diff options
Diffstat (limited to 'arch/powerpc')
116 files changed, 3067 insertions, 992 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 0e11a095a9d1..84cb0c932153 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -90,6 +90,7 @@ config GENERIC_GPIO config PPC bool default y + select BINFMT_ELF select OF select OF_EARLY_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD @@ -98,7 +99,7 @@ config PPC select HAVE_FUNCTION_GRAPH_TRACER select SYSCTL_EXCEPTION_TRACE select ARCH_WANT_OPTIONAL_GPIOLIB - select HAVE_VIRT_TO_BUS if !PPC64 + select VIRT_TO_BUS if !PPC64 select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -427,11 +428,6 @@ config NODES_SHIFT default "4" depends on NEED_MULTIPLE_NODES -config MAX_ACTIVE_REGIONS - int - default "256" if PPC64 - default "32" - config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 @@ -646,14 +642,14 @@ menu "Bus options" config ISA bool "Support for ISA-bus hardware" - depends on PPC_PREP || PPC_CHRP + depends on PPC_CHRP select PPC_I8259 help Find out whether you have ISA slots on your motherboard. ISA is the name of a bus system, i.e. the way the CPU talks to the other stuff inside your box. If you have an Apple machine, say N here; if you - have an IBM RS/6000 or pSeries machine or a PReP machine, say Y. If - you have an embedded board, consult your board documentation. + have an IBM RS/6000 or pSeries machine, say Y. If you have an + embedded board, consult your board documentation. config ZONE_DMA bool @@ -743,7 +739,6 @@ config PCI bool "PCI support" if PPC_PCI_CHOICE default y if !40x && !CPM2 && !8xx && !PPC_83xx \ && !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON - default PCI_PERMEDIA if !4xx && !CPM2 && !8xx default PCI_QSPAN if !4xx && !CPM2 && 8xx select ARCH_SUPPORTS_MSI select GENERIC_PCI_IOMAP @@ -962,7 +957,7 @@ config TASK_SIZE_BOOL config TASK_SIZE hex "Size of user task space" if TASK_SIZE_BOOL - default "0x80000000" if PPC_PREP || PPC_8xx + default "0x80000000" if PPC_8xx default "0xc0000000" config CONSISTENT_SIZE_BOOL diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts new file mode 100644 index 000000000000..a27a4609bb42 --- /dev/null +++ b/arch/powerpc/boot/dts/ac14xx.dts @@ -0,0 +1,392 @@ +/* + * Device Tree Source for the MPC5121e based ac14xx board + * + * Copyright 2012 Anatolij Gustschin <agust@denx.de> + * + * 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/ "mpc5121.dtsi" + +/ { + model = "ac14xx"; + compatible = "ifm,ac14xx", "fsl,mpc5121"; + #address-cells = <1>; + #size-cells = <1>; + + aliases { + serial0 = &serial0; + serial1 = &serial7; + spi4 = &spi4; + spi5 = &spi5; + }; + + cpus { + PowerPC,5121@0 { + timebase-frequency = <40000000>; /* 40 MHz (csb/4) */ + bus-frequency = <160000000>; /* 160 MHz csb bus */ + clock-frequency = <400000000>; /* 400 MHz ppc core */ + }; + }; + + memory { + reg = <0x00000000 0x10000000>; /* 256MB at 0 */ + }; + + nfc@40000000 { + status = "disabled"; + }; + + localbus@80000020 { + ranges = <0x0 0x0 0xfc000000 0x04000000 /* CS0: NOR flash */ + 0x1 0x0 0xe0000000 0x00010000 /* CS1: FRAM */ + 0x2 0x0 0xe0100000 0x00080000 /* CS2: asi1 */ + 0x3 0x0 0xe0300000 0x00020000 /* CS3: comm */ + 0x5 0x0 0xe0400000 0x00010000 /* CS5: safety */ + 0x6 0x0 0xe0200000 0x00080000>; /* CS6: asi2 */ + + flash@0,0 { + compatible = "cfi-flash"; + reg = <0 0x00000000 0x04000000>; + #address-cells = <1>; + #size-cells = <1>; + bank-width = <2>; + device-width = <2>; + + partition@0 { + label = "dtb-kernel-production"; + reg = <0x00000000 0x00400000>; + }; + partition@1 { + label = "filesystem-production"; + reg = <0x00400000 0x03400000>; + }; + + partition@2 { + label = "recovery"; + reg = <0x03800000 0x00700000>; + }; + + partition@3 { + label = "uboot-code"; + reg = <0x03f00000 0x00040000>; + }; + partition@4 { + label = "uboot-env1"; + reg = <0x03f40000 0x00020000>; + }; + partition@5 { + label = "uboot-env2"; + reg = <0x03f60000 0x00020000>; + }; + }; + + fram@1,0 { + compatible = "ifm,ac14xx-fram", "linux,uio-pdrv-genirq"; + reg = <1 0x00000000 0x00010000>; + }; + + asi@2,0 { + /* masters mapping: CS, CS offset, size */ + reg = <2 0x00000000 0x00080000 + 6 0x00000000 0x00080000>; + #address-cells = <1>; + #size-cells = <1>; + compatible = "ifm,ac14xx-asi-fpga"; + gpios = < + &gpio_pic 26 0 /* prog */ + &gpio_pic 27 0 /* done */ + &gpio_pic 10 0 /* reset */ + >; + + master@1 { + interrupts = <20 0x2>; + interrupt-parent = <&gpio_pic>; + chipselect = <2 0x00009000 0x00009100>; + label = "AS-i master 1"; + }; + + master@2 { + interrupts = <21 0x2>; + interrupt-parent = <&gpio_pic>; + chipselect = <6 0x00009000 0x00009100>; + label = "AS-i master 2"; + }; + }; + + netx@3,0 { + compatible = "ifm,netx"; + reg = <0x3 0x00000000 0x00020000>; + chipselect = <3 0x00101140 0x00203100>; + interrupts = <17 0x8>; + gpios = <&gpio_pic 15 0>; + }; + + safety@5,0 { + compatible = "ifm,safety"; + reg = <0x5 0x00000000 0x00010000>; + chipselect = <5 0x00009000 0x00009100>; + interrupts = <22 0x2>; + interrupt-parent = <&gpio_pic>; + gpios = < + &gpio_pic 12 0 /* prog */ + &gpio_pic 11 0 /* done */ + >; + }; + }; + + soc@80000000 { + + clock@f00 { + compatible = "fsl,mpc5121rev2-clock", "fsl,mpc5121-clock"; + }; + + /* + * GPIO PIC: + * interrupts cell = <pin nr, sense> + * sense == 8: Level, low assertion + * sense == 2: Edge, high-to-low change + */ + gpio_pic: gpio@1100 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + sdhc@1500 { + cd-gpios = <&gpio_pic 23 0>; /* card detect */ + wp-gpios = <&gpio_pic 24 0>; /* write protect */ + wp-inverted; /* WP active high */ + }; + + i2c@1700 { + /* use Fast-mode */ + clock-frequency = <400000>; + + at24@30 { + compatible = "at24,24c01"; + reg = <0x30>; + }; + + at24@31 { + compatible = "at24,24c01"; + reg = <0x31>; + }; + + temp@48 { + compatible = "ad,ad7414"; + reg = <0x48>; + }; + + at24@50 { + compatible = "at24,24c01"; + reg = <0x50>; + }; + + at24@51 { + compatible = "at24,24c01"; + reg = <0x51>; + }; + + at24@52 { + compatible = "at24,24c01"; + reg = <0x52>; + }; + + at24@53 { + compatible = "at24,24c01"; + reg = <0x53>; + }; + + at24@54 { + compatible = "at24,24c01"; + reg = <0x54>; + }; + + at24@55 { + compatible = "at24,24c01"; + reg = <0x55>; + }; + + at24@56 { + compatible = "at24,24c01"; + reg = <0x56>; + }; + + at24@57 { + compatible = "at24,24c01"; + reg = <0x57>; + }; + + rtc@68 { + compatible = "stm,m41t00"; + reg = <0x68>; + }; + }; + + axe_pic: axe-base@2000 { + compatible = "fsl,mpc5121-axe-base"; + reg = <0x2000 0x100>; + interrupts = <42 0x8>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + axe-app { + compatible = "fsl,mpc5121-axe-app"; + interrupt-parent = <&axe_pic>; + interrupts = < + /* soft interrupts */ + 0 0x0 1 0x0 2 0x0 3 0x0 + 4 0x0 5 0x0 6 0x0 7 0x0 + /* fifo interrupts */ + 8 0x0 9 0x0 10 0x0 11 0x0 + >; + }; + + display@2100 { + edid = [00 FF FF FF FF FF FF 00 14 94 00 00 00 00 00 00 + 0A 12 01 03 80 1C 23 78 CA 88 FF 94 52 54 8E 27 + 1E 4C 50 00 00 00 01 01 01 01 01 01 01 01 01 01 + 01 01 01 01 01 01 FB 00 B0 14 00 DC 05 00 08 04 + 21 00 1C 23 00 00 00 18 00 00 00 FD 00 38 3C 1F + 3C 01 0A 20 20 20 20 20 20 20 00 00 00 FC 00 45 + 54 30 31 38 30 30 33 44 4D 55 0A 0A 00 00 00 10 + 00 41 30 30 30 30 30 30 30 30 30 30 30 31 00 D5]; + }; + + can@2300 { + status = "disabled"; + }; + + can@2380 { + status = "disabled"; + }; + + viu@2400 { + status = "disabled"; + }; + + mdio@2800 { + phy0: ethernet-phy@1f { + compatible = "smsc,lan8700"; + reg = <0x1f>; + }; + }; + + enet: ethernet@2800 { + phy-handle = <&phy0>; + }; + + usb@3000 { + status = "disabled"; + }; + + usb@4000 { + status = "disabled"; + }; + + /* PSC3 serial port A, aka ttyPSC0 */ + serial0: psc@11300 { + compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc"; + fsl,rx-fifo-size = <512>; + fsl,tx-fifo-size = <512>; + }; + + /* PSC4 in SPI mode */ + spi4: psc@11400 { + compatible = "fsl,mpc5121-psc-spi", "fsl,mpc5121-psc"; + fsl,rx-fifo-size = <768>; + fsl,tx-fifo-size = <768>; + #address-cells = <1>; + #size-cells = <0>; + num-cs = <1>; + cs-gpios = <&gpio_pic 25 0>; + + flash: m25p128@0 { + compatible = "st,m25p128"; + spi-max-frequency = <20000000>; + reg = <0>; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "spi-flash0"; + reg = <0x00000000 0x01000000>; + }; + }; + }; + + /* PSC5 in SPI mode */ + spi5: psc@11500 { + compatible = "fsl,mpc5121-psc-spi", "fsl,mpc5121-psc"; + fsl,mode = "spi-master"; + fsl,rx-fifo-size = <128>; + fsl,tx-fifo-size = <128>; + #address-cells = <1>; + #size-cells = <0>; + + lcd@0 { + compatible = "ilitek,ili922x"; + reg = <0>; + spi-max-frequency = <100000>; + spi-cpol; + spi-cpha; + }; + }; + + /* PSC7 serial port C, aka ttyPSC2 */ + serial7: psc@11700 { + compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc"; + fsl,rx-fifo-size = <512>; + fsl,tx-fifo-size = <512>; + }; + + matrix_keypad@0 { + compatible = "gpio-matrix-keypad"; + debounce-delay-ms = <5>; + col-scan-delay-us = <1>; + gpio-activelow; + col-gpios-binary; + col-switch-delay-ms = <200>; + + col-gpios = <&gpio_pic 1 0>; /* pin1 */ + + row-gpios = <&gpio_pic 2 0 /* pin2 */ + &gpio_pic 3 0 /* pin3 */ + &gpio_pic 4 0>; /* pin4 */ + + linux,keymap = <0x0000006e /* FN LEFT */ + 0x01000067 /* UP */ + 0x02000066 /* FN RIGHT */ + 0x00010069 /* LEFT */ + 0x0101006a /* DOWN */ + 0x0201006c>; /* RIGHT */ + }; + }; + + leds { + compatible = "gpio-leds"; + + backlight { + label = "backlight"; + gpios = <&gpio_pic 0 0>; + default-state = "keep"; + }; + green { + label = "green"; + gpios = <&gpio_pic 18 0>; + default-state = "keep"; + }; + red { + label = "red"; + gpios = <&gpio_pic 19 0>; + default-state = "keep"; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi index 723e292b6b4e..2e82d0e71dd3 100644 --- a/arch/powerpc/boot/dts/mpc5121.dtsi +++ b/arch/powerpc/boot/dts/mpc5121.dtsi @@ -384,7 +384,7 @@ interrupts = <40 0x8>; }; - dma@14000 { + dma0: dma@14000 { compatible = "fsl,mpc5121-dma"; reg = <0x14000 0x1800>; interrupts = <65 0x8>; diff --git a/arch/powerpc/boot/dts/mpc5121ads.dts b/arch/powerpc/boot/dts/mpc5121ads.dts index f269b1382ef7..7d3cb79185cb 100644 --- a/arch/powerpc/boot/dts/mpc5121ads.dts +++ b/arch/powerpc/boot/dts/mpc5121ads.dts @@ -13,7 +13,7 @@ / { model = "mpc5121ads"; - compatible = "fsl,mpc5121ads"; + compatible = "fsl,mpc5121ads", "fsl,mpc5121"; nfc@40000000 { /* diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts new file mode 100644 index 000000000000..4177b62240c2 --- /dev/null +++ b/arch/powerpc/boot/dts/mpc5125twr.dts @@ -0,0 +1,233 @@ +/* + * STx/Freescale ADS5125 MPC5125 silicon + * + * Copyright (C) 2009 Freescale Semiconductor Inc. All rights reserved. + * + * Reworked by Matteo Facchinetti (engineering@sirius-es.it) + * Copyright (C) 2013 Sirius Electronic Systems + * + * 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. + */ + +/dts-v1/; + +/ { + model = "mpc5125twr"; // In BSP "mpc5125ads" + compatible = "fsl,mpc5125ads", "fsl,mpc5125"; + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&ipic>; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + ethernet0 = ð0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + PowerPC,5125@0 { + device_type = "cpu"; + reg = <0>; + d-cache-line-size = <0x20>; // 32 bytes + i-cache-line-size = <0x20>; // 32 bytes + d-cache-size = <0x8000>; // L1, 32K + i-cache-size = <0x8000>; // L1, 32K + timebase-frequency = <49500000>;// 49.5 MHz (csb/4) + bus-frequency = <198000000>; // 198 MHz csb bus + clock-frequency = <396000000>; // 396 MHz ppc core + }; + }; + + memory { + device_type = "memory"; + reg = <0x00000000 0x10000000>; // 256MB at 0 + }; + + sram@30000000 { + compatible = "fsl,mpc5121-sram"; + reg = <0x30000000 0x08000>; // 32K at 0x30000000 + }; + + soc@80000000 { + compatible = "fsl,mpc5121-immr"; + #address-cells = <1>; + #size-cells = <1>; + #interrupt-cells = <2>; + ranges = <0x0 0x80000000 0x400000>; + reg = <0x80000000 0x400000>; + bus-frequency = <66000000>; // 66 MHz ips bus + + // IPIC + // interrupts cell = <intr #, sense> + // sense values match linux IORESOURCE_IRQ_* defines: + // sense == 8: Level, low assertion + // sense == 2: Edge, high-to-low change + // + ipic: interrupt-controller@c00 { + compatible = "fsl,mpc5121-ipic", "fsl,ipic"; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + reg = <0xc00 0x100>; + }; + + rtc@a00 { // Real time clock + compatible = "fsl,mpc5121-rtc"; + reg = <0xa00 0x100>; + interrupts = <79 0x8 80 0x8>; + }; + + reset@e00 { // Reset module + compatible = "fsl,mpc5125-reset"; + reg = <0xe00 0x100>; + }; + + clock@f00 { // Clock control + compatible = "fsl,mpc5121-clock"; + reg = <0xf00 0x100>; + }; + + pmc@1000{ // Power Management Controller + compatible = "fsl,mpc5121-pmc"; + reg = <0x1000 0x100>; + interrupts = <83 0x2>; + }; + + gpio0: gpio@1100 { + compatible = "fsl,mpc5125-gpio"; + reg = <0x1100 0x080>; + interrupts = <78 0x8>; + }; + + gpio1: gpio@1180 { + compatible = "fsl,mpc5125-gpio"; + reg = <0x1180 0x080>; + interrupts = <86 0x8>; + }; + + can@1300 { // CAN rev.2 + compatible = "fsl,mpc5121-mscan"; + interrupts = <12 0x8>; + reg = <0x1300 0x80>; + }; + + can@1380 { + compatible = "fsl,mpc5121-mscan"; + interrupts = <13 0x8>; + reg = <0x1380 0x80>; + }; + + sdhc@1500 { + compatible = "fsl,mpc5121-sdhc"; + interrupts = <8 0x8>; + reg = <0x1500 0x100>; + }; + + i2c@1700 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5121-i2c", "fsl-i2c"; + reg = <0x1700 0x20>; + interrupts = <0x9 0x8>; + }; + + i2c@1720 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5121-i2c", "fsl-i2c"; + reg = <0x1720 0x20>; + interrupts = <0xa 0x8>; + }; + + i2c@1740 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5121-i2c", "fsl-i2c"; + reg = <0x1740 0x20>; + interrupts = <0xb 0x8>; + }; + + i2ccontrol@1760 { + compatible = "fsl,mpc5121-i2c-ctrl"; + reg = <0x1760 0x8>; + }; + + diu@2100 { + compatible = "fsl,mpc5121-diu"; + reg = <0x2100 0x100>; + interrupts = <64 0x8>; + }; + + mdio@2800 { + compatible = "fsl,mpc5121-fec-mdio"; + reg = <0x2800 0x800>; + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <1>; + }; + }; + + eth0: ethernet@2800 { + compatible = "fsl,mpc5125-fec"; + reg = <0x2800 0x800>; + local-mac-address = [ 00 00 00 00 00 00 ]; + interrupts = <4 0x8>; + phy-handle = < &phy0 >; + phy-connection-type = "rmii"; + }; + + // IO control + ioctl@a000 { + compatible = "fsl,mpc5125-ioctl"; + reg = <0xA000 0x1000>; + }; + + usb@3000 { + compatible = "fsl,mpc5121-usb2-dr"; + reg = <0x3000 0x400>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <43 0x8>; + dr_mode = "host"; + phy_type = "ulpi"; + }; + + // 5125 PSCs are not 52xx or 5121 PSC compatible + // PSC1 uart0 aka ttyPSC0 + serial@11100 { + compatible = "fsl,mpc5125-psc-uart", "fsl,mpc5125-psc"; + reg = <0x11100 0x100>; + interrupts = <40 0x8>; + fsl,rx-fifo-size = <16>; + fsl,tx-fifo-size = <16>; + }; + + // PSC9 uart1 aka ttyPSC1 + serial@11900 { + compatible = "fsl,mpc5125-psc-uart", "fsl,mpc5125-psc"; + reg = <0x11900 0x100>; + interrupts = <40 0x8>; + fsl,rx-fifo-size = <16>; + fsl,tx-fifo-size = <16>; + }; + + pscfifo@11f00 { + compatible = "fsl,mpc5121-psc-fifo"; + reg = <0x11f00 0x100>; + interrupts = <40 0x8>; + }; + + dma@14000 { + compatible = "fsl,mpc5121-dma"; // BSP name: "mpc512x-dma2" + reg = <0x14000 0x1800>; + interrupts = <65 0x8>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts index 0b069477838a..74337403faee 100644 --- a/arch/powerpc/boot/dts/pdm360ng.dts +++ b/arch/powerpc/boot/dts/pdm360ng.dts @@ -17,7 +17,7 @@ / { model = "pdm360ng"; - compatible = "ifm,pdm360ng"; + compatible = "ifm,pdm360ng", "fsl,mpc5121"; #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&ipic>; diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index 211fcc9ed700..0d0d981442fd 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -13,7 +13,7 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_PPC_CHRP is not set CONFIG_PPC_MPC512x=y CONFIG_MPC5121_ADS=y -CONFIG_MPC5121_GENERIC=y +CONFIG_MPC512x_GENERIC=y CONFIG_PDM360NG=y # CONFIG_PPC_PMAC is not set CONFIG_NO_HZ=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 7a5c15fcc7cf..f79196232917 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -3,11 +3,11 @@ CONFIG_TUNE_CELL=y CONFIG_ALTIVEC=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y +CONFIG_RD_LZMA=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_PERF_EVENTS is not set diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 08bd299c75b1..910194e9a1e2 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -53,7 +53,7 @@ #define smp_mb__after_clear_bit() smp_mb() /* Macro for generating the ***_bits() functions */ -#define DEFINE_BITOP(fn, op, prefix, postfix) \ +#define DEFINE_BITOP(fn, op, prefix) \ static __inline__ void fn(unsigned long mask, \ volatile unsigned long *_p) \ { \ @@ -66,16 +66,15 @@ static __inline__ void fn(unsigned long mask, \ PPC405_ERR77(0,%3) \ PPC_STLCX "%0,0,%3\n" \ "bne- 1b\n" \ - postfix \ : "=&r" (old), "+m" (*p) \ : "r" (mask), "r" (p) \ : "cc", "memory"); \ } -DEFINE_BITOP(set_bits, or, "", "") -DEFINE_BITOP(clear_bits, andc, "", "") -DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER, "") -DEFINE_BITOP(change_bits, xor, "", "") +DEFINE_BITOP(set_bits, or, "") +DEFINE_BITOP(clear_bits, andc, "") +DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER) +DEFINE_BITOP(change_bits, xor, "") static __inline__ void set_bit(int nr, volatile unsigned long *addr) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index f3264445d09f..284e50bc7b68 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -52,6 +52,7 @@ struct cpu_spec { char *cpu_name; unsigned long cpu_features; /* Kernel features */ unsigned int cpu_user_features; /* Userland features */ + unsigned int cpu_user_features2; /* Userland features v2 */ unsigned int mmu_features; /* MMU features */ /* cache line sizes */ diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h index f6813e919bb2..a5c6d83b5f60 100644 --- a/arch/powerpc/include/asm/dma.h +++ b/arch/powerpc/include/asm/dma.h @@ -16,10 +16,6 @@ * * None of this really applies for Power Macintoshes. There is * basically just enough here to get kernel/dma.c to compile. - * - * There may be some comments or restrictions made here which are - * not valid for the PReP platform. Take what you read - * with a grain of salt. */ #include <asm/io.h> @@ -57,7 +53,6 @@ * - page registers for 5-7 don't use data bit 0, represent 128K pages * - page registers for 0-3 use bit 0, represent 64K pages * - * On PReP, DMA transfers are limited to the lower 16MB of _physical_ memory. * On CHRP, the W83C553F (and VLSI Tollgate?) support full 32 bit addressing. * Note that addresses loaded into registers must be _physical_ addresses, * not logical addresses (which may differ if paging is active). diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index ac9790fc3836..cc0655a702a7 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -61,6 +61,7 @@ typedef elf_vrregset_t elf_fpxregset_t; instruction set this cpu supports. This could be done in userspace, but it's not easy, and we've already done it here. */ # define ELF_HWCAP (cur_cpu_spec->cpu_user_features) +# define ELF_HWCAP2 (cur_cpu_spec->cpu_user_features2) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 05e6d2ee1db9..8e5fae8beaf6 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -414,7 +414,6 @@ label##_relon_hv: \ #define SOFTEN_NOTEST_HV(vec) _SOFTEN_TEST(EXC_HV, vec) #define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ - HMT_MEDIUM_PPR_DISCARD; \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ @@ -427,6 +426,7 @@ label##_relon_hv: \ . = loc; \ .globl label##_pSeries; \ label##_pSeries: \ + HMT_MEDIUM_PPR_DISCARD; \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ EXC_STD, SOFTEN_TEST_PR) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 097dee57a7a9..0df54646f968 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -18,7 +18,6 @@ #include <asm/feature-fixups.h> /* firmware feature bitmask values */ -#define FIRMWARE_MAX_FEATURES 63 #define FW_FEATURE_PFT ASM_CONST(0x0000000000000001) #define FW_FEATURE_TCE ASM_CONST(0x0000000000000002) @@ -51,6 +50,8 @@ #define FW_FEATURE_OPALv2 ASM_CONST(0x0000000020000000) #define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000) #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) +#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) +#define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #ifndef __ASSEMBLY__ @@ -65,7 +66,8 @@ enum { FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | - FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY, + FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | + FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 3147a2970125..3bdcfce2c42a 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -10,6 +10,9 @@ typedef struct { unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; +#ifdef CONFIG_PPC_DOORBELL + unsigned int doorbell_irqs; +#endif } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index f94ef4213e9d..dd15e5e37d6d 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -15,10 +15,6 @@ extern int check_legacy_ioport(unsigned long base_port); #define I8042_DATA_REG 0x60 #define FDC_BASE 0x3f0 -/* only relevant for PReP */ -#define _PIDXR 0x279 -#define _PNPWRP 0xa79 -#define PNPBIOS_BASE 0xf000 #if defined(CONFIG_PPC64) && defined(CONFIG_PCI) extern struct pci_dev *isa_bridge_pcidev; diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 2fdb47a19efd..b59e06f507ea 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -343,17 +343,16 @@ extern void slb_set_size(u16 size); /* * VSID allocation (256MB segment) * - * We first generate a 38-bit "proto-VSID". For kernel addresses this - * is equal to the ESID | 1 << 37, for user addresses it is: - * (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1) + * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated + * from mmu context id and effective segment id of the address. * - * This splits the proto-VSID into the below range - * 0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range - * 2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range - * - * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1 - * That is, we assign half of the space to user processes and half - * to the kernel. + * For user processes max context id is limited to ((1ul << 19) - 5) + * for kernel space, we use the top 4 context ids to map address as below + * NOTE: each context only support 64TB now. + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: @@ -363,41 +362,49 @@ extern void slb_set_size(u16 size); * VSID_MULTIPLIER is prime, so in particular it is * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. * Because the modulus is 2^n-1 we can compute it efficiently without - * a divide or extra multiply (see below). - * - * This scheme has several advantages over older methods: - * - * - We have VSIDs allocated for every kernel address - * (i.e. everything above 0xC000000000000000), except the very top - * segment, which simplifies several things. + * a divide or extra multiply (see below). The scramble function gives + * robust scattering in the hash table (at least based on some initial + * results). * - * - We allow for USER_ESID_BITS significant bits of ESID and - * CONTEXT_BITS bits of context for user addresses. - * i.e. 64T (46 bits) of address space for up to half a million contexts. + * We also consider VSID 0 special. We use VSID 0 for slb entries mapping + * bad address. This enables us to consolidate bad address handling in + * hash_page. * - * - The scramble function gives robust scattering in the hash - * table (at least based on some initial results). The previous - * method was more susceptible to pathological cases giving excessive - * hash collisions. + * We also need to avoid the last segment of the last context, because that + * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 + * because of the modulo operation in vsid scramble. But the vmemmap + * (which is what uses region 0xf) will never be close to 64TB in size + * (it's 56 bytes per page of system memory). */ +#define CONTEXT_BITS 19 +#define ESID_BITS 18 +#define ESID_BITS_1T 6 + +/* + * 256MB segment + * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments + * available for user + kernel mapping. The top 4 contexts are used for + * kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts + * (19 == 37 + 28 - 46). + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5) + /* * This should be computed such that protovosid * vsid_mulitplier * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus */ #define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_256M 38 +#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS) #define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1) #define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_1T 26 +#define VSID_BITS_1T (CONTEXT_BITS + ESID_BITS_1T) #define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1) -#define CONTEXT_BITS 19 -#define USER_ESID_BITS 18 -#define USER_ESID_BITS_1T 6 -#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT)) +#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) /* * This macro generates asm code to compute the VSID scramble @@ -421,7 +428,8 @@ extern void slb_set_size(u16 size); srdi rx,rt,VSID_BITS_##size; \ clrldi rt,rt,(64-VSID_BITS_##size); \ add rt,rt,rx; /* add high and low bits */ \ - /* Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ + /* NOTE: explanation based on VSID_BITS_##size = 36 \ + * Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ * 2^36-1+2^28-1. That in particular means that if r3 >= \ * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \ * the bit clear, r3 already has the answer we want, if it \ @@ -513,34 +521,6 @@ typedef struct { }) #endif /* 1 */ -/* - * This is only valid for addresses >= PAGE_OFFSET - * The proto-VSID space is divided into two class - * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1 - * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1 - * - * With KERNEL_START at 0xc000000000000000, the proto vsid for - * the kernel ends up with 0xc00000000 (36 bits). With 64TB - * support we need to have kernel proto-VSID in the - * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS. - */ -static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) -{ - unsigned long proto_vsid; - /* - * We need to make sure proto_vsid for the kernel is - * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T]) - */ - if (ssize == MMU_SEGSIZE_256M) { - proto_vsid = ea >> SID_SHIFT; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS)); - return vsid_scramble(proto_vsid, 256M); - } - proto_vsid = ea >> SID_SHIFT_1T; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T)); - return vsid_scramble(proto_vsid, 1T); -} - /* Returns the segment size indicator for a user address */ static inline int user_segment_size(unsigned long addr) { @@ -550,17 +530,41 @@ static inline int user_segment_size(unsigned long addr) return MMU_SEGSIZE_256M; } -/* This is only valid for user addresses (which are below 2^44) */ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, int ssize) { + /* + * Bad address. We return VSID 0 for that + */ + if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) + return 0; + if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble((context << USER_ESID_BITS) + return vsid_scramble((context << ESID_BITS) | (ea >> SID_SHIFT), 256M); - return vsid_scramble((context << USER_ESID_BITS_1T) + return vsid_scramble((context << ESID_BITS_1T) | (ea >> SID_SHIFT_1T), 1T); } +/* + * This is only valid for addresses >= PAGE_OFFSET + * + * For kernel space, we use the top 4 context ids to map address as below + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + */ +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) +{ + unsigned long context; + + /* + * kernel take the top 4 context from the available range + */ + context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1; + return get_vsid(context, ea, ssize); +} #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_HASH64_H_ */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a4b28f165b6c..b6c8b58b1d76 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -117,6 +117,7 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_SET_SLOT_LED_STATUS 55 #define OPAL_GET_EPOW_STATUS 56 #define OPAL_SET_SYSTEM_ATTENTION_LED 57 +#define OPAL_PCI_MSI_EOI 63 #ifndef __ASSEMBLY__ @@ -506,6 +507,7 @@ int64_t opal_pci_get_xive_reissue(uint64_t phb_id, uint32_t xive_number, uint8_t *p_bit, uint8_t *q_bit); int64_t opal_pci_set_xive_reissue(uint64_t phb_id, uint32_t xive_number, uint8_t p_bit, uint8_t q_bit); +int64_t opal_pci_msi_eoi(uint64_t phb_id, uint32_t hw_irq); int64_t opal_pci_set_xive_pe(uint64_t phb_id, uint32_t pe_number, uint32_t xive_num); int64_t opal_get_xive_source(uint64_t phb_id, uint32_t xive_num, diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index cd915d6b093d..88693cef4f3d 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -99,8 +99,7 @@ extern unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, - int use_cache); + int topdown); extern unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index 6dc2577932b1..a452968b29ea 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -21,9 +21,7 @@ static int parport_pc_find_nonpci_ports (int autoirq, int autodma) int count = 0; int virq; - for (np = NULL; (np = of_find_compatible_node(np, - "parallel", - "pnpPNP,400")) != NULL;) { + for_each_compatible_node(np, "parallel", "pnpPNP,400") { prop = of_get_property(np, "reg", &propsize); if (!prop || propsize > 6*sizeof(u32)) continue; diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index d0aec72722e9..f265049dd7d6 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -33,6 +33,8 @@ struct power_pmu { unsigned long *valp); int (*get_alternatives)(u64 event_id, unsigned int flags, u64 alt[]); + u64 (*bhrb_filter_map)(u64 branch_sample_type); + void (*config_bhrb)(u64 pmu_bhrb_filter); void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); int (*limited_pmc_event)(u64 event_id); u32 flags; @@ -42,6 +44,9 @@ struct power_pmu { int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; + + /* BHRB entries in the PMU */ + int bhrb_nr; }; /* @@ -52,6 +57,9 @@ struct power_pmu { #define PPMU_NO_SIPR 0x00000004 /* no SIPR/HV in MMCRA at all */ #define PPMU_NO_CONT_SAMPLING 0x00000008 /* no continuous sampling */ #define PPMU_SIAR_VALID 0x00000010 /* Processor has SIAR Valid bit */ +#define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */ +#define PPMU_HAS_SIER 0x00000040 /* Has SIER */ +#define PPMU_BHRB 0x00000080 /* has BHRB feature enabled */ /* * Values for flags to get_alternatives() @@ -65,6 +73,7 @@ extern int register_power_pmu(struct power_pmu *); struct pt_regs; extern unsigned long perf_misc_flags(struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long int read_bhrb(int n); /* * Only override the default definitions in include/linux/perf_event.h diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 8752bc8e34a3..0c34e4803499 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -82,6 +82,8 @@ #define __REGA0_R31 31 /* sorted alphabetically */ +#define PPC_INST_BHRBE 0x7c00025c +#define PPC_INST_CLRBHRB 0x7c00035c #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe #define PPC_INST_DCBAL 0x7c2005ec @@ -297,6 +299,12 @@ #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) +/* BHRB instructions */ +#define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB) +#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_INST_BHRBE | \ + __PPC_RT(r) | \ + (((n) & 0x3ff) << 11)) + /* Transactional memory instructions */ #define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT) #define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7ff9eaa3ea6c..0a4cc5d649e1 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -40,7 +40,7 @@ * -- BenH. */ -/* PREP sub-platform types see residual.h for these */ +/* PREP sub-platform types. Unused */ #define _PREP_Motorola 0x01 /* motorola prep */ #define _PREP_Firm 0x02 /* firmworks prep */ #define _PREP_IBM 0x00 /* ibm prep */ @@ -56,13 +56,6 @@ extern int _chrp_type; -#ifdef CONFIG_PPC_PREP - -/* what kind of prep workstation we are */ -extern int _prep_type; - -#endif /* CONFIG_PPC_PREP */ - #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */ /* diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 99c92d5363e4..bc2da154f68b 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -74,6 +74,75 @@ struct of_drconf_cell { #define DRCONF_MEM_AI_INVALID 0x00000040 #define DRCONF_MEM_RESERVED 0x00000080 +/* + * There are two methods for telling firmware what our capabilities are. + * Newer machines have an "ibm,client-architecture-support" method on the + * root node. For older machines, we have to call the "process-elf-header" + * method in the /packages/elf-loader node, passing it a fake 32-bit + * ELF header containing a couple of PT_NOTE sections that contain + * structures that contain various information. + */ + +/* New method - extensible architecture description vector. */ + +/* Option vector bits - generic bits in byte 1 */ +#define OV_IGNORE 0x80 /* ignore this vector */ +#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/ + +/* Option vector 1: processor architectures supported */ +#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */ +#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */ +#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */ +#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */ +#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */ +#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */ +#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ +#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ + +/* Option vector 2: Open Firmware options supported */ +#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ + +/* Option vector 3: processor options supported */ +#define OV3_FP 0x80 /* floating point */ +#define OV3_VMX 0x40 /* VMX/Altivec */ +#define OV3_DFP 0x20 /* decimal FP */ + +/* Option vector 4: IBM PAPR implementation */ +#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ + +/* Option vector 5: PAPR/OF options supported + * These bits are also used in firmware_has_feature() to validate + * the capabilities reported for vector 5 in the device tree so we + * encode the vector index in the define and use the OV5_FEAT() + * and OV5_INDX() macros to extract the desired information. + */ +#define OV5_FEAT(x) ((x) & 0xff) +#define OV5_INDX(x) ((x) >> 8) +#define OV5_LPAR 0x0280 /* logical partitioning supported */ +#define OV5_SPLPAR 0x0240 /* shared-processor LPAR supported */ +/* ibm,dynamic-reconfiguration-memory property supported */ +#define OV5_DRCONF_MEMORY 0x0220 +#define OV5_LARGE_PAGES 0x0210 /* large pages supported */ +#define OV5_DONATE_DEDICATE_CPU 0x0202 /* donate dedicated CPU support */ +#define OV5_MSI 0x0201 /* PCIe/MSI support */ +#define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */ +#define OV5_XCMO 0x0440 /* Page Coalescing */ +#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ +#define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ +#define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */ +#define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */ +#define OV5_SUB_PROCESSORS 0x0F01 /* 1,2,or 4 Sub-Processors supported */ + +/* Option Vector 6: IBM PAPR hints */ +#define OV6_LINUX 0x02 /* Linux is our OS */ + +/* + * The architecture vector has an array of PVR mask/value pairs, + * followed by # option vectors - 1, followed by the option vectors. + */ +extern unsigned char ibm_architecture_vec[]; + /* These includes are put at the bottom because they may contain things * that are overridden by this file. Ideally they shouldn't be included * by this file, but there are a bunch of .c files that currently depend diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 5f995681bc1d..becc08e6a65c 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -92,7 +92,8 @@ static inline long regs_return_value(struct pt_regs *regs) } while(0) struct task_struct; -extern unsigned long ptrace_get_reg(struct task_struct *task, int regno); +extern int ptrace_get_reg(struct task_struct *task, int regno, + unsigned long *data); extern int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c9c67fc888c9..5c6fbe2c5ce6 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -268,6 +268,13 @@ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ #define FSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ #define FSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ +#define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ +#define HFSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ +#define HFSCR_TM (1 << (63-58)) /* Enable Transactional Memory */ +#define HFSCR_PM (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */ +#define HFSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ +#define HFSCR_VECVSX (1 << (63-62)) /* Enable VMX/VSX */ +#define HFSCR_FP (1 << (63-63)) /* Enable Floating Point */ #define SPRN_TAR 0x32f /* Target Address Register */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ #define LPCR_VPM0 (1ul << (63-0)) @@ -631,6 +638,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 +#define SPRN_MMCR2 769 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -649,6 +657,10 @@ #define POWER7P_MMCRA_SIAR_VALID 0x10000000 /* P7+ SIAR contents valid */ #define POWER7P_MMCRA_SDAR_VALID 0x08000000 /* P7+ SDAR contents valid */ +#define SPRN_MMCRH 316 /* Hypervisor monitor mode control register */ +#define SPRN_MMCRS 894 /* Supervisor monitor mode control register */ +#define SPRN_MMCRC 851 /* Core monitor mode control register */ + #define SPRN_PMC1 787 #define SPRN_PMC2 788 #define SPRN_PMC3 789 @@ -659,6 +671,11 @@ #define SPRN_PMC8 794 #define SPRN_SIAR 780 #define SPRN_SDAR 781 +#define SPRN_SIER 784 +#define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ +#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ +#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ +#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ #define SPRN_PA6T_MMCR0 795 #define PA6T_MMCR0_EN0 0x0000000000000001UL diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index aef00c675905..a8bc2bb4adc9 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -143,6 +143,8 @@ struct rtas_suspend_me_data { #define RTAS_TYPE_PMGM_TIME_ALARM 0x6f #define RTAS_TYPE_PMGM_CONFIG_CHANGE 0x70 #define RTAS_TYPE_PMGM_SERVICE_PROC 0x71 +/* Platform Resource Reassignment Notification */ +#define RTAS_TYPE_PRRN 0xA0 /* RTAS check-exception vector offset */ #define RTAS_VECTOR_EXTERNAL_INTERRUPT 0x500 @@ -277,6 +279,10 @@ extern int early_init_dt_scan_rtas(unsigned long node, extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal); +#ifdef CONFIG_PPC_PSERIES +extern int pseries_devicetree_update(s32 scope); +#endif + #ifdef CONFIG_PPC_RTAS_DAEMON extern void rtas_cancel_event_scan(void); #else diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 195ce2ac5691..ffbaabebcdca 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -143,6 +143,8 @@ extern void __cpu_die(unsigned int cpu); /* for UP */ #define hard_smp_processor_id() get_hard_smp_processor_id(0) #define smp_setup_cpu_maps() +static inline void inhibit_secondary_onlining(void) {} +static inline void uninhibit_secondary_onlining(void) {} #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 852ed1b384f6..161ab662843b 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -71,6 +71,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev, #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); +extern int prrn_is_enabled(void); #else static inline int start_topology_update(void) { @@ -80,6 +81,10 @@ static inline int stop_topology_update(void) { return 0; } +static inline int prrn_is_enabled(void) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include <asm-generic/topology.h> diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 4ae9a09c3b89..282d43a0c855 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -150,6 +150,7 @@ extern void xics_register_ics(struct ics *ics); extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); +extern void icp_native_eoi(struct irq_data *d); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index 66b9ca4ee94a..77d2ed35b111 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -211,6 +211,7 @@ struct ppc_debug_info { #define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x0000000000000002 #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x0000000000000004 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x0000000000000008 +#define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x0000000000000010 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index ea847abb0d0a..e0c419b8d65b 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -49,6 +49,7 @@ _GLOBAL(__restore_cpu_power7) _GLOBAL(__setup_cpu_power8) mflr r11 bl __init_FSCR + bl __init_PMU bl __init_hvmode_206 mtlr r11 beqlr @@ -57,22 +58,28 @@ _GLOBAL(__setup_cpu_power8) mfspr r3,SPRN_LPCR oris r3, r3, LPCR_AIL_3@h bl __init_LPCR + bl __init_HFSCR bl __init_TLB + bl __init_PMU_HV mtlr r11 blr _GLOBAL(__restore_cpu_power8) mflr r11 bl __init_FSCR + bl __init_PMU mfmsr r3 rldicl. r0,r3,4,63 + mtlr r11 beqlr li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR oris r3, r3, LPCR_AIL_3@h bl __init_LPCR + bl __init_HFSCR bl __init_TLB + bl __init_PMU_HV mtlr r11 blr @@ -120,6 +127,12 @@ __init_FSCR: mtspr SPRN_FSCR,r3 blr +__init_HFSCR: + mfspr r3,SPRN_HFSCR + ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_PM + mtspr SPRN_HFSCR,r3 + blr + __init_TLB: /* Clear the TLB */ li r6,128 @@ -131,3 +144,18 @@ __init_TLB: bdnz 2b ptesync 1: blr + +__init_PMU_HV: + li r5,0 + mtspr SPRN_MMCRC,r5 + mtspr SPRN_MMCRH,r5 + blr + +__init_PMU: + li r5,0 + mtspr SPRN_MMCRS,r5 + mtspr SPRN_MMCRA,r5 + mtspr SPRN_MMCR0,r5 + mtspr SPRN_MMCR1,r5 + mtspr SPRN_MMCR2,r5 + blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index cc39139233d7..ae9f433daabf 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -277,7 +277,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 9ebbc24bb23c..d55c76c571f3 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -41,6 +41,8 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); + __get_cpu_var(irq_stat).doorbell_irqs++; + smp_ipi_demux(); irq_exit(); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf0adb7..04d69c4a5ac2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index f3eab8594d9f..d44a571e45a7 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -23,8 +23,10 @@ #include <asm/code-patching.h> #include <asm/machdep.h> +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) extern void epapr_ev_idle(void); extern u32 epapr_ev_idle_start[]; +#endif bool epapr_paravirt_enabled; @@ -47,11 +49,15 @@ static int __init epapr_paravirt_init(void) for (i = 0; i < (len / 4); i++) { patch_instruction(epapr_hypercall_start + i, insts[i]); +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) patch_instruction(epapr_ev_idle_start + i, insts[i]); +#endif } +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (of_get_property(hyper_node, "has-idle", NULL)) ppc_md.power_save = epapr_ev_idle; +#endif epapr_paravirt_enabled = true; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 87ef8f5ee5bc..80d56f094a0d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -235,6 +235,7 @@ instruction_access_slb_pSeries: .globl hardware_interrupt_hv; hardware_interrupt_pSeries: hardware_interrupt_hv: + HMT_MEDIUM_PPR_DISCARD BEGIN_FTR_SECTION _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) @@ -254,7 +255,11 @@ hardware_interrupt_hv: STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) - MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) + . = 0x900 + .globl decrementer_pSeries +decrementer_pSeries: + _MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD, SOFTEN_TEST_PR) + STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super) @@ -797,7 +802,7 @@ hardware_interrupt_relon_hv: _MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) FTR_SECTION_ELSE _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_206) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment) STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check) STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable) @@ -870,10 +875,6 @@ tm_unavailable_relon_pSeries_1: . = 0x5500 b denorm_exception_hv #endif -#ifdef CONFIG_HVC_SCOM - STD_RELON_EXCEPTION_HV(0x5600, 0x1600, maintence_interrupt) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1600) -#endif /* CONFIG_HVC_SCOM */ STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) /* Other future vectors */ @@ -1066,78 +1067,6 @@ unrecov_user_slb: #endif /* __DISABLED__ */ -/* - * r13 points to the PACA, r9 contains the saved CR, - * r12 contain the saved SRR1, SRR0 is still ready for return - * r3 has the faulting address - * r9 - r13 are saved in paca->exslb. - * r3 is saved in paca->slb_r3 - * We assume we aren't going to take any exceptions during this procedure. - */ -_GLOBAL(slb_miss_realmode) - mflr r10 -#ifdef CONFIG_RELOCATABLE - mtctr r11 -#endif - - stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ - std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - - bl .slb_allocate_realmode - - /* All done -- return from exception. */ - - ld r10,PACA_EXSLB+EX_LR(r13) - ld r3,PACA_EXSLB+EX_R3(r13) - lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - - mtlr r10 - - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ - beq- 2f - -.machine push -.machine "power4" - mtcrf 0x80,r9 - mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ -.machine pop - - RESTORE_PPR_PACA(PACA_EXSLB, r9) - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - ld r11,PACA_EXSLB+EX_R11(r13) - ld r12,PACA_EXSLB+EX_R12(r13) - ld r13,PACA_EXSLB+EX_R13(r13) - rfid - b . /* prevent speculative execution */ - -2: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10,unrecov_slb) - mtspr SPRN_SRR0,r10 - ld r10,PACAKMSR(r13) - mtspr SPRN_SRR1,r10 - rfid - b . - -unrecov_slb: - EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) - DISABLE_INTS - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - - -#ifdef CONFIG_PPC_970_NAP -power4_fixup_nap: - andc r9,r9,r10 - std r9,TI_LOCAL_FLAGS(r11) - ld r10,_LINK(r1) /* make idle task do the */ - std r10,_NIP(r1) /* equivalent of a blr */ - blr -#endif - .align 7 .globl alignment_common alignment_common: @@ -1336,6 +1265,78 @@ _GLOBAL(opal_mc_secondary_handler) /* + * r13 points to the PACA, r9 contains the saved CR, + * r12 contain the saved SRR1, SRR0 is still ready for return + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * We assume we aren't going to take any exceptions during this procedure. + */ +_GLOBAL(slb_miss_realmode) + mflr r10 +#ifdef CONFIG_RELOCATABLE + mtctr r11 +#endif + + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + + bl .slb_allocate_realmode + + /* All done -- return from exception. */ + + ld r10,PACA_EXSLB+EX_LR(r13) + ld r3,PACA_EXSLB+EX_R3(r13) + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ + + mtlr r10 + + andi. r10,r12,MSR_RI /* check for unrecoverable exception */ + beq- 2f + +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_PPR_PACA(PACA_EXSLB, r9) + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +2: mfspr r11,SPRN_SRR0 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10,unrecov_slb) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + rfid + b . + +unrecov_slb: + EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) + DISABLE_INTS + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + + +#ifdef CONFIG_PPC_970_NAP +power4_fixup_nap: + andc r9,r9,r10 + std r9,TI_LOCAL_FLAGS(r11) + ld r10,_LINK(r1) /* make idle task do the */ + std r10,_NIP(r1) /* equivalent of a blr */ + blr +#endif + +/* * Hash table stuff */ .align 7 @@ -1452,20 +1453,36 @@ do_ste_alloc: _GLOBAL(do_stab_bolted) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ + mfspr r11,SPRN_DAR /* ea */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r11,4,(63 - 46 - 4) + li r9,0 /* VSID = 0 for bad address */ + bne- 0f + + /* + * Calculate VSID: + * This is the kernel vsid, we take the top for context from + * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * Here we know that (ea >> 60) == 0xc + */ + lis r9,(MAX_USER_CONTEXT + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT + 1)@l + + srdi r10,r11,SID_SHIFT + rldimi r10,r9,ESID_BITS,0 /* proto vsid */ + ASM_VSID_SCRAMBLE(r10, r9, 256M) + rldic r9,r10,12,16 /* r9 = vsid << 12 */ + +0: /* Hash to the primary group */ ld r10,PACASTABVIRT(r13) - mfspr r11,SPRN_DAR - srdi r11,r11,28 + srdi r11,r11,SID_SHIFT rldimi r10,r11,7,52 /* r10 = first ste of the group */ - /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID | 1 << 37 */ - li r9,0x1 - rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0 - ASM_VSID_SCRAMBLE(r11, r9, 256M) - rldic r9,r11,12,16 /* r9 = vsid << 12 */ - /* Search the primary group for a free entry */ 1: ld r11,0(r10) /* Test valid bit of the current ste */ andi. r11,r11,0x80 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 0886ae6dd5be..b61363d557b5 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -509,6 +509,7 @@ _GLOBAL(copy_and_flush) sync addi r5,r5,8 addi r6,r6,8 + isync blr .align 8 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 31c4fdc6859c..c0d0dbddfba1 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -102,7 +102,7 @@ static int __init fail_iommu_debugfs(void) struct dentry *dir = fault_create_debugfs_attr("fail_iommu", NULL, &fail_iommu); - return IS_ERR(dir) ? PTR_ERR(dir) : 0; + return PTR_RET(dir); } late_initcall(fail_iommu_debugfs); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 4f97fe345526..5cbcf4d5a808 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -374,6 +374,15 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); seq_printf(p, " Machine check exceptions\n"); +#ifdef CONFIG_PPC_DOORBELL + if (cpu_has_feature(CPU_FTR_DBELL)) { + seq_printf(p, "%*s: ", prec, "DBL"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs); + seq_printf(p, " Doorbell interrupts\n"); + } +#endif + return 0; } @@ -387,6 +396,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; +#ifdef CONFIG_PPC_DOORBELL + sum += per_cpu(irq_stat, cpu).doorbell_irqs; +#endif return sum; } diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 5ca82cd4a374..c1eef241017a 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -159,7 +159,7 @@ static int kgdb_singlestep(struct pt_regs *regs) if (user_mode(regs)) return 0; - backup_current_thread_info = (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); + backup_current_thread_info = kmalloc(sizeof(struct thread_info), GFP_KERNEL); /* * On Book E and perhaps other processors, singlestep is handled on * the critical exception stack. This causes current_thread_info() diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index f5725bce9ed2..ab297f492c67 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -301,6 +301,7 @@ static void parse_system_parameter_string(struct seq_file *m) __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; spin_unlock(&rtas_data_buf_lock); if (call_status != 0) { diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index bec1e930ed73..48fbc2b97e95 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -511,8 +511,7 @@ int __init nvram_scan_partitions(void) "detected: 0-length partition\n"); goto out; } - tmp_part = (struct nvram_partition *) - kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); + tmp_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); err = -ENOMEM; if (!tmp_part) { printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n"); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fa12ae42d98c..f325dc923409 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -30,6 +30,7 @@ #include <linux/irq.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/vgaarb.h> #include <asm/processor.h> #include <asm/io.h> @@ -1023,6 +1024,27 @@ void pcibios_setup_bus_self(struct pci_bus *bus) ppc_md.pci_dma_bus_setup(bus); } +void pcibios_setup_device(struct pci_dev *dev) +{ + /* Fixup NUMA node as it may not be setup yet by the generic + * code and is needed by the DMA init + */ + set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); + + /* Hook up default DMA ops */ + set_dma_ops(&dev->dev, pci_dma_ops); + set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); + + /* Additional platform DMA/iommu setup */ + if (ppc_md.pci_dma_dev_setup) + ppc_md.pci_dma_dev_setup(dev); + + /* Read default IRQs and fixup if necessary */ + pci_read_irq_line(dev); + if (ppc_md.pci_irq_fixup) + ppc_md.pci_irq_fixup(dev); +} + void pcibios_setup_bus_devices(struct pci_bus *bus) { struct pci_dev *dev; @@ -1037,23 +1059,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Fixup NUMA node as it may not be setup yet by the generic - * code and is needed by the DMA init - */ - set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); - - /* Hook up default DMA ops */ - set_dma_ops(&dev->dev, pci_dma_ops); - set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); - - /* Additional platform DMA/iommu setup */ - if (ppc_md.pci_dma_dev_setup) - ppc_md.pci_dma_dev_setup(dev); - - /* Read default IRQs and fixup if necessary */ - pci_read_irq_line(dev); - if (ppc_md.pci_irq_fixup) - ppc_md.pci_irq_fixup(dev); + pcibios_setup_device(dev); } } @@ -1494,6 +1500,10 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) if (ppc_md.pcibios_enable_device_hook(dev)) return -EINVAL; + /* avoid pcie irq fix up impact on cardbus */ + if (dev->hdr_type != PCI_HEADER_TYPE_CARDBUS) + pcibios_setup_device(dev); + return pci_enable_resources(dev, mask); } @@ -1725,3 +1735,15 @@ static void fixup_hide_host_resource_fsl(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); + +static void fixup_vga(struct pci_dev *pdev) +{ + u16 cmd; + + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if ((cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) || !vga_default_device()) + vga_set_default_device(pdev); + +} +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, fixup_vga); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545fdde1..c0dea6f23567 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; @@ -910,10 +912,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); -#ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(src); -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ - *dst = *src; return 0; } @@ -984,6 +982,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.ksp_limit = (unsigned long)task_stack_page(p) + _ALIGN_UP(sizeof(struct thread_info), 16); +#ifdef CONFIG_HAVE_HW_BREAKPOINT + p->thread.ptrace_bps[0] = NULL; +#endif + #ifdef CONFIG_PPC_STD_MMU_64 if (mmu_has_feature(MMU_FTR_SLB)) { unsigned long sp_vsid; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 7f7fb7fd991b..5eccda9fd33f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -627,16 +627,11 @@ static void __init early_cmdline_parse(void) #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* - * There are two methods for telling firmware what our capabilities are. - * Newer machines have an "ibm,client-architecture-support" method on the - * root node. For older machines, we have to call the "process-elf-header" - * method in the /packages/elf-loader node, passing it a fake 32-bit - * ELF header containing a couple of PT_NOTE sections that contain - * structures that contain various information. - */ - -/* - * New method - extensible architecture description vector. + * The architecture vector has an array of PVR mask/value pairs, + * followed by # option vectors - 1, followed by the option vectors. + * + * See prom.h for the definition of the bits specified in the + * architecture vector. * * Because the description vector contains a mix of byte and word * values, we declare it as an unsigned char array, and use this @@ -645,65 +640,7 @@ static void __init early_cmdline_parse(void) #define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \ ((x) >> 8) & 0xff, (x) & 0xff -/* Option vector bits - generic bits in byte 1 */ -#define OV_IGNORE 0x80 /* ignore this vector */ -#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/ - -/* Option vector 1: processor architectures supported */ -#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */ -#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */ -#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */ -#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */ -#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */ -#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */ -#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ -#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ - -/* Option vector 2: Open Firmware options supported */ -#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ - -/* Option vector 3: processor options supported */ -#define OV3_FP 0x80 /* floating point */ -#define OV3_VMX 0x40 /* VMX/Altivec */ -#define OV3_DFP 0x20 /* decimal FP */ - -/* Option vector 4: IBM PAPR implementation */ -#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ - -/* Option vector 5: PAPR/OF options supported */ -#define OV5_LPAR 0x80 /* logical partitioning supported */ -#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */ -/* ibm,dynamic-reconfiguration-memory property supported */ -#define OV5_DRCONF_MEMORY 0x20 -#define OV5_LARGE_PAGES 0x10 /* large pages supported */ -#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */ -/* PCIe/MSI support. Without MSI full PCIe is not supported */ -#ifdef CONFIG_PCI_MSI -#define OV5_MSI 0x01 /* PCIe/MSI support */ -#else -#define OV5_MSI 0x00 -#endif /* CONFIG_PCI_MSI */ -#ifdef CONFIG_PPC_SMLPAR -#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */ -#define OV5_XCMO 0x40 /* Page Coalescing */ -#else -#define OV5_CMO 0x00 -#define OV5_XCMO 0x00 -#endif -#define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ -#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ -#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */ -#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ -#define OV5_SUB_PROCESSORS 0x01 /* 1,2,or 4 Sub-Processors supported */ - -/* Option Vector 6: IBM PAPR hints */ -#define OV6_LINUX 0x02 /* Linux is our OS */ - -/* - * The architecture vector has an array of PVR mask/value pairs, - * followed by # option vectors - 1, followed by the option vectors. - */ -static unsigned char ibm_architecture_vec[] = { +unsigned char ibm_architecture_vec[] = { W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */ W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ @@ -747,11 +684,21 @@ static unsigned char ibm_architecture_vec[] = { /* option vector 5: PAPR/OF options */ 19 - 2, /* length */ 0, /* don't ignore, don't halt */ - OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | - OV5_DONATE_DEDICATE_CPU | OV5_MSI, + OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | + OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | +#ifdef CONFIG_PCI_MSI + /* PCIe/MSI support. Without MSI full PCIe is not supported */ + OV5_FEAT(OV5_MSI), +#else 0, - OV5_CMO | OV5_XCMO, - OV5_TYPE1_AFFINITY, +#endif + 0, +#ifdef CONFIG_PPC_SMLPAR + OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO), +#else + 0, +#endif + OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), 0, 0, 0, @@ -765,8 +712,9 @@ static unsigned char ibm_architecture_vec[] = { 0, 0, 0, - OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842, - OV5_SUB_PROCESSORS, + OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | + OV5_FEAT(OV5_PFO_HW_842), + OV5_FEAT(OV5_SUB_PROCESSORS), /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ 0, @@ -2832,11 +2780,13 @@ static void unreloc_toc(void) { } #else -static void __reloc_toc(void *tocstart, unsigned long offset, - unsigned long nr_entries) +static void __reloc_toc(unsigned long offset, unsigned long nr_entries) { unsigned long i; - unsigned long *toc_entry = (unsigned long *)tocstart; + unsigned long *toc_entry; + + /* Get the start of the TOC by using r2 directly. */ + asm volatile("addi %0,2,-0x8000" : "=b" (toc_entry)); for (i = 0; i < nr_entries; i++) { *toc_entry = *toc_entry + offset; @@ -2850,8 +2800,7 @@ static void reloc_toc(void) unsigned long nr_entries = (__prom_init_toc_end - __prom_init_toc_start) / sizeof(long); - /* Need to add offset to get at __prom_init_toc_start */ - __reloc_toc(__prom_init_toc_start + offset, offset, nr_entries); + __reloc_toc(offset, nr_entries); mb(); } @@ -2864,8 +2813,7 @@ static void unreloc_toc(void) mb(); - /* __prom_init_toc_start has been relocated, no need to add offset */ - __reloc_toc(__prom_init_toc_start, -offset, nr_entries); + __reloc_toc(-offset, nr_entries); } #endif #endif diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 245c1b6a0858..3b14d320e69f 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -180,9 +180,10 @@ static int set_user_msr(struct task_struct *task, unsigned long msr) } #ifdef CONFIG_PPC64 -static unsigned long get_user_dscr(struct task_struct *task) +static int get_user_dscr(struct task_struct *task, unsigned long *data) { - return task->thread.dscr; + *data = task->thread.dscr; + return 0; } static int set_user_dscr(struct task_struct *task, unsigned long dscr) @@ -192,7 +193,7 @@ static int set_user_dscr(struct task_struct *task, unsigned long dscr) return 0; } #else -static unsigned long get_user_dscr(struct task_struct *task) +static int get_user_dscr(struct task_struct *task, unsigned long *data) { return -EIO; } @@ -216,19 +217,23 @@ static int set_user_trap(struct task_struct *task, unsigned long trap) /* * Get contents of register REGNO in task TASK. */ -unsigned long ptrace_get_reg(struct task_struct *task, int regno) +int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) { - if (task->thread.regs == NULL) + if ((task->thread.regs == NULL) || !data) return -EIO; - if (regno == PT_MSR) - return get_user_msr(task); + if (regno == PT_MSR) { + *data = get_user_msr(task); + return 0; + } if (regno == PT_DSCR) - return get_user_dscr(task); + return get_user_dscr(task, data); - if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) - return ((unsigned long *)task->thread.regs)[regno]; + if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) { + *data = ((unsigned long *)task->thread.regs)[regno]; + return 0; + } return -EIO; } @@ -1428,6 +1433,7 @@ static long ppc_set_hwdebug(struct task_struct *child, brk.address = bp_info->addr & ~7UL; brk.type = HW_BRK_TYPE_TRANSLATE; + brk.len = 8; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) @@ -1559,7 +1565,9 @@ long arch_ptrace(struct task_struct *child, long request, CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { - tmp = ptrace_get_reg(child, (int) index); + ret = ptrace_get_reg(child, (int) index, &tmp); + if (ret) + break; } else { unsigned int fpidx = index - PT_FPR0; @@ -1636,6 +1644,8 @@ long arch_ptrace(struct task_struct *child, long request, dbginfo.sizeof_condition = 0; #ifdef CONFIG_HAVE_HW_BREAKPOINT dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE; + if (cpu_has_feature(CPU_FTR_DAWR)) + dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR; #else dbginfo.features = 0; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index c0244e766834..f51599e941c7 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -95,7 +95,9 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { - tmp = ptrace_get_reg(child, index); + ret = ptrace_get_reg(child, index, &tmp); + if (ret) + break; } else { flush_fp_to_thread(child); /* @@ -148,7 +150,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, tmp = ((u64 *)child->thread.fpr) [FPRINDEX_3264(numReg)]; } else { /* register within PT_REGS struct */ - tmp = ptrace_get_reg(child, numReg); + unsigned long tmp2; + ret = ptrace_get_reg(child, numReg, &tmp2); + if (ret) + break; + tmp = tmp2; } reg32bits = ((u32*)&tmp)[part]; ret = put_user(reg32bits, (u32 __user *)data); @@ -232,7 +238,10 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, break; CHECK_FULL_REGS(child->thread.regs); if (numReg < PT_FPR0) { - unsigned long freg = ptrace_get_reg(child, numReg); + unsigned long freg; + ret = ptrace_get_reg(child, numReg, &freg); + if (ret) + break; if (index % 2) freg = (freg & ~0xfffffffful) | (data & 0xfffffffful); else diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index c642f0132988..a3e4034b6843 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -57,13 +57,31 @@ #define VALIDATE_READY -1001 /* Firmware image ready for validation */ #define VALIDATE_PARAM_ERR -3 /* RTAS Parameter Error */ #define VALIDATE_HW_ERR -1 /* RTAS Hardware Error */ -#define VALIDATE_TMP_UPDATE 0 /* Validate Return Status */ -#define VALIDATE_FLASH_AUTH 1 /* Validate Return Status */ -#define VALIDATE_INVALID_IMG 2 /* Validate Return Status */ -#define VALIDATE_CUR_UNKNOWN 3 /* Validate Return Status */ -#define VALIDATE_TMP_COMMIT_DL 4 /* Validate Return Status */ -#define VALIDATE_TMP_COMMIT 5 /* Validate Return Status */ -#define VALIDATE_TMP_UPDATE_DL 6 /* Validate Return Status */ + +/* ibm,validate-flash-image update result tokens */ +#define VALIDATE_TMP_UPDATE 0 /* T side will be updated */ +#define VALIDATE_FLASH_AUTH 1 /* Partition does not have authority */ +#define VALIDATE_INVALID_IMG 2 /* Candidate image is not valid */ +#define VALIDATE_CUR_UNKNOWN 3 /* Current fixpack level is unknown */ +/* + * Current T side will be committed to P side before being replace with new + * image, and the new image is downlevel from current image + */ +#define VALIDATE_TMP_COMMIT_DL 4 +/* + * Current T side will be committed to P side before being replaced with new + * image + */ +#define VALIDATE_TMP_COMMIT 5 +/* + * T side will be updated with a downlevel image + */ +#define VALIDATE_TMP_UPDATE_DL 6 +/* + * The candidate image's release date is later than the system's firmware + * service entitlement date - service warranty period has expired + */ +#define VALIDATE_OUT_OF_WRNTY 7 /* ibm,manage-flash-image operation tokens */ #define RTAS_REJECT_TMP_IMG 0 @@ -790,6 +808,11 @@ static void __exit rtas_flash_cleanup(void) { rtas_flash_term_hook = NULL; + if (rtas_firmware_flash_list) { + free_flash_list(rtas_firmware_flash_list); + rtas_firmware_flash_list = NULL; + } + if (flash_block_cache) kmem_cache_destroy(flash_block_cache); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 71cb20d6ec61..6e7b7cdeec65 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -201,7 +201,7 @@ static void python_countermeasures(struct device_node *dev) iounmap(chip_regs); } -void __init init_pci_config_tokens (void) +void __init init_pci_config_tokens(void) { read_pci_config = rtas_token("read-pci-config"); write_pci_config = rtas_token("write-pci-config"); @@ -209,7 +209,7 @@ void __init init_pci_config_tokens (void) ibm_write_pci_config = rtas_token("ibm,write-pci-config"); } -unsigned long get_phb_buid (struct device_node *phb) +unsigned long get_phb_buid(struct device_node *phb) { struct resource r; diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 1045ff49cc6d..1130c53ad652 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -29,6 +29,7 @@ #include <asm/nvram.h> #include <linux/atomic.h> #include <asm/machdep.h> +#include <asm/topology.h> static DEFINE_SPINLOCK(rtasd_log_lock); @@ -87,6 +88,8 @@ static char *rtas_event_type(int type) return "Resource Deallocation Event"; case RTAS_TYPE_DUMP: return "Dump Notification Event"; + case RTAS_TYPE_PRRN: + return "Platform Resource Reassignment Event"; } return rtas_type[0]; @@ -265,9 +268,51 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) spin_unlock_irqrestore(&rtasd_log_lock, s); return; } +} + +#ifdef CONFIG_PPC_PSERIES +static s32 prrn_update_scope; +static void prrn_work_fn(struct work_struct *work) +{ + /* + * For PRRN, we must pass the negative of the scope value in + * the RTAS event. + */ + pseries_devicetree_update(-prrn_update_scope); } +static DECLARE_WORK(prrn_work, prrn_work_fn); + +void prrn_schedule_update(u32 scope) +{ + flush_work(&prrn_work); + prrn_update_scope = scope; + schedule_work(&prrn_work); +} + +static void handle_rtas_event(const struct rtas_error_log *log) +{ + if (log->type == RTAS_TYPE_PRRN) { + /* For PRRN Events the extended log length is used to denote + * the scope for calling rtas update-nodes. + */ + if (prrn_is_enabled()) + prrn_schedule_update(log->extended_log_length); + } + + return; +} + +#else + +static void handle_rtas_event(const struct rtas_error_log *log) +{ + return; +} + +#endif + static int rtas_log_open(struct inode * inode, struct file * file) { return 0; @@ -388,8 +433,10 @@ static void do_event_scan(void) break; } - if (error == 0) + if (error == 0) { pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0); + handle_rtas_event((struct rtas_error_log *)logdata); + } } while(error == 0); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bdc499c17872..63d051f5b7a5 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -621,12 +621,6 @@ int check_legacy_ioport(unsigned long base_port) case FDC_BASE: /* FDC1 */ np = of_find_node_by_type(NULL, "fdc"); break; -#ifdef CONFIG_PPC_PREP - case _PIDXR: - case _PNPWRP: - case PNPBIOS_BASE: - /* implement me */ -#endif default: /* ipmi is supposed to fail here */ break; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e245b4..95068bf569ad 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f8543cb57..c1794286098c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f77fa22754bc..5fc29ad7e26f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -1049,10 +1049,8 @@ static int __init rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_RET(pdev); } module_init(rtc_init); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace657ce..2da67e7a16d5 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 1b2076f049ce..d4f463ac65b1 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -113,6 +113,10 @@ static struct vdso_patch_def vdso_patches[] = { CPU_FTR_USE_TB, 0, "__kernel_get_tbfreq", NULL }, + { + CPU_FTR_USE_TB, 0, + "__kernel_time", NULL + }, }; /* diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 4ee09ee2e836..27e2f623210b 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -181,6 +181,32 @@ V_FUNCTION_END(__kernel_clock_getres) /* + * Exact prototype of time() + * + * time_t time(time *t); + * + */ +V_FUNCTION_BEGIN(__kernel_time) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds t */ + bl __get_datapage@local + mr r9, r3 /* datapage ptr in r9 */ + + lwz r3,STAMP_XTIME+TSPEC_TV_SEC(r9) + + cmplwi r11,0 /* check if t is NULL */ + beq 2f + stw r3,0(r11) /* store result at *t */ +2: mtlr r12 + crclr cr0*4+so + blr + .cfi_endproc +V_FUNCTION_END(__kernel_time) + +/* * This is the core of clock_gettime() and gettimeofday(), * it returns the current time in r3 (seconds) and r4. * On entry, r7 gives the resolution of r4, either USEC_PER_SEC diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 43200ba2e570..f223409629b9 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -150,6 +150,7 @@ VERSION #ifdef CONFIG_PPC64 __kernel_getcpu; #endif + __kernel_time; local: *; }; diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index e97a9a0dc4ac..a76b4af37ef2 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -164,6 +164,32 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) .cfi_endproc V_FUNCTION_END(__kernel_clock_getres) +/* + * Exact prototype of time() + * + * time_t time(time *t); + * + */ +V_FUNCTION_BEGIN(__kernel_time) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds t */ + bl V_LOCAL_FUNC(__get_datapage) + + ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + + cmpldi r11,0 /* check if t is NULL */ + beq 2f + std r4,0(r11) /* store result at *t */ +2: mtlr r12 + crclr cr0*4+so + mr r3,r4 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_time) + /* * This is the core of clock_gettime() and gettimeofday(), diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index e6c1758f3588..e4863819663b 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -147,6 +147,7 @@ VERSION __kernel_sync_dicache_p5; __kernel_sigtramp_rt64; __kernel_getcpu; + __kernel_time; local: *; }; diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index ead58e317294..5d7d29a313eb 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -326,8 +326,8 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu) vcpu3s->context_id[0] = err; vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1) - << USER_ESID_BITS) - 1; - vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS; + << ESID_BITS) - 1; + vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << ESID_BITS; vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first; kvmppc_mmu_hpte_init(vcpu); diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 84035a528c80..37f1cc417ca0 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -122,11 +122,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) add r8,r8,r7 std r8,HSTATE_DECEXP(r13) +#ifdef CONFIG_SMP /* * On PPC970, if the guest vcpu has an external interrupt pending, * send ourselves an IPI so as to interrupt the guest once it * enables interrupts. (It must have interrupts disabled, * otherwise we would already have delivered the interrupt.) + * + * XXX If this is a UP build, smp_send_reschedule is not available, + * so the interrupt will be delayed until the next time the vcpu + * enters the guest with interrupts enabled. */ BEGIN_FTR_SECTION ld r0, VCPU_PENDING_EXC(r4) @@ -141,6 +146,7 @@ BEGIN_FTR_SECTION mr r4, r31 32: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) +#endif /* CONFIG_SMP */ /* Jump to partition switch code */ bl .kvmppc_hv_entry_trampoline diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 5e93438afb06..dbdc15aa8127 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1039,7 +1039,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) if (!vcpu_book3s) goto out; - vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) + vcpu_book3s->shadow_vcpu = kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); if (!vcpu_book3s->shadow_vcpu) goto free_vcpu; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd43655f..33db48a8ce24 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edfb9a9b..1c6a9d729df4 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; - int i; - - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } -} - -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; + int tlbsel; int i; - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } - - clear_tlb_privs(vcpu_e500); } void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26e65fb..2f4baa074b2e 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 1b6e1271719f..1ed4419c533b 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -195,6 +195,11 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); unsigned long tprot = prot; + /* + * If we hit a bad address return error. + */ + if (!vsid) + return -1; /* Make kernel text executable */ if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; @@ -759,6 +764,8 @@ void __init early_init_mmu(void) /* Initialize stab / SLB management */ if (mmu_has_feature(MMU_FTR_SLB)) slb_initialize(); + else + stab_initialize(get_paca()->stab_real); } #ifdef CONFIG_SMP @@ -922,11 +929,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n", ea, access, trap); - if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) { - DBG_LOW(" out of pgtable range !\n"); - return 1; - } - /* Get region & vsid */ switch (REGION_ID(ea)) { case USER_REGION_ID: @@ -957,6 +959,11 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) } DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid); + /* Bad address. */ + if (!vsid) { + DBG_LOW("Bad address!\n"); + return 1; + } /* Get pgdir */ pgdir = mm->pgd; if (pgdir == NULL) @@ -1126,6 +1133,8 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, /* Get VSID */ ssize = user_segment_size(ea); vsid = get_vsid(mm->context.id, ea, ssize); + if (!vsid) + return; /* Hash doesn't like irqs */ local_irq_save(flags); @@ -1221,21 +1230,60 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) bad_page_fault(regs, address, SIGBUS); } +long hpte_insert_repeating(unsigned long hash, unsigned long vpn, + unsigned long pa, unsigned long rflags, + unsigned long vflags, int psize, int ssize) +{ + unsigned long hpte_group; + long slot; + +repeat: + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, vflags, + psize, ssize); + + /* Primary is full, try the secondary */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, + vflags | HPTE_V_SECONDARY, + psize, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP)&~0x7UL; + + ppc_md.hpte_remove(hpte_group); + goto repeat; + } + } + + return slot; +} + #ifdef CONFIG_DEBUG_PAGEALLOC static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { - unsigned long hash, hpteg; + unsigned long hash; unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize); unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize); unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL); - int ret; + long ret; hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); - hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); - ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr), - mode, HPTE_V_BOLTED, - mmu_linear_psize, mmu_kernel_ssize); + /* Don't create HPTE entries for bad address */ + if (!vsid) + return; + + ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode, + HPTE_V_BOLTED, + mmu_linear_psize, mmu_kernel_ssize); + BUG_ON (ret < 0); spin_lock(&linear_map_hash_lock); BUG_ON(linear_map_hash_slots[lmi] & 0x80); diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index cecad348f604..b913f416d97a 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -14,6 +14,10 @@ #include <asm/cacheflush.h> #include <asm/machdep.h> +extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn, + unsigned long pa, unsigned long rlags, + unsigned long vflags, int psize, int ssize); + int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, int local, int ssize, unsigned int shift, unsigned int mmu_psize) @@ -83,14 +87,9 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, if (likely(!(old_pte & _PAGE_HASHPTE))) { unsigned long hash = hpt_hash(vpn, shift, ssize); - unsigned long hpte_group; pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; -repeat: - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - /* clear HPTE slot informations in new PTE */ #ifdef CONFIG_PPC_64K_PAGES new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0; @@ -101,26 +100,8 @@ repeat: rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); - /* Insert into the hash table, primary slot */ - slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, - mmu_psize, ssize); - - /* Primary is full, try the secondary */ - if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, - HPTE_V_SECONDARY, - mmu_psize, ssize); - if (slot == -1) { - if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP)&~0x7UL; - - ppc_md.hpte_remove(hpte_group); - goto repeat; - } - } + slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, + mmu_psize, ssize); /* * Hypervisor failure. Restore old pte and return -1 diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a6de0a7d8eb..5dc52d803ed8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -742,7 +742,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct hstate *hstate = hstate_file(file); int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate)); - return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0); + return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1); } #endif diff --git a/arch/powerpc/mm/icswx.c b/arch/powerpc/mm/icswx.c index 8cdbd8634a58..915412e4d5ba 100644 --- a/arch/powerpc/mm/icswx.c +++ b/arch/powerpc/mm/icswx.c @@ -67,7 +67,7 @@ void switch_cop(struct mm_struct *next) { -#ifdef CONFIG_ICSWX_PID +#ifdef CONFIG_PPC_ICSWX_PID mtspr(SPRN_PID, next->context.cop_pid); #endif mtspr(SPRN_ACOP, next->context.acop); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f1f7409a4183..056732e8ca38 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -66,10 +66,9 @@ unsigned long long memory_limit; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; +EXPORT_SYMBOL(kmap_pte); pgprot_t kmap_prot; - EXPORT_SYMBOL(kmap_prot); -EXPORT_SYMBOL(kmap_pte); static inline pte_t *virt_to_kpte(unsigned long vaddr) { diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 40bc5b0ace54..d1d1b92c5b99 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -29,15 +29,6 @@ static DEFINE_SPINLOCK(mmu_context_lock); static DEFINE_IDA(mmu_context_ida); -/* - * 256MB segment - * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments - * available for user mappings. Each segment contains 2^28 bytes. Each - * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts - * (19 == 37 + 28 - 46). - */ -#define MAX_CONTEXT ((1UL << CONTEXT_BITS) - 1) - int __init_new_context(void) { int index; @@ -56,7 +47,7 @@ again: else if (err) return err; - if (index > MAX_CONTEXT) { + if (index > MAX_USER_CONTEXT) { spin_lock(&mmu_context_lock); ida_remove(&mmu_context_ida, index); spin_unlock(&mmu_context_lock); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index bba87ca2b4d7..2d13f90476bd 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -22,6 +22,10 @@ #include <linux/pfn.h> #include <linux/cpuset.h> #include <linux/node.h> +#include <linux/stop_machine.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> @@ -29,6 +33,7 @@ #include <asm/paca.h> #include <asm/hvcall.h> #include <asm/setup.h> +#include <asm/vdso.h> static int numa_enabled = 1; @@ -79,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void) dbg("Node to cpumask map for %d nodes\n", nr_node_ids); } -static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn, +static int __init fake_numa_create_new_node(unsigned long end_pfn, unsigned int *nid) { unsigned long long mem; @@ -201,7 +206,7 @@ int __node_distance(int a, int b) int distance = LOCAL_DISTANCE; if (!form1_affinity) - return distance; + return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); for (i = 0; i < distance_ref_points_depth; i++) { if (distance_lookup_table[a][i] == distance_lookup_table[b][i]) @@ -291,9 +296,7 @@ EXPORT_SYMBOL_GPL(of_node_to_nid); static int __init find_min_common_depth(void) { int depth; - struct device_node *chosen; struct device_node *root; - const char *vec5; if (firmware_has_feature(FW_FEATURE_OPAL)) root = of_find_node_by_path("/ibm,opal"); @@ -325,24 +328,10 @@ static int __init find_min_common_depth(void) distance_ref_points_depth /= sizeof(int); -#define VEC5_AFFINITY_BYTE 5 -#define VEC5_AFFINITY 0x80 - - if (firmware_has_feature(FW_FEATURE_OPAL)) + if (firmware_has_feature(FW_FEATURE_OPAL) || + firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) { + dbg("Using form 1 affinity\n"); form1_affinity = 1; - else { - chosen = of_find_node_by_path("/chosen"); - if (chosen) { - vec5 = of_get_property(chosen, - "ibm,architecture-vec-5", NULL); - if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & - VEC5_AFFINITY)) { - dbg("Using form 1 affinity\n"); - form1_affinity = 1; - } - - of_node_put(chosen); - } } if (form1_affinity) { @@ -1270,10 +1259,18 @@ u64 memory_hotplug_max(void) /* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR +struct topology_update_data { + struct topology_update_data *next; + unsigned int cpu; + int old_nid; + int new_nid; +}; + static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS]; static cpumask_t cpu_associativity_changes_mask; static int vphn_enabled; -static void set_topology_timer(void); +static int prrn_enabled; +static void reset_topology_timer(void); /* * Store the current values of the associativity change counters in the @@ -1309,11 +1306,9 @@ static void setup_cpu_associativity_change_counters(void) */ static int update_cpu_associativity_changes_mask(void) { - int cpu, nr_cpus = 0; + int cpu; cpumask_t *changes = &cpu_associativity_changes_mask; - cpumask_clear(changes); - for_each_possible_cpu(cpu) { int i, changed = 0; u8 *counts = vphn_cpu_change_counts[cpu]; @@ -1327,11 +1322,10 @@ static int update_cpu_associativity_changes_mask(void) } if (changed) { cpumask_set_cpu(cpu, changes); - nr_cpus++; } } - return nr_cpus; + return cpumask_weight(changes); } /* @@ -1423,40 +1417,84 @@ static long vphn_get_associativity(unsigned long cpu, } /* + * Update the CPU maps and sysfs entries for a single CPU when its NUMA + * characteristics change. This function doesn't perform any locking and is + * only safe to call from stop_machine(). + */ +static int update_cpu_topology(void *data) +{ + struct topology_update_data *update; + unsigned long cpu; + + if (!data) + return -EINVAL; + + cpu = get_cpu(); + + for (update = data; update; update = update->next) { + if (cpu != update->cpu) + continue; + + unregister_cpu_under_node(update->cpu, update->old_nid); + unmap_cpu_from_node(update->cpu); + map_cpu_to_node(update->cpu, update->new_nid); + vdso_getcpu_init(); + register_cpu_under_node(update->cpu, update->new_nid); + } + + return 0; +} + +/* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. */ int arch_update_cpu_topology(void) { - int cpu, nid, old_nid, changed = 0; + unsigned int cpu, changed = 0; + struct topology_update_data *updates, *ud; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; + cpumask_t updated_cpus; struct device *dev; + int weight, i = 0; + + weight = cpumask_weight(&cpu_associativity_changes_mask); + if (!weight) + return 0; + + updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL); + if (!updates) + return 0; - for_each_cpu(cpu,&cpu_associativity_changes_mask) { + cpumask_clear(&updated_cpus); + + for_each_cpu(cpu, &cpu_associativity_changes_mask) { + ud = &updates[i++]; + ud->cpu = cpu; vphn_get_associativity(cpu, associativity); - nid = associativity_to_nid(associativity); + ud->new_nid = associativity_to_nid(associativity); - if (nid < 0 || !node_online(nid)) - nid = first_online_node; + if (ud->new_nid < 0 || !node_online(ud->new_nid)) + ud->new_nid = first_online_node; - old_nid = numa_cpu_lookup_table[cpu]; + ud->old_nid = numa_cpu_lookup_table[cpu]; + cpumask_set_cpu(cpu, &updated_cpus); - /* Disable hotplug while we update the cpu - * masks and sysfs. - */ - get_online_cpus(); - unregister_cpu_under_node(cpu, old_nid); - unmap_cpu_from_node(cpu); - map_cpu_to_node(cpu, nid); - register_cpu_under_node(cpu, nid); - put_online_cpus(); - - dev = get_cpu_device(cpu); + if (i < weight) + ud->next = &updates[i]; + } + + stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + + for (ud = &updates[0]; ud; ud = ud->next) { + dev = get_cpu_device(ud->cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); + cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask); changed = 1; } + kfree(updates); return changed; } @@ -1473,49 +1511,157 @@ void topology_schedule_update(void) static void topology_timer_fn(unsigned long ignored) { - if (!vphn_enabled) - return; - if (update_cpu_associativity_changes_mask() > 0) + if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask)) topology_schedule_update(); - set_topology_timer(); + else if (vphn_enabled) { + if (update_cpu_associativity_changes_mask() > 0) + topology_schedule_update(); + reset_topology_timer(); + } } static struct timer_list topology_timer = TIMER_INITIALIZER(topology_timer_fn, 0, 0); -static void set_topology_timer(void) +static void reset_topology_timer(void) { topology_timer.data = 0; topology_timer.expires = jiffies + 60 * HZ; - add_timer(&topology_timer); + mod_timer(&topology_timer, topology_timer.expires); +} + +static void stage_topology_update(int core_id) +{ + cpumask_or(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, cpu_sibling_mask(core_id)); + reset_topology_timer(); +} + +static int dt_update_callback(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct of_prop_reconfig *update; + int rc = NOTIFY_DONE; + + switch (action) { + case OF_RECONFIG_UPDATE_PROPERTY: + update = (struct of_prop_reconfig *)data; + if (!of_prop_cmp(update->dn->type, "cpu") && + !of_prop_cmp(update->prop->name, "ibm,associativity")) { + u32 core_id; + of_property_read_u32(update->dn, "reg", &core_id); + stage_topology_update(core_id); + rc = NOTIFY_OK; + } + break; + } + + return rc; } +static struct notifier_block dt_update_nb = { + .notifier_call = dt_update_callback, +}; + /* - * Start polling for VPHN associativity changes. + * Start polling for associativity changes. */ int start_topology_update(void) { int rc = 0; - /* Disabled until races with load balancing are fixed */ - if (0 && firmware_has_feature(FW_FEATURE_VPHN) && - get_lppaca()->shared_proc) { - vphn_enabled = 1; - setup_cpu_associativity_change_counters(); - init_timer_deferrable(&topology_timer); - set_topology_timer(); - rc = 1; + if (firmware_has_feature(FW_FEATURE_PRRN)) { + if (!prrn_enabled) { + prrn_enabled = 1; + vphn_enabled = 0; + rc = of_reconfig_notifier_register(&dt_update_nb); + } + } else if (firmware_has_feature(FW_FEATURE_VPHN) && + get_lppaca()->shared_proc) { + if (!vphn_enabled) { + prrn_enabled = 0; + vphn_enabled = 1; + setup_cpu_associativity_change_counters(); + init_timer_deferrable(&topology_timer); + reset_topology_timer(); + } } return rc; } -__initcall(start_topology_update); /* * Disable polling for VPHN associativity changes. */ int stop_topology_update(void) { - vphn_enabled = 0; - return del_timer_sync(&topology_timer); + int rc = 0; + + if (prrn_enabled) { + prrn_enabled = 0; + rc = of_reconfig_notifier_unregister(&dt_update_nb); + } else if (vphn_enabled) { + vphn_enabled = 0; + rc = del_timer_sync(&topology_timer); + } + + return rc; +} + +int prrn_is_enabled(void) +{ + return prrn_enabled; +} + +static int topology_read(struct seq_file *file, void *v) +{ + if (vphn_enabled || prrn_enabled) + seq_puts(file, "on\n"); + else + seq_puts(file, "off\n"); + + return 0; +} + +static int topology_open(struct inode *inode, struct file *file) +{ + return single_open(file, topology_read, NULL); +} + +static ssize_t topology_write(struct file *file, const char __user *buf, + size_t count, loff_t *off) +{ + char kbuf[4]; /* "on" or "off" plus null. */ + int read_len; + + read_len = count < 3 ? count : 3; + if (copy_from_user(kbuf, buf, read_len)) + return -EINVAL; + + kbuf[read_len] = '\0'; + + if (!strncmp(kbuf, "on", 2)) + start_topology_update(); + else if (!strncmp(kbuf, "off", 3)) + stop_topology_update(); + else + return -EINVAL; + + return count; +} + +static const struct file_operations topology_ops = { + .read = seq_read, + .write = topology_write, + .open = topology_open, + .release = single_release +}; + +static int topology_update_init(void) +{ + start_topology_update(); + proc_create("powerpc/topology_updates", 644, NULL, &topology_ops); + + return 0; } +device_initcall(topology_update_init); #endif /* CONFIG_PPC_SPLPAR */ diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e212a271c7a4..654258f165ae 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -61,7 +61,7 @@ #endif #ifdef CONFIG_PPC_STD_MMU_64 -#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT)) +#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT)) #error TASK_SIZE_USER64 exceeds user VSID range #endif #endif diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 1a16ca227757..17aa6dfceb34 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -31,10 +31,15 @@ * No other registers are examined or changed. */ _GLOBAL(slb_allocate_realmode) - /* r3 = faulting address */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r3,4,(63 - 46 - 4) + bne- 8f srdi r9,r3,60 /* get region */ - srdi r10,r3,28 /* get esid */ + srdi r10,r3,SID_SHIFT /* get esid */ cmpldi cr7,r9,0xc /* cmp PAGE_OFFSET for later use */ /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */ @@ -56,12 +61,14 @@ _GLOBAL(slb_allocate_realmode) */ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) @@ -91,24 +98,19 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) _GLOBAL(slb_miss_kernel_load_io) li r11,0 6: - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T -0: /* user address: proto-VSID = context << 15 | ESID. First check - * if the address is within the boundaries of the user region - */ - srdi. r9,r10,USER_ESID_BITS - bne- 8f /* invalid ea bits set */ - - +0: /* when using slices, we extract the psize off the slice bitmaps * and then we need to get the sllp encoding off the mmu_psize_defs * array. @@ -164,15 +166,13 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) ld r9,PACACONTEXTID(r13) BEGIN_FTR_SECTION cmpldi r10,0x1000 -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - rldimi r10,r9,USER_ESID_BITS,0 -BEGIN_FTR_SECTION bge slb_finish_load_1T END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ li r10,0 /* BAD_VSID */ + li r9,0 /* BAD_VSID */ li r11,SLB_VSID_USER /* flags don't much matter */ b slb_finish_load @@ -221,8 +221,6 @@ _GLOBAL(slb_allocate_user) /* get context to calculate proto-VSID */ ld r9,PACACONTEXTID(r13) - rldimi r10,r9,USER_ESID_BITS,0 - /* fall through slb_finish_load */ #endif /* __DISABLED__ */ @@ -231,9 +229,10 @@ _GLOBAL(slb_allocate_user) /* * Finish loading of an SLB entry and return * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET + * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET */ slb_finish_load: + rldimi r10,r9,ESID_BITS,0 ASM_VSID_SCRAMBLE(r10,r9,256M) /* * bits above VSID_BITS_256M need to be ignored from r10 @@ -298,10 +297,11 @@ _GLOBAL(slb_compare_rr_to_size) /* * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return. * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9 + * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9 */ slb_finish_load_1T: - srdi r10,r10,40-28 /* get 1T ESID */ + srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */ + rldimi r10,r9,ESID_BITS_1T,0 ASM_VSID_SCRAMBLE(r10,r9,1T) /* * bits above VSID_BITS_1T need to be ignored from r10 diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index cf9dada734b6..3e99c149271a 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -237,134 +237,112 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz #endif } +/* + * Compute which slice addr is part of; + * set *boundary_addr to the start or end boundary of that slice + * (depending on 'end' parameter); + * return boolean indicating if the slice is marked as available in the + * 'available' slice_mark. + */ +static bool slice_scan_available(unsigned long addr, + struct slice_mask available, + int end, + unsigned long *boundary_addr) +{ + unsigned long slice; + if (addr < SLICE_LOW_TOP) { + slice = GET_LOW_SLICE_INDEX(addr); + *boundary_addr = (slice + end) << SLICE_LOW_SHIFT; + return !!(available.low_slices & (1u << slice)); + } else { + slice = GET_HIGH_SLICE_INDEX(addr); + *boundary_addr = (slice + end) ? + ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; + return !!(available.high_slices & (1u << slice)); + } +} + static unsigned long slice_find_area_bottomup(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long start_addr, addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); - - if (use_cache) { - if (len <= mm->cached_hole_size) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - } else - start_addr = addr = mm->free_area_cache; - } else - start_addr = addr = TASK_UNMAPPED_BASE; - -full_search: - for (;;) { - addr = _ALIGN_UP(addr, 1ul << pshift); - if ((TASK_SIZE - len) < addr) - break; - vma = find_vma(mm, addr); - BUG_ON(vma && (addr >= vma->vm_end)); - - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_LOW_SHIFT); - else - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_HIGH_SHIFT); + unsigned long addr, found, next_end; + struct vm_unmapped_area_info info; + + info.flags = 0; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; + + addr = TASK_UNMAPPED_BASE; + while (addr < TASK_SIZE) { + info.low_limit = addr; + if (!slice_scan_available(addr, available, 1, &addr)) continue; + + next_slice: + /* + * At this point [info.low_limit; addr) covers + * available slices only and ends at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the next available slice. + */ + if (addr >= TASK_SIZE) + addr = TASK_SIZE; + else if (slice_scan_available(addr, available, 1, &next_end)) { + addr = next_end; + goto next_slice; } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - if (use_cache) - mm->free_area_cache = addr + len; - return addr; - } - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - } + info.high_limit = addr; - /* Make sure we didn't miss any holes */ - if (use_cache && start_addr != TASK_UNMAPPED_BASE) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - goto full_search; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } + return -ENOMEM; } static unsigned long slice_find_area_topdown(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); + unsigned long addr, found, prev; + struct vm_unmapped_area_info info; - /* check if free_area_cache is useful for us */ - if (use_cache) { - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - - /* either no address requested or can't fit in requested - * address hole - */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - mask = slice_range_to_mask(addr, len); - if (slice_check_fit(mask, available) && - slice_area_is_free(mm, addr, len)) - /* remember the address as a hint for - * next time - */ - return (mm->free_area_cache = addr); - } - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; addr = mm->mmap_base; - while (addr > len) { - /* Go down by chunk size */ - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - - /* Check for hit with different page size */ - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_DOWN(addr, 1ul << SLICE_LOW_SHIFT); - else if (addr < (1ul << SLICE_HIGH_SHIFT)) - addr = SLICE_LOW_TOP; - else - addr = _ALIGN_DOWN(addr, 1ul << SLICE_HIGH_SHIFT); + while (addr > PAGE_SIZE) { + info.high_limit = addr; + if (!slice_scan_available(addr - 1, available, 0, &addr)) continue; - } + prev_slice: /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: + * At this point [addr; info.high_limit) covers + * available slices only and starts at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the previous available slice. */ - vma = find_vma(mm, addr); - if (!vma || (addr + len) <= vma->vm_start) { - /* remember the address as a hint for next time */ - if (use_cache) - mm->free_area_cache = addr; - return addr; + if (addr < PAGE_SIZE) + addr = PAGE_SIZE; + else if (slice_scan_available(addr - 1, available, 0, &prev)) { + addr = prev; + goto prev_slice; } + info.low_limit = addr; - /* remember the largest hole we saw so far */ - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } /* @@ -373,28 +351,18 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * can happen with large stack limits and large mmap() * allocations. */ - addr = slice_find_area_bottomup(mm, len, available, psize, 0); - - /* - * Restore the topdown base: - */ - if (use_cache) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - } - - return addr; + return slice_find_area_bottomup(mm, len, available, psize); } static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, struct slice_mask mask, int psize, - int topdown, int use_cache) + int topdown) { if (topdown) - return slice_find_area_topdown(mm, len, mask, psize, use_cache); + return slice_find_area_topdown(mm, len, mask, psize); else - return slice_find_area_bottomup(mm, len, mask, psize, use_cache); + return slice_find_area_bottomup(mm, len, mask, psize); } #define or_mask(dst, src) do { \ @@ -415,7 +383,7 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, int use_cache) + int topdown) { struct slice_mask mask = {0, 0}; struct slice_mask good_mask; @@ -430,8 +398,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, BUG_ON(mm->task_size == 0); slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize); - slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d, use_cache=%d\n", - addr, len, flags, topdown, use_cache); + slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n", + addr, len, flags, topdown); if (len > mm->task_size) return -ENOMEM; @@ -503,8 +471,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing * slices for that size */ - newaddr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + newaddr = slice_find_area(mm, len, good_mask, psize, topdown); if (newaddr != -ENOMEM) { /* Found within the good mask, we don't have to setup, * we thus return directly @@ -536,8 +503,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, * anywhere in the good area. */ if (addr) { - addr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, good_mask, psize, topdown); if (addr != -ENOMEM) { slice_dbg(" found area at 0x%lx\n", addr); return addr; @@ -547,15 +513,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing slices * for that size plus free slices */ - addr = slice_find_area(mm, len, potential_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, potential_mask, psize, topdown); #ifdef CONFIG_PPC_64K_PAGES if (addr == -ENOMEM && psize == MMU_PAGE_64K) { /* retry the search with 4k-page slices included */ or_mask(potential_mask, compat_mask); addr = slice_find_area(mm, len, potential_mask, psize, - topdown, use_cache); + topdown); } #endif @@ -586,8 +551,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long flags) { return slice_get_unmapped_area(addr, len, flags, - current->mm->context.user_psize, - 0, 1); + current->mm->context.user_psize, 0); } unsigned long arch_get_unmapped_area_topdown(struct file *filp, @@ -597,8 +561,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long flags) { return slice_get_unmapped_area(addr0, len, flags, - current->mm->context.user_psize, - 1, 1); + current->mm->context.user_psize, 1); } unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 0d82ef50dc3f..023ec8a13f38 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -82,11 +82,11 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, if (!is_kernel_addr(addr)) { ssize = user_segment_size(addr); vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); } else { vsid = get_kernel_vsid(addr, mmu_kernel_ssize); ssize = mmu_kernel_ssize; } + WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); rpte = __real_pte(__pte(pte), ptep); diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index af3fac23768c..510fae10513d 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -2,9 +2,10 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror obj-$(CONFIG_PERF_EVENTS) += callchain.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ - power5+-pmu.o power6-pmu.o power7-pmu.o + power5+-pmu.o power6-pmu.o power7-pmu.o \ + power8-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o diff --git a/arch/powerpc/perf/bhrb.S b/arch/powerpc/perf/bhrb.S new file mode 100644 index 000000000000..d85f9a58ddbc --- /dev/null +++ b/arch/powerpc/perf/bhrb.S @@ -0,0 +1,44 @@ +/* + * Basic assembly code to read BHRB entries + * + * Copyright 2013 Anshuman Khandual, 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 <asm/ppc_asm.h> +#include <asm/ppc-opcode.h> + + .text + +.balign 8 + +/* r3 = n (where n = [0-31]) + * The maximum number of BHRB entries supported with PPC_MFBHRBE instruction + * is 1024. We have limited number of table entries here as POWER8 implements + * 32 BHRB entries. + */ + +/* .global read_bhrb */ +_GLOBAL(read_bhrb) + cmpldi r3,31 + bgt 1f + ld r4,bhrb_table@got(r2) + sldi r3,r3,3 + add r3,r4,r3 + mtctr r3 + bctr +1: li r3,0 + blr + +#define MFBHRB_TABLE1(n) PPC_MFBHRBE(R3,n); blr +#define MFBHRB_TABLE2(n) MFBHRB_TABLE1(n); MFBHRB_TABLE1(n+1) +#define MFBHRB_TABLE4(n) MFBHRB_TABLE2(n); MFBHRB_TABLE2(n+2) +#define MFBHRB_TABLE8(n) MFBHRB_TABLE4(n); MFBHRB_TABLE4(n+4) +#define MFBHRB_TABLE16(n) MFBHRB_TABLE8(n); MFBHRB_TABLE8(n+8) +#define MFBHRB_TABLE32(n) MFBHRB_TABLE16(n); MFBHRB_TABLE16(n+16) + +bhrb_table: + MFBHRB_TABLE32(0) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 65362e98eb26..c627843c5b2e 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -19,6 +19,11 @@ #include <asm/firmware.h> #include <asm/ptrace.h> +#define BHRB_MAX_ENTRIES 32 +#define BHRB_TARGET 0x0000000000000002 +#define BHRB_PREDICTION 0x0000000000000001 +#define BHRB_EA 0xFFFFFFFFFFFFFFFC + struct cpu_hw_events { int n_events; int n_percpu; @@ -38,7 +43,15 @@ struct cpu_hw_events { unsigned int group_flag; int n_txn_start; + + /* BHRB bits */ + u64 bhrb_filter; /* BHRB HW branch filter */ + int bhrb_users; + void *bhrb_context; + struct perf_branch_stack bhrb_stack; + struct perf_branch_entry bhrb_entries[BHRB_MAX_ENTRIES]; }; + DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); struct power_pmu *ppmu; @@ -89,6 +102,11 @@ static inline int siar_valid(struct pt_regs *regs) #endif /* CONFIG_PPC32 */ +static bool regs_use_siar(struct pt_regs *regs) +{ + return !!(regs->result & 1); +} + /* * Things that are specific to 64-bit implementations. */ @@ -98,11 +116,12 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { unsigned long mmcra = regs->dsisr; - if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + if ((ppmu->flags & PPMU_HAS_SSLOT) && (mmcra & MMCRA_SAMPLE_ENABLE)) { unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; if (slot > 1) return 4 * (slot - 1); } + return 0; } @@ -130,24 +149,35 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) *addrp = mfspr(SPRN_SDAR); } -static bool mmcra_sihv(unsigned long mmcra) +static bool regs_sihv(struct pt_regs *regs) { unsigned long sihv = MMCRA_SIHV; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIHV); + if (ppmu->flags & PPMU_ALT_SIPR) sihv = POWER6_MMCRA_SIHV; - return !!(mmcra & sihv); + return !!(regs->dsisr & sihv); } -static bool mmcra_sipr(unsigned long mmcra) +static bool regs_sipr(struct pt_regs *regs) { unsigned long sipr = MMCRA_SIPR; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIPR); + if (ppmu->flags & PPMU_ALT_SIPR) sipr = POWER6_MMCRA_SIPR; - return !!(mmcra & sipr); + return !!(regs->dsisr & sipr); +} + +static bool regs_no_sipr(struct pt_regs *regs) +{ + return !!(regs->result & 2); } static inline u32 perf_flags_from_msr(struct pt_regs *regs) @@ -161,8 +191,7 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs) static inline u32 perf_get_misc_flags(struct pt_regs *regs) { - unsigned long mmcra = regs->dsisr; - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (!use_siar) return perf_flags_from_msr(regs); @@ -173,7 +202,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) * SIAR which should give slightly more reliable * results */ - if (ppmu->flags & PPMU_NO_SIPR) { + if (regs_no_sipr(regs)) { unsigned long siar = mfspr(SPRN_SIAR); if (siar >= PAGE_OFFSET) return PERF_RECORD_MISC_KERNEL; @@ -181,16 +210,19 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) } /* PR has priority over HV, so order below is important */ - if (mmcra_sipr(mmcra)) + if (regs_sipr(regs)) return PERF_RECORD_MISC_USER; - if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV)) + + if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV)) return PERF_RECORD_MISC_HYPERVISOR; + return PERF_RECORD_MISC_KERNEL; } /* * Overload regs->dsisr to store MMCRA so we only need to read it once * on each interrupt. + * Overload regs->dar to store SIER if we have it. * Overload regs->result to specify whether we should use the MSR (result * is zero) or the SIAR (result is non zero). */ @@ -200,6 +232,24 @@ static inline void perf_read_regs(struct pt_regs *regs) int marked = mmcra & MMCRA_SAMPLE_ENABLE; int use_siar; + regs->dsisr = mmcra; + regs->result = 0; + + if (ppmu->flags & PPMU_NO_SIPR) + regs->result |= 2; + + /* + * On power8 if we're in random sampling mode, the SIER is updated. + * If we're in continuous sampling mode, we don't have SIPR. + */ + if (ppmu->flags & PPMU_HAS_SIER) { + if (marked) + regs->dar = mfspr(SPRN_SIER); + else + regs->result |= 2; + } + + /* * If this isn't a PMU exception (eg a software event) the SIAR is * not valid. Use pt_regs. @@ -223,13 +273,12 @@ static inline void perf_read_regs(struct pt_regs *regs) use_siar = 1; else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING)) use_siar = 0; - else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra)) + else if (!regs_no_sipr(regs) && regs_sipr(regs)) use_siar = 0; else use_siar = 1; - regs->dsisr = mmcra; - regs->result = use_siar; + regs->result |= use_siar; } /* @@ -822,6 +871,9 @@ static void power_pmu_enable(struct pmu *pmu) } out: + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + local_irq_restore(flags); } @@ -852,6 +904,47 @@ static int collect_events(struct perf_event *group, int max_count, return n; } +/* Reset all possible BHRB entries */ +static void power_pmu_bhrb_reset(void) +{ + asm volatile(PPC_CLRBHRB); +} + +void power_pmu_bhrb_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + /* Clear BHRB if we changed task context to avoid data leaks */ + if (event->ctx->task && cpuhw->bhrb_context != event->ctx) { + power_pmu_bhrb_reset(); + cpuhw->bhrb_context = event->ctx; + } + cpuhw->bhrb_users++; +} + +void power_pmu_bhrb_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + cpuhw->bhrb_users--; + WARN_ON_ONCE(cpuhw->bhrb_users < 0); + + if (!cpuhw->disabled && !cpuhw->bhrb_users) { + /* BHRB cannot be turned off when other + * events are active on the PMU. + */ + + /* avoid stale pointer */ + cpuhw->bhrb_context = NULL; + } +} + /* * Add a event to the PMU. * If all events are not already frozen, then we disable and @@ -911,6 +1004,9 @@ nocheck: ret = 0; out: + if (has_branch_stack(event)) + power_pmu_bhrb_enable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; @@ -963,6 +1059,9 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); } + if (has_branch_stack(event)) + power_pmu_bhrb_disable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1081,6 +1180,15 @@ int power_pmu_commit_txn(struct pmu *pmu) return 0; } +/* Called from ctxsw to prevent one process's branch entries to + * mingle with the other process's entries during context switch. + */ +void power_pmu_flush_branch_stack(void) +{ + if (ppmu->bhrb_nr) + power_pmu_bhrb_reset(); +} + /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. @@ -1195,9 +1303,11 @@ static int power_pmu_event_init(struct perf_event *event) if (!ppmu) return -ENOENT; - /* does not support taken branch sampling */ - if (has_branch_stack(event)) - return -EOPNOTSUPP; + if (has_branch_stack(event)) { + /* PMU has BHRB enabled */ + if (!(ppmu->flags & PPMU_BHRB)) + return -EOPNOTSUPP; + } switch (event->attr.type) { case PERF_TYPE_HARDWARE: @@ -1278,6 +1388,15 @@ static int power_pmu_event_init(struct perf_event *event) cpuhw = &get_cpu_var(cpu_hw_events); err = power_check_constraints(cpuhw, events, cflags, n + 1); + + if (has_branch_stack(event)) { + cpuhw->bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if(cpuhw->bhrb_filter == -1) + return -EOPNOTSUPP; + } + put_cpu_var(cpu_hw_events); if (err) return -EINVAL; @@ -1336,8 +1455,79 @@ struct pmu power_pmu = { .cancel_txn = power_pmu_cancel_txn, .commit_txn = power_pmu_commit_txn, .event_idx = power_pmu_event_idx, + .flush_branch_stack = power_pmu_flush_branch_stack, }; +/* Processing BHRB entries */ +void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +{ + u64 val; + u64 addr; + int r_index, u_index, target, pred; + + r_index = 0; + u_index = 0; + while (r_index < ppmu->bhrb_nr) { + /* Assembly read function */ + val = read_bhrb(r_index); + + /* Terminal marker: End of valid BHRB entries */ + if (val == 0) { + break; + } else { + /* BHRB field break up */ + addr = val & BHRB_EA; + pred = val & BHRB_PREDICTION; + target = val & BHRB_TARGET; + + /* Probable Missed entry: Not applicable for POWER8 */ + if ((addr == 0) && (target == 0) && (pred == 1)) { + r_index++; + continue; + } + + /* Real Missed entry: Power8 based missed entry */ + if ((addr == 0) && (target == 1) && (pred == 1)) { + r_index++; + continue; + } + + /* Reserved condition: Not a valid entry */ + if ((addr == 0) && (target == 1) && (pred == 0)) { + r_index++; + continue; + } + + /* Is a target address */ + if (val & BHRB_TARGET) { + /* First address cannot be a target address */ + if (r_index == 0) { + r_index++; + continue; + } + + /* Update target address for the previous entry */ + cpuhw->bhrb_entries[u_index - 1].to = addr; + cpuhw->bhrb_entries[u_index - 1].mispred = pred; + cpuhw->bhrb_entries[u_index - 1].predicted = ~pred; + + /* Dont increment u_index */ + r_index++; + } else { + /* Update address, flags for current entry */ + cpuhw->bhrb_entries[u_index].from = addr; + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + + /* Successfully popullated one entry */ + u_index++; + r_index++; + } + } + } + cpuhw->bhrb_stack.nr = u_index; + return; +} /* * A counter has overflowed; update its count and record @@ -1397,6 +1587,13 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); + if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { + struct cpu_hw_events *cpuhw; + cpuhw = &__get_cpu_var(cpu_hw_events); + power_pmu_bhrb_read(cpuhw); + data.br_stack = &cpuhw->bhrb_stack; + } + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } @@ -1422,7 +1619,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) */ unsigned long perf_instruction_pointer(struct pt_regs *regs) { - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (use_siar && siar_valid(regs)) return mfspr(SPRN_SIAR) + perf_ip_adjust(regs); diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index a8757baa28f3..b03b6dc0172d 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -671,7 +671,7 @@ static struct power_pmu power5p_pmu = { .get_alternatives = power5p_get_alternatives, .disable_pmc = power5p_disable_pmc, .limited_pmc_event = power5p_limited_pmc_event, - .flags = PPMU_LIMITED_PMC5_6, + .flags = PPMU_LIMITED_PMC5_6 | PPMU_HAS_SSLOT, .n_generic = ARRAY_SIZE(power5p_generic_events), .generic_events = power5p_generic_events, .cache_events = &power5p_cache_events, diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index e7f06eb7a861..1e8ce423c3af 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -615,6 +615,7 @@ static struct power_pmu power5_pmu = { .n_generic = ARRAY_SIZE(power5_generic_events), .generic_events = power5_generic_events, .cache_events = &power5_cache_events, + .flags = PPMU_HAS_SSLOT, }; static int __init init_power5_pmu(void) diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index b554879bd31e..3c475d6267c7 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -420,7 +420,20 @@ static struct attribute_group power7_pmu_events_group = { .attrs = power7_events_attr, }; +PMU_FORMAT_ATTR(event, "config:0-19"); + +static struct attribute *power7_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +struct attribute_group power7_pmu_format_group = { + .name = "format", + .attrs = power7_pmu_format_attr, +}; + static const struct attribute_group *power7_pmu_attr_groups[] = { + &power7_pmu_format_group, &power7_pmu_events_group, NULL, }; diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c new file mode 100644 index 000000000000..f7d1c4fff303 --- /dev/null +++ b/arch/powerpc/perf/power8-pmu.c @@ -0,0 +1,592 @@ +/* + * Performance counter support for POWER8 processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * Copyright 2013 Michael Ellerman, 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_event.h> +#include <asm/firmware.h> + + +/* + * Some power8 event codes. + */ +#define PM_CYC 0x0001e +#define PM_GCT_NOSLOT_CYC 0x100f8 +#define PM_CMPLU_STALL 0x4000a +#define PM_INST_CMPL 0x00002 +#define PM_BRU_FIN 0x10068 +#define PM_BR_MPRED_CMPL 0x400f6 + + +/* + * Raw event encoding for POWER8: + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ thresh_cmp ] [ thresh_ctl ] + * | + * thresh start/stop OR FAB match -* + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [cache] [ pmc ] [unit ] c m [ pmcxsel ] + * | | | | | + * | | | | *- mark + * | | *- L1/L2/L3 cache_sel | + * | | | + * | *- sampling mode for marked events *- combine + * | + * *- thresh_sel + * + * Below uses IBM bit numbering. + * + * MMCR1[x:y] = unit (PMCxUNIT) + * MMCR1[x] = combine (PMCxCOMB) + * + * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 + * # PM_MRK_FAB_RSP_MATCH + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 + * # PM_MRK_FAB_RSP_MATCH_CYC + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else + * MMCRA[48:55] = thresh_ctl (THRESH START/END) + * + * if thresh_sel: + * MMCRA[45:47] = thresh_sel + * + * if thresh_cmp: + * MMCRA[22:24] = thresh_cmp[0:2] + * MMCRA[25:31] = thresh_cmp[3:9] + * + * if unit == 6 or unit == 7 + * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) + * else if unit == 8 or unit == 9: + * if cache_sel[0] == 0: # L3 bank + * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) + * else if cache_sel[0] == 1: + * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) + * else if cache_sel[1]: # L1 event + * MMCR1[16] = cache_sel[2] +Â * MMCR1[17] = cache_sel[3] + * + * if mark: + * MMCRA[63] = 1 (SAMPLE_ENABLE) + * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) +Â * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) + * + */ + +#define EVENT_THR_CMP_SHIFT 40 /* Threshold CMP value */ +#define EVENT_THR_CMP_MASK 0x3ff +#define EVENT_THR_CTL_SHIFT 32 /* Threshold control value (start/stop) */ +#define EVENT_THR_CTL_MASK 0xffull +#define EVENT_THR_SEL_SHIFT 29 /* Threshold select value */ +#define EVENT_THR_SEL_MASK 0x7 +#define EVENT_THRESH_SHIFT 29 /* All threshold bits */ +#define EVENT_THRESH_MASK 0x1fffffull +#define EVENT_SAMPLE_SHIFT 24 /* Sampling mode & eligibility */ +#define EVENT_SAMPLE_MASK 0x1f +#define EVENT_CACHE_SEL_SHIFT 20 /* L2/L3 cache select */ +#define EVENT_CACHE_SEL_MASK 0xf +#define EVENT_IS_L1 (4 << EVENT_CACHE_SEL_SHIFT) +#define EVENT_PMC_SHIFT 16 /* PMC number (1-based) */ +#define EVENT_PMC_MASK 0xf +#define EVENT_UNIT_SHIFT 12 /* Unit */ +#define EVENT_UNIT_MASK 0xf +#define EVENT_COMBINE_SHIFT 11 /* Combine bit */ +#define EVENT_COMBINE_MASK 0x1 +#define EVENT_MARKED_SHIFT 8 /* Marked bit */ +#define EVENT_MARKED_MASK 0x1 +#define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) +#define EVENT_PSEL_MASK 0xff /* PMCxSEL value */ + +/* MMCRA IFM bits - POWER8 */ +#define POWER8_MMCRA_IFM1 0x0000000040000000UL +#define POWER8_MMCRA_IFM2 0x0000000080000000UL +#define POWER8_MMCRA_IFM3 0x00000000C0000000UL + +#define ONLY_PLM \ + (PERF_SAMPLE_BRANCH_USER |\ + PERF_SAMPLE_BRANCH_KERNEL |\ + PERF_SAMPLE_BRANCH_HV) + +/* + * Layout of constraint bits: + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ fab_match ] [ thresh_cmp ] [ thresh_ctl ] [ ] + * | + * thresh_sel -* + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1] + * | | + * L1 I/D qualifier -* | Count of events for each PMC. + * | p1, p2, p3, p4, p5, p6. + * nc - number of counters -* + * + * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints + * we want the low bit of each field to be added to any existing value. + * + * Everything else is a value field. + */ + +#define CNST_FAB_MATCH_VAL(v) (((v) & EVENT_THR_CTL_MASK) << 56) +#define CNST_FAB_MATCH_MASK CNST_FAB_MATCH_VAL(EVENT_THR_CTL_MASK) + +/* We just throw all the threshold bits into the constraint */ +#define CNST_THRESH_VAL(v) (((v) & EVENT_THRESH_MASK) << 32) +#define CNST_THRESH_MASK CNST_THRESH_VAL(EVENT_THRESH_MASK) + +#define CNST_L1_QUAL_VAL(v) (((v) & 3) << 22) +#define CNST_L1_QUAL_MASK CNST_L1_QUAL_VAL(3) + +#define CNST_SAMPLE_VAL(v) (((v) & EVENT_SAMPLE_MASK) << 16) +#define CNST_SAMPLE_MASK CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK) + +/* + * For NC we are counting up to 4 events. This requires three bits, and we need + * the fifth event to overflow and set the 4th bit. To achieve that we bias the + * fields by 3 in test_adder. + */ +#define CNST_NC_SHIFT 12 +#define CNST_NC_VAL (1 << CNST_NC_SHIFT) +#define CNST_NC_MASK (8 << CNST_NC_SHIFT) +#define POWER8_TEST_ADDER (3 << CNST_NC_SHIFT) + +/* + * For the per-PMC fields we have two bits. The low bit is added, so if two + * events ask for the same PMC the sum will overflow, setting the high bit, + * indicating an error. So our mask sets the high bit. + */ +#define CNST_PMC_SHIFT(pmc) ((pmc - 1) * 2) +#define CNST_PMC_VAL(pmc) (1 << CNST_PMC_SHIFT(pmc)) +#define CNST_PMC_MASK(pmc) (2 << CNST_PMC_SHIFT(pmc)) + +/* Our add_fields is defined as: */ +#define POWER8_ADD_FIELDS \ + CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \ + CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL + + +/* Bits in MMCR1 for POWER8 */ +#define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1))) +#define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) +#define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8) +#define MMCR1_DC_QUAL_SHIFT 47 +#define MMCR1_IC_QUAL_SHIFT 46 + +/* Bits in MMCRA for POWER8 */ +#define MMCRA_SAMP_MODE_SHIFT 1 +#define MMCRA_SAMP_ELIG_SHIFT 4 +#define MMCRA_THR_CTL_SHIFT 8 +#define MMCRA_THR_SEL_SHIFT 16 +#define MMCRA_THR_CMP_SHIFT 32 +#define MMCRA_SDAR_MODE_TLB (1ull << 42) + + +static inline bool event_is_fab_match(u64 event) +{ + /* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */ + event &= 0xff0fe; + + /* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */ + return (event == 0x30056 || event == 0x4f052); +} + +static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) +{ + unsigned int unit, pmc, cache; + unsigned long mask, value; + + mask = value = 0; + + pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; + cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK; + + if (pmc) { + if (pmc > 6) + return -1; + + mask |= CNST_PMC_MASK(pmc); + value |= CNST_PMC_VAL(pmc); + + if (pmc >= 5 && event != 0x500fa && event != 0x600f4) + return -1; + } + + if (pmc <= 4) { + /* + * Add to number of counters in use. Note this includes events with + * a PMC of 0 - they still need a PMC, it's just assigned later. + * Don't count events on PMC 5 & 6, there is only one valid event + * on each of those counters, and they are handled above. + */ + mask |= CNST_NC_MASK; + value |= CNST_NC_VAL; + } + + if (unit >= 6 && unit <= 9) { + /* + * L2/L3 events contain a cache selector field, which is + * supposed to be programmed into MMCRC. However MMCRC is only + * HV writable, and there is no API for guest kernels to modify + * it. The solution is for the hypervisor to initialise the + * field to zeroes, and for us to only ever allow events that + * have a cache selector of zero. + */ + if (cache) + return -1; + + } else if (event & EVENT_IS_L1) { + mask |= CNST_L1_QUAL_MASK; + value |= CNST_L1_QUAL_VAL(cache); + } + + if (event & EVENT_IS_MARKED) { + mask |= CNST_SAMPLE_MASK; + value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT); + } + + /* + * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC, + * the threshold control bits are used for the match value. + */ + if (event_is_fab_match(event)) { + mask |= CNST_FAB_MATCH_MASK; + value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT); + } else { + /* + * Check the mantissa upper two bits are not zero, unless the + * exponent is also zero. See the THRESH_CMP_MANTISSA doc. + */ + unsigned int cmp, exp; + + cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; + exp = cmp >> 7; + + if (exp && (cmp & 0x60) == 0) + return -1; + + mask |= CNST_THRESH_MASK; + value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT); + } + + *maskp = mask; + *valp = value; + + return 0; +} + +static int power8_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], unsigned long mmcr[]) +{ + unsigned long mmcra, mmcr1, unit, combine, psel, cache, val; + unsigned int pmc, pmc_inuse; + int i; + + pmc_inuse = 0; + + /* First pass to count resource use */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + if (pmc) + pmc_inuse |= 1 << pmc; + } + + /* In continous sampling mode, update SDAR on TLB miss */ + mmcra = MMCRA_SDAR_MODE_TLB; + mmcr1 = 0; + + /* Second pass: assign PMCs, set all MMCR1 fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + unit = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; + combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK; + psel = event[i] & EVENT_PSEL_MASK; + + if (!pmc) { + for (pmc = 1; pmc <= 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + + pmc_inuse |= 1 << pmc; + } + + if (pmc <= 4) { + mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc); + mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc); + mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc); + } + + if (event[i] & EVENT_IS_L1) { + cache = event[i] >> EVENT_CACHE_SEL_SHIFT; + mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT; + cache >>= 1; + mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT; + } + + if (event[i] & EVENT_IS_MARKED) { + mmcra |= MMCRA_SAMPLE_ENABLE; + + val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK; + if (val) { + mmcra |= (val & 3) << MMCRA_SAMP_MODE_SHIFT; + mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT; + } + } + + /* + * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC, + * the threshold bits are used for the match value. + */ + if (event_is_fab_match(event[i])) { + mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) & + EVENT_THR_CTL_MASK; + } else { + val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK; + mmcra |= val << MMCRA_THR_CTL_SHIFT; + val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK; + mmcra |= val << MMCRA_THR_SEL_SHIFT; + val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; + mmcra |= val << MMCRA_THR_CMP_SHIFT; + } + + hwc[i] = pmc - 1; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + + /* pmc_inuse is 1-based */ + if (pmc_inuse & 2) + mmcr[0] = MMCR0_PMC1CE; + + if (pmc_inuse & 0x7c) + mmcr[0] |= MMCR0_PMCjCE; + + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + + return 0; +} + +#define MAX_ALT 2 + +/* Table of alternatives, sorted by column 0 */ +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x10134, 0x301e2 }, /* PM_MRK_ST_CMPL */ + { 0x10138, 0x40138 }, /* PM_BR_MRK_2PATH */ + { 0x18082, 0x3e05e }, /* PM_L3_CO_MEPF */ + { 0x1d14e, 0x401e8 }, /* PM_MRK_DATA_FROM_L2MISS */ + { 0x1e054, 0x4000a }, /* PM_CMPLU_STALL */ + { 0x20036, 0x40036 }, /* PM_BR_2PATH */ + { 0x200f2, 0x300f2 }, /* PM_INST_DISP */ + { 0x200f4, 0x600f4 }, /* PM_RUN_CYC */ + { 0x2013c, 0x3012e }, /* PM_MRK_FILT_MATCH */ + { 0x3e054, 0x400f0 }, /* PM_LD_MISS_L1 */ + { 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 int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, num_alt = 0; + u64 alt_event; + + alt[num_alt++] = event; + + i = find_alternative(event); + if (i >= 0) { + /* Filter out the original event, it's already in alt[0] */ + for (j = 0; j < MAX_ALT; ++j) { + alt_event = event_alternatives[i][j]; + if (alt_event && alt_event != event) + alt[num_alt++] = alt_event; + } + } + + 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. + */ + j = num_alt; + for (i = 0; i < num_alt; ++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; + } + } + num_alt = j; + } + + return num_alt; +} + +static void power8_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1)); +} + +PMU_FORMAT_ATTR(event, "config:0-49"); +PMU_FORMAT_ATTR(pmcxsel, "config:0-7"); +PMU_FORMAT_ATTR(mark, "config:8"); +PMU_FORMAT_ATTR(combine, "config:11"); +PMU_FORMAT_ATTR(unit, "config:12-15"); +PMU_FORMAT_ATTR(pmc, "config:16-19"); +PMU_FORMAT_ATTR(cache_sel, "config:20-23"); +PMU_FORMAT_ATTR(sample_mode, "config:24-28"); +PMU_FORMAT_ATTR(thresh_sel, "config:29-31"); +PMU_FORMAT_ATTR(thresh_stop, "config:32-35"); +PMU_FORMAT_ATTR(thresh_start, "config:36-39"); +PMU_FORMAT_ATTR(thresh_cmp, "config:40-49"); + +static struct attribute *power8_pmu_format_attr[] = { + &format_attr_event.attr, + &format_attr_pmcxsel.attr, + &format_attr_mark.attr, + &format_attr_combine.attr, + &format_attr_unit.attr, + &format_attr_pmc.attr, + &format_attr_cache_sel.attr, + &format_attr_sample_mode.attr, + &format_attr_thresh_sel.attr, + &format_attr_thresh_stop.attr, + &format_attr_thresh_start.attr, + &format_attr_thresh_cmp.attr, + NULL, +}; + +struct attribute_group power8_pmu_format_group = { + .name = "format", + .attrs = power8_pmu_format_attr, +}; + +static const struct attribute_group *power8_pmu_attr_groups[] = { + &power8_pmu_format_group, + NULL, +}; + +static int power8_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_GCT_NOSLOT_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, + [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, +}; + +static u64 power8_bhrb_filter_map(u64 branch_sample_type) +{ + u64 pmu_bhrb_filter = 0; + u64 br_privilege = branch_sample_type & ONLY_PLM; + + /* BHRB and regular PMU events share the same prvillege state + * filter configuration. BHRB is always recorded along with a + * regular PMU event. So privilege state filter criteria for BHRB + * and the companion PMU events has to be the same. As a default + * "perf record" tool sets all privillege bits ON when no filter + * criteria is provided in the command line. So as along as all + * privillege bits are ON or they are OFF, we are good to go. + */ + if ((br_privilege != 7) && (br_privilege != 0)) + return -1; + + /* No branch filter requested */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + return pmu_bhrb_filter; + + /* Invalid branch filter options - HW does not support */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) { + pmu_bhrb_filter |= POWER8_MMCRA_IFM1; + return pmu_bhrb_filter; + } + + /* Every thing else is unsupported */ + return -1; +} + +static void power8_config_bhrb(u64 pmu_bhrb_filter) +{ + /* Enable BHRB filter in PMU */ + mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); +} + +static struct power_pmu power8_pmu = { + .name = "POWER8", + .n_counter = 6, + .max_alternatives = MAX_ALT + 1, + .add_fields = POWER8_ADD_FIELDS, + .test_adder = POWER8_TEST_ADDER, + .compute_mmcr = power8_compute_mmcr, + .config_bhrb = power8_config_bhrb, + .bhrb_filter_map = power8_bhrb_filter_map, + .get_constraint = power8_get_constraint, + .get_alternatives = power8_get_alternatives, + .disable_pmc = power8_disable_pmc, + .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB, + .n_generic = ARRAY_SIZE(power8_generic_events), + .generic_events = power8_generic_events, + .attr_groups = power8_pmu_attr_groups, + .bhrb_nr = 32, +}; + +static int __init init_power8_pmu(void) +{ + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8")) + return -ENODEV; + + return register_power_pmu(&power8_pmu); +} +early_initcall(init_power8_pmu); diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index a392d12dd21f..bd40bbb15e14 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -20,7 +20,6 @@ config HOTFOOT bool "Hotfoot" depends on 40x default n - select 405EP select PPC40x_SIMPLE select PCI help @@ -105,9 +104,6 @@ config 405GP select IBM405_ERR51 select IBM_EMAC_ZMII -config 405EP - bool - config 405EX bool select IBM_EMAC_EMAC4 @@ -119,9 +115,6 @@ config 405EZ select IBM_EMAC_MAL_CLR_ICINTSTAT select IBM_EMAC_MAL_COMMON_ERR -config 405GPR - bool - config XILINX_VIRTEX bool select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index c16999802ecf..eb4620355e7b 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -15,16 +15,16 @@ config MPC5121_ADS help This option enables support for the MPC5121E ADS board. -config MPC5121_GENERIC - bool "Generic support for simple MPC5121 based boards" +config MPC512x_GENERIC + bool "Generic support for simple MPC512x based boards" depends on PPC_MPC512x select DEFAULT_UIMAGE help - This option enables support for simple MPC5121 based boards + This option enables support for simple MPC512x based boards which do not need custom platform specific setup. Compatible boards include: Protonic LVT base boards (ZANMCU - and VICVT2). + and VICVT2), Freescale MPC5125 Tower system. config PDM360NG bool "ifm PDM360NG board" diff --git a/arch/powerpc/platforms/512x/Makefile b/arch/powerpc/platforms/512x/Makefile index 4efc1c4b6fb5..72fb9340e09f 100644 --- a/arch/powerpc/platforms/512x/Makefile +++ b/arch/powerpc/platforms/512x/Makefile @@ -3,5 +3,5 @@ # obj-y += clock.o mpc512x_shared.o obj-$(CONFIG_MPC5121_ADS) += mpc5121_ads.o mpc5121_ads_cpld.o -obj-$(CONFIG_MPC5121_GENERIC) += mpc5121_generic.o +obj-$(CONFIG_MPC512x_GENERIC) += mpc512x_generic.o obj-$(CONFIG_PDM360NG) += pdm360ng.o diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c index 52d57d281724..e504166e089a 100644 --- a/arch/powerpc/platforms/512x/clock.c +++ b/arch/powerpc/platforms/512x/clock.c @@ -29,6 +29,8 @@ #include <asm/mpc5121.h> #include <asm/clk_interface.h> +#include "mpc512x.h" + #undef CLK_DEBUG static int clocks_initialized; @@ -683,8 +685,13 @@ static void psc_clks_init(void) struct device_node *np; struct platform_device *ofdev; u32 reg; + const char *psc_compat; + + psc_compat = mpc512x_select_psc_compat(); + if (!psc_compat) + return; - for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { + for_each_compatible_node(np, NULL, psc_compat) { if (!of_property_read_u32(np, "reg", ®)) { int pscnum = (reg & 0xf00) >> 8; struct clk *clk = psc_dev_clk(pscnum); diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h index c32b399eb952..0a8e60023944 100644 --- a/arch/powerpc/platforms/512x/mpc512x.h +++ b/arch/powerpc/platforms/512x/mpc512x.h @@ -15,6 +15,7 @@ extern void __init mpc512x_init_IRQ(void); extern void __init mpc512x_init(void); extern int __init mpc5121_clk_init(void); void __init mpc512x_declare_of_platform_devices(void); +extern const char *mpc512x_select_psc_compat(void); extern void mpc512x_restart(char *cmd); #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) diff --git a/arch/powerpc/platforms/512x/mpc5121_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c index ca1ca6669990..5fb919b30924 100644 --- a/arch/powerpc/platforms/512x/mpc5121_generic.c +++ b/arch/powerpc/platforms/512x/mpc512x_generic.c @@ -4,7 +4,7 @@ * Author: John Rigby, <jrigby@freescale.com> * * Description: - * MPC5121 SoC setup + * MPC512x SoC setup * * This is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by @@ -28,20 +28,22 @@ */ static const char * const board[] __initconst = { "prt,prtlvt", + "fsl,mpc5125ads", + "ifm,ac14xx", NULL }; /* * Called very early, MMU is off, device-tree isn't unflattened */ -static int __init mpc5121_generic_probe(void) +static int __init mpc512x_generic_probe(void) { return of_flat_dt_match(of_get_flat_dt_root(), board); } -define_machine(mpc5121_generic) { - .name = "MPC5121 generic", - .probe = mpc5121_generic_probe, +define_machine(mpc512x_generic) { + .name = "MPC512x generic", + .probe = mpc512x_generic_probe, .init = mpc512x_init, .init_early = mpc512x_init_diu, .setup_arch = mpc512x_setup_diu, diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index d30235b7e3f7..7642cd7aad73 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -330,26 +330,34 @@ void __init mpc512x_init_IRQ(void) static struct of_device_id __initdata of_bus_ids[] = { { .compatible = "fsl,mpc5121-immr", }, { .compatible = "fsl,mpc5121-localbus", }, + { .compatible = "fsl,mpc5121-mbx", }, + { .compatible = "fsl,mpc5121-nfc", }, + { .compatible = "fsl,mpc5121-sram", }, + { .compatible = "fsl,mpc5121-pci", }, + { .compatible = "gpio-leds", }, {}, }; void __init mpc512x_declare_of_platform_devices(void) { - struct device_node *np; - if (of_platform_bus_probe(NULL, of_bus_ids, NULL)) printk(KERN_ERR __FILE__ ": " "Error while probing of_platform bus\n"); - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-nfc"); - if (np) { - of_platform_device_create(np, NULL, NULL); - of_node_put(np); - } } #define DEFAULT_FIFO_SIZE 16 +const char *mpc512x_select_psc_compat(void) +{ + if (of_machine_is_compatible("fsl,mpc5121")) + return "fsl,mpc5121-psc"; + + if (of_machine_is_compatible("fsl,mpc5125")) + return "fsl,mpc5125-psc"; + + return NULL; +} + static unsigned int __init get_fifo_size(struct device_node *np, char *prop_name) { @@ -375,9 +383,16 @@ void __init mpc512x_psc_fifo_init(void) void __iomem *psc; unsigned int tx_fifo_size; unsigned int rx_fifo_size; + const char *psc_compat; int fifobase = 0; /* current fifo address in 32 bit words */ - for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { + psc_compat = mpc512x_select_psc_compat(); + if (!psc_compat) { + pr_err("%s: no compatible devices found\n", __func__); + return; + } + + for_each_compatible_node(np, NULL, psc_compat) { tx_fifo_size = get_fifo_size(np, "fsl,tx-fifo-size"); rx_fifo_size = get_fifo_size(np, "fsl,rx-fifo-size"); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 6b29ab1316f7..34d224be93ba 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -6,7 +6,6 @@ source "arch/powerpc/platforms/chrp/Kconfig" source "arch/powerpc/platforms/512x/Kconfig" source "arch/powerpc/platforms/52xx/Kconfig" source "arch/powerpc/platforms/powermac/Kconfig" -source "arch/powerpc/platforms/prep/Kconfig" source "arch/powerpc/platforms/maple/Kconfig" source "arch/powerpc/platforms/pasemi/Kconfig" source "arch/powerpc/platforms/ps3/Kconfig" @@ -233,7 +232,7 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on 6xx && (PPC_PREP || PPC_PMAC) + depends on 6xx && PPC_PMAC help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 6dfdb658c9f8..54f3936001aa 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -124,9 +124,8 @@ config 6xx select PPC_HAVE_PMU_SUPPORT config POWER3 - bool depends on PPC64 && PPC_BOOK3S - default y if !POWER4_ONLY + def_bool y config POWER4 depends on PPC64 && PPC_BOOK3S @@ -145,8 +144,7 @@ config TUNE_CELL but somewhat slower on other machines. This option only changes the scheduling of instructions, not the selection of instructions itself, so the resulting kernel will keep running on all other - machines. When building a kernel that is supposed to run only - on Cell, you should also select the POWER4_ONLY option. + machines. # this is temp to handle compat with arch=ppc config 8xx diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 59c1a1694104..348a27b12512 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -382,7 +382,7 @@ static int __init cbe_init_pm_irq(void) unsigned int irq; int rc, node; - for_each_node(node) { + for_each_online_node(node) { irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); if (irq == NO_IRQ) { diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 68c57d38745a..0026a37e21fd 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -352,7 +352,7 @@ static unsigned long spufs_get_unmapped_area(struct file *file, /* Else, try to obtain a 64K pages slice */ return slice_get_unmapped_area(addr, len, flags, - MMU_PAGE_64K, 1, 0); + MMU_PAGE_64K, 1); } #endif /* CONFIG_SPU_FS_64K_LS */ diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 863184b182f4..35f77a42bedf 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -99,6 +99,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) if (!inode) goto out; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -749,6 +750,7 @@ static struct file_system_type spufs_type = { .mount = spufs_mount, .kill_sb = kill_litter_super, }; +MODULE_ALIAS_FS("spufs"); static int __init spufs_init(void) { diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 74fea5c21839..d3e840d643af 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -8,6 +8,11 @@ config PPC_POWERNV select PPC_PCI_CHOICE if EMBEDDED default y +config POWERNV_MSI + bool "Support PCI MSI on PowerNV platform" + depends on PCI_MSI + default y + config PPC_POWERNV_RTAS depends on PPC_POWERNV bool "Support for RTAS based PowerNV platforms such as BML" diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3bb07e5e43cd..6fabe92eafb6 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -107,3 +107,4 @@ OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); +OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 8e90e8906df3..8c6c9cf91c13 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -26,10 +26,12 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/xics.h> #include "powernv.h" #include "pci.h" @@ -87,6 +89,7 @@ static int pnv_ioda_alloc_pe(struct pnv_phb *phb) return IODA_INVALID_PE; } while(test_and_set_bit(pe, phb->ioda.pe_alloc)); + phb->ioda.pe_array[pe].phb = phb; phb->ioda.pe_array[pe].pe_number = pe; return pe; } @@ -431,22 +434,102 @@ static void pnv_pci_ioda_setup_PEs(void) } } -static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *dev) +static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - /* We delay DMA setup after we have assigned all PE# */ + struct pci_dn *pdn = pnv_ioda_get_pdn(pdev); + struct pnv_ioda_pe *pe; + + /* + * The function can be called while the PE# + * hasn't been assigned. Do nothing for the + * case. + */ + if (!pdn || pdn->pe_number == IODA_INVALID_PE) + return; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + set_iommu_table_base(&pdev->dev, &pe->tce32_table); } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) +static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) { - struct pci_dev *dev; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + unsigned long start, end, inc; + + start = __pa(startp); + end = __pa(endp); + + /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ + if (tbl->it_busno) { + start <<= 12; + end <<= 12; + inc = 128 << 12; + start |= tbl->it_busno; + end |= tbl->it_busno; + } else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { + /* p7ioc-style invalidation, 2 TCEs per write */ + start |= (1ull << 63); + end |= (1ull << 63); + inc = 16; + } else { + /* Default (older HW) */ + inc = 128; + } - list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); - if (dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate); + end |= inc - 1; /* round up end to be different than start */ + + mb(); /* Ensure above stores are visible */ + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; + } + + /* + * The iommu layer will do another mb() for us on build() + * and we don't care on free() + */ +} + +static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, + struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + unsigned long start, end, inc; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + + /* We'll invalidate DMA address in PE scope */ + start = 0x2ul << 60; + start |= (pe->pe_number & 0xFF); + end = start; + + /* Figure out the start, end and step */ + inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64)); + start |= (inc << 12); + inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64)); + end |= (inc << 12); + inc = (0x1ul << 12); + mb(); + + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; } } +void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + struct pnv_phb *phb = pe->phb; + + if (phb->type == PNV_PHB_IODA1) + pnv_pci_ioda1_tce_invalidate(tbl, startp, endp); + else + pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp); +} + static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe, unsigned int base, unsigned int segs) @@ -518,16 +601,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, */ tbl->it_busno = 0; tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE - | TCE_PCI_SWINV_PAIR; + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE | + TCE_PCI_SWINV_PAIR; } iommu_init_table(tbl, phb->hose->node); - if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); - else - pnv_ioda_setup_bus_dma(pe, pe->pbus); - return; fail: /* XXX Failure: Try to fallback to 64-bit only ? */ @@ -537,6 +615,76 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + struct page *tce_mem = NULL; + void *addr; + const __be64 *swinvp; + struct iommu_table *tbl; + unsigned int tce_table_size, end; + int64_t rc; + + /* We shouldn't already have a 32-bit DMA associated */ + if (WARN_ON(pe->tce32_seg >= 0)) + return; + + /* The PE will reserve all possible 32-bits space */ + pe->tce32_seg = 0; + end = (1 << ilog2(phb->ioda.m32_pci_base)); + tce_table_size = (end / 0x1000) * 8; + pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", + end); + + /* Allocate TCE table */ + tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL, + get_order(tce_table_size)); + if (!tce_mem) { + pe_err(pe, "Failed to allocate a 32-bit TCE memory\n"); + goto fail; + } + addr = page_address(tce_mem); + memset(addr, 0, tce_table_size); + + /* + * Map TCE table through TVT. The TVE index is the PE number + * shifted by 1 bit for 32-bits DMA space. + */ + rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + tce_table_size, 0x1000); + if (rc) { + pe_err(pe, "Failed to configure 32-bit TCE table," + " err %ld\n", rc); + goto fail; + } + + /* Setup linux iommu table */ + tbl = &pe->tce32_table; + pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0); + + /* OPAL variant of PHB3 invalidated TCEs */ + swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL); + if (swinvp) { + /* We need a couple more fields -- an address and a data + * to or. Since the bus is only printed out on table free + * errors, and on the first pass the data will be a relative + * bus number, print that out instead. + */ + tbl->it_busno = 0; + tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; + } + iommu_init_table(tbl, phb->hose->node); + + return; +fail: + if (pe->tce32_seg >= 0) + pe->tce32_seg = -1; + if (tce_mem) + __free_pages(tce_mem, get_order(tce_table_size)); +} + static void pnv_ioda_setup_dma(struct pnv_phb *phb) { struct pci_controller *hose = phb->hose; @@ -579,20 +727,49 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) if (segs > remaining) segs = remaining; } - pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", - pe->dma_weight, segs); - pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + + /* + * For IODA2 compliant PHB3, we needn't care about the weight. + * The all available 32-bits DMA space will be assigned to + * the specific PE. + */ + if (phb->type == PNV_PHB_IODA1) { + pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", + pe->dma_weight, segs); + pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + } else { + pe_info(pe, "Assign DMA32 space\n"); + segs = 0; + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + remaining -= segs; base += segs; } } #ifdef CONFIG_PCI_MSI +static void pnv_ioda2_msi_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct irq_chip *chip = irq_data_get_irq_chip(d); + struct pnv_phb *phb = container_of(chip, struct pnv_phb, + ioda.irq_chip); + int64_t rc; + + rc = opal_pci_msi_eoi(phb->opal_id, hw_irq); + WARN_ON_ONCE(rc); + + icp_native_eoi(d); +} + static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); + struct irq_data *idata; + struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; uint64_t addr64; uint32_t addr32, data; @@ -637,6 +814,23 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, } msg->data = data; + /* + * Change the IRQ chip for the MSI interrupts on PHB3. + * The corresponding IRQ chip should be populated for + * the first time. + */ + if (phb->type == PNV_PHB_IODA2) { + if (!phb->ioda.irq_chip_init) { + idata = irq_get_irq_data(virq); + ichip = irq_data_get_irq_chip(idata); + phb->ioda.irq_chip_init = 1; + phb->ioda.irq_chip = *ichip; + phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi; + } + + irq_set_chip(virq, &phb->ioda.irq_chip); + } + pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d)," " address=%x_%08x data=%x PE# %d\n", pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num, @@ -647,7 +841,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) { @@ -658,18 +852,17 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; } + phb->msi_setup = pnv_pci_ioda_msi_setup; phb->msi32_support = 1; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } @@ -852,18 +1045,19 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, return phb->ioda.pe_rmap[(bus->number << 8) | devfn]; } -void __init pnv_pci_init_ioda1_phb(struct device_node *np) +void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type) { struct pci_controller *hose; static int primary = 1; struct pnv_phb *phb; unsigned long size, m32map_off, iomap_off, pemap_off; const u64 *prop64; + const u32 *prop32; u64 phb_id; void *aux; long rc; - pr_info(" Initializing IODA OPAL PHB %s\n", np->full_name); + pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name); prop64 = of_get_property(np, "ibm,opal-phbid", NULL); if (!prop64) { @@ -890,37 +1084,34 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->last_busno = 0xff; hose->private_data = phb; phb->opal_id = phb_id; - phb->type = PNV_PHB_IODA1; + phb->type = ioda_type; /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) phb->model = PNV_PHB_MODEL_P7IOC; + else if (of_device_is_compatible(np, "ibm,p8-pciex")) + phb->model = PNV_PHB_MODEL_PHB3; else phb->model = PNV_PHB_MODEL_UNKNOWN; - /* We parse "ranges" now since we need to deduce the register base - * from the IO base - */ + /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(phb->hose, np, primary); primary = 0; - /* Magic formula from Milton */ + /* Get registers */ phb->regs = of_iomap(np, 0); if (phb->regs == NULL) pr_err(" Failed to map registers !\n"); - - /* XXX This is hack-a-thon. This needs to be changed so that: - * - we obtain stuff like PE# etc... from device-tree - * - we properly re-allocate M32 ourselves - * (the OFW one isn't very good) - */ - /* Initialize more IODA stuff */ - phb->ioda.total_pe = 128; + prop32 = of_get_property(np, "ibm,opal-num-pes", NULL); + if (!prop32) + phb->ioda.total_pe = 1; + else + phb->ioda.total_pe = *prop32; phb->ioda.m32_size = resource_size(&hose->mem_resources[0]); - /* OFW Has already off top 64k of M32 space (MSI space) */ + /* FW Has already off top 64k of M32 space (MSI space) */ phb->ioda.m32_size += 0x10000; phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe; @@ -930,7 +1121,10 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe; phb->ioda.io_pci_base = 0; /* XXX calculate this ? */ - /* Allocate aux data & arrays */ + /* Allocate aux data & arrays + * + * XXX TODO: Don't allocate io segmap on PHB3 + */ size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long)); m32map_off = size; size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]); @@ -960,7 +1154,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->mem_resources[2].start = 0; hose->mem_resources[2].end = 0; -#if 0 +#if 0 /* We should really do that ... */ rc = opal_pci_set_phb_mem_window(opal->phb_id, window_type, window_num, @@ -974,16 +1168,6 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) phb->ioda.m32_size, phb->ioda.m32_segsize, phb->ioda.io_size, phb->ioda.io_segsize); - if (phb->regs) { - pr_devel(" BUID = 0x%016llx\n", in_be64(phb->regs + 0x100)); - pr_devel(" PHB2_CR = 0x%016llx\n", in_be64(phb->regs + 0x160)); - pr_devel(" IO_BAR = 0x%016llx\n", in_be64(phb->regs + 0x170)); - pr_devel(" IO_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x178)); - pr_devel(" IO_SAR = 0x%016llx\n", in_be64(phb->regs + 0x180)); - pr_devel(" M32_BAR = 0x%016llx\n", in_be64(phb->regs + 0x190)); - pr_devel(" M32_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x198)); - pr_devel(" M32_SAR = 0x%016llx\n", in_be64(phb->regs + 0x1a0)); - } phb->hose->ops = &pnv_pci_ops; /* Setup RID -> PE mapping function */ @@ -1011,7 +1195,18 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET); if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); - opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); + + /* + * On IODA1 map everything to PE#0, on IODA2 we assume the IODA reset + * has cleared the RTT which has the same effect + */ + if (ioda_type == PNV_PHB_IODA1) + opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); +} + +void pnv_pci_init_ioda2_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2); } void __init pnv_pci_init_ioda_hub(struct device_node *np) @@ -1034,6 +1229,6 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np) for_each_child_of_node(np, phbn) { /* Look for IODA1 PHBs */ if (of_device_is_compatible(phbn, "ibm,ioda-phb")) - pnv_pci_init_ioda1_phb(phbn); + pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1); } } diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 7db8771a40f5..92b37a0186c9 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -41,8 +42,8 @@ #ifdef CONFIG_PCI_MSI static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { if (WARN_ON(!is_64)) return -ENXIO; @@ -55,7 +56,7 @@ static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) @@ -67,10 +68,8 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; @@ -78,7 +77,7 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) phb->msi_setup = pnv_pci_p5ioc2_msi_setup; phb->msi32_support = 0; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b8b8e0bd9897..55dfca844ddf 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -47,43 +48,7 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; - return (phb && phb->msi_map) ? 0 : -ENODEV; -} - -static unsigned int pnv_get_one_msi(struct pnv_phb *phb) -{ - unsigned long flags; - unsigned int id, rc; - - spin_lock_irqsave(&phb->lock, flags); - - id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); - if (id >= phb->msi_count && phb->msi_next) - id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); - if (id >= phb->msi_count) { - rc = 0; - goto out; - } - __set_bit(id, phb->msi_map); - rc = id + phb->msi_base; -out: - spin_unlock_irqrestore(&phb->lock, flags); - return rc; -} - -static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) -{ - unsigned long flags; - unsigned int id; - - if (WARN_ON(hwirq < phb->msi_base || - hwirq >= (phb->msi_base + phb->msi_count))) - return; - id = hwirq - phb->msi_base; - - spin_lock_irqsave(&phb->lock, flags); - __clear_bit(id, phb->msi_map); - spin_unlock_irqrestore(&phb->lock, flags); + return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; } static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) @@ -92,7 +57,8 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct pnv_phb *phb = hose->private_data; struct msi_desc *entry; struct msi_msg msg; - unsigned int hwirq, virq; + int hwirq; + unsigned int virq; int rc; if (WARN_ON(!phb)) @@ -104,25 +70,25 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) pci_name(pdev)); return -ENXIO; } - hwirq = pnv_get_one_msi(phb); - if (!hwirq) { + hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1); + if (hwirq < 0) { pr_warn("%s: Failed to find a free MSI\n", pci_name(pdev)); return -ENOSPC; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping(NULL, phb->msi_base + hwirq); if (virq == NO_IRQ) { pr_warn("%s: Failed to map MSI to linux irq\n", pci_name(pdev)); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return -ENOMEM; } - rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64, - &msg); + rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq, + virq, entry->msi_attrib.is_64, &msg); if (rc) { pr_warn("%s: Failed to setup MSI\n", pci_name(pdev)); irq_dispose_mapping(virq); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return rc; } irq_set_msi_desc(virq, entry); @@ -144,7 +110,8 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev) if (entry->irq == NO_IRQ) continue; irq_set_msi_desc(entry->irq, NULL); - pnv_put_msi(phb, virq_to_hw(entry->irq)); + msi_bitmap_free_hwirqs(&phb->msi_bmp, + virq_to_hw(entry->irq) - phb->msi_base, 1); irq_dispose_mapping(entry->irq); } } @@ -362,48 +329,6 @@ struct pci_ops pnv_pci_ops = { .write = pnv_pci_write_config, }; - -static void pnv_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp) -{ - u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; - unsigned long start, end, inc; - - start = __pa(startp); - end = __pa(endp); - - - /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ - if (tbl->it_busno) { - start <<= 12; - end <<= 12; - inc = 128 << 12; - start |= tbl->it_busno; - end |= tbl->it_busno; - } - /* p7ioc-style invalidation, 2 TCEs per write */ - else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { - start |= (1ull << 63); - end |= (1ull << 63); - inc = 16; - } - /* Default (older HW) */ - else - inc = 128; - - end |= inc - 1; /* round up end to be different than start */ - - mb(); /* Ensure above stores are visible */ - while (start <= end) { - __raw_writeq(start, invalidate); - start += inc; - } - /* The iommu layer will do another mb() for us on build() and - * we don't care on free() - */ -} - - static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) @@ -428,7 +353,7 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, * of flags if that becomes the case */ if (tbl->it_type & TCE_PCI_SWINV_CREATE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); return 0; } @@ -442,8 +367,8 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type & TCE_PCI_SWINV_FREE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + if (tbl->it_type & TCE_PCI_SWINV_CREATE) + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); } static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) @@ -525,7 +450,7 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } -/* Fixup wrong class code in p7ioc root complex */ +/* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; @@ -591,6 +516,10 @@ void __init pnv_pci_init(void) if (!found_ioda) for_each_compatible_node(np, NULL, "ibm,p5ioc2") pnv_pci_init_p5ioc2_hub(np); + + /* Look for ioda2 built-in PHB3's */ + for_each_compatible_node(np, NULL, "ibm,ioda2-phb") + pnv_pci_init_ioda2_phb(np); } /* Setup the linkage between OF nodes and PHBs */ diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 7cfb7c883deb..48dc4bb856a1 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -4,9 +4,9 @@ struct pci_dn; enum pnv_phb_type { - PNV_PHB_P5IOC2, - PNV_PHB_IODA1, - PNV_PHB_IODA2, + PNV_PHB_P5IOC2 = 0, + PNV_PHB_IODA1 = 1, + PNV_PHB_IODA2 = 2, }; /* Precise PHB model for error management */ @@ -14,6 +14,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_UNKNOWN, PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, + PNV_PHB_MODEL_PHB3, }; #define PNV_PCI_DIAG_BUF_SIZE 4096 @@ -22,8 +23,10 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ /* Data associated with a PE, including IOMMU tracking etc.. */ +struct pnv_phb; struct pnv_ioda_pe { unsigned long flags; + struct pnv_phb *phb; /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev @@ -73,15 +76,13 @@ struct pnv_phb { spinlock_t lock; #ifdef CONFIG_PCI_MSI - unsigned long *msi_map; unsigned int msi_base; - unsigned int msi_count; - unsigned int msi_next; unsigned int msi32_support; + struct msi_bitmap msi_bmp; #endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg); + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); @@ -109,6 +110,10 @@ struct pnv_phb { unsigned int *io_segmap; struct pnv_ioda_pe *pe_array; + /* IRQ chip */ + int irq_chip_init; + struct irq_chip irq_chip; + /* Sorted list of used PE's based * on the sequence of creation */ @@ -150,6 +155,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, u64 dma_offset); extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); - - +extern void pnv_pci_init_ioda2_phb(struct device_node *np); +extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig deleted file mode 100644 index 1547f66235d9..000000000000 --- a/arch/powerpc/platforms/prep/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ -config PPC_PREP - bool "PowerPC Reference Platform (PReP) based machines" - depends on 6xx && BROKEN - select HAVE_PCSPKR_PLATFORM - select MPIC - select PPC_I8259 - select PPC_INDIRECT_PCI - select PPC_UDBG_16550 - select PPC_NATIVE - default n - -config PREP_RESIDUAL - bool "Support for PReP Residual Data" - depends on PPC_PREP - help - Some PReP systems have residual data passed to the kernel by the - firmware. This allows detection of memory size, devices present and - other useful pieces of information. Sometimes this information is - not present or incorrect, in which case it could lead to the machine - behaving incorrectly. If this happens, either disable PREP_RESIDUAL - or pass the 'noresidual' option to the kernel. - - If you are running a PReP system, say Y here, otherwise say N. diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c index 40b5cb433005..cba1e6be68e5 100644 --- a/arch/powerpc/platforms/ps3/time.c +++ b/arch/powerpc/platforms/ps3/time.c @@ -89,10 +89,8 @@ static int __init ps3_rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_RET(pdev); } module_init(ps3_rtc_init); diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index aa3693f7fb27..8c80588abacc 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -28,18 +28,18 @@ #include "pseries.h" -typedef struct { +struct hypertas_fw_feature { unsigned long val; char * name; -} firmware_feature_t; +}; /* * The names in this table match names in rtas/ibm,hypertas-functions. If the * entry ends in a '*', only upto the '*' is matched. Otherwise the entire * string must match. */ -static __initdata firmware_feature_t -firmware_features_table[FIRMWARE_MAX_FEATURES] = { +static __initdata struct hypertas_fw_feature +hypertas_fw_features_table[] = { {FW_FEATURE_PFT, "hcall-pft"}, {FW_FEATURE_TCE, "hcall-tce"}, {FW_FEATURE_SPRG0, "hcall-sprg0"}, @@ -69,20 +69,18 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = { * device-tree/ibm,hypertas-functions. Ultimately this functionality may * be moved into prom.c prom_init(). */ -void __init fw_feature_init(const char *hypertas, unsigned long len) +void __init fw_hypertas_feature_init(const char *hypertas, unsigned long len) { const char *s; int i; - pr_debug(" -> fw_feature_init()\n"); + pr_debug(" -> fw_hypertas_feature_init()\n"); for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) { - for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) { - const char *name = firmware_features_table[i].name; + for (i = 0; i < ARRAY_SIZE(hypertas_fw_features_table); i++) { + const char *name = hypertas_fw_features_table[i].name; size_t size; - /* check value against table of strings */ - if (!name) - continue; + /* * If there is a '*' at the end of name, only check * upto there @@ -96,10 +94,40 @@ void __init fw_feature_init(const char *hypertas, unsigned long len) /* we have a match */ powerpc_firmware_features |= - firmware_features_table[i].val; + hypertas_fw_features_table[i].val; break; } } - pr_debug(" <- fw_feature_init()\n"); + pr_debug(" <- fw_hypertas_feature_init()\n"); +} + +struct vec5_fw_feature { + unsigned long val; + unsigned int feature; +}; + +static __initdata struct vec5_fw_feature +vec5_fw_features_table[] = { + {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY}, + {FW_FEATURE_PRRN, OV5_PRRN}, +}; + +void __init fw_vec5_feature_init(const char *vec5, unsigned long len) +{ + unsigned int index, feat; + int i; + + pr_debug(" -> fw_vec5_feature_init()\n"); + + for (i = 0; i < ARRAY_SIZE(vec5_fw_features_table); i++) { + index = OV5_INDX(vec5_fw_features_table[i].feature); + feat = OV5_FEAT(vec5_fw_features_table[i].feature); + + if (vec5[index] & feat) + powerpc_firmware_features |= + vec5_fw_features_table[i].val; + } + + pr_debug(" <- fw_vec5_feature_init()\n"); } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1b2a174e7c59..86ae364900d6 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -924,6 +924,13 @@ static void restore_default_window(struct pci_dev *dev, __restore_default_window(pci_dev_to_eeh_dev(dev), ddw_restore_token); } +struct failed_ddw_pdn { + struct device_node *pdn; + struct list_head list; +}; + +static LIST_HEAD(failed_ddw_pdn_list); + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -951,6 +958,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct dynamic_dma_window_prop *ddwprop; const void *dma_window = NULL; unsigned long liobn, offset, size; + struct failed_ddw_pdn *fpdn; mutex_lock(&direct_window_init_mutex); @@ -959,6 +967,18 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) goto out_unlock; /* + * If we already went through this for a previous function of + * the same device and failed, we don't want to muck with the + * DMA window again, as it will race with in-flight operations + * and can lead to EEHs. The above mutex protects access to the + * list. + */ + list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { + if (!strcmp(fpdn->pdn->full_name, pdn->full_name)) + goto out_unlock; + } + + /* * the ibm,ddw-applicable property holds the tokens for: * ibm,query-pe-dma-window * ibm,create-pe-dma-window @@ -1114,6 +1134,12 @@ out_restore_window: if (ddw_restore_token) restore_default_window(dev, ddw_restore_token); + fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); + if (!fpdn) + goto out_unlock; + fpdn->pdn = pdn; + list_add(&fpdn->list, &failed_ddw_pdn_list); + out_unlock: mutex_unlock(&direct_window_init_mutex); return dma_addr; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0da39fed355a..299731e9036b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 6573808cc5f3..3d01eee9ffb1 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -37,14 +37,16 @@ struct update_props_workarea { #define UPDATE_DT_NODE 0x02000000 #define ADD_DT_NODE 0x03000000 -static int mobility_rtas_call(int token, char *buf) +#define MIGRATION_SCOPE (1) + +static int mobility_rtas_call(int token, char *buf, s32 scope) { int rc; spin_lock(&rtas_data_buf_lock); memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE); - rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1); + rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, scope); memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE); spin_unlock(&rtas_data_buf_lock); @@ -123,7 +125,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle) +static int update_dt_node(u32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -132,6 +134,7 @@ static int update_dt_node(u32 phandle) char *prop_data; char *rtas_buf; int update_properties_token; + u32 vd; update_properties_token = rtas_token("ibm,update-properties"); if (update_properties_token == RTAS_UNKNOWN_SERVICE) @@ -151,19 +154,31 @@ static int update_dt_node(u32 phandle) upwa->phandle = phandle; do { - rc = mobility_rtas_call(update_properties_token, rtas_buf); + rc = mobility_rtas_call(update_properties_token, rtas_buf, + scope); if (rc < 0) break; prop_data = rtas_buf + sizeof(*upwa); - for (i = 0; i < upwa->nprops; i++) { + /* The first element of the buffer is the path of the node + * being updated in the form of a 8 byte string length + * followed by the string. Skip past this to get to the + * properties being updated. + */ + vd = *prop_data++; + prop_data += vd; + + /* The path we skipped over is counted as one of the elements + * returned so start counting at one. + */ + for (i = 1; i < upwa->nprops; i++) { char *prop_name; - u32 vd; - prop_name = prop_data + 1; + prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *prop_data++; + vd = *(u32 *)prop_data; + prop_data += sizeof(vd); switch (vd) { case 0x00000000: @@ -219,7 +234,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) return rc; } -static int pseries_devicetree_update(void) +int pseries_devicetree_update(s32 scope) { char *rtas_buf; u32 *data; @@ -235,7 +250,7 @@ static int pseries_devicetree_update(void) return -ENOMEM; do { - rc = mobility_rtas_call(update_nodes_token, rtas_buf); + rc = mobility_rtas_call(update_nodes_token, rtas_buf, scope); if (rc && rc != 1) break; @@ -256,7 +271,7 @@ static int pseries_devicetree_update(void) delete_dt_node(phandle); break; case UPDATE_DT_NODE: - update_dt_node(phandle); + update_dt_node(phandle, scope); break; case ADD_DT_NODE: drc_index = *data++; @@ -276,7 +291,7 @@ void post_mobility_fixup(void) int rc; int activate_fw_token; - rc = pseries_devicetree_update(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) { printk(KERN_ERR "Initial post-mobility device tree update " "failed: %d\n", rc); @@ -292,7 +307,7 @@ void post_mobility_fixup(void) rc = rtas_call(activate_fw_token, 0, 1, NULL); if (!rc) { - rc = pseries_devicetree_update(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) printk(KERN_ERR "Secondary post-mobility device tree " "update failed: %d\n", rc); diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index f368668d97b3..f35787b6a5e0 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -58,40 +58,39 @@ static inline long extended_cede_processor(unsigned long latency_hint) static inline long vpa_call(unsigned long flags, unsigned long cpu, unsigned long vpa) { - /* flags are in bits 16-18 (counting from most significant bit) */ - flags = flags << (63 - 18); + flags = flags << H_VPA_FUNC_SHIFT; return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa); } static inline long unregister_vpa(unsigned long cpu) { - return vpa_call(0x5, cpu, 0); + return vpa_call(H_VPA_DEREG_VPA, cpu, 0); } static inline long register_vpa(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x1, cpu, vpa); + return vpa_call(H_VPA_REG_VPA, cpu, vpa); } static inline long unregister_slb_shadow(unsigned long cpu) { - return vpa_call(0x7, cpu, 0); + return vpa_call(H_VPA_DEREG_SLB, cpu, 0); } static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x3, cpu, vpa); + return vpa_call(H_VPA_REG_SLB, cpu, vpa); } static inline long unregister_dtl(unsigned long cpu) { - return vpa_call(0x6, cpu, 0); + return vpa_call(H_VPA_DEREG_DTL, cpu, 0); } static inline long register_dtl(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x2, cpu, vpa); + return vpa_call(H_VPA_REG_DTL, cpu, vpa); } static inline long plpar_page_set_loaned(unsigned long vpa) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 9a3dda07566f..8af71e4cc17f 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -19,7 +19,10 @@ extern void request_event_sources_irqs(struct device_node *np, #include <linux/of.h> -extern void __init fw_feature_init(const char *hypertas, unsigned long len); +extern void __init fw_hypertas_feature_init(const char *hypertas, + unsigned long len); +extern void __init fw_vec5_feature_init(const char *hypertas, + unsigned long len); struct pt_regs; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8bcc9ca6682f..ac932a9eb440 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -628,25 +628,39 @@ static void __init pSeries_init_early(void) * Called very early, MMU is off, device-tree isn't unflattened */ -static int __init pSeries_probe_hypertas(unsigned long node, - const char *uname, int depth, - void *data) +static int __init pseries_probe_fw_features(unsigned long node, + const char *uname, int depth, + void *data) { - const char *hypertas; + const char *prop; unsigned long len; + static int hypertas_found; + static int vec5_found; - if (depth != 1 || - (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0)) + if (depth != 1) return 0; - hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len); - if (!hypertas) - return 1; + if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) { + prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions", + &len); + if (prop) { + powerpc_firmware_features |= FW_FEATURE_LPAR; + fw_hypertas_feature_init(prop, len); + } - powerpc_firmware_features |= FW_FEATURE_LPAR; - fw_feature_init(hypertas, len); + hypertas_found = 1; + } - return 1; + if (!strcmp(uname, "chosen")) { + prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5", + &len); + if (prop) + fw_vec5_feature_init(prop, len); + + vec5_found = 1; + } + + return hypertas_found && vec5_found; } static int __init pSeries_probe(void) @@ -669,7 +683,7 @@ static int __init pSeries_probe(void) pr_debug("pSeries detected, looking for LPAR capability...\n"); /* Now try to figure out if we are running on LPAR */ - of_scan_flat_dt(pSeries_probe_hypertas, NULL); + of_scan_flat_dt(pseries_probe_fw_features, NULL); if (firmware_has_feature(FW_FEATURE_LPAR)) hpte_init_lpar(); diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig index 79d2225b7608..422a175b10ee 100644 --- a/arch/powerpc/platforms/wsp/Kconfig +++ b/arch/powerpc/platforms/wsp/Kconfig @@ -9,7 +9,6 @@ config PPC_WSP select PCI select PPC_IO_WORKAROUNDS if PCI select PPC_INDIRECT_PIO if PCI - select PPC_WSP_COPRO default n menu "WSP platform selection" @@ -29,7 +28,3 @@ config PPC_CHROMA default y endmenu - -config PPC_A2_DD2 - bool "Support for DD2 based A2/WSP systems" - depends on PPC_A2 diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index a84fecf63c4d..ab4cb5476472 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -19,6 +19,7 @@ config PPC_MSI_BITMAP default y if MPIC default y if FSL_PCI default y if PPC4xx_MSI + default y if POWERNV_MSI source "arch/powerpc/sysdev/xics/Kconfig" diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c index 9afba924e94f..af79e1ea74b6 100644 --- a/arch/powerpc/sysdev/rtc_cmos_setup.c +++ b/arch/powerpc/sysdev/rtc_cmos_setup.c @@ -62,10 +62,7 @@ static int __init add_rtc(void) pd = platform_device_register_simple("rtc_cmos", -1, &res[0], num_res); - if (IS_ERR(pd)) - return PTR_ERR(pd); - - return 0; + return PTR_RET(pd); } fs_initcall(add_rtc); diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 48861d3fcd07..89db29d17c25 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -81,7 +81,7 @@ static void icp_native_set_cpu_priority(unsigned char cppr) iosync(); } -static void icp_native_eoi(struct irq_data *d) +void icp_native_eoi(struct irq_data *d) { unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); |