # CONFIG_DEBUG_STACK_USAGE is not set # CONFIG_CODE_PATCHING_SELFTEST is not set @@ -2033,6 +2136,7 @@ CONFIG_XMON_DEFAULT=y CONFIG_XMON_DISASSEMBLY=y CONFIG_DEBUGGER=y CONFIG_IRQSTACKS=y +# CONFIG_VIRQ_DEBUG is not set # CONFIG_BDI_SWITCH is not set CONFIG_BOOTX_TEXT=y # CONFIG_PPC_EARLY_DEBUG is not set @@ -2051,13 +2155,20 @@ CONFIG_CRYPTO=y # # CONFIG_CRYPTO_FIPS is not set CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_AEAD2=y CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_BLKCIPHER2=y CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_RNG=y +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG2=y +CONFIG_CRYPTO_PCOMP=y CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y # CONFIG_CRYPTO_GF128MUL is not set CONFIG_CRYPTO_NULL=m +CONFIG_CRYPTO_WORKQUEUE=y # CONFIG_CRYPTO_CRYPTD is not set CONFIG_CRYPTO_AUTHENC=y # CONFIG_CRYPTO_TEST is not set @@ -2127,6 +2238,7 @@ CONFIG_CRYPTO_TWOFISH_COMMON=m # Compression # CONFIG_CRYPTO_DEFLATE=m +# CONFIG_CRYPTO_ZLIB is not set # CONFIG_CRYPTO_LZO is not set # diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index b7e034b..5351237 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -131,5 +131,41 @@ static inline int irqs_disabled_flags(unsigned long flags) */ struct irq_chip; +#ifdef CONFIG_PERF_COUNTERS +static inline unsigned long test_perf_counter_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, perf_counter_pending))); + return x; +} + +static inline void set_perf_counter_pending(void) +{ + asm volatile("stb %0,%1(13)" : : + "r" (1), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +static inline void clear_perf_counter_pending(void) +{ + asm volatile("stb %0,%1(13)" : : + "r" (0), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +#else + +static inline unsigned long test_perf_counter_pending(void) +{ + return 0; +} + +static inline void set_perf_counter_pending(void) {} +static inline void clear_perf_counter_pending(void) {} +#endif /* CONFIG_PERF_COUNTERS */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 0ea1985..c8a3cbf 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -105,6 +105,7 @@ struct paca_struct { u8 soft_enabled; /* irq soft-enable flag */ u8 hard_enabled; /* set if irqs are enabled in MSR */ u8 io_sync; /* writel() needs spin_unlock sync */ + u8 perf_counter_pending; /* PM interrupt while soft-disabled */ /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h new file mode 100644 index 0000000..cc7c887 --- /dev/null +++ b/arch/powerpc/include/asm/perf_counter.h @@ -0,0 +1,98 @@ +/* + * Performance counter support - PowerPC-specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/types.h> + +#define MAX_HWCOUNTERS 8 +#define MAX_EVENT_ALTERNATIVES 8 +#define MAX_LIMITED_HWCOUNTERS 2 + +/* + * This struct provides the constants and functions needed to + * describe the PMU on a particular POWER-family CPU. + */ +struct power_pmu { + int n_counter; + int max_alternatives; + u64 add_fields; + u64 test_adder; + int (*compute_mmcr)(u64 events[], int n_ev, + unsigned int hwc[], u64 mmcr[]); + int (*get_constraint)(u64 event, u64 *mskp, u64 *valp); + int (*get_alternatives)(u64 event, unsigned int flags, + u64 alt[]); + void (*disable_pmc)(unsigned int pmc, u64 mmcr[]); + int (*limited_pmc_event)(u64 event); + u32 flags; + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +extern struct power_pmu *ppmu; + +/* + * Values for power_pmu.flags + */ +#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ +#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ + +/* + * Values for flags to get_alternatives() + */ +#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ +#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ +#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ + +struct pt_regs; +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) + +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); + +/* + * The power_pmu.get_constraint function returns a 64-bit value and + * a 64-bit mask that express the constraints between this event and + * other events. + * + * The value and mask are divided up into (non-overlapping) bitfields + * of three different types: + * + * Select field: this expresses the constraint that some set of bits + * in MMCR* needs to be set to a specific value for this event. For a + * select field, the mask contains 1s in every bit of the field, and + * the value contains a unique value for each possible setting of the + * MMCR* bits. The constraint checking code will ensure that two events + * that set the same field in their masks have the same value in their + * value dwords. + * + * Add field: this expresses the constraint that there can be at most + * N events in a particular class. A field of k bits can be used for + * N <= 2^(k-1) - 1. The mask has the most significant bit of the field + * set (and the other bits 0), and the value has only the least significant + * bit of the field set. In addition, the 'add_fields' and 'test_adder' + * in the struct power_pmu for this processor come into play. The + * add_fields value contains 1 in the LSB of the field, and the + * test_adder contains 2^(k-1) - 1 - N in the field. + * + * NAND field: this expresses the constraint that you may not have events + * in all of a set of classes. (For example, on PPC970, you can't select + * events from the FPU, ISU and IDU simultaneously, although any two are + * possible.) For N classes, the field is N+1 bits wide, and each class + * is assigned one bit from the least-significant N bits. The mask has + * only the most-significant bit set, and the value has only the bit + * for the event's class set. The test_adder has the least significant + * bit set in the field. + * + * If an event is not subject to the constraint expressed by a particular + * field, then it will have 0 in both the mask and value for that field. + */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e8018d5..fb359b0 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -492,11 +492,13 @@ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 #define SPRN_MMCRA 0x312 +#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */ #define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ #define MMCRA_SLOT_SHIFT 24 #define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */ +#define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */ #define POWER6_MMCRA_SIHV 0x0000040000000000ULL #define POWER6_MMCRA_SIPR 0x0000020000000000ULL #define POWER6_MMCRA_THRM 0x00000020UL diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index d98a30d..a0b92de 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -322,6 +322,6 @@ SYSCALL_SPU(epoll_create1) SYSCALL_SPU(dup3) SYSCALL_SPU(pipe2) SYSCALL(inotify_init1) -SYSCALL(ni_syscall) +SYSCALL_SPU(perf_counter_open) COMPAT_SYS_SPU(preadv) COMPAT_SYS_SPU(pwritev) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 3f06f8e..4badac2 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -341,6 +341,7 @@ #define __NR_dup3 316 #define __NR_pipe2 317 #define __NR_inotify_init1 318 +#define __NR_perf_counter_open 319 #define __NR_preadv 320 #define __NR_pwritev 321 diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 65cf365..a7def5f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -95,6 +95,9 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \ + power5-pmu.o power5+-pmu.o power6-pmu.o \ + power7-pmu.o obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ce90c57..561b646 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -129,6 +129,7 @@ int main(void) DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr)); DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled)); DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled)); + DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending)); DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); #ifdef CONFIG_PPC_MM_SLICES DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index abfc323..43e0734 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) 2: TRACE_AND_RESTORE_IRQ(r5); +#ifdef CONFIG_PERF_COUNTERS + /* check paca->perf_counter_pending if we're enabling ints */ + lbz r3,PACAPERFPEND(r13) + and. r3,r3,r5 + beq 27f + bl .perf_counter_do_pending +27: +#endif /* CONFIG_PERF_COUNTERS */ + /* extract EE bit and use it to restore paca->hard_enabled */ ld r3,_MSR(r1) rldicl r4,r3,49,63 /* r0 = (r3 >> 15) & 1 */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 8564a41..f7f376e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -53,6 +53,7 @@ #include <linux/bootmem.h> #include <linux/pci.h> #include <linux/debugfs.h> +#include <linux/perf_counter.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -137,6 +138,11 @@ notrace void raw_local_irq_restore(unsigned long en) } #endif /* CONFIG_PPC_STD_MMU_64 */ + if (test_perf_counter_pending()) { + clear_perf_counter_pending(); + perf_counter_do_pending(); + } + /* * if (get_paca()->hard_enabled) return; * But again we need to take care that gcc gets hard_enabled directly diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c new file mode 100644 index 0000000..bb20238 --- /dev/null +++ b/arch/powerpc/kernel/perf_counter.c @@ -0,0 +1,1263 @@ +/* + * Performance counter support - powerpc architecture code + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/perf_counter.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <asm/reg.h> +#include <asm/pmc.h> +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/ptrace.h> + +struct cpu_hw_counters { + int n_counters; + int n_percpu; + int disabled; + int n_added; + int n_limited; + u8 pmcs_enabled; + struct perf_counter *counter[MAX_HWCOUNTERS]; + u64 events[MAX_HWCOUNTERS]; + unsigned int flags[MAX_HWCOUNTERS]; + u64 mmcr[3]; + struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS]; + u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS]; +}; +DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters); + +struct power_pmu *ppmu; + +/* + * Normally, to ignore kernel events we set the FCS (freeze counters + * in supervisor mode) bit in MMCR0, but if the kernel runs with the + * hypervisor bit set in the MSR, or if we are running on a processor + * where the hypervisor bit is forced to 1 (as on Apple G5 processors), + * then we need to use the FCHV bit to ignore kernel events. + */ +static unsigned int freeze_counters_kernel = MMCR0_FCS; + +static void perf_counter_interrupt(struct pt_regs *regs); + +void perf_counter_print_debug(void) +{ +} + +/* + * Read one performance monitor counter (PMC). + */ +static unsigned long read_pmc(int idx) +{ + unsigned long val; + + switch (idx) { + case 1: + val = mfspr(SPRN_PMC1); + break; + case 2: + val = mfspr(SPRN_PMC2); + break; + case 3: + val = mfspr(SPRN_PMC3); + break; + case 4: + val = mfspr(SPRN_PMC4); + break; + case 5: + val = mfspr(SPRN_PMC5); + break; + case 6: + val = mfspr(SPRN_PMC6); + break; + case 7: + val = mfspr(SPRN_PMC7); + break; + case 8: + val = mfspr(SPRN_PMC8); + break; + default: + printk(KERN_ERR "oops trying to read PMC%d\n", idx); + val = 0; + } + return val; +} + +/* + * Write one PMC. + */ +static void write_pmc(int idx, unsigned long val) +{ + switch (idx) { + case 1: + mtspr(SPRN_PMC1, val); + break; + case 2: + mtspr(SPRN_PMC2, val); + break; + case 3: + mtspr(SPRN_PMC3, val); + break; + case 4: + mtspr(SPRN_PMC4, val); + break; + case 5: + mtspr(SPRN_PMC5, val); + break; + case 6: + mtspr(SPRN_PMC6, val); + break; + case 7: + mtspr(SPRN_PMC7, val); + break; + case 8: + mtspr(SPRN_PMC8, val); + break; + default: + printk(KERN_ERR "oops trying to write PMC%d\n", idx); + } +} + +/* + * 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 + * and see if any combination of alternative codes is feasible. + * The feasible set is returned in event[]. + */ +static int power_check_constraints(u64 event[], unsigned int cflags[], + int n_ev) +{ + u64 mask, value, nv; + u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS]; + int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS]; + int i, j; + u64 addf = ppmu->add_fields; + u64 tadd = ppmu->test_adder; + + if (n_ev > ppmu->n_counter) + return -1; + + /* First see if the events will go on as-is */ + for (i = 0; i < n_ev; ++i) { + if ((cflags[i] & PPMU_LIMITED_PMC_REQD) + && !ppmu->limited_pmc_event(event[i])) { + ppmu->get_alternatives(event[i], cflags[i], + alternatives[i]); + event[i] = alternatives[i][0]; + } + if (ppmu->get_constraint(event[i], &amasks[i][0], + &avalues[i][0])) + return -1; + } + value = mask = 0; + for (i = 0; i < n_ev; ++i) { + nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf); + if ((((nv + tadd) ^ value) & mask) != 0 || + (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0) + break; + value = nv; + mask |= amasks[i][0]; + } + if (i == n_ev) + return 0; /* all OK */ + + /* doesn't work, gather alternatives... */ + if (!ppmu->get_alternatives) + return -1; + for (i = 0; i < n_ev; ++i) { + choice[i] = 0; + n_alt[i] = ppmu->get_alternatives(event[i], cflags[i], + alternatives[i]); + for (j = 1; j < n_alt[i]; ++j) + ppmu->get_constraint(alternatives[i][j], + &amasks[i][j], &avalues[i][j]); + } + + /* enumerate all possibilities and see if any will work */ + i = 0; + j = -1; + value = mask = nv = 0; + while (i < n_ev) { + if (j >= 0) { + /* we're backtracking, restore context */ + value = svalues[i]; + mask = smasks[i]; + j = choice[i]; + } + /* + * See if any alternative k for event i, + * where k > j, will satisfy the constraints. + */ + while (++j < n_alt[i]) { + nv = (value | avalues[i][j]) + + (value & avalues[i][j] & addf); + if ((((nv + tadd) ^ value) & mask) == 0 && + (((nv + tadd) ^ avalues[i][j]) + & amasks[i][j]) == 0) + break; + } + if (j >= n_alt[i]) { + /* + * No feasible alternative, backtrack + * to event i-1 and continue enumerating its + * alternatives from where we got up to. + */ + if (--i < 0) + return -1; + } else { + /* + * Found a feasible alternative for event i, + * remember where we got up to with this event, + * go on to the next event, and start with + * the first alternative for it. + */ + choice[i] = j; + svalues[i] = value; + smasks[i] = mask; + value = nv; + mask |= amasks[i][j]; + ++i; + j = -1; + } + } + + /* OK, we have a feasible combination, tell the caller the solution */ + for (i = 0; i < n_ev; ++i) + event[i] = alternatives[i][choice[i]]; + return 0; +} + +/* + * Check if newly-added counters have consistent settings for + * exclude_{user,kernel,hv} with each other and any previously + * added counters. + */ +static int check_excludes(struct perf_counter **ctrs, unsigned int cflags[], + int n_prev, int n_new) +{ + int eu = 0, ek = 0, eh = 0; + int i, n, first; + struct perf_counter *counter; + + n = n_prev + n_new; + if (n <= 1) + return 0; + + first = 1; + for (i = 0; i < n; ++i) { + if (cflags[i] & PPMU_LIMITED_PMC_OK) { + cflags[i] &= ~PPMU_LIMITED_PMC_REQD; + continue; + } + counter = ctrs[i]; + if (first) { + eu = counter->attr.exclude_user; + ek = counter->attr.exclude_kernel; + eh = counter->attr.exclude_hv; + first = 0; + } else if (counter->attr.exclude_user != eu || + counter->attr.exclude_kernel != ek || + counter->attr.exclude_hv != eh) { + return -EAGAIN; + } + } + + if (eu || ek || eh) + for (i = 0; i < n; ++i) + if (cflags[i] & PPMU_LIMITED_PMC_OK) + cflags[i] |= PPMU_LIMITED_PMC_REQD; + + return 0; +} + +static void power_pmu_read(struct perf_counter *counter) +{ + long val, delta, prev; + + if (!counter->hw.idx) + return; + /* + * Performance monitor interrupts come even when interrupts + * are soft-disabled, as long as interrupts are hard-enabled. + * Therefore we treat them like NMIs. + */ + do { + prev = atomic64_read(&counter->hw.prev_count); + barrier(); + val = read_pmc(counter->hw.idx); + } while (atomic64_cmpxchg(&counter->hw.prev_count, prev, val) != prev); + + /* The counters are only 32 bits wide */ + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + atomic64_sub(delta, &counter->hw.period_left); +} + +/* + * On some machines, PMC5 and PMC6 can't be written, don't respect + * the freeze conditions, and don't generate interrupts. This tells + * us if `counter' is using such a PMC. + */ +static int is_limited_pmc(int pmcnum) +{ + return (ppmu->flags & PPMU_LIMITED_PMC5_6) + && (pmcnum == 5 || pmcnum == 6); +} + +static void freeze_limited_counters(struct cpu_hw_counters *cpuhw, + unsigned long pmc5, unsigned long pmc6) +{ + struct perf_counter *counter; + u64 val, prev, delta; + int i; + + for (i = 0; i < cpuhw->n_limited; ++i) { + counter = cpuhw->limited_counter[i]; + if (!counter->hw.idx) + continue; + val = (counter->hw.idx == 5) ? pmc5 : pmc6; + prev = atomic64_read(&counter->hw.prev_count); + counter->hw.idx = 0; + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + } +} + +static void thaw_limited_counters(struct cpu_hw_counters *cpuhw, + unsigned long pmc5, unsigned long pmc6) +{ + struct perf_counter *counter; + u64 val; + int i; + + for (i = 0; i < cpuhw->n_limited; ++i) { + counter = cpuhw->limited_counter[i]; + counter->hw.idx = cpuhw->limited_hwidx[i]; + val = (counter->hw.idx == 5) ? pmc5 : pmc6; + atomic64_set(&counter->hw.prev_count, val); + perf_counter_update_userpage(counter); + } +} + +/* + * Since limited counters don't respect the freeze conditions, we + * have to read them immediately after freezing or unfreezing the + * other counters. We try to keep the values from the limited + * counters as consistent as possible by keeping the delay (in + * cycles and instructions) between freezing/unfreezing and reading + * the limited counters as small and consistent as possible. + * Therefore, if any limited counters are in use, we read them + * both, and always in the same order, to minimize variability, + * and do it inside the same asm that writes MMCR0. + */ +static void write_mmcr0(struct cpu_hw_counters *cpuhw, unsigned long mmcr0) +{ + unsigned long pmc5, pmc6; + + if (!cpuhw->n_limited) { + mtspr(SPRN_MMCR0, mmcr0); + return; + } + + /* + * Write MMCR0, then read PMC5 and PMC6 immediately. + * To ensure we don't get a performance monitor interrupt + * between writing MMCR0 and freezing/thawing the limited + * counters, we first write MMCR0 with the counter overflow + * interrupt enable bits turned off. + */ + asm volatile("mtspr %3,%2; mfspr %0,%4; mfspr %1,%5" + : "=&r" (pmc5), "=&r" (pmc6) + : "r" (mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)), + "i" (SPRN_MMCR0), + "i" (SPRN_PMC5), "i" (SPRN_PMC6)); + + if (mmcr0 & MMCR0_FC) + freeze_limited_counters(cpuhw, pmc5, pmc6); + else + thaw_limited_counters(cpuhw, pmc5, pmc6); + + /* + * Write the full MMCR0 including the counter overflow interrupt + * enable bits, if necessary. + */ + if (mmcr0 & (MMCR0_PMC1CE | MMCR0_PMCjCE)) + mtspr(SPRN_MMCR0, mmcr0); +} + +/* + * Disable all counters to prevent PMU interrupts and to allow + * counters to be added or removed. + */ +void hw_perf_disable(void) +{ + struct cpu_hw_counters *cpuhw; + unsigned long ret; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + + ret = cpuhw->disabled; + if (!ret) { + cpuhw->disabled = 1; + cpuhw->n_added = 0; + + /* + * Check if we ever enabled the PMU on this cpu. + */ + if (!cpuhw->pmcs_enabled) { + if (ppc_md.enable_pmcs) + ppc_md.enable_pmcs(); + cpuhw->pmcs_enabled = 1; + } + + /* + * Disable instruction sampling if it was enabled + */ + if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { + mtspr(SPRN_MMCRA, + cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mb(); + } + + /* + * Set the 'freeze counters' bit. + * The barrier is to make sure the mtspr has been + * executed and the PMU has frozen the counters + * before we return. + */ + write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC); + mb(); + } + local_irq_restore(flags); +} + +/* + * Re-enable all counters if disable == 0. + * If we were previously disabled and counters were added, then + * put the new config on the PMU. + */ +void hw_perf_enable(void) +{ + struct perf_counter *counter; + struct cpu_hw_counters *cpuhw; + unsigned long flags; + long i; + unsigned long val; + s64 left; + unsigned int hwc_index[MAX_HWCOUNTERS]; + int n_lim; + int idx; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + if (!cpuhw->disabled) { + local_irq_restore(flags); + return; + } + cpuhw->disabled = 0; + + /* + * If we didn't change anything, or only removed counters, + * no need to recalculate MMCR* settings and reset the PMCs. + * Just reenable the PMU with the current MMCR* settings + * (possibly updated for removal of counters). + */ + if (!cpuhw->n_added) { + mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + if (cpuhw->n_counters == 0) + get_lppaca()->pmcregs_in_use = 0; + goto out_enable; + } + + /* + * Compute MMCR* values for the new set of counters + */ + if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_counters, hwc_index, + cpuhw->mmcr)) { + /* shouldn't ever get here */ + printk(KERN_ERR "oops compute_mmcr failed\n"); + goto out; + } + + /* + * Add in MMCR0 freeze bits corresponding to the + * attr.exclude_* bits for the first counter. + * We have already checked that all counters have the + * same values for these bits as the first counter. + */ + counter = cpuhw->counter[0]; + if (counter->attr.exclude_user) + cpuhw->mmcr[0] |= MMCR0_FCP; + if (counter->attr.exclude_kernel) + cpuhw->mmcr[0] |= freeze_counters_kernel; + if (counter->attr.exclude_hv) + cpuhw->mmcr[0] |= MMCR0_FCHV; + + /* + * Write the new configuration to MMCR* with the freeze + * bit set and set the hardware counters to their initial values. + * Then unfreeze the counters. + */ + get_lppaca()->pmcregs_in_use = 1; + mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) + | MMCR0_FC); + + /* + * Read off any pre-existing counters that need to move + * to another PMC. + */ + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx && counter->hw.idx != hwc_index[i] + 1) { + power_pmu_read(counter); + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + } + } + + /* + * Initialize the PMCs for all the new and moved counters. + */ + cpuhw->n_limited = n_lim = 0; + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx) + continue; + idx = hwc_index[i] + 1; + if (is_limited_pmc(idx)) { + cpuhw->limited_counter[n_lim] = counter; + cpuhw->limited_hwidx[n_lim] = idx; + ++n_lim; + continue; + } + val = 0; + if (counter->hw.sample_period) { + left = atomic64_read(&counter->hw.period_left); + if (left < 0x80000000L) + val = 0x80000000L - left; + } + atomic64_set(&counter->hw.prev_count, val); + counter->hw.idx = idx; + write_pmc(idx, val); + perf_counter_update_userpage(counter); + } + cpuhw->n_limited = n_lim; + cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE; + + out_enable: + mb(); + write_mmcr0(cpuhw, cpuhw->mmcr[0]); + + /* + * Enable instruction sampling if necessary + */ + if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { + mb(); + mtspr(SPRN_MMCRA, cpuhw->mmcr[2]); + } + + out: + local_irq_restore(flags); +} + +static int collect_events(struct perf_counter *group, int max_count, + struct perf_counter *ctrs[], u64 *events, + unsigned int *flags) +{ + int n = 0; + struct perf_counter *counter; + + if (!is_software_counter(group)) { + if (n >= max_count) + return -1; + ctrs[n] = group; + flags[n] = group->hw.counter_base; + events[n++] = group->hw.config; + } + list_for_each_entry(counter, &group->sibling_list, list_entry) { + if (!is_software_counter(counter) && + counter->state != PERF_COUNTER_STATE_OFF) { + if (n >= max_count) + return -1; + ctrs[n] = counter; + flags[n] = counter->hw.counter_base; + events[n++] = counter->hw.config; + } + } + return n; +} + +static void counter_sched_in(struct perf_counter *counter, int cpu) +{ + counter->state = PERF_COUNTER_STATE_ACTIVE; + counter->oncpu = cpu; + counter->tstamp_running += counter->ctx->time - counter->tstamp_stopped; + if (is_software_counter(counter)) + counter->pmu->enable(counter); +} + +/* + * Called to enable a whole group of counters. + * Returns 1 if the group was enabled, or -EAGAIN if it could not be. + * Assumes the caller has disabled interrupts and has + * frozen the PMU with hw_perf_save_disable. + */ +int hw_perf_group_sched_in(struct perf_counter *group_leader, + struct perf_cpu_context *cpuctx, + struct perf_counter_context *ctx, int cpu) +{ + struct cpu_hw_counters *cpuhw; + long i, n, n0; + struct perf_counter *sub; + + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + n = collect_events(group_leader, ppmu->n_counter - n0, + &cpuhw->counter[n0], &cpuhw->events[n0], + &cpuhw->flags[n0]); + if (n < 0) + return -EAGAIN; + if (check_excludes(cpuhw->counter, cpuhw->flags, n0, n)) + return -EAGAIN; + i = power_check_constraints(cpuhw->events, cpuhw->flags, n + n0); + if (i < 0) + return -EAGAIN; + cpuhw->n_counters = n0 + n; + cpuhw->n_added += n; + + /* + * OK, this group can go on; update counter states etc., + * and enable any software counters + */ + for (i = n0; i < n0 + n; ++i) + cpuhw->counter[i]->hw.config = cpuhw->events[i]; + cpuctx->active_oncpu += n; + n = 1; + counter_sched_in(group_leader, cpu); + list_for_each_entry(sub, &group_leader->sibling_list, list_entry) { + if (sub->state != PERF_COUNTER_STATE_OFF) { + counter_sched_in(sub, cpu); + ++n; + } + } + ctx->nr_active += n; + + return 1; +} + +/* + * Add a counter to the PMU. + * If all counters are not already frozen, then we disable and + * re-enable the PMU in order to get hw_perf_enable to do the + * actual work of reconfiguring the PMU. + */ +static int power_pmu_enable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + unsigned long flags; + int n0; + int ret = -EAGAIN; + + local_irq_save(flags); + perf_disable(); + + /* + * Add the counter to the list (if there is room) + * and check whether the total set is still feasible. + */ + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + if (n0 >= ppmu->n_counter) + goto out; + cpuhw->counter[n0] = counter; + cpuhw->events[n0] = counter->hw.config; + cpuhw->flags[n0] = counter->hw.counter_base; + if (check_excludes(cpuhw->counter, cpuhw->flags, n0, 1)) + goto out; + if (power_check_constraints(cpuhw->events, cpuhw->flags, n0 + 1)) + goto out; + + counter->hw.config = cpuhw->events[n0]; + ++cpuhw->n_counters; + ++cpuhw->n_added; + + ret = 0; + out: + perf_enable(); + local_irq_restore(flags); + return ret; +} + +/* + * Remove a counter from the PMU. + */ +static void power_pmu_disable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + long i; + unsigned long flags; + + local_irq_save(flags); + perf_disable(); + + power_pmu_read(counter); + + cpuhw = &__get_cpu_var(cpu_hw_counters); + for (i = 0; i < cpuhw->n_counters; ++i) { + if (counter == cpuhw->counter[i]) { + while (++i < cpuhw->n_counters) + cpuhw->counter[i-1] = cpuhw->counter[i]; + --cpuhw->n_counters; + ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr); + if (counter->hw.idx) { + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + } + perf_counter_update_userpage(counter); + break; + } + } + for (i = 0; i < cpuhw->n_limited; ++i) + if (counter == cpuhw->limited_counter[i]) + break; + if (i < cpuhw->n_limited) { + while (++i < cpuhw->n_limited) { + cpuhw->limited_counter[i-1] = cpuhw->limited_counter[i]; + cpuhw->limited_hwidx[i-1] = cpuhw->limited_hwidx[i]; + } + --cpuhw->n_limited; + } + if (cpuhw->n_counters == 0) { + /* disable exceptions if no counters are running */ + cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); + } + + perf_enable(); + local_irq_restore(flags); +} + +/* + * Re-enable interrupts on a counter after they were throttled + * because they were coming too fast. + */ +static void power_pmu_unthrottle(struct perf_counter *counter) +{ + s64 val, left; + unsigned long flags; + + if (!counter->hw.idx || !counter->hw.sample_period) + return; + local_irq_save(flags); + perf_disable(); + power_pmu_read(counter); + left = counter->hw.sample_period; + counter->hw.last_period = left; + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + write_pmc(counter->hw.idx, val); + atomic64_set(&counter->hw.prev_count, val); + atomic64_set(&counter->hw.period_left, left); + perf_counter_update_userpage(counter); + perf_enable(); + local_irq_restore(flags); +} + +struct pmu power_pmu = { + .enable = power_pmu_enable, + .disable = power_pmu_disable, + .read = power_pmu_read, + .unthrottle = power_pmu_unthrottle, +}; + +/* + * Return 1 if we might be able to put counter on a limited PMC, + * or 0 if not. + * A counter can only go on a limited PMC if it counts something + * that a limited PMC can count, doesn't require interrupts, and + * doesn't exclude any processor mode. + */ +static int can_go_on_limited_pmc(struct perf_counter *counter, u64 ev, + unsigned int flags) +{ + int n; + u64 alt[MAX_EVENT_ALTERNATIVES]; + + if (counter->attr.exclude_user + || counter->attr.exclude_kernel + || counter->attr.exclude_hv + || counter->attr.sample_period) + return 0; + + if (ppmu->limited_pmc_event(ev)) + return 1; + + /* + * The requested event isn't on a limited PMC already; + * see if any alternative code goes on a limited PMC. + */ + if (!ppmu->get_alternatives) + return 0; + + flags |= PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD; + n = ppmu->get_alternatives(ev, flags, alt); + + return n > 0; +} + +/* + * Find an alternative event that goes on a normal PMC, if possible, + * and return the event code, or 0 if there is no such alternative. + * (Note: event code 0 is "don't count" on all machines.) + */ +static u64 normal_pmc_alternative(u64 ev, unsigned long flags) +{ + u64 alt[MAX_EVENT_ALTERNATIVES]; + int n; + + flags &= ~(PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD); + n = ppmu->get_alternatives(ev, flags, alt); + if (!n) + return 0; + return alt[0]; +} + +/* Number of perf_counters counting hardware events */ +static atomic_t num_counters; +/* Used to avoid races in calling reserve/release_pmc_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +/* + * Release the PMU if this is the last perf_counter. + */ +static void hw_perf_counter_destroy(struct perf_counter *counter) +{ + if (!atomic_add_unless(&num_counters, -1, 1)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_dec_return(&num_counters) == 0) + release_pmc_hardware(); + mutex_unlock(&pmc_reserve_mutex); + } +} + +/* + * Translate a generic cache event config to a raw event code. + */ +static int hw_perf_cache_event(u64 config, u64 *eventp) +{ + unsigned long type, op, result; + int ev; + + if (!ppmu->cache_events) + return -EINVAL; + + /* unpack config */ + type = config & 0xff; + op = (config >> 8) & 0xff; + result = (config >> 16) & 0xff; + + if (type >= PERF_COUNT_HW_CACHE_MAX || + op >= PERF_COUNT_HW_CACHE_OP_MAX || + result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ev = (*ppmu->cache_events)[type][op][result]; + if (ev == 0) + return -EOPNOTSUPP; + if (ev == -1) + return -EINVAL; + *eventp = ev; + return 0; +} + +const struct pmu *hw_perf_counter_init(struct perf_counter *counter) +{ + u64 ev; + unsigned long flags; + struct perf_counter *ctrs[MAX_HWCOUNTERS]; + u64 events[MAX_HWCOUNTERS]; + unsigned int cflags[MAX_HWCOUNTERS]; + int n; + int err; + + if (!ppmu) + return ERR_PTR(-ENXIO); + switch (counter->attr.type) { + case PERF_TYPE_HARDWARE: + ev = counter->attr.config; + if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) + return ERR_PTR(-EOPNOTSUPP); + ev = ppmu->generic_events[ev]; + break; + case PERF_TYPE_HW_CACHE: + err = hw_perf_cache_event(counter->attr.config, &ev); + if (err) + return ERR_PTR(err); + break; + case PERF_TYPE_RAW: + ev = counter->attr.config; + break; + } + counter->hw.config_base = ev; + counter->hw.idx = 0; + + /* + * If we are not running on a hypervisor, force the + * exclude_hv bit to 0 so that we don't care what + * the user set it to. + */ + if (!firmware_has_feature(FW_FEATURE_LPAR)) + counter->attr.exclude_hv = 0; + + /* + * If this is a per-task counter, then we can use + * PM_RUN_* events interchangeably with their non RUN_* + * equivalents, e.g. PM_RUN_CYC instead of PM_CYC. + * XXX we should check if the task is an idle task. + */ + flags = 0; + if (counter->ctx->task) + flags |= PPMU_ONLY_COUNT_RUN; + + /* + * If this machine has limited counters, check whether this + * event could go on a limited counter. + */ + if (ppmu->flags & PPMU_LIMITED_PMC5_6) { + if (can_go_on_limited_pmc(counter, ev, flags)) { + flags |= PPMU_LIMITED_PMC_OK; + } else if (ppmu->limited_pmc_event(ev)) { + /* + * The requested event is on a limited PMC, + * but we can't use a limited PMC; see if any + * alternative goes on a normal PMC. + */ + ev = normal_pmc_alternative(ev, flags); + if (!ev) + return ERR_PTR(-EINVAL); + } + } + + /* + * If this is in a group, check if it can go on with all the + * other hardware counters in the group. We assume the counter + * hasn't been linked into its leader's sibling list at this point. + */ + n = 0; + if (counter->group_leader != counter) { + n = collect_events(counter->group_leader, ppmu->n_counter - 1, + ctrs, events, cflags); + if (n < 0) + return ERR_PTR(-EINVAL); + } + events[n] = ev; + ctrs[n] = counter; + cflags[n] = flags; + if (check_excludes(ctrs, cflags, n, 1)) + return ERR_PTR(-EINVAL); + if (power_check_constraints(events, cflags, n + 1)) + return ERR_PTR(-EINVAL); + + counter->hw.config = events[n]; + counter->hw.counter_base = cflags[n]; + counter->hw.last_period = counter->hw.sample_period; + atomic64_set(&counter->hw.period_left, counter->hw.last_period); + + /* + * See if we need to reserve the PMU. + * If no counters are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * reserve_pmc_hardware or release_pmc_hardware. + */ + err = 0; + if (!atomic_inc_not_zero(&num_counters)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&num_counters) == 0 && + reserve_pmc_hardware(perf_counter_interrupt)) + err = -EBUSY; + else + atomic_inc(&num_counters); + mutex_unlock(&pmc_reserve_mutex); + } + counter->destroy = hw_perf_counter_destroy; + + if (err) + return ERR_PTR(err); + return &power_pmu; +} + +/* + * A counter has overflowed; update its count and record + * things if requested. Note that interrupts are hard-disabled + * here so there is no possibility of being interrupted. + */ +static void record_and_restart(struct perf_counter *counter, long val, + struct pt_regs *regs, int nmi) +{ + u64 period = counter->hw.sample_period; + s64 prev, delta, left; + int record = 0; + u64 addr, mmcra, sdsync; + + /* we don't have to worry about interrupts here */ + prev = atomic64_read(&counter->hw.prev_count); + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + + /* + * See if the total period for this counter has expired, + * and update for the next period. + */ + val = 0; + left = atomic64_read(&counter->hw.period_left) - delta; + if (period) { + if (left <= 0) { + left += period; + if (left <= 0) + left = period; + record = 1; + } + if (left < 0x80000000L) + val = 0x80000000L - left; + } + + /* + * Finally record data if requested. + */ + if (record) { + struct perf_sample_data data = { + .regs = regs, + .addr = 0, + .period = counter->hw.last_period, + }; + + if (counter->attr.sample_type & PERF_SAMPLE_ADDR) { + /* + * The user wants a data address recorded. + * If we're not doing instruction sampling, + * give them the SDAR (sampled data address). + * If we are doing instruction sampling, then only + * give them the SDAR if it corresponds to the + * instruction pointed to by SIAR; this is indicated + * by the [POWER6_]MMCRA_SDSYNC bit in MMCRA. + */ + mmcra = regs->dsisr; + sdsync = (ppmu->flags & PPMU_ALT_SIPR) ? + POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC; + if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync)) + data.addr = mfspr(SPRN_SDAR); + } + if (perf_counter_overflow(counter, nmi, &data)) { + /* + * Interrupts are coming too fast - throttle them + * by setting the counter to 0, so it will be + * at least 2^30 cycles until the next interrupt + * (assuming each counter counts at most 2 counts + * per cycle). + */ + val = 0; + left = ~0ULL >> 1; + } + } + + write_pmc(counter->hw.idx, val); + atomic64_set(&counter->hw.prev_count, val); + atomic64_set(&counter->hw.period_left, left); + perf_counter_update_userpage(counter); +} + +/* + * Called from generic code to get the misc flags (i.e. processor mode) + * for an event. + */ +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + unsigned long mmcra; + + if (TRAP(regs) != 0xf00) { + /* not a PMU interrupt */ + return user_mode(regs) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; + } + + mmcra = regs->dsisr; + if (ppmu->flags & PPMU_ALT_SIPR) { + if (mmcra & POWER6_MMCRA_SIHV) + return PERF_EVENT_MISC_HYPERVISOR; + return (mmcra & POWER6_MMCRA_SIPR) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; + } + if (mmcra & MMCRA_SIHV) + return PERF_EVENT_MISC_HYPERVISOR; + return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; +} + +/* + * Called from generic code to get the instruction pointer + * for an event. + */ +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + unsigned long mmcra; + unsigned long ip; + unsigned long slot; + + if (TRAP(regs) != 0xf00) + return regs->nip; /* not a PMU interrupt */ + + ip = mfspr(SPRN_SIAR); + mmcra = regs->dsisr; + if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; + if (slot > 1) + ip += 4 * (slot - 1); + } + return ip; +} + +/* + * Performance monitor interrupt stuff + */ +static void perf_counter_interrupt(struct pt_regs *regs) +{ + int i; + struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters); + struct perf_counter *counter; + long val; + int found = 0; + int nmi; + + if (cpuhw->n_limited) + freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5), + mfspr(SPRN_PMC6)); + + /* + * Overload regs->dsisr to store MMCRA so we only need to read it once. + */ + regs->dsisr = mfspr(SPRN_MMCRA); + + /* + * If interrupts were soft-disabled when this PMU interrupt + * occurred, treat it as an NMI. + */ + nmi = !regs->softe; + if (nmi) + nmi_enter(); + else + irq_enter(); + + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (!counter->hw.idx || is_limited_pmc(counter->hw.idx)) + continue; + val = read_pmc(counter->hw.idx); + if ((int)val < 0) { + /* counter has overflowed */ + found = 1; + record_and_restart(counter, val, regs, nmi); + } + } + + /* + * In case we didn't find and reset the counter that caused + * the interrupt, scan all counters and reset any that are + * negative, to avoid getting continual interrupts. + * Any that we processed in the previous loop will not be negative. + */ + if (!found) { + for (i = 0; i < ppmu->n_counter; ++i) { + if (is_limited_pmc(i + 1)) + continue; + val = read_pmc(i + 1); + if ((int)val < 0) + write_pmc(i + 1, 0); + } + } + + /* + * Reset MMCR0 to its normal value. This will set PMXE and + * clear FC (freeze counters) and PMAO (perf mon alert occurred) + * and thus allow interrupts to occur again. + * XXX might want to use MSR.PM to keep the counters frozen until + * we get back out of this interrupt. + */ + write_mmcr0(cpuhw, cpuhw->mmcr[0]); + + if (nmi) + nmi_exit(); + else + irq_exit(); +} + +void hw_perf_counter_setup(int cpu) +{ + struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu); + + memset(cpuhw, 0, sizeof(*cpuhw)); + cpuhw->mmcr[0] = MMCR0_FC; +} + +extern struct power_pmu power4_pmu; +extern struct power_pmu ppc970_pmu; +extern struct power_pmu power5_pmu; +extern struct power_pmu power5p_pmu; +extern struct power_pmu power6_pmu; +extern struct power_pmu power7_pmu; + +static int init_perf_counters(void) +{ + unsigned long pvr; + + /* XXX should get this from cputable */ + pvr = mfspr(SPRN_PVR); + switch (PVR_VER(pvr)) { + case PV_POWER4: + case PV_POWER4p: + ppmu = &power4_pmu; + break; + case PV_970: + case PV_970FX: + case PV_970MP: + ppmu = &ppc970_pmu; + break; + case PV_POWER5: + ppmu = &power5_pmu; + break; + case PV_POWER5p: + ppmu = &power5p_pmu; + break; + case 0x3e: + ppmu = &power6_pmu; + break; + case 0x3f: + ppmu = &power7_pmu; + break; + } + + /* + * Use FCHV to ignore kernel events if MSR.HV is set. + */ + if (mfmsr() & MSR_HV) + freeze_counters_kernel = MMCR0_FCHV; + + return 0; +} + +arch_initcall(init_perf_counters); diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c new file mode 100644 index 0000000..07bd308 --- /dev/null +++ b/arch/powerpc/kernel/power4-pmu.c @@ -0,0 +1,598 @@ +/* + * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for POWER4 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_LOWER_SH 6 +#define PM_LOWER_MSK 1 +#define PM_LOWER_MSKS 0x40 +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 7 + +/* + * Unit code values + */ +#define PM_FPU 1 +#define PM_ISU1 2 +#define PM_IFU 3 +#define PM_IDU0 4 +#define PM_ISU1_ALT 6 +#define PM_ISU2 7 +#define PM_IFU_ALT 8 +#define PM_LSU0 9 +#define PM_LSU1 0xc +#define PM_GPS 0xf + +/* + * Bits in MMCR0 for POWER4 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for POWER4 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTC0SEL_SH 61 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTC1SEL_SH 58 +#define MMCR1_TTM2SEL_SH 56 +#define MMCR1_TTC2SEL_SH 55 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTC3SEL_SH 52 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_DEBUG0SEL_SH 43 +#define MMCR1_DEBUG1SEL_SH 42 +#define MMCR1_DEBUG2SEL_SH 41 +#define MMCR1_DEBUG3SEL_SH 40 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 /* note bit 0 is in MMCRA for GP */ + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ +#define MMCRA_PMC8SEL0_SH 17 /* PMC8SEL bit 0 for GP */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * |[ >[ >[ >|||[ >[ >< >< >< >< ><><><><><><><><> + * | UC1 UC2 UC3 ||| PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * \SMPL ||\TTC3SEL + * |\TTC_IFU_SEL + * \TTM2SEL0 + * + * SMPL - SAMPLE_ENABLE constraint + * 56: SAMPLE_ENABLE value 0x0100_0000_0000_0000 + * + * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2 + * 55: UC1 error 0x0080_0000_0000_0000 + * 54: FPU events needed 0x0040_0000_0000_0000 + * 53: ISU1 events needed 0x0020_0000_0000_0000 + * 52: IDU0|ISU2 events needed 0x0010_0000_0000_0000 + * + * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0 + * 51: UC2 error 0x0008_0000_0000_0000 + * 50: FPU events needed 0x0004_0000_0000_0000 + * 49: IFU events needed 0x0002_0000_0000_0000 + * 48: LSU0 events needed 0x0001_0000_0000_0000 + * + * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1 + * 47: UC3 error 0x8000_0000_0000 + * 46: LSU0 events needed 0x4000_0000_0000 + * 45: IFU events needed 0x2000_0000_0000 + * 44: IDU0|ISU2 events needed 0x1000_0000_0000 + * 43: ISU1 events needed 0x0800_0000_0000 + * + * TTM2SEL0 + * 42: 0 = IDU0 events needed + * 1 = ISU2 events needed 0x0400_0000_0000 + * + * TTC_IFU_SEL + * 41: 0 = IFU.U events needed + * 1 = IFU.L events needed 0x0200_0000_0000 + * + * TTC3SEL + * 40: 0 = LSU1.U events needed + * 1 = LSU1.L events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * 1 = FPU + * 2 = ISU1 + * 3 = IFU + * 4 = IDU0 + * 7 = ISU2 + * 9 = LSU0 + * c = LSU1 + * f = GPS + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P8 + * 15: P8 error 0x8000 + * 14-15: Count of events needing PMC8 + * + * P1..P7 + * 0-13: Count of events needing PMC1..PMC7 + * + * Note: this doesn't allow events using IFU.U to be combined with events + * using IFU.L, though that is feasible (using TTM0 and TTM2). However + * there are no listed events for IFU.L (they are debug events not + * verified for performance monitoring) so this shouldn't cause a + * problem. + */ + +static struct unitinfo { + u64 value, mask; + int unit; + int lowerbit; +} p4_unitinfo[16] = { + [PM_FPU] = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 }, + [PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_ISU1_ALT] = + { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_IFU] = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IFU_ALT] = + { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 }, + [PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 }, + [PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 }, + [PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 }, + [PM_GPS] = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 } +}; + +static unsigned char direct_marked_event[8] = { + (1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */ + (1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */ + (1<<3), /* PMC3: PM_MRK_ST_CMPL_INT */ + (1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */ + (1<<4) | (1<<5), /* PMC5: PM_MRK_GRP_TIMEO */ + (1<<3) | (1<<4) | (1<<5), + /* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */ + (1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */ + (1<<4), /* PMC8: PM_MRK_LSU_FIN */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int p4_marked_instr_event(u64 event) +{ + int pmc, psel, unit, byte, bit; + unsigned int mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc) { + if (direct_marked_event[pmc - 1] & (1 << psel)) + return 1; + if (psel == 0) /* add events */ + bit = (pmc <= 4)? pmc - 1: 8 - pmc; + else if (psel == 6) /* decode events */ + bit = 4; + else + return 0; + } else + bit = psel; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = 0; + switch (unit) { + case PM_LSU1: + if (event & PM_LOWER_MSKS) + mask = 1 << 28; /* byte 7 bit 4 */ + else + mask = 6 << 24; /* byte 3 bits 1 and 2 */ + break; + case PM_LSU0: + /* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */ + mask = 0x083dff00; + } + return (mask >> (byte * 8 + bit)) & 1; +} + +static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, lower, sh; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK; + + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + + if (!p4_unitinfo[unit].unit) + return -1; + mask |= p4_unitinfo[unit].mask; + value |= p4_unitinfo[unit].value; + sh = p4_unitinfo[unit].lowerbit; + if (sh > 1) + value |= (u64)lower << sh; + else if (lower != sh) + return -1; + unit = p4_unitinfo[unit].unit; + + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + + /* Marked instruction events need sample_enable set */ + if (p4_marked_instr_event(event)) { + mask |= 1ull << 56; + value |= 1ull << 56; + } + + /* PMCSEL=6 decode events on byte 2 need sample_enable clear */ + if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2) + mask |= 1ull << 56; + + *maskp = mask; + *valp = value; + return 0; +} + +static unsigned int ppc_inst_cmpl[] = { + 0x1001, 0x4001, 0x6001, 0x7001, 0x8001 +}; + +static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, na; + + alt[0] = event; + na = 1; + + /* 2 possibilities for PM_GRP_DISP_REJECT */ + if (event == 0x8003 || event == 0x0224) { + alt[1] = event ^ (0x8003 ^ 0x0224); + return 2; + } + + /* 2 possibilities for PM_ST_MISS_L1 */ + if (event == 0x0c13 || event == 0x0c23) { + alt[1] = event ^ (0x0c13 ^ 0x0c23); + return 2; + } + + /* several possibilities for PM_INST_CMPL */ + for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) { + if (event == ppc_inst_cmpl[i]) { + for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j) + if (j != i) + alt[na++] = ppc_inst_cmpl[j]; + break; + } + } + + return na; +} + +static int p4_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel, lower; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned int unitlower = 0; + int i; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK; + if (unit) { + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (unit == 6 || unit == 8) + /* map alt ISU1/IFU codes: 6->2, 8->3 */ + unit = (unit >> 1) - 1; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + lower <<= unit; + if (unituse[unit] && lower != (unitlower & lower)) + return -1; + unituse[unit] = 1; + unitlower |= lower; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2. + * Each TTMx can only select one unit, but since + * units 2 and 6 are both ISU1, and 3 and 8 are both IFU, + * we have some choices. + */ + if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) { + unituse[6] = 1; /* Move 2 to 6 */ + unituse[2] = 0; + } + if (unituse[3] & (unituse[1] | unituse[2])) { + unituse[8] = 1; /* Move 3 to 8 */ + unituse[3] = 0; + unitlower = (unitlower & ~8) | ((unitlower & 8) << 5); + } + /* Check only one unit per TTMx */ + if (unituse[1] + unituse[2] + unituse[3] > 1 || + unituse[4] + unituse[6] + unituse[7] > 1 || + unituse[8] + unituse[9] > 1 || + (unituse[5] | unituse[10] | unituse[11] | + unituse[13] | unituse[14])) + return -1; + + /* Set TTMxSEL fields. Note, units 1-3 => TTM0SEL codes 0-2 */ + mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH; + mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH; + mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH; + + /* Set TTCxSEL fields. */ + if (unitlower & 0xe) + mmcr1 |= 1ull << MMCR1_TTC0SEL_SH; + if (unitlower & 0xf0) + mmcr1 |= 1ull << MMCR1_TTC1SEL_SH; + if (unitlower & 0xf00) + mmcr1 |= 1ull << MMCR1_TTC2SEL_SH; + if (unitlower & 0x7000) + mmcr1 |= 1ull << MMCR1_TTC3SEL_SH; + + /* Set byte lane select fields. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == 0xf) { + /* special case for GPS */ + mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte); + } else { + if (!unituse[unit]) + ttm = unit - 1; /* 2->1, 3->2 */ + else + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte); + } + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or 00xxx direct event (off or cycles) */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + else if (psel == 6 && byte == 3) + /* seem to need to set sample_enable here */ + mmcra |= MMCRA_SAMPLE_ENABLE; + psel |= 8; + } + if (pmc <= 1) + mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc); + else + mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc == 7) /* PMC8 */ + mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH; + hwc[i] = pmc; + if (p4_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + } + + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p4_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* + * Setting the PMCxSEL field to 0 disables PMC x. + * (Note that pmc is 0-based here, not 1-based.) + */ + if (pmc <= 1) { + mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc)); + } else { + mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2))); + if (pmc == 7) + mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH); + } +} + +static int p4_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 7, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x1001, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x8c10, /* PM_LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c10, /* PM_LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x330, /* PM_BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x331, /* PM_BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x8c10, 0x3c10 }, + [C(OP_WRITE)] = { 0x7c10, 0xc13 }, + [C(OP_PREFETCH)] = { 0xc35, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc34, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x904 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x900 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x330, 0x331 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power4_pmu = { + .n_counter = 8, + .max_alternatives = 5, + .add_fields = 0x0000001100005555ull, + .test_adder = 0x0011083300000000ull, + .compute_mmcr = p4_compute_mmcr, + .get_constraint = p4_get_constraint, + .get_alternatives = p4_get_alternatives, + .disable_pmc = p4_disable_pmc, + .n_generic = ARRAY_SIZE(p4_generic_events), + .generic_events = p4_generic_events, + .cache_events = &power4_cache_events, +}; diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c new file mode 100644 index 0000000..41e5d2d --- /dev/null +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -0,0 +1,671 @@ +/* + * Performance counter support for POWER5+/++ (not POWER5) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5+ + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * [ ><><>< ><> <><>[ > < >< >< >< ><><><><><><> + * NC G0G1G2 G3 T0T1 UC B0 B1 B2 B3 P6P5P4P3P2P1 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * T0 - TTM0 constraint + * 36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000 + * + * T1 - TTM1 constraint + * 34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 33: UC3 error 0x02_0000_0000 + * 32: FPU|IFU|ISU1 events needed 0x01_0000_0000 + * 31: ISU0 events needed 0x01_8000_0000 + * 30: IDU|GRS events needed 0x00_4000_0000 + * + * B0 + * 24-27: Byte 0 event source 0x0f00_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources + * + * P6 + * 11: P6 error 0x800 + * 10-11: Count of events needing PMC6 + * + * P1..P5 + * 0-9: Count of events needing PMC1..PMC5 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0x3200000000ull, 0x0100000000ull }, + [PM_ISU0] = { 0x0200000000ull, 0x0080000000ull }, + [PM_ISU1] = { 0x3200000000ull, 0x3100000000ull }, + [PM_IFU] = { 0x3200000000ull, 0x2100000000ull }, + [PM_IDU] = { 0x0e00000000ull, 0x0040000000ull }, + [PM_GRS] = { 0x0e00000000ull, 0x0c40000000ull }, +}; + +static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc >= 5 && !(event == 0x500009 || event == 0x600005)) + return -1; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* Set byte lane select field */ + mask |= 0xfULL << (24 - 4 * byte); + value |= (u64)unit << (24 - 4 * byte); + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int power5p_limited_pmc_event(u64 event) +{ + int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + + return pmc == 5 || pmc == 6; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x100c0, 0x40001f }, /* PM_GCT_FULL_CYC */ + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x230e2, 0x323087 }, /* PM_BR_PRED_CR */ + { 0x230e3, 0x223087, 0x3230a0 }, /* PM_BR_PRED_TA */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x800c4, 0xc20e0 }, /* PM_DTLB_MISS */ + { 0xc50c6, 0xc60e0 }, /* PM_MRK_DTLB_MISS */ + { 0x100005, 0x600005 }, /* PM_RUN_CYC */ + { 0x100009, 0x200009 }, /* PM_INST_CMPL */ + { 0x200015, 0x300015 }, /* PM_LSU_LMQ_SRQ_EMPTY_CYC */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(unsigned int event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. This also handles + * alternative PCMSEL values for add events. + */ +static s64 find_alternative_bdecode(u64 event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + + /* new decode alternatives for power5+ */ + if (pmc == 1 && (pp == 0x0d || pp == 0x0e)) + return event + (2 << PM_PMC_SH) + (0x2e - 0x0d); + if (pmc == 3 && (pp == 0x2e || pp == 0x2f)) + return event - (2 << PM_PMC_SH) - (0x2e - 0x0d); + + /* alternative add event encodings */ + if (pp == 0x10 || pp == 0x28) + return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) | + (altpmc << PM_PMC_SH); + + return -1; +} + +static int power5p_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + int nlim; + s64 ae; + + alt[0] = event; + nalt = 1; + nlim = power5p_limited_pmc_event(event); + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + nlim += power5p_limited_pmc_event(ae); + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC + * and PM_INST_CMPL === PM_RUN_INST_CMPL. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs (e.g. + * 0x100005 for PM_RUN_CYC vs. 0xf for PM_CYC). + * Note that even with these additional alternatives + * we never end up with more than 3 alternatives for any event. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0xf: /* PM_CYC */ + alt[j++] = 0x600005; /* PM_RUN_CYC */ + ++nlim; + break; + case 0x600005: /* PM_RUN_CYC */ + alt[j++] = 0xf; + break; + case 0x100009: /* PM_INST_CMPL */ + alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */ + ++nlim; + break; + case 0x500009: /* PM_RUN_INST_CMPL */ + alt[j++] = 0x100009; /* PM_INST_CMPL */ + alt[j++] = 0x200009; + break; + } + } + nalt = j; + } + + if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) { + /* remove the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (!power5p_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) { + /* remove all but the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (power5p_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } + + return nalt; +} + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event. + * Bit 0 is set if it is marked for all PMCs. + * The 0x80 bit indicates a byte decode PMCSEL value. + */ +static unsigned char direct_event_is_marked[0x28] = { + 0, /* 00 */ + 0x1f, /* 01 PM_IOPS_CMPL */ + 0x2, /* 02 PM_MRK_GRP_DISP */ + 0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0, /* 04 */ + 0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */ + 0x80, /* 06 */ + 0x80, /* 07 */ + 0, 0, 0,/* 08 - 0a */ + 0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */ + 0, /* 0c */ + 0x80, /* 0d */ + 0x80, /* 0e */ + 0, /* 0f */ + 0, /* 10 */ + 0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */ + 0, /* 12 */ + 0x10, /* 13 PM_MRK_GRP_CMPL */ + 0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x2, /* 15 PM_MRK_GRP_ISSUED */ + 0x80, /* 16 */ + 0x80, /* 17 */ + 0, 0, 0, 0, 0, + 0x80, /* 1d */ + 0x80, /* 1e */ + 0, /* 1f */ + 0x80, /* 20 */ + 0x80, /* 21 */ + 0x80, /* 22 */ + 0x80, /* 23 */ + 0x80, /* 24 */ + 0x80, /* 25 */ + 0x80, /* 26 */ + 0x80, /* 27 */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power5p_marked_instr_event(u64 event) +{ + int pmc, psel; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + if (direct_event_is_marked[psel] & (1 << pmc)) + return 1; + if (direct_event_is_marked[psel] & 0x80) + bit = 4; + else if (psel == 0x08) + bit = pmc - 1; + else if (psel == 0x10) + bit = 4 - pmc; + else if (psel == 0x1b && (pmc == 1 || pmc == 3)) + bit = 4; + } else if ((psel & 0x48) == 0x40) { + bit = psel & 7; + } else if (psel == 0x28) { + bit = pmc - 1; + } else if (pmc == 3 && (psel == 0x2e || psel == 0x2f)) { + bit = 4; + } + + if (!(event & PM_BUSEVENT_MSK) || bit == -1) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit == PM_LSU0) { + /* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */ + mask = 0x5dff00; + } else if (unit == PM_LSU1 && byte >= 4) { + byte -= 4; + /* byte 5 bits 6-7, byte 6 bits 0,4, byte 7 bits 0-4,6 */ + mask = 0x5f11c000; + } else + return 0; + + return (mask >> (byte * 8 + bit)) & 1; +} + +static int power5p_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 6) + return -1; + + /* First pass to count resource use */ + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } else if (pmc <= 4) { + /* Direct event */ + --pmc; + if (isbus && (byte & 2) && + (psel == 8 || psel == 0x10 || psel == 0x28)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } else { + /* Instructions or run cycles on PMC5/6 */ + --pmc; + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if (power5p_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1)) + /* select alternate byte lane */ + psel |= 0x10; + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5p_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0xf, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x1c10a8, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x1c10a8, 0x3c1088 }, + [C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 }, + [C(OP_PREFETCH)] = { 0xc70e7, -1 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc50c3, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0xc20e4, 0x800c4 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x800c0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x230e4, 0x230e5 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power5p_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000000000055ull, + .test_adder = 0x3000040000000ull, + .compute_mmcr = power5p_compute_mmcr, + .get_constraint = power5p_get_constraint, + .get_alternatives = power5p_get_alternatives, + .disable_pmc = power5p_disable_pmc, + .limited_pmc_event = power5p_limited_pmc_event, + .flags = PPMU_LIMITED_PMC5_6, + .n_generic = ARRAY_SIZE(power5p_generic_events), + .generic_events = power5p_generic_events, + .cache_events = &power5p_cache_events, +}; diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c new file mode 100644 index 0000000..05600b6 --- /dev/null +++ b/arch/powerpc/kernel/power5-pmu.c @@ -0,0 +1,611 @@ +/* + * Performance counter support for POWER5 (not POWER5++) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for POWER5 (not POWER5++) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><>[ ><><>< ><> [ >[ >[ >< >< >< >< ><><><><><><> + * T0T1 NC G0G1G2 G3 UC PS1PS2 B0 B1 B2 B3 P6P5P4P3P2P1 + * + * T0 - TTM0 constraint + * 54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000 + * + * T1 - TTM1 constraint + * 52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 37: UC3 error 0x20_0000_0000 + * 36: FPU|IFU|ISU1 events needed 0x10_0000_0000 + * 35: ISU0 events needed 0x08_0000_0000 + * 34: IDU|GRS events needed 0x04_0000_0000 + * + * PS1 + * 33: PS1 error 0x2_0000_0000 + * 31-32: count of events needing PMC1/2 0x1_8000_0000 + * + * PS2 + * 30: PS2 error 0x4000_0000 + * 28-29: count of events needing PMC3/4 0x3000_0000 + * + * B0 + * 24-27: Byte 0 event source 0x0f00_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources + * + * P1..P6 + * 0-11: Count of events needing PMC1..PMC6 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc0002000000000ull, 0x00001000000000ull }, + [PM_ISU0] = { 0x00002000000000ull, 0x00000800000000ull }, + [PM_ISU1] = { 0xc0002000000000ull, 0xc0001000000000ull }, + [PM_IFU] = { 0xc0002000000000ull, 0x80001000000000ull }, + [PM_IDU] = { 0x30002000000000ull, 0x00000400000000ull }, + [PM_GRS] = { 0x30002000000000ull, 0x30000400000000ull }, +}; + +static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc <= 4) + grp = (pmc - 1) >> 1; + else if (event != 0x500009 && event != 0x600005) + return -1; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2; bytes 1 and 3 on PMC3/4. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (24 - 4 * byte); + value |= (u64)unit << (24 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2 field */ + mask |= 0x200000000ull; + value |= 0x080000000ull; + } else if (grp == 1) { + /* increment PMC3/4 field */ + mask |= 0x40000000ull; + value |= 0x10000000ull; + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x100005, 0x600005 }, /* PM_RUN_CYC */ + { 0x100009, 0x200009, 0x500009 }, /* PM_INST_CMPL */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u64 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. + */ +static s64 find_alternative_bdecode(u64 event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + return -1; +} + +static int power5_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + s64 ae; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + return nalt; +} + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event. + * Bit 0 is set if it is marked for all PMCs. + * The 0x80 bit indicates a byte decode PMCSEL value. + */ +static unsigned char direct_event_is_marked[0x28] = { + 0, /* 00 */ + 0x1f, /* 01 PM_IOPS_CMPL */ + 0x2, /* 02 PM_MRK_GRP_DISP */ + 0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0, /* 04 */ + 0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */ + 0x80, /* 06 */ + 0x80, /* 07 */ + 0, 0, 0,/* 08 - 0a */ + 0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */ + 0, /* 0c */ + 0x80, /* 0d */ + 0x80, /* 0e */ + 0, /* 0f */ + 0, /* 10 */ + 0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */ + 0, /* 12 */ + 0x10, /* 13 PM_MRK_GRP_CMPL */ + 0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x2, /* 15 PM_MRK_GRP_ISSUED */ + 0x80, /* 16 */ + 0x80, /* 17 */ + 0, 0, 0, 0, 0, + 0x80, /* 1d */ + 0x80, /* 1e */ + 0, /* 1f */ + 0x80, /* 20 */ + 0x80, /* 21 */ + 0x80, /* 22 */ + 0x80, /* 23 */ + 0x80, /* 24 */ + 0x80, /* 25 */ + 0x80, /* 26 */ + 0x80, /* 27 */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power5_marked_instr_event(u64 event) +{ + int pmc, psel; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + if (direct_event_is_marked[psel] & (1 << pmc)) + return 1; + if (direct_event_is_marked[psel] & 0x80) + bit = 4; + else if (psel == 0x08) + bit = pmc - 1; + else if (psel == 0x10) + bit = 4 - pmc; + else if (psel == 0x1b && (pmc == 1 || pmc == 3)) + bit = 4; + } else if ((psel & 0x58) == 0x40) + bit = psel & 7; + + if (!(event & PM_BUSEVENT_MSK)) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit == PM_LSU0) { + /* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */ + mask = 0x5dff00; + } else if (unit == PM_LSU1 && byte >= 4) { + byte -= 4; + /* byte 4 bits 1,3,5,7, byte 5 bits 6-7, byte 7 bits 0-4,6 */ + mask = 0x5f00c0aa; + } else + return 0; + + return (mask >> (byte * 8 + bit)) & 1; +} + +static int power5_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 6) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2 vs 3/4 use */ + if (pmc <= 4) + ++pmc_grp_use[(pmc - 1) >> 1]; + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (isbus) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 2) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else if (pmc <= 4) { + /* Direct event */ + --pmc; + if ((psel == 8 || psel == 0x10) && isbus && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } else { + /* Instructions or run cycles on PMC5/6 */ + --pmc; + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if (power5_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power5_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0xf, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4c1090, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x4c1090, 0x3c1088 }, + [C(OP_WRITE)] = { 0x3c1090, 0xc10c3 }, + [C(OP_PREFETCH)] = { 0xc70e7, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x3c309b }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc50c3, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x2c4090, 0x800c4 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x800c0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x230e4, 0x230e5 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power5_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000090000555ull, + .test_adder = 0x3000490000000ull, + .compute_mmcr = power5_compute_mmcr, + .get_constraint = power5_get_constraint, + .get_alternatives = power5_get_alternatives, + .disable_pmc = power5_disable_pmc, + .n_generic = ARRAY_SIZE(power5_generic_events), + .generic_events = power5_generic_events, + .cache_events = &power5_cache_events, +}; diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c new file mode 100644 index 0000000..46f74be --- /dev/null +++ b/arch/powerpc/kernel/power6-pmu.c @@ -0,0 +1,532 @@ +/* + * Performance counter support for POWER6 processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for POWER6 + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0x7 +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* Unit event comes (TTMxSEL encoding) */ +#define PM_UNIT_MSK 0xf +#define PM_UNIT_MSKS (PM_UNIT_MSK << PM_UNIT_SH) +#define PM_LLAV 0x8000 /* Load lookahead match value */ +#define PM_LLA 0x4000 /* Load lookahead match enable */ +#define PM_BYTE_SH 12 /* Byte of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_SUBUNIT_SH 8 /* Subunit event comes from (NEST_SEL enc.) */ +#define PM_SUBUNIT_MSK 7 +#define PM_SUBUNIT_MSKS (PM_SUBUNIT_MSK << PM_SUBUNIT_SH) +#define PM_PMCSEL_MSK 0xff /* PMCxSEL value */ +#define PM_BUSEVENT_MSK 0xf3700 + +/* + * Bits in MMCR1 for POWER6 + */ +#define MMCR1_TTM0SEL_SH 60 +#define MMCR1_TTMSEL_SH(n) (MMCR1_TTM0SEL_SH - (n) * 4) +#define MMCR1_TTMSEL_MSK 0xf +#define MMCR1_TTMSEL(m, n) (((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK) +#define MMCR1_NESTSEL_SH 45 +#define MMCR1_NESTSEL_MSK 0x7 +#define MMCR1_NESTSEL(m) (((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK) +#define MMCR1_PMC1_LLA ((u64)1 << 44) +#define MMCR1_PMC1_LLA_VALUE ((u64)1 << 39) +#define MMCR1_PMC1_ADDR_SEL ((u64)1 << 35) +#define MMCR1_PMC1SEL_SH 24 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0xff + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value >> 1. + * Bottom 4 bits are a map of which PMCs are interesting, + * top 4 bits say what sort of event: + * 0 = direct marked event, + * 1 = byte decode event, + * 4 = add/and event (PMC1 -> bits 0 & 4), + * 5 = add/and event (PMC1 -> bits 1 & 5), + * 6 = add/and event (PMC1 -> bits 2 & 6), + * 7 = add/and event (PMC1 -> bits 3 & 7). + */ +static unsigned char direct_event_is_marked[0x60 >> 1] = { + 0, /* 00 */ + 0, /* 02 */ + 0, /* 04 */ + 0x07, /* 06 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0x04, /* 08 PM_MRK_DFU_FIN */ + 0x06, /* 0a PM_MRK_IFU_FIN, PM_MRK_INST_FIN */ + 0, /* 0c */ + 0, /* 0e */ + 0x02, /* 10 PM_MRK_INST_DISP */ + 0x08, /* 12 PM_MRK_LSU_DERAT_MISS */ + 0, /* 14 */ + 0, /* 16 */ + 0x0c, /* 18 PM_THRESH_TIMEO, PM_MRK_INST_FIN */ + 0x0f, /* 1a PM_MRK_INST_DISP, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x01, /* 1c PM_MRK_INST_ISSUED */ + 0, /* 1e */ + 0, /* 20 */ + 0, /* 22 */ + 0, /* 24 */ + 0, /* 26 */ + 0x15, /* 28 PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L3MISS */ + 0, /* 2a */ + 0, /* 2c */ + 0, /* 2e */ + 0x4f, /* 30 */ + 0x7f, /* 32 */ + 0x4f, /* 34 */ + 0x5f, /* 36 */ + 0x6f, /* 38 */ + 0x4f, /* 3a */ + 0, /* 3c */ + 0x08, /* 3e PM_MRK_INST_TIMEO */ + 0x1f, /* 40 */ + 0x1f, /* 42 */ + 0x1f, /* 44 */ + 0x1f, /* 46 */ + 0x1f, /* 48 */ + 0x1f, /* 4a */ + 0x1f, /* 4c */ + 0x1f, /* 4e */ + 0, /* 50 */ + 0x05, /* 52 PM_MRK_BR_TAKEN, PM_MRK_BR_MPRED */ + 0x1c, /* 54 PM_MRK_PTEG_FROM_L3MISS, PM_MRK_PTEG_FROM_L2MISS */ + 0x02, /* 56 PM_MRK_LD_MISS_L1 */ + 0, /* 58 */ + 0, /* 5a */ + 0, /* 5c */ + 0, /* 5e */ +}; + +/* + * Masks showing for each unit which bits are marked events. + * These masks are in LE order, i.e. 0x00000001 is byte 0, bit 0. + */ +static u32 marked_bus_events[16] = { + 0x01000000, /* direct events set 1: byte 3 bit 0 */ + 0x00010000, /* direct events set 2: byte 2 bit 0 */ + 0, 0, 0, 0, /* IDU, IFU, nest: nothing */ + 0x00000088, /* VMX set 1: byte 0 bits 3, 7 */ + 0x000000c0, /* VMX set 2: byte 0 bits 4-7 */ + 0x04010000, /* LSU set 1: byte 2 bit 0, byte 3 bit 2 */ + 0xff010000u, /* LSU set 2: byte 2 bit 0, all of byte 3 */ + 0, /* LSU set 3 */ + 0x00000010, /* VMX set 3: byte 0 bit 4 */ + 0, /* BFP set 1 */ + 0x00000022, /* BFP set 2: byte 0 bits 1, 5 */ + 0, 0 +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power6_marked_instr_event(u64 event) +{ + int pmc, psel, ptype; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = (event & PM_PMCSEL_MSK) >> 1; /* drop edge/level bit */ + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + ptype = direct_event_is_marked[psel]; + if (pmc == 0 || !(ptype & (1 << (pmc - 1)))) + return 0; + ptype >>= 4; + if (ptype == 0) + return 1; + if (ptype == 1) + bit = 0; + else + bit = ptype ^ (pmc - 1); + } else if ((psel & 0x48) == 0x40) + bit = psel & 7; + + if (!(event & PM_BUSEVENT_MSK) || bit == -1) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = marked_bus_events[unit]; + return (mask >> (byte * 8 + bit)) & 1; +} + +/* + * Assign PMC numbers and compute MMCR1 value for a set of events + */ +static int p6_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + int i; + unsigned int pmc, ev, b, u, s, psel; + unsigned int ttmset = 0; + unsigned int pmc_inuse = 0; + + if (n_ev > 6) + return -1; + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; /* collision! */ + pmc_inuse |= 1 << (pmc - 1); + } + } + for (i = 0; i < n_ev; ++i) { + ev = event[i]; + pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + --pmc; + } else { + /* can go on any PMC; find a free one */ + for (pmc = 0; pmc < 4; ++pmc) + if (!(pmc_inuse & (1 << pmc))) + break; + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } + hwc[i] = pmc; + psel = ev & PM_PMCSEL_MSK; + if (ev & PM_BUSEVENT_MSK) { + /* this event uses the event bus */ + b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK; + u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK; + /* check for conflict on this byte of event bus */ + if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u) + return -1; + mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b); + ttmset |= 1 << b; + if (u == 5) { + /* Nest events have a further mux */ + s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK; + if ((ttmset & 0x10) && + MMCR1_NESTSEL(mmcr1) != s) + return -1; + ttmset |= 0x10; + mmcr1 |= (u64)s << MMCR1_NESTSEL_SH; + } + if (0x30 <= psel && psel <= 0x3d) { + /* these need the PMCx_ADDR_SEL bits */ + if (b >= 2) + mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc; + } + /* bus select values are different for PMC3/4 */ + if (pmc >= 2 && (psel & 0x90) == 0x80) + psel ^= 0x20; + } + if (ev & PM_LLA) { + mmcr1 |= MMCR1_PMC1_LLA >> pmc; + if (ev & PM_LLAV) + mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc; + } + if (power6_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if (pmc < 4) + mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc); + } + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0xe) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +/* + * Layout of constraint bits: + * + * 0-1 add field: number of uses of PMC1 (max 1) + * 2-3, 4-5, 6-7, 8-9, 10-11: ditto for PMC2, 3, 4, 5, 6 + * 12-15 add field: number of uses of PMC1-4 (max 4) + * 16-19 select field: unit on byte 0 of event bus + * 20-23, 24-27, 28-31 ditto for bytes 1, 2, 3 + * 32-34 select field: nest (subunit) event selector + */ +static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, sh, subunit; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 4 && !(event == 0x500009 || event == 0x600005)) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + } + if (event & PM_BUSEVENT_MSK) { + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + sh = byte * 4 + (16 - PM_UNIT_SH); + mask |= PM_UNIT_MSKS << sh; + value |= (u64)(event & PM_UNIT_MSKS) << sh; + if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) { + subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK; + mask |= (u64)PM_SUBUNIT_MSK << 32; + value |= (u64)subunit << 32; + } + } + if (pmc <= 4) { + mask |= 0x8000; /* add field for count of PMC1-4 uses */ + value |= 0x1000; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int p6_limited_pmc_event(u64 event) +{ + int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + + return pmc == 5 || pmc == 6; +} + +#define MAX_ALT 4 /* at most 4 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x0130e8, 0x2000f6, 0x3000fc }, /* PM_PTEG_RELOAD_VALID */ + { 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */ + { 0x080088, 0x200054, 0x3000f0 }, /* PM_ST_MISS_L1 */ + { 0x10000a, 0x2000f4, 0x600005 }, /* PM_RUN_CYC */ + { 0x10000b, 0x2000f5 }, /* PM_RUN_COUNT */ + { 0x10000e, 0x400010 }, /* PM_PURR */ + { 0x100010, 0x4000f8 }, /* PM_FLUSH */ + { 0x10001a, 0x200010 }, /* PM_MRK_INST_DISP */ + { 0x100026, 0x3000f8 }, /* PM_TB_BIT_TRANS */ + { 0x100054, 0x2000f0 }, /* PM_ST_FIN */ + { 0x100056, 0x2000fc }, /* PM_L1_ICACHE_MISS */ + { 0x1000f0, 0x40000a }, /* PM_INST_IMC_MATCH_CMPL */ + { 0x1000f8, 0x200008 }, /* PM_GCT_EMPTY_CYC */ + { 0x1000fc, 0x400006 }, /* PM_LSU_DERAT_MISS_CYC */ + { 0x20000e, 0x400007 }, /* PM_LSU_DERAT_MISS */ + { 0x200012, 0x300012 }, /* PM_INST_DISP */ + { 0x2000f2, 0x3000f2 }, /* PM_INST_DISP */ + { 0x2000f8, 0x300010 }, /* PM_EXT_INT */ + { 0x2000fe, 0x300056 }, /* PM_DATA_FROM_L2MISS */ + { 0x2d0030, 0x30001a }, /* PM_MRK_FPU_FIN */ + { 0x30000a, 0x400018 }, /* PM_MRK_INST_FIN */ + { 0x3000f6, 0x40000e }, /* PM_L1_DCACHE_RELOAD_VALID */ + { 0x3000fe, 0x400056 }, /* PM_DATA_FROM_L3MISS */ +}; + +/* + * This could be made more efficient with a binary search on + * a presorted list, if necessary + */ +static int find_alternatives_list(u64 event) +{ + int i, j; + unsigned int alt; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + return -1; + for (j = 0; j < MAX_ALT; ++j) { + alt = event_alternatives[i][j]; + if (!alt || event < alt) + break; + if (event == alt) + return i; + } + } + return -1; +} + +static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nlim; + unsigned int psel, pmc; + unsigned int nalt = 1; + u64 aevent; + + alt[0] = event; + nlim = p6_limited_pmc_event(event); + + /* check the alternatives table */ + i = find_alternatives_list(event); + if (i >= 0) { + /* copy out alternatives from list */ + for (j = 0; j < MAX_ALT; ++j) { + aevent = event_alternatives[i][j]; + if (!aevent) + break; + if (aevent != event) + alt[nalt++] = aevent; + nlim += p6_limited_pmc_event(aevent); + } + + } else { + /* Check for alternative ways of computing sum events */ + /* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */ + psel = event & (PM_PMCSEL_MSK & ~1); /* ignore edge bit */ + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc && (psel == 0x32 || psel == 0x34)) + alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) | + ((5 - pmc) << PM_PMC_SH); + + /* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */ + if (pmc && (psel == 0x38 || psel == 0x3a)) + alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) | + ((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH); + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC, + * PM_INST_CMPL === PM_RUN_INST_CMPL, PM_PURR === PM_RUN_PURR. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs (e.g. + * 0x10000a for PM_RUN_CYC vs. 0x1e for PM_CYC). + * Note that even with these additional alternatives + * we never end up with more than 4 alternatives for any event. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0x1e: /* PM_CYC */ + alt[j++] = 0x600005; /* PM_RUN_CYC */ + ++nlim; + break; + case 0x10000a: /* PM_RUN_CYC */ + alt[j++] = 0x1e; /* PM_CYC */ + break; + case 2: /* PM_INST_CMPL */ + alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */ + ++nlim; + break; + case 0x500009: /* PM_RUN_INST_CMPL */ + alt[j++] = 2; /* PM_INST_CMPL */ + break; + case 0x10000e: /* PM_PURR */ + alt[j++] = 0x4000f4; /* PM_RUN_PURR */ + break; + case 0x4000f4: /* PM_RUN_PURR */ + alt[j++] = 0x10000e; /* PM_PURR */ + break; + } + } + nalt = j; + } + + if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) { + /* remove the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (!p6_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) { + /* remove all but the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (p6_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } + + return nalt; +} + +static void p6_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* Set PMCxSEL to 0 to disable PMCx */ + if (pmc <= 3) + mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power6_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0x1e, + [PERF_COUNT_HW_INSTRUCTIONS] = 2, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x280030, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x30000c, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x410a0, /* BR_PRED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x400052, /* BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + * The "DTLB" and "ITLB" events relate to the DERAT and IERAT. + */ +static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x80082, 0x80080 }, + [C(OP_WRITE)] = { 0x80086, 0x80088 }, + [C(OP_PREFETCH)] = { 0x810a4, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x100056 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0x4008c, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x150730, 0x250532 }, + [C(OP_WRITE)] = { 0x250432, 0x150432 }, + [C(OP_PREFETCH)] = { 0x810a6, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x20000e }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x420ce }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x430e6, 0x400052 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power6_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x1555, + .test_adder = 0x3000, + .compute_mmcr = p6_compute_mmcr, + .get_constraint = p6_get_constraint, + .get_alternatives = p6_get_alternatives, + .disable_pmc = p6_disable_pmc, + .limited_pmc_event = p6_limited_pmc_event, + .flags = PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR, + .n_generic = ARRAY_SIZE(power6_generic_events), + .generic_events = power6_generic_events, + .cache_events = &power6_cache_events, +}; diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c new file mode 100644 index 0000000..b3f7d12 --- /dev/null +++ b/arch/powerpc/kernel/power7-pmu.c @@ -0,0 +1,357 @@ +/* + * Performance counter support for POWER7 processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for POWER7 + */ +#define PM_PMC_SH 16 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 12 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_COMBINE_SH 11 /* Combined event bit */ +#define PM_COMBINE_MSK 1 +#define PM_COMBINE_MSKS 0x800 +#define PM_L2SEL_SH 8 /* L2 event select */ +#define PM_L2SEL_MSK 7 +#define PM_PMCSEL_MSK 0xff + +/* + * Bits in MMCR1 for POWER7 + */ +#define MMCR1_TTM0SEL_SH 60 +#define MMCR1_TTM1SEL_SH 56 +#define MMCR1_TTM2SEL_SH 52 +#define MMCR1_TTM3SEL_SH 48 +#define MMCR1_TTMSEL_MSK 0xf +#define MMCR1_L2SEL_SH 45 +#define MMCR1_L2SEL_MSK 7 +#define MMCR1_PMC1_COMBINE_SH 35 +#define MMCR1_PMC2_COMBINE_SH 34 +#define MMCR1_PMC3_COMBINE_SH 33 +#define MMCR1_PMC4_COMBINE_SH 32 +#define MMCR1_PMC1SEL_SH 24 +#define MMCR1_PMC2SEL_SH 16 +#define MMCR1_PMC3SEL_SH 8 +#define MMCR1_PMC4SEL_SH 0 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0xff + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * [ ><><><><><><> + * NC P6P5P4P3P2P1 + * + * NC - number of counters + * 15: NC error 0x8000 + * 12-14: number of events needing PMC1-4 0x7000 + * + * P6 + * 11: P6 error 0x800 + * 10-11: Count of events needing PMC6 + * + * P1..P5 + * 0-9: Count of events needing PMC1..PMC5 + */ + +static int power7_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, sh; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc >= 5 && !(event == 0x500fa || event == 0x600f4)) + return -1; + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000; + value |= 0x1000; + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 2 /* at most 2 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x200f2, 0x300f2 }, /* PM_INST_DISP */ + { 0x200f4, 0x600f4 }, /* PM_RUN_CYC */ + { 0x400fa, 0x500fa }, /* PM_RUN_INST_CMPL */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u64 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static s64 find_alternative_decode(u64 event) +{ + int pmc, psel; + + /* this only handles the 4x decode events */ + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if ((pmc == 2 || pmc == 4) && (psel & ~7) == 0x40) + return event - (1 << PM_PMC_SH) + 8; + if ((pmc == 1 || pmc == 3) && (psel & ~7) == 0x48) + return event + (1 << PM_PMC_SH) - 8; + return -1; +} + +static int power7_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + s64 ae; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_decode(event); + if (ae > 0) + alt[nalt++] = ae; + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC + * and PM_INST_CMPL === PM_RUN_INST_CMPL. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0x1e: /* PM_CYC */ + alt[j++] = 0x600f4; /* PM_RUN_CYC */ + break; + case 0x600f4: /* PM_RUN_CYC */ + alt[j++] = 0x1e; + break; + case 0x2: /* PM_PPC_CMPL */ + alt[j++] = 0x500fa; /* PM_RUN_INST_CMPL */ + break; + case 0x500fa: /* PM_RUN_INST_CMPL */ + alt[j++] = 0x2; /* PM_PPC_CMPL */ + break; + } + } + nalt = j; + } + + return nalt; +} + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power7_marked_instr_event(u64 event) +{ + int pmc, psel; + int unit; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + psel = event & PM_PMCSEL_MSK & ~1; /* trim off edge/level bit */ + if (pmc >= 5) + return 0; + + switch (psel >> 4) { + case 2: + return pmc == 2 || pmc == 4; + case 3: + if (psel == 0x3c) + return pmc == 1; + if (psel == 0x3e) + return pmc != 2; + return 1; + case 4: + case 5: + return unit == 0xd; + case 6: + if (psel == 0x64) + return pmc >= 3; + case 8: + return unit == 0xd; + } + return 0; +} + +static int power7_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, combine, l2sel, psel; + unsigned int pmc_inuse = 0; + int i; + + /* First pass to count resource use */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + } + } + + /* Second pass: assign PMCs, set all MMCR1 fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + combine = (event[i] >> PM_COMBINE_SH) & PM_COMBINE_MSK; + l2sel = (event[i] >> PM_L2SEL_SH) & PM_L2SEL_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } else { + /* Direct or decoded event */ + --pmc; + } + if (pmc <= 3) { + mmcr1 |= (u64) unit << (MMCR1_TTM0SEL_SH - 4 * pmc); + mmcr1 |= (u64) combine << (MMCR1_PMC1_COMBINE_SH - pmc); + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + if (unit == 6) /* L2 events */ + mmcr1 |= (u64) l2sel << MMCR1_L2SEL_SH; + } + if (power7_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power7_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0xffULL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power7_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 0x1e, + [PERF_COUNT_INSTRUCTIONS] = 2, + [PERF_COUNT_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU */ + [PERF_COUNT_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x10068, /* BRU_FIN */ + [PERF_COUNT_BRANCH_MISSES] = 0x400f6, /* BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x400f0, 0xc880 }, + [C(OP_WRITE)] = { 0, 0x300f0 }, + [C(OP_PREFETCH)] = { 0xd8b8, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x200fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0x408a, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x6080, 0x6084 }, + [C(OP_WRITE)] = { 0x6082, 0x6086 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x300fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x400fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x10068, 0x400f6 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power7_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT + 1, + .add_fields = 0x1555ull, + .test_adder = 0x3000ull, + .compute_mmcr = power7_compute_mmcr, + .get_constraint = power7_get_constraint, + .get_alternatives = power7_get_alternatives, + .disable_pmc = power7_disable_pmc, + .n_generic = ARRAY_SIZE(power7_generic_events), + .generic_events = power7_generic_events, + .cache_events = &power7_cache_events, +}; diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c new file mode 100644 index 0000000..ba0a357 --- /dev/null +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -0,0 +1,482 @@ +/* + * Performance counter support for PPC970-family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/string.h> +#include <linux/perf_counter.h> +#include <asm/reg.h> + +/* + * Bits in event code for PPC970 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_SPCSEL_SH 6 +#define PM_SPCSEL_MSK 3 +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 0xf + +/* Values in PM_UNIT field */ +#define PM_NONE 0 +#define PM_FPU 1 +#define PM_VPU 2 +#define PM_ISU 3 +#define PM_IFU 4 +#define PM_IDU 5 +#define PM_STS 6 +#define PM_LSU0 7 +#define PM_LSU1U 8 +#define PM_LSU1L 9 +#define PM_LASTUNIT 9 + +/* + * Bits in MMCR0 for PPC970 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for PPC970 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><><>[ >[ >[ >< >< >< >< ><><><><><><><><> + * SPT0T1 UC PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * + * SP - SPCSEL constraint + * 48-49: SPCSEL value 0x3_0000_0000_0000 + * + * T0 - TTM0 constraint + * 46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000 + * + * T1 - TTM1 constraint + * 44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS + * 43: UC3 error 0x0800_0000_0000 + * 42: FPU|IFU|VPU events needed 0x0400_0000_0000 + * 41: ISU events needed 0x0200_0000_0000 + * 40: IDU|STS events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P1 + * 15: P1 error 0x8000 + * 14-15: Count of events needing PMC1 + * + * P2..P8 + * 0-13: Count of events needing PMC2..PMC8 + */ + +static unsigned char direct_marked_event[8] = { + (1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */ + (1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */ + (1<<3) | (1<<5), /* PMC3: PM_MRK_ST_CMPL_INT, PM_MRK_VMX_FIN */ + (1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */ + (1<<4) | (1<<5), /* PMC5: PM_GRP_MRK, PM_MRK_GRP_TIMEO */ + (1<<3) | (1<<4) | (1<<5), + /* PMC6: PM_MRK_ST_STS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */ + (1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */ + (1<<4) /* PMC8: PM_MRK_LSU_FIN */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int p970_marked_instr_event(u64 event) +{ + int pmc, psel, unit, byte, bit; + unsigned int mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc) { + if (direct_marked_event[pmc - 1] & (1 << psel)) + return 1; + if (psel == 0) /* add events */ + bit = (pmc <= 4)? pmc - 1: 8 - pmc; + else if (psel == 7 || psel == 13) /* decode events */ + bit = 4; + else + return 0; + } else + bit = psel; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = 0; + switch (unit) { + case PM_VPU: + mask = 0x4c; /* byte 0 bits 2,3,6 */ + case PM_LSU0: + /* byte 2 bits 0,2,3,4,6; all of byte 1 */ + mask = 0x085dff00; + case PM_LSU1L: + mask = 0x50 << 24; /* byte 3 bits 4,6 */ + break; + } + return (mask >> (byte * 8 + bit)) & 1; +} + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc80000000000ull, 0x040000000000ull }, + [PM_VPU] = { 0xc80000000000ull, 0xc40000000000ull }, + [PM_ISU] = { 0x080000000000ull, 0x020000000000ull }, + [PM_IFU] = { 0xc80000000000ull, 0x840000000000ull }, + [PM_IDU] = { 0x380000000000ull, 0x010000000000ull }, + [PM_STS] = { 0x380000000000ull, 0x310000000000ull }, +}; + +static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh, spcsel; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else if (grp == 1) { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK; + if (spcsel) { + mask |= 3ull << 48; + value |= (u64)spcsel << 48; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + alt[0] = event; + + /* 2 alternatives for LSU empty */ + if (event == 0x2002 || event == 0x3002) { + alt[1] = event ^ 0x1000; + return 2; + } + + return 1; +} + +static int p970_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 }; + unsigned char ttmuse[2]; + unsigned char pmcsel[8]; + int i; + int spcsel; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU])) + unitmap[PM_ISU] = 2 | 4; /* move ISU to TTM1 */ + /* Set TTM[01]SEL fields. */ + ttmuse[0] = ttmuse[1] = 0; + for (i = PM_FPU; i <= PM_STS; ++i) { + if (!unituse[i]) + continue; + ttm = unitmap[i]; + ++ttmuse[(ttm >> 2) & 1]; + mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH; + } + /* Check only one unit per TTMx */ + if (ttmuse[0] > 1 || ttmuse[1] > 1) + return -1; + + /* Set byte lane select fields and TTM3SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit <= PM_STS) + ttm = (unitmap[unit] >> 2) & 1; + else if (unit == PM_LSU0) + ttm = 2; + else { + ttm = 3; + if (unit == PM_LSU1L && byte >= 2) + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + memset(pmcsel, 0x8, sizeof(pmcsel)); /* 8 means don't count */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + else + psel |= 8; + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + } + pmcsel[pmc] = psel; + hwc[i] = pmc; + spcsel = (event[i] >> PM_SPCSEL_SH) & PM_SPCSEL_MSK; + mmcr1 |= spcsel; + if (p970_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + } + for (pmc = 0; pmc < 2; ++pmc) + mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc); + for (; pmc < 8; ++pmc) + mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p970_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + int shift, i; + + if (pmc <= 1) { + shift = MMCR0_PMC1SEL_SH - 7 * pmc; + i = 0; + } else { + shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2); + i = 1; + } + /* + * Setting the PMCxSEL field to 0x08 disables PMC x. + */ + mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift); +} + +static int ppc970_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 7, + [PERF_COUNT_HW_INSTRUCTIONS] = 1, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x8810, /* PM_LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3810, /* PM_LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x431, /* PM_BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x327, /* PM_GRP_BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x8810, 0x3810 }, + [C(OP_WRITE)] = { 0x7810, 0x813 }, + [C(OP_PREFETCH)] = { 0x731, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0x733, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x704 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x700 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x431, 0x327 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu ppc970_pmu = { + .n_counter = 8, + .max_alternatives = 2, + .add_fields = 0x001100005555ull, + .test_adder = 0x013300000000ull, + .compute_mmcr = p970_compute_mmcr, + .get_constraint = p970_get_constraint, + .get_alternatives = p970_get_alternatives, + .disable_pmc = p970_disable_pmc, + .n_generic = ARRAY_SIZE(ppc970_generic_events), + .generic_events = ppc970_generic_events, + .cache_events = &ppc970_cache_events, +}; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9057335..2cf915e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -41,6 +41,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions); } +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + /* do real check here */ + return 1; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { return !(v->arch.msr & MSR_WE); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 7699394..5beffc8 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/kprobes.h> #include <linux/kdebug.h> +#include <linux/perf_counter.h> #include <asm/firmware.h> #include <asm/page.h> @@ -170,6 +171,8 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, die("Weird page fault", regs, SIGSEGV); } + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -309,6 +312,8 @@ good_area: } if (ret & VM_FAULT_MAJOR) { current->maj_flt++; + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + regs, address); #ifdef CONFIG_PPC_SMLPAR if (firmware_has_feature(FW_FEATURE_CMO)) { preempt_disable(); @@ -316,8 +321,11 @@ good_area: preempt_enable(); } #endif - } else + } else { current->min_flt++; + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + regs, address); + } up_read(&mm->mmap_sem); return 0; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 25f8a9c..cca6b4f 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,6 +1,7 @@ config PPC64 bool "64-bit kernel" default n + select HAVE_PERF_COUNTERS help This option selects whether a 32-bit or a 64-bit kernel will be built. diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 80b5134..be3581a 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -333,7 +333,7 @@ static void xics_eoi_lpar(unsigned int virq) lpar_xirr_info_set((0xff << 24) | irq); } -static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) +static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) { unsigned int irq; int status; @@ -342,14 +342,14 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) irq = (unsigned int)irq_map[virq].hwirq; if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS) - return; + return -1; status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq); if (status) { printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", __func__, irq, status); - return; + return -1; } /* @@ -363,7 +363,7 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) printk(KERN_WARNING "%s: No online cpus in the mask %s for irq %d\n", __func__, cpulist, virq); - return; + return -1; } status = rtas_call(ibm_set_xive, 3, 1, NULL, @@ -372,8 +372,10 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) if (status) { printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", __func__, irq, status); - return; + return -1; } + + return 0; } static struct irq_chip xics_pic_direct = { diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 9e105cb..a477991 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -250,7 +250,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT); blk_queue_make_request(bank->disk->queue, axon_ram_make_request); - blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); + blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); add_disk(bank->disk); bank->irq_id = irq_of_parse_and_map(device->node, 0); diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index bbee441..9c3af50 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq) #endif /* CONFIG_SMP */ -void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) { struct mpic *mpic = mpic_from_irq(irq); unsigned int src = mpic_irq_to_hw(irq); @@ -824,6 +824,8 @@ void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), mpic_physmask(cpus_addr(tmp)[0])); } + + return 0; } static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type) diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h index 3cef2af..eff433c 100644 --- a/arch/powerpc/sysdev/mpic.h +++ b/arch/powerpc/sysdev/mpic.h @@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic) extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type); extern void mpic_set_vector(unsigned int virq, unsigned int vector); -extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); +extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); #endif /* _POWERPC_SYSDEV_MPIC_H */ |