diff options
Diffstat (limited to 'arch/powerpc')
308 files changed, 13501 insertions, 3130 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 80821512e9cc..c33e3ad2c8fd 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -82,14 +82,10 @@ config GENERIC_HWEIGHT bool default y -config GENERIC_GPIO - bool - help - Generic GPIO API support - config PPC bool default y + select BINFMT_ELF select OF select OF_EARLY_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD @@ -113,7 +109,6 @@ config PPC select USE_GENERIC_SMP_HELPERS if SMP select HAVE_OPROFILE select HAVE_DEBUG_KMEMLEAK - select HAVE_SYSCALL_WRAPPERS if PPC64 select GENERIC_ATOMIC64 if PPC32 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_PERF_EVENTS @@ -427,11 +422,6 @@ 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 +636,14 @@ 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 @@ -685,7 +675,6 @@ config SBUS config FSL_SOC bool select HAVE_CAN_FLEXCAN if NET && CAN - select PPC_CLOCK config FSL_PCI bool @@ -744,7 +733,6 @@ 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 @@ -774,11 +762,6 @@ config PCI_8260 select PPC_INDIRECT_PCI default y -config 8260_PCI9 - bool "Enable workaround for MPC826x erratum PCI 9" - depends on PCI_8260 && !8272 - default y - source "drivers/pci/pcie/Kconfig" source "drivers/pci/Kconfig" @@ -968,7 +951,7 @@ 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/Kconfig.debug b/arch/powerpc/Kconfig.debug index 5416e28a7538..863d877e0b5f 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -262,8 +262,31 @@ config PPC_EARLY_DEBUG_OPAL_HVSI Select this to enable early debugging for the PowerNV platform using an "hvsi" console +config PPC_EARLY_DEBUG_MEMCONS + bool "In memory console" + help + Select this to enable early debugging using an in memory console. + This console provides input and output buffers stored within the + kernel BSS and should be safe to select on any system. A debugger + can then be used to read kernel output or send input to the console. endchoice +config PPC_MEMCONS_OUTPUT_SIZE + int "In memory console output buffer size" + depends on PPC_EARLY_DEBUG_MEMCONS + default 4096 + help + Selects the size of the output buffer (in bytes) of the in memory + console. + +config PPC_MEMCONS_INPUT_SIZE + int "In memory console input buffer size" + depends on PPC_EARLY_DEBUG_MEMCONS + default 128 + help + Selects the size of the input buffer (in bytes) of the in memory + console. + config PPC_EARLY_DEBUG_OPAL def_bool y depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI 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/b4420qds.dts b/arch/powerpc/boot/dts/b4420qds.dts new file mode 100644 index 000000000000..923156d03b30 --- /dev/null +++ b/arch/powerpc/boot/dts/b4420qds.dts @@ -0,0 +1,50 @@ +/* + * B4420DS Device Tree Source + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of + * this software, even if advised of the possibility of such damage. + */ + +/include/ "fsl/b4420si-pre.dtsi" +/include/ "b4qds.dts" + +/ { + model = "fsl,B4420QDS"; + compatible = "fsl,B4420QDS"; + + ifc: localbus@ffe124000 { + board-control@3,0 { + compatible = "fsl,b4420qds-fpga", "fsl,fpga-qixis"; + }; + }; + +}; + +/include/ "fsl/b4420si-post.dtsi" diff --git a/arch/powerpc/boot/dts/b4860qds.dts b/arch/powerpc/boot/dts/b4860qds.dts new file mode 100644 index 000000000000..78907f38bb77 --- /dev/null +++ b/arch/powerpc/boot/dts/b4860qds.dts @@ -0,0 +1,61 @@ +/* + * B4860DS Device Tree Source + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/b4860si-pre.dtsi" +/include/ "b4qds.dts" + +/ { + model = "fsl,B4860QDS"; + compatible = "fsl,B4860QDS"; + + ifc: localbus@ffe124000 { + board-control@3,0 { + compatible = "fsl,b4860qds-fpga", "fsl,fpga-qixis"; + }; + }; + + rio: rapidio@ffe0c0000 { + reg = <0xf 0xfe0c0000 0 0x11000>; + + port1 { + ranges = <0 0 0xc 0x20000000 0 0x10000000>; + }; + port2 { + ranges = <0 0 0xc 0x30000000 0 0x10000000>; + }; + }; + +}; + +/include/ "fsl/b4860si-post.dtsi" diff --git a/arch/powerpc/boot/dts/b4qds.dts b/arch/powerpc/boot/dts/b4qds.dts new file mode 100644 index 000000000000..e6d2f8f90544 --- /dev/null +++ b/arch/powerpc/boot/dts/b4qds.dts @@ -0,0 +1,169 @@ +/* + * B4420DS Device Tree Source + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of + * this software, even if advised of the possibility of such damage. + */ + +/ { + model = "fsl,B4QDS"; + compatible = "fsl,B4QDS"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + ifc: localbus@ffe124000 { + reg = <0xf 0xfe124000 0 0x2000>; + ranges = <0 0 0xf 0xe8000000 0x08000000 + 2 0 0xf 0xff800000 0x00010000 + 3 0 0xf 0xffdf0000 0x00008000>; + + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + + partition@0 { + /* This location must not be altered */ + /* 1MB for u-boot Bootloader Image */ + reg = <0x0 0x00100000>; + label = "NAND U-Boot Image"; + read-only; + }; + + partition@100000 { + /* 1MB for DTB Image */ + reg = <0x00100000 0x00100000>; + label = "NAND DTB Image"; + }; + + partition@200000 { + /* 10MB for Linux Kernel Image */ + reg = <0x00200000 0x00A00000>; + label = "NAND Linux Kernel Image"; + }; + + partition@c00000 { + /* 500MB for Root file System Image */ + reg = <0x00c00000 0x1F400000>; + label = "NAND RFS Image"; + }; + }; + + board-control@3,0 { + compatible = "fsl,b4qds-fpga", "fsl,fpga-qixis"; + reg = <3 0 0x300>; + }; + }; + + memory { + device_type = "memory"; + }; + + dcsr: dcsr@f00000000 { + ranges = <0x00000000 0xf 0x00000000 0x01052000>; + }; + + soc: soc@ffe000000 { + ranges = <0x00000000 0xf 0xfe000000 0x1000000>; + reg = <0xf 0xfe000000 0 0x00001000>; + spi@110000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "sst,sst25wf040"; + reg = <0>; + spi-max-frequency = <40000000>; /* input clock */ + }; + }; + + sdhc@114000 { + /*Disabled as there is no sdhc connector on B4420QDS board*/ + status = "disabled"; + }; + + i2c@118000 { + eeprom@50 { + compatible = "at24,24c64"; + reg = <0x50>; + }; + eeprom@51 { + compatible = "at24,24c256"; + reg = <0x51>; + }; + eeprom@53 { + compatible = "at24,24c256"; + reg = <0x53>; + }; + eeprom@57 { + compatible = "at24,24c256"; + reg = <0x57>; + }; + rtc@68 { + compatible = "dallas,ds3232"; + reg = <0x68>; + }; + }; + + usb@210000 { + dr_mode = "host"; + phy_type = "ulpi"; + }; + + }; + + pci0: pcie@ffe200000 { + reg = <0xf 0xfe200000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + +}; + +/include/ "fsl/b4si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi new file mode 100644 index 000000000000..5a6615d0ade2 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi @@ -0,0 +1,98 @@ +/* + * B4420 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of + * this software, even if advised of the possibility of such damage. + */ + +/include/ "b4si-post.dtsi" + +/* controller at 0x200000 */ +&pci0 { + compatible = "fsl,b4420-pcie", "fsl,qoriq-pcie-v2.4"; +}; + +&dcsr { + dcsr-epu@0 { + compatible = "fsl,b4420-dcsr-epu", "fsl,dcsr-epu"; + }; + dcsr-npc { + compatible = "fsl,b4420-dcsr-cnpc", "fsl,dcsr-cnpc"; + }; + dcsr-dpaa@9000 { + compatible = "fsl,b4420-dcsr-dpaa", "fsl,dcsr-dpaa"; + }; + dcsr-ocn@11000 { + compatible = "fsl,b4420-dcsr-ocn", "fsl,dcsr-ocn"; + }; + dcsr-nal@18000 { + compatible = "fsl,b4420-dcsr-nal", "fsl,dcsr-nal"; + }; + dcsr-rcpm@22000 { + compatible = "fsl,b4420-dcsr-rcpm", "fsl,dcsr-rcpm"; + }; + dcsr-snpc@30000 { + compatible = "fsl,b4420-dcsr-snpc", "fsl,dcsr-snpc"; + }; + dcsr-snpc@31000 { + compatible = "fsl,b4420-dcsr-snpc", "fsl,dcsr-snpc"; + }; + dcsr-cpu-sb-proxy@108000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu1>; + reg = <0x108000 0x1000 0x109000 0x1000>; + }; +}; + +&soc { + cpc: l3-cache-controller@10000 { + compatible = "fsl,b4420-l3-cache-controller", "cache"; + }; + + corenet-cf@18000 { + compatible = "fsl,b4420-corenet-cf"; + }; + + guts: global-utilities@e0000 { + compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0"; + }; + + clockgen: global-utilities@e1000 { + compatible = "fsl,b4420-clockgen", "fsl,qoriq-clockgen-2.0"; + }; + + rcpm: global-utilities@e2000 { + compatible = "fsl,b4420-rcpm", "fsl,qoriq-rcpm-2.0"; + }; + + L2: l2-cache-controller@c20000 { + compatible = "fsl,b4420-l2-cache-controller"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi new file mode 100644 index 000000000000..7b4426e0a5a5 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi @@ -0,0 +1,73 @@ +/* + * B4420 Silicon/SoC Device Tree Source (pre include) + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of + * this software, even if advised of the possibility of such damage. + */ + +/dts-v1/; + +/ { + compatible = "fsl,B4420"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + aliases { + ccsr = &soc; + dcsr = &dcsr; + + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + serial3 = &serial3; + pci0 = &pci0; + dma0 = &dma0; + dma1 = &dma1; + sdhc = &sdhc; + }; + + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: PowerPC,e6500@0 { + device_type = "cpu"; + reg = <0 1>; + next-level-cache = <&L2>; + }; + cpu1: PowerPC,e6500@2 { + device_type = "cpu"; + reg = <2 3>; + next-level-cache = <&L2>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi new file mode 100644 index 000000000000..e5cf6c81dd66 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi @@ -0,0 +1,142 @@ +/* + * B4860 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "b4si-post.dtsi" + +/* controller at 0x200000 */ +&pci0 { + compatible = "fsl,b4860-pcie", "fsl,qoriq-pcie-v2.4"; +}; + +&rio { + compatible = "fsl,srio"; + interrupts = <16 2 1 11>; + #address-cells = <2>; + #size-cells = <2>; + fsl,iommu-parent = <&pamu0>; + ranges; + + port1 { + #address-cells = <2>; + #size-cells = <2>; + cell-index = <1>; + fsl,liodn-reg = <&guts 0x510>; /* RIO1LIODNR */ + }; + + port2 { + #address-cells = <2>; + #size-cells = <2>; + cell-index = <2>; + fsl,liodn-reg = <&guts 0x514>; /* RIO2LIODNR */ + }; +}; + +&dcsr { + dcsr-epu@0 { + compatible = "fsl,b4860-dcsr-epu", "fsl,dcsr-epu"; + }; + dcsr-npc { + compatible = "fsl,b4860-dcsr-cnpc", "fsl,dcsr-cnpc"; + }; + dcsr-dpaa@9000 { + compatible = "fsl,b4860-dcsr-dpaa", "fsl,dcsr-dpaa"; + }; + dcsr-ocn@11000 { + compatible = "fsl,b4860-dcsr-ocn", "fsl,dcsr-ocn"; + }; + dcsr-ddr@13000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr2>; + reg = <0x13000 0x1000>; + }; + dcsr-nal@18000 { + compatible = "fsl,b4860-dcsr-nal", "fsl,dcsr-nal"; + }; + dcsr-rcpm@22000 { + compatible = "fsl,b4860-dcsr-rcpm", "fsl,dcsr-rcpm"; + }; + dcsr-snpc@30000 { + compatible = "fsl,b4860-dcsr-snpc", "fsl,dcsr-snpc"; + }; + dcsr-snpc@31000 { + compatible = "fsl,b4860-dcsr-snpc", "fsl,dcsr-snpc"; + }; + dcsr-cpu-sb-proxy@108000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu1>; + reg = <0x108000 0x1000 0x109000 0x1000>; + }; + dcsr-cpu-sb-proxy@110000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu2>; + reg = <0x110000 0x1000 0x111000 0x1000>; + }; + dcsr-cpu-sb-proxy@118000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu3>; + reg = <0x118000 0x1000 0x119000 0x1000>; + }; +}; + +&soc { + ddr2: memory-controller@9000 { + compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller"; + reg = <0x9000 0x1000>; + interrupts = <16 2 1 9>; + }; + + cpc: l3-cache-controller@10000 { + compatible = "fsl,b4860-l3-cache-controller", "cache"; + }; + + corenet-cf@18000 { + compatible = "fsl,b4860-corenet-cf"; + }; + + guts: global-utilities@e0000 { + compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0"; + }; + + clockgen: global-utilities@e1000 { + compatible = "fsl,b4860-clockgen", "fsl,qoriq-clockgen-2.0"; + }; + + rcpm: global-utilities@e2000 { + compatible = "fsl,b4860-rcpm", "fsl,qoriq-rcpm-2.0"; + }; + + L2: l2-cache-controller@c20000 { + compatible = "fsl,b4860-l2-cache-controller"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi new file mode 100644 index 000000000000..5263fa46a3fb --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi @@ -0,0 +1,83 @@ +/* + * B4860 Silicon/SoC Device Tree Source (pre include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/dts-v1/; + +/ { + compatible = "fsl,B4860"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + aliases { + ccsr = &soc; + dcsr = &dcsr; + + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + serial3 = &serial3; + pci0 = &pci0; + dma0 = &dma0; + dma1 = &dma1; + sdhc = &sdhc; + }; + + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: PowerPC,e6500@0 { + device_type = "cpu"; + reg = <0 1>; + next-level-cache = <&L2>; + }; + cpu1: PowerPC,e6500@2 { + device_type = "cpu"; + reg = <2 3>; + next-level-cache = <&L2>; + }; + cpu2: PowerPC,e6500@4 { + device_type = "cpu"; + reg = <4 5>; + next-level-cache = <&L2>; + }; + cpu3: PowerPC,e6500@6 { + device_type = "cpu"; + reg = <6 7>; + next-level-cache = <&L2>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi new file mode 100644 index 000000000000..73991547c69b --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -0,0 +1,268 @@ +/* + * B4420 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * This software is provided by Freescale Semiconductor "as is" and any + * express or implied warranties, including, but not limited to, the implied + * warranties of merchantability and fitness for a particular purpose are + * disclaimed. In no event shall Freescale Semiconductor be liable for any + * direct, indirect, incidental, special, exemplary, or consequential damages + * (including, but not limited to, procurement of substitute goods or services; + * loss of use, data, or profits; or business interruption) however caused and + * on any theory of liability, whether in contract, strict liability, or tort + * (including negligence or otherwise) arising in any way out of the use of + * this software, even if advised of the possibility of such damage. + */ + +&ifc { + #address-cells = <2>; + #size-cells = <1>; + compatible = "fsl,ifc", "simple-bus"; + interrupts = <25 2 0 0>; +}; + +/* controller at 0x200000 */ +&pci0 { + compatible = "fsl,b4-pcie", "fsl,qoriq-pcie-v2.4"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <20 2 0 0>; + fsl,iommu-parent = <&pamu0>; + pcie@0 { + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + reg = <0 0 0 0 0>; + interrupts = <20 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 40 1 0 0 + 0000 0 0 2 &mpic 1 1 0 0 + 0000 0 0 3 &mpic 2 1 0 0 + 0000 0 0 4 &mpic 3 1 0 0 + >; + }; +}; + +&dcsr { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,dcsr", "simple-bus"; + + dcsr-epu@0 { + compatible = "fsl,b4-dcsr-epu", "fsl,dcsr-epu"; + interrupts = <52 2 0 0 + 84 2 0 0 + 85 2 0 0 + 94 2 0 0 + 95 2 0 0>; + reg = <0x0 0x1000>; + }; + dcsr-npc { + compatible = "fsl,b4-dcsr-cnpc", "fsl,dcsr-cnpc"; + reg = <0x1000 0x1000 0x1002000 0x10000>; + }; + dcsr-nxc@2000 { + compatible = "fsl,dcsr-nxc"; + reg = <0x2000 0x1000>; + }; + dcsr-corenet { + compatible = "fsl,dcsr-corenet"; + reg = <0x8000 0x1000 0x1A000 0x1000>; + }; + dcsr-dpaa@9000 { + compatible = "fsl,b4-dcsr-dpaa", "fsl,dcsr-dpaa"; + reg = <0x9000 0x1000>; + }; + dcsr-ocn@11000 { + compatible = "fsl,b4-dcsr-ocn", "fsl,dcsr-ocn"; + reg = <0x11000 0x1000>; + }; + dcsr-ddr@12000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr1>; + reg = <0x12000 0x1000>; + }; + dcsr-nal@18000 { + compatible = "fsl,b4-dcsr-nal", "fsl,dcsr-nal"; + reg = <0x18000 0x1000>; + }; + dcsr-rcpm@22000 { + compatible = "fsl,b4-dcsr-rcpm", "fsl,dcsr-rcpm"; + reg = <0x22000 0x1000>; + }; + dcsr-snpc@30000 { + compatible = "fsl,b4-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x30000 0x1000 0x1022000 0x10000>; + }; + dcsr-snpc@31000 { + compatible = "fsl,b4-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x31000 0x1000 0x1042000 0x10000>; + }; + dcsr-cpu-sb-proxy@100000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu0>; + reg = <0x100000 0x1000 0x101000 0x1000>; + }; +}; + +&soc { + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + compatible = "simple-bus"; + + soc-sram-error { + compatible = "fsl,soc-sram-error"; + interrupts = <16 2 1 2>; + }; + + corenet-law@0 { + compatible = "fsl,corenet-law"; + reg = <0x0 0x1000>; + fsl,num-laws = <32>; + }; + + ddr1: memory-controller@8000 { + compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller"; + reg = <0x8000 0x1000>; + interrupts = <16 2 1 8>; + }; + + cpc: l3-cache-controller@10000 { + compatible = "fsl,b4-l3-cache-controller", "cache"; + reg = <0x10000 0x1000>; + interrupts = <16 2 1 4>; + }; + + corenet-cf@18000 { + compatible = "fsl,b4-corenet-cf"; + reg = <0x18000 0x1000>; + interrupts = <16 2 1 0>; + fsl,ccf-num-csdids = <32>; + fsl,ccf-num-snoopids = <32>; + }; + + iommu@20000 { + compatible = "fsl,pamu-v1.0", "fsl,pamu"; + reg = <0x20000 0x4000>; + #address-cells = <1>; + #size-cells = <1>; + interrupts = < + 24 2 0 0 + 16 2 1 1>; + + + /* PCIe, DMA, SRIO */ + pamu0: pamu@0 { + reg = <0 0x1000>; + fsl,primary-cache-geometry = <8 1>; + fsl,secondary-cache-geometry = <32 2>; + }; + + /* AXI2, Maple */ + pamu1: pamu@1000 { + reg = <0x1000 0x1000>; + fsl,primary-cache-geometry = <32 1>; + fsl,secondary-cache-geometry = <32 2>; + }; + + /* Q/BMan */ + pamu2: pamu@2000 { + reg = <0x2000 0x1000>; + fsl,primary-cache-geometry = <32 1>; + fsl,secondary-cache-geometry = <32 2>; + }; + + /* AXI1, FMAN */ + pamu3: pamu@3000 { + reg = <0x3000 0x1000>; + fsl,primary-cache-geometry = <32 1>; + fsl,secondary-cache-geometry = <32 2>; + }; + }; + +/include/ "qoriq-mpic.dtsi" + + guts: global-utilities@e0000 { + compatible = "fsl,b4-device-config"; + reg = <0xe0000 0xe00>; + fsl,has-rstcr; + fsl,liodn-bits = <12>; + }; + + clockgen: global-utilities@e1000 { + compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0"; + reg = <0xe1000 0x1000>; + }; + + rcpm: global-utilities@e2000 { + compatible = "fsl,b4-rcpm", "fsl,qoriq-rcpm-2.0"; + reg = <0xe2000 0x1000>; + }; + +/include/ "qoriq-dma-0.dtsi" + dma@100300 { + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x580>; /* DMA1LIODNR */ + }; + +/include/ "qoriq-dma-1.dtsi" + dma@101300 { + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x584>; /* DMA2LIODNR */ + }; + +/include/ "qonverge-usb2-dr-0.dtsi" + usb0: usb@210000 { + compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr"; + fsl,iommu-parent = <&pamu1>; + fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */ + }; + +/include/ "qoriq-espi-0.dtsi" + spi@110000 { + fsl,espi-num-chipselects = <4>; + }; + +/include/ "qoriq-esdhc-0.dtsi" + sdhc@114000 { + sdhci,auto-cmd12; + fsl,iommu-parent = <&pamu1>; + fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */ + }; + +/include/ "qoriq-i2c-0.dtsi" +/include/ "qoriq-i2c-1.dtsi" +/include/ "qoriq-duart-0.dtsi" +/include/ "qoriq-duart-1.dtsi" +/include/ "qoriq-sec5.3-0.dtsi" + + L2: l2-cache-controller@c20000 { + compatible = "fsl,b4-l2-cache-controller"; + reg = <0xc20000 0x1000>; + next-level-cache = <&cpc>; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/e500mc_power_isa.dtsi b/arch/powerpc/boot/dts/fsl/e500mc_power_isa.dtsi index 870c6535a053..ea145c91cfbd 100644 --- a/arch/powerpc/boot/dts/fsl/e500mc_power_isa.dtsi +++ b/arch/powerpc/boot/dts/fsl/e500mc_power_isa.dtsi @@ -53,6 +53,7 @@ power-isa-mmc; // Memory Coherence power-isa-scpm; // Store Conditional Page Mobility power-isa-wt; // Wait + fsl,eref-deo; // Data Cache Extended Operations mmu-type = "power-embedded"; }; }; diff --git a/arch/powerpc/boot/dts/fsl/e5500_power_isa.dtsi b/arch/powerpc/boot/dts/fsl/e5500_power_isa.dtsi index 3230212f7ad5..c254c981ae87 100644 --- a/arch/powerpc/boot/dts/fsl/e5500_power_isa.dtsi +++ b/arch/powerpc/boot/dts/fsl/e5500_power_isa.dtsi @@ -54,6 +54,7 @@ power-isa-scpm; // Store Conditional Page Mobility power-isa-wt; // Wait power-isa-64; // 64-bit + fsl,eref-deo; // Data Cache Extended Operations mmu-type = "power-embedded"; }; }; diff --git a/arch/powerpc/boot/dts/fsl/e6500_power_isa.dtsi b/arch/powerpc/boot/dts/fsl/e6500_power_isa.dtsi new file mode 100644 index 000000000000..a912dbeff359 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/e6500_power_isa.dtsi @@ -0,0 +1,65 @@ +/* + * e6500 Power ISA Device Tree Source (include) + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/ { + cpus { + power-isa-version = "2.06"; + power-isa-b; // Base + power-isa-e; // Embedded + power-isa-atb; // Alternate Time Base + power-isa-cs; // Cache Specification + power-isa-ds; // Decorated Storage + power-isa-e.ed; // Embedded.Enhanced Debug + power-isa-e.pd; // Embedded.External PID + power-isa-e.hv; // Embedded.Hypervisor + power-isa-e.le; // Embedded.Little-Endian + power-isa-e.pm; // Embedded.Performance Monitor + power-isa-e.pc; // Embedded.Processor Control + power-isa-ecl; // Embedded Cache Locking + power-isa-exp; // External Proxy + power-isa-fp; // Floating Point + power-isa-fp.r; // Floating Point.Record + power-isa-mmc; // Memory Coherence + power-isa-scpm; // Store Conditional Page Mobility + power-isa-wt; // Wait + power-isa-64; // 64-bit + power-isa-e.pt; // Embedded.Page Table + power-isa-e.hv.lrat; // Embedded.Hypervisor.LRAT + power-isa-e.em; // Embedded Multi-Threading + power-isa-v; // Vector (AltiVec) + fsl,eref-er; // Enhanced Reservations (Load and Reserve and Store Cond.) + fsl,eref-deo; // Data Cache Extended Operations + mmu-type = "power-embedded"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi index 941fa159cefb..f1105bffa915 100644 --- a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi @@ -148,6 +148,7 @@ crypto: crypto@300000 { compatible = "fsl,sec-v4.2", "fsl,sec-v4.0"; + fsl,sec-era = <3>; #address-cells = <1>; #size-cells = <1>; reg = <0x30000 0x10000>; diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi index 69ac1acd4349..dc6cc5afd189 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -155,7 +155,7 @@ compatible = "fsl,dcsr", "simple-bus"; dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; + compatible = "fsl,p2041-dcsr-epu", "fsl,dcsr-epu"; interrupts = <52 2 0 0 84 2 0 0 85 2 0 0>; diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi index 9b5a81a4529c..3fa1e22d544a 100644 --- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi @@ -182,7 +182,7 @@ compatible = "fsl,dcsr", "simple-bus"; dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; + compatible = "fsl,p3041-dcsr-epu", "fsl,dcsr-epu"; interrupts = <52 2 0 0 84 2 0 0 85 2 0 0>; diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi index 19859ad851eb..34769a7eafea 100644 --- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi @@ -156,7 +156,7 @@ compatible = "fsl,dcsr", "simple-bus"; dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; + compatible = "fsl,p4080-dcsr-epu", "fsl,dcsr-epu"; interrupts = <52 2 0 0 84 2 0 0 85 2 0 0>; diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi index 9ea77c3513f6..bc3ae5a2252f 100644 --- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi @@ -184,7 +184,7 @@ compatible = "fsl,dcsr", "simple-bus"; dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; + compatible = "fsl,p5020-dcsr-epu", "fsl,dcsr-epu"; interrupts = <52 2 0 0 84 2 0 0 85 2 0 0>; diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi index 97f8c26f9709..a91897f6af09 100644 --- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi @@ -129,7 +129,7 @@ compatible = "fsl,dcsr", "simple-bus"; dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; + compatible = "fsl,p5040-dcsr-epu", "fsl,dcsr-epu"; interrupts = <52 2 0 0 84 2 0 0 85 2 0 0>; diff --git a/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi index ffadcb563ada..bb3d8266b5ce 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi @@ -34,6 +34,7 @@ crypto@30000 { compatible = "fsl,sec-v4.4", "fsl,sec-v4.0"; + fsl,sec-era = <3>; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x30000 0x10000>; diff --git a/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi b/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi new file mode 100644 index 000000000000..29dad723091e --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ Qonverge USB Host device tree stub [ controller @ offset 0x210000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +usb@210000 { + compatible = "fsl-usb2-dr"; + reg = <0x210000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <44 0x2 0 0>; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-gpio-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-gpio-1.dtsi new file mode 100644 index 000000000000..c2f9cdadb604 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-gpio-1.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ GPIO device tree stub [ controller @ offset 0x131000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +gpio1: gpio@131000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x131000 0x1000>; + interrupts = <54 2 0 0>; + #gpio-cells = <2>; + gpio-controller; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-gpio-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-gpio-2.dtsi new file mode 100644 index 000000000000..33f3ccbac83f --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-gpio-2.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ GPIO device tree stub [ controller @ offset 0x132000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +gpio2: gpio@132000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x132000 0x1000>; + interrupts = <86 2 0 0>; + #gpio-cells = <2>; + gpio-controller; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-gpio-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-gpio-3.dtsi new file mode 100644 index 000000000000..86954e95ea02 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-gpio-3.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ GPIO device tree stub [ controller @ offset 0x133000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +gpio3: gpio@133000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x133000 0x1000>; + interrupts = <87 2 0 0>; + #gpio-cells = <2>; + gpio-controller; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec4.0-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec4.0-0.dtsi index 0cbbac329539..02bee5fcbb9a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-sec4.0-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-sec4.0-0.dtsi @@ -34,6 +34,7 @@ crypto: crypto@300000 { compatible = "fsl,sec-v4.0"; + fsl,sec-era = <1>; #address-cells = <1>; #size-cells = <1>; reg = <0x300000 0x10000>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec4.2-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec4.2-0.dtsi index 7990e0d3d6f2..7f7574e53323 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-sec4.2-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-sec4.2-0.dtsi @@ -34,6 +34,7 @@ crypto: crypto@300000 { compatible = "fsl,sec-v4.2", "fsl,sec-v4.0"; + fsl,sec-era = <3>; #address-cells = <1>; #size-cells = <1>; reg = <0x300000 0x10000>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec4.1-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec5.0-0.dtsi index 3308986bba0d..e298efbb0f3e 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-sec4.1-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-sec5.0-0.dtsi @@ -1,7 +1,7 @@ /* - * QorIQ Sec/Crypto 4.1 device tree stub [ controller @ offset 0x300000 ] + * QorIQ Sec/Crypto 5.0 device tree stub [ controller @ offset 0x300000 ] * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -33,7 +33,8 @@ */ crypto: crypto@300000 { - compatible = "fsl,sec-v4.1", "fsl,sec-v4.0"; + compatible = "fsl,sec-v5.0", "fsl,sec-v4.0"; + fsl,sec-era = <5>; #address-cells = <1>; #size-cells = <1>; reg = <0x300000 0x10000>; @@ -41,35 +42,35 @@ crypto: crypto@300000 { interrupts = <92 2 0 0>; sec_jr0: jr@1000 { - compatible = "fsl,sec-v4.1-job-ring", + compatible = "fsl,sec-v5.0-job-ring", "fsl,sec-v4.0-job-ring"; reg = <0x1000 0x1000>; interrupts = <88 2 0 0>; }; sec_jr1: jr@2000 { - compatible = "fsl,sec-v4.1-job-ring", + compatible = "fsl,sec-v5.0-job-ring", "fsl,sec-v4.0-job-ring"; reg = <0x2000 0x1000>; interrupts = <89 2 0 0>; }; sec_jr2: jr@3000 { - compatible = "fsl,sec-v4.1-job-ring", + compatible = "fsl,sec-v5.0-job-ring", "fsl,sec-v4.0-job-ring"; reg = <0x3000 0x1000>; interrupts = <90 2 0 0>; }; sec_jr3: jr@4000 { - compatible = "fsl,sec-v4.1-job-ring", + compatible = "fsl,sec-v5.0-job-ring", "fsl,sec-v4.0-job-ring"; reg = <0x4000 0x1000>; interrupts = <91 2 0 0>; }; rtic@6000 { - compatible = "fsl,sec-v4.1-rtic", + compatible = "fsl,sec-v5.0-rtic", "fsl,sec-v4.0-rtic"; #address-cells = <1>; #size-cells = <1>; @@ -77,25 +78,25 @@ crypto: crypto@300000 { ranges = <0x0 0x6100 0xe00>; rtic_a: rtic-a@0 { - compatible = "fsl,sec-v4.1-rtic-memory", + compatible = "fsl,sec-v5.0-rtic-memory", "fsl,sec-v4.0-rtic-memory"; reg = <0x00 0x20 0x100 0x80>; }; rtic_b: rtic-b@20 { - compatible = "fsl,sec-v4.1-rtic-memory", + compatible = "fsl,sec-v5.0-rtic-memory", "fsl,sec-v4.0-rtic-memory"; reg = <0x20 0x20 0x200 0x80>; }; rtic_c: rtic-c@40 { - compatible = "fsl,sec-v4.1-rtic-memory", + compatible = "fsl,sec-v5.0-rtic-memory", "fsl,sec-v4.0-rtic-memory"; reg = <0x40 0x20 0x300 0x80>; }; rtic_d: rtic-d@60 { - compatible = "fsl,sec-v4.1-rtic-memory", + compatible = "fsl,sec-v5.0-rtic-memory", "fsl,sec-v4.0-rtic-memory"; reg = <0x60 0x20 0x500 0x80>; }; @@ -103,7 +104,7 @@ crypto: crypto@300000 { }; sec_mon: sec_mon@314000 { - compatible = "fsl,sec-v4.1-mon", "fsl,sec-v4.0-mon"; + compatible = "fsl,sec-v5.0-mon", "fsl,sec-v4.0-mon"; reg = <0x314000 0x1000>; interrupts = <93 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec5.2-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec5.2-0.dtsi index 7b2ab8a8c1f4..33ff09d52e05 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-sec5.2-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-sec5.2-0.dtsi @@ -34,6 +34,7 @@ crypto: crypto@300000 { compatible = "fsl,sec-v5.2", "fsl,sec-v5.0", "fsl,sec-v4.0"; + fsl,sec-era = <5>; #address-cells = <1>; #size-cells = <1>; reg = <0x300000 0x10000>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec5.3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec5.3-0.dtsi new file mode 100644 index 000000000000..08778221c194 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-sec5.3-0.dtsi @@ -0,0 +1,119 @@ +/* + * QorIQ Sec/Crypto 5.3 device tree stub [ controller @ offset 0x300000 ] + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +crypto: crypto@300000 { + compatible = "fsl,sec-v5.3", "fsl,sec-v5.0", "fsl,sec-v4.0"; + fsl,sec-era = <4>; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x300000 0x10000>; + ranges = <0 0x300000 0x10000>; + interrupts = <92 2 0 0>; + + sec_jr0: jr@1000 { + compatible = "fsl,sec-v5.3-job-ring", + "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x1000 0x1000>; + interrupts = <88 2 0 0>; + }; + + sec_jr1: jr@2000 { + compatible = "fsl,sec-v5.3-job-ring", + "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x2000 0x1000>; + interrupts = <89 2 0 0>; + }; + + sec_jr2: jr@3000 { + compatible = "fsl,sec-v5.3-job-ring", + "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x3000 0x1000>; + interrupts = <90 2 0 0>; + }; + + sec_jr3: jr@4000 { + compatible = "fsl,sec-v5.3-job-ring", + "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x4000 0x1000>; + interrupts = <91 2 0 0>; + }; + + rtic@6000 { + compatible = "fsl,sec-v5.3-rtic", + "fsl,sec-v5.0-rtic", + "fsl,sec-v4.0-rtic"; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x6000 0x100>; + ranges = <0x0 0x6100 0xe00>; + + rtic_a: rtic-a@0 { + compatible = "fsl,sec-v5.3-rtic-memory", + "fsl,sec-v5.0-rtic-memory", + "fsl,sec-v4.0-rtic-memory"; + reg = <0x00 0x20 0x100 0x80>; + }; + + rtic_b: rtic-b@20 { + compatible = "fsl,sec-v5.3-rtic-memory", + "fsl,sec-v5.0-rtic-memory", + "fsl,sec-v4.0-rtic-memory"; + reg = <0x20 0x20 0x200 0x80>; + }; + + rtic_c: rtic-c@40 { + compatible = "fsl,sec-v5.3-rtic-memory", + "fsl,sec-v5.0-rtic-memory", + "fsl,sec-v4.0-rtic-memory"; + reg = <0x40 0x20 0x300 0x80>; + }; + + rtic_d: rtic-d@60 { + compatible = "fsl,sec-v5.3-rtic-memory", + "fsl,sec-v5.0-rtic-memory", + "fsl,sec-v4.0-rtic-memory"; + reg = <0x60 0x20 0x500 0x80>; + }; + }; +}; + +sec_mon: sec_mon@314000 { + compatible = "fsl,sec-v5.3-mon", "fsl,sec-v5.0-mon", "fsl,sec-v4.0-mon"; + reg = <0x314000 0x1000>; + interrupts = <93 2 0 0>; +}; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi new file mode 100644 index 000000000000..bd611a9cad32 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -0,0 +1,442 @@ +/* + * T4240 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&ifc { + #address-cells = <2>; + #size-cells = <1>; + compatible = "fsl,ifc", "simple-bus"; + interrupts = <25 2 0 0>; +}; + +/* controller at 0x240000 */ +&pci0 { + compatible = "fsl,t4240-pcie", "fsl,qoriq-pcie-v3.0"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <20 2 0 0>; + pcie@0 { + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + reg = <0 0 0 0 0>; + interrupts = <20 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 40 1 0 0 + 0000 0 0 2 &mpic 1 1 0 0 + 0000 0 0 3 &mpic 2 1 0 0 + 0000 0 0 4 &mpic 3 1 0 0 + >; + }; +}; + +/* controller at 0x250000 */ +&pci1 { + compatible = "fsl,t4240-pcie", "fsl,qoriq-pcie-v3.0"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0 0xff>; + interrupts = <21 2 0 0>; + pcie@0 { + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + reg = <0 0 0 0 0>; + interrupts = <21 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 41 1 0 0 + 0000 0 0 2 &mpic 5 1 0 0 + 0000 0 0 3 &mpic 6 1 0 0 + 0000 0 0 4 &mpic 7 1 0 0 + >; + }; +}; + +/* controller at 0x260000 */ +&pci2 { + compatible = "fsl,t4240-pcie", "fsl,qoriq-pcie-v3.0"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <22 2 0 0>; + pcie@0 { + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + reg = <0 0 0 0 0>; + interrupts = <22 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 42 1 0 0 + 0000 0 0 2 &mpic 9 1 0 0 + 0000 0 0 3 &mpic 10 1 0 0 + 0000 0 0 4 &mpic 11 1 0 0 + >; + }; +}; + +/* controller at 0x270000 */ +&pci3 { + compatible = "fsl,t4240-pcie", "fsl,qoriq-pcie-v3.0"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <23 2 0 0>; + pcie@0 { + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + reg = <0 0 0 0 0>; + interrupts = <23 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 43 1 0 0 + 0000 0 0 2 &mpic 0 1 0 0 + 0000 0 0 3 &mpic 4 1 0 0 + 0000 0 0 4 &mpic 8 1 0 0 + >; + }; +}; + +&rio { + compatible = "fsl,srio"; + interrupts = <16 2 1 11>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + port1 { + #address-cells = <2>; + #size-cells = <2>; + cell-index = <1>; + }; + + port2 { + #address-cells = <2>; + #size-cells = <2>; + cell-index = <2>; + }; +}; + +&dcsr { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,dcsr", "simple-bus"; + + dcsr-epu@0 { + compatible = "fsl,t4240-dcsr-epu", "fsl,dcsr-epu"; + interrupts = <52 2 0 0 + 84 2 0 0 + 85 2 0 0 + 94 2 0 0 + 95 2 0 0>; + reg = <0x0 0x1000>; + }; + dcsr-npc { + compatible = "fsl,t4240-dcsr-cnpc", "fsl,dcsr-cnpc"; + reg = <0x1000 0x1000 0x1002000 0x10000>; + }; + dcsr-nxc@2000 { + compatible = "fsl,dcsr-nxc"; + reg = <0x2000 0x1000>; + }; + dcsr-corenet { + compatible = "fsl,dcsr-corenet"; + reg = <0x8000 0x1000 0x1A000 0x1000>; + }; + dcsr-dpaa@9000 { + compatible = "fsl,t4240-dcsr-dpaa", "fsl,dcsr-dpaa"; + reg = <0x9000 0x1000>; + }; + dcsr-ocn@11000 { + compatible = "fsl,t4240-dcsr-ocn", "fsl,dcsr-ocn"; + reg = <0x11000 0x1000>; + }; + dcsr-ddr@12000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr1>; + reg = <0x12000 0x1000>; + }; + dcsr-ddr@13000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr2>; + reg = <0x13000 0x1000>; + }; + dcsr-ddr@14000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr3>; + reg = <0x14000 0x1000>; + }; + dcsr-nal@18000 { + compatible = "fsl,t4240-dcsr-nal", "fsl,dcsr-nal"; + reg = <0x18000 0x1000>; + }; + dcsr-rcpm@22000 { + compatible = "fsl,t4240-dcsr-rcpm", "fsl,dcsr-rcpm"; + reg = <0x22000 0x1000>; + }; + dcsr-snpc@30000 { + compatible = "fsl,t4240-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x30000 0x1000 0x1022000 0x10000>; + }; + dcsr-snpc@31000 { + compatible = "fsl,t4240-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x31000 0x1000 0x1042000 0x10000>; + }; + dcsr-snpc@32000 { + compatible = "fsl,t4240-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x32000 0x1000 0x1062000 0x10000>; + }; + dcsr-cpu-sb-proxy@100000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu0>; + reg = <0x100000 0x1000 0x101000 0x1000>; + }; + dcsr-cpu-sb-proxy@108000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu1>; + reg = <0x108000 0x1000 0x109000 0x1000>; + }; + dcsr-cpu-sb-proxy@110000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu2>; + reg = <0x110000 0x1000 0x111000 0x1000>; + }; + dcsr-cpu-sb-proxy@118000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu3>; + reg = <0x118000 0x1000 0x119000 0x1000>; + }; + dcsr-cpu-sb-proxy@120000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu4>; + reg = <0x120000 0x1000 0x121000 0x1000>; + }; + dcsr-cpu-sb-proxy@128000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu5>; + reg = <0x128000 0x1000 0x129000 0x1000>; + }; + dcsr-cpu-sb-proxy@130000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu6>; + reg = <0x130000 0x1000 0x131000 0x1000>; + }; + dcsr-cpu-sb-proxy@138000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu7>; + reg = <0x138000 0x1000 0x139000 0x1000>; + }; + dcsr-cpu-sb-proxy@140000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu8>; + reg = <0x140000 0x1000 0x141000 0x1000>; + }; + dcsr-cpu-sb-proxy@148000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu9>; + reg = <0x148000 0x1000 0x149000 0x1000>; + }; + dcsr-cpu-sb-proxy@150000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu10>; + reg = <0x150000 0x1000 0x151000 0x1000>; + }; + dcsr-cpu-sb-proxy@158000 { + compatible = "fsl,dcsr-e6500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu11>; + reg = <0x158000 0x1000 0x159000 0x1000>; + }; +}; + +&soc { + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + compatible = "simple-bus"; + + soc-sram-error { + compatible = "fsl,soc-sram-error"; + interrupts = <16 2 1 29>; + }; + + corenet-law@0 { + compatible = "fsl,corenet-law"; + reg = <0x0 0x1000>; + fsl,num-laws = <32>; + }; + + ddr1: memory-controller@8000 { + compatible = "fsl,qoriq-memory-controller-v4.7", + "fsl,qoriq-memory-controller"; + reg = <0x8000 0x1000>; + interrupts = <16 2 1 23>; + }; + + ddr2: memory-controller@9000 { + compatible = "fsl,qoriq-memory-controller-v4.7", + "fsl,qoriq-memory-controller"; + reg = <0x9000 0x1000>; + interrupts = <16 2 1 22>; + }; + + ddr3: memory-controller@a000 { + compatible = "fsl,qoriq-memory-controller-v4.7", + "fsl,qoriq-memory-controller"; + reg = <0xa000 0x1000>; + interrupts = <16 2 1 21>; + }; + + cpc: l3-cache-controller@10000 { + compatible = "fsl,t4240-l3-cache-controller", "cache"; + reg = <0x10000 0x1000 + 0x11000 0x1000 + 0x12000 0x1000>; + interrupts = <16 2 1 27 + 16 2 1 26 + 16 2 1 25>; + }; + + corenet-cf@18000 { + compatible = "fsl,corenet-cf"; + reg = <0x18000 0x1000>; + interrupts = <16 2 1 31>; + fsl,ccf-num-csdids = <32>; + fsl,ccf-num-snoopids = <32>; + }; + + iommu@20000 { + compatible = "fsl,pamu-v1.0", "fsl,pamu"; + reg = <0x20000 0x6000>; + interrupts = < + 24 2 0 0 + 16 2 1 30>; + }; + +/include/ "qoriq-mpic.dtsi" + + guts: global-utilities@e0000 { + compatible = "fsl,t4240-device-config", "fsl,qoriq-device-config-2.0"; + reg = <0xe0000 0xe00>; + fsl,has-rstcr; + fsl,liodn-bits = <12>; + }; + + clockgen: global-utilities@e1000 { + compatible = "fsl,t4240-clockgen", "fsl,qoriq-clockgen-2.0"; + reg = <0xe1000 0x1000>; + }; + + rcpm: global-utilities@e2000 { + compatible = "fsl,t4240-rcpm", "fsl,qoriq-rcpm-2.0"; + reg = <0xe2000 0x1000>; + }; + + sfp: sfp@e8000 { + compatible = "fsl,t4240-sfp"; + reg = <0xe8000 0x1000>; + }; + + serdes: serdes@ea000 { + compatible = "fsl,t4240-serdes"; + reg = <0xea000 0x4000>; + }; + +/include/ "qoriq-dma-0.dtsi" +/include/ "qoriq-dma-1.dtsi" + +/include/ "qoriq-espi-0.dtsi" + spi@110000 { + fsl,espi-num-chipselects = <4>; + }; + +/include/ "qoriq-esdhc-0.dtsi" + sdhc@114000 { + compatible = "fsl,t4240-esdhc", "fsl,esdhc"; + sdhci,auto-cmd12; + }; +/include/ "qoriq-i2c-0.dtsi" +/include/ "qoriq-i2c-1.dtsi" +/include/ "qoriq-duart-0.dtsi" +/include/ "qoriq-duart-1.dtsi" +/include/ "qoriq-gpio-0.dtsi" +/include/ "qoriq-gpio-1.dtsi" +/include/ "qoriq-gpio-2.dtsi" +/include/ "qoriq-gpio-3.dtsi" +/include/ "qoriq-usb2-mph-0.dtsi" + usb0: usb@210000 { + compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph"; + phy_type = "utmi"; + port0; + }; +/include/ "qoriq-usb2-dr-0.dtsi" + usb1: usb@211000 { + compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr"; + dr_mode = "host"; + phy_type = "utmi"; + }; +/include/ "qoriq-sata2-0.dtsi" +/include/ "qoriq-sata2-1.dtsi" +/include/ "qoriq-sec5.0-0.dtsi" + + L2_1: l2-cache-controller@c20000 { + compatible = "fsl,t4240-l2-cache-controller"; + reg = <0xc20000 0x40000>; + next-level-cache = <&cpc>; + }; + L2_2: l2-cache-controller@c60000 { + compatible = "fsl,t4240-l2-cache-controller"; + reg = <0xc60000 0x40000>; + next-level-cache = <&cpc>; + }; + L2_3: l2-cache-controller@ca0000 { + compatible = "fsl,t4240-l2-cache-controller"; + reg = <0xca0000 0x40000>; + next-level-cache = <&cpc>; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi new file mode 100644 index 000000000000..a93c55a88560 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi @@ -0,0 +1,128 @@ +/* + * T4240 Silicon/SoC Device Tree Source (pre include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/dts-v1/; + +/include/ "e6500_power_isa.dtsi" + +/ { + compatible = "fsl,T4240"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + aliases { + ccsr = &soc; + dcsr = &dcsr; + + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + serial3 = &serial3; + crypto = &crypto; + pci0 = &pci0; + pci1 = &pci1; + pci2 = &pci2; + pci3 = &pci3; + dma0 = &dma0; + dma1 = &dma1; + sdhc = &sdhc; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: PowerPC,e6500@0 { + device_type = "cpu"; + reg = <0 1>; + next-level-cache = <&L2_1>; + }; + cpu1: PowerPC,e6500@2 { + device_type = "cpu"; + reg = <2 3>; + next-level-cache = <&L2_1>; + }; + cpu2: PowerPC,e6500@4 { + device_type = "cpu"; + reg = <4 5>; + next-level-cache = <&L2_1>; + }; + cpu3: PowerPC,e6500@6 { + device_type = "cpu"; + reg = <6 7>; + next-level-cache = <&L2_1>; + }; + cpu4: PowerPC,e6500@8 { + device_type = "cpu"; + reg = <8 9>; + next-level-cache = <&L2_2>; + }; + cpu5: PowerPC,e6500@10 { + device_type = "cpu"; + reg = <10 11>; + next-level-cache = <&L2_2>; + }; + cpu6: PowerPC,e6500@12 { + device_type = "cpu"; + reg = <12 13>; + next-level-cache = <&L2_2>; + }; + cpu7: PowerPC,e6500@14 { + device_type = "cpu"; + reg = <14 15>; + next-level-cache = <&L2_2>; + }; + cpu8: PowerPC,e6500@16 { + device_type = "cpu"; + reg = <16 17>; + next-level-cache = <&L2_3>; + }; + cpu9: PowerPC,e6500@18 { + device_type = "cpu"; + reg = <18 19>; + next-level-cache = <&L2_3>; + }; + cpu10: PowerPC,e6500@20 { + device_type = "cpu"; + reg = <20 21>; + next-level-cache = <&L2_3>; + }; + cpu11: PowerPC,e6500@22 { + device_type = "cpu"; + reg = <22 23>; + next-level-cache = <&L2_3>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi index 723e292b6b4e..bd14c00e5146 100644 --- a/arch/powerpc/boot/dts/mpc5121.dtsi +++ b/arch/powerpc/boot/dts/mpc5121.dtsi @@ -152,6 +152,8 @@ compatible = "fsl,mpc5121-sdhc"; reg = <0x1500 0x100>; interrupts = <8 0x8>; + dmas = <&dma0 30>; + dma-names = "rx-tx"; }; i2c@1700 { @@ -384,7 +386,7 @@ 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/mpc8536ds_36b.dts b/arch/powerpc/boot/dts/mpc8536ds_36b.dts index f8a3b3413176..6c723ee108cd 100644 --- a/arch/powerpc/boot/dts/mpc8536ds_36b.dts +++ b/arch/powerpc/boot/dts/mpc8536ds_36b.dts @@ -32,7 +32,7 @@ reg = <0 0 0 0>; // Filled by U-Boot }; - lbc: localbus@ffe05000 { + lbc: localbus@fffe05000 { reg = <0xf 0xffe05000 0 0x1000>; ranges = <0x0 0x0 0xf 0xe8000000 0x08000000 @@ -44,7 +44,7 @@ ranges = <0x0 0xf 0xffe00000 0x100000>; }; - pci0: pci@ffe08000 { + pci0: pci@fffe08000 { reg = <0xf 0xffe08000 0 0x1000>; ranges = <0x02000000 0 0xf0000000 0xc 0x00000000 0 0x10000000 0x01000000 0 0x00000000 0xf 0xffc00000 0 0x00010000>; @@ -59,7 +59,7 @@ 0x8800 0 0 4 &mpic 4 1 0 0>; }; - pci1: pcie@ffe09000 { + pci1: pcie@fffe09000 { reg = <0xf 0xffe09000 0 0x1000>; ranges = <0x02000000 0 0xf8000000 0xc 0x18000000 0 0x08000000 0x01000000 0 0x00000000 0xf 0xffc20000 0 0x00010000>; diff --git a/arch/powerpc/boot/dts/p1021rdb-pc.dtsi b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi index c13abfbbe2e2..d6274c58f496 100644 --- a/arch/powerpc/boot/dts/p1021rdb-pc.dtsi +++ b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi @@ -62,11 +62,19 @@ }; partition@400000 { - /* 11MB for JFFS2 based Root file System */ - reg = <0x00400000 0x00b00000>; + /* 10.75MB for JFFS2 based Root file System */ + reg = <0x00400000 0x00ac0000>; label = "NOR JFFS2 Root File System"; }; + partition@ec0000 { + /* This location must not be altered */ + /* 256KB for QE ucode firmware*/ + reg = <0x00ec0000 0x00040000>; + label = "NOR QE microcode firmware"; + read-only; + }; + partition@f00000 { /* This location must not be altered */ /* 512KB for u-boot Bootloader Image */ diff --git a/arch/powerpc/boot/dts/p1025rdb_36b.dts b/arch/powerpc/boot/dts/p1025rdb_36b.dts index 4ce4bfa0eda4..06deb6f341ba 100644 --- a/arch/powerpc/boot/dts/p1025rdb_36b.dts +++ b/arch/powerpc/boot/dts/p1025rdb_36b.dts @@ -82,6 +82,11 @@ 0x0 0x100000>; }; }; + + qe: qe@fffe80000 { + status = "disabled"; /* no firmware loaded */ + }; + }; /include/ "p1025rdb.dtsi" 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/boot/dts/t4240qds.dts b/arch/powerpc/boot/dts/t4240qds.dts new file mode 100644 index 000000000000..0555976dd0f3 --- /dev/null +++ b/arch/powerpc/boot/dts/t4240qds.dts @@ -0,0 +1,224 @@ +/* + * T4240QDS Device Tree Source + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/t4240si-pre.dtsi" + +/ { + model = "fsl,T4240QDS"; + compatible = "fsl,T4240QDS"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + ifc: localbus@ffe124000 { + reg = <0xf 0xfe124000 0 0x2000>; + ranges = <0 0 0xf 0xe8000000 0x08000000 + 2 0 0xf 0xff800000 0x00010000 + 3 0 0xf 0xffdf0000 0x00008000>; + + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + + partition@0 { + /* This location must not be altered */ + /* 1MB for u-boot Bootloader Image */ + reg = <0x0 0x00100000>; + label = "NAND U-Boot Image"; + read-only; + }; + + partition@100000 { + /* 1MB for DTB Image */ + reg = <0x00100000 0x00100000>; + label = "NAND DTB Image"; + }; + + partition@200000 { + /* 10MB for Linux Kernel Image */ + reg = <0x00200000 0x00A00000>; + label = "NAND Linux Kernel Image"; + }; + + partition@C00000 { + /* 500MB for Root file System Image */ + reg = <0x00c00000 0x1F400000>; + label = "NAND RFS Image"; + }; + }; + + board-control@3,0 { + compatible = "fsl,t4240qds-fpga", "fsl,fpga-qixis"; + reg = <3 0 0x300>; + }; + }; + + memory { + device_type = "memory"; + }; + + dcsr: dcsr@f00000000 { + ranges = <0x00000000 0xf 0x00000000 0x01072000>; + }; + + soc: soc@ffe000000 { + ranges = <0x00000000 0xf 0xfe000000 0x1000000>; + reg = <0xf 0xfe000000 0 0x00001000>; + spi@110000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "sst,sst25wf040"; + reg = <0>; + spi-max-frequency = <40000000>; /* input clock */ + }; + }; + + i2c@118000 { + eeprom@51 { + compatible = "at24,24c256"; + reg = <0x51>; + }; + eeprom@52 { + compatible = "at24,24c256"; + reg = <0x52>; + }; + eeprom@53 { + compatible = "at24,24c256"; + reg = <0x53>; + }; + eeprom@54 { + compatible = "at24,24c256"; + reg = <0x54>; + }; + eeprom@55 { + compatible = "at24,24c256"; + reg = <0x55>; + }; + eeprom@56 { + compatible = "at24,24c256"; + reg = <0x56>; + }; + rtc@68 { + compatible = "dallas,ds3232"; + reg = <0x68>; + interrupts = <0x1 0x1 0 0>; + }; + }; + }; + + pci0: pcie@ffe240000 { + reg = <0xf 0xfe240000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci1: pcie@ffe250000 { + reg = <0xf 0xfe250000 0 0x10000>; + ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000 + 0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci2: pcie@ffe260000 { + reg = <0xf 0xfe260000 0 0x1000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci3: pcie@ffe270000 { + reg = <0xf 0xfe270000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + rio: rapidio@ffe0c0000 { + reg = <0xf 0xfe0c0000 0 0x11000>; + + port1 { + ranges = <0 0 0xc 0x20000000 0 0x10000000>; + }; + port2 { + ranges = <0 0 0xc 0x30000000 0 0x10000000>; + }; + }; +}; + +/include/ "fsl/t4240si-post.dtsi" diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index 3d139fa04050..6c8b020806ff 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -1,14 +1,13 @@ CONFIG_PPC64=y CONFIG_PPC_BOOK3E_64=y -# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set +CONFIG_ALTIVEC=y CONFIG_SMP=y -CONFIG_NR_CPUS=2 -CONFIG_EXPERIMENTAL=y +CONFIG_NR_CPUS=24 CONFIG_SYSVIPC=y -CONFIG_BSD_PROCESS_ACCT=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -22,10 +21,13 @@ CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_MAC_PARTITION=y +CONFIG_B4_QDS=y CONFIG_P5020_DS=y CONFIG_P5040_DS=y +CONFIG_T4240_QDS=y # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set CONFIG_BINFMT_MISC=m +CONFIG_FSL_IFC=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_MSI=y CONFIG_RAPIDIO=y @@ -58,16 +60,33 @@ CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_MTD=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_OF_PARTS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y CONFIG_MTD_BLOCK=y +CONFIG_FTL=y CONFIG_MTD_CFI=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_M25P80=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_NAND_ECC=y CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_IDS=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y @@ -78,6 +97,7 @@ CONFIG_SATA_FSL=y CONFIG_SATA_SIL24=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y +CONFIG_E1000E=y CONFIG_INPUT_FF_MEMLESS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -121,7 +141,16 @@ CONFIG_NTFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y -# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_MISC_FILESYSTEMS=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_DEBUG=1 +CONFIG_JFFS2_FS_WRITEBUFFER=y +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +CONFIG_UBIFS_FS=y +CONFIG_UBIFS_FS_XATTR=y +CONFIG_UBIFS_FS_LZO=y +CONFIG_UBIFS_FS_ZLIB=y CONFIG_NFS_FS=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y @@ -129,6 +158,12 @@ CONFIG_NFSD=m CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=m CONFIG_CRC_T10DIF=y +CONFIG_CRC16=y +CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y +CONFIG_CRYPTO_DEFLATE=y +CONFIG_CRYPTO_LZO=y CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y @@ -140,6 +175,5 @@ CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y -CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_FSL_CAAM=y 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/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index cf815e847cdc..5a58882e351e 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -1,13 +1,12 @@ CONFIG_PPC_85xx=y CONFIG_PHYS_64BIT=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y CONFIG_AUDIT=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -48,6 +47,7 @@ CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y CONFIG_FORCE_MAX_ZONEORDER=12 +CONFIG_FSL_IFC=y CONFIG_PCI=y CONFIG_PCI_MSI=y CONFIG_RAPIDIO=y @@ -79,18 +79,33 @@ CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_MTD=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_OF_PARTS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y CONFIG_MTD_BLOCK=y CONFIG_FTL=y CONFIG_MTD_CFI=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_M25P80=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_NAND_ECC=y CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_IDS=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y @@ -106,6 +121,7 @@ CONFIG_SCSI_LOGGING=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_FSL=y +CONFIG_SATA_SIL24=y CONFIG_PATA_ALI=y CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y @@ -113,6 +129,9 @@ CONFIG_DUMMY=y CONFIG_FS_ENET=y CONFIG_UCC_GETH=y CONFIG_GIANFAR=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_IGB=y CONFIG_MARVELL_PHY=y CONFIG_DAVICOM_PHY=y CONFIG_CICADA_PHY=y @@ -132,7 +151,6 @@ CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_SERIAL_QE=m CONFIG_NVRAM=y -CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_CPM=m CONFIG_I2C_MPC=y @@ -206,6 +224,15 @@ CONFIG_NTFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_DEBUG=1 +CONFIG_JFFS2_FS_WRITEBUFFER=y +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +CONFIG_UBIFS_FS=y +CONFIG_UBIFS_FS_XATTR=y +CONFIG_UBIFS_FS_LZO=y +CONFIG_UBIFS_FS_ZLIB=y CONFIG_ADFS_FS=m CONFIG_AFFS_FS=m CONFIG_HFS_FS=m @@ -224,13 +251,18 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y CONFIG_CRC_T10DIF=y +CONFIG_CRC16=y +CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y +CONFIG_CRYPTO_DEFLATE=y +CONFIG_CRYPTO_LZO=y CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y -CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_FSL_CAAM=y CONFIG_CRYPTO_DEV_TALITOS=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index 8d00ea5b8a9f..165e6b32baef 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -50,6 +50,7 @@ CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y CONFIG_FORCE_MAX_ZONEORDER=12 +CONFIG_FSL_IFC=y CONFIG_PCI=y CONFIG_PCI_MSI=y CONFIG_RAPIDIO=y @@ -81,18 +82,33 @@ CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_MTD=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_OF_PARTS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y CONFIG_MTD_BLOCK=y CONFIG_FTL=y CONFIG_MTD_CFI=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_M25P80=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_NAND_ECC=y CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_IDS=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y @@ -108,6 +124,7 @@ CONFIG_SCSI_LOGGING=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_FSL=y +CONFIG_SATA_SIL24=y CONFIG_PATA_ALI=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y @@ -207,6 +224,15 @@ CONFIG_NTFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_DEBUG=1 +CONFIG_JFFS2_FS_WRITEBUFFER=y +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +CONFIG_UBIFS_FS=y +CONFIG_UBIFS_FS_XATTR=y +CONFIG_UBIFS_FS_LZO=y +CONFIG_UBIFS_FS_ZLIB=y CONFIG_ADFS_FS=m CONFIG_AFFS_FS=m CONFIG_HFS_FS=m @@ -225,6 +251,12 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y CONFIG_CRC_T10DIF=y +CONFIG_CRC16=y +CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y +CONFIG_CRYPTO_DEFLATE=y +CONFIG_CRYPTO_LZO=y CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 7a5c15fcc7cf..139a8308070c 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 @@ -136,7 +136,6 @@ CONFIG_HID_SMARTJOYPLUS=m CONFIG_USB_HIDDEV=y CONFIG_USB=m CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_SUSPEND=y CONFIG_USB_MON=m CONFIG_USB_EHCI_HCD=m # CONFIG_USB_EHCI_HCD_PPC_OF 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/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h new file mode 100644 index 000000000000..b6f5a33b8ee2 --- /dev/null +++ b/arch/powerpc/include/asm/context_tracking.h @@ -0,0 +1,10 @@ +#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H +#define _ASM_POWERPC_CONTEXT_TRACKING_H + +#ifdef CONFIG_CONTEXT_TRACKING +#define SCHEDULE_USER bl .schedule_user +#else +#define SCHEDULE_USER bl .schedule +#endif + +#endif diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fb3245e928ea..26807e5aff51 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 */ @@ -151,7 +152,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_HVMODE LONG_ASM_CONST(0x0000000100000000) #define CPU_FTR_ARCH_201 LONG_ASM_CONST(0x0000000200000000) #define CPU_FTR_ARCH_206 LONG_ASM_CONST(0x0000000400000000) -#define CPU_FTR_CFAR LONG_ASM_CONST(0x0000000800000000) +#define CPU_FTR_ARCH_207S LONG_ASM_CONST(0x0000000800000000) #define CPU_FTR_IABR LONG_ASM_CONST(0x0000001000000000) #define CPU_FTR_MMCRA LONG_ASM_CONST(0x0000002000000000) #define CPU_FTR_CTRL LONG_ASM_CONST(0x0000004000000000) @@ -172,7 +173,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_ICSWX LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_VMX_COPY LONG_ASM_CONST(0x0040000000000000) #define CPU_FTR_TM LONG_ASM_CONST(0x0080000000000000) -#define CPU_FTR_BCTAR LONG_ASM_CONST(0x0100000000000000) +#define CPU_FTR_CFAR LONG_ASM_CONST(0x0100000000000000) #define CPU_FTR_HAS_PPR LONG_ASM_CONST(0x0200000000000000) #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) @@ -223,8 +224,10 @@ extern const char *powerpc_base_platform; /* We only set the TM feature if the kernel was compiled with TM supprt */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM #define CPU_FTR_TM_COMP CPU_FTR_TM +#define PPC_FEATURE2_HTM_COMP PPC_FEATURE2_HTM #else #define CPU_FTR_TM_COMP 0 +#define PPC_FEATURE2_HTM_COMP 0 #endif /* We need to mark all pages as being coherent if we're SMP or we have a @@ -374,7 +377,7 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_E6500 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \ CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ - CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV) + CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP) #define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ @@ -421,8 +424,8 @@ extern const char *powerpc_base_platform; CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ - CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | CPU_FTR_BCTAR | \ - CPU_FTR_TM_COMP) + CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ 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..681bc0314b6b 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 +50,9 @@ #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) +#define FW_FEATURE_OPALv3 ASM_CONST(0x0000000400000000) #ifndef __ASSEMBLY__ @@ -65,9 +67,11 @@ 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_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 | + FW_FEATURE_OPALv3, FW_FEATURE_POWERNV_ALWAYS = 0, FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, 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/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 62e11a32c4c2..f2498c8e595d 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -3,9 +3,37 @@ #ifdef CONFIG_HUGETLB_PAGE #include <asm/page.h> +#include <asm-generic/hugetlb.h> extern struct kmem_cache *hugepte_cache; +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * This should work for other subarchs too. But right now we use the + * new format only for 64bit book3s + */ +static inline pte_t *hugepd_page(hugepd_t hpd) +{ + BUG_ON(!hugepd_ok(hpd)); + /* + * We have only four bits to encode, MMU page size + */ + BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf); + return (pte_t *)(hpd.pd & ~HUGEPD_SHIFT_MASK); +} + +static inline unsigned int hugepd_mmu_psize(hugepd_t hpd) +{ + return (hpd.pd & HUGEPD_SHIFT_MASK) >> 2; +} + +static inline unsigned int hugepd_shift(hugepd_t hpd) +{ + return mmu_psize_to_shift(hugepd_mmu_psize(hpd)); +} + +#else + static inline pte_t *hugepd_page(hugepd_t hpd) { BUG_ON(!hugepd_ok(hpd)); @@ -17,6 +45,9 @@ static inline unsigned int hugepd_shift(hugepd_t hpd) return hpd.pd & HUGEPD_SHIFT_MASK; } +#endif /* CONFIG_PPC_BOOK3S_64 */ + + static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift) { diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 4bc2c3dad6ad..0c7f2bfcf134 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -264,12 +264,16 @@ #define H_GET_MPP 0x2D4 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC #define H_BEST_ENERGY 0x2F4 +#define H_XIRR_X 0x2FC #define H_RANDOM 0x300 #define H_COP 0x304 #define H_GET_MPP_X 0x314 #define H_SET_MODE 0x31C #define MAX_HCALL_OPCODE H_SET_MODE +/* Platform specific hcalls, used by KVM */ +#define H_RTAS 0xf000 + #ifndef __ASSEMBLY__ /** diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index e45c4947a772..ba713f166fa5 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -95,15 +95,14 @@ static inline bool arch_irqs_disabled(void) #define __hard_irq_disable() __mtmsrd(local_paca->kernel_msr, 1) #endif -static inline void hard_irq_disable(void) -{ - __hard_irq_disable(); - get_paca()->soft_enabled = 0; - get_paca()->irq_happened |= PACA_IRQ_HARD_DIS; -} - -/* include/linux/interrupt.h needs hard_irq_disable to be a macro */ -#define hard_irq_disable hard_irq_disable +#define hard_irq_disable() do { \ + u8 _was_enabled = get_paca()->soft_enabled; \ + __hard_irq_disable(); \ + get_paca()->soft_enabled = 0; \ + get_paca()->irq_happened |= PACA_IRQ_HARD_DIS; \ + if (_was_enabled) \ + trace_hardirqs_off(); \ +} while(0) static inline bool lazy_irq_pending(void) { 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/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index aabcdba8f6b0..b9dd382cb349 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -67,6 +67,10 @@ #define BOOKE_INTERRUPT_HV_SYSCALL 40 #define BOOKE_INTERRUPT_HV_PRIV 41 +/* altivec */ +#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL 42 +#define BOOKE_INTERRUPT_ALTIVEC_ASSIST 43 + /* book3s */ #define BOOK3S_INTERRUPT_SYSTEM_RESET 0x100 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 5a56e1c5f851..349ed85c7d61 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -142,6 +142,8 @@ extern int kvmppc_mmu_hv_init(void); extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec); +extern void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, + unsigned int vec); extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags); extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); @@ -156,7 +158,8 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep, unsigned long pte_index); extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr, unsigned long *nb_ret); -extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr); +extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr, + unsigned long gpa, bool dirty); extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel); extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, @@ -458,6 +461,8 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) #define OSI_SC_MAGIC_R4 0x77810F9B #define INS_DCBZ 0x7c0007ec +/* TO = 31 for unconditional trap */ +#define INS_TW 0x7fe00008 /* LPIDs we support with this build -- runtime limit may be lower */ #define KVMPPC_NR_LPIDS (LPID_RSVD + 1) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 38bec1dc9928..9c1ff330c805 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -268,4 +268,17 @@ static inline int is_vrma_hpte(unsigned long hpte_v) (HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16))); } +#ifdef CONFIG_KVM_BOOK3S_64_HV +/* + * Note modification of an HPTE; set the HPTE modified bit + * if anyone is interested. + */ +static inline void note_hpte_modification(struct kvm *kvm, + struct revmap_entry *rev) +{ + if (atomic_read(&kvm->arch.hpte_mod_interest)) + rev->guest_rpte |= HPTE_GR_MODIFIED; +} +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index cdc3d2717cc6..9039d3c97eec 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -20,6 +20,11 @@ #ifndef __ASM_KVM_BOOK3S_ASM_H__ #define __ASM_KVM_BOOK3S_ASM_H__ +/* XICS ICP register offsets */ +#define XICS_XIRR 4 +#define XICS_MFRR 0xc +#define XICS_IPI 2 /* interrupt source # for IPIs */ + #ifdef __ASSEMBLY__ #ifdef CONFIG_KVM_BOOK3S_HANDLER @@ -81,10 +86,11 @@ struct kvmppc_host_state { #ifdef CONFIG_KVM_BOOK3S_64_HV u8 hwthread_req; u8 hwthread_state; - + u8 host_ipi; struct kvm_vcpu *kvm_vcpu; struct kvmppc_vcore *kvm_vcore; unsigned long xics_phys; + u32 saved_xirr; u64 dabr; u64 host_mmcr[3]; u32 host_pmc[8]; diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index b7cd3356a532..d3c1eb34c986 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -26,6 +26,8 @@ /* LPIDs we support with this build -- runtime limit may be lower */ #define KVMPPC_NR_LPIDS 64 +#define KVMPPC_INST_EHPRIV 0x7c00021c + static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { vcpu->arch.gpr[num] = val; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d1bb86074721..af326cde7cb6 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -44,6 +44,10 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #endif +/* These values are internal and can be increased later */ +#define KVM_NR_IRQCHIPS 1 +#define KVM_IRQCHIP_NUM_PINS 256 + #if !defined(CONFIG_KVM_440) #include <linux/mmu_notifier.h> @@ -188,6 +192,10 @@ struct kvmppc_linear_info { int type; }; +/* XICS components, defined in book3s_xics.c */ +struct kvmppc_xics; +struct kvmppc_icp; + /* * The reverse mapping array has one entry for each HPTE, * which stores the guest's view of the second word of the HPTE @@ -255,6 +263,13 @@ struct kvm_arch { #endif /* CONFIG_KVM_BOOK3S_64_HV */ #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; + struct list_head rtas_tokens; +#endif +#ifdef CONFIG_KVM_MPIC + struct openpic *mpic; +#endif +#ifdef CONFIG_KVM_XICS + struct kvmppc_xics *xics; #endif }; @@ -301,11 +316,13 @@ struct kvmppc_vcore { * that a guest can register. */ struct kvmppc_vpa { + unsigned long gpa; /* Current guest phys addr */ void *pinned_addr; /* Address in kernel linear mapping */ void *pinned_end; /* End of region */ unsigned long next_gpa; /* Guest phys addr for update */ unsigned long len; /* Number of bytes required */ u8 update_pending; /* 1 => update pinned_addr from next_gpa */ + bool dirty; /* true => area has been modified by kernel */ }; struct kvmppc_pte { @@ -359,6 +376,11 @@ struct kvmppc_slb { #define KVMPPC_BOOKE_MAX_IAC 4 #define KVMPPC_BOOKE_MAX_DAC 2 +/* KVMPPC_EPR_USER takes precedence over KVMPPC_EPR_KERNEL */ +#define KVMPPC_EPR_NONE 0 /* EPR not supported */ +#define KVMPPC_EPR_USER 1 /* exit to userspace to fill EPR */ +#define KVMPPC_EPR_KERNEL 2 /* in-kernel irqchip */ + struct kvmppc_booke_debug_reg { u32 dbcr0; u32 dbcr1; @@ -370,6 +392,12 @@ struct kvmppc_booke_debug_reg { u64 dac[KVMPPC_BOOKE_MAX_DAC]; }; +#define KVMPPC_IRQ_DEFAULT 0 +#define KVMPPC_IRQ_MPIC 1 +#define KVMPPC_IRQ_XICS 2 + +struct openpic; + struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; @@ -502,8 +530,11 @@ struct kvm_vcpu_arch { spinlock_t wdt_lock; struct timer_list wdt_timer; u32 tlbcfg[4]; + u32 tlbps[4]; u32 mmucfg; + u32 eptcfg; u32 epr; + u32 crit_save; struct kvmppc_booke_debug_reg dbg_reg; #endif gpa_t paddr_accessed; @@ -521,7 +552,7 @@ struct kvm_vcpu_arch { u8 sane; u8 cpu_type; u8 hcall_needed; - u8 epr_enabled; + u8 epr_flags; /* KVMPPC_EPR_xxx */ u8 epr_needed; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -548,6 +579,13 @@ struct kvm_vcpu_arch { unsigned long magic_page_pa; /* phys addr to map the magic page to */ unsigned long magic_page_ea; /* effect. addr to map the magic page to */ + int irq_type; /* one of KVM_IRQ_* */ + int irq_cpu_id; + struct openpic *mpic; /* KVM_IRQ_MPIC */ +#ifdef CONFIG_KVM_XICS + struct kvmppc_icp *icp; /* XICS presentation controller */ +#endif + #ifdef CONFIG_KVM_BOOK3S_64_HV struct kvm_vcpu_arch_shared shregs; @@ -588,5 +626,6 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_FQPR 0x0060 #define __KVM_HAVE_ARCH_WQP +#define __KVM_HAVE_CREATE_DEVICE #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 44a657adf416..a5287fe03d77 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -44,7 +44,7 @@ enum emulation_result { EMULATE_DO_DCR, /* kvm_run filled with DCR request */ EMULATE_FAIL, /* can't emulate this instruction */ EMULATE_AGAIN, /* something went wrong. go again */ - EMULATE_DO_PAPR, /* kvm_run filled with PAPR request */ + EMULATE_EXIT_USER, /* emulation requires exit to user-space */ }; extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -104,8 +104,7 @@ extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); -extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, - struct kvm_interrupt *irq); +extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu); extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu); extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, @@ -131,6 +130,7 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm, extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long porder); extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); + extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce *args); extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, @@ -152,7 +152,7 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old); + const struct kvm_memory_slot *old); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info); extern void kvmppc_core_flush_memslot(struct kvm *kvm, @@ -165,6 +165,18 @@ extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); +int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); + +extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp); +extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu); +extern void kvmppc_rtas_tokens_free(struct kvm *kvm); +extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, + u32 priority); +extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, + u32 *priority); +extern int kvmppc_xics_int_on(struct kvm *kvm, u32 irq); +extern int kvmppc_xics_int_off(struct kvm *kvm, u32 irq); + /* * Cuts out inst bits with ordering according to spec. * That means the leftmost bit is zero. All given bits are included. @@ -246,12 +258,29 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *); void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); +struct openpic; + #ifdef CONFIG_KVM_BOOK3S_64_HV static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) { paca[cpu].kvm_hstate.xics_phys = addr; } +static inline u32 kvmppc_get_xics_latch(void) +{ + u32 xirr = get_paca()->kvm_hstate.saved_xirr; + + get_paca()->kvm_hstate.saved_xirr = 0; + + return xirr; +} + +static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi) +{ + paca[cpu].kvm_hstate.host_ipi = host_ipi; +} + +extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu); extern void kvm_linear_init(void); #else @@ -260,6 +289,46 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) static inline void kvm_linear_init(void) {} + +static inline u32 kvmppc_get_xics_latch(void) +{ + return 0; +} + +static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi) +{} + +static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) +{ + kvm_vcpu_kick(vcpu); +} +#endif + +#ifdef CONFIG_KVM_XICS +static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.irq_type == KVMPPC_IRQ_XICS; +} +extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); +extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server); +extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args); +extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd); +extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu); +extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); +extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev, + struct kvm_vcpu *vcpu, u32 cpu); +#else +static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) + { return 0; } +static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } +static inline int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, + unsigned long server) + { return -EINVAL; } +static inline int kvm_vm_ioctl_xics_irq(struct kvm *kvm, + struct kvm_irq_level *args) + { return -ENOTTY; } +static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) + { return 0; } #endif static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr) @@ -271,6 +340,32 @@ static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr) #endif } +#ifdef CONFIG_KVM_MPIC + +void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu); +int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, + u32 cpu); +void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu); + +#else + +static inline void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu) +{ +} + +static inline int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, + struct kvm_vcpu *vcpu, u32 cpu) +{ + return -EINVAL; +} + +static inline void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, + struct kvm_vcpu *vcpu) +{ +} + +#endif /* CONFIG_KVM_MPIC */ + int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, struct kvm_config_tlb *cfg); int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, @@ -283,8 +378,15 @@ void kvmppc_init_lpid(unsigned long nr_lpids); static inline void kvmppc_mmu_flush_icache(pfn_t pfn) { - /* Clear i-cache for new pages */ struct page *page; + /* + * We can only access pages that the kernel maps + * as memory. Bail out for unmapped ones. + */ + if (!pfn_valid(pfn)) + return; + + /* Clear i-cache for new pages */ page = pfn_to_page(pfn); if (!test_bit(PG_arch_1, &page->flags)) { flush_dcache_icache_page(page); @@ -324,4 +426,6 @@ static inline ulong kvmppc_get_ea_indexed(struct kvm_vcpu *vcpu, int ra, int rb) return ea; } +extern void xics_wake_cpu(int cpu); + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h new file mode 100644 index 000000000000..b36f650a13ff --- /dev/null +++ b/arch/powerpc/include/asm/linkage.h @@ -0,0 +1,13 @@ +#ifndef _ASM_POWERPC_LINKAGE_H +#define _ASM_POWERPC_LINKAGE_H + +#ifdef CONFIG_PPC64 +#define cond_syscall(x) \ + asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n" \ + "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n") +#define SYSCALL_ALIAS(alias, name) \ + asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n" \ + "\t.globl ." #alias "\n\t.set ." #alias ", ." #name) +#endif + +#endif /* _ASM_POWERPC_LINKAGE_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 3d6b4100dac1..92386fc4e82a 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -29,6 +29,7 @@ struct rtc_time; struct file; struct pci_controller; struct kimage; +struct pci_host_bridge; struct machdep_calls { char *name; @@ -50,7 +51,8 @@ struct machdep_calls { unsigned long prpn, unsigned long rflags, unsigned long vflags, - int psize, int ssize); + int psize, int apsize, + int ssize); long (*hpte_remove)(unsigned long hpte_group); void (*hpte_removebolted)(unsigned long ea, int psize, int ssize); @@ -107,6 +109,8 @@ struct machdep_calls { void (*pcibios_fixup)(void); int (*pci_probe_mode)(struct pci_bus *); void (*pci_irq_fixup)(struct pci_dev *dev); + int (*pcibios_root_bridge_prepare)(struct pci_host_bridge + *bridge); /* To setup PHBs when using automatic OF platform driver for PCI */ int (*pci_setup_phb)(struct pci_controller *host); diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index 99d43e0c1e4a..936db360790a 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -215,6 +215,7 @@ #define TLBILX_T_CLASS3 7 #ifndef __ASSEMBLY__ +#include <asm/bug.h> extern unsigned int tlbcam_index; @@ -231,6 +232,10 @@ typedef struct { u64 high_slices_psize; /* 4 bits per slice for now */ u16 user_psize; /* page size index */ #endif +#ifdef CONFIG_PPC_64K_PAGES + /* for 4K PTE fragment support */ + void *pte_frag; +#endif } mm_context_t; /* Page size definitions, common between 32 and 64-bit @@ -250,6 +255,23 @@ struct mmu_psize_def }; extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; +static inline int shift_to_mmu_psize(unsigned int shift) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) + if (mmu_psize_defs[psize].shift == shift) + return psize; + return -1; +} + +static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +{ + if (mmu_psize_defs[mmu_psize].shift) + return mmu_psize_defs[mmu_psize].shift; + BUG(); +} + /* The page sizes use the same names as 64-bit hash but are * constants */ diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 2fdb47a19efd..2accc9611248 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -21,6 +21,7 @@ * complete pgtable.h but only a portion of it. */ #include <asm/pgtable-ppc64.h> +#include <asm/bug.h> /* * Segment table @@ -154,11 +155,29 @@ extern unsigned long htab_hash_mask; struct mmu_psize_def { unsigned int shift; /* number of bits */ - unsigned int penc; /* HPTE encoding */ + int penc[MMU_PAGE_COUNT]; /* HPTE encoding */ unsigned int tlbiel; /* tlbiel supported for that page size */ unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */ unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ }; +extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; + +static inline int shift_to_mmu_psize(unsigned int shift) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) + if (mmu_psize_defs[psize].shift == shift) + return psize; + return -1; +} + +static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +{ + if (mmu_psize_defs[mmu_psize].shift) + return mmu_psize_defs[mmu_psize].shift; + BUG(); +} #endif /* __ASSEMBLY__ */ @@ -181,6 +200,13 @@ struct mmu_psize_def */ #define VPN_SHIFT 12 +/* + * HPTE Large Page (LP) details + */ +#define LP_SHIFT 12 +#define LP_BITS 8 +#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT) + #ifndef __ASSEMBLY__ static inline int segment_shift(int ssize) @@ -193,7 +219,6 @@ static inline int segment_shift(int ssize) /* * The current system page and segment sizes */ -extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; @@ -237,14 +262,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize, /* * This function sets the AVPN and L fields of the HPTE appropriately - * for the page size + * using the base page size and actual page size. */ -static inline unsigned long hpte_encode_v(unsigned long vpn, - int psize, int ssize) +static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize, + int actual_psize, int ssize) { unsigned long v; - v = hpte_encode_avpn(vpn, psize, ssize); - if (psize != MMU_PAGE_4K) + v = hpte_encode_avpn(vpn, base_psize, ssize); + if (actual_psize != MMU_PAGE_4K) v |= HPTE_V_LARGE; return v; } @@ -254,19 +279,17 @@ static inline unsigned long hpte_encode_v(unsigned long vpn, * for the page size. We assume the pa is already "clean" that is properly * aligned for the requested page size */ -static inline unsigned long hpte_encode_r(unsigned long pa, int psize) +static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize, + int actual_psize) { - unsigned long r; - /* A 4K page needs no special encoding */ - if (psize == MMU_PAGE_4K) + if (actual_psize == MMU_PAGE_4K) return pa & HPTE_R_RPN; else { - unsigned int penc = mmu_psize_defs[psize].penc; - unsigned int shift = mmu_psize_defs[psize].shift; - return (pa & ~((1ul << shift) - 1)) | (penc << 12); + unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize]; + unsigned int shift = mmu_psize_defs[actual_psize].shift; + return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT); } - return r; } /* @@ -319,7 +342,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned int shift, unsigned int mmu_psize); extern void hash_failure_debug(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long trap, - int ssize, int psize, unsigned long pte); + int ssize, int psize, int lpsize, + unsigned long pte); extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long pstart, unsigned long prot, int psize, int ssize); @@ -343,17 +367,16 @@ 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) - * - * 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 first generate a 37-bit "proto-VSID". Proto-VSIDs are generated + * from mmu context id and effective segment id of the address. * - * 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 +386,49 @@ 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: + * 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 have VSIDs allocated for every kernel address - * (i.e. everything above 0xC000000000000000), except the very top - * segment, which simplifies several things. + * 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. * - * - 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. - * - * - 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 +452,8 @@ 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 \ @@ -490,6 +522,10 @@ typedef struct { unsigned long acop; /* mask of enabled coprocessor types */ unsigned int cop_pid; /* pid value used with coprocessors */ #endif /* CONFIG_PPC_ICSWX */ +#ifdef CONFIG_PPC_64K_PAGES + /* for 4K PTE fragment support */ + void *pte_frag; +#endif } mm_context_t; @@ -513,34 +549,6 @@ 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 +558,41 @@ 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..cbb9305ab15a 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__ @@ -242,7 +243,8 @@ enum OpalMCE_TlbErrorType { enum OpalThreadStatus { OPAL_THREAD_INACTIVE = 0x0, - OPAL_THREAD_STARTED = 0x1 + OPAL_THREAD_STARTED = 0x1, + OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */ }; enum OpalPciBusCompare { @@ -506,6 +508,7 @@ 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, @@ -561,6 +564,8 @@ extern void opal_nvram_init(void); extern int opal_machine_check(struct pt_regs *regs); +extern void opal_shutdown(void); + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_H */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index f072e974f8a2..988c812aab5b 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -249,6 +249,7 @@ extern long long virt_phys_offset; #define is_kernel_addr(x) ((x) >= PAGE_OFFSET) #endif +#ifndef CONFIG_PPC_BOOK3S_64 /* * Use the top bit of the higher-level page table entries to indicate whether * the entries we point to contain hugepages. This works because we know that @@ -260,6 +261,7 @@ extern long long virt_phys_offset; #else #define PD_HUGE 0x80000000 #endif +#endif /* CONFIG_PPC_BOOK3S_64 */ /* * Some number of bits at the level of the page table that points to @@ -354,14 +356,27 @@ typedef unsigned long pgprot_t; typedef struct { signed long pd; } hugepd_t; #ifdef CONFIG_HUGETLB_PAGE +#ifdef CONFIG_PPC_BOOK3S_64 +static inline int hugepd_ok(hugepd_t hpd) +{ + /* + * hugepd pointer, bottom two bits == 00 and next 4 bits + * indicate size of table + */ + return (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0)); +} +#else static inline int hugepd_ok(hugepd_t hpd) { return (hpd.pd > 0); } +#endif #define is_hugepd(pdep) (hugepd_ok(*((hugepd_t *)(pdep)))) +int pgd_huge(pgd_t pgd); #else /* CONFIG_HUGETLB_PAGE */ #define is_hugepd(pdep) 0 +#define pgd_huge(pgd) 0 #endif /* CONFIG_HUGETLB_PAGE */ struct page; @@ -378,7 +393,11 @@ void arch_free_page(struct page *page, int order); struct vm_area_struct; +#ifdef CONFIG_PPC_64K_PAGES +typedef pte_t *pgtable_t; +#else typedef struct page *pgtable_t; +#endif #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ 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/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 025a130729bc..2c1d8cb9b265 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -39,11 +39,6 @@ struct pci_controller { resource_size_t io_base_phys; resource_size_t pci_io_size; - /* Some machines (PReP) have a non 1:1 mapping of - * the PCI memory space in the CPU bus space - */ - resource_size_t pci_mem_offset; - /* Some machines have a special region to forward the ISA * "memory" cycles such as VGA memory regions. Left to 0 * if unsupported @@ -70,6 +65,8 @@ struct pci_controller { * BIG_ENDIAN - cfg_addr is a big endian register * BROKEN_MRM - the 440EPx/GRx chips have an errata that causes hangs on * the PLB4. Effectively disable MRM commands by setting this. + * FSL_CFG_REG_LINK - Freescale controller version in which the PCIe + * link status is in a RC PCIe cfg register (vs being a SoC register) */ #define PPC_INDIRECT_TYPE_SET_CFG_TYPE 0x00000001 #define PPC_INDIRECT_TYPE_EXT_REG 0x00000002 @@ -77,12 +74,14 @@ struct pci_controller { #define PPC_INDIRECT_TYPE_NO_PCIE_LINK 0x00000008 #define PPC_INDIRECT_TYPE_BIG_ENDIAN 0x00000010 #define PPC_INDIRECT_TYPE_BROKEN_MRM 0x00000020 +#define PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK 0x00000040 u32 indirect_type; /* Currently, we limit ourselves to 1 IO range and 3 mem * ranges since the common pci_bus structure can't handle more */ struct resource io_resource; struct resource mem_resources[3]; + resource_size_t mem_offset[3]; int global_number; /* PCI domain number */ resource_size_t dma_window_base_cur; @@ -90,9 +89,9 @@ struct pci_controller { #ifdef CONFIG_PPC64 unsigned long buid; +#endif /* CONFIG_PPC64 */ void *private_data; -#endif /* CONFIG_PPC64 */ }; /* These are used for config access before all the PCI probing @@ -117,6 +116,12 @@ extern void setup_indirect_pci(struct pci_controller* hose, resource_size_t cfg_addr, resource_size_t cfg_data, u32 flags); +extern int indirect_read_config(struct pci_bus *bus, unsigned int devfn, + int offset, int len, u32 *val); + +extern int indirect_write_config(struct pci_bus *bus, unsigned int devfn, + int offset, int len, u32 val); + static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) { return bus->sysdata; @@ -154,6 +159,8 @@ struct pci_dn { int pci_ext_config_space; /* for pci devices */ + int force_32bit_msi:1; + struct pci_dev *pcidev; /* back-pointer to the pci device */ #ifdef CONFIG_EEH struct eeh_dev *edev; /* eeh device */ @@ -167,6 +174,8 @@ struct pci_dn { /* Get the pointer to a device_node's pci_dn */ #define PCI_DN(dn) ((struct pci_dn *) (dn)->data) +extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev); + extern void * update_dn_pci_info(struct device_node *dn, void *data); static inline int pci_device_from_OF_node(struct device_node *np, 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/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h index 580cf73b96e8..27b2386f738a 100644 --- a/arch/powerpc/include/asm/pgalloc-32.h +++ b/arch/powerpc/include/asm/pgalloc-32.h @@ -37,6 +37,17 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) +{ + pgtable_page_dtor(ptepage); + __free_page(ptepage); +} + static inline void pgtable_free(void *table, unsigned index_size) { BUG_ON(index_size); /* 32-bit doesn't use this */ @@ -45,4 +56,38 @@ static inline void pgtable_free(void *table, unsigned index_size) #define check_pgt_cache() do { } while (0) +#ifdef CONFIG_SMP +static inline void pgtable_free_tlb(struct mmu_gather *tlb, + void *table, int shift) +{ + unsigned long pgf = (unsigned long)table; + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + pgf |= shift; + tlb_remove_table(tlb, (void *)pgf); +} + +static inline void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; + + pgtable_free(table, shift); +} +#else +static inline void pgtable_free_tlb(struct mmu_gather *tlb, + void *table, int shift) +{ + pgtable_free(table, shift); +} +#endif + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, + unsigned long address) +{ + struct page *page = page_address(table); + + tlb_flush_pgtable(tlb, address); + pgtable_page_dtor(page); + pgtable_free_tlb(tlb, page, 0); +} #endif /* _ASM_POWERPC_PGALLOC_32_H */ diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 292725cec2e3..b66ae722a8e9 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -35,7 +35,10 @@ struct vmemmap_backing { #define MAX_PGTABLE_INDEX_SIZE 0xf extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) (pgtable_cache[(shift)-1]) +#define PGT_CACHE(shift) ({ \ + BUG_ON(!(shift)); \ + pgtable_cache[(shift) - 1]; \ + }) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -72,8 +75,100 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) #define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte)) #define pmd_pgtable(pmd) pmd_page(pmd) +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, + unsigned long address) +{ + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); +} + +static inline pgtable_t pte_alloc_one(struct mm_struct *mm, + unsigned long address) +{ + struct page *page; + pte_t *pte; + + pte = pte_alloc_one_kernel(mm, address); + if (!pte) + return NULL; + page = virt_to_page(pte); + pgtable_page_ctor(page); + return page; +} + +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) +{ + pgtable_page_dtor(ptepage); + __free_page(ptepage); +} + +static inline void pgtable_free(void *table, unsigned index_size) +{ + if (!index_size) + free_page((unsigned long)table); + else { + BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(index_size), table); + } +} + +#ifdef CONFIG_SMP +static inline void pgtable_free_tlb(struct mmu_gather *tlb, + void *table, int shift) +{ + unsigned long pgf = (unsigned long)table; + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + pgf |= shift; + tlb_remove_table(tlb, (void *)pgf); +} + +static inline void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; + + pgtable_free(table, shift); +} +#else /* !CONFIG_SMP */ +static inline void pgtable_free_tlb(struct mmu_gather *tlb, + void *table, int shift) +{ + pgtable_free(table, shift); +} +#endif /* CONFIG_SMP */ + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, + unsigned long address) +{ + struct page *page = page_address(table); + + tlb_flush_pgtable(tlb, address); + pgtable_page_dtor(page); + pgtable_free_tlb(tlb, page, 0); +} + +#else /* if CONFIG_PPC_64K_PAGES */ +/* + * we support 16 fragments per PTE page. + */ +#define PTE_FRAG_NR 16 +/* + * We use a 2K PTE page fragment and another 2K for storing + * real_pte_t hash index + */ +#define PTE_FRAG_SIZE_SHIFT 12 +#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t)) -#else /* CONFIG_PPC_64K_PAGES */ +extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int); +extern void page_table_free(struct mm_struct *, unsigned long *, int); +extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); +#ifdef CONFIG_SMP +extern void __tlb_remove_table(void *_table); +#endif #define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd) @@ -83,51 +178,56 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pmd_set(pmd, (unsigned long)pte); } -#define pmd_populate(mm, pmd, pte_page) \ - pmd_populate_kernel(mm, pmd, page_address(pte_page)) -#define pmd_pgtable(pmd) pmd_page(pmd) - -#endif /* CONFIG_PPC_64K_PAGES */ - -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + pgtable_t pte_page) { - return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE), - GFP_KERNEL|__GFP_REPEAT); + pmd_set(pmd, (unsigned long)pte_page); } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +static inline pgtable_t pmd_pgtable(pmd_t pmd) { - kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd); + return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + return (pte_t *)page_table_alloc(mm, address, 1); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page; - pte_t *pte; + return (pgtable_t)page_table_alloc(mm, address, 0); +} - pte = pte_alloc_one_kernel(mm, address); - if (!pte) - return NULL; - page = virt_to_page(pte); - pgtable_page_ctor(page); - return page; +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + page_table_free(mm, (unsigned long *)pte, 1); } -static inline void pgtable_free(void *table, unsigned index_size) +static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { - if (!index_size) - free_page((unsigned long)table); - else { - BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); - kmem_cache_free(PGT_CACHE(index_size), table); - } + page_table_free(mm, (unsigned long *)ptepage, 0); +} + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, + unsigned long address) +{ + tlb_flush_pgtable(tlb, address); + pgtable_free_tlb(tlb, table, 0); +} +#endif /* CONFIG_PPC_64K_PAGES */ + +static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE), + GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd); } #define __pmd_free_tlb(tlb, pmd, addr) \ diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index bf301ac62f35..e9a9f60e596d 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -3,6 +3,7 @@ #ifdef __KERNEL__ #include <linux/mm.h> +#include <asm-generic/tlb.h> #ifdef CONFIG_PPC_BOOK3E extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address); @@ -13,56 +14,11 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb, } #endif /* !CONFIG_PPC_BOOK3E */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) -{ - pgtable_page_dtor(ptepage); - __free_page(ptepage); -} - #ifdef CONFIG_PPC64 #include <asm/pgalloc-64.h> #else #include <asm/pgalloc-32.h> #endif -#ifdef CONFIG_SMP -struct mmu_gather; -extern void tlb_remove_table(struct mmu_gather *, void *); - -static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - unsigned long pgf = (unsigned long)table; - BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); - pgf |= shift; - tlb_remove_table(tlb, (void *)pgf); -} - -static inline void __tlb_remove_table(void *_table) -{ - void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); - unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; - - pgtable_free(table, shift); -} -#else /* CONFIG_SMP */ -static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift) -{ - pgtable_free(table, shift); -} -#endif /* !CONFIG_SMP */ - -static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage, - unsigned long address) -{ - tlb_flush_pgtable(tlb, address); - pgtable_page_dtor(ptepage); - pgtable_free_tlb(tlb, page_address(ptepage), 0); -} - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h index be4e2878fbc0..45142d640720 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h @@ -4,10 +4,10 @@ #include <asm-generic/pgtable-nopud.h> -#define PTE_INDEX_SIZE 12 -#define PMD_INDEX_SIZE 12 +#define PTE_INDEX_SIZE 8 +#define PMD_INDEX_SIZE 10 #define PUD_INDEX_SIZE 0 -#define PGD_INDEX_SIZE 6 +#define PGD_INDEX_SIZE 12 #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 0182c203e411..e3d55f6f24fe 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -167,8 +167,7 @@ * Find an entry in a page-table-directory. We combine the address region * (the high order N bits) and the pgd portion of the address. */ -/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */ -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff) +#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index a9cbd3ba5c33..7aeb9555f6ea 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -17,6 +17,12 @@ struct mm_struct; # include <asm/pgtable-ppc32.h> #endif +/* + * We save the slot number & secondary bit in the second half of the + * PTE page. We use the 8 bytes per each pte entry. + */ +#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8) + #ifndef __ASSEMBLY__ #include <asm/tlbflush.h> @@ -212,6 +218,8 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr); +extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr); #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 8752bc8e34a3..eccfc161e58e 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 @@ -113,6 +115,10 @@ #define PPC_INST_MFSPR_DSCR_MASK 0xfc1fffff #define PPC_INST_MTSPR_DSCR 0x7c1103a6 #define PPC_INST_MTSPR_DSCR_MASK 0xfc1fffff +#define PPC_INST_MFSPR_DSCR_USER 0x7c0302a6 +#define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1fffff +#define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6 +#define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1fffff #define PPC_INST_SLBFEE 0x7c0007a7 #define PPC_INST_STRING 0x7c00042a @@ -297,6 +303,12 @@ #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/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index cea8496091ff..2f1b6c5f8174 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -523,6 +523,17 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946) #define PPC440EP_ERR42 #endif +/* The following stops all load and store data streams associated with stream + * ID (ie. streams created explicitly). The embedded and server mnemonics for + * dcbt are different so we use machine "power4" here explicitly. + */ +#define DCBT_STOP_ALL_STREAM_IDS(scratch) \ +.machine push ; \ +.machine "power4" ; \ + lis scratch,0x60000000@h; \ + dcbt r0,scratch,0b01010; \ +.machine pop + /* * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them * keep the address intact to be compatible with code shared with diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7ff9eaa3ea6c..14a658363698 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) */ /* @@ -288,6 +281,15 @@ struct thread_struct { #endif #ifdef CONFIG_PPC_BOOK3S_64 unsigned long tar; + unsigned long ebbrr; + unsigned long ebbhr; + unsigned long bescr; + unsigned long siar; + unsigned long sdar; + unsigned long sier; + unsigned long mmcr0; + unsigned long mmcr2; + unsigned long mmcra; #endif }; @@ -407,21 +409,16 @@ static inline void prefetchw(const void *x) #endif #ifdef CONFIG_PPC64 -static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32) +static inline unsigned long get_clean_sp(unsigned long sp, int is_32) { - unsigned long sp; - if (is_32) - sp = regs->gpr[1] & 0x0ffffffffUL; - else - sp = regs->gpr[1]; - + return sp & 0x0ffffffffUL; return sp; } #else -static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32) +static inline unsigned long get_clean_sp(unsigned long sp, int is_32) { - return regs->gpr[1]; + return sp; } #endif 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/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index 3e13e23e4fdf..d836d945068d 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -47,7 +47,7 @@ * generic accessors and iterators here */ #define __real_pte(e,p) ((real_pte_t) { \ - (e), ((e) & _PAGE_COMBO) ? \ + (e), (pte_val(e) & _PAGE_COMBO) ? \ (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) #define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) 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..4a9e408644fe 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -111,17 +111,6 @@ #define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T) #define MSR_TM_SUSPENDED(x) (((x) & MSR_TS_MASK) == MSR_TS_S) -/* Reason codes describing kernel causes for transaction aborts. By - convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if - the failure is persistent. -*/ -#define TM_CAUSE_RESCHED 0xfe -#define TM_CAUSE_TLBI 0xfc -#define TM_CAUSE_FAC_UNAV 0xfa -#define TM_CAUSE_SYSCALL 0xf9 /* Persistent */ -#define TM_CAUSE_MISC 0xf6 -#define TM_CAUSE_SIGNAL 0xf4 - #if defined(CONFIG_PPC_BOOK3S_64) #define MSR_64BIT MSR_SF @@ -267,7 +256,17 @@ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ #define FSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ +#define FSCR_EBB (1 << (63-56)) /* Enable Event Based Branching */ #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_EBB (1 << (63-56)) /* Enable Event Based Branching */ +#define HFSCR_TM (1 << (63-58)) /* Enable Transactional Memory */ +#define HFSCR_PM (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */ +#define HFSCR_BHRB (1 << (63-59)) /* Enable Branch History Rolling Buffer*/ +#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)) @@ -290,6 +289,7 @@ #define LPCR_PECE1 0x00002000 /* decrementer can cause exit */ #define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */ #define LPCR_MER 0x00000800 /* Mediated External Exception */ +#define LPCR_MER_SH 11 #define LPCR_LPES 0x0000000c #define LPCR_LPES0 0x00000008 /* LPAR Env selector 0 */ #define LPCR_LPES1 0x00000004 /* LPAR Env selector 1 */ @@ -631,6 +631,7 @@ #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 +650,13 @@ #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_EBBHR 804 /* Event based branch handler register */ +#define SPRN_EBBRR 805 /* Event based branch return register */ +#define SPRN_BESCR 806 /* Branch event status and control register */ + #define SPRN_PMC1 787 #define SPRN_PMC2 788 #define SPRN_PMC3 789 @@ -659,6 +667,11 @@ #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..34fd70488d83 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 @@ -262,6 +264,8 @@ extern void rtas_progress(char *s, unsigned short hex); extern void rtas_initialize(void); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); +extern int rtas_online_cpus_mask(cpumask_var_t cpus); +extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(struct rtas_args *); struct rtc_time; @@ -277,6 +281,10 @@ 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/signal.h b/arch/powerpc/include/asm/signal.h index fbe66c463891..9322c28aebd2 100644 --- a/arch/powerpc/include/asm/signal.h +++ b/arch/powerpc/include/asm/signal.h @@ -3,5 +3,8 @@ #define __ARCH_HAS_SA_RESTORER #include <uapi/asm/signal.h> +#include <uapi/asm/ptrace.h> + +extern unsigned long get_tm_stackpointer(struct pt_regs *regs); #endif /* _ASM_POWERPC_SIGNAL_H */ 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/systbl.h b/arch/powerpc/include/asm/systbl.h index ebbec52d21bd..43523fe0d8b4 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -SYSX_SPU(sys_sendfile,compat_sys_sendfile_wrapper,sys_sendfile) +COMPAT_SYS_SPU(sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) @@ -230,7 +230,7 @@ COMPAT_SYS_SPU(sched_setaffinity) COMPAT_SYS_SPU(sched_getaffinity) SYSCALL(ni_syscall) SYSCALL(ni_syscall) -SYSX(sys_ni_syscall,compat_sys_sendfile64_wrapper,sys_sendfile64) +SYS32ONLY(sendfile64) COMPAT_SYS_SPU(io_setup) SYSCALL_SPU(io_destroy) COMPAT_SYS_SPU(io_getevents) @@ -239,7 +239,7 @@ SYSCALL_SPU(io_cancel) SYSCALL(set_tid_address) SYSX_SPU(sys_fadvise64,ppc32_fadvise64,sys_fadvise64) SYSCALL(exit_group) -SYSX(sys_lookup_dcookie,ppc32_lookup_dcookie,sys_lookup_dcookie) +COMPAT_SYS(lookup_dcookie) SYSCALL_SPU(epoll_create) SYSCALL_SPU(epoll_ctl) SYSCALL_SPU(epoll_wait) @@ -273,8 +273,8 @@ COMPAT_SYS(mq_timedreceive) COMPAT_SYS(mq_notify) COMPAT_SYS(mq_getsetattr) COMPAT_SYS(kexec_load) -COMPAT_SYS(add_key) -COMPAT_SYS(request_key) +SYSCALL(add_key) +SYSCALL(request_key) COMPAT_SYS(keyctl) COMPAT_SYS(waitid) SYSCALL(ioprio_set) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 406b7b9a1341..ba7b1973866e 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_PERFMON_CTXSW 6 /* perfmon needs ctxsw calls */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ -#define TIF_MEMDIE 9 /* is terminating due to OOM killer */ +#define TIF_NOHZ 9 /* in adaptive nohz mode */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation for stack store? */ +#define TIF_MEMDIE 17 /* is terminating due to OOM killer */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) +#define _TIF_NOHZ (1<<TIF_NOHZ) #define _TIF_SYSCALL_T_OR_A (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) + _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE) @@ -182,8 +185,6 @@ static inline bool test_thread_local_flags(unsigned int flags) #define is_32bit_task() (1) #endif -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h index 4b4449abf3f8..9dfbc34bdbf5 100644 --- a/arch/powerpc/include/asm/tm.h +++ b/arch/powerpc/include/asm/tm.h @@ -5,6 +5,8 @@ * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation. */ +#include <uapi/asm/tm.h> + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM extern void do_load_up_transact_fpu(struct thread_struct *thread); extern void do_load_up_transact_altivec(struct thread_struct *thread); 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/udbg.h b/arch/powerpc/include/asm/udbg.h index 5a7510e9d09d..dc590919f8eb 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -52,6 +52,7 @@ extern void __init udbg_init_40x_realmode(void); extern void __init udbg_init_cpm(void); extern void __init udbg_init_usbgecko(void); extern void __init udbg_init_wsp(void); +extern void __init udbg_init_memcons(void); extern void __init udbg_init_ehv_bc(void); extern void __init udbg_init_ps3gelic(void); extern void __init udbg_init_debug_opal_raw(void); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 1487f0f12293..3ca819f541bf 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -56,11 +56,5 @@ #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE -/* - * "Conditional" syscalls - */ -#define cond_syscall(x) \ - asmlinkage long x (void) __attribute__((weak,alias("sys_ni_syscall"))) - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h index b532060d0916..23016020915e 100644 --- a/arch/powerpc/include/asm/uprobes.h +++ b/arch/powerpc/include/asm/uprobes.h @@ -51,4 +51,5 @@ extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_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/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index f7bca6370745..5182c8622b54 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -40,6 +40,7 @@ header-y += statfs.h header-y += swab.h header-y += termbits.h header-y += termios.h +header-y += tm.h header-y += types.h header-y += ucontext.h header-y += unistd.h diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index ed9dd8156962..5b7657959faa 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -1,6 +1,7 @@ #ifndef _UAPI__ASM_POWERPC_CPUTABLE_H #define _UAPI__ASM_POWERPC_CPUTABLE_H +/* in AT_HWCAP */ #define PPC_FEATURE_32 0x80000000 #define PPC_FEATURE_64 0x40000000 #define PPC_FEATURE_601_INSTR 0x20000000 @@ -33,4 +34,12 @@ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 +/* in AT_HWCAP2 */ +#define PPC_FEATURE2_ARCH_2_07 0x80000000 +#define PPC_FEATURE2_HTM 0x40000000 +#define PPC_FEATURE2_DSCR 0x20000000 +#define PPC_FEATURE2_EBB 0x10000000 +#define PPC_FEATURE2_ISEL 0x08000000 +#define PPC_FEATURE2_TAR 0x04000000 + #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 16064d00adb9..0fb1a6e9ff90 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -25,6 +25,8 @@ /* Select powerpc specific features in <linux/kvm.h> */ #define __KVM_HAVE_SPAPR_TCE #define __KVM_HAVE_PPC_SMT +#define __KVM_HAVE_IRQCHIP +#define __KVM_HAVE_IRQ_LINE struct kvm_regs { __u64 pc; @@ -272,8 +274,31 @@ struct kvm_debug_exit_arch { /* for KVM_SET_GUEST_DEBUG */ struct kvm_guest_debug_arch { + struct { + /* H/W breakpoint/watchpoint address */ + __u64 addr; + /* + * Type denotes h/w breakpoint, read watchpoint, write + * watchpoint or watchpoint (both read and write). + */ +#define KVMPPC_DEBUG_NONE 0x0 +#define KVMPPC_DEBUG_BREAKPOINT (1UL << 1) +#define KVMPPC_DEBUG_WATCH_WRITE (1UL << 2) +#define KVMPPC_DEBUG_WATCH_READ (1UL << 3) + __u32 type; + __u32 reserved; + } bp[16]; }; +/* Debug related defines */ +/* + * kvm_guest_debug->control is a 32 bit field. The lower 16 bits are generic + * and upper 16 bits are architecture specific. Architecture specific defines + * that ioctl is for setting hardware breakpoint or software breakpoint. + */ +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 +#define KVM_GUESTDBG_USE_HW_BP 0x00020000 + /* definition of registers in kvm_run */ struct kvm_sync_regs { }; @@ -299,6 +324,12 @@ struct kvm_allocate_rma { __u64 rma_size; }; +/* for KVM_CAP_PPC_RTAS */ +struct kvm_rtas_token_args { + char name[120]; + __u64 token; /* Use a token of 0 to undefine a mapping */ +}; + struct kvm_book3e_206_tlb_entry { __u32 mas8; __u32 mas1; @@ -359,6 +390,26 @@ struct kvm_get_htab_header { __u16 n_invalid; }; +/* Per-vcpu XICS interrupt controller state */ +#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) + +#define KVM_REG_PPC_ICP_CPPR_SHIFT 56 /* current proc priority */ +#define KVM_REG_PPC_ICP_CPPR_MASK 0xff +#define KVM_REG_PPC_ICP_XISR_SHIFT 32 /* interrupt status field */ +#define KVM_REG_PPC_ICP_XISR_MASK 0xffffff +#define KVM_REG_PPC_ICP_MFRR_SHIFT 24 /* pending IPI priority */ +#define KVM_REG_PPC_ICP_MFRR_MASK 0xff +#define KVM_REG_PPC_ICP_PPRI_SHIFT 16 /* pending irq priority */ +#define KVM_REG_PPC_ICP_PPRI_MASK 0xff + +/* Device control API: PPC-specific devices */ +#define KVM_DEV_MPIC_GRP_MISC 1 +#define KVM_DEV_MPIC_BASE_ADDR 0 /* 64-bit */ + +#define KVM_DEV_MPIC_GRP_REGISTER 2 /* 32-bit */ +#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE 3 /* 32-bit */ + +/* One-Reg API: PPC-specific registers */ #define KVM_REG_PPC_HIOR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1) #define KVM_REG_PPC_IAC1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2) #define KVM_REG_PPC_IAC2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3) @@ -417,4 +468,47 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_EPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85) #define KVM_REG_PPC_EPR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86) +/* Timer Status Register OR/CLEAR interface */ +#define KVM_REG_PPC_OR_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x87) +#define KVM_REG_PPC_CLEAR_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x88) +#define KVM_REG_PPC_TCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x89) +#define KVM_REG_PPC_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8a) + +/* Debugging: Special instruction for software breakpoint */ +#define KVM_REG_PPC_DEBUG_INST (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8b) + +/* MMU registers */ +#define KVM_REG_PPC_MAS0 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8c) +#define KVM_REG_PPC_MAS1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8d) +#define KVM_REG_PPC_MAS2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8e) +#define KVM_REG_PPC_MAS7_3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8f) +#define KVM_REG_PPC_MAS4 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x90) +#define KVM_REG_PPC_MAS6 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x91) +#define KVM_REG_PPC_MMUCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x92) +/* + * TLBnCFG fields TLBnCFG_N_ENTRY and TLBnCFG_ASSOC can be changed only using + * KVM_CAP_SW_TLB ioctl + */ +#define KVM_REG_PPC_TLB0CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x93) +#define KVM_REG_PPC_TLB1CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x94) +#define KVM_REG_PPC_TLB2CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x95) +#define KVM_REG_PPC_TLB3CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x96) +#define KVM_REG_PPC_TLB0PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x97) +#define KVM_REG_PPC_TLB1PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x98) +#define KVM_REG_PPC_TLB2PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x99) +#define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a) +#define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b) + +/* PPC64 eXternal Interrupt Controller Specification */ +#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ + +/* Layout of 64-bit source attribute values */ +#define KVM_XICS_DESTINATION_SHIFT 0 +#define KVM_XICS_DESTINATION_MASK 0xffffffffULL +#define KVM_XICS_PRIORITY_SHIFT 32 +#define KVM_XICS_PRIORITY_MASK 0xff +#define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40) +#define KVM_XICS_MASKED (1ULL << 41) +#define KVM_XICS_PENDING (1ULL << 42) + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/include/uapi/asm/linkage.h b/arch/powerpc/include/uapi/asm/linkage.h deleted file mode 100644 index e1c4ac1cc4ba..000000000000 --- a/arch/powerpc/include/uapi/asm/linkage.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_POWERPC_LINKAGE_H -#define _ASM_POWERPC_LINKAGE_H - -/* Nothing to see here... */ - -#endif /* _ASM_POWERPC_LINKAGE_H */ 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/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index a26dcaece509..a36daf3c6f9a 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -79,4 +79,6 @@ #define SO_LOCK_FILTER 44 +#define SO_SELECT_ERR_QUEUE 45 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h new file mode 100644 index 000000000000..85059a00f560 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -0,0 +1,18 @@ +#ifndef _ASM_POWERPC_TM_H +#define _ASM_POWERPC_TM_H + +/* Reason codes describing kernel causes for transaction aborts. By + * convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if + * the failure is persistent. PAPR saves 0xff-0xe0 for the hypervisor. + */ +#define TM_CAUSE_PERSISTENT 0x01 +#define TM_CAUSE_RESCHED 0xde +#define TM_CAUSE_TLBI 0xdc +#define TM_CAUSE_FAC_UNAV 0xda +#define TM_CAUSE_SYSCALL 0xd8 /* future use */ +#define TM_CAUSE_MISC 0xd6 /* future use */ +#define TM_CAUSE_SIGNAL 0xd4 +#define TM_CAUSE_ALIGNMENT 0xd2 +#define TM_CAUSE_EMULATE 0xd0 + +#endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b6c17ec9b169..6f16ffafa6f0 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -124,6 +124,15 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S_64 DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar)); + DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr)); + DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr)); + DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr)); + DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar)); + DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar)); + DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier)); + DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0)); + DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2)); + DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra)); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch)); @@ -477,6 +486,7 @@ int main(void) DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); + DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty)); #endif #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); @@ -573,6 +583,8 @@ int main(void) HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore); HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys); + HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr); + HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi); HSTATE_FIELD(HSTATE_MMCR, host_mmcr); HSTATE_FIELD(HSTATE_PMC, host_pmc); HSTATE_FIELD(HSTATE_PURR, host_purr); @@ -596,6 +608,7 @@ int main(void) DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); + DEFINE(VCPU_CRIT_SAVE, offsetof(struct kvm_vcpu, arch.crit_save)); #endif /* CONFIG_PPC_BOOK3S */ #endif /* CONFIG_KVM */ diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index dcd881937f7a..0b9af015bedc 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -53,6 +53,15 @@ _GLOBAL(__e500_dcache_setup) isync blr +_GLOBAL(__setup_cpu_e6500) + mflr r6 +#ifdef CONFIG_PPC64 + bl .setup_altivec_ivors +#endif + bl __setup_cpu_e5500 + mtlr r6 + blr + #ifdef CONFIG_PPC32 _GLOBAL(__setup_cpu_e200) /* enable dedicated debug exception handling resources (Debug APU) */ @@ -107,6 +116,13 @@ _GLOBAL(__setup_cpu_e5500) #endif #ifdef CONFIG_PPC_BOOK3E_64 +_GLOBAL(__restore_cpu_e6500) + mflr r5 + bl .setup_altivec_ivors + bl __restore_cpu_e5500 + mtlr r5 + blr + _GLOBAL(__restore_cpu_e5500) mflr r4 bl __e500_icache_setup diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index ea847abb0d0a..18b5b9cf8e37 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 @@ -116,13 +123,24 @@ __init_LPCR: __init_FSCR: mfspr r3,SPRN_FSCR - ori r3,r3,FSCR_TAR|FSCR_DSCR + ori r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB mtspr SPRN_FSCR,r3 blr +__init_HFSCR: + mfspr r3,SPRN_HFSCR + ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\ + HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB + mtspr SPRN_HFSCR,r3 + blr + __init_TLB: - /* Clear the TLB */ - li r6,128 + /* + * Clear the TLB using the "IS 3" form of tlbiel instruction + * (invalidate by congruence class). P7 has 128 CCs, P8 has 512 + * so we just always do 512 + */ + li r6,512 mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync @@ -131,3 +149,18 @@ __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 75a3d71b895d..1f0937d7d4b5 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -74,7 +74,9 @@ extern void __restore_cpu_a2(void); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_e6500(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_e5500(void); +extern void __restore_cpu_e6500(void); #endif /* CONFIG_E500 */ /* This table only contains "desktop" CPUs, it need to be filled with embedded @@ -96,10 +98,14 @@ extern void __restore_cpu_e5500(void); PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR) #define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \ + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR) #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) @@ -275,7 +281,7 @@ 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, @@ -426,6 +432,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (architected)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, @@ -441,11 +448,12 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER8 (architected)", .cpu_features = CPU_FTRS_POWER8, .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, .mmu_features = MMU_FTRS_POWER8, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_type = PPC_OPROFILE_POWER4, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", + .oprofile_cpu_type = 0, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .platform = "power8", @@ -456,6 +464,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, @@ -473,6 +482,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7+ (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, @@ -490,12 +500,13 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER8 (raw)", .cpu_features = CPU_FTRS_POWER8, .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, .mmu_features = MMU_FTRS_POWER8, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", + .oprofile_cpu_type = 0, .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, @@ -1993,6 +2004,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, .mmu_features = MMU_FTR_TYPE_FSL_E, .icache_bsize = 32, .dcache_bsize = 32, @@ -2012,6 +2024,7 @@ static struct cpu_spec __initdata cpu_specs[] = { PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_HAS_EFP_DOUBLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, .icache_bsize = 32, .dcache_bsize = 32, @@ -2028,6 +2041,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e500mc", .cpu_features = CPU_FTRS_E500MC, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, .icache_bsize = 64, @@ -2046,6 +2060,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e5500", .cpu_features = CPU_FTRS_E5500, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, .icache_bsize = 64, @@ -2065,7 +2080,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_value = 0x80400000, .cpu_name = "e6500", .cpu_features = CPU_FTRS_E6500, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, .icache_bsize = 64, @@ -2073,9 +2090,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 4, .oprofile_cpu_type = "ppc/e6500", .oprofile_type = PPC_OPROFILE_FSL_EMB, - .cpu_setup = __setup_cpu_e5500, + .cpu_setup = __setup_cpu_e6500, #ifndef CONFIG_PPC32 - .cpu_restore = __restore_cpu_e5500, + .cpu_restore = __restore_cpu_e6500, #endif .machine_check = machine_check_e500mc, .platform = "ppce6500", diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index b3ba5163eae2..9ec3fe174cba 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -150,10 +150,7 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start)) continue; - ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); - init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); - free_page((unsigned long)__va(addr)); - totalram_pages++; + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); } } #endif 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_32.S b/arch/powerpc/kernel/entry_32.S index e514de57a125..22b45a4955cd 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -439,8 +439,6 @@ ret_from_fork: ret_from_kernel_thread: REST_NVGPRS(r1) bl schedule_tail - li r3,0 - stw r3,0(r1) mtlr r14 mr r3,r15 PPC440EP_ERR42 @@ -851,7 +849,7 @@ resume_kernel: /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ CURRENT_THREAD_INFO(r9, r1) lwz r8,TI_FLAGS(r9) - andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + andis. r0,r8,_TIF_EMULATE_STACK_STORE@h beq+ 1f addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf0adb7..246b11c4fe7e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -33,6 +33,7 @@ #include <asm/irqflags.h> #include <asm/ftrace.h> #include <asm/hw_irq.h> +#include <asm/context_tracking.h> /* * System calls. @@ -150,7 +151,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) CURRENT_THREAD_INFO(r11, r1) ld r10,TI_FLAGS(r11) andi. r11,r10,_TIF_SYSCALL_T_OR_A - bne- syscall_dotrace + bne syscall_dotrace .Lsyscall_dotrace_cont: cmpldi 0,r0,NR_syscalls bge- syscall_enosys @@ -304,7 +305,7 @@ 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 @@ -376,8 +377,6 @@ _GLOBAL(ret_from_fork) _GLOBAL(ret_from_kernel_thread) bl .schedule_tail REST_NVGPRS(r1) - li r3,0 - std r3,0(r1) ld r14, 0(r14) mtlr r14 mr r3,r15 @@ -458,7 +457,29 @@ BEGIN_FTR_SECTION */ mfspr r0,SPRN_TAR std r0,THREAD_TAR(r3) -END_FTR_SECTION_IFSET(CPU_FTR_BCTAR) + + /* Event based branch registers */ + mfspr r0, SPRN_BESCR + std r0, THREAD_BESCR(r3) + mfspr r0, SPRN_EBBHR + std r0, THREAD_EBBHR(r3) + mfspr r0, SPRN_EBBRR + std r0, THREAD_EBBRR(r3) + + /* PMU registers made user read/(write) by EBB */ + mfspr r0, SPRN_SIAR + std r0, THREAD_SIAR(r3) + mfspr r0, SPRN_SDAR + std r0, THREAD_SDAR(r3) + mfspr r0, SPRN_SIER + std r0, THREAD_SIER(r3) + mfspr r0, SPRN_MMCR0 + std r0, THREAD_MMCR0(r3) + mfspr r0, SPRN_MMCR2 + std r0, THREAD_MMCR2(r3) + mfspr r0, SPRN_MMCRA + std r0, THREAD_MMCRA(r3) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) #endif #ifdef CONFIG_SMP @@ -480,6 +501,13 @@ BEGIN_FTR_SECTION ldarx r6,0,r1 END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS) +#ifdef CONFIG_PPC_BOOK3S +/* Cancel all explict user streams as they will have no use after context + * switch and will stop the HW from creating streams itself + */ + DCBT_STOP_ALL_STREAM_IDS(r6) +#endif + addi r6,r4,-THREAD /* Convert THREAD to 'current' */ std r6,PACACURRENT(r13) /* Set new 'current' */ @@ -545,9 +573,31 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) #ifdef CONFIG_PPC_BOOK3S_64 BEGIN_FTR_SECTION + /* Event based branch registers */ + ld r0, THREAD_BESCR(r4) + mtspr SPRN_BESCR, r0 + ld r0, THREAD_EBBHR(r4) + mtspr SPRN_EBBHR, r0 + ld r0, THREAD_EBBRR(r4) + mtspr SPRN_EBBRR, r0 + + /* PMU registers made user read/(write) by EBB */ + ld r0, THREAD_SIAR(r4) + mtspr SPRN_SIAR, r0 + ld r0, THREAD_SDAR(r4) + mtspr SPRN_SDAR, r0 + ld r0, THREAD_SIER(r4) + mtspr SPRN_SIER, r0 + ld r0, THREAD_MMCR0(r4) + mtspr SPRN_MMCR0, r0 + ld r0, THREAD_MMCR2(r4) + mtspr SPRN_MMCR2, r0 + ld r0, THREAD_MMCRA(r4) + mtspr SPRN_MMCRA, r0 + ld r0,THREAD_TAR(r4) mtspr SPRN_TAR,r0 -END_FTR_SECTION_IFSET(CPU_FTR_BCTAR) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) #endif #ifdef CONFIG_ALTIVEC @@ -618,7 +668,7 @@ _GLOBAL(ret_from_except_lite) andi. r0,r4,_TIF_NEED_RESCHED beq 1f bl .restore_interrupts - bl .schedule + SCHEDULE_USER b .ret_from_except_lite 1: bl .save_nvgprs @@ -657,7 +707,7 @@ 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_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S index 62c0dc237826..9f1ebf7338f1 100644 --- a/arch/powerpc/kernel/epapr_hcalls.S +++ b/arch/powerpc/kernel/epapr_hcalls.S @@ -17,6 +17,7 @@ #include <asm/asm-compat.h> #include <asm/asm-offsets.h> +#ifndef CONFIG_PPC64 /* epapr_ev_idle() was derived from e500_idle() */ _GLOBAL(epapr_ev_idle) CURRENT_THREAD_INFO(r3, r1) @@ -42,6 +43,7 @@ epapr_ev_idle_start: * _TLF_NAPPING. */ b idle_loop +#endif /* Hypercall entry point. Will be patched with device tree instructions. */ .global epapr_hypercall_start 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-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ae54553eacd9..645170a07ada 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -299,6 +299,8 @@ interrupt_base_book3e: /* fake trap */ EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */ EXCEPTION_STUB(0x1c0, data_tlb_miss) EXCEPTION_STUB(0x1e0, instruction_tlb_miss) + EXCEPTION_STUB(0x200, altivec_unavailable) /* 0x0f20 */ + EXCEPTION_STUB(0x220, altivec_assist) /* 0x1700 */ EXCEPTION_STUB(0x260, perfmon) EXCEPTION_STUB(0x280, doorbell) EXCEPTION_STUB(0x2a0, doorbell_crit) @@ -395,6 +397,45 @@ interrupt_end_book3e: bl .kernel_fp_unavailable_exception b .ret_from_except +/* Altivec Unavailable Interrupt */ + START_EXCEPTION(altivec_unavailable); + NORMAL_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_ALTIVEC_UNAVAIL, + PROLOG_ADDITION_NONE) + /* we can probably do a shorter exception entry for that one... */ + EXCEPTION_COMMON(0x200, PACA_EXGEN, INTS_KEEP) +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + ld r12,_MSR(r1) + andi. r0,r12,MSR_PR; + beq- 1f + bl .load_up_altivec + b fast_exception_return +1: +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + INTS_DISABLE + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .altivec_unavailable_exception + b .ret_from_except + +/* AltiVec Assist */ + START_EXCEPTION(altivec_assist); + NORMAL_EXCEPTION_PROLOG(0x220, BOOKE_INTERRUPT_ALTIVEC_ASSIST, + PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x220, PACA_EXGEN, INTS_DISABLE) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + bl .altivec_assist_exception +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#else + bl .unknown_exception +#endif + b .ret_from_except + + /* Decrementer Interrupt */ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, decrementer, .timer_interrupt, ACK_DEC) @@ -448,7 +489,7 @@ interrupt_end_book3e: */ mfspr r14,SPRN_DBSR /* check single-step/branch taken */ - andis. r15,r14,DBSR_IC@h + andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) @@ -459,7 +500,7 @@ interrupt_end_book3e: bge+ cr1,1f /* here it looks like we got an inappropriate debug exception. */ - lis r14,DBSR_IC@h /* clear the IC event */ + lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */ rlwinm r11,r11,0,~MSR_DE /* clear DE in the CSRR1 value */ mtspr SPRN_DBSR,r14 mtspr SPRN_CSRR1,r11 @@ -514,7 +555,7 @@ kernel_dbg_exc: */ mfspr r14,SPRN_DBSR /* check single-step/branch taken */ - andis. r15,r14,DBSR_IC@h + andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) @@ -525,7 +566,7 @@ kernel_dbg_exc: bge+ cr1,1f /* here it looks like we got an inappropriate debug exception. */ - lis r14,DBSR_IC@h /* clear the IC event */ + lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */ rlwinm r11,r11,0,~MSR_DE /* clear DE in the DSRR1 value */ mtspr SPRN_DBSR,r14 mtspr SPRN_DSRR1,r11 @@ -807,6 +848,7 @@ fast_exception_return: BAD_STACK_TRAMPOLINE(0x000) BAD_STACK_TRAMPOLINE(0x100) BAD_STACK_TRAMPOLINE(0x200) +BAD_STACK_TRAMPOLINE(0x220) BAD_STACK_TRAMPOLINE(0x260) BAD_STACK_TRAMPOLINE(0x280) BAD_STACK_TRAMPOLINE(0x2a0) @@ -1350,6 +1392,11 @@ _GLOBAL(__setup_base_ivors) blr +_GLOBAL(setup_altivec_ivors) + SET_IVOR(32, 0x200) /* AltiVec Unavailable */ + SET_IVOR(33, 0x220) /* AltiVec Assist */ + blr + _GLOBAL(setup_perfmon_ivor) SET_IVOR(35, 0x260) /* Performance Monitor */ blr diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 87ef8f5ee5bc..e6eba1bf61ad 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) @@ -688,9 +693,18 @@ slb_miss_user_pseries: .align 7 .globl machine_check_common machine_check_common: + + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP DISABLE_INTS + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD bl .machine_check_exception @@ -797,7 +811,7 @@ 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 +884,6 @@ 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 +1076,6 @@ 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 +1274,78 @@ _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 +1462,36 @@ 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/fadump.c b/arch/powerpc/kernel/fadump.c index 06c8202a69cf..2230fd0ca3e4 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1045,10 +1045,7 @@ static void fadump_release_memory(unsigned long begin, unsigned long end) if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start)) continue; - ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); - init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); - free_page((unsigned long)__va(addr)); - totalram_pages++; + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); } } diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 7a2e5e421abf..97e2671cde7f 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -769,6 +769,8 @@ finish_tlb_load_47x: */ DEBUG_CRIT_EXCEPTION +interrupt_end: + /* * Global functions */ 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/head_booke.h b/arch/powerpc/kernel/head_booke.h index 5f051eeb93a2..a620203f7de3 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -199,11 +199,6 @@ .align 5; \ label: -#define FINISH_EXCEPTION(func) \ - bl transfer_to_handler_full; \ - .long func; \ - .long ret_from_except_full - #define EXCEPTION(n, intno, label, hdlr, xfer) \ START_EXCEPTION(label); \ NORMAL_EXCEPTION_PROLOG(intno); \ @@ -286,13 +281,13 @@ label: andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \ beq+ 2f; \ \ - lis r10,KERNELBASE@h; /* check if exception in vectors */ \ - ori r10,r10,KERNELBASE@l; \ + lis r10,interrupt_base@h; /* check if exception in vectors */ \ + ori r10,r10,interrupt_base@l; \ cmplw r12,r10; \ blt+ 2f; /* addr below exception vectors */ \ \ - lis r10,DebugDebug@h; \ - ori r10,r10,DebugDebug@l; \ + lis r10,interrupt_end@h; \ + ori r10,r10,interrupt_end@l; \ cmplw r12,r10; \ bgt+ 2f; /* addr above exception vectors */ \ \ @@ -339,13 +334,13 @@ label: andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \ beq+ 2f; \ \ - lis r10,KERNELBASE@h; /* check if exception in vectors */ \ - ori r10,r10,KERNELBASE@l; \ + lis r10,interrupt_base@h; /* check if exception in vectors */ \ + ori r10,r10,interrupt_base@l; \ cmplw r12,r10; \ blt+ 2f; /* addr below exception vectors */ \ \ - lis r10,DebugCrit@h; \ - ori r10,r10,DebugCrit@l; \ + lis r10,interrupt_end@h; \ + ori r10,r10,interrupt_end@l; \ cmplw r12,r10; \ bgt+ 2f; /* addr above exception vectors */ \ \ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 6f62a737f607..d10a7cacccd2 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -605,6 +605,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) /* Embedded Hypervisor Privilege */ EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE) +interrupt_end: + /* * Local functions */ diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ea78761aa169..939ea7ef0dc8 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -33,11 +33,6 @@ #include <asm/runlatch.h> #include <asm/smp.h> -#ifdef CONFIG_HOTPLUG_CPU -#define cpu_should_die() cpu_is_offline(smp_processor_id()) -#else -#define cpu_should_die() 0 -#endif unsigned long cpuidle_disable = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(cpuidle_disable); @@ -50,64 +45,38 @@ static int __init powersave_off(char *arg) } __setup("powersave=off", powersave_off); -/* - * The body of the idle task. - */ -void cpu_idle(void) +#ifdef CONFIG_HOTPLUG_CPU +void arch_cpu_idle_dead(void) { - set_thread_flag(TIF_POLLING_NRFLAG); - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched() && !cpu_should_die()) { - ppc64_runlatch_off(); - - if (ppc_md.power_save) { - clear_thread_flag(TIF_POLLING_NRFLAG); - /* - * smp_mb is so clearing of TIF_POLLING_NRFLAG - * is ordered w.r.t. need_resched() test. - */ - smp_mb(); - local_irq_disable(); - - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* check again after disabling irqs */ - if (!need_resched() && !cpu_should_die()) - ppc_md.power_save(); - - start_critical_timings(); - - /* Some power_save functions return with - * interrupts enabled, some don't. - */ - if (irqs_disabled()) - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - - } else { - /* - * Go into low thread priority and possibly - * low power mode. - */ - HMT_low(); - HMT_very_low(); - } - } + sched_preempt_enable_no_resched(); + cpu_die(); +} +#endif - HMT_medium(); - ppc64_runlatch_on(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - if (cpu_should_die()) { - sched_preempt_enable_no_resched(); - cpu_die(); - } - schedule_preempt_disabled(); +void arch_cpu_idle(void) +{ + ppc64_runlatch_off(); + + if (ppc_md.power_save) { + ppc_md.power_save(); + /* + * Some power_save functions return with + * interrupts enabled, some don't. + */ + if (irqs_disabled()) + local_irq_enable(); + } else { + local_irq_enable(); + /* + * Go into low thread priority and possibly + * low power mode. + */ + HMT_low(); + HMT_very_low(); } + + HMT_medium(); + ppc64_runlatch_on(); } int powersave_nap; diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index 4c7cb4008585..bfb73cc209ce 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -16,11 +16,13 @@ #include <asm/ppc-opcode.h> #include <asm/processor.h> #include <asm/thread_info.h> +#include <asm/epapr_hcalls.h> /* 64-bit version only for now */ #ifdef CONFIG_PPC64 -_GLOBAL(book3e_idle) +.macro BOOK3E_IDLE name loop +_GLOBAL(\name) /* Save LR for later */ mflr r0 std r0,16(r1) @@ -67,7 +69,33 @@ _GLOBAL(book3e_idle) /* We can now re-enable hard interrupts and go to sleep */ wrteei 1 -1: PPC_WAIT(0) + \loop + +.endm + +.macro BOOK3E_IDLE_LOOP +1: + PPC_WAIT(0) b 1b +.endm + +/* epapr_ev_idle_start below is patched with the proper hcall + opcodes during kernel initialization */ +.macro EPAPR_EV_IDLE_LOOP +idle_loop: + LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE)) + +.global epapr_ev_idle_start +epapr_ev_idle_start: + li r3, -1 + nop + nop + nop + b idle_loop +.endm + +BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP + +BOOK3E_IDLE book3e_idle BOOK3E_IDLE_LOOP #endif /* CONFIG_PPC64 */ 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/kvm.c b/arch/powerpc/kernel/kvm.c index a61b133c4f99..6782221d49bd 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -756,12 +756,7 @@ static __init void kvm_free_tmp(void) end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK; /* Free the tmp space we don't need */ - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, NULL); } static int __init kvm_guest_init(void) diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index f5725bce9ed2..d92f3871e9cf 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -41,8 +41,6 @@ /* #define LPARCFG_DEBUG */ -static struct proc_dir_entry *proc_ppc64_lparcfg; - /* * Track sum of all purrs across all processors. This is used to further * calculate usage values by different applications @@ -301,6 +299,7 @@ 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) { @@ -688,27 +687,22 @@ static const struct file_operations lparcfg_fops = { static int __init lparcfg_init(void) { - struct proc_dir_entry *ent; umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; /* Allow writing if we have FW_FEATURE_SPLPAR */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) mode |= S_IWUSR; - ent = proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops); - if (!ent) { + if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) { printk(KERN_ERR "Failed to create powerpc/lparcfg\n"); return -EIO; } - - proc_ppc64_lparcfg = ent; return 0; } static void __exit lparcfg_cleanup(void) { - if (proc_ppc64_lparcfg) - remove_proc_entry("lparcfg", proc_ppc64_lparcfg->parent); + remove_proc_subtree("powerpc/lparcfg", NULL); } module_init(lparcfg_init); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 466a2908bb63..611acdf30096 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/cpu.h> +#include <linux/hardirq.h> #include <asm/page.h> #include <asm/current.h> @@ -335,10 +336,13 @@ void default_machine_kexec(struct kimage *image) pr_debug("kexec: Starting switchover sequence.\n"); /* switch to a staticly allocated stack. Based on irq stack code. + * We setup preempt_count to avoid using VMX in memcpy. * XXX: the task struct will likely be invalid once we do the copy! */ kexec_stack.thread_info.task = current_thread_info()->task; kexec_stack.thread_info.flags = 0; + kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET; + kexec_stack.thread_info.cpu = current_thread_info()->cpu; /* We need a static PACA, too; copy this CPU's PACA over and switch to * it. Also poison per_cpu_offset to catch anyone using non-static diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 19e096bd0e73..e469f30e6eeb 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -657,6 +657,17 @@ _GLOBAL(__ucmpdi2) li r3,2 blr +_GLOBAL(__bswapdi2) + rotlwi r9,r4,8 + rotlwi r10,r3,8 + rlwimi r9,r4,24,0,7 + rlwimi r10,r3,24,0,7 + rlwimi r9,r4,24,16,23 + rlwimi r10,r3,24,16,23 + mr r3,r9 + mr r4,r10 + blr + _GLOBAL(abs) srawi r4,r3,31 xor r3,r3,r4 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 5cfa8008693b..6820e45f557b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -234,6 +234,17 @@ _GLOBAL(__flush_dcache_icache) isync blr +_GLOBAL(__bswapdi2) + srdi r8,r3,32 + rlwinm r7,r3,8,0xffffffff + rlwimi r7,r3,24,0,7 + rlwinm r9,r8,8,0xffffffff + rlwimi r7,r3,24,16,23 + rlwimi r9,r8,24,0,7 + rlwimi r9,r8,24,16,23 + sldi r7,r7,32 + or r3,r7,r9 + blr #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) /* 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..7f2273cc3c7d 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> @@ -358,7 +359,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long prot = pgprot_val(protection); /* Write combine is always 0 on non-memory space mappings. On * memory space, if the user didn't pass 1, we check for a @@ -375,9 +375,9 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, /* XXX would be nice to have a way to ask for write-through */ if (write_combine) - return pgprot_noncached_wc(prot); + return pgprot_noncached_wc(protection); else - return pgprot_noncached(prot); + return pgprot_noncached(protection); } /* @@ -657,15 +657,6 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, * ranges. However, some machines (thanks Apple !) tend to split their * space into lots of small contiguous ranges. So we have to coalesce. * - * - We can only cope with all memory ranges having the same offset - * between CPU addresses and PCI addresses. Unfortunately, some bridges - * are setup for a large 1:1 mapping along with a small "window" which - * maps PCI address 0 to some arbitrary high address of the CPU space in - * order to give access to the ISA memory hole. - * The way out of here that I've chosen for now is to always set the - * offset based on the first resource found, then override it if we - * have a different offset and the previous was set by an ISA hole. - * * - Some busses have IO space not starting at 0, which causes trouble with * the way we do our IO resource renumbering. The code somewhat deals with * it for 64 bits but I would expect problems on 32 bits. @@ -680,10 +671,9 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, int rlen; int pna = of_n_addr_cells(dev); int np = pna + 5; - int memno = 0, isa_hole = -1; + int memno = 0; u32 pci_space; unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size; - unsigned long long isa_mb = 0; struct resource *res; printk(KERN_INFO "PCI host bridge %s %s ranges:\n", @@ -777,30 +767,14 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, } /* Handles ISA memory hole space here */ if (pci_addr == 0) { - isa_mb = cpu_addr; - isa_hole = memno; if (primary || isa_mem_base == 0) isa_mem_base = cpu_addr; hose->isa_mem_phys = cpu_addr; hose->isa_mem_size = size; } - /* We get the PCI/Mem offset from the first range or - * the, current one if the offset came from an ISA - * hole. If they don't match, bugger. - */ - if (memno == 0 || - (isa_hole >= 0 && pci_addr != 0 && - hose->pci_mem_offset == isa_mb)) - hose->pci_mem_offset = cpu_addr - pci_addr; - else if (pci_addr != 0 && - hose->pci_mem_offset != cpu_addr - pci_addr) { - printk(KERN_INFO - " \\--> Skipped (offset mismatch) !\n"); - continue; - } - /* Build resource */ + hose->mem_offset[memno] = cpu_addr - pci_addr; res = &hose->mem_resources[memno++]; res->flags = IORESOURCE_MEM; if (pci_space & 0x40000000) @@ -816,20 +790,6 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, res->child = NULL; } } - - /* If there's an ISA hole and the pci_mem_offset is -not- matching - * the ISA hole offset, then we need to remove the ISA hole from - * the resource list for that brige - */ - if (isa_hole >= 0 && hose->pci_mem_offset != isa_mb) { - unsigned int next = isa_hole + 1; - printk(KERN_INFO " Removing ISA hole at 0x%016llx\n", isa_mb); - if (next < memno) - memmove(&hose->mem_resources[isa_hole], - &hose->mem_resources[next], - sizeof(struct resource) * (memno - next)); - hose->mem_resources[--memno].flags = 0; - } } /* Decide whether to display the domain number in /proc */ @@ -844,6 +804,14 @@ int pci_proc_domain(struct pci_bus *bus) return 1; } +int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) +{ + if (ppc_md.pcibios_root_bridge_prepare) + return ppc_md.pcibios_root_bridge_prepare(bridge); + + return 0; +} + /* This header fixup will do the resource fixup for all devices as they are * probed, but not for bridge ranges */ @@ -907,6 +875,7 @@ static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus, struct pci_controller *hose = pci_bus_to_host(bus); struct pci_dev *dev = bus->self; resource_size_t offset; + struct pci_bus_region region; u16 command; int i; @@ -916,10 +885,10 @@ static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus, /* Job is a bit different between memory and IO */ if (res->flags & IORESOURCE_MEM) { - /* If the BAR is non-0 (res != pci_mem_offset) then it's probably been - * initialized by somebody - */ - if (res->start != hose->pci_mem_offset) + pcibios_resource_to_bus(dev, ®ion, res); + + /* If the BAR is non-0 then it's probably been initialized */ + if (region.start != 0) return 0; /* The BAR is 0, let's check if memory decoding is enabled on @@ -931,11 +900,11 @@ static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus, /* Memory decoding is enabled and the BAR is 0. If any of the bridge * resources covers that starting address (0 then it's good enough for - * us for memory + * us for memory space) */ for (i = 0; i < 3; i++) { if ((hose->mem_resources[i].flags & IORESOURCE_MEM) && - hose->mem_resources[i].start == hose->pci_mem_offset) + hose->mem_resources[i].start == hose->mem_offset[i]) return 0; } @@ -1023,6 +992,27 @@ 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 +1027,7 @@ 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); } } @@ -1367,10 +1341,9 @@ static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus) no_io: /* Check for memory */ - offset = hose->pci_mem_offset; - pr_debug("hose mem offset: %016llx\n", (unsigned long long)offset); for (i = 0; i < 3; i++) { pres = &hose->mem_resources[i]; + offset = hose->mem_offset[i]; if (!(pres->flags & IORESOURCE_MEM)) continue; pr_debug("hose mem res: %pR\n", pres); @@ -1494,6 +1467,10 @@ 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); } @@ -1506,6 +1483,7 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, struct list_head *resources) { struct resource *res; + resource_size_t offset; int i; /* Hookup PHB IO resource */ @@ -1515,49 +1493,38 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, printk(KERN_WARNING "PCI: I/O resource not set for host" " bridge %s (domain %d)\n", hose->dn->full_name, hose->global_number); -#ifdef CONFIG_PPC32 - /* Workaround for lack of IO resource only on 32-bit */ - res->start = (unsigned long)hose->io_base_virt - isa_io_base; - res->end = res->start + IO_SPACE_LIMIT; - res->flags = IORESOURCE_IO; -#endif /* CONFIG_PPC32 */ - } + } else { + offset = pcibios_io_space_offset(hose); - pr_debug("PCI: PHB IO resource = %016llx-%016llx [%lx]\n", - (unsigned long long)res->start, - (unsigned long long)res->end, - (unsigned long)res->flags); - pci_add_resource_offset(resources, res, pcibios_io_space_offset(hose)); + pr_debug("PCI: PHB IO resource = %08llx-%08llx [%lx] off 0x%08llx\n", + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned long)res->flags, + (unsigned long long)offset); + pci_add_resource_offset(resources, res, offset); + } /* Hookup PHB Memory resources */ for (i = 0; i < 3; ++i) { res = &hose->mem_resources[i]; if (!res->flags) { - if (i > 0) - continue; - printk(KERN_ERR "PCI: Memory resource 0 not set for " - "host bridge %s (domain %d)\n", - hose->dn->full_name, hose->global_number); -#ifdef CONFIG_PPC32 - /* Workaround for lack of MEM resource only on 32-bit */ - res->start = hose->pci_mem_offset; - res->end = (resource_size_t)-1LL; - res->flags = IORESOURCE_MEM; -#endif /* CONFIG_PPC32 */ + if (i == 0) + printk(KERN_ERR "PCI: Memory resource 0 not set for " + "host bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); + continue; } + offset = hose->mem_offset[i]; - pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i, + + pr_debug("PCI: PHB MEM resource %d = %08llx-%08llx [%lx] off 0x%08llx\n", i, (unsigned long long)res->start, (unsigned long long)res->end, - (unsigned long)res->flags); - pci_add_resource_offset(resources, res, hose->pci_mem_offset); - } - - pr_debug("PCI: PHB MEM offset = %016llx\n", - (unsigned long long)hose->pci_mem_offset); - pr_debug("PCI: PHB IO offset = %08lx\n", - (unsigned long)hose->io_base_virt - _IO_BASE); + (unsigned long)res->flags, + (unsigned long long)offset); + pci_add_resource_offset(resources, res, offset); + } } /* @@ -1725,3 +1692,15 @@ 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/pci_32.c b/arch/powerpc/kernel/pci_32.c index e37c2152acf4..432459c817fa 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -295,7 +295,7 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) case IOBASE_BRIDGE_NUMBER: return (long)hose->first_busno; case IOBASE_MEMORY: - return (long)hose->pci_mem_offset; + return (long)hose->mem_offset[0]; case IOBASE_IO: return (long)hose->io_base_phys; case IOBASE_ISA_IO: diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 51a133a78a09..2e8629654ca8 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -246,7 +246,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, case IOBASE_BRIDGE_NUMBER: return (long)hose->first_busno; case IOBASE_MEMORY: - return (long)hose->pci_mem_offset; + return (long)hose->mem_offset[0]; case IOBASE_IO: return (long)hose->io_base_phys; case IOBASE_ISA_IO: @@ -266,3 +266,13 @@ int pcibus_to_node(struct pci_bus *bus) } EXPORT_SYMBOL(pcibus_to_node); #endif + +static void quirk_radeon_32bit_msi(struct pci_dev *dev) +{ + struct pci_dn *pdn = pci_get_pdn(dev); + + if (pdn) + pdn->force_32bit_msi = 1; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi); diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index e7af165f8b9d..df038442548a 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -32,6 +32,14 @@ #include <asm/ppc-pci.h> #include <asm/firmware.h> +struct pci_dn *pci_get_pdn(struct pci_dev *pdev) +{ + struct device_node *dn = pci_device_to_OF_node(pdev); + if (!dn) + return NULL; + return PCI_DN(dn); +} + /* * Traverse_func that inits the PCI fields of the device node. * NOTE: this *must* be done before read/write config to the device. diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 78b8766fd79e..c29666586998 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -143,7 +143,8 @@ EXPORT_SYMBOL(__lshrdi3); int __ucmpdi2(unsigned long long, unsigned long long); EXPORT_SYMBOL(__ucmpdi2); #endif - +long long __bswapdi2(long long); +EXPORT_SYMBOL(__bswapdi2); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index f19d0bdc3241..feb8580fdc84 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -32,8 +32,6 @@ static loff_t page_map_seek( struct file *file, loff_t off, int whence) { loff_t new; - struct proc_dir_entry *dp = PDE(file_inode(file)); - switch(whence) { case 0: new = off; @@ -42,12 +40,12 @@ static loff_t page_map_seek( struct file *file, loff_t off, int whence) new = file->f_pos + off; break; case 2: - new = dp->size + off; + new = PAGE_SIZE + off; break; default: return -EINVAL; } - if ( new < 0 || new > dp->size ) + if ( new < 0 || new > PAGE_SIZE ) return -EINVAL; return (file->f_pos = new); } @@ -55,19 +53,18 @@ static loff_t page_map_seek( struct file *file, loff_t off, int whence) static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - return simple_read_from_buffer(buf, nbytes, ppos, dp->data, dp->size); + return simple_read_from_buffer(buf, nbytes, ppos, + PDE_DATA(file_inode(file)), PAGE_SIZE); } static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - - if ((vma->vm_end - vma->vm_start) > dp->size) + if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) return -EINVAL; - remap_pfn_range(vma, vma->vm_start, __pa(dp->data) >> PAGE_SHIFT, - dp->size, vma->vm_page_prot); + remap_pfn_range(vma, vma->vm_start, + __pa(PDE_DATA(file_inode(file))) >> PAGE_SHIFT, + PAGE_SIZE, vma->vm_page_prot); return 0; } @@ -86,7 +83,7 @@ static int __init proc_ppc64_init(void) &page_map_fops, vdso_data); if (!pde) return 1; - pde->size = PAGE_SIZE; + proc_set_size(pde, PAGE_SIZE); return 0; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545fdde1..a902723fdc69 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -339,6 +339,13 @@ static void set_debug_reg_defaults(struct thread_struct *thread) static void prime_debug_regs(struct thread_struct *thread) { + /* + * We could have inherited MSR_DE from userspace, since + * it doesn't get cleared on exception entry. Make sure + * MSR_DE is clear before we enable any debug events. + */ + mtmsr(mfmsr() & ~MSR_DE); + mtspr(SPRN_IAC1, thread->iac1); mtspr(SPRN_IAC2, thread->iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 @@ -555,10 +562,12 @@ 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; @@ -829,6 +838,8 @@ void show_regs(struct pt_regs * regs) { int i, trap; + show_regs_print_info(KERN_DEFAULT); + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); printk("REGS: %p TRAP: %04lx %s (%s)\n", @@ -848,12 +859,6 @@ void show_regs(struct pt_regs * regs) #else printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); #endif - printk("TASK = %p[%d] '%s' THREAD: %p", - current, task_pid_nr(current), current->comm, task_thread_info(current)); - -#ifdef CONFIG_SMP - printk(" CPU: %d", raw_smp_processor_id()); -#endif /* CONFIG_SMP */ for (i = 0; i < 32; i++) { if ((i % REGS_PER_LINE) == 0) @@ -910,10 +915,6 @@ 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; } @@ -977,6 +978,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, * do some house keeping and then return from the fork or clone * system call, using the stack frame created above. */ + ((unsigned long *)sp)[0] = 0; sp -= sizeof(struct pt_regs); kregs = (struct pt_regs *) sp; sp -= STACK_FRAME_OVERHEAD; @@ -984,6 +986,10 @@ 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; @@ -1360,12 +1366,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) } while (count++ < kstack_depth_to_print); } -void dump_stack(void) -{ - show_stack(current, NULL); -} -EXPORT_SYMBOL(dump_stack); - #ifdef CONFIG_PPC64 /* Called with hard IRQs off */ void __ppc64_runlatch_on(void) 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..98c2fc198712 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -32,6 +32,7 @@ #include <trace/syscall.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -180,9 +181,10 @@ 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 +194,7 @@ 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 +218,23 @@ 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 +1434,7 @@ 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 +1566,9 @@ 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 +1645,8 @@ 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 */ @@ -1778,6 +1789,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + user_exit(); + secure_computing_strict(regs->gpr[0]); if (test_thread_flag(TIF_SYSCALL_TRACE) && @@ -1822,4 +1835,6 @@ void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + user_enter(); } 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.c b/arch/powerpc/kernel/rtas.c index 1fd6e7b2f390..52add6f3e201 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/capability.h> #include <linux/delay.h> +#include <linux/cpu.h> #include <linux/smp.h> #include <linux/completion.h> #include <linux/cpumask.h> @@ -807,6 +808,95 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } +enum rtas_cpu_state { + DOWN, + UP, +}; + +#ifndef CONFIG_SMP +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + if (!cpumask_empty(cpus)) { + cpumask_clear(cpus); + return -EINVAL; + } else + return 0; +} +#else +/* On return cpumask will be altered to indicate CPUs changed. + * CPUs with states changed will be set in the mask, + * CPUs with status unchanged will be unset in the mask. */ +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + int cpu; + int cpuret = 0; + int ret = 0; + + if (cpumask_empty(cpus)) + return 0; + + for_each_cpu(cpu, cpus) { + switch (state) { + case DOWN: + cpuret = cpu_down(cpu); + break; + case UP: + cpuret = cpu_up(cpu); + break; + } + if (cpuret) { + pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", + __func__, + ((state == UP) ? "up" : "down"), + cpu, cpuret); + if (!ret) + ret = cpuret; + if (state == UP) { + /* clear bits for unchanged cpus, return */ + cpumask_shift_right(cpus, cpus, cpu); + cpumask_shift_left(cpus, cpus, cpu); + break; + } else { + /* clear bit for unchanged cpu, continue */ + cpumask_clear_cpu(cpu, cpus); + } + } + } + + return ret; +} +#endif + +int rtas_online_cpus_mask(cpumask_var_t cpus) +{ + int ret; + + ret = rtas_cpu_state_change_mask(UP, cpus); + + if (ret) { + cpumask_var_t tmp_mask; + + if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY)) + return ret; + + /* Use tmp_mask to preserve cpus mask from first failure */ + cpumask_copy(tmp_mask, cpus); + rtas_offline_cpus_mask(tmp_mask); + free_cpumask_var(tmp_mask); + } + + return ret; +} +EXPORT_SYMBOL(rtas_online_cpus_mask); + +int rtas_offline_cpus_mask(cpumask_var_t cpus) +{ + return rtas_cpu_state_change_mask(DOWN, cpus); +} +EXPORT_SYMBOL(rtas_offline_cpus_mask); + int rtas_ibm_suspend_me(struct rtas_args *args) { long state; @@ -814,6 +904,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); + cpumask_var_t offline_mask; + int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -837,11 +929,24 @@ int rtas_ibm_suspend_me(struct rtas_args *args) return 0; } + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); + cpuret = rtas_online_cpus_mask(offline_mask); + if (cpuret) { + pr_err("%s: Could not bring present CPUs online.\n", __func__); + atomic_set(&data.error, cpuret); + goto out; + } + stop_topology_update(); /* Call function on all CPUs. One of us will make the @@ -857,6 +962,14 @@ int rtas_ibm_suspend_me(struct rtas_args *args) start_topology_update(); + /* Take down CPUs not online prior to suspend */ + cpuret = rtas_offline_cpus_mask(offline_mask); + if (cpuret) + pr_warn("%s: Could not restore CPUs to offline state.\n", + __func__); + +out: + free_cpumask_var(offline_mask); return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index c642f0132988..2f3cdb01506d 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 @@ -71,6 +89,7 @@ /* Array sizes */ #define VALIDATE_BUF_SIZE 4096 +#define VALIDATE_MSG_LEN 256 #define RTAS_MSG_MAXLEN 64 /* Quirk - RTAS requires 4k list length and block size */ @@ -102,9 +121,10 @@ static struct kmem_cache *flash_block_cache = NULL; #define FLASH_BLOCK_LIST_VERSION (1UL) -/* Local copy of the flash block list. - * We only allow one open of the flash proc file and create this - * list as we go. The rtas_firmware_flash_list varable will be +/* + * Local copy of the flash block list. + * + * The rtas_firmware_flash_list varable will be * set once the data is fully read. * * For convenience as we build the list we use virtual addrs, @@ -125,23 +145,23 @@ struct rtas_update_flash_t struct rtas_manage_flash_t { int status; /* Returned status */ - unsigned int op; /* Reject or commit image */ }; /* Status int must be first member of struct */ struct rtas_validate_flash_t { int status; /* Returned status */ - char buf[VALIDATE_BUF_SIZE]; /* Candidate image buffer */ + char *buf; /* Candidate image buffer */ unsigned int buf_size; /* Size of image buf */ unsigned int update_results; /* Update results token */ }; -static DEFINE_SPINLOCK(flash_file_open_lock); -static struct proc_dir_entry *firmware_flash_pde; -static struct proc_dir_entry *firmware_update_pde; -static struct proc_dir_entry *validate_pde; -static struct proc_dir_entry *manage_pde; +static struct rtas_update_flash_t rtas_update_flash_data; +static struct rtas_manage_flash_t rtas_manage_flash_data; +static struct rtas_validate_flash_t rtas_validate_flash_data; +static DEFINE_MUTEX(rtas_update_flash_mutex); +static DEFINE_MUTEX(rtas_manage_flash_mutex); +static DEFINE_MUTEX(rtas_validate_flash_mutex); /* Do simple sanity checks on the flash image. */ static int flash_list_valid(struct flash_block_list *flist) @@ -191,10 +211,10 @@ static void free_flash_list(struct flash_block_list *f) static int rtas_flash_release(struct inode *inode, struct file *file) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_update_flash_t *uf; - - uf = (struct rtas_update_flash_t *) dp->data; + struct rtas_update_flash_t *const uf = &rtas_update_flash_data; + + mutex_lock(&rtas_update_flash_mutex); + if (uf->flist) { /* File was opened in write mode for a new flash attempt */ /* Clear saved list */ @@ -214,13 +234,14 @@ static int rtas_flash_release(struct inode *inode, struct file *file) uf->flist = NULL; } - atomic_dec(&dp->count); + mutex_unlock(&rtas_update_flash_mutex); return 0; } -static void get_flash_status_msg(int status, char *buf) +static size_t get_flash_status_msg(int status, char *buf) { - char *msg; + const char *msg; + size_t len; switch (status) { case FLASH_AUTH: @@ -242,36 +263,47 @@ static void get_flash_status_msg(int status, char *buf) msg = "ready: firmware image ready for flash on reboot\n"; break; default: - sprintf(buf, "error: unexpected status value %d\n", status); - return; + return sprintf(buf, "error: unexpected status value %d\n", + status); } - strcpy(buf, msg); + len = strlen(msg); + memcpy(buf, msg, len + 1); + return len; } /* Reading the proc file will show status (not the firmware contents) */ -static ssize_t rtas_flash_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +static ssize_t rtas_flash_read_msg(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_update_flash_t *uf; + struct rtas_update_flash_t *const uf = &rtas_update_flash_data; char msg[RTAS_MSG_MAXLEN]; + size_t len; + int status; - uf = dp->data; - - if (!strcmp(dp->name, FIRMWARE_FLASH_NAME)) { - get_flash_status_msg(uf->status, msg); - } else { /* FIRMWARE_UPDATE_NAME */ - sprintf(msg, "%d\n", uf->status); - } + mutex_lock(&rtas_update_flash_mutex); + status = uf->status; + mutex_unlock(&rtas_update_flash_mutex); - return simple_read_from_buffer(buf, count, ppos, msg, strlen(msg)); + /* Read as text message */ + len = get_flash_status_msg(status, msg); + return simple_read_from_buffer(buf, count, ppos, msg, len); } -/* constructor for flash_block_cache */ -void rtas_block_ctor(void *ptr) +static ssize_t rtas_flash_read_num(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - memset(ptr, 0, RTAS_BLK_SIZE); + struct rtas_update_flash_t *const uf = &rtas_update_flash_data; + char msg[RTAS_MSG_MAXLEN]; + int status; + + mutex_lock(&rtas_update_flash_mutex); + status = uf->status; + mutex_unlock(&rtas_update_flash_mutex); + + /* Read as number */ + sprintf(msg, "%d\n", status); + return simple_read_from_buffer(buf, count, ppos, msg, strlen(msg)); } /* We could be much more efficient here. But to keep this function @@ -282,25 +314,24 @@ void rtas_block_ctor(void *ptr) static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, size_t count, loff_t *off) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_update_flash_t *uf; + struct rtas_update_flash_t *const uf = &rtas_update_flash_data; char *p; - int next_free; + int next_free, rc; struct flash_block_list *fl; - uf = (struct rtas_update_flash_t *) dp->data; + mutex_lock(&rtas_update_flash_mutex); if (uf->status == FLASH_AUTH || count == 0) - return count; /* discard data */ + goto out; /* discard data */ /* In the case that the image is not ready for flashing, the memory * allocated for the block list will be freed upon the release of the * proc file */ if (uf->flist == NULL) { - uf->flist = kmem_cache_alloc(flash_block_cache, GFP_KERNEL); + uf->flist = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!uf->flist) - return -ENOMEM; + goto nomem; } fl = uf->flist; @@ -309,63 +340,48 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, next_free = fl->num_blocks; if (next_free == FLASH_BLOCKS_PER_NODE) { /* Need to allocate another block_list */ - fl->next = kmem_cache_alloc(flash_block_cache, GFP_KERNEL); + fl->next = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!fl->next) - return -ENOMEM; + goto nomem; fl = fl->next; next_free = 0; } if (count > RTAS_BLK_SIZE) count = RTAS_BLK_SIZE; - p = kmem_cache_alloc(flash_block_cache, GFP_KERNEL); + p = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!p) - return -ENOMEM; + goto nomem; if(copy_from_user(p, buffer, count)) { kmem_cache_free(flash_block_cache, p); - return -EFAULT; + rc = -EFAULT; + goto error; } fl->blocks[next_free].data = p; fl->blocks[next_free].length = count; fl->num_blocks++; - +out: + mutex_unlock(&rtas_update_flash_mutex); return count; -} -static int rtas_excl_open(struct inode *inode, struct file *file) -{ - struct proc_dir_entry *dp = PDE(inode); - - /* Enforce exclusive open with use count of PDE */ - spin_lock(&flash_file_open_lock); - if (atomic_read(&dp->count) > 2) { - spin_unlock(&flash_file_open_lock); - return -EBUSY; - } - - atomic_inc(&dp->count); - spin_unlock(&flash_file_open_lock); - - return 0; -} - -static int rtas_excl_release(struct inode *inode, struct file *file) -{ - struct proc_dir_entry *dp = PDE(inode); - - atomic_dec(&dp->count); - - return 0; +nomem: + rc = -ENOMEM; +error: + mutex_unlock(&rtas_update_flash_mutex); + return rc; } -static void manage_flash(struct rtas_manage_flash_t *args_buf) +/* + * Flash management routines. + */ +static void manage_flash(struct rtas_manage_flash_t *args_buf, unsigned int op) { s32 rc; do { - rc = rtas_call(rtas_token("ibm,manage-flash-image"), 1, - 1, NULL, args_buf->op); + rc = rtas_call(rtas_token("ibm,manage-flash-image"), 1, 1, + NULL, op); } while (rtas_busy_delay(rc)); args_buf->status = rc; @@ -374,55 +390,62 @@ static void manage_flash(struct rtas_manage_flash_t *args_buf) static ssize_t manage_flash_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_manage_flash_t *args_buf; + struct rtas_manage_flash_t *const args_buf = &rtas_manage_flash_data; char msg[RTAS_MSG_MAXLEN]; - int msglen; - - args_buf = dp->data; - if (args_buf == NULL) - return 0; + int msglen, status; - msglen = sprintf(msg, "%d\n", args_buf->status); + mutex_lock(&rtas_manage_flash_mutex); + status = args_buf->status; + mutex_unlock(&rtas_manage_flash_mutex); + msglen = sprintf(msg, "%d\n", status); return simple_read_from_buffer(buf, count, ppos, msg, msglen); } static ssize_t manage_flash_write(struct file *file, const char __user *buf, size_t count, loff_t *off) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_manage_flash_t *args_buf; - const char reject_str[] = "0"; - const char commit_str[] = "1"; + struct rtas_manage_flash_t *const args_buf = &rtas_manage_flash_data; + static const char reject_str[] = "0"; + static const char commit_str[] = "1"; char stkbuf[10]; - int op; + int op, rc; + + mutex_lock(&rtas_manage_flash_mutex); - args_buf = (struct rtas_manage_flash_t *) dp->data; if ((args_buf->status == MANAGE_AUTH) || (count == 0)) - return count; + goto out; op = -1; if (buf) { if (count > 9) count = 9; - if (copy_from_user (stkbuf, buf, count)) { - return -EFAULT; - } + rc = -EFAULT; + if (copy_from_user (stkbuf, buf, count)) + goto error; if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0) op = RTAS_REJECT_TMP_IMG; else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0) op = RTAS_COMMIT_TMP_IMG; } - if (op == -1) /* buf is empty, or contains invalid string */ - return -EINVAL; - - args_buf->op = op; - manage_flash(args_buf); + if (op == -1) { /* buf is empty, or contains invalid string */ + rc = -EINVAL; + goto error; + } + manage_flash(args_buf, op); +out: + mutex_unlock(&rtas_manage_flash_mutex); return count; + +error: + mutex_unlock(&rtas_manage_flash_mutex); + return rc; } +/* + * Validation routines. + */ static void validate_flash(struct rtas_validate_flash_t *args_buf) { int token = rtas_token("ibm,validate-flash-image"); @@ -444,7 +467,7 @@ static void validate_flash(struct rtas_validate_flash_t *args_buf) } static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, - char *msg) + char *msg, int msglen) { int n; @@ -452,7 +475,8 @@ static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, n = sprintf(msg, "%d\n", args_buf->update_results); if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) || (args_buf->update_results == VALIDATE_TMP_UPDATE)) - n += sprintf(msg + n, "%s\n", args_buf->buf); + n += snprintf(msg + n, msglen - n, "%s\n", + args_buf->buf); } else { n = sprintf(msg, "%d\n", args_buf->status); } @@ -462,14 +486,14 @@ static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, static ssize_t validate_flash_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_validate_flash_t *args_buf; - char msg[RTAS_MSG_MAXLEN]; + struct rtas_validate_flash_t *const args_buf = + &rtas_validate_flash_data; + char msg[VALIDATE_MSG_LEN]; int msglen; - args_buf = dp->data; - - msglen = get_validate_flash_msg(args_buf, msg); + mutex_lock(&rtas_validate_flash_mutex); + msglen = get_validate_flash_msg(args_buf, msg, VALIDATE_MSG_LEN); + mutex_unlock(&rtas_validate_flash_mutex); return simple_read_from_buffer(buf, count, ppos, msg, msglen); } @@ -477,24 +501,18 @@ static ssize_t validate_flash_read(struct file *file, char __user *buf, static ssize_t validate_flash_write(struct file *file, const char __user *buf, size_t count, loff_t *off) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_validate_flash_t *args_buf; + struct rtas_validate_flash_t *const args_buf = + &rtas_validate_flash_data; int rc; - args_buf = (struct rtas_validate_flash_t *) dp->data; - - if (dp->data == NULL) { - dp->data = kmalloc(sizeof(struct rtas_validate_flash_t), - GFP_KERNEL); - if (dp->data == NULL) - return -ENOMEM; - } + mutex_lock(&rtas_validate_flash_mutex); /* We are only interested in the first 4K of the * candidate image */ if ((*off >= VALIDATE_BUF_SIZE) || (args_buf->status == VALIDATE_AUTH)) { *off += count; + mutex_unlock(&rtas_validate_flash_mutex); return count; } @@ -517,31 +535,29 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf, *off += count; rc = count; done: - if (rc < 0) { - kfree(dp->data); - dp->data = NULL; - } + mutex_unlock(&rtas_validate_flash_mutex); return rc; } static int validate_flash_release(struct inode *inode, struct file *file) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - struct rtas_validate_flash_t *args_buf; + struct rtas_validate_flash_t *const args_buf = + &rtas_validate_flash_data; - args_buf = (struct rtas_validate_flash_t *) dp->data; + mutex_lock(&rtas_validate_flash_mutex); if (args_buf->status == VALIDATE_READY) { args_buf->buf_size = VALIDATE_BUF_SIZE; validate_flash(args_buf); } - /* The matching atomic_inc was in rtas_excl_open() */ - atomic_dec(&dp->count); - + mutex_unlock(&rtas_validate_flash_mutex); return 0; } +/* + * On-reboot flash update applicator. + */ static void rtas_flash_firmware(int reboot_type) { unsigned long image_size; @@ -634,75 +650,57 @@ static void rtas_flash_firmware(int reboot_type) spin_unlock(&rtas_data_buf_lock); } -static void remove_flash_pde(struct proc_dir_entry *dp) -{ - if (dp) { - kfree(dp->data); - remove_proc_entry(dp->name, dp->parent); - } -} - -static int initialize_flash_pde_data(const char *rtas_call_name, - size_t buf_size, - struct proc_dir_entry *dp) -{ +/* + * Manifest of proc files to create + */ +struct rtas_flash_file { + const char *filename; + const char *rtas_call_name; int *status; - int token; - - dp->data = kzalloc(buf_size, GFP_KERNEL); - if (dp->data == NULL) - return -ENOMEM; - - /* - * This code assumes that the status int is the first member of the - * struct - */ - status = (int *) dp->data; - token = rtas_token(rtas_call_name); - if (token == RTAS_UNKNOWN_SERVICE) - *status = FLASH_AUTH; - else - *status = FLASH_NO_OP; - - return 0; -} - -static struct proc_dir_entry *create_flash_pde(const char *filename, - const struct file_operations *fops) -{ - return proc_create(filename, S_IRUSR | S_IWUSR, NULL, fops); -} - -static const struct file_operations rtas_flash_operations = { - .owner = THIS_MODULE, - .read = rtas_flash_read, - .write = rtas_flash_write, - .open = rtas_excl_open, - .release = rtas_flash_release, - .llseek = default_llseek, -}; - -static const struct file_operations manage_flash_operations = { - .owner = THIS_MODULE, - .read = manage_flash_read, - .write = manage_flash_write, - .open = rtas_excl_open, - .release = rtas_excl_release, - .llseek = default_llseek, + const struct file_operations fops; }; -static const struct file_operations validate_flash_operations = { - .owner = THIS_MODULE, - .read = validate_flash_read, - .write = validate_flash_write, - .open = rtas_excl_open, - .release = validate_flash_release, - .llseek = default_llseek, +static const struct rtas_flash_file rtas_flash_files[] = { + { + .filename = "powerpc/rtas/" FIRMWARE_FLASH_NAME, + .rtas_call_name = "ibm,update-flash-64-and-reboot", + .status = &rtas_update_flash_data.status, + .fops.read = rtas_flash_read_msg, + .fops.write = rtas_flash_write, + .fops.release = rtas_flash_release, + .fops.llseek = default_llseek, + }, + { + .filename = "powerpc/rtas/" FIRMWARE_UPDATE_NAME, + .rtas_call_name = "ibm,update-flash-64-and-reboot", + .status = &rtas_update_flash_data.status, + .fops.read = rtas_flash_read_num, + .fops.write = rtas_flash_write, + .fops.release = rtas_flash_release, + .fops.llseek = default_llseek, + }, + { + .filename = "powerpc/rtas/" VALIDATE_FLASH_NAME, + .rtas_call_name = "ibm,validate-flash-image", + .status = &rtas_validate_flash_data.status, + .fops.read = validate_flash_read, + .fops.write = validate_flash_write, + .fops.release = validate_flash_release, + .fops.llseek = default_llseek, + }, + { + .filename = "powerpc/rtas/" MANAGE_FLASH_NAME, + .rtas_call_name = "ibm,manage-flash-image", + .status = &rtas_manage_flash_data.status, + .fops.read = manage_flash_read, + .fops.write = manage_flash_write, + .fops.llseek = default_llseek, + } }; static int __init rtas_flash_init(void) { - int rc; + int i; if (rtas_token("ibm,update-flash-64-and-reboot") == RTAS_UNKNOWN_SERVICE) { @@ -710,93 +708,70 @@ static int __init rtas_flash_init(void) return 1; } - firmware_flash_pde = create_flash_pde("powerpc/rtas/" - FIRMWARE_FLASH_NAME, - &rtas_flash_operations); - if (firmware_flash_pde == NULL) { - rc = -ENOMEM; - goto cleanup; - } + rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL); + if (!rtas_validate_flash_data.buf) + return -ENOMEM; - rc = initialize_flash_pde_data("ibm,update-flash-64-and-reboot", - sizeof(struct rtas_update_flash_t), - firmware_flash_pde); - if (rc != 0) - goto cleanup; - - firmware_update_pde = create_flash_pde("powerpc/rtas/" - FIRMWARE_UPDATE_NAME, - &rtas_flash_operations); - if (firmware_update_pde == NULL) { - rc = -ENOMEM; - goto cleanup; + flash_block_cache = kmem_cache_create("rtas_flash_cache", + RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, + NULL); + if (!flash_block_cache) { + printk(KERN_ERR "%s: failed to create block cache\n", + __func__); + goto enomem_buf; } - rc = initialize_flash_pde_data("ibm,update-flash-64-and-reboot", - sizeof(struct rtas_update_flash_t), - firmware_update_pde); - if (rc != 0) - goto cleanup; - - validate_pde = create_flash_pde("powerpc/rtas/" VALIDATE_FLASH_NAME, - &validate_flash_operations); - if (validate_pde == NULL) { - rc = -ENOMEM; - goto cleanup; - } + for (i = 0; i < ARRAY_SIZE(rtas_flash_files); i++) { + const struct rtas_flash_file *f = &rtas_flash_files[i]; + int token; - rc = initialize_flash_pde_data("ibm,validate-flash-image", - sizeof(struct rtas_validate_flash_t), - validate_pde); - if (rc != 0) - goto cleanup; - - manage_pde = create_flash_pde("powerpc/rtas/" MANAGE_FLASH_NAME, - &manage_flash_operations); - if (manage_pde == NULL) { - rc = -ENOMEM; - goto cleanup; - } + if (!proc_create(f->filename, S_IRUSR | S_IWUSR, NULL, &f->fops)) + goto enomem; - rc = initialize_flash_pde_data("ibm,manage-flash-image", - sizeof(struct rtas_manage_flash_t), - manage_pde); - if (rc != 0) - goto cleanup; + /* + * This code assumes that the status int is the first member of the + * struct + */ + token = rtas_token(f->rtas_call_name); + if (token == RTAS_UNKNOWN_SERVICE) + *f->status = FLASH_AUTH; + else + *f->status = FLASH_NO_OP; + } rtas_flash_term_hook = rtas_flash_firmware; - - flash_block_cache = kmem_cache_create("rtas_flash_cache", - RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, - rtas_block_ctor); - if (!flash_block_cache) { - printk(KERN_ERR "%s: failed to create block cache\n", - __func__); - rc = -ENOMEM; - goto cleanup; - } return 0; -cleanup: - remove_flash_pde(firmware_flash_pde); - remove_flash_pde(firmware_update_pde); - remove_flash_pde(validate_pde); - remove_flash_pde(manage_pde); +enomem: + while (--i >= 0) { + const struct rtas_flash_file *f = &rtas_flash_files[i]; + remove_proc_entry(f->filename, NULL); + } - return rc; + kmem_cache_destroy(flash_block_cache); +enomem_buf: + kfree(rtas_validate_flash_data.buf); + return -ENOMEM; } static void __exit rtas_flash_cleanup(void) { + int i; + rtas_flash_term_hook = NULL; - if (flash_block_cache) - kmem_cache_destroy(flash_block_cache); + if (rtas_firmware_flash_list) { + free_flash_list(rtas_firmware_flash_list); + rtas_firmware_flash_list = NULL; + } + + for (i = 0; i < ARRAY_SIZE(rtas_flash_files); i++) { + const struct rtas_flash_file *f = &rtas_flash_files[i]; + remove_proc_entry(f->filename, NULL); + } - remove_flash_pde(firmware_flash_pde); - remove_flash_pde(firmware_update_pde); - remove_flash_pde(validate_pde); - remove_flash_pde(manage_pde); + kmem_cache_destroy(flash_block_cache); + kfree(rtas_validate_flash_data.buf); } module_init(rtas_flash_init); 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/setup_64.c b/arch/powerpc/kernel/setup_64.c index 75fbaceb5c87..e379d3fd1694 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -583,7 +583,9 @@ void __init setup_arch(char **cmdline_p) init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; init_mm.brk = klimit; - +#ifdef CONFIG_PPC_64K_PAGES + init_mm.context.pte_frag = NULL; +#endif irqstack_early_init(); exc_lvl_early_init(); emergency_stack_init(); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index cf12eae02de5..457e97aa2945 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -13,10 +13,12 @@ #include <linux/signal.h> #include <linux/uprobes.h> #include <linux/key.h> +#include <linux/context_tracking.h> #include <asm/hw_breakpoint.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/debug.h> +#include <asm/tm.h> #include "signal.h" @@ -24,18 +26,18 @@ * through debug.exception-trace sysctl. */ -int show_unhandled_signals = 0; +int show_unhandled_signals = 1; /* * Allocate space for the signal frame */ -void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, +void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp, size_t frame_size, int is_32) { unsigned long oldsp, newsp; /* Default to using normal stack */ - oldsp = get_clean_sp(regs, is_32); + oldsp = get_clean_sp(sp, is_32); /* Check for alt stack */ if ((ka->sa.sa_flags & SA_ONSTACK) && @@ -159,6 +161,8 @@ static int do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + user_exit(); + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -169,4 +173,41 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); } + + user_enter(); +} + +unsigned long get_tm_stackpointer(struct pt_regs *regs) +{ + /* When in an active transaction that takes a signal, we need to be + * careful with the stack. It's possible that the stack has moved back + * up after the tbegin. The obvious case here is when the tbegin is + * called inside a function that returns before a tend. In this case, + * the stack is part of the checkpointed transactional memory state. + * If we write over this non transactionally or in suspend, we are in + * trouble because if we get a tm abort, the program counter and stack + * pointer will be back at the tbegin but our in memory stack won't be + * valid anymore. + * + * To avoid this, when taking a signal in an active transaction, we + * need to use the stack pointer from the checkpointed state, rather + * than the speculated state. This ensures that the signal context + * (written tm suspended) will be written below the stack required for + * the rollback. The transaction is aborted becuase of the treclaim, + * so any memory written between the tbegin and the signal will be + * rolled back anyway. + * + * For signals taken in non-TM or suspended mode, we use the + * normal/non-checkpointed stack pointer. + */ + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(regs->msr)) { + tm_enable(); + tm_reclaim(¤t->thread, regs->msr, TM_CAUSE_SIGNAL); + if (MSR_TM_TRANSACTIONAL(regs->msr)) + return current->thread.ckpt_regs.gpr[1]; + } +#endif + return regs->gpr[1]; } diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index ec84c901ceab..c69b9aeb9f23 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -12,7 +12,7 @@ extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); -extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, +extern void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp, size_t frame_size, int is_32); extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e245b4..201385c3a1ae 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -503,12 +503,6 @@ static int save_tm_user_regs(struct pt_regs *regs, { unsigned long msr = regs->msr; - /* tm_reclaim rolls back all reg states, updating thread.ckpt_regs, - * thread.transact_fpr[], thread.transact_vr[], etc. - */ - tm_enable(); - tm_reclaim(¤t->thread, msr, TM_CAUSE_SIGNAL); - /* Make sure floating point registers are stored in regs */ flush_fp_to_thread(current); @@ -866,10 +860,12 @@ 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; } @@ -963,7 +959,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ - rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf), 1); + rt_sf = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*rt_sf), 1); addr = rt_sf; if (unlikely(rt_sf == NULL)) goto badframe; @@ -1401,7 +1397,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, unsigned long tramp; /* Set up Signal Frame */ - frame = get_sigframe(ka, regs, sizeof(*frame), 1); + frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 1); if (unlikely(frame == NULL)) goto badframe; sc = (struct sigcontext __user *) &frame->sctx; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f8543cb57..345947367ec0 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -154,11 +154,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, * As above, but Transactional Memory is in use, so deliver sigcontexts * containing checkpointed and transactional register states. * - * To do this, we treclaim to gather both sets of registers and set up the - * 'normal' sigcontext registers with rolled-back register values such that a - * simple signal handler sees a correct checkpointed register state. - * If interested, a TM-aware sighandler can examine the transactional registers - * in the 2nd sigcontext to determine the real origin of the signal. + * To do this, we treclaim (done before entering here) to gather both sets of + * registers and set up the 'normal' sigcontext registers with rolled-back + * register values such that a simple signal handler sees a correct + * checkpointed register state. If interested, a TM-aware sighandler can + * examine the transactional registers in the 2nd sigcontext to determine the + * real origin of the signal. */ static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, @@ -184,16 +185,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, BUG_ON(!MSR_TM_ACTIVE(regs->msr)); - /* tm_reclaim rolls back all reg states, saving checkpointed (older) - * GPRs to thread.ckpt_regs and (if used) FPRs to (newer) - * thread.transact_fp and/or VRs to (newer) thread.transact_vr. - * THEN we save out FP/VRs, if necessary, to the checkpointed (older) - * thread.fr[]/vr[]s. The transactional (newer) GPRs are on the - * stack, in *regs. - */ - tm_enable(); - tm_reclaim(¤t->thread, msr, TM_CAUSE_SIGNAL); - flush_fp_to_thread(current); #ifdef CONFIG_ALTIVEC @@ -522,10 +513,12 @@ 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; } @@ -709,7 +702,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, unsigned long newsp = 0; long err = 0; - frame = get_sigframe(ka, regs, sizeof(*frame), 0); + frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 0); if (unlikely(frame == NULL)) goto badframe; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 76bd9da8cb71..ee7ac5e6e28a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -669,7 +669,7 @@ __cpuinit void start_secondary(void *unused) local_irq_enable(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); BUG(); } diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index d0bafc0cdf06..8a285876aef8 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -61,91 +61,6 @@ asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); } -#ifdef CONFIG_SYSVIPC -long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, - u32 fifth) -{ - int version; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - - case SEMTIMEDOP: - if (fifth) - /* sign extend semid */ - return compat_sys_semtimedop((int)first, - compat_ptr(ptr), second, - compat_ptr(fifth)); - /* else fall through for normal semop() */ - case SEMOP: - /* struct sembuf is the same on 32 and 64bit :)) */ - /* sign extend semid */ - return sys_semtimedop((int)first, compat_ptr(ptr), second, - NULL); - case SEMGET: - /* sign extend key, nsems */ - return sys_semget((int)first, (int)second, third); - case SEMCTL: - /* sign extend semid, semnum */ - return compat_sys_semctl((int)first, (int)second, third, - compat_ptr(ptr)); - - case MSGSND: - /* sign extend msqid */ - return compat_sys_msgsnd((int)first, (int)second, third, - compat_ptr(ptr)); - case MSGRCV: - /* sign extend msqid, msgtyp */ - return compat_sys_msgrcv((int)first, second, (int)fifth, - third, version, compat_ptr(ptr)); - case MSGGET: - /* sign extend key */ - return sys_msgget((int)first, second); - case MSGCTL: - /* sign extend msqid */ - return compat_sys_msgctl((int)first, second, compat_ptr(ptr)); - - case SHMAT: - /* sign extend shmid */ - return compat_sys_shmat((int)first, second, third, version, - compat_ptr(ptr)); - case SHMDT: - return sys_shmdt(compat_ptr(ptr)); - case SHMGET: - /* sign extend key_t */ - return sys_shmget((int)first, second, third); - case SHMCTL: - /* sign extend shmid */ - return compat_sys_shmctl((int)first, second, compat_ptr(ptr)); - - default: - return -ENOSYS; - } - - return -ENOSYS; -} -#endif - -/* Note: it is necessary to treat out_fd and in_fd as unsigned ints, - * with the corresponding cast to a signed int to insure that the - * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) - * and the register representation of a signed int (msr in 64-bit mode) is performed. - */ -asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd, - compat_off_t __user *offset, u32 count) -{ - return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); -} - -asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd, - compat_loff_t __user *offset, u32 count) -{ - return sys_sendfile((int)out_fd, (int)in_fd, - (off_t __user *)offset, count); -} - unsigned long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) @@ -195,13 +110,6 @@ asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long h return sys_ftruncate(fd, (high << 32) | low); } -long ppc32_lookup_dcookie(u32 cookie_high, u32 cookie_low, char __user *buf, - size_t len) -{ - return sys_lookup_dcookie((u64)cookie_high << 32 | cookie_low, - buf, len); -} - long ppc32_fadvise64(int fd, u32 unused, u32 offset_high, u32 offset_low, size_t len, int advice) { @@ -209,23 +117,6 @@ long ppc32_fadvise64(int fd, u32 unused, u32 offset_high, u32 offset_low, advice); } -asmlinkage long compat_sys_add_key(const char __user *_type, - const char __user *_description, - const void __user *_payload, - u32 plen, - u32 ringid) -{ - return sys_add_key(_type, _description, _payload, plen, ringid); -} - -asmlinkage long compat_sys_request_key(const char __user *_type, - const char __user *_description, - const char __user *_callout_info, - u32 destringid) -{ - return sys_request_key(_type, _description, _callout_info, destringid); -} - asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, unsigned offset_hi, unsigned offset_lo, unsigned nbytes_hi, unsigned nbytes_lo) @@ -235,11 +126,3 @@ asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, return sys_sync_file_range(fd, offset, nbytes, flags); } - -asmlinkage long compat_sys_fanotify_mark(int fanotify_fd, unsigned int flags, - unsigned mask_hi, unsigned mask_lo, - int dfd, const char __user *pathname) -{ - u64 mask = ((u64)mask_hi << 32) | mask_lo; - return sys_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); -} diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 3ce1f864c2d3..e68a84568b8b 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -180,7 +180,7 @@ SYSFS_PMCSETUP(dscr, SPRN_DSCR); SYSFS_PMCSETUP(pir, SPRN_PIR); static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); -static DEVICE_ATTR(spurr, 0600, show_spurr, NULL); +static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static DEVICE_ATTR(purr, 0600, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); 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/traps.c b/arch/powerpc/kernel/traps.c index 37cc40ef5043..f18c79c324ef 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -35,6 +35,7 @@ #include <linux/kdebug.h> #include <linux/debugfs.h> #include <linux/ratelimit.h> +#include <linux/context_tracking.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -52,6 +53,7 @@ #ifdef CONFIG_PPC64 #include <asm/firmware.h> #include <asm/processor.h> +#include <asm/tm.h> #endif #include <asm/kexec.h> #include <asm/ppc-opcode.h> @@ -667,6 +669,7 @@ int machine_check_generic(struct pt_regs *regs) void machine_check_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); int recover = 0; __get_cpu_var(irq_stat).mce_exceptions++; @@ -683,7 +686,7 @@ void machine_check_exception(struct pt_regs *regs) recover = cur_cpu_spec->machine_check(regs); if (recover > 0) - return; + goto bail; #if defined(CONFIG_8xx) && defined(CONFIG_PCI) /* the qspan pci read routines can cause machine checks -- Cort @@ -693,20 +696,23 @@ void machine_check_exception(struct pt_regs *regs) * -- BenH */ bad_page_fault(regs, regs->dar, SIGBUS); - return; + goto bail; #endif if (debugger_fault_handler(regs)) - return; + goto bail; if (check_io_access(regs)) - return; + goto bail; die("Machine check", regs, SIGBUS); /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) panic("Unrecoverable Machine check"); + +bail: + exception_exit(prev_state); } void SMIException(struct pt_regs *regs) @@ -716,20 +722,29 @@ void SMIException(struct pt_regs *regs) void unknown_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n", regs->nip, regs->msr, regs->trap); _exception(SIGTRAP, regs, 0, 0); + + exception_exit(prev_state); } void instruction_breakpoint_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (debugger_iabr_match(regs)) - return; + goto bail; _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + +bail: + exception_exit(prev_state); } void RunModeException(struct pt_regs *regs) @@ -739,15 +754,20 @@ void RunModeException(struct pt_regs *regs) void __kprobes single_step_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + clear_single_step(regs); if (notify_die(DIE_SSTEP, "single_step", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (debugger_sstep(regs)) - return; + goto bail; _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); + +bail: + exception_exit(prev_state); } /* @@ -913,6 +933,28 @@ static int emulate_isel(struct pt_regs *regs, u32 instword) return 0; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static inline bool tm_abort_check(struct pt_regs *regs, int cause) +{ + /* If we're emulating a load/store in an active transaction, we cannot + * emulate it as the kernel operates in transaction suspended context. + * We need to abort the transaction. This creates a persistent TM + * abort so tell the user what caused it with a new code. + */ + if (MSR_TM_TRANSACTIONAL(regs->msr)) { + tm_enable(); + tm_abort(cause); + return true; + } + return false; +} +#else +static inline bool tm_abort_check(struct pt_regs *regs, int reason) +{ + return false; +} +#endif + static int emulate_instruction(struct pt_regs *regs) { u32 instword; @@ -952,6 +994,9 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate load/store string insn. */ if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) { + if (tm_abort_check(regs, + TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT)) + return -EINVAL; PPC_WARN_EMULATED(string, regs); return emulate_string_inst(regs, instword); } @@ -970,7 +1015,10 @@ static int emulate_instruction(struct pt_regs *regs) #ifdef CONFIG_PPC64 /* Emulate the mfspr rD, DSCR. */ - if (((instword & PPC_INST_MFSPR_DSCR_MASK) == PPC_INST_MFSPR_DSCR) && + if ((((instword & PPC_INST_MFSPR_DSCR_USER_MASK) == + PPC_INST_MFSPR_DSCR_USER) || + ((instword & PPC_INST_MFSPR_DSCR_MASK) == + PPC_INST_MFSPR_DSCR)) && cpu_has_feature(CPU_FTR_DSCR)) { PPC_WARN_EMULATED(mfdscr, regs); rd = (instword >> 21) & 0x1f; @@ -978,7 +1026,10 @@ static int emulate_instruction(struct pt_regs *regs) return 0; } /* Emulate the mtspr DSCR, rD. */ - if (((instword & PPC_INST_MTSPR_DSCR_MASK) == PPC_INST_MTSPR_DSCR) && + if ((((instword & PPC_INST_MTSPR_DSCR_USER_MASK) == + PPC_INST_MTSPR_DSCR_USER) || + ((instword & PPC_INST_MTSPR_DSCR_MASK) == + PPC_INST_MTSPR_DSCR)) && cpu_has_feature(CPU_FTR_DSCR)) { PPC_WARN_EMULATED(mtdscr, regs); rd = (instword >> 21) & 0x1f; @@ -999,6 +1050,7 @@ int is_valid_bugaddr(unsigned long addr) void __kprobes program_check_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); unsigned int reason = get_reason(regs); extern int do_mathemu(struct pt_regs *regs); @@ -1008,26 +1060,26 @@ void __kprobes program_check_exception(struct pt_regs *regs) if (reason & REASON_FP) { /* IEEE FP exception */ parse_fpe(regs); - return; + goto bail; } if (reason & REASON_TRAP) { /* Debugger is first in line to stop recursive faults in * rcu_lock, notify_die, or atomic_notifier_call_chain */ if (debugger_bpt(regs)) - return; + goto bail; /* trap exception */ if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (!(regs->msr & MSR_PR) && /* not user-mode */ report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; - return; + goto bail; } _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); - return; + goto bail; } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (reason & REASON_TM) { @@ -1043,7 +1095,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) if (!user_mode(regs) && report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; - return; + goto bail; } /* If usermode caused this, it's done something illegal and * gets a SIGILL slap on the wrist. We call it an illegal @@ -1053,7 +1105,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) */ if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); - return; + goto bail; } else { printk(KERN_EMERG "Unexpected TM Bad Thing exception " "at %lx (msr 0x%x)\n", regs->nip, reason); @@ -1077,16 +1129,16 @@ void __kprobes program_check_exception(struct pt_regs *regs) switch (do_mathemu(regs)) { case 0: emulate_single_step(regs); - return; + goto bail; case 1: { int code = 0; code = __parse_fpscr(current->thread.fpscr.val); _exception(SIGFPE, regs, code, regs->nip); - return; + goto bail; } case -EFAULT: _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; + goto bail; } /* fall through on any other errors */ #endif /* CONFIG_MATH_EMULATION */ @@ -1097,10 +1149,10 @@ void __kprobes program_check_exception(struct pt_regs *regs) case 0: regs->nip += 4; emulate_single_step(regs); - return; + goto bail; case -EFAULT: _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; + goto bail; } } @@ -1108,16 +1160,23 @@ void __kprobes program_check_exception(struct pt_regs *regs) _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); else _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + +bail: + exception_exit(prev_state); } void alignment_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); int sig, code, fixed = 0; /* We restore the interrupt state now */ if (!arch_irq_disabled_regs(regs)) local_irq_enable(); + if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT)) + goto bail; + /* we don't implement logging of alignment exceptions */ if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS)) fixed = fix_alignment(regs); @@ -1125,7 +1184,7 @@ void alignment_exception(struct pt_regs *regs) if (fixed == 1) { regs->nip += 4; /* skip over emulated instruction */ emulate_single_step(regs); - return; + goto bail; } /* Operand address was bad */ @@ -1140,6 +1199,9 @@ void alignment_exception(struct pt_regs *regs) _exception(sig, regs, code, regs->dar); else bad_page_fault(regs, regs->dar, sig); + +bail: + exception_exit(prev_state); } void StackOverflow(struct pt_regs *regs) @@ -1168,23 +1230,32 @@ void trace_syscall(struct pt_regs *regs) void kernel_fp_unavailable_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + printk(KERN_EMERG "Unrecoverable FP Unavailable Exception " "%lx at %lx\n", regs->trap, regs->nip); die("Unrecoverable FP Unavailable Exception", regs, SIGABRT); + + exception_exit(prev_state); } void altivec_unavailable_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + if (user_mode(regs)) { /* A user program has executed an altivec instruction, but this kernel doesn't support altivec. */ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return; + goto bail; } printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception " "%lx at %lx\n", regs->trap, regs->nip); die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT); + +bail: + exception_exit(prev_state); } void vsx_unavailable_exception(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index f9748498fe58..9d3fdcd66290 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -64,6 +64,9 @@ void __init udbg_early_init(void) udbg_init_usbgecko(); #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) udbg_init_wsp(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS) + /* In memory console */ + udbg_init_memcons(); #elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC) udbg_init_ehv_bc(); #elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) @@ -156,15 +159,13 @@ static struct console udbg_console = { .index = 0, }; -static int early_console_initialized; - /* * Called by setup_system after ppc_md->probe and ppc_md->early_init. * Call it again after setting udbg_putc in ppc_md->setup_arch. */ void __init register_early_udbg_console(void) { - if (early_console_initialized) + if (early_console) return; if (!udbg_putc) @@ -174,7 +175,7 @@ void __init register_early_udbg_console(void) printk(KERN_INFO "early console immortal !\n"); udbg_console.flags &= ~CON_BOOT; } - early_console_initialized = 1; + early_console = &udbg_console; register_console(&udbg_console); } diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index bc77834dbf43..59f419b935f2 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -31,6 +31,16 @@ #define UPROBE_TRAP_NR UINT_MAX /** + * is_trap_insn - check if the instruction is a trap variant + * @insn: instruction to be checked. + * Returns true if @insn is a trap variant. + */ +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return (is_trap(*insn)); +} + +/** * arch_uprobe_analyze_insn * @mm: the probed address space. * @arch_uprobe: the probepoint information. @@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, if (addr & 0x03) return -EINVAL; - /* - * We currently don't support a uprobe on an already - * existing breakpoint instruction underneath - */ - if (is_trap(auprobe->ainsn)) - return -ENOTSUPP; return 0; } @@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) return false; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + unsigned long orig_ret_vaddr; + + orig_ret_vaddr = regs->link; + + /* Replace the return addr with trampoline addr */ + regs->link = trampoline_vaddr; + + return orig_ret_vaddr; +} 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/44x.c b/arch/powerpc/kvm/44x.c index 3d7fd21c65f9..2f5c6b6d6877 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -124,6 +124,18 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvmppc_set_sregs_ivor(vcpu, sregs); } +int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + return -EINVAL; +} + +int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + return -EINVAL; +} + struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_44x *vcpu_44x; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 63c67ec72e43..eb643f862579 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -136,21 +136,41 @@ config KVM_E500V2 If unsure, say N. config KVM_E500MC - bool "KVM support for PowerPC E500MC/E5500 processors" + bool "KVM support for PowerPC E500MC/E5500/E6500 processors" depends on PPC_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV select MMU_NOTIFIER ---help--- - Support running unmodified E500MC/E5500 (32-bit) guest kernels in - virtual machines on E500MC/E5500 host processors. + Support running unmodified E500MC/E5500/E6500 guest kernels in + virtual machines on E500MC/E5500/E6500 host processors. This module provides access to the hardware capabilities through a character device node named /dev/kvm. If unsure, say N. +config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQ_ROUTING + select HAVE_KVM_MSI + help + Enable support for emulating MPIC devices inside the + host kernel, rather than relying on userspace to emulate. + Currently, support is limited to certain versions of + Freescale's MPIC implementation. + +config KVM_XICS + bool "KVM in-kernel XICS emulation" + depends on KVM_BOOK3S_64 && !KVM_MPIC + ---help--- + Include support for the XICS (eXternal Interrupt Controller + Specification) interrupt controller architecture used on + IBM POWER (pSeries) servers. + source drivers/vhost/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index b772eded8c26..422de3f4d46c 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -72,12 +72,18 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ book3s_hv.o \ book3s_hv_interrupts.o \ book3s_64_mmu_hv.o +kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ + book3s_hv_rm_xics.o kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_64_vio_hv.o \ book3s_hv_ras.o \ - book3s_hv_builtin.o + book3s_hv_builtin.o \ + $(kvm-book3s_64-builtin-xics-objs-y) + +kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ + book3s_xics.o kvm-book3s_64-module-objs := \ ../../../virt/kvm/kvm_main.o \ @@ -86,6 +92,7 @@ kvm-book3s_64-module-objs := \ emulate.o \ book3s.o \ book3s_64_vio.o \ + book3s_rtas.o \ $(kvm-book3s_64-objs-y) kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs) @@ -103,6 +110,9 @@ kvm-book3s_32-objs := \ book3s_32_mmu.o kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) +kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o +kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(addprefix ../../../virt/kvm/, irqchip.o) + kvm-objs := $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_440) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index a4b645285240..700df6f1d32c 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -104,7 +104,7 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec) return prio; } -static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, +void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) { unsigned long old_pending = vcpu->arch.pending_exceptions; @@ -160,8 +160,7 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_book3s_queue_irqprio(vcpu, vec); } -void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, - struct kvm_interrupt *irq) +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu) { kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL); @@ -530,6 +529,21 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]); break; #endif /* CONFIG_ALTIVEC */ + case KVM_REG_PPC_DEBUG_INST: { + u32 opcode = INS_TW; + r = copy_to_user((u32 __user *)(long)reg->addr, + &opcode, sizeof(u32)); + break; + } +#ifdef CONFIG_KVM_XICS + case KVM_REG_PPC_ICP_STATE: + if (!vcpu->arch.icp) { + r = -ENXIO; + break; + } + val = get_reg_val(reg->id, kvmppc_xics_get_icp(vcpu)); + break; +#endif /* CONFIG_KVM_XICS */ default: r = -EINVAL; break; @@ -592,6 +606,16 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_KVM_XICS + case KVM_REG_PPC_ICP_STATE: + if (!vcpu->arch.icp) { + r = -ENXIO; + break; + } + r = kvmppc_xics_set_icp(vcpu, + set_reg_val(reg->id, val)); + break; +#endif /* CONFIG_KVM_XICS */ default: r = -EINVAL; break; @@ -607,6 +631,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return 0; } +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + return -EINVAL; +} + void kvmppc_decrementer_func(unsigned long data) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index ead58e317294..3a9a1aceb14f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -143,7 +143,7 @@ map_again: } ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags, - MMU_PAGE_4K, MMU_SEGSIZE_256M); + MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M); if (ret < 0) { /* If we couldn't map a primary PTE, try a secondary */ @@ -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_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 8cc18abd6dde..5880dfb31074 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -893,7 +893,10 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, /* Harvest R and C */ rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C); *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; - rev[i].guest_rpte = ptel | rcbits; + if (rcbits & ~rev[i].guest_rpte) { + rev[i].guest_rpte = ptel | rcbits; + note_hpte_modification(kvm, &rev[i]); + } } unlock_rmap(rmapp); hptep[0] &= ~HPTE_V_HVLOCK; @@ -976,7 +979,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, /* Now check and modify the HPTE */ if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) { kvmppc_clear_ref_hpte(kvm, hptep, i); - rev[i].guest_rpte |= HPTE_R_R; + if (!(rev[i].guest_rpte & HPTE_R_R)) { + rev[i].guest_rpte |= HPTE_R_R; + note_hpte_modification(kvm, &rev[i]); + } ret = 1; } hptep[0] &= ~HPTE_V_HVLOCK; @@ -1080,7 +1086,10 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp) hptep[1] &= ~HPTE_R_C; eieio(); hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID; - rev[i].guest_rpte |= HPTE_R_C; + if (!(rev[i].guest_rpte & HPTE_R_C)) { + rev[i].guest_rpte |= HPTE_R_C; + note_hpte_modification(kvm, &rev[i]); + } ret = 1; } hptep[0] &= ~HPTE_V_HVLOCK; @@ -1090,11 +1099,30 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp) return ret; } +static void harvest_vpa_dirty(struct kvmppc_vpa *vpa, + struct kvm_memory_slot *memslot, + unsigned long *map) +{ + unsigned long gfn; + + if (!vpa->dirty || !vpa->pinned_addr) + return; + gfn = vpa->gpa >> PAGE_SHIFT; + if (gfn < memslot->base_gfn || + gfn >= memslot->base_gfn + memslot->npages) + return; + + vpa->dirty = false; + if (map) + __set_bit_le(gfn - memslot->base_gfn, map); +} + long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long *map) { unsigned long i; unsigned long *rmapp; + struct kvm_vcpu *vcpu; preempt_disable(); rmapp = memslot->arch.rmap; @@ -1103,6 +1131,15 @@ long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot, __set_bit_le(i, map); ++rmapp; } + + /* Harvest dirty bits from VPA and DTL updates */ + /* Note: we never modify the SLB shadow buffer areas */ + kvm_for_each_vcpu(i, vcpu, kvm) { + spin_lock(&vcpu->arch.vpa_update_lock); + harvest_vpa_dirty(&vcpu->arch.vpa, memslot, map); + harvest_vpa_dirty(&vcpu->arch.dtl, memslot, map); + spin_unlock(&vcpu->arch.vpa_update_lock); + } preempt_enable(); return 0; } @@ -1114,7 +1151,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, unsigned long gfn = gpa >> PAGE_SHIFT; struct page *page, *pages[1]; int npages; - unsigned long hva, psize, offset; + unsigned long hva, offset; unsigned long pa; unsigned long *physp; int srcu_idx; @@ -1146,14 +1183,9 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, } srcu_read_unlock(&kvm->srcu, srcu_idx); - psize = PAGE_SIZE; - if (PageHuge(page)) { - page = compound_head(page); - psize <<= compound_order(page); - } - offset = gpa & (psize - 1); + offset = gpa & (PAGE_SIZE - 1); if (nb_ret) - *nb_ret = psize - offset; + *nb_ret = PAGE_SIZE - offset; return page_address(page) + offset; err: @@ -1161,11 +1193,31 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, return NULL; } -void kvmppc_unpin_guest_page(struct kvm *kvm, void *va) +void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, + bool dirty) { struct page *page = virt_to_page(va); + struct kvm_memory_slot *memslot; + unsigned long gfn; + unsigned long *rmap; + int srcu_idx; put_page(page); + + if (!dirty || !kvm->arch.using_mmu_notifiers) + return; + + /* We need to mark this page dirty in the rmap chain */ + gfn = gpa >> PAGE_SHIFT; + srcu_idx = srcu_read_lock(&kvm->srcu); + memslot = gfn_to_memslot(kvm, gfn); + if (memslot) { + rmap = &memslot->arch.rmap[gfn - memslot->base_gfn]; + lock_rmap(rmap); + *rmap |= KVMPPC_RMAP_CHANGED; + unlock_rmap(rmap); + } + srcu_read_unlock(&kvm->srcu, srcu_idx); } /* @@ -1193,16 +1245,36 @@ struct kvm_htab_ctx { #define HPTE_SIZE (2 * sizeof(unsigned long)) +/* + * Returns 1 if this HPT entry has been modified or has pending + * R/C bit changes. + */ +static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp) +{ + unsigned long rcbits_unset; + + if (revp->guest_rpte & HPTE_GR_MODIFIED) + return 1; + + /* Also need to consider changes in reference and changed bits */ + rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C); + if ((hptp[0] & HPTE_V_VALID) && (hptp[1] & rcbits_unset)) + return 1; + + return 0; +} + static long record_hpte(unsigned long flags, unsigned long *hptp, unsigned long *hpte, struct revmap_entry *revp, int want_valid, int first_pass) { unsigned long v, r; + unsigned long rcbits_unset; int ok = 1; int valid, dirty; /* Unmodified entries are uninteresting except on the first pass */ - dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED); + dirty = hpte_dirty(revp, hptp); if (!first_pass && !dirty) return 0; @@ -1223,16 +1295,28 @@ static long record_hpte(unsigned long flags, unsigned long *hptp, while (!try_lock_hpte(hptp, HPTE_V_HVLOCK)) cpu_relax(); v = hptp[0]; + + /* re-evaluate valid and dirty from synchronized HPTE value */ + valid = !!(v & HPTE_V_VALID); + dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED); + + /* Harvest R and C into guest view if necessary */ + rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C); + if (valid && (rcbits_unset & hptp[1])) { + revp->guest_rpte |= (hptp[1] & (HPTE_R_R | HPTE_R_C)) | + HPTE_GR_MODIFIED; + dirty = 1; + } + if (v & HPTE_V_ABSENT) { v &= ~HPTE_V_ABSENT; v |= HPTE_V_VALID; + valid = 1; } - /* re-evaluate valid and dirty from synchronized HPTE value */ - valid = !!(v & HPTE_V_VALID); if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED)) valid = 0; - r = revp->guest_rpte | (hptp[1] & (HPTE_R_R | HPTE_R_C)); - dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED); + + r = revp->guest_rpte; /* only clear modified if this is the right sort of entry */ if (valid == want_valid && dirty) { r &= ~HPTE_GR_MODIFIED; @@ -1288,7 +1372,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, /* Skip uninteresting entries, i.e. clean on not-first pass */ if (!first_pass) { while (i < kvm->arch.hpt_npte && - !(revp->guest_rpte & HPTE_GR_MODIFIED)) { + !hpte_dirty(revp, hptp)) { ++i; hptp += 2; ++revp; @@ -1467,7 +1551,7 @@ static int kvm_htab_release(struct inode *inode, struct file *filp) return 0; } -static struct file_operations kvm_htab_fops = { +static const struct file_operations kvm_htab_fops = { .read = kvm_htab_read, .write = kvm_htab_write, .llseek = default_llseek, diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 72ffc899c082..b2d3f3b2de72 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -92,7 +92,7 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) return 0; } -static struct file_operations kvm_spapr_tce_fops = { +static const struct file_operations kvm_spapr_tce_fops = { .mmap = kvm_spapr_tce_mmap, .release = kvm_spapr_tce_release, }; diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 836c56975e21..1f6344c4408d 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -194,7 +194,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, run->papr_hcall.args[i] = gpr; } - emulated = EMULATE_DO_PAPR; + run->exit_reason = KVM_EXIT_PAPR_HCALL; + vcpu->arch.hcall_needed = 1; + emulated = EMULATE_EXIT_USER; break; } #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 80dcc53a1aba..550f5928b394 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -66,6 +66,31 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); +void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) +{ + int me; + int cpu = vcpu->cpu; + wait_queue_head_t *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); + if (waitqueue_active(wqp)) { + wake_up_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + + me = get_cpu(); + + /* CPU points to the first thread of the core */ + if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { + int real_cpu = cpu + vcpu->arch.ptid; + if (paca[real_cpu].kvm_hstate.xics_phys) + xics_wake_cpu(real_cpu); + else if (cpu_online(cpu)) + smp_send_reschedule(cpu); + } + put_cpu(); +} + /* * We use the vcpu_load/put functions to measure stolen time. * Stolen time is counted as time when either the vcpu is able to @@ -259,7 +284,7 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, len = ((struct reg_vpa *)va)->length.hword; else len = ((struct reg_vpa *)va)->length.word; - kvmppc_unpin_guest_page(kvm, va); + kvmppc_unpin_guest_page(kvm, va, vpa, false); /* Check length */ if (len > nb || len < sizeof(struct reg_vpa)) @@ -359,13 +384,13 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) va = NULL; nb = 0; if (gpa) - va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb); + va = kvmppc_pin_guest_page(kvm, gpa, &nb); spin_lock(&vcpu->arch.vpa_update_lock); if (gpa == vpap->next_gpa) break; /* sigh... unpin that one and try again */ if (va) - kvmppc_unpin_guest_page(kvm, va); + kvmppc_unpin_guest_page(kvm, va, gpa, false); } vpap->update_pending = 0; @@ -375,12 +400,15 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) * has changed the mappings underlying guest memory, * so unregister the region. */ - kvmppc_unpin_guest_page(kvm, va); + kvmppc_unpin_guest_page(kvm, va, gpa, false); va = NULL; } if (vpap->pinned_addr) - kvmppc_unpin_guest_page(kvm, vpap->pinned_addr); + kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa, + vpap->dirty); + vpap->gpa = gpa; vpap->pinned_addr = va; + vpap->dirty = false; if (va) vpap->pinned_end = va + vpap->len; } @@ -472,6 +500,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, /* order writing *dt vs. writing vpa->dtl_idx */ smp_wmb(); vpa->dtl_idx = ++vcpu->arch.dtl_index; + vcpu->arch.dtl.dirty = true; } int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) @@ -479,7 +508,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; struct kvm_vcpu *tvcpu; - int idx; + int idx, rc; switch (req) { case H_ENTER: @@ -515,6 +544,30 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6)); break; + case H_RTAS: + if (list_empty(&vcpu->kvm->arch.rtas_tokens)) + return RESUME_HOST; + + rc = kvmppc_rtas_hcall(vcpu); + + if (rc == -ENOENT) + return RESUME_HOST; + else if (rc == 0) + break; + + /* Send the error out to userspace via KVM_RUN */ + return rc; + + case H_XIRR: + case H_CPPR: + case H_EOI: + case H_IPI: + case H_IPOLL: + case H_XIRR_X: + if (kvmppc_xics_enabled(vcpu)) { + ret = kvmppc_xics_hcall(vcpu, req); + break; + } /* fallthrough */ default: return RESUME_HOST; } @@ -913,15 +966,19 @@ out: return ERR_PTR(err); } +static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa) +{ + if (vpa->pinned_addr) + kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa, + vpa->dirty); +} + void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) { spin_lock(&vcpu->arch.vpa_update_lock); - if (vcpu->arch.dtl.pinned_addr) - kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl.pinned_addr); - if (vcpu->arch.slb_shadow.pinned_addr) - kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow.pinned_addr); - if (vcpu->arch.vpa.pinned_addr) - kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa.pinned_addr); + unpin_vpa(vcpu->kvm, &vcpu->arch.dtl); + unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow); + unpin_vpa(vcpu->kvm, &vcpu->arch.vpa); spin_unlock(&vcpu->arch.vpa_update_lock); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); @@ -955,7 +1012,6 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu) } extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); -extern void xics_wake_cpu(int cpu); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, struct kvm_vcpu *vcpu) @@ -1330,9 +1386,12 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) break; vc->runner = vcpu; n_ceded = 0; - list_for_each_entry(v, &vc->runnable_threads, arch.run_list) + list_for_each_entry(v, &vc->runnable_threads, arch.run_list) { if (!v->arch.pending_exceptions) n_ceded += v->arch.ceded; + else + v->arch.ceded = 0; + } if (n_ceded == vc->n_runnable) kvmppc_vcore_blocked(vc); else @@ -1483,7 +1542,7 @@ static int kvm_rma_release(struct inode *inode, struct file *filp) return 0; } -static struct file_operations kvm_rma_fops = { +static const struct file_operations kvm_rma_fops = { .mmap = kvm_rma_mmap, .release = kvm_rma_release, }; @@ -1515,7 +1574,13 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps, (*sps)->page_shift = def->shift; (*sps)->slb_enc = def->sllp; (*sps)->enc[0].page_shift = def->shift; - (*sps)->enc[0].pte_enc = def->penc; + /* + * Only return base page encoding. We don't want to return + * all the supporting pte_enc, because our H_ENTER doesn't + * support MPSS yet. Once they do, we can start passing all + * support pte_enc here + */ + (*sps)->enc[0].pte_enc = def->penc[linux_psize]; (*sps)++; } @@ -1639,12 +1704,12 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old) + const struct kvm_memory_slot *old) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; struct kvm_memory_slot *memslot; - if (npages && old.npages) { + if (npages && old->npages) { /* * If modifying a memslot, reset all the rmap dirty bits. * If this is a new memslot, we don't need to do anything @@ -1821,6 +1886,7 @@ int kvmppc_core_init_vm(struct kvm *kvm) cpumask_setall(&kvm->arch.need_tlb_flush); INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + INIT_LIST_HEAD(&kvm->arch.rtas_tokens); kvm->arch.rma = NULL; @@ -1866,6 +1932,8 @@ void kvmppc_core_destroy_vm(struct kvm *kvm) kvm->arch.rma = NULL; } + kvmppc_rtas_tokens_free(kvm); + kvmppc_free_hpt(kvm); WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); } 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_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 19c93bae1aea..6dcbb49105a4 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -97,17 +97,6 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, } EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain); -/* - * Note modification of an HPTE; set the HPTE modified bit - * if anyone is interested. - */ -static inline void note_hpte_modification(struct kvm *kvm, - struct revmap_entry *rev) -{ - if (atomic_read(&kvm->arch.hpte_mod_interest)) - rev->guest_rpte |= HPTE_GR_MODIFIED; -} - /* Remove this HPTE from the chain for a real page */ static void remove_revmap_chain(struct kvm *kvm, long pte_index, struct revmap_entry *rev, diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c new file mode 100644 index 000000000000..b4b0082f761c --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -0,0 +1,406 @@ +/* + * Copyright 2012 Michael Ellerman, IBM Corporation. + * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <linux/err.h> + +#include <asm/kvm_book3s.h> +#include <asm/kvm_ppc.h> +#include <asm/hvcall.h> +#include <asm/xics.h> +#include <asm/debug.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> + +#include "book3s_xics.h" + +#define DEBUG_PASSUP + +static inline void rm_writeb(unsigned long paddr, u8 val) +{ + __asm__ __volatile__("sync; stbcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + +static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, + struct kvm_vcpu *this_vcpu) +{ + struct kvmppc_icp *this_icp = this_vcpu->arch.icp; + unsigned long xics_phys; + int cpu; + + /* Mark the target VCPU as having an interrupt pending */ + vcpu->stat.queue_intr++; + set_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions); + + /* Kick self ? Just set MER and return */ + if (vcpu == this_vcpu) { + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_MER); + return; + } + + /* Check if the core is loaded, if not, too hard */ + cpu = vcpu->cpu; + if (cpu < 0 || cpu >= nr_cpu_ids) { + this_icp->rm_action |= XICS_RM_KICK_VCPU; + this_icp->rm_kick_target = vcpu; + return; + } + /* In SMT cpu will always point to thread 0, we adjust it */ + cpu += vcpu->arch.ptid; + + /* Not too hard, then poke the target */ + xics_phys = paca[cpu].kvm_hstate.xics_phys; + rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY); +} + +static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu) +{ + /* Note: Only called on self ! */ + clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, + &vcpu->arch.pending_exceptions); + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_MER); +} + +static inline bool icp_rm_try_update(struct kvmppc_icp *icp, + union kvmppc_icp_state old, + union kvmppc_icp_state new) +{ + struct kvm_vcpu *this_vcpu = local_paca->kvm_hstate.kvm_vcpu; + bool success; + + /* Calculate new output value */ + new.out_ee = (new.xisr && (new.pending_pri < new.cppr)); + + /* Attempt atomic update */ + success = cmpxchg64(&icp->state.raw, old.raw, new.raw) == old.raw; + if (!success) + goto bail; + + /* + * Check for output state update + * + * Note that this is racy since another processor could be updating + * the state already. This is why we never clear the interrupt output + * here, we only ever set it. The clear only happens prior to doing + * an update and only by the processor itself. Currently we do it + * in Accept (H_XIRR) and Up_Cppr (H_XPPR). + * + * We also do not try to figure out whether the EE state has changed, + * we unconditionally set it if the new state calls for it. The reason + * for that is that we opportunistically remove the pending interrupt + * flag when raising CPPR, so we need to set it back here if an + * interrupt is still pending. + */ + if (new.out_ee) + icp_rm_set_vcpu_irq(icp->vcpu, this_vcpu); + + /* Expose the state change for debug purposes */ + this_vcpu->arch.icp->rm_dbgstate = new; + this_vcpu->arch.icp->rm_dbgtgt = icp->vcpu; + + bail: + return success; +} + +static inline int check_too_hard(struct kvmppc_xics *xics, + struct kvmppc_icp *icp) +{ + return (xics->real_mode_dbg || icp->rm_action) ? H_TOO_HARD : H_SUCCESS; +} + +static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u8 new_cppr) +{ + union kvmppc_icp_state old_state, new_state; + bool resend; + + /* + * This handles several related states in one operation: + * + * ICP State: Down_CPPR + * + * Load CPPR with new value and if the XISR is 0 + * then check for resends: + * + * ICP State: Resend + * + * If MFRR is more favored than CPPR, check for IPIs + * and notify ICS of a potential resend. This is done + * asynchronously (when used in real mode, we will have + * to exit here). + * + * We do not handle the complete Check_IPI as documented + * here. In the PAPR, this state will be used for both + * Set_MFRR and Down_CPPR. However, we know that we aren't + * changing the MFRR state here so we don't need to handle + * the case of an MFRR causing a reject of a pending irq, + * this will have been handled when the MFRR was set in the + * first place. + * + * Thus we don't have to handle rejects, only resends. + * + * When implementing real mode for HV KVM, resend will lead to + * a H_TOO_HARD return and the whole transaction will be handled + * in virtual mode. + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + /* Down_CPPR */ + new_state.cppr = new_cppr; + + /* + * Cut down Resend / Check_IPI / IPI + * + * The logic is that we cannot have a pending interrupt + * trumped by an IPI at this point (see above), so we + * know that either the pending interrupt is already an + * IPI (in which case we don't care to override it) or + * it's either more favored than us or non existent + */ + if (new_state.mfrr < new_cppr && + new_state.mfrr <= new_state.pending_pri) { + new_state.pending_pri = new_state.mfrr; + new_state.xisr = XICS_IPI; + } + + /* Latch/clear resend bit */ + resend = new_state.need_resend; + new_state.need_resend = 0; + + } while (!icp_rm_try_update(icp, old_state, new_state)); + + /* + * Now handle resend checks. Those are asynchronous to the ICP + * state update in HW (ie bus transactions) so we can handle them + * separately here as well. + */ + if (resend) + icp->rm_action |= XICS_RM_CHECK_RESEND; +} + + +unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 xirr; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + /* First clear the interrupt */ + icp_rm_clr_vcpu_irq(icp->vcpu); + + /* + * ICP State: Accept_Interrupt + * + * Return the pending interrupt (if any) along with the + * current CPPR, then clear the XISR & set CPPR to the + * pending priority + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + xirr = old_state.xisr | (((u32)old_state.cppr) << 24); + if (!old_state.xisr) + break; + new_state.cppr = new_state.pending_pri; + new_state.pending_pri = 0xff; + new_state.xisr = 0; + + } while (!icp_rm_try_update(icp, old_state, new_state)); + + /* Return the result in GPR4 */ + vcpu->arch.gpr[4] = xirr; + + return check_too_hard(xics, icp); +} + +int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, + unsigned long mfrr) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp, *this_icp = vcpu->arch.icp; + u32 reject; + bool resend; + bool local; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + local = this_icp->server_num == server; + if (local) + icp = this_icp; + else + icp = kvmppc_xics_find_server(vcpu->kvm, server); + if (!icp) + return H_PARAMETER; + + /* + * ICP state: Set_MFRR + * + * If the CPPR is more favored than the new MFRR, then + * nothing needs to be done as there can be no XISR to + * reject. + * + * If the CPPR is less favored, then we might be replacing + * an interrupt, and thus need to possibly reject it as in + * + * ICP state: Check_IPI + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + /* Set_MFRR */ + new_state.mfrr = mfrr; + + /* Check_IPI */ + reject = 0; + resend = false; + if (mfrr < new_state.cppr) { + /* Reject a pending interrupt if not an IPI */ + if (mfrr <= new_state.pending_pri) + reject = new_state.xisr; + new_state.pending_pri = mfrr; + new_state.xisr = XICS_IPI; + } + + if (mfrr > old_state.mfrr && mfrr > new_state.cppr) { + resend = new_state.need_resend; + new_state.need_resend = 0; + } + } while (!icp_rm_try_update(icp, old_state, new_state)); + + /* Pass rejects to virtual mode */ + if (reject && reject != XICS_IPI) { + this_icp->rm_action |= XICS_RM_REJECT; + this_icp->rm_reject = reject; + } + + /* Pass resends to virtual mode */ + if (resend) + this_icp->rm_action |= XICS_RM_CHECK_RESEND; + + return check_too_hard(xics, this_icp); +} + +int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 reject; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + /* + * ICP State: Set_CPPR + * + * We can safely compare the new value with the current + * value outside of the transaction as the CPPR is only + * ever changed by the processor on itself + */ + if (cppr > icp->state.cppr) { + icp_rm_down_cppr(xics, icp, cppr); + goto bail; + } else if (cppr == icp->state.cppr) + return H_SUCCESS; + + /* + * ICP State: Up_CPPR + * + * The processor is raising its priority, this can result + * in a rejection of a pending interrupt: + * + * ICP State: Reject_Current + * + * We can remove EE from the current processor, the update + * transaction will set it again if needed + */ + icp_rm_clr_vcpu_irq(icp->vcpu); + + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + reject = 0; + new_state.cppr = cppr; + + if (cppr <= new_state.pending_pri) { + reject = new_state.xisr; + new_state.xisr = 0; + new_state.pending_pri = 0xff; + } + + } while (!icp_rm_try_update(icp, old_state, new_state)); + + /* Pass rejects to virtual mode */ + if (reject && reject != XICS_IPI) { + icp->rm_action |= XICS_RM_REJECT; + icp->rm_reject = reject; + } + bail: + return check_too_hard(xics, icp); +} + +int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u32 irq = xirr & 0x00ffffff; + u16 src; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + /* + * ICP State: EOI + * + * Note: If EOI is incorrectly used by SW to lower the CPPR + * value (ie more favored), we do not check for rejection of + * a pending interrupt, this is a SW error and PAPR sepcifies + * that we don't have to deal with it. + * + * The sending of an EOI to the ICS is handled after the + * CPPR update + * + * ICP State: Down_CPPR which we handle + * in a separate function as it's shared with H_CPPR. + */ + icp_rm_down_cppr(xics, icp, xirr >> 24); + + /* IPIs have no EOI */ + if (irq == XICS_IPI) + goto bail; + /* + * EOI handling: If the interrupt is still asserted, we need to + * resend it. We can take a lockless "peek" at the ICS state here. + * + * "Message" interrupts will never have "asserted" set + */ + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + goto bail; + state = &ics->irq_state[src]; + + /* Still asserted, resend it, we make it look like a reject */ + if (state->asserted) { + icp->rm_action |= XICS_RM_REJECT; + icp->rm_reject = irq; + } + bail: + return check_too_hard(xics, icp); +} diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index e33d11f1b977..b02f91e4c70d 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -79,10 +79,6 @@ _GLOBAL(kvmppc_hv_entry_trampoline) * * *****************************************************************************/ -#define XICS_XIRR 4 -#define XICS_QIRR 0xc -#define XICS_IPI 2 /* interrupt source # for IPIs */ - /* * We come in here when wakened from nap mode on a secondary hw thread. * Relocation is off and most register values are lost. @@ -101,50 +97,51 @@ kvm_start_guest: li r0,1 stb r0,PACA_NAPSTATELOST(r13) - /* get vcpu pointer, NULL if we have no vcpu to run */ - ld r4,HSTATE_KVM_VCPU(r13) - cmpdi cr1,r4,0 + /* were we napping due to cede? */ + lbz r0,HSTATE_NAPPING(r13) + cmpwi r0,0 + bne kvm_end_cede + + /* + * We weren't napping due to cede, so this must be a secondary + * thread being woken up to run a guest, or being woken up due + * to a stray IPI. (Or due to some machine check or hypervisor + * maintenance interrupt while the core is in KVM.) + */ /* Check the wake reason in SRR1 to see why we got here */ mfspr r3,SPRN_SRR1 rlwinm r3,r3,44-31,0x7 /* extract wake reason field */ cmpwi r3,4 /* was it an external interrupt? */ - bne 27f - - /* - * External interrupt - for now assume it is an IPI, since we - * should never get any other interrupts sent to offline threads. - * Only do this for secondary threads. - */ - beq cr1,25f - lwz r3,VCPU_PTID(r4) - cmpwi r3,0 - beq 27f -25: ld r5,HSTATE_XICS_PHYS(r13) - li r0,0xff - li r6,XICS_QIRR - li r7,XICS_XIRR + bne 27f /* if not */ + ld r5,HSTATE_XICS_PHYS(r13) + li r7,XICS_XIRR /* if it was an external interrupt, */ lwzcix r8,r5,r7 /* get and ack the interrupt */ sync clrldi. r9,r8,40 /* get interrupt source ID. */ - beq 27f /* none there? */ - cmpwi r9,XICS_IPI - bne 26f + beq 28f /* none there? */ + cmpwi r9,XICS_IPI /* was it an IPI? */ + bne 29f + li r0,0xff + li r6,XICS_MFRR stbcix r0,r5,r6 /* clear IPI */ -26: stwcix r8,r5,r7 /* EOI the interrupt */ - -27: /* XXX should handle hypervisor maintenance interrupts etc. here */ + stwcix r8,r5,r7 /* EOI the interrupt */ + sync /* order loading of vcpu after that */ - /* reload vcpu pointer after clearing the IPI */ + /* get vcpu pointer, NULL if we have no vcpu to run */ ld r4,HSTATE_KVM_VCPU(r13) cmpdi r4,0 /* if we have no vcpu to run, go back to sleep */ beq kvm_no_guest + b kvmppc_hv_entry - /* were we napping due to cede? */ - lbz r0,HSTATE_NAPPING(r13) - cmpwi r0,0 - bne kvm_end_cede +27: /* XXX should handle hypervisor maintenance interrupts etc. here */ + b kvm_no_guest +28: /* SRR1 said external but ICP said nope?? */ + b kvm_no_guest +29: /* External non-IPI interrupt to offline secondary thread? help?? */ + stw r8,HSTATE_SAVED_XIRR(r13) + b kvm_no_guest .global kvmppc_hv_entry kvmppc_hv_entry: @@ -260,6 +257,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) lwz r5, LPPACA_YIELDCOUNT(r3) addi r5, r5, 1 stw r5, LPPACA_YIELDCOUNT(r3) + li r6, 1 + stb r6, VCPU_VPA_DIRTY(r4) 25: /* Load up DAR and DSISR */ ld r5, VCPU_DAR(r4) @@ -485,20 +484,20 @@ toc_tlbie_lock: mtctr r6 mtxer r7 + ld r10, VCPU_PC(r4) + ld r11, VCPU_MSR(r4) kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ ld r6, VCPU_SRR0(r4) ld r7, VCPU_SRR1(r4) - ld r10, VCPU_PC(r4) - ld r11, VCPU_MSR(r4) /* r11 = vcpu->arch.msr & ~MSR_HV */ + /* r11 = vcpu->arch.msr & ~MSR_HV */ rldicl r11, r11, 63 - MSR_HV_LG, 1 rotldi r11, r11, 1 + MSR_HV_LG ori r11, r11, MSR_ME /* Check if we can deliver an external or decrementer interrupt now */ ld r0,VCPU_PENDING_EXC(r4) - li r8,(1 << BOOK3S_IRQPRIO_EXTERNAL) - oris r8,r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h + lis r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h and r0,r0,r8 cmpdi cr1,r0,0 andi. r0,r11,MSR_EE @@ -526,10 +525,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* Move SRR0 and SRR1 into the respective regs */ 5: mtspr SPRN_SRR0, r6 mtspr SPRN_SRR1, r7 - li r0,0 - stb r0,VCPU_CEDED(r4) /* cancel cede */ fast_guest_return: + li r0,0 + stb r0,VCPU_CEDED(r4) /* cancel cede */ mtspr SPRN_HSRR0,r10 mtspr SPRN_HSRR1,r11 @@ -676,17 +675,99 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) cmpwi r12,BOOK3S_INTERRUPT_SYSCALL beq hcall_try_real_mode - /* Check for mediated interrupts (could be done earlier really ...) */ + /* Only handle external interrupts here on arch 206 and later */ BEGIN_FTR_SECTION - cmpwi r12,BOOK3S_INTERRUPT_EXTERNAL - bne+ 1f - andi. r0,r11,MSR_EE - beq 1f - mfspr r5,SPRN_LPCR - andi. r0,r5,LPCR_MER - bne bounce_ext_interrupt -1: -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + b ext_interrupt_to_host +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) + + /* External interrupt ? */ + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL + bne+ ext_interrupt_to_host + + /* External interrupt, first check for host_ipi. If this is + * set, we know the host wants us out so let's do it now + */ +do_ext_interrupt: + lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 + bne ext_interrupt_to_host + + /* Now read the interrupt from the ICP */ + ld r5, HSTATE_XICS_PHYS(r13) + li r7, XICS_XIRR + cmpdi r5, 0 + beq- ext_interrupt_to_host + lwzcix r3, r5, r7 + rlwinm. r0, r3, 0, 0xffffff + sync + beq 3f /* if nothing pending in the ICP */ + + /* We found something in the ICP... + * + * If it's not an IPI, stash it in the PACA and return to + * the host, we don't (yet) handle directing real external + * interrupts directly to the guest + */ + cmpwi r0, XICS_IPI + bne ext_stash_for_host + + /* It's an IPI, clear the MFRR and EOI it */ + li r0, 0xff + li r6, XICS_MFRR + stbcix r0, r5, r6 /* clear the IPI */ + stwcix r3, r5, r7 /* EOI it */ + sync + + /* We need to re-check host IPI now in case it got set in the + * meantime. If it's clear, we bounce the interrupt to the + * guest + */ + lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 + bne- 1f + + /* Allright, looks like an IPI for the guest, we need to set MER */ +3: + /* Check if any CPU is heading out to the host, if so head out too */ + ld r5, HSTATE_KVM_VCORE(r13) + lwz r0, VCORE_ENTRY_EXIT(r5) + cmpwi r0, 0x100 + bge ext_interrupt_to_host + + /* See if there is a pending interrupt for the guest */ + mfspr r8, SPRN_LPCR + ld r0, VCPU_PENDING_EXC(r9) + /* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */ + rldicl. r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63 + rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH + beq 2f + + /* And if the guest EE is set, we can deliver immediately, else + * we return to the guest with MER set + */ + andi. r0, r11, MSR_EE + beq 2f + mtspr SPRN_SRR0, r10 + mtspr SPRN_SRR1, r11 + li r10, BOOK3S_INTERRUPT_EXTERNAL + li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ + rotldi r11, r11, 63 +2: mr r4, r9 + mtspr SPRN_LPCR, r8 + b fast_guest_return + + /* We raced with the host, we need to resend that IPI, bummer */ +1: li r0, IPI_PRIORITY + stbcix r0, r5, r6 /* set the IPI */ + sync + b ext_interrupt_to_host + +ext_stash_for_host: + /* It's not an IPI and it's for the host, stash it in the PACA + * before exit, it will be picked up by the host ICP driver + */ + stw r3, HSTATE_SAVED_XIRR(r13) +ext_interrupt_to_host: guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ /* Save DEC */ @@ -829,7 +910,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) beq 44f ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */ li r0,IPI_PRIORITY - li r7,XICS_QIRR + li r7,XICS_MFRR stbcix r0,r7,r8 /* trigger the IPI */ 44: srdi. r3,r3,1 addi r6,r6,PACA_SIZE @@ -1018,6 +1099,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) lwz r3, LPPACA_YIELDCOUNT(r8) addi r3, r3, 1 stw r3, LPPACA_YIELDCOUNT(r8) + li r3, 1 + stb r3, VCPU_VPA_DIRTY(r9) 25: /* Save PMU registers if requested */ /* r8 and cr0.eq are live here */ @@ -1350,11 +1433,19 @@ hcall_real_table: .long 0 /* 0x58 */ .long 0 /* 0x5c */ .long 0 /* 0x60 */ - .long 0 /* 0x64 */ - .long 0 /* 0x68 */ - .long 0 /* 0x6c */ - .long 0 /* 0x70 */ - .long 0 /* 0x74 */ +#ifdef CONFIG_KVM_XICS + .long .kvmppc_rm_h_eoi - hcall_real_table + .long .kvmppc_rm_h_cppr - hcall_real_table + .long .kvmppc_rm_h_ipi - hcall_real_table + .long 0 /* 0x70 - H_IPOLL */ + .long .kvmppc_rm_h_xirr - hcall_real_table +#else + .long 0 /* 0x64 - H_EOI */ + .long 0 /* 0x68 - H_CPPR */ + .long 0 /* 0x6c - H_IPI */ + .long 0 /* 0x70 - H_IPOLL */ + .long 0 /* 0x74 - H_XIRR */ +#endif .long 0 /* 0x78 */ .long 0 /* 0x7c */ .long 0 /* 0x80 */ @@ -1405,15 +1496,6 @@ ignore_hdec: mr r4,r9 b fast_guest_return -bounce_ext_interrupt: - mr r4,r9 - mtspr SPRN_SRR0,r10 - mtspr SPRN_SRR1,r11 - li r10,BOOK3S_INTERRUPT_EXTERNAL - li r11,(MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11,r11,63 - b fast_guest_return - _GLOBAL(kvmppc_h_set_dabr) std r4,VCPU_DABR(r3) /* Work around P7 bug where DABR can get corrupted on mtspr */ @@ -1519,6 +1601,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) b . kvm_end_cede: + /* get vcpu pointer */ + ld r4, HSTATE_KVM_VCPU(r13) + /* Woken by external or decrementer interrupt */ ld r1, HSTATE_HOST_R1(r13) @@ -1558,6 +1643,16 @@ kvm_end_cede: li r0,0 stb r0,HSTATE_NAPPING(r13) + /* Check the wake reason in SRR1 to see why we got here */ + mfspr r3, SPRN_SRR1 + rlwinm r3, r3, 44-31, 0x7 /* extract wake reason field */ + cmpwi r3, 4 /* was it an external interrupt? */ + li r12, BOOK3S_INTERRUPT_EXTERNAL + mr r9, r4 + ld r10, VCPU_PC(r9) + ld r11, VCPU_MSR(r9) + beq do_ext_interrupt /* if so */ + /* see if any other thread is already exiting */ lwz r0,VCORE_ENTRY_EXIT(r5) cmpwi r0,0x100 @@ -1577,8 +1672,7 @@ kvm_cede_prodded: /* we've ceded but we want to give control to the host */ kvm_cede_exit: - li r3,H_TOO_HARD - blr + b hcall_real_fallback /* Try to handle a machine check in real mode */ machine_check_realmode: @@ -1626,7 +1720,7 @@ secondary_nap: beq 37f sync li r0, 0xff - li r6, XICS_QIRR + li r6, XICS_MFRR stbcix r0, r5, r6 /* clear the IPI */ stwcix r3, r5, r7 /* EOI it */ 37: sync diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 5e93438afb06..bdc40b8e77d9 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -762,9 +762,7 @@ program_interrupt: run->exit_reason = KVM_EXIT_MMIO; r = RESUME_HOST_NV; break; - case EMULATE_DO_PAPR: - run->exit_reason = KVM_EXIT_PAPR_HCALL; - vcpu->arch.hcall_needed = 1; + case EMULATE_EXIT_USER: r = RESUME_HOST_NV; break; default: @@ -1039,7 +1037,7 @@ 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; @@ -1283,7 +1281,7 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old) + const struct kvm_memory_slot *old) { } @@ -1298,6 +1296,7 @@ int kvmppc_core_init_vm(struct kvm *kvm) { #ifdef CONFIG_PPC64 INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + INIT_LIST_HEAD(&kvm->arch.rtas_tokens); #endif if (firmware_has_feature(FW_FEATURE_SET_MODE)) { diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ee02b30878ed..da0e0bc268bd 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -227,6 +227,13 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) +{ + long rc = kvmppc_xics_hcall(vcpu, cmd); + kvmppc_set_gpr(vcpu, 3, rc); + return EMULATE_DONE; +} + int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) { switch (cmd) { @@ -246,6 +253,22 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) clear_bit(KVM_REQ_UNHALT, &vcpu->requests); vcpu->stat.halt_wakeup++; return EMULATE_DONE; + case H_XIRR: + case H_CPPR: + case H_EOI: + case H_IPI: + case H_IPOLL: + case H_XIRR_X: + if (kvmppc_xics_enabled(vcpu)) + return kvmppc_h_pr_xics_hcall(vcpu, cmd); + break; + case H_RTAS: + if (list_empty(&vcpu->kvm->arch.rtas_tokens)) + return RESUME_HOST; + if (kvmppc_rtas_hcall(vcpu)) + break; + kvmppc_set_gpr(vcpu, 3, 0); + return EMULATE_DONE; } return EMULATE_FAIL; diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c new file mode 100644 index 000000000000..3219ba895246 --- /dev/null +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -0,0 +1,274 @@ +/* + * Copyright 2012 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, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/err.h> + +#include <asm/uaccess.h> +#include <asm/kvm_book3s.h> +#include <asm/kvm_ppc.h> +#include <asm/hvcall.h> +#include <asm/rtas.h> + +#ifdef CONFIG_KVM_XICS +static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) +{ + u32 irq, server, priority; + int rc; + + if (args->nargs != 3 || args->nret != 1) { + rc = -3; + goto out; + } + + irq = args->args[0]; + server = args->args[1]; + priority = args->args[2]; + + rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority); + if (rc) + rc = -3; +out: + args->rets[0] = rc; +} + +static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) +{ + u32 irq, server, priority; + int rc; + + if (args->nargs != 1 || args->nret != 3) { + rc = -3; + goto out; + } + + irq = args->args[0]; + + server = priority = 0; + rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority); + if (rc) { + rc = -3; + goto out; + } + + args->rets[1] = server; + args->rets[2] = priority; +out: + args->rets[0] = rc; +} + +static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args) +{ + u32 irq; + int rc; + + if (args->nargs != 1 || args->nret != 1) { + rc = -3; + goto out; + } + + irq = args->args[0]; + + rc = kvmppc_xics_int_off(vcpu->kvm, irq); + if (rc) + rc = -3; +out: + args->rets[0] = rc; +} + +static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args) +{ + u32 irq; + int rc; + + if (args->nargs != 1 || args->nret != 1) { + rc = -3; + goto out; + } + + irq = args->args[0]; + + rc = kvmppc_xics_int_on(vcpu->kvm, irq); + if (rc) + rc = -3; +out: + args->rets[0] = rc; +} +#endif /* CONFIG_KVM_XICS */ + +struct rtas_handler { + void (*handler)(struct kvm_vcpu *vcpu, struct rtas_args *args); + char *name; +}; + +static struct rtas_handler rtas_handlers[] = { +#ifdef CONFIG_KVM_XICS + { .name = "ibm,set-xive", .handler = kvm_rtas_set_xive }, + { .name = "ibm,get-xive", .handler = kvm_rtas_get_xive }, + { .name = "ibm,int-off", .handler = kvm_rtas_int_off }, + { .name = "ibm,int-on", .handler = kvm_rtas_int_on }, +#endif +}; + +struct rtas_token_definition { + struct list_head list; + struct rtas_handler *handler; + u64 token; +}; + +static int rtas_name_matches(char *s1, char *s2) +{ + struct kvm_rtas_token_args args; + return !strncmp(s1, s2, sizeof(args.name)); +} + +static int rtas_token_undefine(struct kvm *kvm, char *name) +{ + struct rtas_token_definition *d, *tmp; + + lockdep_assert_held(&kvm->lock); + + list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) { + if (rtas_name_matches(d->handler->name, name)) { + list_del(&d->list); + kfree(d); + return 0; + } + } + + /* It's not an error to undefine an undefined token */ + return 0; +} + +static int rtas_token_define(struct kvm *kvm, char *name, u64 token) +{ + struct rtas_token_definition *d; + struct rtas_handler *h = NULL; + bool found; + int i; + + lockdep_assert_held(&kvm->lock); + + list_for_each_entry(d, &kvm->arch.rtas_tokens, list) { + if (d->token == token) + return -EEXIST; + } + + found = false; + for (i = 0; i < ARRAY_SIZE(rtas_handlers); i++) { + h = &rtas_handlers[i]; + if (rtas_name_matches(h->name, name)) { + found = true; + break; + } + } + + if (!found) + return -ENOENT; + + d = kzalloc(sizeof(*d), GFP_KERNEL); + if (!d) + return -ENOMEM; + + d->handler = h; + d->token = token; + + list_add_tail(&d->list, &kvm->arch.rtas_tokens); + + return 0; +} + +int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp) +{ + struct kvm_rtas_token_args args; + int rc; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + if (args.token) + rc = rtas_token_define(kvm, args.name, args.token); + else + rc = rtas_token_undefine(kvm, args.name); + + mutex_unlock(&kvm->lock); + + return rc; +} + +int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) +{ + struct rtas_token_definition *d; + struct rtas_args args; + rtas_arg_t *orig_rets; + gpa_t args_phys; + int rc; + + /* r4 contains the guest physical address of the RTAS args */ + args_phys = kvmppc_get_gpr(vcpu, 4); + + rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); + if (rc) + goto fail; + + /* + * args->rets is a pointer into args->args. Now that we've + * copied args we need to fix it up to point into our copy, + * not the guest args. We also need to save the original + * value so we can restore it on the way out. + */ + orig_rets = args.rets; + args.rets = &args.args[args.nargs]; + + mutex_lock(&vcpu->kvm->lock); + + rc = -ENOENT; + list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) { + if (d->token == args.token) { + d->handler->handler(vcpu, &args); + rc = 0; + break; + } + } + + mutex_unlock(&vcpu->kvm->lock); + + if (rc == 0) { + args.rets = orig_rets; + rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args)); + if (rc) + goto fail; + } + + return rc; + +fail: + /* + * We only get here if the guest has called RTAS with a bogus + * args pointer. That means we can't get to the args, and so we + * can't fail the RTAS call. So fail right out to userspace, + * which should kill the guest. + */ + return rc; +} + +void kvmppc_rtas_tokens_free(struct kvm *kvm) +{ + struct rtas_token_definition *d, *tmp; + + lockdep_assert_held(&kvm->lock); + + list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) { + list_del(&d->list); + kfree(d); + } +} diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c new file mode 100644 index 000000000000..94c1dd46b83d --- /dev/null +++ b/arch/powerpc/kvm/book3s_xics.c @@ -0,0 +1,1299 @@ +/* + * Copyright 2012 Michael Ellerman, IBM Corporation. + * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <linux/err.h> +#include <linux/gfp.h> +#include <linux/anon_inodes.h> + +#include <asm/uaccess.h> +#include <asm/kvm_book3s.h> +#include <asm/kvm_ppc.h> +#include <asm/hvcall.h> +#include <asm/xics.h> +#include <asm/debug.h> + +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +#include "book3s_xics.h" + +#if 1 +#define XICS_DBG(fmt...) do { } while (0) +#else +#define XICS_DBG(fmt...) trace_printk(fmt) +#endif + +#define ENABLE_REALMODE true +#define DEBUG_REALMODE false + +/* + * LOCKING + * ======= + * + * Each ICS has a mutex protecting the information about the IRQ + * sources and avoiding simultaneous deliveries if the same interrupt. + * + * ICP operations are done via a single compare & swap transaction + * (most ICP state fits in the union kvmppc_icp_state) + */ + +/* + * TODO + * ==== + * + * - To speed up resends, keep a bitmap of "resend" set bits in the + * ICS + * + * - Speed up server# -> ICP lookup (array ? hash table ?) + * + * - Make ICS lockless as well, or at least a per-interrupt lock or hashed + * locks array to improve scalability + */ + +/* -- ICS routines -- */ + +static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u32 new_irq); + +static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level, + bool report_status) +{ + struct ics_irq_state *state; + struct kvmppc_ics *ics; + u16 src; + + XICS_DBG("ics deliver %#x (level: %d)\n", irq, level); + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) { + XICS_DBG("ics_deliver_irq: IRQ 0x%06x not found !\n", irq); + return -EINVAL; + } + state = &ics->irq_state[src]; + if (!state->exists) + return -EINVAL; + + if (report_status) + return state->asserted; + + /* + * We set state->asserted locklessly. This should be fine as + * we are the only setter, thus concurrent access is undefined + * to begin with. + */ + if (level == KVM_INTERRUPT_SET_LEVEL) + state->asserted = 1; + else if (level == KVM_INTERRUPT_UNSET) { + state->asserted = 0; + return 0; + } + + /* Attempt delivery */ + icp_deliver_irq(xics, NULL, irq); + + return state->asserted; +} + +static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics, + struct kvmppc_icp *icp) +{ + int i; + + mutex_lock(&ics->lock); + + for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { + struct ics_irq_state *state = &ics->irq_state[i]; + + if (!state->resend) + continue; + + XICS_DBG("resend %#x prio %#x\n", state->number, + state->priority); + + mutex_unlock(&ics->lock); + icp_deliver_irq(xics, icp, state->number); + mutex_lock(&ics->lock); + } + + mutex_unlock(&ics->lock); +} + +static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, + struct ics_irq_state *state, + u32 server, u32 priority, u32 saved_priority) +{ + bool deliver; + + mutex_lock(&ics->lock); + + state->server = server; + state->priority = priority; + state->saved_priority = saved_priority; + deliver = false; + if ((state->masked_pending || state->resend) && priority != MASKED) { + state->masked_pending = 0; + deliver = true; + } + + mutex_unlock(&ics->lock); + + return deliver; +} + +int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_icp *icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u16 src; + + if (!xics) + return -ENODEV; + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return -EINVAL; + state = &ics->irq_state[src]; + + icp = kvmppc_xics_find_server(kvm, server); + if (!icp) + return -EINVAL; + + XICS_DBG("set_xive %#x server %#x prio %#x MP:%d RS:%d\n", + irq, server, priority, + state->masked_pending, state->resend); + + if (write_xive(xics, ics, state, server, priority, priority)) + icp_deliver_irq(xics, icp, irq); + + return 0; +} + +int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u16 src; + + if (!xics) + return -ENODEV; + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return -EINVAL; + state = &ics->irq_state[src]; + + mutex_lock(&ics->lock); + *server = state->server; + *priority = state->priority; + mutex_unlock(&ics->lock); + + return 0; +} + +int kvmppc_xics_int_on(struct kvm *kvm, u32 irq) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_icp *icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u16 src; + + if (!xics) + return -ENODEV; + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return -EINVAL; + state = &ics->irq_state[src]; + + icp = kvmppc_xics_find_server(kvm, state->server); + if (!icp) + return -EINVAL; + + if (write_xive(xics, ics, state, state->server, state->saved_priority, + state->saved_priority)) + icp_deliver_irq(xics, icp, irq); + + return 0; +} + +int kvmppc_xics_int_off(struct kvm *kvm, u32 irq) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u16 src; + + if (!xics) + return -ENODEV; + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return -EINVAL; + state = &ics->irq_state[src]; + + write_xive(xics, ics, state, state->server, MASKED, state->priority); + + return 0; +} + +/* -- ICP routines, including hcalls -- */ + +static inline bool icp_try_update(struct kvmppc_icp *icp, + union kvmppc_icp_state old, + union kvmppc_icp_state new, + bool change_self) +{ + bool success; + + /* Calculate new output value */ + new.out_ee = (new.xisr && (new.pending_pri < new.cppr)); + + /* Attempt atomic update */ + success = cmpxchg64(&icp->state.raw, old.raw, new.raw) == old.raw; + if (!success) + goto bail; + + XICS_DBG("UPD [%04x] - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n", + icp->server_num, + old.cppr, old.mfrr, old.pending_pri, old.xisr, + old.need_resend, old.out_ee); + XICS_DBG("UPD - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n", + new.cppr, new.mfrr, new.pending_pri, new.xisr, + new.need_resend, new.out_ee); + /* + * Check for output state update + * + * Note that this is racy since another processor could be updating + * the state already. This is why we never clear the interrupt output + * here, we only ever set it. The clear only happens prior to doing + * an update and only by the processor itself. Currently we do it + * in Accept (H_XIRR) and Up_Cppr (H_XPPR). + * + * We also do not try to figure out whether the EE state has changed, + * we unconditionally set it if the new state calls for it. The reason + * for that is that we opportunistically remove the pending interrupt + * flag when raising CPPR, so we need to set it back here if an + * interrupt is still pending. + */ + if (new.out_ee) { + kvmppc_book3s_queue_irqprio(icp->vcpu, + BOOK3S_INTERRUPT_EXTERNAL_LEVEL); + if (!change_self) + kvmppc_fast_vcpu_kick(icp->vcpu); + } + bail: + return success; +} + +static void icp_check_resend(struct kvmppc_xics *xics, + struct kvmppc_icp *icp) +{ + u32 icsid; + + /* Order this load with the test for need_resend in the caller */ + smp_rmb(); + for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) { + struct kvmppc_ics *ics = xics->ics[icsid]; + + if (!test_and_clear_bit(icsid, icp->resend_map)) + continue; + if (!ics) + continue; + ics_check_resend(xics, ics, icp); + } +} + +static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, + u32 *reject) +{ + union kvmppc_icp_state old_state, new_state; + bool success; + + XICS_DBG("try deliver %#x(P:%#x) to server %#x\n", irq, priority, + icp->server_num); + + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + *reject = 0; + + /* See if we can deliver */ + success = new_state.cppr > priority && + new_state.mfrr > priority && + new_state.pending_pri > priority; + + /* + * If we can, check for a rejection and perform the + * delivery + */ + if (success) { + *reject = new_state.xisr; + new_state.xisr = irq; + new_state.pending_pri = priority; + } else { + /* + * If we failed to deliver we set need_resend + * so a subsequent CPPR state change causes us + * to try a new delivery. + */ + new_state.need_resend = true; + } + + } while (!icp_try_update(icp, old_state, new_state, false)); + + return success; +} + +static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u32 new_irq) +{ + struct ics_irq_state *state; + struct kvmppc_ics *ics; + u32 reject; + u16 src; + + /* + * This is used both for initial delivery of an interrupt and + * for subsequent rejection. + * + * Rejection can be racy vs. resends. We have evaluated the + * rejection in an atomic ICP transaction which is now complete, + * so potentially the ICP can already accept the interrupt again. + * + * So we need to retry the delivery. Essentially the reject path + * boils down to a failed delivery. Always. + * + * Now the interrupt could also have moved to a different target, + * thus we may need to re-do the ICP lookup as well + */ + + again: + /* Get the ICS state and lock it */ + ics = kvmppc_xics_find_ics(xics, new_irq, &src); + if (!ics) { + XICS_DBG("icp_deliver_irq: IRQ 0x%06x not found !\n", new_irq); + return; + } + state = &ics->irq_state[src]; + + /* Get a lock on the ICS */ + mutex_lock(&ics->lock); + + /* Get our server */ + if (!icp || state->server != icp->server_num) { + icp = kvmppc_xics_find_server(xics->kvm, state->server); + if (!icp) { + pr_warn("icp_deliver_irq: IRQ 0x%06x server 0x%x not found !\n", + new_irq, state->server); + goto out; + } + } + + /* Clear the resend bit of that interrupt */ + state->resend = 0; + + /* + * If masked, bail out + * + * Note: PAPR doesn't mention anything about masked pending + * when doing a resend, only when doing a delivery. + * + * However that would have the effect of losing a masked + * interrupt that was rejected and isn't consistent with + * the whole masked_pending business which is about not + * losing interrupts that occur while masked. + * + * I don't differenciate normal deliveries and resends, this + * implementation will differ from PAPR and not lose such + * interrupts. + */ + if (state->priority == MASKED) { + XICS_DBG("irq %#x masked pending\n", new_irq); + state->masked_pending = 1; + goto out; + } + + /* + * Try the delivery, this will set the need_resend flag + * in the ICP as part of the atomic transaction if the + * delivery is not possible. + * + * Note that if successful, the new delivery might have itself + * rejected an interrupt that was "delivered" before we took the + * icp mutex. + * + * In this case we do the whole sequence all over again for the + * new guy. We cannot assume that the rejected interrupt is less + * favored than the new one, and thus doesn't need to be delivered, + * because by the time we exit icp_try_to_deliver() the target + * processor may well have alrady consumed & completed it, and thus + * the rejected interrupt might actually be already acceptable. + */ + if (icp_try_to_deliver(icp, new_irq, state->priority, &reject)) { + /* + * Delivery was successful, did we reject somebody else ? + */ + if (reject && reject != XICS_IPI) { + mutex_unlock(&ics->lock); + new_irq = reject; + goto again; + } + } else { + /* + * We failed to deliver the interrupt we need to set the + * resend map bit and mark the ICS state as needing a resend + */ + set_bit(ics->icsid, icp->resend_map); + state->resend = 1; + + /* + * If the need_resend flag got cleared in the ICP some time + * between icp_try_to_deliver() atomic update and now, then + * we know it might have missed the resend_map bit. So we + * retry + */ + smp_mb(); + if (!icp->state.need_resend) { + mutex_unlock(&ics->lock); + goto again; + } + } + out: + mutex_unlock(&ics->lock); +} + +static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u8 new_cppr) +{ + union kvmppc_icp_state old_state, new_state; + bool resend; + + /* + * This handles several related states in one operation: + * + * ICP State: Down_CPPR + * + * Load CPPR with new value and if the XISR is 0 + * then check for resends: + * + * ICP State: Resend + * + * If MFRR is more favored than CPPR, check for IPIs + * and notify ICS of a potential resend. This is done + * asynchronously (when used in real mode, we will have + * to exit here). + * + * We do not handle the complete Check_IPI as documented + * here. In the PAPR, this state will be used for both + * Set_MFRR and Down_CPPR. However, we know that we aren't + * changing the MFRR state here so we don't need to handle + * the case of an MFRR causing a reject of a pending irq, + * this will have been handled when the MFRR was set in the + * first place. + * + * Thus we don't have to handle rejects, only resends. + * + * When implementing real mode for HV KVM, resend will lead to + * a H_TOO_HARD return and the whole transaction will be handled + * in virtual mode. + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + /* Down_CPPR */ + new_state.cppr = new_cppr; + + /* + * Cut down Resend / Check_IPI / IPI + * + * The logic is that we cannot have a pending interrupt + * trumped by an IPI at this point (see above), so we + * know that either the pending interrupt is already an + * IPI (in which case we don't care to override it) or + * it's either more favored than us or non existent + */ + if (new_state.mfrr < new_cppr && + new_state.mfrr <= new_state.pending_pri) { + WARN_ON(new_state.xisr != XICS_IPI && + new_state.xisr != 0); + new_state.pending_pri = new_state.mfrr; + new_state.xisr = XICS_IPI; + } + + /* Latch/clear resend bit */ + resend = new_state.need_resend; + new_state.need_resend = 0; + + } while (!icp_try_update(icp, old_state, new_state, true)); + + /* + * Now handle resend checks. Those are asynchronous to the ICP + * state update in HW (ie bus transactions) so we can handle them + * separately here too + */ + if (resend) + icp_check_resend(xics, icp); +} + +static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 xirr; + + /* First, remove EE from the processor */ + kvmppc_book3s_dequeue_irqprio(icp->vcpu, + BOOK3S_INTERRUPT_EXTERNAL_LEVEL); + + /* + * ICP State: Accept_Interrupt + * + * Return the pending interrupt (if any) along with the + * current CPPR, then clear the XISR & set CPPR to the + * pending priority + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + xirr = old_state.xisr | (((u32)old_state.cppr) << 24); + if (!old_state.xisr) + break; + new_state.cppr = new_state.pending_pri; + new_state.pending_pri = 0xff; + new_state.xisr = 0; + + } while (!icp_try_update(icp, old_state, new_state, true)); + + XICS_DBG("h_xirr vcpu %d xirr %#x\n", vcpu->vcpu_id, xirr); + + return xirr; +} + +static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, + unsigned long mfrr) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp; + u32 reject; + bool resend; + bool local; + + XICS_DBG("h_ipi vcpu %d to server %lu mfrr %#lx\n", + vcpu->vcpu_id, server, mfrr); + + icp = vcpu->arch.icp; + local = icp->server_num == server; + if (!local) { + icp = kvmppc_xics_find_server(vcpu->kvm, server); + if (!icp) + return H_PARAMETER; + } + + /* + * ICP state: Set_MFRR + * + * If the CPPR is more favored than the new MFRR, then + * nothing needs to be rejected as there can be no XISR to + * reject. If the MFRR is being made less favored then + * there might be a previously-rejected interrupt needing + * to be resent. + * + * If the CPPR is less favored, then we might be replacing + * an interrupt, and thus need to possibly reject it as in + * + * ICP state: Check_IPI + */ + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + /* Set_MFRR */ + new_state.mfrr = mfrr; + + /* Check_IPI */ + reject = 0; + resend = false; + if (mfrr < new_state.cppr) { + /* Reject a pending interrupt if not an IPI */ + if (mfrr <= new_state.pending_pri) + reject = new_state.xisr; + new_state.pending_pri = mfrr; + new_state.xisr = XICS_IPI; + } + + if (mfrr > old_state.mfrr && mfrr > new_state.cppr) { + resend = new_state.need_resend; + new_state.need_resend = 0; + } + } while (!icp_try_update(icp, old_state, new_state, local)); + + /* Handle reject */ + if (reject && reject != XICS_IPI) + icp_deliver_irq(xics, icp, reject); + + /* Handle resend */ + if (resend) + icp_check_resend(xics, icp); + + return H_SUCCESS; +} + +static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server) +{ + union kvmppc_icp_state state; + struct kvmppc_icp *icp; + + icp = vcpu->arch.icp; + if (icp->server_num != server) { + icp = kvmppc_xics_find_server(vcpu->kvm, server); + if (!icp) + return H_PARAMETER; + } + state = ACCESS_ONCE(icp->state); + kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr); + kvmppc_set_gpr(vcpu, 5, state.mfrr); + return H_SUCCESS; +} + +static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) +{ + union kvmppc_icp_state old_state, new_state; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 reject; + + XICS_DBG("h_cppr vcpu %d cppr %#lx\n", vcpu->vcpu_id, cppr); + + /* + * ICP State: Set_CPPR + * + * We can safely compare the new value with the current + * value outside of the transaction as the CPPR is only + * ever changed by the processor on itself + */ + if (cppr > icp->state.cppr) + icp_down_cppr(xics, icp, cppr); + else if (cppr == icp->state.cppr) + return; + + /* + * ICP State: Up_CPPR + * + * The processor is raising its priority, this can result + * in a rejection of a pending interrupt: + * + * ICP State: Reject_Current + * + * We can remove EE from the current processor, the update + * transaction will set it again if needed + */ + kvmppc_book3s_dequeue_irqprio(icp->vcpu, + BOOK3S_INTERRUPT_EXTERNAL_LEVEL); + + do { + old_state = new_state = ACCESS_ONCE(icp->state); + + reject = 0; + new_state.cppr = cppr; + + if (cppr <= new_state.pending_pri) { + reject = new_state.xisr; + new_state.xisr = 0; + new_state.pending_pri = 0xff; + } + + } while (!icp_try_update(icp, old_state, new_state, true)); + + /* + * Check for rejects. They are handled by doing a new delivery + * attempt (see comments in icp_deliver_irq). + */ + if (reject && reject != XICS_IPI) + icp_deliver_irq(xics, icp, reject); +} + +static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; + u32 irq = xirr & 0x00ffffff; + u16 src; + + XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr); + + /* + * ICP State: EOI + * + * Note: If EOI is incorrectly used by SW to lower the CPPR + * value (ie more favored), we do not check for rejection of + * a pending interrupt, this is a SW error and PAPR sepcifies + * that we don't have to deal with it. + * + * The sending of an EOI to the ICS is handled after the + * CPPR update + * + * ICP State: Down_CPPR which we handle + * in a separate function as it's shared with H_CPPR. + */ + icp_down_cppr(xics, icp, xirr >> 24); + + /* IPIs have no EOI */ + if (irq == XICS_IPI) + return H_SUCCESS; + /* + * EOI handling: If the interrupt is still asserted, we need to + * resend it. We can take a lockless "peek" at the ICS state here. + * + * "Message" interrupts will never have "asserted" set + */ + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) { + XICS_DBG("h_eoi: IRQ 0x%06x not found !\n", irq); + return H_PARAMETER; + } + state = &ics->irq_state[src]; + + /* Still asserted, resend it */ + if (state->asserted) + icp_deliver_irq(xics, icp, irq); + + return H_SUCCESS; +} + +static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + + XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n", + hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt); + + if (icp->rm_action & XICS_RM_KICK_VCPU) + kvmppc_fast_vcpu_kick(icp->rm_kick_target); + if (icp->rm_action & XICS_RM_CHECK_RESEND) + icp_check_resend(xics, icp); + if (icp->rm_action & XICS_RM_REJECT) + icp_deliver_irq(xics, icp, icp->rm_reject); + + icp->rm_action = 0; + + return H_SUCCESS; +} + +int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + unsigned long res; + int rc = H_SUCCESS; + + /* Check if we have an ICP */ + if (!xics || !vcpu->arch.icp) + return H_HARDWARE; + + /* These requests don't have real-mode implementations at present */ + switch (req) { + case H_XIRR_X: + res = kvmppc_h_xirr(vcpu); + kvmppc_set_gpr(vcpu, 4, res); + kvmppc_set_gpr(vcpu, 5, get_tb()); + return rc; + case H_IPOLL: + rc = kvmppc_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4)); + return rc; + } + + /* Check for real mode returning too hard */ + if (xics->real_mode) + return kvmppc_xics_rm_complete(vcpu, req); + + switch (req) { + case H_XIRR: + res = kvmppc_h_xirr(vcpu); + kvmppc_set_gpr(vcpu, 4, res); + break; + case H_CPPR: + kvmppc_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4)); + break; + case H_EOI: + rc = kvmppc_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4)); + break; + case H_IPI: + rc = kvmppc_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + break; + } + + return rc; +} + + +/* -- Initialisation code etc. -- */ + +static int xics_debug_show(struct seq_file *m, void *private) +{ + struct kvmppc_xics *xics = m->private; + struct kvm *kvm = xics->kvm; + struct kvm_vcpu *vcpu; + int icsid, i; + + if (!kvm) + return 0; + + seq_printf(m, "=========\nICP state\n=========\n"); + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct kvmppc_icp *icp = vcpu->arch.icp; + union kvmppc_icp_state state; + + if (!icp) + continue; + + state.raw = ACCESS_ONCE(icp->state.raw); + seq_printf(m, "cpu server %#lx XIRR:%#x PPRI:%#x CPPR:%#x MFRR:%#x OUT:%d NR:%d\n", + icp->server_num, state.xisr, + state.pending_pri, state.cppr, state.mfrr, + state.out_ee, state.need_resend); + } + + for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) { + struct kvmppc_ics *ics = xics->ics[icsid]; + + if (!ics) + continue; + + seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n", + icsid); + + mutex_lock(&ics->lock); + + for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { + struct ics_irq_state *irq = &ics->irq_state[i]; + + seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x asserted %d resend %d masked pending %d\n", + irq->number, irq->server, irq->priority, + irq->saved_priority, irq->asserted, + irq->resend, irq->masked_pending); + + } + mutex_unlock(&ics->lock); + } + return 0; +} + +static int xics_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, xics_debug_show, inode->i_private); +} + +static const struct file_operations xics_debug_fops = { + .open = xics_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void xics_debugfs_init(struct kvmppc_xics *xics) +{ + char *name; + + name = kasprintf(GFP_KERNEL, "kvm-xics-%p", xics); + if (!name) { + pr_err("%s: no memory for name\n", __func__); + return; + } + + xics->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root, + xics, &xics_debug_fops); + + pr_debug("%s: created %s\n", __func__, name); + kfree(name); +} + +static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm, + struct kvmppc_xics *xics, int irq) +{ + struct kvmppc_ics *ics; + int i, icsid; + + icsid = irq >> KVMPPC_XICS_ICS_SHIFT; + + mutex_lock(&kvm->lock); + + /* ICS already exists - somebody else got here first */ + if (xics->ics[icsid]) + goto out; + + /* Create the ICS */ + ics = kzalloc(sizeof(struct kvmppc_ics), GFP_KERNEL); + if (!ics) + goto out; + + mutex_init(&ics->lock); + ics->icsid = icsid; + + for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { + ics->irq_state[i].number = (icsid << KVMPPC_XICS_ICS_SHIFT) | i; + ics->irq_state[i].priority = MASKED; + ics->irq_state[i].saved_priority = MASKED; + } + smp_wmb(); + xics->ics[icsid] = ics; + + if (icsid > xics->max_icsid) + xics->max_icsid = icsid; + + out: + mutex_unlock(&kvm->lock); + return xics->ics[icsid]; +} + +int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num) +{ + struct kvmppc_icp *icp; + + if (!vcpu->kvm->arch.xics) + return -ENODEV; + + if (kvmppc_xics_find_server(vcpu->kvm, server_num)) + return -EEXIST; + + icp = kzalloc(sizeof(struct kvmppc_icp), GFP_KERNEL); + if (!icp) + return -ENOMEM; + + icp->vcpu = vcpu; + icp->server_num = server_num; + icp->state.mfrr = MASKED; + icp->state.pending_pri = MASKED; + vcpu->arch.icp = icp; + + XICS_DBG("created server for vcpu %d\n", vcpu->vcpu_id); + + return 0; +} + +u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu) +{ + struct kvmppc_icp *icp = vcpu->arch.icp; + union kvmppc_icp_state state; + + if (!icp) + return 0; + state = icp->state; + return ((u64)state.cppr << KVM_REG_PPC_ICP_CPPR_SHIFT) | + ((u64)state.xisr << KVM_REG_PPC_ICP_XISR_SHIFT) | + ((u64)state.mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT) | + ((u64)state.pending_pri << KVM_REG_PPC_ICP_PPRI_SHIFT); +} + +int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval) +{ + struct kvmppc_icp *icp = vcpu->arch.icp; + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + union kvmppc_icp_state old_state, new_state; + struct kvmppc_ics *ics; + u8 cppr, mfrr, pending_pri; + u32 xisr; + u16 src; + bool resend; + + if (!icp || !xics) + return -ENOENT; + + cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT; + xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) & + KVM_REG_PPC_ICP_XISR_MASK; + mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT; + pending_pri = icpval >> KVM_REG_PPC_ICP_PPRI_SHIFT; + + /* Require the new state to be internally consistent */ + if (xisr == 0) { + if (pending_pri != 0xff) + return -EINVAL; + } else if (xisr == XICS_IPI) { + if (pending_pri != mfrr || pending_pri >= cppr) + return -EINVAL; + } else { + if (pending_pri >= mfrr || pending_pri >= cppr) + return -EINVAL; + ics = kvmppc_xics_find_ics(xics, xisr, &src); + if (!ics) + return -EINVAL; + } + + new_state.raw = 0; + new_state.cppr = cppr; + new_state.xisr = xisr; + new_state.mfrr = mfrr; + new_state.pending_pri = pending_pri; + + /* + * Deassert the CPU interrupt request. + * icp_try_update will reassert it if necessary. + */ + kvmppc_book3s_dequeue_irqprio(icp->vcpu, + BOOK3S_INTERRUPT_EXTERNAL_LEVEL); + + /* + * Note that if we displace an interrupt from old_state.xisr, + * we don't mark it as rejected. We expect userspace to set + * the state of the interrupt sources to be consistent with + * the ICP states (either before or afterwards, which doesn't + * matter). We do handle resends due to CPPR becoming less + * favoured because that is necessary to end up with a + * consistent state in the situation where userspace restores + * the ICS states before the ICP states. + */ + do { + old_state = ACCESS_ONCE(icp->state); + + if (new_state.mfrr <= old_state.mfrr) { + resend = false; + new_state.need_resend = old_state.need_resend; + } else { + resend = old_state.need_resend; + new_state.need_resend = 0; + } + } while (!icp_try_update(icp, old_state, new_state, false)); + + if (resend) + icp_check_resend(xics, icp); + + return 0; +} + +static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr) +{ + int ret; + struct kvmppc_ics *ics; + struct ics_irq_state *irqp; + u64 __user *ubufp = (u64 __user *) addr; + u16 idx; + u64 val, prio; + + ics = kvmppc_xics_find_ics(xics, irq, &idx); + if (!ics) + return -ENOENT; + + irqp = &ics->irq_state[idx]; + mutex_lock(&ics->lock); + ret = -ENOENT; + if (irqp->exists) { + val = irqp->server; + prio = irqp->priority; + if (prio == MASKED) { + val |= KVM_XICS_MASKED; + prio = irqp->saved_priority; + } + val |= prio << KVM_XICS_PRIORITY_SHIFT; + if (irqp->asserted) + val |= KVM_XICS_LEVEL_SENSITIVE | KVM_XICS_PENDING; + else if (irqp->masked_pending || irqp->resend) + val |= KVM_XICS_PENDING; + ret = 0; + } + mutex_unlock(&ics->lock); + + if (!ret && put_user(val, ubufp)) + ret = -EFAULT; + + return ret; +} + +static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) +{ + struct kvmppc_ics *ics; + struct ics_irq_state *irqp; + u64 __user *ubufp = (u64 __user *) addr; + u16 idx; + u64 val; + u8 prio; + u32 server; + + if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS) + return -ENOENT; + + ics = kvmppc_xics_find_ics(xics, irq, &idx); + if (!ics) { + ics = kvmppc_xics_create_ics(xics->kvm, xics, irq); + if (!ics) + return -ENOMEM; + } + irqp = &ics->irq_state[idx]; + if (get_user(val, ubufp)) + return -EFAULT; + + server = val & KVM_XICS_DESTINATION_MASK; + prio = val >> KVM_XICS_PRIORITY_SHIFT; + if (prio != MASKED && + kvmppc_xics_find_server(xics->kvm, server) == NULL) + return -EINVAL; + + mutex_lock(&ics->lock); + irqp->server = server; + irqp->saved_priority = prio; + if (val & KVM_XICS_MASKED) + prio = MASKED; + irqp->priority = prio; + irqp->resend = 0; + irqp->masked_pending = 0; + irqp->asserted = 0; + if ((val & KVM_XICS_PENDING) && (val & KVM_XICS_LEVEL_SENSITIVE)) + irqp->asserted = 1; + irqp->exists = 1; + mutex_unlock(&ics->lock); + + if (val & KVM_XICS_PENDING) + icp_deliver_irq(xics, NULL, irqp->number); + + return 0; +} + +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, + bool line_status) +{ + struct kvmppc_xics *xics = kvm->arch.xics; + + return ics_deliver_irq(xics, irq, level, line_status); +} + +static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + struct kvmppc_xics *xics = dev->private; + + switch (attr->group) { + case KVM_DEV_XICS_GRP_SOURCES: + return xics_set_source(xics, attr->attr, attr->addr); + } + return -ENXIO; +} + +static int xics_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + struct kvmppc_xics *xics = dev->private; + + switch (attr->group) { + case KVM_DEV_XICS_GRP_SOURCES: + return xics_get_source(xics, attr->attr, attr->addr); + } + return -ENXIO; +} + +static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_XICS_GRP_SOURCES: + if (attr->attr >= KVMPPC_XICS_FIRST_IRQ && + attr->attr < KVMPPC_XICS_NR_IRQS) + return 0; + break; + } + return -ENXIO; +} + +static void kvmppc_xics_free(struct kvm_device *dev) +{ + struct kvmppc_xics *xics = dev->private; + int i; + struct kvm *kvm = xics->kvm; + + debugfs_remove(xics->dentry); + + if (kvm) + kvm->arch.xics = NULL; + + for (i = 0; i <= xics->max_icsid; i++) + kfree(xics->ics[i]); + kfree(xics); + kfree(dev); +} + +static int kvmppc_xics_create(struct kvm_device *dev, u32 type) +{ + struct kvmppc_xics *xics; + struct kvm *kvm = dev->kvm; + int ret = 0; + + xics = kzalloc(sizeof(*xics), GFP_KERNEL); + if (!xics) + return -ENOMEM; + + dev->private = xics; + xics->dev = dev; + xics->kvm = kvm; + + /* Already there ? */ + mutex_lock(&kvm->lock); + if (kvm->arch.xics) + ret = -EEXIST; + else + kvm->arch.xics = xics; + mutex_unlock(&kvm->lock); + + if (ret) + return ret; + + xics_debugfs_init(xics); + +#ifdef CONFIG_KVM_BOOK3S_64_HV + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + /* Enable real mode support */ + xics->real_mode = ENABLE_REALMODE; + xics->real_mode_dbg = DEBUG_REALMODE; + } +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + + return 0; +} + +struct kvm_device_ops kvm_xics_ops = { + .name = "kvm-xics", + .create = kvmppc_xics_create, + .destroy = kvmppc_xics_free, + .set_attr = xics_set_attr, + .get_attr = xics_get_attr, + .has_attr = xics_has_attr, +}; + +int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, + u32 xcpu) +{ + struct kvmppc_xics *xics = dev->private; + int r = -EBUSY; + + if (dev->ops != &kvm_xics_ops) + return -EPERM; + if (xics->kvm != vcpu->kvm) + return -EPERM; + if (vcpu->arch.irq_type) + return -EBUSY; + + r = kvmppc_xics_create_icp(vcpu, xcpu); + if (!r) + vcpu->arch.irq_type = KVMPPC_IRQ_XICS; + + return r; +} + +void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.icp) + return; + kfree(vcpu->arch.icp); + vcpu->arch.icp = NULL; + vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT; +} diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h new file mode 100644 index 000000000000..dd9326c5c19b --- /dev/null +++ b/arch/powerpc/kvm/book3s_xics.h @@ -0,0 +1,130 @@ +/* + * Copyright 2012 Michael Ellerman, IBM Corporation. + * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#ifndef _KVM_PPC_BOOK3S_XICS_H +#define _KVM_PPC_BOOK3S_XICS_H + +/* + * We use a two-level tree to store interrupt source information. + * There are up to 1024 ICS nodes, each of which can represent + * 1024 sources. + */ +#define KVMPPC_XICS_MAX_ICS_ID 1023 +#define KVMPPC_XICS_ICS_SHIFT 10 +#define KVMPPC_XICS_IRQ_PER_ICS (1 << KVMPPC_XICS_ICS_SHIFT) +#define KVMPPC_XICS_SRC_MASK (KVMPPC_XICS_IRQ_PER_ICS - 1) + +/* + * Interrupt source numbers below this are reserved, for example + * 0 is "no interrupt", and 2 is used for IPIs. + */ +#define KVMPPC_XICS_FIRST_IRQ 16 +#define KVMPPC_XICS_NR_IRQS ((KVMPPC_XICS_MAX_ICS_ID + 1) * \ + KVMPPC_XICS_IRQ_PER_ICS) + +/* Priority value to use for disabling an interrupt */ +#define MASKED 0xff + +/* State for one irq source */ +struct ics_irq_state { + u32 number; + u32 server; + u8 priority; + u8 saved_priority; + u8 resend; + u8 masked_pending; + u8 asserted; /* Only for LSI */ + u8 exists; +}; + +/* Atomic ICP state, updated with a single compare & swap */ +union kvmppc_icp_state { + unsigned long raw; + struct { + u8 out_ee:1; + u8 need_resend:1; + u8 cppr; + u8 mfrr; + u8 pending_pri; + u32 xisr; + }; +}; + +/* One bit per ICS */ +#define ICP_RESEND_MAP_SIZE (KVMPPC_XICS_MAX_ICS_ID / BITS_PER_LONG + 1) + +struct kvmppc_icp { + struct kvm_vcpu *vcpu; + unsigned long server_num; + union kvmppc_icp_state state; + unsigned long resend_map[ICP_RESEND_MAP_SIZE]; + + /* Real mode might find something too hard, here's the action + * it might request from virtual mode + */ +#define XICS_RM_KICK_VCPU 0x1 +#define XICS_RM_CHECK_RESEND 0x2 +#define XICS_RM_REJECT 0x4 + u32 rm_action; + struct kvm_vcpu *rm_kick_target; + u32 rm_reject; + + /* Debug stuff for real mode */ + union kvmppc_icp_state rm_dbgstate; + struct kvm_vcpu *rm_dbgtgt; +}; + +struct kvmppc_ics { + struct mutex lock; + u16 icsid; + struct ics_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS]; +}; + +struct kvmppc_xics { + struct kvm *kvm; + struct kvm_device *dev; + struct dentry *dentry; + u32 max_icsid; + bool real_mode; + bool real_mode_dbg; + struct kvmppc_ics *ics[KVMPPC_XICS_MAX_ICS_ID + 1]; +}; + +static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm, + u32 nr) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num) + return vcpu->arch.icp; + } + return NULL; +} + +static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics, + u32 irq, u16 *source) +{ + u32 icsid = irq >> KVMPPC_XICS_ICS_SHIFT; + u16 src = irq & KVMPPC_XICS_SRC_MASK; + struct kvmppc_ics *ics; + + if (source) + *source = src; + if (icsid > KVMPPC_XICS_MAX_ICS_ID) + return NULL; + ics = xics->ics[icsid]; + if (!ics) + return NULL; + return ics; +} + + +#endif /* _KVM_PPC_BOOK3S_XICS_H */ diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 020923e43134..1020119226db 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -222,8 +222,7 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_booke_queue_irqprio(vcpu, prio); } -void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, - struct kvm_interrupt *irq) +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu) { clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions); clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions); @@ -347,7 +346,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, keep_irq = true; } - if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled) + if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_flags) update_epr = true; switch (priority) { @@ -428,8 +427,14 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, set_guest_esr(vcpu, vcpu->arch.queued_esr); if (update_dear == true) set_guest_dear(vcpu, vcpu->arch.queued_dear); - if (update_epr == true) - kvm_make_request(KVM_REQ_EPR_EXIT, vcpu); + if (update_epr == true) { + if (vcpu->arch.epr_flags & KVMPPC_EPR_USER) + kvm_make_request(KVM_REQ_EPR_EXIT, vcpu); + else if (vcpu->arch.epr_flags & KVMPPC_EPR_KERNEL) { + BUG_ON(vcpu->arch.irq_type != KVMPPC_IRQ_MPIC); + kvmppc_mpic_set_epr(vcpu); + } + } new_msr &= msr_mask; #if defined(CONFIG_64BIT) @@ -746,6 +751,9 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_core_queue_program(vcpu, ESR_PIL); return RESUME_HOST; + case EMULATE_EXIT_USER: + return RESUME_HOST; + default: BUG(); } @@ -1148,6 +1156,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, return r; } +static void kvmppc_set_tsr(struct kvm_vcpu *vcpu, u32 new_tsr) +{ + u32 old_tsr = vcpu->arch.tsr; + + vcpu->arch.tsr = new_tsr; + + if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS)) + arm_next_watchdog(vcpu); + + update_timer_ints(vcpu); +} + /* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { @@ -1287,16 +1307,8 @@ static int set_sregs_base(struct kvm_vcpu *vcpu, kvmppc_emulate_dec(vcpu); } - if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) { - u32 old_tsr = vcpu->arch.tsr; - - vcpu->arch.tsr = sregs->u.e.tsr; - - if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS)) - arm_next_watchdog(vcpu); - - update_timer_ints(vcpu); - } + if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) + kvmppc_set_tsr(vcpu, sregs->u.e.tsr); return 0; } @@ -1409,84 +1421,134 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) { - int r = -EINVAL; + int r = 0; + union kvmppc_one_reg val; + int size; + long int i; + + size = one_reg_size(reg->id); + if (size > sizeof(val)) + return -EINVAL; switch (reg->id) { case KVM_REG_PPC_IAC1: case KVM_REG_PPC_IAC2: case KVM_REG_PPC_IAC3: - case KVM_REG_PPC_IAC4: { - int iac = reg->id - KVM_REG_PPC_IAC1; - r = copy_to_user((u64 __user *)(long)reg->addr, - &vcpu->arch.dbg_reg.iac[iac], sizeof(u64)); + case KVM_REG_PPC_IAC4: + i = reg->id - KVM_REG_PPC_IAC1; + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac[i]); break; - } case KVM_REG_PPC_DAC1: - case KVM_REG_PPC_DAC2: { - int dac = reg->id - KVM_REG_PPC_DAC1; - r = copy_to_user((u64 __user *)(long)reg->addr, - &vcpu->arch.dbg_reg.dac[dac], sizeof(u64)); + case KVM_REG_PPC_DAC2: + i = reg->id - KVM_REG_PPC_DAC1; + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac[i]); break; - } case KVM_REG_PPC_EPR: { u32 epr = get_guest_epr(vcpu); - r = put_user(epr, (u32 __user *)(long)reg->addr); + val = get_reg_val(reg->id, epr); break; } #if defined(CONFIG_64BIT) case KVM_REG_PPC_EPCR: - r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr); + val = get_reg_val(reg->id, vcpu->arch.epcr); break; #endif + case KVM_REG_PPC_TCR: + val = get_reg_val(reg->id, vcpu->arch.tcr); + break; + case KVM_REG_PPC_TSR: + val = get_reg_val(reg->id, vcpu->arch.tsr); + break; + case KVM_REG_PPC_DEBUG_INST: + val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV); + break; default: + r = kvmppc_get_one_reg(vcpu, reg->id, &val); break; } + + if (r) + return r; + + if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size)) + r = -EFAULT; + return r; } int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) { - int r = -EINVAL; + int r = 0; + union kvmppc_one_reg val; + int size; + long int i; + + size = one_reg_size(reg->id); + if (size > sizeof(val)) + return -EINVAL; + + if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size)) + return -EFAULT; switch (reg->id) { case KVM_REG_PPC_IAC1: case KVM_REG_PPC_IAC2: case KVM_REG_PPC_IAC3: - case KVM_REG_PPC_IAC4: { - int iac = reg->id - KVM_REG_PPC_IAC1; - r = copy_from_user(&vcpu->arch.dbg_reg.iac[iac], - (u64 __user *)(long)reg->addr, sizeof(u64)); + case KVM_REG_PPC_IAC4: + i = reg->id - KVM_REG_PPC_IAC1; + vcpu->arch.dbg_reg.iac[i] = set_reg_val(reg->id, val); break; - } case KVM_REG_PPC_DAC1: - case KVM_REG_PPC_DAC2: { - int dac = reg->id - KVM_REG_PPC_DAC1; - r = copy_from_user(&vcpu->arch.dbg_reg.dac[dac], - (u64 __user *)(long)reg->addr, sizeof(u64)); + case KVM_REG_PPC_DAC2: + i = reg->id - KVM_REG_PPC_DAC1; + vcpu->arch.dbg_reg.dac[i] = set_reg_val(reg->id, val); break; - } case KVM_REG_PPC_EPR: { - u32 new_epr; - r = get_user(new_epr, (u32 __user *)(long)reg->addr); - if (!r) - kvmppc_set_epr(vcpu, new_epr); + u32 new_epr = set_reg_val(reg->id, val); + kvmppc_set_epr(vcpu, new_epr); break; } #if defined(CONFIG_64BIT) case KVM_REG_PPC_EPCR: { - u32 new_epcr; - r = get_user(new_epcr, (u32 __user *)(long)reg->addr); - if (r == 0) - kvmppc_set_epcr(vcpu, new_epcr); + u32 new_epcr = set_reg_val(reg->id, val); + kvmppc_set_epcr(vcpu, new_epcr); break; } #endif + case KVM_REG_PPC_OR_TSR: { + u32 tsr_bits = set_reg_val(reg->id, val); + kvmppc_set_tsr_bits(vcpu, tsr_bits); + break; + } + case KVM_REG_PPC_CLEAR_TSR: { + u32 tsr_bits = set_reg_val(reg->id, val); + kvmppc_clr_tsr_bits(vcpu, tsr_bits); + break; + } + case KVM_REG_PPC_TSR: { + u32 tsr = set_reg_val(reg->id, val); + kvmppc_set_tsr(vcpu, tsr); + break; + } + case KVM_REG_PPC_TCR: { + u32 tcr = set_reg_val(reg->id, val); + kvmppc_set_tcr(vcpu, tcr); + break; + } default: + r = kvmppc_set_one_reg(vcpu, reg->id, &val); break; } + return r; } +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + return -EINVAL; +} + int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -ENOTSUPP; @@ -1531,7 +1593,7 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old) + const struct kvm_memory_slot *old) { } diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index f4bb55c96517..2c6deb5ef2fe 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -54,8 +54,7 @@ (1<<BOOKE_INTERRUPT_DTLB_MISS) | \ (1<<BOOKE_INTERRUPT_ALIGNMENT)) -.macro KVM_HANDLER ivor_nr scratch srr0 -_GLOBAL(kvmppc_handler_\ivor_nr) +.macro __KVM_HANDLER ivor_nr scratch srr0 /* Get pointer to vcpu and record exit number. */ mtspr \scratch , r4 mfspr r4, SPRN_SPRG_THREAD @@ -76,6 +75,43 @@ _GLOBAL(kvmppc_handler_\ivor_nr) bctr .endm +.macro KVM_HANDLER ivor_nr scratch srr0 +_GLOBAL(kvmppc_handler_\ivor_nr) + __KVM_HANDLER \ivor_nr \scratch \srr0 +.endm + +.macro KVM_DBG_HANDLER ivor_nr scratch srr0 +_GLOBAL(kvmppc_handler_\ivor_nr) + mtspr \scratch, r4 + mfspr r4, SPRN_SPRG_THREAD + lwz r4, THREAD_KVM_VCPU(r4) + stw r3, VCPU_CRIT_SAVE(r4) + mfcr r3 + mfspr r4, SPRN_CSRR1 + andi. r4, r4, MSR_PR + bne 1f + /* debug interrupt happened in enter/exit path */ + mfspr r4, SPRN_CSRR1 + rlwinm r4, r4, 0, ~MSR_DE + mtspr SPRN_CSRR1, r4 + lis r4, 0xffff + ori r4, r4, 0xffff + mtspr SPRN_DBSR, r4 + mfspr r4, SPRN_SPRG_THREAD + lwz r4, THREAD_KVM_VCPU(r4) + mtcr r3 + lwz r3, VCPU_CRIT_SAVE(r4) + mfspr r4, \scratch + rfci +1: /* debug interrupt happened in guest */ + mtcr r3 + mfspr r4, SPRN_SPRG_THREAD + lwz r4, THREAD_KVM_VCPU(r4) + lwz r3, VCPU_CRIT_SAVE(r4) + mfspr r4, \scratch + __KVM_HANDLER \ivor_nr \scratch \srr0 +.endm + .macro KVM_HANDLER_ADDR ivor_nr .long kvmppc_handler_\ivor_nr .endm @@ -100,7 +136,7 @@ KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0 KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 -KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_DBG_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0 diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 6dd4de7802bf..ce6b73c29612 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -425,6 +425,20 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvmppc_set_sregs_ivor(vcpu, sregs); } +int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); + return r; +} + +int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); + return r; +} + struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_e500 *vcpu_e500; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd43655f..c2e5e98453a6 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -23,20 +23,27 @@ #include <asm/mmu-book3e.h> #include <asm/tlb.h> +enum vcpu_ftr { + VCPU_FTR_MMU_V2 +}; + #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 +70,6 @@ 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; @@ -139,6 +135,10 @@ void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500); void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvmppc_get_one_reg_e500_tlb(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val); +int kvmppc_set_one_reg_e500_tlb(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val); #ifdef CONFIG_KVM_E500V2 unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500, @@ -303,4 +303,18 @@ static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu) #define get_tlb_sts(gtlbe) (MAS1_TS) #endif /* !BOOKE_HV */ +static inline bool has_feature(const struct kvm_vcpu *vcpu, + enum vcpu_ftr ftr) +{ + bool has_ftr; + switch (ftr) { + case VCPU_FTR_MMU_V2: + has_ftr = ((vcpu->arch.mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2); + break; + default: + return false; + } + return has_ftr; +} + #endif /* KVM_E500_H */ diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index e78f353a836a..b10a01243abd 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -284,6 +284,16 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) case SPRN_TLB1CFG: *spr_val = vcpu->arch.tlbcfg[1]; break; + case SPRN_TLB0PS: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + *spr_val = vcpu->arch.tlbps[0]; + break; + case SPRN_TLB1PS: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + *spr_val = vcpu->arch.tlbps[1]; + break; case SPRN_L1CSR0: *spr_val = vcpu_e500->l1csr0; break; @@ -307,6 +317,15 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) case SPRN_MMUCFG: *spr_val = vcpu->arch.mmucfg; break; + case SPRN_EPTCFG: + if (!has_feature(vcpu, VCPU_FTR_MMU_V2)) + return EMULATE_FAIL; + /* + * Legacy Linux guests access EPTCFG register even if the E.PT + * category is disabled in the VM. Give them a chance to live. + */ + *spr_val = vcpu->arch.eptcfg; + break; /* extra exceptions */ case SPRN_IVOR32: diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 5c4475983f78..c41a5a96b558 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -596,6 +596,140 @@ int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return 0; } +int kvmppc_get_one_reg_e500_tlb(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = 0; + long int i; + + switch (id) { + case KVM_REG_PPC_MAS0: + *val = get_reg_val(id, vcpu->arch.shared->mas0); + break; + case KVM_REG_PPC_MAS1: + *val = get_reg_val(id, vcpu->arch.shared->mas1); + break; + case KVM_REG_PPC_MAS2: + *val = get_reg_val(id, vcpu->arch.shared->mas2); + break; + case KVM_REG_PPC_MAS7_3: + *val = get_reg_val(id, vcpu->arch.shared->mas7_3); + break; + case KVM_REG_PPC_MAS4: + *val = get_reg_val(id, vcpu->arch.shared->mas4); + break; + case KVM_REG_PPC_MAS6: + *val = get_reg_val(id, vcpu->arch.shared->mas6); + break; + case KVM_REG_PPC_MMUCFG: + *val = get_reg_val(id, vcpu->arch.mmucfg); + break; + case KVM_REG_PPC_EPTCFG: + *val = get_reg_val(id, vcpu->arch.eptcfg); + break; + case KVM_REG_PPC_TLB0CFG: + case KVM_REG_PPC_TLB1CFG: + case KVM_REG_PPC_TLB2CFG: + case KVM_REG_PPC_TLB3CFG: + i = id - KVM_REG_PPC_TLB0CFG; + *val = get_reg_val(id, vcpu->arch.tlbcfg[i]); + break; + case KVM_REG_PPC_TLB0PS: + case KVM_REG_PPC_TLB1PS: + case KVM_REG_PPC_TLB2PS: + case KVM_REG_PPC_TLB3PS: + i = id - KVM_REG_PPC_TLB0PS; + *val = get_reg_val(id, vcpu->arch.tlbps[i]); + break; + default: + r = -EINVAL; + break; + } + + return r; +} + +int kvmppc_set_one_reg_e500_tlb(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = 0; + long int i; + + switch (id) { + case KVM_REG_PPC_MAS0: + vcpu->arch.shared->mas0 = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MAS1: + vcpu->arch.shared->mas1 = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MAS2: + vcpu->arch.shared->mas2 = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MAS7_3: + vcpu->arch.shared->mas7_3 = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MAS4: + vcpu->arch.shared->mas4 = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MAS6: + vcpu->arch.shared->mas6 = set_reg_val(id, *val); + break; + /* Only allow MMU registers to be set to the config supported by KVM */ + case KVM_REG_PPC_MMUCFG: { + u32 reg = set_reg_val(id, *val); + if (reg != vcpu->arch.mmucfg) + r = -EINVAL; + break; + } + case KVM_REG_PPC_EPTCFG: { + u32 reg = set_reg_val(id, *val); + if (reg != vcpu->arch.eptcfg) + r = -EINVAL; + break; + } + case KVM_REG_PPC_TLB0CFG: + case KVM_REG_PPC_TLB1CFG: + case KVM_REG_PPC_TLB2CFG: + case KVM_REG_PPC_TLB3CFG: { + /* MMU geometry (N_ENTRY/ASSOC) can be set only using SW_TLB */ + u32 reg = set_reg_val(id, *val); + i = id - KVM_REG_PPC_TLB0CFG; + if (reg != vcpu->arch.tlbcfg[i]) + r = -EINVAL; + break; + } + case KVM_REG_PPC_TLB0PS: + case KVM_REG_PPC_TLB1PS: + case KVM_REG_PPC_TLB2PS: + case KVM_REG_PPC_TLB3PS: { + u32 reg = set_reg_val(id, *val); + i = id - KVM_REG_PPC_TLB0PS; + if (reg != vcpu->arch.tlbps[i]) + r = -EINVAL; + break; + } + default: + r = -EINVAL; + break; + } + + return r; +} + +static int vcpu_mmu_geometry_update(struct kvm_vcpu *vcpu, + struct kvm_book3e_206_tlb_params *params) +{ + vcpu->arch.tlbcfg[0] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); + if (params->tlb_sizes[0] <= 2048) + vcpu->arch.tlbcfg[0] |= params->tlb_sizes[0]; + vcpu->arch.tlbcfg[0] |= params->tlb_ways[0] << TLBnCFG_ASSOC_SHIFT; + + vcpu->arch.tlbcfg[1] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); + vcpu->arch.tlbcfg[1] |= params->tlb_sizes[1]; + vcpu->arch.tlbcfg[1] |= params->tlb_ways[1] << TLBnCFG_ASSOC_SHIFT; + return 0; +} + int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, struct kvm_config_tlb *cfg) { @@ -692,16 +826,8 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0]; - vcpu->arch.mmucfg = mfspr(SPRN_MMUCFG) & ~MMUCFG_LPIDSIZE; - - vcpu->arch.tlbcfg[0] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); - if (params.tlb_sizes[0] <= 2048) - vcpu->arch.tlbcfg[0] |= params.tlb_sizes[0]; - vcpu->arch.tlbcfg[0] |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT; - - vcpu->arch.tlbcfg[1] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); - vcpu->arch.tlbcfg[1] |= params.tlb_sizes[1]; - vcpu->arch.tlbcfg[1] |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT; + /* Update vcpu's MMU geometry based on SW_TLB input */ + vcpu_mmu_geometry_update(vcpu, ¶ms); vcpu_e500->shared_tlb_pages = pages; vcpu_e500->num_shared_tlb_pages = num_pages; @@ -737,6 +863,39 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, return 0; } +/* Vcpu's MMU default configuration */ +static int vcpu_mmu_init(struct kvm_vcpu *vcpu, + struct kvmppc_e500_tlb_params *params) +{ + /* Initialize RASIZE, PIDSIZE, NTLBS and MAVN fields with host values*/ + vcpu->arch.mmucfg = mfspr(SPRN_MMUCFG) & ~MMUCFG_LPIDSIZE; + + /* Initialize TLBnCFG fields with host values and SW_TLB geometry*/ + vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) & + ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); + vcpu->arch.tlbcfg[0] |= params[0].entries; + vcpu->arch.tlbcfg[0] |= params[0].ways << TLBnCFG_ASSOC_SHIFT; + + vcpu->arch.tlbcfg[1] = mfspr(SPRN_TLB1CFG) & + ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); + vcpu->arch.tlbcfg[1] |= params[1].entries; + vcpu->arch.tlbcfg[1] |= params[1].ways << TLBnCFG_ASSOC_SHIFT; + + if (has_feature(vcpu, VCPU_FTR_MMU_V2)) { + vcpu->arch.tlbps[0] = mfspr(SPRN_TLB0PS); + vcpu->arch.tlbps[1] = mfspr(SPRN_TLB1PS); + + vcpu->arch.mmucfg &= ~MMUCFG_LRAT; + + /* Guest mmu emulation currently doesn't handle E.PT */ + vcpu->arch.eptcfg = 0; + vcpu->arch.tlbcfg[0] &= ~TLBnCFG_PT; + vcpu->arch.tlbcfg[1] &= ~TLBnCFG_IND; + } + + return 0; +} + int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) { struct kvm_vcpu *vcpu = &vcpu_e500->vcpu; @@ -781,18 +940,7 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) if (!vcpu_e500->g2h_tlb1_map) goto err; - /* Init TLB configuration register */ - vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) & - ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); - vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[0].entries; - vcpu->arch.tlbcfg[0] |= - vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT; - - vcpu->arch.tlbcfg[1] = mfspr(SPRN_TLB1CFG) & - ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC); - vcpu->arch.tlbcfg[1] |= vcpu_e500->gtlb_params[1].entries; - vcpu->arch.tlbcfg[1] |= - vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT; + vcpu_mmu_init(vcpu, vcpu_e500->gtlb_params); kvmppc_recalc_tlb1map_range(vcpu_e500); return 0; 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..753cc99eff2b 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); } @@ -172,6 +177,8 @@ int kvmppc_core_check_processor_compat(void) r = 0; else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0) r = 0; + else if (strcmp(cur_cpu_spec->cpu_name, "e6500") == 0) + r = 0; else r = -ENOTSUPP; @@ -255,6 +262,20 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvmppc_set_sregs_ivor(vcpu, sregs); } +int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); + return r; +} + +int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) +{ + int r = kvmppc_set_one_reg_e500_tlb(vcpu, id, val); + return r; +} + struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_e500 *vcpu_e500; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 7a73b6f72a8b..631a2650e4e4 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -38,6 +38,7 @@ #define OP_31_XOP_TRAP 4 #define OP_31_XOP_LWZX 23 +#define OP_31_XOP_DCBST 54 #define OP_31_XOP_TRAP_64 68 #define OP_31_XOP_DCBF 86 #define OP_31_XOP_LBZX 87 @@ -370,6 +371,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) emulated = kvmppc_emulate_mtspr(vcpu, sprn, rs); break; + case OP_31_XOP_DCBST: case OP_31_XOP_DCBF: case OP_31_XOP_DCBI: /* Do nothing. The guest is performing dcbi because diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h new file mode 100644 index 000000000000..5a9a10b90762 --- /dev/null +++ b/arch/powerpc/kvm/irq.h @@ -0,0 +1,20 @@ +#ifndef __IRQ_H +#define __IRQ_H + +#include <linux/kvm_host.h> + +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + int ret = 0; + +#ifdef CONFIG_KVM_MPIC + ret = ret || (kvm->arch.mpic != NULL); +#endif +#ifdef CONFIG_KVM_XICS + ret = ret || (kvm->arch.xics != NULL); +#endif + smp_rmb(); + return ret; +} + +#endif diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c new file mode 100644 index 000000000000..2861ae9eaae6 --- /dev/null +++ b/arch/powerpc/kvm/mpic.c @@ -0,0 +1,1853 @@ +/* + * OpenPIC emulation + * + * Copyright (c) 2004 Jocelyn Mayer + * 2011 Alexander Graf + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/kvm_host.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/anon_inodes.h> +#include <asm/uaccess.h> +#include <asm/mpic.h> +#include <asm/kvm_para.h> +#include <asm/kvm_host.h> +#include <asm/kvm_ppc.h> +#include "iodev.h" + +#define MAX_CPU 32 +#define MAX_SRC 256 +#define MAX_TMR 4 +#define MAX_IPI 4 +#define MAX_MSI 8 +#define MAX_IRQ (MAX_SRC + MAX_IPI + MAX_TMR) +#define VID 0x03 /* MPIC version ID */ + +/* OpenPIC capability flags */ +#define OPENPIC_FLAG_IDR_CRIT (1 << 0) +#define OPENPIC_FLAG_ILR (2 << 0) + +/* OpenPIC address map */ +#define OPENPIC_REG_SIZE 0x40000 +#define OPENPIC_GLB_REG_START 0x0 +#define OPENPIC_GLB_REG_SIZE 0x10F0 +#define OPENPIC_TMR_REG_START 0x10F0 +#define OPENPIC_TMR_REG_SIZE 0x220 +#define OPENPIC_MSI_REG_START 0x1600 +#define OPENPIC_MSI_REG_SIZE 0x200 +#define OPENPIC_SUMMARY_REG_START 0x3800 +#define OPENPIC_SUMMARY_REG_SIZE 0x800 +#define OPENPIC_SRC_REG_START 0x10000 +#define OPENPIC_SRC_REG_SIZE (MAX_SRC * 0x20) +#define OPENPIC_CPU_REG_START 0x20000 +#define OPENPIC_CPU_REG_SIZE (0x100 + ((MAX_CPU - 1) * 0x1000)) + +struct fsl_mpic_info { + int max_ext; +}; + +static struct fsl_mpic_info fsl_mpic_20 = { + .max_ext = 12, +}; + +static struct fsl_mpic_info fsl_mpic_42 = { + .max_ext = 12, +}; + +#define FRR_NIRQ_SHIFT 16 +#define FRR_NCPU_SHIFT 8 +#define FRR_VID_SHIFT 0 + +#define VID_REVISION_1_2 2 +#define VID_REVISION_1_3 3 + +#define VIR_GENERIC 0x00000000 /* Generic Vendor ID */ + +#define GCR_RESET 0x80000000 +#define GCR_MODE_PASS 0x00000000 +#define GCR_MODE_MIXED 0x20000000 +#define GCR_MODE_PROXY 0x60000000 + +#define TBCR_CI 0x80000000 /* count inhibit */ +#define TCCR_TOG 0x80000000 /* toggles when decrement to zero */ + +#define IDR_EP_SHIFT 31 +#define IDR_EP_MASK (1 << IDR_EP_SHIFT) +#define IDR_CI0_SHIFT 30 +#define IDR_CI1_SHIFT 29 +#define IDR_P1_SHIFT 1 +#define IDR_P0_SHIFT 0 + +#define ILR_INTTGT_MASK 0x000000ff +#define ILR_INTTGT_INT 0x00 +#define ILR_INTTGT_CINT 0x01 /* critical */ +#define ILR_INTTGT_MCP 0x02 /* machine check */ +#define NUM_OUTPUTS 3 + +#define MSIIR_OFFSET 0x140 +#define MSIIR_SRS_SHIFT 29 +#define MSIIR_SRS_MASK (0x7 << MSIIR_SRS_SHIFT) +#define MSIIR_IBS_SHIFT 24 +#define MSIIR_IBS_MASK (0x1f << MSIIR_IBS_SHIFT) + +static int get_current_cpu(void) +{ +#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE) + struct kvm_vcpu *vcpu = current->thread.kvm_vcpu; + return vcpu ? vcpu->arch.irq_cpu_id : -1; +#else + /* XXX */ + return -1; +#endif +} + +static int openpic_cpu_write_internal(void *opaque, gpa_t addr, + u32 val, int idx); +static int openpic_cpu_read_internal(void *opaque, gpa_t addr, + u32 *ptr, int idx); + +enum irq_type { + IRQ_TYPE_NORMAL = 0, + IRQ_TYPE_FSLINT, /* FSL internal interrupt -- level only */ + IRQ_TYPE_FSLSPECIAL, /* FSL timer/IPI interrupt, edge, no polarity */ +}; + +struct irq_queue { + /* Round up to the nearest 64 IRQs so that the queue length + * won't change when moving between 32 and 64 bit hosts. + */ + unsigned long queue[BITS_TO_LONGS((MAX_IRQ + 63) & ~63)]; + int next; + int priority; +}; + +struct irq_source { + uint32_t ivpr; /* IRQ vector/priority register */ + uint32_t idr; /* IRQ destination register */ + uint32_t destmask; /* bitmap of CPU destinations */ + int last_cpu; + int output; /* IRQ level, e.g. ILR_INTTGT_INT */ + int pending; /* TRUE if IRQ is pending */ + enum irq_type type; + bool level:1; /* level-triggered */ + bool nomask:1; /* critical interrupts ignore mask on some FSL MPICs */ +}; + +#define IVPR_MASK_SHIFT 31 +#define IVPR_MASK_MASK (1 << IVPR_MASK_SHIFT) +#define IVPR_ACTIVITY_SHIFT 30 +#define IVPR_ACTIVITY_MASK (1 << IVPR_ACTIVITY_SHIFT) +#define IVPR_MODE_SHIFT 29 +#define IVPR_MODE_MASK (1 << IVPR_MODE_SHIFT) +#define IVPR_POLARITY_SHIFT 23 +#define IVPR_POLARITY_MASK (1 << IVPR_POLARITY_SHIFT) +#define IVPR_SENSE_SHIFT 22 +#define IVPR_SENSE_MASK (1 << IVPR_SENSE_SHIFT) + +#define IVPR_PRIORITY_MASK (0xF << 16) +#define IVPR_PRIORITY(_ivprr_) ((int)(((_ivprr_) & IVPR_PRIORITY_MASK) >> 16)) +#define IVPR_VECTOR(opp, _ivprr_) ((_ivprr_) & (opp)->vector_mask) + +/* IDR[EP/CI] are only for FSL MPIC prior to v4.0 */ +#define IDR_EP 0x80000000 /* external pin */ +#define IDR_CI 0x40000000 /* critical interrupt */ + +struct irq_dest { + struct kvm_vcpu *vcpu; + + int32_t ctpr; /* CPU current task priority */ + struct irq_queue raised; + struct irq_queue servicing; + + /* Count of IRQ sources asserting on non-INT outputs */ + uint32_t outputs_active[NUM_OUTPUTS]; +}; + +#define MAX_MMIO_REGIONS 10 + +struct openpic { + struct kvm *kvm; + struct kvm_device *dev; + struct kvm_io_device mmio; + const struct mem_reg *mmio_regions[MAX_MMIO_REGIONS]; + int num_mmio_regions; + + gpa_t reg_base; + spinlock_t lock; + + /* Behavior control */ + struct fsl_mpic_info *fsl; + uint32_t model; + uint32_t flags; + uint32_t nb_irqs; + uint32_t vid; + uint32_t vir; /* Vendor identification register */ + uint32_t vector_mask; + uint32_t tfrr_reset; + uint32_t ivpr_reset; + uint32_t idr_reset; + uint32_t brr1; + uint32_t mpic_mode_mask; + + /* Global registers */ + uint32_t frr; /* Feature reporting register */ + uint32_t gcr; /* Global configuration register */ + uint32_t pir; /* Processor initialization register */ + uint32_t spve; /* Spurious vector register */ + uint32_t tfrr; /* Timer frequency reporting register */ + /* Source registers */ + struct irq_source src[MAX_IRQ]; + /* Local registers per output pin */ + struct irq_dest dst[MAX_CPU]; + uint32_t nb_cpus; + /* Timer registers */ + struct { + uint32_t tccr; /* Global timer current count register */ + uint32_t tbcr; /* Global timer base count register */ + } timers[MAX_TMR]; + /* Shared MSI registers */ + struct { + uint32_t msir; /* Shared Message Signaled Interrupt Register */ + } msi[MAX_MSI]; + uint32_t max_irq; + uint32_t irq_ipi0; + uint32_t irq_tim0; + uint32_t irq_msi; +}; + + +static void mpic_irq_raise(struct openpic *opp, struct irq_dest *dst, + int output) +{ + struct kvm_interrupt irq = { + .irq = KVM_INTERRUPT_SET_LEVEL, + }; + + if (!dst->vcpu) { + pr_debug("%s: destination cpu %d does not exist\n", + __func__, (int)(dst - &opp->dst[0])); + return; + } + + pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id, + output); + + if (output != ILR_INTTGT_INT) /* TODO */ + return; + + kvm_vcpu_ioctl_interrupt(dst->vcpu, &irq); +} + +static void mpic_irq_lower(struct openpic *opp, struct irq_dest *dst, + int output) +{ + if (!dst->vcpu) { + pr_debug("%s: destination cpu %d does not exist\n", + __func__, (int)(dst - &opp->dst[0])); + return; + } + + pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id, + output); + + if (output != ILR_INTTGT_INT) /* TODO */ + return; + + kvmppc_core_dequeue_external(dst->vcpu); +} + +static inline void IRQ_setbit(struct irq_queue *q, int n_IRQ) +{ + set_bit(n_IRQ, q->queue); +} + +static inline void IRQ_resetbit(struct irq_queue *q, int n_IRQ) +{ + clear_bit(n_IRQ, q->queue); +} + +static inline int IRQ_testbit(struct irq_queue *q, int n_IRQ) +{ + return test_bit(n_IRQ, q->queue); +} + +static void IRQ_check(struct openpic *opp, struct irq_queue *q) +{ + int irq = -1; + int next = -1; + int priority = -1; + + for (;;) { + irq = find_next_bit(q->queue, opp->max_irq, irq + 1); + if (irq == opp->max_irq) + break; + + pr_debug("IRQ_check: irq %d set ivpr_pr=%d pr=%d\n", + irq, IVPR_PRIORITY(opp->src[irq].ivpr), priority); + + if (IVPR_PRIORITY(opp->src[irq].ivpr) > priority) { + next = irq; + priority = IVPR_PRIORITY(opp->src[irq].ivpr); + } + } + + q->next = next; + q->priority = priority; +} + +static int IRQ_get_next(struct openpic *opp, struct irq_queue *q) +{ + /* XXX: optimize */ + IRQ_check(opp, q); + + return q->next; +} + +static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ, + bool active, bool was_active) +{ + struct irq_dest *dst; + struct irq_source *src; + int priority; + + dst = &opp->dst[n_CPU]; + src = &opp->src[n_IRQ]; + + pr_debug("%s: IRQ %d active %d was %d\n", + __func__, n_IRQ, active, was_active); + + if (src->output != ILR_INTTGT_INT) { + pr_debug("%s: output %d irq %d active %d was %d count %d\n", + __func__, src->output, n_IRQ, active, was_active, + dst->outputs_active[src->output]); + + /* On Freescale MPIC, critical interrupts ignore priority, + * IACK, EOI, etc. Before MPIC v4.1 they also ignore + * masking. + */ + if (active) { + if (!was_active && + dst->outputs_active[src->output]++ == 0) { + pr_debug("%s: Raise OpenPIC output %d cpu %d irq %d\n", + __func__, src->output, n_CPU, n_IRQ); + mpic_irq_raise(opp, dst, src->output); + } + } else { + if (was_active && + --dst->outputs_active[src->output] == 0) { + pr_debug("%s: Lower OpenPIC output %d cpu %d irq %d\n", + __func__, src->output, n_CPU, n_IRQ); + mpic_irq_lower(opp, dst, src->output); + } + } + + return; + } + + priority = IVPR_PRIORITY(src->ivpr); + + /* Even if the interrupt doesn't have enough priority, + * it is still raised, in case ctpr is lowered later. + */ + if (active) + IRQ_setbit(&dst->raised, n_IRQ); + else + IRQ_resetbit(&dst->raised, n_IRQ); + + IRQ_check(opp, &dst->raised); + + if (active && priority <= dst->ctpr) { + pr_debug("%s: IRQ %d priority %d too low for ctpr %d on CPU %d\n", + __func__, n_IRQ, priority, dst->ctpr, n_CPU); + active = 0; + } + + if (active) { + if (IRQ_get_next(opp, &dst->servicing) >= 0 && + priority <= dst->servicing.priority) { + pr_debug("%s: IRQ %d is hidden by servicing IRQ %d on CPU %d\n", + __func__, n_IRQ, dst->servicing.next, n_CPU); + } else { + pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d/%d\n", + __func__, n_CPU, n_IRQ, dst->raised.next); + mpic_irq_raise(opp, dst, ILR_INTTGT_INT); + } + } else { + IRQ_get_next(opp, &dst->servicing); + if (dst->raised.priority > dst->ctpr && + dst->raised.priority > dst->servicing.priority) { + pr_debug("%s: IRQ %d inactive, IRQ %d prio %d above %d/%d, CPU %d\n", + __func__, n_IRQ, dst->raised.next, + dst->raised.priority, dst->ctpr, + dst->servicing.priority, n_CPU); + /* IRQ line stays asserted */ + } else { + pr_debug("%s: IRQ %d inactive, current prio %d/%d, CPU %d\n", + __func__, n_IRQ, dst->ctpr, + dst->servicing.priority, n_CPU); + mpic_irq_lower(opp, dst, ILR_INTTGT_INT); + } + } +} + +/* update pic state because registers for n_IRQ have changed value */ +static void openpic_update_irq(struct openpic *opp, int n_IRQ) +{ + struct irq_source *src; + bool active, was_active; + int i; + + src = &opp->src[n_IRQ]; + active = src->pending; + + if ((src->ivpr & IVPR_MASK_MASK) && !src->nomask) { + /* Interrupt source is disabled */ + pr_debug("%s: IRQ %d is disabled\n", __func__, n_IRQ); + active = false; + } + + was_active = !!(src->ivpr & IVPR_ACTIVITY_MASK); + + /* + * We don't have a similar check for already-active because + * ctpr may have changed and we need to withdraw the interrupt. + */ + if (!active && !was_active) { + pr_debug("%s: IRQ %d is already inactive\n", __func__, n_IRQ); + return; + } + + if (active) + src->ivpr |= IVPR_ACTIVITY_MASK; + else + src->ivpr &= ~IVPR_ACTIVITY_MASK; + + if (src->destmask == 0) { + /* No target */ + pr_debug("%s: IRQ %d has no target\n", __func__, n_IRQ); + return; + } + + if (src->destmask == (1 << src->last_cpu)) { + /* Only one CPU is allowed to receive this IRQ */ + IRQ_local_pipe(opp, src->last_cpu, n_IRQ, active, was_active); + } else if (!(src->ivpr & IVPR_MODE_MASK)) { + /* Directed delivery mode */ + for (i = 0; i < opp->nb_cpus; i++) { + if (src->destmask & (1 << i)) { + IRQ_local_pipe(opp, i, n_IRQ, active, + was_active); + } + } + } else { + /* Distributed delivery mode */ + for (i = src->last_cpu + 1; i != src->last_cpu; i++) { + if (i == opp->nb_cpus) + i = 0; + + if (src->destmask & (1 << i)) { + IRQ_local_pipe(opp, i, n_IRQ, active, + was_active); + src->last_cpu = i; + break; + } + } + } +} + +static void openpic_set_irq(void *opaque, int n_IRQ, int level) +{ + struct openpic *opp = opaque; + struct irq_source *src; + + if (n_IRQ >= MAX_IRQ) { + WARN_ONCE(1, "%s: IRQ %d out of range\n", __func__, n_IRQ); + return; + } + + src = &opp->src[n_IRQ]; + pr_debug("openpic: set irq %d = %d ivpr=0x%08x\n", + n_IRQ, level, src->ivpr); + if (src->level) { + /* level-sensitive irq */ + src->pending = level; + openpic_update_irq(opp, n_IRQ); + } else { + /* edge-sensitive irq */ + if (level) { + src->pending = 1; + openpic_update_irq(opp, n_IRQ); + } + + if (src->output != ILR_INTTGT_INT) { + /* Edge-triggered interrupts shouldn't be used + * with non-INT delivery, but just in case, + * try to make it do something sane rather than + * cause an interrupt storm. This is close to + * what you'd probably see happen in real hardware. + */ + src->pending = 0; + openpic_update_irq(opp, n_IRQ); + } + } +} + +static void openpic_reset(struct openpic *opp) +{ + int i; + + opp->gcr = GCR_RESET; + /* Initialise controller registers */ + opp->frr = ((opp->nb_irqs - 1) << FRR_NIRQ_SHIFT) | + (opp->vid << FRR_VID_SHIFT); + + opp->pir = 0; + opp->spve = -1 & opp->vector_mask; + opp->tfrr = opp->tfrr_reset; + /* Initialise IRQ sources */ + for (i = 0; i < opp->max_irq; i++) { + opp->src[i].ivpr = opp->ivpr_reset; + opp->src[i].idr = opp->idr_reset; + + switch (opp->src[i].type) { + case IRQ_TYPE_NORMAL: + opp->src[i].level = + !!(opp->ivpr_reset & IVPR_SENSE_MASK); + break; + + case IRQ_TYPE_FSLINT: + opp->src[i].ivpr |= IVPR_POLARITY_MASK; + break; + + case IRQ_TYPE_FSLSPECIAL: + break; + } + } + /* Initialise IRQ destinations */ + for (i = 0; i < MAX_CPU; i++) { + opp->dst[i].ctpr = 15; + memset(&opp->dst[i].raised, 0, sizeof(struct irq_queue)); + opp->dst[i].raised.next = -1; + memset(&opp->dst[i].servicing, 0, sizeof(struct irq_queue)); + opp->dst[i].servicing.next = -1; + } + /* Initialise timers */ + for (i = 0; i < MAX_TMR; i++) { + opp->timers[i].tccr = 0; + opp->timers[i].tbcr = TBCR_CI; + } + /* Go out of RESET state */ + opp->gcr = 0; +} + +static inline uint32_t read_IRQreg_idr(struct openpic *opp, int n_IRQ) +{ + return opp->src[n_IRQ].idr; +} + +static inline uint32_t read_IRQreg_ilr(struct openpic *opp, int n_IRQ) +{ + if (opp->flags & OPENPIC_FLAG_ILR) + return opp->src[n_IRQ].output; + + return 0xffffffff; +} + +static inline uint32_t read_IRQreg_ivpr(struct openpic *opp, int n_IRQ) +{ + return opp->src[n_IRQ].ivpr; +} + +static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ, + uint32_t val) +{ + struct irq_source *src = &opp->src[n_IRQ]; + uint32_t normal_mask = (1UL << opp->nb_cpus) - 1; + uint32_t crit_mask = 0; + uint32_t mask = normal_mask; + int crit_shift = IDR_EP_SHIFT - opp->nb_cpus; + int i; + + if (opp->flags & OPENPIC_FLAG_IDR_CRIT) { + crit_mask = mask << crit_shift; + mask |= crit_mask | IDR_EP; + } + + src->idr = val & mask; + pr_debug("Set IDR %d to 0x%08x\n", n_IRQ, src->idr); + + if (opp->flags & OPENPIC_FLAG_IDR_CRIT) { + if (src->idr & crit_mask) { + if (src->idr & normal_mask) { + pr_debug("%s: IRQ configured for multiple output types, using critical\n", + __func__); + } + + src->output = ILR_INTTGT_CINT; + src->nomask = true; + src->destmask = 0; + + for (i = 0; i < opp->nb_cpus; i++) { + int n_ci = IDR_CI0_SHIFT - i; + + if (src->idr & (1UL << n_ci)) + src->destmask |= 1UL << i; + } + } else { + src->output = ILR_INTTGT_INT; + src->nomask = false; + src->destmask = src->idr & normal_mask; + } + } else { + src->destmask = src->idr; + } +} + +static inline void write_IRQreg_ilr(struct openpic *opp, int n_IRQ, + uint32_t val) +{ + if (opp->flags & OPENPIC_FLAG_ILR) { + struct irq_source *src = &opp->src[n_IRQ]; + + src->output = val & ILR_INTTGT_MASK; + pr_debug("Set ILR %d to 0x%08x, output %d\n", n_IRQ, src->idr, + src->output); + + /* TODO: on MPIC v4.0 only, set nomask for non-INT */ + } +} + +static inline void write_IRQreg_ivpr(struct openpic *opp, int n_IRQ, + uint32_t val) +{ + uint32_t mask; + + /* NOTE when implementing newer FSL MPIC models: starting with v4.0, + * the polarity bit is read-only on internal interrupts. + */ + mask = IVPR_MASK_MASK | IVPR_PRIORITY_MASK | IVPR_SENSE_MASK | + IVPR_POLARITY_MASK | opp->vector_mask; + + /* ACTIVITY bit is read-only */ + opp->src[n_IRQ].ivpr = + (opp->src[n_IRQ].ivpr & IVPR_ACTIVITY_MASK) | (val & mask); + + /* For FSL internal interrupts, The sense bit is reserved and zero, + * and the interrupt is always level-triggered. Timers and IPIs + * have no sense or polarity bits, and are edge-triggered. + */ + switch (opp->src[n_IRQ].type) { + case IRQ_TYPE_NORMAL: + opp->src[n_IRQ].level = + !!(opp->src[n_IRQ].ivpr & IVPR_SENSE_MASK); + break; + + case IRQ_TYPE_FSLINT: + opp->src[n_IRQ].ivpr &= ~IVPR_SENSE_MASK; + break; + + case IRQ_TYPE_FSLSPECIAL: + opp->src[n_IRQ].ivpr &= ~(IVPR_POLARITY_MASK | IVPR_SENSE_MASK); + break; + } + + openpic_update_irq(opp, n_IRQ); + pr_debug("Set IVPR %d to 0x%08x -> 0x%08x\n", n_IRQ, val, + opp->src[n_IRQ].ivpr); +} + +static void openpic_gcr_write(struct openpic *opp, uint64_t val) +{ + if (val & GCR_RESET) { + openpic_reset(opp); + return; + } + + opp->gcr &= ~opp->mpic_mode_mask; + opp->gcr |= val & opp->mpic_mode_mask; +} + +static int openpic_gbl_write(void *opaque, gpa_t addr, u32 val) +{ + struct openpic *opp = opaque; + int err = 0; + + pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); + if (addr & 0xF) + return 0; + + switch (addr) { + case 0x00: /* Block Revision Register1 (BRR1) is Readonly */ + break; + case 0x40: + case 0x50: + case 0x60: + case 0x70: + case 0x80: + case 0x90: + case 0xA0: + case 0xB0: + err = openpic_cpu_write_internal(opp, addr, val, + get_current_cpu()); + break; + case 0x1000: /* FRR */ + break; + case 0x1020: /* GCR */ + openpic_gcr_write(opp, val); + break; + case 0x1080: /* VIR */ + break; + case 0x1090: /* PIR */ + /* + * This register is used to reset a CPU core -- + * let userspace handle it. + */ + err = -ENXIO; + break; + case 0x10A0: /* IPI_IVPR */ + case 0x10B0: + case 0x10C0: + case 0x10D0: { + int idx; + idx = (addr - 0x10A0) >> 4; + write_IRQreg_ivpr(opp, opp->irq_ipi0 + idx, val); + break; + } + case 0x10E0: /* SPVE */ + opp->spve = val & opp->vector_mask; + break; + default: + break; + } + + return err; +} + +static int openpic_gbl_read(void *opaque, gpa_t addr, u32 *ptr) +{ + struct openpic *opp = opaque; + u32 retval; + int err = 0; + + pr_debug("%s: addr %#llx\n", __func__, addr); + retval = 0xFFFFFFFF; + if (addr & 0xF) + goto out; + + switch (addr) { + case 0x1000: /* FRR */ + retval = opp->frr; + retval |= (opp->nb_cpus - 1) << FRR_NCPU_SHIFT; + break; + case 0x1020: /* GCR */ + retval = opp->gcr; + break; + case 0x1080: /* VIR */ + retval = opp->vir; + break; + case 0x1090: /* PIR */ + retval = 0x00000000; + break; + case 0x00: /* Block Revision Register1 (BRR1) */ + retval = opp->brr1; + break; + case 0x40: + case 0x50: + case 0x60: + case 0x70: + case 0x80: + case 0x90: + case 0xA0: + case 0xB0: + err = openpic_cpu_read_internal(opp, addr, + &retval, get_current_cpu()); + break; + case 0x10A0: /* IPI_IVPR */ + case 0x10B0: + case 0x10C0: + case 0x10D0: + { + int idx; + idx = (addr - 0x10A0) >> 4; + retval = read_IRQreg_ivpr(opp, opp->irq_ipi0 + idx); + } + break; + case 0x10E0: /* SPVE */ + retval = opp->spve; + break; + default: + break; + } + +out: + pr_debug("%s: => 0x%08x\n", __func__, retval); + *ptr = retval; + return err; +} + +static int openpic_tmr_write(void *opaque, gpa_t addr, u32 val) +{ + struct openpic *opp = opaque; + int idx; + + addr += 0x10f0; + + pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); + if (addr & 0xF) + return 0; + + if (addr == 0x10f0) { + /* TFRR */ + opp->tfrr = val; + return 0; + } + + idx = (addr >> 6) & 0x3; + addr = addr & 0x30; + + switch (addr & 0x30) { + case 0x00: /* TCCR */ + break; + case 0x10: /* TBCR */ + if ((opp->timers[idx].tccr & TCCR_TOG) != 0 && + (val & TBCR_CI) == 0 && + (opp->timers[idx].tbcr & TBCR_CI) != 0) + opp->timers[idx].tccr &= ~TCCR_TOG; + + opp->timers[idx].tbcr = val; + break; + case 0x20: /* TVPR */ + write_IRQreg_ivpr(opp, opp->irq_tim0 + idx, val); + break; + case 0x30: /* TDR */ + write_IRQreg_idr(opp, opp->irq_tim0 + idx, val); + break; + } + + return 0; +} + +static int openpic_tmr_read(void *opaque, gpa_t addr, u32 *ptr) +{ + struct openpic *opp = opaque; + uint32_t retval = -1; + int idx; + + pr_debug("%s: addr %#llx\n", __func__, addr); + if (addr & 0xF) + goto out; + + idx = (addr >> 6) & 0x3; + if (addr == 0x0) { + /* TFRR */ + retval = opp->tfrr; + goto out; + } + + switch (addr & 0x30) { + case 0x00: /* TCCR */ + retval = opp->timers[idx].tccr; + break; + case 0x10: /* TBCR */ + retval = opp->timers[idx].tbcr; + break; + case 0x20: /* TIPV */ + retval = read_IRQreg_ivpr(opp, opp->irq_tim0 + idx); + break; + case 0x30: /* TIDE (TIDR) */ + retval = read_IRQreg_idr(opp, opp->irq_tim0 + idx); + break; + } + +out: + pr_debug("%s: => 0x%08x\n", __func__, retval); + *ptr = retval; + return 0; +} + +static int openpic_src_write(void *opaque, gpa_t addr, u32 val) +{ + struct openpic *opp = opaque; + int idx; + + pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); + + addr = addr & 0xffff; + idx = addr >> 5; + + switch (addr & 0x1f) { + case 0x00: + write_IRQreg_ivpr(opp, idx, val); + break; + case 0x10: + write_IRQreg_idr(opp, idx, val); + break; + case 0x18: + write_IRQreg_ilr(opp, idx, val); + break; + } + + return 0; +} + +static int openpic_src_read(void *opaque, gpa_t addr, u32 *ptr) +{ + struct openpic *opp = opaque; + uint32_t retval; + int idx; + + pr_debug("%s: addr %#llx\n", __func__, addr); + retval = 0xFFFFFFFF; + + addr = addr & 0xffff; + idx = addr >> 5; + + switch (addr & 0x1f) { + case 0x00: + retval = read_IRQreg_ivpr(opp, idx); + break; + case 0x10: + retval = read_IRQreg_idr(opp, idx); + break; + case 0x18: + retval = read_IRQreg_ilr(opp, idx); + break; + } + + pr_debug("%s: => 0x%08x\n", __func__, retval); + *ptr = retval; + return 0; +} + +static int openpic_msi_write(void *opaque, gpa_t addr, u32 val) +{ + struct openpic *opp = opaque; + int idx = opp->irq_msi; + int srs, ibs; + + pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val); + if (addr & 0xF) + return 0; + + switch (addr) { + case MSIIR_OFFSET: + srs = val >> MSIIR_SRS_SHIFT; + idx += srs; + ibs = (val & MSIIR_IBS_MASK) >> MSIIR_IBS_SHIFT; + opp->msi[srs].msir |= 1 << ibs; + openpic_set_irq(opp, idx, 1); + break; + default: + /* most registers are read-only, thus ignored */ + break; + } + + return 0; +} + +static int openpic_msi_read(void *opaque, gpa_t addr, u32 *ptr) +{ + struct openpic *opp = opaque; + uint32_t r = 0; + int i, srs; + + pr_debug("%s: addr %#llx\n", __func__, addr); + if (addr & 0xF) + return -ENXIO; + + srs = addr >> 4; + + switch (addr) { + case 0x00: + case 0x10: + case 0x20: + case 0x30: + case 0x40: + case 0x50: + case 0x60: + case 0x70: /* MSIRs */ + r = opp->msi[srs].msir; + /* Clear on read */ + opp->msi[srs].msir = 0; + openpic_set_irq(opp, opp->irq_msi + srs, 0); + break; + case 0x120: /* MSISR */ + for (i = 0; i < MAX_MSI; i++) + r |= (opp->msi[i].msir ? 1 : 0) << i; + break; + } + + pr_debug("%s: => 0x%08x\n", __func__, r); + *ptr = r; + return 0; +} + +static int openpic_summary_read(void *opaque, gpa_t addr, u32 *ptr) +{ + uint32_t r = 0; + + pr_debug("%s: addr %#llx\n", __func__, addr); + + /* TODO: EISR/EIMR */ + + *ptr = r; + return 0; +} + +static int openpic_summary_write(void *opaque, gpa_t addr, u32 val) +{ + pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val); + + /* TODO: EISR/EIMR */ + return 0; +} + +static int openpic_cpu_write_internal(void *opaque, gpa_t addr, + u32 val, int idx) +{ + struct openpic *opp = opaque; + struct irq_source *src; + struct irq_dest *dst; + int s_IRQ, n_IRQ; + + pr_debug("%s: cpu %d addr %#llx <= 0x%08x\n", __func__, idx, + addr, val); + + if (idx < 0) + return 0; + + if (addr & 0xF) + return 0; + + dst = &opp->dst[idx]; + addr &= 0xFF0; + switch (addr) { + case 0x40: /* IPIDR */ + case 0x50: + case 0x60: + case 0x70: + idx = (addr - 0x40) >> 4; + /* we use IDE as mask which CPUs to deliver the IPI to still. */ + opp->src[opp->irq_ipi0 + idx].destmask |= val; + openpic_set_irq(opp, opp->irq_ipi0 + idx, 1); + openpic_set_irq(opp, opp->irq_ipi0 + idx, 0); + break; + case 0x80: /* CTPR */ + dst->ctpr = val & 0x0000000F; + + pr_debug("%s: set CPU %d ctpr to %d, raised %d servicing %d\n", + __func__, idx, dst->ctpr, dst->raised.priority, + dst->servicing.priority); + + if (dst->raised.priority <= dst->ctpr) { + pr_debug("%s: Lower OpenPIC INT output cpu %d due to ctpr\n", + __func__, idx); + mpic_irq_lower(opp, dst, ILR_INTTGT_INT); + } else if (dst->raised.priority > dst->servicing.priority) { + pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d\n", + __func__, idx, dst->raised.next); + mpic_irq_raise(opp, dst, ILR_INTTGT_INT); + } + + break; + case 0x90: /* WHOAMI */ + /* Read-only register */ + break; + case 0xA0: /* IACK */ + /* Read-only register */ + break; + case 0xB0: { /* EOI */ + int notify_eoi; + + pr_debug("EOI\n"); + s_IRQ = IRQ_get_next(opp, &dst->servicing); + + if (s_IRQ < 0) { + pr_debug("%s: EOI with no interrupt in service\n", + __func__); + break; + } + + IRQ_resetbit(&dst->servicing, s_IRQ); + /* Notify listeners that the IRQ is over */ + notify_eoi = s_IRQ; + /* Set up next servicing IRQ */ + s_IRQ = IRQ_get_next(opp, &dst->servicing); + /* Check queued interrupts. */ + n_IRQ = IRQ_get_next(opp, &dst->raised); + src = &opp->src[n_IRQ]; + if (n_IRQ != -1 && + (s_IRQ == -1 || + IVPR_PRIORITY(src->ivpr) > dst->servicing.priority)) { + pr_debug("Raise OpenPIC INT output cpu %d irq %d\n", + idx, n_IRQ); + mpic_irq_raise(opp, dst, ILR_INTTGT_INT); + } + + spin_unlock(&opp->lock); + kvm_notify_acked_irq(opp->kvm, 0, notify_eoi); + spin_lock(&opp->lock); + + break; + } + default: + break; + } + + return 0; +} + +static int openpic_cpu_write(void *opaque, gpa_t addr, u32 val) +{ + struct openpic *opp = opaque; + + return openpic_cpu_write_internal(opp, addr, val, + (addr & 0x1f000) >> 12); +} + +static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst, + int cpu) +{ + struct irq_source *src; + int retval, irq; + + pr_debug("Lower OpenPIC INT output\n"); + mpic_irq_lower(opp, dst, ILR_INTTGT_INT); + + irq = IRQ_get_next(opp, &dst->raised); + pr_debug("IACK: irq=%d\n", irq); + + if (irq == -1) + /* No more interrupt pending */ + return opp->spve; + + src = &opp->src[irq]; + if (!(src->ivpr & IVPR_ACTIVITY_MASK) || + !(IVPR_PRIORITY(src->ivpr) > dst->ctpr)) { + pr_err("%s: bad raised IRQ %d ctpr %d ivpr 0x%08x\n", + __func__, irq, dst->ctpr, src->ivpr); + openpic_update_irq(opp, irq); + retval = opp->spve; + } else { + /* IRQ enter servicing state */ + IRQ_setbit(&dst->servicing, irq); + retval = IVPR_VECTOR(opp, src->ivpr); + } + + if (!src->level) { + /* edge-sensitive IRQ */ + src->ivpr &= ~IVPR_ACTIVITY_MASK; + src->pending = 0; + IRQ_resetbit(&dst->raised, irq); + } + + if ((irq >= opp->irq_ipi0) && (irq < (opp->irq_ipi0 + MAX_IPI))) { + src->destmask &= ~(1 << cpu); + if (src->destmask && !src->level) { + /* trigger on CPUs that didn't know about it yet */ + openpic_set_irq(opp, irq, 1); + openpic_set_irq(opp, irq, 0); + /* if all CPUs knew about it, set active bit again */ + src->ivpr |= IVPR_ACTIVITY_MASK; + } + } + + return retval; +} + +void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu) +{ + struct openpic *opp = vcpu->arch.mpic; + int cpu = vcpu->arch.irq_cpu_id; + unsigned long flags; + + spin_lock_irqsave(&opp->lock, flags); + + if ((opp->gcr & opp->mpic_mode_mask) == GCR_MODE_PROXY) + kvmppc_set_epr(vcpu, openpic_iack(opp, &opp->dst[cpu], cpu)); + + spin_unlock_irqrestore(&opp->lock, flags); +} + +static int openpic_cpu_read_internal(void *opaque, gpa_t addr, + u32 *ptr, int idx) +{ + struct openpic *opp = opaque; + struct irq_dest *dst; + uint32_t retval; + + pr_debug("%s: cpu %d addr %#llx\n", __func__, idx, addr); + retval = 0xFFFFFFFF; + + if (idx < 0) + goto out; + + if (addr & 0xF) + goto out; + + dst = &opp->dst[idx]; + addr &= 0xFF0; + switch (addr) { + case 0x80: /* CTPR */ + retval = dst->ctpr; + break; + case 0x90: /* WHOAMI */ + retval = idx; + break; + case 0xA0: /* IACK */ + retval = openpic_iack(opp, dst, idx); + break; + case 0xB0: /* EOI */ + retval = 0; + break; + default: + break; + } + pr_debug("%s: => 0x%08x\n", __func__, retval); + +out: + *ptr = retval; + return 0; +} + +static int openpic_cpu_read(void *opaque, gpa_t addr, u32 *ptr) +{ + struct openpic *opp = opaque; + + return openpic_cpu_read_internal(opp, addr, ptr, + (addr & 0x1f000) >> 12); +} + +struct mem_reg { + int (*read)(void *opaque, gpa_t addr, u32 *ptr); + int (*write)(void *opaque, gpa_t addr, u32 val); + gpa_t start_addr; + int size; +}; + +static const struct mem_reg openpic_gbl_mmio = { + .write = openpic_gbl_write, + .read = openpic_gbl_read, + .start_addr = OPENPIC_GLB_REG_START, + .size = OPENPIC_GLB_REG_SIZE, +}; + +static const struct mem_reg openpic_tmr_mmio = { + .write = openpic_tmr_write, + .read = openpic_tmr_read, + .start_addr = OPENPIC_TMR_REG_START, + .size = OPENPIC_TMR_REG_SIZE, +}; + +static const struct mem_reg openpic_cpu_mmio = { + .write = openpic_cpu_write, + .read = openpic_cpu_read, + .start_addr = OPENPIC_CPU_REG_START, + .size = OPENPIC_CPU_REG_SIZE, +}; + +static const struct mem_reg openpic_src_mmio = { + .write = openpic_src_write, + .read = openpic_src_read, + .start_addr = OPENPIC_SRC_REG_START, + .size = OPENPIC_SRC_REG_SIZE, +}; + +static const struct mem_reg openpic_msi_mmio = { + .read = openpic_msi_read, + .write = openpic_msi_write, + .start_addr = OPENPIC_MSI_REG_START, + .size = OPENPIC_MSI_REG_SIZE, +}; + +static const struct mem_reg openpic_summary_mmio = { + .read = openpic_summary_read, + .write = openpic_summary_write, + .start_addr = OPENPIC_SUMMARY_REG_START, + .size = OPENPIC_SUMMARY_REG_SIZE, +}; + +static void add_mmio_region(struct openpic *opp, const struct mem_reg *mr) +{ + if (opp->num_mmio_regions >= MAX_MMIO_REGIONS) { + WARN(1, "kvm mpic: too many mmio regions\n"); + return; + } + + opp->mmio_regions[opp->num_mmio_regions++] = mr; +} + +static void fsl_common_init(struct openpic *opp) +{ + int i; + int virq = MAX_SRC; + + add_mmio_region(opp, &openpic_msi_mmio); + add_mmio_region(opp, &openpic_summary_mmio); + + opp->vid = VID_REVISION_1_2; + opp->vir = VIR_GENERIC; + opp->vector_mask = 0xFFFF; + opp->tfrr_reset = 0; + opp->ivpr_reset = IVPR_MASK_MASK; + opp->idr_reset = 1 << 0; + opp->max_irq = MAX_IRQ; + + opp->irq_ipi0 = virq; + virq += MAX_IPI; + opp->irq_tim0 = virq; + virq += MAX_TMR; + + BUG_ON(virq > MAX_IRQ); + + opp->irq_msi = 224; + + for (i = 0; i < opp->fsl->max_ext; i++) + opp->src[i].level = false; + + /* Internal interrupts, including message and MSI */ + for (i = 16; i < MAX_SRC; i++) { + opp->src[i].type = IRQ_TYPE_FSLINT; + opp->src[i].level = true; + } + + /* timers and IPIs */ + for (i = MAX_SRC; i < virq; i++) { + opp->src[i].type = IRQ_TYPE_FSLSPECIAL; + opp->src[i].level = false; + } +} + +static int kvm_mpic_read_internal(struct openpic *opp, gpa_t addr, u32 *ptr) +{ + int i; + + for (i = 0; i < opp->num_mmio_regions; i++) { + const struct mem_reg *mr = opp->mmio_regions[i]; + + if (mr->start_addr > addr || addr >= mr->start_addr + mr->size) + continue; + + return mr->read(opp, addr - mr->start_addr, ptr); + } + + return -ENXIO; +} + +static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val) +{ + int i; + + for (i = 0; i < opp->num_mmio_regions; i++) { + const struct mem_reg *mr = opp->mmio_regions[i]; + + if (mr->start_addr > addr || addr >= mr->start_addr + mr->size) + continue; + + return mr->write(opp, addr - mr->start_addr, val); + } + + return -ENXIO; +} + +static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, + int len, void *ptr) +{ + struct openpic *opp = container_of(this, struct openpic, mmio); + int ret; + union { + u32 val; + u8 bytes[4]; + } u; + + if (addr & (len - 1)) { + pr_debug("%s: bad alignment %llx/%d\n", + __func__, addr, len); + return -EINVAL; + } + + spin_lock_irq(&opp->lock); + ret = kvm_mpic_read_internal(opp, addr - opp->reg_base, &u.val); + spin_unlock_irq(&opp->lock); + + /* + * Technically only 32-bit accesses are allowed, but be nice to + * people dumping registers a byte at a time -- it works in real + * hardware (reads only, not writes). + */ + if (len == 4) { + *(u32 *)ptr = u.val; + pr_debug("%s: addr %llx ret %d len 4 val %x\n", + __func__, addr, ret, u.val); + } else if (len == 1) { + *(u8 *)ptr = u.bytes[addr & 3]; + pr_debug("%s: addr %llx ret %d len 1 val %x\n", + __func__, addr, ret, u.bytes[addr & 3]); + } else { + pr_debug("%s: bad length %d\n", __func__, len); + return -EINVAL; + } + + return ret; +} + +static int kvm_mpic_write(struct kvm_io_device *this, gpa_t addr, + int len, const void *ptr) +{ + struct openpic *opp = container_of(this, struct openpic, mmio); + int ret; + + if (len != 4) { + pr_debug("%s: bad length %d\n", __func__, len); + return -EOPNOTSUPP; + } + if (addr & 3) { + pr_debug("%s: bad alignment %llx/%d\n", __func__, addr, len); + return -EOPNOTSUPP; + } + + spin_lock_irq(&opp->lock); + ret = kvm_mpic_write_internal(opp, addr - opp->reg_base, + *(const u32 *)ptr); + spin_unlock_irq(&opp->lock); + + pr_debug("%s: addr %llx ret %d val %x\n", + __func__, addr, ret, *(const u32 *)ptr); + + return ret; +} + +static const struct kvm_io_device_ops mpic_mmio_ops = { + .read = kvm_mpic_read, + .write = kvm_mpic_write, +}; + +static void map_mmio(struct openpic *opp) +{ + kvm_iodevice_init(&opp->mmio, &mpic_mmio_ops); + + kvm_io_bus_register_dev(opp->kvm, KVM_MMIO_BUS, + opp->reg_base, OPENPIC_REG_SIZE, + &opp->mmio); +} + +static void unmap_mmio(struct openpic *opp) +{ + kvm_io_bus_unregister_dev(opp->kvm, KVM_MMIO_BUS, &opp->mmio); +} + +static int set_base_addr(struct openpic *opp, struct kvm_device_attr *attr) +{ + u64 base; + + if (copy_from_user(&base, (u64 __user *)(long)attr->addr, sizeof(u64))) + return -EFAULT; + + if (base & 0x3ffff) { + pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx not aligned\n", + __func__, base); + return -EINVAL; + } + + if (base == opp->reg_base) + return 0; + + mutex_lock(&opp->kvm->slots_lock); + + unmap_mmio(opp); + opp->reg_base = base; + + pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx\n", + __func__, base); + + if (base == 0) + goto out; + + map_mmio(opp); + +out: + mutex_unlock(&opp->kvm->slots_lock); + return 0; +} + +#define ATTR_SET 0 +#define ATTR_GET 1 + +static int access_reg(struct openpic *opp, gpa_t addr, u32 *val, int type) +{ + int ret; + + if (addr & 3) + return -ENXIO; + + spin_lock_irq(&opp->lock); + + if (type == ATTR_SET) + ret = kvm_mpic_write_internal(opp, addr, *val); + else + ret = kvm_mpic_read_internal(opp, addr, val); + + spin_unlock_irq(&opp->lock); + + pr_debug("%s: type %d addr %llx val %x\n", __func__, type, addr, *val); + + return ret; +} + +static int mpic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + struct openpic *opp = dev->private; + u32 attr32; + + switch (attr->group) { + case KVM_DEV_MPIC_GRP_MISC: + switch (attr->attr) { + case KVM_DEV_MPIC_BASE_ADDR: + return set_base_addr(opp, attr); + } + + break; + + case KVM_DEV_MPIC_GRP_REGISTER: + if (get_user(attr32, (u32 __user *)(long)attr->addr)) + return -EFAULT; + + return access_reg(opp, attr->attr, &attr32, ATTR_SET); + + case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: + if (attr->attr > MAX_SRC) + return -EINVAL; + + if (get_user(attr32, (u32 __user *)(long)attr->addr)) + return -EFAULT; + + if (attr32 != 0 && attr32 != 1) + return -EINVAL; + + spin_lock_irq(&opp->lock); + openpic_set_irq(opp, attr->attr, attr32); + spin_unlock_irq(&opp->lock); + return 0; + } + + return -ENXIO; +} + +static int mpic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + struct openpic *opp = dev->private; + u64 attr64; + u32 attr32; + int ret; + + switch (attr->group) { + case KVM_DEV_MPIC_GRP_MISC: + switch (attr->attr) { + case KVM_DEV_MPIC_BASE_ADDR: + mutex_lock(&opp->kvm->slots_lock); + attr64 = opp->reg_base; + mutex_unlock(&opp->kvm->slots_lock); + + if (copy_to_user((u64 __user *)(long)attr->addr, + &attr64, sizeof(u64))) + return -EFAULT; + + return 0; + } + + break; + + case KVM_DEV_MPIC_GRP_REGISTER: + ret = access_reg(opp, attr->attr, &attr32, ATTR_GET); + if (ret) + return ret; + + if (put_user(attr32, (u32 __user *)(long)attr->addr)) + return -EFAULT; + + return 0; + + case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: + if (attr->attr > MAX_SRC) + return -EINVAL; + + spin_lock_irq(&opp->lock); + attr32 = opp->src[attr->attr].pending; + spin_unlock_irq(&opp->lock); + + if (put_user(attr32, (u32 __user *)(long)attr->addr)) + return -EFAULT; + + return 0; + } + + return -ENXIO; +} + +static int mpic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_MPIC_GRP_MISC: + switch (attr->attr) { + case KVM_DEV_MPIC_BASE_ADDR: + return 0; + } + + break; + + case KVM_DEV_MPIC_GRP_REGISTER: + return 0; + + case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: + if (attr->attr > MAX_SRC) + break; + + return 0; + } + + return -ENXIO; +} + +static void mpic_destroy(struct kvm_device *dev) +{ + struct openpic *opp = dev->private; + + dev->kvm->arch.mpic = NULL; + kfree(opp); +} + +static int mpic_set_default_irq_routing(struct openpic *opp) +{ + struct kvm_irq_routing_entry *routing; + + /* Create a nop default map, so that dereferencing it still works */ + routing = kzalloc((sizeof(*routing)), GFP_KERNEL); + if (!routing) + return -ENOMEM; + + kvm_set_irq_routing(opp->kvm, routing, 0, 0); + + kfree(routing); + return 0; +} + +static int mpic_create(struct kvm_device *dev, u32 type) +{ + struct openpic *opp; + int ret; + + /* We only support one MPIC at a time for now */ + if (dev->kvm->arch.mpic) + return -EINVAL; + + opp = kzalloc(sizeof(struct openpic), GFP_KERNEL); + if (!opp) + return -ENOMEM; + + dev->private = opp; + opp->kvm = dev->kvm; + opp->dev = dev; + opp->model = type; + spin_lock_init(&opp->lock); + + add_mmio_region(opp, &openpic_gbl_mmio); + add_mmio_region(opp, &openpic_tmr_mmio); + add_mmio_region(opp, &openpic_src_mmio); + add_mmio_region(opp, &openpic_cpu_mmio); + + switch (opp->model) { + case KVM_DEV_TYPE_FSL_MPIC_20: + opp->fsl = &fsl_mpic_20; + opp->brr1 = 0x00400200; + opp->flags |= OPENPIC_FLAG_IDR_CRIT; + opp->nb_irqs = 80; + opp->mpic_mode_mask = GCR_MODE_MIXED; + + fsl_common_init(opp); + + break; + + case KVM_DEV_TYPE_FSL_MPIC_42: + opp->fsl = &fsl_mpic_42; + opp->brr1 = 0x00400402; + opp->flags |= OPENPIC_FLAG_ILR; + opp->nb_irqs = 196; + opp->mpic_mode_mask = GCR_MODE_PROXY; + + fsl_common_init(opp); + + break; + + default: + ret = -ENODEV; + goto err; + } + + ret = mpic_set_default_irq_routing(opp); + if (ret) + goto err; + + openpic_reset(opp); + + smp_wmb(); + dev->kvm->arch.mpic = opp; + + return 0; + +err: + kfree(opp); + return ret; +} + +struct kvm_device_ops kvm_mpic_ops = { + .name = "kvm-mpic", + .create = mpic_create, + .destroy = mpic_destroy, + .set_attr = mpic_set_attr, + .get_attr = mpic_get_attr, + .has_attr = mpic_has_attr, +}; + +int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, + u32 cpu) +{ + struct openpic *opp = dev->private; + int ret = 0; + + if (dev->ops != &kvm_mpic_ops) + return -EPERM; + if (opp->kvm != vcpu->kvm) + return -EPERM; + if (cpu < 0 || cpu >= MAX_CPU) + return -EPERM; + + spin_lock_irq(&opp->lock); + + if (opp->dst[cpu].vcpu) { + ret = -EEXIST; + goto out; + } + if (vcpu->arch.irq_type) { + ret = -EBUSY; + goto out; + } + + opp->dst[cpu].vcpu = vcpu; + opp->nb_cpus = max(opp->nb_cpus, cpu + 1); + + vcpu->arch.mpic = opp; + vcpu->arch.irq_cpu_id = cpu; + vcpu->arch.irq_type = KVMPPC_IRQ_MPIC; + + /* This might need to be changed if GCR gets extended */ + if (opp->mpic_mode_mask == GCR_MODE_PROXY) + vcpu->arch.epr_flags |= KVMPPC_EPR_KERNEL; + +out: + spin_unlock_irq(&opp->lock); + return ret; +} + +/* + * This should only happen immediately before the mpic is destroyed, + * so we shouldn't need to worry about anything still trying to + * access the vcpu pointer. + */ +void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu) +{ + BUG_ON(!opp->dst[vcpu->arch.irq_cpu_id].vcpu); + + opp->dst[vcpu->arch.irq_cpu_id].vcpu = NULL; +} + +/* + * Return value: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +static int mpic_set_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + u32 irq = e->irqchip.pin; + struct openpic *opp = kvm->arch.mpic; + unsigned long flags; + + spin_lock_irqsave(&opp->lock, flags); + openpic_set_irq(opp, irq, level); + spin_unlock_irqrestore(&opp->lock, flags); + + /* All code paths we care about don't check for the return value */ + return 0; +} + +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, bool line_status) +{ + struct openpic *opp = kvm->arch.mpic; + unsigned long flags; + + spin_lock_irqsave(&opp->lock, flags); + + /* + * XXX We ignore the target address for now, as we only support + * a single MSI bank. + */ + openpic_msi_write(kvm->arch.mpic, MSIIR_OFFSET, e->msi.data); + spin_unlock_irqrestore(&opp->lock, flags); + + /* All code paths we care about don't check for the return value */ + return 0; +} + +int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + int r = -EINVAL; + + switch (ue->type) { + case KVM_IRQ_ROUTING_IRQCHIP: + e->set = mpic_set_irq; + e->irqchip.irqchip = ue->u.irqchip.irqchip; + e->irqchip.pin = ue->u.irqchip.pin; + if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) + goto out; + rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; + break; + case KVM_IRQ_ROUTING_MSI: + e->set = kvm_set_msi; + e->msi.address_lo = ue->u.msi.address_lo; + e->msi.address_hi = ue->u.msi.address_hi; + e->msi.data = ue->u.msi.data; + break; + default: + goto out; + } + + r = 0; +out: + return r; +} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 934413cd3a1b..6316ee336e88 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -25,6 +25,7 @@ #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/file.h> #include <asm/cputable.h> #include <asm/uaccess.h> #include <asm/kvm_ppc.h> @@ -32,6 +33,7 @@ #include <asm/cputhreads.h> #include <asm/irqflags.h> #include "timing.h" +#include "irq.h" #include "../mm/mmu_decl.h" #define CREATE_TRACE_POINTS @@ -317,6 +319,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: + case KVM_CAP_DEVICE_CTRL: r = 1; break; #ifndef CONFIG_KVM_BOOK3S_64_HV @@ -326,6 +329,9 @@ int kvm_dev_ioctl_check_extension(long ext) #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC) case KVM_CAP_SW_TLB: #endif +#ifdef CONFIG_KVM_MPIC + case KVM_CAP_IRQ_MPIC: +#endif r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -335,6 +341,10 @@ int kvm_dev_ioctl_check_extension(long ext) #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: case KVM_CAP_PPC_ALLOC_HTAB: + case KVM_CAP_PPC_RTAS: +#ifdef CONFIG_KVM_XICS + case KVM_CAP_IRQ_XICS: +#endif r = 1; break; #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -411,18 +421,17 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_memory_slot old, - struct kvm_userspace_memory_region *mem, - bool user_alloc) + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) { return kvmppc_core_prepare_memory_region(kvm, memslot, mem); } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - bool user_alloc) + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) { kvmppc_core_commit_memory_region(kvm, mem, old); } @@ -460,6 +469,16 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) tasklet_kill(&vcpu->arch.tasklet); kvmppc_remove_vcpu_debugfs(vcpu); + + switch (vcpu->arch.irq_type) { + case KVMPPC_IRQ_MPIC: + kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu); + break; + case KVMPPC_IRQ_XICS: + kvmppc_xics_free_icp(vcpu); + break; + } + kvmppc_core_vcpu_free(vcpu); } @@ -532,12 +551,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) #endif } -int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg) -{ - return -EINVAL; -} - static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { @@ -612,6 +625,8 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_bigendian) { + int idx, ret; + if (bytes > sizeof(run->mmio.data)) { printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, run->mmio.len); @@ -627,8 +642,14 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->mmio_is_write = 0; vcpu->arch.mmio_sign_extend = 0; - if (!kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, - bytes, &run->mmio.data)) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + + ret = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + bytes, &run->mmio.data); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + if (!ret) { kvmppc_complete_mmio_load(vcpu, run); vcpu->mmio_needed = 0; return EMULATE_DONE; @@ -653,6 +674,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_bigendian) { void *data = run->mmio.data; + int idx, ret; if (bytes > sizeof(run->mmio.data)) { printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, @@ -682,9 +704,14 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - if (!kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, - bytes, &run->mmio.data)) { - kvmppc_complete_mmio_load(vcpu, run); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + ret = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + bytes, &run->mmio.data); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + if (!ret) { vcpu->mmio_needed = 0; return EMULATE_DONE; } @@ -740,7 +767,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq == KVM_INTERRUPT_UNSET) { - kvmppc_core_dequeue_external(vcpu, irq); + kvmppc_core_dequeue_external(vcpu); return 0; } @@ -770,7 +797,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; case KVM_CAP_PPC_EPR: r = 0; - vcpu->arch.epr_enabled = cap->args[0]; + if (cap->args[0]) + vcpu->arch.epr_flags |= KVMPPC_EPR_USER; + else + vcpu->arch.epr_flags &= ~KVMPPC_EPR_USER; break; #ifdef CONFIG_BOOKE case KVM_CAP_PPC_BOOKE_WATCHDOG: @@ -791,6 +821,44 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; } #endif +#ifdef CONFIG_KVM_MPIC + case KVM_CAP_IRQ_MPIC: { + struct file *filp; + struct kvm_device *dev; + + r = -EBADF; + filp = fget(cap->args[0]); + if (!filp) + break; + + r = -EPERM; + dev = kvm_device_from_filp(filp); + if (dev) + r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]); + + fput(filp); + break; + } +#endif +#ifdef CONFIG_KVM_XICS + case KVM_CAP_IRQ_XICS: { + struct file *filp; + struct kvm_device *dev; + + r = -EBADF; + filp = fget(cap->args[0]); + if (!filp) + break; + + r = -EPERM; + dev = kvm_device_from_filp(filp); + if (dev) + r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]); + + fput(filp); + break; + } +#endif /* CONFIG_KVM_XICS */ default: r = -EINVAL; break; @@ -913,9 +981,22 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo) return 0; } +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, + line_status); + return 0; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { + struct kvm *kvm __maybe_unused = filp->private_data; void __user *argp = (void __user *)arg; long r; @@ -934,7 +1015,6 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CREATE_SPAPR_TCE: { struct kvm_create_spapr_tce create_tce; - struct kvm *kvm = filp->private_data; r = -EFAULT; if (copy_from_user(&create_tce, argp, sizeof(create_tce))) @@ -946,8 +1026,8 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_KVM_BOOK3S_64_HV case KVM_ALLOCATE_RMA: { - struct kvm *kvm = filp->private_data; struct kvm_allocate_rma rma; + struct kvm *kvm = filp->private_data; r = kvm_vm_ioctl_allocate_rma(kvm, &rma); if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma))) @@ -956,7 +1036,6 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_PPC_ALLOCATE_HTAB: { - struct kvm *kvm = filp->private_data; u32 htab_order; r = -EFAULT; @@ -973,7 +1052,6 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_PPC_GET_HTAB_FD: { - struct kvm *kvm = filp->private_data; struct kvm_get_htab_fd ghf; r = -EFAULT; @@ -986,7 +1064,6 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_PPC_BOOK3S_64 case KVM_PPC_GET_SMMU_INFO: { - struct kvm *kvm = filp->private_data; struct kvm_ppc_smmu_info info; memset(&info, 0, sizeof(info)); @@ -995,6 +1072,12 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_PPC_RTAS_DEFINE_TOKEN: { + struct kvm *kvm = filp->private_data; + + r = kvm_vm_ioctl_rtas_define_token(kvm, argp); + break; + } #endif /* CONFIG_PPC_BOOK3S_64 */ default: r = -ENOTTY; diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index 0ef75bf0695c..395c594722a2 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -28,13 +28,14 @@ _GLOBAL(copypage_power7) * aligned we don't need to clear the bottom 7 bits of either * address. */ - ori r9,r3,1 /* stream=1 */ + ori r9,r3,1 /* stream=1 => to */ #ifdef CONFIG_PPC_64K_PAGES - lis r7,0x0E01 /* depth=7, units=512 */ + lis r7,0x0E01 /* depth=7 + * units/cachelines=512 */ #else lis r7,0x0E00 /* depth=7 */ - ori r7,r7,0x1000 /* units=32 */ + ori r7,r7,0x1000 /* units/cachelines=32 */ #endif ori r10,r7,1 /* stream=1 */ @@ -43,12 +44,14 @@ _GLOBAL(copypage_power7) .machine push .machine "power4" - dcbt r0,r4,0b01000 - dcbt r0,r7,0b01010 - dcbtst r0,r9,0b01000 - dcbtst r0,r10,0b01010 + /* setup read stream 0 */ + dcbt r0,r4,0b01000 /* addr from */ + dcbt r0,r7,0b01010 /* length and depth from */ + /* setup write stream 1 */ + dcbtst r0,r9,0b01000 /* addr to */ + dcbtst r0,r10,0b01010 /* length and depth to */ eieio - dcbt r0,r8,0b01010 /* GO */ + dcbt r0,r8,0b01010 /* all streams GO */ .machine pop #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 0d24ff15f5f6..d1f11795a7ad 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -318,12 +318,14 @@ err1; stb r0,0(r3) .machine push .machine "power4" - dcbt r0,r6,0b01000 - dcbt r0,r7,0b01010 - dcbtst r0,r9,0b01000 - dcbtst r0,r10,0b01010 + /* setup read stream 0 */ + dcbt r0,r6,0b01000 /* addr from */ + dcbt r0,r7,0b01010 /* length and depth from */ + /* setup write stream 1 */ + dcbtst r0,r9,0b01000 /* addr to */ + dcbtst r0,r10,0b01010 /* length and depth to */ eieio - dcbt r0,r8,0b01010 /* GO */ + dcbt r0,r8,0b01010 /* all streams GO */ .machine pop beq cr1,.Lunwind_stack_nonvmx_copy diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 229951ffc351..8726779e1409 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -32,6 +32,7 @@ #include <linux/perf_event.h> #include <linux/magic.h> #include <linux/ratelimit.h> +#include <linux/context_tracking.h> #include <asm/firmware.h> #include <asm/page.h> @@ -196,6 +197,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, unsigned long error_code) { + enum ctx_state prev_state = exception_enter(); struct vm_area_struct * vma; struct mm_struct *mm = current->mm; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -204,6 +206,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, int trap = TRAP(regs); int is_exec = trap == 0x400; int fault; + int rc = 0; #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) /* @@ -230,28 +233,30 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, * look at it */ if (error_code & ICSWX_DSI_UCT) { - int rc = acop_handle_fault(regs, address, error_code); + rc = acop_handle_fault(regs, address, error_code); if (rc) - return rc; + goto bail; } #endif /* CONFIG_PPC_ICSWX */ if (notify_page_fault(regs)) - return 0; + goto bail; if (unlikely(debugger_fault_handler(regs))) - return 0; + goto bail; /* On a kernel SLB miss we can only check for a valid exception entry */ - if (!user_mode(regs) && (address >= TASK_SIZE)) - return SIGSEGV; + if (!user_mode(regs) && (address >= TASK_SIZE)) { + rc = SIGSEGV; + goto bail; + } #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \ defined(CONFIG_PPC_BOOK3S_64)) if (error_code & DSISR_DABRMATCH) { /* breakpoint match */ do_break(regs, address, error_code); - return 0; + goto bail; } #endif @@ -260,8 +265,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, local_irq_enable(); if (in_atomic() || mm == NULL) { - if (!user_mode(regs)) - return SIGSEGV; + if (!user_mode(regs)) { + rc = SIGSEGV; + goto bail; + } /* in_atomic() in user mode is really bad, as is current->mm == NULL. */ printk(KERN_EMERG "Page fault in user mode with " @@ -417,9 +424,11 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { - int rc = mm_fault_error(regs, address, fault); + rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) - return rc; + goto bail; + else + rc = 0; } /* @@ -454,7 +463,7 @@ good_area: } up_read(&mm->mmap_sem); - return 0; + goto bail; bad_area: up_read(&mm->mmap_sem); @@ -463,7 +472,7 @@ bad_area_nosemaphore: /* User mode accesses cause a SIGSEGV */ if (user_mode(regs)) { _exception(SIGSEGV, regs, code, address); - return 0; + goto bail; } if (is_exec && (error_code & DSISR_PROTFAULT)) @@ -471,7 +480,11 @@ bad_area_nosemaphore: " page (%lx) - exploit attempt? (uid: %d)\n", address, from_kuid(&init_user_ns, current_uid())); - return SIGSEGV; + rc = SIGSEGV; + +bail: + exception_exit(prev_state); + return rc; } diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index d7efdbf640c7..4b921affa495 100644 --- a/arch/powerpc/mm/gup.c +++ b/arch/powerpc/mm/gup.c @@ -68,7 +68,11 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, next = pmd_addr_end(addr, end); if (pmd_none(pmd)) return 0; - if (is_hugepd(pmdp)) { + if (pmd_huge(pmd)) { + if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next, + write, pages, nr)) + return 0; + } else if (is_hugepd(pmdp)) { if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT, addr, next, write, pages, nr)) return 0; @@ -92,7 +96,11 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, next = pud_addr_end(addr, end); if (pud_none(pud)) return 0; - if (is_hugepd(pudp)) { + if (pud_huge(pud)) { + if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next, + write, pages, nr)) + return 0; + } else if (is_hugepd(pudp)) { if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT, addr, next, write, pages, nr)) return 0; @@ -153,7 +161,11 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) goto slow; - if (is_hugepd(pgdp)) { + if (pgd_huge(pgd)) { + if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next, + write, pages, &nr)) + goto slow; + } else if (is_hugepd(pgdp)) { if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT, addr, next, write, pages, &nr)) goto slow; diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 7443481a315c..0e980acae67c 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -196,7 +196,8 @@ htab_insert_pte: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -219,7 +220,8 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -490,7 +492,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) beq htab_inval_old_hpte ld r6,STK_PARAM(R6)(r1) - ori r26,r6,0x8000 /* Load the hidx mask */ + ori r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */ ld r26,0(r26) addi r5,r25,36 /* Check actual HPTE_SUB bit, this */ rldcr. r0,r31,r5,0 /* must match pgtable.h definition */ @@ -515,7 +517,8 @@ htab_special_pfn: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -542,7 +545,8 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -607,7 +611,7 @@ htab_pte_insert_ok: sld r4,r4,r5 andc r26,r26,r4 or r26,r26,r3 - ori r5,r6,0x8000 + ori r5,r6,PTE_PAGE_HIDX_OFFSET std r26,0(r5) lwsync std r30,0(r6) @@ -840,7 +844,8 @@ ht64_insert_pte: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_64K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -863,7 +868,8 @@ _GLOBAL(ht64_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_64K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index ffc1e00f7a22..4c122c3f1623 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -39,7 +39,7 @@ DEFINE_RAW_SPINLOCK(native_tlbie_lock); -static inline void __tlbie(unsigned long vpn, int psize, int ssize) +static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) { unsigned long va; unsigned int penc; @@ -61,17 +61,31 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize) switch (psize) { case MMU_PAGE_4K: + /* clear out bits after (52) [0....52.....63] */ + va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; + va |= mmu_psize_defs[apsize].sllp << 6; asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) : "memory"); break; default: /* We need 14 to 14 + i bits of va */ - penc = mmu_psize_defs[psize].penc; - va &= ~((1ul << mmu_psize_defs[psize].shift) - 1); + penc = mmu_psize_defs[psize].penc[apsize]; + va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; + /* Add AVAL part */ + if (psize != apsize) { + /* + * MPSS, 64K base page size and 16MB parge page size + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); + } va |= 1; /* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -80,7 +94,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize) } } -static inline void __tlbiel(unsigned long vpn, int psize, int ssize) +static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) { unsigned long va; unsigned int penc; @@ -96,16 +110,30 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize) switch (psize) { case MMU_PAGE_4K: + /* clear out bits after(52) [0....52.....63] */ + va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; + va |= mmu_psize_defs[apsize].sllp << 6; asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)" : : "r"(va) : "memory"); break; default: /* We need 14 to 14 + i bits of va */ - penc = mmu_psize_defs[psize].penc; - va &= ~((1ul << mmu_psize_defs[psize].shift) - 1); + penc = mmu_psize_defs[psize].penc[apsize]; + va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; + /* Add AVAL part */ + if (psize != apsize) { + /* + * MPSS, 64K base page size and 16MB parge page size + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); + } va |= 1; /* L */ asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)" : : "r"(va) : "memory"); @@ -114,7 +142,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize) } -static inline void tlbie(unsigned long vpn, int psize, int ssize, int local) +static inline void tlbie(unsigned long vpn, int psize, int apsize, + int ssize, int local) { unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL); int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); @@ -125,10 +154,10 @@ static inline void tlbie(unsigned long vpn, int psize, int ssize, int local) raw_spin_lock(&native_tlbie_lock); asm volatile("ptesync": : :"memory"); if (use_local) { - __tlbiel(vpn, psize, ssize); + __tlbiel(vpn, psize, apsize, ssize); asm volatile("ptesync": : :"memory"); } else { - __tlbie(vpn, psize, ssize); + __tlbie(vpn, psize, apsize, ssize); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } if (lock_tlbie && !use_local) @@ -156,7 +185,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep) static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, - unsigned long vflags, int psize, int ssize) + unsigned long vflags, int psize, int apsize, int ssize) { struct hash_pte *hptep = htab_address + hpte_group; unsigned long hpte_v, hpte_r; @@ -183,8 +212,8 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, if (i == HPTES_PER_GROUP) return -1; - hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; if (!(vflags & HPTE_V_BOLTED)) { DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n", @@ -244,6 +273,51 @@ static long native_hpte_remove(unsigned long hpte_group) return i; } +static inline int __hpte_actual_psize(unsigned int lp, int psize) +{ + int i, shift; + unsigned int mask; + + /* start from 1 ignoring MMU_PAGE_4K */ + for (i = 1; i < MMU_PAGE_COUNT; i++) { + + /* invalid penc */ + if (mmu_psize_defs[psize].penc[i] == -1) + continue; + /* + * encoding bits per actual page size + * PTE LP actual page size + * rrrr rrrz >=8KB + * rrrr rrzz >=16KB + * rrrr rzzz >=32KB + * rrrr zzzz >=64KB + * ....... + */ + shift = mmu_psize_defs[i].shift - LP_SHIFT; + if (shift > LP_BITS) + shift = LP_BITS; + mask = (1 << shift) - 1; + if ((lp & mask) == mmu_psize_defs[psize].penc[i]) + return i; + } + return -1; +} + +static inline int hpte_actual_psize(struct hash_pte *hptep, int psize) +{ + /* Look at the 8 bit LP value */ + unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1); + + if (!(hptep->v & HPTE_V_VALID)) + return -1; + + /* First check if it is large page */ + if (!(hptep->v & HPTE_V_LARGE)) + return MMU_PAGE_4K; + + return __hpte_actual_psize(lp, psize); +} + static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long vpn, int psize, int ssize, int local) @@ -251,8 +325,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, struct hash_pte *hptep = htab_address + slot; unsigned long hpte_v, want_v; int ret = 0; + int actual_psize; - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)", vpn, want_v & HPTE_V_AVPN, slot, newpp); @@ -260,9 +335,20 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, native_lock_hpte(hptep); hpte_v = hptep->v; - - /* Even if we miss, we need to invalidate the TLB */ - if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) { + actual_psize = hpte_actual_psize(hptep, psize); + /* + * We need to invalidate the TLB always because hpte_remove doesn't do + * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less + * random entry from it. When we do that we don't invalidate the TLB + * (hpte_remove) because we assume the old translation is still + * technically "valid". + */ + if (actual_psize < 0) { + actual_psize = psize; + ret = -1; + goto err_out; + } + if (!HPTE_V_COMPARE(hpte_v, want_v)) { DBG_LOW(" -> miss\n"); ret = -1; } else { @@ -271,10 +357,11 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)); } +err_out: native_unlock_hpte(hptep); /* Ensure it is out of the tlb too. */ - tlbie(vpn, psize, ssize, local); + tlbie(vpn, psize, actual_psize, ssize, local); return ret; } @@ -288,7 +375,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) unsigned long want_v, hpte_v; hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); /* Bolted mappings are only ever in the primary group */ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; @@ -315,6 +402,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, int psize, int ssize) { + int actual_psize; unsigned long vpn; unsigned long vsid; long slot; @@ -327,13 +415,16 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, if (slot == -1) panic("could not find page to bolt\n"); hptep = htab_address + slot; + actual_psize = hpte_actual_psize(hptep, psize); + if (actual_psize < 0) + actual_psize = psize; /* Update the HPTE */ hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | (newpp & (HPTE_R_PP | HPTE_R_N)); /* Ensure it is out of the tlb too. */ - tlbie(vpn, psize, ssize, 0); + tlbie(vpn, psize, actual_psize, ssize, 0); } static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, @@ -343,64 +434,66 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, unsigned long hpte_v; unsigned long want_v; unsigned long flags; + int actual_psize; local_irq_save(flags); DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot); - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); hpte_v = hptep->v; - /* Even if we miss, we need to invalidate the TLB */ - if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) + actual_psize = hpte_actual_psize(hptep, psize); + /* + * We need to invalidate the TLB always because hpte_remove doesn't do + * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less + * random entry from it. When we do that we don't invalidate the TLB + * (hpte_remove) because we assume the old translation is still + * technically "valid". + */ + if (actual_psize < 0) { + actual_psize = psize; + native_unlock_hpte(hptep); + goto err_out; + } + if (!HPTE_V_COMPARE(hpte_v, want_v)) native_unlock_hpte(hptep); else /* Invalidate the hpte. NOTE: this also unlocks it */ hptep->v = 0; +err_out: /* Invalidate the TLB */ - tlbie(vpn, psize, ssize, local); - + tlbie(vpn, psize, actual_psize, ssize, local); local_irq_restore(flags); } -#define LP_SHIFT 12 -#define LP_BITS 8 -#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT) - static void hpte_decode(struct hash_pte *hpte, unsigned long slot, - int *psize, int *ssize, unsigned long *vpn) + int *psize, int *apsize, int *ssize, unsigned long *vpn) { unsigned long avpn, pteg, vpi; - unsigned long hpte_r = hpte->r; unsigned long hpte_v = hpte->v; unsigned long vsid, seg_off; - int i, size, shift, penc; + int size, a_size, shift; + /* Look at the 8 bit LP value */ + unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1); - if (!(hpte_v & HPTE_V_LARGE)) - size = MMU_PAGE_4K; - else { - for (i = 0; i < LP_BITS; i++) { - if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1)) - break; - } - penc = LP_MASK(i+1) >> LP_SHIFT; + if (!(hpte_v & HPTE_V_LARGE)) { + size = MMU_PAGE_4K; + a_size = MMU_PAGE_4K; + } else { for (size = 0; size < MMU_PAGE_COUNT; size++) { - /* 4K pages are not represented by LP */ - if (size == MMU_PAGE_4K) - continue; - /* valid entries have a shift value */ if (!mmu_psize_defs[size].shift) continue; - if (penc == mmu_psize_defs[size].penc) + a_size = __hpte_actual_psize(lp, size); + if (a_size != -1) break; } } - /* This works for all page sizes, and for 256M and 1T segments */ *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; shift = mmu_psize_defs[size].shift; @@ -433,7 +526,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, default: *vpn = size = 0; } - *psize = size; + *psize = size; + *apsize = a_size; } /* @@ -451,7 +545,7 @@ static void native_hpte_clear(void) struct hash_pte *hptep = htab_address; unsigned long hpte_v; unsigned long pteg_count; - int psize, ssize; + int psize, apsize, ssize; pteg_count = htab_hash_mask + 1; @@ -477,9 +571,9 @@ static void native_hpte_clear(void) * already hold the native_tlbie_lock. */ if (hpte_v & HPTE_V_VALID) { - hpte_decode(hptep, slot, &psize, &ssize, &vpn); + hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn); hptep->v = 0; - __tlbie(vpn, psize, ssize); + __tlbie(vpn, psize, apsize, ssize); } } @@ -520,7 +614,7 @@ static void native_flush_hash_range(unsigned long number, int local) slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; slot += hidx & _PTEIDX_GROUP_IX; hptep = htab_address + slot; - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); hpte_v = hptep->v; if (!HPTE_V_COMPARE(hpte_v, want_v) || @@ -540,7 +634,7 @@ static void native_flush_hash_range(unsigned long number, int local) pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) { - __tlbiel(vpn, psize, ssize); + __tlbiel(vpn, psize, psize, ssize); } pte_iterate_hashed_end(); } asm volatile("ptesync":::"memory"); @@ -557,7 +651,7 @@ static void native_flush_hash_range(unsigned long number, int local) pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) { - __tlbie(vpn, psize, ssize); + __tlbie(vpn, psize, psize, ssize); } pte_iterate_hashed_end(); } asm volatile("eieio; tlbsync; ptesync":::"memory"); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 1b6e1271719f..e303a6d74e3a 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -33,6 +33,7 @@ #include <linux/init.h> #include <linux/signal.h> #include <linux/memblock.h> +#include <linux/context_tracking.h> #include <asm/processor.h> #include <asm/pgtable.h> @@ -126,7 +127,7 @@ static struct mmu_psize_def mmu_psize_defaults_old[] = { [MMU_PAGE_4K] = { .shift = 12, .sllp = 0, - .penc = 0, + .penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1}, .avpnm = 0, .tlbiel = 0, }, @@ -140,14 +141,15 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = { [MMU_PAGE_4K] = { .shift = 12, .sllp = 0, - .penc = 0, + .penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1}, .avpnm = 0, .tlbiel = 1, }, [MMU_PAGE_16M] = { .shift = 24, .sllp = SLB_VSID_L, - .penc = 0, + .penc = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0, + [MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 }, .avpnm = 0x1UL, .tlbiel = 0, }, @@ -195,6 +197,11 @@ 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; @@ -204,7 +211,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, BUG_ON(!ppc_md.hpte_insert); ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot, - HPTE_V_BOLTED, psize, ssize); + HPTE_V_BOLTED, psize, psize, ssize); if (ret < 0) break; @@ -271,6 +278,30 @@ static void __init htab_init_seg_sizes(void) of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); } +static int __init get_idx_from_shift(unsigned int shift) +{ + int idx = -1; + + switch (shift) { + case 0xc: + idx = MMU_PAGE_4K; + break; + case 0x10: + idx = MMU_PAGE_64K; + break; + case 0x14: + idx = MMU_PAGE_1M; + break; + case 0x18: + idx = MMU_PAGE_16M; + break; + case 0x22: + idx = MMU_PAGE_16G; + break; + } + return idx; +} + static int __init htab_dt_scan_page_sizes(unsigned long node, const char *uname, int depth, void *data) @@ -286,64 +317,65 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, prop = (u32 *)of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size); if (prop != NULL) { - DBG("Page sizes from device-tree:\n"); + pr_info("Page sizes from device-tree:\n"); size /= 4; cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE); while(size > 0) { - unsigned int shift = prop[0]; + unsigned int base_shift = prop[0]; unsigned int slbenc = prop[1]; unsigned int lpnum = prop[2]; - unsigned int lpenc = 0; struct mmu_psize_def *def; - int idx = -1; + int idx, base_idx; size -= 3; prop += 3; - while(size > 0 && lpnum) { - if (prop[0] == shift) - lpenc = prop[1]; - prop += 2; size -= 2; - lpnum--; + base_idx = get_idx_from_shift(base_shift); + if (base_idx < 0) { + /* + * skip the pte encoding also + */ + prop += lpnum * 2; size -= lpnum * 2; + continue; } - switch(shift) { - case 0xc: - idx = MMU_PAGE_4K; - break; - case 0x10: - idx = MMU_PAGE_64K; - break; - case 0x14: - idx = MMU_PAGE_1M; - break; - case 0x18: - idx = MMU_PAGE_16M; + def = &mmu_psize_defs[base_idx]; + if (base_idx == MMU_PAGE_16M) cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE; - break; - case 0x22: - idx = MMU_PAGE_16G; - break; - } - if (idx < 0) - continue; - def = &mmu_psize_defs[idx]; - def->shift = shift; - if (shift <= 23) + + def->shift = base_shift; + if (base_shift <= 23) def->avpnm = 0; else - def->avpnm = (1 << (shift - 23)) - 1; + def->avpnm = (1 << (base_shift - 23)) - 1; def->sllp = slbenc; - def->penc = lpenc; - /* We don't know for sure what's up with tlbiel, so + /* + * We don't know for sure what's up with tlbiel, so * for now we only set it for 4K and 64K pages */ - if (idx == MMU_PAGE_4K || idx == MMU_PAGE_64K) + if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K) def->tlbiel = 1; else def->tlbiel = 0; - DBG(" %d: shift=%02x, sllp=%04lx, avpnm=%08lx, " - "tlbiel=%d, penc=%d\n", - idx, shift, def->sllp, def->avpnm, def->tlbiel, - def->penc); + while (size > 0 && lpnum) { + unsigned int shift = prop[0]; + int penc = prop[1]; + + prop += 2; size -= 2; + lpnum--; + + idx = get_idx_from_shift(shift); + if (idx < 0) + continue; + + if (penc == -1) + pr_err("Invalid penc for base_shift=%d " + "shift=%d\n", base_shift, shift); + + def->penc[idx] = penc; + pr_info("base_shift=%d: shift=%d, sllp=0x%04lx," + " avpnm=0x%08lx, tlbiel=%d, penc=%d\n", + base_shift, shift, def->sllp, + def->avpnm, def->tlbiel, def->penc[idx]); + } } return 1; } @@ -392,10 +424,21 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, } #endif /* CONFIG_HUGETLB_PAGE */ +static void mmu_psize_set_default_penc(void) +{ + int bpsize, apsize; + for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) + for (apsize = 0; apsize < MMU_PAGE_COUNT; apsize++) + mmu_psize_defs[bpsize].penc[apsize] = -1; +} + static void __init htab_init_page_sizes(void) { int rc; + /* se the invalid penc to -1 */ + mmu_psize_set_default_penc(); + /* Default to 4K pages only */ memcpy(mmu_psize_defs, mmu_psize_defaults_old, sizeof(mmu_psize_defaults_old)); @@ -759,6 +802,8 @@ 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 @@ -892,14 +937,14 @@ static inline int subpage_protection(struct mm_struct *mm, unsigned long ea) void hash_failure_debug(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long trap, - int ssize, int psize, unsigned long pte) + int ssize, int psize, int lpsize, unsigned long pte) { if (!printk_ratelimit()) return; pr_info("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n", ea, access, current->comm); - pr_info(" trap=0x%lx vsid=0x%lx ssize=%d psize=%d pte=0x%lx\n", - trap, vsid, ssize, psize, pte); + pr_info(" trap=0x%lx vsid=0x%lx ssize=%d base psize=%d psize %d pte=0x%lx\n", + trap, vsid, ssize, psize, lpsize, pte); } /* Result code is: @@ -910,6 +955,7 @@ void hash_failure_debug(unsigned long ea, unsigned long access, */ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) { + enum ctx_state prev_state = exception_enter(); pgd_t *pgdir; unsigned long vsid; struct mm_struct *mm; @@ -922,11 +968,6 @@ 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: @@ -934,7 +975,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) mm = current->mm; if (! mm) { DBG_LOW(" user region with no mm !\n"); - return 1; + rc = 1; + goto bail; } psize = get_slice_psize(mm, ea); ssize = user_segment_size(ea); @@ -953,14 +995,23 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) /* Not a valid range * Send the problem up to do_page_fault */ - return 1; + rc = 1; + goto bail; } DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid); + /* Bad address. */ + if (!vsid) { + DBG_LOW("Bad address!\n"); + rc = 1; + goto bail; + } /* Get pgdir */ pgdir = mm->pgd; - if (pgdir == NULL) - return 1; + if (pgdir == NULL) { + rc = 1; + goto bail; + } /* Check CPU locality */ tmp = cpumask_of(smp_processor_id()); @@ -983,7 +1034,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift); if (ptep == NULL || !pte_present(*ptep)) { DBG_LOW(" no PTE !\n"); - return 1; + rc = 1; + goto bail; } /* Add _PAGE_PRESENT to the required access perm */ @@ -994,13 +1046,16 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) */ if (access & ~pte_val(*ptep)) { DBG_LOW(" no access !\n"); - return 1; + rc = 1; + goto bail; } #ifdef CONFIG_HUGETLB_PAGE - if (hugeshift) - return __hash_page_huge(ea, access, vsid, ptep, trap, local, + if (hugeshift) { + rc = __hash_page_huge(ea, access, vsid, ptep, trap, local, ssize, hugeshift, psize); + goto bail; + } #endif /* CONFIG_HUGETLB_PAGE */ #ifndef CONFIG_PPC_64K_PAGES @@ -1072,7 +1127,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) */ if (rc == -1) hash_failure_debug(ea, access, vsid, trap, ssize, psize, - pte_val(*ptep)); + psize, pte_val(*ptep)); #ifndef CONFIG_PPC_64K_PAGES DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep)); #else @@ -1080,6 +1135,9 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) pte_val(*(ptep + PTRS_PER_PTE))); #endif DBG_LOW(" -> rc=%d\n", rc); + +bail: + exception_exit(prev_state); return rc; } EXPORT_SYMBOL_GPL(hash_page); @@ -1126,6 +1184,8 @@ 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); @@ -1148,7 +1208,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, */ if (rc == -1) hash_failure_debug(ea, access, vsid, trap, ssize, - mm->context.user_psize, pte_val(*ptep)); + mm->context.user_psize, + mm->context.user_psize, + pte_val(*ptep)); local_irq_restore(flags); } @@ -1182,6 +1244,7 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, * unmapping it first, it may see the speculated version. */ if (local && cpu_has_feature(CPU_FTR_TM) && + current->thread.regs && MSR_TM_ACTIVE(current->thread.regs->msr)) { tm_enable(); tm_abort(TM_CAUSE_TLBI); @@ -1210,6 +1273,8 @@ void flush_hash_range(unsigned long number, int local) */ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) { + enum ctx_state prev_state = exception_enter(); + if (user_mode(regs)) { #ifdef CONFIG_PPC_SUBPAGE_PROT if (rc == -2) @@ -1219,23 +1284,64 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) _exception(SIGBUS, regs, BUS_ADRERR, address); } else bad_page_fault(regs, address, SIGBUS); + + exception_exit(prev_state); +} + +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, 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, 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..0f1d94a1fb82 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 @@ -129,7 +110,7 @@ repeat: if (unlikely(slot == -2)) { *ptep = __pte(old_pte); hash_failure_debug(ea, access, vsid, trap, ssize, - mmu_psize, old_pte); + mmu_psize, mmu_psize, old_pte); return -1; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a6de0a7d8eb..237c8e5f2640 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -48,30 +48,71 @@ static u64 gpage_freearray[MAX_NUMBER_GPAGES]; static unsigned nr_gpages; #endif -static inline int shift_to_mmu_psize(unsigned int shift) +#define hugepd_none(hpd) ((hpd).pd == 0) + +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * At this point we do the placement change only for BOOK3S 64. This would + * possibly work on other subarchs. + */ + +/* + * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have + * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; + */ +int pmd_huge(pmd_t pmd) { - int psize; + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return ((pmd_val(pmd) & 0x3) != 0x0); +} - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) - if (mmu_psize_defs[psize].shift == shift) - return psize; - return -1; +int pud_huge(pud_t pud) +{ + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return ((pud_val(pud) & 0x3) != 0x0); } -static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +int pgd_huge(pgd_t pgd) { - if (mmu_psize_defs[mmu_psize].shift) - return mmu_psize_defs[mmu_psize].shift; - BUG(); + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return ((pgd_val(pgd) & 0x3) != 0x0); +} +#else +int pmd_huge(pmd_t pmd) +{ + return 0; } -#define hugepd_none(hpd) ((hpd).pd == 0) +int pud_huge(pud_t pud) +{ + return 0; +} + +int pgd_huge(pgd_t pgd) +{ + return 0; +} +#endif +/* + * We have 4 cases for pgds and pmds: + * (1) invalid (all zeroes) + * (2) pointer to next table, as normal; bottom 6 bits == 0 + * (3) leaf pte for huge page, bottom two bits != 00 + * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table + */ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift) { pgd_t *pg; pud_t *pu; pmd_t *pm; + pte_t *ret_pte; hugepd_t *hpdp = NULL; unsigned pdshift = PGDIR_SHIFT; @@ -79,30 +120,43 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift *shift = 0; pg = pgdir + pgd_index(ea); - if (is_hugepd(pg)) { + + if (pgd_huge(*pg)) { + ret_pte = (pte_t *) pg; + goto out; + } else if (is_hugepd(pg)) hpdp = (hugepd_t *)pg; - } else if (!pgd_none(*pg)) { + else if (!pgd_none(*pg)) { pdshift = PUD_SHIFT; pu = pud_offset(pg, ea); - if (is_hugepd(pu)) + + if (pud_huge(*pu)) { + ret_pte = (pte_t *) pu; + goto out; + } else if (is_hugepd(pu)) hpdp = (hugepd_t *)pu; else if (!pud_none(*pu)) { pdshift = PMD_SHIFT; pm = pmd_offset(pu, ea); - if (is_hugepd(pm)) + + if (pmd_huge(*pm)) { + ret_pte = (pte_t *) pm; + goto out; + } else if (is_hugepd(pm)) hpdp = (hugepd_t *)pm; - else if (!pmd_none(*pm)) { + else if (!pmd_none(*pm)) return pte_offset_kernel(pm, ea); - } } } - if (!hpdp) return NULL; + ret_pte = hugepte_offset(hpdp, ea, pdshift); + pdshift = hugepd_shift(*hpdp); +out: if (shift) - *shift = hugepd_shift(*hpdp); - return hugepte_offset(hpdp, ea, pdshift); + *shift = pdshift; + return ret_pte; } EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte); @@ -145,6 +199,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (unlikely(!hugepd_none(*hpdp))) break; else + /* We use the old format for PPC_FSL_BOOK3E */ hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift; } /* If we bailed from the for loop early, an error occurred, clean up */ @@ -156,9 +211,15 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, #else if (!hugepd_none(*hpdp)) kmem_cache_free(cachep, new); - else + else { +#ifdef CONFIG_PPC_BOOK3S_64 + hpdp->pd = (unsigned long)new | + (shift_to_mmu_psize(pshift) << 2); +#else hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift; #endif + } +#endif spin_unlock(&mm->page_table_lock); return 0; } @@ -175,6 +236,61 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, #define HUGEPD_PUD_SHIFT PMD_SHIFT #endif +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * At this point we do the placement change only for BOOK3S 64. This would + * possibly work on other subarchs. + */ +pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) +{ + pgd_t *pg; + pud_t *pu; + pmd_t *pm; + hugepd_t *hpdp = NULL; + unsigned pshift = __ffs(sz); + unsigned pdshift = PGDIR_SHIFT; + + addr &= ~(sz-1); + pg = pgd_offset(mm, addr); + + if (pshift == PGDIR_SHIFT) + /* 16GB huge page */ + return (pte_t *) pg; + else if (pshift > PUD_SHIFT) + /* + * We need to use hugepd table + */ + hpdp = (hugepd_t *)pg; + else { + pdshift = PUD_SHIFT; + pu = pud_alloc(mm, pg, addr); + if (pshift == PUD_SHIFT) + return (pte_t *)pu; + else if (pshift > PMD_SHIFT) + hpdp = (hugepd_t *)pu; + else { + pdshift = PMD_SHIFT; + pm = pmd_alloc(mm, pu, addr); + if (pshift == PMD_SHIFT) + /* 16MB hugepage */ + return (pte_t *)pm; + else + hpdp = (hugepd_t *)pm; + } + } + if (!hpdp) + return NULL; + + BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp)); + + if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift)) + return NULL; + + return hugepte_offset(hpdp, addr, pdshift); +} + +#else + pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pg; @@ -212,6 +328,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz return hugepte_offset(hpdp, addr, pdshift); } +#endif #ifdef CONFIG_PPC_FSL_BOOK3E /* Build list of addresses of gigantic pages. This function is used in early @@ -475,7 +592,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, do { pmd = pmd_offset(pud, addr); next = pmd_addr_end(addr, end); - if (pmd_none(*pmd)) + if (pmd_none_or_clear_bad(pmd)) continue; #ifdef CONFIG_PPC_FSL_BOOK3E /* @@ -628,16 +745,6 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) return page; } -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -646,8 +753,8 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, return NULL; } -static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) +int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; unsigned long pte_end; @@ -742,7 +849,7 @@ 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 @@ -883,11 +990,16 @@ static int __init hugetlbpage_init(void) pdshift = PUD_SHIFT; else pdshift = PGDIR_SHIFT; - - pgtable_cache_add(pdshift - shift, NULL); - if (!PGT_CACHE(pdshift - shift)) - panic("hugetlbpage_init(): could not create " - "pgtable cache for %d bit pagesize\n", shift); + /* + * if we have pdshift and shift value same, we don't + * use pgt cache for hugepd. + */ + if (pdshift != shift) { + pgtable_cache_add(pdshift - shift, NULL); + if (!PGT_CACHE(pdshift - shift)) + panic("hugetlbpage_init(): could not create " + "pgtable cache for %d bit pagesize\n", shift); + } } /* Set default large page size. Currently, we pick 16M or 1M 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/init_64.c b/arch/powerpc/mm/init_64.c index 7e2246fb2f31..a90b9c458990 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -129,8 +129,7 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); new = kmem_cache_create(name, table_size, align, 0, ctor); - PGT_CACHE(shift) = new; - + pgtable_cache[shift - 1] = new; pr_debug("Allocated pgtable cache for order %d\n", shift); } @@ -216,7 +215,8 @@ static void __meminit vmemmap_create_mapping(unsigned long start, unsigned long phys) { int mapped = htab_bolt_mapping(start, start + page_size, phys, - PAGE_KERNEL, mmu_vmemmap_psize, + pgprot_val(PAGE_KERNEL), + mmu_vmemmap_psize, mmu_kernel_ssize); BUG_ON(mapped < 0); } @@ -263,19 +263,14 @@ static __meminit void vmemmap_list_populate(unsigned long phys, vmemmap_list = vmem_back; } -int __meminit vmemmap_populate(struct page *start_page, - unsigned long nr_pages, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - unsigned long start = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; /* Align to the page size of the linear mapping. */ start = _ALIGN_DOWN(start, page_size); - pr_debug("vmemmap_populate page %p, %ld pages, node %d\n", - start_page, nr_pages, node); - pr_debug(" -> map %lx..%lx\n", start, end); + pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node); for (; start < end; start += page_size) { void *p; @@ -298,7 +293,7 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f1f7409a4183..0988a26e0413 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) { @@ -352,13 +351,9 @@ void __init mem_init(void) struct page *page = pfn_to_page(pfn); if (memblock_is_reserved(paddr)) continue; - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; + free_highmem_page(page); reservedpages--; } - totalram_pages += totalhigh_pages; printk(KERN_DEBUG "High memory: %luk\n", totalhigh_pages << (PAGE_SHIFT-10)); } @@ -405,39 +400,14 @@ void __init mem_init(void) void free_initmem(void) { - unsigned long addr; - ppc_md.progress = ppc_printk_progress; - - addr = (unsigned long)__init_begin; - for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) { - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - pr_info("Freeing unused kernel memory: %luk freed\n", - ((unsigned long)__init_end - - (unsigned long)__init_begin) >> 10); + free_initmem_default(POISON_FREE_INITMEM); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - if (start >= end) - return; - - start = _ALIGN_DOWN(start, PAGE_SIZE); - end = _ALIGN_UP(end, PAGE_SIZE); - pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 40bc5b0ace54..178876aef40f 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -23,21 +23,13 @@ #include <linux/slab.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> #include "icswx.h" 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 +48,7 @@ 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); @@ -94,6 +86,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) spin_lock_init(mm->context.cop_lockp); #endif /* CONFIG_PPC_ICSWX */ +#ifdef CONFIG_PPC_64K_PAGES + mm->context.pte_frag = NULL; +#endif return 0; } @@ -105,13 +100,46 @@ void __destroy_context(int context_id) } EXPORT_SYMBOL_GPL(__destroy_context); +#ifdef CONFIG_PPC_64K_PAGES +static void destroy_pagetable_page(struct mm_struct *mm) +{ + int count; + void *pte_frag; + struct page *page; + + pte_frag = mm->context.pte_frag; + if (!pte_frag) + return; + + page = virt_to_page(pte_frag); + /* drop all the pending references */ + count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; + /* We allow PTE_FRAG_NR fragments from a PTE page */ + count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count); + if (!count) { + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } +} + +#else +static inline void destroy_pagetable_page(struct mm_struct *mm) +{ + return; +} +#endif + + void destroy_context(struct mm_struct *mm) { + #ifdef CONFIG_PPC_ICSWX drop_cop(mm->context.acop, mm); kfree(mm->context.cop_lockp); mm->context.cop_lockp = NULL; #endif /* CONFIG_PPC_ICSWX */ + + destroy_pagetable_page(mm); __destroy_context(mm->context.id); subpage_prot_free(mm); mm->context.id = MMU_NO_CONTEXT; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index bba87ca2b4d7..88c0425dc0a8 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -22,6 +22,11 @@ #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 <linux/slab.h> #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> @@ -29,6 +34,7 @@ #include <asm/paca.h> #include <asm/hvcall.h> #include <asm/setup.h> +#include <asm/vdso.h> static int numa_enabled = 1; @@ -62,14 +68,11 @@ static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS]; */ static void __init setup_node_to_cpumask_map(void) { - unsigned int node, num = 0; + unsigned int node; /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } + if (nr_node_ids == MAX_NUMNODES) + setup_nr_node_ids(); /* allocate the map */ for (node = 0; node < nr_node_ids; node++) @@ -79,7 +82,7 @@ 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 +204,7 @@ 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 +294,7 @@ 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 +326,10 @@ 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 +1257,18 @@ 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 +1304,9 @@ 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 +1320,10 @@ 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 +1415,84 @@ 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 +1509,165 @@ 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); +} + +#ifdef CONFIG_SMP + +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, +}; + +#endif + /* - * 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; +#ifdef CONFIG_SMP + rc = of_reconfig_notifier_register(&dt_update_nb); +#endif + } + } 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; +#ifdef CONFIG_SMP + rc = of_reconfig_notifier_unregister(&dt_update_nb); +#endif + } 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..a854096e1023 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 @@ -337,3 +337,121 @@ EXPORT_SYMBOL(__ioremap_at); EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(__iounmap); EXPORT_SYMBOL(__iounmap_at); + +#ifdef CONFIG_PPC_64K_PAGES +static pte_t *get_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + spin_lock(&mm->page_table_lock); + ret = mm->context.pte_frag; + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + mm->context.pte_frag = pte_frag; + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | + __GFP_REPEAT | __GFP_ZERO); + if (!page) + return NULL; + + ret = page_address(page); + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!mm->context.pte_frag)) { + atomic_set(&page->_count, PTE_FRAG_NR); + mm->context.pte_frag = ret + PTE_FRAG_SIZE; + } + spin_unlock(&mm->page_table_lock); + + if (!kernel) + pgtable_page_ctor(page); + + return (pte_t *)ret; +} + +pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_cache(mm, kernel); +} + +void page_table_free(struct mm_struct *mm, unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + if (!kernel) + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } +} + +#ifdef CONFIG_SMP +static void page_table_free_rcu(void *table) +{ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } +} + +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) +{ + unsigned long pgf = (unsigned long)table; + + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + pgf |= shift; + tlb_remove_table(tlb, (void *)pgf); +} + +void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; + + if (!shift) + /* PTE page needs special handling */ + page_table_free_rcu(table); + else { + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(shift), table); + } +} +#else +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) +{ + if (!shift) { + /* PTE page needs special handling */ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } + } else { + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(shift), table); + } +} +#endif +#endif /* CONFIG_PPC_64K_PAGES */ 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/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index df32a838dcfa..6888cad5103d 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -414,9 +414,9 @@ static void setup_page_sizes(void) #ifdef CONFIG_PPC_FSL_BOOK3E unsigned int mmucfg = mfspr(SPRN_MMUCFG); + int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); - if (((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) && - (mmu_has_feature(MMU_FTR_TYPE_FSL_E))) { + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) { unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG); unsigned int min_pg, max_pg; @@ -442,6 +442,20 @@ static void setup_page_sizes(void) goto no_indirect; } + + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { + u32 tlb1ps = mfspr(SPRN_TLB1PS); + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def = &mmu_psize_defs[psize]; + + if (tlb1ps & (1U << (def->shift - 10))) { + def->flags |= MMU_PAGE_SIZE_DIRECT; + } + } + + goto no_indirect; + } #endif tlb0cfg = mfspr(SPRN_TLB0CFG); diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e834f1ec23c8..c427ae36374a 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -671,16 +671,12 @@ void bpf_jit_compile(struct sk_filter *fp) } if (bpf_jit_enable > 1) - pr_info("flen=%d proglen=%u pass=%d image=%p\n", - flen, proglen, pass, image); + /* Note that we output the base address of the code_base + * rather than image, since opcodes are in code_base. + */ + bpf_jit_dump(flen, proglen, pass, code_base); if (image) { - if (bpf_jit_enable > 1) - print_hex_dump(KERN_ERR, "JIT code: ", - DUMP_PREFIX_ADDRESS, - 16, 1, code_base, - proglen, false); - bpf_flush_icache(code_base, code_base + (proglen/4)); /* Function descriptor nastiness: Address + TOC */ ((u64 *)image)[0] = (u64)code_base; 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..845c867444e6 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -13,11 +13,18 @@ #include <linux/perf_event.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> #include <asm/reg.h> #include <asm/pmc.h> #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> +#include <asm/code-patching.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; @@ -38,7 +45,15 @@ 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; @@ -87,8 +102,17 @@ static inline int siar_valid(struct pt_regs *regs) return 1; } +static inline void power_pmu_bhrb_enable(struct perf_event *event) {} +static inline void power_pmu_bhrb_disable(struct perf_event *event) {} +void power_pmu_flush_branch_stack(void) {} +static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} #endif /* CONFIG_PPC32 */ +static bool regs_use_siar(struct pt_regs *regs) +{ + return !!regs->result; +} + /* * Things that are specific to 64-bit implementations. */ @@ -98,11 +122,12 @@ 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; } @@ -111,43 +136,57 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) * If we're not doing instruction sampling, give them the SDAR * (sampled data address). If we are doing instruction sampling, then * only give them the SDAR if it corresponds to the instruction - * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC or - * the [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA. + * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the + * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER. */ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { unsigned long mmcra = regs->dsisr; - unsigned long sdsync; + bool sdar_valid; - if (ppmu->flags & PPMU_SIAR_VALID) - sdsync = POWER7P_MMCRA_SDAR_VALID; - else if (ppmu->flags & PPMU_ALT_SIPR) - sdsync = POWER6_MMCRA_SDSYNC; - else - sdsync = MMCRA_SDSYNC; + if (ppmu->flags & PPMU_HAS_SIER) + sdar_valid = regs->dar & SIER_SDAR_VALID; + else { + unsigned long sdsync; + + if (ppmu->flags & PPMU_SIAR_VALID) + sdsync = POWER7P_MMCRA_SDAR_VALID; + else if (ppmu->flags & PPMU_ALT_SIPR) + sdsync = POWER6_MMCRA_SDSYNC; + else + sdsync = MMCRA_SDSYNC; + + sdar_valid = mmcra & sdsync; + } - if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync)) + if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid) *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 inline u32 perf_flags_from_msr(struct pt_regs *regs) @@ -161,8 +200,7 @@ 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); @@ -181,16 +219,19 @@ 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 +241,11 @@ static inline void perf_read_regs(struct pt_regs *regs) int marked = mmcra & MMCRA_SAMPLE_ENABLE; int use_siar; + regs->dsisr = mmcra; + + if (ppmu->flags & PPMU_HAS_SIER) + regs->dar = mfspr(SPRN_SIER); + /* * If this isn't a PMU exception (eg a software event) the SIAR is * not valid. Use pt_regs. @@ -223,12 +269,11 @@ 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 (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs)) use_siar = 0; else use_siar = 1; - regs->dsisr = mmcra; regs->result = use_siar; } @@ -253,12 +298,170 @@ static inline int siar_valid(struct pt_regs *regs) unsigned long mmcra = regs->dsisr; int marked = mmcra & MMCRA_SAMPLE_ENABLE; - if ((ppmu->flags & PPMU_SIAR_VALID) && marked) - return mmcra & POWER7P_MMCRA_SIAR_VALID; + if (marked) { + if (ppmu->flags & PPMU_HAS_SIER) + return regs->dar & SIER_SIAR_VALID; + + if (ppmu->flags & PPMU_SIAR_VALID) + return mmcra & POWER7P_MMCRA_SIAR_VALID; + } return 1; } + +/* Reset all possible BHRB entries */ +static void power_pmu_bhrb_reset(void) +{ + asm volatile(PPC_CLRBHRB); +} + +static 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++; +} + +static 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; + } +} + +/* 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(); +} +/* Calculate the to address for a branch */ +static __u64 power_pmu_bhrb_to(u64 addr) +{ + unsigned int instr; + int ret; + __u64 target; + + if (is_kernel_addr(addr)) + return branch_target((unsigned int *)addr); + + /* Userspace: need copy instruction here then translate it */ + pagefault_disable(); + ret = __get_user_inatomic(instr, (unsigned int __user *)addr); + if (ret) { + pagefault_enable(); + return 0; + } + pagefault_enable(); + + target = branch_target(&instr); + if ((!target) || (instr & BRANCH_ABSOLUTE)) + return target; + + /* Translate relative branch target from kernel to user address */ + return target - (unsigned long)&instr + addr; +} + +/* Processing BHRB entries */ +void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +{ + u64 val; + u64 addr; + int r_index, u_index, pred; + + r_index = 0; + u_index = 0; + while (r_index < ppmu->bhrb_nr) { + /* Assembly read function */ + val = read_bhrb(r_index++); + if (!val) + /* Terminal marker: End of valid BHRB entries */ + break; + else { + addr = val & BHRB_EA; + pred = val & BHRB_PREDICTION; + + if (!addr) + /* invalid entry */ + continue; + + /* Branches are read most recent first (ie. mfbhrb 0 is + * the most recent branch). + * There are two types of valid entries: + * 1) a target entry which is the to address of a + * computed goto like a blr,bctr,btar. The next + * entry read from the bhrb will be branch + * corresponding to this target (ie. the actual + * blr/bctr/btar instruction). + * 2) a from address which is an actual branch. If a + * target entry proceeds this, then this is the + * matching branch for that target. If this is not + * following a target entry, then this is a branch + * where the target is given as an immediate field + * in the instruction (ie. an i or b form branch). + * In this case we need to read the instruction from + * memory to determine the target/to address. + */ + + if (val & BHRB_TARGET) { + /* Target branches use two entries + * (ie. computed gotos/XL form) + */ + cpuhw->bhrb_entries[u_index].to = addr; + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + + /* Get from address in next entry */ + val = read_bhrb(r_index++); + addr = val & BHRB_EA; + if (val & BHRB_TARGET) { + /* Shouldn't have two targets in a + row.. Reset index and try again */ + r_index--; + addr = 0; + } + cpuhw->bhrb_entries[u_index].from = addr; + } else { + /* Branches to immediate field + (ie I or B form) */ + cpuhw->bhrb_entries[u_index].from = addr; + cpuhw->bhrb_entries[u_index].to = + power_pmu_bhrb_to(addr); + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + } + u_index++; + + } + } + cpuhw->bhrb_stack.nr = u_index; + return; +} + #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -822,6 +1025,9 @@ static void power_pmu_enable(struct pmu *pmu) } out: + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + local_irq_restore(flags); } @@ -911,6 +1117,9 @@ 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 +1172,9 @@ 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); } @@ -1195,9 +1407,11 @@ 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 +1492,15 @@ 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; @@ -1336,9 +1559,9 @@ 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, }; - /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -1397,6 +1620,13 @@ 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 +1652,7 @@ 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..6e287f1294fa 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 @@ -145,7 +138,6 @@ config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 40x select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help Enable gpiolib support for ppc40x based boards diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 0effe9f5a1ea..d6c7506ec7d9 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -248,7 +248,6 @@ config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 44x select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help Enable gpiolib support for ppc440 based boards @@ -274,6 +273,8 @@ config 440EPX select IBM_EMAC_EMAC4 select IBM_EMAC_RGMII select IBM_EMAC_ZMII + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config 440GRX bool diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index c16999802ecf..fc9c1cbfcb1d 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -7,6 +7,8 @@ config PPC_MPC512x select PPC_PCI_CHOICE select FSL_PCI if PCI select ARCH_WANT_OPTIONAL_GPIOLIB + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config MPC5121_ADS bool "Freescale MPC5121E ADS" @@ -15,16 +17,16 @@ 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..6eb94ab99d39 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -172,12 +172,9 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb; static inline void mpc512x_free_bootmem(struct page *page) { - __ClearPageReserved(page); BUG_ON(PageTail(page)); BUG_ON(atomic_read(&page->_count) > 1); - atomic_set(&page->_count, 1); - __free_page(page); - totalram_pages++; + free_reserved_page(page); } void mpc512x_release_bootmem(void) @@ -330,26 +327,34 @@ 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 +380,16 @@ 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/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index a0dcd577fb0d..efdd37c775ad 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -203,7 +203,6 @@ config GE_IMP3A select DEFAULT_UIMAGE select SWIOTLB select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -305,6 +304,40 @@ config PPC_QEMU_E500 unset based on the emulated CPU (or actual host CPU in the case of KVM). +if PPC64 + +config T4240_QDS + bool "Freescale T4240 QDS" + select DEFAULT_UIMAGE + select E500 + select PPC_E500MC + select PHYS_64BIT + select SWIOTLB + select ARCH_REQUIRE_GPIOLIB + select GPIO_MPC8XXX + select HAS_RAPIDIO + select PPC_EPAPR_HV_PIC + help + This option enables support for the T4240 QDS board + +config B4_QDS + bool "Freescale B4 QDS" + select DEFAULT_UIMAGE + select E500 + select PPC_E500MC + select PHYS_64BIT + select SWIOTLB + select GPIOLIB + select ARCH_REQUIRE_GPIOLIB + select HAS_RAPIDIO + select PPC_EPAPR_HV_PIC + help + This option enables support for the B4 QDS board + The B4 application development system B4 QDS is a complete + debugging environment intended for engineers developing + applications for the B4. + +endif endif # FSL_SOC_BOOKE config TQM85xx diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 07d0dbb141c0..2eab37ea4a9d 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -22,6 +22,8 @@ obj-$(CONFIG_P3041_DS) += p3041_ds.o corenet_ds.o obj-$(CONFIG_P4080_DS) += p4080_ds.o corenet_ds.o obj-$(CONFIG_P5020_DS) += p5020_ds.o corenet_ds.o obj-$(CONFIG_P5040_DS) += p5040_ds.o corenet_ds.o +obj-$(CONFIG_T4240_QDS) += t4240_qds.o corenet_ds.o +obj-$(CONFIG_B4_QDS) += b4_qds.o corenet_ds.o obj-$(CONFIG_STX_GP3) += stx_gp3.o obj-$(CONFIG_TQM85xx) += tqm85xx.o obj-$(CONFIG_SBC8548) += sbc8548.o diff --git a/arch/powerpc/platforms/85xx/b4_qds.c b/arch/powerpc/platforms/85xx/b4_qds.c new file mode 100644 index 000000000000..0c6702f8b88e --- /dev/null +++ b/arch/powerpc/platforms/85xx/b4_qds.c @@ -0,0 +1,102 @@ +/* + * B4 QDS Setup + * Should apply for QDS platform of B4860 and it's personalities. + * viz B4860/B4420/B4220QDS + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * 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/pci.h> +#include <linux/kdev_t.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/phy.h> + +#include <asm/time.h> +#include <asm/machdep.h> +#include <asm/pci-bridge.h> +#include <mm/mmu_decl.h> +#include <asm/prom.h> +#include <asm/udbg.h> +#include <asm/mpic.h> + +#include <linux/of_platform.h> +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> +#include <asm/ehv_pic.h> + +#include "corenet_ds.h" + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init b4_qds_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); +#ifdef CONFIG_SMP + extern struct smp_ops_t smp_85xx_ops; +#endif + + if ((of_flat_dt_is_compatible(root, "fsl,B4860QDS")) || + (of_flat_dt_is_compatible(root, "fsl,B4420QDS")) || + (of_flat_dt_is_compatible(root, "fsl,B4220QDS"))) + return 1; + + /* Check if we're running under the Freescale hypervisor */ + if ((of_flat_dt_is_compatible(root, "fsl,B4860QDS-hv")) || + (of_flat_dt_is_compatible(root, "fsl,B4420QDS-hv")) || + (of_flat_dt_is_compatible(root, "fsl,B4220QDS-hv"))) { + ppc_md.init_IRQ = ehv_pic_init; + ppc_md.get_irq = ehv_pic_get_irq; + ppc_md.restart = fsl_hv_restart; + ppc_md.power_off = fsl_hv_halt; + ppc_md.halt = fsl_hv_halt; +#ifdef CONFIG_SMP + /* + * Disable the timebase sync operations because we can't write + * to the timebase registers under the hypervisor. + */ + smp_85xx_ops.give_timebase = NULL; + smp_85xx_ops.take_timebase = NULL; +#endif + return 1; + } + + return 0; +} + +define_machine(b4_qds) { + .name = "B4 QDS", + .probe = b4_qds_probe, + .setup_arch = corenet_ds_setup_arch, + .init_IRQ = corenet_ds_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif +/* coreint doesn't play nice with lazy EE, use legacy mpic for now */ +#ifdef CONFIG_PPC64 + .get_irq = mpic_get_irq, +#else + .get_irq = mpic_get_coreint_irq, +#endif + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +#ifdef CONFIG_PPC64 + .power_save = book3e_idle, +#else + .power_save = e500_idle, +#endif +}; + +machine_arch_initcall(b4_qds, corenet_ds_publish_devices); + +#ifdef CONFIG_SWIOTLB +machine_arch_initcall(b4_qds, swiotlb_setup_bus_notifier); +#endif diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c index 6f355d8c92f6..c59c617eee93 100644 --- a/arch/powerpc/platforms/85xx/corenet_ds.c +++ b/arch/powerpc/platforms/85xx/corenet_ds.c @@ -40,7 +40,7 @@ void __init corenet_ds_pic_init(void) if (ppc_md.get_irq == mpic_get_coreint_irq) flags |= MPIC_ENABLE_COREINT; - mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); + mpic = mpic_alloc(NULL, 0, flags, 0, 512, " OpenPIC "); BUG_ON(mpic == NULL); mpic_init(mpic); @@ -83,6 +83,9 @@ static const struct of_device_id of_device_ids[] = { { .compatible = "fsl,qoriq-pcie-v2.4", }, + { + .compatible = "fsl,qoriq-pcie-v3.0", + }, /* The following two are for the Freescale hypervisor */ { .name = "hypervisor", diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index 611e92f291c4..7179726ba5c5 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -69,7 +69,7 @@ static irqreturn_t gpio_halt_irq(int irq, void *__data) return IRQ_HANDLED; }; -static int __devinit gpio_halt_probe(struct platform_device *pdev) +static int gpio_halt_probe(struct platform_device *pdev) { enum of_gpio_flags flags; struct device_node *node = pdev->dev.of_node; @@ -128,7 +128,7 @@ static int __devinit gpio_halt_probe(struct platform_device *pdev) return 0; } -static int __devexit gpio_halt_remove(struct platform_device *pdev) +static int gpio_halt_remove(struct platform_device *pdev) { if (halt_node) { int gpio = of_get_gpio(halt_node, 0); @@ -165,7 +165,7 @@ static struct platform_driver gpio_halt_driver = { .of_match_table = gpio_halt_match, }, .probe = gpio_halt_probe, - .remove = __devexit_p(gpio_halt_remove), + .remove = gpio_halt_remove, }; module_platform_driver(gpio_halt_driver); diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 148c2f2d9780..6a1759939c6b 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -201,7 +201,7 @@ static int __cpuinit smp_85xx_kick_cpu(int nr) * We don't set the BPTR register here since it already points * to the boot page properly. */ - mpic_reset_core(hw_cpu); + mpic_reset_core(nr); /* * wait until core is ready... diff --git a/arch/powerpc/platforms/85xx/t4240_qds.c b/arch/powerpc/platforms/85xx/t4240_qds.c new file mode 100644 index 000000000000..5998e9f33304 --- /dev/null +++ b/arch/powerpc/platforms/85xx/t4240_qds.c @@ -0,0 +1,98 @@ +/* + * T4240 QDS Setup + * + * Maintained by Kumar Gala (see MAINTAINERS for contact information) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * 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/pci.h> +#include <linux/kdev_t.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/phy.h> + +#include <asm/time.h> +#include <asm/machdep.h> +#include <asm/pci-bridge.h> +#include <mm/mmu_decl.h> +#include <asm/prom.h> +#include <asm/udbg.h> +#include <asm/mpic.h> + +#include <linux/of_platform.h> +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> +#include <asm/ehv_pic.h> + +#include "corenet_ds.h" + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init t4240_qds_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); +#ifdef CONFIG_SMP + extern struct smp_ops_t smp_85xx_ops; +#endif + + if (of_flat_dt_is_compatible(root, "fsl,T4240QDS")) + return 1; + + /* Check if we're running under the Freescale hypervisor */ + if (of_flat_dt_is_compatible(root, "fsl,T4240QDS-hv")) { + ppc_md.init_IRQ = ehv_pic_init; + ppc_md.get_irq = ehv_pic_get_irq; + ppc_md.restart = fsl_hv_restart; + ppc_md.power_off = fsl_hv_halt; + ppc_md.halt = fsl_hv_halt; +#ifdef CONFIG_SMP + /* + * Disable the timebase sync operations because we can't write + * to the timebase registers under the hypervisor. + */ + smp_85xx_ops.give_timebase = NULL; + smp_85xx_ops.take_timebase = NULL; +#endif + return 1; + } + + return 0; +} + +define_machine(t4240_qds) { + .name = "T4240 QDS", + .probe = t4240_qds_probe, + .setup_arch = corenet_ds_setup_arch, + .init_IRQ = corenet_ds_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif +/* coreint doesn't play nice with lazy EE, use legacy mpic for now */ +#ifdef CONFIG_PPC64 + .get_irq = mpic_get_irq, +#else + .get_irq = mpic_get_coreint_irq, +#endif + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +#ifdef CONFIG_PPC64 + .power_save = book3e_idle, +#else + .power_save = e500_idle, +#endif +}; + +machine_arch_initcall(t4240_qds, corenet_ds_publish_devices); + +#ifdef CONFIG_SWIOTLB +machine_arch_initcall(t4240_qds, swiotlb_setup_bus_notifier); +#endif diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 7a6279e38213..1afd1e4a2dd2 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -37,7 +37,6 @@ config GEF_PPC9A bool "GE PPC9A" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -47,7 +46,6 @@ config GEF_SBC310 bool "GE SBC310" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -57,7 +55,6 @@ config GEF_SBC610 bool "GE SBC610" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA select HAS_RAPIDIO diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 1fb0b3cddeb3..8dec3c0911ad 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -114,7 +114,6 @@ config 8xx_COPYBACK config 8xx_GPIO bool "GPIO API Support" - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Saying Y here will cause the ports on an MPC8xx processor to be used diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 52de8bccfb30..b62aab3e22ec 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" @@ -129,7 +128,7 @@ config PPC_RTAS_DAEMON config RTAS_PROC bool "Proc interface to RTAS" - depends on PPC_RTAS + depends on PPC_RTAS && PROC_FS default y config RTAS_FLASH @@ -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 @@ -303,7 +302,6 @@ config QUICC_ENGINE config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here if you're going to use hardware that connects to the @@ -316,7 +314,6 @@ config CPM2 select PPC_LIB_RHEAP select PPC_PCI_CHOICE select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help The CPM2 (Communications Processor Module) is a coprocessor on embedded CPUs made by Freescale. Selecting this option means that @@ -344,7 +341,6 @@ config FSL_ULI1575 config CPM bool - select PPC_CLOCK config OF_RTC bool @@ -355,7 +351,6 @@ config OF_RTC config SIMPLE_GPIO bool "Support for simple, memory-mapped GPIO controllers" depends on PPC - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here to support simple, memory-mapped GPIO controllers. @@ -366,7 +361,6 @@ config SIMPLE_GPIO config MCU_MPC8349EMITX bool "MPC8349E-mITX MCU driver" depends on I2C=y && PPC_83xx - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here to enable soft power-off functionality on the Freescale diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index cea2f09c4241..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 @@ -232,7 +230,7 @@ config PHYS_64BIT config ALTIVEC bool "AltiVec Support" - depends on 6xx || POWER4 + depends on 6xx || POWER4 || (PPC_E500MC && PPC64) ---help--- This option enables kernel support for the Altivec extensions to the PowerPC processor. The kernel currently supports saving and restoring diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 53aaefeb3386..9978f594cac0 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -113,34 +113,10 @@ config CBE_THERM default m depends on CBE_RAS && SPU_BASE -config CBE_CPUFREQ - tristate "CBE frequency scaling" - depends on CBE_RAS && CPU_FREQ - default m - help - This adds the cpufreq driver for Cell BE processors. - For details, take a look at <file:Documentation/cpu-freq/>. - If you don't have such processor, say N - -config CBE_CPUFREQ_PMI_ENABLE - bool "CBE frequency scaling using PMI interface" - depends on CBE_CPUFREQ - default n - help - Select this, if you want to use the PMI interface - to switch frequencies. Using PMI, the - processor will not only be able to run at lower speed, - but also at lower core voltage. - -config CBE_CPUFREQ_PMI - tristate - depends on CBE_CPUFREQ_PMI_ENABLE - default CBE_CPUFREQ - config PPC_PMI tristate default y - depends on CBE_CPUFREQ_PMI || PPC_IBM_CELL_POWERBUTTON + depends on CPU_FREQ_CBE_PMI || PPC_IBM_CELL_POWERBUTTON help PMI (Platform Management Interrupt) is a way to communicate with the BMC (Baseboard Management Controller). diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index a4a89350bcfc..fe053e7c73ee 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -5,9 +5,6 @@ obj-$(CONFIG_PPC_CELL_NATIVE) += iommu.o setup.o spider-pic.o \ obj-$(CONFIG_CBE_RAS) += ras.o obj-$(CONFIG_CBE_THERM) += cbe_thermal.o -obj-$(CONFIG_CBE_CPUFREQ_PMI) += cbe_cpufreq_pmi.o -obj-$(CONFIG_CBE_CPUFREQ) += cbe-cpufreq.o -cbe-cpufreq-y += cbe_cpufreq_pervasive.o cbe_cpufreq.o obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR) += cpufreq_spudemand.o obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON) += cbe_powerbutton.o diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c index 0f6f83988b3d..246e1d8b3af3 100644 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ b/arch/powerpc/platforms/cell/beat_htab.c @@ -90,7 +90,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group) static long beat_lpar_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; u64 hpte_v, hpte_r, slot; @@ -103,9 +103,9 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group, "rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, va, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) | + hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; if (!(vflags & HPTE_V_BOLTED)) DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); @@ -191,7 +191,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot, u64 dummy0, dummy1; unsigned long want_v; - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); DBG_LOW(" update: " "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", @@ -228,7 +228,7 @@ static long beat_lpar_hpte_find(unsigned long vpn, int psize) unsigned long want_v, hpte_v; hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M); - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); for (j = 0; j < 2; j++) { slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; @@ -283,7 +283,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n", slot, va, psize, local); - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); raw_spin_lock_irqsave(&beat_htab_lock, flags); dummy1 = beat_lpar_hpte_getword0(slot); @@ -314,7 +314,7 @@ void __init hpte_init_beat(void) static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; u64 hpte_v, hpte_r, slot; @@ -327,9 +327,9 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, "rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, vpn, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) | + hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; if (!(vflags & HPTE_V_BOLTED)) DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); @@ -372,8 +372,8 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot, unsigned long want_v; unsigned long pss; - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc; + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); + pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; DBG_LOW(" update: " "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", @@ -402,8 +402,8 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn, DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n", slot, vpn, psize, local); - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc; + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); + pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss); diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c deleted file mode 100644 index d4c39e32f147..000000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq.c +++ /dev/null @@ -1,209 +0,0 @@ -/* - * cpufreq driver for the cell processor - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/cpufreq.h> -#include <linux/module.h> -#include <linux/of_platform.h> - -#include <asm/machdep.h> -#include <asm/prom.h> -#include <asm/cell-regs.h> -#include "cbe_cpufreq.h" - -static DEFINE_MUTEX(cbe_switch_mutex); - - -/* the CBE supports an 8 step frequency scaling */ -static struct cpufreq_frequency_table cbe_freqs[] = { - {1, 0}, - {2, 0}, - {3, 0}, - {4, 0}, - {5, 0}, - {6, 0}, - {8, 0}, - {10, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -/* - * hardware specific functions - */ - -static int set_pmode(unsigned int cpu, unsigned int slow_mode) -{ - int rc; - - if (cbe_cpufreq_has_pmi) - rc = cbe_cpufreq_set_pmode_pmi(cpu, slow_mode); - else - rc = cbe_cpufreq_set_pmode(cpu, slow_mode); - - pr_debug("register contains slow mode %d\n", cbe_cpufreq_get_pmode(cpu)); - - return rc; -} - -/* - * cpufreq functions - */ - -static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - const u32 *max_freqp; - u32 max_freq; - int i, cur_pmode; - struct device_node *cpu; - - cpu = of_get_cpu_node(policy->cpu, NULL); - - if (!cpu) - return -ENODEV; - - pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - /* - * Let's check we can actually get to the CELL regs - */ - if (!cbe_get_cpu_pmd_regs(policy->cpu) || - !cbe_get_cpu_mic_tm_regs(policy->cpu)) { - pr_info("invalid CBE regs pointers for cpufreq\n"); - return -EINVAL; - } - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - - of_node_put(cpu); - - if (!max_freqp) - return -EINVAL; - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - - pr_debug("max clock-frequency is at %u kHz\n", max_freq); - pr_debug("initializing frequency table\n"); - - /* initialize frequency table */ - for (i=0; cbe_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) { - cbe_freqs[i].frequency = max_freq / cbe_freqs[i].index; - pr_debug("%d: %d\n", i, cbe_freqs[i].frequency); - } - - /* if DEBUG is enabled set_pmode() measures the latency - * of a transition */ - policy->cpuinfo.transition_latency = 25000; - - cur_pmode = cbe_cpufreq_get_pmode(policy->cpu); - pr_debug("current pmode is at %d\n",cur_pmode); - - policy->cur = cbe_freqs[cur_pmode].frequency; - -#ifdef CONFIG_SMP - cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); -#endif - - cpufreq_frequency_table_get_attr(cbe_freqs, policy->cpu); - - /* this ensures that policy->cpuinfo_min - * and policy->cpuinfo_max are set correctly */ - return cpufreq_frequency_table_cpuinfo(policy, cbe_freqs); -} - -static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy) -{ - cpufreq_frequency_table_put_attr(policy->cpu); - return 0; -} - -static int cbe_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, cbe_freqs); -} - -static int cbe_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - int rc; - struct cpufreq_freqs freqs; - unsigned int cbe_pmode_new; - - cpufreq_frequency_table_target(policy, - cbe_freqs, - target_freq, - relation, - &cbe_pmode_new); - - freqs.old = policy->cur; - freqs.new = cbe_freqs[cbe_pmode_new].frequency; - freqs.cpu = policy->cpu; - - mutex_lock(&cbe_switch_mutex); - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - - pr_debug("setting frequency for cpu %d to %d kHz, " \ - "1/%d of max frequency\n", - policy->cpu, - cbe_freqs[cbe_pmode_new].frequency, - cbe_freqs[cbe_pmode_new].index); - - rc = set_pmode(policy->cpu, cbe_pmode_new); - - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - mutex_unlock(&cbe_switch_mutex); - - return rc; -} - -static struct cpufreq_driver cbe_cpufreq_driver = { - .verify = cbe_cpufreq_verify, - .target = cbe_cpufreq_target, - .init = cbe_cpufreq_cpu_init, - .exit = cbe_cpufreq_cpu_exit, - .name = "cbe-cpufreq", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, -}; - -/* - * module init and destoy - */ - -static int __init cbe_cpufreq_init(void) -{ - if (!machine_is(cell)) - return -ENODEV; - - return cpufreq_register_driver(&cbe_cpufreq_driver); -} - -static void __exit cbe_cpufreq_exit(void) -{ - cpufreq_unregister_driver(&cbe_cpufreq_driver); -} - -module_init(cbe_cpufreq_init); -module_exit(cbe_cpufreq_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>"); diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.h b/arch/powerpc/platforms/cell/cbe_cpufreq.h deleted file mode 100644 index c1d86bfa92ff..000000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * cbe_cpufreq.h - * - * This file contains the definitions used by the cbe_cpufreq driver. - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - */ - -#include <linux/cpufreq.h> -#include <linux/types.h> - -int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode); -int cbe_cpufreq_get_pmode(int cpu); - -int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode); - -#if defined(CONFIG_CBE_CPUFREQ_PMI) || defined(CONFIG_CBE_CPUFREQ_PMI_MODULE) -extern bool cbe_cpufreq_has_pmi; -#else -#define cbe_cpufreq_has_pmi (0) -#endif diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c deleted file mode 100644 index 20472e487b6f..000000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * pervasive backend for the cbe_cpufreq driver - * - * This driver makes use of the pervasive unit to - * engage the desired frequency. - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/io.h> -#include <linux/kernel.h> -#include <linux/time.h> -#include <asm/machdep.h> -#include <asm/hw_irq.h> -#include <asm/cell-regs.h> - -#include "cbe_cpufreq.h" - -/* to write to MIC register */ -static u64 MIC_Slow_Fast_Timer_table[] = { - [0 ... 7] = 0x007fc00000000000ull, -}; - -/* more values for the MIC */ -static u64 MIC_Slow_Next_Timer_table[] = { - 0x0000240000000000ull, - 0x0000268000000000ull, - 0x000029C000000000ull, - 0x00002D0000000000ull, - 0x0000300000000000ull, - 0x0000334000000000ull, - 0x000039C000000000ull, - 0x00003FC000000000ull, -}; - - -int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode) -{ - struct cbe_pmd_regs __iomem *pmd_regs; - struct cbe_mic_tm_regs __iomem *mic_tm_regs; - unsigned long flags; - u64 value; -#ifdef DEBUG - long time; -#endif - - local_irq_save(flags); - - mic_tm_regs = cbe_get_cpu_mic_tm_regs(cpu); - pmd_regs = cbe_get_cpu_pmd_regs(cpu); - -#ifdef DEBUG - time = jiffies; -#endif - - out_be64(&mic_tm_regs->slow_fast_timer_0, MIC_Slow_Fast_Timer_table[pmode]); - out_be64(&mic_tm_regs->slow_fast_timer_1, MIC_Slow_Fast_Timer_table[pmode]); - - out_be64(&mic_tm_regs->slow_next_timer_0, MIC_Slow_Next_Timer_table[pmode]); - out_be64(&mic_tm_regs->slow_next_timer_1, MIC_Slow_Next_Timer_table[pmode]); - - value = in_be64(&pmd_regs->pmcr); - /* set bits to zero */ - value &= 0xFFFFFFFFFFFFFFF8ull; - /* set bits to next pmode */ - value |= pmode; - - out_be64(&pmd_regs->pmcr, value); - -#ifdef DEBUG - /* wait until new pmode appears in status register */ - value = in_be64(&pmd_regs->pmsr) & 0x07; - while (value != pmode) { - cpu_relax(); - value = in_be64(&pmd_regs->pmsr) & 0x07; - } - - time = jiffies - time; - time = jiffies_to_msecs(time); - pr_debug("had to wait %lu ms for a transition using " \ - "pervasive unit\n", time); -#endif - local_irq_restore(flags); - - return 0; -} - - -int cbe_cpufreq_get_pmode(int cpu) -{ - int ret; - struct cbe_pmd_regs __iomem *pmd_regs; - - pmd_regs = cbe_get_cpu_pmd_regs(cpu); - ret = in_be64(&pmd_regs->pmsr) & 0x07; - - return ret; -} - diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c deleted file mode 100644 index 60a07a4f9326..000000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c +++ /dev/null @@ -1,156 +0,0 @@ -/* - * pmi backend for the cbe_cpufreq driver - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/timer.h> -#include <linux/module.h> -#include <linux/of_platform.h> - -#include <asm/processor.h> -#include <asm/prom.h> -#include <asm/pmi.h> -#include <asm/cell-regs.h> - -#ifdef DEBUG -#include <asm/time.h> -#endif - -#include "cbe_cpufreq.h" - -static u8 pmi_slow_mode_limit[MAX_CBE]; - -bool cbe_cpufreq_has_pmi = false; -EXPORT_SYMBOL_GPL(cbe_cpufreq_has_pmi); - -/* - * hardware specific functions - */ - -int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode) -{ - int ret; - pmi_message_t pmi_msg; -#ifdef DEBUG - long time; -#endif - pmi_msg.type = PMI_TYPE_FREQ_CHANGE; - pmi_msg.data1 = cbe_cpu_to_node(cpu); - pmi_msg.data2 = pmode; - -#ifdef DEBUG - time = jiffies; -#endif - pmi_send_message(pmi_msg); - -#ifdef DEBUG - time = jiffies - time; - time = jiffies_to_msecs(time); - pr_debug("had to wait %lu ms for a transition using " \ - "PMI\n", time); -#endif - ret = pmi_msg.data2; - pr_debug("PMI returned slow mode %d\n", ret); - - return ret; -} -EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi); - - -static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg) -{ - u8 node, slow_mode; - - BUG_ON(pmi_msg.type != PMI_TYPE_FREQ_CHANGE); - - node = pmi_msg.data1; - slow_mode = pmi_msg.data2; - - pmi_slow_mode_limit[node] = slow_mode; - - pr_debug("cbe_handle_pmi: node: %d max_freq: %d\n", node, slow_mode); -} - -static int pmi_notifier(struct notifier_block *nb, - unsigned long event, void *data) -{ - struct cpufreq_policy *policy = data; - struct cpufreq_frequency_table *cbe_freqs; - u8 node; - - /* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE - * and CPUFREQ_NOTIFY policy events?) - */ - if (event == CPUFREQ_START) - return 0; - - cbe_freqs = cpufreq_frequency_get_table(policy->cpu); - node = cbe_cpu_to_node(policy->cpu); - - pr_debug("got notified, event=%lu, node=%u\n", event, node); - - if (pmi_slow_mode_limit[node] != 0) { - pr_debug("limiting node %d to slow mode %d\n", - node, pmi_slow_mode_limit[node]); - - cpufreq_verify_within_limits(policy, 0, - - cbe_freqs[pmi_slow_mode_limit[node]].frequency); - } - - return 0; -} - -static struct notifier_block pmi_notifier_block = { - .notifier_call = pmi_notifier, -}; - -static struct pmi_handler cbe_pmi_handler = { - .type = PMI_TYPE_FREQ_CHANGE, - .handle_pmi_message = cbe_cpufreq_handle_pmi, -}; - - - -static int __init cbe_cpufreq_pmi_init(void) -{ - cbe_cpufreq_has_pmi = pmi_register_handler(&cbe_pmi_handler) == 0; - - if (!cbe_cpufreq_has_pmi) - return -ENODEV; - - cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER); - - return 0; -} - -static void __exit cbe_cpufreq_pmi_exit(void) -{ - cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER); - pmi_unregister_handler(&cbe_pmi_handler); -} - -module_init(cbe_cpufreq_pmi_init); -module_exit(cbe_cpufreq_pmi_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>"); diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index e56bb651da1a..946306b1bb4e 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -550,7 +550,7 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) */ iommu = cell_iommu_for_node(dev_to_node(dev)); if (iommu == NULL || list_empty(&iommu->windows)) { - printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n", + dev_err(dev, "iommu: missing iommu for %s (node %d)\n", of_node_full_name(dev->of_node), dev_to_node(dev)); return NULL; } 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/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 8b1213993b10..f85db3a69b4a 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -715,7 +715,7 @@ static ssize_t spu_stat_show(struct device *dev, spu->stats.libassist); } -static DEVICE_ATTR(stat, 0644, spu_stat_show, NULL); +static DEVICE_ATTR(stat, 0444, spu_stat_show, NULL); #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 68c57d38745a..90986923a53a 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -149,7 +149,6 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ return spufs_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ - .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = spufs_attr_release, \ .read = spufs_attr_read, \ @@ -352,7 +351,7 @@ 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 */ @@ -2591,7 +2590,6 @@ static unsigned int spufs_switch_log_poll(struct file *file, poll_table *wait) } static const struct file_operations spufs_switch_log_fops = { - .owner = THIS_MODULE, .open = spufs_switch_log_open, .read = spufs_switch_log_read, .poll = spufs_switch_log_poll, diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 3f3bb4cdbbec..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(); diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c index 039fc8e82199..2b4dc6abde6c 100644 --- a/arch/powerpc/platforms/chrp/pegasos_eth.c +++ b/arch/powerpc/platforms/chrp/pegasos_eth.c @@ -47,6 +47,25 @@ static struct platform_device mv643xx_eth_shared_device = { .resource = mv643xx_eth_shared_resources, }; +/* + * The orion mdio driver only covers shared + 0x4 up to shared + 0x84 - 1 + */ +static struct resource mv643xx_eth_mvmdio_resources[] = { + [0] = { + .name = "ethernet mdio base", + .start = 0xf1000000 + MV643XX_ETH_SHARED_REGS + 0x4, + .end = 0xf1000000 + MV643XX_ETH_SHARED_REGS + 0x83, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device mv643xx_eth_mvmdio_device = { + .name = "orion-mdio", + .id = -1, + .num_resources = ARRAY_SIZE(mv643xx_eth_mvmdio_resources), + .resource = mv643xx_eth_shared_resources, +}; + static struct resource mv643xx_eth_port1_resources[] = { [0] = { .name = "eth port1 irq", @@ -82,6 +101,7 @@ static struct platform_device eth_port1_device = { static struct platform_device *mv643xx_eth_pd_devs[] __initdata = { &mv643xx_eth_shared_device, + &mv643xx_eth_mvmdio_device, ð_port1_device, }; diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 5a8f50a9afa7..302ba43d73a1 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -9,7 +9,6 @@ config LINKSTATION select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 select DEFAULT_UIMAGE - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select LINKSTATION if configuring for one of PPC- (MPC8241) @@ -24,7 +23,6 @@ config STORCENTER select MPIC select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select STORCENTER if configuring for the iomega StorCenter @@ -84,9 +82,6 @@ config MV64X60 select PPC_INDIRECT_PCI select CHECK_CACHE_COHERENCY -config MPC10X_OPENPIC - bool - config GAMECUBE_COMMON bool diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index b30a6a3b5bd2..b290b63661f1 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -81,17 +81,6 @@ #define MPC10X_MAPB_PCI_MEM_OFFSET (MPC10X_MAPB_ISA_MEM_BASE - \ MPC10X_MAPB_PCI_MEM_START) -/* Set hose members to values appropriate for the mem map used */ -#define MPC10X_SETUP_HOSE(hose, map) { \ - (hose)->pci_mem_offset = MPC10X_MAP##map##_PCI_MEM_OFFSET; \ - (hose)->io_space.start = MPC10X_MAP##map##_PCI_IO_START; \ - (hose)->io_space.end = MPC10X_MAP##map##_PCI_IO_END; \ - (hose)->mem_space.start = MPC10X_MAP##map##_PCI_MEM_START; \ - (hose)->mem_space.end = MPC10X_MAP##map##_PCI_MEM_END; \ - (hose)->io_base_virt = (void *)MPC10X_MAP##map##_ISA_IO_BASE; \ -} - - /* Miscellaneous Configuration register offsets */ #define MPC10X_CFG_PIR_REG 0x09 #define MPC10X_CFG_PIR_HOST_BRIDGE 0x00 diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c index 890f30e70f98..be1e7958909e 100644 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ b/arch/powerpc/platforms/pasemi/cpufreq.c @@ -273,10 +273,9 @@ static int pas_cpufreq_target(struct cpufreq_policy *policy, freqs.old = policy->cur; freqs.new = pas_freqs[pas_astate_new].frequency; - freqs.cpu = policy->cpu; mutex_lock(&pas_switch_mutex); - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n", policy->cpu, @@ -288,7 +287,7 @@ static int pas_cpufreq_target(struct cpufreq_policy *policy, for_each_online_cpu(i) set_astate(i, pas_astate_new); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); mutex_unlock(&pas_switch_mutex); ppc_proc_freq = freqs.new * 1000ul; diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c index 311b804353b1..3104fad82480 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_32.c +++ b/arch/powerpc/platforms/powermac/cpufreq_32.c @@ -335,7 +335,8 @@ static int pmu_set_cpu_speed(int low_speed) return 0; } -static int do_set_cpu_speed(int speed_mode, int notify) +static int do_set_cpu_speed(struct cpufreq_policy *policy, int speed_mode, + int notify) { struct cpufreq_freqs freqs; unsigned long l3cr; @@ -343,13 +344,12 @@ static int do_set_cpu_speed(int speed_mode, int notify) freqs.old = cur_freq; freqs.new = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; - freqs.cpu = smp_processor_id(); if (freqs.old == freqs.new) return 0; if (notify) - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); if (speed_mode == CPUFREQ_LOW && cpu_has_feature(CPU_FTR_L3CR)) { l3cr = _get_L3CR(); @@ -366,7 +366,7 @@ static int do_set_cpu_speed(int speed_mode, int notify) _set_L3CR(prev_l3cr); } if (notify) - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); cur_freq = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; return 0; @@ -393,7 +393,7 @@ static int pmac_cpufreq_target( struct cpufreq_policy *policy, target_freq, relation, &newstate)) return -EINVAL; - rc = do_set_cpu_speed(newstate, 1); + rc = do_set_cpu_speed(policy, newstate, 1); ppc_proc_freq = cur_freq * 1000ul; return rc; @@ -442,7 +442,7 @@ static int pmac_cpufreq_suspend(struct cpufreq_policy *policy) no_schedule = 1; sleep_freq = cur_freq; if (cur_freq == low_freq && !is_pmu_based) - do_set_cpu_speed(CPUFREQ_HIGH, 0); + do_set_cpu_speed(policy, CPUFREQ_HIGH, 0); return 0; } @@ -458,7 +458,7 @@ static int pmac_cpufreq_resume(struct cpufreq_policy *policy) * is that we force a switch to whatever it was, which is * probably high speed due to our suspend() routine */ - do_set_cpu_speed(sleep_freq == low_freq ? + do_set_cpu_speed(policy, sleep_freq == low_freq ? CPUFREQ_LOW : CPUFREQ_HIGH, 0); ppc_proc_freq = cur_freq * 1000ul; diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c index 9650c6029c82..7ba423431cfe 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ b/arch/powerpc/platforms/powermac/cpufreq_64.c @@ -339,11 +339,10 @@ static int g5_cpufreq_target(struct cpufreq_policy *policy, freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency; freqs.new = g5_cpu_freqs[newstate].frequency; - freqs.cpu = 0; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); rc = g5_switch_freq(newstate); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); mutex_unlock(&g5_switch_mutex); diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 2b8af75abc23..cf7009b8c7b6 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -824,6 +824,7 @@ static void __init parse_region_decode(struct pci_controller *hose, hose->mem_resources[cur].name = hose->dn->full_name; hose->mem_resources[cur].start = base; hose->mem_resources[cur].end = end; + hose->mem_offset[cur] = 0; DBG(" %d: 0x%08lx-0x%08lx\n", cur, base, end); } else { DBG(" : -0x%08lx\n", end); @@ -866,7 +867,6 @@ static void __init setup_u3_ht(struct pci_controller* hose) hose->io_resource.start = 0; hose->io_resource.end = 0x003fffff; hose->io_resource.flags = IORESOURCE_IO; - hose->pci_mem_offset = 0; hose->first_busno = 0; hose->last_busno = 0xef; diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 74fea5c21839..c24684c818ab 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -6,6 +6,12 @@ config PPC_POWERNV select PPC_ICP_NATIVE select PPC_P7_NAP select PPC_PCI_CHOICE if EMBEDDED + select EPAPR_BOOT + default y + +config POWERNV_MSI + bool "Support PCI MSI on PowerNV platform" + depends on PCI_MSI default y config PPC_POWERNV_RTAS 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/opal.c b/arch/powerpc/platforms/powernv/opal.c index aaa0dba49471..628c564ceadb 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/interrupt.h> +#include <linux/slab.h> #include <asm/opal.h> #include <asm/firmware.h> @@ -28,13 +29,14 @@ struct opal { static struct device_node *opal_node; static DEFINE_SPINLOCK(opal_write_lock); extern u64 opal_mc_secondary_handler[]; +static unsigned int *opal_irqs; +static unsigned int opal_irq_count; int __init early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data) { const void *basep, *entryp; unsigned long basesz, entrysz; - u64 glue; if (depth != 1 || strcmp(uname, "ibm,opal") != 0) return 0; @@ -54,13 +56,27 @@ int __init early_init_dt_scan_opal(unsigned long node, opal.entry, entryp, entrysz); powerpc_firmware_features |= FW_FEATURE_OPAL; - if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { + if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { + powerpc_firmware_features |= FW_FEATURE_OPALv2; + powerpc_firmware_features |= FW_FEATURE_OPALv3; + printk("OPAL V3 detected !\n"); + } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { powerpc_firmware_features |= FW_FEATURE_OPALv2; printk("OPAL V2 detected !\n"); } else { printk("OPAL V1 detected !\n"); } + return 1; +} + +static int __init opal_register_exception_handlers(void) +{ + u64 glue; + + if (!(powerpc_firmware_features & FW_FEATURE_OPAL)) + return -ENODEV; + /* Hookup some exception handlers. We use the fwnmi area at 0x7000 * to provide the glue space to OPAL */ @@ -74,9 +90,11 @@ int __init early_init_dt_scan_opal(unsigned long node, glue += 128; opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); - return 1; + return 0; } +early_initcall(opal_register_exception_handlers); + int opal_get_chars(uint32_t vtermno, char *buf, int count) { s64 len, rc; @@ -133,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { len = total_len; rc = opal_console_write(vtermno, &len, data); + + /* Closed or other error drop */ + if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && + rc != OPAL_BUSY_EVENT) { + written = total_len; + break; + } if (rc == OPAL_SUCCESS) { total_len -= len; data += len; @@ -305,6 +330,8 @@ static int __init opal_init(void) irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); pr_debug("opal: Found %d interrupts reserved for OPAL\n", irqs ? (irqlen / 4) : 0); + opal_irq_count = irqlen / 4; + opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL); for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) { unsigned int hwirq = be32_to_cpup(irqs); unsigned int irq = irq_create_mapping(NULL, hwirq); @@ -316,7 +343,19 @@ static int __init opal_init(void) if (rc) pr_warning("opal: Error %d requesting irq %d" " (0x%x)\n", rc, irq, hwirq); + opal_irqs[i] = irq; } return 0; } subsys_initcall(opal_init); + +void opal_shutdown(void) +{ + unsigned int i; + + for (i = 0; i < opal_irq_count; i++) { + if (opal_irqs[i]) + free_irq(opal_irqs[i], 0); + opal_irqs[i] = 0; + } +} diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 8e90e8906df3..9c9d15e4cdf2 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" @@ -66,16 +68,6 @@ define_pe_printk_level(pe_err, KERN_ERR); define_pe_printk_level(pe_warn, KERN_WARNING); define_pe_printk_level(pe_info, KERN_INFO); -static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev) -{ - struct device_node *np; - - np = pci_device_to_OF_node(dev); - if (!np) - return NULL; - return PCI_DN(np); -} - static int pnv_ioda_alloc_pe(struct pnv_phb *phb) { unsigned long pe; @@ -87,6 +79,7 @@ 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; } @@ -107,7 +100,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (!pdn) return NULL; @@ -170,7 +163,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) /* Add to all parents PELT-V */ while (parent) { - struct pci_dn *pdn = pnv_ioda_get_pdn(parent); + struct pci_dn *pdn = pci_get_pdn(parent); if (pdn && pdn->pe_number != IODA_INVALID_PE) { rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); @@ -249,7 +242,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); struct pnv_ioda_pe *pe; int pe_num; @@ -320,7 +313,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (pdn == NULL) { pr_warn("%s: No device node associated with device !\n", @@ -431,22 +424,102 @@ 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 = pci_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 +591,11 @@ 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 +605,76 @@ 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 +717,50 @@ 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 pci_dn *pdn = pci_get_pdn(dev); + struct irq_data *idata; + struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; uint64_t addr64; uint32_t addr32, data; @@ -606,6 +774,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, if (pe->mve_number < 0) return -ENXIO; + /* Force 32-bit MSI on some broken devices */ + if (pdn && pdn->force_32bit_msi) + is_64 = 0; + /* Assign XIVE to PE */ rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num); if (rc) { @@ -637,6 +809,23 @@ 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 +836,7 @@ 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 +847,17 @@ 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) { } @@ -722,11 +910,14 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, index++; } } else if (res->flags & IORESOURCE_MEM) { + /* WARNING: Assumes M32 is mem region 0 in PHB. We need to + * harden that algorithm when we start supporting M64 + */ region.start = res->start - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; region.end = res->end - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; index = region.start / phb->ioda.m32_segsize; @@ -839,7 +1030,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) if (!phb->initialized) return 0; - pdn = pnv_ioda_get_pdn(dev); + pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) return -EINVAL; @@ -852,18 +1043,25 @@ 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) +static void pnv_pci_ioda_shutdown(struct pnv_phb *phb) +{ + opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET, + OPAL_ASSERT_RESET); +} + +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) { @@ -890,47 +1088,46 @@ 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,power8-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; - phb->ioda.m32_pci_base = hose->mem_resources[0].start - - hose->pci_mem_offset; + phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0]; phb->ioda.io_size = hose->pci_io_size; 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 +1157,7 @@ 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 +1171,6 @@ 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 */ @@ -992,6 +1179,9 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + /* Setup shutdown function for kexec */ + phb->shutdown = pnv_pci_ioda_shutdown; + /* Setup MSI support */ pnv_pci_init_ioda_msis(phb); @@ -1011,7 +1201,18 @@ 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 +1235,6 @@ 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..277343cc6a3d 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> @@ -46,44 +47,12 @@ 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; + struct pci_dn *pdn = pci_get_pdn(pdev); - 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; + if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + return -ENODEV; - 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 +61,8 @@ 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 +74,25 @@ 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 +114,8 @@ 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 +333,6 @@ 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 +357,7 @@ 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; } @@ -443,7 +372,7 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) *(tcep++) = 0; if (tbl->it_type & TCE_PCI_SWINV_FREE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); } static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) @@ -525,7 +454,19 @@ 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 */ +void pnv_pci_shutdown(void) +{ + struct pci_controller *hose; + + list_for_each_entry(hose, &hose_list, list_node) { + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->shutdown) + phb->shutdown(phb); + } +} + +/* 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 +532,10 @@ 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..25d76c4df50b 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 @@ -73,18 +76,17 @@ 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); + void (*shutdown)(struct pnv_phb *phb); union { struct { @@ -109,6 +111,10 @@ 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 +156,8 @@ 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/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 8a9df7f9667e..a1c6f83fc391 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { } #ifdef CONFIG_PCI extern void pnv_pci_init(void); +extern void pnv_pci_shutdown(void); #else static inline void pnv_pci_init(void) { } +static inline void pnv_pci_shutdown(void) { } #endif #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index db1ad1c8f68f..d4459bfc92f7 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv2)) + if (firmware_has_feature(FW_FEATURE_OPALv3)) + seq_printf(m, "firmware\t: OPAL v3\n"); + else if (firmware_has_feature(FW_FEATURE_OPALv2)) seq_printf(m, "firmware\t: OPAL v2\n"); else if (firmware_has_feature(FW_FEATURE_OPAL)) seq_printf(m, "firmware\t: OPAL v1\n"); @@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex) { } +static void pnv_shutdown(void) +{ + /* Let the PCI code clear up IODA tables */ + pnv_pci_shutdown(); + + /* And unregister all OPAL interrupts so they don't fire + * up while we kexec + */ + opal_shutdown(); +} + #ifdef CONFIG_KEXEC static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { @@ -187,6 +200,7 @@ define_machine(powernv) { .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, .progress = pnv_progress, + .machine_shutdown = pnv_shutdown, .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 0bdc735db16f..88c9459c3e07 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -71,16 +71,68 @@ int pnv_smp_kick_cpu(int nr) BUG_ON(nr < 0 || nr >= NR_CPUS); - /* On OPAL v2 the CPU are still spinning inside OPAL itself, - * get them back now + /* + * If we already started or OPALv2 is not supported, we just + * kick the CPU via the PACA */ - if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); - if (rc != OPAL_SUCCESS) - pr_warn("OPAL Error %ld starting CPU %d\n", + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + goto kick; + + /* + * At this point, the CPU can either be spinning on the way in + * from kexec or be inside OPAL waiting to be started for the + * first time. OPAL v3 allows us to query OPAL to know if it + * has the CPUs, so we do that + */ + if (firmware_has_feature(FW_FEATURE_OPALv3)) { + uint8_t status; + + rc = opal_query_cpu_status(pcpu, &status); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); + return -ENODEV; + } + + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; + + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", + nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", + rc, nr); + return -ENODEV; + } + } else { + /* + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen + */ + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; + } + } else { + /* + * On OPAL v2, we just kick it and hope for the best, + * we must not test the error from opal_start_cpu() or + * we would fail to get CPUs from kexec. + */ + opal_start_cpu(pcpu, start_here); } + kick: return smp_generic_kick_cpu(nr); } 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/htab.c b/arch/powerpc/platforms/ps3/htab.c index 6cc58201db8c..177a2f70700c 100644 --- a/arch/powerpc/platforms/ps3/htab.c +++ b/arch/powerpc/platforms/ps3/htab.c @@ -46,7 +46,7 @@ static DEFINE_SPINLOCK(ps3_htab_lock); static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { int result; u64 hpte_v, hpte_r; @@ -62,8 +62,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn, */ vflags &= ~HPTE_V_SECONDARY; - hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags; + hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags; spin_lock_irqsave(&ps3_htab_lock, flags); @@ -117,7 +117,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long flags; long ret; - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); spin_lock_irqsave(&ps3_htab_lock, flags); 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/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 9a0941bc4d31..4459eff7a75a 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -18,6 +18,9 @@ config PPC_PSERIES select PPC_PCI_CHOICE if EXPERT select ZLIB_DEFLATE select PPC_DOORBELL + select HAVE_CONTEXT_TRACKING + select HOTPLUG if SMP + select HOTPLUG_CPU if SMP default y config PPC_SPLPAR 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/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2372c609fa2b..9a432de363b8 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -72,6 +72,7 @@ unsigned long memory_block_size_bytes(void) return get_memblock_size(); } +#ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long start, start_pfn; @@ -153,6 +154,17 @@ static int pseries_remove_memory(struct device_node *np) ret = pseries_remove_memblock(base, lmb_size); return ret; } +#else +static inline int pseries_remove_memblock(unsigned long base, + unsigned int memblock_size) +{ + return -EOPNOTSUPP; +} +static inline int pseries_remove_memory(struct device_node *np) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ static int pseries_add_memory(struct device_node *np) { 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..6d62072a7d5a 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -109,7 +109,7 @@ void vpa_init(int cpu) static long pSeries_lpar_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; unsigned long flags; @@ -121,8 +121,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, vpn, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; if (!(vflags & HPTE_V_BOLTED)) pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); @@ -155,7 +155,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, */ if (unlikely(lpar_rc != H_SUCCESS)) { if (!(vflags & HPTE_V_BOLTED)) - pr_devel(" lpar err %lu\n", lpar_rc); + pr_devel(" lpar err %ld\n", lpar_rc); return -2; } if (!(vflags & HPTE_V_BOLTED)) @@ -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/msi.c b/arch/powerpc/platforms/pseries/msi.c index e5b084723131..6d2f0abce6fa 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -24,26 +24,7 @@ static int query_token, change_token; #define RTAS_RESET_FN 2 #define RTAS_CHANGE_MSI_FN 3 #define RTAS_CHANGE_MSIX_FN 4 - -static struct pci_dn *get_pdn(struct pci_dev *pdev) -{ - struct device_node *dn; - struct pci_dn *pdn; - - dn = pci_device_to_OF_node(pdev); - if (!dn) { - dev_dbg(&pdev->dev, "rtas_msi: No OF device node\n"); - return NULL; - } - - pdn = PCI_DN(dn); - if (!pdn) { - dev_dbg(&pdev->dev, "rtas_msi: No PCI DN\n"); - return NULL; - } - - return pdn; -} +#define RTAS_CHANGE_32MSI_FN 5 /* RTAS Helpers */ @@ -58,7 +39,8 @@ static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs) seq_num = 1; do { - if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN) + if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN || + func == RTAS_CHANGE_32MSI_FN) rc = rtas_call(change_token, 6, 4, rtas_ret, addr, BUID_HI(buid), BUID_LO(buid), func, num_irqs, seq_num); @@ -89,7 +71,7 @@ static void rtas_disable_msi(struct pci_dev *pdev) { struct pci_dn *pdn; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return; @@ -150,7 +132,7 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) struct pci_dn *pdn; const u32 *req_msi; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; @@ -392,6 +374,23 @@ static int check_msix_entries(struct pci_dev *pdev) return 0; } +static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev) +{ + u32 addr_hi, addr_lo; + + /* + * We should only get in here for IODA1 configs. This is based on the + * fact that we using RTAS for MSIs, we don't have the 32 bit MSI RTAS + * support, and we are in a PCIe Gen2 slot. + */ + dev_info(&pdev->dev, + "rtas_msi: No 32 bit MSI firmware support, forcing 32 bit MSI\n"); + pci_read_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, &addr_hi); + addr_lo = 0xffff0000 | ((addr_hi >> (48 - 32)) << 4); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, addr_lo); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0); +} + static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) { struct pci_dn *pdn; @@ -399,8 +398,9 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) struct msi_desc *entry; struct msi_msg msg; int nvec = nvec_in; + int use_32bit_msi_hack = 0; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; @@ -426,12 +426,31 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) */ again: if (type == PCI_CAP_ID_MSI) { - rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); + if (pdn->force_32bit_msi) { + rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec); + if (rc < 0) { + /* + * We only want to run the 32 bit MSI hack below if + * the max bus speed is Gen2 speed + */ + if (pdev->bus->max_bus_speed != PCIE_SPEED_5_0GT) + return rc; + + use_32bit_msi_hack = 1; + } + } else + rc = -1; + + if (rc < 0) + rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); if (rc < 0) { pr_debug("rtas_msi: trying the old firmware call.\n"); rc = rtas_change_msi(pdn, RTAS_CHANGE_FN, nvec); } + + if (use_32bit_msi_hack && rc > 0) + rtas_hack_32bit_msi_gen2(pdev); } else rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec); @@ -512,3 +531,4 @@ static int rtas_msi_init(void) return 0; } arch_initcall(rtas_msi_init); + diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 0b580f413a9a..5f93856cdf47 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -108,3 +108,56 @@ static void fixup_winbond_82c105(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_WINBOND, PCI_DEVICE_ID_WINBOND_82C105, fixup_winbond_82c105); + +int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) +{ + struct device_node *dn, *pdn; + struct pci_bus *bus; + const uint32_t *pcie_link_speed_stats; + + bus = bridge->bus; + + dn = pcibios_get_phb_of_node(bus); + if (!dn) + return 0; + + for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { + pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn, + "ibm,pcie-link-speed-stats", NULL); + if (pcie_link_speed_stats) + break; + } + + of_node_put(pdn); + + if (!pcie_link_speed_stats) { + pr_err("no ibm,pcie-link-speed-stats property\n"); + return 0; + } + + switch (pcie_link_speed_stats[0]) { + case 0x01: + bus->max_bus_speed = PCIE_SPEED_2_5GT; + break; + case 0x02: + bus->max_bus_speed = PCIE_SPEED_5_0GT; + break; + default: + bus->max_bus_speed = PCI_SPEED_UNKNOWN; + break; + } + + switch (pcie_link_speed_stats[1]) { + case 0x01: + bus->cur_bus_speed = PCIE_SPEED_2_5GT; + break; + case 0x02: + bus->cur_bus_speed = PCIE_SPEED_5_0GT; + break; + default: + bus->cur_bus_speed = PCI_SPEED_UNKNOWN; + break; + } + + return 0; +} 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/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index 4d806b419606..4644efa06941 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -23,8 +23,8 @@ #include "pseries.h" struct cpuidle_driver pseries_idle_driver = { - .name = "pseries_idle", - .owner = THIS_MODULE, + .name = "pseries_idle", + .owner = THIS_MODULE, }; #define MAX_IDLE_STATE_COUNT 2 @@ -33,10 +33,8 @@ static int max_idle_state = MAX_IDLE_STATE_COUNT - 1; static struct cpuidle_device __percpu *pseries_cpuidle_devices; static struct cpuidle_state *cpuidle_state_table; -static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before) +static inline void idle_loop_prolog(unsigned long *in_purr) { - - *kt_before = ktime_get(); *in_purr = mfspr(SPRN_PURR); /* * Indicate to the HV that we are idle. Now would be @@ -45,12 +43,10 @@ static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before) get_lppaca()->idle = 1; } -static inline s64 idle_loop_epilog(unsigned long in_purr, ktime_t kt_before) +static inline void idle_loop_epilog(unsigned long in_purr) { get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr; get_lppaca()->idle = 0; - - return ktime_to_us(ktime_sub(ktime_get(), kt_before)); } static int snooze_loop(struct cpuidle_device *dev, @@ -58,10 +54,9 @@ static int snooze_loop(struct cpuidle_device *dev, int index) { unsigned long in_purr; - ktime_t kt_before; int cpu = dev->cpu; - idle_loop_prolog(&in_purr, &kt_before); + idle_loop_prolog(&in_purr); local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); @@ -75,8 +70,8 @@ static int snooze_loop(struct cpuidle_device *dev, clear_thread_flag(TIF_POLLING_NRFLAG); smp_mb(); - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); + idle_loop_epilog(in_purr); + return index; } @@ -102,9 +97,8 @@ static int dedicated_cede_loop(struct cpuidle_device *dev, int index) { unsigned long in_purr; - ktime_t kt_before; - idle_loop_prolog(&in_purr, &kt_before); + idle_loop_prolog(&in_purr); get_lppaca()->donate_dedicated_cpu = 1; ppc64_runlatch_off(); @@ -112,8 +106,9 @@ static int dedicated_cede_loop(struct cpuidle_device *dev, check_and_cede_processor(); get_lppaca()->donate_dedicated_cpu = 0; - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); + + idle_loop_epilog(in_purr); + return index; } @@ -122,9 +117,8 @@ static int shared_cede_loop(struct cpuidle_device *dev, int index) { unsigned long in_purr; - ktime_t kt_before; - idle_loop_prolog(&in_purr, &kt_before); + idle_loop_prolog(&in_purr); /* * Yield the processor to the hypervisor. We return if @@ -135,8 +129,8 @@ static int shared_cede_loop(struct cpuidle_device *dev, */ check_and_cede_processor(); - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); + idle_loop_epilog(in_purr); + return index; } diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 9a3dda07566f..c2a3a258001c 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; @@ -60,4 +63,8 @@ extern int dlpar_detach_node(struct device_node *); /* Snooze Delay, pseries_idle */ DECLARE_PER_CPU(long, smt_snooze_delay); +/* PCI root bridge prepare function override for pseries */ +struct pci_host_bridge; +int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index d6491bd481d0..f93cdf55628c 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -452,7 +452,7 @@ static int proc_ppc64_create_ofdt(void) ent = proc_create("powerpc/ofdt", S_IWUSR, NULL, &ofdt_fops); if (ent) - ent->size = 0; + proc_set_size(ent, 0); return 0; } diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index 47f3cda2a68b..b502ab61aafa 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -41,13 +41,12 @@ static unsigned int ibm_scan_log_dump; /* RTAS token */ -static struct proc_dir_entry *proc_ppc64_scan_log_dump; /* The proc file */ +static unsigned int *scanlog_buffer; /* The data buffer */ static ssize_t scanlog_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct proc_dir_entry *dp = PDE(file_inode(file)); - unsigned int *data = (unsigned int *)dp->data; + unsigned int *data = scanlog_buffer; int status; unsigned long len, off; unsigned int wait_time; @@ -135,8 +134,7 @@ static ssize_t scanlog_write(struct file * file, const char __user * buf, static int scanlog_open(struct inode * inode, struct file * file) { - struct proc_dir_entry *dp = PDE(inode); - unsigned int *data = (unsigned int *)dp->data; + unsigned int *data = scanlog_buffer; if (data[0] != 0) { /* This imperfect test stops a second copy of the @@ -152,11 +150,9 @@ static int scanlog_open(struct inode * inode, struct file * file) static int scanlog_release(struct inode * inode, struct file * file) { - struct proc_dir_entry *dp = PDE(inode); - unsigned int *data = (unsigned int *)dp->data; + unsigned int *data = scanlog_buffer; data[0] = 0; - return 0; } @@ -172,7 +168,6 @@ const struct file_operations scanlog_fops = { static int __init scanlog_init(void) { struct proc_dir_entry *ent; - void *data; int err = -ENOMEM; ibm_scan_log_dump = rtas_token("ibm,scan-log-dump"); @@ -180,29 +175,24 @@ static int __init scanlog_init(void) return -ENODEV; /* Ideally we could allocate a buffer < 4G */ - data = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); - if (!data) + scanlog_buffer = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); + if (!scanlog_buffer) goto err; - ent = proc_create_data("powerpc/rtas/scan-log-dump", S_IRUSR, NULL, - &scanlog_fops, data); + ent = proc_create("powerpc/rtas/scan-log-dump", S_IRUSR, NULL, + &scanlog_fops); if (!ent) goto err; - - proc_ppc64_scan_log_dump = ent; - return 0; err: - kfree(data); + kfree(scanlog_buffer); return err; } static void __exit scanlog_cleanup(void) { - if (proc_ppc64_scan_log_dump) { - kfree(proc_ppc64_scan_log_dump->data); - remove_proc_entry("scan-log-dump", proc_ppc64_scan_log_dump->parent); - } + remove_proc_entry("powerpc/rtas/scan-log-dump", NULL); + kfree(scanlog_buffer); } module_init(scanlog_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8bcc9ca6682f..c11c8238797c 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -466,6 +466,8 @@ static void __init pSeries_setup_arch(void) else ppc_md.enable_pmcs = power4_enable_pmcs; + ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { long rc; if ((rc = pSeries_enable_reloc_on_exc()) != H_SUCCESS) { @@ -628,25 +630,39 @@ 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 +685,7 @@ 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/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 47226e04126d..5f997e79d570 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -16,6 +16,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/delay.h> #include <linux/suspend.h> #include <linux/stat.h> @@ -126,11 +127,15 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + stream_id = simple_strtoul(buf, NULL, 16); do { @@ -140,15 +145,32 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, + cpu_online_mask); + rc = rtas_online_cpus_mask(offline_mask); + if (rc) { + pr_err("%s: Could not bring present CPUs online.\n", + __func__); + goto out; + } + stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); + + /* Take down CPUs not online prior to suspend */ + if (!rtas_offline_cpus_mask(offline_mask)) + pr_warn("%s: Could not restore CPUs to offline " + "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; +out: + free_cpumask_var(offline_mask); return rc; } 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/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c index 97fe82ee8633..2d3b1dd9571d 100644 --- a/arch/powerpc/platforms/wsp/ics.c +++ b/arch/powerpc/platforms/wsp/ics.c @@ -361,7 +361,7 @@ static int wsp_chip_set_affinity(struct irq_data *d, xive = xive_set_server(xive, get_irq_server(ics, hw_irq)); wsp_ics_set_xive(ics, hw_irq, xive); - return 0; + return IRQ_SET_MASK_OK; } static struct irq_chip wsp_irq_chip = { diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c index 8e22f561d171..62cb527493e7 100644 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ b/arch/powerpc/platforms/wsp/wsp_pci.c @@ -502,7 +502,7 @@ static void __init wsp_pcie_configure_hw(struct pci_controller *hose) (~(hose->mem_resources[0].end - hose->mem_resources[0].start)) & 0x3ffffff0000ul); out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR, - (hose->mem_resources[0].start - hose->pci_mem_offset) | 1); + (hose->mem_resources[0].start - hose->mem_offset[0]) | 1); /* Clear all TVT entries * 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/Makefile b/arch/powerpc/sysdev/Makefile index b0a518e97599..99464a7bdb3b 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -64,6 +64,8 @@ endif obj-$(CONFIG_PPC_SCOM) += scom.o +obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS) += udbg_memcons.o + subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror obj-$(CONFIG_PPC_XICS) += xics/ diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index 6e0e1005227f..9cd0e60716fe 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -81,7 +81,7 @@ int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest, ev_int_set_config(src, config, prio, cpuid); spin_unlock_irqrestore(&ehv_pic_lock, flags); - return 0; + return IRQ_SET_MASK_OK; } static unsigned int ehv_pic_type_to_vecpri(unsigned int type) diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 178c99427b1c..ab02db3d02d8 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -333,6 +333,8 @@ static int fsl_of_msi_remove(struct platform_device *ofdev) return 0; } +static struct lock_class_key fsl_msi_irq_class; + static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, int offset, int irq_index) { @@ -351,7 +353,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, dev_err(&dev->dev, "No memory for MSI cascade data\n"); return -ENOMEM; } - + irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class); msi->msi_virqs[irq_index] = virt_msir; cascade_data->index = offset; cascade_data->msi_data = msi; diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 682084dba19b..028ac1f71b51 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -54,16 +54,63 @@ static void quirk_fsl_pcie_header(struct pci_dev *dev) return; } -static int __init fsl_pcie_check_link(struct pci_controller *hose) +static int fsl_indirect_read_config(struct pci_bus *, unsigned int, + int, int, u32 *); + +static int fsl_pcie_check_link(struct pci_controller *hose) { - u32 val; + u32 val = 0; + + if (hose->indirect_type & PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK) { + if (hose->ops->read == fsl_indirect_read_config) { + struct pci_bus bus; + bus.number = 0; + bus.sysdata = hose; + bus.ops = hose->ops; + indirect_read_config(&bus, 0, PCIE_LTSSM, 4, &val); + } else + early_read_config_dword(hose, 0, 0, PCIE_LTSSM, &val); + if (val < PCIE_LTSSM_L0) + return 1; + } else { + struct ccsr_pci __iomem *pci = hose->private_data; + /* for PCIe IP rev 3.0 or greater use CSR0 for link state */ + val = (in_be32(&pci->pex_csr0) & PEX_CSR0_LTSSM_MASK) + >> PEX_CSR0_LTSSM_SHIFT; + if (val != PEX_CSR0_LTSSM_L0) + return 1; + } - early_read_config_dword(hose, 0, 0, PCIE_LTSSM, &val); - if (val < PCIE_LTSSM_L0) - return 1; return 0; } +static int fsl_indirect_read_config(struct pci_bus *bus, unsigned int devfn, + int offset, int len, u32 *val) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + + if (fsl_pcie_check_link(hose)) + hose->indirect_type |= PPC_INDIRECT_TYPE_NO_PCIE_LINK; + else + hose->indirect_type &= ~PPC_INDIRECT_TYPE_NO_PCIE_LINK; + + return indirect_read_config(bus, devfn, offset, len, val); +} + +static struct pci_ops fsl_indirect_pci_ops = +{ + .read = fsl_indirect_read_config, + .write = indirect_write_config, +}; + +static void __init fsl_setup_indirect_pci(struct pci_controller* hose, + resource_size_t cfg_addr, + resource_size_t cfg_data, u32 flags) +{ + setup_indirect_pci(hose, cfg_addr, cfg_data, flags); + hose->ops = &fsl_indirect_pci_ops; +} + #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx) #define MAX_PHYS_ADDR_BITS 40 @@ -106,7 +153,7 @@ static int setup_one_atmu(struct ccsr_pci __iomem *pci, flags |= 0x10000000; /* enable relaxed ordering */ for (i = 0; size > 0; i++) { - unsigned int bits = min(__ilog2(size), + unsigned int bits = min(ilog2(size), __ffs(pci_addr | phys_addr)); if (index + i >= 5) @@ -126,13 +173,12 @@ static int setup_one_atmu(struct ccsr_pci __iomem *pci, } /* atmu setup for fsl pci/pcie controller */ -static void setup_pci_atmu(struct pci_controller *hose, - struct resource *rsrc) +static void setup_pci_atmu(struct pci_controller *hose) { - struct ccsr_pci __iomem *pci; + struct ccsr_pci __iomem *pci = hose->private_data; int i, j, n, mem_log, win_idx = 3, start_idx = 1, end_idx = 4; u64 mem, sz, paddr_hi = 0; - u64 paddr_lo = ULLONG_MAX; + u64 offset = 0, paddr_lo = ULLONG_MAX; u32 pcicsrbar = 0, pcicsrbar_sz; u32 piwar = PIWAR_EN | PIWAR_PF | PIWAR_TGI_LOCAL | PIWAR_READ_SNOOP | PIWAR_WRITE_SNOOP; @@ -140,15 +186,6 @@ static void setup_pci_atmu(struct pci_controller *hose, const u64 *reg; int len; - pr_debug("PCI memory map start 0x%016llx, size 0x%016llx\n", - (u64)rsrc->start, (u64)resource_size(rsrc)); - - pci = ioremap(rsrc->start, resource_size(rsrc)); - if (!pci) { - dev_err(hose->parent, "Unable to map ATMU registers\n"); - return; - } - if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { if (in_be32(&pci->block_rev1) >= PCIE_IP_REV_2_2) { win_idx = 2; @@ -171,8 +208,9 @@ static void setup_pci_atmu(struct pci_controller *hose, paddr_lo = min(paddr_lo, (u64)hose->mem_resources[i].start); paddr_hi = max(paddr_hi, (u64)hose->mem_resources[i].end); - n = setup_one_atmu(pci, j, &hose->mem_resources[i], - hose->pci_mem_offset); + /* We assume all memory resources have the same offset */ + offset = hose->mem_offset[i]; + n = setup_one_atmu(pci, j, &hose->mem_resources[i], offset); if (n < 0 || j >= 5) { pr_err("Ran out of outbound PCI ATMUs for resource %d!\n", i); @@ -196,23 +234,23 @@ static void setup_pci_atmu(struct pci_controller *hose, out_be32(&pci->pow[j].powbar, (hose->io_base_phys >> 12)); /* Enable, IO R/W */ out_be32(&pci->pow[j].powar, 0x80088000 - | (__ilog2(hose->io_resource.end + | (ilog2(hose->io_resource.end - hose->io_resource.start + 1) - 1)); } } /* convert to pci address space */ - paddr_hi -= hose->pci_mem_offset; - paddr_lo -= hose->pci_mem_offset; + paddr_hi -= offset; + paddr_lo -= offset; if (paddr_hi == paddr_lo) { pr_err("%s: No outbound window space\n", name); - goto out; + return; } if (paddr_lo == 0) { pr_err("%s: No space for inbound window\n", name); - goto out; + return; } /* setup PCSRBAR/PEXCSRBAR */ @@ -261,7 +299,7 @@ static void setup_pci_atmu(struct pci_controller *hose, } sz = min(mem, paddr_lo); - mem_log = __ilog2_u64(sz); + mem_log = ilog2(sz); /* PCIe can overmap inbound & outbound since RX & TX are separated */ if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { @@ -290,7 +328,7 @@ static void setup_pci_atmu(struct pci_controller *hose, * SWIOTLB and access the full range of memory */ if (sz != mem) { - mem_log = __ilog2_u64(mem); + mem_log = ilog2(mem); /* Size window up if we dont fit in exact power-of-2 */ if ((1ull << mem_log) != mem) @@ -327,7 +365,7 @@ static void setup_pci_atmu(struct pci_controller *hose, sz -= 1ull << mem_log; if (sz) { - mem_log = __ilog2_u64(sz); + mem_log = ilog2(sz); piwar |= (mem_log - 1); out_be32(&pci->piw[win_idx].pitar, paddr >> 12); @@ -358,9 +396,6 @@ static void setup_pci_atmu(struct pci_controller *hose, pr_info("%s: DMA window size is 0x%llx\n", name, (u64)hose->dma_window_size); } - -out: - iounmap(pci); } static void __init setup_pci_cmd(struct pci_controller *hose) @@ -429,6 +464,7 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary) const int *bus_range; u8 hdr_type, progif; struct device_node *dev; + struct ccsr_pci __iomem *pci; dev = pdev->dev.of_node; @@ -461,8 +497,18 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary) hose->first_busno = bus_range ? bus_range[0] : 0x0; hose->last_busno = bus_range ? bus_range[1] : 0xff; - setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4, - PPC_INDIRECT_TYPE_BIG_ENDIAN); + pr_debug("PCI memory map start 0x%016llx, size 0x%016llx\n", + (u64)rsrc.start, (u64)resource_size(&rsrc)); + + pci = hose->private_data = ioremap(rsrc.start, resource_size(&rsrc)); + if (!hose->private_data) + goto no_bridge; + + fsl_setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4, + PPC_INDIRECT_TYPE_BIG_ENDIAN); + + if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0) + hose->indirect_type |= PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK; if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { /* For PCIE read HEADER_TYPE to identify controler mode */ @@ -500,11 +546,12 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary) pci_process_bridge_OF_ranges(hose, dev, is_primary); /* Setup PEX window registers */ - setup_pci_atmu(hose, &rsrc); + setup_pci_atmu(hose); return 0; no_bridge: + iounmap(hose->private_data); /* unmap cfg_data & cfg_addr separately if not on same page */ if (((unsigned long)hose->cfg_data & PAGE_MASK) != ((unsigned long)hose->cfg_addr & PAGE_MASK)) @@ -681,6 +728,7 @@ static int __init mpc83xx_pcie_setup(struct pci_controller *hose, WARN_ON(hose->dn->data); hose->dn->data = pcie; hose->ops = &mpc83xx_pcie_ops; + hose->indirect_type |= PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK; out_le32(pcie->cfg_type0 + PEX_OUTWIN0_TAH, 0); out_le32(pcie->cfg_type0 + PEX_OUTWIN0_TAL, 0); @@ -766,8 +814,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev) if (ret) goto err0; } else { - setup_indirect_pci(hose, rsrc_cfg.start, - rsrc_cfg.start + 4, 0); + fsl_setup_indirect_pci(hose, rsrc_cfg.start, + rsrc_cfg.start + 4, 0); } printk(KERN_INFO "Found FSL PCI host bridge at 0x%016llx. " @@ -836,6 +884,7 @@ static const struct of_device_id pci_ids[] = { { .compatible = "fsl,qoriq-pcie-v2.2", }, { .compatible = "fsl,qoriq-pcie-v2.3", }, { .compatible = "fsl,qoriq-pcie-v2.4", }, + { .compatible = "fsl,qoriq-pcie-v3.0", }, /* * The following entries are for compatibility with older device @@ -927,7 +976,7 @@ static int fsl_pci_resume(struct device *dev) return -ENODEV; } - setup_pci_atmu(hose, &pci_rsrc); + setup_pci_atmu(hose); return 0; } diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h index c495c00c8740..72b5625330e2 100644 --- a/arch/powerpc/sysdev/fsl_pci.h +++ b/arch/powerpc/sysdev/fsl_pci.h @@ -14,9 +14,12 @@ #ifndef __POWERPC_FSL_PCI_H #define __POWERPC_FSL_PCI_H +struct platform_device; + #define PCIE_LTSSM 0x0404 /* PCIE Link Training and Status */ #define PCIE_LTSSM_L0 0x16 /* L0 state */ #define PCIE_IP_REV_2_2 0x02080202 /* PCIE IP block version Rev2.2 */ +#define PCIE_IP_REV_3_0 0x02080300 /* PCIE IP block version Rev3.0 */ #define PIWAR_EN 0x80000000 /* Enable */ #define PIWAR_PF 0x20000000 /* prefetch */ #define PIWAR_TGI_LOCAL 0x00f00000 /* target - local memory */ @@ -89,6 +92,16 @@ struct ccsr_pci { __be32 pex_err_cap_r1; /* 0x.e2c - PCIE error capture register 0 */ __be32 pex_err_cap_r2; /* 0x.e30 - PCIE error capture register 0 */ __be32 pex_err_cap_r3; /* 0x.e34 - PCIE error capture register 0 */ + u8 res_e38[200]; + __be32 pdb_stat; /* 0x.f00 - PCIE Debug Status */ + u8 res_f04[16]; + __be32 pex_csr0; /* 0x.f14 - PEX Control/Status register 0*/ +#define PEX_CSR0_LTSSM_MASK 0xFC +#define PEX_CSR0_LTSSM_SHIFT 2 +#define PEX_CSR0_LTSSM_L0 0x11 + __be32 pex_csr1; /* 0x.f18 - PEX Control/Status register 1*/ + u8 res_f1c[228]; + }; extern int fsl_add_bridge(struct platform_device *pdev, int is_primary); diff --git a/arch/powerpc/sysdev/indirect_pci.c b/arch/powerpc/sysdev/indirect_pci.c index 82fdad885d20..c6c8b526a4f6 100644 --- a/arch/powerpc/sysdev/indirect_pci.c +++ b/arch/powerpc/sysdev/indirect_pci.c @@ -20,9 +20,8 @@ #include <asm/pci-bridge.h> #include <asm/machdep.h> -static int -indirect_read_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 *val) +int indirect_read_config(struct pci_bus *bus, unsigned int devfn, + int offset, int len, u32 *val) { struct pci_controller *hose = pci_bus_to_host(bus); volatile void __iomem *cfg_data; @@ -78,9 +77,8 @@ indirect_read_config(struct pci_bus *bus, unsigned int devfn, int offset, return PCIBIOS_SUCCESSFUL; } -static int -indirect_write_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 val) +int indirect_write_config(struct pci_bus *bus, unsigned int devfn, + int offset, int len, u32 val) { struct pci_controller *hose = pci_bus_to_host(bus); volatile void __iomem *cfg_data; diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index d30e6a676c89..3cc2f9159ab1 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -54,7 +54,7 @@ static DEFINE_RAW_SPINLOCK(mpic_lock); #ifdef CONFIG_PPC32 /* XXX for now */ #ifdef CONFIG_IRQ_ALL_CPUS -#define distribute_irqs (!(mpic->flags & MPIC_SINGLE_DEST_CPU)) +#define distribute_irqs (1) #else #define distribute_irqs (0) #endif @@ -836,7 +836,7 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, mpic_physmask(mask)); } - return 0; + return IRQ_SET_MASK_OK; } static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type) @@ -1001,8 +1001,12 @@ static int mpic_host_map(struct irq_domain *h, unsigned int virq, if (hw == mpic->spurious_vec) return -EINVAL; - if (mpic->protected && test_bit(hw, mpic->protected)) - return -EINVAL; + if (mpic->protected && test_bit(hw, mpic->protected)) { + pr_warning("mpic: Mapping of source 0x%x failed, " + "source protected by firmware !\n",\ + (unsigned int)hw); + return -EPERM; + } #ifdef CONFIG_SMP else if (hw >= mpic->ipi_vecs[0]) { @@ -1029,8 +1033,12 @@ static int mpic_host_map(struct irq_domain *h, unsigned int virq, if (mpic_map_error_int(mpic, virq, hw)) return 0; - if (hw >= mpic->num_sources) + if (hw >= mpic->num_sources) { + pr_warning("mpic: Mapping of source 0x%x failed, " + "source out of range !\n",\ + (unsigned int)hw); return -EINVAL; + } mpic_msi_reserve_hwirq(mpic, hw); @@ -1695,7 +1703,7 @@ void mpic_setup_this_cpu(void) * it differently, then we should make sure we also change the default * values of irq_desc[].affinity in irq.c. */ - if (distribute_irqs) { + if (distribute_irqs && !(mpic->flags & MPIC_SINGLE_DEST_CPU)) { for (i = 0; i < mpic->num_sources ; i++) mpic_irq_write(i, MPIC_INFO(IRQ_DESTINATION), mpic_irq_read(i, MPIC_INFO(IRQ_DESTINATION)) | msk); diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c index 0f6af41ebb44..4a25c26f0bf4 100644 --- a/arch/powerpc/sysdev/mv64x60_dev.c +++ b/arch/powerpc/sysdev/mv64x60_dev.c @@ -214,15 +214,27 @@ static struct platform_device * __init mv64x60_eth_register_shared_pdev( struct device_node *np, int id) { struct platform_device *pdev; - struct resource r[1]; + struct resource r[2]; int err; err = of_address_to_resource(np, 0, &r[0]); if (err) return ERR_PTR(err); + /* register an orion mdio bus driver */ + r[1].start = r[0].start + 0x4; + r[1].end = r[0].start + 0x84 - 1; + r[1].flags = IORESOURCE_MEM; + + if (id == 0) { + pdev = platform_device_register_simple("orion-mdio", -1, &r[1], 1); + if (!pdev) + return pdev; + } + pdev = platform_device_register_simple(MV643XX_ETH_SHARED_NAME, id, - r, 1); + &r[0], 1); + return pdev; } diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index 56e8b3c3c890..64603a10b863 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -257,6 +257,7 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose, /* Setup outbound memory windows */ for (i = j = 0; i < 3; i++) { struct resource *res = &hose->mem_resources[i]; + resource_size_t offset = hose->mem_offset[i]; /* we only care about memory windows */ if (!(res->flags & IORESOURCE_MEM)) @@ -270,7 +271,7 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose, /* Configure the resource */ if (ppc4xx_setup_one_pci_PMM(hose, reg, res->start, - res->start - hose->pci_mem_offset, + res->start - offset, resource_size(res), res->flags, j) == 0) { @@ -279,7 +280,7 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose, /* If the resource PCI address is 0 then we have our * ISA memory hole */ - if (res->start == hose->pci_mem_offset) + if (res->start == offset) found_isa_hole = 1; } } @@ -457,6 +458,7 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose, /* Setup outbound memory windows */ for (i = j = 0; i < 3; i++) { struct resource *res = &hose->mem_resources[i]; + resource_size_t offset = hose->mem_offset[i]; /* we only care about memory windows */ if (!(res->flags & IORESOURCE_MEM)) @@ -470,7 +472,7 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose, /* Configure the resource */ if (ppc4xx_setup_one_pcix_POM(hose, reg, res->start, - res->start - hose->pci_mem_offset, + res->start - offset, resource_size(res), res->flags, j) == 0) { @@ -479,7 +481,7 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose, /* If the resource PCI address is 0 then we have our * ISA memory hole */ - if (res->start == hose->pci_mem_offset) + if (res->start == offset) found_isa_hole = 1; } } @@ -1792,6 +1794,7 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port, /* Setup outbound memory windows */ for (i = j = 0; i < 3; i++) { struct resource *res = &hose->mem_resources[i]; + resource_size_t offset = hose->mem_offset[i]; /* we only care about memory windows */ if (!(res->flags & IORESOURCE_MEM)) @@ -1805,7 +1808,7 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port, /* Configure the resource */ if (ppc4xx_setup_one_pciex_POM(port, hose, mbase, res->start, - res->start - hose->pci_mem_offset, + res->start - offset, resource_size(res), res->flags, j) == 0) { @@ -1814,7 +1817,7 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port, /* If the resource PCI address is 0 then we have our * ISA memory hole */ - if (res->start == hose->pci_mem_offset) + if (res->start == offset) found_isa_hole = 1; } } diff --git a/arch/powerpc/sysdev/qe_lib/Kconfig b/arch/powerpc/sysdev/qe_lib/Kconfig index 41ac3dfac98e..3c251993bacd 100644 --- a/arch/powerpc/sysdev/qe_lib/Kconfig +++ b/arch/powerpc/sysdev/qe_lib/Kconfig @@ -22,6 +22,6 @@ config UCC config QE_USB bool - default y if USB_GADGET_FSL_QE + default y if USB_FSL_QE help QE USB Controller support 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/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c new file mode 100644 index 000000000000..ce5a7b489e4b --- /dev/null +++ b/arch/powerpc/sysdev/udbg_memcons.c @@ -0,0 +1,105 @@ +/* + * A udbg backend which logs messages and reads input from in memory + * buffers. + * + * The console output can be read from memcons_output which is a + * circular buffer whose next write position is stored in memcons.output_pos. + * + * Input may be passed by writing into the memcons_input buffer when it is + * empty. The input buffer is empty when both input_pos == input_start and + * *input_start == '\0'. + * + * Copyright (C) 2003-2005 Anton Blanchard and Milton Miller, IBM Corp + * Copyright (C) 2013 Alistair Popple, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <asm/barrier.h> +#include <asm/page.h> +#include <asm/processor.h> +#include <asm/udbg.h> + +struct memcons { + char *output_start; + char *output_pos; + char *output_end; + char *input_start; + char *input_pos; + char *input_end; +}; + +static char memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE]; +static char memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE]; + +struct memcons memcons = { + .output_start = memcons_output, + .output_pos = memcons_output, + .output_end = &memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE], + .input_start = memcons_input, + .input_pos = memcons_input, + .input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE], +}; + +void memcons_putc(char c) +{ + char *new_output_pos; + + *memcons.output_pos = c; + wmb(); + new_output_pos = memcons.output_pos + 1; + if (new_output_pos >= memcons.output_end) + new_output_pos = memcons.output_start; + + memcons.output_pos = new_output_pos; +} + +int memcons_getc_poll(void) +{ + char c; + char *new_input_pos; + + if (*memcons.input_pos) { + c = *memcons.input_pos; + + new_input_pos = memcons.input_pos + 1; + if (new_input_pos >= memcons.input_end) + new_input_pos = memcons.input_start; + else if (*new_input_pos == '\0') + new_input_pos = memcons.input_start; + + *memcons.input_pos = '\0'; + wmb(); + memcons.input_pos = new_input_pos; + return c; + } + + return -1; +} + +int memcons_getc(void) +{ + int c; + + while (1) { + c = memcons_getc_poll(); + if (c == -1) + cpu_relax(); + else + break; + } + + return c; +} + +void udbg_init_memcons(void) +{ + udbg_putc = memcons_putc; + udbg_getc = memcons_getc; + udbg_getc_poll = memcons_getc_poll; +} diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 48861d3fcd07..7cd728b3b5e4 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -51,6 +51,12 @@ static struct icp_ipl __iomem *icp_native_regs[NR_CPUS]; static inline unsigned int icp_native_get_xirr(void) { int cpu = smp_processor_id(); + unsigned int xirr; + + /* Handled an interrupt latched by KVM */ + xirr = kvmppc_get_xics_latch(); + if (xirr) + return xirr; return in_be32(&icp_native_regs[cpu]->xirr.word); } @@ -81,7 +87,7 @@ 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); @@ -138,6 +144,7 @@ static unsigned int icp_native_get_irq(void) static void icp_native_cause_ipi(int cpu, unsigned long data) { + kvmppc_set_host_ipi(cpu, 1); icp_native_set_qirr(cpu, IPI_PRIORITY); } @@ -151,6 +158,7 @@ static irqreturn_t icp_native_ipi_action(int irq, void *dev_id) { int cpu = smp_processor_id(); + kvmppc_set_host_ipi(cpu, 0); icp_native_set_qirr(cpu, 0xff); return smp_ipi_demux(); diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index f7e8609df0d5..39d72212655e 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -148,7 +148,7 @@ static int ics_opal_set_affinity(struct irq_data *d, __func__, d->irq, hw_irq, server, rc); return -1; } - return 0; + return IRQ_SET_MASK_OK; } static struct irq_chip ics_opal_irq_chip = { diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 13f85defabed..96bf5bd30fbc 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1430,7 +1430,7 @@ static void excprint(struct pt_regs *fp) printf(" sp: %lx\n", fp->gpr[1]); printf(" msr: %lx\n", fp->msr); - if (trap == 0x300 || trap == 0x380 || trap == 0x600) { + if (trap == 0x300 || trap == 0x380 || trap == 0x600 || trap == 0x200) { printf(" dar: %lx\n", fp->dar); if (trap != 0x380) printf(" dsisr: %lx\n", fp->dsisr); @@ -2947,7 +2947,7 @@ static void sysrq_handle_xmon(int key) static struct sysrq_key_op sysrq_xmon_op = { .handler = sysrq_handle_xmon, - .help_msg = "Xmon", + .help_msg = "xmon(x)", .action_msg = "Entering xmon", }; |