diff options
Diffstat (limited to 'arch/powerpc')
174 files changed, 8530 insertions, 1619 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2e19500921f..c4c4549c22b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -140,6 +140,7 @@ config PPC select HAVE_SYSCALL_WRAPPERS if PPC64 select GENERIC_ATOMIC64 if PPC32 select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API config EARLY_PRINTK bool diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 5cdd7ed9a12..53696da4518 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -44,6 +44,18 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. +config DEBUG_PER_CPU_MAPS + bool "Debug access to per_cpu maps" + depends on DEBUG_KERNEL + depends on SMP + default n + ---help--- + Say Y to verify that the per_cpu map being accessed has + been setup. Adds a fair amount of code to kernel memory + and decreases performance. + + Say N if unsure. + config HCALL_STATS bool "Hypervisor call instrumentation" depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index bb2465bcb32..ad0df7d0a64 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -44,6 +44,7 @@ $(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405 $(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405 $(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405 +$(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405 @@ -77,7 +78,7 @@ src-plat := of.c cuboot-52xx.c cuboot-824x.c cuboot-83xx.c cuboot-85xx.c holly.c cuboot-warp.c cuboot-85xx-cpm2.c cuboot-yosemite.c simpleboot.c \ virtex405-head.S virtex.c redboot-83xx.c cuboot-sam440ep.c \ cuboot-acadia.c cuboot-amigaone.c cuboot-kilauea.c \ - gamecube-head.S gamecube.c wii-head.S wii.c + gamecube-head.S gamecube.c wii-head.S wii.c treeboot-iss4xx.c src-boot := $(src-wlib) $(src-plat) empty.c src-boot := $(addprefix $(obj)/, $(src-boot)) @@ -169,7 +170,7 @@ quiet_cmd_wrap = WRAP $@ $(if $3, -s $3)$(if $4, -d $4)$(if $5, -i $5) vmlinux image-$(CONFIG_PPC_PSERIES) += zImage.pseries -image-$(CONFIG_PPC_MAPLE) += zImage.pseries +image-$(CONFIG_PPC_MAPLE) += zImage.maple image-$(CONFIG_PPC_IBM_CELL_BLADE) += zImage.pseries image-$(CONFIG_PPC_PS3) += dtbImage.ps3 image-$(CONFIG_PPC_CELLEB) += zImage.pseries @@ -206,6 +207,8 @@ image-$(CONFIG_TAISHAN) += cuImage.taishan image-$(CONFIG_KATMAI) += cuImage.katmai image-$(CONFIG_WARP) += cuImage.warp image-$(CONFIG_YOSEMITE) += cuImage.yosemite +image-$(CONFIG_ISS4xx) += treeImage.iss4xx \ + treeImage.iss4xx-mpic # Board ports in arch/powerpc/platform/8xx/Kconfig image-$(CONFIG_MPC86XADS) += cuImage.mpc866ads @@ -351,7 +354,7 @@ install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y)) clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \ zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \ zImage.iseries zImage.miboot zImage.pmac zImage.pseries \ - simpleImage.* otheros.bld *.dtb + zImage.maple simpleImage.* otheros.bld *.dtb # clean up files cached by wrapper clean-kernel := vmlinux.strip vmlinux.bin diff --git a/arch/powerpc/boot/dts/iss4xx-mpic.dts b/arch/powerpc/boot/dts/iss4xx-mpic.dts new file mode 100644 index 00000000000..23e9d9b7e40 --- /dev/null +++ b/arch/powerpc/boot/dts/iss4xx-mpic.dts @@ -0,0 +1,155 @@ +/* + * Device Tree Source for IBM Embedded PPC 476 Platform + * + * Copyright 2010 Torez Smith, IBM Corporation. + * + * Based on earlier code: + * Copyright (c) 2006, 2007 IBM Corp. + * Josh Boyer <jwboyer@linux.vnet.ibm.com>, David Gibson <dwg@au1.ibm.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without + * any warranty of any kind, whether express or implied. + */ + +/dts-v1/; + +/memreserve/ 0x01f00000 0x00100000; + +/ { + #address-cells = <2>; + #size-cells = <1>; + model = "ibm,iss-4xx"; + compatible = "ibm,iss-4xx"; + dcr-parent = <&{/cpus/cpu@0}>; + + aliases { + serial0 = &UART0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + model = "PowerPC,4xx"; // real CPU changed in sim + reg = <0>; + clock-frequency = <100000000>; // 100Mhz :-) + timebase-frequency = <100000000>; + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "ok"; + }; + cpu@1 { + device_type = "cpu"; + model = "PowerPC,4xx"; // real CPU changed in sim + reg = <1>; + clock-frequency = <100000000>; // 100Mhz :-) + timebase-frequency = <100000000>; + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "disabled"; + enable-method = "spin-table"; + cpu-release-addr = <0 0x01f00100>; + }; + cpu@2 { + device_type = "cpu"; + model = "PowerPC,4xx"; // real CPU changed in sim + reg = <2>; + clock-frequency = <100000000>; // 100Mhz :-) + timebase-frequency = <100000000>; + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "disabled"; + enable-method = "spin-table"; + cpu-release-addr = <0 0x01f00200>; + }; + cpu@3 { + device_type = "cpu"; + model = "PowerPC,4xx"; // real CPU changed in sim + reg = <3>; + clock-frequency = <100000000>; // 100Mhz :-) + timebase-frequency = <100000000>; + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "disabled"; + enable-method = "spin-table"; + cpu-release-addr = <0 0x01f00300>; + }; + }; + + memory { + device_type = "memory"; + reg = <0x00000000 0x00000000 0x00000000>; // Filled in by zImage + + }; + + MPIC: interrupt-controller { + compatible = "chrp,open-pic"; + interrupt-controller; + dcr-reg = <0xffc00000 0x00030000>; + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + }; + + plb { + compatible = "ibm,plb-4xx", "ibm,plb4"; /* Could be PLB6, doesn't matter */ + #address-cells = <2>; + #size-cells = <1>; + ranges; + clock-frequency = <0>; // Filled in by zImage + + POB0: opb { + compatible = "ibm,opb-4xx", "ibm,opb"; + #address-cells = <1>; + #size-cells = <1>; + /* Wish there was a nicer way of specifying a full 32-bit + range */ + ranges = <0x00000000 0x00000001 0x00000000 0x80000000 + 0x80000000 0x00000001 0x80000000 0x80000000>; + clock-frequency = <0>; // Filled in by zImage + UART0: serial@40000200 { + device_type = "serial"; + compatible = "ns16550a"; + reg = <0x40000200 0x00000008>; + virtual-reg = <0xe0000200>; + clock-frequency = <11059200>; + current-speed = <115200>; + interrupt-parent = <&MPIC>; + interrupts = <0x0 0x2>; + }; + }; + }; + + nvrtc { + compatible = "ds1743-nvram", "ds1743", "rtc-ds1743"; + reg = <0 0xEF703000 0x2000>; + }; + iss-block { + compatible = "ibm,iss-sim-block-device"; + reg = <0 0xEF701000 0x1000>; + }; + + chosen { + linux,stdout-path = "/plb/opb/serial@40000200"; + }; +}; diff --git a/arch/powerpc/boot/dts/iss4xx.dts b/arch/powerpc/boot/dts/iss4xx.dts new file mode 100644 index 00000000000..4ff6555c866 --- /dev/null +++ b/arch/powerpc/boot/dts/iss4xx.dts @@ -0,0 +1,116 @@ +/* + * Device Tree Source for IBM Embedded PPC 476 Platform + * + * Copyright 2010 Torez Smith, IBM Corporation. + * + * Based on earlier code: + * Copyright (c) 2006, 2007 IBM Corp. + * Josh Boyer <jwboyer@linux.vnet.ibm.com>, David Gibson <dwg@au1.ibm.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without + * any warranty of any kind, whether express or implied. + */ + +/dts-v1/; + +/ { + #address-cells = <2>; + #size-cells = <1>; + model = "ibm,iss-4xx"; + compatible = "ibm,iss-4xx"; + dcr-parent = <&{/cpus/cpu@0}>; + + aliases { + serial0 = &UART0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + model = "PowerPC,4xx"; // real CPU changed in sim + reg = <0x00000000>; + clock-frequency = <100000000>; // 100Mhz :-) + timebase-frequency = <100000000>; + i-cache-line-size = <32>; // may need fixup in sim + d-cache-line-size = <32>; // may need fixup in sim + i-cache-size = <32768>; /* may need fixup in sim */ + d-cache-size = <32768>; /* may need fixup in sim */ + dcr-controller; + dcr-access-method = "native"; + }; + }; + + memory { + device_type = "memory"; + reg = <0x00000000 0x00000000 0x00000000>; // Filled in by zImage + }; + + UIC0: interrupt-controller0 { + compatible = "ibm,uic-4xx", "ibm,uic"; + interrupt-controller; + cell-index = <0>; + dcr-reg = <0x0c0 0x009>; + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + }; + + UIC1: interrupt-controller1 { + compatible = "ibm,uic-4xx", "ibm,uic"; + interrupt-controller; + cell-index = <1>; + dcr-reg = <0x0d0 0x009>; + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */ + interrupt-parent = <&UIC0>; + }; + + plb { + compatible = "ibm,plb-4xx", "ibm,plb4"; /* Could be PLB6, doesn't matter */ + #address-cells = <2>; + #size-cells = <1>; + ranges; + clock-frequency = <0>; // Filled in by zImage + + POB0: opb { + compatible = "ibm,opb-4xx", "ibm,opb"; + #address-cells = <1>; + #size-cells = <1>; + /* Wish there was a nicer way of specifying a full 32-bit + range */ + ranges = <0x00000000 0x00000001 0x00000000 0x80000000 + 0x80000000 0x00000001 0x80000000 0x80000000>; + clock-frequency = <0>; // Filled in by zImage + UART0: serial@40000200 { + device_type = "serial"; + compatible = "ns16550a"; + reg = <0x40000200 0x00000008>; + virtual-reg = <0xe0000200>; + clock-frequency = <11059200>; + current-speed = <115200>; + interrupt-parent = <&UIC0>; + interrupts = <0x0 0x4>; + }; + }; + }; + + nvrtc { + compatible = "ds1743-nvram", "ds1743", "rtc-ds1743"; + reg = <0 0xEF703000 0x2000>; + }; + iss-block { + compatible = "ibm,iss-sim-block-device"; + reg = <0 0xEF701000 0x1000>; + }; + + chosen { + linux,stdout-path = "/plb/opb/serial@40000200"; + }; +}; diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index 8a3a4f3ef83..4dd08c32297 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -292,7 +292,7 @@ fsl,num-channels = <4>; fsl,channel-fifo-len = <24>; fsl,exec-units-mask = <0x97c>; - fsl,descriptor-types-mask = <0x3ab0abf>; + fsl,descriptor-types-mask = <0x3a30abf>; }; sata@18000 { @@ -463,4 +463,18 @@ 0 0x00800000>; }; }; + + leds { + compatible = "gpio-leds"; + + pwr { + gpios = <&mcu_pio 0 0>; + default-state = "on"; + }; + + hdd { + gpios = <&mcu_pio 1 0>; + linux,default-trigger = "ide-disk"; + }; + }; }; diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts index 9e2264b1000..dbc1b988b29 100644 --- a/arch/powerpc/boot/dts/mpc8377_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts @@ -486,4 +486,18 @@ 0 0x00800000>; }; }; + + leds { + compatible = "gpio-leds"; + + pwr { + gpios = <&mcu_pio 0 0>; + default-state = "on"; + }; + + hdd { + gpios = <&mcu_pio 1 0>; + linux,default-trigger = "ide-disk"; + }; + }; }; diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts index 4e6a1a407bb..3447eb9f6e8 100644 --- a/arch/powerpc/boot/dts/mpc8378_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts @@ -470,4 +470,18 @@ 0 0x00800000>; }; }; + + leds { + compatible = "gpio-leds"; + + pwr { + gpios = <&mcu_pio 0 0>; + default-state = "on"; + }; + + hdd { + gpios = <&mcu_pio 1 0>; + linux,default-trigger = "ide-disk"; + }; + }; }; diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts index 72336d50452..15560c619b0 100644 --- a/arch/powerpc/boot/dts/mpc8379_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts @@ -436,4 +436,18 @@ compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; + + leds { + compatible = "gpio-leds"; + + pwr { + gpios = <&mcu_pio 0 0>; + default-state = "on"; + }; + + hdd { + gpios = <&mcu_pio 1 0>; + linux,default-trigger = "ide-disk"; + }; + }; }; diff --git a/arch/powerpc/boot/dts/p1020rdb.dts b/arch/powerpc/boot/dts/p1020rdb.dts index df5269093af..22f64b62d7f 100644 --- a/arch/powerpc/boot/dts/p1020rdb.dts +++ b/arch/powerpc/boot/dts/p1020rdb.dts @@ -19,6 +19,9 @@ aliases { serial0 = &serial0; serial1 = &serial1; + ethernet0 = &enet0; + ethernet1 = &enet1; + ethernet2 = &enet2; pci0 = &pci0; pci1 = &pci1; }; @@ -346,6 +349,122 @@ }; }; + mdio@24000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,etsec2-mdio"; + reg = <0x24000 0x1000 0xb0030 0x4>; + + phy0: ethernet-phy@0 { + interrupt-parent = <&mpic>; + interrupts = <3 1>; + reg = <0x0>; + }; + + phy1: ethernet-phy@1 { + interrupt-parent = <&mpic>; + interrupts = <2 1>; + reg = <0x1>; + }; + }; + + mdio@25000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,etsec2-tbi"; + reg = <0x25000 0x1000 0xb1030 0x4>; + + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + enet0: ethernet@b0000 { + #address-cells = <1>; + #size-cells = <1>; + device_type = "network"; + model = "eTSEC"; + compatible = "fsl,etsec2"; + fsl,num_rx_queues = <0x8>; + fsl,num_tx_queues = <0x8>; + local-mac-address = [ 00 00 00 00 00 00 ]; + interrupt-parent = <&mpic>; + fixed-link = <1 1 1000 0 0>; + phy-connection-type = "rgmii-id"; + + queue-group@0 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb0000 0x1000>; + interrupts = <29 2 30 2 34 2>; + }; + + queue-group@1 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb4000 0x1000>; + interrupts = <17 2 18 2 24 2>; + }; + }; + + enet1: ethernet@b1000 { + #address-cells = <1>; + #size-cells = <1>; + device_type = "network"; + model = "eTSEC"; + compatible = "fsl,etsec2"; + fsl,num_rx_queues = <0x8>; + fsl,num_tx_queues = <0x8>; + local-mac-address = [ 00 00 00 00 00 00 ]; + interrupt-parent = <&mpic>; + phy-handle = <&phy0>; + tbi-handle = <&tbi0>; + phy-connection-type = "sgmii"; + + queue-group@0 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb1000 0x1000>; + interrupts = <35 2 36 2 40 2>; + }; + + queue-group@1 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb5000 0x1000>; + interrupts = <51 2 52 2 67 2>; + }; + }; + + enet2: ethernet@b2000 { + #address-cells = <1>; + #size-cells = <1>; + device_type = "network"; + model = "eTSEC"; + compatible = "fsl,etsec2"; + fsl,num_rx_queues = <0x8>; + fsl,num_tx_queues = <0x8>; + local-mac-address = [ 00 00 00 00 00 00 ]; + interrupt-parent = <&mpic>; + phy-handle = <&phy1>; + phy-connection-type = "rgmii-id"; + + queue-group@0 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb2000 0x1000>; + interrupts = <31 2 32 2 33 2>; + }; + + queue-group@1 { + #address-cells = <1>; + #size-cells = <1>; + reg = <0xb6000 0x1000>; + interrupts = <25 2 26 2 27 2>; + }; + }; + usb@22000 { #address-cells = <1>; #size-cells = <0>; @@ -356,6 +475,11 @@ phy_type = "ulpi"; }; + /* USB2 is shared with localbus, so it must be disabled + by default. We can't put 'status = "disabled";' here + since U-Boot doesn't clear the status property when + it enables USB2. OTOH, U-Boot does create a new node + when there isn't any. So, just comment it out. usb@23000 { #address-cells = <1>; #size-cells = <0>; @@ -365,6 +489,7 @@ interrupts = <46 0x2>; phy_type = "ulpi"; }; + */ sdhci@2e000 { compatible = "fsl,p1020-esdhc", "fsl,esdhc"; diff --git a/arch/powerpc/boot/treeboot-iss4xx.c b/arch/powerpc/boot/treeboot-iss4xx.c new file mode 100644 index 00000000000..fcc44952874 --- /dev/null +++ b/arch/powerpc/boot/treeboot-iss4xx.c @@ -0,0 +1,56 @@ +/* + * Copyright 2010 Ben. Herrenschmidt, IBM Corporation. + * + * Based on earlier code: + * Copyright (C) Paul Mackerras 1997. + * + * Matt Porter <mporter@kernel.crashing.org> + * Copyright 2002-2005 MontaVista Software Inc. + * + * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net> + * Copyright (c) 2003, 2004 Zultys Technologies + * + * Copyright 2007 David Gibson, 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 <stdarg.h> +#include <stddef.h> +#include "types.h" +#include "elf.h" +#include "string.h" +#include "stdio.h" +#include "page.h" +#include "ops.h" +#include "reg.h" +#include "io.h" +#include "dcr.h" +#include "4xx.h" +#include "44x.h" +#include "libfdt.h" + +BSS_STACK(4096); + +static void iss_4xx_fixups(void) +{ + ibm4xx_sdram_fixup_memsize(); +} + +#define SPRN_PIR 0x11E /* Processor Indentification Register */ +void platform_init(void) +{ + unsigned long end_of_ram = 0x08000000; + unsigned long avail_ram = end_of_ram - (unsigned long)_end; + u32 pir_reg; + + simple_alloc_init(_end, avail_ram, 128, 64); + platform_ops.fixups = iss_4xx_fixups; + platform_ops.exit = ibm44x_dbcr_reset; + pir_reg = mfspr(SPRN_PIR); + fdt_set_boot_cpuid_phys(_dtb_start, pir_reg); + fdt_init(_dtb_start); + serial_console_init(); +} diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index f4594ed09a2..cb97e7511d7 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -149,6 +149,10 @@ pseries) platformo=$object/of.o link_address='0x4000000' ;; +maple) + platformo=$object/of.o + link_address='0x400000' + ;; pmac|chrp) platformo=$object/of.o ;; @@ -237,6 +241,9 @@ gamecube|wii) link_address='0x600000' platformo="$object/$platform-head.o $object/$platform.o" ;; +treeboot-iss4xx-mpic) + platformo="$object/treeboot-iss4xx.o" + ;; esac vmz="$tmpdir/`basename \"$kernel\"`.$ext" @@ -321,7 +328,7 @@ fi # post-processing needed for some platforms case "$platform" in -pseries|chrp) +pseries|chrp|maple) $objbin/addnote "$ofile" ;; coff) diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig new file mode 100644 index 00000000000..8683cbc6c3e --- /dev/null +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -0,0 +1,1026 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.33 +# Thu Mar 4 11:50:12 2010 +# +# CONFIG_PPC64 is not set + +# +# Processor support +# +# CONFIG_PPC_BOOK3S_32 is not set +# CONFIG_PPC_85xx is not set +# CONFIG_PPC_8xx is not set +# CONFIG_40x is not set +CONFIG_44x=y +# CONFIG_E200 is not set +CONFIG_PPC_FPU=y +CONFIG_4xx=y +CONFIG_BOOKE=y +CONFIG_PTE_64BIT=y +CONFIG_PHYS_64BIT=y +CONFIG_PPC_MMU_NOHASH=y +CONFIG_PPC_MMU_NOHASH_32=y +# CONFIG_PPC_MM_SLICES is not set +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +# CONFIG_NOT_COHERENT_CACHE is not set +CONFIG_PPC32=y +CONFIG_WORD_SIZE=32 +CONFIG_ARCH_PHYS_ADDR_T_64BIT=y +CONFIG_MMU=y +CONFIG_GENERIC_CMOS_UPDATE=y +CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_TIME_VSYSCALL=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y +# CONFIG_HAVE_SETUP_PER_CPU_AREA is not set +# CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK is not set +CONFIG_IRQ_PER_CPU=y +CONFIG_NR_IRQS=512 +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_HAVE_LATENCYTOP_SUPPORT=y +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_ARCH_HAS_ILOG2_U32=y +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_FIND_NEXT_BIT=y +# CONFIG_ARCH_NO_VIRT_TO_BUS is not set +CONFIG_PPC=y +CONFIG_EARLY_PRINTK=y +CONFIG_GENERIC_NVRAM=y +CONFIG_SCHED_OMIT_FRAME_POINTER=y +CONFIG_ARCH_MAY_HAVE_PC_FDC=y +CONFIG_PPC_OF=y +CONFIG_OF=y +CONFIG_PPC_UDBG_16550=y +CONFIG_GENERIC_TBSYNC=y +CONFIG_AUDIT_ARCH=y +CONFIG_GENERIC_BUG=y +CONFIG_DTC=y +# CONFIG_DEFAULT_UIMAGE is not set +CONFIG_ARCH_HIBERNATION_POSSIBLE=y +CONFIG_PPC_DCR_NATIVE=y +# CONFIG_PPC_DCR_MMIO is not set +CONFIG_PPC_DCR=y +CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_CONSTRUCTORS=y + +# +# General setup +# +CONFIG_EXPERIMENTAL=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y +# CONFIG_BSD_PROCESS_ACCT is not set +# CONFIG_TASKSTATS is not set +# CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_TREE_RCU=y +# CONFIG_TREE_PREEMPT_RCU is not set +# CONFIG_TINY_RCU is not set +# CONFIG_RCU_TRACE is not set +CONFIG_RCU_FANOUT=32 +# CONFIG_RCU_FANOUT_EXACT is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_IKCONFIG is not set +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_GROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +# CONFIG_RT_GROUP_SCHED is not set +CONFIG_USER_SCHED=y +# CONFIG_CGROUP_SCHED is not set +# CONFIG_CGROUPS is not set +CONFIG_SYSFS_DEPRECATED=y +CONFIG_SYSFS_DEPRECATED_V2=y +# CONFIG_RELAY is not set +# CONFIG_NAMESPACES is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_LZO is not set +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_SYSCTL=y +CONFIG_ANON_INODES=y +CONFIG_EMBEDDED=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_KALLSYMS=y +CONFIG_KALLSYMS_ALL=y +CONFIG_KALLSYMS_EXTRA_PASS=y +CONFIG_HOTPLUG=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y +CONFIG_SHMEM=y +CONFIG_AIO=y +CONFIG_HAVE_PERF_EVENTS=y + +# +# Kernel Performance Events And Counters +# +CONFIG_PERF_EVENTS=y +CONFIG_EVENT_PROFILE=y +# CONFIG_PERF_COUNTERS is not set +# CONFIG_DEBUG_PERF_USE_VMALLOC is not set +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLUB_DEBUG=y +CONFIG_COMPAT_BRK=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y +# CONFIG_SLOB is not set +CONFIG_PROFILING=y +CONFIG_TRACEPOINTS=y +CONFIG_OPROFILE=y +CONFIG_HAVE_OPROFILE=y +# CONFIG_KPROBES is not set +CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y +CONFIG_HAVE_IOREMAP_PROT=y +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +CONFIG_HAVE_ARCH_TRACEHOOK=y +CONFIG_HAVE_DMA_ATTRS=y +CONFIG_USE_GENERIC_SMP_HELPERS=y +CONFIG_HAVE_DMA_API_DEBUG=y + +# +# GCOV-based kernel profiling +# +# CONFIG_GCOV_KERNEL is not set +# CONFIG_SLOW_WORK is not set +# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set +CONFIG_SLABINFO=y +CONFIG_RT_MUTEXES=y +CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_FORCE_LOAD is not set +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_STOP_MACHINE=y +CONFIG_BLOCK=y +CONFIG_LBDAF=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_BLK_DEV_INTEGRITY is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" +# CONFIG_INLINE_SPIN_TRYLOCK is not set +# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set +# CONFIG_INLINE_SPIN_LOCK is not set +# CONFIG_INLINE_SPIN_LOCK_BH is not set +# CONFIG_INLINE_SPIN_LOCK_IRQ is not set +# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set +CONFIG_INLINE_SPIN_UNLOCK=y +# CONFIG_INLINE_SPIN_UNLOCK_BH is not set +CONFIG_INLINE_SPIN_UNLOCK_IRQ=y +# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set +# CONFIG_INLINE_READ_TRYLOCK is not set +# CONFIG_INLINE_READ_LOCK is not set +# CONFIG_INLINE_READ_LOCK_BH is not set +# CONFIG_INLINE_READ_LOCK_IRQ is not set +# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set +CONFIG_INLINE_READ_UNLOCK=y +# CONFIG_INLINE_READ_UNLOCK_BH is not set +CONFIG_INLINE_READ_UNLOCK_IRQ=y +# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set +# CONFIG_INLINE_WRITE_TRYLOCK is not set +# CONFIG_INLINE_WRITE_LOCK is not set +# CONFIG_INLINE_WRITE_LOCK_BH is not set +# CONFIG_INLINE_WRITE_LOCK_IRQ is not set +# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set +CONFIG_INLINE_WRITE_UNLOCK=y +# CONFIG_INLINE_WRITE_UNLOCK_BH is not set +CONFIG_INLINE_WRITE_UNLOCK_IRQ=y +# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set +CONFIG_MUTEX_SPIN_ON_OWNER=y +# CONFIG_FREEZER is not set + +# +# Platform support +# +# CONFIG_PPC_CELL is not set +# CONFIG_PPC_CELL_NATIVE is not set +# CONFIG_PQ2ADS is not set +CONFIG_PPC_47x=y +# CONFIG_BAMBOO is not set +# CONFIG_EBONY is not set +# CONFIG_SAM440EP is not set +# CONFIG_SEQUOIA is not set +# CONFIG_TAISHAN is not set +# CONFIG_KATMAI is not set +# CONFIG_RAINIER is not set +# CONFIG_WARP is not set +# CONFIG_ARCHES is not set +# CONFIG_CANYONLANDS is not set +# CONFIG_GLACIER is not set +# CONFIG_REDWOOD is not set +# CONFIG_EIGER is not set +# CONFIG_YOSEMITE is not set +CONFIG_ISS4xx=y +# CONFIG_XILINX_VIRTEX440_GENERIC_BOARD is not set +# CONFIG_PPC44x_SIMPLE is not set +# CONFIG_PPC4xx_GPIO is not set +# CONFIG_IPIC is not set +CONFIG_MPIC=y +# CONFIG_MPIC_WEIRD is not set +# CONFIG_PPC_I8259 is not set +# CONFIG_PPC_RTAS is not set +# CONFIG_MMIO_NVRAM is not set +# CONFIG_PPC_MPC106 is not set +# CONFIG_PPC_970_NAP is not set +# CONFIG_PPC_INDIRECT_IO is not set +# CONFIG_GENERIC_IOMAP is not set +# CONFIG_CPU_FREQ is not set +# CONFIG_FSL_ULI1575 is not set +CONFIG_OF_RTC=y +# CONFIG_SIMPLE_GPIO is not set + +# +# Kernel options +# +# CONFIG_HIGHMEM is not set +# CONFIG_NO_HZ is not set +# CONFIG_HIGH_RES_TIMERS is not set +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y +CONFIG_HZ_100=y +# CONFIG_HZ_250 is not set +# CONFIG_HZ_300 is not set +# CONFIG_HZ_1000 is not set +CONFIG_HZ=100 +# CONFIG_SCHED_HRTICK is not set +CONFIG_PREEMPT_NONE=y +# CONFIG_PREEMPT_VOLUNTARY is not set +# CONFIG_PREEMPT is not set +CONFIG_BINFMT_ELF=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_HAVE_AOUT is not set +# CONFIG_BINFMT_MISC is not set +CONFIG_MATH_EMULATION=y +# CONFIG_IOMMU_HELPER is not set +# CONFIG_SWIOTLB is not set +CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y +CONFIG_ARCH_HAS_WALK_MEMORY=y +CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y +CONFIG_IRQ_ALL_CPUS=y +CONFIG_SPARSE_IRQ=y +CONFIG_MAX_ACTIVE_REGIONS=32 +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_ARCH_POPULATES_NODE_MAP=y +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_PAGEFLAGS_EXTENDED=y +CONFIG_SPLIT_PTLOCK_CPUS=4 +CONFIG_MIGRATION=y +CONFIG_PHYS_ADDR_T_64BIT=y +CONFIG_ZONE_DMA_FLAG=1 +CONFIG_BOUNCE=y +CONFIG_VIRT_TO_BUS=y +# CONFIG_KSM is not set +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 +CONFIG_STDBINUTILS=y +CONFIG_PPC_4K_PAGES=y +# CONFIG_PPC_16K_PAGES is not set +# CONFIG_PPC_64K_PAGES is not set +# CONFIG_PPC_256K_PAGES is not set +CONFIG_FORCE_MAX_ZONEORDER=11 +CONFIG_PROC_DEVICETREE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="root=/dev/issblk0" +CONFIG_EXTRA_TARGETS="" +CONFIG_SECCOMP=y +CONFIG_ISA_DMA_API=y + +# +# Bus options +# +CONFIG_ZONE_DMA=y +CONFIG_4xx_SOC=y +CONFIG_PPC_PCI_CHOICE=y +# CONFIG_PCI is not set +# CONFIG_PCI_DOMAINS is not set +# CONFIG_PCI_SYSCALL is not set +# CONFIG_ARCH_SUPPORTS_MSI is not set +# CONFIG_PCCARD is not set +# CONFIG_HAS_RAPIDIO is not set + +# +# Advanced setup +# +# CONFIG_ADVANCED_OPTIONS is not set + +# +# Default settings for advanced configuration options are used +# +CONFIG_LOWMEM_SIZE=0x30000000 +CONFIG_PAGE_OFFSET=0xc0000000 +CONFIG_KERNEL_START=0xc0000000 +CONFIG_PHYSICAL_START=0x00000000 +CONFIG_TASK_SIZE=0xc0000000 +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set +# CONFIG_INET_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG=y +CONFIG_INET_TCP_DIAG=y +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +# CONFIG_TCP_MD5SIG is not set +# CONFIG_IPV6 is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set +# CONFIG_IP_DCCP is not set +# CONFIG_IP_SCTP is not set +# CONFIG_RDS is not set +# CONFIG_TIPC is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_NET_DSA is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set +# CONFIG_PHONET is not set +# CONFIG_IEEE802154 is not set +# CONFIG_NET_SCHED is not set +# CONFIG_DCB is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_NET_DROP_MONITOR is not set +# CONFIG_HAMRADIO is not set +# CONFIG_CAN is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_AF_RXRPC is not set +CONFIG_WIRELESS=y +# CONFIG_CFG80211 is not set +# CONFIG_LIB80211 is not set + +# +# CFG80211 needs to be enabled for MAC80211 +# +# CONFIG_WIMAX is not set +# CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_DEVTMPFS is not set +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +CONFIG_FW_LOADER=y +CONFIG_FIRMWARE_IN_KERNEL=y +CONFIG_EXTRA_FIRMWARE="" +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_DEBUG_DEVRES is not set +# CONFIG_SYS_HYPERVISOR is not set +CONFIG_CONNECTOR=y +CONFIG_PROC_EVENTS=y +CONFIG_MTD=y +# CONFIG_MTD_DEBUG is not set +# CONFIG_MTD_TESTS is not set +# CONFIG_MTD_CONCAT is not set +CONFIG_MTD_PARTITIONS=y +# CONFIG_MTD_REDBOOT_PARTS is not set +# CONFIG_MTD_CMDLINE_PARTS is not set +CONFIG_MTD_OF_PARTS=y +# CONFIG_MTD_AR7_PARTS is not set + +# +# User Modules And Translation Layers +# +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y +CONFIG_MTD_BLOCK=y +# CONFIG_FTL is not set +# CONFIG_NFTL is not set +# CONFIG_INFTL is not set +# CONFIG_RFD_FTL is not set +# CONFIG_SSFDC is not set +# CONFIG_MTD_OOPS is not set + +# +# RAM/ROM/Flash chip drivers +# +# CONFIG_MTD_CFI is not set +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_GEN_PROBE=y +# CONFIG_MTD_CFI_ADV_OPTIONS is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +# CONFIG_MTD_CFI_I4 is not set +# CONFIG_MTD_CFI_I8 is not set +# CONFIG_MTD_CFI_INTELEXT is not set +CONFIG_MTD_CFI_AMDSTD=y +# CONFIG_MTD_CFI_STAA is not set +CONFIG_MTD_CFI_UTIL=y +# CONFIG_MTD_RAM is not set +# CONFIG_MTD_ROM is not set +# CONFIG_MTD_ABSENT is not set + +# +# Mapping drivers for chip access +# +# CONFIG_MTD_COMPLEX_MAPPINGS is not set +# CONFIG_MTD_PHYSMAP is not set +CONFIG_MTD_PHYSMAP_OF=y +# CONFIG_MTD_PLATRAM is not set + +# +# Self-contained MTD device drivers +# +# CONFIG_MTD_SLRAM is not set +# CONFIG_MTD_PHRAM is not set +# CONFIG_MTD_MTDRAM is not set +# CONFIG_MTD_BLOCK2MTD is not set + +# +# Disk-On-Chip Device Drivers +# +# CONFIG_MTD_DOC2000 is not set +# CONFIG_MTD_DOC2001 is not set +# CONFIG_MTD_DOC2001PLUS is not set +# CONFIG_MTD_NAND is not set +# CONFIG_MTD_ONENAND is not set + +# +# LPDDR flash memory drivers +# +# CONFIG_MTD_LPDDR is not set + +# +# UBI - Unsorted block images +# +# CONFIG_MTD_UBI is not set +CONFIG_OF_DEVICE=y +# CONFIG_PARPORT is not set +CONFIG_BLK_DEV=y +# CONFIG_BLK_DEV_FD is not set +# CONFIG_BLK_DEV_COW_COMMON is not set +# CONFIG_BLK_DEV_LOOP is not set +# CONFIG_BLK_DEV_DRBD is not set +# CONFIG_BLK_DEV_NBD is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=35000 +# CONFIG_BLK_DEV_XIP is not set +# CONFIG_CDROM_PKTCDVD is not set +# CONFIG_ATA_OVER_ETH is not set +# CONFIG_XILINX_SYSACE is not set +# CONFIG_BLK_DEV_HD is not set +CONFIG_MISC_DEVICES=y +# CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_93CX6 is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +# CONFIG_SCSI is not set +# CONFIG_SCSI_DMA is not set +# CONFIG_SCSI_NETLINK is not set +# CONFIG_ATA is not set +# CONFIG_MD is not set +# CONFIG_MACINTOSH_DRIVERS is not set +# CONFIG_NETDEVICES is not set +# CONFIG_ISDN is not set +# CONFIG_PHONE is not set + +# +# Input device support +# +# CONFIG_INPUT is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +# CONFIG_VT is not set +CONFIG_DEVKMEM=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=4 +CONFIG_SERIAL_8250_RUNTIME_UARTS=4 +CONFIG_SERIAL_8250_EXTENDED=y +# CONFIG_SERIAL_8250_MANY_PORTS is not set +CONFIG_SERIAL_8250_SHARE_IRQ=y +# CONFIG_SERIAL_8250_DETECT_IRQ is not set +# CONFIG_SERIAL_8250_RSA is not set + +# +# Non-8250 serial port support +# +# CONFIG_SERIAL_UARTLITE is not set +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL is not set +# CONFIG_SERIAL_GRLIB_GAISLER_APBUART is not set +CONFIG_UNIX98_PTYS=y +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_HVC_UDBG is not set +# CONFIG_IPMI_HANDLER is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_NVRAM is not set +# CONFIG_GEN_RTC is not set +# CONFIG_R3964 is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_TCG_TPM is not set +# CONFIG_I2C is not set +# CONFIG_SPI is not set + +# +# PPS support +# +# CONFIG_PPS is not set +CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y +# CONFIG_GPIOLIB is not set +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +# CONFIG_HWMON is not set +CONFIG_THERMAL=y +# CONFIG_WATCHDOG is not set +CONFIG_SSB_POSSIBLE=y + +# +# Sonics Silicon Backplane +# +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_CORE is not set +# CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set +# CONFIG_MFD_TMIO is not set +# CONFIG_REGULATOR is not set +# CONFIG_MEDIA_SUPPORT is not set + +# +# Graphics support +# +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +# CONFIG_FB is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set +# CONFIG_SOUND is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +# CONFIG_NEW_LEDS is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_EDAC is not set +# CONFIG_RTC_CLASS is not set +# CONFIG_DMADEVICES is not set +# CONFIG_AUXDISPLAY is not set +# CONFIG_UIO is not set + +# +# TI VLYNQ +# +# CONFIG_STAGING is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +# CONFIG_EXT2_FS_XIP is not set +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_XATTR=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +# CONFIG_EXT4_FS is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +CONFIG_FS_POSIX_ACL=y +# CONFIG_XFS_FS is not set +# CONFIG_GFS2_FS is not set +# CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set +# CONFIG_NILFS2_FS is not set +CONFIG_FILE_LOCKING=y +CONFIG_FSNOTIFY=y +CONFIG_DNOTIFY=y +CONFIG_INOTIFY=y +CONFIG_INOTIFY_USER=y +# CONFIG_QUOTA is not set +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set + +# +# Caches +# +# CONFIG_FSCACHE is not set + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +# CONFIG_MSDOS_FS is not set +# CONFIG_VFAT_FS is not set +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_PROC_SYSCTL=y +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +# CONFIG_TMPFS_POSIX_ACL is not set +# CONFIG_HUGETLB_PAGE is not set +# CONFIG_CONFIGFS_FS is not set +CONFIG_MISC_FILESYSTEMS=y +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +# CONFIG_JFFS2_FS is not set +CONFIG_CRAMFS=y +# CONFIG_SQUASHFS is not set +# CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_OMFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set +# CONFIG_NETWORK_FILESYSTEMS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +# CONFIG_NLS is not set +# CONFIG_DLM is not set +CONFIG_BINARY_PRINTF=y + +# +# Library routines +# +CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_LAST_BIT=y +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +# CONFIG_CRC_T10DIF is not set +# CONFIG_CRC_ITU_T is not set +CONFIG_CRC32=y +# CONFIG_CRC7 is not set +# CONFIG_LIBCRC32C is not set +CONFIG_ZLIB_INFLATE=y +CONFIG_DECOMPRESS_GZIP=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_IOPORT=y +CONFIG_HAS_DMA=y +CONFIG_HAVE_LMB=y +CONFIG_NLATTR=y +CONFIG_GENERIC_ATOMIC64=y + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_ENABLE_WARN_DEPRECATED=y +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=1024 +CONFIG_MAGIC_SYSRQ=y +# CONFIG_STRIP_ASM_SYMS is not set +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_DEBUG_FS=y +# CONFIG_HEADERS_CHECK is not set +CONFIG_DEBUG_KERNEL=y +# CONFIG_DEBUG_SHIRQ is not set +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +CONFIG_DETECT_HUNG_TASK=y +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 +CONFIG_SCHED_DEBUG=y +# CONFIG_SCHEDSTATS is not set +# CONFIG_TIMER_STATS is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set +# CONFIG_DEBUG_KMEMLEAK is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +CONFIG_STACKTRACE=y +# CONFIG_DEBUG_KOBJECT is not set +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_INFO=y +# CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set +# CONFIG_DEBUG_MEMORY_INIT is not set +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set +# CONFIG_DEBUG_CREDENTIALS is not set +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_RCU_CPU_STALL_DETECTOR is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_LATENCYTOP is not set +CONFIG_SYSCTL_SYSCALL_CHECK=y +# CONFIG_DEBUG_PAGEALLOC is not set +CONFIG_NOP_TRACER=y +CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y +CONFIG_RING_BUFFER=y +CONFIG_EVENT_TRACING=y +CONFIG_CONTEXT_SWITCH_TRACER=y +CONFIG_RING_BUFFER_ALLOW_SWAP=y +CONFIG_TRACING=y +CONFIG_TRACING_SUPPORT=y +CONFIG_FTRACE=y +# CONFIG_FUNCTION_TRACER is not set +# CONFIG_IRQSOFF_TRACER is not set +# CONFIG_SCHED_TRACER is not set +# CONFIG_ENABLE_DEFAULT_TRACERS is not set +# CONFIG_BOOT_TRACER is not set +CONFIG_BRANCH_PROFILE_NONE=y +# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set +# CONFIG_PROFILE_ALL_BRANCHES is not set +# CONFIG_STACK_TRACER is not set +# CONFIG_KMEMTRACE is not set +# CONFIG_WORKQUEUE_TRACER is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_RING_BUFFER_BENCHMARK is not set +# CONFIG_DYNAMIC_DEBUG is not set +# CONFIG_DMA_API_DEBUG is not set +# CONFIG_SAMPLES is not set +CONFIG_HAVE_ARCH_KGDB=y +# CONFIG_KGDB is not set +# CONFIG_PPC_DISABLE_WERROR is not set +CONFIG_PPC_WERROR=y +CONFIG_PRINT_STACK_DEPTH=64 +# CONFIG_DEBUG_STACKOVERFLOW is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_PPC_EMULATED_STATS is not set +# CONFIG_CODE_PATCHING_SELFTEST is not set +# CONFIG_FTR_FIXUP_SELFTEST is not set +# CONFIG_MSI_BITMAP_SELFTEST is not set +# CONFIG_XMON is not set +# CONFIG_IRQSTACKS is not set +# CONFIG_VIRQ_DEBUG is not set +# CONFIG_BDI_SWITCH is not set +CONFIG_PPC_EARLY_DEBUG=y +# CONFIG_PPC_EARLY_DEBUG_LPAR is not set +# CONFIG_PPC_EARLY_DEBUG_G5 is not set +# CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL is not set +# CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE is not set +# CONFIG_PPC_EARLY_DEBUG_MAPLE is not set +# CONFIG_PPC_EARLY_DEBUG_ISERIES is not set +# CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE is not set +# CONFIG_PPC_EARLY_DEBUG_BEAT is not set +CONFIG_PPC_EARLY_DEBUG_44x=y +# CONFIG_PPC_EARLY_DEBUG_40x is not set +# CONFIG_PPC_EARLY_DEBUG_CPM is not set +# CONFIG_PPC_EARLY_DEBUG_USBGECKO is not set +CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW=0x40000200 +CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH=0x1 + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set +# CONFIG_SECURITYFS is not set +# CONFIG_DEFAULT_SECURITY_SELINUX is not set +# CONFIG_DEFAULT_SECURITY_SMACK is not set +# CONFIG_DEFAULT_SECURITY_TOMOYO is not set +CONFIG_DEFAULT_SECURITY_DAC=y +CONFIG_DEFAULT_SECURITY="" +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y +CONFIG_CRYPTO_AEAD2=y +CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_BLKCIPHER2=y +CONFIG_CRYPTO_HASH=y +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG2=y +CONFIG_CRYPTO_PCOMP=y +CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +CONFIG_CRYPTO_WORKQUEUE=y +# CONFIG_CRYPTO_CRYPTD is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +CONFIG_CRYPTO_ECB=y +# CONFIG_CRYPTO_LRW is not set +CONFIG_CRYPTO_PCBC=y +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_XCBC is not set +# CONFIG_CRYPTO_VMAC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_GHASH is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_RMD128 is not set +# CONFIG_CRYPTO_RMD160 is not set +# CONFIG_CRYPTO_RMD256 is not set +# CONFIG_CRYPTO_RMD320 is not set +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_ZLIB is not set +# CONFIG_CRYPTO_LZO is not set + +# +# Random Number Generation +# +# CONFIG_CRYPTO_ANSI_CPRNG is not set +# CONFIG_CRYPTO_HW is not set +# CONFIG_PPC_CLOCK is not set +# CONFIG_VIRTUALIZATION is not set diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 12980d54465..dad617e2a88 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -988,7 +988,7 @@ CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y # CONFIG_DL2K is not set CONFIG_E1000=y -CONFIG_E1000E=m +CONFIG_E1000E=y # CONFIG_IP1000 is not set # CONFIG_IGB is not set # CONFIG_NS83820 is not set diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 41de3ddc9f2..16a14589bd4 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -804,7 +804,7 @@ CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y # CONFIG_DL2K is not set CONFIG_E1000=y -CONFIG_E1000E=m +CONFIG_E1000E=y # CONFIG_IP1000 is not set # CONFIG_IGB is not set # CONFIG_NS83820 is not set diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index a9b91ed3d4b..2048a6aeea9 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -21,6 +21,7 @@ /* operations for longs and pointers */ #define PPC_LL stringify_in_c(ld) #define PPC_STL stringify_in_c(std) +#define PPC_STLU stringify_in_c(stdu) #define PPC_LCMPI stringify_in_c(cmpdi) #define PPC_LONG stringify_in_c(.llong) #define PPC_LONG_ALIGN stringify_in_c(.balign 8) @@ -44,6 +45,7 @@ /* operations for longs and pointers */ #define PPC_LL stringify_in_c(lwz) #define PPC_STL stringify_in_c(stw) +#define PPC_STLU stringify_in_c(stwu) #define PPC_LCMPI stringify_in_c(cmpwi) #define PPC_LONG stringify_in_c(.long) #define PPC_LONG_ALIGN stringify_in_c(.balign 4) diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 2c15212e170..065c590c991 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -85,12 +85,12 @@ } \ } while (0) -#define __WARN() do { \ +#define __WARN_TAINT(taint) do { \ __asm__ __volatile__( \ "1: twi 31,0,0\n" \ _EMIT_BUG_ENTRY \ : : "i" (__FILE__), "i" (__LINE__), \ - "i" (BUGFLAG_WARNING), \ + "i" (BUGFLAG_TAINT(taint)), \ "i" (sizeof(struct bug_entry))); \ } while (0) @@ -104,7 +104,7 @@ "1: "PPC_TLNEI" %4,0\n" \ _EMIT_BUG_ENTRY \ : : "i" (__FILE__), "i" (__LINE__), \ - "i" (BUGFLAG_WARNING), \ + "i" (BUGFLAG_TAINT(TAINT_WARN)), \ "i" (sizeof(struct bug_entry)), \ "r" (__ret_warn_on)); \ } \ diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 81de6eb3455..725634fc18c 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -12,8 +12,12 @@ #define L1_CACHE_SHIFT 6 #define MAX_COPY_PREFETCH 4 #elif defined(CONFIG_PPC32) -#define L1_CACHE_SHIFT 5 #define MAX_COPY_PREFETCH 4 +#if defined(CONFIG_PPC_47x) +#define L1_CACHE_SHIFT 7 +#else +#define L1_CACHE_SHIFT 5 +#endif #else /* CONFIG_PPC64 */ #define L1_CACHE_SHIFT 7 #endif diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index abb833b0e58..e3cba4e1eb3 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -72,6 +72,7 @@ extern int machine_check_4xx(struct pt_regs *regs); extern int machine_check_440A(struct pt_regs *regs); extern int machine_check_e500(struct pt_regs *regs); extern int machine_check_e200(struct pt_regs *regs); +extern int machine_check_47x(struct pt_regs *regs); /* NOTE WELL: Update identify_cpu() if fields are added or removed! */ struct cpu_spec { @@ -365,6 +366,7 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_440x6 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \ CPU_FTR_INDEXED_DCR) +#define CPU_FTRS_47X (CPU_FTRS_440x6) #define CPU_FTRS_E200 (CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE) @@ -453,6 +455,9 @@ enum { #ifdef CONFIG_44x CPU_FTRS_44X | CPU_FTRS_440x6 | #endif +#ifdef CONFIG_PPC_47x + CPU_FTRS_47X | +#endif #ifdef CONFIG_E200 CPU_FTRS_E200 | #endif diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 6d94d27ed85..a3954e4fcbe 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -10,9 +10,6 @@ struct dma_map_ops; struct device_node; struct dev_archdata { - /* Optional pointer to an OF device node */ - struct device_node *of_node; - /* DMA operations on that device */ struct dma_map_ops *dma_ops; @@ -30,19 +27,8 @@ struct dev_archdata { #endif }; -static inline void dev_archdata_set_node(struct dev_archdata *ad, - struct device_node *np) -{ - ad->of_node = np; -} - -static inline struct device_node * -dev_archdata_get_node(const struct dev_archdata *ad) -{ - return ad->of_node; -} - struct pdev_archdata { + u64 dma_mask; }; #endif /* _ASM_POWERPC_DEVICE_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index f0275818b95..5119b7db314 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -228,6 +228,7 @@ #define H_JOIN 0x298 #define H_VASI_STATE 0x2A4 #define H_ENABLE_CRQ 0x2B0 +#define H_GET_EM_PARMS 0x2B8 #define H_SET_MPP 0x2D0 #define H_GET_MPP 0x2D4 #define MAX_HCALL_OPCODE H_GET_MPP @@ -281,6 +282,7 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); */ #define PLPAR_HCALL9_BUFSIZE 9 long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); /* For hcall instrumentation. One structure per-hcall, per-CPU */ struct hcall_stats { diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 7e06b43720d..a6ca6da1430 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -31,6 +31,10 @@ #define KEXEC_ARCH KEXEC_ARCH_PPC #endif +#define KEXEC_STATE_NONE 0 +#define KEXEC_STATE_IRQS_OFF 1 +#define KEXEC_STATE_REAL_MODE 2 + #ifndef __ASSEMBLY__ #include <linux/cpumask.h> #include <asm/reg.h> diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index 916369575c9..bca8fdcd254 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -26,6 +26,7 @@ enum km_type { KM_SOFTIRQ1, KM_PPC_SYNC_PAGE, KM_PPC_SYNC_ICACHE, + KM_KDB, KM_TYPE_NR }; diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index 81f3b0b5601..6c5547d82bb 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -77,4 +77,14 @@ struct kvm_debug_exit_arch { struct kvm_guest_debug_arch { }; +#define KVM_REG_MASK 0x001f +#define KVM_REG_EXT_MASK 0xffe0 +#define KVM_REG_GPR 0x0000 +#define KVM_REG_FPR 0x0020 +#define KVM_REG_QPR 0x0040 +#define KVM_REG_FQPR 0x0060 + +#define KVM_INTERRUPT_SET -1U +#define KVM_INTERRUPT_UNSET -2U + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index aadf2dd6f84..c5ea4cda34b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -88,6 +88,8 @@ #define BOOK3S_HFLAG_DCBZ32 0x1 #define BOOK3S_HFLAG_SLB 0x2 +#define BOOK3S_HFLAG_PAIRED_SINGLE 0x4 +#define BOOK3S_HFLAG_NATIVE_PS 0x8 #define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ #define RESUME_FLAG_HOST (1<<1) /* Resume host? */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index db7db0a9696..6f74d93725a 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -22,46 +22,47 @@ #include <linux/types.h> #include <linux/kvm_host.h> -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> struct kvmppc_slb { u64 esid; u64 vsid; u64 orige; u64 origv; - bool valid; - bool Ks; - bool Kp; - bool nx; - bool large; /* PTEs are 16MB */ - bool tb; /* 1TB segment */ - bool class; + bool valid : 1; + bool Ks : 1; + bool Kp : 1; + bool nx : 1; + bool large : 1; /* PTEs are 16MB */ + bool tb : 1; /* 1TB segment */ + bool class : 1; }; struct kvmppc_sr { u32 raw; u32 vsid; - bool Ks; - bool Kp; - bool nx; + bool Ks : 1; + bool Kp : 1; + bool nx : 1; + bool valid : 1; }; struct kvmppc_bat { u64 raw; u32 bepi; u32 bepi_mask; - bool vs; - bool vp; u32 brpn; u8 wimg; u8 pp; + bool vs : 1; + bool vp : 1; }; struct kvmppc_sid_map { u64 guest_vsid; u64 guest_esid; u64 host_vsid; - bool valid; + bool valid : 1; }; #define SID_MAP_BITS 9 @@ -70,7 +71,7 @@ struct kvmppc_sid_map { struct kvmppc_vcpu_book3s { struct kvm_vcpu vcpu; - struct kvmppc_book3s_shadow_vcpu shadow_vcpu; + struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct kvmppc_slb slb[64]; struct { @@ -82,9 +83,10 @@ struct kvmppc_vcpu_book3s { struct kvmppc_bat ibat[8]; struct kvmppc_bat dbat[8]; u64 hid[6]; + u64 gqr[8]; int slb_nr; + u32 dsisr; u64 sdr1; - u64 dsisr; u64 hior; u64 msr_mask; u64 vsid_first; @@ -98,15 +100,15 @@ struct kvmppc_vcpu_book3s { #define CONTEXT_GUEST 1 #define CONTEXT_GUEST_END 2 -#define VSID_REAL 0xfffffffffff00000 -#define VSID_REAL_DR 0xffffffffffe00000 -#define VSID_REAL_IR 0xffffffffffd00000 -#define VSID_BAT 0xffffffffffc00000 -#define VSID_PR 0x8000000000000000 +#define VSID_REAL 0x1fffffffffc00000ULL +#define VSID_BAT 0x1fffffffffb00000ULL +#define VSID_REAL_DR 0x2000000000000000ULL +#define VSID_REAL_IR 0x4000000000000000ULL +#define VSID_PR 0x8000000000000000ULL -extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 ea, u64 ea_mask); +extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask); extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask); -extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end); +extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end); extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr); extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu); @@ -114,11 +116,13 @@ extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data); -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); +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_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); +extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); +extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); extern u32 kvmppc_trampoline_lowmem; extern u32 kvmppc_trampoline_enter; @@ -126,6 +130,8 @@ extern void kvmppc_rmcall(ulong srr0, ulong srr1); extern void kvmppc_load_up_fpu(void); extern void kvmppc_load_up_altivec(void); extern void kvmppc_load_up_vsx(void); +extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); +extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { @@ -140,7 +146,108 @@ static inline ulong dsisr(void) } extern void kvm_return_point(void); +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu); + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + if ( num < 14 ) { + to_svcpu(vcpu)->gpr[num] = val; + to_book3s(vcpu)->shadow_vcpu->gpr[num] = val; + } else + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + if ( num < 14 ) + return to_svcpu(vcpu)->gpr[num]; + else + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + to_svcpu(vcpu)->cr = val; + to_book3s(vcpu)->shadow_vcpu->cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + to_svcpu(vcpu)->xer = val; + to_book3s(vcpu)->shadow_vcpu->xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->xer; +} + +static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->ctr = val; +} + +static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->ctr; +} + +static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->lr = val; +} + +static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->lr; +} + +static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->pc = val; +} + +static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->pc; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + ulong pc = kvmppc_get_pc(vcpu); + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + /* Load the instruction manually if it failed to do so in the + * exit path */ + if (svcpu->last_inst == KVM_INST_FETCH_FAILED) + kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false); + + return svcpu->last_inst; +} + +static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->fault_dar; +} + +/* Magic register values loaded into r3 and r4 before the 'sc' assembly + * instruction for the OSI hypercalls */ +#define OSI_SC_MAGIC_R3 0x113724FA +#define OSI_SC_MAGIC_R4 0x77810F9B #define INS_DCBZ 0x7c0007ec +/* Also add subarch specific defines */ + +#ifdef CONFIG_PPC_BOOK3S_32 +#include <asm/kvm_book3s_32.h> +#else +#include <asm/kvm_book3s_64.h> +#endif + #endif /* __ASM_KVM_BOOK3S_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h new file mode 100644 index 00000000000..de604db135f --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_32.h @@ -0,0 +1,42 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOK3S_32_H__ +#define __ASM_KVM_BOOK3S_32_H__ + +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) +{ + return to_book3s(vcpu)->shadow_vcpu; +} + +#define PTE_SIZE 12 +#define VSID_ALL 0 +#define SR_INVALID 0x00000001 /* VSID 1 should always be unused */ +#define SR_KP 0x20000000 +#define PTE_V 0x80000000 +#define PTE_SEC 0x00000040 +#define PTE_M 0x00000010 +#define PTE_R 0x00000100 +#define PTE_C 0x00000080 + +#define SID_SHIFT 28 +#define ESID_MASK 0xf0000000 +#define VSID_MASK 0x00fffffff0000000ULL + +#endif /* __ASM_KVM_BOOK3S_32_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h new file mode 100644 index 00000000000..4cadd612d57 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -0,0 +1,28 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOK3S_64_H__ +#define __ASM_KVM_BOOK3S_64_H__ + +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) +{ + return &get_paca()->shadow_vcpu; +} + +#endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 183461b4840..36fdb3aff30 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -22,7 +22,7 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#ifdef CONFIG_KVM_BOOK3S_HANDLER #include <asm/kvm_asm.h> @@ -55,7 +55,7 @@ kvmppc_resume_\intno: .macro DO_KVM intno .endm -#endif /* CONFIG_KVM_BOOK3S_64_HANDLER */ +#endif /* CONFIG_KVM_BOOK3S_HANDLER */ #else /*__ASSEMBLY__ */ @@ -63,12 +63,33 @@ struct kvmppc_book3s_shadow_vcpu { ulong gpr[14]; u32 cr; u32 xer; + + u32 fault_dsisr; + u32 last_inst; + ulong ctr; + ulong lr; + ulong pc; + ulong shadow_srr1; + ulong fault_dar; + ulong host_r1; ulong host_r2; ulong handler; ulong scratch0; ulong scratch1; ulong vmhandler; + u8 in_guest; + +#ifdef CONFIG_PPC_BOOK3S_32 + u32 sr[16]; /* Guest SRs */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + u8 slb_max; /* highest used guest slb entry */ + struct { + u64 esid; + u64 vsid; + } slb[64]; /* guest SLB */ +#endif }; #endif /*__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h new file mode 100644 index 00000000000..9c9ba3d59b1 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -0,0 +1,96 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOKE_H__ +#define __ASM_KVM_BOOKE_H__ + +#include <linux/types.h> +#include <linux/kvm_host.h> + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.xer; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.last_inst; +} + +static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.ctr = val; +} + +static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.ctr; +} + +static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.lr = val; +} + +static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.lr; +} + +static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.pc = val; +} + +static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pc; +} + +static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault_dear; +} + +#endif /* __ASM_KVM_BOOKE_H__ */ diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h new file mode 100644 index 00000000000..94f05de9ad0 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_fpu.h @@ -0,0 +1,85 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright Novell Inc. 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_FPU_H__ +#define __ASM_KVM_FPU_H__ + +#include <linux/types.h> + +extern void fps_fres(struct thread_struct *t, u32 *dst, u32 *src1); +extern void fps_frsqrte(struct thread_struct *t, u32 *dst, u32 *src1); +extern void fps_fsqrts(struct thread_struct *t, u32 *dst, u32 *src1); + +extern void fps_fadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fdivs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fmuls(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); + +extern void fps_fmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fnmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fnmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fsel(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); + +#define FPD_ONE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1); +#define FPD_TWO_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1, u64 *src2); +#define FPD_THREE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1, u64 *src2, u64 *src3); + +extern void fpd_fcmpu(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2); +extern void fpd_fcmpo(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2); + +FPD_ONE_IN(fsqrts) +FPD_ONE_IN(frsqrtes) +FPD_ONE_IN(fres) +FPD_ONE_IN(frsp) +FPD_ONE_IN(fctiw) +FPD_ONE_IN(fctiwz) +FPD_ONE_IN(fsqrt) +FPD_ONE_IN(fre) +FPD_ONE_IN(frsqrte) +FPD_ONE_IN(fneg) +FPD_ONE_IN(fabs) +FPD_TWO_IN(fadds) +FPD_TWO_IN(fsubs) +FPD_TWO_IN(fdivs) +FPD_TWO_IN(fmuls) +FPD_TWO_IN(fcpsgn) +FPD_TWO_IN(fdiv) +FPD_TWO_IN(fadd) +FPD_TWO_IN(fmul) +FPD_TWO_IN(fsub) +FPD_THREE_IN(fmsubs) +FPD_THREE_IN(fmadds) +FPD_THREE_IN(fnmsubs) +FPD_THREE_IN(fnmadds) +FPD_THREE_IN(fsel) +FPD_THREE_IN(fmsub) +FPD_THREE_IN(fmadd) +FPD_THREE_IN(fnmsub) +FPD_THREE_IN(fnmadd) + +#endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 5e5bae7e152..0c9ad869dec 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -66,7 +66,7 @@ struct kvm_vcpu_stat { u32 dec_exits; u32 ext_intr_exits; u32 halt_wakeup; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S u32 pf_storage; u32 pf_instruc; u32 sp_storage; @@ -124,12 +124,12 @@ struct kvm_arch { }; struct kvmppc_pte { - u64 eaddr; + ulong eaddr; u64 vpage; - u64 raddr; - bool may_read; - bool may_write; - bool may_execute; + ulong raddr; + bool may_read : 1; + bool may_write : 1; + bool may_execute : 1; }; struct kvmppc_mmu { @@ -145,7 +145,7 @@ struct kvmppc_mmu { int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data); void (*reset_msr)(struct kvm_vcpu *vcpu); void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large); - int (*esid_to_vsid)(struct kvm_vcpu *vcpu, u64 esid, u64 *vsid); + int (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); u64 (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data); bool (*is_dcbz32)(struct kvm_vcpu *vcpu); }; @@ -160,7 +160,7 @@ struct hpte_cache { struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S ulong host_msr; ulong host_r2; void *host_retip; @@ -175,7 +175,7 @@ struct kvm_vcpu_arch { ulong gpr[32]; u64 fpr[32]; - u32 fpscr; + u64 fpscr; #ifdef CONFIG_ALTIVEC vector128 vr[32]; @@ -186,19 +186,23 @@ struct kvm_vcpu_arch { u64 vsr[32]; #endif +#ifdef CONFIG_PPC_BOOK3S + /* For Gekko paired singles */ + u32 qpr[32]; +#endif + +#ifdef CONFIG_BOOKE ulong pc; ulong ctr; ulong lr; -#ifdef CONFIG_BOOKE ulong xer; u32 cr; #endif ulong msr; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S ulong shadow_msr; - ulong shadow_srr1; ulong hflags; ulong guest_owned_ext; #endif @@ -253,20 +257,22 @@ struct kvm_vcpu_arch { struct dentry *debugfs_exit_timing; #endif +#ifdef CONFIG_BOOKE u32 last_inst; -#ifdef CONFIG_PPC64 - ulong fault_dsisr; -#endif ulong fault_dear; ulong fault_esr; ulong queued_dear; ulong queued_esr; +#endif gpa_t paddr_accessed; u8 io_gpr; /* GPR used as IO source/target */ u8 mmio_is_bigendian; + u8 mmio_sign_extend; u8 dcr_needed; u8 dcr_is_write; + u8 osi_needed; + u8 osi_enabled; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -275,7 +281,7 @@ struct kvm_vcpu_arch { u64 dec_jiffies; unsigned long pending_exceptions; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S struct hpte_cache hpte_cache[HPTEG_CACHE_NUM]; int hpte_cache_offset; #endif diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index e2642829e43..18d139ec2d2 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -30,6 +30,8 @@ #include <linux/kvm_host.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/kvm_book3s.h> +#else +#include <asm/kvm_booke.h> #endif enum emulation_result { @@ -37,6 +39,7 @@ enum emulation_result { EMULATE_DO_MMIO, /* kvm_run filled with MMIO request */ EMULATE_DO_DCR, /* kvm_run filled with DCR request */ EMULATE_FAIL, /* can't emulate this instruction */ + EMULATE_AGAIN, /* something went wrong. go again */ }; extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -48,8 +51,11 @@ extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_bigendian); +extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, + int is_bigendian); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u32 val, unsigned int bytes, int is_bigendian); + u64 val, unsigned int bytes, int is_bigendian); extern int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu); @@ -63,6 +69,7 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu); +extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index, @@ -88,6 +95,8 @@ 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 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int op, int *advance); @@ -99,81 +108,37 @@ extern void kvmppc_booke_exit(void); extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); -#ifdef CONFIG_PPC_BOOK3S - -/* We assume we're always acting on the current vcpu */ - -static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) -{ - if ( num < 14 ) { - get_paca()->shadow_vcpu.gpr[num] = val; - to_book3s(vcpu)->shadow_vcpu.gpr[num] = val; - } else - vcpu->arch.gpr[num] = val; -} - -static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) -{ - if ( num < 14 ) - return get_paca()->shadow_vcpu.gpr[num]; - else - return vcpu->arch.gpr[num]; -} - -static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) -{ - get_paca()->shadow_vcpu.cr = val; - to_book3s(vcpu)->shadow_vcpu.cr = val; -} - -static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) -{ - return get_paca()->shadow_vcpu.cr; -} - -static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) -{ - get_paca()->shadow_vcpu.xer = val; - to_book3s(vcpu)->shadow_vcpu.xer = val; -} - -static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +/* + * Cuts out inst bits with ordering according to spec. + * That means the leftmost bit is zero. All given bits are included. + */ +static inline u32 kvmppc_get_field(u64 inst, int msb, int lsb) { - return get_paca()->shadow_vcpu.xer; -} + u32 r; + u32 mask; -#else + BUG_ON(msb > lsb); -static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) -{ - vcpu->arch.gpr[num] = val; -} + mask = (1 << (lsb - msb + 1)) - 1; + r = (inst >> (63 - lsb)) & mask; -static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) -{ - return vcpu->arch.gpr[num]; + return r; } -static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +/* + * Replaces inst bits with ordering according to spec. + */ +static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value) { - vcpu->arch.cr = val; -} + u32 r; + u32 mask; -static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.cr; -} + BUG_ON(msb > lsb); -static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) -{ - vcpu->arch.xer = val; -} + mask = ((1 << (lsb - msb + 1)) - 1) << (63 - lsb); + r = (inst & ~mask) | ((value << (63 - lsb)) & mask); -static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.xer; + return r; } -#endif - #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index a062c57696d..19a661b4cb9 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -108,7 +108,7 @@ static inline void* macio_get_drvdata(struct macio_dev *dev) static inline struct device_node *macio_get_of_node(struct macio_dev *mdev) { - return mdev->ofdev.node; + return mdev->ofdev.dev.of_node; } #ifdef CONFIG_PCI diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h index 0372669383a..bf52d704fc4 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/mmu-44x.h @@ -40,7 +40,7 @@ #define PPC44x_TLB_I 0x00000400 /* Caching is inhibited */ #define PPC44x_TLB_M 0x00000200 /* Memory is coherent */ #define PPC44x_TLB_G 0x00000100 /* Memory is guarded */ -#define PPC44x_TLB_E 0x00000080 /* Memory is guarded */ +#define PPC44x_TLB_E 0x00000080 /* Memory is little endian */ #define PPC44x_TLB_PERM_MASK 0x0000003f #define PPC44x_TLB_UX 0x00000020 /* User execution */ @@ -53,6 +53,52 @@ /* Number of TLB entries */ #define PPC44x_TLB_SIZE 64 +/* 47x bits */ +#define PPC47x_MMUCR_TID 0x0000ffff +#define PPC47x_MMUCR_STS 0x00010000 + +/* Page identification fields */ +#define PPC47x_TLB0_EPN_MASK 0xfffff000 /* Effective Page Number */ +#define PPC47x_TLB0_VALID 0x00000800 /* Valid flag */ +#define PPC47x_TLB0_TS 0x00000400 /* Translation address space */ +#define PPC47x_TLB0_4K 0x00000000 +#define PPC47x_TLB0_16K 0x00000010 +#define PPC47x_TLB0_64K 0x00000030 +#define PPC47x_TLB0_1M 0x00000070 +#define PPC47x_TLB0_16M 0x000000f0 +#define PPC47x_TLB0_256M 0x000001f0 +#define PPC47x_TLB0_1G 0x000003f0 +#define PPC47x_TLB0_BOLTED_R 0x00000008 /* tlbre only */ + +/* Translation fields */ +#define PPC47x_TLB1_RPN_MASK 0xfffff000 /* Real Page Number */ +#define PPC47x_TLB1_ERPN_MASK 0x000003ff + +/* Storage attribute and access control fields */ +#define PPC47x_TLB2_ATTR_MASK 0x0003ff80 +#define PPC47x_TLB2_IL1I 0x00020000 /* Memory is guarded */ +#define PPC47x_TLB2_IL1D 0x00010000 /* Memory is guarded */ +#define PPC47x_TLB2_U0 0x00008000 /* User 0 */ +#define PPC47x_TLB2_U1 0x00004000 /* User 1 */ +#define PPC47x_TLB2_U2 0x00002000 /* User 2 */ +#define PPC47x_TLB2_U3 0x00001000 /* User 3 */ +#define PPC47x_TLB2_W 0x00000800 /* Caching is write-through */ +#define PPC47x_TLB2_I 0x00000400 /* Caching is inhibited */ +#define PPC47x_TLB2_M 0x00000200 /* Memory is coherent */ +#define PPC47x_TLB2_G 0x00000100 /* Memory is guarded */ +#define PPC47x_TLB2_E 0x00000080 /* Memory is little endian */ +#define PPC47x_TLB2_PERM_MASK 0x0000003f +#define PPC47x_TLB2_UX 0x00000020 /* User execution */ +#define PPC47x_TLB2_UW 0x00000010 /* User write */ +#define PPC47x_TLB2_UR 0x00000008 /* User read */ +#define PPC47x_TLB2_SX 0x00000004 /* Super execution */ +#define PPC47x_TLB2_SW 0x00000002 /* Super write */ +#define PPC47x_TLB2_SR 0x00000001 /* Super read */ +#define PPC47x_TLB2_U_RWX (PPC47x_TLB2_UX|PPC47x_TLB2_UW|PPC47x_TLB2_UR) +#define PPC47x_TLB2_S_RWX (PPC47x_TLB2_SX|PPC47x_TLB2_SW|PPC47x_TLB2_SR) +#define PPC47x_TLB2_S_RW (PPC47x_TLB2_SW | PPC47x_TLB2_SR) +#define PPC47x_TLB2_IMG (PPC47x_TLB2_I | PPC47x_TLB2_M | PPC47x_TLB2_G) + #ifndef __ASSEMBLY__ extern unsigned int tlb_44x_hwater; @@ -79,12 +125,15 @@ typedef struct { #if (PAGE_SHIFT == 12) #define PPC44x_TLBE_SIZE PPC44x_TLB_4K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_4K #define mmu_virtual_psize MMU_PAGE_4K #elif (PAGE_SHIFT == 14) #define PPC44x_TLBE_SIZE PPC44x_TLB_16K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_16K #define mmu_virtual_psize MMU_PAGE_16K #elif (PAGE_SHIFT == 16) #define PPC44x_TLBE_SIZE PPC44x_TLB_64K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_64K #define mmu_virtual_psize MMU_PAGE_64K #elif (PAGE_SHIFT == 18) #define PPC44x_TLBE_SIZE PPC44x_TLB_256K diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 7ffbb65ff7a..7ebf42ed84a 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -18,6 +18,7 @@ #define MMU_FTR_TYPE_44x ASM_CONST(0x00000008) #define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010) #define MMU_FTR_TYPE_3E ASM_CONST(0x00000020) +#define MMU_FTR_TYPE_47x ASM_CONST(0x00000040) /* * This is individual features diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 26383e0778a..81fb41289d6 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -27,6 +27,8 @@ extern int __init_new_context(void); extern void __destroy_context(int context_id); static inline void mmu_context_init(void) { } #else +extern unsigned long __init_new_context(void); +extern void __destroy_context(unsigned long context_id); extern void mmu_context_init(void); #endif diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 35acac90c8c..aac87cbceb5 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -30,7 +30,7 @@ extern struct pglist_data *node_data[]; */ extern int numa_cpu_lookup_table[]; -extern cpumask_t numa_cpumask_lookup_table[]; +extern cpumask_var_t node_to_cpumask_map[]; #ifdef CONFIG_MEMORY_HOTPLUG extern unsigned long max_pfn; #endif diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h index 61913d9a21a..e000cce8f6d 100644 --- a/arch/powerpc/include/asm/mpic.h +++ b/arch/powerpc/include/asm/mpic.h @@ -463,9 +463,6 @@ extern void mpic_cpu_set_priority(int prio); /* Request IPIs on primary mpic */ extern void mpic_request_ipis(void); -/* Send an IPI (non offseted number 0..3) */ -extern void mpic_send_ipi(unsigned int ipi_no, unsigned int cpu_mask); - /* Send a message (IPI) to a given target (cpu number or MSG_*) */ void smp_mpic_message_pass(int target, int msg); diff --git a/arch/powerpc/include/asm/of_device.h b/arch/powerpc/include/asm/of_device.h index a64debf177d..444e97e2982 100644 --- a/arch/powerpc/include/asm/of_device.h +++ b/arch/powerpc/include/asm/of_device.h @@ -12,9 +12,8 @@ */ struct of_device { - struct device_node *node; /* to be obsoleted */ - u64 dma_mask; /* DMA mask */ struct device dev; /* Generic device interface */ + struct pdev_archdata archdata; }; extern struct of_device *of_device_alloc(struct device_node *np, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index a011603d407..8ce7963ad41 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -23,7 +23,7 @@ #include <asm/page.h> #include <asm/exception-64e.h> #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> #endif register struct paca_struct *local_paca asm("r13"); @@ -82,6 +82,7 @@ struct paca_struct { s16 hw_cpu_id; /* Physical processor number */ u8 cpu_start; /* At startup, processor spins until */ /* this becomes non-zero. */ + u8 kexec_state; /* set when kexec down has irqs off */ #ifdef CONFIG_PPC_STD_MMU_64 struct slb_shadow *slb_shadow_ptr; @@ -136,15 +137,9 @@ struct paca_struct { u64 startpurr; /* PURR/TB value snapshot */ u64 startspurr; /* SPURR value snapshot */ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - struct { - u64 esid; - u64 vsid; - } kvm_slb[64]; /* guest SLB */ +#ifdef CONFIG_KVM_BOOK3S_HANDLER /* We use this to store guest state in */ struct kvmppc_book3s_shadow_vcpu shadow_vcpu; - u8 kvm_slb_max; /* highest used guest slb entry */ - u8 kvm_in_guest; /* are we inside the guest? */ #endif }; diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index 94942d60ddf..1ca1102b4a2 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -19,6 +19,8 @@ static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma) u32 io1, io2; int propsize; int count = 0; + int virq; + for (np = NULL; (np = of_find_compatible_node(np, "parallel", "pnpPNP,400")) != NULL;) { @@ -26,10 +28,13 @@ static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma) if (!prop || propsize > 6*sizeof(u32)) continue; io1 = prop[1]; io2 = prop[2]; - prop = of_get_property(np, "interrupts", NULL); - if (!prop) + + virq = irq_of_parse_and_map(np, 0); + if (virq == NO_IRQ) continue; - if (parport_pc_probe_port(io1, io2, prop[0], autodma, NULL, 0) != NULL) + + if (parport_pc_probe_port(io1, io2, virq, autodma, NULL, 0) + != NULL) count++; } return count; diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 605f5c5398d..292725cec2e 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -11,6 +11,12 @@ #include <linux/cpumask.h> #include <linux/percpu.h> +struct vmemmap_backing { + struct vmemmap_backing *list; + unsigned long phys; + unsigned long virt_addr; +}; + /* * Functions that deal with pagetables that could be at any level of * the table need to be passed an "index_size" so they know how to diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h index 55646adfa84..a7db96f2b5c 100644 --- a/arch/powerpc/include/asm/pgtable-ppc32.h +++ b/arch/powerpc/include/asm/pgtable-ppc32.h @@ -287,7 +287,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) #define pmd_page_vaddr(pmd) \ ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) #define pmd_page(pmd) \ - (mem_map + (pmd_val(pmd) >> PAGE_SHIFT)) + pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) #else #define pmd_page_vaddr(pmd) \ ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 221ba624046..7492fe8ad6e 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -229,6 +229,9 @@ struct thread_struct { unsigned long spefscr; /* SPE & eFP status */ int used_spe; /* set if process has used spe */ #endif /* CONFIG_SPE */ +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + void* kvm_shadow_vcpu; /* KVM internal data */ +#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */ }; #define ARCH_MIN_TASKALIGN 16 diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 9e2d84c06b7..5d8be041622 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -89,6 +89,7 @@ struct pt_regs { #define instruction_pointer(regs) ((regs)->nip) #define user_stack_pointer(regs) ((regs)->gpr[1]) +#define kernel_stack_pointer(regs) ((regs)->gpr[1]) #define regs_return_value(regs) ((regs)->gpr[3]) #ifdef CONFIG_SMP @@ -141,6 +142,69 @@ do { \ #define arch_has_block_step() (!cpu_has_feature(CPU_FTR_601)) #define ARCH_HAS_USER_SINGLE_STEP_INFO +/* + * kprobe-based event tracer support + */ + +#include <linux/stddef.h> +#include <linux/thread_info.h> +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); +#define MAX_REG_OFFSET (offsetof(struct pt_regs, dsisr)) + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset number of the register. + * + * regs_get_register returns the value of a register whose offset from @regs. + * The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + return *(unsigned long *)((unsigned long)regs + offset); +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ + +static inline bool regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 5572e86223f..d62fdf4e504 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -293,10 +293,12 @@ #define HID1_ABE (1<<10) /* 7450 Address Broadcast Enable */ #define HID1_PS (1<<16) /* 750FX PLL selection */ #define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ +#define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ #define SPRN_HID4 0x3F4 /* 970 HID4 */ +#define SPRN_HID4_GEKKO 0x3F3 /* Gekko HID4 */ #define SPRN_HID5 0x3F6 /* 970 HID5 */ #define SPRN_HID6 0x3F9 /* BE HID 6 */ #define HID6_LB (0x0F<<12) /* Concurrent Large Page Modes */ @@ -465,6 +467,14 @@ #define SPRN_VRSAVE 0x100 /* Vector Register Save Register */ #define SPRN_XER 0x001 /* Fixed Point Exception Register */ +#define SPRN_MMCR0_GEKKO 0x3B8 /* Gekko Monitor Mode Control Register 0 */ +#define SPRN_MMCR1_GEKKO 0x3BC /* Gekko Monitor Mode Control Register 1 */ +#define SPRN_PMC1_GEKKO 0x3B9 /* Gekko Performance Monitor Control 1 */ +#define SPRN_PMC2_GEKKO 0x3BA /* Gekko Performance Monitor Control 2 */ +#define SPRN_PMC3_GEKKO 0x3BD /* Gekko Performance Monitor Control 3 */ +#define SPRN_PMC4_GEKKO 0x3BE /* Gekko Performance Monitor Control 4 */ +#define SPRN_WPAR_GEKKO 0x399 /* Gekko Write Pipe Address Register */ + #define SPRN_SCOMC 0x114 /* SCOM Access Control */ #define SPRN_SCOMD 0x115 /* SCOM Access DATA */ @@ -817,6 +827,7 @@ #define PVR_403GC 0x00200200 #define PVR_403GCX 0x00201400 #define PVR_405GP 0x40110000 +#define PVR_476 0x11a52000 #define PVR_STB03XXX 0x40310000 #define PVR_NP405H 0x41410000 #define PVR_NP405L 0x41610000 @@ -853,6 +864,9 @@ #define PVR_8245 0x80811014 #define PVR_8260 PVR_8240 +/* 476 Simulator seems to currently have the PVR of the 602... */ +#define PVR_476_ISS 0x00052000 + /* 64-bit processors */ /* XXX the prefix should be PVR_, we'll do a global sweep to fix it one day */ #define PV_NORTHSTAR 0x0033 diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 414d434a66d..5304a37ba42 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -191,6 +191,10 @@ #define MCSR_DCFP 0x01000000 /* D-Cache Flush Parity Error */ #define MCSR_IMPE 0x00800000 /* Imprecise Machine Check Exception */ +#define PPC47x_MCSR_GPR 0x01000000 /* GPR parity error */ +#define PPC47x_MCSR_FPR 0x00800000 /* FPR parity error */ +#define PPC47x_MCSR_IPR 0x00400000 /* Imprecise Machine Check Exception */ + #ifdef CONFIG_E500 #define MCSR_MCP 0x80000000UL /* Machine Check Input Pin */ #define MCSR_ICPERR 0x40000000UL /* I-Cache Parity Error */ @@ -604,5 +608,25 @@ #define DBCR_JOI 0x00000002 /* JTAG Serial Outbound Int. Enable */ #define DBCR_JII 0x00000001 /* JTAG Serial Inbound Int. Enable */ #endif /* 403GCX */ + +/* Some 476 specific registers */ +#define SPRN_SSPCR 830 +#define SPRN_USPCR 831 +#define SPRN_ISPCR 829 +#define SPRN_MMUBE0 820 +#define MMUBE0_IBE0_SHIFT 24 +#define MMUBE0_IBE1_SHIFT 16 +#define MMUBE0_IBE2_SHIFT 8 +#define MMUBE0_VBE0 0x00000004 +#define MMUBE0_VBE1 0x00000002 +#define MMUBE0_VBE2 0x00000001 +#define SPRN_MMUBE1 821 +#define MMUBE1_IBE3_SHIFT 24 +#define MMUBE1_IBE4_SHIFT 16 +#define MMUBE1_IBE5_SHIFT 8 +#define MMUBE1_VBE3 0x00000004 +#define MMUBE1_VBE4 0x00000002 +#define MMUBE1_VBE5 0x00000001 + #endif /* __ASM_POWERPC_REG_BOOKE_H__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 1d3b270d308..66e237bbe15 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -40,7 +40,7 @@ extern void smp_message_recv(int); DECLARE_PER_CPU(unsigned int, cpu_pvr); #ifdef CONFIG_HOTPLUG_CPU -extern void fixup_irqs(cpumask_t map); +extern void fixup_irqs(const struct cpumask *map); int generic_cpu_disable(void); int generic_cpu_enable(unsigned int cpu); void generic_cpu_die(unsigned int cpu); @@ -68,8 +68,19 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) } #endif -DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); -DECLARE_PER_CPU(cpumask_t, cpu_core_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); + +static inline struct cpumask *cpu_sibling_mask(int cpu) +{ + return per_cpu(cpu_sibling_map, cpu); +} + +static inline struct cpumask *cpu_core_mask(int cpu) +{ + return per_cpu(cpu_core_map, cpu); +} + extern int cpu_to_core_id(int cpu); /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. @@ -93,7 +104,6 @@ void smp_init_pSeries(void); void smp_init_cell(void); void smp_init_celleb(void); void smp_setup_cpu_maps(void); -void smp_setup_cpu_sibling_map(void); extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index aa9d383a1c0..65eb85976a0 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -104,7 +104,7 @@ 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 +#define TIF_MEMDIE 9 /* is terminating due to OOM killer */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8eaec310a25..32adf728072 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -8,6 +8,26 @@ struct device_node; #ifdef CONFIG_NUMA +/* + * Before going off node we want the VM to try and reclaim from the local + * node. It does this if the remote distance is larger than RECLAIM_DISTANCE. + * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of + * 20, we never reclaim and go off node straight away. + * + * To fix this we choose a smaller value of RECLAIM_DISTANCE. + */ +#define RECLAIM_DISTANCE 10 + +/* + * Before going off node we want the VM to try and reclaim from the local + * node. It does this if the remote distance is larger than RECLAIM_DISTANCE. + * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of + * 20, we never reclaim and go off node straight away. + * + * To fix this we choose a smaller value of RECLAIM_DISTANCE. + */ +#define RECLAIM_DISTANCE 10 + #include <asm/mmzone.h> static inline int cpu_to_node(int cpu) @@ -19,7 +39,7 @@ static inline int cpu_to_node(int cpu) #define cpumask_of_node(node) ((node) == -1 ? \ cpu_all_mask : \ - &numa_cpumask_lookup_table[node]) + node_to_cpumask_map[node]) int of_node_to_nid(struct device_node *device); @@ -102,8 +122,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, #ifdef CONFIG_PPC64 #include <asm/smp.h> -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (&per_cpu(cpu_core_map, cpu)) +#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) #endif #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c09138d150d..496cc5b3984 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -50,6 +50,9 @@ #endif #ifdef CONFIG_KVM #include <linux/kvm_host.h> +#ifndef CONFIG_BOOKE +#include <asm/kvm_book3s.h> +#endif #endif #ifdef CONFIG_PPC32 @@ -105,6 +108,9 @@ int main(void) DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe)); #endif /* CONFIG_SPE */ #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu)); +#endif DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags)); @@ -183,6 +189,7 @@ int main(void) #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); + DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr)); DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); @@ -190,33 +197,9 @@ int main(void) DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); #ifdef CONFIG_KVM_BOOK3S_64_HANDLER - DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest)); - DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb)); - DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max)); - DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr)); - DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer)); - DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0])); - DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1])); - DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2])); - DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3])); - DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4])); - DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5])); - DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6])); - DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7])); - DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8])); - DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9])); - DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10])); - DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11])); - DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12])); - DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13])); - DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1)); - DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2)); - DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct, - shadow_vcpu.vmhandler)); - DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct, - shadow_vcpu.scratch0)); - DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct, - shadow_vcpu.scratch1)); + DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu)); + DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb)); + DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max)); #endif #endif /* CONFIG_PPC64 */ @@ -227,8 +210,8 @@ int main(void) /* Interrupt register frame */ DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD); DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE); -#ifdef CONFIG_PPC64 DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); +#ifdef CONFIG_PPC64 /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); @@ -411,9 +394,6 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); - DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); - DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); - DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr)); DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); @@ -421,32 +401,81 @@ int main(void) DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); - 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)); - - /* book3s_64 */ -#ifdef CONFIG_PPC64 - DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); + /* book3s */ +#ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); - DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2)); DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); - DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); + DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - + offsetof(struct kvmppc_vcpu_book3s, vcpu)); + DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr)); + DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer)); + DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr)); + DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr)); + DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc)); + DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0])); + DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1])); + DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2])); + DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3])); + DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4])); + DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5])); + DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6])); + DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7])); + DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8])); + DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9])); + DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10])); + DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11])); + DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12])); + DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13])); + DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1)); + DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2)); + DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu, + vmhandler)); + DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu, + scratch0)); + DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu, + scratch1)); + DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu, + in_guest)); + DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu, + fault_dsisr)); + DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu, + fault_dar)); + DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu, + last_inst)); + DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu, + shadow_srr1)); +#ifdef CONFIG_PPC_BOOK3S_32 + DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr)); +#endif #else DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); -#endif /* CONFIG_PPC64 */ + DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); + DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); + DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); + 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)); +#endif /* CONFIG_PPC_BOOK3S */ #endif #ifdef CONFIG_44x DEFINE(PGD_T_LOG2, PGD_T_LOG2); DEFINE(PTE_T_LOG2, PTE_T_LOG2); #endif +#ifdef CONFIG_FSL_BOOKE + DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam)); + DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0)); + DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1)); + DEFINE(TLBCAM_MAS2, offsetof(struct tlbcam, MAS2)); + DEFINE(TLBCAM_MAS3, offsetof(struct tlbcam, MAS3)); + DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7)); +#endif #ifdef CONFIG_KVM_EXIT_TIMING DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu, diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 8af4949434b..9556be903e9 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1701,6 +1701,35 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_440A, .platform = "ppc440", }, + { /* 476 core */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x11a50000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | + MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476 iss */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00050000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_FPU, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_47x | + MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 6f4613dd05e..8c066d6a8e4 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -162,6 +162,32 @@ static void crash_kexec_prepare_cpus(int cpu) /* Leave the IPI callback set */ } +/* wait for all the CPUs to hit real mode but timeout if they don't come in */ +static void crash_kexec_wait_realmode(int cpu) +{ + unsigned int msecs; + int i; + + msecs = 10000; + for (i=0; i < NR_CPUS && msecs > 0; i++) { + if (i == cpu) + continue; + + while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) { + barrier(); + if (!cpu_possible(i)) { + break; + } + if (!cpu_online(i)) { + break; + } + msecs--; + mdelay(1); + } + } + mb(); +} + /* * This function will be called by secondary cpus or by kexec cpu * if soft-reset is activated to stop some CPUs. @@ -347,10 +373,12 @@ int crash_shutdown_unregister(crash_shutdown_t handler) EXPORT_SYMBOL(crash_shutdown_unregister); static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; +static int crash_shutdown_cpu = -1; static int handle_fault(struct pt_regs *regs) { - longjmp(crash_shutdown_buf, 1); + if (crash_shutdown_cpu == smp_processor_id()) + longjmp(crash_shutdown_buf, 1); return 0; } @@ -375,11 +403,14 @@ void default_machine_crash_shutdown(struct pt_regs *regs) for_each_irq(i) { struct irq_desc *desc = irq_to_desc(i); + if (!desc || !desc->chip || !desc->chip->eoi) + continue; + if (desc->status & IRQ_INPROGRESS) desc->chip->eoi(i); if (!(desc->status & IRQ_DISABLED)) - desc->chip->disable(i); + desc->chip->shutdown(i); } /* @@ -388,6 +419,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) */ old_handler = __debugger_fault_handler; __debugger_fault_handler = handle_fault; + crash_shutdown_cpu = smp_processor_id(); for (i = 0; crash_shutdown_handles[i]; i++) { if (setjmp(crash_shutdown_buf) == 0) { /* @@ -401,6 +433,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) asm volatile("sync; isync"); } } + crash_shutdown_cpu = -1; __debugger_fault_handler = old_handler; /* @@ -412,6 +445,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crash_kexec_prepare_cpus(crashing_cpu); cpu_set(crashing_cpu, cpus_in_crash); crash_kexec_stop_spus(); + crash_kexec_wait_realmode(crashing_cpu); if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 1175a8539e6..ed4aeb96398 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -373,11 +373,13 @@ syscall_exit_cont: bnel- load_dbcr0 #endif #ifdef CONFIG_44x +BEGIN_MMU_FTR_SECTION lis r4,icache_44x_need_flush@ha lwz r5,icache_44x_need_flush@l(r4) cmplwi cr0,r5,0 bne- 2f 1: +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_47x) #endif /* CONFIG_44x */ BEGIN_FTR_SECTION lwarx r7,0,r1 @@ -848,6 +850,9 @@ resume_kernel: /* interrupts are hard-disabled at this point */ restore: #ifdef CONFIG_44x +BEGIN_MMU_FTR_SECTION + b 1f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x) lis r4,icache_44x_need_flush@ha lwz r5,icache_44x_need_flush@l(r4) cmplwi cr0,r5,0 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e3be98ffe2a..3e423fbad6b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -735,8 +735,11 @@ _STATIC(do_hash_page) std r3,_DAR(r1) std r4,_DSISR(r1) - andis. r0,r4,0xa450 /* weird error? */ + andis. r0,r4,0xa410 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ + andis. r0,r4,DSISR_DABRMATCH@h + bne- handle_dabr_fault + BEGIN_FTR_SECTION andis. r0,r4,0x0020 /* Is it a segment table fault? */ bne- do_ste_alloc /* If so handle it */ @@ -823,6 +826,14 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES) bl .raw_local_irq_restore b 11f +/* We have a data breakpoint exception - handle it */ +handle_dabr_fault: + ld r4,_DAR(r1) + ld r5,_DSISR(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_dabr + b .ret_from_except_lite + /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: ENABLE_INTS diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index e025e89fe93..98c4b29a56f 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -33,6 +33,7 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/bug.h> +#include <asm/kvm_book3s_asm.h> /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ @@ -303,6 +304,7 @@ __secondary_hold_acknowledge: */ #define EXCEPTION(n, label, hdlr, xfer) \ . = n; \ + DO_KVM n; \ label: \ EXCEPTION_PROLOG; \ addi r3,r1,STACK_FRAME_OVERHEAD; \ @@ -358,6 +360,7 @@ i##n: \ * -- paulus. */ . = 0x200 + DO_KVM 0x200 mtspr SPRN_SPRG_SCRATCH0,r10 mtspr SPRN_SPRG_SCRATCH1,r11 mfcr r10 @@ -381,6 +384,7 @@ i##n: \ /* Data access exception. */ . = 0x300 + DO_KVM 0x300 DataAccess: EXCEPTION_PROLOG mfspr r10,SPRN_DSISR @@ -397,6 +401,7 @@ DataAccess: /* Instruction access exception. */ . = 0x400 + DO_KVM 0x400 InstructionAccess: EXCEPTION_PROLOG andis. r0,r9,0x4000 /* no pte found? */ @@ -413,6 +418,7 @@ InstructionAccess: /* Alignment exception */ . = 0x600 + DO_KVM 0x600 Alignment: EXCEPTION_PROLOG mfspr r4,SPRN_DAR @@ -427,6 +433,7 @@ Alignment: /* Floating-point unavailable */ . = 0x800 + DO_KVM 0x800 FPUnavailable: BEGIN_FTR_SECTION /* @@ -450,6 +457,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) /* System call */ . = 0xc00 + DO_KVM 0xc00 SystemCall: EXCEPTION_PROLOG EXC_XFER_EE_LITE(0xc00, DoSyscall) @@ -467,9 +475,11 @@ SystemCall: * by executing an altivec instruction. */ . = 0xf00 + DO_KVM 0xf00 b PerformanceMonitor . = 0xf20 + DO_KVM 0xf20 b AltiVecUnavailable /* @@ -882,6 +892,10 @@ __secondary_start: RFI #endif /* CONFIG_SMP */ +#ifdef CONFIG_KVM_BOOK3S_HANDLER +#include "../kvm/book3s_rmhandlers.S" +#endif + /* * Those generic dummy functions are kept for CPUs not * included in CONFIG_6xx diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 711368b993f..5ab484ef06a 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -37,6 +37,7 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/synch.h> #include "head_booke.h" @@ -69,165 +70,7 @@ _ENTRY(_start); mr r27,r7 li r24,0 /* CPU number */ -/* - * In case the firmware didn't do it, we apply some workarounds - * that are good for all 440 core variants here - */ - mfspr r3,SPRN_CCR0 - rlwinm r3,r3,0,0,27 /* disable icache prefetch */ - isync - mtspr SPRN_CCR0,r3 - isync - sync - -/* - * Set up the initial MMU state - * - * We are still executing code at the virtual address - * mappings set by the firmware for the base of RAM. - * - * We first invalidate all TLB entries but the one - * we are running from. We then load the KERNELBASE - * mappings so we can begin to use kernel addresses - * natively and so the interrupt vector locations are - * permanently pinned (necessary since Book E - * implementations always have translation enabled). - * - * TODO: Use the known TLB entry we are running from to - * determine which physical region we are located - * in. This can be used to determine where in RAM - * (on a shared CPU system) or PCI memory space - * (on a DRAMless system) we are located. - * For now, we assume a perfect world which means - * we are located at the base of DRAM (physical 0). - */ - -/* - * Search TLB for entry that we are currently using. - * Invalidate all entries but the one we are using. - */ - /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */ - mfspr r3,SPRN_PID /* Get PID */ - mfmsr r4 /* Get MSR */ - andi. r4,r4,MSR_IS@l /* TS=1? */ - beq wmmucr /* If not, leave STS=0 */ - oris r3,r3,PPC44x_MMUCR_STS@h /* Set STS=1 */ -wmmucr: mtspr SPRN_MMUCR,r3 /* Put MMUCR */ - sync - - bl invstr /* Find our address */ -invstr: mflr r5 /* Make it accessible */ - tlbsx r23,0,r5 /* Find entry we are in */ - li r4,0 /* Start at TLB entry 0 */ - li r3,0 /* Set PAGEID inval value */ -1: cmpw r23,r4 /* Is this our entry? */ - beq skpinv /* If so, skip the inval */ - tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ -skpinv: addi r4,r4,1 /* Increment */ - cmpwi r4,64 /* Are we done? */ - bne 1b /* If not, repeat */ - isync /* If so, context change */ - -/* - * Configure and load pinned entry into TLB slot 63. - */ - - lis r3,PAGE_OFFSET@h - ori r3,r3,PAGE_OFFSET@l - - /* Kernel is at the base of RAM */ - li r4, 0 /* Load the kernel physical address */ - - /* Load the kernel PID = 0 */ - li r0,0 - mtspr SPRN_PID,r0 - sync - - /* Initialize MMUCR */ - li r5,0 - mtspr SPRN_MMUCR,r5 - sync - - /* pageid fields */ - clrrwi r3,r3,10 /* Mask off the effective page number */ - ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M - - /* xlat fields */ - clrrwi r4,r4,10 /* Mask off the real page number */ - /* ERPN is 0 for first 4GB page */ - - /* attrib fields */ - /* Added guarded bit to protect against speculative loads/stores */ - li r5,0 - ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) - - li r0,63 /* TLB slot 63 */ - - tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */ - tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */ - tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */ - - /* Force context change */ - mfmsr r0 - mtspr SPRN_SRR1, r0 - lis r0,3f@h - ori r0,r0,3f@l - mtspr SPRN_SRR0,r0 - sync - rfi - - /* If necessary, invalidate original entry we used */ -3: cmpwi r23,63 - beq 4f - li r6,0 - tlbwe r6,r23,PPC44x_TLB_PAGEID - isync - -4: -#ifdef CONFIG_PPC_EARLY_DEBUG_44x - /* Add UART mapping for early debug. */ - - /* pageid fields */ - lis r3,PPC44x_EARLY_DEBUG_VIRTADDR@h - ori r3,r3,PPC44x_TLB_VALID|PPC44x_TLB_TS|PPC44x_TLB_64K - - /* xlat fields */ - lis r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW@h - ori r4,r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH - - /* attrib fields */ - li r5,(PPC44x_TLB_SW|PPC44x_TLB_SR|PPC44x_TLB_I|PPC44x_TLB_G) - li r0,62 /* TLB slot 0 */ - - tlbwe r3,r0,PPC44x_TLB_PAGEID - tlbwe r4,r0,PPC44x_TLB_XLAT - tlbwe r5,r0,PPC44x_TLB_ATTRIB - - /* Force context change */ - isync -#endif /* CONFIG_PPC_EARLY_DEBUG_44x */ - - /* Establish the interrupt vector offsets */ - SET_IVOR(0, CriticalInput); - SET_IVOR(1, MachineCheck); - SET_IVOR(2, DataStorage); - SET_IVOR(3, InstructionStorage); - SET_IVOR(4, ExternalInput); - SET_IVOR(5, Alignment); - SET_IVOR(6, Program); - SET_IVOR(7, FloatingPointUnavailable); - SET_IVOR(8, SystemCall); - SET_IVOR(9, AuxillaryProcessorUnavailable); - SET_IVOR(10, Decrementer); - SET_IVOR(11, FixedIntervalTimer); - SET_IVOR(12, WatchdogTimer); - SET_IVOR(13, DataTLBError); - SET_IVOR(14, InstructionTLBError); - SET_IVOR(15, DebugCrit); - - /* Establish the interrupt vector base */ - lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */ - mtspr SPRN_IVPR,r4 + bl init_cpu_state /* * This is where the main kernel code starts. @@ -349,7 +192,7 @@ interrupt_base: #endif /* Data TLB Error Interrupt */ - START_EXCEPTION(DataTLBError) + START_EXCEPTION(DataTLBError44x) mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ mtspr SPRN_SPRG_WSCRATCH1, r11 mtspr SPRN_SPRG_WSCRATCH2, r12 @@ -440,7 +283,7 @@ tlb_44x_patch_hwater_D: mfspr r10,SPRN_DEAR /* Jump to common tlb load */ - b finish_tlb_load + b finish_tlb_load_44x 2: /* The bailout. Restore registers to pre-exception conditions @@ -460,7 +303,7 @@ tlb_44x_patch_hwater_D: * information from different registers and bailout * to a different point. */ - START_EXCEPTION(InstructionTLBError) + START_EXCEPTION(InstructionTLBError44x) mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ mtspr SPRN_SPRG_WSCRATCH1, r11 mtspr SPRN_SPRG_WSCRATCH2, r12 @@ -536,7 +379,7 @@ tlb_44x_patch_hwater_I: mfspr r10,SPRN_SRR0 /* Jump to common TLB load point */ - b finish_tlb_load + b finish_tlb_load_44x 2: /* The bailout. Restore registers to pre-exception conditions @@ -550,15 +393,7 @@ tlb_44x_patch_hwater_I: mfspr r10, SPRN_SPRG_RSCRATCH0 b InstructionStorage - /* Debug Interrupt */ - DEBUG_CRIT_EXCEPTION - -/* - * Local functions - */ - /* - * Both the instruction and data TLB miss get to this * point to load the TLB. * r10 - EA of fault @@ -568,7 +403,7 @@ tlb_44x_patch_hwater_I: * MMUCR - loaded with proper value when we get here * Upon exit, we reload everything and RFI. */ -finish_tlb_load: +finish_tlb_load_44x: /* Combine RPN & ERPN an write WS 0 */ rlwimi r11,r12,0,0,31-PAGE_SHIFT tlbwe r11,r13,PPC44x_TLB_XLAT @@ -601,6 +436,227 @@ finish_tlb_load: mfspr r10, SPRN_SPRG_RSCRATCH0 rfi /* Force context change */ +/* TLB error interrupts for 476 + */ +#ifdef CONFIG_PPC_47x + START_EXCEPTION(DataTLBError47x) + mtspr SPRN_SPRG_WSCRATCH0,r10 /* Save some working registers */ + mtspr SPRN_SPRG_WSCRATCH1,r11 + mtspr SPRN_SPRG_WSCRATCH2,r12 + mtspr SPRN_SPRG_WSCRATCH3,r13 + mfcr r11 + mtspr SPRN_SPRG_WSCRATCH4,r11 + mfspr r10,SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11,PAGE_OFFSET@h + cmplw cr0,r10,r11 + blt+ 3f + lis r11,swapper_pg_dir@h + ori r11,r11, swapper_pg_dir@l + li r12,0 /* MMUCR = 0 */ + b 4f + + /* Get the PGD for the current thread and setup MMUCR */ +3: mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + mfspr r12,SPRN_PID /* Get PID */ +4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */ + + /* Mask of required permission bits. Note that while we + * do copy ESR:ST to _PAGE_RW position as trying to write + * to an RO page is pretty common, we don't do it with + * _PAGE_DIRTY. We could do it, but it's a fairly rare + * event so I'd rather take the overhead when it happens + * rather than adding an instruction here. We should measure + * whether the whole thing is worth it in the first place + * as we could avoid loading SPRN_ESR completely in the first + * place... + * + * TODO: Is it worth doing that mfspr & rlwimi in the first + * place or can we save a couple of instructions here ? + */ + mfspr r12,SPRN_ESR + li r13,_PAGE_PRESENT|_PAGE_ACCESSED + rlwimi r13,r12,10,30,30 + + /* Load the PTE */ + /* Compute pgdir/pmd offset */ + rlwinm r12,r10,PPC44x_PGD_OFF_SHIFT,PPC44x_PGD_OFF_MASK_BIT,29 + lwzx r11,r12,r11 /* Get pgd/pmd entry */ + + /* Word 0 is EPN,V,TS,DSIZ */ + li r12,PPC47x_TLB0_VALID | PPC47x_TLBE_SIZE + rlwimi r10,r12,0,32-PAGE_SHIFT,31 /* Insert valid and page size*/ + li r12,0 + tlbwe r10,r12,0 + + /* XXX can we do better ? Need to make sure tlbwe has established + * latch V bit in MMUCR0 before the PTE is loaded further down */ +#ifdef CONFIG_SMP + isync +#endif + + rlwinm. r12,r11,0,0,20 /* Extract pt base address */ + /* Compute pte address */ + rlwimi r12,r10,PPC44x_PTE_ADD_SHIFT,PPC44x_PTE_ADD_MASK_BIT,28 + beq 2f /* Bail if no table */ + lwz r11,0(r12) /* Get high word of pte entry */ + + /* XXX can we do better ? maybe insert a known 0 bit from r11 into the + * bottom of r12 to create a data dependency... We can also use r10 + * as destination nowadays + */ +#ifdef CONFIG_SMP + lwsync +#endif + lwz r12,4(r12) /* Get low word of pte entry */ + + andc. r13,r13,r12 /* Check permission */ + + /* Jump to common tlb load */ + beq finish_tlb_load_47x + +2: /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11,SPRN_SPRG_RSCRATCH4 + mtcr r11 + mfspr r13,SPRN_SPRG_RSCRATCH3 + mfspr r12,SPRN_SPRG_RSCRATCH2 + mfspr r11,SPRN_SPRG_RSCRATCH1 + mfspr r10,SPRN_SPRG_RSCRATCH0 + b DataStorage + + /* Instruction TLB Error Interrupt */ + /* + * Nearly the same as above, except we get our + * information from different registers and bailout + * to a different point. + */ + START_EXCEPTION(InstructionTLBError47x) + mtspr SPRN_SPRG_WSCRATCH0,r10 /* Save some working registers */ + mtspr SPRN_SPRG_WSCRATCH1,r11 + mtspr SPRN_SPRG_WSCRATCH2,r12 + mtspr SPRN_SPRG_WSCRATCH3,r13 + mfcr r11 + mtspr SPRN_SPRG_WSCRATCH4,r11 + mfspr r10,SPRN_SRR0 /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11,PAGE_OFFSET@h + cmplw cr0,r10,r11 + blt+ 3f + lis r11,swapper_pg_dir@h + ori r11,r11, swapper_pg_dir@l + li r12,0 /* MMUCR = 0 */ + b 4f + + /* Get the PGD for the current thread and setup MMUCR */ +3: mfspr r11,SPRN_SPRG_THREAD + lwz r11,PGDIR(r11) + mfspr r12,SPRN_PID /* Get PID */ +4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */ + + /* Make up the required permissions */ + li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC + + /* Load PTE */ + /* Compute pgdir/pmd offset */ + rlwinm r12,r10,PPC44x_PGD_OFF_SHIFT,PPC44x_PGD_OFF_MASK_BIT,29 + lwzx r11,r12,r11 /* Get pgd/pmd entry */ + + /* Word 0 is EPN,V,TS,DSIZ */ + li r12,PPC47x_TLB0_VALID | PPC47x_TLBE_SIZE + rlwimi r10,r12,0,32-PAGE_SHIFT,31 /* Insert valid and page size*/ + li r12,0 + tlbwe r10,r12,0 + + /* XXX can we do better ? Need to make sure tlbwe has established + * latch V bit in MMUCR0 before the PTE is loaded further down */ +#ifdef CONFIG_SMP + isync +#endif + + rlwinm. r12,r11,0,0,20 /* Extract pt base address */ + /* Compute pte address */ + rlwimi r12,r10,PPC44x_PTE_ADD_SHIFT,PPC44x_PTE_ADD_MASK_BIT,28 + beq 2f /* Bail if no table */ + + lwz r11,0(r12) /* Get high word of pte entry */ + /* XXX can we do better ? maybe insert a known 0 bit from r11 into the + * bottom of r12 to create a data dependency... We can also use r10 + * as destination nowadays + */ +#ifdef CONFIG_SMP + lwsync +#endif + lwz r12,4(r12) /* Get low word of pte entry */ + + andc. r13,r13,r12 /* Check permission */ + + /* Jump to common TLB load point */ + beq finish_tlb_load_47x + +2: /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG_RSCRATCH4 + mtcr r11 + mfspr r13, SPRN_SPRG_RSCRATCH3 + mfspr r12, SPRN_SPRG_RSCRATCH2 + mfspr r11, SPRN_SPRG_RSCRATCH1 + mfspr r10, SPRN_SPRG_RSCRATCH0 + b InstructionStorage + +/* + * Both the instruction and data TLB miss get to this + * point to load the TLB. + * r10 - free to use + * r11 - PTE high word value + * r12 - PTE low word value + * r13 - free to use + * MMUCR - loaded with proper value when we get here + * Upon exit, we reload everything and RFI. + */ +finish_tlb_load_47x: + /* Combine RPN & ERPN an write WS 1 */ + rlwimi r11,r12,0,0,31-PAGE_SHIFT + tlbwe r11,r13,1 + + /* And make up word 2 */ + li r10,0xf85 /* Mask to apply from PTE */ + rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */ + and r11,r12,r10 /* Mask PTE bits to keep */ + andi. r10,r12,_PAGE_USER /* User page ? */ + beq 1f /* nope, leave U bits empty */ + rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ +1: tlbwe r11,r13,2 + + /* Done...restore registers and get out of here. + */ + mfspr r11, SPRN_SPRG_RSCRATCH4 + mtcr r11 + mfspr r13, SPRN_SPRG_RSCRATCH3 + mfspr r12, SPRN_SPRG_RSCRATCH2 + mfspr r11, SPRN_SPRG_RSCRATCH1 + mfspr r10, SPRN_SPRG_RSCRATCH0 + rfi + +#endif /* CONFIG_PPC_47x */ + + /* Debug Interrupt */ + /* + * This statement needs to exist at the end of the IVPR + * definition just in case you end up taking a debug + * exception within another exception. + */ + DEBUG_CRIT_EXCEPTION + /* * Global functions */ @@ -647,6 +703,428 @@ _GLOBAL(set_context) blr /* + * Init CPU state. This is called at boot time or for secondary CPUs + * to setup initial TLB entries, setup IVORs, etc... + * + */ +_GLOBAL(init_cpu_state) + mflr r22 +#ifdef CONFIG_PPC_47x + /* We use the PVR to differenciate 44x cores from 476 */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmplwi cr0,r3,PVR_476@h + beq head_start_47x + cmplwi cr0,r3,PVR_476_ISS@h + beq head_start_47x +#endif /* CONFIG_PPC_47x */ + +/* + * In case the firmware didn't do it, we apply some workarounds + * that are good for all 440 core variants here + */ + mfspr r3,SPRN_CCR0 + rlwinm r3,r3,0,0,27 /* disable icache prefetch */ + isync + mtspr SPRN_CCR0,r3 + isync + sync + +/* + * Set up the initial MMU state for 44x + * + * We are still executing code at the virtual address + * mappings set by the firmware for the base of RAM. + * + * We first invalidate all TLB entries but the one + * we are running from. We then load the KERNELBASE + * mappings so we can begin to use kernel addresses + * natively and so the interrupt vector locations are + * permanently pinned (necessary since Book E + * implementations always have translation enabled). + * + * TODO: Use the known TLB entry we are running from to + * determine which physical region we are located + * in. This can be used to determine where in RAM + * (on a shared CPU system) or PCI memory space + * (on a DRAMless system) we are located. + * For now, we assume a perfect world which means + * we are located at the base of DRAM (physical 0). + */ + +/* + * Search TLB for entry that we are currently using. + * Invalidate all entries but the one we are using. + */ + /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */ + mfspr r3,SPRN_PID /* Get PID */ + mfmsr r4 /* Get MSR */ + andi. r4,r4,MSR_IS@l /* TS=1? */ + beq wmmucr /* If not, leave STS=0 */ + oris r3,r3,PPC44x_MMUCR_STS@h /* Set STS=1 */ +wmmucr: mtspr SPRN_MMUCR,r3 /* Put MMUCR */ + sync + + bl invstr /* Find our address */ +invstr: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skpinv /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skpinv: addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync /* If so, context change */ + +/* + * Configure and load pinned entry into TLB slot 63. + */ + + lis r3,PAGE_OFFSET@h + ori r3,r3,PAGE_OFFSET@l + + /* Kernel is at the base of RAM */ + li r4, 0 /* Load the kernel physical address */ + + /* Load the kernel PID = 0 */ + li r0,0 + mtspr SPRN_PID,r0 + sync + + /* Initialize MMUCR */ + li r5,0 + mtspr SPRN_MMUCR,r5 + sync + + /* pageid fields */ + clrrwi r3,r3,10 /* Mask off the effective page number */ + ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M + + /* xlat fields */ + clrrwi r4,r4,10 /* Mask off the real page number */ + /* ERPN is 0 for first 4GB page */ + + /* attrib fields */ + /* Added guarded bit to protect against speculative loads/stores */ + li r5,0 + ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + li r0,63 /* TLB slot 63 */ + + tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */ + tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */ + tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */ + + /* Force context change */ + mfmsr r0 + mtspr SPRN_SRR1, r0 + lis r0,3f@h + ori r0,r0,3f@l + mtspr SPRN_SRR0,r0 + sync + rfi + + /* If necessary, invalidate original entry we used */ +3: cmpwi r23,63 + beq 4f + li r6,0 + tlbwe r6,r23,PPC44x_TLB_PAGEID + isync + +4: +#ifdef CONFIG_PPC_EARLY_DEBUG_44x + /* Add UART mapping for early debug. */ + + /* pageid fields */ + lis r3,PPC44x_EARLY_DEBUG_VIRTADDR@h + ori r3,r3,PPC44x_TLB_VALID|PPC44x_TLB_TS|PPC44x_TLB_64K + + /* xlat fields */ + lis r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW@h + ori r4,r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH + + /* attrib fields */ + li r5,(PPC44x_TLB_SW|PPC44x_TLB_SR|PPC44x_TLB_I|PPC44x_TLB_G) + li r0,62 /* TLB slot 0 */ + + tlbwe r3,r0,PPC44x_TLB_PAGEID + tlbwe r4,r0,PPC44x_TLB_XLAT + tlbwe r5,r0,PPC44x_TLB_ATTRIB + + /* Force context change */ + isync +#endif /* CONFIG_PPC_EARLY_DEBUG_44x */ + + /* Establish the interrupt vector offsets */ + SET_IVOR(0, CriticalInput); + SET_IVOR(1, MachineCheck); + SET_IVOR(2, DataStorage); + SET_IVOR(3, InstructionStorage); + SET_IVOR(4, ExternalInput); + SET_IVOR(5, Alignment); + SET_IVOR(6, Program); + SET_IVOR(7, FloatingPointUnavailable); + SET_IVOR(8, SystemCall); + SET_IVOR(9, AuxillaryProcessorUnavailable); + SET_IVOR(10, Decrementer); + SET_IVOR(11, FixedIntervalTimer); + SET_IVOR(12, WatchdogTimer); + SET_IVOR(13, DataTLBError44x); + SET_IVOR(14, InstructionTLBError44x); + SET_IVOR(15, DebugCrit); + + b head_start_common + + +#ifdef CONFIG_PPC_47x + +#ifdef CONFIG_SMP + +/* Entry point for secondary 47x processors */ +_GLOBAL(start_secondary_47x) + mr r24,r3 /* CPU number */ + + bl init_cpu_state + + /* Now we need to bolt the rest of kernel memory which + * is done in C code. We must be careful because our task + * struct or our stack can (and will probably) be out + * of reach of the initial 256M TLB entry, so we use a + * small temporary stack in .bss for that. This works + * because only one CPU at a time can be in this code + */ + lis r1,temp_boot_stack@h + ori r1,r1,temp_boot_stack@l + addi r1,r1,1024-STACK_FRAME_OVERHEAD + li r0,0 + stw r0,0(r1) + bl mmu_init_secondary + + /* Now we can get our task struct and real stack pointer */ + + /* Get current_thread_info and current */ + lis r1,secondary_ti@ha + lwz r1,secondary_ti@l(r1) + lwz r2,TI_TASK(r1) + + /* Current stack pointer */ + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + li r0,0 + stw r0,0(r1) + + /* Kernel stack for exception entry in SPRG3 */ + addi r4,r2,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + + b start_secondary + +#endif /* CONFIG_SMP */ + +/* + * Set up the initial MMU state for 44x + * + * We are still executing code at the virtual address + * mappings set by the firmware for the base of RAM. + */ + +head_start_47x: + /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */ + mfspr r3,SPRN_PID /* Get PID */ + mfmsr r4 /* Get MSR */ + andi. r4,r4,MSR_IS@l /* TS=1? */ + beq 1f /* If not, leave STS=0 */ + oris r3,r3,PPC47x_MMUCR_STS@h /* Set STS=1 */ +1: mtspr SPRN_MMUCR,r3 /* Put MMUCR */ + sync + + /* Find the entry we are running from */ + bl 1f +1: mflr r23 + tlbsx r23,0,r23 + tlbre r24,r23,0 + tlbre r25,r23,1 + tlbre r26,r23,2 + +/* + * Cleanup time + */ + + /* Initialize MMUCR */ + li r5,0 + mtspr SPRN_MMUCR,r5 + sync + +clear_all_utlb_entries: + + #; Set initial values. + + addis r3,0,0x8000 + addi r4,0,0 + addi r5,0,0 + b clear_utlb_entry + + #; Align the loop to speed things up. + + .align 6 + +clear_utlb_entry: + + tlbwe r4,r3,0 + tlbwe r5,r3,1 + tlbwe r5,r3,2 + addis r3,r3,0x2000 + cmpwi r3,0 + bne clear_utlb_entry + addis r3,0,0x8000 + addis r4,r4,0x100 + cmpwi r4,0 + bne clear_utlb_entry + + #; Restore original entry. + + oris r23,r23,0x8000 /* specify the way */ + tlbwe r24,r23,0 + tlbwe r25,r23,1 + tlbwe r26,r23,2 + +/* + * Configure and load pinned entry into TLB for the kernel core + */ + + lis r3,PAGE_OFFSET@h + ori r3,r3,PAGE_OFFSET@l + + /* Kernel is at the base of RAM */ + li r4, 0 /* Load the kernel physical address */ + + /* Load the kernel PID = 0 */ + li r0,0 + mtspr SPRN_PID,r0 + sync + + /* Word 0 */ + clrrwi r3,r3,12 /* Mask off the effective page number */ + ori r3,r3,PPC47x_TLB0_VALID | PPC47x_TLB0_256M + + /* Word 1 */ + clrrwi r4,r4,12 /* Mask off the real page number */ + /* ERPN is 0 for first 4GB page */ + /* Word 2 */ + li r5,0 + ori r5,r5,PPC47x_TLB2_S_RWX +#ifdef CONFIG_SMP + ori r5,r5,PPC47x_TLB2_M +#endif + + /* We write to way 0 and bolted 0 */ + lis r0,0x8800 + tlbwe r3,r0,0 + tlbwe r4,r0,1 + tlbwe r5,r0,2 + +/* + * Configure SSPCR, ISPCR and USPCR for now to search everything, we can fix + * them up later + */ + LOAD_REG_IMMEDIATE(r3, 0x9abcdef0) + mtspr SPRN_SSPCR,r3 + mtspr SPRN_USPCR,r3 + LOAD_REG_IMMEDIATE(r3, 0x12345670) + mtspr SPRN_ISPCR,r3 + + /* Force context change */ + mfmsr r0 + mtspr SPRN_SRR1, r0 + lis r0,3f@h + ori r0,r0,3f@l + mtspr SPRN_SRR0,r0 + sync + rfi + + /* Invalidate original entry we used */ +3: + rlwinm r24,r24,0,21,19 /* clear the "valid" bit */ + tlbwe r24,r23,0 + addi r24,0,0 + tlbwe r24,r23,1 + tlbwe r24,r23,2 + isync /* Clear out the shadow TLB entries */ + +#ifdef CONFIG_PPC_EARLY_DEBUG_44x + /* Add UART mapping for early debug. */ + + /* Word 0 */ + lis r3,PPC44x_EARLY_DEBUG_VIRTADDR@h + ori r3,r3,PPC47x_TLB0_VALID | PPC47x_TLB0_TS | PPC47x_TLB0_1M + + /* Word 1 */ + lis r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW@h + ori r4,r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH + + /* Word 2 */ + li r5,(PPC47x_TLB2_S_RW | PPC47x_TLB2_IMG) + + /* Bolted in way 0, bolt slot 5, we -hope- we don't hit the same + * congruence class as the kernel, we need to make sure of it at + * some point + */ + lis r0,0x8d00 + tlbwe r3,r0,0 + tlbwe r4,r0,1 + tlbwe r5,r0,2 + + /* Force context change */ + isync +#endif /* CONFIG_PPC_EARLY_DEBUG_44x */ + + /* Establish the interrupt vector offsets */ + SET_IVOR(0, CriticalInput); + SET_IVOR(1, MachineCheckA); + SET_IVOR(2, DataStorage); + SET_IVOR(3, InstructionStorage); + SET_IVOR(4, ExternalInput); + SET_IVOR(5, Alignment); + SET_IVOR(6, Program); + SET_IVOR(7, FloatingPointUnavailable); + SET_IVOR(8, SystemCall); + SET_IVOR(9, AuxillaryProcessorUnavailable); + SET_IVOR(10, Decrementer); + SET_IVOR(11, FixedIntervalTimer); + SET_IVOR(12, WatchdogTimer); + SET_IVOR(13, DataTLBError47x); + SET_IVOR(14, InstructionTLBError47x); + SET_IVOR(15, DebugCrit); + + /* We configure icbi to invalidate 128 bytes at a time since the + * current 32-bit kernel code isn't too happy with icache != dcache + * block size + */ + mfspr r3,SPRN_CCR0 + oris r3,r3,0x0020 + mtspr SPRN_CCR0,r3 + isync + +#endif /* CONFIG_PPC_47x */ + +/* + * Here we are back to code that is common between 44x and 47x + * + * We proceed to further kernel initialization and return to the + * main kernel entry + */ +head_start_common: + /* Establish the interrupt vector base */ + lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */ + mtspr SPRN_IVPR,r4 + + addis r22,r22,KERNELBASE@h + mtlr r22 + isync + blr + +/* * We put a few things here that have to be page-aligned. This stuff * goes at the beginning of the data segment, which is page-aligned. */ @@ -671,3 +1149,9 @@ swapper_pg_dir: */ abatron_pteptrs: .space 8 + +#ifdef CONFIG_SMP + .align 12 +temp_boot_stack: + .space 1024 +#endif /* CONFIG_SMP */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index bed9a29ee38..844a44b6447 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -37,7 +37,7 @@ #include <asm/firmware.h> #include <asm/page_64.h> #include <asm/irqflags.h> -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> /* The physical memory is layed out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow @@ -169,7 +169,7 @@ exception_marker: /* KVM trampoline code needs to be close to the interrupt handlers */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include "../kvm/book3s_64_rmhandlers.S" +#include "../kvm/book3s_rmhandlers.S" #endif _GLOBAL(generic_secondary_thread_init) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 3ef743fa5d7..1f1a04b5c2a 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -71,9 +71,6 @@ _ENTRY(_start); * in the first level table, but that would require many changes to the * Linux page directory/table functions that I don't want to do right now. * - * I used to use SPRG2 for a temporary register in the TLB handler, but it - * has since been put to other uses. I now use a hack to save a register - * and the CCR at memory location 0.....Someday I'll fix this..... * -- Dan */ .globl __start @@ -302,8 +299,13 @@ InstructionTLBMiss: DO_8xx_CPU6(0x3f80, r3) mtspr SPRN_M_TW, r10 /* Save a couple of working registers */ mfcr r10 +#ifdef CONFIG_8xx_CPU6 stw r10, 0(r0) stw r11, 4(r0) +#else + mtspr SPRN_DAR, r10 + mtspr SPRN_SPRG2, r11 +#endif mfspr r10, SPRN_SRR0 /* Get effective address of fault */ #ifdef CONFIG_8xx_CPU15 addi r11, r10, 0x1000 @@ -318,12 +320,16 @@ InstructionTLBMiss: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ +#ifdef CONFIG_MODULES + /* Only modules will cause ITLB Misses as we always + * pin the first 8MB of kernel memory */ andi. r11, r10, 0x0800 /* Address >= 0x80000000 */ beq 3f lis r11, swapper_pg_dir@h ori r11, r11, swapper_pg_dir@l rlwimi r10, r11, 0, 2, 19 3: +#endif lwz r11, 0(r10) /* Get the level 1 entry */ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ beq 2f /* If zero, don't try to find a pte */ @@ -339,31 +345,35 @@ InstructionTLBMiss: mfspr r11, SPRN_MD_TWC /* ....and get the pte address */ lwz r10, 0(r11) /* Get the pte */ +#ifdef CONFIG_SWAP andi. r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT cmpwi cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT bne- cr0, 2f - - /* Clear PP lsb, 0x400 */ - rlwinm r10, r10, 0, 22, 20 - +#endif /* The Linux PTE won't go exactly into the MMU TLB. - * Software indicator bits 22 and 28 must be clear. + * Software indicator bits 21 and 28 must be clear. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior * of the MMU. */ li r11, 0x00f0 - rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ + rlwimi r10, r11, 0, 0x07f8 /* Set 24-27, clear 21-23,28 */ DO_8xx_CPU6(0x2d80, r3) mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ - mfspr r10, SPRN_M_TW /* Restore registers */ + /* Restore registers */ +#ifndef CONFIG_8xx_CPU6 + mfspr r10, SPRN_DAR + mtcr r10 + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_SPRG2 +#else lwz r11, 0(r0) mtcr r11 lwz r11, 4(r0) -#ifdef CONFIG_8xx_CPU6 lwz r3, 8(r0) #endif + mfspr r10, SPRN_M_TW rfi 2: mfspr r11, SPRN_SRR1 @@ -373,13 +383,20 @@ InstructionTLBMiss: rlwinm r11, r11, 0, 0xffff mtspr SPRN_SRR1, r11 - mfspr r10, SPRN_M_TW /* Restore registers */ + /* Restore registers */ +#ifndef CONFIG_8xx_CPU6 + mfspr r10, SPRN_DAR + mtcr r10 + li r11, 0x00f0 + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_SPRG2 +#else lwz r11, 0(r0) mtcr r11 lwz r11, 4(r0) -#ifdef CONFIG_8xx_CPU6 lwz r3, 8(r0) #endif + mfspr r10, SPRN_M_TW b InstructionAccess . = 0x1200 @@ -390,8 +407,13 @@ DataStoreTLBMiss: DO_8xx_CPU6(0x3f80, r3) mtspr SPRN_M_TW, r10 /* Save a couple of working registers */ mfcr r10 +#ifdef CONFIG_8xx_CPU6 stw r10, 0(r0) stw r11, 4(r0) +#else + mtspr SPRN_DAR, r10 + mtspr SPRN_SPRG2, r11 +#endif mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ /* If we are faulting a kernel address, we have to use the @@ -438,15 +460,14 @@ DataStoreTLBMiss: * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); * r10 = (r10 & ~PRESENT) | r11; */ +#ifdef CONFIG_SWAP rlwinm r11, r10, 32-5, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT - +#endif /* Honour kernel RO, User NA */ /* 0x200 == Extended encoding, bit 22 */ - /* r11 = (r10 & _PAGE_USER) >> 2 */ - rlwinm r11, r10, 32-2, 0x200 - or r10, r11, r10 + rlwimi r10, r10, 32-2, 0x200 /* Copy USER to bit 22, 0x200 */ /* r11 = (r10 & _PAGE_RW) >> 1 */ rlwinm r11, r10, 32-1, 0x200 or r10, r11, r10 @@ -460,18 +481,24 @@ DataStoreTLBMiss: * of the MMU. */ 2: li r11, 0x00f0 - mtspr SPRN_DAR,r11 /* Tag DAR */ rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ DO_8xx_CPU6(0x3d80, r3) mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ - mfspr r10, SPRN_M_TW /* Restore registers */ + /* Restore registers */ +#ifndef CONFIG_8xx_CPU6 + mfspr r10, SPRN_DAR + mtcr r10 + mtspr SPRN_DAR, r11 /* Tag DAR */ + mfspr r11, SPRN_SPRG2 +#else + mtspr SPRN_DAR, r11 /* Tag DAR */ lwz r11, 0(r0) mtcr r11 lwz r11, 4(r0) -#ifdef CONFIG_8xx_CPU6 lwz r3, 8(r0) #endif + mfspr r10, SPRN_M_TW rfi /* This is an instruction TLB error on the MPC8xx. This could be due @@ -683,9 +710,6 @@ start_here: tophys(r4,r2) addi r4,r4,THREAD /* init task's THREAD */ mtspr SPRN_SPRG_THREAD,r4 - li r3,0 - /* XXX What is that for ? SPRG2 appears otherwise unused on 8xx */ - mtspr SPRN_SPRG2,r3 /* 0 => r1 has kernel sp */ /* stack */ lis r1,init_thread_union@ha diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 50504ae39cb..a0bf158c8b4 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -1,6 +1,7 @@ #ifndef __HEAD_BOOKE_H__ #define __HEAD_BOOKE_H__ +#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */ /* * Macros used for common Book-e exception handling */ @@ -48,6 +49,9 @@ stw r10,0(r11); \ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ stw r0,GPR0(r11); \ + lis r10, STACK_FRAME_REGS_MARKER@ha;/* exception frame marker */ \ + addi r10, r10, STACK_FRAME_REGS_MARKER@l; \ + stw r10, 8(r11); \ SAVE_4GPRS(3, r11); \ SAVE_2GPRS(7, r11) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 72552654799..edd4a57fd29 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -639,6 +639,13 @@ interrupt_base: rlwinm r12,r12,0,16,1 mtspr SPRN_MAS1,r12 + /* Make up the required permissions for kernel code */ +#ifdef CONFIG_PTE_64BIT + li r13,_PAGE_PRESENT | _PAGE_BAP_SX + oris r13,r13,_PAGE_ACCESSED@h +#else + li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC +#endif b 4f /* Get the PGD for the current thread */ @@ -646,15 +653,15 @@ interrupt_base: mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) -4: - /* Make up the required permissions */ + /* Make up the required permissions for user code */ #ifdef CONFIG_PTE_64BIT - li r13,_PAGE_PRESENT | _PAGE_EXEC + li r13,_PAGE_PRESENT | _PAGE_BAP_UX oris r13,r13,_PAGE_ACCESSED@h #else li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC #endif +4: FIND_PTE andc. r13,r13,r11 /* Check permission */ diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 71cf280da18..21266abfbda 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -140,14 +140,14 @@ static struct dma_map_ops ibmebus_dma_ops = { static int ibmebus_match_path(struct device *dev, void *data) { - struct device_node *dn = to_of_device(dev)->node; + struct device_node *dn = to_of_device(dev)->dev.of_node; return (dn->full_name && (strcasecmp((char *)data, dn->full_name) == 0)); } static int ibmebus_match_node(struct device *dev, void *data) { - return to_of_device(dev)->node == data; + return to_of_device(dev)->dev.of_node == data; } static int ibmebus_create_device(struct device_node *dn) @@ -202,7 +202,7 @@ static int ibmebus_create_devices(const struct of_device_id *matches) int ibmebus_register_driver(struct of_platform_driver *drv) { /* If the driver uses devices that ibmebus doesn't know, add them */ - ibmebus_create_devices(drv->match_table); + ibmebus_create_devices(drv->driver.of_match_table); return of_register_driver(drv, &ibmebus_bus_type); } diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ec94f906ea4..d5839179ec7 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -43,20 +43,9 @@ #define DBG(...) static int novmerge; -static int protect4gb = 1; static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int); -static int __init setup_protect4gb(char *str) -{ - if (strcmp(str, "on") == 0) - protect4gb = 1; - else if (strcmp(str, "off") == 0) - protect4gb = 0; - - return 1; -} - static int __init setup_iommu(char *str) { if (!strcmp(str, "novmerge")) @@ -66,7 +55,6 @@ static int __init setup_iommu(char *str) return 1; } -__setup("protect4gb=", setup_protect4gb); __setup("iommu=", setup_iommu); static unsigned long iommu_range_alloc(struct device *dev, diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 066bd31551d..30817d9b20c 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -284,30 +284,33 @@ u64 arch_irq_stat_cpu(unsigned int cpu) } #ifdef CONFIG_HOTPLUG_CPU -void fixup_irqs(cpumask_t map) +void fixup_irqs(const struct cpumask *map) { struct irq_desc *desc; unsigned int irq; static int warned; + cpumask_var_t mask; - for_each_irq(irq) { - cpumask_t mask; + alloc_cpumask_var(&mask, GFP_KERNEL); + for_each_irq(irq) { desc = irq_to_desc(irq); if (desc && desc->status & IRQ_PER_CPU) continue; - cpumask_and(&mask, desc->affinity, &map); - if (any_online_cpu(mask) == NR_CPUS) { + cpumask_and(mask, desc->affinity, map); + if (cpumask_any(mask) >= nr_cpu_ids) { printk("Breaking affinity for irq %i\n", irq); - mask = map; + cpumask_copy(mask, map); } if (desc->chip->set_affinity) - desc->chip->set_affinity(irq, &mask); + desc->chip->set_affinity(irq, mask); else if (desc->action && !(warned++)) printk("Cannot set affinity for irq %i\n", irq); } + free_cpumask_var(mask); + local_irq_enable(); mdelay(1); local_irq_disable(); diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 41bada0298c..82a7b228c81 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -20,6 +20,7 @@ #include <linux/smp.h> #include <linux/signal.h> #include <linux/ptrace.h> +#include <linux/kdebug.h> #include <asm/current.h> #include <asm/processor.h> #include <asm/machdep.h> @@ -115,7 +116,8 @@ void kgdb_roundup_cpus(unsigned long flags) /* KGDB functions to use existing PowerPC64 hooks. */ static int kgdb_debugger(struct pt_regs *regs) { - return kgdb_handle_exception(0, computeSignal(TRAP(regs)), 0, regs); + return !kgdb_handle_exception(1, computeSignal(TRAP(regs)), + DIE_OOPS, regs); } static int kgdb_handle_breakpoint(struct pt_regs *regs) @@ -123,7 +125,7 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) if (user_mode(regs)) return 0; - if (kgdb_handle_exception(0, SIGTRAP, 0, regs) != 0) + if (kgdb_handle_exception(1, SIGTRAP, 0, regs) != 0) return 0; if (*(u32 *) (regs->nip) == *(u32 *) (&arch_kgdb_ops.gdb_bpt_instr)) @@ -309,6 +311,11 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) (unsigned long)(((void *)gdb_regs) + NUMREGBYTES)); } +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) +{ + regs->nip = pc; +} + /* * This function does PowerPC specific procesing for interfacing to gdb. */ diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index b36f074524a..c533525ca56 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -114,6 +114,9 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) #ifdef CONFIG_PPC_ADV_DEBUG_REGS regs->msr &= ~MSR_CE; mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM); +#ifdef CONFIG_PPC_47x + isync(); +#endif #endif /* diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index c2c70e1b32c..50362b6ef6e 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -38,7 +38,7 @@ #include <asm/vio.h> #include <asm/mmu.h> -#define MODULE_VERS "1.8" +#define MODULE_VERS "1.9" #define MODULE_NAME "lparcfg" /* #define LPARCFG_DEBUG */ @@ -487,6 +487,14 @@ static void splpar_dispatch_data(struct seq_file *m) seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions); } +static void parse_em_data(struct seq_file *m) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); +} + static int pseries_lparcfg_data(struct seq_file *m, void *v) { int partition_potential_processors; @@ -541,6 +549,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "slb_size=%d\n", mmu_slb_size); + parse_em_data(m); + return 0; } diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 040bd1de8d9..26f9900f773 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -155,33 +155,38 @@ void kexec_copy_flush(struct kimage *image) #ifdef CONFIG_SMP -/* FIXME: we should schedule this function to be called on all cpus based - * on calling the interrupts, but we would like to call it off irq level - * so that the interrupt controller is clean. - */ +static int kexec_all_irq_disabled = 0; + static void kexec_smp_down(void *arg) { + local_irq_disable(); + mb(); /* make sure our irqs are disabled before we say they are */ + get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; + while(kexec_all_irq_disabled == 0) + cpu_relax(); + mb(); /* make sure all irqs are disabled before this */ + /* + * Now every CPU has IRQs off, we can clear out any pending + * IPIs and be sure that no more will come in after this. + */ if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(0, 1); - local_irq_disable(); kexec_smp_wait(); /* NOTREACHED */ } -static void kexec_prepare_cpus(void) +static void kexec_prepare_cpus_wait(int wait_state) { int my_cpu, i, notified=-1; - smp_call_function(kexec_smp_down, NULL, /* wait */0); my_cpu = get_cpu(); - - /* check the others cpus are now down (via paca hw cpu id == -1) */ + /* Make sure each CPU has atleast made it to the state we need */ for (i=0; i < NR_CPUS; i++) { if (i == my_cpu) continue; - while (paca[i].hw_cpu_id != -1) { + while (paca[i].kexec_state < wait_state) { barrier(); if (!cpu_possible(i)) { printk("kexec: cpu %d hw_cpu_id %d is not" @@ -201,20 +206,35 @@ static void kexec_prepare_cpus(void) } if (i != notified) { printk( "kexec: waiting for cpu %d (physical" - " %d) to go down\n", - i, paca[i].hw_cpu_id); + " %d) to enter %i state\n", + i, paca[i].hw_cpu_id, wait_state); notified = i; } } } + mb(); +} + +static void kexec_prepare_cpus(void) +{ + + smp_call_function(kexec_smp_down, NULL, /* wait */0); + local_irq_disable(); + mb(); /* make sure IRQs are disabled before we say they are */ + get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; + + kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF); + /* we are sure every CPU has IRQs off at this point */ + kexec_all_irq_disabled = 1; /* after we tell the others to go down */ if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(0, 0); - put_cpu(); + /* Before removing MMU mapings make sure all CPUs have entered real mode */ + kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE); - local_irq_disable(); + put_cpu(); } #else /* ! SMP */ diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 8649f536f8d..8043d1b73cf 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -441,7 +441,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) addi r3,r3,L1_CACHE_BYTES bdnz 0b sync -#ifndef CONFIG_44x +#ifdef CONFIG_44x /* We don't flush the icache on 44x. Those have a virtual icache * and we don't have access to the virtual address here (it's * not the page vaddr but where it's mapped in user space). The @@ -449,15 +449,19 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) * a change in the address space occurs, before returning to * user space */ +BEGIN_MMU_FTR_SECTION + blr +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) +#endif /* CONFIG_44x */ mtctr r4 1: icbi 0,r6 addi r6,r6,L1_CACHE_BYTES bdnz 1b sync isync -#endif /* CONFIG_44x */ blr +#ifndef CONFIG_BOOKE /* * Flush a particular page from the data cache to RAM, identified * by its physical address. We turn off the MMU so we can just use @@ -490,6 +494,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mtmsr r10 /* restore DR */ isync blr +#endif /* CONFIG_BOOKE */ /* * Clear pages using the dcbz instruction, which doesn't cause any diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index a5cf9c1356a..a2b18dffa03 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -24,6 +24,7 @@ #include <asm/asm-offsets.h> #include <asm/cputable.h> #include <asm/thread_info.h> +#include <asm/kexec.h> .text @@ -471,6 +472,10 @@ _GLOBAL(kexec_wait) 1: mflr r5 addi r5,r5,kexec_flag-1b + li r4,KEXEC_STATE_REAL_MODE + stb r4,PACAKEXECSTATE(r13) + SYNC + 99: HMT_LOW #ifdef CONFIG_KEXEC /* use no memory without kexec */ lwz r4,0(r5) @@ -494,14 +499,11 @@ kexec_flag: * note: this is a terminal routine, it does not save lr * * get phys id from paca - * set paca id to -1 to say we got here * switch to real mode * join other cpus in kexec_wait(phys_id) */ _GLOBAL(kexec_smp_wait) lhz r3,PACAHWCPUID(r13) - li r4,-1 - sth r4,PACAHWCPUID(r13) /* let others know we left */ bl real_mode b .kexec_wait diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index a359cb08e90..df78e0236a0 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -13,7 +13,7 @@ static void of_device_make_bus_id(struct of_device *dev) { static atomic_t bus_no_reg_magic; - struct device_node *node = dev->node; + struct device_node *node = dev->dev.of_node; const u32 *reg; u64 addr; int magic; @@ -69,11 +69,10 @@ struct of_device *of_device_alloc(struct device_node *np, if (!dev) return NULL; - dev->node = of_node_get(np); - dev->dev.dma_mask = &dev->dma_mask; + dev->dev.of_node = of_node_get(np); + dev->dev.dma_mask = &dev->archdata.dma_mask; dev->dev.parent = parent; dev->dev.release = of_release_dev; - dev->dev.archdata.of_node = np; if (bus_id) dev_set_name(&dev->dev, "%s", bus_id); @@ -95,17 +94,17 @@ int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) ofdev = to_of_device(dev); - if (add_uevent_var(env, "OF_NAME=%s", ofdev->node->name)) + if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name)) return -ENOMEM; - if (add_uevent_var(env, "OF_TYPE=%s", ofdev->node->type)) + if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type)) return -ENOMEM; /* Since the compatible field can contain pretty much anything * it's not really legal to split it out with commas. We split it * up using a number of environment variables instead. */ - compat = of_get_property(ofdev->node, "compatible", &cplen); + compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); while (compat && *compat && cplen > 0) { if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) return -ENOMEM; diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 6c1dfc3ff8b..487a98851ba 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -74,7 +74,7 @@ struct of_device* of_platform_device_create(struct device_node *np, if (!dev) return NULL; - dev->dma_mask = 0xffffffffUL; + dev->archdata.dma_mask = 0xffffffffUL; dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); dev->dev.bus = &of_platform_bus_type; @@ -195,7 +195,7 @@ EXPORT_SYMBOL(of_platform_bus_probe); static int of_dev_node_match(struct device *dev, void *data) { - return to_of_device(dev)->node == data; + return to_of_device(dev)->dev.of_node == data; } struct of_device *of_find_device_by_node(struct device_node *np) @@ -213,7 +213,7 @@ EXPORT_SYMBOL(of_find_device_by_node); static int of_dev_phandle_match(struct device *dev, void *data) { phandle *ph = data; - return to_of_device(dev)->node->phandle == *ph; + return to_of_device(dev)->dev.of_node->phandle == *ph; } struct of_device *of_find_device_by_phandle(phandle ph) @@ -246,10 +246,10 @@ static int __devinit of_pci_phb_probe(struct of_device *dev, if (ppc_md.pci_setup_phb == NULL) return -ENODEV; - printk(KERN_INFO "Setting up PCI bus %s\n", dev->node->full_name); + pr_info("Setting up PCI bus %s\n", dev->dev.of_node->full_name); /* Alloc and setup PHB data structure */ - phb = pcibios_alloc_controller(dev->node); + phb = pcibios_alloc_controller(dev->dev.of_node); if (!phb) return -ENODEV; @@ -263,19 +263,19 @@ static int __devinit of_pci_phb_probe(struct of_device *dev, } /* Process "ranges" property */ - pci_process_bridge_OF_ranges(phb, dev->node, 0); + pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0); /* Init pci_dn data structures */ pci_devs_phb_init_dynamic(phb); /* Register devices with EEH */ #ifdef CONFIG_EEH - if (dev->node->child) - eeh_add_device_tree_early(dev->node); + if (dev->dev.of_node->child) + eeh_add_device_tree_early(dev->dev.of_node); #endif /* CONFIG_EEH */ /* Scan the bus */ - pcibios_scan_phb(phb, dev->node); + pcibios_scan_phb(phb, dev->dev.of_node); if (phb->bus == NULL) return -ENXIO; @@ -306,10 +306,11 @@ static struct of_device_id of_pci_phb_ids[] = { }; static struct of_platform_driver of_pci_phb_driver = { - .match_table = of_pci_phb_ids, .probe = of_pci_phb_probe, .driver = { .name = "of-pci", + .owner = THIS_MODULE, + .of_match_table = of_pci_phb_ids, }, }; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0c40c6f476f..f88acf0218d 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -18,6 +18,7 @@ #include <asm/pgtable.h> #include <asm/iseries/lpar_map.h> #include <asm/iseries/hv_types.h> +#include <asm/kexec.h> /* This symbol is provided by the linker - let it fill in the paca * field correctly */ @@ -97,6 +98,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->kernelbase = (unsigned long) _stext; new_paca->kernel_msr = MSR_KERNEL; new_paca->hw_cpu_id = 0xffff; + new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = &slb_shadow[cpu]; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 0c0567e5840..6646005dffb 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1097,8 +1097,8 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Setup OF node pointer in archdata */ - sd->of_node = pci_device_to_OF_node(dev); + /* Setup OF node pointer in the device */ + dev->dev.of_node = pci_device_to_OF_node(dev); /* Fixup NUMA node as it may not be setup yet by the generic * code and is needed by the DMA init diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index cd11d5ca80d..6ddb795f83e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -310,6 +310,8 @@ static void __devinit __of_scan_bus(struct device_node *node, /* Scan direct children */ for_each_child_of_node(node, child) { pr_debug(" * %s\n", child->full_name); + if (!of_device_is_available(child)) + continue; reg = of_get_property(child, "reg", ®len); if (reg == NULL || reglen < 20) continue; diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 08460a2e9f4..43b83c35cf5 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -35,6 +35,9 @@ struct cpu_hw_events { u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; + + unsigned int group_flag; + int n_txn_start; }; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); @@ -718,66 +721,6 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -static void event_sched_in(struct perf_event *event) -{ - event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = smp_processor_id(); - event->tstamp_running += event->ctx->time - event->tstamp_stopped; - if (is_software_event(event)) - event->pmu->enable(event); -} - -/* - * Called to enable a whole group of events. - * Returns 1 if the group was enabled, or -EAGAIN if it could not be. - * Assumes the caller has disabled interrupts and has - * frozen the PMU with hw_perf_save_disable. - */ -int hw_perf_group_sched_in(struct perf_event *group_leader, - struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - struct cpu_hw_events *cpuhw; - long i, n, n0; - struct perf_event *sub; - - if (!ppmu) - return 0; - cpuhw = &__get_cpu_var(cpu_hw_events); - n0 = cpuhw->n_events; - n = collect_events(group_leader, ppmu->n_counter - n0, - &cpuhw->event[n0], &cpuhw->events[n0], - &cpuhw->flags[n0]); - if (n < 0) - return -EAGAIN; - if (check_excludes(cpuhw->event, cpuhw->flags, n0, n)) - return -EAGAIN; - i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n + n0); - if (i < 0) - return -EAGAIN; - cpuhw->n_events = n0 + n; - cpuhw->n_added += n; - - /* - * OK, this group can go on; update event states etc., - * and enable any software events - */ - for (i = n0; i < n0 + n; ++i) - cpuhw->event[i]->hw.config = cpuhw->events[i]; - cpuctx->active_oncpu += n; - n = 1; - event_sched_in(group_leader); - list_for_each_entry(sub, &group_leader->sibling_list, group_entry) { - if (sub->state != PERF_EVENT_STATE_OFF) { - event_sched_in(sub); - ++n; - } - } - ctx->nr_active += n; - - return 1; -} - /* * Add a event to the PMU. * If all events are not already frozen, then we disable and @@ -805,12 +748,22 @@ static int power_pmu_enable(struct perf_event *event) cpuhw->event[n0] = event; cpuhw->events[n0] = event->hw.config; cpuhw->flags[n0] = event->hw.event_base; + + /* + * If group events scheduling transaction was started, + * skip the schedulability test here, it will be peformed + * at commit time(->commit_txn) as a whole + */ + if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED) + goto nocheck; + if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1)) goto out; if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1)) goto out; - event->hw.config = cpuhw->events[n0]; + +nocheck: ++cpuhw->n_events; ++cpuhw->n_added; @@ -896,11 +849,65 @@ static void power_pmu_unthrottle(struct perf_event *event) local_irq_restore(flags); } +/* + * Start group events scheduling transaction + * Set the flag to make pmu::enable() not perform the + * schedulability test, it will be performed at commit time + */ +void power_pmu_start_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + cpuhw->group_flag |= PERF_EVENT_TXN_STARTED; + cpuhw->n_txn_start = cpuhw->n_events; +} + +/* + * Stop group events scheduling transaction + * Clear the flag and pmu::enable() will perform the + * schedulability test. + */ +void power_pmu_cancel_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED; +} + +/* + * Commit group events scheduling transaction + * Perform the group schedulability test as a whole + * Return 0 if success + */ +int power_pmu_commit_txn(const struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw; + long i, n; + + if (!ppmu) + return -EAGAIN; + cpuhw = &__get_cpu_var(cpu_hw_events); + n = cpuhw->n_events; + if (check_excludes(cpuhw->event, cpuhw->flags, 0, n)) + return -EAGAIN; + i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n); + if (i < 0) + return -EAGAIN; + + for (i = cpuhw->n_txn_start; i < n; ++i) + cpuhw->event[i]->hw.config = cpuhw->events[i]; + + return 0; +} + struct pmu power_pmu = { .enable = power_pmu_enable, .disable = power_pmu_disable, .read = power_pmu_read, .unthrottle = power_pmu_unthrottle, + .start_txn = power_pmu_start_txn, + .cancel_txn = power_pmu_cancel_txn, + .commit_txn = power_pmu_commit_txn, }; /* diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ab3e392ac63..bc9f39d2598 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -101,6 +101,10 @@ EXPORT_SYMBOL(pci_dram_offset); EXPORT_SYMBOL(start_thread); EXPORT_SYMBOL(kernel_thread); +#ifndef CONFIG_BOOKE +EXPORT_SYMBOL_GPL(cvt_df); +EXPORT_SYMBOL_GPL(cvt_fd); +#endif EXPORT_SYMBOL(giveup_fpu); #ifdef CONFIG_ALTIVEC EXPORT_SYMBOL(giveup_altivec); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e4d71ced97e..9d255b4f0a0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -371,6 +371,9 @@ int set_dabr(unsigned long dabr) /* XXX should we have a CPU_FTR_HAS_DABR ? */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS mtspr(SPRN_DAC1, dabr); +#ifdef CONFIG_PPC_47x + isync(); +#endif #elif defined(CONFIG_PPC_BOOK3S) mtspr(SPRN_DABR, dabr); #endif diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index ed2cfe17d25..7a0c0199ea2 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -39,6 +39,109 @@ #include <asm/system.h> /* + * The parameter save area on the stack is used to store arguments being passed + * to callee function and is located at fixed offset from stack pointer. + */ +#ifdef CONFIG_PPC32 +#define PARAMETER_SAVE_AREA_OFFSET 24 /* bytes */ +#else /* CONFIG_PPC32 */ +#define PARAMETER_SAVE_AREA_OFFSET 48 /* bytes */ +#endif + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define STR(s) #s /* convert to string */ +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define GPR_OFFSET_NAME(num) \ + {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + GPR_OFFSET_NAME(0), + GPR_OFFSET_NAME(1), + GPR_OFFSET_NAME(2), + GPR_OFFSET_NAME(3), + GPR_OFFSET_NAME(4), + GPR_OFFSET_NAME(5), + GPR_OFFSET_NAME(6), + GPR_OFFSET_NAME(7), + GPR_OFFSET_NAME(8), + GPR_OFFSET_NAME(9), + GPR_OFFSET_NAME(10), + GPR_OFFSET_NAME(11), + GPR_OFFSET_NAME(12), + GPR_OFFSET_NAME(13), + GPR_OFFSET_NAME(14), + GPR_OFFSET_NAME(15), + GPR_OFFSET_NAME(16), + GPR_OFFSET_NAME(17), + GPR_OFFSET_NAME(18), + GPR_OFFSET_NAME(19), + GPR_OFFSET_NAME(20), + GPR_OFFSET_NAME(21), + GPR_OFFSET_NAME(22), + GPR_OFFSET_NAME(23), + GPR_OFFSET_NAME(24), + GPR_OFFSET_NAME(25), + GPR_OFFSET_NAME(26), + GPR_OFFSET_NAME(27), + GPR_OFFSET_NAME(28), + GPR_OFFSET_NAME(29), + GPR_OFFSET_NAME(30), + GPR_OFFSET_NAME(31), + REG_OFFSET_NAME(nip), + REG_OFFSET_NAME(msr), + REG_OFFSET_NAME(ctr), + REG_OFFSET_NAME(link), + REG_OFFSET_NAME(xer), + REG_OFFSET_NAME(ccr), +#ifdef CONFIG_PPC64 + REG_OFFSET_NAME(softe), +#else + REG_OFFSET_NAME(mq), +#endif + REG_OFFSET_NAME(trap), + REG_OFFSET_NAME(dar), + REG_OFFSET_NAME(dsisr), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} + +/* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 74367841615..0e1ec6f746f 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -691,10 +691,14 @@ void rtas_os_term(char *str) { int status; - if (panic_timeout) - return; - - if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term")) + /* + * Firmware with the ibm,extended-os-term property is guaranteed + * to always return from an ibm,os-term call. Earlier versions without + * this property may terminate the partition which we want to avoid + * since it interferes with panic_timeout. + */ + if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") || + RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term")) return; snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str); @@ -705,8 +709,7 @@ void rtas_os_term(char *str) } while (rtas_busy_delay(status)); if (status != 0) - printk(KERN_EMERG "ibm,os-term call failed %d\n", - status); + printk(KERN_EMERG "ibm,os-term call failed %d\n", status); } static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE; diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 4190eae7850..638883e23e3 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -411,9 +411,9 @@ static void rtas_event_scan(struct work_struct *w) get_online_cpus(); - cpu = next_cpu(smp_processor_id(), cpu_online_map); - if (cpu == NR_CPUS) { - cpu = first_cpu(cpu_online_map); + cpu = cpumask_next(smp_processor_id(), cpu_online_mask); + if (cpu >= nr_cpu_ids) { + cpu = cpumask_first(cpu_online_mask); if (first_pass) { first_pass = 0; @@ -466,8 +466,8 @@ static void start_event_scan(void) /* Retreive errors from nvram if any */ retreive_nvram_error_log(); - schedule_delayed_work_on(first_cpu(cpu_online_map), &event_scan_work, - event_scan_delay); + schedule_delayed_work_on(cpumask_first(cpu_online_mask), + &event_scan_work, event_scan_delay); } static int __init rtas_init(void) @@ -490,6 +490,12 @@ static int __init rtas_init(void) return -ENODEV; } + if (!rtas_event_scan_rate) { + /* Broken firmware: take a rate of zero to mean don't scan */ + printk(KERN_DEBUG "rtasd: scan rate is 0, not scanning\n"); + return 0; + } + /* Make room for the sequence number */ rtas_error_log_max = rtas_get_error_log_max(); rtas_error_log_buffer_max = rtas_error_log_max + sizeof(int); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 48f0a008b20..5e4d852f640 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -161,45 +161,44 @@ extern u32 cpu_temp_both(unsigned long cpu); DEFINE_PER_CPU(unsigned int, cpu_pvr); #endif -static int show_cpuinfo(struct seq_file *m, void *v) +static void show_cpuinfo_summary(struct seq_file *m) { - unsigned long cpu_id = (unsigned long)v - 1; - unsigned int pvr; - unsigned short maj; - unsigned short min; - - if (cpu_id == NR_CPUS) { - struct device_node *root; - const char *model = NULL; + struct device_node *root; + const char *model = NULL; #if defined(CONFIG_SMP) && defined(CONFIG_PPC32) - unsigned long bogosum = 0; - int i; - for_each_online_cpu(i) - bogosum += loops_per_jiffy; - seq_printf(m, "total bogomips\t: %lu.%02lu\n", - bogosum/(500000/HZ), bogosum/(5000/HZ) % 100); + unsigned long bogosum = 0; + int i; + for_each_online_cpu(i) + bogosum += loops_per_jiffy; + seq_printf(m, "total bogomips\t: %lu.%02lu\n", + bogosum/(500000/HZ), bogosum/(5000/HZ) % 100); #endif /* CONFIG_SMP && CONFIG_PPC32 */ - seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq); - if (ppc_md.name) - seq_printf(m, "platform\t: %s\n", ppc_md.name); - root = of_find_node_by_path("/"); - if (root) - model = of_get_property(root, "model", NULL); - if (model) - seq_printf(m, "model\t\t: %s\n", model); - of_node_put(root); - - if (ppc_md.show_cpuinfo != NULL) - ppc_md.show_cpuinfo(m); + seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq); + if (ppc_md.name) + seq_printf(m, "platform\t: %s\n", ppc_md.name); + root = of_find_node_by_path("/"); + if (root) + model = of_get_property(root, "model", NULL); + if (model) + seq_printf(m, "model\t\t: %s\n", model); + of_node_put(root); + + if (ppc_md.show_cpuinfo != NULL) + ppc_md.show_cpuinfo(m); #ifdef CONFIG_PPC32 - /* Display the amount of memory */ - seq_printf(m, "Memory\t\t: %d MB\n", - (unsigned int)(total_memory / (1024 * 1024))); + /* Display the amount of memory */ + seq_printf(m, "Memory\t\t: %d MB\n", + (unsigned int)(total_memory / (1024 * 1024))); #endif +} - return 0; - } +static int show_cpuinfo(struct seq_file *m, void *v) +{ + unsigned long cpu_id = (unsigned long)v - 1; + unsigned int pvr; + unsigned short maj; + unsigned short min; /* We only show online cpus: disable preempt (overzealous, I * knew) to prevent cpu going down. */ @@ -308,19 +307,28 @@ static int show_cpuinfo(struct seq_file *m, void *v) #endif preempt_enable(); + + /* If this is the last cpu, print the summary */ + if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids) + show_cpuinfo_summary(m); + return 0; } static void *c_start(struct seq_file *m, loff_t *pos) { - unsigned long i = *pos; - - return i <= NR_CPUS ? (void *)(i + 1) : NULL; + if (*pos == 0) /* just in case, cpu 0 is not the first */ + *pos = cpumask_first(cpu_online_mask); + else + *pos = cpumask_next(*pos - 1, cpu_online_mask); + if ((*pos) < nr_cpu_ids) + return (void *)(unsigned long)(*pos + 1); + return NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) { - ++*pos; + (*pos)++; return c_start(m, pos); } @@ -386,14 +394,14 @@ static void __init cpu_init_thread_core_maps(int tpc) /** * setup_cpu_maps - initialize the following cpu maps: - * cpu_possible_map - * cpu_present_map + * cpu_possible_mask + * cpu_present_mask * * Having the possible map set up early allows us to restrict allocations * of things like irqstacks to num_possible_cpus() rather than NR_CPUS. * * We do not initialize the online map here; cpus set their own bits in - * cpu_online_map as they come up. + * cpu_online_mask as they come up. * * This function is valid only for Open Firmware systems. finish_device_tree * must be called before using this. diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 914389158a9..f3fb5a79de5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -424,9 +424,18 @@ void __init setup_system(void) DBG(" <- setup_system()\n"); } +static u64 slb0_limit(void) +{ + if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { + return 1UL << SID_SHIFT_1T; + } + return 1UL << SID_SHIFT; +} + #ifdef CONFIG_IRQSTACKS static void __init irqstack_early_init(void) { + u64 limit = slb0_limit(); unsigned int i; /* @@ -436,10 +445,10 @@ static void __init irqstack_early_init(void) for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) __va(lmb_alloc_base(THREAD_SIZE, - THREAD_SIZE, 0x10000000)); + THREAD_SIZE, limit)); hardirq_ctx[i] = (struct thread_info *) __va(lmb_alloc_base(THREAD_SIZE, - THREAD_SIZE, 0x10000000)); + THREAD_SIZE, limit)); } } #else @@ -470,7 +479,7 @@ static void __init exc_lvl_early_init(void) */ static void __init emergency_stack_init(void) { - unsigned long limit; + u64 limit; unsigned int i; /* @@ -482,7 +491,7 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(0x10000000ULL, lmb.rmo_size); + limit = min(slb0_limit(), lmb.rmo_size); for_each_possible_cpu(i) { unsigned long sp; @@ -573,12 +582,6 @@ void ppc64_boot_msg(unsigned int src, const char *msg) printk("[boot]%04x %s\n", src, msg); } -void cpu_die(void) -{ - if (ppc_md.cpu_die) - ppc_md.cpu_die(); -} - #ifdef CONFIG_SMP #define PCPU_DYN_SIZE () diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c2ee1449807..5c196d1086d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -59,8 +59,8 @@ struct thread_info *secondary_ti; -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE; -DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE; +DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); @@ -271,6 +271,16 @@ void __init smp_prepare_cpus(unsigned int max_cpus) smp_store_cpu_info(boot_cpuid); cpu_callin_map[boot_cpuid] = 1; + for_each_possible_cpu(cpu) { + zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + } + + cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); + cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); + if (smp_ops) if (smp_ops->probe) max_cpus = smp_ops->probe(); @@ -289,10 +299,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) void __devinit smp_prepare_boot_cpu(void) { BUG_ON(smp_processor_id() != boot_cpuid); - - set_cpu_online(boot_cpuid, true); - cpu_set(boot_cpuid, per_cpu(cpu_sibling_map, boot_cpuid)); - cpu_set(boot_cpuid, per_cpu(cpu_core_map, boot_cpuid)); #ifdef CONFIG_PPC64 paca[boot_cpuid].__current = current; #endif @@ -313,7 +319,7 @@ int generic_cpu_disable(void) set_cpu_online(cpu, false); #ifdef CONFIG_PPC64 vdso_data->processorCount--; - fixup_irqs(cpu_online_map); + fixup_irqs(cpu_online_mask); #endif return 0; } @@ -333,7 +339,7 @@ int generic_cpu_enable(unsigned int cpu) cpu_relax(); #ifdef CONFIG_PPC64 - fixup_irqs(cpu_online_map); + fixup_irqs(cpu_online_mask); /* counter the irq disable in fixup_irqs */ local_irq_enable(); #endif @@ -462,7 +468,7 @@ out: return id; } -/* Must be called when no change can occur to cpu_present_map, +/* Must be called when no change can occur to cpu_present_mask, * i.e. during cpu online or offline. */ static struct device_node *cpu_to_l2cache(int cpu) @@ -495,6 +501,14 @@ int __devinit start_secondary(void *unused) current->active_mm = &init_mm; smp_store_cpu_info(cpu); + +#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) + /* Clear any pending timer interrupts */ + mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); + + /* Enable decrementer interrupt */ + mtspr(SPRN_TCR, TCR_DIE); +#endif set_dec(tb_ticks_per_jiffy); preempt_disable(); cpu_callin_map[cpu] = 1; @@ -517,15 +531,15 @@ int __devinit start_secondary(void *unused) for (i = 0; i < threads_per_core; i++) { if (cpu_is_offline(base + i)) continue; - cpu_set(cpu, per_cpu(cpu_sibling_map, base + i)); - cpu_set(base + i, per_cpu(cpu_sibling_map, cpu)); + cpumask_set_cpu(cpu, cpu_sibling_mask(base + i)); + cpumask_set_cpu(base + i, cpu_sibling_mask(cpu)); /* cpu_core_map should be a superset of * cpu_sibling_map even if we don't have cache * information, so update the former here, too. */ - cpu_set(cpu, per_cpu(cpu_core_map, base +i)); - cpu_set(base + i, per_cpu(cpu_core_map, cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(base + i)); + cpumask_set_cpu(base + i, cpu_core_mask(cpu)); } l2_cache = cpu_to_l2cache(cpu); for_each_online_cpu(i) { @@ -533,8 +547,8 @@ int __devinit start_secondary(void *unused) if (!np) continue; if (np == l2_cache) { - cpu_set(cpu, per_cpu(cpu_core_map, i)); - cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(i)); + cpumask_set_cpu(i, cpu_core_mask(cpu)); } of_node_put(np); } @@ -554,19 +568,22 @@ int setup_profiling_timer(unsigned int multiplier) void __init smp_cpus_done(unsigned int max_cpus) { - cpumask_t old_mask; + cpumask_var_t old_mask; /* We want the setup_cpu() here to be called from CPU 0, but our * init thread may have been "borrowed" by another CPU in the meantime * se we pin us down to CPU 0 for a short while */ - old_mask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid)); + alloc_cpumask_var(&old_mask, GFP_NOWAIT); + cpumask_copy(old_mask, ¤t->cpus_allowed); + set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid)); if (smp_ops && smp_ops->setup_cpu) smp_ops->setup_cpu(boot_cpuid); - set_cpus_allowed(current, old_mask); + set_cpus_allowed_ptr(current, old_mask); + + free_cpumask_var(old_mask); snapshot_timebases(); @@ -591,10 +608,10 @@ int __cpu_disable(void) /* Update sibling maps */ base = cpu_first_thread_in_core(cpu); for (i = 0; i < threads_per_core; i++) { - cpu_clear(cpu, per_cpu(cpu_sibling_map, base + i)); - cpu_clear(base + i, per_cpu(cpu_sibling_map, cpu)); - cpu_clear(cpu, per_cpu(cpu_core_map, base +i)); - cpu_clear(base + i, per_cpu(cpu_core_map, cpu)); + cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); + cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); + cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); + cpumask_clear_cpu(base + i, cpu_core_mask(cpu)); } l2_cache = cpu_to_l2cache(cpu); @@ -603,8 +620,8 @@ int __cpu_disable(void) if (!np) continue; if (np == l2_cache) { - cpu_clear(cpu, per_cpu(cpu_core_map, i)); - cpu_clear(i, per_cpu(cpu_core_map, cpu)); + cpumask_clear_cpu(cpu, cpu_core_mask(i)); + cpumask_clear_cpu(i, cpu_core_mask(cpu)); } of_node_put(np); } @@ -631,4 +648,10 @@ void cpu_hotplug_driver_unlock() { mutex_unlock(&powerpc_cpu_hotplug_driver_mutex); } + +void cpu_die(void) +{ + if (ppc_md.cpu_die) + ppc_md.cpu_die(); +} #endif diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index e235e52dc4f..c0d8c2006bf 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -35,7 +35,7 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); #ifdef CONFIG_PPC64 /* Time in microseconds we delay before sleeping in the idle loop */ -DEFINE_PER_CPU(unsigned long, smt_snooze_delay) = { 100 }; +DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; static ssize_t store_smt_snooze_delay(struct sys_device *dev, struct sysdev_attribute *attr, @@ -44,9 +44,9 @@ static ssize_t store_smt_snooze_delay(struct sys_device *dev, { struct cpu *cpu = container_of(dev, struct cpu, sysdev); ssize_t ret; - unsigned long snooze; + long snooze; - ret = sscanf(buf, "%lu", &snooze); + ret = sscanf(buf, "%ld", &snooze); if (ret != 1) return -EINVAL; @@ -61,53 +61,23 @@ static ssize_t show_smt_snooze_delay(struct sys_device *dev, { struct cpu *cpu = container_of(dev, struct cpu, sysdev); - return sprintf(buf, "%lu\n", per_cpu(smt_snooze_delay, cpu->sysdev.id)); + return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->sysdev.id)); } static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, store_smt_snooze_delay); -/* Only parse OF options if the matching cmdline option was not specified */ -static int smt_snooze_cmdline; - -static int __init smt_setup(void) -{ - struct device_node *options; - const unsigned int *val; - unsigned int cpu; - - if (!cpu_has_feature(CPU_FTR_SMT)) - return -ENODEV; - - options = of_find_node_by_path("/options"); - if (!options) - return -ENODEV; - - val = of_get_property(options, "ibm,smt-snooze-delay", NULL); - if (!smt_snooze_cmdline && val) { - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = *val; - } - - of_node_put(options); - return 0; -} -__initcall(smt_setup); - static int __init setup_smt_snooze_delay(char *str) { unsigned int cpu; - int snooze; + long snooze; if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - smt_snooze_cmdline = 1; - - if (get_option(&str, &snooze)) { - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - } + snooze = simple_strtol(str, NULL, 10); + for_each_possible_cpu(cpu) + per_cpu(smt_snooze_delay, cpu) = snooze; return 1; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 29d128eb6c4..3031fc712ad 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -380,6 +380,46 @@ int machine_check_440A(struct pt_regs *regs) } return 0; } + +int machine_check_47x(struct pt_regs *regs) +{ + unsigned long reason = get_mc_reason(regs); + u32 mcsr; + + printk(KERN_ERR "Machine check in kernel mode.\n"); + if (reason & ESR_IMCP) { + printk(KERN_ERR + "Instruction Synchronous Machine Check exception\n"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + return 0; + } + mcsr = mfspr(SPRN_MCSR); + if (mcsr & MCSR_IB) + printk(KERN_ERR "Instruction Read PLB Error\n"); + if (mcsr & MCSR_DRB) + printk(KERN_ERR "Data Read PLB Error\n"); + if (mcsr & MCSR_DWB) + printk(KERN_ERR "Data Write PLB Error\n"); + if (mcsr & MCSR_TLBP) + printk(KERN_ERR "TLB Parity Error\n"); + if (mcsr & MCSR_ICP) { + flush_instruction_cache(); + printk(KERN_ERR "I-Cache Parity Error\n"); + } + if (mcsr & MCSR_DCSP) + printk(KERN_ERR "D-Cache Search Parity Error\n"); + if (mcsr & PPC47x_MCSR_GPR) + printk(KERN_ERR "GPR Parity Error\n"); + if (mcsr & PPC47x_MCSR_FPR) + printk(KERN_ERR "FPR Parity Error\n"); + if (mcsr & PPC47x_MCSR_IPR) + printk(KERN_ERR "Machine Check exception is imprecise\n"); + + /* Clear MCSR */ + mtspr(SPRN_MCSR, mcsr); + + return 0; +} #elif defined(CONFIG_E500) int machine_check_e500(struct pt_regs *regs) { @@ -815,12 +855,15 @@ void __kprobes program_check_exception(struct pt_regs *regs) return; } 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; + /* trap exception */ if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) return; - if (debugger_bpt(regs)) - return; if (!(regs->msr & MSR_PR) && /* not user-mode */ report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 82237176a2a..00b9436f765 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -645,8 +645,10 @@ void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) found = 1; break; } - if (!found) + if (!found) { + spin_unlock_irqrestore(&vio_cmo.lock, flags); return; + } /* Increase/decrease in desired device entitlement */ if (desired >= viodev->cmo.desired) { @@ -705,7 +707,7 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) * Check to see that device has a DMA window and configure * entitlement for the device. */ - if (of_get_property(viodev->dev.archdata.of_node, + if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) { /* Check that the driver is CMO enabled and get desired DMA */ if (!viodrv->get_desired_dma) { @@ -958,9 +960,12 @@ viodev_cmo_rd_attr(allocated); static ssize_t name_show(struct device *, struct device_attribute *, char *); static ssize_t devspec_show(struct device *, struct device_attribute *, char *); +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf); static struct device_attribute vio_cmo_dev_attrs[] = { __ATTR_RO(name), __ATTR_RO(devspec), + __ATTR_RO(modalias), __ATTR(cmo_desired, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH, viodev_cmo_desired_show, viodev_cmo_desired_set), __ATTR(cmo_entitled, S_IRUGO, viodev_cmo_entitled_show, NULL), @@ -1049,7 +1054,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) if (firmware_has_feature(FW_FEATURE_ISERIES)) return vio_build_iommu_table_iseries(dev); - dma_window = of_get_property(dev->dev.archdata.of_node, + dma_window = of_get_property(dev->dev.of_node, "ibm,my-dma-window", NULL); if (!dma_window) return NULL; @@ -1058,7 +1063,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) if (tbl == NULL) return NULL; - of_parse_dma_window(dev->dev.archdata.of_node, dma_window, + of_parse_dma_window(dev->dev.of_node, dma_window, &tbl->it_index, &offset, &size); /* TCE table size - measured in tce entries */ @@ -1086,7 +1091,7 @@ static const struct vio_device_id *vio_match_device( { while (ids->type[0] != '\0') { if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) && - of_device_is_compatible(dev->dev.archdata.of_node, + of_device_is_compatible(dev->dev.of_node, ids->compat)) return ids; ids++; @@ -1179,7 +1184,7 @@ EXPORT_SYMBOL(vio_unregister_driver); static void __devinit vio_dev_release(struct device *dev) { /* XXX should free TCE table */ - of_node_put(dev->archdata.of_node); + of_node_put(dev->of_node); kfree(to_vio_dev(dev)); } @@ -1230,7 +1235,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (unit_address != NULL) viodev->unit_address = *unit_address; } - viodev->dev.archdata.of_node = of_node_get(of_node); + viodev->dev.of_node = of_node_get(of_node); if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_set_dma_ops(viodev); @@ -1315,14 +1320,32 @@ static ssize_t name_show(struct device *dev, static ssize_t devspec_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct device_node *of_node = dev->archdata.of_node; + struct device_node *of_node = dev->of_node; return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none"); } +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const struct vio_dev *vio_dev = to_vio_dev(dev); + struct device_node *dn; + const char *cp; + + dn = dev->of_node; + if (!dn) + return -ENODEV; + cp = of_get_property(dn, "compatible", NULL); + if (!cp) + return -ENODEV; + + return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp); +} + static struct device_attribute vio_dev_attrs[] = { __ATTR_RO(name), __ATTR_RO(devspec), + __ATTR_RO(modalias), __ATTR_NULL }; @@ -1347,7 +1370,7 @@ static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) struct device_node *dn; const char *cp; - dn = dev->archdata.of_node; + dn = dev->of_node; if (!dn) return -ENODEV; cp = of_get_property(dn, "compatible", NULL); @@ -1365,6 +1388,7 @@ static struct bus_type vio_bus_type = { .match = vio_bus_match, .probe = vio_bus_probe, .remove = vio_bus_remove, + .pm = GENERIC_SUBSYS_PM_OPS, }; /** @@ -1378,7 +1402,7 @@ static struct bus_type vio_bus_type = { */ const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length) { - return of_get_property(vdev->dev.archdata.of_node, which, length); + return of_get_property(vdev->dev.of_node, which, length); } EXPORT_SYMBOL(vio_get_attribute); diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index 689a57c2ac8..73c0a3f64ed 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -147,7 +147,7 @@ static int __init kvmppc_44x_init(void) if (r) return r; - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE); + return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE); } static void __exit kvmppc_44x_exit(void) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 60624cc9f4d..b7baff78f90 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -22,12 +22,34 @@ config KVM select ANON_INODES select KVM_MMIO +config KVM_BOOK3S_HANDLER + bool + +config KVM_BOOK3S_32_HANDLER + bool + select KVM_BOOK3S_HANDLER + config KVM_BOOK3S_64_HANDLER bool + select KVM_BOOK3S_HANDLER + +config KVM_BOOK3S_32 + tristate "KVM support for PowerPC book3s_32 processors" + depends on EXPERIMENTAL && PPC_BOOK3S_32 && !SMP && !PTE_64BIT + select KVM + select KVM_BOOK3S_32_HANDLER + ---help--- + Support running unmodified book3s_32 guest kernels + in virtual machines on book3s_32 host processors. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + If unsure, say N. config KVM_BOOK3S_64 tristate "KVM support for PowerPC book3s_64 processors" - depends on EXPERIMENTAL && PPC64 + depends on EXPERIMENTAL && PPC_BOOK3S_64 select KVM select KVM_BOOK3S_64_HANDLER ---help--- diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 56484d65237..ff436066bf7 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -14,7 +14,7 @@ CFLAGS_emulate.o := -I. common-objs-y += powerpc.o emulate.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o -obj-$(CONFIG_KVM_BOOK3S_64_HANDLER) += book3s_64_exports.o +obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o AFLAGS_booke_interrupts.o := -I$(obj) @@ -40,17 +40,31 @@ kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs) kvm-book3s_64-objs := \ $(common-objs-y) \ + fpu.o \ + book3s_paired_singles.o \ book3s.o \ - book3s_64_emulate.o \ - book3s_64_interrupts.o \ + book3s_emulate.o \ + book3s_interrupts.o \ book3s_64_mmu_host.o \ book3s_64_mmu.o \ book3s_32_mmu.o kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs) +kvm-book3s_32-objs := \ + $(common-objs-y) \ + fpu.o \ + book3s_paired_singles.o \ + book3s.o \ + book3s_emulate.o \ + book3s_interrupts.o \ + book3s_32_mmu_host.o \ + book3s_32_mmu.o +kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) + kvm-objs := $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_440) += kvm.o obj-$(CONFIG_KVM_E500) += kvm.o obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o +obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 604af29b71e..b998abf1a63 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -16,6 +16,7 @@ #include <linux/kvm_host.h> #include <linux/err.h> +#include <linux/slab.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -29,6 +30,7 @@ #include <linux/gfp.h> #include <linux/sched.h> #include <linux/vmalloc.h> +#include <linux/highmem.h> #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU @@ -36,7 +38,15 @@ /* #define EXIT_DEBUG_SIMPLE */ /* #define DEBUG_EXT */ -static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); +static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, + ulong msr); + +/* Some compatibility defines */ +#ifdef CONFIG_PPC_BOOK3S_32 +#define MSR_USER32 MSR_USER +#define MSR_USER64 MSR_USER +#define HW_PAGE_SIZE PAGE_SIZE +#endif struct kvm_stats_debugfs_item debugfs_entries[] = { { "exits", VCPU_STAT(sum_exits) }, @@ -69,18 +79,26 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb)); - memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu, +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb)); + memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu, sizeof(get_paca()->shadow_vcpu)); - get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max; + to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max; +#endif + +#ifdef CONFIG_PPC_BOOK3S_32 + current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu; +#endif } void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { - memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb)); - memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb)); + memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, sizeof(get_paca()->shadow_vcpu)); - to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max; + to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max; +#endif kvmppc_giveup_ext(vcpu, MSR_FP); kvmppc_giveup_ext(vcpu, MSR_VEC); @@ -131,18 +149,22 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) } } - if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) || - (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) { + if ((vcpu->arch.msr & (MSR_PR|MSR_IR|MSR_DR)) != + (old_msr & (MSR_PR|MSR_IR|MSR_DR))) { kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc); + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); } + + /* Preload FPU if it's enabled */ + if (vcpu->arch.msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); } void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { - vcpu->arch.srr0 = vcpu->arch.pc; + vcpu->arch.srr0 = kvmppc_get_pc(vcpu); vcpu->arch.srr1 = vcpu->arch.msr | flags; - vcpu->arch.pc = to_book3s(vcpu)->hior + vec; + kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec); vcpu->arch.mmu.reset_msr(vcpu); } @@ -218,6 +240,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); } +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); +} + int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { int deliver = 1; @@ -302,7 +330,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions); #endif priority = __ffs(*pending); - while (priority <= (sizeof(unsigned int) * 8)) { + while (priority < BOOK3S_IRQPRIO_MAX) { if (kvmppc_book3s_irqprio_deliver(vcpu, priority) && (priority != BOOK3S_IRQPRIO_DECREMENTER)) { /* DEC interrupts get cleared by mtdec */ @@ -318,13 +346,18 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) { + u32 host_pvr; + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; vcpu->arch.pvr = pvr; +#ifdef CONFIG_PPC_BOOK3S_64 if ((pvr >= 0x330000) && (pvr < 0x70330000)) { kvmppc_mmu_book3s_64_init(vcpu); to_book3s(vcpu)->hior = 0xfff00000; to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; - } else { + } else +#endif + { kvmppc_mmu_book3s_32_init(vcpu); to_book3s(vcpu)->hior = 0; to_book3s(vcpu)->msr_mask = 0xffffffffULL; @@ -337,6 +370,32 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) !strcmp(cur_cpu_spec->platform, "ppc970")) vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; + /* Cell performs badly if MSR_FEx are set. So let's hope nobody + really needs them in a VM on Cell and force disable them. */ + if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be")) + to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1); + +#ifdef CONFIG_PPC_BOOK3S_32 + /* 32 bit Book3S always has 32 byte dcbz */ + vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; +#endif + + /* On some CPUs we can execute paired single operations natively */ + asm ( "mfpvr %0" : "=r"(host_pvr)); + switch (host_pvr) { + case 0x00080200: /* lonestar 2.0 */ + case 0x00088202: /* lonestar 2.2 */ + case 0x70000100: /* gekko 1.0 */ + case 0x00080100: /* gekko 2.0 */ + case 0x00083203: /* gekko 2.3a */ + case 0x00083213: /* gekko 2.3b */ + case 0x00083204: /* gekko 2.4 */ + case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ + case 0x00087200: /* broadway */ + vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS; + /* Enable HID2.PSE - in case we need it later */ + mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29)); + } } /* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To @@ -350,34 +409,29 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) */ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) { - bool touched = false; - hva_t hpage; + struct page *hpage; + u64 hpage_offset; u32 *page; int i; - hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT); - if (kvm_is_error_hva(hpage)) + hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT); + if (is_error_page(hpage)) return; - hpage |= pte->raddr & ~PAGE_MASK; - hpage &= ~0xFFFULL; - - page = vmalloc(HW_PAGE_SIZE); - - if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE)) - goto out; + hpage_offset = pte->raddr & ~PAGE_MASK; + hpage_offset &= ~0xFFFULL; + hpage_offset /= 4; - for (i=0; i < HW_PAGE_SIZE / 4; i++) - if ((page[i] & 0xff0007ff) == INS_DCBZ) { - page[i] &= 0xfffffff7; // reserved instruction, so we trap - touched = true; - } + get_page(hpage); + page = kmap_atomic(hpage, KM_USER0); - if (touched) - copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE); + /* patch dcbz into reserved instruction, so we trap */ + for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++) + if ((page[i] & 0xff0007ff) == INS_DCBZ) + page[i] &= 0xfffffff7; -out: - vfree(page); + kunmap_atomic(page, KM_USER0); + put_page(hpage); } static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, @@ -391,15 +445,7 @@ static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, } else { pte->eaddr = eaddr; pte->raddr = eaddr & 0xffffffff; - pte->vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte->vpage |= VSID_REAL; - case MSR_DR: - pte->vpage |= VSID_REAL_DR; - case MSR_IR: - pte->vpage |= VSID_REAL_IR; - } + pte->vpage = VSID_REAL | eaddr >> 12; pte->may_read = true; pte->may_write = true; pte->may_execute = true; @@ -434,55 +480,55 @@ err: return kvmppc_bad_hva(); } -int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr) +int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, + bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; vcpu->stat.st++; - if (kvmppc_xlate(vcpu, eaddr, false, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + return -ENOENT; - hva = kvmppc_pte_to_hva(vcpu, &pte, false); - if (kvm_is_error_hva(hva)) - goto err; + *eaddr = pte.raddr; - if (copy_to_user((void __user *)hva, ptr, size)) { - printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva); - goto err; - } + if (!pte.may_write) + return -EPERM; - return 0; + if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size)) + return EMULATE_DO_MMIO; -err: - return -ENOENT; + return EMULATE_DONE; } -int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, +int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; + hva_t hva = *eaddr; vcpu->stat.ld++; - if (kvmppc_xlate(vcpu, eaddr, data, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + goto nopte; + + *eaddr = pte.raddr; hva = kvmppc_pte_to_hva(vcpu, &pte, true); if (kvm_is_error_hva(hva)) - goto err; + goto mmio; if (copy_from_user(ptr, (void __user *)hva, size)) { printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva); - goto err; + goto mmio; } - return 0; + return EMULATE_DONE; -err: +nopte: return -ENOENT; +mmio: + return EMULATE_DO_MMIO; } static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -499,12 +545,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, int page_found = 0; struct kvmppc_pte pte; bool is_mmio = false; + bool dr = (vcpu->arch.msr & MSR_DR) ? true : false; + bool ir = (vcpu->arch.msr & MSR_IR) ? true : false; + u64 vsid; - if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) { - relocated = (vcpu->arch.msr & MSR_DR); - } else { - relocated = (vcpu->arch.msr & MSR_IR); - } + relocated = data ? dr : ir; /* Resolve real address if translation turned on */ if (relocated) { @@ -516,14 +561,25 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte.raddr = eaddr & 0xffffffff; pte.eaddr = eaddr; pte.vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte.vpage |= VSID_REAL; - case MSR_DR: - pte.vpage |= VSID_REAL_DR; - case MSR_IR: - pte.vpage |= VSID_REAL_IR; - } + } + + switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + case 0: + pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12)); + break; + case MSR_DR: + case MSR_IR: + vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); + + if ((vcpu->arch.msr & (MSR_DR|MSR_IR)) == MSR_DR) + pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12)); + else + pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12)); + pte.vpage |= vsid; + + if (vsid == -1) + page_found = -EINVAL; + break; } if (vcpu->arch.mmu.is_dcbz32(vcpu) && @@ -538,20 +594,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (page_found == -ENOENT) { /* Page not found in guest PTE entries */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr; + vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EPERM) { /* Storage protection */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE; to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT; - vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); + vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EINVAL) { /* Page not found in guest SLB */ - vcpu->arch.dear = vcpu->arch.fault_dear; + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); } else if (!is_mmio && kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { @@ -583,11 +639,13 @@ static inline int get_fpr_index(int i) } /* Give up external provider (FPU, Altivec, VSX) */ -static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) +void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) { struct thread_struct *t = ¤t->thread; u64 *vcpu_fpr = vcpu->arch.fpr; +#ifdef CONFIG_VSX u64 *vcpu_vsx = vcpu->arch.vsr; +#endif u64 *thread_fpr = (u64*)t->fpr; int i; @@ -629,21 +687,65 @@ static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) kvmppc_recalc_shadow_msr(vcpu); } +static int kvmppc_read_inst(struct kvm_vcpu *vcpu) +{ + ulong srr0 = kvmppc_get_pc(vcpu); + u32 last_inst = kvmppc_get_last_inst(vcpu); + int ret; + + ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false); + if (ret == -ENOENT) { + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 33, 1); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 34, 36, 0); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0); + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE); + return EMULATE_AGAIN; + } + + return EMULATE_DONE; +} + +static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr) +{ + + /* Need to do paired single emulation? */ + if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) + return EMULATE_DONE; + + /* Read out the instruction */ + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) + /* Need to emulate */ + return EMULATE_FAIL; + + return EMULATE_AGAIN; +} + /* Handle external providers (FPU, Altivec, VSX) */ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, ulong msr) { struct thread_struct *t = ¤t->thread; u64 *vcpu_fpr = vcpu->arch.fpr; +#ifdef CONFIG_VSX u64 *vcpu_vsx = vcpu->arch.vsr; +#endif u64 *thread_fpr = (u64*)t->fpr; int i; + /* When we have paired singles, we emulate in software */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) + return RESUME_GUEST; + if (!(vcpu->arch.msr & msr)) { kvmppc_book3s_queue_irqprio(vcpu, exit_nr); return RESUME_GUEST; } + /* We already own the ext */ + if (vcpu->arch.guest_owned_ext & msr) { + return RESUME_GUEST; + } + #ifdef DEBUG_EXT printk(KERN_INFO "Loading up ext 0x%lx\n", msr); #endif @@ -696,21 +798,33 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; #ifdef EXIT_DEBUG printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, - kvmppc_get_dec(vcpu), vcpu->arch.msr); + exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu), + kvmppc_get_dec(vcpu), to_svcpu(vcpu)->shadow_srr1); #elif defined (EXIT_DEBUG_SIMPLE) if ((exit_nr != 0x900) && (exit_nr != 0x500)) printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, + exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu), vcpu->arch.msr); #endif kvm_resched(vcpu); switch (exit_nr) { case BOOK3S_INTERRUPT_INST_STORAGE: vcpu->stat.pf_instruc++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] + == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); + r = RESUME_GUEST; + break; + } +#endif + /* only care about PTEG not found errors, but leave NX alone */ - if (vcpu->arch.shadow_srr1 & 0x40000000) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr); + if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) { + r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr); vcpu->stat.sp_instruc++; } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { @@ -719,37 +833,52 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, * so we can't use the NX bit inside the guest. Let's cross our fingers, * that no guest that needs the dcbz hack does NX. */ - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); + r = RESUME_GUEST; } else { - vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000; + vcpu->arch.msr |= to_svcpu(vcpu)->shadow_srr1 & 0x58000000; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); r = RESUME_GUEST; } break; case BOOK3S_INTERRUPT_DATA_STORAGE: + { + ulong dar = kvmppc_get_fault_dar(vcpu); vcpu->stat.pf_storage++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, dar); + r = RESUME_GUEST; + break; + } +#endif + /* The only case we need to handle is missing shadow PTEs */ - if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr); + if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) { + r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr); } else { - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; + vcpu->arch.dear = dar; + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL); r = RESUME_GUEST; } break; + } case BOOK3S_INTERRUPT_DATA_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) { - vcpu->arch.dear = vcpu->arch.fault_dear; + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) { + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_SEGMENT); } r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_INST_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) { + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) { kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_SEGMENT); } @@ -764,18 +893,22 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + case BOOK3S_INTERRUPT_PERFMON: + r = RESUME_GUEST; + break; case BOOK3S_INTERRUPT_PROGRAM: { enum emulation_result er; ulong flags; - flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; +program_interrupt: + flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull; if (vcpu->arch.msr & MSR_PR) { #ifdef EXIT_DEBUG - printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst); + printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); #endif - if ((vcpu->arch.last_inst & 0xff0007ff) != + if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; @@ -789,33 +922,80 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case EMULATE_DONE: r = RESUME_GUEST_NV; break; + case EMULATE_AGAIN: + r = RESUME_GUEST; + break; case EMULATE_FAIL: printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, vcpu->arch.pc, vcpu->arch.last_inst); + __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST_NV; + break; default: BUG(); } break; } case BOOK3S_INTERRUPT_SYSCALL: -#ifdef EXIT_DEBUG - printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0)); -#endif - vcpu->stat.syscall_exits++; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; + // XXX make user settable + if (vcpu->arch.osi_enabled && + (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) && + (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) { + u64 *gprs = run->osi.gprs; + int i; + + run->exit_reason = KVM_EXIT_OSI; + for (i = 0; i < 32; i++) + gprs[i] = kvmppc_get_gpr(vcpu, i); + vcpu->arch.osi_needed = 1; + r = RESUME_HOST_NV; + + } else { + vcpu->stat.syscall_exits++; + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + r = RESUME_GUEST; + } break; case BOOK3S_INTERRUPT_FP_UNAVAIL: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP); - break; case BOOK3S_INTERRUPT_ALTIVEC: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC); - break; case BOOK3S_INTERRUPT_VSX: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX); + { + int ext_msr = 0; + + switch (exit_nr) { + case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP; break; + case BOOK3S_INTERRUPT_ALTIVEC: ext_msr = MSR_VEC; break; + case BOOK3S_INTERRUPT_VSX: ext_msr = MSR_VSX; break; + } + + switch (kvmppc_check_ext(vcpu, exit_nr)) { + case EMULATE_DONE: + /* everything ok - let's enable the ext */ + r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr); + break; + case EMULATE_FAIL: + /* we need to emulate this instruction */ + goto program_interrupt; + break; + default: + /* nothing to worry about - go again */ + break; + } + break; + } + case BOOK3S_INTERRUPT_ALIGNMENT: + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) { + to_book3s(vcpu)->dsisr = kvmppc_alignment_dsisr(vcpu, + kvmppc_get_last_inst(vcpu)); + vcpu->arch.dear = kvmppc_alignment_dar(vcpu, + kvmppc_get_last_inst(vcpu)); + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + } + r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_MACHINE_CHECK: case BOOK3S_INTERRUPT_TRACE: @@ -825,7 +1005,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, default: /* Ugh - bork here! What did we get? */ printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1); + exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1); r = RESUME_HOST; BUG(); break; @@ -852,7 +1032,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } #ifdef EXIT_DEBUG - printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r); + printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, kvmppc_get_pc(vcpu), r); #endif return r; @@ -867,10 +1047,12 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; - regs->pc = vcpu->arch.pc; + vcpu_load(vcpu); + + regs->pc = kvmppc_get_pc(vcpu); regs->cr = kvmppc_get_cr(vcpu); - regs->ctr = vcpu->arch.ctr; - regs->lr = vcpu->arch.lr; + regs->ctr = kvmppc_get_ctr(vcpu); + regs->lr = kvmppc_get_lr(vcpu); regs->xer = kvmppc_get_xer(vcpu); regs->msr = vcpu->arch.msr; regs->srr0 = vcpu->arch.srr0; @@ -887,6 +1069,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) regs->gpr[i] = kvmppc_get_gpr(vcpu, i); + vcpu_put(vcpu); + return 0; } @@ -894,10 +1078,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; - vcpu->arch.pc = regs->pc; + vcpu_load(vcpu); + + kvmppc_set_pc(vcpu, regs->pc); kvmppc_set_cr(vcpu, regs->cr); - vcpu->arch.ctr = regs->ctr; - vcpu->arch.lr = regs->lr; + kvmppc_set_ctr(vcpu, regs->ctr); + kvmppc_set_lr(vcpu, regs->lr); kvmppc_set_xer(vcpu, regs->xer); kvmppc_set_msr(vcpu, regs->msr); vcpu->arch.srr0 = regs->srr0; @@ -913,6 +1099,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) kvmppc_set_gpr(vcpu, i, regs->gpr[i]); + vcpu_put(vcpu); + return 0; } @@ -922,6 +1110,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int i; + vcpu_load(vcpu); + sregs->pvr = vcpu->arch.pvr; sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1; @@ -940,6 +1130,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw; } } + + vcpu_put(vcpu); + return 0; } @@ -949,6 +1142,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int i; + vcpu_load(vcpu); + kvmppc_set_pvr(vcpu, sregs->pvr); vcpu3s->sdr1 = sregs->u.s.sdr1; @@ -975,6 +1170,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, /* Flush the MMU after messing with the segments */ kvmppc_mmu_pte_flush(vcpu, 0, 0); + + vcpu_put(vcpu); + return 0; } @@ -1042,24 +1240,33 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_book3s *vcpu_book3s; struct kvm_vcpu *vcpu; - int err; + int err = -ENOMEM; - vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, - get_order(sizeof(struct kvmppc_vcpu_book3s))); - if (!vcpu_book3s) { - err = -ENOMEM; + vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s)); + if (!vcpu_book3s) goto out; - } + + memset(vcpu_book3s, 0, sizeof(struct kvmppc_vcpu_book3s)); + + vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) + kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); + if (!vcpu_book3s->shadow_vcpu) + goto free_vcpu; vcpu = &vcpu_book3s->vcpu; err = kvm_vcpu_init(vcpu, kvm, id); if (err) - goto free_vcpu; + goto free_shadow_vcpu; vcpu->arch.host_retip = kvm_return_point; vcpu->arch.host_msr = mfmsr(); +#ifdef CONFIG_PPC_BOOK3S_64 /* default to book3s_64 (970fx) */ vcpu->arch.pvr = 0x3C0301; +#else + /* default to book3s_32 (750) */ + vcpu->arch.pvr = 0x84202; +#endif kvmppc_set_pvr(vcpu, vcpu->arch.pvr); vcpu_book3s->slb_nr = 64; @@ -1067,23 +1274,24 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; +#ifdef CONFIG_PPC_BOOK3S_64 vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; +#else + vcpu->arch.rmcall = (ulong)kvmppc_rmcall; +#endif vcpu->arch.shadow_msr = MSR_USER64; - err = __init_new_context(); + err = kvmppc_mmu_init(vcpu); if (err < 0) - goto free_vcpu; - vcpu_book3s->context_id = err; - - vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1; - vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS; - vcpu_book3s->vsid_next = vcpu_book3s->vsid_first; + goto free_shadow_vcpu; return vcpu; +free_shadow_vcpu: + kfree(vcpu_book3s->shadow_vcpu); free_vcpu: - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); + vfree(vcpu_book3s); out: return ERR_PTR(err); } @@ -1092,9 +1300,9 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); - __destroy_context(vcpu_book3s->context_id); kvm_vcpu_uninit(vcpu); - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); + kfree(vcpu_book3s->shadow_vcpu); + vfree(vcpu_book3s); } extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -1102,8 +1310,12 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; struct thread_struct ext_bkp; +#ifdef CONFIG_ALTIVEC bool save_vec = current->thread.used_vr; +#endif +#ifdef CONFIG_VSX bool save_vsx = current->thread.used_vsr; +#endif ulong ext_msr; /* No need to go into the guest when all we do is going out */ @@ -1144,6 +1356,10 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* XXX we get called with irq disabled - change that! */ local_irq_enable(); + /* Preload FPU if it's enabled */ + if (vcpu->arch.msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); + ret = __kvmppc_vcpu_entry(kvm_run, vcpu); local_irq_disable(); @@ -1179,7 +1395,8 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) static int kvmppc_book3s_init(void) { - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), THIS_MODULE); + return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0, + THIS_MODULE); } static void kvmppc_book3s_exit(void) diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index faf99f20d99..0b10503c8a4 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -37,7 +37,7 @@ #define dprintk(X...) do { } while(0) #endif -#ifdef DEBUG_PTE +#ifdef DEBUG_MMU_PTE #define dprintk_pte(X...) printk(KERN_INFO X) #else #define dprintk_pte(X...) do { } while(0) @@ -45,6 +45,9 @@ #define PTEG_FLAG_ACCESSED 0x00000100 #define PTEG_FLAG_DIRTY 0x00000080 +#ifndef SID_SHIFT +#define SID_SHIFT 28 +#endif static inline bool check_debug_ip(struct kvm_vcpu *vcpu) { @@ -57,6 +60,8 @@ static inline bool check_debug_ip(struct kvm_vcpu *vcpu) static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data); +static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, + u64 *vsid); static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr) { @@ -66,13 +71,14 @@ static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t e static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, bool data) { - struct kvmppc_sr *sre = find_sr(to_book3s(vcpu), eaddr); + u64 vsid; struct kvmppc_pte pte; if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data)) return pte.vpage; - return (((u64)eaddr >> 12) & 0xffff) | (((u64)sre->vsid) << 16); + kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); + return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16); } static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu) @@ -142,8 +148,13 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, bat->bepi_mask); } if ((eaddr & bat->bepi_mask) == bat->bepi) { + u64 vsid; + kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, + eaddr >> SID_SHIFT, &vsid); + vsid <<= 16; + pte->vpage = (((u64)eaddr >> 12) & 0xffff) | vsid; + pte->raddr = bat->brpn | (eaddr & ~bat->bepi_mask); - pte->vpage = (eaddr >> 12) | VSID_BAT; pte->may_read = bat->pp; pte->may_write = bat->pp > 1; pte->may_execute = true; @@ -172,7 +183,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_sr *sre; hva_t ptegp; u32 pteg[16]; - u64 ptem = 0; + u32 ptem = 0; int i; int found = 0; @@ -302,6 +313,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, /* And then put in the new SR */ sre->raw = value; sre->vsid = (value & 0x0fffffff); + sre->valid = (value & 0x80000000) ? false : true; sre->Ks = (value & 0x40000000) ? true : false; sre->Kp = (value & 0x20000000) ? true : false; sre->nx = (value & 0x10000000) ? true : false; @@ -312,36 +324,48 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - kvmppc_mmu_pte_flush(vcpu, ea, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000); } -static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid, +static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid) { + ulong ea = esid << SID_SHIFT; + struct kvmppc_sr *sr; + u64 gvsid = esid; + + if (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + sr = find_sr(to_book3s(vcpu), ea); + if (sr->valid) + gvsid = sr->vsid; + } + /* In case we only have one of MSR_IR or MSR_DR set, let's put that in the real-mode context (and hope RM doesn't access high memory) */ switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { case 0: - *vsid = (VSID_REAL >> 16) | esid; + *vsid = VSID_REAL | esid; break; case MSR_IR: - *vsid = (VSID_REAL_IR >> 16) | esid; + *vsid = VSID_REAL_IR | gvsid; break; case MSR_DR: - *vsid = (VSID_REAL_DR >> 16) | esid; + *vsid = VSID_REAL_DR | gvsid; break; case MSR_DR|MSR_IR: - { - ulong ea; - ea = esid << SID_SHIFT; - *vsid = find_sr(to_book3s(vcpu), ea)->vsid; + if (!sr->valid) + return -1; + + *vsid = sr->vsid; break; - } default: BUG(); } + if (vcpu->arch.msr & MSR_PR) + *vsid |= VSID_PR; + return 0; } diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c new file mode 100644 index 00000000000..0bb66005338 --- /dev/null +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -0,0 +1,483 @@ +/* + * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved. + * + * Authors: + * Alexander Graf <agraf@suse.de> + * + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include <linux/kvm_host.h> + +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash32.h> +#include <asm/machdep.h> +#include <asm/mmu_context.h> +#include <asm/hw_irq.h> + +/* #define DEBUG_MMU */ +/* #define DEBUG_SR */ + +#ifdef DEBUG_MMU +#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__) +#else +#define dprintk_mmu(a, ...) do { } while(0) +#endif + +#ifdef DEBUG_SR +#define dprintk_sr(a, ...) printk(KERN_INFO a, __VA_ARGS__) +#else +#define dprintk_sr(a, ...) do { } while(0) +#endif + +#if PAGE_SHIFT != 12 +#error Unknown page size +#endif + +#ifdef CONFIG_SMP +#error XXX need to grab mmu_hash_lock +#endif + +#ifdef CONFIG_PTE_64BIT +#error Only 32 bit pages are supported for now +#endif + +static ulong htab; +static u32 htabmask; + +static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) +{ + volatile u32 *pteg; + + dprintk_mmu("KVM: Flushing SPTE: 0x%llx (0x%llx) -> 0x%llx\n", + pte->pte.eaddr, pte->pte.vpage, pte->host_va); + + pteg = (u32*)pte->slot; + + pteg[0] = 0; + asm volatile ("sync"); + asm volatile ("tlbie %0" : : "r" (pte->pte.eaddr) : "memory"); + asm volatile ("sync"); + asm volatile ("tlbsync"); + + pte->host_va = 0; + + if (pte->pte.may_write) + kvm_release_pfn_dirty(pte->pfn); + else + kvm_release_pfn_clean(pte->pfn); +} + +void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%x & 0x%x\n", + vcpu->arch.hpte_cache_offset, guest_ea, ea_mask); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + guest_ea &= ea_mask; + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.eaddr & ea_mask) == guest_ea) { + invalidate_pte(vcpu, pte); + } + } + + /* Doing a complete flush -> start from scratch */ + if (!ea_mask) + vcpu->arch.hpte_cache_offset = 0; +} + +void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n", + vcpu->arch.hpte_cache_offset, guest_vp, vp_mask); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + guest_vp &= vp_mask; + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.vpage & vp_mask) == guest_vp) { + invalidate_pte(vcpu, pte); + } + } +} + +void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n", + vcpu->arch.hpte_cache_offset, pa_start, pa_end); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.raddr >= pa_start) && + (pte->pte.raddr < pa_end)) { + invalidate_pte(vcpu, pte); + } + } +} + +struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data) +{ + int i; + u64 guest_vp; + + guest_vp = vcpu->arch.mmu.ea_to_vp(vcpu, ea, false); + for (i=0; i<vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if (pte->pte.vpage == guest_vp) + return &pte->pte; + } + + return NULL; +} + +static int kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.hpte_cache_offset == HPTEG_CACHE_NUM) + kvmppc_mmu_pte_flush(vcpu, 0, 0); + + return vcpu->arch.hpte_cache_offset++; +} + +/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using + * a hash, so we don't waste cycles on looping */ +static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid) +{ + return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK)); +} + + +static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) +{ + struct kvmppc_sid_map *map; + u16 sid_map_mask; + + if (vcpu->arch.msr & MSR_PR) + gvsid |= VSID_PR; + + sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); + map = &to_book3s(vcpu)->sid_map[sid_map_mask]; + if (map->guest_vsid == gvsid) { + dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n", + gvsid, map->host_vsid); + return map; + } + + map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask]; + if (map->guest_vsid == gvsid) { + dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n", + gvsid, map->host_vsid); + return map; + } + + dprintk_sr("SR: Searching 0x%llx -> not found\n", gvsid); + return NULL; +} + +static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr, + bool primary) +{ + u32 page, hash; + ulong pteg = htab; + + page = (eaddr & ~ESID_MASK) >> 12; + + hash = ((vsid ^ page) << 6); + if (!primary) + hash = ~hash; + + hash &= htabmask; + + pteg |= hash; + + dprintk_mmu("htab: %lx | hash: %x | htabmask: %x | pteg: %lx\n", + htab, hash, htabmask, pteg); + + return (u32*)pteg; +} + +extern char etext[]; + +int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) +{ + pfn_t hpaddr; + u64 va; + u64 vsid; + struct kvmppc_sid_map *map; + volatile u32 *pteg; + u32 eaddr = orig_pte->eaddr; + u32 pteg0, pteg1; + register int rr = 0; + bool primary = false; + bool evict = false; + int hpte_id; + struct hpte_cache *pte; + + /* Get host physical address for gpa */ + hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + if (kvm_is_error_hva(hpaddr)) { + printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", + orig_pte->eaddr); + return -EINVAL; + } + hpaddr <<= PAGE_SHIFT; + + /* and write the mapping ea -> hpa into the pt */ + vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid); + map = find_sid_vsid(vcpu, vsid); + if (!map) { + kvmppc_mmu_map_segment(vcpu, eaddr); + map = find_sid_vsid(vcpu, vsid); + } + BUG_ON(!map); + + vsid = map->host_vsid; + va = (vsid << SID_SHIFT) | (eaddr & ~ESID_MASK); + +next_pteg: + if (rr == 16) { + primary = !primary; + evict = true; + rr = 0; + } + + pteg = kvmppc_mmu_get_pteg(vcpu, vsid, eaddr, primary); + + /* not evicting yet */ + if (!evict && (pteg[rr] & PTE_V)) { + rr += 2; + goto next_pteg; + } + + dprintk_mmu("KVM: old PTEG: %p (%d)\n", pteg, rr); + dprintk_mmu("KVM: %08x - %08x\n", pteg[0], pteg[1]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[2], pteg[3]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[4], pteg[5]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[6], pteg[7]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[8], pteg[9]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[10], pteg[11]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[12], pteg[13]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[14], pteg[15]); + + pteg0 = ((eaddr & 0x0fffffff) >> 22) | (vsid << 7) | PTE_V | + (primary ? 0 : PTE_SEC); + pteg1 = hpaddr | PTE_M | PTE_R | PTE_C; + + if (orig_pte->may_write) { + pteg1 |= PP_RWRW; + mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + } else { + pteg1 |= PP_RWRX; + } + + local_irq_disable(); + + if (pteg[rr]) { + pteg[rr] = 0; + asm volatile ("sync"); + } + pteg[rr + 1] = pteg1; + pteg[rr] = pteg0; + asm volatile ("sync"); + + local_irq_enable(); + + dprintk_mmu("KVM: new PTEG: %p\n", pteg); + dprintk_mmu("KVM: %08x - %08x\n", pteg[0], pteg[1]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[2], pteg[3]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[4], pteg[5]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[6], pteg[7]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[8], pteg[9]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[10], pteg[11]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[12], pteg[13]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[14], pteg[15]); + + + /* Now tell our Shadow PTE code about the new page */ + + hpte_id = kvmppc_mmu_hpte_cache_next(vcpu); + pte = &vcpu->arch.hpte_cache[hpte_id]; + + dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n", + orig_pte->may_write ? 'w' : '-', + orig_pte->may_execute ? 'x' : '-', + orig_pte->eaddr, (ulong)pteg, va, + orig_pte->vpage, hpaddr); + + pte->slot = (ulong)&pteg[rr]; + pte->host_va = va; + pte->pte = *orig_pte; + pte->pfn = hpaddr >> PAGE_SHIFT; + + return 0; +} + +static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) +{ + struct kvmppc_sid_map *map; + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + u16 sid_map_mask; + static int backwards_map = 0; + + if (vcpu->arch.msr & MSR_PR) + gvsid |= VSID_PR; + + /* We might get collisions that trap in preceding order, so let's + map them differently */ + + sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); + if (backwards_map) + sid_map_mask = SID_MAP_MASK - sid_map_mask; + + map = &to_book3s(vcpu)->sid_map[sid_map_mask]; + + /* Make sure we're taking the other map next time */ + backwards_map = !backwards_map; + + /* Uh-oh ... out of mappings. Let's flush! */ + if (vcpu_book3s->vsid_next >= vcpu_book3s->vsid_max) { + vcpu_book3s->vsid_next = vcpu_book3s->vsid_first; + memset(vcpu_book3s->sid_map, 0, + sizeof(struct kvmppc_sid_map) * SID_MAP_NUM); + kvmppc_mmu_pte_flush(vcpu, 0, 0); + kvmppc_mmu_flush_segments(vcpu); + } + map->host_vsid = vcpu_book3s->vsid_next; + + /* Would have to be 111 to be completely aligned with the rest of + Linux, but that is just way too little space! */ + vcpu_book3s->vsid_next+=1; + + map->guest_vsid = gvsid; + map->valid = true; + + return map; +} + +int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) +{ + u32 esid = eaddr >> SID_SHIFT; + u64 gvsid; + u32 sr; + struct kvmppc_sid_map *map; + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) { + /* Invalidate an entry */ + svcpu->sr[esid] = SR_INVALID; + return -ENOENT; + } + + map = find_sid_vsid(vcpu, gvsid); + if (!map) + map = create_sid_map(vcpu, gvsid); + + map->guest_esid = esid; + sr = map->host_vsid | SR_KP; + svcpu->sr[esid] = sr; + + dprintk_sr("MMU: mtsr %d, 0x%x\n", esid, sr); + + return 0; +} + +void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) +{ + int i; + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + dprintk_sr("MMU: flushing all segments (%d)\n", ARRAY_SIZE(svcpu->sr)); + for (i = 0; i < ARRAY_SIZE(svcpu->sr); i++) + svcpu->sr[i] = SR_INVALID; +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + kvmppc_mmu_pte_flush(vcpu, 0, 0); + preempt_disable(); + __destroy_context(to_book3s(vcpu)->context_id); + preempt_enable(); +} + +/* From mm/mmu_context_hash32.c */ +#define CTX_TO_VSID(ctx) (((ctx) * (897 * 16)) & 0xffffff) + +int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int err; + ulong sdr1; + + err = __init_new_context(); + if (err < 0) + return -1; + vcpu3s->context_id = err; + + vcpu3s->vsid_max = CTX_TO_VSID(vcpu3s->context_id + 1) - 1; + vcpu3s->vsid_first = CTX_TO_VSID(vcpu3s->context_id); + +#if 0 /* XXX still doesn't guarantee uniqueness */ + /* We could collide with the Linux vsid space because the vsid + * wraps around at 24 bits. We're safe if we do our own space + * though, so let's always set the highest bit. */ + + vcpu3s->vsid_max |= 0x00800000; + vcpu3s->vsid_first |= 0x00800000; +#endif + BUG_ON(vcpu3s->vsid_max < vcpu3s->vsid_first); + + vcpu3s->vsid_next = vcpu3s->vsid_first; + + /* Remember where the HTAB is */ + asm ( "mfsdr1 %0" : "=r"(sdr1) ); + htabmask = ((sdr1 & 0x1FF) << 16) | 0xFFC0; + htab = (ulong)__va(sdr1 & 0xffff0000); + + return 0; +} diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S new file mode 100644 index 00000000000..3608471ad2d --- /dev/null +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -0,0 +1,143 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2009 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + +.macro LOAD_GUEST_SEGMENTS + + /* Required state: + * + * MSR = ~IR|DR + * R1 = host R1 + * R2 = host R2 + * R3 = shadow vcpu + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + */ + +#define XCHG_SR(n) lwz r9, (SVCPU_SR+(n*4))(r3); \ + mtsr n, r9 + + XCHG_SR(0) + XCHG_SR(1) + XCHG_SR(2) + XCHG_SR(3) + XCHG_SR(4) + XCHG_SR(5) + XCHG_SR(6) + XCHG_SR(7) + XCHG_SR(8) + XCHG_SR(9) + XCHG_SR(10) + XCHG_SR(11) + XCHG_SR(12) + XCHG_SR(13) + XCHG_SR(14) + XCHG_SR(15) + + /* Clear BATs. */ + +#define KVM_KILL_BAT(n, reg) \ + mtspr SPRN_IBAT##n##U,reg; \ + mtspr SPRN_IBAT##n##L,reg; \ + mtspr SPRN_DBAT##n##U,reg; \ + mtspr SPRN_DBAT##n##L,reg; \ + + li r9, 0 + KVM_KILL_BAT(0, r9) + KVM_KILL_BAT(1, r9) + KVM_KILL_BAT(2, r9) + KVM_KILL_BAT(3, r9) + +.endm + +/****************************************************************************** + * * + * Exit code * + * * + *****************************************************************************/ + +.macro LOAD_HOST_SEGMENTS + + /* Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF + * SVCPU.* = guest * + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + * + */ + + /* Restore BATs */ + + /* We only overwrite the upper part, so we only restoree + the upper part. */ +#define KVM_LOAD_BAT(n, reg, RA, RB) \ + lwz RA,(n*16)+0(reg); \ + lwz RB,(n*16)+4(reg); \ + mtspr SPRN_IBAT##n##U,RA; \ + mtspr SPRN_IBAT##n##L,RB; \ + lwz RA,(n*16)+8(reg); \ + lwz RB,(n*16)+12(reg); \ + mtspr SPRN_DBAT##n##U,RA; \ + mtspr SPRN_DBAT##n##L,RB; \ + + lis r9, BATS@ha + addi r9, r9, BATS@l + tophys(r9, r9) + KVM_LOAD_BAT(0, r9, r10, r11) + KVM_LOAD_BAT(1, r9, r10, r11) + KVM_LOAD_BAT(2, r9, r10, r11) + KVM_LOAD_BAT(3, r9, r10, r11) + + /* Restore Segment Registers */ + + /* 0xc - 0xf */ + + li r0, 4 + mtctr r0 + LOAD_REG_IMMEDIATE(r3, 0x20000000 | (0x111 * 0xc)) + lis r4, 0xc000 +3: mtsrin r3, r4 + addi r3, r3, 0x111 /* increment VSID */ + addis r4, r4, 0x1000 /* address of next segment */ + bdnz 3b + + /* 0x0 - 0xb */ + + /* 'current->mm' needs to be in r4 */ + tophys(r4, r2) + lwz r4, MM(r4) + tophys(r4, r4) + /* This only clobbers r0, r3, r4 and r5 */ + bl switch_mmu_context + +.endm diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 512dcff7755..4025ea26b3c 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -232,7 +232,7 @@ do_second: } dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx " - "-> 0x%llx\n", + "-> 0x%lx\n", eaddr, avpn, gpte->vpage, gpte->raddr); found = true; break; @@ -383,7 +383,7 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu) if (vcpu->arch.msr & MSR_IR) { kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc); + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); } } @@ -439,37 +439,43 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask); } -static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid, +static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid) { + ulong ea = esid << SID_SHIFT; + struct kvmppc_slb *slb; + u64 gvsid = esid; + + if (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea); + if (slb) + gvsid = slb->vsid; + } + switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { case 0: - *vsid = (VSID_REAL >> 16) | esid; + *vsid = VSID_REAL | esid; break; case MSR_IR: - *vsid = (VSID_REAL_IR >> 16) | esid; + *vsid = VSID_REAL_IR | gvsid; break; case MSR_DR: - *vsid = (VSID_REAL_DR >> 16) | esid; + *vsid = VSID_REAL_DR | gvsid; break; case MSR_DR|MSR_IR: - { - ulong ea; - struct kvmppc_slb *slb; - ea = esid << SID_SHIFT; - slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea); - if (slb) - *vsid = slb->vsid; - else + if (!slb) return -ENOENT; + *vsid = gvsid; break; - } default: BUG(); break; } + if (vcpu->arch.msr & MSR_PR) + *vsid |= VSID_PR; + return 0; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index f2899b297ff..e4b5744977f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -48,21 +48,25 @@ static void invalidate_pte(struct hpte_cache *pte) { - dprintk_mmu("KVM: Flushing SPT %d: 0x%llx (0x%llx) -> 0x%llx\n", - i, pte->pte.eaddr, pte->pte.vpage, pte->host_va); + dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n", + pte->pte.eaddr, pte->pte.vpage, pte->host_va); ppc_md.hpte_invalidate(pte->slot, pte->host_va, MMU_PAGE_4K, MMU_SEGSIZE_256M, false); pte->host_va = 0; - kvm_release_pfn_dirty(pte->pfn); + + if (pte->pte.may_write) + kvm_release_pfn_dirty(pte->pfn); + else + kvm_release_pfn_clean(pte->pfn); } -void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 guest_ea, u64 ea_mask) +void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask) { int i; - dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%llx & 0x%llx\n", + dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n", vcpu->arch.hpte_cache_offset, guest_ea, ea_mask); BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); @@ -106,12 +110,12 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) } } -void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end) +void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) { int i; - dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n", - vcpu->arch.hpte_cache_offset, guest_pa, pa_mask); + dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx & 0x%lx\n", + vcpu->arch.hpte_cache_offset, pa_start, pa_end); BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { @@ -182,7 +186,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); map = &to_book3s(vcpu)->sid_map[sid_map_mask]; if (map->guest_vsid == gvsid) { - dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n", + dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n", gvsid, map->host_vsid); return map; } @@ -194,7 +198,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) return map; } - dprintk_slb("SLB: Searching 0x%llx -> not found\n", gvsid); + dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n", + sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid); return NULL; } @@ -212,7 +217,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) /* Get host physical address for gpa */ hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); if (kvm_is_error_hva(hpaddr)) { - printk(KERN_INFO "Couldn't get guest page for gfn %llx!\n", orig_pte->eaddr); + printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr); return -EINVAL; } hpaddr <<= PAGE_SHIFT; @@ -227,10 +232,16 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid); map = find_sid_vsid(vcpu, vsid); if (!map) { - kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr); + ret = kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr); + WARN_ON(ret < 0); map = find_sid_vsid(vcpu, vsid); } - BUG_ON(!map); + if (!map) { + printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n", + vsid, orig_pte->eaddr); + WARN_ON(true); + return -EINVAL; + } vsid = map->host_vsid; va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M); @@ -257,26 +268,26 @@ map_again: if (ret < 0) { /* If we couldn't map a primary PTE, try a secondary */ -#ifdef USE_SECONDARY hash = ~hash; + vflags ^= HPTE_V_SECONDARY; attempt++; - if (attempt % 2) - vflags = HPTE_V_SECONDARY; - else - vflags = 0; -#else - attempt = 2; -#endif goto map_again; } else { int hpte_id = kvmppc_mmu_hpte_cache_next(vcpu); struct hpte_cache *pte = &vcpu->arch.hpte_cache[hpte_id]; - dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%lx (0x%llx) -> %lx\n", + dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n", ((rflags & HPTE_R_PP) == 3) ? '-' : 'w', (rflags & HPTE_R_N) ? '-' : 'x', orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr); + /* The ppc_md code may give us a secondary entry even though we + asked for a primary. Fix up. */ + if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) { + hash = ~hash; + hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); + } + pte->slot = hpteg + (ret & 7); pte->host_va = va; pte->pte = *orig_pte; @@ -321,6 +332,9 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) map->guest_vsid = gvsid; map->valid = true; + dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n", + sid_map_mask, gvsid, map->host_vsid); + return map; } @@ -331,14 +345,14 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid) int found_inval = -1; int r; - if (!get_paca()->kvm_slb_max) - get_paca()->kvm_slb_max = 1; + if (!to_svcpu(vcpu)->slb_max) + to_svcpu(vcpu)->slb_max = 1; /* Are we overwriting? */ - for (i = 1; i < get_paca()->kvm_slb_max; i++) { - if (!(get_paca()->kvm_slb[i].esid & SLB_ESID_V)) + for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) { + if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V)) found_inval = i; - else if ((get_paca()->kvm_slb[i].esid & ESID_MASK) == esid) + else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid) return i; } @@ -352,11 +366,11 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid) max_slb_size = mmu_slb_size; /* Overflowing -> purge */ - if ((get_paca()->kvm_slb_max) == max_slb_size) + if ((to_svcpu(vcpu)->slb_max) == max_slb_size) kvmppc_mmu_flush_segments(vcpu); - r = get_paca()->kvm_slb_max; - get_paca()->kvm_slb_max++; + r = to_svcpu(vcpu)->slb_max; + to_svcpu(vcpu)->slb_max++; return r; } @@ -374,7 +388,7 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) { /* Invalidate an entry */ - get_paca()->kvm_slb[slb_index].esid = 0; + to_svcpu(vcpu)->slb[slb_index].esid = 0; return -ENOENT; } @@ -388,8 +402,8 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) slb_vsid &= ~SLB_VSID_KP; slb_esid |= slb_index; - get_paca()->kvm_slb[slb_index].esid = slb_esid; - get_paca()->kvm_slb[slb_index].vsid = slb_vsid; + to_svcpu(vcpu)->slb[slb_index].esid = slb_esid; + to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid; dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid); @@ -398,11 +412,29 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) { - get_paca()->kvm_slb_max = 1; - get_paca()->kvm_slb[0].esid = 0; + to_svcpu(vcpu)->slb_max = 1; + to_svcpu(vcpu)->slb[0].esid = 0; } void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) { kvmppc_mmu_pte_flush(vcpu, 0, 0); + __destroy_context(to_book3s(vcpu)->context_id); +} + +int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int err; + + err = __init_new_context(); + if (err < 0) + return -1; + vcpu3s->context_id = err; + + vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1; + vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS; + vcpu3s->vsid_next = vcpu3s->vsid_first; + + return 0; } diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 35b76272218..04e7d3bbfe8 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -44,8 +44,7 @@ slb_exit_skip_ ## num: * * *****************************************************************************/ -.global kvmppc_handler_trampoline_enter -kvmppc_handler_trampoline_enter: +.macro LOAD_GUEST_SEGMENTS /* Required state: * @@ -53,20 +52,14 @@ kvmppc_handler_trampoline_enter: * R13 = PACA * R1 = host R1 * R2 = host R2 - * R9 = guest IP - * R10 = guest MSR - * all other GPRS = free - * PACA[KVM_CR] = guest CR - * PACA[KVM_XER] = guest XER + * R3 = shadow vcpu + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR */ - mtsrr0 r9 - mtsrr1 r10 - - /* Activate guest mode, so faults get handled by KVM */ - li r11, KVM_GUEST_MODE_GUEST - stb r11, PACA_KVM_IN_GUEST(r13) - /* Remove LPAR shadow entries */ #if SLB_NUM_BOLTED == 3 @@ -101,14 +94,14 @@ kvmppc_handler_trampoline_enter: /* Fill SLB with our shadow */ - lbz r12, PACA_KVM_SLB_MAX(r13) + lbz r12, SVCPU_SLB_MAX(r3) mulli r12, r12, 16 - addi r12, r12, PACA_KVM_SLB - add r12, r12, r13 + addi r12, r12, SVCPU_SLB + add r12, r12, r3 /* for (r11 = kvm_slb; r11 < kvm_slb + kvm_slb_size; r11+=slb_entry) */ - li r11, PACA_KVM_SLB - add r11, r11, r13 + li r11, SVCPU_SLB + add r11, r11, r3 slb_loop_enter: @@ -127,34 +120,7 @@ slb_loop_enter_skip: slb_do_enter: - /* Enter guest */ - - ld r0, (PACA_KVM_R0)(r13) - ld r1, (PACA_KVM_R1)(r13) - ld r2, (PACA_KVM_R2)(r13) - ld r3, (PACA_KVM_R3)(r13) - ld r4, (PACA_KVM_R4)(r13) - ld r5, (PACA_KVM_R5)(r13) - ld r6, (PACA_KVM_R6)(r13) - ld r7, (PACA_KVM_R7)(r13) - ld r8, (PACA_KVM_R8)(r13) - ld r9, (PACA_KVM_R9)(r13) - ld r10, (PACA_KVM_R10)(r13) - ld r12, (PACA_KVM_R12)(r13) - - lwz r11, (PACA_KVM_CR)(r13) - mtcr r11 - - ld r11, (PACA_KVM_XER)(r13) - mtxer r11 - - ld r11, (PACA_KVM_R11)(r13) - ld r13, (PACA_KVM_R13)(r13) - - RFI -kvmppc_handler_trampoline_enter_end: - - +.endm /****************************************************************************** * * @@ -162,99 +128,22 @@ kvmppc_handler_trampoline_enter_end: * * *****************************************************************************/ -.global kvmppc_handler_trampoline_exit -kvmppc_handler_trampoline_exit: +.macro LOAD_HOST_SEGMENTS /* Register usage at this point: * - * SPRG_SCRATCH0 = guest R13 - * R12 = exit handler id - * R13 = PACA - * PACA.KVM.SCRATCH0 = guest R12 - * PACA.KVM.SCRATCH1 = guest CR + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.* = guest * + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR * */ - /* Save registers */ - - std r0, PACA_KVM_R0(r13) - std r1, PACA_KVM_R1(r13) - std r2, PACA_KVM_R2(r13) - std r3, PACA_KVM_R3(r13) - std r4, PACA_KVM_R4(r13) - std r5, PACA_KVM_R5(r13) - std r6, PACA_KVM_R6(r13) - std r7, PACA_KVM_R7(r13) - std r8, PACA_KVM_R8(r13) - std r9, PACA_KVM_R9(r13) - std r10, PACA_KVM_R10(r13) - std r11, PACA_KVM_R11(r13) - - /* Restore R1/R2 so we can handle faults */ - ld r1, PACA_KVM_HOST_R1(r13) - ld r2, PACA_KVM_HOST_R2(r13) - - /* Save guest PC and MSR in GPRs */ - mfsrr0 r3 - mfsrr1 r4 - - /* Get scratch'ed off registers */ - mfspr r9, SPRN_SPRG_SCRATCH0 - std r9, PACA_KVM_R13(r13) - - ld r8, PACA_KVM_SCRATCH0(r13) - std r8, PACA_KVM_R12(r13) - - lwz r7, PACA_KVM_SCRATCH1(r13) - stw r7, PACA_KVM_CR(r13) - - /* Save more register state */ - - mfxer r6 - stw r6, PACA_KVM_XER(r13) - - mfdar r5 - mfdsisr r6 - - /* - * In order for us to easily get the last instruction, - * we got the #vmexit at, we exploit the fact that the - * virtual layout is still the same here, so we can just - * ld from the guest's PC address - */ - - /* We only load the last instruction when it's safe */ - cmpwi r12, BOOK3S_INTERRUPT_DATA_STORAGE - beq ld_last_inst - cmpwi r12, BOOK3S_INTERRUPT_PROGRAM - beq ld_last_inst - - b no_ld_last_inst - -ld_last_inst: - /* Save off the guest instruction we're at */ - - /* Set guest mode to 'jump over instruction' so if lwz faults - * we'll just continue at the next IP. */ - li r9, KVM_GUEST_MODE_SKIP - stb r9, PACA_KVM_IN_GUEST(r13) - - /* 1) enable paging for data */ - mfmsr r9 - ori r11, r9, MSR_DR /* Enable paging for data */ - mtmsr r11 - /* 2) fetch the instruction */ - li r0, KVM_INST_FETCH_FAILED /* In case lwz faults */ - lwz r0, 0(r3) - /* 3) disable paging again */ - mtmsr r9 - -no_ld_last_inst: - - /* Unset guest mode */ - li r9, KVM_GUEST_MODE_NONE - stb r9, PACA_KVM_IN_GUEST(r13) - /* Restore bolted entries from the shadow and fix it along the way */ /* We don't store anything in entry 0, so we don't need to take care of it */ @@ -275,28 +164,4 @@ no_ld_last_inst: slb_do_exit: - /* Register usage at this point: - * - * R0 = guest last inst - * R1 = host R1 - * R2 = host R2 - * R3 = guest PC - * R4 = guest MSR - * R5 = guest DAR - * R6 = guest DSISR - * R12 = exit handler id - * R13 = PACA - * PACA.KVM.* = guest * - * - */ - - /* RFI into the highmem handler */ - mfmsr r7 - ori r7, r7, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ - mtsrr1 r7 - ld r8, PACA_KVM_VMHANDLER(r13) /* Highmem handler address */ - mtsrr0 r8 - - RFI -kvmppc_handler_trampoline_exit_end: - +.endm diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 2b0ee7e040c..c85f906038c 100644 --- a/arch/powerpc/kvm/book3s_64_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -28,13 +28,16 @@ #define OP_31_XOP_MFMSR 83 #define OP_31_XOP_MTMSR 146 #define OP_31_XOP_MTMSRD 178 +#define OP_31_XOP_MTSR 210 #define OP_31_XOP_MTSRIN 242 #define OP_31_XOP_TLBIEL 274 #define OP_31_XOP_TLBIE 306 #define OP_31_XOP_SLBMTE 402 #define OP_31_XOP_SLBIE 434 #define OP_31_XOP_SLBIA 498 +#define OP_31_XOP_MFSR 595 #define OP_31_XOP_MFSRIN 659 +#define OP_31_XOP_DCBA 758 #define OP_31_XOP_SLBMFEV 851 #define OP_31_XOP_EIOIO 854 #define OP_31_XOP_SLBMFEE 915 @@ -42,6 +45,24 @@ /* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */ #define OP_31_XOP_DCBZ 1010 +#define OP_LFS 48 +#define OP_LFD 50 +#define OP_STFS 52 +#define OP_STFD 54 + +#define SPRN_GQR0 912 +#define SPRN_GQR1 913 +#define SPRN_GQR2 914 +#define SPRN_GQR3 915 +#define SPRN_GQR4 916 +#define SPRN_GQR5 917 +#define SPRN_GQR6 918 +#define SPRN_GQR7 919 + +/* Book3S_32 defines mfsrin(v) - but that messes up our abstract + * function pointers, so let's just disable the define. */ +#undef mfsrin + int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { @@ -52,7 +73,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, switch (get_xop(inst)) { case OP_19_XOP_RFID: case OP_19_XOP_RFI: - vcpu->arch.pc = vcpu->arch.srr0; + kvmppc_set_pc(vcpu, vcpu->arch.srr0); kvmppc_set_msr(vcpu, vcpu->arch.srr1); *advance = 0; break; @@ -80,6 +101,18 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, case OP_31_XOP_MTMSR: kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst))); break; + case OP_31_XOP_MFSR: + { + int srnum; + + srnum = kvmppc_get_field(inst, 12 + 32, 15 + 32); + if (vcpu->arch.mmu.mfsrin) { + u32 sr; + sr = vcpu->arch.mmu.mfsrin(vcpu, srnum); + kvmppc_set_gpr(vcpu, get_rt(inst), sr); + } + break; + } case OP_31_XOP_MFSRIN: { int srnum; @@ -92,6 +125,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, } break; } + case OP_31_XOP_MTSR: + vcpu->arch.mmu.mtsrin(vcpu, + (inst >> 16) & 0xf, + kvmppc_get_gpr(vcpu, get_rs(inst))); + break; case OP_31_XOP_MTSRIN: vcpu->arch.mmu.mtsrin(vcpu, (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf, @@ -150,12 +188,17 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_set_gpr(vcpu, get_rt(inst), t); } break; + case OP_31_XOP_DCBA: + /* Gets treated as NOP */ + break; case OP_31_XOP_DCBZ: { ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst)); ulong ra = 0; - ulong addr; + ulong addr, vaddr; u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 }; + u32 dsisr; + int r; if (get_ra(inst)) ra = kvmppc_get_gpr(vcpu, get_ra(inst)); @@ -163,15 +206,25 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, addr = (ra + rb) & ~31ULL; if (!(vcpu->arch.msr & MSR_SF)) addr &= 0xffffffff; + vaddr = addr; + + r = kvmppc_st(vcpu, &addr, 32, zeros, true); + if ((r == -ENOENT) || (r == -EPERM)) { + *advance = 0; + vcpu->arch.dear = vaddr; + to_svcpu(vcpu)->fault_dar = vaddr; + + dsisr = DSISR_ISSTORE; + if (r == -ENOENT) + dsisr |= DSISR_NOHPTE; + else if (r == -EPERM) + dsisr |= DSISR_PROTFAULT; + + to_book3s(vcpu)->dsisr = dsisr; + to_svcpu(vcpu)->fault_dsisr = dsisr; - if (kvmppc_st(vcpu, addr, 32, zeros)) { - vcpu->arch.dear = addr; - vcpu->arch.fault_dear = addr; - to_book3s(vcpu)->dsisr = DSISR_PROTFAULT | - DSISR_ISSTORE; kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); - kvmppc_mmu_pte_flush(vcpu, addr, ~0xFFFULL); } break; @@ -184,6 +237,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, emulated = EMULATE_FAIL; } + if (emulated == EMULATE_FAIL) + emulated = kvmppc_emulate_paired_single(run, vcpu); + return emulated; } @@ -207,6 +263,34 @@ void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, } } +static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn) +{ + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + struct kvmppc_bat *bat; + + switch (sprn) { + case SPRN_IBAT0U ... SPRN_IBAT3L: + bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2]; + break; + case SPRN_IBAT4U ... SPRN_IBAT7L: + bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)]; + break; + case SPRN_DBAT0U ... SPRN_DBAT3L: + bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2]; + break; + case SPRN_DBAT4U ... SPRN_DBAT7L: + bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)]; + break; + default: + BUG(); + } + + if (sprn % 2) + return bat->raw >> 32; + else + return bat->raw; +} + static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); @@ -217,13 +301,13 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2]; break; case SPRN_IBAT4U ... SPRN_IBAT7L: - bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT4U) / 2]; + bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)]; break; case SPRN_DBAT0U ... SPRN_DBAT3L: bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2]; break; case SPRN_DBAT4U ... SPRN_DBAT7L: - bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT4U) / 2]; + bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)]; break; default: BUG(); @@ -258,6 +342,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) /* BAT writes happen so rarely that we're ok to flush * everything here */ kvmppc_mmu_pte_flush(vcpu, 0, 0); + kvmppc_mmu_flush_segments(vcpu); break; case SPRN_HID0: to_book3s(vcpu)->hid[0] = spr_val; @@ -268,7 +353,32 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_HID2: to_book3s(vcpu)->hid[2] = spr_val; break; + case SPRN_HID2_GEKKO: + to_book3s(vcpu)->hid[2] = spr_val; + /* HID2.PSE controls paired single on gekko */ + switch (vcpu->arch.pvr) { + case 0x00080200: /* lonestar 2.0 */ + case 0x00088202: /* lonestar 2.2 */ + case 0x70000100: /* gekko 1.0 */ + case 0x00080100: /* gekko 2.0 */ + case 0x00083203: /* gekko 2.3a */ + case 0x00083213: /* gekko 2.3b */ + case 0x00083204: /* gekko 2.4 */ + case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ + case 0x00087200: /* broadway */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_NATIVE_PS) { + /* Native paired singles */ + } else if (spr_val & (1 << 29)) { /* HID2.PSE */ + vcpu->arch.hflags |= BOOK3S_HFLAG_PAIRED_SINGLE; + kvmppc_giveup_ext(vcpu, MSR_FP); + } else { + vcpu->arch.hflags &= ~BOOK3S_HFLAG_PAIRED_SINGLE; + } + break; + } + break; case SPRN_HID4: + case SPRN_HID4_GEKKO: to_book3s(vcpu)->hid[4] = spr_val; break; case SPRN_HID5: @@ -278,12 +388,30 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) (mfmsr() & MSR_HV)) vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; break; + case SPRN_GQR0: + case SPRN_GQR1: + case SPRN_GQR2: + case SPRN_GQR3: + case SPRN_GQR4: + case SPRN_GQR5: + case SPRN_GQR6: + case SPRN_GQR7: + to_book3s(vcpu)->gqr[sprn - SPRN_GQR0] = spr_val; + break; case SPRN_ICTC: case SPRN_THRM1: case SPRN_THRM2: case SPRN_THRM3: case SPRN_CTRLF: case SPRN_CTRLT: + case SPRN_L2CR: + case SPRN_MMCR0_GEKKO: + case SPRN_MMCR1_GEKKO: + case SPRN_PMC1_GEKKO: + case SPRN_PMC2_GEKKO: + case SPRN_PMC3_GEKKO: + case SPRN_PMC4_GEKKO: + case SPRN_WPAR_GEKKO: break; default: printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn); @@ -301,6 +429,12 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) int emulated = EMULATE_DONE; switch (sprn) { + case SPRN_IBAT0U ... SPRN_IBAT3L: + case SPRN_IBAT4U ... SPRN_IBAT7L: + case SPRN_DBAT0U ... SPRN_DBAT3L: + case SPRN_DBAT4U ... SPRN_DBAT7L: + kvmppc_set_gpr(vcpu, rt, kvmppc_read_bat(vcpu, sprn)); + break; case SPRN_SDR1: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1); break; @@ -320,19 +454,40 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]); break; case SPRN_HID2: + case SPRN_HID2_GEKKO: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]); break; case SPRN_HID4: + case SPRN_HID4_GEKKO: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]); break; case SPRN_HID5: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]); break; + case SPRN_GQR0: + case SPRN_GQR1: + case SPRN_GQR2: + case SPRN_GQR3: + case SPRN_GQR4: + case SPRN_GQR5: + case SPRN_GQR6: + case SPRN_GQR7: + kvmppc_set_gpr(vcpu, rt, + to_book3s(vcpu)->gqr[sprn - SPRN_GQR0]); + break; case SPRN_THRM1: case SPRN_THRM2: case SPRN_THRM3: case SPRN_CTRLF: case SPRN_CTRLT: + case SPRN_L2CR: + case SPRN_MMCR0_GEKKO: + case SPRN_MMCR1_GEKKO: + case SPRN_PMC1_GEKKO: + case SPRN_PMC2_GEKKO: + case SPRN_PMC3_GEKKO: + case SPRN_PMC4_GEKKO: + case SPRN_WPAR_GEKKO: kvmppc_set_gpr(vcpu, rt, 0); break; default: @@ -346,3 +501,73 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) return emulated; } +u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst) +{ + u32 dsisr = 0; + + /* + * This is what the spec says about DSISR bits (not mentioned = 0): + * + * 12:13 [DS] Set to bits 30:31 + * 15:16 [X] Set to bits 29:30 + * 17 [X] Set to bit 25 + * [D/DS] Set to bit 5 + * 18:21 [X] Set to bits 21:24 + * [D/DS] Set to bits 1:4 + * 22:26 Set to bits 6:10 (RT/RS/FRT/FRS) + * 27:31 Set to bits 11:15 (RA) + */ + + switch (get_op(inst)) { + /* D-form */ + case OP_LFS: + case OP_LFD: + case OP_STFD: + case OP_STFS: + dsisr |= (inst >> 12) & 0x4000; /* bit 17 */ + dsisr |= (inst >> 17) & 0x3c00; /* bits 18:21 */ + break; + /* X-form */ + case 31: + dsisr |= (inst << 14) & 0x18000; /* bits 15:16 */ + dsisr |= (inst << 8) & 0x04000; /* bit 17 */ + dsisr |= (inst << 3) & 0x03c00; /* bits 18:21 */ + break; + default: + printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst); + break; + } + + dsisr |= (inst >> 16) & 0x03ff; /* bits 22:31 */ + + return dsisr; +} + +ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst) +{ + ulong dar = 0; + ulong ra; + + switch (get_op(inst)) { + case OP_LFS: + case OP_LFD: + case OP_STFD: + case OP_STFS: + ra = get_ra(inst); + if (ra) + dar = kvmppc_get_gpr(vcpu, ra); + dar += (s32)((s16)inst); + break; + case 31: + ra = get_ra(inst); + if (ra) + dar = kvmppc_get_gpr(vcpu, ra); + dar += kvmppc_get_gpr(vcpu, get_rb(inst)); + break; + default: + printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst); + break; + } + + return dar; +} diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_exports.c index 1dd5a1ddfd0..1dd5a1ddfd0 100644 --- a/arch/powerpc/kvm/book3s_64_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index c1584d0cbce..2f0bc928b08 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -24,36 +24,56 @@ #include <asm/asm-offsets.h> #include <asm/exception-64s.h> -#define KVMPPC_HANDLE_EXIT .kvmppc_handle_exit -#define ULONG_SIZE 8 -#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) +#if defined(CONFIG_PPC_BOOK3S_64) -.macro DISABLE_INTERRUPTS - mfmsr r0 - rldicl r0,r0,48,1 - rotldi r0,r0,16 - mtmsrd r0,1 -.endm +#define ULONG_SIZE 8 +#define FUNC(name) GLUE(.,name) +#define GET_SHADOW_VCPU(reg) \ + addi reg, r13, PACA_KVM_SVCPU + +#define DISABLE_INTERRUPTS \ + mfmsr r0; \ + rldicl r0,r0,48,1; \ + rotldi r0,r0,16; \ + mtmsrd r0,1; \ + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define ULONG_SIZE 4 +#define FUNC(name) name + +#define GET_SHADOW_VCPU(reg) \ + lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) + +#define DISABLE_INTERRUPTS \ + mfmsr r0; \ + rlwinm r0,r0,0,17,15; \ + mtmsr r0; \ + +#endif /* CONFIG_PPC_BOOK3S_XX */ + + +#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) #define VCPU_LOAD_NVGPRS(vcpu) \ - ld r14, VCPU_GPR(r14)(vcpu); \ - ld r15, VCPU_GPR(r15)(vcpu); \ - ld r16, VCPU_GPR(r16)(vcpu); \ - ld r17, VCPU_GPR(r17)(vcpu); \ - ld r18, VCPU_GPR(r18)(vcpu); \ - ld r19, VCPU_GPR(r19)(vcpu); \ - ld r20, VCPU_GPR(r20)(vcpu); \ - ld r21, VCPU_GPR(r21)(vcpu); \ - ld r22, VCPU_GPR(r22)(vcpu); \ - ld r23, VCPU_GPR(r23)(vcpu); \ - ld r24, VCPU_GPR(r24)(vcpu); \ - ld r25, VCPU_GPR(r25)(vcpu); \ - ld r26, VCPU_GPR(r26)(vcpu); \ - ld r27, VCPU_GPR(r27)(vcpu); \ - ld r28, VCPU_GPR(r28)(vcpu); \ - ld r29, VCPU_GPR(r29)(vcpu); \ - ld r30, VCPU_GPR(r30)(vcpu); \ - ld r31, VCPU_GPR(r31)(vcpu); \ + PPC_LL r14, VCPU_GPR(r14)(vcpu); \ + PPC_LL r15, VCPU_GPR(r15)(vcpu); \ + PPC_LL r16, VCPU_GPR(r16)(vcpu); \ + PPC_LL r17, VCPU_GPR(r17)(vcpu); \ + PPC_LL r18, VCPU_GPR(r18)(vcpu); \ + PPC_LL r19, VCPU_GPR(r19)(vcpu); \ + PPC_LL r20, VCPU_GPR(r20)(vcpu); \ + PPC_LL r21, VCPU_GPR(r21)(vcpu); \ + PPC_LL r22, VCPU_GPR(r22)(vcpu); \ + PPC_LL r23, VCPU_GPR(r23)(vcpu); \ + PPC_LL r24, VCPU_GPR(r24)(vcpu); \ + PPC_LL r25, VCPU_GPR(r25)(vcpu); \ + PPC_LL r26, VCPU_GPR(r26)(vcpu); \ + PPC_LL r27, VCPU_GPR(r27)(vcpu); \ + PPC_LL r28, VCPU_GPR(r28)(vcpu); \ + PPC_LL r29, VCPU_GPR(r29)(vcpu); \ + PPC_LL r30, VCPU_GPR(r30)(vcpu); \ + PPC_LL r31, VCPU_GPR(r31)(vcpu); \ /***************************************************************************** * * @@ -69,11 +89,11 @@ _GLOBAL(__kvmppc_vcpu_entry) kvm_start_entry: /* Write correct stack frame */ - mflr r0 - std r0,16(r1) + mflr r0 + PPC_STL r0,PPC_LR_STKOFF(r1) /* Save host state to the stack */ - stdu r1, -SWITCH_FRAME_SIZE(r1) + PPC_STLU r1, -SWITCH_FRAME_SIZE(r1) /* Save r3 (kvm_run) and r4 (vcpu) */ SAVE_2GPRS(3, r1) @@ -82,33 +102,28 @@ kvm_start_entry: SAVE_NVGPRS(r1) /* Save LR */ - std r0, _LINK(r1) + PPC_STL r0, _LINK(r1) /* Load non-volatile guest state from the vcpu */ VCPU_LOAD_NVGPRS(r4) + GET_SHADOW_VCPU(r5) + /* Save R1/R2 in the PACA */ - std r1, PACA_KVM_HOST_R1(r13) - std r2, PACA_KVM_HOST_R2(r13) + PPC_STL r1, SVCPU_HOST_R1(r5) + PPC_STL r2, SVCPU_HOST_R2(r5) /* XXX swap in/out on load? */ - ld r3, VCPU_HIGHMEM_HANDLER(r4) - std r3, PACA_KVM_VMHANDLER(r13) + PPC_LL r3, VCPU_HIGHMEM_HANDLER(r4) + PPC_STL r3, SVCPU_VMHANDLER(r5) kvm_start_lightweight: - ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ - ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ - - /* Load some guest state in the respective registers */ - ld r5, VCPU_CTR(r4) /* r5 = vcpu->arch.ctr */ - /* will be swapped in by rmcall */ - - ld r3, VCPU_LR(r4) /* r3 = vcpu->arch.lr */ - mtlr r3 /* LR = r3 */ + PPC_LL r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ DISABLE_INTERRUPTS +#ifdef CONFIG_PPC_BOOK3S_64 /* Some guests may need to have dcbz set to 32 byte length. * * Usually we ensure that by patching the guest's instructions @@ -118,7 +133,7 @@ kvm_start_lightweight: * because that's a lot faster. */ - ld r3, VCPU_HFLAGS(r4) + PPC_LL r3, VCPU_HFLAGS(r4) rldicl. r3, r3, 0, 63 /* CR = ((r3 & 1) == 0) */ beq no_dcbz32_on @@ -128,13 +143,15 @@ kvm_start_lightweight: no_dcbz32_on: - ld r6, VCPU_RMCALL(r4) +#endif /* CONFIG_PPC_BOOK3S_64 */ + + PPC_LL r6, VCPU_RMCALL(r4) mtctr r6 - ld r3, VCPU_TRAMPOLINE_ENTER(r4) + PPC_LL r3, VCPU_TRAMPOLINE_ENTER(r4) LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - /* Jump to SLB patching handlder and into our guest */ + /* Jump to segment patching handler and into our guest */ bctr /* @@ -149,31 +166,20 @@ kvmppc_handler_highmem: /* * Register usage at this point: * - * R0 = guest last inst - * R1 = host R1 - * R2 = host R2 - * R3 = guest PC - * R4 = guest MSR - * R5 = guest DAR - * R6 = guest DSISR - * R13 = PACA - * PACA.KVM.* = guest * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = PACA + * SVCPU.* = guest * * */ /* R7 = vcpu */ - ld r7, GPR4(r1) + PPC_LL r7, GPR4(r1) - /* Now save the guest state */ +#ifdef CONFIG_PPC_BOOK3S_64 - stw r0, VCPU_LAST_INST(r7) - - std r3, VCPU_PC(r7) - std r4, VCPU_SHADOW_SRR1(r7) - std r5, VCPU_FAULT_DEAR(r7) - std r6, VCPU_FAULT_DSISR(r7) - - ld r5, VCPU_HFLAGS(r7) + PPC_LL r5, VCPU_HFLAGS(r7) rldicl. r5, r5, 0, 63 /* CR = ((r5 & 1) == 0) */ beq no_dcbz32_off @@ -184,35 +190,29 @@ kvmppc_handler_highmem: no_dcbz32_off: - std r14, VCPU_GPR(r14)(r7) - std r15, VCPU_GPR(r15)(r7) - std r16, VCPU_GPR(r16)(r7) - std r17, VCPU_GPR(r17)(r7) - std r18, VCPU_GPR(r18)(r7) - std r19, VCPU_GPR(r19)(r7) - std r20, VCPU_GPR(r20)(r7) - std r21, VCPU_GPR(r21)(r7) - std r22, VCPU_GPR(r22)(r7) - std r23, VCPU_GPR(r23)(r7) - std r24, VCPU_GPR(r24)(r7) - std r25, VCPU_GPR(r25)(r7) - std r26, VCPU_GPR(r26)(r7) - std r27, VCPU_GPR(r27)(r7) - std r28, VCPU_GPR(r28)(r7) - std r29, VCPU_GPR(r29)(r7) - std r30, VCPU_GPR(r30)(r7) - std r31, VCPU_GPR(r31)(r7) - - /* Save guest CTR */ - mfctr r5 - std r5, VCPU_CTR(r7) - - /* Save guest LR */ - mflr r5 - std r5, VCPU_LR(r7) +#endif /* CONFIG_PPC_BOOK3S_64 */ + + PPC_STL r14, VCPU_GPR(r14)(r7) + PPC_STL r15, VCPU_GPR(r15)(r7) + PPC_STL r16, VCPU_GPR(r16)(r7) + PPC_STL r17, VCPU_GPR(r17)(r7) + PPC_STL r18, VCPU_GPR(r18)(r7) + PPC_STL r19, VCPU_GPR(r19)(r7) + PPC_STL r20, VCPU_GPR(r20)(r7) + PPC_STL r21, VCPU_GPR(r21)(r7) + PPC_STL r22, VCPU_GPR(r22)(r7) + PPC_STL r23, VCPU_GPR(r23)(r7) + PPC_STL r24, VCPU_GPR(r24)(r7) + PPC_STL r25, VCPU_GPR(r25)(r7) + PPC_STL r26, VCPU_GPR(r26)(r7) + PPC_STL r27, VCPU_GPR(r27)(r7) + PPC_STL r28, VCPU_GPR(r28)(r7) + PPC_STL r29, VCPU_GPR(r29)(r7) + PPC_STL r30, VCPU_GPR(r30)(r7) + PPC_STL r31, VCPU_GPR(r31)(r7) /* Restore host msr -> SRR1 */ - ld r6, VCPU_HOST_MSR(r7) + PPC_LL r6, VCPU_HOST_MSR(r7) /* * For some interrupts, we need to call the real Linux @@ -228,9 +228,12 @@ no_dcbz32_off: beq call_linux_handler cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER beq call_linux_handler + cmpwi r12, BOOK3S_INTERRUPT_PERFMON + beq call_linux_handler /* Back to EE=1 */ mtmsr r6 + sync b kvm_return_point call_linux_handler: @@ -249,14 +252,14 @@ call_linux_handler: */ /* Restore host IP -> SRR0 */ - ld r5, VCPU_HOST_RETIP(r7) + PPC_LL r5, VCPU_HOST_RETIP(r7) /* XXX Better move to a safe function? * What if we get an HTAB flush in between mtsrr0 and mtsrr1? */ mtlr r12 - ld r4, VCPU_TRAMPOLINE_LOWMEM(r7) + PPC_LL r4, VCPU_TRAMPOLINE_LOWMEM(r7) mtsrr0 r4 LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) mtsrr1 r3 @@ -274,7 +277,7 @@ kvm_return_point: /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) - bl KVMPPC_HANDLE_EXIT + bl FUNC(kvmppc_handle_exit) /* If RESUME_GUEST, get back in the loop */ cmpwi r3, RESUME_GUEST @@ -285,7 +288,7 @@ kvm_return_point: kvm_exit_loop: - ld r4, _LINK(r1) + PPC_LL r4, _LINK(r1) mtlr r4 /* Restore non-volatile host registers (r14 - r31) */ @@ -296,8 +299,8 @@ kvm_exit_loop: kvm_loop_heavyweight: - ld r4, _LINK(r1) - std r4, (16 + SWITCH_FRAME_SIZE)(r1) + PPC_LL r4, _LINK(r1) + PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1) /* Load vcpu and cpu_run */ REST_2GPRS(3, r1) @@ -315,4 +318,3 @@ kvm_loop_lightweight: /* Jump back into the beginning of this function */ b kvm_start_lightweight - diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c new file mode 100644 index 00000000000..a9f66abafcb --- /dev/null +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -0,0 +1,1289 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright Novell Inc 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#include <asm/kvm.h> +#include <asm/kvm_ppc.h> +#include <asm/disassemble.h> +#include <asm/kvm_book3s.h> +#include <asm/kvm_fpu.h> +#include <asm/reg.h> +#include <asm/cacheflush.h> +#include <linux/vmalloc.h> + +/* #define DEBUG */ + +#ifdef DEBUG +#define dprintk printk +#else +#define dprintk(...) do { } while(0); +#endif + +#define OP_LFS 48 +#define OP_LFSU 49 +#define OP_LFD 50 +#define OP_LFDU 51 +#define OP_STFS 52 +#define OP_STFSU 53 +#define OP_STFD 54 +#define OP_STFDU 55 +#define OP_PSQ_L 56 +#define OP_PSQ_LU 57 +#define OP_PSQ_ST 60 +#define OP_PSQ_STU 61 + +#define OP_31_LFSX 535 +#define OP_31_LFSUX 567 +#define OP_31_LFDX 599 +#define OP_31_LFDUX 631 +#define OP_31_STFSX 663 +#define OP_31_STFSUX 695 +#define OP_31_STFX 727 +#define OP_31_STFUX 759 +#define OP_31_LWIZX 887 +#define OP_31_STFIWX 983 + +#define OP_59_FADDS 21 +#define OP_59_FSUBS 20 +#define OP_59_FSQRTS 22 +#define OP_59_FDIVS 18 +#define OP_59_FRES 24 +#define OP_59_FMULS 25 +#define OP_59_FRSQRTES 26 +#define OP_59_FMSUBS 28 +#define OP_59_FMADDS 29 +#define OP_59_FNMSUBS 30 +#define OP_59_FNMADDS 31 + +#define OP_63_FCMPU 0 +#define OP_63_FCPSGN 8 +#define OP_63_FRSP 12 +#define OP_63_FCTIW 14 +#define OP_63_FCTIWZ 15 +#define OP_63_FDIV 18 +#define OP_63_FADD 21 +#define OP_63_FSQRT 22 +#define OP_63_FSEL 23 +#define OP_63_FRE 24 +#define OP_63_FMUL 25 +#define OP_63_FRSQRTE 26 +#define OP_63_FMSUB 28 +#define OP_63_FMADD 29 +#define OP_63_FNMSUB 30 +#define OP_63_FNMADD 31 +#define OP_63_FCMPO 32 +#define OP_63_MTFSB1 38 // XXX +#define OP_63_FSUB 20 +#define OP_63_FNEG 40 +#define OP_63_MCRFS 64 +#define OP_63_MTFSB0 70 +#define OP_63_FMR 72 +#define OP_63_MTFSFI 134 +#define OP_63_FABS 264 +#define OP_63_MFFS 583 +#define OP_63_MTFSF 711 + +#define OP_4X_PS_CMPU0 0 +#define OP_4X_PSQ_LX 6 +#define OP_4XW_PSQ_STX 7 +#define OP_4A_PS_SUM0 10 +#define OP_4A_PS_SUM1 11 +#define OP_4A_PS_MULS0 12 +#define OP_4A_PS_MULS1 13 +#define OP_4A_PS_MADDS0 14 +#define OP_4A_PS_MADDS1 15 +#define OP_4A_PS_DIV 18 +#define OP_4A_PS_SUB 20 +#define OP_4A_PS_ADD 21 +#define OP_4A_PS_SEL 23 +#define OP_4A_PS_RES 24 +#define OP_4A_PS_MUL 25 +#define OP_4A_PS_RSQRTE 26 +#define OP_4A_PS_MSUB 28 +#define OP_4A_PS_MADD 29 +#define OP_4A_PS_NMSUB 30 +#define OP_4A_PS_NMADD 31 +#define OP_4X_PS_CMPO0 32 +#define OP_4X_PSQ_LUX 38 +#define OP_4XW_PSQ_STUX 39 +#define OP_4X_PS_NEG 40 +#define OP_4X_PS_CMPU1 64 +#define OP_4X_PS_MR 72 +#define OP_4X_PS_CMPO1 96 +#define OP_4X_PS_NABS 136 +#define OP_4X_PS_ABS 264 +#define OP_4X_PS_MERGE00 528 +#define OP_4X_PS_MERGE01 560 +#define OP_4X_PS_MERGE10 592 +#define OP_4X_PS_MERGE11 624 + +#define SCALAR_NONE 0 +#define SCALAR_HIGH (1 << 0) +#define SCALAR_LOW (1 << 1) +#define SCALAR_NO_PS0 (1 << 2) +#define SCALAR_NO_PS1 (1 << 3) + +#define GQR_ST_TYPE_MASK 0x00000007 +#define GQR_ST_TYPE_SHIFT 0 +#define GQR_ST_SCALE_MASK 0x00003f00 +#define GQR_ST_SCALE_SHIFT 8 +#define GQR_LD_TYPE_MASK 0x00070000 +#define GQR_LD_TYPE_SHIFT 16 +#define GQR_LD_SCALE_MASK 0x3f000000 +#define GQR_LD_SCALE_SHIFT 24 + +#define GQR_QUANTIZE_FLOAT 0 +#define GQR_QUANTIZE_U8 4 +#define GQR_QUANTIZE_U16 5 +#define GQR_QUANTIZE_S8 6 +#define GQR_QUANTIZE_S16 7 + +#define FPU_LS_SINGLE 0 +#define FPU_LS_DOUBLE 1 +#define FPU_LS_SINGLE_LOW 2 + +static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt) +{ + struct thread_struct t; + + t.fpscr.val = vcpu->arch.fpscr; + cvt_df((double*)&vcpu->arch.fpr[rt], (float*)&vcpu->arch.qpr[rt], &t); +} + +static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store) +{ + u64 dsisr; + + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 36, 0); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0); + vcpu->arch.dear = eaddr; + /* Page Fault */ + dsisr = kvmppc_set_field(0, 33, 33, 1); + if (is_store) + to_book3s(vcpu)->dsisr = kvmppc_set_field(dsisr, 38, 38, 1); + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); +} + +static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, int ls_type) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + char tmp[8]; + int len = sizeof(u32); + + if (ls_type == FPU_LS_DOUBLE) + len = sizeof(u64); + + t.fpscr.val = vcpu->arch.fpscr; + + /* read from memory */ + r = kvmppc_ld(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, false); + goto done_load; + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, len, 1); + goto done_load; + } + + emulated = EMULATE_DONE; + + /* put in registers */ + switch (ls_type) { + case FPU_LS_SINGLE: + cvt_fd((float*)tmp, (double*)&vcpu->arch.fpr[rs], &t); + vcpu->arch.qpr[rs] = *((u32*)tmp); + break; + case FPU_LS_DOUBLE: + vcpu->arch.fpr[rs] = *((u64*)tmp); + break; + } + + dprintk(KERN_INFO "KVM: FPR_LD [0x%llx] at 0x%lx (%d)\n", *(u64*)tmp, + addr, len); + +done_load: + return emulated; +} + +static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, int ls_type) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + char tmp[8]; + u64 val; + int len; + + t.fpscr.val = vcpu->arch.fpscr; + + switch (ls_type) { + case FPU_LS_SINGLE: + cvt_df((double*)&vcpu->arch.fpr[rs], (float*)tmp, &t); + val = *((u32*)tmp); + len = sizeof(u32); + break; + case FPU_LS_SINGLE_LOW: + *((u32*)tmp) = vcpu->arch.fpr[rs]; + val = vcpu->arch.fpr[rs] & 0xffffffff; + len = sizeof(u32); + break; + case FPU_LS_DOUBLE: + *((u64*)tmp) = vcpu->arch.fpr[rs]; + val = vcpu->arch.fpr[rs]; + len = sizeof(u64); + break; + default: + val = 0; + len = 0; + } + + r = kvmppc_st(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, true); + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_store(run, vcpu, val, len, 1); + } else { + emulated = EMULATE_DONE; + } + + dprintk(KERN_INFO "KVM: FPR_ST [0x%llx] at 0x%lx (%d)\n", + val, addr, len); + + return emulated; +} + +static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, bool w, int i) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + float one = 1.0; + u32 tmp[2]; + + t.fpscr.val = vcpu->arch.fpscr; + + /* read from memory */ + if (w) { + r = kvmppc_ld(vcpu, &addr, sizeof(u32), tmp, true); + memcpy(&tmp[1], &one, sizeof(u32)); + } else { + r = kvmppc_ld(vcpu, &addr, sizeof(u32) * 2, tmp, true); + } + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, false); + goto done_load; + } else if ((r == EMULATE_DO_MMIO) && w) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, 4, 1); + vcpu->arch.qpr[rs] = tmp[1]; + goto done_load; + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FQPR | rs, 8, 1); + goto done_load; + } + + emulated = EMULATE_DONE; + + /* put in registers */ + cvt_fd((float*)&tmp[0], (double*)&vcpu->arch.fpr[rs], &t); + vcpu->arch.qpr[rs] = tmp[1]; + + dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0], + tmp[1], addr, w ? 4 : 8); + +done_load: + return emulated; +} + +static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, bool w, int i) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + u32 tmp[2]; + int len = w ? sizeof(u32) : sizeof(u64); + + t.fpscr.val = vcpu->arch.fpscr; + + cvt_df((double*)&vcpu->arch.fpr[rs], (float*)&tmp[0], &t); + tmp[1] = vcpu->arch.qpr[rs]; + + r = kvmppc_st(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, true); + } else if ((r == EMULATE_DO_MMIO) && w) { + emulated = kvmppc_handle_store(run, vcpu, tmp[0], 4, 1); + } else if (r == EMULATE_DO_MMIO) { + u64 val = ((u64)tmp[0] << 32) | tmp[1]; + emulated = kvmppc_handle_store(run, vcpu, val, 8, 1); + } else { + emulated = EMULATE_DONE; + } + + dprintk(KERN_INFO "KVM: PSQ_ST [0x%x, 0x%x] at 0x%lx (%d)\n", + tmp[0], tmp[1], addr, len); + + return emulated; +} + +/* + * Cuts out inst bits with ordering according to spec. + * That means the leftmost bit is zero. All given bits are included. + */ +static inline u32 inst_get_field(u32 inst, int msb, int lsb) +{ + return kvmppc_get_field(inst, msb + 32, lsb + 32); +} + +/* + * Replaces inst bits with ordering according to spec. + */ +static inline u32 inst_set_field(u32 inst, int msb, int lsb, int value) +{ + return kvmppc_set_field(inst, msb + 32, lsb + 32, value); +} + +bool kvmppc_inst_is_paired_single(struct kvm_vcpu *vcpu, u32 inst) +{ + if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) + return false; + + switch (get_op(inst)) { + case OP_PSQ_L: + case OP_PSQ_LU: + case OP_PSQ_ST: + case OP_PSQ_STU: + case OP_LFS: + case OP_LFSU: + case OP_LFD: + case OP_LFDU: + case OP_STFS: + case OP_STFSU: + case OP_STFD: + case OP_STFDU: + return true; + case 4: + /* X form */ + switch (inst_get_field(inst, 21, 30)) { + case OP_4X_PS_CMPU0: + case OP_4X_PSQ_LX: + case OP_4X_PS_CMPO0: + case OP_4X_PSQ_LUX: + case OP_4X_PS_NEG: + case OP_4X_PS_CMPU1: + case OP_4X_PS_MR: + case OP_4X_PS_CMPO1: + case OP_4X_PS_NABS: + case OP_4X_PS_ABS: + case OP_4X_PS_MERGE00: + case OP_4X_PS_MERGE01: + case OP_4X_PS_MERGE10: + case OP_4X_PS_MERGE11: + return true; + } + /* XW form */ + switch (inst_get_field(inst, 25, 30)) { + case OP_4XW_PSQ_STX: + case OP_4XW_PSQ_STUX: + return true; + } + /* A form */ + switch (inst_get_field(inst, 26, 30)) { + case OP_4A_PS_SUM1: + case OP_4A_PS_SUM0: + case OP_4A_PS_MULS0: + case OP_4A_PS_MULS1: + case OP_4A_PS_MADDS0: + case OP_4A_PS_MADDS1: + case OP_4A_PS_DIV: + case OP_4A_PS_SUB: + case OP_4A_PS_ADD: + case OP_4A_PS_SEL: + case OP_4A_PS_RES: + case OP_4A_PS_MUL: + case OP_4A_PS_RSQRTE: + case OP_4A_PS_MSUB: + case OP_4A_PS_MADD: + case OP_4A_PS_NMSUB: + case OP_4A_PS_NMADD: + return true; + } + break; + case 59: + switch (inst_get_field(inst, 21, 30)) { + case OP_59_FADDS: + case OP_59_FSUBS: + case OP_59_FDIVS: + case OP_59_FRES: + case OP_59_FRSQRTES: + return true; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_59_FMULS: + case OP_59_FMSUBS: + case OP_59_FMADDS: + case OP_59_FNMSUBS: + case OP_59_FNMADDS: + return true; + } + break; + case 63: + switch (inst_get_field(inst, 21, 30)) { + case OP_63_MTFSB0: + case OP_63_MTFSB1: + case OP_63_MTFSF: + case OP_63_MTFSFI: + case OP_63_MCRFS: + case OP_63_MFFS: + case OP_63_FCMPU: + case OP_63_FCMPO: + case OP_63_FNEG: + case OP_63_FMR: + case OP_63_FABS: + case OP_63_FRSP: + case OP_63_FDIV: + case OP_63_FADD: + case OP_63_FSUB: + case OP_63_FCTIW: + case OP_63_FCTIWZ: + case OP_63_FRSQRTE: + case OP_63_FCPSGN: + return true; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_63_FMUL: + case OP_63_FSEL: + case OP_63_FMSUB: + case OP_63_FMADD: + case OP_63_FNMSUB: + case OP_63_FNMADD: + return true; + } + break; + case 31: + switch (inst_get_field(inst, 21, 30)) { + case OP_31_LFSX: + case OP_31_LFSUX: + case OP_31_LFDX: + case OP_31_LFDUX: + case OP_31_STFSX: + case OP_31_STFSUX: + case OP_31_STFX: + case OP_31_STFUX: + case OP_31_STFIWX: + return true; + } + break; + } + + return false; +} + +static int get_d_signext(u32 inst) +{ + int d = inst & 0x8ff; + + if (d & 0x800) + return -(d & 0x7ff); + + return (d & 0x7ff); +} + +static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in1, int reg_in2, + int reg_in3, int scalar, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1, + u32 *src2, u32 *src3)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out; + u32 ps0_in1, ps0_in2, ps0_in3; + u32 ps1_in1, ps1_in2, ps1_in3; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t); + cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t); + cvt_df((double*)&fpr[reg_in3], (float*)&ps0_in3, &t); + + if (scalar & SCALAR_LOW) + ps0_in2 = qpr[reg_in2]; + + func(&t, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3); + + dprintk(KERN_INFO "PS3 ps0 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", + ps0_in1, ps0_in2, ps0_in3, ps0_out); + + if (!(scalar & SCALAR_NO_PS0)) + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + + /* PS1 */ + ps1_in1 = qpr[reg_in1]; + ps1_in2 = qpr[reg_in2]; + ps1_in3 = qpr[reg_in3]; + + if (scalar & SCALAR_HIGH) + ps1_in2 = ps0_in2; + + if (!(scalar & SCALAR_NO_PS1)) + func(&t, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3); + + dprintk(KERN_INFO "PS3 ps1 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", + ps1_in1, ps1_in2, ps1_in3, qpr[reg_out]); + + return EMULATE_DONE; +} + +static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in1, int reg_in2, + int scalar, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1, + u32 *src2)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out; + u32 ps0_in1, ps0_in2; + u32 ps1_out; + u32 ps1_in1, ps1_in2; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t); + + if (scalar & SCALAR_LOW) + ps0_in2 = qpr[reg_in2]; + else + cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t); + + func(&t, &ps0_out, &ps0_in1, &ps0_in2); + + if (!(scalar & SCALAR_NO_PS0)) { + dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n", + ps0_in1, ps0_in2, ps0_out); + + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + } + + /* PS1 */ + ps1_in1 = qpr[reg_in1]; + ps1_in2 = qpr[reg_in2]; + + if (scalar & SCALAR_HIGH) + ps1_in2 = ps0_in2; + + func(&t, &ps1_out, &ps1_in1, &ps1_in2); + + if (!(scalar & SCALAR_NO_PS1)) { + qpr[reg_out] = ps1_out; + + dprintk(KERN_INFO "PS2 ps1 -> f(0x%x, 0x%x) = 0x%x\n", + ps1_in1, ps1_in2, qpr[reg_out]); + } + + return EMULATE_DONE; +} + +static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out, ps0_in; + u32 ps1_in; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in], (float*)&ps0_in, &t); + func(&t, &ps0_out, &ps0_in); + + dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n", + ps0_in, ps0_out); + + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + + /* PS1 */ + ps1_in = qpr[reg_in]; + func(&t, &qpr[reg_out], &ps1_in); + + dprintk(KERN_INFO "PS1 ps1 -> f(0x%x) = 0x%x\n", + ps1_in, qpr[reg_out]); + + return EMULATE_DONE; +} + +int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) +{ + u32 inst = kvmppc_get_last_inst(vcpu); + enum emulation_result emulated = EMULATE_DONE; + + int ax_rd = inst_get_field(inst, 6, 10); + int ax_ra = inst_get_field(inst, 11, 15); + int ax_rb = inst_get_field(inst, 16, 20); + int ax_rc = inst_get_field(inst, 21, 25); + short full_d = inst_get_field(inst, 16, 31); + + u64 *fpr_d = &vcpu->arch.fpr[ax_rd]; + u64 *fpr_a = &vcpu->arch.fpr[ax_ra]; + u64 *fpr_b = &vcpu->arch.fpr[ax_rb]; + u64 *fpr_c = &vcpu->arch.fpr[ax_rc]; + + bool rcomp = (inst & 1) ? true : false; + u32 cr = kvmppc_get_cr(vcpu); + struct thread_struct t; +#ifdef DEBUG + int i; +#endif + + t.fpscr.val = vcpu->arch.fpscr; + + if (!kvmppc_inst_is_paired_single(vcpu, inst)) + return EMULATE_FAIL; + + if (!(vcpu->arch.msr & MSR_FP)) { + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL); + return EMULATE_AGAIN; + } + + kvmppc_giveup_ext(vcpu, MSR_FP); + preempt_disable(); + enable_kernel_fp(); + /* Do we need to clear FE0 / FE1 here? Don't think so. */ + +#ifdef DEBUG + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + u32 f; + cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t); + dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx QPR[%d] = 0x%x\n", + i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]); + } +#endif + + switch (get_op(inst)) { + case OP_PSQ_L: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_PSQ_LU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_PSQ_ST: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_PSQ_STU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case 4: + /* X form */ + switch (inst_get_field(inst, 21, 30)) { + case OP_4X_PS_CMPU0: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PSQ_LX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_4X_PS_CMPO0: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PSQ_LUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_4X_PS_NEG: + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] ^= 0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] ^= 0x80000000; + break; + case OP_4X_PS_CMPU1: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PS_MR: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + case OP_4X_PS_CMPO1: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PS_NABS: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] |= 0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] |= 0x80000000; + break; + case OP_4X_PS_ABS: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] &= ~0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] &= ~0x80000000; + break; + case OP_4X_PS_MERGE00: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; + /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ + cvt_df((double*)&vcpu->arch.fpr[ax_rb], + (float*)&vcpu->arch.qpr[ax_rd], &t); + break; + case OP_4X_PS_MERGE01: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + case OP_4X_PS_MERGE10: + WARN_ON(rcomp); + /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + cvt_fd((float*)&vcpu->arch.qpr[ax_ra], + (double*)&vcpu->arch.fpr[ax_rd], &t); + /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ + cvt_df((double*)&vcpu->arch.fpr[ax_rb], + (float*)&vcpu->arch.qpr[ax_rd], &t); + break; + case OP_4X_PS_MERGE11: + WARN_ON(rcomp); + /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + cvt_fd((float*)&vcpu->arch.qpr[ax_ra], + (double*)&vcpu->arch.fpr[ax_rd], &t); + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + } + /* XW form */ + switch (inst_get_field(inst, 25, 30)) { + case OP_4XW_PSQ_STX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_4XW_PSQ_STUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + } + /* A form */ + switch (inst_get_field(inst, 26, 30)) { + case OP_4A_PS_SUM1: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_rb, ax_ra, SCALAR_NO_PS0 | SCALAR_HIGH, fps_fadds); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rc]; + break; + case OP_4A_PS_SUM0: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NO_PS1 | SCALAR_LOW, fps_fadds); + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rc]; + break; + case OP_4A_PS_MULS0: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_HIGH, fps_fmuls); + break; + case OP_4A_PS_MULS1: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_LOW, fps_fmuls); + break; + case OP_4A_PS_MADDS0: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_HIGH, fps_fmadds); + break; + case OP_4A_PS_MADDS1: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_LOW, fps_fmadds); + break; + case OP_4A_PS_DIV: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fdivs); + break; + case OP_4A_PS_SUB: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fsubs); + break; + case OP_4A_PS_ADD: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fadds); + break; + case OP_4A_PS_SEL: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fsel); + break; + case OP_4A_PS_RES: + emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd, + ax_rb, fps_fres); + break; + case OP_4A_PS_MUL: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_NONE, fps_fmuls); + break; + case OP_4A_PS_RSQRTE: + emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd, + ax_rb, fps_frsqrte); + break; + case OP_4A_PS_MSUB: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmsubs); + break; + case OP_4A_PS_MADD: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmadds); + break; + case OP_4A_PS_NMSUB: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmsubs); + break; + case OP_4A_PS_NMADD: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmadds); + break; + } + break; + + /* Real FPU operations */ + + case OP_LFS: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + break; + } + case OP_LFSU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_LFD: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + break; + } + case OP_LFDU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_STFS: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + break; + } + case OP_STFSU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_STFD: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + break; + } + case OP_STFDU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case 31: + switch (inst_get_field(inst, 21, 30)) { + case OP_31_LFSX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + break; + } + case OP_31_LFSUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_LFDX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + break; + } + case OP_31_LFDUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFSX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + break; + } + case OP_31_STFSUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + break; + } + case OP_31_STFUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFIWX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, + FPU_LS_SINGLE_LOW); + break; + } + break; + } + break; + case 59: + switch (inst_get_field(inst, 21, 30)) { + case OP_59_FADDS: + fpd_fadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FSUBS: + fpd_fsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FDIVS: + fpd_fdivs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FRES: + fpd_fres(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FRSQRTES: + fpd_frsqrtes(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_59_FMULS: + fpd_fmuls(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FMSUBS: + fpd_fmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FMADDS: + fpd_fmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FNMSUBS: + fpd_fnmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FNMADDS: + fpd_fnmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + } + break; + case 63: + switch (inst_get_field(inst, 21, 30)) { + case OP_63_MTFSB0: + case OP_63_MTFSB1: + case OP_63_MCRFS: + case OP_63_MTFSFI: + /* XXX need to implement */ + break; + case OP_63_MFFS: + /* XXX missing CR */ + *fpr_d = vcpu->arch.fpscr; + break; + case OP_63_MTFSF: + /* XXX missing fm bits */ + /* XXX missing CR */ + vcpu->arch.fpscr = *fpr_b; + break; + case OP_63_FCMPU: + { + u32 tmp_cr; + u32 cr0_mask = 0xf0000000; + u32 cr_shift = inst_get_field(inst, 6, 8) * 4; + + fpd_fcmpu(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + cr &= ~(cr0_mask >> cr_shift); + cr |= (cr & cr0_mask) >> cr_shift; + break; + } + case OP_63_FCMPO: + { + u32 tmp_cr; + u32 cr0_mask = 0xf0000000; + u32 cr_shift = inst_get_field(inst, 6, 8) * 4; + + fpd_fcmpo(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + cr &= ~(cr0_mask >> cr_shift); + cr |= (cr & cr0_mask) >> cr_shift; + break; + } + case OP_63_FNEG: + fpd_fneg(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FMR: + *fpr_d = *fpr_b; + break; + case OP_63_FABS: + fpd_fabs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FCPSGN: + fpd_fcpsgn(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FDIV: + fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FADD: + fpd_fadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FSUB: + fpd_fsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FCTIW: + fpd_fctiw(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FCTIWZ: + fpd_fctiwz(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FRSP: + fpd_frsp(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_63_FRSQRTE: + { + double one = 1.0f; + + /* fD = sqrt(fB) */ + fpd_fsqrt(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + /* fD = 1.0f / fD */ + fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, (u64*)&one, fpr_d); + break; + } + } + switch (inst_get_field(inst, 26, 30)) { + case OP_63_FMUL: + fpd_fmul(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + break; + case OP_63_FSEL: + fpd_fsel(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FMSUB: + fpd_fmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FMADD: + fpd_fmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FNMSUB: + fpd_fnmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FNMADD: + fpd_fnmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + } + break; + } + +#ifdef DEBUG + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + u32 f; + cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t); + dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f); + } +#endif + + if (rcomp) + kvmppc_set_cr(vcpu, cr); + + preempt_enable(); + + return emulated; +} diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index c83c60ad96c..506d5c316c9 100644 --- a/arch/powerpc/kvm/book3s_64_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -22,7 +22,10 @@ #include <asm/reg.h> #include <asm/page.h> #include <asm/asm-offsets.h> + +#ifdef CONFIG_PPC_BOOK3S_64 #include <asm/exception-64s.h> +#endif /***************************************************************************** * * @@ -30,6 +33,39 @@ * * ****************************************************************************/ +#if defined(CONFIG_PPC_BOOK3S_64) + +#define LOAD_SHADOW_VCPU(reg) \ + mfspr reg, SPRN_SPRG_PACA + +#define SHADOW_VCPU_OFF PACA_KVM_SVCPU +#define MSR_NOIRQ MSR_KERNEL & ~(MSR_IR | MSR_DR) +#define FUNC(name) GLUE(.,name) + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define LOAD_SHADOW_VCPU(reg) \ + mfspr reg, SPRN_SPRG_THREAD; \ + lwz reg, THREAD_KVM_SVCPU(reg); \ + /* PPC32 can have a NULL pointer - let's check for that */ \ + mtspr SPRN_SPRG_SCRATCH1, r12; /* Save r12 */ \ + mfcr r12; \ + cmpwi reg, 0; \ + bne 1f; \ + mfspr reg, SPRN_SPRG_SCRATCH0; \ + mtcr r12; \ + mfspr r12, SPRN_SPRG_SCRATCH1; \ + b kvmppc_resume_\intno; \ +1:; \ + mtcr r12; \ + mfspr r12, SPRN_SPRG_SCRATCH1; \ + tophys(reg, reg) + +#define SHADOW_VCPU_OFF 0 +#define MSR_NOIRQ MSR_KERNEL +#define FUNC(name) name + +#endif .macro INTERRUPT_TRAMPOLINE intno @@ -42,19 +78,19 @@ kvmppc_trampoline_\intno: * First thing to do is to find out if we're coming * from a KVM guest or a Linux process. * - * To distinguish, we check a magic byte in the PACA + * To distinguish, we check a magic byte in the PACA/current */ - mfspr r13, SPRN_SPRG_PACA /* r13 = PACA */ - std r12, PACA_KVM_SCRATCH0(r13) + LOAD_SHADOW_VCPU(r13) + PPC_STL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfcr r12 - stw r12, PACA_KVM_SCRATCH1(r13) - lbz r12, PACA_KVM_IN_GUEST(r13) + stw r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + lbz r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) cmpwi r12, KVM_GUEST_MODE_NONE bne ..kvmppc_handler_hasmagic_\intno /* No KVM guest? Then jump back to the Linux handler! */ - lwz r12, PACA_KVM_SCRATCH1(r13) + lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 - ld r12, PACA_KVM_SCRATCH0(r13) + PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ b kvmppc_resume_\intno /* Get back original handler */ @@ -76,9 +112,7 @@ kvmppc_trampoline_\intno: INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_SYSTEM_RESET INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_MACHINE_CHECK INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_STORAGE -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_STORAGE -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALIGNMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PROGRAM @@ -88,7 +122,14 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_SYSCALL INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_TRACE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PERFMON INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALTIVEC + +/* Those are only available on 64 bit machines */ + +#ifdef CONFIG_PPC_BOOK3S_64 +INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_SEGMENT +INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX +#endif /* * Bring us back to the faulting code, but skip the @@ -99,11 +140,11 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX * * Input Registers: * - * R12 = free - * R13 = PACA - * PACA.KVM.SCRATCH0 = guest R12 - * PACA.KVM.SCRATCH1 = guest CR - * SPRG_SCRATCH0 = guest R13 + * R12 = free + * R13 = Shadow VCPU (PACA) + * SVCPU.SCRATCH0 = guest R12 + * SVCPU.SCRATCH1 = guest CR + * SPRG_SCRATCH0 = guest R13 * */ kvmppc_handler_skip_ins: @@ -114,9 +155,9 @@ kvmppc_handler_skip_ins: mtsrr0 r12 /* Clean up all state */ - lwz r12, PACA_KVM_SCRATCH1(r13) + lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 - ld r12, PACA_KVM_SCRATCH0(r13) + PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* And get back into the code */ @@ -147,41 +188,48 @@ kvmppc_handler_lowmem_trampoline_end: * * R3 = function * R4 = MSR - * R5 = CTR + * R5 = scratch register * */ _GLOBAL(kvmppc_rmcall) - mtmsr r4 /* Disable relocation, so mtsrr + LOAD_REG_IMMEDIATE(r5, MSR_NOIRQ) + mtmsr r5 /* Disable relocation and interrupts, so mtsrr doesn't get interrupted */ - mtctr r5 + sync mtsrr0 r3 mtsrr1 r4 RFI +#if defined(CONFIG_PPC_BOOK3S_32) +#define STACK_LR INT_FRAME_SIZE+4 +#elif defined(CONFIG_PPC_BOOK3S_64) +#define STACK_LR _LINK +#endif + /* * Activate current's external feature (FPU/Altivec/VSX) */ -#define define_load_up(what) \ - \ -_GLOBAL(kvmppc_load_up_ ## what); \ - subi r1, r1, INT_FRAME_SIZE; \ - mflr r3; \ - std r3, _LINK(r1); \ - mfmsr r4; \ - std r31, GPR3(r1); \ - mr r31, r4; \ - li r5, MSR_DR; \ - oris r5, r5, MSR_EE@h; \ - andc r4, r4, r5; \ - mtmsr r4; \ - \ - bl .load_up_ ## what; \ - \ - mtmsr r31; \ - ld r3, _LINK(r1); \ - ld r31, GPR3(r1); \ - addi r1, r1, INT_FRAME_SIZE; \ - mtlr r3; \ +#define define_load_up(what) \ + \ +_GLOBAL(kvmppc_load_up_ ## what); \ + PPC_STLU r1, -INT_FRAME_SIZE(r1); \ + mflr r3; \ + PPC_STL r3, STACK_LR(r1); \ + PPC_STL r20, _NIP(r1); \ + mfmsr r20; \ + LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \ + andc r3,r20,r3; /* Disable DR,EE */ \ + mtmsr r3; \ + sync; \ + \ + bl FUNC(load_up_ ## what); \ + \ + mtmsr r20; /* Enable DR,EE */ \ + sync; \ + PPC_LL r3, STACK_LR(r1); \ + PPC_LL r20, _NIP(r1); \ + mtlr r3; \ + addi r1, r1, INT_FRAME_SIZE; \ blr define_load_up(fpu) @@ -194,11 +242,10 @@ define_load_up(vsx) .global kvmppc_trampoline_lowmem kvmppc_trampoline_lowmem: - .long kvmppc_handler_lowmem_trampoline - _stext + .long kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START .global kvmppc_trampoline_enter kvmppc_trampoline_enter: - .long kvmppc_handler_trampoline_enter - _stext - -#include "book3s_64_slb.S" + .long kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START +#include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S new file mode 100644 index 00000000000..7c52ed0b705 --- /dev/null +++ b/arch/powerpc/kvm/book3s_segment.S @@ -0,0 +1,259 @@ +/* + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +/* Real mode helpers */ + +#if defined(CONFIG_PPC_BOOK3S_64) + +#define GET_SHADOW_VCPU(reg) \ + addi reg, r13, PACA_KVM_SVCPU + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define GET_SHADOW_VCPU(reg) \ + tophys(reg, r2); \ + lwz reg, (THREAD + THREAD_KVM_SVCPU)(reg); \ + tophys(reg, reg) + +#endif + +/* Disable for nested KVM */ +#define USE_QUICK_LAST_INST + + +/* Get helper functions for subarch specific functionality */ + +#if defined(CONFIG_PPC_BOOK3S_64) +#include "book3s_64_slb.S" +#elif defined(CONFIG_PPC_BOOK3S_32) +#include "book3s_32_sr.S" +#endif + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + +.global kvmppc_handler_trampoline_enter +kvmppc_handler_trampoline_enter: + + /* Required state: + * + * MSR = ~IR|DR + * R13 = PACA + * R1 = host R1 + * R2 = host R2 + * R10 = guest MSR + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + */ + + /* r3 = shadow vcpu */ + GET_SHADOW_VCPU(r3) + + /* Move SRR0 and SRR1 into the respective regs */ + PPC_LL r9, SVCPU_PC(r3) + mtsrr0 r9 + mtsrr1 r10 + + /* Activate guest mode, so faults get handled by KVM */ + li r11, KVM_GUEST_MODE_GUEST + stb r11, SVCPU_IN_GUEST(r3) + + /* Switch to guest segment. This is subarch specific. */ + LOAD_GUEST_SEGMENTS + + /* Enter guest */ + + PPC_LL r4, (SVCPU_CTR)(r3) + PPC_LL r5, (SVCPU_LR)(r3) + lwz r6, (SVCPU_CR)(r3) + lwz r7, (SVCPU_XER)(r3) + + mtctr r4 + mtlr r5 + mtcr r6 + mtxer r7 + + PPC_LL r0, (SVCPU_R0)(r3) + PPC_LL r1, (SVCPU_R1)(r3) + PPC_LL r2, (SVCPU_R2)(r3) + PPC_LL r4, (SVCPU_R4)(r3) + PPC_LL r5, (SVCPU_R5)(r3) + PPC_LL r6, (SVCPU_R6)(r3) + PPC_LL r7, (SVCPU_R7)(r3) + PPC_LL r8, (SVCPU_R8)(r3) + PPC_LL r9, (SVCPU_R9)(r3) + PPC_LL r10, (SVCPU_R10)(r3) + PPC_LL r11, (SVCPU_R11)(r3) + PPC_LL r12, (SVCPU_R12)(r3) + PPC_LL r13, (SVCPU_R13)(r3) + + PPC_LL r3, (SVCPU_R3)(r3) + + RFI +kvmppc_handler_trampoline_enter_end: + + + +/****************************************************************************** + * * + * Exit code * + * * + *****************************************************************************/ + +.global kvmppc_handler_trampoline_exit +kvmppc_handler_trampoline_exit: + + /* Register usage at this point: + * + * SPRG_SCRATCH0 = guest R13 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.SCRATCH0 = guest R12 + * SVCPU.SCRATCH1 = guest CR + * + */ + + /* Save registers */ + + PPC_STL r0, (SHADOW_VCPU_OFF + SVCPU_R0)(r13) + PPC_STL r1, (SHADOW_VCPU_OFF + SVCPU_R1)(r13) + PPC_STL r2, (SHADOW_VCPU_OFF + SVCPU_R2)(r13) + PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_R3)(r13) + PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_R4)(r13) + PPC_STL r5, (SHADOW_VCPU_OFF + SVCPU_R5)(r13) + PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_R6)(r13) + PPC_STL r7, (SHADOW_VCPU_OFF + SVCPU_R7)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R8)(r13) + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R9)(r13) + PPC_STL r10, (SHADOW_VCPU_OFF + SVCPU_R10)(r13) + PPC_STL r11, (SHADOW_VCPU_OFF + SVCPU_R11)(r13) + + /* Restore R1/R2 so we can handle faults */ + PPC_LL r1, (SHADOW_VCPU_OFF + SVCPU_HOST_R1)(r13) + PPC_LL r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13) + + /* Save guest PC and MSR */ + mfsrr0 r3 + mfsrr1 r4 + + PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13) + PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13) + + /* Get scratch'ed off registers */ + mfspr r9, SPRN_SPRG_SCRATCH0 + PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) + lwz r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R13)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R12)(r13) + stw r7, (SHADOW_VCPU_OFF + SVCPU_CR)(r13) + + /* Save more register state */ + + mfxer r5 + mfdar r6 + mfdsisr r7 + mfctr r8 + mflr r9 + + stw r5, (SHADOW_VCPU_OFF + SVCPU_XER)(r13) + PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_FAULT_DAR)(r13) + stw r7, (SHADOW_VCPU_OFF + SVCPU_FAULT_DSISR)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_CTR)(r13) + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_LR)(r13) + + /* + * In order for us to easily get the last instruction, + * we got the #vmexit at, we exploit the fact that the + * virtual layout is still the same here, so we can just + * ld from the guest's PC address + */ + + /* We only load the last instruction when it's safe */ + cmpwi r12, BOOK3S_INTERRUPT_DATA_STORAGE + beq ld_last_inst + cmpwi r12, BOOK3S_INTERRUPT_PROGRAM + beq ld_last_inst + cmpwi r12, BOOK3S_INTERRUPT_ALIGNMENT + beq- ld_last_inst + + b no_ld_last_inst + +ld_last_inst: + /* Save off the guest instruction we're at */ + + /* In case lwz faults */ + li r0, KVM_INST_FETCH_FAILED + +#ifdef USE_QUICK_LAST_INST + + /* Set guest mode to 'jump over instruction' so if lwz faults + * we'll just continue at the next IP. */ + li r9, KVM_GUEST_MODE_SKIP + stb r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + + /* 1) enable paging for data */ + mfmsr r9 + ori r11, r9, MSR_DR /* Enable paging for data */ + mtmsr r11 + sync + /* 2) fetch the instruction */ + lwz r0, 0(r3) + /* 3) disable paging again */ + mtmsr r9 + sync + +#endif + stw r0, (SHADOW_VCPU_OFF + SVCPU_LAST_INST)(r13) + +no_ld_last_inst: + + /* Unset guest mode */ + li r9, KVM_GUEST_MODE_NONE + stb r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + + /* Switch back to host MMU */ + LOAD_HOST_SEGMENTS + + /* Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.* = guest * + * + */ + + /* RFI into the highmem handler */ + mfmsr r7 + ori r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME /* Enable paging */ + mtsrr1 r7 + /* Load highmem handler address */ + PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_VMHANDLER)(r13) + mtsrr0 r8 + + RFI +kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 2a3a1953d4b..a33ab8cc2cc 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -133,6 +133,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_EXTERNAL); } +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions); +} + /* Deliver the interrupt of the corresponding priority, if possible. */ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) @@ -479,6 +485,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + regs->pc = vcpu->arch.pc; regs->cr = kvmppc_get_cr(vcpu); regs->ctr = vcpu->arch.ctr; @@ -499,6 +507,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) regs->gpr[i] = kvmppc_get_gpr(vcpu, i); + vcpu_put(vcpu); + return 0; } @@ -506,6 +516,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + vcpu->arch.pc = regs->pc; kvmppc_set_cr(vcpu, regs->cr); vcpu->arch.ctr = regs->ctr; @@ -525,6 +537,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) kvmppc_set_gpr(vcpu, i, regs->gpr[i]); + vcpu_put(vcpu); + return 0; } @@ -553,7 +567,12 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { - return kvmppc_core_vcpu_translate(vcpu, tr); + int r; + + vcpu_load(vcpu); + r = kvmppc_core_vcpu_translate(vcpu, tr); + vcpu_put(vcpu); + return r; } int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 669a5c5fc7d..bc2b4004eb2 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -161,7 +161,7 @@ static int __init kvmppc_e500_init(void) flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers + max_ivor + kvmppc_handler_len); - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE); + return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); } static void __init kvmppc_e500_exit(void) diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index cb72a65f4ec..4568ec386c2 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -38,10 +38,12 @@ #define OP_31_XOP_LBZX 87 #define OP_31_XOP_STWX 151 #define OP_31_XOP_STBX 215 +#define OP_31_XOP_LBZUX 119 #define OP_31_XOP_STBUX 247 #define OP_31_XOP_LHZX 279 #define OP_31_XOP_LHZUX 311 #define OP_31_XOP_MFSPR 339 +#define OP_31_XOP_LHAX 343 #define OP_31_XOP_STHX 407 #define OP_31_XOP_STHUX 439 #define OP_31_XOP_MTSPR 467 @@ -62,10 +64,12 @@ #define OP_STBU 39 #define OP_LHZ 40 #define OP_LHZU 41 +#define OP_LHA 42 +#define OP_LHAU 43 #define OP_STH 44 #define OP_STHU 45 -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu) { return 1; @@ -82,7 +86,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) unsigned long dec_nsec; pr_debug("mtDEC: %x\n", vcpu->arch.dec); -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S /* mtdec lowers the interrupt line when positive. */ kvmppc_core_dequeue_dec(vcpu); @@ -128,7 +132,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) * from opcode tables in the future. */ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) { - u32 inst = vcpu->arch.last_inst; + u32 inst = kvmppc_get_last_inst(vcpu); u32 ea; int ra; int rb; @@ -143,13 +147,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst)); - /* Try again next time */ - if (inst == KVM_INST_FETCH_FAILED) - return EMULATE_DONE; - switch (get_op(inst)) { case OP_TRAP: -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S case OP_TRAP_64: kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP); #else @@ -171,6 +171,19 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); break; + case OP_31_XOP_LBZUX: + rt = get_rt(inst); + ra = get_ra(inst); + rb = get_rb(inst); + + ea = kvmppc_get_gpr(vcpu, rb); + if (ra) + ea += kvmppc_get_gpr(vcpu, ra); + + emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); + kvmppc_set_gpr(vcpu, ra, ea); + break; + case OP_31_XOP_STWX: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, @@ -200,6 +213,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_set_gpr(vcpu, rs, ea); break; + case OP_31_XOP_LHAX: + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + break; + case OP_31_XOP_LHZX: rt = get_rt(inst); emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1); @@ -450,6 +468,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; + case OP_LHA: + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + break; + + case OP_LHAU: + ra = get_ra(inst); + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); + break; + case OP_STH: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, @@ -472,7 +502,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) if (emulated == EMULATE_FAIL) { emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance); - if (emulated == EMULATE_FAIL) { + if (emulated == EMULATE_AGAIN) { + advance = 0; + } else if (emulated == EMULATE_FAIL) { advance = 0; printk(KERN_ERR "Couldn't emulate instruction 0x%08x " "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst)); @@ -480,10 +512,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) } } - trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated); + trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated); + /* Advance past emulated instruction. */ if (advance) - vcpu->arch.pc += 4; /* Advance past emulated instruction. */ + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); return emulated; } diff --git a/arch/powerpc/kvm/fpu.S b/arch/powerpc/kvm/fpu.S new file mode 100644 index 00000000000..2b340a3eee9 --- /dev/null +++ b/arch/powerpc/kvm/fpu.S @@ -0,0 +1,273 @@ +/* + * FPU helper code to use FPU operations from inside the kernel + * + * Copyright (C) 2010 Alexander Graf (agraf@suse.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 <asm/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* Instructions operating on single parameters */ + +/* + * Single operation with one input operand + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + */ +#define FPS_ONE_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + \ + name 0,0; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +/* + * Single operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + * R6 = (short*)¶m2 + */ +#define FPS_TWO_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + lfs 1,0(r6); \ + \ + name 0,0,1; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +/* + * Single operation with three input operands + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + * R6 = (short*)¶m2 + * R7 = (short*)¶m3 + */ +#define FPS_THREE_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + lfs 1,0(r6); \ + lfs 2,0(r7); \ + \ + name 0,0,1,2; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +FPS_ONE_IN(fres) +FPS_ONE_IN(frsqrte) +FPS_ONE_IN(fsqrts) +FPS_TWO_IN(fadds) +FPS_TWO_IN(fdivs) +FPS_TWO_IN(fmuls) +FPS_TWO_IN(fsubs) +FPS_THREE_IN(fmadds) +FPS_THREE_IN(fmsubs) +FPS_THREE_IN(fnmadds) +FPS_THREE_IN(fnmsubs) +FPS_THREE_IN(fsel) + + +/* Instructions operating on double parameters */ + +/* + * Beginning of double instruction processing + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 [load_two] + * R8 = (double*)¶m3 [load_three] + * LR = instruction call function + */ +fpd_load_three: + lfd 2,0(r8) /* load param3 */ +fpd_load_two: + lfd 1,0(r7) /* load param2 */ +fpd_load_one: + lfd 0,0(r6) /* load param1 */ +fpd_load_none: + lfd 3,0(r3) /* load up fpscr value */ + MTFSF_L(3) + lwz r6, 0(r4) /* load cr */ + mtcr r6 + blr + +/* + * End of double instruction processing + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * LR = caller of instruction call function + */ +fpd_return: + mfcr r6 + stfd 0,0(r5) /* save result */ + mffs 0 + stfd 0,0(r3) /* save new fpscr value */ + stw r6,0(r4) /* save new cr value */ + blr + +/* + * Double operation with no input operand + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + */ +#define FPD_NONE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_none; \ + mtlr r12; \ + \ + name. 0; /* call instruction */ \ + b fpd_return + +/* + * Double operation with one input operand + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + */ +#define FPD_ONE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_one; \ + mtlr r12; \ + \ + name. 0,0; /* call instruction */ \ + b fpd_return + +/* + * Double operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 + * R8 = (double*)¶m3 + */ +#define FPD_TWO_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_two; \ + mtlr r12; \ + \ + name. 0,0,1; /* call instruction */ \ + b fpd_return + +/* + * CR Double operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)¶m1 + * R6 = (double*)¶m2 + * R7 = (double*)¶m3 + */ +#define FPD_TWO_IN_CR(name) \ +_GLOBAL(fpd_ ## name); \ + lfd 1,0(r6); /* load param2 */ \ + lfd 0,0(r5); /* load param1 */ \ + lfd 3,0(r3); /* load up fpscr value */ \ + MTFSF_L(3); \ + lwz r6, 0(r4); /* load cr */ \ + mtcr r6; \ + \ + name 0,0,1; /* call instruction */ \ + mfcr r6; \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + stw r6,0(r4); /* save new cr value */ \ + blr + +/* + * Double operation with three input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 + * R8 = (double*)¶m3 + */ +#define FPD_THREE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_three; \ + mtlr r12; \ + \ + name. 0,0,1,2; /* call instruction */ \ + b fpd_return + +FPD_ONE_IN(fsqrts) +FPD_ONE_IN(frsqrtes) +FPD_ONE_IN(fres) +FPD_ONE_IN(frsp) +FPD_ONE_IN(fctiw) +FPD_ONE_IN(fctiwz) +FPD_ONE_IN(fsqrt) +FPD_ONE_IN(fre) +FPD_ONE_IN(frsqrte) +FPD_ONE_IN(fneg) +FPD_ONE_IN(fabs) +FPD_TWO_IN(fadds) +FPD_TWO_IN(fsubs) +FPD_TWO_IN(fdivs) +FPD_TWO_IN(fmuls) +FPD_TWO_IN_CR(fcmpu) +FPD_TWO_IN(fcpsgn) +FPD_TWO_IN(fdiv) +FPD_TWO_IN(fadd) +FPD_TWO_IN(fmul) +FPD_TWO_IN_CR(fcmpo) +FPD_TWO_IN(fsub) +FPD_THREE_IN(fmsubs) +FPD_THREE_IN(fmadds) +FPD_THREE_IN(fnmsubs) +FPD_THREE_IN(fnmadds) +FPD_THREE_IN(fsel) +FPD_THREE_IN(fmsub) +FPD_THREE_IN(fmadd) +FPD_THREE_IN(fnmsub) +FPD_THREE_IN(fnmadd) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 297fcd2ff7d..9b8683f39e0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -70,7 +70,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) case EMULATE_FAIL: /* XXX Deliver Program interrupt to guest. */ printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__, - vcpu->arch.last_inst); + kvmppc_get_last_inst(vcpu)); r = RESUME_HOST; break; default: @@ -148,6 +148,10 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_PPC_SEGSTATE: + case KVM_CAP_PPC_PAIRED_SINGLES: + case KVM_CAP_PPC_UNSET_IRQ: + case KVM_CAP_ENABLE_CAP: + case KVM_CAP_PPC_OSI: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -193,12 +197,17 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvm_vcpu *vcpu; vcpu = kvmppc_core_vcpu_create(kvm, id); - kvmppc_create_vcpu_debugfs(vcpu, id); + if (!IS_ERR(vcpu)) + kvmppc_create_vcpu_debugfs(vcpu, id); return vcpu; } void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + /* Make sure we're not using the vcpu anymore */ + hrtimer_cancel(&vcpu->arch.dec_timer); + tasklet_kill(&vcpu->arch.tasklet); + kvmppc_remove_vcpu_debugfs(vcpu); kvmppc_core_vcpu_free(vcpu); } @@ -278,7 +287,7 @@ static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu, static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { - ulong gpr; + u64 gpr; if (run->mmio.len > sizeof(gpr)) { printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len); @@ -287,6 +296,7 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, if (vcpu->arch.mmio_is_bigendian) { switch (run->mmio.len) { + case 8: gpr = *(u64 *)run->mmio.data; break; case 4: gpr = *(u32 *)run->mmio.data; break; case 2: gpr = *(u16 *)run->mmio.data; break; case 1: gpr = *(u8 *)run->mmio.data; break; @@ -300,7 +310,43 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, } } + if (vcpu->arch.mmio_sign_extend) { + switch (run->mmio.len) { +#ifdef CONFIG_PPC64 + case 4: + gpr = (s64)(s32)gpr; + break; +#endif + case 2: + gpr = (s64)(s16)gpr; + break; + case 1: + gpr = (s64)(s8)gpr; + break; + } + } + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); + + switch (vcpu->arch.io_gpr & KVM_REG_EXT_MASK) { + case KVM_REG_GPR: + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); + break; + case KVM_REG_FPR: + vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; +#ifdef CONFIG_PPC_BOOK3S + case KVM_REG_QPR: + vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; + case KVM_REG_FQPR: + vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; +#endif + default: + BUG(); + } } int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, @@ -319,12 +365,25 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.mmio_is_bigendian = is_bigendian; vcpu->mmio_needed = 1; vcpu->mmio_is_write = 0; + vcpu->arch.mmio_sign_extend = 0; return EMULATE_DO_MMIO; } +/* Same as above, but sign extends */ +int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, int is_bigendian) +{ + int r; + + r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian); + vcpu->arch.mmio_sign_extend = 1; + + return r; +} + int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u32 val, unsigned int bytes, int is_bigendian) + u64 val, unsigned int bytes, int is_bigendian) { void *data = run->mmio.data; @@ -342,6 +401,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, /* Store the value at the lowest bytes in 'data'. */ if (is_bigendian) { switch (bytes) { + case 8: *(u64 *)data = val; break; case 4: *(u32 *)data = val; break; case 2: *(u16 *)data = val; break; case 1: *(u8 *)data = val; break; @@ -376,6 +436,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (!vcpu->arch.dcr_is_write) kvmppc_complete_dcr_load(vcpu, run); vcpu->arch.dcr_needed = 0; + } else if (vcpu->arch.osi_needed) { + u64 *gprs = run->osi.gprs; + int i; + + for (i = 0; i < 32; i++) + kvmppc_set_gpr(vcpu, i, gprs[i]); + vcpu->arch.osi_needed = 0; } kvmppc_core_deliver_interrupts(vcpu); @@ -396,7 +463,10 @@ 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) { - kvmppc_core_queue_external(vcpu, irq); + if (irq->irq == KVM_INTERRUPT_UNSET) + kvmppc_core_dequeue_external(vcpu, irq); + else + kvmppc_core_queue_external(vcpu, irq); if (waitqueue_active(&vcpu->wq)) { wake_up_interruptible(&vcpu->wq); @@ -406,6 +476,27 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_PPC_OSI: + r = 0; + vcpu->arch.osi_enabled = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { @@ -434,6 +525,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } + case KVM_ENABLE_CAP: + { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -EINVAL; } diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S index 64e2e499e32..455881a5563 100644 --- a/arch/powerpc/lib/string.S +++ b/arch/powerpc/lib/string.S @@ -28,7 +28,7 @@ _GLOBAL(strcpy) /* This clears out any unused part of the destination buffer, just as the libc version does. -- paulus */ _GLOBAL(strncpy) - cmpwi 0,r5,0 + PPC_LCMPI 0,r5,0 beqlr mtctr r5 addi r6,r3,-1 @@ -39,7 +39,7 @@ _GLOBAL(strncpy) bdnzf 2,1b /* dec ctr, branch if ctr != 0 && !cr0.eq */ bnelr /* if we didn't hit a null char, we're done */ mfctr r5 - cmpwi 0,r5,0 /* any space left in destination buffer? */ + PPC_LCMPI 0,r5,0 /* any space left in destination buffer? */ beqlr /* we know r0 == 0 here */ 2: stbu r0,1(r6) /* clear it out if so */ bdnz 2b @@ -70,8 +70,8 @@ _GLOBAL(strcmp) blr _GLOBAL(strncmp) - PPC_LCMPI r5,0 - beqlr + PPC_LCMPI 0,r5,0 + beq- 2f mtctr r5 addi r5,r3,-1 addi r4,r4,-1 @@ -82,6 +82,8 @@ _GLOBAL(strncmp) beqlr 1 bdnzt eq,1b blr +2: li r3,0 + blr _GLOBAL(strlen) addi r4,r3,-1 @@ -92,8 +94,8 @@ _GLOBAL(strlen) blr _GLOBAL(memcmp) - cmpwi 0,r5,0 - ble- 2f + PPC_LCMPI 0,r5,0 + beq- 2f mtctr r5 addi r6,r3,-1 addi r4,r4,-1 @@ -106,8 +108,8 @@ _GLOBAL(memcmp) blr _GLOBAL(memchr) - cmpwi 0,r5,0 - ble- 2f + PPC_LCMPI 0,r5,0 + beq- 2f mtctr r5 addi r3,r3,-1 1: lbzu r0,1(r3) diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c index 3986264b099..d8c6efb32bc 100644 --- a/arch/powerpc/mm/44x_mmu.c +++ b/arch/powerpc/mm/44x_mmu.c @@ -38,7 +38,9 @@ unsigned int tlb_44x_index; /* = 0 */ unsigned int tlb_44x_hwater = PPC44x_TLB_SIZE - 1 - PPC44x_EARLY_TLBS; int icache_44x_need_flush; -static void __init ppc44x_update_tlb_hwater(void) +unsigned long tlb_47x_boltmap[1024/8]; + +static void __cpuinit ppc44x_update_tlb_hwater(void) { extern unsigned int tlb_44x_patch_hwater_D[]; extern unsigned int tlb_44x_patch_hwater_I[]; @@ -59,7 +61,7 @@ static void __init ppc44x_update_tlb_hwater(void) } /* - * "Pins" a 256MB TLB entry in AS0 for kernel lowmem + * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 44x type MMU */ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys) { @@ -67,12 +69,18 @@ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys) ppc44x_update_tlb_hwater(); + mtspr(SPRN_MMUCR, 0); + __asm__ __volatile__( "tlbwe %2,%3,%4\n" "tlbwe %1,%3,%5\n" "tlbwe %0,%3,%6\n" : +#ifdef CONFIG_PPC47x + : "r" (PPC47x_TLB2_S_RWX), +#else : "r" (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G), +#endif "r" (phys), "r" (virt | PPC44x_TLB_VALID | PPC44x_TLB_256M), "r" (entry), @@ -81,8 +89,93 @@ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys) "i" (PPC44x_TLB_ATTRIB)); } +static int __init ppc47x_find_free_bolted(void) +{ + unsigned int mmube0 = mfspr(SPRN_MMUBE0); + unsigned int mmube1 = mfspr(SPRN_MMUBE1); + + if (!(mmube0 & MMUBE0_VBE0)) + return 0; + if (!(mmube0 & MMUBE0_VBE1)) + return 1; + if (!(mmube0 & MMUBE0_VBE2)) + return 2; + if (!(mmube1 & MMUBE1_VBE3)) + return 3; + if (!(mmube1 & MMUBE1_VBE4)) + return 4; + if (!(mmube1 & MMUBE1_VBE5)) + return 5; + return -1; +} + +static void __init ppc47x_update_boltmap(void) +{ + unsigned int mmube0 = mfspr(SPRN_MMUBE0); + unsigned int mmube1 = mfspr(SPRN_MMUBE1); + + if (mmube0 & MMUBE0_VBE0) + __set_bit((mmube0 >> MMUBE0_IBE0_SHIFT) & 0xff, + tlb_47x_boltmap); + if (mmube0 & MMUBE0_VBE1) + __set_bit((mmube0 >> MMUBE0_IBE1_SHIFT) & 0xff, + tlb_47x_boltmap); + if (mmube0 & MMUBE0_VBE2) + __set_bit((mmube0 >> MMUBE0_IBE2_SHIFT) & 0xff, + tlb_47x_boltmap); + if (mmube1 & MMUBE1_VBE3) + __set_bit((mmube1 >> MMUBE1_IBE3_SHIFT) & 0xff, + tlb_47x_boltmap); + if (mmube1 & MMUBE1_VBE4) + __set_bit((mmube1 >> MMUBE1_IBE4_SHIFT) & 0xff, + tlb_47x_boltmap); + if (mmube1 & MMUBE1_VBE5) + __set_bit((mmube1 >> MMUBE1_IBE5_SHIFT) & 0xff, + tlb_47x_boltmap); +} + +/* + * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 47x type MMU + */ +static void __cpuinit ppc47x_pin_tlb(unsigned int virt, unsigned int phys) +{ + unsigned int rA; + int bolted; + + /* Base rA is HW way select, way 0, bolted bit set */ + rA = 0x88000000; + + /* Look for a bolted entry slot */ + bolted = ppc47x_find_free_bolted(); + BUG_ON(bolted < 0); + + /* Insert bolted slot number */ + rA |= bolted << 24; + + pr_debug("256M TLB entry for 0x%08x->0x%08x in bolt slot %d\n", + virt, phys, bolted); + + mtspr(SPRN_MMUCR, 0); + + __asm__ __volatile__( + "tlbwe %2,%3,0\n" + "tlbwe %1,%3,1\n" + "tlbwe %0,%3,2\n" + : + : "r" (PPC47x_TLB2_SW | PPC47x_TLB2_SR | + PPC47x_TLB2_SX +#ifdef CONFIG_SMP + | PPC47x_TLB2_M +#endif + ), + "r" (phys), + "r" (virt | PPC47x_TLB0_VALID | PPC47x_TLB0_256M), + "r" (rA)); +} + void __init MMU_init_hw(void) { + /* This is not useful on 47x but won't hurt either */ ppc44x_update_tlb_hwater(); flush_instruction_cache(); @@ -95,8 +188,51 @@ unsigned long __init mmu_mapin_ram(unsigned long top) /* Pin in enough TLBs to cover any lowmem not covered by the * initial 256M mapping established in head_44x.S */ for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr; - addr += PPC_PIN_SIZE) - ppc44x_pin_tlb(addr + PAGE_OFFSET, addr); + addr += PPC_PIN_SIZE) { + if (mmu_has_feature(MMU_FTR_TYPE_47x)) + ppc47x_pin_tlb(addr + PAGE_OFFSET, addr); + else + ppc44x_pin_tlb(addr + PAGE_OFFSET, addr); + } + if (mmu_has_feature(MMU_FTR_TYPE_47x)) { + ppc47x_update_boltmap(); +#ifdef DEBUG + { + int i; + + printk(KERN_DEBUG "bolted entries: "); + for (i = 0; i < 255; i++) { + if (test_bit(i, tlb_47x_boltmap)) + printk("%d ", i); + } + printk("\n"); + } +#endif /* DEBUG */ + } return total_lowmem; } + +#ifdef CONFIG_SMP +void __cpuinit mmu_init_secondary(int cpu) +{ + unsigned long addr; + + /* Pin in enough TLBs to cover any lowmem not covered by the + * initial 256M mapping established in head_44x.S + * + * WARNING: This is called with only the first 256M of the + * linear mapping in the TLB and we can't take faults yet + * so beware of what this code uses. It runs off a temporary + * stack. current (r2) isn't initialized, smp_processor_id() + * will not work, current thread info isn't accessible, ... + */ + for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr; + addr += PPC_PIN_SIZE) { + if (mmu_has_feature(MMU_FTR_TYPE_47x)) + ppc47x_pin_tlb(addr + PAGE_OFFSET, addr); + else + ppc44x_pin_tlb(addr + PAGE_OFFSET, addr); + } +} +#endif /* CONFIG_SMP */ diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 26fb6b990b0..1bd712c33ce 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -151,13 +151,14 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, if (!user_mode(regs) && (address >= TASK_SIZE)) return SIGSEGV; -#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) +#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \ + defined(CONFIG_PPC_BOOK3S_64)) if (error_code & DSISR_DABRMATCH) { /* DABR match */ do_dabr(regs, address, error_code); return 0; } -#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/ +#endif if (in_atomic() || mm == NULL) { if (!user_mode(regs)) @@ -307,7 +308,6 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - survive: ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(ret & VM_FAULT_ERROR)) { if (ret & VM_FAULT_OOM) @@ -359,15 +359,10 @@ bad_area_nosemaphore: */ out_of_memory: up_read(&mm->mmap_sem); - if (is_global_init(current)) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } - printk("VM: killing process %s\n", current->comm); - if (user_mode(regs)) - do_group_exit(SIGKILL); - return SIGKILL; + if (!user_mode(regs)) + return SIGKILL; + pagefault_out_of_memory(); + return 0; do_sigbus: up_read(&mm->mmap_sem); diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index 1ed6b52f303..cdc7526e9c9 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -2,7 +2,7 @@ * Modifications by Kumar Gala (galak@kernel.crashing.org) to support * E500 Book E processors. * - * Copyright 2004 Freescale Semiconductor, Inc + * Copyright 2004,2010 Freescale Semiconductor, Inc. * * This file contains the routines for initializing the MMU * on the 4xx series of chips. @@ -56,19 +56,13 @@ unsigned int tlbcam_index; -#define NUM_TLBCAMS (64) #if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS) #error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS" #endif -struct tlbcam { - u32 MAS0; - u32 MAS1; - unsigned long MAS2; - u32 MAS3; - u32 MAS7; -} TLBCAM[NUM_TLBCAMS]; +#define NUM_TLBCAMS (64) +struct tlbcam TLBCAM[NUM_TLBCAMS]; struct tlbcamrange { unsigned long start; @@ -109,19 +103,6 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa) return 0; } -void loadcam_entry(int idx) -{ - mtspr(SPRN_MAS0, TLBCAM[idx].MAS0); - mtspr(SPRN_MAS1, TLBCAM[idx].MAS1); - mtspr(SPRN_MAS2, TLBCAM[idx].MAS2); - mtspr(SPRN_MAS3, TLBCAM[idx].MAS3); - - if (mmu_has_feature(MMU_FTR_BIG_PHYS)) - mtspr(SPRN_MAS7, TLBCAM[idx].MAS7); - - asm volatile("isync;tlbwe;isync" : : : "memory"); -} - /* * Set up one of the I/D BAT (block address translation) register pairs. * The parameters are not checked; in particular size must be a power diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index d7fa50b09b4..e267f223fdf 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -252,6 +252,47 @@ static void __meminit vmemmap_create_mapping(unsigned long start, } #endif /* CONFIG_PPC_BOOK3E */ +struct vmemmap_backing *vmemmap_list; + +static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node) +{ + static struct vmemmap_backing *next; + static int num_left; + + /* allocate a page when required and hand out chunks */ + if (!next || !num_left) { + next = vmemmap_alloc_block(PAGE_SIZE, node); + if (unlikely(!next)) { + WARN_ON(1); + return NULL; + } + num_left = PAGE_SIZE / sizeof(struct vmemmap_backing); + } + + num_left--; + + return next++; +} + +static __meminit void vmemmap_list_populate(unsigned long phys, + unsigned long start, + int node) +{ + struct vmemmap_backing *vmem_back; + + vmem_back = vmemmap_list_alloc(node); + if (unlikely(!vmem_back)) { + WARN_ON(1); + return; + } + + vmem_back->phys = phys; + vmem_back->virt_addr = start; + vmem_back->list = vmemmap_list; + + vmemmap_list = vmem_back; +} + int __meminit vmemmap_populate(struct page *start_page, unsigned long nr_pages, int node) { @@ -276,6 +317,8 @@ int __meminit vmemmap_populate(struct page *start_page, if (!p) return -ENOMEM; + vmemmap_list_populate(__pa(p), start, node); + pr_debug(" * %016lx..%016lx allocated at %p\n", start, start + page_size, p); diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c index 0dfba2bf7f3..d0ee554e86e 100644 --- a/arch/powerpc/mm/mmu_context_hash32.c +++ b/arch/powerpc/mm/mmu_context_hash32.c @@ -60,11 +60,7 @@ static unsigned long next_mmu_context; static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; - -/* - * Set up the context for a new address space. - */ -int init_new_context(struct task_struct *t, struct mm_struct *mm) +unsigned long __init_new_context(void) { unsigned long ctx = next_mmu_context; @@ -74,19 +70,38 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) ctx = 0; } next_mmu_context = (ctx + 1) & LAST_CONTEXT; - mm->context.id = ctx; + + return ctx; +} +EXPORT_SYMBOL_GPL(__init_new_context); + +/* + * Set up the context for a new address space. + */ +int init_new_context(struct task_struct *t, struct mm_struct *mm) +{ + mm->context.id = __init_new_context(); return 0; } /* + * Free a context ID. Make sure to call this with preempt disabled! + */ +void __destroy_context(unsigned long ctx) +{ + clear_bit(ctx, context_map); +} +EXPORT_SYMBOL_GPL(__destroy_context); + +/* * We're finished using the context for an address space. */ void destroy_context(struct mm_struct *mm) { preempt_disable(); if (mm->context.id != NO_CONTEXT) { - clear_bit(mm->context.id, context_map); + __destroy_context(mm->context.id); mm->context.id = NO_CONTEXT; } preempt_enable(); diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 1f2d9ff0989..ddfd7ad4e1d 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -395,10 +395,18 @@ void __init mmu_context_init(void) * the PID/TID comparison is disabled, so we can use a TID of zero * to represent all kernel pages as shared among all contexts. * -- Dan + * + * The IBM 47x core supports 16-bit PIDs, thus 65535 contexts. We + * should normally never have to steal though the facility is + * present if needed. + * -- BenH */ if (mmu_has_feature(MMU_FTR_TYPE_8xx)) { first_context = 0; last_context = 15; + } else if (mmu_has_feature(MMU_FTR_TYPE_47x)) { + first_context = 1; + last_context = 65535; } else { first_context = 1; last_context = 255; diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index d49a77503e1..63b84a0d3b1 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -69,12 +69,7 @@ static inline void _tlbil_va(unsigned long address, unsigned int pid, } #endif /* CONIFG_8xx */ -/* - * As of today, we don't support tlbivax broadcast on any - * implementation. When that becomes the case, this will be - * an extern. - */ -#ifdef CONFIG_PPC_BOOK3E +#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_PPC_47x) extern void _tlbivax_bcast(unsigned long address, unsigned int pid, unsigned int tsize, unsigned int ind); #else @@ -149,7 +144,15 @@ extern unsigned long mmu_mapin_ram(unsigned long top); extern void MMU_init_hw(void); extern unsigned long mmu_mapin_ram(unsigned long top); extern void adjust_total_lowmem(void); - +extern void loadcam_entry(unsigned int index); + +struct tlbcam { + u32 MAS0; + u32 MAS1; + unsigned long MAS2; + u32 MAS3; + u32 MAS7; +}; #elif defined(CONFIG_PPC32) /* anything 32-bit except 4xx or 8xx */ extern void MMU_init_hw(void); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index eaa7633515b..80d110635d2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -33,16 +33,41 @@ static int numa_debug; #define dbg(args...) if (numa_debug) { printk(KERN_INFO args); } int numa_cpu_lookup_table[NR_CPUS]; -cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(numa_cpu_lookup_table); -EXPORT_SYMBOL(numa_cpumask_lookup_table); +EXPORT_SYMBOL(node_to_cpumask_map); EXPORT_SYMBOL(node_data); static int min_common_depth; static int n_mem_addr_cells, n_mem_size_cells; +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + */ +static void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + + /* 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; + } + + /* allocate the map */ + for (node = 0; node < nr_node_ids; node++) + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + + /* cpumask_of_node() will now work */ + dbg("Node to cpumask map for %d nodes\n", nr_node_ids); +} + static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn, unsigned int *nid) { @@ -138,8 +163,8 @@ static void __cpuinit map_cpu_to_node(int cpu, int node) dbg("adding cpu %d to node %d\n", cpu, node); - if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) - cpu_set(cpu, numa_cpumask_lookup_table[node]); + if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node]))) + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); } #ifdef CONFIG_HOTPLUG_CPU @@ -149,8 +174,8 @@ static void unmap_cpu_from_node(unsigned long cpu) dbg("removing cpu %lu from node %d\n", cpu, node); - if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) { - cpu_clear(cpu, numa_cpumask_lookup_table[node]); + if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) { + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); } else { printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n", cpu, node); @@ -246,7 +271,8 @@ static int __init find_min_common_depth(void) const unsigned int *ref_points; struct device_node *rtas_root; unsigned int len; - struct device_node *options; + struct device_node *chosen; + const char *vec5; rtas_root = of_find_node_by_path("/rtas"); @@ -264,14 +290,17 @@ static int __init find_min_common_depth(void) "ibm,associativity-reference-points", &len); /* - * For type 1 affinity information we want the first field + * For form 1 affinity information we want the first field */ - options = of_find_node_by_path("/options"); - if (options) { - const char *str; - str = of_get_property(options, "ibm,associativity-form", NULL); - if (str && !strcmp(str, "1")) - index = 0; +#define VEC5_AFFINITY_BYTE 5 +#define VEC5_AFFINITY 0x80 + 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"); + index = 0; + } } if ((len >= 2 * sizeof(unsigned int)) && ref_points) { @@ -750,8 +779,9 @@ void __init dump_numa_cpu_topology(void) * If we used a CPU iterator here we would miss printing * the holes in the cpumap. */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { - if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) { + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { + if (cpumask_test_cpu(cpu, + node_to_cpumask_map[node])) { if (count == 0) printk(" %u", cpu); ++count; @@ -763,7 +793,7 @@ void __init dump_numa_cpu_topology(void) } if (count > 1) - printk("-%u", NR_CPUS - 1); + printk("-%u", nr_cpu_ids - 1); printk("\n"); } } @@ -939,10 +969,6 @@ void __init do_init_bootmem(void) else dump_numa_memory_topology(); - register_cpu_notifier(&ppc64_numa_nb); - cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, - (void *)(unsigned long)boot_cpuid); - for_each_online_node(nid) { unsigned long start_pfn, end_pfn; void *bootmem_vaddr; @@ -996,6 +1022,16 @@ void __init do_init_bootmem(void) } init_bootmem_done = 1; + + /* + * Now bootmem is initialised we can create the node to cpumask + * lookup tables and setup the cpu callback to populate them. + */ + setup_node_to_cpumask_map(); + + register_cpu_notifier(&ppc64_numa_nb); + cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, + (void *)(unsigned long)boot_cpuid); } void __init paging_init(void) diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index b9243e7557a..9fc02dc72ce 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -146,6 +146,14 @@ ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags) /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ flags &= ~(_PAGE_USER | _PAGE_EXEC); +#ifdef _PAGE_BAP_SR + /* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format + * which means that we just cleared supervisor access... oops ;-) This + * restores it + */ + flags |= _PAGE_BAP_SR; +#endif + return __ioremap_caller(addr, size, flags, __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_flags); @@ -385,11 +393,7 @@ static int __change_page_attr(struct page *page, pgprot_t prot) return -EINVAL; __set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0); wmb(); -#ifdef CONFIG_PPC_STD_MMU - flush_hash_pages(0, address, pmd_val(*kpmd), 1); -#else flush_tlb_page(NULL, address); -#endif pte_unmap(kpte); return 0; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index d95679a5fb2..d050fc8d971 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -265,6 +265,14 @@ void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size, /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ flags &= ~(_PAGE_USER | _PAGE_EXEC); +#ifdef _PAGE_BAP_SR + /* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format + * which means that we just cleared supervisor access... oops ;-) This + * restores it + */ + flags |= _PAGE_BAP_SR; +#endif + if (ppc_md.ioremap) return ppc_md.ioremap(addr, size, flags, caller); return __ioremap_caller(addr, size, flags, caller); diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index bbdc5b577b8..cfa768203d0 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -10,7 +10,7 @@ * - tlbil_va * - tlbil_pid * - tlbil_all - * - tlbivax_bcast (not yet) + * - tlbivax_bcast * * Code mostly moved over from misc_32.S * @@ -33,6 +33,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/processor.h> +#include <asm/bug.h> #if defined(CONFIG_40x) @@ -65,7 +66,7 @@ _GLOBAL(__tlbil_va) * Nothing to do for 8xx, everything is inline */ -#elif defined(CONFIG_44x) +#elif defined(CONFIG_44x) /* Includes 47x */ /* * 440 implementation uses tlbsx/we for tlbil_va and a full sweep @@ -73,7 +74,13 @@ _GLOBAL(__tlbil_va) */ _GLOBAL(__tlbil_va) mfspr r5,SPRN_MMUCR - rlwimi r5,r4,0,24,31 /* Set TID */ + mfmsr r10 + + /* + * We write 16 bits of STID since 47x supports that much, we + * will never be passed out of bounds values on 440 (hopefully) + */ + rlwimi r5,r4,0,16,31 /* We have to run the search with interrupts disabled, otherwise * an interrupt which causes a TLB miss can clobber the MMUCR @@ -83,24 +90,41 @@ _GLOBAL(__tlbil_va) * and restoring MMUCR, so only normal interrupts have to be * taken care of. */ - mfmsr r4 wrteei 0 mtspr SPRN_MMUCR,r5 - tlbsx. r3, 0, r3 - wrtee r4 - bne 1f + tlbsx. r6,0,r3 + bne 10f sync - /* There are only 64 TLB entries, so r3 < 64, - * which means bit 22, is clear. Since 22 is - * the V bit in the TLB_PAGEID, loading this +BEGIN_MMU_FTR_SECTION + b 2f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x) + /* On 440 There are only 64 TLB entries, so r3 < 64, which means bit + * 22, is clear. Since 22 is the V bit in the TLB_PAGEID, loading this * value will invalidate the TLB entry. */ - tlbwe r3, r3, PPC44x_TLB_PAGEID + tlbwe r6,r6,PPC44x_TLB_PAGEID isync -1: blr +10: wrtee r10 + blr +2: +#ifdef CONFIG_PPC_47x + oris r7,r6,0x8000 /* specify way explicitely */ + clrrwi r4,r3,12 /* get an EPN for the hashing with V = 0 */ + ori r4,r4,PPC47x_TLBE_SIZE + tlbwe r4,r7,0 /* write it */ + isync + wrtee r10 + blr +#else /* CONFIG_PPC_47x */ +1: trap + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; +#endif /* !CONFIG_PPC_47x */ _GLOBAL(_tlbil_all) _GLOBAL(_tlbil_pid) +BEGIN_MMU_FTR_SECTION + b 2f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x) li r3,0 sync @@ -115,6 +139,76 @@ _GLOBAL(_tlbil_pid) isync blr +2: +#ifdef CONFIG_PPC_47x + /* 476 variant. There's not simple way to do this, hopefully we'll + * try to limit the amount of such full invalidates + */ + mfmsr r11 /* Interrupts off */ + wrteei 0 + li r3,-1 /* Current set */ + lis r10,tlb_47x_boltmap@h + ori r10,r10,tlb_47x_boltmap@l + lis r7,0x8000 /* Specify way explicitely */ + + b 9f /* For each set */ + +1: li r9,4 /* Number of ways */ + li r4,0 /* Current way */ + li r6,0 /* Default entry value 0 */ + andi. r0,r8,1 /* Check if way 0 is bolted */ + mtctr r9 /* Load way counter */ + bne- 3f /* Bolted, skip loading it */ + +2: /* For each way */ + or r5,r3,r4 /* Make way|index for tlbre */ + rlwimi r5,r5,16,8,15 /* Copy index into position */ + tlbre r6,r5,0 /* Read entry */ +3: addis r4,r4,0x2000 /* Next way */ + andi. r0,r6,PPC47x_TLB0_VALID /* Valid entry ? */ + beq 4f /* Nope, skip it */ + rlwimi r7,r5,0,1,2 /* Insert way number */ + rlwinm r6,r6,0,21,19 /* Clear V */ + tlbwe r6,r7,0 /* Write it */ +4: bdnz 2b /* Loop for each way */ + srwi r8,r8,1 /* Next boltmap bit */ +9: cmpwi cr1,r3,255 /* Last set done ? */ + addi r3,r3,1 /* Next set */ + beq cr1,1f /* End of loop */ + andi. r0,r3,0x1f /* Need to load a new boltmap word ? */ + bne 1b /* No, loop */ + lwz r8,0(r10) /* Load boltmap entry */ + addi r10,r10,4 /* Next word */ + b 1b /* Then loop */ +1: isync /* Sync shadows */ + wrtee r11 +#else /* CONFIG_PPC_47x */ +1: trap + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; +#endif /* !CONFIG_PPC_47x */ + blr + +#ifdef CONFIG_PPC_47x +/* + * _tlbivax_bcast is only on 47x. We don't bother doing a runtime + * check though, it will blow up soon enough if we mistakenly try + * to use it on a 440. + */ +_GLOBAL(_tlbivax_bcast) + mfspr r5,SPRN_MMUCR + mfmsr r10 + rlwimi r5,r4,0,16,31 + wrteei 0 + mtspr SPRN_MMUCR,r5 +/* tlbivax 0,r3 - use .long to avoid binutils deps */ + .long 0x7c000624 | (r3 << 11) + isync + eieio + tlbsync + sync + wrtee r10 + blr +#endif /* CONFIG_PPC_47x */ #elif defined(CONFIG_FSL_BOOKE) /* @@ -271,3 +365,31 @@ _GLOBAL(set_context) #else #error Unsupported processor type ! #endif + +#if defined(CONFIG_FSL_BOOKE) +/* + * extern void loadcam_entry(unsigned int index) + * + * Load TLBCAM[index] entry in to the L2 CAM MMU + */ +_GLOBAL(loadcam_entry) + LOAD_REG_ADDR(r4, TLBCAM) + mulli r5,r3,TLBCAM_SIZE + add r3,r5,r4 + lwz r4,TLBCAM_MAS0(r3) + mtspr SPRN_MAS0,r4 + lwz r4,TLBCAM_MAS1(r3) + mtspr SPRN_MAS1,r4 + PPC_LL r4,TLBCAM_MAS2(r3) + mtspr SPRN_MAS2,r4 + lwz r4,TLBCAM_MAS3(r3) + mtspr SPRN_MAS3,r4 +BEGIN_MMU_FTR_SECTION + lwz r4,TLBCAM_MAS7(r3) + mtspr SPRN_MAS7,r4 +END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) + isync + tlbwe + isync + blr +#endif diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 7486bffd3eb..eeba0a70e46 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -1,3 +1,12 @@ +config PPC_47x + bool "Support for 47x variant" + depends on 44x + default n + select MPIC + help + This option enables support for the 47x family of processors and is + not currently compatible with other 44x or 46x varients + config BAMBOO bool "Bamboo" depends on 44x @@ -151,6 +160,17 @@ config YOSEMITE help This option enables support for the AMCC PPC440EP evaluation board. +config ISS4xx + bool "ISS 4xx Simulator" + depends on (44x || 40x) + default n + select 405GP if 40x + select 440GP if 44x && !PPC_47x + select PPC_FPU + select OF_RTC + help + This option enables support for the IBM ISS simulation environment + #config LUAN # bool "Luan" # depends on 44x diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index ee6185aeaa3..82ff326e079 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_SAM440EP) += sam440ep.o obj-$(CONFIG_WARP) += warp.o obj-$(CONFIG_XILINX_VIRTEX_5_FXT) += virtex.o obj-$(CONFIG_XILINX_ML510) += virtex_ml510.o +obj-$(CONFIG_ISS4xx) += iss4xx.o diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c new file mode 100644 index 00000000000..aa46e9d1e77 --- /dev/null +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -0,0 +1,167 @@ +/* + * PPC476 board specific routines + * + * Copyright 2010 Torez Smith, IBM Corporation. + * + * Based on earlier code: + * Matt Porter <mporter@kernel.crashing.org> + * Copyright 2002-2005 MontaVista Software Inc. + * + * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net> + * Copyright (c) 2003-2005 Zultys Technologies + * + * Rewritten and ported to the merged powerpc tree: + * Copyright 2007 David Gibson <dwg@au1.ibm.com>, 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/init.h> +#include <linux/of_platform.h> +#include <linux/rtc.h> + +#include <asm/machdep.h> +#include <asm/prom.h> +#include <asm/udbg.h> +#include <asm/time.h> +#include <asm/uic.h> +#include <asm/ppc4xx.h> +#include <asm/mpic.h> +#include <asm/mmu.h> + +static __initdata struct of_device_id iss4xx_of_bus[] = { + { .compatible = "ibm,plb4", }, + { .compatible = "ibm,plb6", }, + { .compatible = "ibm,opb", }, + { .compatible = "ibm,ebc", }, + {}, +}; + +static int __init iss4xx_device_probe(void) +{ + of_platform_bus_probe(NULL, iss4xx_of_bus, NULL); + of_instantiate_rtc(); + + return 0; +} +machine_device_initcall(iss4xx, iss4xx_device_probe); + +/* We can have either UICs or MPICs */ +static void __init iss4xx_init_irq(void) +{ + struct device_node *np; + + /* Find top level interrupt controller */ + for_each_node_with_property(np, "interrupt-controller") { + if (of_get_property(np, "interrupts", NULL) == NULL) + break; + } + if (np == NULL) + panic("Can't find top level interrupt controller"); + + /* Check type and do appropriate initialization */ + if (of_device_is_compatible(np, "ibm,uic")) { + uic_init_tree(); + ppc_md.get_irq = uic_get_irq; +#ifdef CONFIG_MPIC + } else if (of_device_is_compatible(np, "chrp,open-pic")) { + /* The MPIC driver will get everything it needs from the + * device-tree, just pass 0 to all arguments + */ + struct mpic *mpic = mpic_alloc(np, 0, MPIC_PRIMARY, 0, 0, + " MPIC "); + BUG_ON(mpic == NULL); + mpic_init(mpic); + ppc_md.get_irq = mpic_get_irq; +#endif + } else + panic("Unrecognized top level interrupt controller"); +} + +#ifdef CONFIG_SMP +static void __cpuinit smp_iss4xx_setup_cpu(int cpu) +{ + mpic_setup_this_cpu(); +} + +static void __cpuinit smp_iss4xx_kick_cpu(int cpu) +{ + struct device_node *cpunode = of_get_cpu_node(cpu, NULL); + const u64 *spin_table_addr_prop; + u32 *spin_table; + extern void start_secondary_47x(void); + + BUG_ON(cpunode == NULL); + + /* Assume spin table. We could test for the enable-method in + * the device-tree but currently there's little point as it's + * our only supported method + */ + spin_table_addr_prop = of_get_property(cpunode, "cpu-release-addr", + NULL); + if (spin_table_addr_prop == NULL) { + pr_err("CPU%d: Can't start, missing cpu-release-addr !\n", cpu); + return; + } + + /* Assume it's mapped as part of the linear mapping. This is a bit + * fishy but will work fine for now + */ + spin_table = (u32 *)__va(*spin_table_addr_prop); + pr_debug("CPU%d: Spin table mapped at %p\n", cpu, spin_table); + + spin_table[3] = cpu; + smp_wmb(); + spin_table[1] = __pa(start_secondary_47x); + mb(); +} + +static struct smp_ops_t iss_smp_ops = { + .probe = smp_mpic_probe, + .message_pass = smp_mpic_message_pass, + .setup_cpu = smp_iss4xx_setup_cpu, + .kick_cpu = smp_iss4xx_kick_cpu, + .give_timebase = smp_generic_give_timebase, + .take_timebase = smp_generic_take_timebase, +}; + +static void __init iss4xx_smp_init(void) +{ + if (mmu_has_feature(MMU_FTR_TYPE_47x)) + smp_ops = &iss_smp_ops; +} + +#else /* CONFIG_SMP */ +static void __init iss4xx_smp_init(void) { } +#endif /* CONFIG_SMP */ + +static void __init iss4xx_setup_arch(void) +{ + iss4xx_smp_init(); +} + +/* + * Called very early, MMU is off, device-tree isn't unflattened + */ +static int __init iss4xx_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (!of_flat_dt_is_compatible(root, "ibm,iss-4xx")) + return 0; + + return 1; +} + +define_machine(iss4xx) { + .name = "ISS-4xx", + .probe = iss4xx_probe, + .progress = udbg_progress, + .init_IRQ = iss4xx_init_irq, + .setup_arch = iss4xx_setup_arch, + .restart = ppc4xx_reset_system, + .calibrate_decr = generic_calibrate_decr, +}; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c index fda7c2a1828..ca5305a5bd6 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c @@ -168,7 +168,7 @@ static int __devinit mpc52xx_wkup_gpiochip_probe(struct of_device *ofdev, ofchip->gc.get = mpc52xx_wkup_gpio_get; ofchip->gc.set = mpc52xx_wkup_gpio_set; - ret = of_mm_gpiochip_add(ofdev->node, &chip->mmchip); + ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) return ret; @@ -193,8 +193,11 @@ static const struct of_device_id mpc52xx_wkup_gpiochip_match[] = { }; static struct of_platform_driver mpc52xx_wkup_gpiochip_driver = { - .name = "gpio_wkup", - .match_table = mpc52xx_wkup_gpiochip_match, + .driver = { + .name = "gpio_wkup", + .owner = THIS_MODULE, + .of_match_table = mpc52xx_wkup_gpiochip_match, + }, .probe = mpc52xx_wkup_gpiochip_probe, .remove = mpc52xx_gpiochip_remove, }; @@ -329,7 +332,7 @@ static int __devinit mpc52xx_simple_gpiochip_probe(struct of_device *ofdev, ofchip->gc.get = mpc52xx_simple_gpio_get; ofchip->gc.set = mpc52xx_simple_gpio_set; - ret = of_mm_gpiochip_add(ofdev->node, &chip->mmchip); + ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) return ret; @@ -349,8 +352,11 @@ static const struct of_device_id mpc52xx_simple_gpiochip_match[] = { }; static struct of_platform_driver mpc52xx_simple_gpiochip_driver = { - .name = "gpio", - .match_table = mpc52xx_simple_gpiochip_match, + .driver = { + .name = "gpio", + .owner = THIS_MODULE, + .of_match_table = mpc52xx_simple_gpiochip_match, + }, .probe = mpc52xx_simple_gpiochip_probe, .remove = mpc52xx_gpiochip_remove, }; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index a60ee39d3b7..46c93578cbf 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -734,8 +734,8 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, spin_lock_init(&gpt->lock); gpt->dev = &ofdev->dev; - gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->node); - gpt->regs = of_iomap(ofdev->node, 0); + gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->dev.of_node); + gpt->regs = of_iomap(ofdev->dev.of_node, 0); if (!gpt->regs) { kfree(gpt); return -ENOMEM; @@ -743,21 +743,21 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, dev_set_drvdata(&ofdev->dev, gpt); - mpc52xx_gpt_gpio_setup(gpt, ofdev->node); - mpc52xx_gpt_irq_setup(gpt, ofdev->node); + mpc52xx_gpt_gpio_setup(gpt, ofdev->dev.of_node); + mpc52xx_gpt_irq_setup(gpt, ofdev->dev.of_node); mutex_lock(&mpc52xx_gpt_list_mutex); list_add(&gpt->list, &mpc52xx_gpt_list); mutex_unlock(&mpc52xx_gpt_list_mutex); /* check if this device could be a watchdog */ - if (of_get_property(ofdev->node, "fsl,has-wdt", NULL) || - of_get_property(ofdev->node, "has-wdt", NULL)) { + if (of_get_property(ofdev->dev.of_node, "fsl,has-wdt", NULL) || + of_get_property(ofdev->dev.of_node, "has-wdt", NULL)) { const u32 *on_boot_wdt; gpt->wdt_mode = MPC52xx_GPT_CAN_WDT; - on_boot_wdt = of_get_property(ofdev->node, "fsl,wdt-on-boot", - NULL); + on_boot_wdt = of_get_property(ofdev->dev.of_node, + "fsl,wdt-on-boot", NULL); if (on_boot_wdt) { dev_info(gpt->dev, "used as watchdog\n"); gpt->wdt_mode |= MPC52xx_GPT_IS_WDT; @@ -784,8 +784,11 @@ static const struct of_device_id mpc52xx_gpt_match[] = { }; static struct of_platform_driver mpc52xx_gpt_driver = { - .name = "mpc52xx-gpt", - .match_table = mpc52xx_gpt_match, + .driver = { + .name = "mpc52xx-gpt", + .owner = THIS_MODULE, + .of_match_table = mpc52xx_gpt_match, + }, .probe = mpc52xx_gpt_probe, .remove = mpc52xx_gpt_remove, }; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c index d4f8be307cd..e86aec64450 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -445,14 +445,14 @@ mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) if (lpbfifo.dev != NULL) return -ENOSPC; - lpbfifo.irq = irq_of_parse_and_map(op->node, 0); + lpbfifo.irq = irq_of_parse_and_map(op->dev.of_node, 0); if (!lpbfifo.irq) return -ENODEV; - if (of_address_to_resource(op->node, 0, &res)) + if (of_address_to_resource(op->dev.of_node, 0, &res)) return -ENODEV; lpbfifo.regs_phys = res.start; - lpbfifo.regs = of_iomap(op->node, 0); + lpbfifo.regs = of_iomap(op->dev.of_node, 0); if (!lpbfifo.regs) return -ENOMEM; @@ -537,9 +537,11 @@ static struct of_device_id mpc52xx_lpbfifo_match[] __devinitconst = { }; static struct of_platform_driver mpc52xx_lpbfifo_driver = { - .owner = THIS_MODULE, - .name = "mpc52xx-lpbfifo", - .match_table = mpc52xx_lpbfifo_match, + .driver = { + .name = "mpc52xx-lpbfifo", + .owner = THIS_MODULE, + .of_match_table = mpc52xx_lpbfifo_match, + }, .probe = mpc52xx_lpbfifo_probe, .remove = __devexit_p(mpc52xx_lpbfifo_remove), }; diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index f21555d3395..9f2e52b36f9 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -119,12 +119,12 @@ static int __devinit ep8248e_mdio_probe(struct of_device *ofdev, struct device_node *node; int ret; - node = of_get_parent(ofdev->node); + node = of_get_parent(ofdev->dev.of_node); of_node_put(node); if (node != ep8248e_bcsr_node) return -ENODEV; - ret = of_address_to_resource(ofdev->node, 0, &res); + ret = of_address_to_resource(ofdev->dev.of_node, 0, &res); if (ret) return ret; @@ -142,7 +142,7 @@ static int __devinit ep8248e_mdio_probe(struct of_device *ofdev, bus->parent = &ofdev->dev; snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start); - ret = of_mdiobus_register(bus, ofdev->node); + ret = of_mdiobus_register(bus, ofdev->dev.of_node); if (ret) goto err_free_irq; @@ -170,8 +170,9 @@ static const struct of_device_id ep8248e_mdio_match[] = { static struct of_platform_driver ep8248e_mdio_driver = { .driver = { .name = "ep8248e-mdio-bitbang", + .owner = THIS_MODULE, + .of_match_table = ep8248e_mdio_match, }, - .match_table = ep8248e_mdio_match, .probe = ep8248e_mdio_probe, .remove = ep8248e_mdio_remove, }; diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c index 0b4f883b20e..ae525e4745d 100644 --- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c @@ -74,6 +74,7 @@ static int __init mpc831x_rdb_probe(void) static struct of_device_id __initdata of_bus_ids[] = { { .compatible = "simple-bus" }, { .compatible = "gianfar" }, + { .compatible = "gpio-leds", }, {}, }; diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c index a1908d26124..e00801c4254 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c @@ -72,6 +72,7 @@ static struct of_device_id mpc837x_ids[] = { { .compatible = "soc", }, { .compatible = "simple-bus", }, { .compatible = "gianfar", }, + { .compatible = "gpio-leds", }, {}, }; diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 43805348b81..ebe6c353720 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -321,7 +321,7 @@ static struct platform_suspend_ops mpc83xx_suspend_ops = { static int pmc_probe(struct of_device *ofdev, const struct of_device_id *match) { - struct device_node *np = ofdev->node; + struct device_node *np = ofdev->dev.of_node; struct resource res; struct pmc_type *type = match->data; int ret = 0; @@ -423,8 +423,11 @@ static struct of_device_id pmc_match[] = { }; static struct of_platform_driver pmc_driver = { - .name = "mpc83xx-pmc", - .match_table = pmc_match, + .driver = { + .name = "mpc83xx-pmc", + .owner = THIS_MODULE, + .of_match_table = pmc_match, + }, .probe = pmc_probe, .remove = pmc_remove }; diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index 5abe137f630..018cc67be42 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -83,7 +83,8 @@ static struct of_device_id __initdata mpc8610_ids[] = { { .compatible = "fsl,mpc8610-immr", }, { .compatible = "fsl,mpc8610-guts", }, { .compatible = "simple-bus", }, - { .compatible = "gianfar", }, + /* So that the DMA channel nodes can be probed individually: */ + { .compatible = "fsl,eloplus-dma", }, {} }; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index a8aae0b5457..d361f8119b1 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -43,7 +43,7 @@ config 40x select PPC_PCI_CHOICE config 44x - bool "AMCC 44x" + bool "AMCC 44x, 46x or 47x" select PPC_DCR_NATIVE select PPC_UDBG_16550 select 4xx_SOC @@ -294,7 +294,7 @@ config PPC_PERF_CTRS This enables the powerpc-specific perf_event back-end. config SMP - depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE + depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE || PPC_47x bool "Symmetric multi-processing support" ---help--- This enables support for systems with more than one CPU. If you have @@ -322,6 +322,7 @@ config NR_CPUS config NOT_COHERENT_CACHE bool depends on 4xx || 8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON + default n if PPC_47x default y config CHECK_CACHE_COHERENCY diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 8efe48192f3..6257e537861 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -345,7 +345,7 @@ static int axon_msi_shutdown(struct of_device *device) static int axon_msi_probe(struct of_device *device, const struct of_device_id *device_id) { - struct device_node *dn = device->node; + struct device_node *dn = device->dev.of_node; struct axon_msic *msic; unsigned int virq; int dcr_base, dcr_len; @@ -447,11 +447,12 @@ static const struct of_device_id axon_msi_device_id[] = { }; static struct of_platform_driver axon_msi_driver = { - .match_table = axon_msi_device_id, .probe = axon_msi_probe, .shutdown = axon_msi_shutdown, - .driver = { - .name = "axon-msi" + .driver = { + .name = "axon-msi", + .owner = THIS_MODULE, + .of_match_table = axon_msi_device_id, }, }; diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c index e6506cd0ff9..bfa2c0cb3d1 100644 --- a/arch/powerpc/platforms/cell/cbe_cpufreq.c +++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c @@ -118,7 +118,7 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->cur = cbe_freqs[cur_pmode].frequency; #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif cpufreq_frequency_table_get_attr(cbe_freqs, policy->cpu); diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index e3ec4976fae..22667a09d40 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -545,7 +545,6 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) { struct iommu_window *window; struct cbe_iommu *iommu; - struct dev_archdata *archdata = &dev->archdata; /* Current implementation uses the first window available in that * node's iommu. We -might- do something smarter later though it may @@ -554,7 +553,7 @@ 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", - archdata->of_node ? archdata->of_node->full_name : "?", + dev->of_node ? dev->of_node->full_name : "?", dev_to_node(dev)); return NULL; } @@ -897,7 +896,7 @@ static u64 cell_iommu_get_fixed_address(struct device *dev) const u32 *ranges = NULL; int i, len, best, naddr, nsize, pna, range_size; - np = of_node_get(dev->archdata.of_node); + np = of_node_get(dev->of_node); while (1) { naddr = of_n_addr_cells(np); nsize = of_n_size_cells(np); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 57e5b608fa1..174a04ac480 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -69,10 +69,10 @@ void __init wii_memory_fixups(void) /* * This is part of a workaround to allow the use of two - * discontiguous RAM ranges on the Wii, even if this is + * discontinuous RAM ranges on the Wii, even if this is * currently unsupported on 32-bit PowerPC Linux. * - * We coealesce the two memory ranges of the Wii into a + * We coalesce the two memory ranges of the Wii into a * single range, then create a reservation for the "hole" * between both ranges. */ diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index fba5bf91507..32a56c6dfa7 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -252,8 +252,8 @@ decrementer_iSeries_masked: li r11,1 ld r12,PACALPPACAPTR(r13) stb r11,LPPACADECRINT(r12) - LOAD_REG_IMMEDIATE(r12, tb_ticks_per_jiffy) - lwz r12,0(r12) + li r12,-1 + clrldi r12,r12,33 /* set DEC to 0x7fffffff */ mtspr SPRN_DEC,r12 /* fall through */ diff --git a/arch/powerpc/platforms/iseries/pci.c b/arch/powerpc/platforms/iseries/pci.c index b841c9a9db8..3fc2e6494b8 100644 --- a/arch/powerpc/platforms/iseries/pci.c +++ b/arch/powerpc/platforms/iseries/pci.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/of.h> +#include <linux/ratelimit.h> #include <asm/types.h> #include <asm/io.h> @@ -584,14 +585,9 @@ static inline struct device_node *xlate_iomm_address( orig_addr = (unsigned long __force)addr; if ((orig_addr < BASE_IO_MEMORY) || (orig_addr >= max_io_memory)) { - static unsigned long last_jiffies; - static int num_printed; + static DEFINE_RATELIMIT_STATE(ratelimit, 60 * HZ, 10); - if (time_after(jiffies, last_jiffies + 60 * HZ)) { - last_jiffies = jiffies; - num_printed = 0; - } - if (num_printed++ < 10) + if (__ratelimit(&ratelimit)) printk(KERN_ERR "iSeries_%s: invalid access at IO address %p\n", func, addr); diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c index 722335e32fd..6590850045a 100644 --- a/arch/powerpc/platforms/iseries/smp.c +++ b/arch/powerpc/platforms/iseries/smp.c @@ -83,7 +83,7 @@ static void smp_iSeries_message_pass(int target, int msg) static int smp_iSeries_probe(void) { - return cpus_weight(cpu_possible_map); + return cpumask_weight(cpu_possible_mask); } static void smp_iSeries_kick_cpu(int nr) diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c index d35e0520abf..c16537bc0c6 100644 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ b/arch/powerpc/platforms/pasemi/cpufreq.c @@ -213,7 +213,7 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) pr_debug("current astate is at %d\n",cur_astate); policy->cur = pas_freqs[cur_astate].frequency; - cpumask_copy(policy->cpus, &cpu_online_map); + cpumask_copy(policy->cpus, cpu_online_mask); ppc_proc_freq = policy->cur * 1000ul; diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index 0f881f64583..627ee089e75 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -220,7 +220,7 @@ static int __devinit gpio_mdio_probe(struct of_device *ofdev, const struct of_device_id *match) { struct device *dev = &ofdev->dev; - struct device_node *np = ofdev->node; + struct device_node *np = ofdev->dev.of_node; struct mii_bus *new_bus; struct gpio_priv *priv; const unsigned int *prop; @@ -301,11 +301,12 @@ MODULE_DEVICE_TABLE(of, gpio_mdio_match); static struct of_platform_driver gpio_mdio_driver = { - .match_table = gpio_mdio_match, .probe = gpio_mdio_probe, .remove = gpio_mdio_remove, - .driver = { - .name = "gpio-mdio-bitbang", + .driver = { + .name = "gpio-mdio-bitbang", + .owner = THIS_MODULE, + .of_match_table = gpio_mdio_match, }, }; diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index ac6fdd97329..f372ec1691a 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -360,10 +360,10 @@ static int pcmcia_notify(struct notifier_block *nb, unsigned long action, /* We know electra_cf devices will always have of_node set, since * electra_cf is an of_platform driver. */ - if (!parent->archdata.of_node) + if (!parent->of_node) return 0; - if (!of_device_is_compatible(parent->archdata.of_node, "electra-cf")) + if (!of_device_is_compatible(parent->of_node, "electra-cf")) return 0; /* We use the direct ops for localbus */ diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c index 3ca09d3ccce..9650c6029c8 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ b/arch/powerpc/platforms/powermac/cpufreq_64.c @@ -362,7 +362,7 @@ static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy) /* secondary CPUs are tied to the primary one by the * cpufreq core if in the secondary policy we tell it that * it actually must be one policy together with all others. */ - cpumask_copy(policy->cpus, &cpu_online_map); + cpumask_copy(policy->cpus, cpu_online_mask); cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu); return cpufreq_frequency_table_cpuinfo(policy, diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index f45331ab97c..06a137c5b8b 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -592,7 +592,7 @@ static void __init kw_i2c_probe(void) /* Probe keywest-i2c busses */ for_each_compatible_node(np, "i2c","keywest-i2c") { struct pmac_i2c_host_kw *host; - int multibus, chans, i; + int multibus; /* Found one, init a host structure */ host = kw_i2c_host_init(np); @@ -614,6 +614,8 @@ static void __init kw_i2c_probe(void) * parent type */ if (multibus) { + int chans, i; + parent = of_get_parent(np); if (parent == NULL) continue; @@ -1258,8 +1260,7 @@ static void pmac_i2c_do_end(struct pmf_function *func, void *instdata) if (inst == NULL) return; pmac_i2c_close(inst->bus); - if (inst) - kfree(inst); + kfree(inst); } static int pmac_i2c_do_read(PMF_STD_ARGS, u32 len) diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 3362e781b6a..f0bc08f6c1f 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -33,6 +33,8 @@ extern void pmac_setup_pci_dma(void); extern void pmac_check_ht_link(void); extern void pmac_setup_smp(void); +extern void pmac32_cpu_die(void); +extern void low_cpu_die(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); extern void pmac_pic_init(void); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 15c2241f9c7..f1d0132ebcc 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -480,7 +480,7 @@ static void __init pmac_init_early(void) #endif /* SMP Init has to be done early as we need to patch up - * cpu_possible_map before interrupt stacks are allocated + * cpu_possible_mask before interrupt stacks are allocated * or kaboom... */ #ifdef CONFIG_SMP @@ -646,7 +646,7 @@ static int pmac_pci_probe_mode(struct pci_bus *bus) /* access per cpu vars from generic smp.c */ DECLARE_PER_CPU(int, cpu_state); -static void pmac_cpu_die(void) +static void pmac64_cpu_die(void) { /* * turn off as much as possible, we'll be @@ -717,8 +717,13 @@ define_machine(powermac) { .pcibios_after_init = pmac_pcibios_after_init, .phys_mem_access_prot = pci_phys_mem_access_prot, #endif -#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC64) - .cpu_die = pmac_cpu_die, +#ifdef CONFIG_HOTPLUG_CPU +#ifdef CONFIG_PPC64 + .cpu_die = pmac64_cpu_die, +#endif +#ifdef CONFIG_PPC32 + .cpu_die = pmac32_cpu_die, +#endif #endif #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32) .cpu_die = generic_mach_cpu_die, diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 6898e8241cd..c95215f4f8b 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -53,6 +53,8 @@ #include <asm/pmac_low_i2c.h> #include <asm/pmac_pfunc.h> +#include "pmac.h" + #undef DEBUG #ifdef DEBUG @@ -315,7 +317,7 @@ static int __init smp_psurge_probe(void) /* This is necessary because OF doesn't know about the * secondary cpu(s), and thus there aren't nodes in the * device tree for them, and smp_setup_cpu_maps hasn't - * set their bits in cpu_present_map. + * set their bits in cpu_present_mask. */ if (ncpus > NR_CPUS) ncpus = NR_CPUS; @@ -878,10 +880,9 @@ int smp_core99_cpu_disable(void) return 0; } -extern void low_cpu_die(void) __attribute__((noreturn)); /* in sleep.S */ static int cpu_dead[NR_CPUS]; -void cpu_die(void) +void pmac32_cpu_die(void) { local_irq_disable(); cpu_dead[smp_processor_id()] = 1; @@ -944,7 +945,7 @@ void __init pmac_setup_smp(void) } #ifdef CONFIG_PPC32 else { - /* We have to set bits in cpu_possible_map here since the + /* We have to set bits in cpu_possible_mask here since the * secondary CPU(s) aren't in the device tree. Various * things won't be initialized for CPUs not in the possible * map, so we really need to fix it up here. diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 6d09f5e3e7e..23083c39752 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -766,7 +766,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev) BUG(); }; - dev->core.archdata.of_node = NULL; + dev->core.of_node = NULL; set_dev_node(&dev->core, 0); pr_debug("%s:%d add %s\n", __func__, __LINE__, dev_name(&dev->core)); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 0ff5174ae4f..3dbef309bc8 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -7,7 +7,7 @@ EXTRA_CFLAGS += -DDEBUG endif obj-y := lpar.o hvCall.o nvram.o reconfig.o \ - setup.o iommu.o ras.o \ + setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_XICS) += xics.o diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index e1682bc168a..d71e5858408 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -79,13 +79,12 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa) * prepend this to the full_name. */ name = (char *)ccwa + ccwa->name_offset; - dn->full_name = kmalloc(strlen(name) + 2, GFP_KERNEL); + dn->full_name = kasprintf(GFP_KERNEL, "/%s", name); if (!dn->full_name) { kfree(dn); return NULL; } - sprintf(dn->full_name, "/%s", name); return dn; } @@ -410,15 +409,13 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) * directory of the device tree. CPUs actually live in the * cpus directory so we need to fixup the full_name. */ - cpu_name = kzalloc(strlen(dn->full_name) + strlen("/cpus") + 1, - GFP_KERNEL); + cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name); if (!cpu_name) { dlpar_free_cc_nodes(dn); rc = -ENOMEM; goto out; } - sprintf(cpu_name, "/cpus%s", dn->full_name); kfree(dn->full_name); dn->full_name = cpu_name; @@ -433,6 +430,7 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) if (rc) { dlpar_release_drc(drc_index); dlpar_free_cc_nodes(dn); + goto out; } rc = dlpar_online_cpu(dn); diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 7df7fbb7cac..34b7dc12e73 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -749,7 +749,7 @@ static void __rtas_set_slot_reset(struct pci_dn *pdn) /* Determine type of EEH reset required by device, * default hot reset or fundamental reset */ - if (dev->needs_freset) + if (dev && dev->needs_freset) rtas_pci_slot_reset(pdn, 3); else rtas_pci_slot_reset(pdn, 1); diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c new file mode 100644 index 00000000000..e889c9d9586 --- /dev/null +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -0,0 +1,79 @@ +/* + * Copyright (C) 2001 Dave Engebretsen 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <asm/prom.h> + +#include "pseries.h" + +void request_event_sources_irqs(struct device_node *np, + irq_handler_t handler, + const char *name) +{ + int i, index, count = 0; + struct of_irq oirq; + const u32 *opicprop; + unsigned int opicplen; + unsigned int virqs[16]; + + /* Check for obsolete "open-pic-interrupt" property. If present, then + * map those interrupts using the default interrupt host and default + * trigger + */ + opicprop = of_get_property(np, "open-pic-interrupt", &opicplen); + if (opicprop) { + opicplen /= sizeof(u32); + for (i = 0; i < opicplen; i++) { + if (count > 15) + break; + virqs[count] = irq_create_mapping(NULL, *(opicprop++)); + if (virqs[count] == NO_IRQ) + printk(KERN_ERR "Unable to allocate interrupt " + "number for %s\n", np->full_name); + else + count++; + + } + } + /* Else use normal interrupt tree parsing */ + else { + /* First try to do a proper OF tree parsing */ + for (index = 0; of_irq_map_one(np, index, &oirq) == 0; + index++) { + if (count > 15) + break; + virqs[count] = irq_create_of_mapping(oirq.controller, + oirq.specifier, + oirq.size); + if (virqs[count] == NO_IRQ) + printk(KERN_ERR "Unable to allocate interrupt " + "number for %s\n", np->full_name); + else + count++; + } + } + + /* Now request them */ + for (i = 0; i < count; i++) { + if (request_irq(virqs[i], handler, 0, name, NULL)) { + printk(KERN_ERR "Unable to request interrupt %d for " + "%s\n", virqs[i], np->full_name); + return; + } + } +} + diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index a8e1d5d17a2..8f85f399ab9 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -154,30 +154,6 @@ static void pseries_mach_cpu_die(void) for(;;); } -static int qcss_tok; /* query-cpu-stopped-state token */ - -/* Get state of physical CPU. - * Return codes: - * 0 - The processor is in the RTAS stopped state - * 1 - stop-self is in progress - * 2 - The processor is not in the RTAS stopped state - * -1 - Hardware Error - * -2 - Hardware Busy, Try again later. - */ -static int query_cpu_stopped(unsigned int pcpu) -{ - int cpu_status, status; - - status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu); - if (status != 0) { - printk(KERN_ERR - "RTAS query-cpu-stopped-state failed: %i\n", status); - return status; - } - - return cpu_status; -} - static int pseries_cpu_disable(void) { int cpu = smp_processor_id(); @@ -187,7 +163,7 @@ static int pseries_cpu_disable(void) /*fix boot_cpuid here*/ if (cpu == boot_cpuid) - boot_cpuid = any_online_cpu(cpu_online_map); + boot_cpuid = cpumask_any(cpu_online_mask); /* FIXME: abstract this to not be platform specific later on */ xics_migrate_irqs_away(); @@ -224,8 +200,9 @@ static void pseries_cpu_die(unsigned int cpu) } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { for (tries = 0; tries < 25; tries++) { - cpu_status = query_cpu_stopped(pcpu); - if (cpu_status == 0 || cpu_status == -1) + cpu_status = smp_query_cpu_stopped(pcpu); + if (cpu_status == QCSS_STOPPED || + cpu_status == QCSS_HARDWARE_ERROR) break; cpu_relax(); } @@ -245,7 +222,7 @@ static void pseries_cpu_die(unsigned int cpu) } /* - * Update cpu_present_map and paca(s) for a new cpu node. The wrinkle + * Update cpu_present_mask and paca(s) for a new cpu node. The wrinkle * here is that a cpu device node may represent up to two logical cpus * in the SMT case. We must honor the assumption in other code that * the logical ids for sibling SMT threads x and y are adjacent, such @@ -254,7 +231,7 @@ static void pseries_cpu_die(unsigned int cpu) static int pseries_add_processor(struct device_node *np) { unsigned int cpu; - cpumask_t candidate_map, tmp = CPU_MASK_NONE; + cpumask_var_t candidate_mask, tmp; int err = -ENOSPC, len, nthreads, i; const u32 *intserv; @@ -262,48 +239,53 @@ static int pseries_add_processor(struct device_node *np) if (!intserv) return 0; + zalloc_cpumask_var(&candidate_mask, GFP_KERNEL); + zalloc_cpumask_var(&tmp, GFP_KERNEL); + nthreads = len / sizeof(u32); for (i = 0; i < nthreads; i++) - cpu_set(i, tmp); + cpumask_set_cpu(i, tmp); cpu_maps_update_begin(); - BUG_ON(!cpus_subset(cpu_present_map, cpu_possible_map)); + BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask)); /* Get a bitmap of unoccupied slots. */ - cpus_xor(candidate_map, cpu_possible_map, cpu_present_map); - if (cpus_empty(candidate_map)) { + cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask); + if (cpumask_empty(candidate_mask)) { /* If we get here, it most likely means that NR_CPUS is * less than the partition's max processors setting. */ printk(KERN_ERR "Cannot add cpu %s; this system configuration" " supports %d logical cpus.\n", np->full_name, - cpus_weight(cpu_possible_map)); + cpumask_weight(cpu_possible_mask)); goto out_unlock; } - while (!cpus_empty(tmp)) - if (cpus_subset(tmp, candidate_map)) + while (!cpumask_empty(tmp)) + if (cpumask_subset(tmp, candidate_mask)) /* Found a range where we can insert the new cpu(s) */ break; else - cpus_shift_left(tmp, tmp, nthreads); + cpumask_shift_left(tmp, tmp, nthreads); - if (cpus_empty(tmp)) { - printk(KERN_ERR "Unable to find space in cpu_present_map for" + if (cpumask_empty(tmp)) { + printk(KERN_ERR "Unable to find space in cpu_present_mask for" " processor %s with %d thread(s)\n", np->name, nthreads); goto out_unlock; } - for_each_cpu_mask(cpu, tmp) { - BUG_ON(cpu_isset(cpu, cpu_present_map)); + for_each_cpu(cpu, tmp) { + BUG_ON(cpumask_test_cpu(cpu, cpu_present_mask)); set_cpu_present(cpu, true); set_hard_smp_processor_id(cpu, *intserv++); } err = 0; out_unlock: cpu_maps_update_done(); + free_cpumask_var(candidate_mask); + free_cpumask_var(tmp); return err; } @@ -334,7 +316,7 @@ static void pseries_remove_processor(struct device_node *np) set_hard_smp_processor_id(cpu, -1); break; } - if (cpu == NR_CPUS) + if (cpu >= nr_cpu_ids) printk(KERN_WARNING "Could not find cpu to remove " "with physical id 0x%x\n", intserv[i]); } @@ -388,6 +370,7 @@ static int __init pseries_cpu_hotplug_init(void) struct device_node *np; const char *typep; int cpu; + int qcss_tok; for_each_node_by_name(np, "interrupt-controller") { typep = of_get_property(np, "compatible", NULL); diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 383a5d0e981..48d20573e4d 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -228,3 +228,41 @@ _GLOBAL(plpar_hcall9) mtcrf 0xff,r0 blr /* return r3 = status */ + +/* See plpar_hcall_raw to see why this is needed */ +_GLOBAL(plpar_hcall9_raw) + HMT_MEDIUM + + mfcr r0 + stw r0,8(r1) + + std r4,STK_PARM(r4)(r1) /* Save ret buffer */ + + mr r4,r5 + mr r5,r6 + mr r6,r7 + mr r7,r8 + mr r8,r9 + mr r9,r10 + ld r10,STK_PARM(r11)(r1) /* put arg7 in R10 */ + ld r11,STK_PARM(r12)(r1) /* put arg8 in R11 */ + ld r12,STK_PARM(r13)(r1) /* put arg9 in R12 */ + + HVSC /* invoke the hypervisor */ + + mr r0,r12 + ld r12,STK_PARM(r4)(r1) + std r4, 0(r12) + std r5, 8(r12) + std r6, 16(r12) + std r7, 24(r12) + std r8, 32(r12) + std r9, 40(r12) + std r10,48(r12) + std r11,56(r12) + std r0, 64(r12) + + lwz r0,8(r1) + mtcrf 0xff,r0 + + blr /* return r3 = status */ diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1a0000a4b6d..d26182d42cb 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -468,7 +468,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) pr_debug("pci_dma_dev_setup_pSeries: %s\n", pci_name(dev)); - dn = dev->dev.archdata.of_node; + dn = dev->dev.of_node; /* If we're the direct child of a root bus, then we need to allocate * an iommu table ourselves. The bus setup code should have setup diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0707653612b..cf79b46d8f8 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -367,21 +367,28 @@ static void pSeries_lpar_hptab_clear(void) { unsigned long size_bytes = 1UL << ppc64_pft_size; unsigned long hpte_count = size_bytes >> 4; - unsigned long dummy1, dummy2, dword0; + struct { + unsigned long pteh; + unsigned long ptel; + } ptes[4]; long lpar_rc; - int i; + int i, j; - /* TODO: Use bulk call */ - for (i = 0; i < hpte_count; i++) { - /* dont remove HPTEs with VRMA mappings */ - lpar_rc = plpar_pte_remove_raw(H_ANDCOND, i, HPTE_V_1TB_SEG, - &dummy1, &dummy2); - if (lpar_rc == H_NOT_FOUND) { - lpar_rc = plpar_pte_read_raw(0, i, &dword0, &dummy1); - if (!lpar_rc && ((dword0 & HPTE_V_VRMA_MASK) - != HPTE_V_VRMA_MASK)) - /* Can be hpte for 1TB Seg. So remove it */ - plpar_pte_remove_raw(0, i, 0, &dummy1, &dummy2); + /* Read in batches of 4, + * invalidate only valid entries not in the VRMA + * hpte_count will be a multiple of 4 + */ + for (i = 0; i < hpte_count; i += 4) { + lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes); + if (lpar_rc != H_SUCCESS) + continue; + for (j = 0; j < 4; j++){ + if ((ptes[j].pteh & HPTE_V_VRMA_MASK) == + HPTE_V_VRMA_MASK) + continue; + if (ptes[j].pteh & HPTE_V_VALID) + plpar_pte_remove_raw(0, i + j, 0, + &(ptes[j].pteh), &(ptes[j].ptel)); } } } diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index a05f8d42785..d9801117124 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -4,6 +4,14 @@ #include <asm/hvcall.h> #include <asm/page.h> +/* Get state of physical CPU from query_cpu_stopped */ +int smp_query_cpu_stopped(unsigned int pcpu); +#define QCSS_STOPPED 0 +#define QCSS_STOPPING 1 +#define QCSS_NOT_STOPPED 2 +#define QCSS_HARDWARE_ERROR -1 +#define QCSS_HARDWARE_BUSY -2 + static inline long poll_pending(void) { return plpar_hcall_norets(H_POLL_PENDING); @@ -183,6 +191,24 @@ static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex, return rc; } +/* + * plpar_pte_read_4_raw can be called in real mode. + * ptes must be 8*sizeof(unsigned long) + */ +static inline long plpar_pte_read_4_raw(unsigned long flags, unsigned long ptex, + unsigned long *ptes) + +{ + long rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + rc = plpar_hcall9_raw(H_READ, retbuf, flags | H_READ_4, ptex); + + memcpy(ptes, retbuf, 8*sizeof(unsigned long)); + + return rc; +} + static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex, unsigned long avpn) { diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 9e17c0d2a0c..40c93cad91d 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -10,6 +10,13 @@ #ifndef _PSERIES_PSERIES_H #define _PSERIES_PSERIES_H +#include <linux/interrupt.h> + +struct device_node; + +extern void request_event_sources_irqs(struct device_node *np, + irq_handler_t handler, const char *name); + extern void __init fw_feature_init(const char *hypertas, unsigned long len); struct pt_regs; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index db940d2c39a..41a3e9a039e 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -67,63 +67,6 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); -static void request_ras_irqs(struct device_node *np, - irq_handler_t handler, - const char *name) -{ - int i, index, count = 0; - struct of_irq oirq; - const u32 *opicprop; - unsigned int opicplen; - unsigned int virqs[16]; - - /* Check for obsolete "open-pic-interrupt" property. If present, then - * map those interrupts using the default interrupt host and default - * trigger - */ - opicprop = of_get_property(np, "open-pic-interrupt", &opicplen); - if (opicprop) { - opicplen /= sizeof(u32); - for (i = 0; i < opicplen; i++) { - if (count > 15) - break; - virqs[count] = irq_create_mapping(NULL, *(opicprop++)); - if (virqs[count] == NO_IRQ) - printk(KERN_ERR "Unable to allocate interrupt " - "number for %s\n", np->full_name); - else - count++; - - } - } - /* Else use normal interrupt tree parsing */ - else { - /* First try to do a proper OF tree parsing */ - for (index = 0; of_irq_map_one(np, index, &oirq) == 0; - index++) { - if (count > 15) - break; - virqs[count] = irq_create_of_mapping(oirq.controller, - oirq.specifier, - oirq.size); - if (virqs[count] == NO_IRQ) - printk(KERN_ERR "Unable to allocate interrupt " - "number for %s\n", np->full_name); - else - count++; - } - } - - /* Now request them */ - for (i = 0; i < count; i++) { - if (request_irq(virqs[i], handler, 0, name, NULL)) { - printk(KERN_ERR "Unable to request interrupt %d for " - "%s\n", virqs[i], np->full_name); - return; - } - } -} - /* * Initialize handlers for the set of interrupts caused by hardware errors * and power system events. @@ -138,14 +81,15 @@ static int __init init_ras_IRQ(void) /* Internal Errors */ np = of_find_node_by_path("/event-sources/internal-errors"); if (np != NULL) { - request_ras_irqs(np, ras_error_interrupt, "RAS_ERROR"); + request_event_sources_irqs(np, ras_error_interrupt, + "RAS_ERROR"); of_node_put(np); } /* EPOW Events */ np = of_find_node_by_path("/event-sources/epow-events"); if (np != NULL) { - request_ras_irqs(np, ras_epow_interrupt, "RAS_EPOW"); + request_event_sources_irqs(np, ras_epow_interrupt, "RAS_EPOW"); of_node_put(np); } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6710761bf60..a6d19e3a505 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -496,13 +496,14 @@ static int __init pSeries_probe(void) } -DECLARE_PER_CPU(unsigned long, smt_snooze_delay); +DECLARE_PER_CPU(long, smt_snooze_delay); static void pseries_dedicated_idle_sleep(void) { unsigned int cpu = smp_processor_id(); unsigned long start_snooze; unsigned long in_purr, out_purr; + long snooze = __get_cpu_var(smt_snooze_delay); /* * Indicate to the HV that we are idle. Now would be @@ -517,13 +518,12 @@ static void pseries_dedicated_idle_sleep(void) * has been checked recently. If we should poll for a little * while, do so. */ - if (__get_cpu_var(smt_snooze_delay)) { - start_snooze = get_tb() + - __get_cpu_var(smt_snooze_delay) * tb_ticks_per_usec; + if (snooze) { + start_snooze = get_tb() + snooze * tb_ticks_per_usec; local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); - while (get_tb() < start_snooze) { + while ((snooze < 0) || (get_tb() < start_snooze)) { if (need_resched() || cpu_is_offline(cpu)) goto out; ppc64_runlatch_off(); diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 4e7f89a8456..3b1bf61c45b 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -55,7 +55,29 @@ * The Primary thread of each non-boot processor was started from the OF client * interface by prom_hold_cpus and is spinning on secondary_hold_spinloop. */ -static cpumask_t of_spin_map; +static cpumask_var_t of_spin_mask; + +/* Query where a cpu is now. Return codes #defined in plpar_wrappers.h */ +int smp_query_cpu_stopped(unsigned int pcpu) +{ + int cpu_status, status; + int qcss_tok = rtas_token("query-cpu-stopped-state"); + + if (qcss_tok == RTAS_UNKNOWN_SERVICE) { + printk(KERN_INFO "Firmware doesn't support " + "query-cpu-stopped-state\n"); + return QCSS_HARDWARE_ERROR; + } + + status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu); + if (status != 0) { + printk(KERN_ERR + "RTAS query-cpu-stopped-state failed: %i\n", status); + return status; + } + + return cpu_status; +} /** * smp_startup_cpu() - start the given cpu @@ -76,12 +98,18 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu) unsigned int pcpu; int start_cpu; - if (cpu_isset(lcpu, of_spin_map)) + if (cpumask_test_cpu(lcpu, of_spin_mask)) /* Already started by OF and sitting in spin loop */ return 1; pcpu = get_hard_smp_processor_id(lcpu); + /* Check to see if the CPU out of FW already for kexec */ + if (smp_query_cpu_stopped(pcpu) == QCSS_NOT_STOPPED){ + cpumask_set_cpu(lcpu, of_spin_mask); + return 1; + } + /* Fixup atomic count: it exited inside IRQ handler. */ task_thread_info(paca[lcpu].__current)->preempt_count = 0; @@ -115,7 +143,7 @@ static void __devinit smp_xics_setup_cpu(int cpu) if (firmware_has_feature(FW_FEATURE_SPLPAR)) vpa_init(cpu); - cpu_clear(cpu, of_spin_map); + cpumask_clear_cpu(cpu, of_spin_mask); set_cpu_current_state(cpu, CPU_STATE_ONLINE); set_default_offline_state(cpu); @@ -186,17 +214,19 @@ static void __init smp_init_pseries(void) pr_debug(" -> smp_init_pSeries()\n"); + alloc_bootmem_cpumask_var(&of_spin_mask); + /* Mark threads which are still spinning in hold loops. */ if (cpu_has_feature(CPU_FTR_SMT)) { for_each_present_cpu(i) { if (cpu_thread_in_core(i) == 0) - cpu_set(i, of_spin_map); + cpumask_set_cpu(i, of_spin_mask); } } else { - of_spin_map = cpu_present_map; + cpumask_copy(of_spin_mask, cpu_present_mask); } - cpu_clear(boot_cpuid, of_spin_map); + cpumask_clear_cpu(boot_cpuid, of_spin_mask); /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 1bcedd8b461..f19d1946839 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -163,29 +163,37 @@ static inline void lpar_qirr_info(int n_cpu , u8 value) /* Interface to generic irq subsystem */ #ifdef CONFIG_SMP -static int get_irq_server(unsigned int virq, cpumask_t cpumask, +/* + * For the moment we only implement delivery to all cpus or one cpu. + * + * If the requested affinity is cpu_all_mask, we set global affinity. + * If not we set it to the first cpu in the mask, even if multiple cpus + * are set. This is so things like irqbalance (which set core and package + * wide affinities) do the right thing. + */ +static int get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check) { - int server; - /* For the moment only implement delivery to all cpus or one cpu */ - cpumask_t tmp = CPU_MASK_NONE; if (!distribute_irqs) return default_server; - if (!cpus_equal(cpumask, CPU_MASK_ALL)) { - cpus_and(tmp, cpu_online_map, cpumask); - - server = first_cpu(tmp); + if (!cpumask_equal(cpumask, cpu_all_mask)) { + int server = cpumask_first_and(cpu_online_mask, cpumask); - if (server < NR_CPUS) + if (server < nr_cpu_ids) return get_hard_smp_processor_id(server); if (strict_check) return -1; } - if (cpus_equal(cpu_online_map, cpu_present_map)) + /* + * Workaround issue with some versions of JS20 firmware that + * deliver interrupts to cpus which haven't been started. This + * happens when using the maxcpus= boot option. + */ + if (cpumask_equal(cpu_online_mask, cpu_present_mask)) return default_distrib_server; return default_server; @@ -207,7 +215,7 @@ static void xics_unmask_irq(unsigned int virq) if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS) return; - server = get_irq_server(virq, *(irq_to_desc(virq)->affinity), 0); + server = get_irq_server(virq, irq_to_desc(virq)->affinity, 0); call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, server, DEFAULT_PRIORITY); @@ -398,11 +406,7 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) return -1; } - /* - * For the moment only implement delivery to all cpus or one cpu. - * Get current irq_server for the given irq - */ - irq_server = get_irq_server(virq, *cpumask, 1); + irq_server = get_irq_server(virq, cpumask, 1); if (irq_server == -1) { char cpulist[128]; cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); @@ -611,7 +615,7 @@ int __init smp_xics_probe(void) { xics_request_ipi(); - return cpus_weight(cpu_possible_map); + return cpumask_weight(cpu_possible_mask); } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 88f4ae78783..402d2212162 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -185,7 +185,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) axon_ram_bank_id++; dev_info(&device->dev, "Found memory controller on %s\n", - device->node->full_name); + device->dev.of_node->full_name); bank = kzalloc(sizeof(struct axon_ram_bank), GFP_KERNEL); if (bank == NULL) { @@ -198,7 +198,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) bank->device = device; - if (of_address_to_resource(device->node, 0, &resource) != 0) { + if (of_address_to_resource(device->dev.of_node, 0, &resource) != 0) { dev_err(&device->dev, "Cannot access device tree\n"); rc = -EFAULT; goto failed; @@ -253,7 +253,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); add_disk(bank->disk); - bank->irq_id = irq_of_parse_and_map(device->node, 0); + bank->irq_id = irq_of_parse_and_map(device->dev.of_node, 0); if (bank->irq_id == NO_IRQ) { dev_err(&device->dev, "Cannot access ECC interrupt ID\n"); rc = -EFAULT; @@ -327,12 +327,12 @@ static struct of_device_id axon_ram_device_id[] = { }; static struct of_platform_driver axon_ram_driver = { - .match_table = axon_ram_device_id, .probe = axon_ram_probe, .remove = axon_ram_remove, - .driver = { - .owner = THIS_MODULE, - .name = AXON_RAM_MODULE_NAME, + .driver = { + .name = AXON_RAM_MODULE_NAME, + .owner = THIS_MODULE, + .of_match_table = axon_ram_device_id, }, }; diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm.c b/arch/powerpc/sysdev/bestcomm/bestcomm.c index 378ebd9aac1..a7c5c470af1 100644 --- a/arch/powerpc/sysdev/bestcomm/bestcomm.c +++ b/arch/powerpc/sysdev/bestcomm/bestcomm.c @@ -377,7 +377,7 @@ mpc52xx_bcom_probe(struct of_device *op, const struct of_device_id *match) printk(KERN_INFO "DMA: MPC52xx BestComm driver\n"); /* Get the bestcomm node */ - of_node_get(op->node); + of_node_get(op->dev.of_node); /* Prepare SRAM */ ofn_sram = of_find_matching_node(NULL, mpc52xx_sram_ids); @@ -406,10 +406,10 @@ mpc52xx_bcom_probe(struct of_device *op, const struct of_device_id *match) } /* Save the node */ - bcom_eng->ofnode = op->node; + bcom_eng->ofnode = op->dev.of_node; /* Get, reserve & map io */ - if (of_address_to_resource(op->node, 0, &res_bcom)) { + if (of_address_to_resource(op->dev.of_node, 0, &res_bcom)) { printk(KERN_ERR DRIVER_NAME ": " "Can't get resource\n"); rv = -EINVAL; @@ -453,7 +453,7 @@ error_sramclean: kfree(bcom_eng); bcom_sram_cleanup(); error_ofput: - of_node_put(op->node); + of_node_put(op->dev.of_node); printk(KERN_ERR "DMA: MPC52xx BestComm init failed !\n"); @@ -494,14 +494,12 @@ MODULE_DEVICE_TABLE(of, mpc52xx_bcom_of_match); static struct of_platform_driver mpc52xx_bcom_of_platform_driver = { - .owner = THIS_MODULE, - .name = DRIVER_NAME, - .match_table = mpc52xx_bcom_of_match, .probe = mpc52xx_bcom_probe, .remove = mpc52xx_bcom_remove, - .driver = { - .name = DRIVER_NAME, - .owner = THIS_MODULE, + .driver = { + .name = DRIVER_NAME, + .owner = THIS_MODULE, + .of_match_table = mpc52xx_bcom_of_match, }, }; diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 3482e3fd89c..a7be144f587 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -249,7 +249,7 @@ static int __devinit fsl_of_msi_probe(struct of_device *dev, goto error_out; } - msi->irqhost = irq_alloc_host(dev->node, IRQ_HOST_MAP_LINEAR, + msi->irqhost = irq_alloc_host(dev->dev.of_node, IRQ_HOST_MAP_LINEAR, NR_MSI_IRQS, &fsl_msi_host_ops, 0); if (msi->irqhost == NULL) { @@ -259,10 +259,10 @@ static int __devinit fsl_of_msi_probe(struct of_device *dev, } /* Get the MSI reg base */ - err = of_address_to_resource(dev->node, 0, &res); + err = of_address_to_resource(dev->dev.of_node, 0, &res); if (err) { dev_err(&dev->dev, "%s resource error!\n", - dev->node->full_name); + dev->dev.of_node->full_name); goto error_out; } @@ -285,16 +285,16 @@ static int __devinit fsl_of_msi_probe(struct of_device *dev, goto error_out; } - p = of_get_property(dev->node, "interrupts", &count); + p = of_get_property(dev->dev.of_node, "interrupts", &count); if (!p) { dev_err(&dev->dev, "no interrupts property found on %s\n", - dev->node->full_name); + dev->dev.of_node->full_name); err = -ENODEV; goto error_out; } if (count % 8 != 0) { dev_err(&dev->dev, "Malformed interrupts property on %s\n", - dev->node->full_name); + dev->dev.of_node->full_name); err = -EINVAL; goto error_out; } @@ -303,7 +303,7 @@ static int __devinit fsl_of_msi_probe(struct of_device *dev, for (i = 0; i < count / 2; i++) { if (i > NR_MSI_REG) break; - virt_msir = irq_of_parse_and_map(dev->node, i); + virt_msir = irq_of_parse_and_map(dev->dev.of_node, i); if (virt_msir != NO_IRQ) { set_irq_data(virt_msir, (void *)i); set_irq_chained_handler(virt_msir, fsl_msi_cascade); @@ -345,8 +345,11 @@ static const struct of_device_id fsl_of_msi_ids[] = { }; static struct of_platform_driver fsl_of_msi_driver = { - .name = "fsl-msi", - .match_table = fsl_of_msi_ids, + .driver = { + .name = "fsl-msi", + .owner = THIS_MODULE, + .of_match_table = fsl_of_msi_ids, + }, .probe = fsl_of_msi_probe, }; diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c index a7635a993dc..9082eb921ad 100644 --- a/arch/powerpc/sysdev/fsl_pmc.c +++ b/arch/powerpc/sysdev/fsl_pmc.c @@ -60,7 +60,7 @@ static struct platform_suspend_ops pmc_suspend_ops = { static int pmc_probe(struct of_device *ofdev, const struct of_device_id *id) { - pmc_regs = of_iomap(ofdev->node, 0); + pmc_regs = of_iomap(ofdev->dev.of_node, 0); if (!pmc_regs) return -ENOMEM; @@ -76,8 +76,11 @@ static const struct of_device_id pmc_ids[] = { }; static struct of_platform_driver pmc_driver = { - .driver.name = "fsl-pmc", - .match_table = pmc_ids, + .driver = { + .name = "fsl-pmc", + .owner = THIS_MODULE, + .of_match_table = pmc_ids, + }, .probe = pmc_probe, }; diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 71fba88f50d..6a1fde0d22b 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -1015,41 +1015,41 @@ int fsl_rio_setup(struct of_device *dev) u64 law_start, law_size; int paw, aw, sw; - if (!dev->node) { + if (!dev->dev.of_node) { dev_err(&dev->dev, "Device OF-Node is NULL"); return -EFAULT; } - rc = of_address_to_resource(dev->node, 0, ®s); + rc = of_address_to_resource(dev->dev.of_node, 0, ®s); if (rc) { dev_err(&dev->dev, "Can't get %s property 'reg'\n", - dev->node->full_name); + dev->dev.of_node->full_name); return -EFAULT; } - dev_info(&dev->dev, "Of-device full name %s\n", dev->node->full_name); + dev_info(&dev->dev, "Of-device full name %s\n", dev->dev.of_node->full_name); dev_info(&dev->dev, "Regs: %pR\n", ®s); - dt_range = of_get_property(dev->node, "ranges", &rlen); + dt_range = of_get_property(dev->dev.of_node, "ranges", &rlen); if (!dt_range) { dev_err(&dev->dev, "Can't get %s property 'ranges'\n", - dev->node->full_name); + dev->dev.of_node->full_name); return -EFAULT; } /* Get node address wide */ - cell = of_get_property(dev->node, "#address-cells", NULL); + cell = of_get_property(dev->dev.of_node, "#address-cells", NULL); if (cell) aw = *cell; else - aw = of_n_addr_cells(dev->node); + aw = of_n_addr_cells(dev->dev.of_node); /* Get node size wide */ - cell = of_get_property(dev->node, "#size-cells", NULL); + cell = of_get_property(dev->dev.of_node, "#size-cells", NULL); if (cell) sw = *cell; else - sw = of_n_size_cells(dev->node); + sw = of_n_size_cells(dev->dev.of_node); /* Get parent address wide wide */ - paw = of_n_addr_cells(dev->node); + paw = of_n_addr_cells(dev->dev.of_node); law_start = of_read_number(dt_range + aw, paw); law_size = of_read_number(dt_range + aw + paw, sw); @@ -1089,9 +1089,9 @@ int fsl_rio_setup(struct of_device *dev) port->iores.flags = IORESOURCE_MEM; port->iores.name = "rio_io_win"; - priv->bellirq = irq_of_parse_and_map(dev->node, 2); - priv->txirq = irq_of_parse_and_map(dev->node, 3); - priv->rxirq = irq_of_parse_and_map(dev->node, 4); + priv->bellirq = irq_of_parse_and_map(dev->dev.of_node, 2); + priv->txirq = irq_of_parse_and_map(dev->dev.of_node, 3); + priv->rxirq = irq_of_parse_and_map(dev->dev.of_node, 4); dev_info(&dev->dev, "bellirq: %d, txirq: %d, rxirq %d\n", priv->bellirq, priv->txirq, priv->rxirq); @@ -1195,7 +1195,7 @@ static int __devinit fsl_of_rio_rpn_probe(struct of_device *dev, { int rc; printk(KERN_INFO "Setting up RapidIO peer-to-peer network %s\n", - dev->node->full_name); + dev->dev.of_node->full_name); rc = fsl_rio_setup(dev); if (rc) @@ -1215,8 +1215,11 @@ static const struct of_device_id fsl_of_rio_rpn_ids[] = { }; static struct of_platform_driver fsl_of_rio_rpn_driver = { - .name = "fsl-of-rio", - .match_table = fsl_of_rio_rpn_ids, + .driver = { + .name = "fsl-of-rio", + .owner = THIS_MODULE, + .of_match_table = fsl_of_rio_rpn_ids, + }, .probe = fsl_of_rio_rpn_probe, }; diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c index 6478eb10691..83f519655fa 100644 --- a/arch/powerpc/sysdev/mpc8xxx_gpio.c +++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c @@ -16,6 +16,7 @@ #include <linux/of_gpio.h> #include <linux/gpio.h> #include <linux/slab.h> +#include <linux/irq.h> #define MPC8XXX_GPIO_PINS 32 @@ -35,6 +36,7 @@ struct mpc8xxx_gpio_chip { * open drain mode safely */ u32 data; + struct irq_host *irq; }; static inline u32 mpc8xxx_gpio2mask(unsigned int gpio) @@ -128,12 +130,136 @@ static int mpc8xxx_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val return 0; } +static int mpc8xxx_gpio_to_irq(struct gpio_chip *gc, unsigned offset) +{ + struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc); + struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm); + + if (mpc8xxx_gc->irq && offset < MPC8XXX_GPIO_PINS) + return irq_create_mapping(mpc8xxx_gc->irq, offset); + else + return -ENXIO; +} + +static void mpc8xxx_gpio_irq_cascade(unsigned int irq, struct irq_desc *desc) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_desc_data(desc); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + unsigned int mask; + + mask = in_be32(mm->regs + GPIO_IER) & in_be32(mm->regs + GPIO_IMR); + if (mask) + generic_handle_irq(irq_linear_revmap(mpc8xxx_gc->irq, + 32 - ffs(mask))); +} + +static void mpc8xxx_irq_unmask(unsigned int virq) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + unsigned long flags; + + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + + setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(virq))); + + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); +} + +static void mpc8xxx_irq_mask(unsigned int virq) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + unsigned long flags; + + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + + clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(virq))); + + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); +} + +static void mpc8xxx_irq_ack(unsigned int virq) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + + out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(virq_to_hw(virq))); +} + +static int mpc8xxx_irq_set_type(unsigned int virq, unsigned int flow_type) +{ + struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq); + struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; + unsigned long flags; + + switch (flow_type) { + case IRQ_TYPE_EDGE_FALLING: + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + setbits32(mm->regs + GPIO_ICR, + mpc8xxx_gpio2mask(virq_to_hw(virq))); + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); + break; + + case IRQ_TYPE_EDGE_BOTH: + spin_lock_irqsave(&mpc8xxx_gc->lock, flags); + clrbits32(mm->regs + GPIO_ICR, + mpc8xxx_gpio2mask(virq_to_hw(virq))); + spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); + break; + + default: + return -EINVAL; + } + + return 0; +} + +static struct irq_chip mpc8xxx_irq_chip = { + .name = "mpc8xxx-gpio", + .unmask = mpc8xxx_irq_unmask, + .mask = mpc8xxx_irq_mask, + .ack = mpc8xxx_irq_ack, + .set_type = mpc8xxx_irq_set_type, +}; + +static int mpc8xxx_gpio_irq_map(struct irq_host *h, unsigned int virq, + irq_hw_number_t hw) +{ + set_irq_chip_data(virq, h->host_data); + set_irq_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_level_irq); + set_irq_type(virq, IRQ_TYPE_NONE); + + return 0; +} + +static int mpc8xxx_gpio_irq_xlate(struct irq_host *h, struct device_node *ct, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_flags) + +{ + /* interrupt sense values coming from the device tree equal either + * EDGE_FALLING or EDGE_BOTH + */ + *out_hwirq = intspec[0]; + *out_flags = intspec[1]; + + return 0; +} + +static struct irq_host_ops mpc8xxx_gpio_irq_ops = { + .map = mpc8xxx_gpio_irq_map, + .xlate = mpc8xxx_gpio_irq_xlate, +}; + static void __init mpc8xxx_add_controller(struct device_node *np) { struct mpc8xxx_gpio_chip *mpc8xxx_gc; struct of_mm_gpio_chip *mm_gc; struct of_gpio_chip *of_gc; struct gpio_chip *gc; + unsigned hwirq; int ret; mpc8xxx_gc = kzalloc(sizeof(*mpc8xxx_gc), GFP_KERNEL); @@ -158,11 +284,32 @@ static void __init mpc8xxx_add_controller(struct device_node *np) else gc->get = mpc8xxx_gpio_get; gc->set = mpc8xxx_gpio_set; + gc->to_irq = mpc8xxx_gpio_to_irq; ret = of_mm_gpiochip_add(np, mm_gc); if (ret) goto err; + hwirq = irq_of_parse_and_map(np, 0); + if (hwirq == NO_IRQ) + goto skip_irq; + + mpc8xxx_gc->irq = + irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, MPC8XXX_GPIO_PINS, + &mpc8xxx_gpio_irq_ops, MPC8XXX_GPIO_PINS); + if (!mpc8xxx_gc->irq) + goto skip_irq; + + mpc8xxx_gc->irq->host_data = mpc8xxx_gc; + + /* ack and mask all irqs */ + out_be32(mm_gc->regs + GPIO_IER, 0xffffffff); + out_be32(mm_gc->regs + GPIO_IMR, 0); + + set_irq_data(hwirq, mpc8xxx_gc); + set_irq_chained_handler(hwirq, mpc8xxx_gpio_irq_cascade); + +skip_irq: return; err: diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 260295b1055..2102487612a 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -568,12 +568,12 @@ static void __init mpic_scan_ht_pics(struct mpic *mpic) #endif /* CONFIG_MPIC_U3_HT_IRQS */ #ifdef CONFIG_SMP -static int irq_choose_cpu(const cpumask_t *mask) +static int irq_choose_cpu(const struct cpumask *mask) { int cpuid; if (cpumask_equal(mask, cpu_all_mask)) { - static int irq_rover; + static int irq_rover = 0; static DEFINE_RAW_SPINLOCK(irq_rover_lock); unsigned long flags; @@ -581,15 +581,11 @@ static int irq_choose_cpu(const cpumask_t *mask) do_round_robin: raw_spin_lock_irqsave(&irq_rover_lock, flags); - while (!cpu_online(irq_rover)) { - if (++irq_rover >= NR_CPUS) - irq_rover = 0; - } + irq_rover = cpumask_next(irq_rover, cpu_online_mask); + if (irq_rover >= nr_cpu_ids) + irq_rover = cpumask_first(cpu_online_mask); + cpuid = irq_rover; - do { - if (++irq_rover >= NR_CPUS) - irq_rover = 0; - } while (!cpu_online(irq_rover)); raw_spin_unlock_irqrestore(&irq_rover_lock, flags); } else { @@ -601,7 +597,7 @@ static int irq_choose_cpu(const cpumask_t *mask) return get_hard_smp_processor_id(cpuid); } #else -static int irq_choose_cpu(const cpumask_t *mask) +static int irq_choose_cpu(const struct cpumask *mask) { return hard_smp_processor_id(); } @@ -814,12 +810,16 @@ int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), 1 << cpuid); } else { - cpumask_t tmp; + cpumask_var_t tmp; - cpumask_and(&tmp, cpumask, cpu_online_mask); + alloc_cpumask_var(&tmp, GFP_KERNEL); + + cpumask_and(tmp, cpumask, cpu_online_mask); mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), - mpic_physmask(cpus_addr(tmp)[0])); + mpic_physmask(cpumask_bits(tmp)[0])); + + free_cpumask_var(tmp); } return 0; @@ -1479,21 +1479,6 @@ void mpic_teardown_this_cpu(int secondary) } -void mpic_send_ipi(unsigned int ipi_no, unsigned int cpu_mask) -{ - struct mpic *mpic = mpic_primary; - - BUG_ON(mpic == NULL); - -#ifdef DEBUG_IPI - DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, ipi_no); -#endif - - mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + - ipi_no * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), - mpic_physmask(cpu_mask & cpus_addr(cpu_online_map)[0])); -} - static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg) { u32 src; @@ -1589,8 +1574,25 @@ void mpic_request_ipis(void) } } +static void mpic_send_ipi(unsigned int ipi_no, const struct cpumask *cpu_mask) +{ + struct mpic *mpic = mpic_primary; + + BUG_ON(mpic == NULL); + +#ifdef DEBUG_IPI + DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, ipi_no); +#endif + + mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + + ipi_no * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), + mpic_physmask(cpumask_bits(cpu_mask)[0])); +} + void smp_mpic_message_pass(int target, int msg) { + cpumask_var_t tmp; + /* make sure we're sending something that translates to an IPI */ if ((unsigned int)msg > 3) { printk("SMP %d: smp_message_pass: unknown msg %d\n", @@ -1599,13 +1601,17 @@ void smp_mpic_message_pass(int target, int msg) } switch (target) { case MSG_ALL: - mpic_send_ipi(msg, 0xffffffff); + mpic_send_ipi(msg, cpu_online_mask); break; case MSG_ALL_BUT_SELF: - mpic_send_ipi(msg, 0xffffffff & ~(1 << smp_processor_id())); + alloc_cpumask_var(&tmp, GFP_NOWAIT); + cpumask_andnot(tmp, cpu_online_mask, + cpumask_of(smp_processor_id())); + mpic_send_ipi(msg, tmp); + free_cpumask_var(tmp); break; default: - mpic_send_ipi(msg, 1 << target); + mpic_send_ipi(msg, cpumask_of(target)); break; } } @@ -1616,7 +1622,7 @@ int __init smp_mpic_probe(void) DBG("smp_mpic_probe()...\n"); - nr_cpus = cpus_weight(cpu_possible_map); + nr_cpus = cpumask_weight(cpu_possible_mask); DBG("nr_cpus: %d\n", nr_cpus); diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index 1456015a22d..198f288570c 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -24,7 +24,7 @@ #define MV64X60_VAL_LEN_MAX 11 #define MV64X60_PCICFG_CPCI_HOTSWAP 0x68 -static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -45,7 +45,7 @@ static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, return sprintf(buf, "0x%08x\n", v); } -static ssize_t mv64x60_hs_reg_write(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c index 652652db4ce..d07137a07d7 100644 --- a/arch/powerpc/sysdev/pmi.c +++ b/arch/powerpc/sysdev/pmi.c @@ -124,7 +124,7 @@ static void pmi_notify_handlers(struct work_struct *work) static int pmi_of_probe(struct of_device *dev, const struct of_device_id *match) { - struct device_node *np = dev->node; + struct device_node *np = dev->dev.of_node; int rc; if (data) { @@ -206,11 +206,12 @@ static int pmi_of_remove(struct of_device *dev) } static struct of_platform_driver pmi_of_platform_driver = { - .match_table = pmi_match, .probe = pmi_of_probe, .remove = pmi_of_remove, - .driver = { - .name = "pmi", + .driver = { + .name = "pmi", + .owner = THIS_MODULE, + .of_match_table = pmi_match, }, }; diff --git a/arch/powerpc/sysdev/ppc4xx_soc.c b/arch/powerpc/sysdev/ppc4xx_soc.c index 5c014350bf1..d3d6ce3c33b 100644 --- a/arch/powerpc/sysdev/ppc4xx_soc.c +++ b/arch/powerpc/sysdev/ppc4xx_soc.c @@ -191,11 +191,31 @@ static int __init ppc4xx_l2c_probe(void) arch_initcall(ppc4xx_l2c_probe); /* - * At present, this routine just applies a system reset. + * Apply a system reset. Alternatively a board specific value may be + * provided via the "reset-type" property in the cpu node. */ void ppc4xx_reset_system(char *cmd) { - mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_RST_SYSTEM); + struct device_node *np; + u32 reset_type = DBCR0_RST_SYSTEM; + const u32 *prop; + + np = of_find_node_by_type(NULL, "cpu"); + if (np) { + prop = of_get_property(np, "reset-type", NULL); + + /* + * Check if property exists and if it is in range: + * 1 - PPC4xx core reset + * 2 - PPC4xx chip reset + * 3 - PPC4xx system reset (default) + */ + if ((prop) && ((prop[0] >= 1) && (prop[0] <= 3))) + reset_type = prop[0] << 28; + } + + mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | reset_type); + while (1) ; /* Just in case the reset doesn't work */ } diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 149393c02c3..093e0ae1a94 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -669,8 +669,11 @@ static const struct of_device_id qe_ids[] = { }; static struct of_platform_driver qe_driver = { - .driver.name = "fsl-qe", - .match_table = qe_ids, + .driver = { + .name = "fsl-qe", + .owner = THIS_MODULE, + .of_match_table = qe_ids, + }, .probe = qe_probe, .resume = qe_resume, }; |