diff options
Diffstat (limited to 'arch/powerpc')
261 files changed, 8914 insertions, 9858 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9b780e0d2c18..190cc48abc0c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -152,6 +152,7 @@ config PPC select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN select NO_BOOTMEM select HAVE_GENERIC_RCU_GUP + select HAVE_PERF_EVENTS_NMI if PPC64 config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN @@ -189,9 +190,6 @@ config ARCH_MAY_HAVE_PC_FDC bool default PCI -config PPC_OF - def_bool y - config PPC_UDBG_16550 bool default n diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index ec2e40f2cc11..0efa8f90a8f1 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -117,7 +117,7 @@ config BDI_SWITCH config BOOTX_TEXT bool "Support for early boot text console (BootX or OpenFirmware only)" - depends on PPC_OF && PPC_BOOK3S + depends on PPC_BOOK3S help Say Y here to see progress messages from the boot firmware in text mode. Requires either BootX or Open Firmware. @@ -193,13 +193,6 @@ config PPC_EARLY_DEBUG_PAS_REALMODE Select this to enable early debugging for PA Semi. Output will be on UART0. -config PPC_EARLY_DEBUG_BEAT - bool "Beat HV Console" - depends on PPC_CELLEB - select PPC_UDBG_BEAT - help - Select this to enable early debugging for Celleb with Beat. - config PPC_EARLY_DEBUG_44x bool "Early serial debugging for IBM/AMCC 44x CPUs" depends on 44x diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index fc502e042438..07a480861f78 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -248,10 +248,10 @@ boot := arch/$(ARCH)/boot ifeq ($(CONFIG_RELOCATABLE),y) quiet_cmd_relocs_check = CALL $< - cmd_relocs_check = perl $< "$(OBJDUMP)" "$(obj)/vmlinux" + cmd_relocs_check = $(CONFIG_SHELL) $< "$(OBJDUMP)" "$(obj)/vmlinux" PHONY += relocs_check -relocs_check: arch/powerpc/relocs_check.pl vmlinux +relocs_check: arch/powerpc/relocs_check.sh vmlinux $(call cmd,relocs_check) zImage: relocs_check diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 8a5bc1cfc6aa..73eddda53b8e 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -110,7 +110,6 @@ src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S -src-plat-$(CONFIG_PPC_CELLEB) += pseries-head.S src-plat-$(CONFIG_PPC_CELL_QPACE) += pseries-head.S src-wlib := $(sort $(src-wlib-y)) @@ -215,7 +214,6 @@ image-$(CONFIG_PPC_POWERNV) += 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 image-$(CONFIG_PPC_CELL_QPACE) += zImage.pseries image-$(CONFIG_PPC_CHRP) += zImage.chrp image-$(CONFIG_PPC_EFIKA) += zImage.chrp @@ -317,7 +315,7 @@ endif # Allow extra targets to be added to the defconfig image-y += $(subst ",,$(CONFIG_EXTRA_TARGETS)) -initrd- := $(patsubst zImage%, zImage.initrd%, $(image-n) $(image-)) +initrd- := $(patsubst zImage%, zImage.initrd%, $(image-)) initrd-y := $(patsubst zImage%, zImage.initrd%, \ $(patsubst dtbImage%, dtbImage.initrd%, \ $(patsubst simpleImage%, simpleImage.initrd%, \ diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 14de4f8778a7..12866ccb5694 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -155,29 +155,29 @@ p_base: mflr r10 /* r10 now points to runtime addr of p_base */ ld r9,(p_rela-p_base)(r10) add r9,r9,r10 - li r7,0 + li r13,0 li r8,0 -9: ld r6,0(r11) /* get tag */ - cmpdi r6,0 +9: ld r12,0(r11) /* get tag */ + cmpdi r12,0 beq 12f /* end of list */ - cmpdi r6,RELA + cmpdi r12,RELA bne 10f - ld r7,8(r11) /* get RELA pointer in r7 */ + ld r13,8(r11) /* get RELA pointer in r13 */ b 11f -10: addis r6,r6,(-RELACOUNT)@ha - cmpdi r6,RELACOUNT@l +10: addis r12,r12,(-RELACOUNT)@ha + cmpdi r12,RELACOUNT@l bne 11f ld r8,8(r11) /* get RELACOUNT value in r8 */ 11: addi r11,r11,16 b 9b 12: - cmpdi r7,0 /* check we have both RELA and RELACOUNT */ + cmpdi r13,0 /* check we have both RELA and RELACOUNT */ cmpdi cr1,r8,0 beq 3f beq cr1,3f /* Calcuate the runtime offset. */ - subf r7,r7,r9 + subf r13,r13,r9 /* Run through the list of relocations and process the * R_PPC64_RELATIVE ones. */ @@ -185,10 +185,10 @@ p_base: mflr r10 /* r10 now points to runtime addr of p_base */ 13: ld r0,8(r9) /* ELF64_R_TYPE(reloc->r_info) */ cmpdi r0,22 /* R_PPC64_RELATIVE */ bne 3f - ld r6,0(r9) /* reloc->r_offset */ + ld r12,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ - add r0,r0,r7 - stdx r0,r7,r6 + add r0,r0,r13 + stdx r0,r13,r12 addi r9,r9,24 bdnz 13b @@ -218,7 +218,7 @@ p_base: mflr r10 /* r10 now points to runtime addr of p_base */ beq 6f ld r1,0(r8) li r0,0 - stdu r0,-16(r1) /* establish a stack frame */ + stdu r0,-112(r1) /* establish a stack frame */ 6: #endif /* __powerpc64__ */ /* Call platform_init() */ diff --git a/arch/powerpc/boot/dts/b4860emu.dts b/arch/powerpc/boot/dts/b4860emu.dts deleted file mode 100644 index 2aa5cd318ce8..000000000000 --- a/arch/powerpc/boot/dts/b4860emu.dts +++ /dev/null @@ -1,223 +0,0 @@ -/* - * B4860 emulator Device Tree Source - * - * Copyright 2013 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * This software is provided by Freescale Semiconductor "as is" and any - * express or implied warranties, including, but not limited to, the implied - * warranties of merchantability and fitness for a particular purpose are - * disclaimed. In no event shall Freescale Semiconductor be liable for any - * direct, indirect, incidental, special, exemplary, or consequential damages - * (including, but not limited to, procurement of substitute goods or services; - * loss of use, data, or profits; or business interruption) however caused and - * on any theory of liability, whether in contract, strict liability, or tort - * (including negligence or otherwise) arising in any way out of the use of - * this software, even if advised of the possibility of such damage. - */ - -/dts-v1/; - -/include/ "fsl/e6500_power_isa.dtsi" - -/ { - compatible = "fsl,B4860"; - #address-cells = <2>; - #size-cells = <2>; - interrupt-parent = <&mpic>; - - aliases { - ccsr = &soc; - - serial0 = &serial0; - serial1 = &serial1; - serial2 = &serial2; - serial3 = &serial3; - dma0 = &dma0; - dma1 = &dma1; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - cpu0: PowerPC,e6500@0 { - device_type = "cpu"; - reg = <0 1>; - next-level-cache = <&L2>; - fsl,portid-mapping = <0x80000000>; - }; - cpu1: PowerPC,e6500@2 { - device_type = "cpu"; - reg = <2 3>; - next-level-cache = <&L2>; - fsl,portid-mapping = <0x80000000>; - }; - cpu2: PowerPC,e6500@4 { - device_type = "cpu"; - reg = <4 5>; - next-level-cache = <&L2>; - fsl,portid-mapping = <0x80000000>; - }; - cpu3: PowerPC,e6500@6 { - device_type = "cpu"; - reg = <6 7>; - next-level-cache = <&L2>; - fsl,portid-mapping = <0x80000000>; - }; - }; -}; - -/ { - model = "fsl,B4860QDS"; - compatible = "fsl,B4860EMU", "fsl,B4860QDS"; - #address-cells = <2>; - #size-cells = <2>; - interrupt-parent = <&mpic>; - - ifc: localbus@ffe124000 { - reg = <0xf 0xfe124000 0 0x2000>; - ranges = <0 0 0xf 0xe8000000 0x08000000 - 2 0 0xf 0xff800000 0x00010000 - 3 0 0xf 0xffdf0000 0x00008000>; - - nor@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "cfi-flash"; - reg = <0x0 0x0 0x8000000>; - bank-width = <2>; - device-width = <1>; - }; - }; - - memory { - device_type = "memory"; - }; - - soc: soc@ffe000000 { - ranges = <0x00000000 0xf 0xfe000000 0x1000000>; - reg = <0xf 0xfe000000 0 0x00001000>; - }; -}; - -&ifc { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; - interrupts = <25 2 0 0>; -}; - -&soc { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - - soc-sram-error { - compatible = "fsl,soc-sram-error"; - interrupts = <16 2 1 2>; - }; - - corenet-law@0 { - compatible = "fsl,corenet-law"; - reg = <0x0 0x1000>; - fsl,num-laws = <32>; - }; - - ddr1: memory-controller@8000 { - compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller"; - reg = <0x8000 0x1000>; - interrupts = <16 2 1 8>; - }; - - ddr2: memory-controller@9000 { - compatible = "fsl,qoriq-memory-controller-v4.5","fsl,qoriq-memory-controller"; - reg = <0x9000 0x1000>; - interrupts = <16 2 1 9>; - }; - - cpc: l3-cache-controller@10000 { - compatible = "fsl,b4-l3-cache-controller", "cache"; - reg = <0x10000 0x1000 - 0x11000 0x1000>; - interrupts = <16 2 1 4>; - }; - - corenet-cf@18000 { - compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; - reg = <0x18000 0x1000>; - interrupts = <16 2 1 0>; - fsl,ccf-num-csdids = <32>; - fsl,ccf-num-snoopids = <32>; - }; - - iommu@20000 { - compatible = "fsl,pamu-v1.0", "fsl,pamu"; - reg = <0x20000 0x4000>; - fsl,portid-mapping = <0x8000>; - #address-cells = <1>; - #size-cells = <1>; - interrupts = < - 24 2 0 0 - 16 2 1 1>; - pamu0: pamu@0 { - reg = <0 0x1000>; - fsl,primary-cache-geometry = <8 1>; - fsl,secondary-cache-geometry = <32 2>; - }; - }; - -/include/ "fsl/qoriq-mpic.dtsi" - - guts: global-utilities@e0000 { - compatible = "fsl,b4-device-config"; - reg = <0xe0000 0xe00>; - fsl,has-rstcr; - fsl,liodn-bits = <12>; - }; - -/include/ "fsl/qoriq-clockgen2.dtsi" - global-utilities@e1000 { - compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0"; - }; - -/include/ "fsl/qoriq-dma-0.dtsi" - dma@100300 { - fsl,iommu-parent = <&pamu0>; - fsl,liodn-reg = <&guts 0x580>; /* DMA1LIODNR */ - }; - -/include/ "fsl/qoriq-dma-1.dtsi" - dma@101300 { - fsl,iommu-parent = <&pamu0>; - fsl,liodn-reg = <&guts 0x584>; /* DMA2LIODNR */ - }; - -/include/ "fsl/qoriq-i2c-0.dtsi" -/include/ "fsl/qoriq-i2c-1.dtsi" -/include/ "fsl/qoriq-duart-0.dtsi" -/include/ "fsl/qoriq-duart-1.dtsi" - - L2: l2-cache-controller@c20000 { - compatible = "fsl,b4-l2-cache-controller"; - reg = <0xc20000 0x1000>; - next-level-cache = <&cpc>; - }; -}; diff --git a/arch/powerpc/boot/dts/b4qds.dtsi b/arch/powerpc/boot/dts/b4qds.dtsi index e5bde0b85135..24ed80dc2120 100644 --- a/arch/powerpc/boot/dts/b4qds.dtsi +++ b/arch/powerpc/boot/dts/b4qds.dtsi @@ -1,7 +1,7 @@ /* * B4420DS Device Tree Source * - * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2012 - 2014 Freescale Semiconductor, Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -97,10 +97,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01052000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi index 65100b9636b7..f35e9e0a5445 100644 --- a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi @@ -1,7 +1,7 @@ /* * B4860 Silicon/SoC Device Tree Source (post include) * - * Copyright 2012 Freescale Semiconductor Inc. + * Copyright 2012 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -109,6 +109,64 @@ }; }; +&bportals { + bman-portal@38000 { + compatible = "fsl,bman-portal"; + reg = <0x38000 0x4000>, <0x100e000 0x1000>; + interrupts = <133 2 0 0>; + }; + bman-portal@3c000 { + compatible = "fsl,bman-portal"; + reg = <0x3c000 0x4000>, <0x100f000 0x1000>; + interrupts = <135 2 0 0>; + }; + bman-portal@40000 { + compatible = "fsl,bman-portal"; + reg = <0x40000 0x4000>, <0x1010000 0x1000>; + interrupts = <137 2 0 0>; + }; + bman-portal@44000 { + compatible = "fsl,bman-portal"; + reg = <0x44000 0x4000>, <0x1011000 0x1000>; + interrupts = <139 2 0 0>; + }; + bman-portal@48000 { + compatible = "fsl,bman-portal"; + reg = <0x48000 0x4000>, <0x1012000 0x1000>; + interrupts = <141 2 0 0>; + }; + bman-portal@4c000 { + compatible = "fsl,bman-portal"; + reg = <0x4c000 0x4000>, <0x1013000 0x1000>; + interrupts = <143 2 0 0>; + }; + bman-portal@50000 { + compatible = "fsl,bman-portal"; + reg = <0x50000 0x4000>, <0x1014000 0x1000>; + interrupts = <145 2 0 0>; + }; + bman-portal@54000 { + compatible = "fsl,bman-portal"; + reg = <0x54000 0x4000>, <0x1015000 0x1000>; + interrupts = <147 2 0 0>; + }; + bman-portal@58000 { + compatible = "fsl,bman-portal"; + reg = <0x58000 0x4000>, <0x1016000 0x1000>; + interrupts = <149 2 0 0>; + }; + bman-portal@5c000 { + compatible = "fsl,bman-portal"; + reg = <0x5c000 0x4000>, <0x1017000 0x1000>; + interrupts = <151 2 0 0>; + }; + bman-portal@60000 { + compatible = "fsl,bman-portal"; + reg = <0x60000 0x4000>, <0x1018000 0x1000>; + interrupts = <153 2 0 0>; + }; +}; + &soc { ddr2: memory-controller@9000 { compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller"; diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi index 1a54ba71f685..73136c0029d2 100644 --- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -1,7 +1,7 @@ /* * B4420 Silicon/SoC Device Tree Source (post include) * - * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2012 - 2014 Freescale Semiconductor, Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * this software, even if advised of the possibility of such damage. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &ifc { #address-cells = <2>; #size-cells = <1>; @@ -128,6 +133,83 @@ }; }; +&bportals { + #address-cells = <0x1>; + #size-cells = <0x1>; + compatible = "simple-bus"; + + bman-portal@0 { + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x1000000 0x1000>; + interrupts = <105 2 0 0>; + }; + bman-portal@4000 { + compatible = "fsl,bman-portal"; + reg = <0x4000 0x4000>, <0x1001000 0x1000>; + interrupts = <107 2 0 0>; + }; + bman-portal@8000 { + compatible = "fsl,bman-portal"; + reg = <0x8000 0x4000>, <0x1002000 0x1000>; + interrupts = <109 2 0 0>; + }; + bman-portal@c000 { + compatible = "fsl,bman-portal"; + reg = <0xc000 0x4000>, <0x1003000 0x1000>; + interrupts = <111 2 0 0>; + }; + bman-portal@10000 { + compatible = "fsl,bman-portal"; + reg = <0x10000 0x4000>, <0x1004000 0x1000>; + interrupts = <113 2 0 0>; + }; + bman-portal@14000 { + compatible = "fsl,bman-portal"; + reg = <0x14000 0x4000>, <0x1005000 0x1000>; + interrupts = <115 2 0 0>; + }; + bman-portal@18000 { + compatible = "fsl,bman-portal"; + reg = <0x18000 0x4000>, <0x1006000 0x1000>; + interrupts = <117 2 0 0>; + }; + bman-portal@1c000 { + compatible = "fsl,bman-portal"; + reg = <0x1c000 0x4000>, <0x1007000 0x1000>; + interrupts = <119 2 0 0>; + }; + bman-portal@20000 { + compatible = "fsl,bman-portal"; + reg = <0x20000 0x4000>, <0x1008000 0x1000>; + interrupts = <121 2 0 0>; + }; + bman-portal@24000 { + compatible = "fsl,bman-portal"; + reg = <0x24000 0x4000>, <0x1009000 0x1000>; + interrupts = <123 2 0 0>; + }; + bman-portal@28000 { + compatible = "fsl,bman-portal"; + reg = <0x28000 0x4000>, <0x100a000 0x1000>; + interrupts = <125 2 0 0>; + }; + bman-portal@2c000 { + compatible = "fsl,bman-portal"; + reg = <0x2c000 0x4000>, <0x100b000 0x1000>; + interrupts = <127 2 0 0>; + }; + bman-portal@30000 { + compatible = "fsl,bman-portal"; + reg = <0x30000 0x4000>, <0x100c000 0x1000>; + interrupts = <129 2 0 0>; + }; + bman-portal@34000 { + compatible = "fsl,bman-portal"; + reg = <0x34000 0x4000>, <0x100d000 0x1000>; + interrupts = <131 2 0 0>; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; @@ -261,6 +343,11 @@ /include/ "qoriq-duart-1.dtsi" /include/ "qoriq-sec5.3-0.dtsi" +/include/ "qoriq-bman1.dtsi" + bman: bman@31a000 { + interrupts = <16 2 1 29>; + }; + L2: l2-cache-controller@c20000 { compatible = "fsl,b4-l2-cache-controller"; reg = <0xc20000 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi index 81437fdf1db4..7780f21430cb 100644 --- a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi @@ -1,7 +1,7 @@ /* * P1023/P1017 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10 0>; +}; + &lbc { #address-cells = <2>; #size-cells = <1>; @@ -97,6 +102,28 @@ }; }; +&bportals { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + + bman-portal@0 { + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x100000 0x1000>; + interrupts = <30 2 0 0>; + }; + bman-portal@4000 { + compatible = "fsl,bman-portal"; + reg = <0x4000 0x4000>, <0x101000 0x1000>; + interrupts = <32 2 0 0>; + }; + bman-portal@8000 { + compatible = "fsl,bman-portal"; + reg = <0x8000 0x4000>, <0x102000 0x1000>; + interrupts = <34 2 0 0>; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; @@ -221,6 +248,14 @@ /include/ "pq3-mpic.dtsi" /include/ "pq3-mpic-timer-B.dtsi" + bman: bman@8a000 { + compatible = "fsl,bman"; + reg = <0x8a000 0x1000>; + interrupts = <16 2 0 0>; + fsl,bman-portals = <&bportals>; + memory-region = <&bman_fbpr>; + }; + global-utilities@e0000 { compatible = "fsl,p1023-guts"; reg = <0xe0000 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi index efd74db4f9b0..f2feacfd9a25 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -1,7 +1,7 @@ /* * P2041/P2040 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10 0>; +}; + &lbc { compatible = "fsl,p2041-elbc", "fsl,elbc", "simple-bus"; interrupts = <25 2 0 0>; @@ -216,6 +221,8 @@ }; }; +/include/ "qoriq-bman1-portals.dtsi" + &soc { #address-cells = <1>; #size-cells = <1>; @@ -407,4 +414,6 @@ crypto: crypto@300000 { fsl,iommu-parent = <&pamu1>; }; + +/include/ "qoriq-bman1.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi index d7425ef1ae41..d6fea37395ad 100644 --- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi @@ -1,7 +1,7 @@ /* * P3041 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10 0>; +}; + &lbc { compatible = "fsl,p3041-elbc", "fsl,elbc", "simple-bus"; interrupts = <25 2 0 0>; @@ -243,6 +248,8 @@ }; }; +/include/ "qoriq-bman1-portals.dtsi" + &soc { #address-cells = <1>; #size-cells = <1>; @@ -434,4 +441,6 @@ crypto: crypto@300000 { fsl,iommu-parent = <&pamu1>; }; + +/include/ "qoriq-bman1.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi index 7005a4a4cef0..89482c9b2301 100644 --- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi @@ -1,7 +1,7 @@ /* * P4080/P4040 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10 0>; +}; + &lbc { compatible = "fsl,p4080-elbc", "fsl,elbc", "simple-bus"; interrupts = <25 2 0 0>; @@ -243,6 +248,8 @@ }; +/include/ "qoriq-bman1-portals.dtsi" + &soc { #address-cells = <1>; #size-cells = <1>; @@ -490,4 +497,6 @@ crypto: crypto@300000 { fsl,iommu-parent = <&pamu1>; }; + +/include/ "qoriq-bman1.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi index 55834211bd28..6e04851e2fc9 100644 --- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi @@ -1,7 +1,7 @@ /* * P5020/5010 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &lbc { compatible = "fsl,p5020-elbc", "fsl,elbc", "simple-bus"; interrupts = <25 2 0 0>; @@ -240,6 +245,8 @@ }; }; +/include/ "qoriq-bman1-portals.dtsi" + &soc { #address-cells = <1>; #size-cells = <1>; @@ -421,6 +428,8 @@ fsl,iommu-parent = <&pamu1>; }; +/include/ "qoriq-bman1.dtsi" + /include/ "qoriq-raid1.0-0.dtsi" raideng@320000 { fsl,iommu-parent = <&pamu1>; diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi index 6e4cd6ce363c..5e44dfa1e1a5 100644 --- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi @@ -1,7 +1,7 @@ /* * P5040 Silicon/SoC Device Tree Source (post include) * - * Copyright 2012 Freescale Semiconductor Inc. + * Copyright 2012 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * software, even if advised of the possibility of such damage. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &lbc { compatible = "fsl,p5040-elbc", "fsl,elbc", "simple-bus"; interrupts = <25 2 0 0>; @@ -195,6 +200,8 @@ }; }; +/include/ "qoriq-bman1-portals.dtsi" + &soc { #address-cells = <1>; #size-cells = <1>; @@ -399,4 +406,6 @@ crypto@300000 { fsl,iommu-parent = <&pamu4>; }; + +/include/ "qoriq-bman1.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index 15ae462e758f..5cc01be5b152 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -1,7 +1,7 @@ /* * T1040 Silicon/SoC Device Tree Source (post include) * - * Copyright 2013 Freescale Semiconductor Inc. + * Copyright 2013 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &ifc { #address-cells = <2>; #size-cells = <1>; @@ -218,6 +223,63 @@ }; }; +&bportals { + #address-cells = <0x1>; + #size-cells = <0x1>; + compatible = "simple-bus"; + + bman-portal@0 { + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x1000000 0x1000>; + interrupts = <105 2 0 0>; + }; + bman-portal@4000 { + compatible = "fsl,bman-portal"; + reg = <0x4000 0x4000>, <0x1001000 0x1000>; + interrupts = <107 2 0 0>; + }; + bman-portal@8000 { + compatible = "fsl,bman-portal"; + reg = <0x8000 0x4000>, <0x1002000 0x1000>; + interrupts = <109 2 0 0>; + }; + bman-portal@c000 { + compatible = "fsl,bman-portal"; + reg = <0xc000 0x4000>, <0x1003000 0x1000>; + interrupts = <111 2 0 0>; + }; + bman-portal@10000 { + compatible = "fsl,bman-portal"; + reg = <0x10000 0x4000>, <0x1004000 0x1000>; + interrupts = <113 2 0 0>; + }; + bman-portal@14000 { + compatible = "fsl,bman-portal"; + reg = <0x14000 0x4000>, <0x1005000 0x1000>; + interrupts = <115 2 0 0>; + }; + bman-portal@18000 { + compatible = "fsl,bman-portal"; + reg = <0x18000 0x4000>, <0x1006000 0x1000>; + interrupts = <117 2 0 0>; + }; + bman-portal@1c000 { + compatible = "fsl,bman-portal"; + reg = <0x1c000 0x4000>, <0x1007000 0x1000>; + interrupts = <119 2 0 0>; + }; + bman-portal@20000 { + compatible = "fsl,bman-portal"; + reg = <0x20000 0x4000>, <0x1008000 0x1000>; + interrupts = <121 2 0 0>; + }; + bman-portal@24000 { + compatible = "fsl,bman-portal"; + reg = <0x24000 0x4000>, <0x1009000 0x1000>; + interrupts = <123 2 0 0>; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; @@ -401,4 +463,5 @@ fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */ }; /include/ "qoriq-sec5.0-0.dtsi" +/include/ "qoriq-bman1.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index 1ce91e3485a9..86bdaf6cbd14 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -1,7 +1,7 @@ /* * T2081 Silicon/SoC Device Tree Source (post include) * - * Copyright 2013 Freescale Semiconductor Inc. + * Copyright 2013 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &ifc { #address-cells = <2>; #size-cells = <1>; @@ -224,6 +229,103 @@ }; }; +&bportals { + #address-cells = <0x1>; + #size-cells = <0x1>; + compatible = "simple-bus"; + + bman-portal@0 { + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x1000000 0x1000>; + interrupts = <105 2 0 0>; + }; + bman-portal@4000 { + compatible = "fsl,bman-portal"; + reg = <0x4000 0x4000>, <0x1001000 0x1000>; + interrupts = <107 2 0 0>; + }; + bman-portal@8000 { + compatible = "fsl,bman-portal"; + reg = <0x8000 0x4000>, <0x1002000 0x1000>; + interrupts = <109 2 0 0>; + }; + bman-portal@c000 { + compatible = "fsl,bman-portal"; + reg = <0xc000 0x4000>, <0x1003000 0x1000>; + interrupts = <111 2 0 0>; + }; + bman-portal@10000 { + compatible = "fsl,bman-portal"; + reg = <0x10000 0x4000>, <0x1004000 0x1000>; + interrupts = <113 2 0 0>; + }; + bman-portal@14000 { + compatible = "fsl,bman-portal"; + reg = <0x14000 0x4000>, <0x1005000 0x1000>; + interrupts = <115 2 0 0>; + }; + bman-portal@18000 { + compatible = "fsl,bman-portal"; + reg = <0x18000 0x4000>, <0x1006000 0x1000>; + interrupts = <117 2 0 0>; + }; + bman-portal@1c000 { + compatible = "fsl,bman-portal"; + reg = <0x1c000 0x4000>, <0x1007000 0x1000>; + interrupts = <119 2 0 0>; + }; + bman-portal@20000 { + compatible = "fsl,bman-portal"; + reg = <0x20000 0x4000>, <0x1008000 0x1000>; + interrupts = <121 2 0 0>; + }; + bman-portal@24000 { + compatible = "fsl,bman-portal"; + reg = <0x24000 0x4000>, <0x1009000 0x1000>; + interrupts = <123 2 0 0>; + }; + bman-portal@28000 { + compatible = "fsl,bman-portal"; + reg = <0x28000 0x4000>, <0x100a000 0x1000>; + interrupts = <125 2 0 0>; + }; + bman-portal@2c000 { + compatible = "fsl,bman-portal"; + reg = <0x2c000 0x4000>, <0x100b000 0x1000>; + interrupts = <127 2 0 0>; + }; + bman-portal@30000 { + compatible = "fsl,bman-portal"; + reg = <0x30000 0x4000>, <0x100c000 0x1000>; + interrupts = <129 2 0 0>; + }; + bman-portal@34000 { + compatible = "fsl,bman-portal"; + reg = <0x34000 0x4000>, <0x100d000 0x1000>; + interrupts = <131 2 0 0>; + }; + bman-portal@38000 { + compatible = "fsl,bman-portal"; + reg = <0x38000 0x4000>, <0x100e000 0x1000>; + interrupts = <133 2 0 0>; + }; + bman-portal@3c000 { + compatible = "fsl,bman-portal"; + reg = <0x3c000 0x4000>, <0x100f000 0x1000>; + interrupts = <135 2 0 0>; + }; + bman-portal@40000 { + compatible = "fsl,bman-portal"; + reg = <0x40000 0x4000>, <0x1010000 0x1000>; + interrupts = <137 2 0 0>; + }; + bman-portal@44000 { + compatible = "fsl,bman-portal"; + reg = <0x44000 0x4000>, <0x1011000 0x1000>; + interrupts = <139 2 0 0>; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; @@ -400,6 +502,7 @@ phy_type = "utmi"; }; /include/ "qoriq-sec5.2-0.dtsi" +/include/ "qoriq-bman1.dtsi" L2_1: l2-cache-controller@c20000 { /* Cluster 0 L2 cache */ diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi index 0e96fcabe812..4d4f25895d8c 100644 --- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -1,7 +1,7 @@ /* * T4240 Silicon/SoC Device Tree Source (post include) * - * Copyright 2012 Freescale Semiconductor Inc. + * Copyright 2012 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -32,6 +32,11 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +&bman_fbpr { + compatible = "fsl,bman-fbpr"; + alloc-ranges = <0 0 0x10000 0>; +}; + &ifc { #address-cells = <2>; #size-cells = <1>; @@ -294,6 +299,263 @@ }; }; +&bportals { + #address-cells = <0x1>; + #size-cells = <0x1>; + compatible = "simple-bus"; + + bman-portal@0 { + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x1000000 0x1000>; + interrupts = <105 2 0 0>; + }; + bman-portal@4000 { + compatible = "fsl,bman-portal"; + reg = <0x4000 0x4000>, <0x1001000 0x1000>; + interrupts = <107 2 0 0>; + }; + bman-portal@8000 { + compatible = "fsl,bman-portal"; + reg = <0x8000 0x4000>, <0x1002000 0x1000>; + interrupts = <109 2 0 0>; + }; + bman-portal@c000 { + compatible = "fsl,bman-portal"; + reg = <0xc000 0x4000>, <0x1003000 0x1000>; + interrupts = <111 2 0 0>; + }; + bman-portal@10000 { + compatible = "fsl,bman-portal"; + reg = <0x10000 0x4000>, <0x1004000 0x1000>; + interrupts = <113 2 0 0>; + }; + bman-portal@14000 { + compatible = "fsl,bman-portal"; + reg = <0x14000 0x4000>, <0x1005000 0x1000>; + interrupts = <115 2 0 0>; + }; + bman-portal@18000 { + compatible = "fsl,bman-portal"; + reg = <0x18000 0x4000>, <0x1006000 0x1000>; + interrupts = <117 2 0 0>; + }; + bman-portal@1c000 { + compatible = "fsl,bman-portal"; + reg = <0x1c000 0x4000>, <0x1007000 0x1000>; + interrupts = <119 2 0 0>; + }; + bman-portal@20000 { + compatible = "fsl,bman-portal"; + reg = <0x20000 0x4000>, <0x1008000 0x1000>; + interrupts = <121 2 0 0>; + }; + bman-portal@24000 { + compatible = "fsl,bman-portal"; + reg = <0x24000 0x4000>, <0x1009000 0x1000>; + interrupts = <123 2 0 0>; + }; + bman-portal@28000 { + compatible = "fsl,bman-portal"; + reg = <0x28000 0x4000>, <0x100a000 0x1000>; + interrupts = <125 2 0 0>; + }; + bman-portal@2c000 { + compatible = "fsl,bman-portal"; + reg = <0x2c000 0x4000>, <0x100b000 0x1000>; + interrupts = <127 2 0 0>; + }; + bman-portal@30000 { + compatible = "fsl,bman-portal"; + reg = <0x30000 0x4000>, <0x100c000 0x1000>; + interrupts = <129 2 0 0>; + }; + bman-portal@34000 { + compatible = "fsl,bman-portal"; + reg = <0x34000 0x4000>, <0x100d000 0x1000>; + interrupts = <131 2 0 0>; + }; + bman-portal@38000 { + compatible = "fsl,bman-portal"; + reg = <0x38000 0x4000>, <0x100e000 0x1000>; + interrupts = <133 2 0 0>; + }; + bman-portal@3c000 { + compatible = "fsl,bman-portal"; + reg = <0x3c000 0x4000>, <0x100f000 0x1000>; + interrupts = <135 2 0 0>; + }; + bman-portal@40000 { + compatible = "fsl,bman-portal"; + reg = <0x40000 0x4000>, <0x1010000 0x1000>; + interrupts = <137 2 0 0>; + }; + bman-portal@44000 { + compatible = "fsl,bman-portal"; + reg = <0x44000 0x4000>, <0x1011000 0x1000>; + interrupts = <139 2 0 0>; + }; + bman-portal@48000 { + compatible = "fsl,bman-portal"; + reg = <0x48000 0x4000>, <0x1012000 0x1000>; + interrupts = <141 2 0 0>; + }; + bman-portal@4c000 { + compatible = "fsl,bman-portal"; + reg = <0x4c000 0x4000>, <0x1013000 0x1000>; + interrupts = <143 2 0 0>; + }; + bman-portal@50000 { + compatible = "fsl,bman-portal"; + reg = <0x50000 0x4000>, <0x1014000 0x1000>; + interrupts = <145 2 0 0>; + }; + bman-portal@54000 { + compatible = "fsl,bman-portal"; + reg = <0x54000 0x4000>, <0x1015000 0x1000>; + interrupts = <147 2 0 0>; + }; + bman-portal@58000 { + compatible = "fsl,bman-portal"; + reg = <0x58000 0x4000>, <0x1016000 0x1000>; + interrupts = <149 2 0 0>; + }; + bman-portal@5c000 { + compatible = "fsl,bman-portal"; + reg = <0x5c000 0x4000>, <0x1017000 0x1000>; + interrupts = <151 2 0 0>; + }; + bman-portal@60000 { + compatible = "fsl,bman-portal"; + reg = <0x60000 0x4000>, <0x1018000 0x1000>; + interrupts = <153 2 0 0>; + }; + bman-portal@64000 { + compatible = "fsl,bman-portal"; + reg = <0x64000 0x4000>, <0x1019000 0x1000>; + interrupts = <155 2 0 0>; + }; + bman-portal@68000 { + compatible = "fsl,bman-portal"; + reg = <0x68000 0x4000>, <0x101a000 0x1000>; + interrupts = <157 2 0 0>; + }; + bman-portal@6c000 { + compatible = "fsl,bman-portal"; + reg = <0x6c000 0x4000>, <0x101b000 0x1000>; + interrupts = <159 2 0 0>; + }; + bman-portal@70000 { + compatible = "fsl,bman-portal"; + reg = <0x70000 0x4000>, <0x101c000 0x1000>; + interrupts = <161 2 0 0>; + }; + bman-portal@74000 { + compatible = "fsl,bman-portal"; + reg = <0x74000 0x4000>, <0x101d000 0x1000>; + interrupts = <163 2 0 0>; + }; + bman-portal@78000 { + compatible = "fsl,bman-portal"; + reg = <0x78000 0x4000>, <0x101e000 0x1000>; + interrupts = <165 2 0 0>; + }; + bman-portal@7c000 { + compatible = "fsl,bman-portal"; + reg = <0x7c000 0x4000>, <0x101f000 0x1000>; + interrupts = <167 2 0 0>; + }; + bman-portal@80000 { + compatible = "fsl,bman-portal"; + reg = <0x80000 0x4000>, <0x1020000 0x1000>; + interrupts = <169 2 0 0>; + }; + bman-portal@84000 { + compatible = "fsl,bman-portal"; + reg = <0x84000 0x4000>, <0x1021000 0x1000>; + interrupts = <171 2 0 0>; + }; + bman-portal@88000 { + compatible = "fsl,bman-portal"; + reg = <0x88000 0x4000>, <0x1022000 0x1000>; + interrupts = <173 2 0 0>; + }; + bman-portal@8c000 { + compatible = "fsl,bman-portal"; + reg = <0x8c000 0x4000>, <0x1023000 0x1000>; + interrupts = <175 2 0 0>; + }; + bman-portal@90000 { + compatible = "fsl,bman-portal"; + reg = <0x90000 0x4000>, <0x1024000 0x1000>; + interrupts = <385 2 0 0>; + }; + bman-portal@94000 { + compatible = "fsl,bman-portal"; + reg = <0x94000 0x4000>, <0x1025000 0x1000>; + interrupts = <387 2 0 0>; + }; + bman-portal@98000 { + compatible = "fsl,bman-portal"; + reg = <0x98000 0x4000>, <0x1026000 0x1000>; + interrupts = <389 2 0 0>; + }; + bman-portal@9c000 { + compatible = "fsl,bman-portal"; + reg = <0x9c000 0x4000>, <0x1027000 0x1000>; + interrupts = <391 2 0 0>; + }; + bman-portal@a0000 { + compatible = "fsl,bman-portal"; + reg = <0xa0000 0x4000>, <0x1028000 0x1000>; + interrupts = <393 2 0 0>; + }; + bman-portal@a4000 { + compatible = "fsl,bman-portal"; + reg = <0xa4000 0x4000>, <0x1029000 0x1000>; + interrupts = <395 2 0 0>; + }; + bman-portal@a8000 { + compatible = "fsl,bman-portal"; + reg = <0xa8000 0x4000>, <0x102a000 0x1000>; + interrupts = <397 2 0 0>; + }; + bman-portal@ac000 { + compatible = "fsl,bman-portal"; + reg = <0xac000 0x4000>, <0x102b000 0x1000>; + interrupts = <399 2 0 0>; + }; + bman-portal@b0000 { + compatible = "fsl,bman-portal"; + reg = <0xb0000 0x4000>, <0x102c000 0x1000>; + interrupts = <401 2 0 0>; + }; + bman-portal@b4000 { + compatible = "fsl,bman-portal"; + reg = <0xb4000 0x4000>, <0x102d000 0x1000>; + interrupts = <403 2 0 0>; + }; + bman-portal@b8000 { + compatible = "fsl,bman-portal"; + reg = <0xb8000 0x4000>, <0x102e000 0x1000>; + interrupts = <405 2 0 0>; + }; + bman-portal@bc000 { + compatible = "fsl,bman-portal"; + reg = <0xbc000 0x4000>, <0x102f000 0x1000>; + interrupts = <407 2 0 0>; + }; + bman-portal@c0000 { + compatible = "fsl,bman-portal"; + reg = <0xc0000 0x4000>, <0x1030000 0x1000>; + interrupts = <409 2 0 0>; + }; + bman-portal@c4000 { + compatible = "fsl,bman-portal"; + reg = <0xc4000 0x4000>, <0x1031000 0x1000>; + interrupts = <411 2 0 0>; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; @@ -486,6 +748,7 @@ /include/ "qoriq-sata2-0.dtsi" /include/ "qoriq-sata2-1.dtsi" /include/ "qoriq-sec5.0-0.dtsi" +/include/ "qoriq-bman1.dtsi" L2_1: l2-cache-controller@c20000 { compatible = "fsl,t4240-l2-cache-controller"; diff --git a/arch/powerpc/boot/dts/kmcoge4.dts b/arch/powerpc/boot/dts/kmcoge4.dts index 89b4119f3b19..97e6d11d1e6d 100644 --- a/arch/powerpc/boot/dts/kmcoge4.dts +++ b/arch/powerpc/boot/dts/kmcoge4.dts @@ -25,10 +25,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/oca4080.dts b/arch/powerpc/boot/dts/oca4080.dts index 3d4c751d1608..eb76caae11d9 100644 --- a/arch/powerpc/boot/dts/oca4080.dts +++ b/arch/powerpc/boot/dts/oca4080.dts @@ -49,10 +49,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/p1023rdb.dts b/arch/powerpc/boot/dts/p1023rdb.dts index 0a06a88ddbd5..9236e3742a23 100644 --- a/arch/powerpc/boot/dts/p1023rdb.dts +++ b/arch/powerpc/boot/dts/p1023rdb.dts @@ -1,7 +1,7 @@ /* * P1023 RDB Device Tree Source * - * Copyright 2013 Freescale Semiconductor Inc. + * Copyright 2013 - 2014 Freescale Semiconductor Inc. * * Author: Chunhe Lan <Chunhe.Lan@freescale.com> * @@ -47,6 +47,21 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + + bportals: bman-portals@ff200000 { + ranges = <0x0 0xf 0xff200000 0x200000>; + }; + soc: soc@ff600000 { ranges = <0x0 0x0 0xff600000 0x200000>; @@ -228,7 +243,6 @@ 0x0 0x100000>; }; }; - }; /include/ "fsl/p1023si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts index d97ad74c7279..c1e69dc7188e 100644 --- a/arch/powerpc/boot/dts/p2041rdb.dts +++ b/arch/powerpc/boot/dts/p2041rdb.dts @@ -1,7 +1,7 @@ /* * P2041RDB Device Tree Source * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -45,10 +45,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts index 394ea9c943c9..2192fe94866d 100644 --- a/arch/powerpc/boot/dts/p3041ds.dts +++ b/arch/powerpc/boot/dts/p3041ds.dts @@ -1,7 +1,7 @@ /* * P3041DS Device Tree Source * - * Copyright 2010-2011 Freescale Semiconductor Inc. + * Copyright 2010 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -45,10 +45,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts index 1cf6148b8b05..fad441654642 100644 --- a/arch/powerpc/boot/dts/p4080ds.dts +++ b/arch/powerpc/boot/dts/p4080ds.dts @@ -1,7 +1,7 @@ /* * P4080DS Device Tree Source * - * Copyright 2009-2011 Freescale Semiconductor Inc. + * Copyright 2009 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -45,10 +45,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts index b7f3057cd894..7382636dc560 100644 --- a/arch/powerpc/boot/dts/p5020ds.dts +++ b/arch/powerpc/boot/dts/p5020ds.dts @@ -1,7 +1,7 @@ /* * P5020DS Device Tree Source * - * Copyright 2010-2011 Freescale Semiconductor Inc. + * Copyright 2010 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -45,10 +45,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/p5040ds.dts b/arch/powerpc/boot/dts/p5040ds.dts index 7e04bf487c04..35dabf5b6098 100644 --- a/arch/powerpc/boot/dts/p5040ds.dts +++ b/arch/powerpc/boot/dts/p5040ds.dts @@ -1,7 +1,7 @@ /* * P5040DS Device Tree Source * - * Copyright 2012 Freescale Semiconductor Inc. + * Copyright 2012 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -45,10 +45,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01008000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x200000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/t104xqds.dtsi index 234f4b596c5b..f7e9bfbeefc7 100644 --- a/arch/powerpc/boot/dts/t104xqds.dtsi +++ b/arch/powerpc/boot/dts/t104xqds.dtsi @@ -1,7 +1,7 @@ /* * T104xQDS Device Tree Source * - * Copyright 2013 Freescale Semiconductor Inc. + * Copyright 2013 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -38,6 +38,17 @@ #size-cells = <2>; interrupt-parent = <&mpic>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + ifc: localbus@ffe124000 { reg = <0xf 0xfe124000 0 0x2000>; ranges = <0 0 0xf 0xe8000000 0x08000000 @@ -77,6 +88,10 @@ ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/t104xrdb.dtsi b/arch/powerpc/boot/dts/t104xrdb.dtsi index 187add885cae..76e07a3f2ca8 100644 --- a/arch/powerpc/boot/dts/t104xrdb.dtsi +++ b/arch/powerpc/boot/dts/t104xrdb.dtsi @@ -33,6 +33,16 @@ */ / { + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; ifc: localbus@ffe124000 { reg = <0xf 0xfe124000 0 0x2000>; @@ -69,6 +79,10 @@ ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/t208xqds.dtsi b/arch/powerpc/boot/dts/t208xqds.dtsi index 59061834d54e..c42e07f4f648 100644 --- a/arch/powerpc/boot/dts/t208xqds.dtsi +++ b/arch/powerpc/boot/dts/t208xqds.dtsi @@ -1,7 +1,7 @@ /* * T2080/T2081 QDS Device Tree Source * - * Copyright 2013 Freescale Semiconductor Inc. + * Copyright 2013 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -39,6 +39,17 @@ #size-cells = <2>; interrupt-parent = <&mpic>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + ifc: localbus@ffe124000 { reg = <0xf 0xfe124000 0 0x2000>; ranges = <0 0 0xf 0xe8000000 0x08000000 @@ -78,6 +89,10 @@ ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; @@ -137,7 +152,7 @@ rtc@68 { compatible = "dallas,ds3232"; reg = <0x68>; - interrupts = <0x1 0x1 0 0>; + interrupts = <0xb 0x1 0 0>; }; }; diff --git a/arch/powerpc/boot/dts/t208xrdb.dtsi b/arch/powerpc/boot/dts/t208xrdb.dtsi index 1481e192e783..e1463b165d0e 100644 --- a/arch/powerpc/boot/dts/t208xrdb.dtsi +++ b/arch/powerpc/boot/dts/t208xrdb.dtsi @@ -39,6 +39,17 @@ #size-cells = <2>; interrupt-parent = <&mpic>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + ifc: localbus@ffe124000 { reg = <0xf 0xfe124000 0 0x2000>; ranges = <0 0 0xf 0xe8000000 0x08000000 @@ -79,6 +90,10 @@ ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/t4240qds.dts b/arch/powerpc/boot/dts/t4240qds.dts index 97683f6a2936..6df77766410b 100644 --- a/arch/powerpc/boot/dts/t4240qds.dts +++ b/arch/powerpc/boot/dts/t4240qds.dts @@ -1,7 +1,7 @@ /* * T4240QDS Device Tree Source * - * Copyright 2012 Freescale Semiconductor Inc. + * Copyright 2012 - 2014 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -100,10 +100,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/dts/t4240rdb.dts b/arch/powerpc/boot/dts/t4240rdb.dts index 53761d4e8c51..46049cf37f02 100644 --- a/arch/powerpc/boot/dts/t4240rdb.dts +++ b/arch/powerpc/boot/dts/t4240rdb.dts @@ -69,10 +69,25 @@ device_type = "memory"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + size = <0 0x1000000>; + alignment = <0 0x1000000>; + }; + }; + dcsr: dcsr@f00000000 { ranges = <0x00000000 0xf 0x00000000 0x01072000>; }; + bportals: bman-portals@ff4000000 { + ranges = <0x0 0xf 0xf4000000 0x2000000>; + }; + soc: soc@ffe000000 { ranges = <0x00000000 0xf 0xfe000000 0x1000000>; reg = <0xf 0xfe000000 0 0x00001000>; diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c index bb8b9b3505ee..535e8fd8900d 100644 --- a/arch/powerpc/boot/libfdt-wrapper.c +++ b/arch/powerpc/boot/libfdt-wrapper.c @@ -44,12 +44,12 @@ #define offset_devp(off) \ ({ \ - int _offset = (off); \ + unsigned long _offset = (off); \ check_err(_offset) ? NULL : (void *)(_offset+1); \ }) -#define devp_offset_find(devp) (((int)(devp))-1) -#define devp_offset(devp) (devp ? ((int)(devp))-1 : 0) +#define devp_offset_find(devp) (((unsigned long)(devp))-1) +#define devp_offset(devp) (devp ? ((unsigned long)(devp))-1 : 0) static void *fdt; static void *buf; /* = NULL */ diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index c89fdb1b80e1..8dcd744e5728 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -4,15 +4,17 @@ #include <types.h> #include <string.h> +#include "of.h" + typedef u32 uint32_t; typedef u64 uint64_t; typedef unsigned long uintptr_t; -#define fdt16_to_cpu(x) (x) -#define cpu_to_fdt16(x) (x) -#define fdt32_to_cpu(x) (x) -#define cpu_to_fdt32(x) (x) -#define fdt64_to_cpu(x) (x) -#define cpu_to_fdt64(x) (x) +#define fdt16_to_cpu(x) be16_to_cpu(x) +#define cpu_to_fdt16(x) cpu_to_be16(x) +#define fdt32_to_cpu(x) be32_to_cpu(x) +#define cpu_to_fdt32(x) cpu_to_be32(x) +#define fdt64_to_cpu(x) be64_to_cpu(x) +#define cpu_to_fdt64(x) cpu_to_be64(x) #endif /* _ARCH_POWERPC_BOOT_LIBFDT_ENV_H */ diff --git a/arch/powerpc/boot/of.h b/arch/powerpc/boot/of.h index c8c1750aba0c..5603320dce07 100644 --- a/arch/powerpc/boot/of.h +++ b/arch/powerpc/boot/of.h @@ -24,11 +24,19 @@ void of_console_init(void); typedef u32 __be32; #ifdef __LITTLE_ENDIAN__ +#define cpu_to_be16(x) swab16(x) +#define be16_to_cpu(x) swab16(x) #define cpu_to_be32(x) swab32(x) #define be32_to_cpu(x) swab32(x) +#define cpu_to_be64(x) swab64(x) +#define be64_to_cpu(x) swab64(x) #else +#define cpu_to_be16(x) (x) +#define be16_to_cpu(x) (x) #define cpu_to_be32(x) (x) #define be32_to_cpu(x) (x) +#define cpu_to_be64(x) (x) +#define be64_to_cpu(x) (x) #endif #define PROM_ERROR (-1u) diff --git a/arch/powerpc/boot/planetcore.c b/arch/powerpc/boot/planetcore.c index 0d8558a475bb..75117e63e6db 100644 --- a/arch/powerpc/boot/planetcore.c +++ b/arch/powerpc/boot/planetcore.c @@ -131,36 +131,3 @@ void planetcore_set_stdout_path(const char *table) setprop_str(chosen, "linux,stdout-path", path); } - -void planetcore_set_serial_speed(const char *table) -{ - void *chosen, *stdout; - u64 baud; - u32 baud32; - int len; - - chosen = finddevice("/chosen"); - if (!chosen) - return; - - len = getprop(chosen, "linux,stdout-path", prop_buf, MAX_PROP_LEN); - if (len <= 0) - return; - - stdout = finddevice(prop_buf); - if (!stdout) { - printf("planetcore_set_serial_speed: " - "Bad /chosen/linux,stdout-path.\r\n"); - - return; - } - - if (!planetcore_get_decimal(table, PLANETCORE_KEY_SERIAL_BAUD, - &baud)) { - printf("planetcore_set_serial_speed: No SB tag.\r\n"); - return; - } - - baud32 = baud; - setprop(stdout, "current-speed", &baud32, 4); -} diff --git a/arch/powerpc/boot/planetcore.h b/arch/powerpc/boot/planetcore.h index 0d4094f1771c..d53c733cc463 100644 --- a/arch/powerpc/boot/planetcore.h +++ b/arch/powerpc/boot/planetcore.h @@ -43,7 +43,4 @@ void planetcore_set_mac_addrs(const char *table); */ void planetcore_set_stdout_path(const char *table); -/* Sets the current-speed property in the serial node. */ -void planetcore_set_serial_speed(const char *table); - #endif diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index ae0f88ec4a32..3f50c27ed8f8 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -277,7 +277,7 @@ treeboot-iss4xx-mpic) platformo="$object/treeboot-iss4xx.o" ;; epapr) - platformo="$object/epapr.o $object/epapr-wrapper.o" + platformo="$object/pseries-head.o $object/epapr.o $object/epapr-wrapper.o" link_address='0x20000000' pie=-pie ;; diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 9788b3c2d563..9227b517560a 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -28,7 +28,6 @@ CONFIG_PS3_ROM=m CONFIG_PS3_FLASH=m CONFIG_PS3_LPM=m CONFIG_PPC_IBM_CELL_BLADE=y -CONFIG_PPC_CELLEB=y CONFIG_RTAS_FLASH=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y @@ -113,7 +112,6 @@ CONFIG_IDE=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_AEC62XX=y CONFIG_BLK_DEV_SIIMAGE=y -CONFIG_BLK_DEV_CELLEB=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y @@ -156,7 +154,6 @@ CONFIG_SERIAL_TXX9_NR_UARTS=2 CONFIG_SERIAL_TXX9_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_HVC_RTAS=y -CONFIG_HVC_BEAT=y CONFIG_IPMI_HANDLER=m CONFIG_IPMI_DEVICE_INTERFACE=m CONFIG_IPMI_SI=m diff --git a/arch/powerpc/configs/celleb_defconfig b/arch/powerpc/configs/celleb_defconfig deleted file mode 100644 index ff454dcd2dd3..000000000000 --- a/arch/powerpc/configs/celleb_defconfig +++ /dev/null @@ -1,152 +0,0 @@ -CONFIG_PPC64=y -CONFIG_TUNE_CELL=y -CONFIG_ALTIVEC=y -CONFIG_SMP=y -CONFIG_NR_CPUS=4 -CONFIG_SYSVIPC=y -CONFIG_FHANDLE=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=15 -CONFIG_BLK_DEV_INITRD=y -# CONFIG_COMPAT_BRK is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_PARTITION_ADVANCED=y -# CONFIG_PPC_POWERNV is not set -# CONFIG_PPC_PSERIES is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_CELLEB=y -CONFIG_SPU_FS=y -# CONFIG_CBE_THERM is not set -CONFIG_UDBG_RTAS_CONSOLE=y -# CONFIG_RTAS_PROC is not set -CONFIG_BINFMT_MISC=m -CONFIG_KEXEC=y -CONFIG_NUMA=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_SYN_COOKIES=y -CONFIG_IPV6=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_TUNNEL=m -CONFIG_NETFILTER=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=m -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_CELLEB=y -CONFIG_SCSI=m -# CONFIG_SCSI_PROC_FS is not set -CONFIG_BLK_DEV_SD=m -CONFIG_BLK_DEV_SR=m -CONFIG_CHR_DEV_SG=m -CONFIG_MD=y -CONFIG_BLK_DEV_MD=m -CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m -CONFIG_MD_RAID1=m -CONFIG_BLK_DEV_DM=m -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m -CONFIG_NETDEVICES=y -CONFIG_SPIDER_NET=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set -# CONFIG_LEGACY_PTYS is not set -CONFIG_SERIAL_NONSTANDARD=y -CONFIG_SERIAL_TXX9_NR_UARTS=3 -CONFIG_SERIAL_TXX9_CONSOLE=y -CONFIG_HVC_RTAS=y -CONFIG_HVC_BEAT=y -# CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y -CONFIG_I2C=y -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_USB_HIDDEV=y -CONFIG_USB=y -CONFIG_USB_MON=y -CONFIG_USB_EHCI_HCD=m -# CONFIG_USB_EHCI_HCD_PPC_OF is not set -CONFIG_USB_OHCI_HCD=m -CONFIG_USB_STORAGE=m -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT2_FS_XIP=y -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_HUGETLBFS=y -CONFIG_NFS_FS=m -CONFIG_NFS_V3_ACL=y -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -CONFIG_NFSD_V3_ACL=y -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_LIBCRC32C=m -CONFIG_DEBUG_FS=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_XMON=y -CONFIG_XMON_DEFAULT=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index ca7957b09a3c..37659937bd12 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -99,6 +99,8 @@ CONFIG_E1000E=y CONFIG_AT803X_PHY=y CONFIG_VITESSE_PHY=y CONFIG_FIXED_PHY=y +CONFIG_MDIO_BUS_MUX_GPIO=y +CONFIG_MDIO_BUS_MUX_MMIOREG=y # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -114,11 +116,14 @@ CONFIG_NVRAM=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y +CONFIG_I2C_MUX=y +CONFIG_I2C_MUX_PCA954x=y CONFIG_SPI=y CONFIG_SPI_GPIO=y CONFIG_SPI_FSL_SPI=y CONFIG_SPI_FSL_ESPI=y -# CONFIG_HWMON is not set +CONFIG_SENSORS_LM90=y +CONFIG_SENSORS_INA2XX=y CONFIG_USB_HID=m CONFIG_USB=y CONFIG_USB_MON=y diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index 04737aaa8b6b..33cd1df818ad 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -12,6 +12,10 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_SCHED=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_KALLSYMS_ALL=y @@ -75,6 +79,10 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 CONFIG_EEPROM_LEGACY=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y CONFIG_ATA=y CONFIG_SATA_FSL=y CONFIG_SATA_SIL24=y @@ -85,6 +93,8 @@ CONFIG_FSL_XGMAC_MDIO=y CONFIG_E1000E=y CONFIG_VITESSE_PHY=y CONFIG_FIXED_PHY=y +CONFIG_MDIO_BUS_MUX_GPIO=y +CONFIG_MDIO_BUS_MUX_MMIOREG=y CONFIG_INPUT_FF_MEMLESS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -99,11 +109,14 @@ CONFIG_SERIAL_8250_RSA=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y +CONFIG_I2C_MUX=y +CONFIG_I2C_MUX_PCA954x=y CONFIG_SPI=y CONFIG_SPI_GPIO=y CONFIG_SPI_FSL_SPI=y CONFIG_SPI_FSL_ESPI=y -# CONFIG_HWMON is not set +CONFIG_SENSORS_LM90=y +CONFIG_SENSORS_INA2XX=y CONFIG_USB_HID=m CONFIG_USB=y CONFIG_USB_MON=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index 8535c343dd57..6ecf7bdbc2f9 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -150,8 +150,7 @@ CONFIG_SPI=y CONFIG_SPI_FSL_SPI=y CONFIG_SPI_FSL_ESPI=y CONFIG_GPIO_MPC8XXX=y -CONFIG_HWMON=m -CONFIG_SENSORS_LM90=m +CONFIG_SENSORS_LM90=y CONFIG_FB=y CONFIG_FB_FSL_DIU=y # CONFIG_VGA_CONSOLE is not set diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index c45ad2e01b0c..b6c7111ea913 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -143,7 +143,7 @@ CONFIG_SPI=y CONFIG_SPI_FSL_SPI=y CONFIG_SPI_FSL_ESPI=y CONFIG_GPIO_MPC8XXX=y -# CONFIG_HWMON is not set +CONFIG_SENSORS_LM90=y CONFIG_FB=y CONFIG_FB_FSL_DIU=y # CONFIG_VGA_CONSOLE is not set diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 3315c9f0828a..aad501ae3834 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -36,7 +36,6 @@ CONFIG_PS3_ROM=m CONFIG_PS3_FLASH=m CONFIG_PS3_LPM=m CONFIG_PPC_IBM_CELL_BLADE=y -CONFIG_PPC_CELLEB=y CONFIG_PPC_CELL_QPACE=y CONFIG_RTAS_FLASH=m CONFIG_IBMEBUS=y @@ -89,7 +88,6 @@ CONFIG_IDE=y CONFIG_BLK_DEV_IDECD=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_AMD74XX=y -CONFIG_BLK_DEV_CELLEB=y CONFIG_BLK_DEV_IDE_PMAC=y CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y CONFIG_BLK_DEV_SD=y @@ -196,7 +194,6 @@ CONFIG_SERIAL_TXX9_CONSOLE=y CONFIG_SERIAL_JSM=m CONFIG_HVC_CONSOLE=y CONFIG_HVC_RTAS=y -CONFIG_HVC_BEAT=y CONFIG_HVCS=m CONFIG_VIRTIO_CONSOLE=m CONFIG_IBM_BSR=m diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 382b28e364dc..4b87205c230c 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -1,6 +1,8 @@ - generic-y += clkdev.h +generic-y += div64.h +generic-y += irq_regs.h generic-y += irq_work.h +generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += rwsem.h diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index bde531103638..0cc6eedc4780 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -30,8 +30,6 @@ static inline int arch_has_random(void) return !!ppc_md.get_random_long; } -int powernv_get_random_long(unsigned long *v); - static inline int arch_get_random_seed_long(unsigned long *v) { return 0; @@ -47,4 +45,13 @@ static inline int arch_has_random_seed(void) #endif /* CONFIG_ARCH_RANDOM */ +#ifdef CONFIG_PPC_POWERNV +int powernv_hwrng_present(void); +int powernv_get_random_long(unsigned long *v); +int powernv_get_random_real_mode(unsigned long *v); +#else +static inline int powernv_hwrng_present(void) { return 0; } +static inline int powernv_get_random_real_mode(unsigned long *v) { return 0; } +#endif + #endif /* _ASM_POWERPC_ARCHRANDOM_H */ diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 34a05a1a990b..0dc42c5082b7 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -76,9 +76,6 @@ extern void _set_L3CR(unsigned long); #define _set_L3CR(val) do { } while(0) #endif -extern void cacheable_memzero(void *p, unsigned int nb); -extern void *cacheable_memcpy(void *, const void *, unsigned int); - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_CACHE_H */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 5cf5a6d10685..6367b8347dad 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -100,7 +100,7 @@ struct cpu_spec { /* * Processor specific routine to flush tlbs. */ - void (*flush_tlb)(unsigned long inval_selector); + void (*flush_tlb)(unsigned int action); }; @@ -114,6 +114,12 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start, extern const char *powerpc_base_platform; +/* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */ +enum { + TLB_INVAL_SCOPE_GLOBAL = 0, /* invalidate all TLBs */ + TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ +}; + #endif /* __ASSEMBLY__ */ /* CPU kernel features */ diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 4c8ad592ae33..5be6c4753667 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -25,7 +25,7 @@ extern cpumask_t threads_core_mask; #define threads_per_core 1 #define threads_per_subcore 1 #define threads_shift 0 -#define threads_core_mask (CPU_MASK_CPU0) +#define threads_core_mask (*get_cpu_mask(0)) #endif /* cpu_thread_mask_to_cores - Return a cpumask of one per cores diff --git a/arch/powerpc/include/asm/dbdma.h b/arch/powerpc/include/asm/dbdma.h index e23f07e73cb3..6c69836b4ec2 100644 --- a/arch/powerpc/include/asm/dbdma.h +++ b/arch/powerpc/include/asm/dbdma.h @@ -42,12 +42,12 @@ struct dbdma_regs { * DBDMA command structure. These fields are all little-endian! */ struct dbdma_cmd { - unsigned short req_count; /* requested byte transfer count */ - unsigned short command; /* command word (has bit-fields) */ - unsigned int phy_addr; /* physical data address */ - unsigned int cmd_dep; /* command-dependent field */ - unsigned short res_count; /* residual count after completion */ - unsigned short xfer_status; /* transfer status */ + __le16 req_count; /* requested byte transfer count */ + __le16 command; /* command word (has bit-fields) */ + __le32 phy_addr; /* physical data address */ + __le32 cmd_dep; /* command-dependent field */ + __le16 res_count; /* residual count after completion */ + __le16 xfer_status; /* transfer status */ }; /* DBDMA command values in command field */ diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 7d2e6235726d..4efc11dacb98 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -31,7 +31,7 @@ typedef struct { static inline bool dcr_map_ok_native(dcr_host_native_t host) { - return 1; + return true; } #define dcr_map_native(dev, dcr_n, dcr_c) \ diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 38faeded7d59..9f1371bab5fc 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -8,6 +8,9 @@ struct dma_map_ops; struct device_node; +#ifdef CONFIG_PPC64 +struct pci_dn; +#endif /* * Arch extensions to struct device. @@ -34,6 +37,9 @@ struct dev_archdata { #ifdef CONFIG_SWIOTLB dma_addr_t max_direct_dma_addr; #endif +#ifdef CONFIG_PPC64 + struct pci_dn *pci_data; +#endif #ifdef CONFIG_EEH struct eeh_dev *edev; #endif diff --git a/arch/powerpc/include/asm/div64.h b/arch/powerpc/include/asm/div64.h deleted file mode 100644 index 6cd978cefb28..000000000000 --- a/arch/powerpc/include/asm/div64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/div64.h> diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 894d538f3567..9103687b0436 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -191,11 +191,11 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) struct dev_archdata *sd = &dev->archdata; if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr) - return 0; + return false; #endif if (!dev->dma_mask) - return 0; + return false; return addr + size - 1 <= *dev->dma_mask; } diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 55abfd09e47f..a52db28ecc1e 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -29,7 +29,7 @@ struct pci_dev; struct pci_bus; -struct device_node; +struct pci_dn; #ifdef CONFIG_EEH @@ -136,14 +136,14 @@ struct eeh_dev { struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ struct pci_controller *phb; /* Associated PHB */ - struct device_node *dn; /* Associated device node */ + struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ struct pci_bus *bus; /* PCI bus for partial hotplug */ }; -static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev) +static inline struct pci_dn *eeh_dev_to_pdn(struct eeh_dev *edev) { - return edev ? edev->dn : NULL; + return edev ? edev->pdn : NULL; } static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev) @@ -200,8 +200,7 @@ struct eeh_ops { char *name; int (*init)(void); int (*post_init)(void); - void* (*of_probe)(struct device_node *dn, void *flag); - int (*dev_probe)(struct pci_dev *dev, void *flag); + void* (*probe)(struct pci_dn *pdn, void *data); int (*set_option)(struct eeh_pe *pe, int option); int (*get_pe_addr)(struct eeh_pe *pe); int (*get_state)(struct eeh_pe *pe, int *state); @@ -211,10 +210,10 @@ struct eeh_ops { int (*configure_bridge)(struct eeh_pe *pe); int (*err_inject)(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); - int (*read_config)(struct device_node *dn, int where, int size, u32 *val); - int (*write_config)(struct device_node *dn, int where, int size, u32 val); + int (*read_config)(struct pci_dn *pdn, int where, int size, u32 *val); + int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); - int (*restore_config)(struct device_node *dn); + int (*restore_config)(struct pci_dn *pdn); }; extern int eeh_subsystem_flags; @@ -272,7 +271,7 @@ void eeh_pe_restore_bars(struct eeh_pe *pe); const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); -void *eeh_dev_init(struct device_node *dn, void *data); +void *eeh_dev_init(struct pci_dn *pdn, void *data); void eeh_dev_phb_init_dynamic(struct pci_controller *phb); int eeh_init(void); int __init eeh_ops_register(struct eeh_ops *ops); @@ -280,8 +279,8 @@ int __exit eeh_ops_unregister(const char *name); int eeh_check_failure(const volatile void __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); void eeh_addr_cache_build(void); -void eeh_add_device_early(struct device_node *); -void eeh_add_device_tree_early(struct device_node *); +void eeh_add_device_early(struct pci_dn *); +void eeh_add_device_tree_early(struct pci_dn *); void eeh_add_device_late(struct pci_dev *); void eeh_add_device_tree_late(struct pci_bus *); void eeh_add_sysfs_files(struct pci_bus *); @@ -323,7 +322,7 @@ static inline int eeh_init(void) return 0; } -static inline void *eeh_dev_init(struct device_node *dn, void *data) +static inline void *eeh_dev_init(struct pci_dn *pdn, void *data) { return NULL; } @@ -339,9 +338,9 @@ static inline int eeh_check_failure(const volatile void __iomem *token) static inline void eeh_addr_cache_build(void) { } -static inline void eeh_add_device_early(struct device_node *dn) { } +static inline void eeh_add_device_early(struct pci_dn *pdn) { } -static inline void eeh_add_device_tree_early(struct device_node *dn) { } +static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { } static inline void eeh_add_device_late(struct pci_dev *dev) { } diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 681bc0314b6b..e05808a328db 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -42,7 +42,7 @@ #define FW_FEATURE_SPLPAR ASM_CONST(0x0000000000100000) #define FW_FEATURE_LPAR ASM_CONST(0x0000000000400000) #define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000) -#define FW_FEATURE_BEAT ASM_CONST(0x0000000001000000) +/* Free ASM_CONST(0x0000000001000000) */ #define FW_FEATURE_CMO ASM_CONST(0x0000000002000000) #define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000) #define FW_FEATURE_XCMO ASM_CONST(0x0000000008000000) @@ -75,8 +75,6 @@ enum { FW_FEATURE_POWERNV_ALWAYS = 0, FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, - FW_FEATURE_CELLEB_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_BEAT, - FW_FEATURE_CELLEB_ALWAYS = 0, FW_FEATURE_NATIVE_POSSIBLE = 0, FW_FEATURE_NATIVE_ALWAYS = 0, FW_FEATURE_POSSIBLE = @@ -89,9 +87,6 @@ enum { #ifdef CONFIG_PPC_PS3 FW_FEATURE_PS3_POSSIBLE | #endif -#ifdef CONFIG_PPC_CELLEB - FW_FEATURE_CELLEB_POSSIBLE | -#endif #ifdef CONFIG_PPC_NATIVE FW_FEATURE_NATIVE_ALWAYS | #endif @@ -106,9 +101,6 @@ enum { #ifdef CONFIG_PPC_PS3 FW_FEATURE_PS3_ALWAYS & #endif -#ifdef CONFIG_PPC_CELLEB - FW_FEATURE_CELLEB_ALWAYS & -#endif #ifdef CONFIG_PPC_NATIVE FW_FEATURE_NATIVE_ALWAYS & #endif diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f1ea5972f6ec..1e27d6338565 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -29,6 +29,7 @@ #include <linux/bitops.h> #include <asm/machdep.h> #include <asm/types.h> +#include <asm/pci-bridge.h> #define IOMMU_PAGE_SHIFT_4K 12 #define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K) @@ -78,6 +79,9 @@ struct iommu_table { struct iommu_group *it_group; #endif void (*set_bypass)(struct iommu_table *tbl, bool enable); +#ifdef CONFIG_PPC_POWERNV + void *data; +#endif }; /* Pure 2^n version of get_order */ @@ -169,7 +173,7 @@ extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, struct dma_attrs *attrs); extern void iommu_init_early_pSeries(void); -extern void iommu_init_early_dart(void); +extern void iommu_init_early_dart(struct pci_controller_ops *controller_ops); extern void iommu_init_early_pasemi(void); extern void alloc_dart_table(void); diff --git a/arch/powerpc/include/asm/irq_regs.h b/arch/powerpc/include/asm/irq_regs.h deleted file mode 100644 index ba94b51a0a70..000000000000 --- a/arch/powerpc/include/asm/irq_regs.h +++ /dev/null @@ -1,2 +0,0 @@ -#include <asm-generic/irq_regs.h> - diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 993090422690..b91e74a817d8 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -288,6 +288,9 @@ static inline bool kvmppc_supports_magic_page(struct kvm_vcpu *vcpu) return !is_kvmppc_hv_enabled(vcpu->kvm); } +extern int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu); +extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); + /* Magic register values loaded into r3 and r4 before the 'sc' assembly * instruction for the OSI hypercalls */ #define OSI_SC_MAGIC_R3 0x113724FA diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 2d81e202bdcc..3536d12eb798 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -85,6 +85,20 @@ static inline long try_lock_hpte(__be64 *hpte, unsigned long bits) return old == 0; } +static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v) +{ + hpte_v &= ~HPTE_V_HVLOCK; + asm volatile(PPC_RELEASE_BARRIER "" : : : "memory"); + hpte[0] = cpu_to_be64(hpte_v); +} + +/* Without barrier */ +static inline void __unlock_hpte(__be64 *hpte, unsigned long hpte_v) +{ + hpte_v &= ~HPTE_V_HVLOCK; + hpte[0] = cpu_to_be64(hpte_v); +} + static inline int __hpte_actual_psize(unsigned int lp, int psize) { int i, shift; @@ -281,40 +295,37 @@ static inline int hpte_cache_flags_ok(unsigned long ptel, unsigned long io_type) /* * If it's present and writable, atomically set dirty and referenced bits and - * return the PTE, otherwise return 0. If we find a transparent hugepage - * and if it is marked splitting we return 0; + * return the PTE, otherwise return 0. */ -static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing, - unsigned int hugepage) +static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing) { pte_t old_pte, new_pte = __pte(0); while (1) { - old_pte = pte_val(*ptep); + /* + * Make sure we don't reload from ptep + */ + old_pte = READ_ONCE(*ptep); /* * wait until _PAGE_BUSY is clear then set it atomically */ - if (unlikely(old_pte & _PAGE_BUSY)) { + if (unlikely(pte_val(old_pte) & _PAGE_BUSY)) { cpu_relax(); continue; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* If hugepage and is trans splitting return None */ - if (unlikely(hugepage && - pmd_trans_splitting(pte_pmd(old_pte)))) - return __pte(0); -#endif /* If pte is not present return None */ - if (unlikely(!(old_pte & _PAGE_PRESENT))) + if (unlikely(!(pte_val(old_pte) & _PAGE_PRESENT))) return __pte(0); new_pte = pte_mkyoung(old_pte); if (writing && pte_write(old_pte)) new_pte = pte_mkdirty(new_pte); - if (old_pte == __cmpxchg_u64((unsigned long *)ptep, old_pte, - new_pte)) + if (pte_val(old_pte) == __cmpxchg_u64((unsigned long *)ptep, + pte_val(old_pte), + pte_val(new_pte))) { break; + } } return new_pte; } @@ -335,7 +346,7 @@ static inline bool hpte_read_permission(unsigned long pp, unsigned long key) { if (key) return PP_RWRX <= pp && pp <= PP_RXRX; - return 1; + return true; } static inline bool hpte_write_permission(unsigned long pp, unsigned long key) @@ -373,7 +384,7 @@ static inline bool slot_is_aligned(struct kvm_memory_slot *memslot, unsigned long mask = (pagesize >> PAGE_SHIFT) - 1; if (pagesize <= PAGE_SIZE) - return 1; + return true; return !(memslot->base_gfn & mask) && !(memslot->npages & mask); } @@ -422,6 +433,10 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) return rcu_dereference_raw_notrace(kvm->memslots); } +extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); + +extern void kvmhv_rm_send_ipi(int cpu); + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 8ef05121d3cd..a193a13cf08b 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -227,10 +227,8 @@ struct kvm_arch { unsigned long host_sdr1; int tlbie_lock; unsigned long lpcr; - unsigned long rmor; - struct kvm_rma_info *rma; unsigned long vrma_slb_v; - int rma_setup_done; + int hpte_setup_done; u32 hpt_order; atomic_t vcpus_running; u32 online_vcores; @@ -239,6 +237,8 @@ struct kvm_arch { atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; int hpt_cma_alloc; + struct dentry *debugfs_dir; + struct dentry *htab_dentry; #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE struct mutex hpt_mutex; @@ -263,18 +263,15 @@ struct kvm_arch { /* * Struct for a virtual core. - * Note: entry_exit_count combines an entry count in the bottom 8 bits - * and an exit count in the next 8 bits. This is so that we can - * atomically increment the entry count iff the exit count is 0 - * without taking the lock. + * Note: entry_exit_map combines a bitmap of threads that have entered + * in the bottom 8 bits and a bitmap of threads that have exited in the + * next 8 bits. This is so that we can atomically set the entry bit + * iff the exit map is 0 without taking a lock. */ struct kvmppc_vcore { int n_runnable; - int n_busy; int num_threads; - int entry_exit_count; - int n_woken; - int nap_count; + int entry_exit_map; int napping_threads; int first_vcpuid; u16 pcpu; @@ -299,13 +296,14 @@ struct kvmppc_vcore { ulong conferring_threads; }; -#define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) -#define VCORE_EXIT_COUNT(vc) ((vc)->entry_exit_count >> 8) +#define VCORE_ENTRY_MAP(vc) ((vc)->entry_exit_map & 0xff) +#define VCORE_EXIT_MAP(vc) ((vc)->entry_exit_map >> 8) +#define VCORE_IS_EXITING(vc) (VCORE_EXIT_MAP(vc) != 0) /* Values for vcore_state */ #define VCORE_INACTIVE 0 #define VCORE_SLEEPING 1 -#define VCORE_STARTING 2 +#define VCORE_PREEMPT 2 #define VCORE_RUNNING 3 #define VCORE_EXITING 4 @@ -368,6 +366,14 @@ struct kvmppc_slb { u8 base_page_size; /* MMU_PAGE_xxx */ }; +/* Struct used to accumulate timing information in HV real mode code */ +struct kvmhv_tb_accumulator { + u64 seqcount; /* used to synchronize access, also count * 2 */ + u64 tb_total; /* total time in timebase ticks */ + u64 tb_min; /* min time */ + u64 tb_max; /* max time */ +}; + # ifdef CONFIG_PPC_FSL_BOOK3E #define KVMPPC_BOOKE_IAC_NUM 2 #define KVMPPC_BOOKE_DAC_NUM 2 @@ -585,7 +591,7 @@ struct kvm_vcpu_arch { pgd_t *pgdir; u8 io_gpr; /* GPR used as IO source/target */ - u8 mmio_is_bigendian; + u8 mmio_host_swabbed; u8 mmio_sign_extend; u8 osi_needed; u8 osi_enabled; @@ -656,6 +662,19 @@ struct kvm_vcpu_arch { u32 emul_inst; #endif + +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */ + u64 cur_tb_start; /* when it started */ + struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */ + struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */ + struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */ + struct kvmhv_tb_accumulator guest_time; /* guest execution */ + struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */ + + struct dentry *debugfs_dir; + struct dentry *debugfs_timings; +#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ }; #define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET] diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 46bf652c9169..b8475daad884 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -302,6 +302,8 @@ static inline bool is_kvmppc_hv_enabled(struct kvm *kvm) return kvm->arch.kvm_ops == kvmppc_hv_ops; } +extern int kvmppc_hwrng_present(void); + /* * Cuts out inst bits with ordering according to spec. * That means the leftmost bit is zero. All given bits are included. diff --git a/arch/powerpc/include/asm/local64.h b/arch/powerpc/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/powerpc/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index c8175a3fe560..ef8899432ae7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -103,9 +103,6 @@ struct machdep_calls { #endif #endif /* CONFIG_PPC64 */ - void (*pci_dma_dev_setup)(struct pci_dev *dev); - void (*pci_dma_bus_setup)(struct pci_bus *bus); - /* Platform set_dma_mask and dma_get_required_mask overrides */ int (*dma_set_mask)(struct device *dev, u64 dma_mask); u64 (*dma_get_required_mask)(struct device *dev); @@ -125,9 +122,8 @@ struct machdep_calls { unsigned int (*get_irq)(void); /* PCI stuff */ - /* Called after scanning the bus, before allocating resources */ + /* Called after allocating resources */ void (*pcibios_fixup)(void); - int (*pci_probe_mode)(struct pci_bus *); void (*pci_irq_fixup)(struct pci_dev *dev); int (*pcibios_root_bridge_prepare)(struct pci_host_bridge *bridge); @@ -237,18 +233,13 @@ struct machdep_calls { /* Called for each PCI bus in the system when it's probed */ void (*pcibios_fixup_bus)(struct pci_bus *); - /* Called when pci_enable_device() is called. Returns 0 to - * allow assignment/enabling of the device. */ - int (*pcibios_enable_device_hook)(struct pci_dev *); - /* Called after scan and before resource survey */ void (*pcibios_fixup_phb)(struct pci_controller *hose); - /* Called during PCI resource reassignment */ - resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); - - /* Reset the secondary bus of bridge */ - void (*pcibios_reset_secondary_bus)(struct pci_dev *dev); +#ifdef CONFIG_PCI_IOV + void (*pcibios_fixup_sriov)(struct pci_dev *pdev); + resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno); +#endif /* CONFIG_PCI_IOV */ /* Called to shutdown machine specific hardware not already controlled * by other drivers. diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 4f13c3ed7acf..1da6a81ce541 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -112,6 +112,7 @@ #define TLBIEL_INVAL_SET_SHIFT 12 #define POWER7_TLB_SETS 128 /* # sets in POWER7 TLB */ +#define POWER8_TLB_SETS 512 /* # sets in POWER8 TLB */ #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/mpc85xx.h b/arch/powerpc/include/asm/mpc85xx.h index 3bef74a9914b..213f3a81593d 100644 --- a/arch/powerpc/include/asm/mpc85xx.h +++ b/arch/powerpc/include/asm/mpc85xx.h @@ -61,6 +61,7 @@ #define SVR_T4240 0x824000 #define SVR_T4120 0x824001 #define SVR_T4160 0x824100 +#define SVR_T4080 0x824102 #define SVR_C291 0x850000 #define SVR_C292 0x850020 #define SVR_C293 0x850030 diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h index 754f93d208fa..98697611e7b3 100644 --- a/arch/powerpc/include/asm/mpic.h +++ b/arch/powerpc/include/asm/mpic.h @@ -34,10 +34,6 @@ #define MPIC_GREG_GCONF_BASE_MASK 0x000fffff #define MPIC_GREG_GCONF_MCK 0x08000000 #define MPIC_GREG_GLOBAL_CONF_1 0x00030 -#define MPIC_GREG_GLOBAL_CONF_1_SIE 0x08000000 -#define MPIC_GREG_GLOBAL_CONF_1_CLK_RATIO_MASK 0x70000000 -#define MPIC_GREG_GLOBAL_CONF_1_CLK_RATIO(r) \ - (((r) << 28) & MPIC_GREG_GLOBAL_CONF_1_CLK_RATIO_MASK) #define MPIC_GREG_VENDOR_0 0x00040 #define MPIC_GREG_VENDOR_1 0x00050 #define MPIC_GREG_VENDOR_2 0x00060 @@ -396,14 +392,7 @@ extern struct bus_type mpic_subsys; #define MPIC_REGSET_TSI108 MPIC_REGSET(1) /* Tsi108/109 PIC */ /* Get the version of primary MPIC */ -#ifdef CONFIG_MPIC extern u32 fsl_mpic_primary_get_version(void); -#else -static inline u32 fsl_mpic_primary_get_version(void) -{ - return 0; -} -#endif /* Allocate the controller structure and setup the linux irq descs * for the range if interrupts passed in. No HW initialization is @@ -496,11 +485,5 @@ extern unsigned int mpic_get_coreint_irq(void); /* Fetch Machine Check interrupt from primary mpic */ extern unsigned int mpic_get_mcirq(void); -/* Set the EPIC clock ratio */ -void mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio); - -/* Enable/Disable EPIC serial interrupt mode */ -void mpic_set_serial_int(struct mpic *mpic, int enable); - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MPIC_H */ diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h new file mode 100644 index 000000000000..ff1ccb375e60 --- /dev/null +++ b/arch/powerpc/include/asm/nmi.h @@ -0,0 +1,4 @@ +#ifndef _ASM_NMI_H +#define _ASM_NMI_H + +#endif /* _ASM_NMI_H */ diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index b0fe0fe4e626..09a518bb7c03 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -9,12 +9,43 @@ #ifndef _ASM_POWERPC_NVRAM_H #define _ASM_POWERPC_NVRAM_H - +#include <linux/types.h> #include <linux/errno.h> #include <linux/list.h> #include <uapi/asm/nvram.h> +/* + * Set oops header version to distinguish between old and new format header. + * lnx,oops-log partition max size is 4000, header version > 4000 will + * help in identifying new header. + */ +#define OOPS_HDR_VERSION 5000 + +struct err_log_info { + __be32 error_type; + __be32 seq_num; +}; + +struct nvram_os_partition { + const char *name; + int req_size; /* desired size, in bytes */ + int min_size; /* minimum acceptable size (0 means req_size) */ + long size; /* size of data portion (excluding err_log_info) */ + long index; /* offset of data portion of partition */ + bool os_partition; /* partition initialized by OS, not FW */ +}; + +struct oops_log_info { + __be16 version; + __be16 report_length; + __be64 timestamp; +} __attribute__((packed)); + +extern struct nvram_os_partition oops_log_partition; + #ifdef CONFIG_PPC_PSERIES +extern struct nvram_os_partition rtas_log_partition; + extern int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int err_seq); extern int nvram_read_error_log(char * buff, int length, @@ -50,6 +81,23 @@ extern void pmac_xpram_write(int xpaddr, u8 data); /* Synchronize NVRAM */ extern void nvram_sync(void); +/* Initialize NVRAM OS partition */ +extern int __init nvram_init_os_partition(struct nvram_os_partition *part); + +/* Initialize NVRAM oops partition */ +extern void __init nvram_init_oops_partition(int rtas_partition_exists); + +/* Read a NVRAM partition */ +extern int nvram_read_partition(struct nvram_os_partition *part, char *buff, + int length, unsigned int *err_type, + unsigned int *error_log_cnt); + +/* Write to NVRAM OS partition */ +extern int nvram_write_os_partition(struct nvram_os_partition *part, + char *buff, int length, + unsigned int err_type, + unsigned int error_log_cnt); + /* Determine NVRAM size */ extern ssize_t nvram_get_size(void); diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h new file mode 100644 index 000000000000..0321a909e663 --- /dev/null +++ b/arch/powerpc/include/asm/opal-api.h @@ -0,0 +1,735 @@ +/* + * OPAL API definitions. + * + * Copyright 2011-2015 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef __OPAL_API_H +#define __OPAL_API_H + +/****** OPAL APIs ******/ + +/* Return codes */ +#define OPAL_SUCCESS 0 +#define OPAL_PARAMETER -1 +#define OPAL_BUSY -2 +#define OPAL_PARTIAL -3 +#define OPAL_CONSTRAINED -4 +#define OPAL_CLOSED -5 +#define OPAL_HARDWARE -6 +#define OPAL_UNSUPPORTED -7 +#define OPAL_PERMISSION -8 +#define OPAL_NO_MEM -9 +#define OPAL_RESOURCE -10 +#define OPAL_INTERNAL_ERROR -11 +#define OPAL_BUSY_EVENT -12 +#define OPAL_HARDWARE_FROZEN -13 +#define OPAL_WRONG_STATE -14 +#define OPAL_ASYNC_COMPLETION -15 +#define OPAL_EMPTY -16 +#define OPAL_I2C_TIMEOUT -17 +#define OPAL_I2C_INVALID_CMD -18 +#define OPAL_I2C_LBUS_PARITY -19 +#define OPAL_I2C_BKEND_OVERRUN -20 +#define OPAL_I2C_BKEND_ACCESS -21 +#define OPAL_I2C_ARBT_LOST -22 +#define OPAL_I2C_NACK_RCVD -23 +#define OPAL_I2C_STOP_ERR -24 + +/* API Tokens (in r0) */ +#define OPAL_INVALID_CALL -1 +#define OPAL_TEST 0 +#define OPAL_CONSOLE_WRITE 1 +#define OPAL_CONSOLE_READ 2 +#define OPAL_RTC_READ 3 +#define OPAL_RTC_WRITE 4 +#define OPAL_CEC_POWER_DOWN 5 +#define OPAL_CEC_REBOOT 6 +#define OPAL_READ_NVRAM 7 +#define OPAL_WRITE_NVRAM 8 +#define OPAL_HANDLE_INTERRUPT 9 +#define OPAL_POLL_EVENTS 10 +#define OPAL_PCI_SET_HUB_TCE_MEMORY 11 +#define OPAL_PCI_SET_PHB_TCE_MEMORY 12 +#define OPAL_PCI_CONFIG_READ_BYTE 13 +#define OPAL_PCI_CONFIG_READ_HALF_WORD 14 +#define OPAL_PCI_CONFIG_READ_WORD 15 +#define OPAL_PCI_CONFIG_WRITE_BYTE 16 +#define OPAL_PCI_CONFIG_WRITE_HALF_WORD 17 +#define OPAL_PCI_CONFIG_WRITE_WORD 18 +#define OPAL_SET_XIVE 19 +#define OPAL_GET_XIVE 20 +#define OPAL_GET_COMPLETION_TOKEN_STATUS 21 /* obsolete */ +#define OPAL_REGISTER_OPAL_EXCEPTION_HANDLER 22 +#define OPAL_PCI_EEH_FREEZE_STATUS 23 +#define OPAL_PCI_SHPC 24 +#define OPAL_CONSOLE_WRITE_BUFFER_SPACE 25 +#define OPAL_PCI_EEH_FREEZE_CLEAR 26 +#define OPAL_PCI_PHB_MMIO_ENABLE 27 +#define OPAL_PCI_SET_PHB_MEM_WINDOW 28 +#define OPAL_PCI_MAP_PE_MMIO_WINDOW 29 +#define OPAL_PCI_SET_PHB_TABLE_MEMORY 30 +#define OPAL_PCI_SET_PE 31 +#define OPAL_PCI_SET_PELTV 32 +#define OPAL_PCI_SET_MVE 33 +#define OPAL_PCI_SET_MVE_ENABLE 34 +#define OPAL_PCI_GET_XIVE_REISSUE 35 +#define OPAL_PCI_SET_XIVE_REISSUE 36 +#define OPAL_PCI_SET_XIVE_PE 37 +#define OPAL_GET_XIVE_SOURCE 38 +#define OPAL_GET_MSI_32 39 +#define OPAL_GET_MSI_64 40 +#define OPAL_START_CPU 41 +#define OPAL_QUERY_CPU_STATUS 42 +#define OPAL_WRITE_OPPANEL 43 /* unimplemented */ +#define OPAL_PCI_MAP_PE_DMA_WINDOW 44 +#define OPAL_PCI_MAP_PE_DMA_WINDOW_REAL 45 +#define OPAL_PCI_RESET 49 +#define OPAL_PCI_GET_HUB_DIAG_DATA 50 +#define OPAL_PCI_GET_PHB_DIAG_DATA 51 +#define OPAL_PCI_FENCE_PHB 52 +#define OPAL_PCI_REINIT 53 +#define OPAL_PCI_MASK_PE_ERROR 54 +#define OPAL_SET_SLOT_LED_STATUS 55 +#define OPAL_GET_EPOW_STATUS 56 +#define OPAL_SET_SYSTEM_ATTENTION_LED 57 +#define OPAL_RESERVED1 58 +#define OPAL_RESERVED2 59 +#define OPAL_PCI_NEXT_ERROR 60 +#define OPAL_PCI_EEH_FREEZE_STATUS2 61 +#define OPAL_PCI_POLL 62 +#define OPAL_PCI_MSI_EOI 63 +#define OPAL_PCI_GET_PHB_DIAG_DATA2 64 +#define OPAL_XSCOM_READ 65 +#define OPAL_XSCOM_WRITE 66 +#define OPAL_LPC_READ 67 +#define OPAL_LPC_WRITE 68 +#define OPAL_RETURN_CPU 69 +#define OPAL_REINIT_CPUS 70 +#define OPAL_ELOG_READ 71 +#define OPAL_ELOG_WRITE 72 +#define OPAL_ELOG_ACK 73 +#define OPAL_ELOG_RESEND 74 +#define OPAL_ELOG_SIZE 75 +#define OPAL_FLASH_VALIDATE 76 +#define OPAL_FLASH_MANAGE 77 +#define OPAL_FLASH_UPDATE 78 +#define OPAL_RESYNC_TIMEBASE 79 +#define OPAL_CHECK_TOKEN 80 +#define OPAL_DUMP_INIT 81 +#define OPAL_DUMP_INFO 82 +#define OPAL_DUMP_READ 83 +#define OPAL_DUMP_ACK 84 +#define OPAL_GET_MSG 85 +#define OPAL_CHECK_ASYNC_COMPLETION 86 +#define OPAL_SYNC_HOST_REBOOT 87 +#define OPAL_SENSOR_READ 88 +#define OPAL_GET_PARAM 89 +#define OPAL_SET_PARAM 90 +#define OPAL_DUMP_RESEND 91 +#define OPAL_ELOG_SEND 92 /* Deprecated */ +#define OPAL_PCI_SET_PHB_CAPI_MODE 93 +#define OPAL_DUMP_INFO2 94 +#define OPAL_WRITE_OPPANEL_ASYNC 95 +#define OPAL_PCI_ERR_INJECT 96 +#define OPAL_PCI_EEH_FREEZE_SET 97 +#define OPAL_HANDLE_HMI 98 +#define OPAL_CONFIG_CPU_IDLE_STATE 99 +#define OPAL_SLW_SET_REG 100 +#define OPAL_REGISTER_DUMP_REGION 101 +#define OPAL_UNREGISTER_DUMP_REGION 102 +#define OPAL_WRITE_TPO 103 +#define OPAL_READ_TPO 104 +#define OPAL_GET_DPO_STATUS 105 +#define OPAL_OLD_I2C_REQUEST 106 /* Deprecated */ +#define OPAL_IPMI_SEND 107 +#define OPAL_IPMI_RECV 108 +#define OPAL_I2C_REQUEST 109 +#define OPAL_FLASH_READ 110 +#define OPAL_FLASH_WRITE 111 +#define OPAL_FLASH_ERASE 112 +#define OPAL_LAST 112 + +/* Device tree flags */ + +/* Flags set in power-mgmt nodes in device tree if + * respective idle states are supported in the platform. + */ +#define OPAL_PM_NAP_ENABLED 0x00010000 +#define OPAL_PM_SLEEP_ENABLED 0x00020000 +#define OPAL_PM_WINKLE_ENABLED 0x00040000 +#define OPAL_PM_SLEEP_ENABLED_ER1 0x00080000 /* with workaround */ + +#ifndef __ASSEMBLY__ + +/* Other enums */ +enum OpalFreezeState { + OPAL_EEH_STOPPED_NOT_FROZEN = 0, + OPAL_EEH_STOPPED_MMIO_FREEZE = 1, + OPAL_EEH_STOPPED_DMA_FREEZE = 2, + OPAL_EEH_STOPPED_MMIO_DMA_FREEZE = 3, + OPAL_EEH_STOPPED_RESET = 4, + OPAL_EEH_STOPPED_TEMP_UNAVAIL = 5, + OPAL_EEH_STOPPED_PERM_UNAVAIL = 6 +}; + +enum OpalEehFreezeActionToken { + OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO = 1, + OPAL_EEH_ACTION_CLEAR_FREEZE_DMA = 2, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL = 3, + + OPAL_EEH_ACTION_SET_FREEZE_MMIO = 1, + OPAL_EEH_ACTION_SET_FREEZE_DMA = 2, + OPAL_EEH_ACTION_SET_FREEZE_ALL = 3 +}; + +enum OpalPciStatusToken { + OPAL_EEH_NO_ERROR = 0, + OPAL_EEH_IOC_ERROR = 1, + OPAL_EEH_PHB_ERROR = 2, + OPAL_EEH_PE_ERROR = 3, + OPAL_EEH_PE_MMIO_ERROR = 4, + OPAL_EEH_PE_DMA_ERROR = 5 +}; + +enum OpalPciErrorSeverity { + OPAL_EEH_SEV_NO_ERROR = 0, + OPAL_EEH_SEV_IOC_DEAD = 1, + OPAL_EEH_SEV_PHB_DEAD = 2, + OPAL_EEH_SEV_PHB_FENCED = 3, + OPAL_EEH_SEV_PE_ER = 4, + OPAL_EEH_SEV_INF = 5 +}; + +enum OpalErrinjectType { + OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR = 0, + OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64 = 1, +}; + +enum OpalErrinjectFunc { + /* IOA bus specific errors */ + OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR = 0, + OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_DATA = 1, + OPAL_ERR_INJECT_FUNC_IOA_LD_IO_ADDR = 2, + OPAL_ERR_INJECT_FUNC_IOA_LD_IO_DATA = 3, + OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_ADDR = 4, + OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_DATA = 5, + OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_ADDR = 6, + OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_DATA = 7, + OPAL_ERR_INJECT_FUNC_IOA_ST_IO_ADDR = 8, + OPAL_ERR_INJECT_FUNC_IOA_ST_IO_DATA = 9, + OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_ADDR = 10, + OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_DATA = 11, + OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_ADDR = 12, + OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_DATA = 13, + OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_MASTER = 14, + OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_TARGET = 15, + OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_ADDR = 16, + OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_DATA = 17, + OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_MASTER = 18, + OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET = 19, +}; + +enum OpalMmioWindowType { + OPAL_M32_WINDOW_TYPE = 1, + OPAL_M64_WINDOW_TYPE = 2, + OPAL_IO_WINDOW_TYPE = 3 +}; + +enum OpalExceptionHandler { + OPAL_MACHINE_CHECK_HANDLER = 1, + OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2, + OPAL_SOFTPATCH_HANDLER = 3 +}; + +enum OpalPendingState { + OPAL_EVENT_OPAL_INTERNAL = 0x1, + OPAL_EVENT_NVRAM = 0x2, + OPAL_EVENT_RTC = 0x4, + OPAL_EVENT_CONSOLE_OUTPUT = 0x8, + OPAL_EVENT_CONSOLE_INPUT = 0x10, + OPAL_EVENT_ERROR_LOG_AVAIL = 0x20, + OPAL_EVENT_ERROR_LOG = 0x40, + OPAL_EVENT_EPOW = 0x80, + OPAL_EVENT_LED_STATUS = 0x100, + OPAL_EVENT_PCI_ERROR = 0x200, + OPAL_EVENT_DUMP_AVAIL = 0x400, + OPAL_EVENT_MSG_PENDING = 0x800, +}; + +enum OpalThreadStatus { + OPAL_THREAD_INACTIVE = 0x0, + OPAL_THREAD_STARTED = 0x1, + OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */ +}; + +enum OpalPciBusCompare { + OpalPciBusAny = 0, /* Any bus number match */ + OpalPciBus3Bits = 2, /* Match top 3 bits of bus number */ + OpalPciBus4Bits = 3, /* Match top 4 bits of bus number */ + OpalPciBus5Bits = 4, /* Match top 5 bits of bus number */ + OpalPciBus6Bits = 5, /* Match top 6 bits of bus number */ + OpalPciBus7Bits = 6, /* Match top 7 bits of bus number */ + OpalPciBusAll = 7, /* Match bus number exactly */ +}; + +enum OpalDeviceCompare { + OPAL_IGNORE_RID_DEVICE_NUMBER = 0, + OPAL_COMPARE_RID_DEVICE_NUMBER = 1 +}; + +enum OpalFuncCompare { + OPAL_IGNORE_RID_FUNCTION_NUMBER = 0, + OPAL_COMPARE_RID_FUNCTION_NUMBER = 1 +}; + +enum OpalPeAction { + OPAL_UNMAP_PE = 0, + OPAL_MAP_PE = 1 +}; + +enum OpalPeltvAction { + OPAL_REMOVE_PE_FROM_DOMAIN = 0, + OPAL_ADD_PE_TO_DOMAIN = 1 +}; + +enum OpalMveEnableAction { + OPAL_DISABLE_MVE = 0, + OPAL_ENABLE_MVE = 1 +}; + +enum OpalM64Action { + OPAL_DISABLE_M64 = 0, + OPAL_ENABLE_M64_SPLIT = 1, + OPAL_ENABLE_M64_NON_SPLIT = 2 +}; + +enum OpalPciResetScope { + OPAL_RESET_PHB_COMPLETE = 1, + OPAL_RESET_PCI_LINK = 2, + OPAL_RESET_PHB_ERROR = 3, + OPAL_RESET_PCI_HOT = 4, + OPAL_RESET_PCI_FUNDAMENTAL = 5, + OPAL_RESET_PCI_IODA_TABLE = 6 +}; + +enum OpalPciReinitScope { + /* + * Note: we chose values that do not overlap + * OpalPciResetScope as OPAL v2 used the same + * enum for both + */ + OPAL_REINIT_PCI_DEV = 1000 +}; + +enum OpalPciResetState { + OPAL_DEASSERT_RESET = 0, + OPAL_ASSERT_RESET = 1 +}; + +/* + * Address cycle types for LPC accesses. These also correspond + * to the content of the first cell of the "reg" property for + * device nodes on the LPC bus + */ +enum OpalLPCAddressType { + OPAL_LPC_MEM = 0, + OPAL_LPC_IO = 1, + OPAL_LPC_FW = 2, +}; + +enum opal_msg_type { + OPAL_MSG_ASYNC_COMP = 0, /* params[0] = token, params[1] = rc, + * additional params function-specific + */ + OPAL_MSG_MEM_ERR, + OPAL_MSG_EPOW, + OPAL_MSG_SHUTDOWN, /* params[0] = 1 reboot, 0 shutdown */ + OPAL_MSG_HMI_EVT, + OPAL_MSG_DPO, + OPAL_MSG_TYPE_MAX, +}; + +struct opal_msg { + __be32 msg_type; + __be32 reserved; + __be64 params[8]; +}; + +/* System parameter permission */ +enum OpalSysparamPerm { + OPAL_SYSPARAM_READ = 0x1, + OPAL_SYSPARAM_WRITE = 0x2, + OPAL_SYSPARAM_RW = (OPAL_SYSPARAM_READ | OPAL_SYSPARAM_WRITE), +}; + +enum { + OPAL_IPMI_MSG_FORMAT_VERSION_1 = 1, +}; + +struct opal_ipmi_msg { + uint8_t version; + uint8_t netfn; + uint8_t cmd; + uint8_t data[]; +}; + +/* FSP memory errors handling */ +enum OpalMemErr_Version { + OpalMemErr_V1 = 1, +}; + +enum OpalMemErrType { + OPAL_MEM_ERR_TYPE_RESILIENCE = 0, + OPAL_MEM_ERR_TYPE_DYN_DALLOC, +}; + +/* Memory Reilience error type */ +enum OpalMemErr_ResilErrType { + OPAL_MEM_RESILIENCE_CE = 0, + OPAL_MEM_RESILIENCE_UE, + OPAL_MEM_RESILIENCE_UE_SCRUB, +}; + +/* Dynamic Memory Deallocation type */ +enum OpalMemErr_DynErrType { + OPAL_MEM_DYNAMIC_DEALLOC = 0, +}; + +struct OpalMemoryErrorData { + enum OpalMemErr_Version version:8; /* 0x00 */ + enum OpalMemErrType type:8; /* 0x01 */ + __be16 flags; /* 0x02 */ + uint8_t reserved_1[4]; /* 0x04 */ + + union { + /* Memory Resilience corrected/uncorrected error info */ + struct { + enum OpalMemErr_ResilErrType resil_err_type:8; + uint8_t reserved_1[7]; + __be64 physical_address_start; + __be64 physical_address_end; + } resilience; + /* Dynamic memory deallocation error info */ + struct { + enum OpalMemErr_DynErrType dyn_err_type:8; + uint8_t reserved_1[7]; + __be64 physical_address_start; + __be64 physical_address_end; + } dyn_dealloc; + } u; +}; + +/* HMI interrupt event */ +enum OpalHMI_Version { + OpalHMIEvt_V1 = 1, +}; + +enum OpalHMI_Severity { + OpalHMI_SEV_NO_ERROR = 0, + OpalHMI_SEV_WARNING = 1, + OpalHMI_SEV_ERROR_SYNC = 2, + OpalHMI_SEV_FATAL = 3, +}; + +enum OpalHMI_Disposition { + OpalHMI_DISPOSITION_RECOVERED = 0, + OpalHMI_DISPOSITION_NOT_RECOVERED = 1, +}; + +enum OpalHMI_ErrType { + OpalHMI_ERROR_MALFUNC_ALERT = 0, + OpalHMI_ERROR_PROC_RECOV_DONE, + OpalHMI_ERROR_PROC_RECOV_DONE_AGAIN, + OpalHMI_ERROR_PROC_RECOV_MASKED, + OpalHMI_ERROR_TFAC, + OpalHMI_ERROR_TFMR_PARITY, + OpalHMI_ERROR_HA_OVERFLOW_WARN, + OpalHMI_ERROR_XSCOM_FAIL, + OpalHMI_ERROR_XSCOM_DONE, + OpalHMI_ERROR_SCOM_FIR, + OpalHMI_ERROR_DEBUG_TRIG_FIR, + OpalHMI_ERROR_HYP_RESOURCE, + OpalHMI_ERROR_CAPP_RECOVERY, +}; + +struct OpalHMIEvent { + uint8_t version; /* 0x00 */ + uint8_t severity; /* 0x01 */ + uint8_t type; /* 0x02 */ + uint8_t disposition; /* 0x03 */ + uint8_t reserved_1[4]; /* 0x04 */ + + __be64 hmer; + /* TFMR register. Valid only for TFAC and TFMR_PARITY error type. */ + __be64 tfmr; +}; + +enum { + OPAL_P7IOC_DIAG_TYPE_NONE = 0, + OPAL_P7IOC_DIAG_TYPE_RGC = 1, + OPAL_P7IOC_DIAG_TYPE_BI = 2, + OPAL_P7IOC_DIAG_TYPE_CI = 3, + OPAL_P7IOC_DIAG_TYPE_MISC = 4, + OPAL_P7IOC_DIAG_TYPE_I2C = 5, + OPAL_P7IOC_DIAG_TYPE_LAST = 6 +}; + +struct OpalIoP7IOCErrorData { + __be16 type; + + /* GEM */ + __be64 gemXfir; + __be64 gemRfir; + __be64 gemRirqfir; + __be64 gemMask; + __be64 gemRwof; + + /* LEM */ + __be64 lemFir; + __be64 lemErrMask; + __be64 lemAction0; + __be64 lemAction1; + __be64 lemWof; + + union { + struct OpalIoP7IOCRgcErrorData { + __be64 rgcStatus; /* 3E1C10 */ + __be64 rgcLdcp; /* 3E1C18 */ + }rgc; + struct OpalIoP7IOCBiErrorData { + __be64 biLdcp0; /* 3C0100, 3C0118 */ + __be64 biLdcp1; /* 3C0108, 3C0120 */ + __be64 biLdcp2; /* 3C0110, 3C0128 */ + __be64 biFenceStatus; /* 3C0130, 3C0130 */ + + uint8_t biDownbound; /* BI Downbound or Upbound */ + }bi; + struct OpalIoP7IOCCiErrorData { + __be64 ciPortStatus; /* 3Dn008 */ + __be64 ciPortLdcp; /* 3Dn010 */ + + uint8_t ciPort; /* Index of CI port: 0/1 */ + }ci; + }; +}; + +/** + * This structure defines the overlay which will be used to store PHB error + * data upon request. + */ +enum { + OPAL_PHB_ERROR_DATA_VERSION_1 = 1, +}; + +enum { + OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1, + OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2 +}; + +enum { + OPAL_P7IOC_NUM_PEST_REGS = 128, + OPAL_PHB3_NUM_PEST_REGS = 256 +}; + +struct OpalIoPhbErrorCommon { + __be32 version; + __be32 ioType; + __be32 len; +}; + +struct OpalIoP7IOCPhbErrorData { + struct OpalIoPhbErrorCommon common; + + __be32 brdgCtl; + + // P7IOC utl regs + __be32 portStatusReg; + __be32 rootCmplxStatus; + __be32 busAgentStatus; + + // P7IOC cfg regs + __be32 deviceStatus; + __be32 slotStatus; + __be32 linkStatus; + __be32 devCmdStatus; + __be32 devSecStatus; + + // cfg AER regs + __be32 rootErrorStatus; + __be32 uncorrErrorStatus; + __be32 corrErrorStatus; + __be32 tlpHdr1; + __be32 tlpHdr2; + __be32 tlpHdr3; + __be32 tlpHdr4; + __be32 sourceId; + + __be32 rsv3; + + // Record data about the call to allocate a buffer. + __be64 errorClass; + __be64 correlator; + + //P7IOC MMIO Error Regs + __be64 p7iocPlssr; // n120 + __be64 p7iocCsr; // n110 + __be64 lemFir; // nC00 + __be64 lemErrorMask; // nC18 + __be64 lemWOF; // nC40 + __be64 phbErrorStatus; // nC80 + __be64 phbFirstErrorStatus; // nC88 + __be64 phbErrorLog0; // nCC0 + __be64 phbErrorLog1; // nCC8 + __be64 mmioErrorStatus; // nD00 + __be64 mmioFirstErrorStatus; // nD08 + __be64 mmioErrorLog0; // nD40 + __be64 mmioErrorLog1; // nD48 + __be64 dma0ErrorStatus; // nD80 + __be64 dma0FirstErrorStatus; // nD88 + __be64 dma0ErrorLog0; // nDC0 + __be64 dma0ErrorLog1; // nDC8 + __be64 dma1ErrorStatus; // nE00 + __be64 dma1FirstErrorStatus; // nE08 + __be64 dma1ErrorLog0; // nE40 + __be64 dma1ErrorLog1; // nE48 + __be64 pestA[OPAL_P7IOC_NUM_PEST_REGS]; + __be64 pestB[OPAL_P7IOC_NUM_PEST_REGS]; +}; + +struct OpalIoPhb3ErrorData { + struct OpalIoPhbErrorCommon common; + + __be32 brdgCtl; + + /* PHB3 UTL regs */ + __be32 portStatusReg; + __be32 rootCmplxStatus; + __be32 busAgentStatus; + + /* PHB3 cfg regs */ + __be32 deviceStatus; + __be32 slotStatus; + __be32 linkStatus; + __be32 devCmdStatus; + __be32 devSecStatus; + + /* cfg AER regs */ + __be32 rootErrorStatus; + __be32 uncorrErrorStatus; + __be32 corrErrorStatus; + __be32 tlpHdr1; + __be32 tlpHdr2; + __be32 tlpHdr3; + __be32 tlpHdr4; + __be32 sourceId; + + __be32 rsv3; + + /* Record data about the call to allocate a buffer */ + __be64 errorClass; + __be64 correlator; + + /* PHB3 MMIO Error Regs */ + __be64 nFir; /* 000 */ + __be64 nFirMask; /* 003 */ + __be64 nFirWOF; /* 008 */ + __be64 phbPlssr; /* 120 */ + __be64 phbCsr; /* 110 */ + __be64 lemFir; /* C00 */ + __be64 lemErrorMask; /* C18 */ + __be64 lemWOF; /* C40 */ + __be64 phbErrorStatus; /* C80 */ + __be64 phbFirstErrorStatus; /* C88 */ + __be64 phbErrorLog0; /* CC0 */ + __be64 phbErrorLog1; /* CC8 */ + __be64 mmioErrorStatus; /* D00 */ + __be64 mmioFirstErrorStatus; /* D08 */ + __be64 mmioErrorLog0; /* D40 */ + __be64 mmioErrorLog1; /* D48 */ + __be64 dma0ErrorStatus; /* D80 */ + __be64 dma0FirstErrorStatus; /* D88 */ + __be64 dma0ErrorLog0; /* DC0 */ + __be64 dma0ErrorLog1; /* DC8 */ + __be64 dma1ErrorStatus; /* E00 */ + __be64 dma1FirstErrorStatus; /* E08 */ + __be64 dma1ErrorLog0; /* E40 */ + __be64 dma1ErrorLog1; /* E48 */ + __be64 pestA[OPAL_PHB3_NUM_PEST_REGS]; + __be64 pestB[OPAL_PHB3_NUM_PEST_REGS]; +}; + +enum { + OPAL_REINIT_CPUS_HILE_BE = (1 << 0), + OPAL_REINIT_CPUS_HILE_LE = (1 << 1), +}; + +typedef struct oppanel_line { + __be64 line; + __be64 line_len; +} oppanel_line_t; + +/* + * SG entries + * + * WARNING: The current implementation requires each entry + * to represent a block that is 4k aligned *and* each block + * size except the last one in the list to be as well. + */ +struct opal_sg_entry { + __be64 data; + __be64 length; +}; + +/* + * Candiate image SG list. + * + * length = VER | length + */ +struct opal_sg_list { + __be64 length; + __be64 next; + struct opal_sg_entry entry[]; +}; + +/* + * Dump region ID range usable by the OS + */ +#define OPAL_DUMP_REGION_HOST_START 0x80 +#define OPAL_DUMP_REGION_LOG_BUF 0x80 +#define OPAL_DUMP_REGION_HOST_END 0xFF + +/* CAPI modes for PHB */ +enum { + OPAL_PHB_CAPI_MODE_PCIE = 0, + OPAL_PHB_CAPI_MODE_CAPI = 1, + OPAL_PHB_CAPI_MODE_SNOOP_OFF = 2, + OPAL_PHB_CAPI_MODE_SNOOP_ON = 3, +}; + +/* OPAL I2C request */ +struct opal_i2c_request { + uint8_t type; +#define OPAL_I2C_RAW_READ 0 +#define OPAL_I2C_RAW_WRITE 1 +#define OPAL_I2C_SM_READ 2 +#define OPAL_I2C_SM_WRITE 3 + uint8_t flags; +#define OPAL_I2C_ADDR_10 0x01 /* Not supported yet */ + uint8_t subaddr_sz; /* Max 4 */ + uint8_t reserved; + __be16 addr; /* 7 or 10 bit address */ + __be16 reserved2; + __be32 subaddr; /* Sub-address if any */ + __be32 size; /* Data size */ + __be64 buffer_ra; /* Buffer real address */ +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* __OPAL_API_H */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 9ee0a30a02ce..042af1abfc4d 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -9,755 +9,17 @@ * 2 of the License, or (at your option) any later version. */ -#ifndef __OPAL_H -#define __OPAL_H +#ifndef _ASM_POWERPC_OPAL_H +#define _ASM_POWERPC_OPAL_H -#ifndef __ASSEMBLY__ -/* - * SG entry - * - * WARNING: The current implementation requires each entry - * to represent a block that is 4k aligned *and* each block - * size except the last one in the list to be as well. - */ -struct opal_sg_entry { - __be64 data; - __be64 length; -}; - -/* SG list */ -struct opal_sg_list { - __be64 length; - __be64 next; - struct opal_sg_entry entry[]; -}; - -/* We calculate number of sg entries based on PAGE_SIZE */ -#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) - -#endif /* __ASSEMBLY__ */ - -/****** OPAL APIs ******/ - -/* Return codes */ -#define OPAL_SUCCESS 0 -#define OPAL_PARAMETER -1 -#define OPAL_BUSY -2 -#define OPAL_PARTIAL -3 -#define OPAL_CONSTRAINED -4 -#define OPAL_CLOSED -5 -#define OPAL_HARDWARE -6 -#define OPAL_UNSUPPORTED -7 -#define OPAL_PERMISSION -8 -#define OPAL_NO_MEM -9 -#define OPAL_RESOURCE -10 -#define OPAL_INTERNAL_ERROR -11 -#define OPAL_BUSY_EVENT -12 -#define OPAL_HARDWARE_FROZEN -13 -#define OPAL_WRONG_STATE -14 -#define OPAL_ASYNC_COMPLETION -15 -#define OPAL_I2C_TIMEOUT -17 -#define OPAL_I2C_INVALID_CMD -18 -#define OPAL_I2C_LBUS_PARITY -19 -#define OPAL_I2C_BKEND_OVERRUN -20 -#define OPAL_I2C_BKEND_ACCESS -21 -#define OPAL_I2C_ARBT_LOST -22 -#define OPAL_I2C_NACK_RCVD -23 -#define OPAL_I2C_STOP_ERR -24 - -/* API Tokens (in r0) */ -#define OPAL_INVALID_CALL -1 -#define OPAL_CONSOLE_WRITE 1 -#define OPAL_CONSOLE_READ 2 -#define OPAL_RTC_READ 3 -#define OPAL_RTC_WRITE 4 -#define OPAL_CEC_POWER_DOWN 5 -#define OPAL_CEC_REBOOT 6 -#define OPAL_READ_NVRAM 7 -#define OPAL_WRITE_NVRAM 8 -#define OPAL_HANDLE_INTERRUPT 9 -#define OPAL_POLL_EVENTS 10 -#define OPAL_PCI_SET_HUB_TCE_MEMORY 11 -#define OPAL_PCI_SET_PHB_TCE_MEMORY 12 -#define OPAL_PCI_CONFIG_READ_BYTE 13 -#define OPAL_PCI_CONFIG_READ_HALF_WORD 14 -#define OPAL_PCI_CONFIG_READ_WORD 15 -#define OPAL_PCI_CONFIG_WRITE_BYTE 16 -#define OPAL_PCI_CONFIG_WRITE_HALF_WORD 17 -#define OPAL_PCI_CONFIG_WRITE_WORD 18 -#define OPAL_SET_XIVE 19 -#define OPAL_GET_XIVE 20 -#define OPAL_GET_COMPLETION_TOKEN_STATUS 21 /* obsolete */ -#define OPAL_REGISTER_OPAL_EXCEPTION_HANDLER 22 -#define OPAL_PCI_EEH_FREEZE_STATUS 23 -#define OPAL_PCI_SHPC 24 -#define OPAL_CONSOLE_WRITE_BUFFER_SPACE 25 -#define OPAL_PCI_EEH_FREEZE_CLEAR 26 -#define OPAL_PCI_PHB_MMIO_ENABLE 27 -#define OPAL_PCI_SET_PHB_MEM_WINDOW 28 -#define OPAL_PCI_MAP_PE_MMIO_WINDOW 29 -#define OPAL_PCI_SET_PHB_TABLE_MEMORY 30 -#define OPAL_PCI_SET_PE 31 -#define OPAL_PCI_SET_PELTV 32 -#define OPAL_PCI_SET_MVE 33 -#define OPAL_PCI_SET_MVE_ENABLE 34 -#define OPAL_PCI_GET_XIVE_REISSUE 35 -#define OPAL_PCI_SET_XIVE_REISSUE 36 -#define OPAL_PCI_SET_XIVE_PE 37 -#define OPAL_GET_XIVE_SOURCE 38 -#define OPAL_GET_MSI_32 39 -#define OPAL_GET_MSI_64 40 -#define OPAL_START_CPU 41 -#define OPAL_QUERY_CPU_STATUS 42 -#define OPAL_WRITE_OPPANEL 43 -#define OPAL_PCI_MAP_PE_DMA_WINDOW 44 -#define OPAL_PCI_MAP_PE_DMA_WINDOW_REAL 45 -#define OPAL_PCI_RESET 49 -#define OPAL_PCI_GET_HUB_DIAG_DATA 50 -#define OPAL_PCI_GET_PHB_DIAG_DATA 51 -#define OPAL_PCI_FENCE_PHB 52 -#define OPAL_PCI_REINIT 53 -#define OPAL_PCI_MASK_PE_ERROR 54 -#define OPAL_SET_SLOT_LED_STATUS 55 -#define OPAL_GET_EPOW_STATUS 56 -#define OPAL_SET_SYSTEM_ATTENTION_LED 57 -#define OPAL_RESERVED1 58 -#define OPAL_RESERVED2 59 -#define OPAL_PCI_NEXT_ERROR 60 -#define OPAL_PCI_EEH_FREEZE_STATUS2 61 -#define OPAL_PCI_POLL 62 -#define OPAL_PCI_MSI_EOI 63 -#define OPAL_PCI_GET_PHB_DIAG_DATA2 64 -#define OPAL_XSCOM_READ 65 -#define OPAL_XSCOM_WRITE 66 -#define OPAL_LPC_READ 67 -#define OPAL_LPC_WRITE 68 -#define OPAL_RETURN_CPU 69 -#define OPAL_REINIT_CPUS 70 -#define OPAL_ELOG_READ 71 -#define OPAL_ELOG_WRITE 72 -#define OPAL_ELOG_ACK 73 -#define OPAL_ELOG_RESEND 74 -#define OPAL_ELOG_SIZE 75 -#define OPAL_FLASH_VALIDATE 76 -#define OPAL_FLASH_MANAGE 77 -#define OPAL_FLASH_UPDATE 78 -#define OPAL_RESYNC_TIMEBASE 79 -#define OPAL_CHECK_TOKEN 80 -#define OPAL_DUMP_INIT 81 -#define OPAL_DUMP_INFO 82 -#define OPAL_DUMP_READ 83 -#define OPAL_DUMP_ACK 84 -#define OPAL_GET_MSG 85 -#define OPAL_CHECK_ASYNC_COMPLETION 86 -#define OPAL_SYNC_HOST_REBOOT 87 -#define OPAL_SENSOR_READ 88 -#define OPAL_GET_PARAM 89 -#define OPAL_SET_PARAM 90 -#define OPAL_DUMP_RESEND 91 -#define OPAL_PCI_SET_PHB_CXL_MODE 93 -#define OPAL_DUMP_INFO2 94 -#define OPAL_PCI_ERR_INJECT 96 -#define OPAL_PCI_EEH_FREEZE_SET 97 -#define OPAL_HANDLE_HMI 98 -#define OPAL_CONFIG_CPU_IDLE_STATE 99 -#define OPAL_SLW_SET_REG 100 -#define OPAL_REGISTER_DUMP_REGION 101 -#define OPAL_UNREGISTER_DUMP_REGION 102 -#define OPAL_WRITE_TPO 103 -#define OPAL_READ_TPO 104 -#define OPAL_IPMI_SEND 107 -#define OPAL_IPMI_RECV 108 -#define OPAL_I2C_REQUEST 109 - -/* Device tree flags */ - -/* Flags set in power-mgmt nodes in device tree if - * respective idle states are supported in the platform. - */ -#define OPAL_PM_NAP_ENABLED 0x00010000 -#define OPAL_PM_SLEEP_ENABLED 0x00020000 -#define OPAL_PM_WINKLE_ENABLED 0x00040000 -#define OPAL_PM_SLEEP_ENABLED_ER1 0x00080000 +#include <asm/opal-api.h> #ifndef __ASSEMBLY__ #include <linux/notifier.h> -/* Other enums */ -enum OpalVendorApiTokens { - OPAL_START_VENDOR_API_RANGE = 1000, OPAL_END_VENDOR_API_RANGE = 1999 -}; - -enum OpalFreezeState { - OPAL_EEH_STOPPED_NOT_FROZEN = 0, - OPAL_EEH_STOPPED_MMIO_FREEZE = 1, - OPAL_EEH_STOPPED_DMA_FREEZE = 2, - OPAL_EEH_STOPPED_MMIO_DMA_FREEZE = 3, - OPAL_EEH_STOPPED_RESET = 4, - OPAL_EEH_STOPPED_TEMP_UNAVAIL = 5, - OPAL_EEH_STOPPED_PERM_UNAVAIL = 6 -}; - -enum OpalEehFreezeActionToken { - OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO = 1, - OPAL_EEH_ACTION_CLEAR_FREEZE_DMA = 2, - OPAL_EEH_ACTION_CLEAR_FREEZE_ALL = 3, - - OPAL_EEH_ACTION_SET_FREEZE_MMIO = 1, - OPAL_EEH_ACTION_SET_FREEZE_DMA = 2, - OPAL_EEH_ACTION_SET_FREEZE_ALL = 3 -}; - -enum OpalPciStatusToken { - OPAL_EEH_NO_ERROR = 0, - OPAL_EEH_IOC_ERROR = 1, - OPAL_EEH_PHB_ERROR = 2, - OPAL_EEH_PE_ERROR = 3, - OPAL_EEH_PE_MMIO_ERROR = 4, - OPAL_EEH_PE_DMA_ERROR = 5 -}; - -enum OpalPciErrorSeverity { - OPAL_EEH_SEV_NO_ERROR = 0, - OPAL_EEH_SEV_IOC_DEAD = 1, - OPAL_EEH_SEV_PHB_DEAD = 2, - OPAL_EEH_SEV_PHB_FENCED = 3, - OPAL_EEH_SEV_PE_ER = 4, - OPAL_EEH_SEV_INF = 5 -}; - -enum OpalErrinjectType { - OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR = 0, - OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64 = 1, -}; - -enum OpalErrinjectFunc { - /* IOA bus specific errors */ - OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR = 0, - OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_DATA = 1, - OPAL_ERR_INJECT_FUNC_IOA_LD_IO_ADDR = 2, - OPAL_ERR_INJECT_FUNC_IOA_LD_IO_DATA = 3, - OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_ADDR = 4, - OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_DATA = 5, - OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_ADDR = 6, - OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_DATA = 7, - OPAL_ERR_INJECT_FUNC_IOA_ST_IO_ADDR = 8, - OPAL_ERR_INJECT_FUNC_IOA_ST_IO_DATA = 9, - OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_ADDR = 10, - OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_DATA = 11, - OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_ADDR = 12, - OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_DATA = 13, - OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_MASTER = 14, - OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_TARGET = 15, - OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_ADDR = 16, - OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_DATA = 17, - OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_MASTER = 18, - OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET = 19, -}; - -enum OpalShpcAction { - OPAL_SHPC_GET_LINK_STATE = 0, - OPAL_SHPC_GET_SLOT_STATE = 1 -}; - -enum OpalShpcLinkState { - OPAL_SHPC_LINK_DOWN = 0, - OPAL_SHPC_LINK_UP = 1 -}; - -enum OpalMmioWindowType { - OPAL_M32_WINDOW_TYPE = 1, - OPAL_M64_WINDOW_TYPE = 2, - OPAL_IO_WINDOW_TYPE = 3 -}; - -enum OpalShpcSlotState { - OPAL_SHPC_DEV_NOT_PRESENT = 0, - OPAL_SHPC_DEV_PRESENT = 1 -}; - -enum OpalExceptionHandler { - OPAL_MACHINE_CHECK_HANDLER = 1, - OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2, - OPAL_SOFTPATCH_HANDLER = 3 -}; - -enum OpalPendingState { - OPAL_EVENT_OPAL_INTERNAL = 0x1, - OPAL_EVENT_NVRAM = 0x2, - OPAL_EVENT_RTC = 0x4, - OPAL_EVENT_CONSOLE_OUTPUT = 0x8, - OPAL_EVENT_CONSOLE_INPUT = 0x10, - OPAL_EVENT_ERROR_LOG_AVAIL = 0x20, - OPAL_EVENT_ERROR_LOG = 0x40, - OPAL_EVENT_EPOW = 0x80, - OPAL_EVENT_LED_STATUS = 0x100, - OPAL_EVENT_PCI_ERROR = 0x200, - OPAL_EVENT_DUMP_AVAIL = 0x400, - OPAL_EVENT_MSG_PENDING = 0x800, -}; - -enum OpalMessageType { - OPAL_MSG_ASYNC_COMP = 0, /* params[0] = token, params[1] = rc, - * additional params function-specific - */ - OPAL_MSG_MEM_ERR, - OPAL_MSG_EPOW, - OPAL_MSG_SHUTDOWN, /* params[0] = 1 reboot, 0 shutdown */ - OPAL_MSG_HMI_EVT, - OPAL_MSG_TYPE_MAX, -}; - -enum OpalThreadStatus { - OPAL_THREAD_INACTIVE = 0x0, - OPAL_THREAD_STARTED = 0x1, - OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */ -}; - -enum OpalPciBusCompare { - OpalPciBusAny = 0, /* Any bus number match */ - OpalPciBus3Bits = 2, /* Match top 3 bits of bus number */ - OpalPciBus4Bits = 3, /* Match top 4 bits of bus number */ - OpalPciBus5Bits = 4, /* Match top 5 bits of bus number */ - OpalPciBus6Bits = 5, /* Match top 6 bits of bus number */ - OpalPciBus7Bits = 6, /* Match top 7 bits of bus number */ - OpalPciBusAll = 7, /* Match bus number exactly */ -}; - -enum OpalDeviceCompare { - OPAL_IGNORE_RID_DEVICE_NUMBER = 0, - OPAL_COMPARE_RID_DEVICE_NUMBER = 1 -}; - -enum OpalFuncCompare { - OPAL_IGNORE_RID_FUNCTION_NUMBER = 0, - OPAL_COMPARE_RID_FUNCTION_NUMBER = 1 -}; - -enum OpalPeAction { - OPAL_UNMAP_PE = 0, - OPAL_MAP_PE = 1 -}; - -enum OpalPeltvAction { - OPAL_REMOVE_PE_FROM_DOMAIN = 0, - OPAL_ADD_PE_TO_DOMAIN = 1 -}; - -enum OpalMveEnableAction { - OPAL_DISABLE_MVE = 0, - OPAL_ENABLE_MVE = 1 -}; - -enum OpalM64EnableAction { - OPAL_DISABLE_M64 = 0, - OPAL_ENABLE_M64_SPLIT = 1, - OPAL_ENABLE_M64_NON_SPLIT = 2 -}; - -enum OpalPciResetScope { - OPAL_RESET_PHB_COMPLETE = 1, - OPAL_RESET_PCI_LINK = 2, - OPAL_RESET_PHB_ERROR = 3, - OPAL_RESET_PCI_HOT = 4, - OPAL_RESET_PCI_FUNDAMENTAL = 5, - OPAL_RESET_PCI_IODA_TABLE = 6 -}; - -enum OpalPciReinitScope { - OPAL_REINIT_PCI_DEV = 1000 -}; - -enum OpalPciResetState { - OPAL_DEASSERT_RESET = 0, - OPAL_ASSERT_RESET = 1 -}; - -enum OpalPciMaskAction { - OPAL_UNMASK_ERROR_TYPE = 0, - OPAL_MASK_ERROR_TYPE = 1 -}; - -enum OpalSlotLedType { - OPAL_SLOT_LED_ID_TYPE = 0, - OPAL_SLOT_LED_FAULT_TYPE = 1 -}; - -enum OpalLedAction { - OPAL_TURN_OFF_LED = 0, - OPAL_TURN_ON_LED = 1, - OPAL_QUERY_LED_STATE_AFTER_BUSY = 2 -}; - -enum OpalEpowStatus { - OPAL_EPOW_NONE = 0, - OPAL_EPOW_UPS = 1, - OPAL_EPOW_OVER_AMBIENT_TEMP = 2, - OPAL_EPOW_OVER_INTERNAL_TEMP = 3 -}; - -/* - * Address cycle types for LPC accesses. These also correspond - * to the content of the first cell of the "reg" property for - * device nodes on the LPC bus - */ -enum OpalLPCAddressType { - OPAL_LPC_MEM = 0, - OPAL_LPC_IO = 1, - OPAL_LPC_FW = 2, -}; - -/* System parameter permission */ -enum OpalSysparamPerm { - OPAL_SYSPARAM_READ = 0x1, - OPAL_SYSPARAM_WRITE = 0x2, - OPAL_SYSPARAM_RW = (OPAL_SYSPARAM_READ | OPAL_SYSPARAM_WRITE), -}; - -struct opal_msg { - __be32 msg_type; - __be32 reserved; - __be64 params[8]; -}; - -enum { - OPAL_IPMI_MSG_FORMAT_VERSION_1 = 1, -}; - -struct opal_ipmi_msg { - uint8_t version; - uint8_t netfn; - uint8_t cmd; - uint8_t data[]; -}; - -/* FSP memory errors handling */ -enum OpalMemErr_Version { - OpalMemErr_V1 = 1, -}; - -enum OpalMemErrType { - OPAL_MEM_ERR_TYPE_RESILIENCE = 0, - OPAL_MEM_ERR_TYPE_DYN_DALLOC, - OPAL_MEM_ERR_TYPE_SCRUB, -}; - -/* Memory Reilience error type */ -enum OpalMemErr_ResilErrType { - OPAL_MEM_RESILIENCE_CE = 0, - OPAL_MEM_RESILIENCE_UE, - OPAL_MEM_RESILIENCE_UE_SCRUB, -}; - -/* Dynamic Memory Deallocation type */ -enum OpalMemErr_DynErrType { - OPAL_MEM_DYNAMIC_DEALLOC = 0, -}; - -/* OpalMemoryErrorData->flags */ -#define OPAL_MEM_CORRECTED_ERROR 0x0001 -#define OPAL_MEM_THRESHOLD_EXCEEDED 0x0002 -#define OPAL_MEM_ACK_REQUIRED 0x8000 - -struct OpalMemoryErrorData { - enum OpalMemErr_Version version:8; /* 0x00 */ - enum OpalMemErrType type:8; /* 0x01 */ - __be16 flags; /* 0x02 */ - uint8_t reserved_1[4]; /* 0x04 */ - - union { - /* Memory Resilience corrected/uncorrected error info */ - struct { - enum OpalMemErr_ResilErrType resil_err_type:8; - uint8_t reserved_1[7]; - __be64 physical_address_start; - __be64 physical_address_end; - } resilience; - /* Dynamic memory deallocation error info */ - struct { - enum OpalMemErr_DynErrType dyn_err_type:8; - uint8_t reserved_1[7]; - __be64 physical_address_start; - __be64 physical_address_end; - } dyn_dealloc; - } u; -}; - -/* HMI interrupt event */ -enum OpalHMI_Version { - OpalHMIEvt_V1 = 1, -}; - -enum OpalHMI_Severity { - OpalHMI_SEV_NO_ERROR = 0, - OpalHMI_SEV_WARNING = 1, - OpalHMI_SEV_ERROR_SYNC = 2, - OpalHMI_SEV_FATAL = 3, -}; - -enum OpalHMI_Disposition { - OpalHMI_DISPOSITION_RECOVERED = 0, - OpalHMI_DISPOSITION_NOT_RECOVERED = 1, -}; - -enum OpalHMI_ErrType { - OpalHMI_ERROR_MALFUNC_ALERT = 0, - OpalHMI_ERROR_PROC_RECOV_DONE, - OpalHMI_ERROR_PROC_RECOV_DONE_AGAIN, - OpalHMI_ERROR_PROC_RECOV_MASKED, - OpalHMI_ERROR_TFAC, - OpalHMI_ERROR_TFMR_PARITY, - OpalHMI_ERROR_HA_OVERFLOW_WARN, - OpalHMI_ERROR_XSCOM_FAIL, - OpalHMI_ERROR_XSCOM_DONE, - OpalHMI_ERROR_SCOM_FIR, - OpalHMI_ERROR_DEBUG_TRIG_FIR, - OpalHMI_ERROR_HYP_RESOURCE, -}; - -struct OpalHMIEvent { - uint8_t version; /* 0x00 */ - uint8_t severity; /* 0x01 */ - uint8_t type; /* 0x02 */ - uint8_t disposition; /* 0x03 */ - uint8_t reserved_1[4]; /* 0x04 */ - - __be64 hmer; - /* TFMR register. Valid only for TFAC and TFMR_PARITY error type. */ - __be64 tfmr; -}; - -enum { - OPAL_P7IOC_DIAG_TYPE_NONE = 0, - OPAL_P7IOC_DIAG_TYPE_RGC = 1, - OPAL_P7IOC_DIAG_TYPE_BI = 2, - OPAL_P7IOC_DIAG_TYPE_CI = 3, - OPAL_P7IOC_DIAG_TYPE_MISC = 4, - OPAL_P7IOC_DIAG_TYPE_I2C = 5, - OPAL_P7IOC_DIAG_TYPE_LAST = 6 -}; - -struct OpalIoP7IOCErrorData { - __be16 type; - - /* GEM */ - __be64 gemXfir; - __be64 gemRfir; - __be64 gemRirqfir; - __be64 gemMask; - __be64 gemRwof; - - /* LEM */ - __be64 lemFir; - __be64 lemErrMask; - __be64 lemAction0; - __be64 lemAction1; - __be64 lemWof; - - union { - struct OpalIoP7IOCRgcErrorData { - __be64 rgcStatus; /* 3E1C10 */ - __be64 rgcLdcp; /* 3E1C18 */ - }rgc; - struct OpalIoP7IOCBiErrorData { - __be64 biLdcp0; /* 3C0100, 3C0118 */ - __be64 biLdcp1; /* 3C0108, 3C0120 */ - __be64 biLdcp2; /* 3C0110, 3C0128 */ - __be64 biFenceStatus; /* 3C0130, 3C0130 */ - - u8 biDownbound; /* BI Downbound or Upbound */ - }bi; - struct OpalIoP7IOCCiErrorData { - __be64 ciPortStatus; /* 3Dn008 */ - __be64 ciPortLdcp; /* 3Dn010 */ - - u8 ciPort; /* Index of CI port: 0/1 */ - }ci; - }; -}; - -/** - * This structure defines the overlay which will be used to store PHB error - * data upon request. - */ -enum { - OPAL_PHB_ERROR_DATA_VERSION_1 = 1, -}; - -enum { - OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1, - OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2 -}; - -enum { - OPAL_P7IOC_NUM_PEST_REGS = 128, - OPAL_PHB3_NUM_PEST_REGS = 256 -}; - -/* CAPI modes for PHB */ -enum { - OPAL_PHB_CAPI_MODE_PCIE = 0, - OPAL_PHB_CAPI_MODE_CAPI = 1, - OPAL_PHB_CAPI_MODE_SNOOP_OFF = 2, - OPAL_PHB_CAPI_MODE_SNOOP_ON = 3, -}; - -struct OpalIoPhbErrorCommon { - __be32 version; - __be32 ioType; - __be32 len; -}; - -struct OpalIoP7IOCPhbErrorData { - struct OpalIoPhbErrorCommon common; - - __be32 brdgCtl; - - // P7IOC utl regs - __be32 portStatusReg; - __be32 rootCmplxStatus; - __be32 busAgentStatus; - - // P7IOC cfg regs - __be32 deviceStatus; - __be32 slotStatus; - __be32 linkStatus; - __be32 devCmdStatus; - __be32 devSecStatus; - - // cfg AER regs - __be32 rootErrorStatus; - __be32 uncorrErrorStatus; - __be32 corrErrorStatus; - __be32 tlpHdr1; - __be32 tlpHdr2; - __be32 tlpHdr3; - __be32 tlpHdr4; - __be32 sourceId; - - __be32 rsv3; - - // Record data about the call to allocate a buffer. - __be64 errorClass; - __be64 correlator; - - //P7IOC MMIO Error Regs - __be64 p7iocPlssr; // n120 - __be64 p7iocCsr; // n110 - __be64 lemFir; // nC00 - __be64 lemErrorMask; // nC18 - __be64 lemWOF; // nC40 - __be64 phbErrorStatus; // nC80 - __be64 phbFirstErrorStatus; // nC88 - __be64 phbErrorLog0; // nCC0 - __be64 phbErrorLog1; // nCC8 - __be64 mmioErrorStatus; // nD00 - __be64 mmioFirstErrorStatus; // nD08 - __be64 mmioErrorLog0; // nD40 - __be64 mmioErrorLog1; // nD48 - __be64 dma0ErrorStatus; // nD80 - __be64 dma0FirstErrorStatus; // nD88 - __be64 dma0ErrorLog0; // nDC0 - __be64 dma0ErrorLog1; // nDC8 - __be64 dma1ErrorStatus; // nE00 - __be64 dma1FirstErrorStatus; // nE08 - __be64 dma1ErrorLog0; // nE40 - __be64 dma1ErrorLog1; // nE48 - __be64 pestA[OPAL_P7IOC_NUM_PEST_REGS]; - __be64 pestB[OPAL_P7IOC_NUM_PEST_REGS]; -}; - -struct OpalIoPhb3ErrorData { - struct OpalIoPhbErrorCommon common; - - __be32 brdgCtl; - - /* PHB3 UTL regs */ - __be32 portStatusReg; - __be32 rootCmplxStatus; - __be32 busAgentStatus; - - /* PHB3 cfg regs */ - __be32 deviceStatus; - __be32 slotStatus; - __be32 linkStatus; - __be32 devCmdStatus; - __be32 devSecStatus; - - /* cfg AER regs */ - __be32 rootErrorStatus; - __be32 uncorrErrorStatus; - __be32 corrErrorStatus; - __be32 tlpHdr1; - __be32 tlpHdr2; - __be32 tlpHdr3; - __be32 tlpHdr4; - __be32 sourceId; - - __be32 rsv3; - - /* Record data about the call to allocate a buffer */ - __be64 errorClass; - __be64 correlator; - - __be64 nFir; /* 000 */ - __be64 nFirMask; /* 003 */ - __be64 nFirWOF; /* 008 */ - - /* PHB3 MMIO Error Regs */ - __be64 phbPlssr; /* 120 */ - __be64 phbCsr; /* 110 */ - __be64 lemFir; /* C00 */ - __be64 lemErrorMask; /* C18 */ - __be64 lemWOF; /* C40 */ - __be64 phbErrorStatus; /* C80 */ - __be64 phbFirstErrorStatus; /* C88 */ - __be64 phbErrorLog0; /* CC0 */ - __be64 phbErrorLog1; /* CC8 */ - __be64 mmioErrorStatus; /* D00 */ - __be64 mmioFirstErrorStatus; /* D08 */ - __be64 mmioErrorLog0; /* D40 */ - __be64 mmioErrorLog1; /* D48 */ - __be64 dma0ErrorStatus; /* D80 */ - __be64 dma0FirstErrorStatus; /* D88 */ - __be64 dma0ErrorLog0; /* DC0 */ - __be64 dma0ErrorLog1; /* DC8 */ - __be64 dma1ErrorStatus; /* E00 */ - __be64 dma1FirstErrorStatus; /* E08 */ - __be64 dma1ErrorLog0; /* E40 */ - __be64 dma1ErrorLog1; /* E48 */ - __be64 pestA[OPAL_PHB3_NUM_PEST_REGS]; - __be64 pestB[OPAL_PHB3_NUM_PEST_REGS]; -}; - -enum { - OPAL_REINIT_CPUS_HILE_BE = (1 << 0), - OPAL_REINIT_CPUS_HILE_LE = (1 << 1), -}; - -typedef struct oppanel_line { - const char * line; - uint64_t line_len; -} oppanel_line_t; - -/* OPAL I2C request */ -struct opal_i2c_request { - uint8_t type; -#define OPAL_I2C_RAW_READ 0 -#define OPAL_I2C_RAW_WRITE 1 -#define OPAL_I2C_SM_READ 2 -#define OPAL_I2C_SM_WRITE 3 - uint8_t flags; -#define OPAL_I2C_ADDR_10 0x01 /* Not supported yet */ - uint8_t subaddr_sz; /* Max 4 */ - uint8_t reserved; - __be16 addr; /* 7 or 10 bit address */ - __be16 reserved2; - __be32 subaddr; /* Sub-address if any */ - __be32 size; /* Data size */ - __be64 buffer_ra; /* Buffer real address */ -}; +/* We calculate number of sg entries based on PAGE_SIZE */ +#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) /* /sys/firmware/opal */ extern struct kobject *opal_kobj; @@ -932,6 +194,13 @@ int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg, int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id, struct opal_i2c_request *oreq); +int64_t opal_flash_read(uint64_t id, uint64_t offset, uint64_t buf, + uint64_t size, uint64_t token); +int64_t opal_flash_write(uint64_t id, uint64_t offset, uint64_t buf, + uint64_t size, uint64_t token); +int64_t opal_flash_erase(uint64_t id, uint64_t offset, uint64_t size, + uint64_t token); + /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); @@ -946,8 +215,10 @@ extern void hvc_opal_init_early(void); extern int opal_notifier_register(struct notifier_block *nb); extern int opal_notifier_unregister(struct notifier_block *nb); -extern int opal_message_notifier_register(enum OpalMessageType msg_type, +extern int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb); +extern int opal_message_notifier_unregister(enum opal_msg_type msg_type, + struct notifier_block *nb); extern void opal_notifier_enable(void); extern void opal_notifier_disable(void); extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); @@ -962,7 +233,7 @@ extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); struct rtc_time; extern unsigned long opal_get_boot_time(void); extern void opal_nvram_init(void); -extern void opal_flash_init(void); +extern void opal_flash_update_init(void); extern void opal_flash_term_callback(void); extern int opal_elog_init(void); extern void opal_platform_dump_init(void); @@ -983,13 +254,8 @@ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, unsigned long vmalloc_size); void opal_free_sg_list(struct opal_sg_list *sg); -/* - * Dump region ID range usable by the OS - */ -#define OPAL_DUMP_REGION_HOST_START 0x80 -#define OPAL_DUMP_REGION_LOG_BUF 0x80 -#define OPAL_DUMP_REGION_HOST_END 0xFF +extern int opal_error_code(int rc); #endif /* __ASSEMBLY__ */ -#endif /* __OPAL_H */ +#endif /* _ASM_POWERPC_OPAL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index e5f22c6c4bf9..70bd4381f8e6 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -106,9 +106,9 @@ struct paca_struct { #endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC_BOOK3E - u64 exgen[8] __attribute__((aligned(0x80))); + u64 exgen[8] __aligned(0x40); /* Keep pgd in the same cacheline as the start of extlb */ - pgd_t *pgd __attribute__((aligned(0x80))); /* Current PGD */ + pgd_t *pgd __aligned(0x40); /* Current PGD */ pgd_t *kernel_pgd; /* Kernel PGD */ /* Shared by all threads of a core -- points to tcd of first thread */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 546d036fe925..1811c44bf34b 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -15,6 +15,24 @@ struct device_node; /* + * PCI controller operations + */ +struct pci_controller_ops { + void (*dma_dev_setup)(struct pci_dev *dev); + void (*dma_bus_setup)(struct pci_bus *bus); + + int (*probe_mode)(struct pci_bus *); + + /* Called when pci_enable_device() is called. Returns true to + * allow assignment/enabling of the device. */ + bool (*enable_device_hook)(struct pci_dev *); + + /* Called during PCI resource reassignment */ + resource_size_t (*window_alignment)(struct pci_bus *, unsigned long type); + void (*reset_secondary_bus)(struct pci_dev *dev); +}; + +/* * Structure of a PCI controller (host bridge) */ struct pci_controller { @@ -46,6 +64,7 @@ struct pci_controller { resource_size_t isa_mem_phys; resource_size_t isa_mem_size; + struct pci_controller_ops controller_ops; struct pci_ops *ops; unsigned int __iomem *cfg_addr; void __iomem *cfg_data; @@ -89,6 +108,7 @@ struct pci_controller { #ifdef CONFIG_PPC64 unsigned long buid; + struct pci_dn *pci_data; #endif /* CONFIG_PPC64 */ void *private_data; @@ -154,31 +174,51 @@ static inline int isa_vaddr_is_ioport(void __iomem *address) struct iommu_table; struct pci_dn { + int flags; +#define PCI_DN_FLAG_IOV_VF 0x01 + int busno; /* pci bus number */ int devfn; /* pci device and function number */ + int vendor_id; /* Vendor ID */ + int device_id; /* Device ID */ + int class_code; /* Device class code */ + struct pci_dn *parent; struct pci_controller *phb; /* for pci devices */ struct iommu_table *iommu_table; /* for phb's or bridges */ struct device_node *node; /* back-pointer to the device_node */ int pci_ext_config_space; /* for pci devices */ - struct pci_dev *pcidev; /* back-pointer to the pci device */ #ifdef CONFIG_EEH struct eeh_dev *edev; /* eeh device */ #endif #define IODA_INVALID_PE (-1) #ifdef CONFIG_PPC_POWERNV int pe_number; +#ifdef CONFIG_PCI_IOV + u16 vfs_expanded; /* number of VFs IOV BAR expanded */ + u16 num_vfs; /* number of VFs enabled*/ + int offset; /* PE# for the first VF PE */ +#define M64_PER_IOV 4 + int m64_per_iov; +#define IODA_INVALID_M64 (-1) + int m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV]; +#endif /* CONFIG_PCI_IOV */ #endif + struct list_head child_list; + struct list_head list; }; /* Get the pointer to a device_node's pci_dn */ #define PCI_DN(dn) ((struct pci_dn *) (dn)->data) +extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus, + int devfn); extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev); - -extern void * update_dn_pci_info(struct device_node *dn, void *data); +extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev); +extern void remove_dev_pci_data(struct pci_dev *pdev); +extern void *update_dn_pci_info(struct device_node *dn, void *data); static inline int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) @@ -191,20 +231,12 @@ static inline int pci_device_from_OF_node(struct device_node *np, } #if defined(CONFIG_EEH) -static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn) +static inline struct eeh_dev *pdn_to_eeh_dev(struct pci_dn *pdn) { - /* - * For those OF nodes whose parent isn't PCI bridge, they - * don't have PCI_DN actually. So we have to skip them for - * any EEH operations. - */ - if (!dn || !PCI_DN(dn)) - return NULL; - - return PCI_DN(dn)->edev; + return pdn ? pdn->edev : NULL; } #else -#define of_node_to_eeh_dev(x) (NULL) +#define pdn_to_eeh_dev(x) (NULL) #endif /** Find the bus corresponding to the indicated device node */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 1b0739bc14b5..4aef8d660999 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -22,7 +22,7 @@ #include <asm-generic/pci-dma-compat.h> -/* Return values for ppc_md.pci_probe_mode function */ +/* Return values for pci_controller_ops.probe_mode function */ #define PCI_PROBE_NONE -1 /* Don't look at this bus at all */ #define PCI_PROBE_NORMAL 0 /* Do normal PCI probing */ #define PCI_PROBE_DEVTREE 1 /* Instantiate from device tree */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 9835ac4173b7..11a38635dd65 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -247,28 +247,16 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, #define pmd_large(pmd) 0 #define has_transparent_hugepage() 0 #endif -pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, +pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift); - -static inline pte_t *lookup_linux_ptep(pgd_t *pgdir, unsigned long hva, - unsigned long *pte_sizep) +static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, + unsigned *shift) { - pte_t *ptep; - unsigned long ps = *pte_sizep; - unsigned int shift; - - ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift); - if (!ptep) - return NULL; - if (shift) - *pte_sizep = 1ul << shift; - else - *pte_sizep = PAGE_SIZE; - - if (ps > *pte_sizep) - return NULL; - - return ptep; + if (!arch_irqs_disabled()) { + pr_info("%s called with irq enabled\n", __func__); + dump_stack(); + } + return __find_linux_pte_or_hugepte(pgdir, ea, shift); } #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index db1e2b8eff3c..4122a86d6858 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -23,8 +23,6 @@ extern void pci_setup_phb_io_dynamic(struct pci_controller *hose, int primary); extern struct list_head hose_list; -extern void find_and_init_phbs(void); - extern struct pci_dev *isa_bridge_pcidev; /* may be NULL if no ISA bus */ /** Bus Unit ID macros; get low and hi 32-bits of the 64-bit BUID */ @@ -33,9 +31,14 @@ extern struct pci_dev *isa_bridge_pcidev; /* may be NULL if no ISA bus */ /* PCI device_node operations */ struct device_node; +struct pci_dn; + typedef void *(*traverse_func)(struct device_node *me, void *data); void *traverse_pci_devices(struct device_node *start, traverse_func pre, void *data); +void *traverse_pci_dn(struct pci_dn *root, + void *(*fn)(struct pci_dn *, void *), + void *data); extern void pci_devs_phb_init(void); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); @@ -76,7 +79,6 @@ static inline const char *eeh_driver_name(struct pci_dev *pdev) #endif /* CONFIG_EEH */ #else /* CONFIG_PCI */ -static inline void find_and_init_phbs(void) { } static inline void init_pci_config_tokens(void) { } #endif /* !CONFIG_PCI */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 7e4612528546..dd0fc18d8103 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -637,105 +637,105 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945) /* AltiVec Registers (VPRs) */ -#define vr0 0 -#define vr1 1 -#define vr2 2 -#define vr3 3 -#define vr4 4 -#define vr5 5 -#define vr6 6 -#define vr7 7 -#define vr8 8 -#define vr9 9 -#define vr10 10 -#define vr11 11 -#define vr12 12 -#define vr13 13 -#define vr14 14 -#define vr15 15 -#define vr16 16 -#define vr17 17 -#define vr18 18 -#define vr19 19 -#define vr20 20 -#define vr21 21 -#define vr22 22 -#define vr23 23 -#define vr24 24 -#define vr25 25 -#define vr26 26 -#define vr27 27 -#define vr28 28 -#define vr29 29 -#define vr30 30 -#define vr31 31 +#define v0 0 +#define v1 1 +#define v2 2 +#define v3 3 +#define v4 4 +#define v5 5 +#define v6 6 +#define v7 7 +#define v8 8 +#define v9 9 +#define v10 10 +#define v11 11 +#define v12 12 +#define v13 13 +#define v14 14 +#define v15 15 +#define v16 16 +#define v17 17 +#define v18 18 +#define v19 19 +#define v20 20 +#define v21 21 +#define v22 22 +#define v23 23 +#define v24 24 +#define v25 25 +#define v26 26 +#define v27 27 +#define v28 28 +#define v29 29 +#define v30 30 +#define v31 31 /* VSX Registers (VSRs) */ -#define vsr0 0 -#define vsr1 1 -#define vsr2 2 -#define vsr3 3 -#define vsr4 4 -#define vsr5 5 -#define vsr6 6 -#define vsr7 7 -#define vsr8 8 -#define vsr9 9 -#define vsr10 10 -#define vsr11 11 -#define vsr12 12 -#define vsr13 13 -#define vsr14 14 -#define vsr15 15 -#define vsr16 16 -#define vsr17 17 -#define vsr18 18 -#define vsr19 19 -#define vsr20 20 -#define vsr21 21 -#define vsr22 22 -#define vsr23 23 -#define vsr24 24 -#define vsr25 25 -#define vsr26 26 -#define vsr27 27 -#define vsr28 28 -#define vsr29 29 -#define vsr30 30 -#define vsr31 31 -#define vsr32 32 -#define vsr33 33 -#define vsr34 34 -#define vsr35 35 -#define vsr36 36 -#define vsr37 37 -#define vsr38 38 -#define vsr39 39 -#define vsr40 40 -#define vsr41 41 -#define vsr42 42 -#define vsr43 43 -#define vsr44 44 -#define vsr45 45 -#define vsr46 46 -#define vsr47 47 -#define vsr48 48 -#define vsr49 49 -#define vsr50 50 -#define vsr51 51 -#define vsr52 52 -#define vsr53 53 -#define vsr54 54 -#define vsr55 55 -#define vsr56 56 -#define vsr57 57 -#define vsr58 58 -#define vsr59 59 -#define vsr60 60 -#define vsr61 61 -#define vsr62 62 -#define vsr63 63 +#define vs0 0 +#define vs1 1 +#define vs2 2 +#define vs3 3 +#define vs4 4 +#define vs5 5 +#define vs6 6 +#define vs7 7 +#define vs8 8 +#define vs9 9 +#define vs10 10 +#define vs11 11 +#define vs12 12 +#define vs13 13 +#define vs14 14 +#define vs15 15 +#define vs16 16 +#define vs17 17 +#define vs18 18 +#define vs19 19 +#define vs20 20 +#define vs21 21 +#define vs22 22 +#define vs23 23 +#define vs24 24 +#define vs25 25 +#define vs26 26 +#define vs27 27 +#define vs28 28 +#define vs29 29 +#define vs30 30 +#define vs31 31 +#define vs32 32 +#define vs33 33 +#define vs34 34 +#define vs35 35 +#define vs36 36 +#define vs37 37 +#define vs38 38 +#define vs39 39 +#define vs40 40 +#define vs41 41 +#define vs42 42 +#define vs43 43 +#define vs44 44 +#define vs45 45 +#define vs46 46 +#define vs47 47 +#define vs48 48 +#define vs49 49 +#define vs50 50 +#define vs51 51 +#define vs52 52 +#define vs53 53 +#define vs54 54 +#define vs55 55 +#define vs56 56 +#define vs57 57 +#define vs58 58 +#define vs59 59 +#define vs60 60 +#define vs61 61 +#define vs62 62 +#define vs63 63 /* SPE Registers (EVPRs) */ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 2e23e92a4372..7a4ede16b283 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -4,6 +4,7 @@ #include <linux/spinlock.h> #include <asm/page.h> +#include <linux/time.h> /* * Definitions for talking to the RTAS on CHRP machines. @@ -273,6 +274,7 @@ inline uint32_t rtas_ext_event_company_id(struct rtas_ext_event_log_v6 *ext_log) #define PSERIES_ELOG_SECT_ID_MANUFACT_INFO (('M' << 8) | 'I') #define PSERIES_ELOG_SECT_ID_CALL_HOME (('C' << 8) | 'H') #define PSERIES_ELOG_SECT_ID_USER_DEF (('U' << 8) | 'D') +#define PSERIES_ELOG_SECT_ID_HOTPLUG (('H' << 8) | 'P') /* Vendor specific Platform Event Log Format, Version 6, section header */ struct pseries_errorlog { @@ -296,6 +298,31 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect) return be16_to_cpu(sect->length); } +/* RTAS pseries hotplug errorlog section */ +struct pseries_hp_errorlog { + u8 resource; + u8 action; + u8 id_type; + u8 reserved; + union { + __be32 drc_index; + __be32 drc_count; + char drc_name[1]; + } _drc_u; +}; + +#define PSERIES_HP_ELOG_RESOURCE_CPU 1 +#define PSERIES_HP_ELOG_RESOURCE_MEM 2 +#define PSERIES_HP_ELOG_RESOURCE_SLOT 3 +#define PSERIES_HP_ELOG_RESOURCE_PHB 4 + +#define PSERIES_HP_ELOG_ACTION_ADD 1 +#define PSERIES_HP_ELOG_ACTION_REMOVE 2 + +#define PSERIES_HP_ELOG_ID_DRC_NAME 1 +#define PSERIES_HP_ELOG_ID_DRC_INDEX 2 +#define PSERIES_HP_ELOG_ID_DRC_COUNT 3 + struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, uint16_t section_id); @@ -327,7 +354,7 @@ extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); extern int rtas_online_cpus_mask(cpumask_var_t cpus); extern int rtas_offline_cpus_mask(cpumask_var_t cpus); -extern int rtas_ibm_suspend_me(u64 handle, int *vasi_return); +extern int rtas_ibm_suspend_me(u64 handle); struct rtc_time; extern unsigned long rtas_get_boot_time(void); @@ -343,8 +370,12 @@ extern int early_init_dt_scan_rtas(unsigned long node, extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal); #ifdef CONFIG_PPC_PSERIES +extern time64_t last_rtas_event; +extern int clobbering_unread_rtas_event(void); extern int pseries_devicetree_update(s32 scope); extern void post_mobility_fixup(void); +#else +static inline int clobbering_unread_rtas_event(void) { return 0; } #endif #ifdef CONFIG_PPC_RTAS_DAEMON diff --git a/arch/powerpc/include/asm/seccomp.h b/arch/powerpc/include/asm/seccomp.h new file mode 100644 index 000000000000..c1818e35cf02 --- /dev/null +++ b/arch/powerpc/include/asm/seccomp.h @@ -0,0 +1,10 @@ +#ifndef _ASM_POWERPC_SECCOMP_H +#define _ASM_POWERPC_SECCOMP_H + +#include <linux/unistd.h> + +#define __NR_seccomp_sigreturn_32 __NR_sigreturn + +#include <asm-generic/seccomp.h> + +#endif /* _ASM_POWERPC_SECCOMP_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index fbdf18cf954c..e9d384cbd021 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -7,7 +7,6 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; -extern int mem_init_done; /* set on boot once kmalloc can be called */ extern unsigned long long memory_limit; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index d607df5081a7..825663c30945 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -42,7 +42,7 @@ struct smp_ops_t { #ifdef CONFIG_PPC_SMP_MUXED_IPI void (*cause_ipi)(int cpu, unsigned long data); #endif - int (*probe)(void); + void (*probe)(void); int (*kick_cpu)(int nr); void (*setup_cpu)(int nr); void (*bringup_done)(void); @@ -125,7 +125,6 @@ extern irqreturn_t smp_ipi_demux(void); void smp_init_pSeries(void); void smp_init_cell(void); -void smp_init_celleb(void); void smp_setup_cpu_maps(void); extern int __cpu_disable(void); @@ -175,7 +174,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) extern int smt_enabled_at_boot; -extern int smp_mpic_probe(void); +extern void smp_mpic_probe(void); extern void smp_mpic_setup_cpu(int cpu); extern int smp_generic_kick_cpu(int nr); extern int smp_generic_cpu_bootable(unsigned int nr); diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h index 96f59de61855..487e09077a3e 100644 --- a/arch/powerpc/include/asm/swab.h +++ b/arch/powerpc/include/asm/swab.h @@ -9,30 +9,4 @@ #include <uapi/asm/swab.h> -static __inline__ __u16 ld_le16(const volatile __u16 *addr) -{ - __u16 val; - - __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); - return val; -} - -static __inline__ void st_le16(volatile __u16 *addr, const __u16 val) -{ - __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); -} - -static __inline__ __u32 ld_le32(const volatile __u32 *addr) -{ - __u32 val; - - __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); - return val; -} - -static __inline__ void st_le32(volatile __u32 *addr, const __u32 val) -{ - __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); -} - #endif /* _ASM_POWERPC_SWAB_H */ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 91062eef582f..f1863a138b4a 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -367,3 +367,4 @@ SYSCALL_SPU(getrandom) SYSCALL_SPU(memfd_create) SYSCALL_SPU(bpf) COMPAT_SYS(execveat) +PPC64ONLY(switch_endian) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 03cbada59d3a..10fc784a2ad4 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void); DECLARE_PER_CPU(u64, decrementers_next_tb); +/* Convert timebase ticks to nanoseconds */ +unsigned long long tb_to_ns(unsigned long long tb_ticks); + #endif /* __KERNEL__ */ #endif /* __POWERPC_TIME_H */ diff --git a/arch/powerpc/include/asm/ucc_slow.h b/arch/powerpc/include/asm/ucc_slow.h index c44131e68e11..233ef5fe5fde 100644 --- a/arch/powerpc/include/asm/ucc_slow.h +++ b/arch/powerpc/include/asm/ucc_slow.h @@ -251,19 +251,6 @@ void ucc_slow_enable(struct ucc_slow_private * uccs, enum comm_dir mode); */ void ucc_slow_disable(struct ucc_slow_private * uccs, enum comm_dir mode); -/* ucc_slow_poll_transmitter_now - * Immediately forces a poll of the transmitter for data to be sent. - * Typically, the hardware performs a periodic poll for data that the - * transmit routine has set up to be transmitted. In cases where - * this polling cycle is not soon enough, this optional routine can - * be invoked to force a poll right away, instead. Proper use for - * each transmission for which this functionality is desired is to - * call the transmit routine and then this routine right after. - * - * uccs - (In) pointer to the slow UCC structure. - */ -void ucc_slow_poll_transmitter_now(struct ucc_slow_private * uccs); - /* ucc_slow_graceful_stop_tx * Smoothly stops transmission on a specified slow UCC. * diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 36b79c31eedd..f4f8b667d75b 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 363 +#define __NR_syscalls 364 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/asm/vga.h b/arch/powerpc/include/asm/vga.h index e5f8dd366212..ab3acd2f2786 100644 --- a/arch/powerpc/include/asm/vga.h +++ b/arch/powerpc/include/asm/vga.h @@ -25,12 +25,12 @@ static inline void scr_writew(u16 val, volatile u16 *addr) { - st_le16(addr, val); + *addr = cpu_to_le16(val); } static inline u16 scr_readw(volatile const u16 *addr) { - return ld_le16(addr); + return le16_to_cpu(*addr); } #define VT_BUF_HAVE_MEMCPYW diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 6997f4a271df..0e25bdb190bb 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -146,7 +146,7 @@ extern void xics_update_irq_servers(void); extern void xics_set_cpu_giq(unsigned int gserver, unsigned int join); extern void xics_mask_unknown_vec(unsigned int vec); extern irqreturn_t xics_ipi_dispatch(int cpu); -extern int xics_smp_probe(void); +extern void xics_smp_probe(void); extern void xics_register_ics(struct ics *ics); extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index 7a3f795ac218..79c4068be278 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -25,7 +25,6 @@ header-y += posix_types.h header-y += ps3fb.h header-y += ptrace.h header-y += resource.h -header-y += seccomp.h header-y += sembuf.h header-y += setup.h header-y += shmbuf.h diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index 77d2ed35b111..8036b385417d 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -136,7 +136,7 @@ struct pt_regs { #endif /* __powerpc64__ */ /* - * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go. + * Get/set all the altivec registers v0..v31, vscr, vrsave, in one go. * The transfer totals 34 quadword. Quadwords 0-31 contain the * corresponding vector registers. Quadword 32 contains the vscr as the * last word (offset 12) within that quadword. Quadword 33 contains the diff --git a/arch/powerpc/include/uapi/asm/seccomp.h b/arch/powerpc/include/uapi/asm/seccomp.h deleted file mode 100644 index 00c1d9133cfe..000000000000 --- a/arch/powerpc/include/uapi/asm/seccomp.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef _ASM_POWERPC_SECCOMP_H -#define _ASM_POWERPC_SECCOMP_H - -#include <linux/unistd.h> - -#define __NR_seccomp_read __NR_read -#define __NR_seccomp_write __NR_write -#define __NR_seccomp_exit __NR_exit -#define __NR_seccomp_sigreturn __NR_rt_sigreturn - -#define __NR_seccomp_read_32 __NR_read -#define __NR_seccomp_write_32 __NR_write -#define __NR_seccomp_exit_32 __NR_exit -#define __NR_seccomp_sigreturn_32 __NR_sigreturn - -#endif /* _ASM_POWERPC_SECCOMP_H */ diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h index 5d836b7c1176..5047659815a5 100644 --- a/arch/powerpc/include/uapi/asm/tm.h +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -11,7 +11,7 @@ #define TM_CAUSE_RESCHED 0xde #define TM_CAUSE_TLBI 0xdc #define TM_CAUSE_FAC_UNAV 0xda -#define TM_CAUSE_SYSCALL 0xd8 /* future use */ +#define TM_CAUSE_SYSCALL 0xd8 #define TM_CAUSE_MISC 0xd6 /* future use */ #define TM_CAUSE_SIGNAL 0xd4 #define TM_CAUSE_ALIGNMENT 0xd2 diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index ef5b5b1f3123..e4aa173dae62 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -385,5 +385,6 @@ #define __NR_memfd_create 360 #define __NR_bpf 361 #define __NR_execveat 362 +#define __NR_switch_endian 363 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 502cf69b6c89..c1ebbdaac28f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -33,7 +33,8 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o dma.o \ - misc_$(CONFIG_WORD_SIZE).o vdso32/ + misc_$(CONFIG_WORD_SIZE).o vdso32/ \ + of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o @@ -47,7 +48,6 @@ obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o -obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 4717859fdd04..0034b6b3556a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -37,6 +37,7 @@ #include <asm/thread_info.h> #include <asm/rtas.h> #include <asm/vdso_datapage.h> +#include <asm/dbell.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> #include <asm/lppaca.h> @@ -459,6 +460,19 @@ int main(void) DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2)); DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3)); #endif +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry)); + DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr)); + DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit)); + DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time)); + DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time)); + DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity)); + DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start)); + DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount)); + DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total)); + DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min)); + DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max)); +#endif DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3)); DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4)); DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5)); @@ -492,7 +506,6 @@ int main(void) DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); - DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); @@ -550,8 +563,7 @@ int main(void) DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop)); DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort)); DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); - DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); - DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); + DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm)); @@ -748,5 +760,7 @@ int main(void) offsetof(struct paca_struct, subcore_sibling_mask)); #endif + DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER); + return 0; } diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index ae77b7e59889..c641983bbdd6 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -61,12 +61,22 @@ struct cache_type_info { }; /* These are used to index the cache_type_info array. */ -#define CACHE_TYPE_UNIFIED 0 -#define CACHE_TYPE_INSTRUCTION 1 -#define CACHE_TYPE_DATA 2 +#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */ +#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */ +#define CACHE_TYPE_INSTRUCTION 2 +#define CACHE_TYPE_DATA 3 static const struct cache_type_info cache_type_info[] = { { + /* Embedded systems that use cache-size, cache-block-size, + * etc. for the Unified (typically L2) cache. */ + .name = "Unified", + .size_prop = "cache-size", + .line_size_props = { "cache-line-size", + "cache-block-size", }, + .nr_sets_prop = "cache-sets", + }, + { /* PowerPC Processor binding says the [di]-cache-* * must be equal on unified caches, so just use * d-cache properties. */ @@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache) { struct cache *iter; - if (cache->type == CACHE_TYPE_UNIFIED) + if (cache->type == CACHE_TYPE_UNIFIED || + cache->type == CACHE_TYPE_UNIFIED_D) return cache; list_for_each_entry(iter, &cache_list, list) @@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np) return of_get_property(np, "cache-unified", NULL); } -static struct cache *cache_do_one_devnode_unified(struct device_node *node, - int level) +/* + * Unified caches can have two different sets of tags. Most embedded + * use cache-size, etc. for the unified cache size, but open firmware systems + * use d-cache-size, etc. Check on initialization for which type we have, and + * return the appropriate structure type. Assume it's embedded if it isn't + * open firmware. If it's yet a 3rd type, then there will be missing entries + * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need + * to be extended further. + */ +static int cache_is_unified_d(const struct device_node *np) { - struct cache *cache; + return of_get_property(np, + cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ? + CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED; +} +/* + */ +static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) +{ pr_debug("creating L%d ucache for %s\n", level, node->full_name); - cache = new_cache(CACHE_TYPE_UNIFIED, level, node); - - return cache; + return new_cache(cache_is_unified_d(node), level, node); } static struct cache *cache_do_one_devnode_split(struct device_node *node, diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 46733535cc0b..9c9b7411b28b 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -137,15 +137,11 @@ __init_HFSCR: /* * Clear the TLB using the specified IS form of tlbiel instruction * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. - * - * r3 = IS field */ __init_tlb_power7: - li r3,0xc00 /* IS field = 0b11 */ -_GLOBAL(__flush_tlb_power7) li r6,128 mtctr r6 - mr r7,r3 /* IS field */ + li r7,0xc00 /* IS field = 0b11 */ ptesync 2: tlbiel r7 addi r7,r7,0x1000 @@ -154,11 +150,9 @@ _GLOBAL(__flush_tlb_power7) 1: blr __init_tlb_power8: - li r3,0xc00 /* IS field = 0b11 */ -_GLOBAL(__flush_tlb_power8) li r6,512 mtctr r6 - mr r7,r3 /* IS field */ + li r7,0xc00 /* IS field = 0b11 */ ptesync 2: tlbiel r7 addi r7,r7,0x1000 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index f83046878336..60262fdf35ba 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -71,8 +71,8 @@ extern void __restore_cpu_power7(void); extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __restore_cpu_a2(void); -extern void __flush_tlb_power7(unsigned long inval_selector); -extern void __flush_tlb_power8(unsigned long inval_selector); +extern void __flush_tlb_power7(unsigned int action); +extern void __flush_tlb_power8(unsigned int action); extern long __machine_check_early_realmode_p7(struct pt_regs *regs); extern long __machine_check_early_realmode_p8(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 735979764cd4..6e8d764ce47b 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -116,16 +116,13 @@ void __init swiotlb_detect_4g(void) } } -static int __init swiotlb_late_init(void) +static int __init check_swiotlb_enabled(void) { - if (ppc_swiotlb_enable) { + if (ppc_swiotlb_enable) swiotlb_print_info(); - set_pci_dma_ops(&swiotlb_dma_ops); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; - } else { + else swiotlb_free(); - } return 0; } -subsys_initcall(swiotlb_late_init); +subsys_initcall(check_swiotlb_enabled); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 3b2252e7731b..44b480e3a5af 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -164,30 +164,34 @@ __setup("eeh=", eeh_setup); */ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) { - struct device_node *dn = eeh_dev_to_of_node(edev); + struct pci_dn *pdn = eeh_dev_to_pdn(edev); u32 cfg; int cap, i; int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); - pr_warn("EEH: of node=%s\n", dn->full_name); + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); + eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); pr_warn("EEH: PCI device/vendor: %08x\n", cfg); - eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); + eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); /* Gather bridge-specific registers */ if (edev->mode & EEH_DEV_BRIDGE) { - eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); + eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); pr_warn("EEH: Bridge secondary status: %04x\n", cfg); - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); pr_warn("EEH: Bridge control: %04x\n", cfg); } @@ -195,11 +199,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) /* Dump out the PCI-X command and status regs */ cap = edev->pcix_cap; if (cap) { - eeh_ops->read_config(dn, cap, 4, &cfg); + eeh_ops->read_config(pdn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); pr_warn("EEH: PCI-X cmd: %08x\n", cfg); - eeh_ops->read_config(dn, cap+4, 4, &cfg); + eeh_ops->read_config(pdn, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); pr_warn("EEH: PCI-X status: %08x\n", cfg); } @@ -211,7 +215,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + eeh_ops->read_config(pdn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); if ((i % 4) == 0) { @@ -238,7 +242,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) pr_warn("EEH: PCI-E AER capability register set follows:\n"); for (i=0; i<=13; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + eeh_ops->read_config(pdn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); if ((i % 4) == 0) { @@ -330,9 +334,11 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) int hugepage_shift; /* - * We won't find hugepages here, iomem + * We won't find hugepages here(this is iomem). Hence we are not + * worried about _PAGE_SPLITTING/collapse. Also we will not hit + * page table free, because of init_mm. */ - ptep = find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift); + ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift); if (!ptep) return token; WARN_ON(hugepage_shift); @@ -414,11 +420,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev) int ret; int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); unsigned long flags; - struct device_node *dn; + struct pci_dn *pdn; struct pci_dev *dev; struct eeh_pe *pe, *parent_pe, *phb_pe; int rc = 0; - const char *location; + const char *location = NULL; eeh_stats.total_mmio_ffs++; @@ -429,15 +435,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev) eeh_stats.no_dn++; return 0; } - dn = eeh_dev_to_of_node(edev); dev = eeh_dev_to_pci_dev(edev); pe = eeh_dev_to_pe(edev); /* Access to IO BARs might get this far and still not want checking. */ if (!pe) { eeh_stats.ignored_check++; - pr_debug("EEH: Ignored check for %s %s\n", - eeh_pci_name(dev), dn->full_name); + pr_debug("EEH: Ignored check for %s\n", + eeh_pci_name(dev)); return 0; } @@ -473,10 +478,13 @@ int eeh_dev_check_failure(struct eeh_dev *edev) if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; if (pe->check_count % EEH_MAX_FAILS == 0) { - location = of_get_property(dn, "ibm,loc-code", NULL); + pdn = eeh_dev_to_pdn(edev); + if (pdn->node) + location = of_get_property(pdn->node, "ibm,loc-code", NULL); printk(KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", - pe->check_count, location, + pe->check_count, + location ? location : "unknown", eeh_driver_name(dev), eeh_pci_name(dev)); printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n", eeh_driver_name(dev)); @@ -667,6 +675,55 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) return rc; } +static void *eeh_disable_and_save_dev_state(void *data, void *userdata) +{ + struct eeh_dev *edev = data; + struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); + struct pci_dev *dev = userdata; + + /* + * The caller should have disabled and saved the + * state for the specified device + */ + if (!pdev || pdev == dev) + return NULL; + + /* Ensure we have D0 power state */ + pci_set_power_state(pdev, PCI_D0); + + /* Save device state */ + pci_save_state(pdev); + + /* + * Disable device to avoid any DMA traffic and + * interrupt from the device + */ + pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE); + + return NULL; +} + +static void *eeh_restore_dev_state(void *data, void *userdata) +{ + struct eeh_dev *edev = data; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); + struct pci_dev *dev = userdata; + + if (!pdev) + return NULL; + + /* Apply customization from firmware */ + if (pdn && eeh_ops->restore_config) + eeh_ops->restore_config(pdn); + + /* The caller should restore state for the specified device */ + if (pdev != dev) + pci_save_state(pdev); + + return NULL; +} + /** * pcibios_set_pcie_slot_reset - Set PCI-E reset state * @dev: pci device struct @@ -689,13 +746,19 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat switch (state) { case pcie_deassert_reset: eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); + eeh_unfreeze_pe(pe, false); eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); break; case pcie_hot_reset: + eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); + eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: + eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); + eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; @@ -815,15 +878,15 @@ out: */ void eeh_save_bars(struct eeh_dev *edev) { + struct pci_dn *pdn; int i; - struct device_node *dn; - if (!edev) + pdn = eeh_dev_to_pdn(edev); + if (!pdn) return; - dn = eeh_dev_to_of_node(edev); for (i = 0; i < 16; i++) - eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); + eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]); /* * For PCI bridges including root port, we need enable bus @@ -914,7 +977,7 @@ static struct notifier_block eeh_reboot_nb = { int eeh_init(void) { struct pci_controller *hose, *tmp; - struct device_node *phb; + struct pci_dn *pdn; static int cnt = 0; int ret = 0; @@ -949,20 +1012,9 @@ int eeh_init(void) return ret; /* Enable EEH for all adapters */ - if (eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb = hose->dn; - traverse_pci_devices(phb, eeh_ops->of_probe, NULL); - } - } else if (eeh_has_flag(EEH_PROBE_MODE_DEV)) { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) - pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL); - } else { - pr_warn("%s: Invalid probe mode %x", - __func__, eeh_subsystem_flags); - return -EINVAL; + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + pdn = hose->pci_data; + traverse_pci_dn(pdn, eeh_ops->probe, NULL); } /* @@ -987,8 +1039,8 @@ int eeh_init(void) core_initcall_sync(eeh_init); /** - * eeh_add_device_early - Enable EEH for the indicated device_node - * @dn: device node for which to set up EEH + * eeh_add_device_early - Enable EEH for the indicated device node + * @pdn: PCI device node for which to set up EEH * * This routine must be used to perform EEH initialization for PCI * devices that were added after system boot (e.g. hotplug, dlpar). @@ -998,44 +1050,41 @@ core_initcall_sync(eeh_init); * on the CEC architecture, type of the device, on earlier boot * command-line arguments & etc. */ -void eeh_add_device_early(struct device_node *dn) +void eeh_add_device_early(struct pci_dn *pdn) { struct pci_controller *phb; + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - /* - * If we're doing EEH probe based on PCI device, we - * would delay the probe until late stage because - * the PCI device isn't available this moment. - */ - if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) + if (!edev || !eeh_enabled()) return; - if (!of_node_to_eeh_dev(dn)) - return; - phb = of_node_to_eeh_dev(dn)->phb; - /* USB Bus children of PCI devices will not have BUID's */ - if (NULL == phb || 0 == phb->buid) + phb = edev->phb; + if (NULL == phb || + (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid)) return; - eeh_ops->of_probe(dn, NULL); + eeh_ops->probe(pdn, NULL); } /** * eeh_add_device_tree_early - Enable EEH for the indicated device - * @dn: device node + * @pdn: PCI device node * * This routine must be used to perform EEH initialization for the * indicated PCI device that was added after system boot (e.g. * hotplug, dlpar). */ -void eeh_add_device_tree_early(struct device_node *dn) +void eeh_add_device_tree_early(struct pci_dn *pdn) { - struct device_node *sib; + struct pci_dn *n; - for_each_child_of_node(dn, sib) - eeh_add_device_tree_early(sib); - eeh_add_device_early(dn); + if (!pdn) + return; + + list_for_each_entry(n, &pdn->child_list, list) + eeh_add_device_tree_early(n); + eeh_add_device_early(pdn); } EXPORT_SYMBOL_GPL(eeh_add_device_tree_early); @@ -1048,7 +1097,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early); */ void eeh_add_device_late(struct pci_dev *dev) { - struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; if (!dev || !eeh_enabled()) @@ -1056,8 +1105,8 @@ void eeh_add_device_late(struct pci_dev *dev) pr_debug("EEH: Adding device %s\n", pci_name(dev)); - dn = pci_device_to_OF_node(dev); - edev = of_node_to_eeh_dev(dn); + pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + edev = pdn_to_eeh_dev(pdn); if (edev->pdev == dev) { pr_debug("EEH: Already referenced !\n"); return; @@ -1089,13 +1138,6 @@ void eeh_add_device_late(struct pci_dev *dev) edev->pdev = dev; dev->dev.archdata.edev = edev; - /* - * We have to do the EEH probe here because the PCI device - * hasn't been created yet in the early stage. - */ - if (eeh_has_flag(EEH_PROBE_MODE_DEV)) - eeh_ops->dev_probe(dev, NULL); - eeh_addr_cache_insert_dev(dev); } diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 07d8a2423a61..eeabeabea49c 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -171,30 +171,27 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo, static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) { - struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; int i; - dn = pci_device_to_OF_node(dev); - if (!dn) { + pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + if (!pdn) { pr_warn("PCI: no pci dn found for dev=%s\n", pci_name(dev)); return; } - edev = of_node_to_eeh_dev(dn); + edev = pdn_to_eeh_dev(pdn); if (!edev) { - pr_warn("PCI: no EEH dev found for dn=%s\n", - dn->full_name); + pr_warn("PCI: no EEH dev found for %s\n", + pci_name(dev)); return; } /* Skip any devices for which EEH is not enabled. */ if (!edev->pe) { -#ifdef DEBUG - pr_info("PCI: skip building address cache for=%s - %s\n", - pci_name(dev), dn->full_name); -#endif + dev_dbg(&dev->dev, "EEH: Skip building address cache\n"); return; } @@ -282,18 +279,18 @@ void eeh_addr_cache_rmv_dev(struct pci_dev *dev) */ void eeh_addr_cache_build(void) { - struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; struct pci_dev *dev = NULL; spin_lock_init(&pci_io_addr_cache_root.piar_lock); for_each_pci_dev(dev) { - dn = pci_device_to_OF_node(dev); - if (!dn) + pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + if (!pdn) continue; - edev = of_node_to_eeh_dev(dn); + edev = pdn_to_eeh_dev(pdn); if (!edev) continue; diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index e5274ee9a75f..aabba94ff9cb 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -43,13 +43,13 @@ /** * eeh_dev_init - Create EEH device according to OF node - * @dn: device node + * @pdn: PCI device node * @data: PHB * * It will create EEH device according to the given OF node. The function * might be called by PCI emunation, DR, PHB hotplug. */ -void *eeh_dev_init(struct device_node *dn, void *data) +void *eeh_dev_init(struct pci_dn *pdn, void *data) { struct pci_controller *phb = data; struct eeh_dev *edev; @@ -63,8 +63,8 @@ void *eeh_dev_init(struct device_node *dn, void *data) } /* Associate EEH device with OF node */ - PCI_DN(dn)->edev = edev; - edev->dn = dn; + pdn->edev = edev; + edev->pdn = pdn; edev->phb = phb; INIT_LIST_HEAD(&edev->list); @@ -80,16 +80,16 @@ void *eeh_dev_init(struct device_node *dn, void *data) */ void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { - struct device_node *dn = phb->dn; + struct pci_dn *root = phb->pci_data; /* EEH PE for PHB */ eeh_phb_pe_create(phb); /* EEH device for PHB */ - eeh_dev_init(dn, phb); + eeh_dev_init(root, phb); /* EEH devices for children OF nodes */ - traverse_pci_devices(dn, eeh_dev_init, phb); + traverse_pci_dn(root, eeh_dev_init, phb); } /** diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d099540c0f56..24768ff3cb73 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -83,28 +83,6 @@ static inline void eeh_pcid_put(struct pci_dev *pdev) module_put(pdev->driver->driver.owner); } -#if 0 -static void print_device_node_tree(struct pci_dn *pdn, int dent) -{ - int i; - struct device_node *pc; - - if (!pdn) - return; - for (i = 0; i < dent; i++) - printk(" "); - printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n", - pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr, - pdn->eeh_pe_config_addr, pdn->node->full_name); - dent += 3; - pc = pdn->node->child; - while (pc) { - print_device_node_tree(PCI_DN(pc), dent); - pc = pc->sibling; - } -} -#endif - /** * eeh_disable_irq - Disable interrupt for the recovering device * @dev: PCI device diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 1e4946c36f9e..35f0b62259bb 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -291,27 +291,25 @@ struct eeh_pe *eeh_pe_get(struct eeh_dev *edev) */ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) { - struct device_node *dn; struct eeh_dev *parent; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); /* * It might have the case for the indirect parent * EEH device already having associated PE, but * the direct parent EEH device doesn't have yet. */ - dn = edev->dn->parent; - while (dn) { + pdn = pdn ? pdn->parent : NULL; + while (pdn) { /* We're poking out of PCI territory */ - if (!PCI_DN(dn)) return NULL; - - parent = of_node_to_eeh_dev(dn); - /* We're poking out of PCI territory */ - if (!parent) return NULL; + parent = pdn_to_eeh_dev(pdn); + if (!parent) + return NULL; if (parent->pe) return parent->pe; - dn = dn->parent; + pdn = pdn->parent; } return NULL; @@ -330,6 +328,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) { struct eeh_pe *pe, *parent; + /* Check if the PE number is valid */ + if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { + pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n", + __func__, edev->config_addr, edev->phb->global_number); + return -EINVAL; + } + /* * Search the PE has been existing or not according * to the PE address. If that has been existing, the @@ -338,21 +343,18 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) */ pe = eeh_pe_get(edev); if (pe && !(pe->type & EEH_PE_INVALID)) { - if (!edev->pe_config_addr) { - pr_err("%s: PE with addr 0x%x already exists\n", - __func__, edev->config_addr); - return -EEXIST; - } - /* Mark the PE as type of PCI bus */ pe->type = EEH_PE_BUS; edev->pe = pe; /* Put the edev to PE */ list_add_tail(&edev->list, &pe->edevs); - pr_debug("EEH: Add %s to Bus PE#%x\n", - edev->dn->full_name, pe->addr); - + pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n", + edev->phb->global_number, + edev->config_addr >> 8, + PCI_SLOT(edev->config_addr & 0xFF), + PCI_FUNC(edev->config_addr & 0xFF), + pe->addr); return 0; } else if (pe && (pe->type & EEH_PE_INVALID)) { list_add_tail(&edev->list, &pe->edevs); @@ -368,9 +370,14 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP); parent = parent->parent; } - pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n", - edev->dn->full_name, pe->addr, pe->parent->addr); + pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device " + "PE#%x, Parent PE#%x\n", + edev->phb->global_number, + edev->config_addr >> 8, + PCI_SLOT(edev->config_addr & 0xFF), + PCI_FUNC(edev->config_addr & 0xFF), + pe->addr, pe->parent->addr); return 0; } @@ -409,8 +416,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) list_add_tail(&pe->child, &parent->child_list); list_add_tail(&edev->list, &pe->edevs); edev->pe = pe; - pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n", - edev->dn->full_name, pe->addr, pe->parent->addr); + pr_debug("EEH: Add %04x:%02x:%02x.%01x to " + "Device PE#%x, Parent PE#%x\n", + edev->phb->global_number, + edev->config_addr >> 8, + PCI_SLOT(edev->config_addr & 0xFF), + PCI_FUNC(edev->config_addr & 0xFF), + pe->addr, pe->parent->addr); return 0; } @@ -430,8 +442,11 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev) int cnt; if (!edev->pe) { - pr_debug("%s: No PE found for EEH device %s\n", - __func__, edev->dn->full_name); + pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n", + __func__, edev->phb->global_number, + edev->config_addr >> 8, + PCI_SLOT(edev->config_addr & 0xFF), + PCI_FUNC(edev->config_addr & 0xFF)); return -EEXIST; } @@ -653,9 +668,9 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state) * blocked on normal path during the stage. So we need utilize * eeh operations, which is always permitted. */ -static void eeh_bridge_check_link(struct eeh_dev *edev, - struct device_node *dn) +static void eeh_bridge_check_link(struct eeh_dev *edev) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); int cap; uint32_t val; int timeout = 0; @@ -675,32 +690,32 @@ static void eeh_bridge_check_link(struct eeh_dev *edev, /* Check slot status */ cap = edev->pcie_cap; - eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val); if (!(val & PCI_EXP_SLTSTA_PDS)) { pr_debug(" No card in the slot (0x%04x) !\n", val); return; } /* Check power status if we have the capability */ - eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val); if (val & PCI_EXP_SLTCAP_PCP) { - eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val); if (val & PCI_EXP_SLTCTL_PCC) { pr_debug(" In power-off state, power it on ...\n"); val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC); val |= (0x0100 & PCI_EXP_SLTCTL_PIC); - eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val); + eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val); msleep(2 * 1000); } } /* Enable link */ - eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val); val &= ~PCI_EXP_LNKCTL_LD; - eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val); + eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val); /* Check link */ - eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val); if (!(val & PCI_EXP_LNKCAP_DLLLARC)) { pr_debug(" No link reporting capability (0x%08x) \n", val); msleep(1000); @@ -713,7 +728,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev, msleep(20); timeout += 20; - eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val); + eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val); if (val & PCI_EXP_LNKSTA_DLLLA) break; } @@ -728,9 +743,9 @@ static void eeh_bridge_check_link(struct eeh_dev *edev, #define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) #define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)]) -static void eeh_restore_bridge_bars(struct eeh_dev *edev, - struct device_node *dn) +static void eeh_restore_bridge_bars(struct eeh_dev *edev) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); int i; /* @@ -738,49 +753,49 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev, * Bus numbers and windows: 0x18 - 0x30 */ for (i = 4; i < 13; i++) - eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); + eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]); /* Rom: 0x38 */ - eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]); + eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]); /* Cache line & Latency timer: 0xC 0xD */ - eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, + eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1, SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, + eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1, SAVED_BYTE(PCI_LATENCY_TIMER)); /* Max latency, min grant, interrupt ping and line: 0x3C */ - eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); + eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]); /* PCI Command: 0x4 */ - eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]); + eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]); /* Check the PCIe link is ready */ - eeh_bridge_check_link(edev, dn); + eeh_bridge_check_link(edev); } -static void eeh_restore_device_bars(struct eeh_dev *edev, - struct device_node *dn) +static void eeh_restore_device_bars(struct eeh_dev *edev) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); int i; u32 cmd; for (i = 4; i < 10; i++) - eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); + eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]); /* 12 == Expansion ROM Address */ - eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]); + eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]); - eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, + eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1, SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, + eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1, SAVED_BYTE(PCI_LATENCY_TIMER)); /* max latency, min grant, interrupt pin and line */ - eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); + eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]); /* * Restore PERR & SERR bits, some devices require it, * don't touch the other command bits */ - eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd); + eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd); if (edev->config_space[1] & PCI_COMMAND_PARITY) cmd |= PCI_COMMAND_PARITY; else @@ -789,7 +804,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev, cmd |= PCI_COMMAND_SERR; else cmd &= ~PCI_COMMAND_SERR; - eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd); + eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd); } /** @@ -804,16 +819,16 @@ static void eeh_restore_device_bars(struct eeh_dev *edev, static void *eeh_restore_one_device_bars(void *data, void *flag) { struct eeh_dev *edev = (struct eeh_dev *)data; - struct device_node *dn = eeh_dev_to_of_node(edev); + struct pci_dn *pdn = eeh_dev_to_pdn(edev); /* Do special restore for bridges */ if (edev->mode & EEH_DEV_BRIDGE) - eeh_restore_bridge_bars(edev, dn); + eeh_restore_bridge_bars(edev); else - eeh_restore_device_bars(edev, dn); + eeh_restore_device_bars(edev); - if (eeh_ops->restore_config) - eeh_ops->restore_config(dn); + if (eeh_ops->restore_config && pdn) + eeh_ops->restore_config(pdn); return NULL; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d180caf2d6de..8ca9434c40e6 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -34,6 +34,7 @@ #include <asm/ftrace.h> #include <asm/hw_irq.h> #include <asm/context_tracking.h> +#include <asm/tm.h> /* * System calls. @@ -145,6 +146,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) andi. r11,r10,_TIF_SYSCALL_DOTRACE bne syscall_dotrace .Lsyscall_dotrace_cont: +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + b 1f +END_FTR_SECTION_IFCLR(CPU_FTR_TM) + extrdi. r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ + beq+ 1f + + /* Doom the transaction and don't perform the syscall: */ + mfmsr r11 + li r12, 1 + rldimi r11, r12, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r11, 0 + li r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) + TABORT(R11) + + b .Lsyscall_exit +1: +#endif cmpldi 0,r0,NR_syscalls bge- syscall_enosys @@ -356,6 +375,11 @@ _GLOBAL(ppc64_swapcontext) bl sys_swapcontext b .Lsyscall_exit +_GLOBAL(ppc_switch_endian) + bl save_nvgprs + bl sys_switch_endian + b .Lsyscall_exit + _GLOBAL(ret_from_fork) bl schedule_tail REST_NVGPRS(r1) diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 05adc8bbdef8..eeaa0d5f69d5 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -94,6 +94,7 @@ _GLOBAL(power7_powersave_common) beq 1f addi r1,r1,INT_FRAME_SIZE ld r0,16(r1) + li r3,0 /* Return 0 (no nap) */ mtlr r0 blr diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index 24b968f8e4d8..63d9cc4d7366 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -71,15 +71,15 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) vaddr = (unsigned long)PCI_FIX_ADDR(addr); if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END) return NULL; - - ptep = find_linux_pte_or_hugepte(init_mm.pgd, vaddr, + /* + * We won't find huge pages here (iomem). Also can't hit + * a page table free due to init_mm + */ + ptep = __find_linux_pte_or_hugepte(init_mm.pgd, vaddr, &hugepage_shift); if (ptep == NULL) paddr = 0; else { - /* - * we don't have hugepages backing iomem - */ WARN_ON(hugepage_shift); paddr = pte_pfn(*ptep) << PAGE_SHIFT; } diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index b6f123ab90ed..2c647b1e62e4 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -28,6 +28,55 @@ #include <asm/mce.h> #include <asm/machdep.h> +static void flush_tlb_206(unsigned int num_sets, unsigned int action) +{ + unsigned long rb; + unsigned int i; + + switch (action) { + case TLB_INVAL_SCOPE_GLOBAL: + rb = TLBIEL_INVAL_SET; + break; + case TLB_INVAL_SCOPE_LPID: + rb = TLBIEL_INVAL_SET_LPID; + break; + default: + BUG(); + break; + } + + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < num_sets; i++) { + asm volatile("tlbiel %0" : : "r" (rb)); + rb += 1 << TLBIEL_INVAL_SET_SHIFT; + } + asm volatile("ptesync" : : : "memory"); +} + +/* + * Generic routine to flush TLB on power7. This routine is used as + * flush_tlb hook in cpu_spec for Power7 processor. + * + * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. + * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. + */ +void __flush_tlb_power7(unsigned int action) +{ + flush_tlb_206(POWER7_TLB_SETS, action); +} + +/* + * Generic routine to flush TLB on power8. This routine is used as + * flush_tlb hook in cpu_spec for power8 processor. + * + * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. + * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. + */ +void __flush_tlb_power8(unsigned int action) +{ + flush_tlb_206(POWER8_TLB_SETS, action); +} + /* flush SLBs and reload */ static void flush_and_reload_slb(void) { @@ -79,7 +128,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) } if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); + cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL); /* reset error bits */ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; } @@ -110,7 +159,7 @@ static long mce_handle_common_ierror(uint64_t srr1) break; case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); + cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL); handled = 1; } break; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 34f7c9b7cd96..1e703f8ebad4 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -26,6 +26,9 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/kmsg_dump.h> +#include <linux/pstore.h> +#include <linux/zlib.h> #include <asm/uaccess.h> #include <asm/nvram.h> #include <asm/rtas.h> @@ -54,6 +57,680 @@ struct nvram_partition { static LIST_HEAD(nvram_partitions); +#ifdef CONFIG_PPC_PSERIES +struct nvram_os_partition rtas_log_partition = { + .name = "ibm,rtas-log", + .req_size = 2079, + .min_size = 1055, + .index = -1, + .os_partition = true +}; +#endif + +struct nvram_os_partition oops_log_partition = { + .name = "lnx,oops-log", + .req_size = 4000, + .min_size = 2000, + .index = -1, + .os_partition = true +}; + +static const char *nvram_os_partitions[] = { +#ifdef CONFIG_PPC_PSERIES + "ibm,rtas-log", +#endif + "lnx,oops-log", + NULL +}; + +static void oops_to_nvram(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason); + +static struct kmsg_dumper nvram_kmsg_dumper = { + .dump = oops_to_nvram +}; + +/* + * For capturing and compressing an oops or panic report... + + * big_oops_buf[] holds the uncompressed text we're capturing. + * + * oops_buf[] holds the compressed text, preceded by a oops header. + * oops header has u16 holding the version of oops header (to differentiate + * between old and new format header) followed by u16 holding the length of + * the compressed* text (*Or uncompressed, if compression fails.) and u64 + * holding the timestamp. oops_buf[] gets written to NVRAM. + * + * oops_log_info points to the header. oops_data points to the compressed text. + * + * +- oops_buf + * | +- oops_data + * v v + * +-----------+-----------+-----------+------------------------+ + * | version | length | timestamp | text | + * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | + * +-----------+-----------+-----------+------------------------+ + * ^ + * +- oops_log_info + * + * We preallocate these buffers during init to avoid kmalloc during oops/panic. + */ +static size_t big_oops_buf_sz; +static char *big_oops_buf, *oops_buf; +static char *oops_data; +static size_t oops_data_sz; + +/* Compression parameters */ +#define COMPR_LEVEL 6 +#define WINDOW_BITS 12 +#define MEM_LEVEL 4 +static struct z_stream_s stream; + +#ifdef CONFIG_PSTORE +#ifdef CONFIG_PPC_POWERNV +static struct nvram_os_partition skiboot_partition = { + .name = "ibm,skiboot", + .index = -1, + .os_partition = false +}; +#endif + +#ifdef CONFIG_PPC_PSERIES +static struct nvram_os_partition of_config_partition = { + .name = "of-config", + .index = -1, + .os_partition = false +}; +#endif + +static struct nvram_os_partition common_partition = { + .name = "common", + .index = -1, + .os_partition = false +}; + +static enum pstore_type_id nvram_type_ids[] = { + PSTORE_TYPE_DMESG, + PSTORE_TYPE_PPC_COMMON, + -1, + -1, + -1 +}; +static int read_type; +#endif + +/* nvram_write_os_partition + * + * We need to buffer the error logs into nvram to ensure that we have + * the failure information to decode. If we have a severe error there + * is no way to guarantee that the OS or the machine is in a state to + * get back to user land and write the error to disk. For example if + * the SCSI device driver causes a Machine Check by writing to a bad + * IO address, there is no way of guaranteeing that the device driver + * is in any state that is would also be able to write the error data + * captured to disk, thus we buffer it in NVRAM for analysis on the + * next boot. + * + * In NVRAM the partition containing the error log buffer will looks like: + * Header (in bytes): + * +-----------+----------+--------+------------+------------------+ + * | signature | checksum | length | name | data | + * |0 |1 |2 3|4 15|16 length-1| + * +-----------+----------+--------+------------+------------------+ + * + * The 'data' section would look like (in bytes): + * +--------------+------------+-----------------------------------+ + * | event_logged | sequence # | error log | + * |0 3|4 7|8 error_log_size-1| + * +--------------+------------+-----------------------------------+ + * + * event_logged: 0 if event has not been logged to syslog, 1 if it has + * sequence #: The unique sequence # for each event. (until it wraps) + * error log: The error log from event_scan + */ +int nvram_write_os_partition(struct nvram_os_partition *part, + char *buff, int length, + unsigned int err_type, + unsigned int error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (part->index == -1) + return -ESPIPE; + + if (length > part->size) + length = part->size; + + info.error_type = cpu_to_be32(err_type); + info.seq_num = cpu_to_be32(error_log_cnt); + + tmp_index = part->index; + + rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), + &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); + return rc; + } + + rc = ppc_md.nvram_write(buff, length, &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); + return rc; + } + + return 0; +} + +/* nvram_read_partition + * + * Reads nvram partition for at most 'length' + */ +int nvram_read_partition(struct nvram_os_partition *part, char *buff, + int length, unsigned int *err_type, + unsigned int *error_log_cnt) +{ + int rc; + loff_t tmp_index; + struct err_log_info info; + + if (part->index == -1) + return -1; + + if (length > part->size) + length = part->size; + + tmp_index = part->index; + + if (part->os_partition) { + rc = ppc_md.nvram_read((char *)&info, + sizeof(struct err_log_info), + &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); + return rc; + } + } + + rc = ppc_md.nvram_read(buff, length, &tmp_index); + if (rc <= 0) { + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); + return rc; + } + + if (part->os_partition) { + *error_log_cnt = be32_to_cpu(info.seq_num); + *err_type = be32_to_cpu(info.error_type); + } + + return 0; +} + +/* nvram_init_os_partition + * + * This sets up a partition with an "OS" signature. + * + * The general strategy is the following: + * 1.) If a partition with the indicated name already exists... + * - If it's large enough, use it. + * - Otherwise, recycle it and keep going. + * 2.) Search for a free partition that is large enough. + * 3.) If there's not a free partition large enough, recycle any obsolete + * OS partitions and try again. + * 4.) Will first try getting a chunk that will satisfy the requested size. + * 5.) If a chunk of the requested size cannot be allocated, then try finding + * a chunk that will satisfy the minum needed. + * + * Returns 0 on success, else -1. + */ +int __init nvram_init_os_partition(struct nvram_os_partition *part) +{ + loff_t p; + int size; + + /* Look for ours */ + p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); + + /* Found one but too small, remove it */ + if (p && size < part->min_size) { + pr_info("nvram: Found too small %s partition," + " removing it...\n", part->name); + nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL); + p = 0; + } + + /* Create one if we didn't find */ + if (!p) { + p = nvram_create_partition(part->name, NVRAM_SIG_OS, + part->req_size, part->min_size); + if (p == -ENOSPC) { + pr_info("nvram: No room to create %s partition, " + "deleting any obsolete OS partitions...\n", + part->name); + nvram_remove_partition(NULL, NVRAM_SIG_OS, + nvram_os_partitions); + p = nvram_create_partition(part->name, NVRAM_SIG_OS, + part->req_size, part->min_size); + } + } + + if (p <= 0) { + pr_err("nvram: Failed to find or create %s" + " partition, err %d\n", part->name, (int)p); + return -1; + } + + part->index = p; + part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info); + + return 0; +} + +/* Derived from logfs_compress() */ +static int nvram_compress(const void *in, void *out, size_t inlen, + size_t outlen) +{ + int err, ret; + + ret = -EIO; + err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, + MEM_LEVEL, Z_DEFAULT_STRATEGY); + if (err != Z_OK) + goto error; + + stream.next_in = in; + stream.avail_in = inlen; + stream.total_in = 0; + stream.next_out = out; + stream.avail_out = outlen; + stream.total_out = 0; + + err = zlib_deflate(&stream, Z_FINISH); + if (err != Z_STREAM_END) + goto error; + + err = zlib_deflateEnd(&stream); + if (err != Z_OK) + goto error; + + if (stream.total_out >= stream.total_in) + goto error; + + ret = stream.total_out; +error: + return ret; +} + +/* Compress the text from big_oops_buf into oops_buf. */ +static int zip_oops(size_t text_len) +{ + struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; + int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len, + oops_data_sz); + if (zipped_len < 0) { + pr_err("nvram: compression failed; returned %d\n", zipped_len); + pr_err("nvram: logging uncompressed oops/panic report\n"); + return -1; + } + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(zipped_len); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + return 0; +} + +#ifdef CONFIG_PSTORE +static int nvram_pstore_open(struct pstore_info *psi) +{ + /* Reset the iterator to start reading partitions again */ + read_type = -1; + return 0; +} + +/** + * nvram_pstore_write - pstore write callback for nvram + * @type: Type of message logged + * @reason: reason behind dump (oops/panic) + * @id: identifier to indicate the write performed + * @part: pstore writes data to registered buffer in parts, + * part number will indicate the same. + * @count: Indicates oops count + * @compressed: Flag to indicate the log is compressed + * @size: number of bytes written to the registered buffer + * @psi: registered pstore_info structure + * + * Called by pstore_dump() when an oops or panic report is logged in the + * printk buffer. + * Returns 0 on successful write. + */ +static int nvram_pstore_write(enum pstore_type_id type, + enum kmsg_dump_reason reason, + u64 *id, unsigned int part, int count, + bool compressed, size_t size, + struct pstore_info *psi) +{ + int rc; + unsigned int err_type = ERR_TYPE_KERNEL_PANIC; + struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; + + /* part 1 has the recent messages from printk buffer */ + if (part > 1 || (type != PSTORE_TYPE_DMESG)) + return -1; + + if (clobbering_unread_rtas_event()) + return -1; + + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(size); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + + if (compressed) + err_type = ERR_TYPE_KERNEL_PANIC_GZ; + + rc = nvram_write_os_partition(&oops_log_partition, oops_buf, + (int) (sizeof(*oops_hdr) + size), err_type, count); + + if (rc != 0) + return rc; + + *id = part; + return 0; +} + +/* + * Reads the oops/panic report, rtas, of-config and common partition. + * Returns the length of the data we read from each partition. + * Returns 0 if we've been called before. + */ +static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, + int *count, struct timespec *time, char **buf, + bool *compressed, struct pstore_info *psi) +{ + struct oops_log_info *oops_hdr; + unsigned int err_type, id_no, size = 0; + struct nvram_os_partition *part = NULL; + char *buff = NULL; + int sig = 0; + loff_t p; + + read_type++; + + switch (nvram_type_ids[read_type]) { + case PSTORE_TYPE_DMESG: + part = &oops_log_partition; + *type = PSTORE_TYPE_DMESG; + break; + case PSTORE_TYPE_PPC_COMMON: + sig = NVRAM_SIG_SYS; + part = &common_partition; + *type = PSTORE_TYPE_PPC_COMMON; + *id = PSTORE_TYPE_PPC_COMMON; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#ifdef CONFIG_PPC_PSERIES + case PSTORE_TYPE_PPC_RTAS: + part = &rtas_log_partition; + *type = PSTORE_TYPE_PPC_RTAS; + time->tv_sec = last_rtas_event; + time->tv_nsec = 0; + break; + case PSTORE_TYPE_PPC_OF: + sig = NVRAM_SIG_OF; + part = &of_config_partition; + *type = PSTORE_TYPE_PPC_OF; + *id = PSTORE_TYPE_PPC_OF; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#endif +#ifdef CONFIG_PPC_POWERNV + case PSTORE_TYPE_PPC_OPAL: + sig = NVRAM_SIG_FW; + part = &skiboot_partition; + *type = PSTORE_TYPE_PPC_OPAL; + *id = PSTORE_TYPE_PPC_OPAL; + time->tv_sec = 0; + time->tv_nsec = 0; + break; +#endif + default: + return 0; + } + + if (!part->os_partition) { + p = nvram_find_partition(part->name, sig, &size); + if (p <= 0) { + pr_err("nvram: Failed to find partition %s, " + "err %d\n", part->name, (int)p); + return 0; + } + part->index = p; + part->size = size; + } + + buff = kmalloc(part->size, GFP_KERNEL); + + if (!buff) + return -ENOMEM; + + if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) { + kfree(buff); + return 0; + } + + *count = 0; + + if (part->os_partition) + *id = id_no; + + if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { + size_t length, hdr_size; + + oops_hdr = (struct oops_log_info *)buff; + if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { + /* Old format oops header had 2-byte record size */ + hdr_size = sizeof(u16); + length = be16_to_cpu(oops_hdr->version); + time->tv_sec = 0; + time->tv_nsec = 0; + } else { + hdr_size = sizeof(*oops_hdr); + length = be16_to_cpu(oops_hdr->report_length); + time->tv_sec = be64_to_cpu(oops_hdr->timestamp); + time->tv_nsec = 0; + } + *buf = kmalloc(length, GFP_KERNEL); + if (*buf == NULL) + return -ENOMEM; + memcpy(*buf, buff + hdr_size, length); + kfree(buff); + + if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) + *compressed = true; + else + *compressed = false; + return length; + } + + *buf = buff; + return part->size; +} + +static struct pstore_info nvram_pstore_info = { + .owner = THIS_MODULE, + .name = "nvram", + .open = nvram_pstore_open, + .read = nvram_pstore_read, + .write = nvram_pstore_write, +}; + +static int nvram_pstore_init(void) +{ + int rc = 0; + + if (machine_is(pseries)) { + nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS; + nvram_type_ids[3] = PSTORE_TYPE_PPC_OF; + } else + nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL; + + nvram_pstore_info.buf = oops_data; + nvram_pstore_info.bufsize = oops_data_sz; + + spin_lock_init(&nvram_pstore_info.buf_lock); + + rc = pstore_register(&nvram_pstore_info); + if (rc != 0) + pr_err("nvram: pstore_register() failed, defaults to " + "kmsg_dump; returned %d\n", rc); + + return rc; +} +#else +static int nvram_pstore_init(void) +{ + return -1; +} +#endif + +void __init nvram_init_oops_partition(int rtas_partition_exists) +{ + int rc; + + rc = nvram_init_os_partition(&oops_log_partition); + if (rc != 0) { +#ifdef CONFIG_PPC_PSERIES + if (!rtas_partition_exists) { + pr_err("nvram: Failed to initialize oops partition!"); + return; + } + pr_notice("nvram: Using %s partition to log both" + " RTAS errors and oops/panic reports\n", + rtas_log_partition.name); + memcpy(&oops_log_partition, &rtas_log_partition, + sizeof(rtas_log_partition)); +#else + pr_err("nvram: Failed to initialize oops partition!"); + return; +#endif + } + oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL); + if (!oops_buf) { + pr_err("nvram: No memory for %s partition\n", + oops_log_partition.name); + return; + } + oops_data = oops_buf + sizeof(struct oops_log_info); + oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); + + rc = nvram_pstore_init(); + + if (!rc) + return; + + /* + * Figure compression (preceded by elimination of each line's <n> + * severity prefix) will reduce the oops/panic report to at most + * 45% of its original size. + */ + big_oops_buf_sz = (oops_data_sz * 100) / 45; + big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); + if (big_oops_buf) { + stream.workspace = kmalloc(zlib_deflate_workspacesize( + WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); + if (!stream.workspace) { + pr_err("nvram: No memory for compression workspace; " + "skipping compression of %s partition data\n", + oops_log_partition.name); + kfree(big_oops_buf); + big_oops_buf = NULL; + } + } else { + pr_err("No memory for uncompressed %s data; " + "skipping compression\n", oops_log_partition.name); + stream.workspace = NULL; + } + + rc = kmsg_dump_register(&nvram_kmsg_dumper); + if (rc != 0) { + pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); + kfree(oops_buf); + kfree(big_oops_buf); + kfree(stream.workspace); + } +} + +/* + * This is our kmsg_dump callback, called after an oops or panic report + * has been written to the printk buffer. We want to capture as much + * of the printk buffer as possible. First, capture as much as we can + * that we think will compress sufficiently to fit in the lnx,oops-log + * partition. If that's too much, go back and capture uncompressed text. + */ +static void oops_to_nvram(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; + static unsigned int oops_count = 0; + static bool panicking = false; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + size_t text_len; + unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; + int rc = -1; + + switch (reason) { + case KMSG_DUMP_RESTART: + case KMSG_DUMP_HALT: + case KMSG_DUMP_POWEROFF: + /* These are almost always orderly shutdowns. */ + return; + case KMSG_DUMP_OOPS: + break; + case KMSG_DUMP_PANIC: + panicking = true; + break; + case KMSG_DUMP_EMERG: + if (panicking) + /* Panic report already captured. */ + return; + break; + default: + pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", + __func__, (int) reason); + return; + } + + if (clobbering_unread_rtas_event()) + return; + + if (!spin_trylock_irqsave(&lock, flags)) + return; + + if (big_oops_buf) { + kmsg_dump_get_buffer(dumper, false, + big_oops_buf, big_oops_buf_sz, &text_len); + rc = zip_oops(text_len); + } + if (rc != 0) { + kmsg_dump_rewind(dumper); + kmsg_dump_get_buffer(dumper, false, + oops_data, oops_data_sz, &text_len); + err_type = ERR_TYPE_KERNEL_PANIC; + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(text_len); + oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds()); + } + + (void) nvram_write_os_partition(&oops_log_partition, oops_buf, + (int) (sizeof(*oops_hdr) + text_len), err_type, + ++oops_count); + + spin_unlock_irqrestore(&lock, flags); +} + static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) { int size; diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 2f35a72642c6..b60a67d92ebd 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -72,7 +72,7 @@ static int of_pci_phb_probe(struct platform_device *dev) /* Register devices with EEH */ if (dev->dev.of_node->child) - eeh_add_device_tree_early(dev->dev.of_node); + eeh_add_device_tree_early(PCI_DN(dev->dev.of_node)); /* Scan the bus */ pcibios_scan_phb(phb); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2a525c938158..0d054068a21d 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -76,7 +76,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) list_add_tail(&phb->list_node, &hose_list); spin_unlock(&hose_spinlock); phb->dn = dev; - phb->is_dynamic = mem_init_done; + phb->is_dynamic = slab_is_available(); #ifdef CONFIG_PPC64 if (dev) { int nid = of_node_to_nid(dev); @@ -109,8 +109,10 @@ void pcibios_free_controller(struct pci_controller *phb) resource_size_t pcibios_window_alignment(struct pci_bus *bus, unsigned long type) { - if (ppc_md.pcibios_window_alignment) - return ppc_md.pcibios_window_alignment(bus, type); + struct pci_controller *phb = pci_bus_to_host(bus); + + if (phb->controller_ops.window_alignment) + return phb->controller_ops.window_alignment(bus, type); /* * PCI core will figure out the default @@ -122,14 +124,26 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, void pcibios_reset_secondary_bus(struct pci_dev *dev) { - if (ppc_md.pcibios_reset_secondary_bus) { - ppc_md.pcibios_reset_secondary_bus(dev); + struct pci_controller *phb = pci_bus_to_host(dev->bus); + + if (phb->controller_ops.reset_secondary_bus) { + phb->controller_ops.reset_secondary_bus(dev); return; } pci_reset_secondary_bus(dev); } +#ifdef CONFIG_PCI_IOV +resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno) +{ + if (ppc_md.pcibios_iov_resource_alignment) + return ppc_md.pcibios_iov_resource_alignment(pdev, resno); + + return pci_iov_resource_size(pdev, resno); +} +#endif /* CONFIG_PCI_IOV */ + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -788,6 +802,10 @@ static void pcibios_fixup_resources(struct pci_dev *dev) pci_name(dev)); return; } + + if (dev->is_virtfn) + return; + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { struct resource *res = dev->resource + i; struct pci_bus_region reg; @@ -942,6 +960,8 @@ static void pcibios_fixup_bridge(struct pci_bus *bus) void pcibios_setup_bus_self(struct pci_bus *bus) { + struct pci_controller *phb; + /* Fix up the bus resources for P2P bridges */ if (bus->self != NULL) pcibios_fixup_bridge(bus); @@ -953,12 +973,14 @@ void pcibios_setup_bus_self(struct pci_bus *bus) ppc_md.pcibios_fixup_bus(bus); /* Setup bus DMA mappings */ - if (ppc_md.pci_dma_bus_setup) - ppc_md.pci_dma_bus_setup(bus); + phb = pci_bus_to_host(bus); + if (phb->controller_ops.dma_bus_setup) + phb->controller_ops.dma_bus_setup(bus); } static void pcibios_setup_device(struct pci_dev *dev) { + struct pci_controller *phb; /* Fixup NUMA node as it may not be setup yet by the generic * code and is needed by the DMA init */ @@ -969,8 +991,9 @@ static void pcibios_setup_device(struct pci_dev *dev) set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); /* Additional platform DMA/iommu setup */ - if (ppc_md.pci_dma_dev_setup) - ppc_md.pci_dma_dev_setup(dev); + phb = pci_bus_to_host(dev->bus); + if (phb->controller_ops.dma_dev_setup) + phb->controller_ops.dma_dev_setup(dev); /* Read default IRQs and fixup if necessary */ pci_read_irq_line(dev); @@ -986,6 +1009,12 @@ int pcibios_add_device(struct pci_dev *dev) */ if (dev->bus->is_added) pcibios_setup_device(dev); + +#ifdef CONFIG_PCI_IOV + if (ppc_md.pcibios_fixup_sriov) + ppc_md.pcibios_fixup_sriov(dev); +#endif /* CONFIG_PCI_IOV */ + return 0; } @@ -1450,8 +1479,10 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus); int pcibios_enable_device(struct pci_dev *dev, int mask) { - if (ppc_md.pcibios_enable_device_hook) - if (ppc_md.pcibios_enable_device_hook(dev)) + struct pci_controller *phb = pci_bus_to_host(dev->bus); + + if (phb->controller_ops.enable_device_hook) + if (!phb->controller_ops.enable_device_hook(dev)) return -EINVAL; return pci_enable_resources(dev, mask); @@ -1624,8 +1655,8 @@ void pcibios_scan_phb(struct pci_controller *hose) /* Get probe mode and perform scan */ mode = PCI_PROBE_NORMAL; - if (node && ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); + if (node && hose->controller_ops.probe_mode) + mode = hose->controller_ops.probe_mode(bus); pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) of_scan_bus(node, bus); diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 5b789177aa29..7ed85a69a9c2 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -73,13 +73,16 @@ void pcibios_add_pci_devices(struct pci_bus * bus) { int slotno, mode, pass, max; struct pci_dev *dev; + struct pci_controller *phb; struct device_node *dn = pci_bus_to_OF_node(bus); - eeh_add_device_tree_early(dn); + eeh_add_device_tree_early(PCI_DN(dn)); + + phb = pci_bus_to_host(bus); mode = PCI_PROBE_NORMAL; - if (ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); + if (phb->controller_ops.probe_mode) + mode = phb->controller_ops.probe_mode(bus); if (mode == PCI_PROBE_DEVTREE) { /* use ofdt-based probe */ diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 83df3075d3df..b3b4df91b792 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -32,12 +32,237 @@ #include <asm/ppc-pci.h> #include <asm/firmware.h> +/* + * The function is used to find the firmware data of one + * specific PCI device, which is attached to the indicated + * PCI bus. For VFs, their firmware data is linked to that + * one of PF's bridge. For other devices, their firmware + * data is linked to that of their bridge. + */ +static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus) +{ + struct pci_bus *pbus; + struct device_node *dn; + struct pci_dn *pdn; + + /* + * We probably have virtual bus which doesn't + * have associated bridge. + */ + pbus = bus; + while (pbus) { + if (pci_is_root_bus(pbus) || pbus->self) + break; + + pbus = pbus->parent; + } + + /* + * Except virtual bus, all PCI buses should + * have device nodes. + */ + dn = pci_bus_to_OF_node(pbus); + pdn = dn ? PCI_DN(dn) : NULL; + + return pdn; +} + +struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus, + int devfn) +{ + struct device_node *dn = NULL; + struct pci_dn *parent, *pdn; + struct pci_dev *pdev = NULL; + + /* Fast path: fetch from PCI device */ + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (pdev->devfn == devfn) { + if (pdev->dev.archdata.pci_data) + return pdev->dev.archdata.pci_data; + + dn = pci_device_to_OF_node(pdev); + break; + } + } + + /* Fast path: fetch from device node */ + pdn = dn ? PCI_DN(dn) : NULL; + if (pdn) + return pdn; + + /* Slow path: fetch from firmware data hierarchy */ + parent = pci_bus_to_pdn(bus); + if (!parent) + return NULL; + + list_for_each_entry(pdn, &parent->child_list, list) { + if (pdn->busno == bus->number && + pdn->devfn == devfn) + return pdn; + } + + return NULL; +} + struct pci_dn *pci_get_pdn(struct pci_dev *pdev) { - struct device_node *dn = pci_device_to_OF_node(pdev); - if (!dn) + struct device_node *dn; + struct pci_dn *parent, *pdn; + + /* Search device directly */ + if (pdev->dev.archdata.pci_data) + return pdev->dev.archdata.pci_data; + + /* Check device node */ + dn = pci_device_to_OF_node(pdev); + pdn = dn ? PCI_DN(dn) : NULL; + if (pdn) + return pdn; + + /* + * VFs don't have device nodes. We hook their + * firmware data to PF's bridge. + */ + parent = pci_bus_to_pdn(pdev->bus); + if (!parent) + return NULL; + + list_for_each_entry(pdn, &parent->child_list, list) { + if (pdn->busno == pdev->bus->number && + pdn->devfn == pdev->devfn) + return pdn; + } + + return NULL; +} + +#ifdef CONFIG_PCI_IOV +static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, + struct pci_dev *pdev, + int busno, int devfn) +{ + struct pci_dn *pdn; + + /* Except PHB, we always have the parent */ + if (!parent) + return NULL; + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) { + dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__); return NULL; - return PCI_DN(dn); + } + + pdn->phb = parent->phb; + pdn->parent = parent; + pdn->busno = busno; + pdn->devfn = devfn; +#ifdef CONFIG_PPC_POWERNV + pdn->pe_number = IODA_INVALID_PE; +#endif + INIT_LIST_HEAD(&pdn->child_list); + INIT_LIST_HEAD(&pdn->list); + list_add_tail(&pdn->list, &parent->child_list); + + /* + * If we already have PCI device instance, lets + * bind them. + */ + if (pdev) + pdev->dev.archdata.pci_data = pdn; + + return pdn; +} +#endif + +struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) +{ +#ifdef CONFIG_PCI_IOV + struct pci_dn *parent, *pdn; + int i; + + /* Only support IOV for now */ + if (!pdev->is_physfn) + return pci_get_pdn(pdev); + + /* Check if VFs have been populated */ + pdn = pci_get_pdn(pdev); + if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF)) + return NULL; + + pdn->flags |= PCI_DN_FLAG_IOV_VF; + parent = pci_bus_to_pdn(pdev->bus); + if (!parent) + return NULL; + + for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { + pdn = add_one_dev_pci_data(parent, NULL, + pci_iov_virtfn_bus(pdev, i), + pci_iov_virtfn_devfn(pdev, i)); + if (!pdn) { + dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n", + __func__, i); + return NULL; + } + } +#endif /* CONFIG_PCI_IOV */ + + return pci_get_pdn(pdev); +} + +void remove_dev_pci_data(struct pci_dev *pdev) +{ +#ifdef CONFIG_PCI_IOV + struct pci_dn *parent; + struct pci_dn *pdn, *tmp; + int i; + + /* + * VF and VF PE are created/released dynamically, so we need to + * bind/unbind them. Otherwise the VF and VF PE would be mismatched + * when re-enabling SR-IOV. + */ + if (pdev->is_virtfn) { + pdn = pci_get_pdn(pdev); +#ifdef CONFIG_PPC_POWERNV + pdn->pe_number = IODA_INVALID_PE; +#endif + return; + } + + /* Only support IOV PF for now */ + if (!pdev->is_physfn) + return; + + /* Check if VFs have been populated */ + pdn = pci_get_pdn(pdev); + if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF)) + return; + + pdn->flags &= ~PCI_DN_FLAG_IOV_VF; + parent = pci_bus_to_pdn(pdev->bus); + if (!parent) + return; + + /* + * We might introduce flag to pci_dn in future + * so that we can release VF's firmware data in + * a batch mode. + */ + for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { + list_for_each_entry_safe(pdn, tmp, + &parent->child_list, list) { + if (pdn->busno != pci_iov_virtfn_bus(pdev, i) || + pdn->devfn != pci_iov_virtfn_devfn(pdev, i)) + continue; + + if (!list_empty(&pdn->list)) + list_del(&pdn->list); + + kfree(pdn); + } + } +#endif /* CONFIG_PCI_IOV */ } /* @@ -49,6 +274,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data) struct pci_controller *phb = data; const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL); const __be32 *regs; + struct device_node *parent; struct pci_dn *pdn; pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); @@ -69,7 +295,25 @@ void *update_dn_pci_info(struct device_node *dn, void *data) pdn->devfn = (addr >> 8) & 0xff; } + /* vendor/device IDs and class code */ + regs = of_get_property(dn, "vendor-id", NULL); + pdn->vendor_id = regs ? of_read_number(regs, 1) : 0; + regs = of_get_property(dn, "device-id", NULL); + pdn->device_id = regs ? of_read_number(regs, 1) : 0; + regs = of_get_property(dn, "class-code", NULL); + pdn->class_code = regs ? of_read_number(regs, 1) : 0; + + /* Extended config space */ pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1); + + /* Attach to parent node */ + INIT_LIST_HEAD(&pdn->child_list); + INIT_LIST_HEAD(&pdn->list); + parent = of_get_parent(dn); + pdn->parent = parent ? PCI_DN(parent) : NULL; + if (pdn->parent) + list_add_tail(&pdn->list, &pdn->parent->child_list); + return NULL; } @@ -131,6 +375,46 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre, return NULL; } +static struct pci_dn *pci_dn_next_one(struct pci_dn *root, + struct pci_dn *pdn) +{ + struct list_head *next = pdn->child_list.next; + + if (next != &pdn->child_list) + return list_entry(next, struct pci_dn, list); + + while (1) { + if (pdn == root) + return NULL; + + next = pdn->list.next; + if (next != &pdn->parent->child_list) + break; + + pdn = pdn->parent; + } + + return list_entry(next, struct pci_dn, list); +} + +void *traverse_pci_dn(struct pci_dn *root, + void *(*fn)(struct pci_dn *, void *), + void *data) +{ + struct pci_dn *pdn = root; + void *ret; + + /* Only scan the child nodes */ + for (pdn = pci_dn_next_one(root, pdn); pdn; + pdn = pci_dn_next_one(root, pdn)) { + ret = fn(pdn, data); + if (ret) + return ret; + } + + return NULL; +} + /** * pci_devs_phb_init_dynamic - setup pci devices under this PHB * phb: pci-to-host bridge (top-level bridge connecting to cpu) @@ -147,8 +431,12 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb) /* PHB nodes themselves must not match */ update_dn_pci_info(dn, phb); pdn = dn->data; - if (pdn) + if (pdn) { pdn->devfn = pdn->busno = -1; + pdn->vendor_id = pdn->device_id = pdn->class_code = 0; + pdn->phb = phb; + phb->pci_data = pdn; + } /* Update dn->phb ptrs for new phb and children devices */ traverse_pci_devices(dn, update_dn_pci_info, phb); @@ -171,3 +459,16 @@ void __init pci_devs_phb_init(void) list_for_each_entry_safe(phb, tmp, &hose_list, list_node) pci_devs_phb_init_dynamic(phb); } + +static void pci_dev_pdn_setup(struct pci_dev *pdev) +{ + struct pci_dn *pdn; + + if (pdev->dev.archdata.pci_data) + return; + + /* Setup the fast path */ + pdn = pci_get_pdn(pdev); + pdev->dev.archdata.pci_data = pdn; +} +DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index e6245e9c7d8d..42e02a2d570b 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -207,6 +207,7 @@ void of_scan_pci_bridge(struct pci_dev *dev) { struct device_node *node = dev->dev.of_node; struct pci_bus *bus; + struct pci_controller *phb; const __be32 *busrange, *ranges; int len, i, mode; struct pci_bus_region region; @@ -286,9 +287,11 @@ void of_scan_pci_bridge(struct pci_dev *dev) bus->number); pr_debug(" bus name: %s\n", bus->name); + phb = pci_bus_to_host(bus); + mode = PCI_PROBE_NORMAL; - if (ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); + if (phb->controller_ops.probe_mode) + mode = phb->controller_ops.probe_mode(bus); pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) @@ -305,7 +308,7 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, const __be32 *reg; int reglen, devfn; #ifdef CONFIG_EEH - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(PCI_DN(dn)); #endif pr_debug(" * %s\n", dn->full_name); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b4cc7bef6b16..febb50dd5328 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1114,8 +1114,11 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) */ extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ +/* + * Copy architecture-specific thread state + */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) + unsigned long kthread_arg, struct task_struct *p) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); @@ -1127,6 +1130,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; if (unlikely(p->flags & PF_KTHREAD)) { + /* kernel thread */ struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); @@ -1137,11 +1141,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = 1; #endif - childregs->gpr[15] = arg; + childregs->gpr[15] = kthread_arg; p->thread.regs = NULL; /* no user register state */ ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; } else { + /* user thread */ struct pt_regs *regs = current_pt_regs(); CHECK_FULL_REGS(regs); *childregs = *regs; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 1a85d8f96739..fd1fe4c37599 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2898,7 +2898,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * Call OF "quiesce" method to shut down pending DMA's from * devices etc... */ - prom_printf("Calling quiesce...\n"); + prom_printf("Quiescing Open Firmware ...\n"); call_prom("quiesce", 0, 0); /* @@ -2910,7 +2910,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("returning from prom_init\n"); + prom_printf("Booting Linux via __start() ...\n"); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 21c45a2d0706..7a488c108410 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -401,7 +401,7 @@ static char *__fetch_rtas_last_error(char *altbuf) buf = altbuf; } else { buf = rtas_err_buf; - if (mem_init_done) + if (slab_is_available()) buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); } if (buf) @@ -461,7 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) if (buff_copy) { log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0); - if (mem_init_done) + if (slab_is_available()) kfree(buff_copy); } return ret; @@ -897,7 +897,7 @@ int rtas_offline_cpus_mask(cpumask_var_t cpus) } EXPORT_SYMBOL(rtas_offline_cpus_mask); -int rtas_ibm_suspend_me(u64 handle, int *vasi_return) +int rtas_ibm_suspend_me(u64 handle) { long state; long rc; @@ -919,13 +919,11 @@ int rtas_ibm_suspend_me(u64 handle, int *vasi_return) printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc); return rc; } else if (state == H_VASI_ENABLED) { - *vasi_return = RTAS_NOT_SUSPENDABLE; - return 0; + return -EAGAIN; } else if (state != H_VASI_SUSPENDING) { printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n", state); - *vasi_return = -1; - return 0; + return -EIO; } if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) @@ -972,7 +970,7 @@ out: return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ -int rtas_ibm_suspend_me(u64 handle, int *vasi_return) +int rtas_ibm_suspend_me(u64 handle) { return -ENOSYS; } @@ -1022,7 +1020,6 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) unsigned long flags; char *buff_copy, *errbuf = NULL; int nargs, nret, token; - int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1054,15 +1051,18 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) if (token == ibm_suspend_me_token) { /* - * rtas_ibm_suspend_me assumes args are in cpu endian, or at least the - * hcall within it requires it. + * rtas_ibm_suspend_me assumes the streamid handle is in cpu + * endian, or at least the hcall within it requires it. */ - int vasi_rc = 0; + int rc = 0; u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32) | be32_to_cpu(args.args[1]); - rc = rtas_ibm_suspend_me(handle, &vasi_rc); - args.rets[0] = cpu_to_be32(vasi_rc); - if (rc) + rc = rtas_ibm_suspend_me(handle); + if (rc == -EAGAIN) + args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE); + else if (rc == -EIO) + args.rets[0] = cpu_to_be32(-1); + else if (rc) return rc; goto copy_return; } diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index ce230da2c015..73f1934582c2 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -113,7 +113,7 @@ static int rtas_pci_read_config(struct pci_bus *bus, ret = rtas_read_config(pdn, where, size, val); if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + eeh_dev_check_failure(pdn_to_eeh_dev(pdn))) return PCIBIOS_DEVICE_NOT_FOUND; return ret; @@ -277,50 +277,3 @@ int rtas_setup_phb(struct pci_controller *phb) return 0; } - -void __init find_and_init_phbs(void) -{ - struct device_node *node; - struct pci_controller *phb; - struct device_node *root = of_find_node_by_path("/"); - - for_each_child_of_node(root, node) { - if (node->type == NULL || (strcmp(node->type, "pci") != 0 && - strcmp(node->type, "pciex") != 0)) - continue; - - phb = pcibios_alloc_controller(node); - if (!phb) - continue; - rtas_setup_phb(phb); - pci_process_bridge_OF_ranges(phb, node, 0); - isa_bridge_find_early(phb); - } - - of_node_put(root); - pci_devs_phb_init(); - - /* - * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties - * in chosen. - */ - if (of_chosen) { - const int *prop; - - prop = of_get_property(of_chosen, - "linux,pci-probe-only", NULL); - if (prop) { - if (*prop) - pci_add_flags(PCI_PROBE_ONLY); - else - pci_clear_flags(PCI_PROBE_ONLY); - } - -#ifdef CONFIG_PPC32 /* Will be made generic soon */ - prop = of_get_property(of_chosen, - "linux,pci-assign-all-buses", NULL); - if (prop && *prop) - pci_add_flags(PCI_REASSIGN_ALL_BUS); -#endif /* CONFIG_PPC32 */ - } -} diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 49f553bbb360..c69671c03c3b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -37,6 +37,7 @@ #include <linux/memblock.h> #include <linux/hugetlb.h> #include <linux/memory.h> +#include <linux/nmi.h> #include <asm/io.h> #include <asm/kdump.h> @@ -779,3 +780,22 @@ unsigned long memory_block_size_bytes(void) struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +u64 hw_nmi_get_sample_period(int watchdog_thresh) +{ + return ppc_proc_freq * watchdog_thresh; +} + +/* + * The hardlockup detector breaks PMU event based branches and is likely + * to get false positives in KVM guests, so disable it by default. + */ +static int __init disable_hardlockup_detector(void) +{ + hardlockup_detector_disable(); + + return 0; +} +early_initcall(disable_hardlockup_detector); +#endif diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index b2702e87db0d..5fa92706444b 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -121,3 +121,20 @@ long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low, (u64)len_high << 32 | len_low, advice); } + +long sys_switch_endian(void) +{ + struct thread_info *ti; + + current->thread.regs->msr ^= MSR_LE; + + /* + * Set TIF_RESTOREALL so that r3 isn't clobbered on return to + * userspace. That also has the effect of restoring the non-volatile + * GPRs, so we saved them on the way in here. + */ + ti = current_thread_info(); + ti->flags |= _TIF_RESTOREALL; + + return 0; +} diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 7ab5d434e2ee..4d6b1d3a747f 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -22,6 +22,7 @@ #define PPC_SYS(func) .llong DOTSYM(ppc_##func),DOTSYM(ppc_##func) #define OLDSYS(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) #define SYS32ONLY(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) +#define PPC64ONLY(func) .llong DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall) #define SYSX(f, f3264, f32) .llong DOTSYM(f),DOTSYM(f3264) #else #define SYSCALL(func) .long sys_##func @@ -29,6 +30,7 @@ #define PPC_SYS(func) .long ppc_##func #define OLDSYS(func) .long sys_##func #define SYS32ONLY(func) .long sys_##func +#define PPC64ONLY(func) .long sys_ni_syscall #define SYSX(f, f3264, f32) .long f32 #endif #define SYSCALL_SPU(func) SYSCALL(func) diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c index 238aa63ced8f..2384129f5893 100644 --- a/arch/powerpc/kernel/systbl_chk.c +++ b/arch/powerpc/kernel/systbl_chk.c @@ -21,9 +21,11 @@ #ifdef CONFIG_PPC64 #define OLDSYS(func) -1 #define SYS32ONLY(func) -1 +#define PPC64ONLY(func) __NR_##func #else #define OLDSYS(func) __NR_old##func #define SYS32ONLY(func) __NR_##func +#define PPC64ONLY(func) -1 #endif #define SYSX(f, f3264, f32) -1 diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 2d7b33fab953..56f44848b044 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void) } #endif +unsigned long long tb_to_ns(unsigned long long ticks) +{ + return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift; +} +EXPORT_SYMBOL_GPL(tb_to_ns); + /* * Scheduler clock - returns current time in nanosec units. * diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 2a324f4cb1b9..5754b226da7e 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -152,9 +152,9 @@ _GLOBAL(tm_reclaim) addi r7, r3, THREAD_TRANSACT_VRSTATE SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */ - mfvscr vr0 + mfvscr v0 li r6, VRSTATE_VSCR - stvx vr0, r7, r6 + stvx v0, r7, r6 dont_backup_vec: mfspr r0, SPRN_VRSAVE std r0, THREAD_TRANSACT_VRSAVE(r3) @@ -359,8 +359,8 @@ _GLOBAL(__tm_recheckpoint) addi r8, r3, THREAD_VRSTATE li r5, VRSTATE_VSCR - lvx vr0, r8, r5 - mtvscr vr0 + lvx v0, r8, r5 + mtvscr v0 REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */ dont_restore_vec: ld r5, THREAD_VRSAVE(r3) diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index b7aa07279a63..7cc38b5b58bc 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -46,8 +46,6 @@ void __init udbg_early_init(void) #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE) /* Maple real mode debug */ udbg_init_maple_realmode(); -#elif defined(CONFIG_PPC_EARLY_DEBUG_BEAT) - udbg_init_debug_beat(); #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE) udbg_init_pas_realmode(); #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 74f8050518d6..f5c80d567d8d 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -24,8 +24,8 @@ _GLOBAL(do_load_up_transact_altivec) stw r4,THREAD_USED_VR(r3) li r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR - lvx vr0,r10,r3 - mtvscr vr0 + lvx v0,r10,r3 + mtvscr v0 addi r10,r3,THREAD_TRANSACT_VRSTATE REST_32VRS(0,r4,r10) @@ -52,8 +52,8 @@ _GLOBAL(vec_enable) */ _GLOBAL(load_vr_state) li r4,VRSTATE_VSCR - lvx vr0,r4,r3 - mtvscr vr0 + lvx v0,r4,r3 + mtvscr v0 REST_32VRS(0,r4,r3) blr @@ -63,9 +63,9 @@ _GLOBAL(load_vr_state) */ _GLOBAL(store_vr_state) SAVE_32VRS(0, r4, r3) - mfvscr vr0 + mfvscr v0 li r4, VRSTATE_VSCR - stvx vr0, r4, r3 + stvx v0, r4, r3 blr /* @@ -104,9 +104,9 @@ _GLOBAL(load_up_altivec) addi r4,r4,THREAD addi r6,r4,THREAD_VRSTATE SAVE_32VRS(0,r5,r6) - mfvscr vr0 + mfvscr v0 li r10,VRSTATE_VSCR - stvx vr0,r10,r6 + stvx v0,r10,r6 /* Disable VMX for last_task_used_altivec */ PPC_LL r5,PT_REGS(r4) toreal(r5) @@ -142,8 +142,8 @@ _GLOBAL(load_up_altivec) li r4,1 li r10,VRSTATE_VSCR stw r4,THREAD_USED_VR(r5) - lvx vr0,r10,r6 - mtvscr vr0 + lvx v0,r10,r6 + mtvscr v0 REST_32VRS(0,r4,r6) #ifndef CONFIG_SMP /* Update last_task_used_altivec to 'current' */ @@ -186,9 +186,9 @@ _GLOBAL(giveup_altivec) addi r7,r3,THREAD_VRSTATE 2: PPC_LCMPI 0,r5,0 SAVE_32VRS(0,r4,r7) - mfvscr vr0 + mfvscr v0 li r4,VRSTATE_VSCR - stvx vr0,r4,r7 + stvx v0,r4,r7 beq 1f PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) #ifdef CONFIG_VSX diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 11850f310fb4..3caec2c42105 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -75,7 +75,7 @@ config KVM_BOOK3S_64 config KVM_BOOK3S_64_HV tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host" - depends on KVM_BOOK3S_64 + depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE select MMU_NOTIFIER select CMA @@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR processor, including emulating 32-bit processors on a 64-bit host. +config KVM_BOOK3S_HV_EXIT_TIMING + bool "Detailed timing for hypervisor real-mode code" + depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS + ---help--- + Calculate time taken for each vcpu in the real-mode guest entry, + exit, and interrupt handling code, plus time spent in the guest + and in nap mode due to idle (cede) while other threads are still + in the guest. The total, minimum and maximum times in nanoseconds + together with the number of executions are reported in debugfs in + kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40 + ns per exit on POWER8. + + If unsure, say N. + config KVM_BOOKE_HV bool diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index cfbcdc654201..453a8a47a467 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -821,6 +821,82 @@ void kvmppc_core_destroy_vm(struct kvm *kvm) #endif } +int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu) +{ + unsigned long size = kvmppc_get_gpr(vcpu, 4); + unsigned long addr = kvmppc_get_gpr(vcpu, 5); + u64 buf; + int ret; + + if (!is_power_of_2(size) || (size > sizeof(buf))) + return H_TOO_HARD; + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf); + if (ret != 0) + return H_TOO_HARD; + + switch (size) { + case 1: + kvmppc_set_gpr(vcpu, 4, *(u8 *)&buf); + break; + + case 2: + kvmppc_set_gpr(vcpu, 4, be16_to_cpu(*(__be16 *)&buf)); + break; + + case 4: + kvmppc_set_gpr(vcpu, 4, be32_to_cpu(*(__be32 *)&buf)); + break; + + case 8: + kvmppc_set_gpr(vcpu, 4, be64_to_cpu(*(__be64 *)&buf)); + break; + + default: + BUG(); + } + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_load); + +int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu) +{ + unsigned long size = kvmppc_get_gpr(vcpu, 4); + unsigned long addr = kvmppc_get_gpr(vcpu, 5); + unsigned long val = kvmppc_get_gpr(vcpu, 6); + u64 buf; + int ret; + + switch (size) { + case 1: + *(u8 *)&buf = val; + break; + + case 2: + *(__be16 *)&buf = cpu_to_be16(val); + break; + + case 4: + *(__be32 *)&buf = cpu_to_be32(val); + break; + + case 8: + *(__be64 *)&buf = cpu_to_be64(val); + break; + + default: + return H_TOO_HARD; + } + + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf); + if (ret != 0) + return H_TOO_HARD; + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_store); + int kvmppc_core_check_processor_compat(void) { /* diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 534acb3c6c3d..1a4acf8bf4f4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -27,6 +27,7 @@ #include <linux/srcu.h> #include <linux/anon_inodes.h> #include <linux/file.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/kvm_ppc.h> @@ -116,12 +117,12 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) long order; mutex_lock(&kvm->lock); - if (kvm->arch.rma_setup_done) { - kvm->arch.rma_setup_done = 0; - /* order rma_setup_done vs. vcpus_running */ + if (kvm->arch.hpte_setup_done) { + kvm->arch.hpte_setup_done = 0; + /* order hpte_setup_done vs. vcpus_running */ smp_mb(); if (atomic_read(&kvm->arch.vcpus_running)) { - kvm->arch.rma_setup_done = 1; + kvm->arch.hpte_setup_done = 1; goto out; } } @@ -338,9 +339,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; gr = kvm->arch.revmap[index].guest_rpte; - /* Unlock the HPTE */ - asm volatile("lwsync" : : : "memory"); - hptep[0] = cpu_to_be64(v); + unlock_hpte(hptep, v); preempt_enable(); gpte->eaddr = eaddr; @@ -469,8 +468,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, hpte[0] = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; hpte[1] = be64_to_cpu(hptep[1]); hpte[2] = r = rev->guest_rpte; - asm volatile("lwsync" : : : "memory"); - hptep[0] = cpu_to_be64(hpte[0]); + unlock_hpte(hptep, hpte[0]); preempt_enable(); if (hpte[0] != vcpu->arch.pgfault_hpte[0] || @@ -537,23 +535,21 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } /* if the guest wants write access, see if that is OK */ if (!writing && hpte_is_writable(r)) { - unsigned int hugepage_shift; pte_t *ptep, pte; - + unsigned long flags; /* * We need to protect against page table destruction - * while looking up and updating the pte. + * hugepage split and collapse. */ - rcu_read_lock_sched(); + local_irq_save(flags); ptep = find_linux_pte_or_hugepte(current->mm->pgd, - hva, &hugepage_shift); + hva, NULL); if (ptep) { - pte = kvmppc_read_update_linux_pte(ptep, 1, - hugepage_shift); + pte = kvmppc_read_update_linux_pte(ptep, 1); if (pte_write(pte)) write_ok = 1; } - rcu_read_unlock_sched(); + local_irq_restore(flags); } } @@ -621,7 +617,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, hptep[1] = cpu_to_be64(r); eieio(); - hptep[0] = cpu_to_be64(hpte[0]); + __unlock_hpte(hptep, hpte[0]); asm volatile("ptesync" : : : "memory"); preempt_enable(); if (page && hpte_is_writable(r)) @@ -642,7 +638,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, return ret; out_unlock: - hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hptep, be64_to_cpu(hptep[0])); preempt_enable(); goto out_put; } @@ -771,7 +767,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, } } unlock_rmap(rmapp); - hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } return 0; } @@ -857,7 +853,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, } ret = 1; } - hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } while ((i = j) != head); unlock_rmap(rmapp); @@ -974,8 +970,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) /* Now check and modify the HPTE */ if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) { - /* unlock and continue */ - hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hptep, be64_to_cpu(hptep[0])); continue; } @@ -996,9 +991,9 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) npages_dirty = n; eieio(); } - v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK); + v &= ~HPTE_V_ABSENT; v |= HPTE_V_VALID; - hptep[0] = cpu_to_be64(v); + __unlock_hpte(hptep, v); } while ((i = j) != head); unlock_rmap(rmapp); @@ -1218,8 +1213,7 @@ static long record_hpte(unsigned long flags, __be64 *hptp, r &= ~HPTE_GR_MODIFIED; revp->guest_rpte = r; } - asm volatile(PPC_RELEASE_BARRIER "" : : : "memory"); - hptp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + unlock_hpte(hptp, be64_to_cpu(hptp[0])); preempt_enable(); if (!(valid == want_valid && (first_pass || dirty))) ok = 0; @@ -1339,20 +1333,20 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, unsigned long tmp[2]; ssize_t nb; long int err, ret; - int rma_setup; + int hpte_setup; if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; /* lock out vcpus from running while we're doing this */ mutex_lock(&kvm->lock); - rma_setup = kvm->arch.rma_setup_done; - if (rma_setup) { - kvm->arch.rma_setup_done = 0; /* temporarily */ - /* order rma_setup_done vs. vcpus_running */ + hpte_setup = kvm->arch.hpte_setup_done; + if (hpte_setup) { + kvm->arch.hpte_setup_done = 0; /* temporarily */ + /* order hpte_setup_done vs. vcpus_running */ smp_mb(); if (atomic_read(&kvm->arch.vcpus_running)) { - kvm->arch.rma_setup_done = 1; + kvm->arch.hpte_setup_done = 1; mutex_unlock(&kvm->lock); return -EBUSY; } @@ -1405,7 +1399,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, "r=%lx\n", ret, i, v, r); goto out; } - if (!rma_setup && is_vrma_hpte(v)) { + if (!hpte_setup && is_vrma_hpte(v)) { unsigned long psize = hpte_base_page_size(v, r); unsigned long senc = slb_pgsize_encoding(psize); unsigned long lpcr; @@ -1414,7 +1408,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, (VRMA_VSID << SLB_VSID_SHIFT_1T); lpcr = senc << (LPCR_VRMASD_SH - 4); kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD); - rma_setup = 1; + hpte_setup = 1; } ++i; hptp += 2; @@ -1430,9 +1424,9 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, } out: - /* Order HPTE updates vs. rma_setup_done */ + /* Order HPTE updates vs. hpte_setup_done */ smp_wmb(); - kvm->arch.rma_setup_done = rma_setup; + kvm->arch.hpte_setup_done = hpte_setup; mutex_unlock(&kvm->lock); if (err) @@ -1495,6 +1489,141 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) return ret; } +struct debugfs_htab_state { + struct kvm *kvm; + struct mutex mutex; + unsigned long hpt_index; + int chars_left; + int buf_index; + char buf[64]; +}; + +static int debugfs_htab_open(struct inode *inode, struct file *file) +{ + struct kvm *kvm = inode->i_private; + struct debugfs_htab_state *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + kvm_get_kvm(kvm); + p->kvm = kvm; + mutex_init(&p->mutex); + file->private_data = p; + + return nonseekable_open(inode, file); +} + +static int debugfs_htab_release(struct inode *inode, struct file *file) +{ + struct debugfs_htab_state *p = file->private_data; + + kvm_put_kvm(p->kvm); + kfree(p); + return 0; +} + +static ssize_t debugfs_htab_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos) +{ + struct debugfs_htab_state *p = file->private_data; + ssize_t ret, r; + unsigned long i, n; + unsigned long v, hr, gr; + struct kvm *kvm; + __be64 *hptp; + + ret = mutex_lock_interruptible(&p->mutex); + if (ret) + return ret; + + if (p->chars_left) { + n = p->chars_left; + if (n > len) + n = len; + r = copy_to_user(buf, p->buf + p->buf_index, n); + n -= r; + p->chars_left -= n; + p->buf_index += n; + buf += n; + len -= n; + ret = n; + if (r) { + if (!n) + ret = -EFAULT; + goto out; + } + } + + kvm = p->kvm; + i = p->hpt_index; + hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); + for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) { + if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT))) + continue; + + /* lock the HPTE so it's stable and read it */ + preempt_disable(); + while (!try_lock_hpte(hptp, HPTE_V_HVLOCK)) + cpu_relax(); + v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK; + hr = be64_to_cpu(hptp[1]); + gr = kvm->arch.revmap[i].guest_rpte; + unlock_hpte(hptp, v); + preempt_enable(); + + if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT))) + continue; + + n = scnprintf(p->buf, sizeof(p->buf), + "%6lx %.16lx %.16lx %.16lx\n", + i, v, hr, gr); + p->chars_left = n; + if (n > len) + n = len; + r = copy_to_user(buf, p->buf, n); + n -= r; + p->chars_left -= n; + p->buf_index = n; + buf += n; + len -= n; + ret += n; + if (r) { + if (!ret) + ret = -EFAULT; + goto out; + } + } + p->hpt_index = i; + + out: + mutex_unlock(&p->mutex); + return ret; +} + +ssize_t debugfs_htab_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return -EACCES; +} + +static const struct file_operations debugfs_htab_fops = { + .owner = THIS_MODULE, + .open = debugfs_htab_open, + .release = debugfs_htab_release, + .read = debugfs_htab_read, + .write = debugfs_htab_write, + .llseek = generic_file_llseek, +}; + +void kvmppc_mmu_debugfs_init(struct kvm *kvm) +{ + kvm->arch.htab_dentry = debugfs_create_file("htab", 0400, + kvm->arch.debugfs_dir, kvm, + &debugfs_htab_fops); +} + void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) { struct kvmppc_mmu *mmu = &vcpu->arch.mmu; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de747563d29d..48d3c5d2ecc9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -32,6 +32,7 @@ #include <linux/page-flags.h> #include <linux/srcu.h> #include <linux/miscdevice.h> +#include <linux/debugfs.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -50,6 +51,7 @@ #include <asm/hvcall.h> #include <asm/switch_to.h> #include <asm/smp.h> +#include <asm/dbell.h> #include <linux/gfp.h> #include <linux/vmalloc.h> #include <linux/highmem.h> @@ -83,9 +85,35 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); +static bool kvmppc_ipi_thread(int cpu) +{ + /* On POWER8 for IPIs to threads in the same core, use msgsnd */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + preempt_disable(); + if (cpu_first_thread_sibling(cpu) == + cpu_first_thread_sibling(smp_processor_id())) { + unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); + msg |= cpu_thread_in_core(cpu); + smp_mb(); + __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); + preempt_enable(); + return true; + } + preempt_enable(); + } + +#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) + if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) { + xics_wake_cpu(cpu); + return true; + } +#endif + + return false; +} + static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { - int me; int cpu = vcpu->cpu; wait_queue_head_t *wqp; @@ -95,20 +123,12 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) ++vcpu->stat.halt_wakeup; } - me = get_cpu(); + if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid)) + return; /* CPU points to the first thread of the core */ - if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { -#ifdef CONFIG_PPC_ICP_NATIVE - int real_cpu = cpu + vcpu->arch.ptid; - if (paca[real_cpu].kvm_hstate.xics_phys) - xics_wake_cpu(real_cpu); - else -#endif - if (cpu_online(cpu)) - smp_send_reschedule(cpu); - } - put_cpu(); + if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu)) + smp_send_reschedule(cpu); } /* @@ -706,6 +726,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) /* Send the error out to userspace via KVM_RUN */ return rc; + case H_LOGICAL_CI_LOAD: + ret = kvmppc_h_logical_ci_load(vcpu); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_LOGICAL_CI_STORE: + ret = kvmppc_h_logical_ci_store(vcpu); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; case H_SET_MODE: ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), @@ -740,6 +770,8 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) case H_CONFER: case H_REGISTER_VPA: case H_SET_MODE: + case H_LOGICAL_CI_LOAD: + case H_LOGICAL_CI_STORE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -1410,6 +1442,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) return vcore; } +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +static struct debugfs_timings_element { + const char *name; + size_t offset; +} timings[] = { + {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)}, + {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)}, + {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)}, + {"guest", offsetof(struct kvm_vcpu, arch.guest_time)}, + {"cede", offsetof(struct kvm_vcpu, arch.cede_time)}, +}; + +#define N_TIMINGS (sizeof(timings) / sizeof(timings[0])) + +struct debugfs_timings_state { + struct kvm_vcpu *vcpu; + unsigned int buflen; + char buf[N_TIMINGS * 100]; +}; + +static int debugfs_timings_open(struct inode *inode, struct file *file) +{ + struct kvm_vcpu *vcpu = inode->i_private; + struct debugfs_timings_state *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + kvm_get_kvm(vcpu->kvm); + p->vcpu = vcpu; + file->private_data = p; + + return nonseekable_open(inode, file); +} + +static int debugfs_timings_release(struct inode *inode, struct file *file) +{ + struct debugfs_timings_state *p = file->private_data; + + kvm_put_kvm(p->vcpu->kvm); + kfree(p); + return 0; +} + +static ssize_t debugfs_timings_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos) +{ + struct debugfs_timings_state *p = file->private_data; + struct kvm_vcpu *vcpu = p->vcpu; + char *s, *buf_end; + struct kvmhv_tb_accumulator tb; + u64 count; + loff_t pos; + ssize_t n; + int i, loops; + bool ok; + + if (!p->buflen) { + s = p->buf; + buf_end = s + sizeof(p->buf); + for (i = 0; i < N_TIMINGS; ++i) { + struct kvmhv_tb_accumulator *acc; + + acc = (struct kvmhv_tb_accumulator *) + ((unsigned long)vcpu + timings[i].offset); + ok = false; + for (loops = 0; loops < 1000; ++loops) { + count = acc->seqcount; + if (!(count & 1)) { + smp_rmb(); + tb = *acc; + smp_rmb(); + if (count == acc->seqcount) { + ok = true; + break; + } + } + udelay(1); + } + if (!ok) + snprintf(s, buf_end - s, "%s: stuck\n", + timings[i].name); + else + snprintf(s, buf_end - s, + "%s: %llu %llu %llu %llu\n", + timings[i].name, count / 2, + tb_to_ns(tb.tb_total), + tb_to_ns(tb.tb_min), + tb_to_ns(tb.tb_max)); + s += strlen(s); + } + p->buflen = s - p->buf; + } + + pos = *ppos; + if (pos >= p->buflen) + return 0; + if (len > p->buflen - pos) + len = p->buflen - pos; + n = copy_to_user(buf, p->buf + pos, len); + if (n) { + if (n == len) + return -EFAULT; + len -= n; + } + *ppos = pos + len; + return len; +} + +static ssize_t debugfs_timings_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return -EACCES; +} + +static const struct file_operations debugfs_timings_ops = { + .owner = THIS_MODULE, + .open = debugfs_timings_open, + .release = debugfs_timings_release, + .read = debugfs_timings_read, + .write = debugfs_timings_write, + .llseek = generic_file_llseek, +}; + +/* Create a debugfs directory for the vcpu */ +static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +{ + char buf[16]; + struct kvm *kvm = vcpu->kvm; + + snprintf(buf, sizeof(buf), "vcpu%u", id); + if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir)) + return; + vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir); + if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir)) + return; + vcpu->arch.debugfs_timings = + debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, + vcpu, &debugfs_timings_ops); +} + +#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ +static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +{ +} +#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ + static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, unsigned int id) { @@ -1479,6 +1659,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); + debugfs_vcpu_init(vcpu, id); + return vcpu; free_vcpu: @@ -1566,8 +1748,10 @@ static int kvmppc_grab_hwthread(int cpu) tpaca = &paca[cpu]; /* Ensure the thread won't go into the kernel if it wakes */ - tpaca->kvm_hstate.hwthread_req = 1; tpaca->kvm_hstate.kvm_vcpu = NULL; + tpaca->kvm_hstate.napping = 0; + smp_wmb(); + tpaca->kvm_hstate.hwthread_req = 1; /* * If the thread is already executing in the kernel (e.g. handling @@ -1610,35 +1794,41 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) } cpu = vc->pcpu + vcpu->arch.ptid; tpaca = &paca[cpu]; - tpaca->kvm_hstate.kvm_vcpu = vcpu; tpaca->kvm_hstate.kvm_vcore = vc; tpaca->kvm_hstate.ptid = vcpu->arch.ptid; vcpu->cpu = vc->pcpu; + /* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */ smp_wmb(); -#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) - if (cpu != smp_processor_id()) { - xics_wake_cpu(cpu); - if (vcpu->arch.ptid) - ++vc->n_woken; - } -#endif + tpaca->kvm_hstate.kvm_vcpu = vcpu; + if (cpu != smp_processor_id()) + kvmppc_ipi_thread(cpu); } -static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc) +static void kvmppc_wait_for_nap(void) { - int i; + int cpu = smp_processor_id(); + int i, loops; - HMT_low(); - i = 0; - while (vc->nap_count < vc->n_woken) { - if (++i >= 1000000) { - pr_err("kvmppc_wait_for_nap timeout %d %d\n", - vc->nap_count, vc->n_woken); - break; + for (loops = 0; loops < 1000000; ++loops) { + /* + * Check if all threads are finished. + * We set the vcpu pointer when starting a thread + * and the thread clears it when finished, so we look + * for any threads that still have a non-NULL vcpu ptr. + */ + for (i = 1; i < threads_per_subcore; ++i) + if (paca[cpu + i].kvm_hstate.kvm_vcpu) + break; + if (i == threads_per_subcore) { + HMT_medium(); + return; } - cpu_relax(); + HMT_low(); } HMT_medium(); + for (i = 1; i < threads_per_subcore; ++i) + if (paca[cpu + i].kvm_hstate.kvm_vcpu) + pr_err("KVM: CPU %d seems to be stuck\n", cpu + i); } /* @@ -1700,63 +1890,103 @@ static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc) mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE); } +static void prepare_threads(struct kvmppc_vcore *vc) +{ + struct kvm_vcpu *vcpu, *vnext; + + list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, + arch.run_list) { + if (signal_pending(vcpu->arch.run_task)) + vcpu->arch.ret = -EINTR; + else if (vcpu->arch.vpa.update_pending || + vcpu->arch.slb_shadow.update_pending || + vcpu->arch.dtl.update_pending) + vcpu->arch.ret = RESUME_GUEST; + else + continue; + kvmppc_remove_runnable(vc, vcpu); + wake_up(&vcpu->arch.cpu_run); + } +} + +static void post_guest_process(struct kvmppc_vcore *vc) +{ + u64 now; + long ret; + struct kvm_vcpu *vcpu, *vnext; + + now = get_tb(); + list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, + arch.run_list) { + /* cancel pending dec exception if dec is positive */ + if (now < vcpu->arch.dec_expires && + kvmppc_core_pending_dec(vcpu)) + kvmppc_core_dequeue_dec(vcpu); + + trace_kvm_guest_exit(vcpu); + + ret = RESUME_GUEST; + if (vcpu->arch.trap) + ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu, + vcpu->arch.run_task); + + vcpu->arch.ret = ret; + vcpu->arch.trap = 0; + + if (vcpu->arch.ceded) { + if (!is_kvmppc_resume_guest(ret)) + kvmppc_end_cede(vcpu); + else + kvmppc_set_timer(vcpu); + } + if (!is_kvmppc_resume_guest(vcpu->arch.ret)) { + kvmppc_remove_runnable(vc, vcpu); + wake_up(&vcpu->arch.cpu_run); + } + } +} + /* * Run a set of guest threads on a physical core. * Called with vc->lock held. */ -static void kvmppc_run_core(struct kvmppc_vcore *vc) +static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu, *vnext; - long ret; - u64 now; - int i, need_vpa_update; + struct kvm_vcpu *vcpu; + int i; int srcu_idx; - struct kvm_vcpu *vcpus_to_update[threads_per_core]; - /* don't start if any threads have a signal pending */ - need_vpa_update = 0; - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { - if (signal_pending(vcpu->arch.run_task)) - return; - if (vcpu->arch.vpa.update_pending || - vcpu->arch.slb_shadow.update_pending || - vcpu->arch.dtl.update_pending) - vcpus_to_update[need_vpa_update++] = vcpu; - } + /* + * Remove from the list any threads that have a signal pending + * or need a VPA update done + */ + prepare_threads(vc); + + /* if the runner is no longer runnable, let the caller pick a new one */ + if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE) + return; /* - * Initialize *vc, in particular vc->vcore_state, so we can - * drop the vcore lock if necessary. + * Initialize *vc. */ - vc->n_woken = 0; - vc->nap_count = 0; - vc->entry_exit_count = 0; + vc->entry_exit_map = 0; vc->preempt_tb = TB_NIL; - vc->vcore_state = VCORE_STARTING; vc->in_guest = 0; vc->napping_threads = 0; vc->conferring_threads = 0; /* - * Updating any of the vpas requires calling kvmppc_pin_guest_page, - * which can't be called with any spinlocks held. - */ - if (need_vpa_update) { - spin_unlock(&vc->lock); - for (i = 0; i < need_vpa_update; ++i) - kvmppc_update_vpas(vcpus_to_update[i]); - spin_lock(&vc->lock); - } - - /* * Make sure we are running on primary threads, and that secondary * threads are offline. Also check if the number of threads in this * guest are greater than the current system threads per guest. */ if ((threads_per_core > 1) && ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { vcpu->arch.ret = -EBUSY; + kvmppc_remove_runnable(vc, vcpu); + wake_up(&vcpu->arch.cpu_run); + } goto out; } @@ -1797,8 +2027,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) vcpu->cpu = -1; /* wait for secondary threads to finish writing their state to memory */ - if (vc->nap_count < vc->n_woken) - kvmppc_wait_for_nap(vc); + kvmppc_wait_for_nap(); for (i = 0; i < threads_per_subcore; ++i) kvmppc_release_hwthread(vc->pcpu + i); /* prevent other vcpu threads from doing kvmppc_start_thread() now */ @@ -1812,44 +2041,12 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) kvm_guest_exit(); preempt_enable(); - cond_resched(); spin_lock(&vc->lock); - now = get_tb(); - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { - /* cancel pending dec exception if dec is positive */ - if (now < vcpu->arch.dec_expires && - kvmppc_core_pending_dec(vcpu)) - kvmppc_core_dequeue_dec(vcpu); - - trace_kvm_guest_exit(vcpu); - - ret = RESUME_GUEST; - if (vcpu->arch.trap) - ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu, - vcpu->arch.run_task); - - vcpu->arch.ret = ret; - vcpu->arch.trap = 0; - - if (vcpu->arch.ceded) { - if (!is_kvmppc_resume_guest(ret)) - kvmppc_end_cede(vcpu); - else - kvmppc_set_timer(vcpu); - } - } + post_guest_process(vc); out: vc->vcore_state = VCORE_INACTIVE; - list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, - arch.run_list) { - if (!is_kvmppc_resume_guest(vcpu->arch.ret)) { - kvmppc_remove_runnable(vc, vcpu); - wake_up(&vcpu->arch.cpu_run); - } - } - trace_kvmppc_run_core(vc, 1); } @@ -1939,8 +2136,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) * this thread straight away and have it join in. */ if (!signal_pending(current)) { - if (vc->vcore_state == VCORE_RUNNING && - VCORE_EXIT_COUNT(vc) == 0) { + if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) { kvmppc_create_dtl_entry(vcpu, vc); kvmppc_start_thread(vcpu); trace_kvm_guest_enter(vcpu); @@ -1971,7 +2167,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) } if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) break; - vc->runner = vcpu; n_ceded = 0; list_for_each_entry(v, &vc->runnable_threads, arch.run_list) { if (!v->arch.pending_exceptions) @@ -1979,10 +2174,17 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) else v->arch.ceded = 0; } - if (n_ceded == vc->n_runnable) + vc->runner = vcpu; + if (n_ceded == vc->n_runnable) { kvmppc_vcore_blocked(vc); - else + } else if (should_resched()) { + vc->vcore_state = VCORE_PREEMPT; + /* Let something else run */ + cond_resched_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; + } else { kvmppc_run_core(vc); + } vc->runner = NULL; } @@ -2032,11 +2234,11 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } atomic_inc(&vcpu->kvm->arch.vcpus_running); - /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */ + /* Order vcpus_running vs. hpte_setup_done, see kvmppc_alloc_reset_hpt */ smp_mb(); /* On the first time here, set up HTAB and VRMA */ - if (!vcpu->kvm->arch.rma_setup_done) { + if (!vcpu->kvm->arch.hpte_setup_done) { r = kvmppc_hv_setup_htab_rma(vcpu); if (r) goto out; @@ -2238,7 +2440,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) int srcu_idx; mutex_lock(&kvm->lock); - if (kvm->arch.rma_setup_done) + if (kvm->arch.hpte_setup_done) goto out; /* another vcpu beat us to it */ /* Allocate hashed page table (if not done already) and reset it */ @@ -2289,9 +2491,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD); - /* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */ + /* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */ smp_wmb(); - kvm->arch.rma_setup_done = 1; + kvm->arch.hpte_setup_done = 1; err = 0; out_srcu: srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -2307,6 +2509,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; + char buf[32]; /* Allocate the guest's logical partition ID */ @@ -2347,6 +2550,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) */ kvm_hv_vm_activated(); + /* + * Create a debugfs directory for the VM + */ + snprintf(buf, sizeof(buf), "vm%d", current->pid); + kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir); + if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir)) + kvmppc_mmu_debugfs_init(kvm); + return 0; } @@ -2367,6 +2578,8 @@ static void kvmppc_free_vcores(struct kvm *kvm) static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { + debugfs_remove_recursive(kvm->arch.debugfs_dir); + kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 1f083ff8a61a..ed2589d4593f 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -21,6 +21,10 @@ #include <asm/cputable.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> +#include <asm/archrandom.h> +#include <asm/xics.h> +#include <asm/dbell.h> +#include <asm/cputhreads.h> #define KVM_CMA_CHUNK_ORDER 18 @@ -114,11 +118,11 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, int rv = H_SUCCESS; /* => don't yield */ set_bit(vcpu->arch.ptid, &vc->conferring_threads); - while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) { - threads_running = VCORE_ENTRY_COUNT(vc); - threads_ceded = hweight32(vc->napping_threads); - threads_conferring = hweight32(vc->conferring_threads); - if (threads_ceded + threads_conferring >= threads_running) { + while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) { + threads_running = VCORE_ENTRY_MAP(vc); + threads_ceded = vc->napping_threads; + threads_conferring = vc->conferring_threads; + if ((threads_ceded | threads_conferring) == threads_running) { rv = H_TOO_HARD; /* => do yield */ break; } @@ -169,3 +173,89 @@ int kvmppc_hcall_impl_hv_realmode(unsigned long cmd) return 0; } EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode); + +int kvmppc_hwrng_present(void) +{ + return powernv_hwrng_present(); +} +EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); + +long kvmppc_h_random(struct kvm_vcpu *vcpu) +{ + if (powernv_get_random_real_mode(&vcpu->arch.gpr[4])) + return H_SUCCESS; + + return H_HARDWARE; +} + +static inline void rm_writeb(unsigned long paddr, u8 val) +{ + __asm__ __volatile__("stbcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + +/* + * Send an interrupt or message to another CPU. + * This can only be called in real mode. + * The caller needs to include any barrier needed to order writes + * to memory vs. the IPI/message. + */ +void kvmhv_rm_send_ipi(int cpu) +{ + unsigned long xics_phys; + + /* On POWER8 for IPIs to threads in the same core, use msgsnd */ + if (cpu_has_feature(CPU_FTR_ARCH_207S) && + cpu_first_thread_sibling(cpu) == + cpu_first_thread_sibling(raw_smp_processor_id())) { + unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); + msg |= cpu_thread_in_core(cpu); + __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); + return; + } + + /* Else poke the target with an IPI */ + xics_phys = paca[cpu].kvm_hstate.xics_phys; + rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY); +} + +/* + * The following functions are called from the assembly code + * in book3s_hv_rmhandlers.S. + */ +static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active) +{ + int cpu = vc->pcpu; + + /* Order setting of exit map vs. msgsnd/IPI */ + smp_mb(); + for (; active; active >>= 1, ++cpu) + if (active & 1) + kvmhv_rm_send_ipi(cpu); +} + +void kvmhv_commence_exit(int trap) +{ + struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore; + int ptid = local_paca->kvm_hstate.ptid; + int me, ee; + + /* Set our bit in the threads-exiting-guest map in the 0xff00 + bits of vcore->entry_exit_map */ + me = 0x100 << ptid; + do { + ee = vc->entry_exit_map; + } while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee); + + /* Are we the first here? */ + if ((ee >> 8) != 0) + return; + + /* + * Trigger the other threads in this vcore to exit the guest. + * If this is a hypervisor decrementer interrupt then they + * will be already on their way out of the guest. + */ + if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER) + kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid)); +} diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 60081bd75847..93b5f5c9b445 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -84,7 +84,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) } if (dsisr & DSISR_MC_TLB_MULTI) { if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); + cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID); dsisr &= ~DSISR_MC_TLB_MULTI; } /* Any other errors we don't understand? */ @@ -102,7 +102,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) break; case SRR1_MC_IFETCH_TLBMULTI: if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); + cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID); break; default: handled = 0; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 625407e4d3b0..b027a89737b6 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -26,11 +26,14 @@ static void *real_vmalloc_addr(void *x) { unsigned long addr = (unsigned long) x; pte_t *p; - - p = find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL); + /* + * assume we don't have huge pages in vmalloc space... + * So don't worry about THP collapse/split. Called + * Only in realmode, hence won't need irq_save/restore. + */ + p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL); if (!p || !pte_present(*p)) return NULL; - /* assume we don't have huge pages in vmalloc space... */ addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK); return __va(addr); } @@ -131,31 +134,6 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index, unlock_rmap(rmap); } -static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva, - int writing, unsigned long *pte_sizep) -{ - pte_t *ptep; - unsigned long ps = *pte_sizep; - unsigned int hugepage_shift; - - ptep = find_linux_pte_or_hugepte(pgdir, hva, &hugepage_shift); - if (!ptep) - return __pte(0); - if (hugepage_shift) - *pte_sizep = 1ul << hugepage_shift; - else - *pte_sizep = PAGE_SIZE; - if (ps > *pte_sizep) - return __pte(0); - return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift); -} - -static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v) -{ - asm volatile(PPC_RELEASE_BARRIER "" : : : "memory"); - hpte[0] = cpu_to_be64(hpte_v); -} - long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret) @@ -166,13 +144,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, struct revmap_entry *rev; unsigned long g_ptel; struct kvm_memory_slot *memslot; - unsigned long pte_size; + unsigned hpage_shift; unsigned long is_io; unsigned long *rmap; - pte_t pte; + pte_t *ptep; unsigned int writing; unsigned long mmu_seq; - unsigned long rcbits; + unsigned long rcbits, irq_flags = 0; psize = hpte_page_size(pteh, ptel); if (!psize) @@ -208,22 +186,46 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Translate to host virtual address */ hva = __gfn_to_hva_memslot(memslot, gfn); - - /* Look up the Linux PTE for the backing page */ - pte_size = psize; - pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size); - if (pte_present(pte) && !pte_protnone(pte)) { - if (writing && !pte_write(pte)) - /* make the actual HPTE be read-only */ - ptel = hpte_make_readonly(ptel); - is_io = hpte_cache_bits(pte_val(pte)); - pa = pte_pfn(pte) << PAGE_SHIFT; - pa |= hva & (pte_size - 1); - pa |= gpa & ~PAGE_MASK; + /* + * If we had a page table table change after lookup, we would + * retry via mmu_notifier_retry. + */ + if (realmode) + ptep = __find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift); + else { + local_irq_save(irq_flags); + ptep = find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift); } + if (ptep) { + pte_t pte; + unsigned int host_pte_size; - if (pte_size < psize) - return H_PARAMETER; + if (hpage_shift) + host_pte_size = 1ul << hpage_shift; + else + host_pte_size = PAGE_SIZE; + /* + * We should always find the guest page size + * to <= host page size, if host is using hugepage + */ + if (host_pte_size < psize) { + if (!realmode) + local_irq_restore(flags); + return H_PARAMETER; + } + pte = kvmppc_read_update_linux_pte(ptep, writing); + if (pte_present(pte) && !pte_protnone(pte)) { + if (writing && !pte_write(pte)) + /* make the actual HPTE be read-only */ + ptel = hpte_make_readonly(ptel); + is_io = hpte_cache_bits(pte_val(pte)); + pa = pte_pfn(pte) << PAGE_SHIFT; + pa |= hva & (host_pte_size - 1); + pa |= gpa & ~PAGE_MASK; + } + } + if (!realmode) + local_irq_restore(irq_flags); ptel &= ~(HPTE_R_PP0 - psize); ptel |= pa; @@ -271,10 +273,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, u64 pte; while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - pte = be64_to_cpu(*hpte); + pte = be64_to_cpu(hpte[0]); if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT))) break; - *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hpte, pte); hpte += 2; } if (i == 8) @@ -290,9 +292,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - pte = be64_to_cpu(*hpte); + pte = be64_to_cpu(hpte[0]); if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) { - *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hpte, pte); return H_PTEG_FULL; } } @@ -331,7 +333,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Write the first HPTE dword, unlocking the HPTE and making it valid */ eieio(); - hpte[0] = cpu_to_be64(pteh); + __unlock_hpte(hpte, pteh); asm volatile("ptesync" : : : "memory"); *pte_idx_ret = pte_index; @@ -412,7 +414,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) || ((flags & H_ANDCOND) && (pte & avpn) != 0)) { - hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hpte, pte); return H_NOT_FOUND; } @@ -548,7 +550,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) be64_to_cpu(hp[0]), be64_to_cpu(hp[1])); rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C); args[j] |= rcbits << (56 - 5); - hp[0] = 0; + __unlock_hpte(hp, 0); } } @@ -574,7 +576,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, pte = be64_to_cpu(hpte[0]); if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) { - hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); + __unlock_hpte(hpte, pte); return H_NOT_FOUND; } @@ -755,8 +757,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, /* Return with the HPTE still locked */ return (hash << 3) + (i >> 1); - /* Unlock and move on */ - hpte[i] = cpu_to_be64(v); + __unlock_hpte(&hpte[i], v); } if (val & HPTE_V_SECONDARY) diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 7c22997de906..00e45b6d4f24 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -23,17 +23,37 @@ #define DEBUG_PASSUP -static inline void rm_writeb(unsigned long paddr, u8 val) +static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u32 new_irq); + +/* -- ICS routines -- */ +static void ics_rm_check_resend(struct kvmppc_xics *xics, + struct kvmppc_ics *ics, struct kvmppc_icp *icp) { - __asm__ __volatile__("sync; stbcix %0,0,%1" - : : "r" (val), "r" (paddr) : "memory"); + int i; + + arch_spin_lock(&ics->lock); + + for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { + struct ics_irq_state *state = &ics->irq_state[i]; + + if (!state->resend) + continue; + + arch_spin_unlock(&ics->lock); + icp_rm_deliver_irq(xics, icp, state->number); + arch_spin_lock(&ics->lock); + } + + arch_spin_unlock(&ics->lock); } +/* -- ICP routines -- */ + static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, struct kvm_vcpu *this_vcpu) { struct kvmppc_icp *this_icp = this_vcpu->arch.icp; - unsigned long xics_phys; int cpu; /* Mark the target VCPU as having an interrupt pending */ @@ -56,9 +76,8 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, /* In SMT cpu will always point to thread 0, we adjust it */ cpu += vcpu->arch.ptid; - /* Not too hard, then poke the target */ - xics_phys = paca[cpu].kvm_hstate.xics_phys; - rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY); + smp_mb(); + kvmhv_rm_send_ipi(cpu); } static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu) @@ -116,6 +135,180 @@ static inline int check_too_hard(struct kvmppc_xics *xics, return (xics->real_mode_dbg || icp->rm_action) ? H_TOO_HARD : H_SUCCESS; } +static void icp_rm_check_resend(struct kvmppc_xics *xics, + struct kvmppc_icp *icp) +{ + u32 icsid; + + /* Order this load with the test for need_resend in the caller */ + smp_rmb(); + for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) { + struct kvmppc_ics *ics = xics->ics[icsid]; + + if (!test_and_clear_bit(icsid, icp->resend_map)) + continue; + if (!ics) + continue; + ics_rm_check_resend(xics, ics, icp); + } +} + +static bool icp_rm_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, + u32 *reject) +{ + union kvmppc_icp_state old_state, new_state; + bool success; + + do { + old_state = new_state = READ_ONCE(icp->state); + + *reject = 0; + + /* See if we can deliver */ + success = new_state.cppr > priority && + new_state.mfrr > priority && + new_state.pending_pri > priority; + + /* + * If we can, check for a rejection and perform the + * delivery + */ + if (success) { + *reject = new_state.xisr; + new_state.xisr = irq; + new_state.pending_pri = priority; + } else { + /* + * If we failed to deliver we set need_resend + * so a subsequent CPPR state change causes us + * to try a new delivery. + */ + new_state.need_resend = true; + } + + } while (!icp_rm_try_update(icp, old_state, new_state)); + + return success; +} + +static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, + u32 new_irq) +{ + struct ics_irq_state *state; + struct kvmppc_ics *ics; + u32 reject; + u16 src; + + /* + * This is used both for initial delivery of an interrupt and + * for subsequent rejection. + * + * Rejection can be racy vs. resends. We have evaluated the + * rejection in an atomic ICP transaction which is now complete, + * so potentially the ICP can already accept the interrupt again. + * + * So we need to retry the delivery. Essentially the reject path + * boils down to a failed delivery. Always. + * + * Now the interrupt could also have moved to a different target, + * thus we may need to re-do the ICP lookup as well + */ + + again: + /* Get the ICS state and lock it */ + ics = kvmppc_xics_find_ics(xics, new_irq, &src); + if (!ics) { + /* Unsafe increment, but this does not need to be accurate */ + xics->err_noics++; + return; + } + state = &ics->irq_state[src]; + + /* Get a lock on the ICS */ + arch_spin_lock(&ics->lock); + + /* Get our server */ + if (!icp || state->server != icp->server_num) { + icp = kvmppc_xics_find_server(xics->kvm, state->server); + if (!icp) { + /* Unsafe increment again*/ + xics->err_noicp++; + goto out; + } + } + + /* Clear the resend bit of that interrupt */ + state->resend = 0; + + /* + * If masked, bail out + * + * Note: PAPR doesn't mention anything about masked pending + * when doing a resend, only when doing a delivery. + * + * However that would have the effect of losing a masked + * interrupt that was rejected and isn't consistent with + * the whole masked_pending business which is about not + * losing interrupts that occur while masked. + * + * I don't differentiate normal deliveries and resends, this + * implementation will differ from PAPR and not lose such + * interrupts. + */ + if (state->priority == MASKED) { + state->masked_pending = 1; + goto out; + } + + /* + * Try the delivery, this will set the need_resend flag + * in the ICP as part of the atomic transaction if the + * delivery is not possible. + * + * Note that if successful, the new delivery might have itself + * rejected an interrupt that was "delivered" before we took the + * ics spin lock. + * + * In this case we do the whole sequence all over again for the + * new guy. We cannot assume that the rejected interrupt is less + * favored than the new one, and thus doesn't need to be delivered, + * because by the time we exit icp_rm_try_to_deliver() the target + * processor may well have already consumed & completed it, and thus + * the rejected interrupt might actually be already acceptable. + */ + if (icp_rm_try_to_deliver(icp, new_irq, state->priority, &reject)) { + /* + * Delivery was successful, did we reject somebody else ? + */ + if (reject && reject != XICS_IPI) { + arch_spin_unlock(&ics->lock); + new_irq = reject; + goto again; + } + } else { + /* + * We failed to deliver the interrupt we need to set the + * resend map bit and mark the ICS state as needing a resend + */ + set_bit(ics->icsid, icp->resend_map); + state->resend = 1; + + /* + * If the need_resend flag got cleared in the ICP some time + * between icp_rm_try_to_deliver() atomic update and now, then + * we know it might have missed the resend_map bit. So we + * retry + */ + smp_mb(); + if (!icp->state.need_resend) { + arch_spin_unlock(&ics->lock); + goto again; + } + } + out: + arch_spin_unlock(&ics->lock); +} + static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, u8 new_cppr) { @@ -184,8 +377,8 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * separately here as well. */ if (resend) { - icp->rm_action |= XICS_RM_CHECK_RESEND; - icp->rm_resend_icp = icp; + icp->n_check_resend++; + icp_rm_check_resend(xics, icp); } } @@ -300,16 +493,16 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, } } while (!icp_rm_try_update(icp, old_state, new_state)); - /* Pass rejects to virtual mode */ + /* Handle reject in real mode */ if (reject && reject != XICS_IPI) { - this_icp->rm_action |= XICS_RM_REJECT; - this_icp->rm_reject = reject; + this_icp->n_reject++; + icp_rm_deliver_irq(xics, icp, reject); } - /* Pass resends to virtual mode */ + /* Handle resends in real mode */ if (resend) { - this_icp->rm_action |= XICS_RM_CHECK_RESEND; - this_icp->rm_resend_icp = icp; + this_icp->n_check_resend++; + icp_rm_check_resend(xics, icp); } return check_too_hard(xics, this_icp); @@ -365,10 +558,13 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) } while (!icp_rm_try_update(icp, old_state, new_state)); - /* Pass rejects to virtual mode */ + /* + * Check for rejects. They are handled by doing a new delivery + * attempt (see comments in icp_rm_deliver_irq). + */ if (reject && reject != XICS_IPI) { - icp->rm_action |= XICS_RM_REJECT; - icp->rm_reject = reject; + icp->n_reject++; + icp_rm_deliver_irq(xics, icp, reject); } bail: return check_too_hard(xics, icp); @@ -416,10 +612,10 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) goto bail; state = &ics->irq_state[src]; - /* Still asserted, resend it, we make it look like a reject */ + /* Still asserted, resend it */ if (state->asserted) { - icp->rm_action |= XICS_RM_REJECT; - icp->rm_reject = irq; + icp->n_reject++; + icp_rm_deliver_irq(xics, icp, irq); } if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6cbf1630cb70..4d70df26c402 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -172,6 +172,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) kvmppc_primary_no_guest: /* We handle this much like a ceded vcpu */ + /* put the HDEC into the DEC, since HDEC interrupts don't wake us */ + mfspr r3, SPRN_HDEC + mtspr SPRN_DEC, r3 + /* + * Make sure the primary has finished the MMU switch. + * We should never get here on a secondary thread, but + * check it for robustness' sake. + */ + ld r5, HSTATE_KVM_VCORE(r13) +65: lbz r0, VCORE_IN_GUEST(r5) + cmpwi r0, 0 + beq 65b + /* Set LPCR. */ + ld r8,VCORE_LPCR(r5) + mtspr SPRN_LPCR,r8 + isync /* set our bit in napping_threads */ ld r5, HSTATE_KVM_VCORE(r13) lbz r7, HSTATE_PTID(r13) @@ -182,7 +198,7 @@ kvmppc_primary_no_guest: or r3, r3, r0 stwcx. r3, 0, r6 bne 1b - /* order napping_threads update vs testing entry_exit_count */ + /* order napping_threads update vs testing entry_exit_map */ isync li r12, 0 lwz r7, VCORE_ENTRY_EXIT(r5) @@ -191,6 +207,7 @@ kvmppc_primary_no_guest: li r3, NAPPING_NOVCPU stb r3, HSTATE_NAPPING(r13) + li r3, 0 /* Don't wake on privileged (OS) doorbell */ b kvm_do_nap kvm_novcpu_wakeup: @@ -202,7 +219,7 @@ kvm_novcpu_wakeup: /* check the wake reason */ bl kvmppc_check_wake_reason - + /* see if any other thread is already exiting */ lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 @@ -222,13 +239,37 @@ kvm_novcpu_wakeup: cmpdi r3, 0 bge kvm_novcpu_exit + /* See if our timeslice has expired (HDEC is negative) */ + mfspr r0, SPRN_HDEC + li r12, BOOK3S_INTERRUPT_HV_DECREMENTER + cmpwi r0, 0 + blt kvm_novcpu_exit + /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */ ld r4, HSTATE_KVM_VCPU(r13) cmpdi r4, 0 - bne kvmppc_got_guest + beq kvmppc_primary_no_guest + +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r4, VCPU_TB_RMENTRY + bl kvmhv_start_timing +#endif + b kvmppc_got_guest kvm_novcpu_exit: - b hdec_soon +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + ld r4, HSTATE_KVM_VCPU(r13) + cmpdi r4, 0 + beq 13f + addi r3, r4, VCPU_TB_RMEXIT + bl kvmhv_accumulate_time +#endif +13: mr r3, r12 + stw r12, 112-4(r1) + bl kvmhv_commence_exit + nop + lwz r12, 112-4(r1) + b kvmhv_switch_to_host /* * We come in here when wakened from nap mode. @@ -239,9 +280,9 @@ kvm_novcpu_exit: kvm_start_guest: /* Set runlatch bit the minute you wake up from nap */ - mfspr r1, SPRN_CTRLF - ori r1, r1, 1 - mtspr SPRN_CTRLT, r1 + mfspr r0, SPRN_CTRLF + ori r0, r0, 1 + mtspr SPRN_CTRLT, r0 ld r2,PACATOC(r13) @@ -286,26 +327,21 @@ kvm_secondary_got_guest: ld r6, PACA_DSCR(r13) std r6, HSTATE_DSCR(r13) + /* Order load of vcore, ptid etc. after load of vcpu */ + lwsync bl kvmppc_hv_entry /* Back from the guest, go back to nap */ /* Clear our vcpu pointer so we don't come back in early */ li r0, 0 - std r0, HSTATE_KVM_VCPU(r13) /* - * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing - * the nap_count, because once the increment to nap_count is - * visible we could be given another vcpu. + * Once we clear HSTATE_KVM_VCPU(r13), the code in + * kvmppc_run_core() is going to assume that all our vcpu + * state is visible in memory. This lwsync makes sure + * that that is true. */ lwsync - - /* increment the nap count and then go to nap mode */ - ld r4, HSTATE_KVM_VCORE(r13) - addi r4, r4, VCORE_NAP_COUNT -51: lwarx r3, 0, r4 - addi r3, r3, 1 - stwcx. r3, 0, r4 - bne 51b + std r0, HSTATE_KVM_VCPU(r13) /* * At this point we have finished executing in the guest. @@ -376,6 +412,14 @@ kvmppc_hv_entry: li r6, KVM_GUEST_MODE_HOST_HV stb r6, HSTATE_IN_GUEST(r13) +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + /* Store initial timestamp */ + cmpdi r4, 0 + beq 1f + addi r3, r4, VCPU_TB_RMENTRY + bl kvmhv_start_timing +1: +#endif /* Clear out SLB */ li r6,0 slbmte r6,r6 @@ -387,21 +431,23 @@ kvmppc_hv_entry: * We don't have to lock against concurrent tlbies, * but we do have to coordinate across hardware threads. */ - /* Increment entry count iff exit count is zero. */ - ld r5,HSTATE_KVM_VCORE(r13) - addi r9,r5,VCORE_ENTRY_EXIT -21: lwarx r3,0,r9 - cmpwi r3,0x100 /* any threads starting to exit? */ + /* Set bit in entry map iff exit map is zero. */ + ld r5, HSTATE_KVM_VCORE(r13) + li r7, 1 + lbz r6, HSTATE_PTID(r13) + sld r7, r7, r6 + addi r9, r5, VCORE_ENTRY_EXIT +21: lwarx r3, 0, r9 + cmpwi r3, 0x100 /* any threads starting to exit? */ bge secondary_too_late /* if so we're too late to the party */ - addi r3,r3,1 - stwcx. r3,0,r9 + or r3, r3, r7 + stwcx. r3, 0, r9 bne 21b /* Primary thread switches to guest partition. */ ld r9,VCORE_KVM(r5) /* pointer to struct kvm */ - lbz r6,HSTATE_PTID(r13) cmpwi r6,0 - bne 20f + bne 10f ld r6,KVM_SDR1(r9) lwz r7,KVM_LPID(r9) li r0,LPID_RSVD /* switch to reserved LPID */ @@ -472,28 +518,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r0,1 stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */ - b 10f - - /* Secondary threads wait for primary to have done partition switch */ -20: lbz r0,VCORE_IN_GUEST(r5) - cmpwi r0,0 - beq 20b - - /* Set LPCR and RMOR. */ -10: ld r8,VCORE_LPCR(r5) - mtspr SPRN_LPCR,r8 - ld r8,KVM_RMOR(r9) - mtspr SPRN_RMOR,r8 - isync - - /* Check if HDEC expires soon */ - mfspr r3,SPRN_HDEC - cmpwi r3,512 /* 1 microsecond */ - li r12,BOOK3S_INTERRUPT_HV_DECREMENTER - blt hdec_soon /* Do we have a guest vcpu to run? */ - cmpdi r4, 0 +10: cmpdi r4, 0 beq kvmppc_primary_no_guest kvmppc_got_guest: @@ -818,6 +845,30 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) clrrdi r6,r6,1 mtspr SPRN_CTRLT,r6 4: + /* Secondary threads wait for primary to have done partition switch */ + ld r5, HSTATE_KVM_VCORE(r13) + lbz r6, HSTATE_PTID(r13) + cmpwi r6, 0 + beq 21f + lbz r0, VCORE_IN_GUEST(r5) + cmpwi r0, 0 + bne 21f + HMT_LOW +20: lbz r0, VCORE_IN_GUEST(r5) + cmpwi r0, 0 + beq 20b + HMT_MEDIUM +21: + /* Set LPCR. */ + ld r8,VCORE_LPCR(r5) + mtspr SPRN_LPCR,r8 + isync + + /* Check if HDEC expires soon */ + mfspr r3, SPRN_HDEC + cmpwi r3, 512 /* 1 microsecond */ + blt hdec_soon + ld r6, VCPU_CTR(r4) lwz r7, VCPU_XER(r4) @@ -880,6 +931,12 @@ fast_guest_return: li r9, KVM_GUEST_MODE_GUEST_HV stb r9, HSTATE_IN_GUEST(r13) +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + /* Accumulate timing */ + addi r3, r4, VCPU_TB_GUEST + bl kvmhv_accumulate_time +#endif + /* Enter guest */ BEGIN_FTR_SECTION @@ -917,6 +974,27 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) hrfid b . +secondary_too_late: + li r12, 0 + cmpdi r4, 0 + beq 11f + stw r12, VCPU_TRAP(r4) +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r4, VCPU_TB_RMEXIT + bl kvmhv_accumulate_time +#endif +11: b kvmhv_switch_to_host + +hdec_soon: + li r12, BOOK3S_INTERRUPT_HV_DECREMENTER + stw r12, VCPU_TRAP(r4) + mr r9, r4 +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r4, VCPU_TB_RMEXIT + bl kvmhv_accumulate_time +#endif + b guest_exit_cont + /****************************************************************************** * * * Exit code * @@ -1002,6 +1080,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) stw r12,VCPU_TRAP(r9) +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r9, VCPU_TB_RMINTR + mr r4, r9 + bl kvmhv_accumulate_time + ld r5, VCPU_GPR(R5)(r9) + ld r6, VCPU_GPR(R6)(r9) + ld r7, VCPU_GPR(R7)(r9) + ld r8, VCPU_GPR(R8)(r9) +#endif + /* Save HEIR (HV emulation assist reg) in emul_inst if this is an HEI (HV emulation interrupt, e40) */ li r3,KVM_INST_FETCH_FAILED @@ -1028,34 +1116,37 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) bne 2f mfspr r3,SPRN_HDEC cmpwi r3,0 - bge ignore_hdec + mr r4,r9 + bge fast_guest_return 2: /* See if this is an hcall we can handle in real mode */ cmpwi r12,BOOK3S_INTERRUPT_SYSCALL beq hcall_try_real_mode + /* Hypervisor doorbell - exit only if host IPI flag set */ + cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL + bne 3f + lbz r0, HSTATE_HOST_IPI(r13) + beq 4f + b guest_exit_cont +3: /* External interrupt ? */ cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL - bne+ ext_interrupt_to_host + bne+ guest_exit_cont /* External interrupt, first check for host_ipi. If this is * set, we know the host wants us out so let's do it now */ bl kvmppc_read_intr cmpdi r3, 0 - bgt ext_interrupt_to_host + bgt guest_exit_cont /* Check if any CPU is heading out to the host, if so head out too */ - ld r5, HSTATE_KVM_VCORE(r13) +4: ld r5, HSTATE_KVM_VCORE(r13) lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 - bge ext_interrupt_to_host - - /* Return to guest after delivering any pending interrupt */ mr r4, r9 - b deliver_guest_interrupt - -ext_interrupt_to_host: + blt deliver_guest_interrupt guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ /* Save more register state */ @@ -1065,7 +1156,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ stw r7, VCPU_DSISR(r9) /* don't overwrite fault_dar/fault_dsisr if HDSI */ cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE - beq 6f + beq mc_cont std r6, VCPU_FAULT_DAR(r9) stw r7, VCPU_FAULT_DSISR(r9) @@ -1073,9 +1164,20 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK beq machine_check_realmode mc_cont: +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r9, VCPU_TB_RMEXIT + mr r4, r9 + bl kvmhv_accumulate_time +#endif + + /* Increment exit count, poke other threads to exit */ + bl kvmhv_commence_exit + nop + ld r9, HSTATE_KVM_VCPU(r13) + lwz r12, VCPU_TRAP(r9) /* Save guest CTRL register, set runlatch to 1 */ -6: mfspr r6,SPRN_CTRLF + mfspr r6,SPRN_CTRLF stw r6,VCPU_CTRL(r9) andi. r0,r6,1 bne 4f @@ -1417,68 +1519,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) slbia ptesync -hdec_soon: /* r12 = trap, r13 = paca */ /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. */ - /* Increment the threads-exiting-guest count in the 0xff00 - bits of vcore->entry_exit_count */ - ld r5,HSTATE_KVM_VCORE(r13) - addi r6,r5,VCORE_ENTRY_EXIT -41: lwarx r3,0,r6 - addi r0,r3,0x100 - stwcx. r0,0,r6 - bne 41b - isync /* order stwcx. vs. reading napping_threads */ - - /* - * At this point we have an interrupt that we have to pass - * up to the kernel or qemu; we can't handle it in real mode. - * Thus we have to do a partition switch, so we have to - * collect the other threads, if we are the first thread - * to take an interrupt. To do this, we set the HDEC to 0, - * which causes an HDEC interrupt in all threads within 2ns - * because the HDEC register is shared between all 4 threads. - * However, we don't need to bother if this is an HDEC - * interrupt, since the other threads will already be on their - * way here in that case. - */ - cmpwi r3,0x100 /* Are we the first here? */ - bge 43f - cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER - beq 40f - li r0,0 - mtspr SPRN_HDEC,r0 -40: - /* - * Send an IPI to any napping threads, since an HDEC interrupt - * doesn't wake CPUs up from nap. - */ - lwz r3,VCORE_NAPPING_THREADS(r5) - lbz r4,HSTATE_PTID(r13) - li r0,1 - sld r0,r0,r4 - andc. r3,r3,r0 /* no sense IPI'ing ourselves */ - beq 43f - /* Order entry/exit update vs. IPIs */ - sync - mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ - subf r6,r4,r13 -42: andi. r0,r3,1 - beq 44f - ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */ - li r0,IPI_PRIORITY - li r7,XICS_MFRR - stbcix r0,r7,r8 /* trigger the IPI */ -44: srdi. r3,r3,1 - addi r6,r6,PACA_SIZE - bne 42b - -secondary_too_late: +kvmhv_switch_to_host: /* Secondary threads wait for primary to do partition switch */ -43: ld r5,HSTATE_KVM_VCORE(r13) + ld r5,HSTATE_KVM_VCORE(r13) ld r4,VCORE_KVM(r5) /* pointer to struct kvm */ lbz r3,HSTATE_PTID(r13) cmpwi r3,0 @@ -1562,6 +1610,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 1: addi r8,r8,16 .endr +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + /* Finish timing, if we have a vcpu */ + ld r4, HSTATE_KVM_VCPU(r13) + cmpdi r4, 0 + li r3, 0 + beq 2f + bl kvmhv_accumulate_time +2: +#endif /* Unset guest mode */ li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) @@ -1696,8 +1753,10 @@ kvmppc_hisi: * Returns to the guest if we handle it, or continues on up to * the kernel if we can't (i.e. if we don't have a handler for * it, or if the handler returns H_TOO_HARD). + * + * r5 - r8 contain hcall args, + * r9 = vcpu, r10 = pc, r11 = msr, r12 = trap, r13 = paca */ - .globl hcall_try_real_mode hcall_try_real_mode: ld r3,VCPU_GPR(R3)(r9) andi. r0,r11,MSR_PR @@ -1839,13 +1898,124 @@ hcall_real_table: .long 0 /* 0x12c */ .long 0 /* 0x130 */ .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table + .long 0 /* 0x138 */ + .long 0 /* 0x13c */ + .long 0 /* 0x140 */ + .long 0 /* 0x144 */ + .long 0 /* 0x148 */ + .long 0 /* 0x14c */ + .long 0 /* 0x150 */ + .long 0 /* 0x154 */ + .long 0 /* 0x158 */ + .long 0 /* 0x15c */ + .long 0 /* 0x160 */ + .long 0 /* 0x164 */ + .long 0 /* 0x168 */ + .long 0 /* 0x16c */ + .long 0 /* 0x170 */ + .long 0 /* 0x174 */ + .long 0 /* 0x178 */ + .long 0 /* 0x17c */ + .long 0 /* 0x180 */ + .long 0 /* 0x184 */ + .long 0 /* 0x188 */ + .long 0 /* 0x18c */ + .long 0 /* 0x190 */ + .long 0 /* 0x194 */ + .long 0 /* 0x198 */ + .long 0 /* 0x19c */ + .long 0 /* 0x1a0 */ + .long 0 /* 0x1a4 */ + .long 0 /* 0x1a8 */ + .long 0 /* 0x1ac */ + .long 0 /* 0x1b0 */ + .long 0 /* 0x1b4 */ + .long 0 /* 0x1b8 */ + .long 0 /* 0x1bc */ + .long 0 /* 0x1c0 */ + .long 0 /* 0x1c4 */ + .long 0 /* 0x1c8 */ + .long 0 /* 0x1cc */ + .long 0 /* 0x1d0 */ + .long 0 /* 0x1d4 */ + .long 0 /* 0x1d8 */ + .long 0 /* 0x1dc */ + .long 0 /* 0x1e0 */ + .long 0 /* 0x1e4 */ + .long 0 /* 0x1e8 */ + .long 0 /* 0x1ec */ + .long 0 /* 0x1f0 */ + .long 0 /* 0x1f4 */ + .long 0 /* 0x1f8 */ + .long 0 /* 0x1fc */ + .long 0 /* 0x200 */ + .long 0 /* 0x204 */ + .long 0 /* 0x208 */ + .long 0 /* 0x20c */ + .long 0 /* 0x210 */ + .long 0 /* 0x214 */ + .long 0 /* 0x218 */ + .long 0 /* 0x21c */ + .long 0 /* 0x220 */ + .long 0 /* 0x224 */ + .long 0 /* 0x228 */ + .long 0 /* 0x22c */ + .long 0 /* 0x230 */ + .long 0 /* 0x234 */ + .long 0 /* 0x238 */ + .long 0 /* 0x23c */ + .long 0 /* 0x240 */ + .long 0 /* 0x244 */ + .long 0 /* 0x248 */ + .long 0 /* 0x24c */ + .long 0 /* 0x250 */ + .long 0 /* 0x254 */ + .long 0 /* 0x258 */ + .long 0 /* 0x25c */ + .long 0 /* 0x260 */ + .long 0 /* 0x264 */ + .long 0 /* 0x268 */ + .long 0 /* 0x26c */ + .long 0 /* 0x270 */ + .long 0 /* 0x274 */ + .long 0 /* 0x278 */ + .long 0 /* 0x27c */ + .long 0 /* 0x280 */ + .long 0 /* 0x284 */ + .long 0 /* 0x288 */ + .long 0 /* 0x28c */ + .long 0 /* 0x290 */ + .long 0 /* 0x294 */ + .long 0 /* 0x298 */ + .long 0 /* 0x29c */ + .long 0 /* 0x2a0 */ + .long 0 /* 0x2a4 */ + .long 0 /* 0x2a8 */ + .long 0 /* 0x2ac */ + .long 0 /* 0x2b0 */ + .long 0 /* 0x2b4 */ + .long 0 /* 0x2b8 */ + .long 0 /* 0x2bc */ + .long 0 /* 0x2c0 */ + .long 0 /* 0x2c4 */ + .long 0 /* 0x2c8 */ + .long 0 /* 0x2cc */ + .long 0 /* 0x2d0 */ + .long 0 /* 0x2d4 */ + .long 0 /* 0x2d8 */ + .long 0 /* 0x2dc */ + .long 0 /* 0x2e0 */ + .long 0 /* 0x2e4 */ + .long 0 /* 0x2e8 */ + .long 0 /* 0x2ec */ + .long 0 /* 0x2f0 */ + .long 0 /* 0x2f4 */ + .long 0 /* 0x2f8 */ + .long 0 /* 0x2fc */ + .long DOTSYM(kvmppc_h_random) - hcall_real_table .globl hcall_real_table_end hcall_real_table_end: -ignore_hdec: - mr r4,r9 - b fast_guest_return - _GLOBAL(kvmppc_h_set_xdabr) andi. r0, r5, DABRX_USER | DABRX_KERNEL beq 6f @@ -1884,7 +2054,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r3, 0 blr -_GLOBAL(kvmppc_h_cede) +_GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */ ori r11,r11,MSR_EE std r11,VCPU_MSR(r3) li r0,1 @@ -1893,8 +2063,8 @@ _GLOBAL(kvmppc_h_cede) lbz r5,VCPU_PRODDED(r3) cmpwi r5,0 bne kvm_cede_prodded - li r0,0 /* set trap to 0 to say hcall is handled */ - stw r0,VCPU_TRAP(r3) + li r12,0 /* set trap to 0 to say hcall is handled */ + stw r12,VCPU_TRAP(r3) li r0,H_SUCCESS std r0,VCPU_GPR(R3)(r3) @@ -1912,12 +2082,11 @@ _GLOBAL(kvmppc_h_cede) addi r6,r5,VCORE_NAPPING_THREADS 31: lwarx r4,0,r6 or r4,r4,r0 - PPC_POPCNTW(R7,R4) - cmpw r7,r8 - bge kvm_cede_exit + cmpw r4,r8 + beq kvm_cede_exit stwcx. r4,0,r6 bne 31b - /* order napping_threads update vs testing entry_exit_count */ + /* order napping_threads update vs testing entry_exit_map */ isync li r0,NAPPING_CEDE stb r0,HSTATE_NAPPING(r13) @@ -1955,21 +2124,52 @@ _GLOBAL(kvmppc_h_cede) bl kvmppc_save_fp /* + * Set DEC to the smaller of DEC and HDEC, so that we wake + * no later than the end of our timeslice (HDEC interrupts + * don't wake us from nap). + */ + mfspr r3, SPRN_DEC + mfspr r4, SPRN_HDEC + mftb r5 + cmpw r3, r4 + ble 67f + mtspr SPRN_DEC, r4 +67: + /* save expiry time of guest decrementer */ + extsw r3, r3 + add r3, r3, r5 + ld r4, HSTATE_KVM_VCPU(r13) + ld r5, HSTATE_KVM_VCORE(r13) + ld r6, VCORE_TB_OFFSET(r5) + subf r3, r6, r3 /* convert to host TB value */ + std r3, VCPU_DEC_EXPIRES(r4) + +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + ld r4, HSTATE_KVM_VCPU(r13) + addi r3, r4, VCPU_TB_CEDE + bl kvmhv_accumulate_time +#endif + + lis r3, LPCR_PECEDP@h /* Do wake on privileged doorbell */ + + /* * Take a nap until a decrementer or external or doobell interrupt - * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the - * runlatch bit before napping. + * occurs, with PECE1 and PECE0 set in LPCR. + * On POWER8, set PECEDH, and if we are ceding, also set PECEDP. + * Also clear the runlatch bit before napping. */ kvm_do_nap: - mfspr r2, SPRN_CTRLF - clrrdi r2, r2, 1 - mtspr SPRN_CTRLT, r2 + mfspr r0, SPRN_CTRLF + clrrdi r0, r0, 1 + mtspr SPRN_CTRLT, r0 li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) mfspr r5,SPRN_LPCR ori r5,r5,LPCR_PECE0 | LPCR_PECE1 BEGIN_FTR_SECTION - oris r5,r5,LPCR_PECEDP@h + ori r5, r5, LPCR_PECEDH + rlwimi r5, r3, 0, LPCR_PECEDP END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_LPCR,r5 isync @@ -1994,9 +2194,23 @@ kvm_end_cede: /* Woken by external or decrementer interrupt */ ld r1, HSTATE_HOST_R1(r13) +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r4, VCPU_TB_RMINTR + bl kvmhv_accumulate_time +#endif + /* load up FP state */ bl kvmppc_load_fp + /* Restore guest decrementer */ + ld r3, VCPU_DEC_EXPIRES(r4) + ld r5, HSTATE_KVM_VCORE(r13) + ld r6, VCORE_TB_OFFSET(r5) + add r3, r3, r6 /* convert host TB to guest TB value */ + mftb r7 + subf r3, r7, r3 + mtspr SPRN_DEC, r3 + /* Load NV GPRS */ ld r14, VCPU_GPR(R14)(r4) ld r15, VCPU_GPR(R15)(r4) @@ -2057,7 +2271,8 @@ kvm_cede_prodded: /* we've ceded but we want to give control to the host */ kvm_cede_exit: - b hcall_real_fallback + ld r9, HSTATE_KVM_VCPU(r13) + b guest_exit_cont /* Try to handle a machine check in real mode */ machine_check_realmode: @@ -2089,13 +2304,14 @@ machine_check_realmode: /* * Check the reason we woke from nap, and take appropriate action. - * Returns: + * Returns (in r3): * 0 if nothing needs to be done * 1 if something happened that needs to be handled by the host - * -1 if there was a guest wakeup (IPI) + * -1 if there was a guest wakeup (IPI or msgsnd) * * Also sets r12 to the interrupt vector for any interrupt that needs * to be handled now by the host (0x500 for external interrupt), or zero. + * Modifies r0, r6, r7, r8. */ kvmppc_check_wake_reason: mfspr r6, SPRN_SRR1 @@ -2122,7 +2338,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* hypervisor doorbell */ 3: li r12, BOOK3S_INTERRUPT_H_DOORBELL + /* see if it's a host IPI */ li r3, 1 + lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 + bnelr + /* if not, clear it and return -1 */ + lis r6, (PPC_DBELL_SERVER << (63-36))@h + PPC_MSGCLR(6) + li r3, -1 blr /* @@ -2131,6 +2355,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * 0 if no interrupt is pending * 1 if an interrupt is pending that needs to be handled by the host * -1 if there was a guest wakeup IPI (which has now been cleared) + * Modifies r0, r6, r7, r8, returns value in r3. */ kvmppc_read_intr: /* see if a host IPI is pending */ @@ -2185,6 +2410,7 @@ kvmppc_read_intr: bne- 43f /* OK, it's an IPI for us */ + li r12, 0 li r3, -1 1: blr @@ -2314,3 +2540,62 @@ kvmppc_fix_pmao: mtspr SPRN_PMC6, r3 isync blr + +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +/* + * Start timing an activity + * r3 = pointer to time accumulation struct, r4 = vcpu + */ +kvmhv_start_timing: + ld r5, HSTATE_KVM_VCORE(r13) + lbz r6, VCORE_IN_GUEST(r5) + cmpwi r6, 0 + beq 5f /* if in guest, need to */ + ld r6, VCORE_TB_OFFSET(r5) /* subtract timebase offset */ +5: mftb r5 + subf r5, r6, r5 + std r3, VCPU_CUR_ACTIVITY(r4) + std r5, VCPU_ACTIVITY_START(r4) + blr + +/* + * Accumulate time to one activity and start another. + * r3 = pointer to new time accumulation struct, r4 = vcpu + */ +kvmhv_accumulate_time: + ld r5, HSTATE_KVM_VCORE(r13) + lbz r8, VCORE_IN_GUEST(r5) + cmpwi r8, 0 + beq 4f /* if in guest, need to */ + ld r8, VCORE_TB_OFFSET(r5) /* subtract timebase offset */ +4: ld r5, VCPU_CUR_ACTIVITY(r4) + ld r6, VCPU_ACTIVITY_START(r4) + std r3, VCPU_CUR_ACTIVITY(r4) + mftb r7 + subf r7, r8, r7 + std r7, VCPU_ACTIVITY_START(r4) + cmpdi r5, 0 + beqlr + subf r3, r6, r7 + ld r8, TAS_SEQCOUNT(r5) + cmpdi r8, 0 + addi r8, r8, 1 + std r8, TAS_SEQCOUNT(r5) + lwsync + ld r7, TAS_TOTAL(r5) + add r7, r7, r3 + std r7, TAS_TOTAL(r5) + ld r6, TAS_MIN(r5) + ld r7, TAS_MAX(r5) + beq 3f + cmpd r3, r6 + bge 1f +3: std r3, TAS_MIN(r5) +1: cmpd r3, r7 + ble 2f + std r3, TAS_MAX(r5) +2: lwsync + addi r8, r8, 1 + std r8, TAS_SEQCOUNT(r5) + blr +#endif diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ce3c893d509b..f2c75a1e0536 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -258,6 +258,28 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu) +{ + long rc; + + rc = kvmppc_h_logical_ci_load(vcpu); + if (rc == H_TOO_HARD) + return EMULATE_FAIL; + kvmppc_set_gpr(vcpu, 3, rc); + return EMULATE_DONE; +} + +static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) +{ + long rc; + + rc = kvmppc_h_logical_ci_store(vcpu); + if (rc == H_TOO_HARD) + return EMULATE_FAIL; + kvmppc_set_gpr(vcpu, 3, rc); + return EMULATE_DONE; +} + static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { long rc = kvmppc_xics_hcall(vcpu, cmd); @@ -290,6 +312,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) clear_bit(KVM_REQ_UNHALT, &vcpu->requests); vcpu->stat.halt_wakeup++; return EMULATE_DONE; + case H_LOGICAL_CI_LOAD: + return kvmppc_h_pr_logical_ci_load(vcpu); + case H_LOGICAL_CI_STORE: + return kvmppc_h_pr_logical_ci_store(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -323,6 +349,8 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_BULK_REMOVE: case H_PUT_TCE: case H_CEDE: + case H_LOGICAL_CI_LOAD: + case H_LOGICAL_CI_STORE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a4a8d9f0dcb7..8f3e6cc54d95 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -20,6 +20,7 @@ #include <asm/xics.h> #include <asm/debug.h> #include <asm/time.h> +#include <asm/spinlock.h> #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -39,7 +40,7 @@ * LOCKING * ======= * - * Each ICS has a mutex protecting the information about the IRQ + * Each ICS has a spin lock protecting the information about the IRQ * sources and avoiding simultaneous deliveries if the same interrupt. * * ICP operations are done via a single compare & swap transaction @@ -109,7 +110,10 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics, { int i; - mutex_lock(&ics->lock); + unsigned long flags; + + local_irq_save(flags); + arch_spin_lock(&ics->lock); for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *state = &ics->irq_state[i]; @@ -120,12 +124,15 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics, XICS_DBG("resend %#x prio %#x\n", state->number, state->priority); - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); icp_deliver_irq(xics, icp, state->number); - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); } - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); } static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, @@ -133,8 +140,10 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, u32 server, u32 priority, u32 saved_priority) { bool deliver; + unsigned long flags; - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); state->server = server; state->priority = priority; @@ -145,7 +154,8 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, deliver = true; } - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); return deliver; } @@ -186,6 +196,7 @@ int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority) struct kvmppc_ics *ics; struct ics_irq_state *state; u16 src; + unsigned long flags; if (!xics) return -ENODEV; @@ -195,10 +206,12 @@ int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority) return -EINVAL; state = &ics->irq_state[src]; - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); *server = state->server; *priority = state->priority; - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); return 0; } @@ -365,6 +378,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, struct kvmppc_ics *ics; u32 reject; u16 src; + unsigned long flags; /* * This is used both for initial delivery of an interrupt and @@ -391,7 +405,8 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, state = &ics->irq_state[src]; /* Get a lock on the ICS */ - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); /* Get our server */ if (!icp || state->server != icp->server_num) { @@ -434,7 +449,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * * Note that if successful, the new delivery might have itself * rejected an interrupt that was "delivered" before we took the - * icp mutex. + * ics spin lock. * * In this case we do the whole sequence all over again for the * new guy. We cannot assume that the rejected interrupt is less @@ -448,7 +463,8 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * Delivery was successful, did we reject somebody else ? */ if (reject && reject != XICS_IPI) { - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); new_irq = reject; goto again; } @@ -468,12 +484,14 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ smp_mb(); if (!icp->state.need_resend) { - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); goto again; } } out: - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); } static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, @@ -802,14 +820,22 @@ static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n", hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt); - if (icp->rm_action & XICS_RM_KICK_VCPU) + if (icp->rm_action & XICS_RM_KICK_VCPU) { + icp->n_rm_kick_vcpu++; kvmppc_fast_vcpu_kick(icp->rm_kick_target); - if (icp->rm_action & XICS_RM_CHECK_RESEND) + } + if (icp->rm_action & XICS_RM_CHECK_RESEND) { + icp->n_rm_check_resend++; icp_check_resend(xics, icp->rm_resend_icp); - if (icp->rm_action & XICS_RM_REJECT) + } + if (icp->rm_action & XICS_RM_REJECT) { + icp->n_rm_reject++; icp_deliver_irq(xics, icp, icp->rm_reject); - if (icp->rm_action & XICS_RM_NOTIFY_EOI) + } + if (icp->rm_action & XICS_RM_NOTIFY_EOI) { + icp->n_rm_notify_eoi++; kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq); + } icp->rm_action = 0; @@ -872,10 +898,21 @@ static int xics_debug_show(struct seq_file *m, void *private) struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; int icsid, i; + unsigned long flags; + unsigned long t_rm_kick_vcpu, t_rm_check_resend; + unsigned long t_rm_reject, t_rm_notify_eoi; + unsigned long t_reject, t_check_resend; if (!kvm) return 0; + t_rm_kick_vcpu = 0; + t_rm_notify_eoi = 0; + t_rm_check_resend = 0; + t_rm_reject = 0; + t_check_resend = 0; + t_reject = 0; + seq_printf(m, "=========\nICP state\n=========\n"); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -890,8 +927,19 @@ static int xics_debug_show(struct seq_file *m, void *private) icp->server_num, state.xisr, state.pending_pri, state.cppr, state.mfrr, state.out_ee, state.need_resend); + t_rm_kick_vcpu += icp->n_rm_kick_vcpu; + t_rm_notify_eoi += icp->n_rm_notify_eoi; + t_rm_check_resend += icp->n_rm_check_resend; + t_rm_reject += icp->n_rm_reject; + t_check_resend += icp->n_check_resend; + t_reject += icp->n_reject; } + seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu reject=%lu notify_eoi=%lu\n", + t_rm_kick_vcpu, t_rm_check_resend, + t_rm_reject, t_rm_notify_eoi); + seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n", + t_check_resend, t_reject); for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) { struct kvmppc_ics *ics = xics->ics[icsid]; @@ -901,7 +949,8 @@ static int xics_debug_show(struct seq_file *m, void *private) seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n", icsid); - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *irq = &ics->irq_state[i]; @@ -912,7 +961,8 @@ static int xics_debug_show(struct seq_file *m, void *private) irq->resend, irq->masked_pending); } - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); } return 0; } @@ -965,7 +1015,6 @@ static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm, if (!ics) goto out; - mutex_init(&ics->lock); ics->icsid = icsid; for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { @@ -1107,13 +1156,15 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr) u64 __user *ubufp = (u64 __user *) addr; u16 idx; u64 val, prio; + unsigned long flags; ics = kvmppc_xics_find_ics(xics, irq, &idx); if (!ics) return -ENOENT; irqp = &ics->irq_state[idx]; - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); ret = -ENOENT; if (irqp->exists) { val = irqp->server; @@ -1129,7 +1180,8 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr) val |= KVM_XICS_PENDING; ret = 0; } - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); if (!ret && put_user(val, ubufp)) ret = -EFAULT; @@ -1146,6 +1198,7 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) u64 val; u8 prio; u32 server; + unsigned long flags; if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS) return -ENOENT; @@ -1166,7 +1219,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) kvmppc_xics_find_server(xics->kvm, server) == NULL) return -EINVAL; - mutex_lock(&ics->lock); + local_irq_save(flags); + arch_spin_lock(&ics->lock); irqp->server = server; irqp->saved_priority = prio; if (val & KVM_XICS_MASKED) @@ -1178,7 +1232,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) if ((val & KVM_XICS_PENDING) && (val & KVM_XICS_LEVEL_SENSITIVE)) irqp->asserted = 1; irqp->exists = 1; - mutex_unlock(&ics->lock); + arch_spin_unlock(&ics->lock); + local_irq_restore(flags); if (val & KVM_XICS_PENDING) icp_deliver_irq(xics, NULL, irqp->number); diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 73f0f2723c07..56ea44f9867f 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -78,13 +78,22 @@ struct kvmppc_icp { u32 rm_reject; u32 rm_eoied_irq; + /* Counters for each reason we exited real mode */ + unsigned long n_rm_kick_vcpu; + unsigned long n_rm_check_resend; + unsigned long n_rm_reject; + unsigned long n_rm_notify_eoi; + /* Counters for handling ICP processing in real mode */ + unsigned long n_check_resend; + unsigned long n_reject; + /* Debug stuff for real mode */ union kvmppc_icp_state rm_dbgstate; struct kvm_vcpu *rm_dbgtgt; }; struct kvmppc_ics { - struct mutex lock; + arch_spinlock_t lock; u16 icsid; struct ics_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS]; }; @@ -96,6 +105,8 @@ struct kvmppc_xics { u32 max_icsid; bool real_mode; bool real_mode_dbg; + u32 err_noics; + u32 err_noicp; struct kvmppc_ics *ics[KVMPPC_XICS_MAX_ICS_ID + 1]; }; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index cc536d4a75ef..4d33e199edcc 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -338,6 +338,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, pte_t *ptep; unsigned int wimg = 0; pgd_t *pgdir; + unsigned long flags; /* used to check for invalidations in progress */ mmu_seq = kvm->mmu_notifier_seq; @@ -468,15 +469,28 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, pgdir = vcpu_e500->vcpu.arch.pgdir; - ptep = lookup_linux_ptep(pgdir, hva, &tsize_pages); - if (pte_present(*ptep)) - wimg = (*ptep >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; - else { - if (printk_ratelimit()) - pr_err("%s: pte not present: gfn %lx, pfn %lx\n", - __func__, (long)gfn, pfn); - ret = -EINVAL; - goto out; + /* + * We are just looking at the wimg bits, so we don't + * care much about the trans splitting bit. + * We are holding kvm->mmu_lock so a notifier invalidate + * can't run hence pfn won't change. + */ + local_irq_save(flags); + ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL); + if (ptep) { + pte_t pte = READ_ONCE(*ptep); + + if (pte_present(pte)) { + wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) & + MAS2_WIMGE_MASK; + local_irq_restore(flags); + } else { + local_irq_restore(flags); + pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n", + __func__, (long)gfn, pfn); + ret = -EINVAL; + goto out; + } } kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 24bfe401373e..ac3ddf115f3d 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -529,6 +529,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PPC_RMA: r = 0; break; + case KVM_CAP_PPC_HWRNG: + r = kvmppc_hwrng_present(); + break; #endif case KVM_CAP_SYNC_MMU: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -720,7 +723,7 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, return; } - if (vcpu->arch.mmio_is_bigendian) { + if (!vcpu->arch.mmio_host_swabbed) { switch (run->mmio.len) { case 8: gpr = *(u64 *)run->mmio.data; break; case 4: gpr = *(u32 *)run->mmio.data; break; @@ -728,10 +731,10 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, case 1: gpr = *(u8 *)run->mmio.data; break; } } else { - /* Convert BE data from userland back to LE. */ switch (run->mmio.len) { - case 4: gpr = ld_le32((u32 *)run->mmio.data); break; - case 2: gpr = ld_le16((u16 *)run->mmio.data); break; + case 8: gpr = swab64(*(u64 *)run->mmio.data); break; + case 4: gpr = swab32(*(u32 *)run->mmio.data); break; + case 2: gpr = swab16(*(u16 *)run->mmio.data); break; case 1: gpr = *(u8 *)run->mmio.data; break; } } @@ -780,14 +783,13 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, int is_default_endian) { int idx, ret; - int is_bigendian; + bool host_swabbed; + /* Pity C doesn't have a logical XOR operator */ if (kvmppc_need_byteswap(vcpu)) { - /* Default endianness is "little endian". */ - is_bigendian = !is_default_endian; + host_swabbed = is_default_endian; } else { - /* Default endianness is "big endian". */ - is_bigendian = is_default_endian; + host_swabbed = !is_default_endian; } if (bytes > sizeof(run->mmio.data)) { @@ -800,7 +802,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, run->mmio.is_write = 0; vcpu->arch.io_gpr = rt; - vcpu->arch.mmio_is_bigendian = is_bigendian; + vcpu->arch.mmio_host_swabbed = host_swabbed; vcpu->mmio_needed = 1; vcpu->mmio_is_write = 0; vcpu->arch.mmio_sign_extend = 0; @@ -840,14 +842,13 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, { void *data = run->mmio.data; int idx, ret; - int is_bigendian; + bool host_swabbed; + /* Pity C doesn't have a logical XOR operator */ if (kvmppc_need_byteswap(vcpu)) { - /* Default endianness is "little endian". */ - is_bigendian = !is_default_endian; + host_swabbed = is_default_endian; } else { - /* Default endianness is "big endian". */ - is_bigendian = is_default_endian; + host_swabbed = !is_default_endian; } if (bytes > sizeof(run->mmio.data)) { @@ -862,7 +863,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->mmio_is_write = 1; /* Store the value at the lowest bytes in 'data'. */ - if (is_bigendian) { + if (!host_swabbed) { switch (bytes) { case 8: *(u64 *)data = val; break; case 4: *(u32 *)data = val; break; @@ -870,11 +871,11 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, case 1: *(u8 *)data = val; break; } } else { - /* Store LE value into 'data'. */ switch (bytes) { - case 4: st_le32(data, val); break; - case 2: st_le16(data, val); break; - case 1: *(u8 *)data = val; break; + case 8: *(u64 *)data = swab64(val); break; + case 4: *(u32 *)data = swab32(val); break; + case 2: *(u16 *)data = swab16(val); break; + case 1: *(u8 *)data = val; break; } } diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index 4a6c2cf890d9..60b0b3fc8fc1 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -10,7 +10,7 @@ void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask) { void *p; - if (mem_init_done) + if (slab_is_available()) p = kzalloc(size, mask); else { p = memblock_virt_alloc(size, 0); diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index 55f19f9fd708..6813f80d1eec 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -69,54 +69,6 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) -/* - * Use dcbz on the complete cache lines in the destination - * to set them to zero. This requires that the destination - * area is cacheable. -- paulus - */ -_GLOBAL(cacheable_memzero) - mr r5,r4 - li r4,0 - addi r6,r3,-4 - cmplwi 0,r5,4 - blt 7f - stwu r4,4(r6) - beqlr - andi. r0,r6,3 - add r5,r0,r5 - subf r6,r0,r6 - clrlwi r7,r6,32-LG_CACHELINE_BYTES - add r8,r7,r5 - srwi r9,r8,LG_CACHELINE_BYTES - addic. r9,r9,-1 /* total number of complete cachelines */ - ble 2f - xori r0,r7,CACHELINE_MASK & ~3 - srwi. r0,r0,2 - beq 3f - mtctr r0 -4: stwu r4,4(r6) - bdnz 4b -3: mtctr r9 - li r7,4 -10: dcbz r7,r6 - addi r6,r6,CACHELINE_BYTES - bdnz 10b - clrlwi r5,r8,32-LG_CACHELINE_BYTES - addi r5,r5,4 -2: srwi r0,r5,2 - mtctr r0 - bdz 6f -1: stwu r4,4(r6) - bdnz 1b -6: andi. r5,r5,3 -7: cmpwi 0,r5,0 - beqlr - mtctr r5 - addi r6,r6,3 -8: stbu r4,1(r6) - bdnz 8b - blr - _GLOBAL(memset) rlwimi r4,r4,8,16,23 rlwimi r4,r4,16,0,15 @@ -142,85 +94,6 @@ _GLOBAL(memset) bdnz 8b blr -/* - * This version uses dcbz on the complete cache lines in the - * destination area to reduce memory traffic. This requires that - * the destination area is cacheable. - * We only use this version if the source and dest don't overlap. - * -- paulus. - */ -_GLOBAL(cacheable_memcpy) - add r7,r3,r5 /* test if the src & dst overlap */ - add r8,r4,r5 - cmplw 0,r4,r7 - cmplw 1,r3,r8 - crand 0,0,4 /* cr0.lt &= cr1.lt */ - blt memcpy /* if regions overlap */ - - addi r4,r4,-4 - addi r6,r3,-4 - neg r0,r3 - andi. r0,r0,CACHELINE_MASK /* # bytes to start of cache line */ - beq 58f - - cmplw 0,r5,r0 /* is this more than total to do? */ - blt 63f /* if not much to do */ - andi. r8,r0,3 /* get it word-aligned first */ - subf r5,r0,r5 - mtctr r8 - beq+ 61f -70: lbz r9,4(r4) /* do some bytes */ - stb r9,4(r6) - addi r4,r4,1 - addi r6,r6,1 - bdnz 70b -61: srwi. r0,r0,2 - mtctr r0 - beq 58f -72: lwzu r9,4(r4) /* do some words */ - stwu r9,4(r6) - bdnz 72b - -58: srwi. r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */ - clrlwi r5,r5,32-LG_CACHELINE_BYTES - li r11,4 - mtctr r0 - beq 63f -53: - dcbz r11,r6 - COPY_16_BYTES -#if L1_CACHE_BYTES >= 32 - COPY_16_BYTES -#if L1_CACHE_BYTES >= 64 - COPY_16_BYTES - COPY_16_BYTES -#if L1_CACHE_BYTES >= 128 - COPY_16_BYTES - COPY_16_BYTES - COPY_16_BYTES - COPY_16_BYTES -#endif -#endif -#endif - bdnz 53b - -63: srwi. r0,r5,2 - mtctr r0 - beq 64f -30: lwzu r0,4(r4) - stwu r0,4(r6) - bdnz 30b - -64: andi. r0,r5,3 - mtctr r0 - beq+ 65f -40: lbz r0,4(r4) - stb r0,4(r6) - addi r4,r4,1 - addi r6,r6,1 - bdnz 40b -65: blr - _GLOBAL(memmove) cmplw 0,r3,r4 bgt backwards_memcpy diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index d7dafb3777ac..a84d333ecb09 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -83,23 +83,23 @@ _GLOBAL(copypage_power7) li r12,112 .align 5 -1: lvx vr7,r0,r4 - lvx vr6,r4,r6 - lvx vr5,r4,r7 - lvx vr4,r4,r8 - lvx vr3,r4,r9 - lvx vr2,r4,r10 - lvx vr1,r4,r11 - lvx vr0,r4,r12 +1: lvx v7,r0,r4 + lvx v6,r4,r6 + lvx v5,r4,r7 + lvx v4,r4,r8 + lvx v3,r4,r9 + lvx v2,r4,r10 + lvx v1,r4,r11 + lvx v0,r4,r12 addi r4,r4,128 - stvx vr7,r0,r3 - stvx vr6,r3,r6 - stvx vr5,r3,r7 - stvx vr4,r3,r8 - stvx vr3,r3,r9 - stvx vr2,r3,r10 - stvx vr1,r3,r11 - stvx vr0,r3,r12 + stvx v7,r0,r3 + stvx v6,r3,r6 + stvx v5,r3,r7 + stvx v4,r3,r8 + stvx v3,r3,r9 + stvx v2,r3,r10 + stvx v1,r3,r11 + stvx v0,r3,r12 addi r3,r3,128 bdnz 1b diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 92ee840529bc..da0c568d18c4 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -388,29 +388,29 @@ err3; std r0,0(r3) li r11,48 bf cr7*4+3,5f -err3; lvx vr1,r0,r4 +err3; lvx v1,r0,r4 addi r4,r4,16 -err3; stvx vr1,r0,r3 +err3; stvx v1,r0,r3 addi r3,r3,16 5: bf cr7*4+2,6f -err3; lvx vr1,r0,r4 -err3; lvx vr0,r4,r9 +err3; lvx v1,r0,r4 +err3; lvx v0,r4,r9 addi r4,r4,32 -err3; stvx vr1,r0,r3 -err3; stvx vr0,r3,r9 +err3; stvx v1,r0,r3 +err3; stvx v0,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f -err3; lvx vr3,r0,r4 -err3; lvx vr2,r4,r9 -err3; lvx vr1,r4,r10 -err3; lvx vr0,r4,r11 +err3; lvx v3,r0,r4 +err3; lvx v2,r4,r9 +err3; lvx v1,r4,r10 +err3; lvx v0,r4,r11 addi r4,r4,64 -err3; stvx vr3,r0,r3 -err3; stvx vr2,r3,r9 -err3; stvx vr1,r3,r10 -err3; stvx vr0,r3,r11 +err3; stvx v3,r0,r3 +err3; stvx v2,r3,r9 +err3; stvx v1,r3,r10 +err3; stvx v0,r3,r11 addi r3,r3,64 7: sub r5,r5,r6 @@ -433,23 +433,23 @@ err3; stvx vr0,r3,r11 */ .align 5 8: -err4; lvx vr7,r0,r4 -err4; lvx vr6,r4,r9 -err4; lvx vr5,r4,r10 -err4; lvx vr4,r4,r11 -err4; lvx vr3,r4,r12 -err4; lvx vr2,r4,r14 -err4; lvx vr1,r4,r15 -err4; lvx vr0,r4,r16 +err4; lvx v7,r0,r4 +err4; lvx v6,r4,r9 +err4; lvx v5,r4,r10 +err4; lvx v4,r4,r11 +err4; lvx v3,r4,r12 +err4; lvx v2,r4,r14 +err4; lvx v1,r4,r15 +err4; lvx v0,r4,r16 addi r4,r4,128 -err4; stvx vr7,r0,r3 -err4; stvx vr6,r3,r9 -err4; stvx vr5,r3,r10 -err4; stvx vr4,r3,r11 -err4; stvx vr3,r3,r12 -err4; stvx vr2,r3,r14 -err4; stvx vr1,r3,r15 -err4; stvx vr0,r3,r16 +err4; stvx v7,r0,r3 +err4; stvx v6,r3,r9 +err4; stvx v5,r3,r10 +err4; stvx v4,r3,r11 +err4; stvx v3,r3,r12 +err4; stvx v2,r3,r14 +err4; stvx v1,r3,r15 +err4; stvx v0,r3,r16 addi r3,r3,128 bdnz 8b @@ -463,29 +463,29 @@ err4; stvx vr0,r3,r16 mtocrf 0x01,r6 bf cr7*4+1,9f -err3; lvx vr3,r0,r4 -err3; lvx vr2,r4,r9 -err3; lvx vr1,r4,r10 -err3; lvx vr0,r4,r11 +err3; lvx v3,r0,r4 +err3; lvx v2,r4,r9 +err3; lvx v1,r4,r10 +err3; lvx v0,r4,r11 addi r4,r4,64 -err3; stvx vr3,r0,r3 -err3; stvx vr2,r3,r9 -err3; stvx vr1,r3,r10 -err3; stvx vr0,r3,r11 +err3; stvx v3,r0,r3 +err3; stvx v2,r3,r9 +err3; stvx v1,r3,r10 +err3; stvx v0,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f -err3; lvx vr1,r0,r4 -err3; lvx vr0,r4,r9 +err3; lvx v1,r0,r4 +err3; lvx v0,r4,r9 addi r4,r4,32 -err3; stvx vr1,r0,r3 -err3; stvx vr0,r3,r9 +err3; stvx v1,r0,r3 +err3; stvx v0,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f -err3; lvx vr1,r0,r4 +err3; lvx v1,r0,r4 addi r4,r4,16 -err3; stvx vr1,r0,r3 +err3; stvx v1,r0,r3 addi r3,r3,16 /* Up to 15B to go */ @@ -560,42 +560,42 @@ err3; stw r7,4(r3) li r10,32 li r11,48 - LVS(vr16,0,r4) /* Setup permute control vector */ -err3; lvx vr0,0,r4 + LVS(v16,0,r4) /* Setup permute control vector */ +err3; lvx v0,0,r4 addi r4,r4,16 bf cr7*4+3,5f -err3; lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) +err3; lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) addi r4,r4,16 -err3; stvx vr8,r0,r3 +err3; stvx v8,r0,r3 addi r3,r3,16 - vor vr0,vr1,vr1 + vor v0,v1,v1 5: bf cr7*4+2,6f -err3; lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) -err3; lvx vr0,r4,r9 - VPERM(vr9,vr1,vr0,vr16) +err3; lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) +err3; lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) addi r4,r4,32 -err3; stvx vr8,r0,r3 -err3; stvx vr9,r3,r9 +err3; stvx v8,r0,r3 +err3; stvx v9,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f -err3; lvx vr3,r0,r4 - VPERM(vr8,vr0,vr3,vr16) -err3; lvx vr2,r4,r9 - VPERM(vr9,vr3,vr2,vr16) -err3; lvx vr1,r4,r10 - VPERM(vr10,vr2,vr1,vr16) -err3; lvx vr0,r4,r11 - VPERM(vr11,vr1,vr0,vr16) +err3; lvx v3,r0,r4 + VPERM(v8,v0,v3,v16) +err3; lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) +err3; lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) +err3; lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) addi r4,r4,64 -err3; stvx vr8,r0,r3 -err3; stvx vr9,r3,r9 -err3; stvx vr10,r3,r10 -err3; stvx vr11,r3,r11 +err3; stvx v8,r0,r3 +err3; stvx v9,r3,r9 +err3; stvx v10,r3,r10 +err3; stvx v11,r3,r11 addi r3,r3,64 7: sub r5,r5,r6 @@ -618,31 +618,31 @@ err3; stvx vr11,r3,r11 */ .align 5 8: -err4; lvx vr7,r0,r4 - VPERM(vr8,vr0,vr7,vr16) -err4; lvx vr6,r4,r9 - VPERM(vr9,vr7,vr6,vr16) -err4; lvx vr5,r4,r10 - VPERM(vr10,vr6,vr5,vr16) -err4; lvx vr4,r4,r11 - VPERM(vr11,vr5,vr4,vr16) -err4; lvx vr3,r4,r12 - VPERM(vr12,vr4,vr3,vr16) -err4; lvx vr2,r4,r14 - VPERM(vr13,vr3,vr2,vr16) -err4; lvx vr1,r4,r15 - VPERM(vr14,vr2,vr1,vr16) -err4; lvx vr0,r4,r16 - VPERM(vr15,vr1,vr0,vr16) +err4; lvx v7,r0,r4 + VPERM(v8,v0,v7,v16) +err4; lvx v6,r4,r9 + VPERM(v9,v7,v6,v16) +err4; lvx v5,r4,r10 + VPERM(v10,v6,v5,v16) +err4; lvx v4,r4,r11 + VPERM(v11,v5,v4,v16) +err4; lvx v3,r4,r12 + VPERM(v12,v4,v3,v16) +err4; lvx v2,r4,r14 + VPERM(v13,v3,v2,v16) +err4; lvx v1,r4,r15 + VPERM(v14,v2,v1,v16) +err4; lvx v0,r4,r16 + VPERM(v15,v1,v0,v16) addi r4,r4,128 -err4; stvx vr8,r0,r3 -err4; stvx vr9,r3,r9 -err4; stvx vr10,r3,r10 -err4; stvx vr11,r3,r11 -err4; stvx vr12,r3,r12 -err4; stvx vr13,r3,r14 -err4; stvx vr14,r3,r15 -err4; stvx vr15,r3,r16 +err4; stvx v8,r0,r3 +err4; stvx v9,r3,r9 +err4; stvx v10,r3,r10 +err4; stvx v11,r3,r11 +err4; stvx v12,r3,r12 +err4; stvx v13,r3,r14 +err4; stvx v14,r3,r15 +err4; stvx v15,r3,r16 addi r3,r3,128 bdnz 8b @@ -656,36 +656,36 @@ err4; stvx vr15,r3,r16 mtocrf 0x01,r6 bf cr7*4+1,9f -err3; lvx vr3,r0,r4 - VPERM(vr8,vr0,vr3,vr16) -err3; lvx vr2,r4,r9 - VPERM(vr9,vr3,vr2,vr16) -err3; lvx vr1,r4,r10 - VPERM(vr10,vr2,vr1,vr16) -err3; lvx vr0,r4,r11 - VPERM(vr11,vr1,vr0,vr16) +err3; lvx v3,r0,r4 + VPERM(v8,v0,v3,v16) +err3; lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) +err3; lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) +err3; lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) addi r4,r4,64 -err3; stvx vr8,r0,r3 -err3; stvx vr9,r3,r9 -err3; stvx vr10,r3,r10 -err3; stvx vr11,r3,r11 +err3; stvx v8,r0,r3 +err3; stvx v9,r3,r9 +err3; stvx v10,r3,r10 +err3; stvx v11,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f -err3; lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) -err3; lvx vr0,r4,r9 - VPERM(vr9,vr1,vr0,vr16) +err3; lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) +err3; lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) addi r4,r4,32 -err3; stvx vr8,r0,r3 -err3; stvx vr9,r3,r9 +err3; stvx v8,r0,r3 +err3; stvx v9,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f -err3; lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) +err3; lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) addi r4,r4,16 -err3; stvx vr8,r0,r3 +err3; stvx v8,r0,r3 addi r3,r3,16 /* Up to 15B to go */ diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S index a5b30c71a8d3..18af0b3d3eb2 100644 --- a/arch/powerpc/lib/crtsavres.S +++ b/arch/powerpc/lib/crtsavres.S @@ -236,78 +236,78 @@ _GLOBAL(_rest32gpr_31_x) _GLOBAL(_savevr_20) li r11,-192 - stvx vr20,r11,r0 + stvx v20,r11,r0 _GLOBAL(_savevr_21) li r11,-176 - stvx vr21,r11,r0 + stvx v21,r11,r0 _GLOBAL(_savevr_22) li r11,-160 - stvx vr22,r11,r0 + stvx v22,r11,r0 _GLOBAL(_savevr_23) li r11,-144 - stvx vr23,r11,r0 + stvx v23,r11,r0 _GLOBAL(_savevr_24) li r11,-128 - stvx vr24,r11,r0 + stvx v24,r11,r0 _GLOBAL(_savevr_25) li r11,-112 - stvx vr25,r11,r0 + stvx v25,r11,r0 _GLOBAL(_savevr_26) li r11,-96 - stvx vr26,r11,r0 + stvx v26,r11,r0 _GLOBAL(_savevr_27) li r11,-80 - stvx vr27,r11,r0 + stvx v27,r11,r0 _GLOBAL(_savevr_28) li r11,-64 - stvx vr28,r11,r0 + stvx v28,r11,r0 _GLOBAL(_savevr_29) li r11,-48 - stvx vr29,r11,r0 + stvx v29,r11,r0 _GLOBAL(_savevr_30) li r11,-32 - stvx vr30,r11,r0 + stvx v30,r11,r0 _GLOBAL(_savevr_31) li r11,-16 - stvx vr31,r11,r0 + stvx v31,r11,r0 blr _GLOBAL(_restvr_20) li r11,-192 - lvx vr20,r11,r0 + lvx v20,r11,r0 _GLOBAL(_restvr_21) li r11,-176 - lvx vr21,r11,r0 + lvx v21,r11,r0 _GLOBAL(_restvr_22) li r11,-160 - lvx vr22,r11,r0 + lvx v22,r11,r0 _GLOBAL(_restvr_23) li r11,-144 - lvx vr23,r11,r0 + lvx v23,r11,r0 _GLOBAL(_restvr_24) li r11,-128 - lvx vr24,r11,r0 + lvx v24,r11,r0 _GLOBAL(_restvr_25) li r11,-112 - lvx vr25,r11,r0 + lvx v25,r11,r0 _GLOBAL(_restvr_26) li r11,-96 - lvx vr26,r11,r0 + lvx v26,r11,r0 _GLOBAL(_restvr_27) li r11,-80 - lvx vr27,r11,r0 + lvx v27,r11,r0 _GLOBAL(_restvr_28) li r11,-64 - lvx vr28,r11,r0 + lvx v28,r11,r0 _GLOBAL(_restvr_29) li r11,-48 - lvx vr29,r11,r0 + lvx v29,r11,r0 _GLOBAL(_restvr_30) li r11,-32 - lvx vr30,r11,r0 + lvx v30,r11,r0 _GLOBAL(_restvr_31) li r11,-16 - lvx vr31,r11,r0 + lvx v31,r11,r0 blr #endif /* CONFIG_ALTIVEC */ @@ -443,101 +443,101 @@ _restgpr0_31: .globl _savevr_20 _savevr_20: li r12,-192 - stvx vr20,r12,r0 + stvx v20,r12,r0 .globl _savevr_21 _savevr_21: li r12,-176 - stvx vr21,r12,r0 + stvx v21,r12,r0 .globl _savevr_22 _savevr_22: li r12,-160 - stvx vr22,r12,r0 + stvx v22,r12,r0 .globl _savevr_23 _savevr_23: li r12,-144 - stvx vr23,r12,r0 + stvx v23,r12,r0 .globl _savevr_24 _savevr_24: li r12,-128 - stvx vr24,r12,r0 + stvx v24,r12,r0 .globl _savevr_25 _savevr_25: li r12,-112 - stvx vr25,r12,r0 + stvx v25,r12,r0 .globl _savevr_26 _savevr_26: li r12,-96 - stvx vr26,r12,r0 + stvx v26,r12,r0 .globl _savevr_27 _savevr_27: li r12,-80 - stvx vr27,r12,r0 + stvx v27,r12,r0 .globl _savevr_28 _savevr_28: li r12,-64 - stvx vr28,r12,r0 + stvx v28,r12,r0 .globl _savevr_29 _savevr_29: li r12,-48 - stvx vr29,r12,r0 + stvx v29,r12,r0 .globl _savevr_30 _savevr_30: li r12,-32 - stvx vr30,r12,r0 + stvx v30,r12,r0 .globl _savevr_31 _savevr_31: li r12,-16 - stvx vr31,r12,r0 + stvx v31,r12,r0 blr .globl _restvr_20 _restvr_20: li r12,-192 - lvx vr20,r12,r0 + lvx v20,r12,r0 .globl _restvr_21 _restvr_21: li r12,-176 - lvx vr21,r12,r0 + lvx v21,r12,r0 .globl _restvr_22 _restvr_22: li r12,-160 - lvx vr22,r12,r0 + lvx v22,r12,r0 .globl _restvr_23 _restvr_23: li r12,-144 - lvx vr23,r12,r0 + lvx v23,r12,r0 .globl _restvr_24 _restvr_24: li r12,-128 - lvx vr24,r12,r0 + lvx v24,r12,r0 .globl _restvr_25 _restvr_25: li r12,-112 - lvx vr25,r12,r0 + lvx v25,r12,r0 .globl _restvr_26 _restvr_26: li r12,-96 - lvx vr26,r12,r0 + lvx v26,r12,r0 .globl _restvr_27 _restvr_27: li r12,-80 - lvx vr27,r12,r0 + lvx v27,r12,r0 .globl _restvr_28 _restvr_28: li r12,-64 - lvx vr28,r12,r0 + lvx v28,r12,r0 .globl _restvr_29 _restvr_29: li r12,-48 - lvx vr29,r12,r0 + lvx v29,r12,r0 .globl _restvr_30 _restvr_30: li r12,-32 - lvx vr30,r12,r0 + lvx v30,r12,r0 .globl _restvr_31 _restvr_31: li r12,-16 - lvx vr31,r12,r0 + lvx v31,r12,r0 blr #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index 85aec08ab234..5d0cdbfbe3f2 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -184,16 +184,16 @@ _GLOBAL(do_stfd) extab 2b,3b #ifdef CONFIG_ALTIVEC -/* Get the contents of vrN into vr0; N is in r3. */ +/* Get the contents of vrN into v0; N is in r3. */ _GLOBAL(get_vr) mflr r0 rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* vr0 is already in vr0 */ + blr /* v0 is already in v0 */ nop reg = 1 .rept 31 - vor vr0,reg,reg /* assembler doesn't know vmr? */ + vor v0,reg,reg /* assembler doesn't know vmr? */ blr reg = reg + 1 .endr @@ -203,16 +203,16 @@ reg = reg + 1 mtlr r0 bctr -/* Put the contents of vr0 into vrN; N is in r3. */ +/* Put the contents of v0 into vrN; N is in r3. */ _GLOBAL(put_vr) mflr r0 rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* vr0 is already in vr0 */ + blr /* v0 is already in v0 */ nop reg = 1 .rept 31 - vor reg,vr0,vr0 + vor reg,v0,v0 blr reg = reg + 1 .endr @@ -234,13 +234,13 @@ _GLOBAL(do_lvx) MTMSRD(r7) isync beq cr7,1f - stvx vr0,r1,r8 + stvx v0,r1,r8 1: li r9,-EFAULT -2: lvx vr0,0,r4 +2: lvx v0,0,r4 li r9,0 3: beq cr7,4f bl put_vr - lvx vr0,r1,r8 + lvx v0,r1,r8 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) @@ -262,13 +262,13 @@ _GLOBAL(do_stvx) MTMSRD(r7) isync beq cr7,1f - stvx vr0,r1,r8 + stvx v0,r1,r8 bl get_vr 1: li r9,-EFAULT -2: stvx vr0,0,r4 +2: stvx v0,0,r4 li r9,0 3: beq cr7,4f - lvx vr0,r1,r8 + lvx v0,r1,r8 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) @@ -280,12 +280,12 @@ _GLOBAL(do_stvx) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -/* Get the contents of vsrN into vsr0; N is in r3. */ +/* Get the contents of vsN into vs0; N is in r3. */ _GLOBAL(get_vsr) mflr r0 rlwinm r3,r3,3,0x1f8 bcl 20,31,1f - blr /* vsr0 is already in vsr0 */ + blr /* vs0 is already in vs0 */ nop reg = 1 .rept 63 @@ -299,12 +299,12 @@ reg = reg + 1 mtlr r0 bctr -/* Put the contents of vsr0 into vsrN; N is in r3. */ +/* Put the contents of vs0 into vsN; N is in r3. */ _GLOBAL(put_vsr) mflr r0 rlwinm r3,r3,3,0x1f8 bcl 20,31,1f - blr /* vr0 is already in vr0 */ + blr /* v0 is already in v0 */ nop reg = 1 .rept 63 diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 170a0346f756..f7deebdf3365 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -41,6 +41,7 @@ void __spin_yield(arch_spinlock_t *lock) plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu), yield_count); } +EXPORT_SYMBOL_GPL(__spin_yield); /* * Waiting for a read lock or a write lock on a rwlock... diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 0830587df16e..786234fd4e91 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -321,29 +321,29 @@ _GLOBAL(memcpy_power7) li r11,48 bf cr7*4+3,5f - lvx vr1,r0,r4 + lvx v1,r0,r4 addi r4,r4,16 - stvx vr1,r0,r3 + stvx v1,r0,r3 addi r3,r3,16 5: bf cr7*4+2,6f - lvx vr1,r0,r4 - lvx vr0,r4,r9 + lvx v1,r0,r4 + lvx v0,r4,r9 addi r4,r4,32 - stvx vr1,r0,r3 - stvx vr0,r3,r9 + stvx v1,r0,r3 + stvx v0,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f - lvx vr3,r0,r4 - lvx vr2,r4,r9 - lvx vr1,r4,r10 - lvx vr0,r4,r11 + lvx v3,r0,r4 + lvx v2,r4,r9 + lvx v1,r4,r10 + lvx v0,r4,r11 addi r4,r4,64 - stvx vr3,r0,r3 - stvx vr2,r3,r9 - stvx vr1,r3,r10 - stvx vr0,r3,r11 + stvx v3,r0,r3 + stvx v2,r3,r9 + stvx v1,r3,r10 + stvx v0,r3,r11 addi r3,r3,64 7: sub r5,r5,r6 @@ -366,23 +366,23 @@ _GLOBAL(memcpy_power7) */ .align 5 8: - lvx vr7,r0,r4 - lvx vr6,r4,r9 - lvx vr5,r4,r10 - lvx vr4,r4,r11 - lvx vr3,r4,r12 - lvx vr2,r4,r14 - lvx vr1,r4,r15 - lvx vr0,r4,r16 + lvx v7,r0,r4 + lvx v6,r4,r9 + lvx v5,r4,r10 + lvx v4,r4,r11 + lvx v3,r4,r12 + lvx v2,r4,r14 + lvx v1,r4,r15 + lvx v0,r4,r16 addi r4,r4,128 - stvx vr7,r0,r3 - stvx vr6,r3,r9 - stvx vr5,r3,r10 - stvx vr4,r3,r11 - stvx vr3,r3,r12 - stvx vr2,r3,r14 - stvx vr1,r3,r15 - stvx vr0,r3,r16 + stvx v7,r0,r3 + stvx v6,r3,r9 + stvx v5,r3,r10 + stvx v4,r3,r11 + stvx v3,r3,r12 + stvx v2,r3,r14 + stvx v1,r3,r15 + stvx v0,r3,r16 addi r3,r3,128 bdnz 8b @@ -396,29 +396,29 @@ _GLOBAL(memcpy_power7) mtocrf 0x01,r6 bf cr7*4+1,9f - lvx vr3,r0,r4 - lvx vr2,r4,r9 - lvx vr1,r4,r10 - lvx vr0,r4,r11 + lvx v3,r0,r4 + lvx v2,r4,r9 + lvx v1,r4,r10 + lvx v0,r4,r11 addi r4,r4,64 - stvx vr3,r0,r3 - stvx vr2,r3,r9 - stvx vr1,r3,r10 - stvx vr0,r3,r11 + stvx v3,r0,r3 + stvx v2,r3,r9 + stvx v1,r3,r10 + stvx v0,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f - lvx vr1,r0,r4 - lvx vr0,r4,r9 + lvx v1,r0,r4 + lvx v0,r4,r9 addi r4,r4,32 - stvx vr1,r0,r3 - stvx vr0,r3,r9 + stvx v1,r0,r3 + stvx v0,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f - lvx vr1,r0,r4 + lvx v1,r0,r4 addi r4,r4,16 - stvx vr1,r0,r3 + stvx v1,r0,r3 addi r3,r3,16 /* Up to 15B to go */ @@ -494,42 +494,42 @@ _GLOBAL(memcpy_power7) li r10,32 li r11,48 - LVS(vr16,0,r4) /* Setup permute control vector */ - lvx vr0,0,r4 + LVS(v16,0,r4) /* Setup permute control vector */ + lvx v0,0,r4 addi r4,r4,16 bf cr7*4+3,5f - lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) + lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) addi r4,r4,16 - stvx vr8,r0,r3 + stvx v8,r0,r3 addi r3,r3,16 - vor vr0,vr1,vr1 + vor v0,v1,v1 5: bf cr7*4+2,6f - lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) - lvx vr0,r4,r9 - VPERM(vr9,vr1,vr0,vr16) + lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) + lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) addi r4,r4,32 - stvx vr8,r0,r3 - stvx vr9,r3,r9 + stvx v8,r0,r3 + stvx v9,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f - lvx vr3,r0,r4 - VPERM(vr8,vr0,vr3,vr16) - lvx vr2,r4,r9 - VPERM(vr9,vr3,vr2,vr16) - lvx vr1,r4,r10 - VPERM(vr10,vr2,vr1,vr16) - lvx vr0,r4,r11 - VPERM(vr11,vr1,vr0,vr16) + lvx v3,r0,r4 + VPERM(v8,v0,v3,v16) + lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) + lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) + lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) addi r4,r4,64 - stvx vr8,r0,r3 - stvx vr9,r3,r9 - stvx vr10,r3,r10 - stvx vr11,r3,r11 + stvx v8,r0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 addi r3,r3,64 7: sub r5,r5,r6 @@ -552,31 +552,31 @@ _GLOBAL(memcpy_power7) */ .align 5 8: - lvx vr7,r0,r4 - VPERM(vr8,vr0,vr7,vr16) - lvx vr6,r4,r9 - VPERM(vr9,vr7,vr6,vr16) - lvx vr5,r4,r10 - VPERM(vr10,vr6,vr5,vr16) - lvx vr4,r4,r11 - VPERM(vr11,vr5,vr4,vr16) - lvx vr3,r4,r12 - VPERM(vr12,vr4,vr3,vr16) - lvx vr2,r4,r14 - VPERM(vr13,vr3,vr2,vr16) - lvx vr1,r4,r15 - VPERM(vr14,vr2,vr1,vr16) - lvx vr0,r4,r16 - VPERM(vr15,vr1,vr0,vr16) + lvx v7,r0,r4 + VPERM(v8,v0,v7,v16) + lvx v6,r4,r9 + VPERM(v9,v7,v6,v16) + lvx v5,r4,r10 + VPERM(v10,v6,v5,v16) + lvx v4,r4,r11 + VPERM(v11,v5,v4,v16) + lvx v3,r4,r12 + VPERM(v12,v4,v3,v16) + lvx v2,r4,r14 + VPERM(v13,v3,v2,v16) + lvx v1,r4,r15 + VPERM(v14,v2,v1,v16) + lvx v0,r4,r16 + VPERM(v15,v1,v0,v16) addi r4,r4,128 - stvx vr8,r0,r3 - stvx vr9,r3,r9 - stvx vr10,r3,r10 - stvx vr11,r3,r11 - stvx vr12,r3,r12 - stvx vr13,r3,r14 - stvx vr14,r3,r15 - stvx vr15,r3,r16 + stvx v8,r0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 + stvx v12,r3,r12 + stvx v13,r3,r14 + stvx v14,r3,r15 + stvx v15,r3,r16 addi r3,r3,128 bdnz 8b @@ -590,36 +590,36 @@ _GLOBAL(memcpy_power7) mtocrf 0x01,r6 bf cr7*4+1,9f - lvx vr3,r0,r4 - VPERM(vr8,vr0,vr3,vr16) - lvx vr2,r4,r9 - VPERM(vr9,vr3,vr2,vr16) - lvx vr1,r4,r10 - VPERM(vr10,vr2,vr1,vr16) - lvx vr0,r4,r11 - VPERM(vr11,vr1,vr0,vr16) + lvx v3,r0,r4 + VPERM(v8,v0,v3,v16) + lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) + lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) + lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) addi r4,r4,64 - stvx vr8,r0,r3 - stvx vr9,r3,r9 - stvx vr10,r3,r10 - stvx vr11,r3,r11 + stvx v8,r0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f - lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) - lvx vr0,r4,r9 - VPERM(vr9,vr1,vr0,vr16) + lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) + lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) addi r4,r4,32 - stvx vr8,r0,r3 - stvx vr9,r3,r9 + stvx v8,r0,r3 + stvx v9,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f - lvx vr1,r0,r4 - VPERM(vr8,vr0,vr1,vr16) + lvx v1,r0,r4 + VPERM(v8,v0,v1,v16) addi r4,r4,16 - stvx vr8,r0,r3 + stvx v8,r0,r3 addi r3,r3,16 /* Up to 15B to go */ diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c index f993959647b5..c7f8e9586316 100644 --- a/arch/powerpc/lib/ppc_ksyms.c +++ b/arch/powerpc/lib/ppc_ksyms.c @@ -8,10 +8,6 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcmp); EXPORT_SYMBOL(memchr); -#ifdef CONFIG_PPC32 -EXPORT_SYMBOL(cacheable_memcpy); -EXPORT_SYMBOL(cacheable_memzero); -#endif EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strncpy); diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c index a1060a868e69..69abf844c2c3 100644 --- a/arch/powerpc/lib/rheap.c +++ b/arch/powerpc/lib/rheap.c @@ -284,7 +284,7 @@ EXPORT_SYMBOL_GPL(rh_create); */ void rh_destroy(rh_info_t * info) { - if ((info->flags & RHIF_STATIC_BLOCK) == 0 && info->block != NULL) + if ((info->flags & RHIF_STATIC_BLOCK) == 0) kfree(info->block); if ((info->flags & RHIF_STATIC_INFO) == 0) diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 438dcd3fd0d1..9c8770b5f96f 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_40x) += 40x_mmu.o obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_PPC_FSL_BOOK3E) += fsl_booke_mmu.o obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o +obj-$(CONFIG_PPC_SPLPAR) += vphn.o obj-$(CONFIG_PPC_MM_SLICES) += slice.o obj-y += hugetlbpage.o ifeq ($(CONFIG_HUGETLB_PAGE),y) diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index d85e86aac7fb..169aba446a74 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -228,7 +228,7 @@ __dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t do { SetPageReserved(page); map_page(vaddr, page_to_phys(page), - pgprot_noncached(PAGE_KERNEL)); + pgprot_val(pgprot_noncached(PAGE_KERNEL))); page++; vaddr += PAGE_SIZE; } while (size -= PAGE_SIZE); diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index b46912fee7cd..9c90e66cffb6 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -181,7 +181,7 @@ static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, unsigned long cam_sz; cam_sz = calc_cam_sz(ram, virt, phys); - settlbcam(i, virt, phys, cam_sz, PAGE_KERNEL_X, 0); + settlbcam(i, virt, phys, cam_sz, pgprot_val(PAGE_KERNEL_X), 0); ram -= cam_sz; amount_mapped += cam_sz; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 2c2022d16059..fda236f908eb 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1066,7 +1066,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, #endif /* CONFIG_PPC_64K_PAGES */ /* Get PTE and page size from page tables */ - ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift); + ptep = __find_linux_pte_or_hugepte(pgdir, ea, &hugeshift); if (ptep == NULL || !pte_present(*ptep)) { DBG_LOW(" no PTE !\n"); rc = 1; @@ -1394,6 +1394,7 @@ tm_abort: tm_abort(TM_CAUSE_TLBI); } #endif + return; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 86686514ae13..43dafb9d6a46 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -33,7 +33,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * atomically mark the linux large page PMD busy and dirty */ do { - pmd_t pmd = ACCESS_ONCE(*pmdp); + pmd_t pmd = READ_ONCE(*pmdp); old_pmd = pmd_val(pmd); /* If PMD busy, retry the access */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7e408bfc7948..0ce968b00b7c 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -109,7 +109,7 @@ int pgd_huge(pgd_t pgd) pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { /* Only called for hugetlbfs pages, hence can ignore THP */ - return find_linux_pte_or_hugepte(mm->pgd, addr, NULL); + return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL); } static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, @@ -581,6 +581,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -681,28 +682,35 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, } while (addr = next, addr != end); } +/* + * We are holding mmap_sem, so a parallel huge page collapse cannot run. + * To prevent hugepage split, disable irq. + */ struct page * follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { pte_t *ptep; struct page *page; unsigned shift; - unsigned long mask; + unsigned long mask, flags; /* * Transparent hugepages are handled by generic code. We can skip them * here. */ + local_irq_save(flags); ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift); /* Verify it is a huge page else bail. */ - if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) + if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) { + local_irq_restore(flags); return ERR_PTR(-EINVAL); - + } mask = (1UL << shift) - 1; page = pte_page(*ptep); if (page) page += (address & mask) / PAGE_SIZE; + local_irq_restore(flags); return page; } @@ -949,9 +957,12 @@ void flush_dcache_icache_hugepage(struct page *page) * * So long as we atomically load page table pointers we are safe against teardown, * we can follow the address down to the the page and take a ref on it. + * This function need to be called with interrupts disabled. We use this variant + * when we have MSR[EE] = 0 but the paca->soft_enabled = 1 */ -pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift) +pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, + unsigned *shift) { pgd_t pgd, *pgdp; pud_t pud, *pudp; @@ -964,7 +975,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift *shift = 0; pgdp = pgdir + pgd_index(ea); - pgd = ACCESS_ONCE(*pgdp); + pgd = READ_ONCE(*pgdp); /* * Always operate on the local stack value. This make sure the * value don't get updated by a parallel THP split/collapse, @@ -1003,12 +1014,11 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift * A hugepage collapse is captured by pmd_none, because * it mark the pmd none and do a hpte invalidate. * - * A hugepage split is captured by pmd_trans_splitting - * because we mark the pmd trans splitting and do a - * hpte invalidate - * + * We don't worry about pmd_trans_splitting here, The + * caller if it needs to handle the splitting case + * should check for that. */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return NULL; if (pmd_huge(pmd) || pmd_large(pmd)) { @@ -1030,7 +1040,7 @@ out: *shift = pdshift; return ret_pte; } -EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte); +EXPORT_SYMBOL_GPL(__find_linux_pte_or_hugepte); int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) @@ -1045,7 +1055,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, if (pte_end < end) end = pte_end; - pte = ACCESS_ONCE(*ptep); + pte = READ_ONCE(*ptep); mask = _PAGE_PRESENT | _PAGE_USER; if (write) mask |= _PAGE_RW; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 10471f9bb63f..d747dd7bc90b 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -132,6 +132,7 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); new = kmem_cache_create(name, table_size, align, 0, ctor); + kfree(name); pgtable_cache[shift - 1] = new; pr_debug("Allocated pgtable cache for order %d\n", shift); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index b7285a5870f8..45fda71feb27 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -61,7 +61,6 @@ #define CPU_FTR_NOEXECUTE 0 #endif -int mem_init_done; unsigned long long memory_limit; #ifdef CONFIG_HIGHMEM @@ -377,8 +376,6 @@ void __init mem_init(void) pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", VMALLOC_START, VMALLOC_END); #endif /* CONFIG_PPC32 */ - - mem_init_done = 1; } void free_initmem(void) diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 78c45f392f5b..085b66b10891 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -96,7 +96,7 @@ extern void _tlbia(void); extern void mapin_ram(void); extern int map_page(unsigned long va, phys_addr_t pa, int flags); extern void setbat(int index, unsigned long virt, phys_addr_t phys, - unsigned int size, int flags); + unsigned int size, pgprot_t prot); extern int __map_without_bats; extern int __allow_ioremap_reserved; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 0257a7d659ef..5e80621d9324 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -958,6 +958,13 @@ void __init initmem_init(void) memblock_dump_all(); + /* + * Reduce the possible NUMA nodes to the online NUMA nodes, + * since we do not support node hotplug. This ensures that we + * lower the maximum NUMA node ID to what is actually present. + */ + nodes_and(node_possible_map, node_possible_map, node_online_map); + for_each_online_node(nid) { unsigned long start_pfn, end_pfn; @@ -1177,6 +1184,9 @@ u64 memory_hotplug_max(void) /* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR + +#include "vphn.h" + struct topology_update_data { struct topology_update_data *next; unsigned int cpu; @@ -1248,55 +1258,6 @@ static int update_cpu_associativity_changes_mask(void) } /* - * 6 64-bit registers unpacked into 12 32-bit associativity values. To form - * the complete property we have to add the length in the first cell. - */ -#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32) + 1) - -/* - * Convert the associativity domain numbers returned from the hypervisor - * to the sequence they would appear in the ibm,associativity property. - */ -static int vphn_unpack_associativity(const long *packed, __be32 *unpacked) -{ - int i, nr_assoc_doms = 0; - const __be16 *field = (const __be16 *) packed; - -#define VPHN_FIELD_UNUSED (0xffff) -#define VPHN_FIELD_MSB (0x8000) -#define VPHN_FIELD_MASK (~VPHN_FIELD_MSB) - - for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) { - if (be16_to_cpup(field) == VPHN_FIELD_UNUSED) { - /* All significant fields processed, and remaining - * fields contain the reserved value of all 1's. - * Just store them. - */ - unpacked[i] = *((__be32 *)field); - field += 2; - } else if (be16_to_cpup(field) & VPHN_FIELD_MSB) { - /* Data is in the lower 15 bits of this field */ - unpacked[i] = cpu_to_be32( - be16_to_cpup(field) & VPHN_FIELD_MASK); - field++; - nr_assoc_doms++; - } else { - /* Data is in the lower 15 bits of this field - * concatenated with the next 16 bit field - */ - unpacked[i] = *((__be32 *)field); - field += 2; - nr_assoc_doms++; - } - } - - /* The first cell contains the length of the property */ - unpacked[0] = cpu_to_be32(nr_assoc_doms); - - return nr_assoc_doms; -} - -/* * Retrieve the new associativity information for a virtual processor's * home node. */ @@ -1306,11 +1267,8 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity) long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; u64 flags = 1; int hwcpu = get_hard_smp_processor_id(cpu); - int i; rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); - for (i = 0; i < 6; i++) - retbuf[i] = cpu_to_be64(retbuf[i]); vphn_unpack_associativity(retbuf, associativity); return rc; diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 03b1a3b0fbd5..7692d1bb1bc6 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -54,9 +54,6 @@ extern char etext[], _stext[]; #ifdef HAVE_BATS extern phys_addr_t v_mapped_by_bats(unsigned long va); extern unsigned long p_mapped_by_bats(phys_addr_t pa); -void setbat(int index, unsigned long virt, phys_addr_t phys, - unsigned int size, int flags); - #else /* !HAVE_BATS */ #define v_mapped_by_bats(x) (0UL) #define p_mapped_by_bats(x) (0UL) @@ -110,9 +107,8 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { pte_t *pte; - extern int mem_init_done; - if (mem_init_done) { + if (slab_is_available()) { pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); } else { pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); @@ -192,7 +188,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, /* Make sure we have the base flags */ if ((flags & _PAGE_PRESENT) == 0) - flags |= PAGE_KERNEL; + flags |= pgprot_val(PAGE_KERNEL); /* Non-cacheable page cannot be coherent */ if (flags & _PAGE_NO_CACHE) @@ -219,9 +215,9 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, * Don't allow anybody to remap normal RAM that we're using. * mem_init() sets high_memory so only do the check after that. */ - if (mem_init_done && (p < virt_to_phys(high_memory)) && + if (slab_is_available() && (p < virt_to_phys(high_memory)) && !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) { - printk("__ioremap(): phys addr 0x%llx is RAM lr %pf\n", + printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n", (unsigned long long)p, __builtin_return_address(0)); return NULL; } @@ -247,7 +243,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, if ((v = p_mapped_by_tlbcam(p))) goto out; - if (mem_init_done) { + if (slab_is_available()) { struct vm_struct *area; area = get_vm_area_caller(size, VM_IOREMAP, caller); if (area == 0) @@ -266,7 +262,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags, for (i = 0; i < size && err == 0; i += PAGE_SIZE) err = map_page(v+i, p+i, flags); if (err) { - if (mem_init_done) + if (slab_is_available()) vunmap((void *)v); return NULL; } @@ -327,7 +323,7 @@ void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) p = memstart_addr + s; for (; s < top; s += PAGE_SIZE) { ktext = ((char *) v >= _stext && (char *) v < etext); - f = ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL; + f = ktext ? pgprot_val(PAGE_KERNEL_TEXT) : pgprot_val(PAGE_KERNEL); map_page(v, p, f); #ifdef CONFIG_PPC_STD_MMU_32 if (ktext) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 6957cc1ca0a7..59daa5eeec25 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -231,7 +231,7 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size, if ((size == 0) || (paligned == 0)) return NULL; - if (mem_init_done) { + if (slab_is_available()) { struct vm_struct *area; area = __get_vm_area_caller(size, VM_IOREMAP, @@ -315,7 +315,7 @@ void __iounmap(volatile void __iomem *token) { void *addr; - if (!mem_init_done) + if (!slab_is_available()) return; addr = (void *) ((unsigned long __force) @@ -723,7 +723,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, assert_spin_locked(&mm->page_table_lock); WARN_ON(!pmd_trans_huge(pmd)); #endif - trace_hugepage_set_pmd(addr, pmd); + trace_hugepage_set_pmd(addr, pmd_val(pmd)); return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 5029dc19b517..6b2f3e457171 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -113,11 +113,12 @@ unsigned long __init mmu_mapin_ram(unsigned long top) * of 2 between 128k and 256M. */ void __init setbat(int index, unsigned long virt, phys_addr_t phys, - unsigned int size, int flags) + unsigned int size, pgprot_t prot) { unsigned int bl; int wimgxpp; struct ppc_bat *bat = BATS[index]; + unsigned long flags = pgprot_val(prot); if ((flags & _PAGE_NO_CACHE) || (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0)) @@ -224,7 +225,7 @@ void __init MMU_init_hw(void) */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); Hash = __va(memblock_alloc(Hash_size, Hash_size)); - cacheable_memzero(Hash, Hash_size); + memset(Hash, 0, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size); diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index d2a94b85dbc2..c522969f012d 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -216,7 +216,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, continue; pte = pte_val(*ptep); if (hugepage_shift) - trace_hugepage_invalidate(start, pte_val(pte)); + trace_hugepage_invalidate(start, pte); if (!(pte & _PAGE_HASHPTE)) continue; if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte))) diff --git a/arch/powerpc/mm/vphn.c b/arch/powerpc/mm/vphn.c new file mode 100644 index 000000000000..5f8ef50e5c66 --- /dev/null +++ b/arch/powerpc/mm/vphn.c @@ -0,0 +1,70 @@ +#include <asm/byteorder.h> +#include "vphn.h" + +/* + * The associativity domain numbers are returned from the hypervisor as a + * stream of mixed 16-bit and 32-bit fields. The stream is terminated by the + * special value of "all ones" (aka. 0xffff) and its size may not exceed 48 + * bytes. + * + * --- 16-bit fields --> + * _________________________ + * | 0 | 1 | 2 | 3 | be_packed[0] + * ------+-----+-----+------ + * _________________________ + * | 4 | 5 | 6 | 7 | be_packed[1] + * ------------------------- + * ... + * _________________________ + * | 20 | 21 | 22 | 23 | be_packed[5] + * ------------------------- + * + * Convert to the sequence they would appear in the ibm,associativity property. + */ +int vphn_unpack_associativity(const long *packed, __be32 *unpacked) +{ + __be64 be_packed[VPHN_REGISTER_COUNT]; + int i, nr_assoc_doms = 0; + const __be16 *field = (const __be16 *) be_packed; + u16 last = 0; + bool is_32bit = false; + +#define VPHN_FIELD_UNUSED (0xffff) +#define VPHN_FIELD_MSB (0x8000) +#define VPHN_FIELD_MASK (~VPHN_FIELD_MSB) + + /* Let's fix the values returned by plpar_hcall9() */ + for (i = 0; i < VPHN_REGISTER_COUNT; i++) + be_packed[i] = cpu_to_be64(packed[i]); + + for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) { + u16 new = be16_to_cpup(field++); + + if (is_32bit) { + /* Let's concatenate the 16 bits of this field to the + * 15 lower bits of the previous field + */ + unpacked[++nr_assoc_doms] = + cpu_to_be32(last << 16 | new); + is_32bit = false; + } else if (new == VPHN_FIELD_UNUSED) + /* This is the list terminator */ + break; + else if (new & VPHN_FIELD_MSB) { + /* Data is in the lower 15 bits of this field */ + unpacked[++nr_assoc_doms] = + cpu_to_be32(new & VPHN_FIELD_MASK); + } else { + /* Data is in the lower 15 bits of this field + * concatenated with the next 16 bit field + */ + last = new; + is_32bit = true; + } + } + + /* The first cell contains the length of the property */ + unpacked[0] = cpu_to_be32(nr_assoc_doms); + + return nr_assoc_doms; +} diff --git a/arch/powerpc/mm/vphn.h b/arch/powerpc/mm/vphn.h new file mode 100644 index 000000000000..fe8b7805b78f --- /dev/null +++ b/arch/powerpc/mm/vphn.h @@ -0,0 +1,16 @@ +#ifndef _ARCH_POWERPC_MM_VPHN_H_ +#define _ARCH_POWERPC_MM_VPHN_H_ + +/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. + */ +#define VPHN_REGISTER_COUNT 6 + +/* + * 6 64-bit registers unpacked into up to 24 be32 associativity values. To + * form the complete property we have to add the length in the first cell. + */ +#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) + +extern int vphn_unpack_associativity(const long *packed, __be32 *unpacked); + +#endif diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index 1c27831df1ac..ed7b0977072a 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -22,6 +22,7 @@ #include <linux/kref.h> #include <linux/mm.h> #include <linux/fs.h> +#include <linux/file.h> #include <linux/module.h> #include <linux/notifier.h> #include <linux/numa.h> @@ -322,18 +323,20 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, unsigned long app_cookie = 0; unsigned int my_offset = 0; struct vm_area_struct *vma; + struct file *exe_file; struct mm_struct *mm = spu->mm; if (!mm) goto out; - down_read(&mm->mmap_sem); - - if (mm->exe_file) { - app_cookie = fast_get_dcookie(&mm->exe_file->f_path); - pr_debug("got dcookie for %pD\n", mm->exe_file); + exe_file = get_mm_exe_file(mm); + if (exe_file) { + app_cookie = fast_get_dcookie(&exe_file->f_path); + pr_debug("got dcookie for %pD\n", exe_file); + fput(exe_file); } + down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->vm_start > spu_ref || vma->vm_end <= spu_ref) continue; diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 2396dda282cd..ff09cde20cd2 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -111,41 +111,45 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) * interrupt context, so if the access faults, we read the page tables * to find which page (if any) is mapped and access it directly. */ -static int read_user_stack_slow(void __user *ptr, void *ret, int nb) +static int read_user_stack_slow(void __user *ptr, void *buf, int nb) { + int ret = -EFAULT; pgd_t *pgdir; pte_t *ptep, pte; unsigned shift; unsigned long addr = (unsigned long) ptr; unsigned long offset; - unsigned long pfn; + unsigned long pfn, flags; void *kaddr; pgdir = current->mm->pgd; if (!pgdir) return -EFAULT; + local_irq_save(flags); ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift); + if (!ptep) + goto err_out; if (!shift) shift = PAGE_SHIFT; /* align address to page boundary */ offset = addr & ((1UL << shift) - 1); - addr -= offset; - if (ptep == NULL) - return -EFAULT; - pte = *ptep; + pte = READ_ONCE(*ptep); if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER)) - return -EFAULT; + goto err_out; pfn = pte_pfn(pte); if (!page_is_ram(pfn)) - return -EFAULT; + goto err_out; /* no highmem to worry about here */ kaddr = pfn_to_kaddr(pfn); - memcpy(ret, kaddr + offset, nb); - return 0; + memcpy(buf, kaddr + offset, nb); + ret = 0; +err_out: + local_irq_restore(flags); + return ret; } static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) @@ -243,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - for (;;) { + while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned long __user *) sp; if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) return; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 7fd60dcb2cb0..12b638425bb9 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1837,8 +1837,10 @@ static int power_pmu_event_init(struct perf_event *event) cpuhw->bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); - if(cpuhw->bhrb_filter == -1) + if (cpuhw->bhrb_filter == -1) { + put_cpu_var(cpu_hw_events); return -EOPNOTSUPP; + } } put_cpu_var(cpu_hw_events); diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index abeb9ec0d117..ec2eb20631d1 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -142,6 +142,15 @@ static struct attribute_group event_long_desc_group = { static struct kmem_cache *hv_page_cache; +/* + * request_buffer and result_buffer are not required to be 4k aligned, + * but are not allowed to cross any 4k boundary. Aligning them to 4k is + * the simplest way to ensure that. + */ +#define H24x7_DATA_BUFFER_SIZE 4096 +DEFINE_PER_CPU(char, hv_24x7_reqb[H24x7_DATA_BUFFER_SIZE]) __aligned(4096); +DEFINE_PER_CPU(char, hv_24x7_resb[H24x7_DATA_BUFFER_SIZE]) __aligned(4096); + static char *event_name(struct hv_24x7_event_data *ev, int *len) { *len = be16_to_cpu(ev->event_name_len) - 2; @@ -152,6 +161,7 @@ static char *event_desc(struct hv_24x7_event_data *ev, int *len) { unsigned nl = be16_to_cpu(ev->event_name_len); __be16 *desc_len = (__be16 *)(ev->remainder + nl - 2); + *len = be16_to_cpu(*desc_len) - 2; return (char *)ev->remainder + nl; } @@ -162,6 +172,7 @@ static char *event_long_desc(struct hv_24x7_event_data *ev, int *len) __be16 *desc_len_ = (__be16 *)(ev->remainder + nl - 2); unsigned desc_len = be16_to_cpu(*desc_len_); __be16 *long_desc_len = (__be16 *)(ev->remainder + nl + desc_len - 2); + *len = be16_to_cpu(*long_desc_len) - 2; return (char *)ev->remainder + nl + desc_len; } @@ -239,14 +250,12 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, unsigned long index) { pr_devel("h_get_24x7_catalog_page(0x%lx, %lu, %lu)", - phys_4096, - version, - index); + phys_4096, version, index); + WARN_ON(!IS_ALIGNED(phys_4096, 4096)); + return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE, - phys_4096, - version, - index); + phys_4096, version, index); } static unsigned long h_get_24x7_catalog_page(char page[], @@ -300,6 +309,7 @@ static ssize_t device_show_string(struct device *dev, struct dev_ext_attribute *d; d = container_of(attr, struct dev_ext_attribute, attr); + return sprintf(buf, "%s\n", (char *)d->var); } @@ -314,6 +324,7 @@ static struct attribute *device_str_attr_create_(char *name, char *str) attr->attr.attr.name = name; attr->attr.attr.mode = 0444; attr->attr.show = device_show_string; + return &attr->attr.attr; } @@ -387,7 +398,6 @@ static struct attribute *event_to_attr(unsigned ix, a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s__%d", (int)event_name_len, ev_name, ev_suffix, nonce); - if (!a_ev_name) goto out_val; @@ -637,7 +647,7 @@ static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event, #define MAX_4K (SIZE_MAX / 4096) -static void create_events_from_catalog(struct attribute ***events_, +static int create_events_from_catalog(struct attribute ***events_, struct attribute ***event_descs_, struct attribute ***event_long_descs_) { @@ -655,19 +665,25 @@ static void create_events_from_catalog(struct attribute ***events_, void *event_data, *end; struct hv_24x7_event_data *event; struct rb_root ev_uniq = RB_ROOT; + int ret = 0; - if (!page) + if (!page) { + ret = -ENOMEM; goto e_out; + } hret = h_get_24x7_catalog_page(page, 0, 0); - if (hret) + if (hret) { + ret = -EIO; goto e_free; + } catalog_version_num = be64_to_cpu(page_0->version); catalog_page_len = be32_to_cpu(page_0->length); if (MAX_4K < catalog_page_len) { pr_err("invalid page count: %zu\n", catalog_page_len); + ret = -EIO; goto e_free; } @@ -686,6 +702,7 @@ static void create_events_from_catalog(struct attribute ***events_, || (MAX_4K - event_data_offs < event_data_len)) { pr_err("invalid event data offs %zu and/or len %zu\n", event_data_offs, event_data_len); + ret = -EIO; goto e_free; } @@ -694,12 +711,14 @@ static void create_events_from_catalog(struct attribute ***events_, event_data_offs, event_data_offs + event_data_len, catalog_page_len); + ret = -EIO; goto e_free; } if (SIZE_MAX / MAX_EVENTS_PER_EVENT_DATA - 1 < event_entry_count) { pr_err("event_entry_count %zu is invalid\n", event_entry_count); + ret = -EIO; goto e_free; } @@ -712,6 +731,7 @@ static void create_events_from_catalog(struct attribute ***events_, event_data = vmalloc(event_data_bytes); if (!event_data) { pr_err("could not allocate event data\n"); + ret = -ENOMEM; goto e_free; } @@ -731,6 +751,7 @@ static void create_events_from_catalog(struct attribute ***events_, if (hret) { pr_err("failed to get event data in page %zu\n", i + event_data_offs); + ret = -EIO; goto e_event_data; } } @@ -778,18 +799,24 @@ static void create_events_from_catalog(struct attribute ***events_, event_idx_last, event_entry_count, junk_events); events = kmalloc_array(attr_max + 1, sizeof(*events), GFP_KERNEL); - if (!events) + if (!events) { + ret = -ENOMEM; goto e_event_data; + } event_descs = kmalloc_array(event_idx + 1, sizeof(*event_descs), GFP_KERNEL); - if (!event_descs) + if (!event_descs) { + ret = -ENOMEM; goto e_event_attrs; + } event_long_descs = kmalloc_array(event_idx + 1, sizeof(*event_long_descs), GFP_KERNEL); - if (!event_long_descs) + if (!event_long_descs) { + ret = -ENOMEM; goto e_event_descs; + } /* Iterate over the catalog filling in the attribute vector */ for (junk_events = 0, event_attr_ct = 0, desc_ct = 0, long_desc_ct = 0, @@ -843,7 +870,7 @@ static void create_events_from_catalog(struct attribute ***events_, *events_ = events; *event_descs_ = event_descs; *event_long_descs_ = event_long_descs; - return; + return 0; e_event_descs: kfree(event_descs); @@ -857,6 +884,7 @@ e_out: *events_ = NULL; *event_descs_ = NULL; *event_long_descs_ = NULL; + return ret; } static ssize_t catalog_read(struct file *filp, struct kobject *kobj, @@ -872,6 +900,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, uint64_t catalog_version_num = 0; void *page = kmem_cache_alloc(hv_page_cache, GFP_USER); struct hv_24x7_catalog_page_0 *page_0 = page; + if (!page) return -ENOMEM; @@ -976,31 +1005,104 @@ static const struct attribute_group *attr_groups[] = { NULL, }; -DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096); -DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096); +static void log_24x7_hcall(struct hv_24x7_request_buffer *request_buffer, + struct hv_24x7_data_result_buffer *result_buffer, + unsigned long ret) +{ + struct hv_24x7_request *req; + + req = &request_buffer->requests[0]; + pr_notice_ratelimited("hcall failed: [%d %#x %#x %d] => " + "ret 0x%lx (%ld) detail=0x%x failing ix=%x\n", + req->performance_domain, req->data_offset, + req->starting_ix, req->starting_lpar_ix, ret, ret, + result_buffer->detailed_rc, + result_buffer->failing_request_ix); +} + +/* + * Start the process for a new H_GET_24x7_DATA hcall. + */ +static void init_24x7_request(struct hv_24x7_request_buffer *request_buffer, + struct hv_24x7_data_result_buffer *result_buffer) +{ + + memset(request_buffer, 0, 4096); + memset(result_buffer, 0, 4096); + + request_buffer->interface_version = HV_24X7_IF_VERSION_CURRENT; + /* memset above set request_buffer->num_requests to 0 */ +} -static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, - u16 lpar, u64 *res, - bool success_expected) +/* + * Commit (i.e perform) the H_GET_24x7_DATA hcall using the data collected + * by 'init_24x7_request()' and 'add_event_to_24x7_request()'. + */ +static int make_24x7_request(struct hv_24x7_request_buffer *request_buffer, + struct hv_24x7_data_result_buffer *result_buffer) { unsigned long ret; /* - * request_buffer and result_buffer are not required to be 4k aligned, - * but are not allowed to cross any 4k boundary. Aligning them to 4k is - * the simplest way to ensure that. + * NOTE: Due to variable number of array elements in request and + * result buffer(s), sizeof() is not reliable. Use the actual + * allocated buffer size, H24x7_DATA_BUFFER_SIZE. */ - struct reqb { - struct hv_24x7_request_buffer buf; - struct hv_24x7_request req; - } __packed *request_buffer; - - struct { - struct hv_24x7_data_result_buffer buf; - struct hv_24x7_result res; - struct hv_24x7_result_element elem; - __be64 result; - } __packed *result_buffer; + ret = plpar_hcall_norets(H_GET_24X7_DATA, + virt_to_phys(request_buffer), H24x7_DATA_BUFFER_SIZE, + virt_to_phys(result_buffer), H24x7_DATA_BUFFER_SIZE); + + if (ret) + log_24x7_hcall(request_buffer, result_buffer, ret); + + return ret; +} + +/* + * Add the given @event to the next slot in the 24x7 request_buffer. + * + * Note that H_GET_24X7_DATA hcall allows reading several counters' + * values in a single HCALL. We expect the caller to add events to the + * request buffer one by one, make the HCALL and process the results. + */ +static int add_event_to_24x7_request(struct perf_event *event, + struct hv_24x7_request_buffer *request_buffer) +{ + u16 idx; + int i; + struct hv_24x7_request *req; + + if (request_buffer->num_requests > 254) { + pr_devel("Too many requests for 24x7 HCALL %d\n", + request_buffer->num_requests); + return -EINVAL; + } + + if (is_physical_domain(event_get_domain(event))) + idx = event_get_core(event); + else + idx = event_get_vcpu(event); + + i = request_buffer->num_requests++; + req = &request_buffer->requests[i]; + + req->performance_domain = event_get_domain(event); + req->data_size = cpu_to_be16(8); + req->data_offset = cpu_to_be32(event_get_offset(event)); + req->starting_lpar_ix = cpu_to_be16(event_get_lpar(event)), + req->max_num_lpars = cpu_to_be16(1); + req->starting_ix = cpu_to_be16(idx); + req->max_ix = cpu_to_be16(1); + + return 0; +} + +static unsigned long single_24x7_request(struct perf_event *event, u64 *count) +{ + unsigned long ret; + struct hv_24x7_request_buffer *request_buffer; + struct hv_24x7_data_result_buffer *result_buffer; + struct hv_24x7_result *resb; BUILD_BUG_ON(sizeof(*request_buffer) > 4096); BUILD_BUG_ON(sizeof(*result_buffer) > 4096); @@ -1008,63 +1110,28 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, request_buffer = (void *)get_cpu_var(hv_24x7_reqb); result_buffer = (void *)get_cpu_var(hv_24x7_resb); - memset(request_buffer, 0, 4096); - memset(result_buffer, 0, 4096); - - *request_buffer = (struct reqb) { - .buf = { - .interface_version = HV_24X7_IF_VERSION_CURRENT, - .num_requests = 1, - }, - .req = { - .performance_domain = domain, - .data_size = cpu_to_be16(8), - .data_offset = cpu_to_be32(offset), - .starting_lpar_ix = cpu_to_be16(lpar), - .max_num_lpars = cpu_to_be16(1), - .starting_ix = cpu_to_be16(ix), - .max_ix = cpu_to_be16(1), - } - }; + init_24x7_request(request_buffer, result_buffer); - ret = plpar_hcall_norets(H_GET_24X7_DATA, - virt_to_phys(request_buffer), sizeof(*request_buffer), - virt_to_phys(result_buffer), sizeof(*result_buffer)); + ret = add_event_to_24x7_request(event, request_buffer); + if (ret) + goto out; + ret = make_24x7_request(request_buffer, result_buffer); if (ret) { - if (success_expected) - pr_err_ratelimited("hcall failed: %d %#x %#x %d => " - "0x%lx (%ld) detail=0x%x failing ix=%x\n", - domain, offset, ix, lpar, ret, ret, - result_buffer->buf.detailed_rc, - result_buffer->buf.failing_request_ix); + log_24x7_hcall(request_buffer, result_buffer, ret); goto out; } - *res = be64_to_cpu(result_buffer->result); + /* process result from hcall */ + resb = &result_buffer->results[0]; + *count = be64_to_cpu(resb->elements[0].element_data[0]); out: + put_cpu_var(hv_24x7_reqb); + put_cpu_var(hv_24x7_resb); return ret; } -static unsigned long event_24x7_request(struct perf_event *event, u64 *res, - bool success_expected) -{ - u16 idx; - unsigned domain = event_get_domain(event); - - if (is_physical_domain(domain)) - idx = event_get_core(event); - else - idx = event_get_vcpu(event); - - return single_24x7_request(event_get_domain(event), - event_get_offset(event), - idx, - event_get_lpar(event), - res, - success_expected); -} static int h_24x7_event_init(struct perf_event *event) { @@ -1133,7 +1200,7 @@ static int h_24x7_event_init(struct perf_event *event) } /* see if the event complains */ - if (event_24x7_request(event, &ct, false)) { + if (single_24x7_request(event, &ct)) { pr_devel("test hcall failed\n"); return -EIO; } @@ -1145,7 +1212,7 @@ static u64 h_24x7_get_value(struct perf_event *event) { unsigned long ret; u64 ct; - ret = event_24x7_request(event, &ct, true); + ret = single_24x7_request(event, &ct); if (ret) /* We checked this in event init, shouldn't fail here... */ return 0; @@ -1153,15 +1220,22 @@ static u64 h_24x7_get_value(struct perf_event *event) return ct; } -static void h_24x7_event_update(struct perf_event *event) +static void update_event_count(struct perf_event *event, u64 now) { s64 prev; - u64 now; - now = h_24x7_get_value(event); + prev = local64_xchg(&event->hw.prev_count, now); local64_add(now - prev, &event->count); } +static void h_24x7_event_read(struct perf_event *event) +{ + u64 now; + + now = h_24x7_get_value(event); + update_event_count(event, now); +} + static void h_24x7_event_start(struct perf_event *event, int flags) { if (flags & PERF_EF_RELOAD) @@ -1170,7 +1244,7 @@ static void h_24x7_event_start(struct perf_event *event, int flags) static void h_24x7_event_stop(struct perf_event *event, int flags) { - h_24x7_event_update(event); + h_24x7_event_read(event); } static int h_24x7_event_add(struct perf_event *event, int flags) @@ -1191,7 +1265,7 @@ static struct pmu h_24x7_pmu = { .del = h_24x7_event_stop, .start = h_24x7_event_start, .stop = h_24x7_event_stop, - .read = h_24x7_event_update, + .read = h_24x7_event_read, }; static int hv_24x7_init(void) @@ -1219,10 +1293,13 @@ static int hv_24x7_init(void) /* sampling not supported */ h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; - create_events_from_catalog(&event_group.attrs, + r = create_events_from_catalog(&event_group.attrs, &event_desc_group.attrs, &event_long_desc_group.attrs); + if (r) + return r; + r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1); if (r) return r; diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h index 69cd4e690f58..0f9fa21a29f2 100644 --- a/arch/powerpc/perf/hv-24x7.h +++ b/arch/powerpc/perf/hv-24x7.h @@ -50,7 +50,7 @@ struct hv_24x7_request_buffer { __u8 interface_version; __u8 num_requests; __u8 reserved[0xE]; - struct hv_24x7_request requests[]; + struct hv_24x7_request requests[1]; } __packed; struct hv_24x7_result_element { @@ -66,7 +66,7 @@ struct hv_24x7_result_element { __be32 lpar_cfg_instance_id; /* size = @result_element_data_size of cointaining result. */ - __u8 element_data[]; + __u64 element_data[1]; } __packed; struct hv_24x7_result { @@ -87,7 +87,7 @@ struct hv_24x7_result { /* WARNING: only valid for first result element due to variable sizes * of result elements */ /* struct hv_24x7_result_element[@num_elements_returned] */ - struct hv_24x7_result_element elements[]; + struct hv_24x7_result_element elements[1]; } __packed; struct hv_24x7_data_result_buffer { @@ -103,7 +103,7 @@ struct hv_24x7_data_result_buffer { __u8 reserved2[0x8]; /* WARNING: only valid for the first result due to variable sizes of * results */ - struct hv_24x7_result results[]; /* [@num_results] */ + struct hv_24x7_result results[1]; /* [@num_results] */ } __packed; #endif diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 4a9ad871a168..7bfb9b184dd4 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -40,6 +40,7 @@ static const struct of_device_id mpc85xx_common_ids[] __initconst = { { .compatible = "fsl,qoriq-pcie-v2.4", }, { .compatible = "fsl,qoriq-pcie-v2.3", }, { .compatible = "fsl,qoriq-pcie-v2.2", }, + { .compatible = "fsl,fman", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 1f309ccb096e..9824d2cf79bd 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -88,6 +88,15 @@ static const struct of_device_id of_device_ids[] = { .compatible = "simple-bus" }, { + .compatible = "mdio-mux-gpio" + }, + { + .compatible = "fsl,fpga-ngpixis" + }, + { + .compatible = "fsl,fpga-qixis" + }, + { .compatible = "fsl,srio", }, { @@ -108,6 +117,9 @@ static const struct of_device_id of_device_ids[] = { { .compatible = "fsl,qe", }, + { + .compatible = "fsl,fman", + }, /* The following two are for the Freescale hypervisor */ { .name = "hypervisor", diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index d7c1e69f3070..8631ac5f0e57 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -360,10 +360,10 @@ static void mpc85xx_smp_kexec_down(void *arg) static void map_and_flush(unsigned long paddr) { struct page *page = pfn_to_page(paddr >> PAGE_SHIFT); - unsigned long kaddr = (unsigned long)kmap(page); + unsigned long kaddr = (unsigned long)kmap_atomic(page); flush_dcache_range(kaddr, kaddr + PAGE_SIZE); - kunmap(page); + kunmap_atomic((void *)kaddr); } /** diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 391b3f6b54a3..b7f9c408bf24 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -72,11 +72,6 @@ config PPC_SMP_MUXED_IPI cpu. This will enable the generic code to multiplex the 4 messages on to one ipi. -config PPC_UDBG_BEAT - bool "BEAT based debug console" - depends on PPC_CELLEB - default n - config IPIC bool default n diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 76483e3acd60..7264e91190be 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -2,6 +2,7 @@ config PPC64 bool "64-bit kernel" default n select HAVE_VIRT_CPU_ACCOUNTING + select ZLIB_DEFLATE help This option selects whether a 32-bit or a 64-bit kernel will be built. @@ -15,7 +16,7 @@ choice The most common ones are the desktop and server CPUs (601, 603, 604, 740, 750, 74xx) CPUs from Freescale and IBM, with their embedded 512x/52xx/82xx/83xx/86xx counterparts. - The other embeeded parts, namely 4xx, 8xx, e200 (55xx) and e500 + The other embedded parts, namely 4xx, 8xx, e200 (55xx) and e500 (85xx) each form a family of their own that is not compatible with the others. diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 870b6dbd4d18..2f23133ab3d1 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -33,17 +33,6 @@ config PPC_IBM_CELL_BLADE select PPC_UDBG_16550 select UDBG_RTAS_CONSOLE -config PPC_CELLEB - bool "Toshiba's Cell Reference Set 'Celleb' Architecture" - depends on PPC64 && PPC_BOOK3S - select PPC_CELL_NATIVE - select PPC_OF_PLATFORM_PCI - select PCI - select HAS_TXX9_SERIAL - select PPC_UDBG_BEAT - select USB_OHCI_BIG_ENDIAN_MMIO - select USB_EHCI_BIG_ENDIAN_MMIO - config PPC_CELL_QPACE bool "IBM Cell - QPACE" depends on PPC64 && PPC_BOOK3S diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 2d16884f67b9..34699bddfddd 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -29,18 +29,3 @@ obj-$(CONFIG_AXON_MSI) += axon_msi.o # qpace setup obj-$(CONFIG_PPC_CELL_QPACE) += qpace_setup.o - -# celleb stuff -ifeq ($(CONFIG_PPC_CELLEB),y) -obj-y += celleb_setup.o \ - celleb_pci.o celleb_scc_epci.o \ - celleb_scc_pciex.o \ - celleb_scc_uhc.o \ - spider-pci.o beat.o beat_htab.o \ - beat_hvCall.o beat_interrupt.o \ - beat_iommu.o - -obj-$(CONFIG_PPC_UDBG_BEAT) += beat_udbg.o -obj-$(CONFIG_SERIAL_TXX9) += celleb_scc_sio.o -obj-$(CONFIG_SPU_BASE) += beat_spu_priv1.o -endif diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c deleted file mode 100644 index affcf566d460..000000000000 --- a/arch/powerpc/platforms/cell/beat.c +++ /dev/null @@ -1,264 +0,0 @@ -/* - * Simple routines for Celleb/Beat - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/export.h> -#include <linux/init.h> -#include <linux/err.h> -#include <linux/rtc.h> -#include <linux/interrupt.h> -#include <linux/irqreturn.h> -#include <linux/reboot.h> - -#include <asm/hvconsole.h> -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/firmware.h> - -#include "beat_wrapper.h" -#include "beat.h" -#include "beat_interrupt.h" - -static int beat_pm_poweroff_flag; - -void beat_restart(char *cmd) -{ - beat_shutdown_logical_partition(!beat_pm_poweroff_flag); -} - -void beat_power_off(void) -{ - beat_shutdown_logical_partition(0); -} - -u64 beat_halt_code = 0x1000000000000000UL; -EXPORT_SYMBOL(beat_halt_code); - -void beat_halt(void) -{ - beat_shutdown_logical_partition(beat_halt_code); -} - -int beat_set_rtc_time(struct rtc_time *rtc_time) -{ - u64 tim; - tim = mktime(rtc_time->tm_year+1900, - rtc_time->tm_mon+1, rtc_time->tm_mday, - rtc_time->tm_hour, rtc_time->tm_min, rtc_time->tm_sec); - if (beat_rtc_write(tim)) - return -1; - return 0; -} - -void beat_get_rtc_time(struct rtc_time *rtc_time) -{ - u64 tim; - - if (beat_rtc_read(&tim)) - tim = 0; - to_tm(tim, rtc_time); - rtc_time->tm_year -= 1900; - rtc_time->tm_mon -= 1; -} - -#define BEAT_NVRAM_SIZE 4096 - -ssize_t beat_nvram_read(char *buf, size_t count, loff_t *index) -{ - unsigned int i; - unsigned long len; - char *p = buf; - - if (*index >= BEAT_NVRAM_SIZE) - return -ENODEV; - i = *index; - if (i + count > BEAT_NVRAM_SIZE) - count = BEAT_NVRAM_SIZE - i; - - for (; count != 0; count -= len) { - len = count; - if (len > BEAT_NVRW_CNT) - len = BEAT_NVRW_CNT; - if (beat_eeprom_read(i, len, p)) - return -EIO; - - p += len; - i += len; - } - *index = i; - return p - buf; -} - -ssize_t beat_nvram_write(char *buf, size_t count, loff_t *index) -{ - unsigned int i; - unsigned long len; - char *p = buf; - - if (*index >= BEAT_NVRAM_SIZE) - return -ENODEV; - i = *index; - if (i + count > BEAT_NVRAM_SIZE) - count = BEAT_NVRAM_SIZE - i; - - for (; count != 0; count -= len) { - len = count; - if (len > BEAT_NVRW_CNT) - len = BEAT_NVRW_CNT; - if (beat_eeprom_write(i, len, p)) - return -EIO; - - p += len; - i += len; - } - *index = i; - return p - buf; -} - -ssize_t beat_nvram_get_size(void) -{ - return BEAT_NVRAM_SIZE; -} - -int beat_set_xdabr(unsigned long dabr, unsigned long dabrx) -{ - if (beat_set_dabr(dabr, dabrx)) - return -1; - return 0; -} - -int64_t beat_get_term_char(u64 vterm, u64 *len, u64 *t1, u64 *t2) -{ - u64 db[2]; - s64 ret; - - ret = beat_get_characters_from_console(vterm, len, (u8 *)db); - if (ret == 0) { - *t1 = db[0]; - *t2 = db[1]; - } - return ret; -} -EXPORT_SYMBOL(beat_get_term_char); - -int64_t beat_put_term_char(u64 vterm, u64 len, u64 t1, u64 t2) -{ - u64 db[2]; - - db[0] = t1; - db[1] = t2; - return beat_put_characters_to_console(vterm, len, (u8 *)db); -} -EXPORT_SYMBOL(beat_put_term_char); - -void beat_power_save(void) -{ - beat_pause(0); -} - -#ifdef CONFIG_KEXEC -void beat_kexec_cpu_down(int crash, int secondary) -{ - beatic_deinit_IRQ(); -} -#endif - -static irqreturn_t beat_power_event(int virq, void *arg) -{ - printk(KERN_DEBUG "Beat: power button pressed\n"); - beat_pm_poweroff_flag = 1; - ctrl_alt_del(); - return IRQ_HANDLED; -} - -static irqreturn_t beat_reset_event(int virq, void *arg) -{ - printk(KERN_DEBUG "Beat: reset button pressed\n"); - beat_pm_poweroff_flag = 0; - ctrl_alt_del(); - return IRQ_HANDLED; -} - -static struct beat_event_list { - const char *typecode; - irq_handler_t handler; - unsigned int virq; -} beat_event_list[] = { - { "power", beat_power_event, 0 }, - { "reset", beat_reset_event, 0 }, -}; - -static int __init beat_register_event(void) -{ - u64 path[4], data[2]; - int rc, i; - unsigned int virq; - - for (i = 0; i < ARRAY_SIZE(beat_event_list); i++) { - struct beat_event_list *ev = &beat_event_list[i]; - - if (beat_construct_event_receive_port(data) != 0) { - printk(KERN_ERR "Beat: " - "cannot construct event receive port for %s\n", - ev->typecode); - return -EINVAL; - } - - virq = irq_create_mapping(NULL, data[0]); - if (virq == NO_IRQ) { - printk(KERN_ERR "Beat: failed to get virtual IRQ" - " for event receive port for %s\n", - ev->typecode); - beat_destruct_event_receive_port(data[0]); - return -EIO; - } - ev->virq = virq; - - rc = request_irq(virq, ev->handler, 0, - ev->typecode, NULL); - if (rc != 0) { - printk(KERN_ERR "Beat: failed to request virtual IRQ" - " for event receive port for %s\n", - ev->typecode); - beat_destruct_event_receive_port(data[0]); - return rc; - } - - path[0] = 0x1000000065780000ul; /* 1,ex */ - path[1] = 0x627574746f6e0000ul; /* button */ - path[2] = 0; - strncpy((char *)&path[2], ev->typecode, 8); - path[3] = 0; - data[1] = 0; - - beat_create_repository_node(path, data); - } - return 0; -} - -static int __init beat_event_init(void) -{ - if (!firmware_has_feature(FW_FEATURE_BEAT)) - return -EINVAL; - - beat_pm_poweroff_flag = 0; - return beat_register_event(); -} - -device_initcall(beat_event_init); diff --git a/arch/powerpc/platforms/cell/beat.h b/arch/powerpc/platforms/cell/beat.h deleted file mode 100644 index bfcb8e351ae5..000000000000 --- a/arch/powerpc/platforms/cell/beat.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Guest OS Interfaces. - * - * (C) Copyright 2006 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_BEAT_H -#define _CELLEB_BEAT_H - -int64_t beat_get_term_char(uint64_t, uint64_t *, uint64_t *, uint64_t *); -int64_t beat_put_term_char(uint64_t, uint64_t, uint64_t, uint64_t); -int64_t beat_repository_encode(int, const char *, uint64_t[4]); -void beat_restart(char *); -void beat_power_off(void); -void beat_halt(void); -int beat_set_rtc_time(struct rtc_time *); -void beat_get_rtc_time(struct rtc_time *); -ssize_t beat_nvram_get_size(void); -ssize_t beat_nvram_read(char *, size_t, loff_t *); -ssize_t beat_nvram_write(char *, size_t, loff_t *); -int beat_set_xdabr(unsigned long, unsigned long); -void beat_power_save(void); -void beat_kexec_cpu_down(int, int); - -#endif /* _CELLEB_BEAT_H */ diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c deleted file mode 100644 index bee9232fe619..000000000000 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ /dev/null @@ -1,445 +0,0 @@ -/* - * "Cell Reference Set" HTAB support. - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/lpar.c: - * Copyright (C) 2001 Todd Inglett, 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG_LOW - -#include <linux/kernel.h> -#include <linux/spinlock.h> - -#include <asm/mmu.h> -#include <asm/page.h> -#include <asm/pgtable.h> -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "beat_wrapper.h" - -#ifdef DEBUG_LOW -#define DBG_LOW(fmt...) do { udbg_printf(fmt); } while (0) -#else -#define DBG_LOW(fmt...) do { } while (0) -#endif - -static DEFINE_RAW_SPINLOCK(beat_htab_lock); - -static inline unsigned int beat_read_mask(unsigned hpte_group) -{ - unsigned long rmask = 0; - u64 hpte_v[5]; - - beat_read_htab_entries(0, hpte_group + 0, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x8000; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x4000; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x2000; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x1000; - beat_read_htab_entries(0, hpte_group + 4, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x0800; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x0400; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x0200; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x0100; - hpte_group = ~hpte_group & (htab_hash_mask * HPTES_PER_GROUP); - beat_read_htab_entries(0, hpte_group + 0, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x80; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x40; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x20; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x10; - beat_read_htab_entries(0, hpte_group + 4, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x08; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x04; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x02; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x01; - return rmask; -} - -static long beat_lpar_hpte_insert(unsigned long hpte_group, - unsigned long vpn, unsigned long pa, - unsigned long rflags, unsigned long vflags, - int psize, int apsize, int ssize) -{ - unsigned long lpar_rc; - u64 hpte_v, hpte_r, slot; - - if (vflags & HPTE_V_SECONDARY) - return -1; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW("hpte_insert(group=%lx, va=%016lx, pa=%016lx, " - "rflags=%lx, vflags=%lx, psize=%d)\n", - hpte_group, va, pa, rflags, vflags, psize); - - hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | - vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); - - if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~HPTE_R_M; - - raw_spin_lock(&beat_htab_lock); - lpar_rc = beat_read_mask(hpte_group); - if (lpar_rc == 0) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" full\n"); - raw_spin_unlock(&beat_htab_lock); - return -1; - } - - lpar_rc = beat_insert_htab_entry(0, hpte_group, lpar_rc << 48, - hpte_v, hpte_r, &slot); - raw_spin_unlock(&beat_htab_lock); - - /* - * Since we try and ioremap PHBs we don't own, the pte insert - * will fail. However we must catch the failure in hash_page - * or we will loop forever, so return -2 in this case. - */ - if (unlikely(lpar_rc != 0)) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" lpar err %lx\n", lpar_rc); - return -2; - } - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" -> slot: %lx\n", slot); - - /* We have to pass down the secondary bucket bit here as well */ - return (slot ^ hpte_group) & 15; -} - -static long beat_lpar_hpte_remove(unsigned long hpte_group) -{ - DBG_LOW("hpte_remove(group=%lx)\n", hpte_group); - return -1; -} - -static unsigned long beat_lpar_hpte_getword0(unsigned long slot) -{ - unsigned long dword0; - unsigned long lpar_rc; - u64 dword[5]; - - lpar_rc = beat_read_htab_entries(0, slot & ~3UL, dword); - - dword0 = dword[slot&3]; - - BUG_ON(lpar_rc != 0); - - return dword0; -} - -static void beat_lpar_hptab_clear(void) -{ - unsigned long size_bytes = 1UL << ppc64_pft_size; - unsigned long hpte_count = size_bytes >> 4; - int i; - u64 dummy0, dummy1; - - /* TODO: Use bulk call */ - for (i = 0; i < hpte_count; i++) - beat_write_htab_entry(0, i, 0, 0, -1UL, -1UL, &dummy0, &dummy1); -} - -/* - * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and - * the low 3 bits of flags happen to line up. So no transform is needed. - * We can probably optimize here and assume the high bits of newpp are - * already zero. For now I am paranoid. - */ -static long beat_lpar_hpte_updatepp(unsigned long slot, - unsigned long newpp, - unsigned long vpn, - int psize, int apsize, - int ssize, unsigned long flags) -{ - unsigned long lpar_rc; - u64 dummy0, dummy1; - unsigned long want_v; - - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - DBG_LOW(" update: " - "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", - want_v & HPTE_V_AVPN, slot, psize, newpp); - - raw_spin_lock(&beat_htab_lock); - dummy0 = beat_lpar_hpte_getword0(slot); - if ((dummy0 & ~0x7FUL) != (want_v & ~0x7FUL)) { - DBG_LOW("not found !\n"); - raw_spin_unlock(&beat_htab_lock); - return -1; - } - - lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7, &dummy0, - &dummy1); - raw_spin_unlock(&beat_htab_lock); - if (lpar_rc != 0 || dummy0 == 0) { - DBG_LOW("not found !\n"); - return -1; - } - - DBG_LOW("ok %lx %lx\n", dummy0, dummy1); - - BUG_ON(lpar_rc != 0); - - return 0; -} - -static long beat_lpar_hpte_find(unsigned long vpn, int psize) -{ - unsigned long hash; - unsigned long i, j; - long slot; - unsigned long want_v, hpte_v; - - hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - for (j = 0; j < 2; j++) { - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hpte_v = beat_lpar_hpte_getword0(slot); - - if (HPTE_V_COMPARE(hpte_v, want_v) - && (hpte_v & HPTE_V_VALID) - && (!!(hpte_v & HPTE_V_SECONDARY) == j)) { - /* HPTE matches */ - if (j) - slot = -slot; - return slot; - } - ++slot; - } - hash = ~hash; - } - - return -1; -} - -static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, - unsigned long ea, - int psize, int ssize) -{ - unsigned long vpn; - unsigned long lpar_rc, slot, vsid; - u64 dummy0, dummy1; - - vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); - vpn = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M); - - raw_spin_lock(&beat_htab_lock); - slot = beat_lpar_hpte_find(vpn, psize); - BUG_ON(slot == -1); - - lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7, - &dummy0, &dummy1); - raw_spin_unlock(&beat_htab_lock); - - BUG_ON(lpar_rc != 0); -} - -static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, - int psize, int apsize, - int ssize, int local) -{ - unsigned long want_v; - unsigned long lpar_rc; - u64 dummy1, dummy2; - unsigned long flags; - - DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n", - slot, va, psize, local); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - raw_spin_lock_irqsave(&beat_htab_lock, flags); - dummy1 = beat_lpar_hpte_getword0(slot); - - if ((dummy1 & ~0x7FUL) != (want_v & ~0x7FUL)) { - DBG_LOW("not found !\n"); - raw_spin_unlock_irqrestore(&beat_htab_lock, flags); - return; - } - - lpar_rc = beat_write_htab_entry(0, slot, 0, 0, HPTE_V_VALID, 0, - &dummy1, &dummy2); - raw_spin_unlock_irqrestore(&beat_htab_lock, flags); - - BUG_ON(lpar_rc != 0); -} - -void __init hpte_init_beat(void) -{ - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear; -} - -static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, - unsigned long vpn, unsigned long pa, - unsigned long rflags, unsigned long vflags, - int psize, int apsize, int ssize) -{ - unsigned long lpar_rc; - u64 hpte_v, hpte_r, slot; - - if (vflags & HPTE_V_SECONDARY) - return -1; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW("hpte_insert(group=%lx, vpn=%016lx, pa=%016lx, " - "rflags=%lx, vflags=%lx, psize=%d)\n", - hpte_group, vpn, pa, rflags, vflags, psize); - - hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | - vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); - - if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~HPTE_R_M; - - /* insert into not-volted entry */ - lpar_rc = beat_insert_htab_entry3(0, hpte_group, hpte_v, hpte_r, - HPTE_V_BOLTED, 0, &slot); - /* - * Since we try and ioremap PHBs we don't own, the pte insert - * will fail. However we must catch the failure in hash_page - * or we will loop forever, so return -2 in this case. - */ - if (unlikely(lpar_rc != 0)) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" lpar err %lx\n", lpar_rc); - return -2; - } - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" -> slot: %lx\n", slot); - - /* We have to pass down the secondary bucket bit here as well */ - return (slot ^ hpte_group) & 15; -} - -/* - * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and - * the low 3 bits of flags happen to line up. So no transform is needed. - * We can probably optimize here and assume the high bits of newpp are - * already zero. For now I am paranoid. - */ -static long beat_lpar_hpte_updatepp_v3(unsigned long slot, - unsigned long newpp, - unsigned long vpn, - int psize, int apsize, - int ssize, unsigned long flags) -{ - unsigned long lpar_rc; - unsigned long want_v; - unsigned long pss; - - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; - - DBG_LOW(" update: " - "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", - want_v & HPTE_V_AVPN, slot, psize, newpp); - - lpar_rc = beat_update_htab_permission3(0, slot, want_v, pss, 7, newpp); - - if (lpar_rc == 0xfffffff7) { - DBG_LOW("not found !\n"); - return -1; - } - - DBG_LOW("ok\n"); - - BUG_ON(lpar_rc != 0); - - return 0; -} - -static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn, - int psize, int apsize, - int ssize, int local) -{ - unsigned long want_v; - unsigned long lpar_rc; - unsigned long pss; - - DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n", - slot, vpn, psize, local); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; - - lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss); - - /* E_busy can be valid output: page may be already replaced */ - BUG_ON(lpar_rc != 0 && lpar_rc != 0xfffffff7); -} - -static int64_t _beat_lpar_hptab_clear_v3(void) -{ - return beat_clear_htab3(0); -} - -static void beat_lpar_hptab_clear_v3(void) -{ - _beat_lpar_hptab_clear_v3(); -} - -void __init hpte_init_beat_v3(void) -{ - if (_beat_lpar_hptab_clear_v3() == 0) { - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate_v3; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp_v3; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert_v3; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear_v3; - } else { - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear; - } -} diff --git a/arch/powerpc/platforms/cell/beat_hvCall.S b/arch/powerpc/platforms/cell/beat_hvCall.S deleted file mode 100644 index 96c801907126..000000000000 --- a/arch/powerpc/platforms/cell/beat_hvCall.S +++ /dev/null @@ -1,285 +0,0 @@ -/* - * Beat hypervisor call I/F - * - * (C) Copyright 2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/hvCall.S. - * - * 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <asm/ppc_asm.h> - -/* Not implemented on Beat, now */ -#define HCALL_INST_PRECALL -#define HCALL_INST_POSTCALL - - .text - -#define HVSC .long 0x44000022 - -/* Note: takes only 7 input parameters at maximum */ -_GLOBAL(beat_hcall_norets) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - mr r11,r3 - mr r3,r4 - mr r4,r5 - mr r5,r6 - mr r6,r7 - mr r7,r8 - mr r8,r9 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes 8 input parameters at maximum */ -_GLOBAL(beat_hcall_norets8) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - mr r11,r3 - mr r3,r4 - mr r4,r5 - mr r5,r6 - mr r6,r7 - mr r7,r8 - mr r8,r9 - ld r10,STK_PARAM(R10)(r1) - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 1 output parameters at maximum */ -_GLOBAL(beat_hcall1) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 2 output parameters at maximum */ -_GLOBAL(beat_hcall2) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 3 output parameters at maximum */ -_GLOBAL(beat_hcall3) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 4 output parameters at maximum */ -_GLOBAL(beat_hcall4) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - std r7, 24(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 5 output parameters at maximum */ -_GLOBAL(beat_hcall5) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - std r7, 24(r12) - std r8, 32(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 6 output parameters at maximum */ -_GLOBAL(beat_hcall6) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(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) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c deleted file mode 100644 index 9e5dfbcc00af..000000000000 --- a/arch/powerpc/platforms/cell/beat_interrupt.c +++ /dev/null @@ -1,253 +0,0 @@ -/* - * Celleb/Beat Interrupt controller - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/percpu.h> -#include <linux/types.h> - -#include <asm/machdep.h> - -#include "beat_interrupt.h" -#include "beat_wrapper.h" - -#define MAX_IRQS NR_IRQS -static DEFINE_RAW_SPINLOCK(beatic_irq_mask_lock); -static uint64_t beatic_irq_mask_enable[(MAX_IRQS+255)/64]; -static uint64_t beatic_irq_mask_ack[(MAX_IRQS+255)/64]; - -static struct irq_domain *beatic_host; - -/* - * In this implementation, "virq" == "IRQ plug number", - * "(irq_hw_number_t)hwirq" == "IRQ outlet number". - */ - -/* assumption: locked */ -static inline void beatic_update_irq_mask(unsigned int irq_plug) -{ - int off; - unsigned long masks[4]; - - off = (irq_plug / 256) * 4; - masks[0] = beatic_irq_mask_enable[off + 0] - & beatic_irq_mask_ack[off + 0]; - masks[1] = beatic_irq_mask_enable[off + 1] - & beatic_irq_mask_ack[off + 1]; - masks[2] = beatic_irq_mask_enable[off + 2] - & beatic_irq_mask_ack[off + 2]; - masks[3] = beatic_irq_mask_enable[off + 3] - & beatic_irq_mask_ack[off + 3]; - if (beat_set_interrupt_mask(irq_plug&~255UL, - masks[0], masks[1], masks[2], masks[3]) != 0) - panic("Failed to set mask IRQ!"); -} - -static void beatic_mask_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_enable[d->irq/64] &= ~(1UL << (63 - (d->irq%64))); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_unmask_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_enable[d->irq/64] |= 1UL << (63 - (d->irq%64)); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_ack_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_ack[d->irq/64] &= ~(1UL << (63 - (d->irq%64))); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_end_irq(struct irq_data *d) -{ - s64 err; - unsigned long flags; - - err = beat_downcount_of_interrupt(d->irq); - if (err != 0) { - if ((err & 0xFFFFFFFF) != 0xFFFFFFF5) /* -11: wrong state */ - panic("Failed to downcount IRQ! Error = %16llx", err); - - printk(KERN_ERR "IRQ over-downcounted, plug %d\n", d->irq); - } - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_ack[d->irq/64] |= 1UL << (63 - (d->irq%64)); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static struct irq_chip beatic_pic = { - .name = "CELL-BEAT", - .irq_unmask = beatic_unmask_irq, - .irq_mask = beatic_mask_irq, - .irq_eoi = beatic_end_irq, -}; - -/* - * Dispose binding hardware IRQ number (hw) and Virtuql IRQ number (virq), - * update flags. - * - * Note that the number (virq) is already assigned at upper layer. - */ -static void beatic_pic_host_unmap(struct irq_domain *h, unsigned int virq) -{ - beat_destruct_irq_plug(virq); -} - -/* - * Create or update binding hardware IRQ number (hw) and Virtuql - * IRQ number (virq). This is called only once for a given mapping. - * - * Note that the number (virq) is already assigned at upper layer. - */ -static int beatic_pic_host_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw) -{ - int64_t err; - - err = beat_construct_and_connect_irq_plug(virq, hw); - if (err < 0) - return -EIO; - - irq_set_status_flags(virq, IRQ_LEVEL); - irq_set_chip_and_handler(virq, &beatic_pic, handle_fasteoi_irq); - return 0; -} - -/* - * Translate device-tree interrupt spec to irq_hw_number_t style (ulong), - * to pass away to irq_create_mapping(). - * - * Called from irq_create_of_mapping() only. - * Note: We have only 1 entry to translate. - */ -static int beatic_pic_host_xlate(struct irq_domain *h, struct device_node *ct, - const u32 *intspec, unsigned int intsize, - irq_hw_number_t *out_hwirq, - unsigned int *out_flags) -{ - const u64 *intspec2 = (const u64 *)intspec; - - *out_hwirq = *intspec2; - *out_flags |= IRQ_TYPE_LEVEL_LOW; - return 0; -} - -static int beatic_pic_host_match(struct irq_domain *h, struct device_node *np) -{ - /* Match all */ - return 1; -} - -static const struct irq_domain_ops beatic_pic_host_ops = { - .map = beatic_pic_host_map, - .unmap = beatic_pic_host_unmap, - .xlate = beatic_pic_host_xlate, - .match = beatic_pic_host_match, -}; - -/* - * Get an IRQ number - * Note: returns VIRQ - */ -static inline unsigned int beatic_get_irq_plug(void) -{ - int i; - uint64_t pending[4], ub; - - for (i = 0; i < MAX_IRQS; i += 256) { - beat_detect_pending_interrupts(i, pending); - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[0] & beatic_irq_mask_enable[i/64+0] - & beatic_irq_mask_ack[i/64+0])); - if (ub != 64) - return i + ub + 0; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[1] & beatic_irq_mask_enable[i/64+1] - & beatic_irq_mask_ack[i/64+1])); - if (ub != 64) - return i + ub + 64; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[2] & beatic_irq_mask_enable[i/64+2] - & beatic_irq_mask_ack[i/64+2])); - if (ub != 64) - return i + ub + 128; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[3] & beatic_irq_mask_enable[i/64+3] - & beatic_irq_mask_ack[i/64+3])); - if (ub != 64) - return i + ub + 192; - } - - return NO_IRQ; -} -unsigned int beatic_get_irq(void) -{ - unsigned int ret; - - ret = beatic_get_irq_plug(); - if (ret != NO_IRQ) - beatic_ack_irq(irq_get_irq_data(ret)); - return ret; -} - -/* - */ -void __init beatic_init_IRQ(void) -{ - int i; - - memset(beatic_irq_mask_enable, 0, sizeof(beatic_irq_mask_enable)); - memset(beatic_irq_mask_ack, 255, sizeof(beatic_irq_mask_ack)); - for (i = 0; i < MAX_IRQS; i += 256) - beat_set_interrupt_mask(i, 0L, 0L, 0L, 0L); - - /* Set out get_irq function */ - ppc_md.get_irq = beatic_get_irq; - - /* Allocate an irq host */ - beatic_host = irq_domain_add_nomap(NULL, ~0, &beatic_pic_host_ops, NULL); - BUG_ON(beatic_host == NULL); - irq_set_default_host(beatic_host); -} - -void beatic_deinit_IRQ(void) -{ - int i; - - for (i = 1; i < nr_irqs; i++) - beat_destruct_irq_plug(i); -} diff --git a/arch/powerpc/platforms/cell/beat_interrupt.h b/arch/powerpc/platforms/cell/beat_interrupt.h deleted file mode 100644 index a7e52f91a078..000000000000 --- a/arch/powerpc/platforms/cell/beat_interrupt.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Celleb/Beat Interrupt controller - * - * (C) Copyright 2006 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef ASM_BEAT_PIC_H -#define ASM_BEAT_PIC_H -#ifdef __KERNEL__ - -extern void beatic_init_IRQ(void); -extern unsigned int beatic_get_irq(void); -extern void beatic_deinit_IRQ(void); - -#endif -#endif /* ASM_BEAT_PIC_H */ diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c deleted file mode 100644 index 3ce685568935..000000000000 --- a/arch/powerpc/platforms/cell/beat_iommu.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Support for IOMMU on Celleb platform. - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/dma-mapping.h> -#include <linux/pci.h> -#include <linux/of_platform.h> - -#include <asm/machdep.h> - -#include "beat_wrapper.h" - -#define DMA_FLAGS 0xf800000000000000UL /* r/w permitted, coherency required, - strongest order */ - -static int __init find_dma_window(u64 *io_space_id, u64 *ioid, - u64 *base, u64 *size, u64 *io_page_size) -{ - struct device_node *dn; - const unsigned long *dma_window; - - for_each_node_by_type(dn, "ioif") { - dma_window = of_get_property(dn, "toshiba,dma-window", NULL); - if (dma_window) { - *io_space_id = (dma_window[0] >> 32) & 0xffffffffUL; - *ioid = dma_window[0] & 0x7ffUL; - *base = dma_window[1]; - *size = dma_window[2]; - *io_page_size = 1 << dma_window[3]; - of_node_put(dn); - return 1; - } - } - return 0; -} - -static unsigned long celleb_dma_direct_offset; - -static void __init celleb_init_direct_mapping(void) -{ - u64 lpar_addr, io_addr; - u64 io_space_id, ioid, dma_base, dma_size, io_page_size; - - if (!find_dma_window(&io_space_id, &ioid, &dma_base, &dma_size, - &io_page_size)) { - pr_info("No dma window found !\n"); - return; - } - - for (lpar_addr = 0; lpar_addr < dma_size; lpar_addr += io_page_size) { - io_addr = lpar_addr + dma_base; - (void)beat_put_iopte(io_space_id, io_addr, lpar_addr, - ioid, DMA_FLAGS); - } - - celleb_dma_direct_offset = dma_base; -} - -static void celleb_dma_dev_setup(struct device *dev) -{ - set_dma_ops(dev, &dma_direct_ops); - set_dma_offset(dev, celleb_dma_direct_offset); -} - -static void celleb_pci_dma_dev_setup(struct pci_dev *pdev) -{ - celleb_dma_dev_setup(&pdev->dev); -} - -static int celleb_of_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - /* We are only intereted in device addition */ - if (action != BUS_NOTIFY_ADD_DEVICE) - return 0; - - celleb_dma_dev_setup(dev); - - return 0; -} - -static struct notifier_block celleb_of_bus_notifier = { - .notifier_call = celleb_of_bus_notify -}; - -static int __init celleb_init_iommu(void) -{ - celleb_init_direct_mapping(); - ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup; - bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier); - - return 0; -} - -machine_arch_initcall(celleb_beat, celleb_init_iommu); diff --git a/arch/powerpc/platforms/cell/beat_spu_priv1.c b/arch/powerpc/platforms/cell/beat_spu_priv1.c deleted file mode 100644 index 13f52589d3a9..000000000000 --- a/arch/powerpc/platforms/cell/beat_spu_priv1.c +++ /dev/null @@ -1,205 +0,0 @@ -/* - * spu hypervisor abstraction for Beat - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <asm/types.h> -#include <asm/spu.h> -#include <asm/spu_priv1.h> - -#include "beat_wrapper.h" - -static inline void _int_mask_set(struct spu *spu, int class, u64 mask) -{ - spu->shadow_int_mask_RW[class] = mask; - beat_set_irq_mask_for_spe(spu->spe_id, class, mask); -} - -static inline u64 _int_mask_get(struct spu *spu, int class) -{ - return spu->shadow_int_mask_RW[class]; -} - -static void int_mask_set(struct spu *spu, int class, u64 mask) -{ - _int_mask_set(spu, class, mask); -} - -static u64 int_mask_get(struct spu *spu, int class) -{ - return _int_mask_get(spu, class); -} - -static void int_mask_and(struct spu *spu, int class, u64 mask) -{ - u64 old_mask; - old_mask = _int_mask_get(spu, class); - _int_mask_set(spu, class, old_mask & mask); -} - -static void int_mask_or(struct spu *spu, int class, u64 mask) -{ - u64 old_mask; - old_mask = _int_mask_get(spu, class); - _int_mask_set(spu, class, old_mask | mask); -} - -static void int_stat_clear(struct spu *spu, int class, u64 stat) -{ - beat_clear_interrupt_status_of_spe(spu->spe_id, class, stat); -} - -static u64 int_stat_get(struct spu *spu, int class) -{ - u64 int_stat; - beat_get_interrupt_status_of_spe(spu->spe_id, class, &int_stat); - return int_stat; -} - -static void cpu_affinity_set(struct spu *spu, int cpu) -{ - return; -} - -static u64 mfc_dar_get(struct spu *spu) -{ - u64 dar; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dar_RW), &dar); - return dar; -} - -static u64 mfc_dsisr_get(struct spu *spu) -{ - u64 dsisr; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dsisr_RW), &dsisr); - return dsisr; -} - -static void mfc_dsisr_set(struct spu *spu, u64 dsisr) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dsisr_RW), dsisr); -} - -static void mfc_sdr_setup(struct spu *spu) -{ - return; -} - -static void mfc_sr1_set(struct spu *spu, u64 sr1) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_sr1_RW), sr1); -} - -static u64 mfc_sr1_get(struct spu *spu) -{ - u64 sr1; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_sr1_RW), &sr1); - return sr1; -} - -static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_tclass_id_RW), tclass_id); -} - -static u64 mfc_tclass_id_get(struct spu *spu) -{ - u64 tclass_id; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_tclass_id_RW), &tclass_id); - return tclass_id; -} - -static void tlb_invalidate(struct spu *spu) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, tlb_invalidate_entry_W), 0ul); -} - -static void resource_allocation_groupID_set(struct spu *spu, u64 id) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_groupID_RW), - id); -} - -static u64 resource_allocation_groupID_get(struct spu *spu) -{ - u64 id; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_groupID_RW), - &id); - return id; -} - -static void resource_allocation_enable_set(struct spu *spu, u64 enable) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_enable_RW), - enable); -} - -static u64 resource_allocation_enable_get(struct spu *spu) -{ - u64 enable; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_enable_RW), - &enable); - return enable; -} - -const struct spu_priv1_ops spu_priv1_beat_ops = { - .int_mask_and = int_mask_and, - .int_mask_or = int_mask_or, - .int_mask_set = int_mask_set, - .int_mask_get = int_mask_get, - .int_stat_clear = int_stat_clear, - .int_stat_get = int_stat_get, - .cpu_affinity_set = cpu_affinity_set, - .mfc_dar_get = mfc_dar_get, - .mfc_dsisr_get = mfc_dsisr_get, - .mfc_dsisr_set = mfc_dsisr_set, - .mfc_sdr_setup = mfc_sdr_setup, - .mfc_sr1_set = mfc_sr1_set, - .mfc_sr1_get = mfc_sr1_get, - .mfc_tclass_id_set = mfc_tclass_id_set, - .mfc_tclass_id_get = mfc_tclass_id_get, - .tlb_invalidate = tlb_invalidate, - .resource_allocation_groupID_set = resource_allocation_groupID_set, - .resource_allocation_groupID_get = resource_allocation_groupID_get, - .resource_allocation_enable_set = resource_allocation_enable_set, - .resource_allocation_enable_get = resource_allocation_enable_get, -}; diff --git a/arch/powerpc/platforms/cell/beat_syscall.h b/arch/powerpc/platforms/cell/beat_syscall.h deleted file mode 100644 index 8580dc7e1798..000000000000 --- a/arch/powerpc/platforms/cell/beat_syscall.h +++ /dev/null @@ -1,164 +0,0 @@ -/* - * Beat hypervisor call numbers - * - * (C) Copyright 2004-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef BEAT_BEAT_syscall_H -#define BEAT_BEAT_syscall_H - -#ifdef __ASSEMBLY__ -#define __BEAT_ADD_VENDOR_ID(__x, __v) ((__v)<<60|(__x)) -#else -#define __BEAT_ADD_VENDOR_ID(__x, __v) ((u64)(__v)<<60|(__x)) -#endif -#define HV_allocate_memory __BEAT_ADD_VENDOR_ID(0, 0) -#define HV_construct_virtual_address_space __BEAT_ADD_VENDOR_ID(2, 0) -#define HV_destruct_virtual_address_space __BEAT_ADD_VENDOR_ID(10, 0) -#define HV_get_virtual_address_space_id_of_ppe __BEAT_ADD_VENDOR_ID(4, 0) -#define HV_query_logical_partition_address_region_info \ - __BEAT_ADD_VENDOR_ID(6, 0) -#define HV_release_memory __BEAT_ADD_VENDOR_ID(13, 0) -#define HV_select_virtual_address_space __BEAT_ADD_VENDOR_ID(7, 0) -#define HV_load_range_registers __BEAT_ADD_VENDOR_ID(68, 0) -#define HV_set_ppe_l2cache_rmt_entry __BEAT_ADD_VENDOR_ID(70, 0) -#define HV_set_ppe_tlb_rmt_entry __BEAT_ADD_VENDOR_ID(71, 0) -#define HV_set_spe_tlb_rmt_entry __BEAT_ADD_VENDOR_ID(72, 0) -#define HV_get_io_address_translation_fault_info __BEAT_ADD_VENDOR_ID(14, 0) -#define HV_get_iopte __BEAT_ADD_VENDOR_ID(16, 0) -#define HV_preload_iopt_cache __BEAT_ADD_VENDOR_ID(17, 0) -#define HV_put_iopte __BEAT_ADD_VENDOR_ID(15, 0) -#define HV_connect_event_ports __BEAT_ADD_VENDOR_ID(21, 0) -#define HV_construct_event_receive_port __BEAT_ADD_VENDOR_ID(18, 0) -#define HV_destruct_event_receive_port __BEAT_ADD_VENDOR_ID(19, 0) -#define HV_destruct_event_send_port __BEAT_ADD_VENDOR_ID(22, 0) -#define HV_get_state_of_event_send_port __BEAT_ADD_VENDOR_ID(25, 0) -#define HV_request_to_connect_event_ports __BEAT_ADD_VENDOR_ID(20, 0) -#define HV_send_event_externally __BEAT_ADD_VENDOR_ID(23, 0) -#define HV_send_event_locally __BEAT_ADD_VENDOR_ID(24, 0) -#define HV_construct_and_connect_irq_plug __BEAT_ADD_VENDOR_ID(28, 0) -#define HV_destruct_irq_plug __BEAT_ADD_VENDOR_ID(29, 0) -#define HV_detect_pending_interrupts __BEAT_ADD_VENDOR_ID(26, 0) -#define HV_end_of_interrupt __BEAT_ADD_VENDOR_ID(27, 0) -#define HV_assign_control_signal_notification_port __BEAT_ADD_VENDOR_ID(45, 0) -#define HV_end_of_control_signal_processing __BEAT_ADD_VENDOR_ID(48, 0) -#define HV_get_control_signal __BEAT_ADD_VENDOR_ID(46, 0) -#define HV_set_irq_mask_for_spe __BEAT_ADD_VENDOR_ID(61, 0) -#define HV_shutdown_logical_partition __BEAT_ADD_VENDOR_ID(44, 0) -#define HV_connect_message_ports __BEAT_ADD_VENDOR_ID(35, 0) -#define HV_destruct_message_port __BEAT_ADD_VENDOR_ID(36, 0) -#define HV_receive_message __BEAT_ADD_VENDOR_ID(37, 0) -#define HV_get_message_port_info __BEAT_ADD_VENDOR_ID(34, 0) -#define HV_request_to_connect_message_ports __BEAT_ADD_VENDOR_ID(33, 0) -#define HV_send_message __BEAT_ADD_VENDOR_ID(32, 0) -#define HV_get_logical_ppe_id __BEAT_ADD_VENDOR_ID(69, 0) -#define HV_pause __BEAT_ADD_VENDOR_ID(9, 0) -#define HV_destruct_shared_memory_handle __BEAT_ADD_VENDOR_ID(51, 0) -#define HV_get_shared_memory_info __BEAT_ADD_VENDOR_ID(52, 0) -#define HV_permit_sharing_memory __BEAT_ADD_VENDOR_ID(50, 0) -#define HV_request_to_attach_shared_memory __BEAT_ADD_VENDOR_ID(49, 0) -#define HV_enable_logical_spe_execution __BEAT_ADD_VENDOR_ID(55, 0) -#define HV_construct_logical_spe __BEAT_ADD_VENDOR_ID(53, 0) -#define HV_disable_logical_spe_execution __BEAT_ADD_VENDOR_ID(56, 0) -#define HV_destruct_logical_spe __BEAT_ADD_VENDOR_ID(54, 0) -#define HV_sense_spe_execution_status __BEAT_ADD_VENDOR_ID(58, 0) -#define HV_insert_htab_entry __BEAT_ADD_VENDOR_ID(101, 0) -#define HV_read_htab_entries __BEAT_ADD_VENDOR_ID(95, 0) -#define HV_write_htab_entry __BEAT_ADD_VENDOR_ID(94, 0) -#define HV_assign_io_address_translation_fault_port \ - __BEAT_ADD_VENDOR_ID(100, 0) -#define HV_set_interrupt_mask __BEAT_ADD_VENDOR_ID(73, 0) -#define HV_get_logical_partition_id __BEAT_ADD_VENDOR_ID(74, 0) -#define HV_create_repository_node2 __BEAT_ADD_VENDOR_ID(90, 0) -#define HV_create_repository_node __BEAT_ADD_VENDOR_ID(90, 0) /* alias */ -#define HV_get_repository_node_value2 __BEAT_ADD_VENDOR_ID(91, 0) -#define HV_get_repository_node_value __BEAT_ADD_VENDOR_ID(91, 0) /* alias */ -#define HV_modify_repository_node_value2 __BEAT_ADD_VENDOR_ID(92, 0) -#define HV_modify_repository_node_value __BEAT_ADD_VENDOR_ID(92, 0) /* alias */ -#define HV_remove_repository_node2 __BEAT_ADD_VENDOR_ID(93, 0) -#define HV_remove_repository_node __BEAT_ADD_VENDOR_ID(93, 0) /* alias */ -#define HV_cancel_shared_memory __BEAT_ADD_VENDOR_ID(104, 0) -#define HV_clear_interrupt_status_of_spe __BEAT_ADD_VENDOR_ID(206, 0) -#define HV_construct_spe_irq_outlet __BEAT_ADD_VENDOR_ID(80, 0) -#define HV_destruct_spe_irq_outlet __BEAT_ADD_VENDOR_ID(81, 0) -#define HV_disconnect_ipspc_service __BEAT_ADD_VENDOR_ID(88, 0) -#define HV_execute_ipspc_command __BEAT_ADD_VENDOR_ID(86, 0) -#define HV_get_interrupt_status_of_spe __BEAT_ADD_VENDOR_ID(205, 0) -#define HV_get_spe_privileged_state_1_registers __BEAT_ADD_VENDOR_ID(208, 0) -#define HV_permit_use_of_ipspc_service __BEAT_ADD_VENDOR_ID(85, 0) -#define HV_reinitialize_logical_spe __BEAT_ADD_VENDOR_ID(82, 0) -#define HV_request_ipspc_service __BEAT_ADD_VENDOR_ID(84, 0) -#define HV_stop_ipspc_command __BEAT_ADD_VENDOR_ID(87, 0) -#define HV_set_spe_privileged_state_1_registers __BEAT_ADD_VENDOR_ID(204, 0) -#define HV_get_status_of_ipspc_service __BEAT_ADD_VENDOR_ID(203, 0) -#define HV_put_characters_to_console __BEAT_ADD_VENDOR_ID(0x101, 1) -#define HV_get_characters_from_console __BEAT_ADD_VENDOR_ID(0x102, 1) -#define HV_get_base_clock __BEAT_ADD_VENDOR_ID(0x111, 1) -#define HV_set_base_clock __BEAT_ADD_VENDOR_ID(0x112, 1) -#define HV_get_frame_cycle __BEAT_ADD_VENDOR_ID(0x114, 1) -#define HV_disable_console __BEAT_ADD_VENDOR_ID(0x115, 1) -#define HV_disable_all_console __BEAT_ADD_VENDOR_ID(0x116, 1) -#define HV_oneshot_timer __BEAT_ADD_VENDOR_ID(0x117, 1) -#define HV_set_dabr __BEAT_ADD_VENDOR_ID(0x118, 1) -#define HV_get_dabr __BEAT_ADD_VENDOR_ID(0x119, 1) -#define HV_start_hv_stats __BEAT_ADD_VENDOR_ID(0x21c, 1) -#define HV_stop_hv_stats __BEAT_ADD_VENDOR_ID(0x21d, 1) -#define HV_get_hv_stats __BEAT_ADD_VENDOR_ID(0x21e, 1) -#define HV_get_hv_error_stats __BEAT_ADD_VENDOR_ID(0x221, 1) -#define HV_get_stats __BEAT_ADD_VENDOR_ID(0x224, 1) -#define HV_get_heap_stats __BEAT_ADD_VENDOR_ID(0x225, 1) -#define HV_get_memory_stats __BEAT_ADD_VENDOR_ID(0x227, 1) -#define HV_get_memory_detail __BEAT_ADD_VENDOR_ID(0x228, 1) -#define HV_set_priority_of_irq_outlet __BEAT_ADD_VENDOR_ID(0x122, 1) -#define HV_get_physical_spe_by_reservation_id __BEAT_ADD_VENDOR_ID(0x128, 1) -#define HV_get_spe_context __BEAT_ADD_VENDOR_ID(0x129, 1) -#define HV_set_spe_context __BEAT_ADD_VENDOR_ID(0x12a, 1) -#define HV_downcount_of_interrupt __BEAT_ADD_VENDOR_ID(0x12e, 1) -#define HV_peek_spe_context __BEAT_ADD_VENDOR_ID(0x12f, 1) -#define HV_read_bpa_register __BEAT_ADD_VENDOR_ID(0x131, 1) -#define HV_write_bpa_register __BEAT_ADD_VENDOR_ID(0x132, 1) -#define HV_map_context_table_of_spe __BEAT_ADD_VENDOR_ID(0x137, 1) -#define HV_get_slb_for_logical_spe __BEAT_ADD_VENDOR_ID(0x138, 1) -#define HV_set_slb_for_logical_spe __BEAT_ADD_VENDOR_ID(0x139, 1) -#define HV_init_pm __BEAT_ADD_VENDOR_ID(0x150, 1) -#define HV_set_pm_signal __BEAT_ADD_VENDOR_ID(0x151, 1) -#define HV_get_pm_signal __BEAT_ADD_VENDOR_ID(0x152, 1) -#define HV_set_pm_config __BEAT_ADD_VENDOR_ID(0x153, 1) -#define HV_get_pm_config __BEAT_ADD_VENDOR_ID(0x154, 1) -#define HV_get_inner_trace_data __BEAT_ADD_VENDOR_ID(0x155, 1) -#define HV_set_ext_trace_buffer __BEAT_ADD_VENDOR_ID(0x156, 1) -#define HV_get_ext_trace_buffer __BEAT_ADD_VENDOR_ID(0x157, 1) -#define HV_set_pm_interrupt __BEAT_ADD_VENDOR_ID(0x158, 1) -#define HV_get_pm_interrupt __BEAT_ADD_VENDOR_ID(0x159, 1) -#define HV_kick_pm __BEAT_ADD_VENDOR_ID(0x160, 1) -#define HV_construct_pm_context __BEAT_ADD_VENDOR_ID(0x164, 1) -#define HV_destruct_pm_context __BEAT_ADD_VENDOR_ID(0x165, 1) -#define HV_be_slow __BEAT_ADD_VENDOR_ID(0x170, 1) -#define HV_assign_ipspc_server_connection_status_notification_port \ - __BEAT_ADD_VENDOR_ID(0x173, 1) -#define HV_get_raid_of_physical_spe __BEAT_ADD_VENDOR_ID(0x174, 1) -#define HV_set_physical_spe_to_rag __BEAT_ADD_VENDOR_ID(0x175, 1) -#define HV_release_physical_spe_from_rag __BEAT_ADD_VENDOR_ID(0x176, 1) -#define HV_rtc_read __BEAT_ADD_VENDOR_ID(0x190, 1) -#define HV_rtc_write __BEAT_ADD_VENDOR_ID(0x191, 1) -#define HV_eeprom_read __BEAT_ADD_VENDOR_ID(0x192, 1) -#define HV_eeprom_write __BEAT_ADD_VENDOR_ID(0x193, 1) -#define HV_insert_htab_entry3 __BEAT_ADD_VENDOR_ID(0x104, 1) -#define HV_invalidate_htab_entry3 __BEAT_ADD_VENDOR_ID(0x105, 1) -#define HV_update_htab_permission3 __BEAT_ADD_VENDOR_ID(0x106, 1) -#define HV_clear_htab3 __BEAT_ADD_VENDOR_ID(0x107, 1) -#endif diff --git a/arch/powerpc/platforms/cell/beat_udbg.c b/arch/powerpc/platforms/cell/beat_udbg.c deleted file mode 100644 index 350735bc8888..000000000000 --- a/arch/powerpc/platforms/cell/beat_udbg.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * udbg function for Beat - * - * (C) Copyright 2006 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/console.h> - -#include <asm/machdep.h> -#include <asm/prom.h> -#include <asm/udbg.h> - -#include "beat.h" - -#define celleb_vtermno 0 - -static void udbg_putc_beat(char c) -{ - unsigned long rc; - - if (c == '\n') - udbg_putc_beat('\r'); - - rc = beat_put_term_char(celleb_vtermno, 1, (uint64_t)c << 56, 0); -} - -/* Buffered chars getc */ -static u64 inbuflen; -static u64 inbuf[2]; /* must be 2 u64s */ - -static int udbg_getc_poll_beat(void) -{ - /* The interface is tricky because it may return up to 16 chars. - * We save them statically for future calls to udbg_getc(). - */ - char ch, *buf = (char *)inbuf; - int i; - long rc; - if (inbuflen == 0) { - /* get some more chars. */ - inbuflen = 0; - rc = beat_get_term_char(celleb_vtermno, &inbuflen, - inbuf+0, inbuf+1); - if (rc != 0) - inbuflen = 0; /* otherwise inbuflen is garbage */ - } - if (inbuflen <= 0 || inbuflen > 16) { - /* Catch error case as well as other oddities (corruption) */ - inbuflen = 0; - return -1; - } - ch = buf[0]; - for (i = 1; i < inbuflen; i++) /* shuffle them down. */ - buf[i-1] = buf[i]; - inbuflen--; - return ch; -} - -static int udbg_getc_beat(void) -{ - int ch; - for (;;) { - ch = udbg_getc_poll_beat(); - if (ch == -1) { - /* This shouldn't be needed...but... */ - volatile unsigned long delay; - for (delay = 0; delay < 2000000; delay++) - ; - } else { - return ch; - } - } -} - -/* call this from early_init() for a working debug console on - * vterm capable LPAR machines - */ -void __init udbg_init_debug_beat(void) -{ - udbg_putc = udbg_putc_beat; - udbg_getc = udbg_getc_beat; - udbg_getc_poll = udbg_getc_poll_beat; -} diff --git a/arch/powerpc/platforms/cell/beat_wrapper.h b/arch/powerpc/platforms/cell/beat_wrapper.h deleted file mode 100644 index c1109969f242..000000000000 --- a/arch/powerpc/platforms/cell/beat_wrapper.h +++ /dev/null @@ -1,290 +0,0 @@ -/* - * Beat hypervisor call I/F - * - * (C) Copyright 2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/plpar_wrapper.h. - * - * 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ -#ifndef BEAT_HCALL -#include <linux/string.h> -#include "beat_syscall.h" - -/* defined in hvCall.S */ -extern s64 beat_hcall_norets(u64 opcode, ...); -extern s64 beat_hcall_norets8(u64 opcode, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -extern s64 beat_hcall1(u64 opcode, u64 retbuf[1], ...); -extern s64 beat_hcall2(u64 opcode, u64 retbuf[2], ...); -extern s64 beat_hcall3(u64 opcode, u64 retbuf[3], ...); -extern s64 beat_hcall4(u64 opcode, u64 retbuf[4], ...); -extern s64 beat_hcall5(u64 opcode, u64 retbuf[5], ...); -extern s64 beat_hcall6(u64 opcode, u64 retbuf[6], ...); - -static inline s64 beat_downcount_of_interrupt(u64 plug_id) -{ - return beat_hcall_norets(HV_downcount_of_interrupt, plug_id); -} - -static inline s64 beat_set_interrupt_mask(u64 index, - u64 val0, u64 val1, u64 val2, u64 val3) -{ - return beat_hcall_norets(HV_set_interrupt_mask, index, - val0, val1, val2, val3); -} - -static inline s64 beat_destruct_irq_plug(u64 plug_id) -{ - return beat_hcall_norets(HV_destruct_irq_plug, plug_id); -} - -static inline s64 beat_construct_and_connect_irq_plug(u64 plug_id, - u64 outlet_id) -{ - return beat_hcall_norets(HV_construct_and_connect_irq_plug, plug_id, - outlet_id); -} - -static inline s64 beat_detect_pending_interrupts(u64 index, u64 *retbuf) -{ - return beat_hcall4(HV_detect_pending_interrupts, retbuf, index); -} - -static inline s64 beat_pause(u64 style) -{ - return beat_hcall_norets(HV_pause, style); -} - -static inline s64 beat_read_htab_entries(u64 htab_id, u64 index, u64 *retbuf) -{ - return beat_hcall5(HV_read_htab_entries, retbuf, htab_id, index); -} - -static inline s64 beat_insert_htab_entry(u64 htab_id, u64 group, - u64 bitmask, u64 hpte_v, u64 hpte_r, u64 *slot) -{ - u64 dummy[3]; - s64 ret; - - ret = beat_hcall3(HV_insert_htab_entry, dummy, htab_id, group, - bitmask, hpte_v, hpte_r); - *slot = dummy[0]; - return ret; -} - -static inline s64 beat_write_htab_entry(u64 htab_id, u64 slot, - u64 hpte_v, u64 hpte_r, u64 mask_v, u64 mask_r, - u64 *ret_v, u64 *ret_r) -{ - u64 dummy[2]; - s64 ret; - - ret = beat_hcall2(HV_write_htab_entry, dummy, htab_id, slot, - hpte_v, hpte_r, mask_v, mask_r); - *ret_v = dummy[0]; - *ret_r = dummy[1]; - return ret; -} - -static inline s64 beat_insert_htab_entry3(u64 htab_id, u64 group, - u64 hpte_v, u64 hpte_r, u64 mask_v, u64 value_v, u64 *slot) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_insert_htab_entry3, dummy, htab_id, group, - hpte_v, hpte_r, mask_v, value_v); - *slot = dummy[0]; - return ret; -} - -static inline s64 beat_invalidate_htab_entry3(u64 htab_id, u64 group, - u64 va, u64 pss) -{ - return beat_hcall_norets(HV_invalidate_htab_entry3, - htab_id, group, va, pss); -} - -static inline s64 beat_update_htab_permission3(u64 htab_id, u64 group, - u64 va, u64 pss, u64 ptel_mask, u64 ptel_value) -{ - return beat_hcall_norets(HV_update_htab_permission3, - htab_id, group, va, pss, ptel_mask, ptel_value); -} - -static inline s64 beat_clear_htab3(u64 htab_id) -{ - return beat_hcall_norets(HV_clear_htab3, htab_id); -} - -static inline void beat_shutdown_logical_partition(u64 code) -{ - (void)beat_hcall_norets(HV_shutdown_logical_partition, code); -} - -static inline s64 beat_rtc_write(u64 time_from_epoch) -{ - return beat_hcall_norets(HV_rtc_write, time_from_epoch); -} - -static inline s64 beat_rtc_read(u64 *time_from_epoch) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_rtc_read, dummy); - *time_from_epoch = dummy[0]; - return ret; -} - -#define BEAT_NVRW_CNT (sizeof(u64) * 6) - -static inline s64 beat_eeprom_write(u64 index, u64 length, u8 *buffer) -{ - u64 b[6]; - - if (length > BEAT_NVRW_CNT) - return -1; - memcpy(b, buffer, sizeof(b)); - return beat_hcall_norets8(HV_eeprom_write, index, length, - b[0], b[1], b[2], b[3], b[4], b[5]); -} - -static inline s64 beat_eeprom_read(u64 index, u64 length, u8 *buffer) -{ - u64 b[6]; - s64 ret; - - if (length > BEAT_NVRW_CNT) - return -1; - ret = beat_hcall6(HV_eeprom_read, b, index, length); - memcpy(buffer, b, length); - return ret; -} - -static inline s64 beat_set_dabr(u64 value, u64 style) -{ - return beat_hcall_norets(HV_set_dabr, value, style); -} - -static inline s64 beat_get_characters_from_console(u64 termno, u64 *len, - u8 *buffer) -{ - u64 dummy[3]; - s64 ret; - - ret = beat_hcall3(HV_get_characters_from_console, dummy, termno, len); - *len = dummy[0]; - memcpy(buffer, dummy + 1, *len); - return ret; -} - -static inline s64 beat_put_characters_to_console(u64 termno, u64 len, - u8 *buffer) -{ - u64 b[2]; - - memcpy(b, buffer, len); - return beat_hcall_norets(HV_put_characters_to_console, termno, len, - b[0], b[1]); -} - -static inline s64 beat_get_spe_privileged_state_1_registers( - u64 id, u64 offsetof, u64 *value) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_get_spe_privileged_state_1_registers, dummy, id, - offsetof); - *value = dummy[0]; - return ret; -} - -static inline s64 beat_set_irq_mask_for_spe(u64 id, u64 class, u64 mask) -{ - return beat_hcall_norets(HV_set_irq_mask_for_spe, id, class, mask); -} - -static inline s64 beat_clear_interrupt_status_of_spe(u64 id, u64 class, - u64 mask) -{ - return beat_hcall_norets(HV_clear_interrupt_status_of_spe, - id, class, mask); -} - -static inline s64 beat_set_spe_privileged_state_1_registers( - u64 id, u64 offsetof, u64 value) -{ - return beat_hcall_norets(HV_set_spe_privileged_state_1_registers, - id, offsetof, value); -} - -static inline s64 beat_get_interrupt_status_of_spe(u64 id, u64 class, u64 *val) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_get_interrupt_status_of_spe, dummy, id, class); - *val = dummy[0]; - return ret; -} - -static inline s64 beat_put_iopte(u64 ioas_id, u64 io_addr, u64 real_addr, - u64 ioid, u64 flags) -{ - return beat_hcall_norets(HV_put_iopte, ioas_id, io_addr, real_addr, - ioid, flags); -} - -static inline s64 beat_construct_event_receive_port(u64 *port) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_construct_event_receive_port, dummy); - *port = dummy[0]; - return ret; -} - -static inline s64 beat_destruct_event_receive_port(u64 port) -{ - s64 ret; - - ret = beat_hcall_norets(HV_destruct_event_receive_port, port); - return ret; -} - -static inline s64 beat_create_repository_node(u64 path[4], u64 data[2]) -{ - s64 ret; - - ret = beat_hcall_norets(HV_create_repository_node2, - path[0], path[1], path[2], path[3], data[0], data[1]); - return ret; -} - -static inline s64 beat_get_repository_node_value(u64 lpid, u64 path[4], - u64 data[2]) -{ - s64 ret; - - ret = beat_hcall2(HV_get_repository_node_value2, data, - lpid, path[0], path[1], path[2], path[3]); - return ret; -} - -#endif diff --git a/arch/powerpc/platforms/cell/cell.h b/arch/powerpc/platforms/cell/cell.h new file mode 100644 index 000000000000..ef143dfee068 --- /dev/null +++ b/arch/powerpc/platforms/cell/cell.h @@ -0,0 +1,24 @@ +/* + * Cell Platform common data structures + * + * Copyright 2015, Daniel Axtens, 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, 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. + */ + +#ifndef CELL_H +#define CELL_H + +#include <asm/pci-bridge.h> + +extern struct pci_controller_ops cell_pci_controller_ops; + +#endif diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c deleted file mode 100644 index 3ce70ded2d6a..000000000000 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ /dev/null @@ -1,500 +0,0 @@ -/* - * Support for PCI on Celleb platform. - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/kernel/rtas_pci.c: - * Copyright (C) 2001 Dave Engebretsen, IBM Corporation - * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/pci.h> -#include <linux/string.h> -#include <linux/init.h> -#include <linux/memblock.h> -#include <linux/pci_regs.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/slab.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -#include "celleb_pci.h" - -#define MAX_PCI_DEVICES 32 -#define MAX_PCI_FUNCTIONS 8 -#define MAX_PCI_BASE_ADDRS 3 /* use 64 bit address */ - -/* definition for fake pci configuration area for GbE, .... ,and etc. */ - -struct celleb_pci_resource { - struct resource r[MAX_PCI_BASE_ADDRS]; -}; - -struct celleb_pci_private { - unsigned char *fake_config[MAX_PCI_DEVICES][MAX_PCI_FUNCTIONS]; - struct celleb_pci_resource *res[MAX_PCI_DEVICES][MAX_PCI_FUNCTIONS]; -}; - -static inline u8 celleb_fake_config_readb(void *addr) -{ - u8 *p = addr; - return *p; -} - -static inline u16 celleb_fake_config_readw(void *addr) -{ - __le16 *p = addr; - return le16_to_cpu(*p); -} - -static inline u32 celleb_fake_config_readl(void *addr) -{ - __le32 *p = addr; - return le32_to_cpu(*p); -} - -static inline void celleb_fake_config_writeb(u32 val, void *addr) -{ - u8 *p = addr; - *p = val; -} - -static inline void celleb_fake_config_writew(u32 val, void *addr) -{ - __le16 val16; - __le16 *p = addr; - val16 = cpu_to_le16(val); - *p = val16; -} - -static inline void celleb_fake_config_writel(u32 val, void *addr) -{ - __le32 val32; - __le32 *p = addr; - val32 = cpu_to_le32(val); - *p = val32; -} - -static unsigned char *get_fake_config_start(struct pci_controller *hose, - int devno, int fn) -{ - struct celleb_pci_private *private = hose->private_data; - - if (private == NULL) - return NULL; - - return private->fake_config[devno][fn]; -} - -static struct celleb_pci_resource *get_resource_start( - struct pci_controller *hose, - int devno, int fn) -{ - struct celleb_pci_private *private = hose->private_data; - - if (private == NULL) - return NULL; - - return private->res[devno][fn]; -} - - -static void celleb_config_read_fake(unsigned char *config, int where, - int size, u32 *val) -{ - char *p = config + where; - - switch (size) { - case 1: - *val = celleb_fake_config_readb(p); - break; - case 2: - *val = celleb_fake_config_readw(p); - break; - case 4: - *val = celleb_fake_config_readl(p); - break; - } -} - -static void celleb_config_write_fake(unsigned char *config, int where, - int size, u32 val) -{ - char *p = config + where; - - switch (size) { - case 1: - celleb_fake_config_writeb(val, p); - break; - case 2: - celleb_fake_config_writew(val, p); - break; - case 4: - celleb_fake_config_writel(val, p); - break; - } -} - -static int celleb_fake_pci_read_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *val) -{ - char *config; - struct pci_controller *hose = pci_bus_to_host(bus); - unsigned int devno = devfn >> 3; - unsigned int fn = devfn & 0x7; - - /* allignment check */ - BUG_ON(where % size); - - pr_debug(" fake read: bus=0x%x, ", bus->number); - config = get_fake_config_start(hose, devno, fn); - - pr_debug("devno=0x%x, where=0x%x, size=0x%x, ", devno, where, size); - if (!config) { - pr_debug("failed\n"); - return PCIBIOS_DEVICE_NOT_FOUND; - } - - celleb_config_read_fake(config, where, size, val); - pr_debug("val=0x%x\n", *val); - - return PCIBIOS_SUCCESSFUL; -} - - -static int celleb_fake_pci_write_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 val) -{ - char *config; - struct pci_controller *hose = pci_bus_to_host(bus); - struct celleb_pci_resource *res; - unsigned int devno = devfn >> 3; - unsigned int fn = devfn & 0x7; - - /* allignment check */ - BUG_ON(where % size); - - config = get_fake_config_start(hose, devno, fn); - - if (!config) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (val == ~0) { - int i = (where - PCI_BASE_ADDRESS_0) >> 3; - - switch (where) { - case PCI_BASE_ADDRESS_0: - case PCI_BASE_ADDRESS_2: - if (size != 4) - return PCIBIOS_DEVICE_NOT_FOUND; - res = get_resource_start(hose, devno, fn); - if (!res) - return PCIBIOS_DEVICE_NOT_FOUND; - celleb_config_write_fake(config, where, size, - (res->r[i].end - res->r[i].start)); - return PCIBIOS_SUCCESSFUL; - case PCI_BASE_ADDRESS_1: - case PCI_BASE_ADDRESS_3: - case PCI_BASE_ADDRESS_4: - case PCI_BASE_ADDRESS_5: - break; - default: - break; - } - } - - celleb_config_write_fake(config, where, size, val); - pr_debug(" fake write: where=%x, size=%d, val=%x\n", - where, size, val); - - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops celleb_fake_pci_ops = { - .read = celleb_fake_pci_read_config, - .write = celleb_fake_pci_write_config, -}; - -static inline void celleb_setup_pci_base_addrs(struct pci_controller *hose, - unsigned int devno, unsigned int fn, - unsigned int num_base_addr) -{ - u32 val; - unsigned char *config; - struct celleb_pci_resource *res; - - config = get_fake_config_start(hose, devno, fn); - res = get_resource_start(hose, devno, fn); - - if (!config || !res) - return; - - switch (num_base_addr) { - case 3: - val = (res->r[2].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_4, 4, val); - val = res->r[2].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_5, 4, val); - /* FALLTHROUGH */ - case 2: - val = (res->r[1].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_2, 4, val); - val = res->r[1].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_3, 4, val); - /* FALLTHROUGH */ - case 1: - val = (res->r[0].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_0, 4, val); - val = res->r[0].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_1, 4, val); - break; - } - - val = PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; - celleb_config_write_fake(config, PCI_COMMAND, 2, val); -} - -static int __init celleb_setup_fake_pci_device(struct device_node *node, - struct pci_controller *hose) -{ - unsigned int rlen; - int num_base_addr = 0; - u32 val; - const u32 *wi0, *wi1, *wi2, *wi3, *wi4; - unsigned int devno, fn; - struct celleb_pci_private *private = hose->private_data; - unsigned char **config = NULL; - struct celleb_pci_resource **res = NULL; - const char *name; - const unsigned long *li; - int size, result; - - if (private == NULL) { - printk(KERN_ERR "PCI: " - "memory space for pci controller is not assigned\n"); - goto error; - } - - name = of_get_property(node, "model", &rlen); - if (!name) { - printk(KERN_ERR "PCI: model property not found.\n"); - goto error; - } - - wi4 = of_get_property(node, "reg", &rlen); - if (wi4 == NULL) - goto error; - - devno = ((wi4[0] >> 8) & 0xff) >> 3; - fn = (wi4[0] >> 8) & 0x7; - - pr_debug("PCI: celleb_setup_fake_pci() %s devno=%x fn=%x\n", name, - devno, fn); - - size = 256; - config = &private->fake_config[devno][fn]; - *config = zalloc_maybe_bootmem(size, GFP_KERNEL); - if (*config == NULL) { - printk(KERN_ERR "PCI: " - "not enough memory for fake configuration space\n"); - goto error; - } - pr_debug("PCI: fake config area assigned 0x%016lx\n", - (unsigned long)*config); - - size = sizeof(struct celleb_pci_resource); - res = &private->res[devno][fn]; - *res = zalloc_maybe_bootmem(size, GFP_KERNEL); - if (*res == NULL) { - printk(KERN_ERR - "PCI: not enough memory for resource data space\n"); - goto error; - } - pr_debug("PCI: res assigned 0x%016lx\n", (unsigned long)*res); - - wi0 = of_get_property(node, "device-id", NULL); - wi1 = of_get_property(node, "vendor-id", NULL); - wi2 = of_get_property(node, "class-code", NULL); - wi3 = of_get_property(node, "revision-id", NULL); - if (!wi0 || !wi1 || !wi2 || !wi3) { - printk(KERN_ERR "PCI: Missing device tree properties.\n"); - goto error; - } - - celleb_config_write_fake(*config, PCI_DEVICE_ID, 2, wi0[0] & 0xffff); - celleb_config_write_fake(*config, PCI_VENDOR_ID, 2, wi1[0] & 0xffff); - pr_debug("class-code = 0x%08x\n", wi2[0]); - - celleb_config_write_fake(*config, PCI_CLASS_PROG, 1, wi2[0] & 0xff); - celleb_config_write_fake(*config, PCI_CLASS_DEVICE, 2, - (wi2[0] >> 8) & 0xffff); - celleb_config_write_fake(*config, PCI_REVISION_ID, 1, wi3[0]); - - while (num_base_addr < MAX_PCI_BASE_ADDRS) { - result = of_address_to_resource(node, - num_base_addr, &(*res)->r[num_base_addr]); - if (result) - break; - num_base_addr++; - } - - celleb_setup_pci_base_addrs(hose, devno, fn, num_base_addr); - - li = of_get_property(node, "interrupts", &rlen); - if (!li) { - printk(KERN_ERR "PCI: interrupts not found.\n"); - goto error; - } - val = li[0]; - celleb_config_write_fake(*config, PCI_INTERRUPT_PIN, 1, 1); - celleb_config_write_fake(*config, PCI_INTERRUPT_LINE, 1, val); - -#ifdef DEBUG - pr_debug("PCI: %s irq=%ld\n", name, li[0]); - for (i = 0; i < 6; i++) { - celleb_config_read_fake(*config, - PCI_BASE_ADDRESS_0 + 0x4 * i, 4, - &val); - pr_debug("PCI: %s fn=%d base_address_%d=0x%x\n", - name, fn, i, val); - } -#endif - - celleb_config_write_fake(*config, PCI_HEADER_TYPE, 1, - PCI_HEADER_TYPE_NORMAL); - - return 0; - -error: - if (mem_init_done) { - if (config && *config) - kfree(*config); - if (res && *res) - kfree(*res); - - } else { - if (config && *config) { - size = 256; - memblock_free(__pa(*config), size); - } - if (res && *res) { - size = sizeof(struct celleb_pci_resource); - memblock_free(__pa(*res), size); - } - } - - return 1; -} - -static int __init phb_set_bus_ranges(struct device_node *dev, - struct pci_controller *phb) -{ - const int *bus_range; - unsigned int len; - - bus_range = of_get_property(dev, "bus-range", &len); - if (bus_range == NULL || len < 2 * sizeof(int)) - return 1; - - phb->first_busno = bus_range[0]; - phb->last_busno = bus_range[1]; - - return 0; -} - -static void __init celleb_alloc_private_mem(struct pci_controller *hose) -{ - hose->private_data = - zalloc_maybe_bootmem(sizeof(struct celleb_pci_private), - GFP_KERNEL); -} - -static int __init celleb_setup_fake_pci(struct device_node *dev, - struct pci_controller *phb) -{ - struct device_node *node; - - phb->ops = &celleb_fake_pci_ops; - celleb_alloc_private_mem(phb); - - for (node = of_get_next_child(dev, NULL); - node != NULL; node = of_get_next_child(dev, node)) - celleb_setup_fake_pci_device(node, phb); - - return 0; -} - -static struct celleb_phb_spec celleb_fake_pci_spec __initdata = { - .setup = celleb_setup_fake_pci, -}; - -static const struct of_device_id celleb_phb_match[] __initconst = { - { - .name = "pci-pseudo", - .data = &celleb_fake_pci_spec, - }, { - .name = "epci", - .data = &celleb_epci_spec, - }, { - .name = "pcie", - .data = &celleb_pciex_spec, - }, { - }, -}; - -int __init celleb_setup_phb(struct pci_controller *phb) -{ - struct device_node *dev = phb->dn; - const struct of_device_id *match; - const struct celleb_phb_spec *phb_spec; - int rc; - - match = of_match_node(celleb_phb_match, dev); - if (!match) - return 1; - - phb_set_bus_ranges(dev, phb); - phb->buid = 1; - - phb_spec = match->data; - rc = (*phb_spec->setup)(dev, phb); - if (rc) - return 1; - - if (phb_spec->ops) - iowa_register_bus(phb, phb_spec->ops, - phb_spec->iowa_init, - phb_spec->iowa_data); - return 0; -} - -int celleb_pci_probe_mode(struct pci_bus *bus) -{ - return PCI_PROBE_DEVTREE; -} diff --git a/arch/powerpc/platforms/cell/celleb_pci.h b/arch/powerpc/platforms/cell/celleb_pci.h deleted file mode 100644 index a801fcc5f389..000000000000 --- a/arch/powerpc/platforms/cell/celleb_pci.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * pci prototypes for Celleb platform - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_PCI_H -#define _CELLEB_PCI_H - -#include <linux/pci.h> - -#include <asm/pci-bridge.h> -#include <asm/prom.h> -#include <asm/ppc-pci.h> -#include <asm/io-workarounds.h> - -struct iowa_bus; - -struct celleb_phb_spec { - int (*setup)(struct device_node *, struct pci_controller *); - struct ppc_pci_io *ops; - int (*iowa_init)(struct iowa_bus *, void *); - void *iowa_data; -}; - -extern int celleb_setup_phb(struct pci_controller *); -extern int celleb_pci_probe_mode(struct pci_bus *); - -extern struct celleb_phb_spec celleb_epci_spec; -extern struct celleb_phb_spec celleb_pciex_spec; - -#endif /* _CELLEB_PCI_H */ diff --git a/arch/powerpc/platforms/cell/celleb_scc.h b/arch/powerpc/platforms/cell/celleb_scc.h deleted file mode 100644 index b596a711c348..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc.h +++ /dev/null @@ -1,232 +0,0 @@ -/* - * SCC (Super Companion Chip) definitions - * - * (C) Copyright 2004-2006 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_SCC_H -#define _CELLEB_SCC_H - -#define PCI_VENDOR_ID_TOSHIBA_2 0x102f -#define PCI_DEVICE_ID_TOSHIBA_SCC_PCIEXC_BRIDGE 0x01b0 -#define PCI_DEVICE_ID_TOSHIBA_SCC_EPCI_BRIDGE 0x01b1 -#define PCI_DEVICE_ID_TOSHIBA_SCC_BRIDGE 0x01b2 -#define PCI_DEVICE_ID_TOSHIBA_SCC_GBE 0x01b3 -#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA 0x01b4 -#define PCI_DEVICE_ID_TOSHIBA_SCC_USB2 0x01b5 -#define PCI_DEVICE_ID_TOSHIBA_SCC_USB 0x01b6 -#define PCI_DEVICE_ID_TOSHIBA_SCC_ENCDEC 0x01b7 - -#define SCC_EPCI_REG 0x0000d000 - -/* EPCI registers */ -#define SCC_EPCI_CNF10_REG 0x010 -#define SCC_EPCI_CNF14_REG 0x014 -#define SCC_EPCI_CNF18_REG 0x018 -#define SCC_EPCI_PVBAT 0x100 -#define SCC_EPCI_VPMBAT 0x104 -#define SCC_EPCI_VPIBAT 0x108 -#define SCC_EPCI_VCSR 0x110 -#define SCC_EPCI_VIENAB 0x114 -#define SCC_EPCI_VISTAT 0x118 -#define SCC_EPCI_VRDCOUNT 0x124 -#define SCC_EPCI_BAM0 0x12c -#define SCC_EPCI_BAM1 0x134 -#define SCC_EPCI_BAM2 0x13c -#define SCC_EPCI_IADR 0x164 -#define SCC_EPCI_CLKRST 0x800 -#define SCC_EPCI_INTSET 0x804 -#define SCC_EPCI_STATUS 0x808 -#define SCC_EPCI_ABTSET 0x80c -#define SCC_EPCI_WATRP 0x810 -#define SCC_EPCI_DUMYRADR 0x814 -#define SCC_EPCI_SWRESP 0x818 -#define SCC_EPCI_CNTOPT 0x81c -#define SCC_EPCI_ECMODE 0xf00 -#define SCC_EPCI_IOM_AC_NUM 5 -#define SCC_EPCI_IOM_ACTE(n) (0xf10 + (n) * 4) -#define SCC_EPCI_IOT_AC_NUM 4 -#define SCC_EPCI_IOT_ACTE(n) (0xf30 + (n) * 4) -#define SCC_EPCI_MAEA 0xf50 -#define SCC_EPCI_MAEC 0xf54 -#define SCC_EPCI_CKCTRL 0xff0 - -/* bits for SCC_EPCI_VCSR */ -#define SCC_EPCI_VCSR_FRE 0x00020000 -#define SCC_EPCI_VCSR_FWE 0x00010000 -#define SCC_EPCI_VCSR_DR 0x00000400 -#define SCC_EPCI_VCSR_SR 0x00000008 -#define SCC_EPCI_VCSR_AT 0x00000004 - -/* bits for SCC_EPCI_VIENAB/SCC_EPCI_VISTAT */ -#define SCC_EPCI_VISTAT_PMPE 0x00000008 -#define SCC_EPCI_VISTAT_PMFE 0x00000004 -#define SCC_EPCI_VISTAT_PRA 0x00000002 -#define SCC_EPCI_VISTAT_PRD 0x00000001 -#define SCC_EPCI_VISTAT_ALL 0x0000000f - -#define SCC_EPCI_VIENAB_PMPEE 0x00000008 -#define SCC_EPCI_VIENAB_PMFEE 0x00000004 -#define SCC_EPCI_VIENAB_PRA 0x00000002 -#define SCC_EPCI_VIENAB_PRD 0x00000001 -#define SCC_EPCI_VIENAB_ALL 0x0000000f - -/* bits for SCC_EPCI_CLKRST */ -#define SCC_EPCI_CLKRST_CKS_MASK 0x00030000 -#define SCC_EPCI_CLKRST_CKS_2 0x00000000 -#define SCC_EPCI_CLKRST_CKS_4 0x00010000 -#define SCC_EPCI_CLKRST_CKS_8 0x00020000 -#define SCC_EPCI_CLKRST_PCICRST 0x00000400 -#define SCC_EPCI_CLKRST_BC 0x00000200 -#define SCC_EPCI_CLKRST_PCIRST 0x00000100 -#define SCC_EPCI_CLKRST_PCKEN 0x00000001 - -/* bits for SCC_EPCI_INTSET/SCC_EPCI_STATUS */ -#define SCC_EPCI_INT_2M 0x01000000 -#define SCC_EPCI_INT_RERR 0x00200000 -#define SCC_EPCI_INT_SERR 0x00100000 -#define SCC_EPCI_INT_PRTER 0x00080000 -#define SCC_EPCI_INT_SER 0x00040000 -#define SCC_EPCI_INT_PER 0x00020000 -#define SCC_EPCI_INT_PAI 0x00010000 -#define SCC_EPCI_INT_1M 0x00000100 -#define SCC_EPCI_INT_PME 0x00000010 -#define SCC_EPCI_INT_INTD 0x00000008 -#define SCC_EPCI_INT_INTC 0x00000004 -#define SCC_EPCI_INT_INTB 0x00000002 -#define SCC_EPCI_INT_INTA 0x00000001 -#define SCC_EPCI_INT_DEVINT 0x0000000f -#define SCC_EPCI_INT_ALL 0x003f001f -#define SCC_EPCI_INT_ALLERR 0x003f0000 - -/* bits for SCC_EPCI_CKCTRL */ -#define SCC_EPCI_CKCTRL_CRST0 0x00010000 -#define SCC_EPCI_CKCTRL_CRST1 0x00020000 -#define SCC_EPCI_CKCTRL_OCLKEN 0x00000100 -#define SCC_EPCI_CKCTRL_LCLKEN 0x00000001 - -#define SCC_EPCI_IDSEL_AD_TO_SLOT(ad) ((ad) - 10) -#define SCC_EPCI_MAX_DEVNU SCC_EPCI_IDSEL_AD_TO_SLOT(32) - -/* bits for SCC_EPCI_CNTOPT */ -#define SCC_EPCI_CNTOPT_O2PMB 0x00000002 - -/* SCC PCIEXC SMMIO registers */ -#define PEXCADRS 0x000 -#define PEXCWDATA 0x004 -#define PEXCRDATA 0x008 -#define PEXDADRS 0x010 -#define PEXDCMND 0x014 -#define PEXDWDATA 0x018 -#define PEXDRDATA 0x01c -#define PEXREQID 0x020 -#define PEXTIDMAP 0x024 -#define PEXINTMASK 0x028 -#define PEXINTSTS 0x02c -#define PEXAERRMASK 0x030 -#define PEXAERRSTS 0x034 -#define PEXPRERRMASK 0x040 -#define PEXPRERRSTS 0x044 -#define PEXPRERRID01 0x048 -#define PEXPRERRID23 0x04c -#define PEXVDMASK 0x050 -#define PEXVDSTS 0x054 -#define PEXRCVCPLIDA 0x060 -#define PEXLENERRIDA 0x068 -#define PEXPHYPLLST 0x070 -#define PEXDMRDEN0 0x100 -#define PEXDMRDADR0 0x104 -#define PEXDMRDENX 0x110 -#define PEXDMRDADRX 0x114 -#define PEXECMODE 0xf00 -#define PEXMAEA(n) (0xf50 + (8 * n)) -#define PEXMAEC(n) (0xf54 + (8 * n)) -#define PEXCCRCTRL 0xff0 - -/* SCC PCIEXC bits and shifts for PEXCADRS */ -#define PEXCADRS_BYTE_EN_SHIFT 20 -#define PEXCADRS_CMD_SHIFT 16 -#define PEXCADRS_CMD_READ (0xa << PEXCADRS_CMD_SHIFT) -#define PEXCADRS_CMD_WRITE (0xb << PEXCADRS_CMD_SHIFT) - -/* SCC PCIEXC shifts for PEXDADRS */ -#define PEXDADRS_BUSNO_SHIFT 20 -#define PEXDADRS_DEVNO_SHIFT 15 -#define PEXDADRS_FUNCNO_SHIFT 12 - -/* SCC PCIEXC bits and shifts for PEXDCMND */ -#define PEXDCMND_BYTE_EN_SHIFT 4 -#define PEXDCMND_IO_READ 0x2 -#define PEXDCMND_IO_WRITE 0x3 -#define PEXDCMND_CONFIG_READ 0xa -#define PEXDCMND_CONFIG_WRITE 0xb - -/* SCC PCIEXC bits for PEXPHYPLLST */ -#define PEXPHYPLLST_PEXPHYAPLLST 0x00000001 - -/* SCC PCIEXC bits for PEXECMODE */ -#define PEXECMODE_ALL_THROUGH 0x00000000 -#define PEXECMODE_ALL_8BIT 0x00550155 -#define PEXECMODE_ALL_16BIT 0x00aa02aa - -/* SCC PCIEXC bits for PEXCCRCTRL */ -#define PEXCCRCTRL_PEXIPCOREEN 0x00040000 -#define PEXCCRCTRL_PEXIPCONTEN 0x00020000 -#define PEXCCRCTRL_PEXPHYPLLEN 0x00010000 -#define PEXCCRCTRL_PCIEXCAOCKEN 0x00000100 - -/* SCC PCIEXC port configuration registers */ -#define PEXTCERRCHK 0x21c -#define PEXTAMAPB0 0x220 -#define PEXTAMAPL0 0x224 -#define PEXTAMAPB(n) (PEXTAMAPB0 + 8 * (n)) -#define PEXTAMAPL(n) (PEXTAMAPL0 + 8 * (n)) -#define PEXCHVC0P 0x500 -#define PEXCHVC0NP 0x504 -#define PEXCHVC0C 0x508 -#define PEXCDVC0P 0x50c -#define PEXCDVC0NP 0x510 -#define PEXCDVC0C 0x514 -#define PEXCHVCXP 0x518 -#define PEXCHVCXNP 0x51c -#define PEXCHVCXC 0x520 -#define PEXCDVCXP 0x524 -#define PEXCDVCXNP 0x528 -#define PEXCDVCXC 0x52c -#define PEXCTTRG 0x530 -#define PEXTSCTRL 0x700 -#define PEXTSSTS 0x704 -#define PEXSKPCTRL 0x708 - -/* UHC registers */ -#define SCC_UHC_CKRCTRL 0xff0 -#define SCC_UHC_ECMODE 0xf00 - -/* bits for SCC_UHC_CKRCTRL */ -#define SCC_UHC_F48MCKLEN 0x00000001 -#define SCC_UHC_P_SUSPEND 0x00000002 -#define SCC_UHC_PHY_SUSPEND_SEL 0x00000004 -#define SCC_UHC_HCLKEN 0x00000100 -#define SCC_UHC_USBEN 0x00010000 -#define SCC_UHC_USBCEN 0x00020000 -#define SCC_UHC_PHYEN 0x00040000 - -/* bits for SCC_UHC_ECMODE */ -#define SCC_UHC_ECMODE_BY_BYTE 0x00000555 -#define SCC_UHC_ECMODE_BY_WORD 0x00000aaa - -#endif /* _CELLEB_SCC_H */ diff --git a/arch/powerpc/platforms/cell/celleb_scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c deleted file mode 100644 index 9438bbed402f..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_epci.c +++ /dev/null @@ -1,428 +0,0 @@ -/* - * Support for SCC external PCI - * - * (C) Copyright 2004-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/pci.h> -#include <linux/init.h> -#include <linux/pci_regs.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -#include "celleb_scc.h" -#include "celleb_pci.h" - -#define MAX_PCI_DEVICES 32 -#define MAX_PCI_FUNCTIONS 8 - -#define iob() __asm__ __volatile__("eieio; sync":::"memory") - -static inline PCI_IO_ADDR celleb_epci_get_epci_base( - struct pci_controller *hose) -{ - /* - * Note: - * Celleb epci uses cfg_addr as a base address for - * epci control registers. - */ - - return hose->cfg_addr; -} - -static inline PCI_IO_ADDR celleb_epci_get_epci_cfg( - struct pci_controller *hose) -{ - /* - * Note: - * Celleb epci uses cfg_data as a base address for - * configuration area for epci devices. - */ - - return hose->cfg_data; -} - -static inline void clear_and_disable_master_abort_interrupt( - struct pci_controller *hose) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR reg; - epci_base = celleb_epci_get_epci_base(hose); - reg = epci_base + PCI_COMMAND; - out_be32(reg, in_be32(reg) | (PCI_STATUS_REC_MASTER_ABORT << 16)); -} - -static int celleb_epci_check_abort(struct pci_controller *hose, - PCI_IO_ADDR addr) -{ - PCI_IO_ADDR reg; - PCI_IO_ADDR epci_base; - u32 val; - - iob(); - epci_base = celleb_epci_get_epci_base(hose); - - reg = epci_base + PCI_COMMAND; - val = in_be32(reg); - - if (val & (PCI_STATUS_REC_MASTER_ABORT << 16)) { - out_be32(reg, - (val & 0xffff) | (PCI_STATUS_REC_MASTER_ABORT << 16)); - - /* clear PCI Controller error, FRE, PMFE */ - reg = epci_base + SCC_EPCI_STATUS; - out_be32(reg, SCC_EPCI_INT_PAI); - - reg = epci_base + SCC_EPCI_VCSR; - val = in_be32(reg) & 0xffff; - val |= SCC_EPCI_VCSR_FRE; - out_be32(reg, val); - - reg = epci_base + SCC_EPCI_VISTAT; - out_be32(reg, SCC_EPCI_VISTAT_PMFE); - return PCIBIOS_DEVICE_NOT_FOUND; - } - - return PCIBIOS_SUCCESSFUL; -} - -static PCI_IO_ADDR celleb_epci_make_config_addr(struct pci_bus *bus, - struct pci_controller *hose, unsigned int devfn, int where) -{ - PCI_IO_ADDR addr; - - if (bus != hose->bus) - addr = celleb_epci_get_epci_cfg(hose) + - (((bus->number & 0xff) << 16) - | ((devfn & 0xff) << 8) - | (where & 0xff) - | 0x01000000); - else - addr = celleb_epci_get_epci_cfg(hose) + - (((devfn & 0xff) << 8) | (where & 0xff)); - - pr_debug("EPCI: config_addr = 0x%p\n", addr); - - return addr; -} - -static int celleb_epci_read_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *val) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR addr; - struct pci_controller *hose = pci_bus_to_host(bus); - - /* allignment check */ - BUG_ON(where % size); - - if (!celleb_epci_get_epci_cfg(hose)) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == hose->first_busno && devfn == 0) { - /* EPCI controller self */ - - epci_base = celleb_epci_get_epci_base(hose); - addr = epci_base + where; - - switch (size) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_be16(addr); - break; - case 4: - *val = in_be32(addr); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - - } else { - - clear_and_disable_master_abort_interrupt(hose); - addr = celleb_epci_make_config_addr(bus, hose, devfn, where); - - switch (size) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_le16(addr); - break; - case 4: - *val = in_le32(addr); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - } - - pr_debug("EPCI: " - "addr=0x%p, devfn=0x%x, where=0x%x, size=0x%x, val=0x%x\n", - addr, devfn, where, size, *val); - - return celleb_epci_check_abort(hose, NULL); -} - -static int celleb_epci_write_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 val) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR addr; - struct pci_controller *hose = pci_bus_to_host(bus); - - /* allignment check */ - BUG_ON(where % size); - - if (!celleb_epci_get_epci_cfg(hose)) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == hose->first_busno && devfn == 0) { - /* EPCI controller self */ - - epci_base = celleb_epci_get_epci_base(hose); - addr = epci_base + where; - - switch (size) { - case 1: - out_8(addr, val); - break; - case 2: - out_be16(addr, val); - break; - case 4: - out_be32(addr, val); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - - } else { - - clear_and_disable_master_abort_interrupt(hose); - addr = celleb_epci_make_config_addr(bus, hose, devfn, where); - - switch (size) { - case 1: - out_8(addr, val); - break; - case 2: - out_le16(addr, val); - break; - case 4: - out_le32(addr, val); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - } - - return celleb_epci_check_abort(hose, addr); -} - -struct pci_ops celleb_epci_ops = { - .read = celleb_epci_read_config, - .write = celleb_epci_write_config, -}; - -/* to be moved in FW */ -static int __init celleb_epci_init(struct pci_controller *hose) -{ - u32 val; - PCI_IO_ADDR reg; - PCI_IO_ADDR epci_base; - int hwres = 0; - - epci_base = celleb_epci_get_epci_base(hose); - - /* PCI core reset(Internal bus and PCI clock) */ - reg = epci_base + SCC_EPCI_CKCTRL; - val = in_be32(reg); - if (val == 0x00030101) - hwres = 1; - else { - val &= ~(SCC_EPCI_CKCTRL_CRST0 | SCC_EPCI_CKCTRL_CRST1); - out_be32(reg, val); - - /* set PCI core clock */ - val = in_be32(reg); - val |= (SCC_EPCI_CKCTRL_OCLKEN | SCC_EPCI_CKCTRL_LCLKEN); - out_be32(reg, val); - - /* release PCI core reset (internal bus) */ - val = in_be32(reg); - val |= SCC_EPCI_CKCTRL_CRST0; - out_be32(reg, val); - - /* set PCI clock select */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val &= ~SCC_EPCI_CLKRST_CKS_MASK; - val |= SCC_EPCI_CLKRST_CKS_2; - out_be32(reg, val); - - /* set arbiter */ - reg = epci_base + SCC_EPCI_ABTSET; - out_be32(reg, 0x0f1f001f); /* temporary value */ - - /* buffer on */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_BC; - out_be32(reg, val); - - /* PCI clock enable */ - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_PCKEN; - out_be32(reg, val); - - /* release PCI core reset (all) */ - reg = epci_base + SCC_EPCI_CKCTRL; - val = in_be32(reg); - val |= (SCC_EPCI_CKCTRL_CRST0 | SCC_EPCI_CKCTRL_CRST1); - out_be32(reg, val); - - /* set base translation registers. (already set by Beat) */ - - /* set base address masks. (already set by Beat) */ - } - - /* release interrupt masks and clear all interrupts */ - reg = epci_base + SCC_EPCI_INTSET; - out_be32(reg, 0x013f011f); /* all interrupts enable */ - reg = epci_base + SCC_EPCI_VIENAB; - val = SCC_EPCI_VIENAB_PMPEE | SCC_EPCI_VIENAB_PMFEE; - out_be32(reg, val); - reg = epci_base + SCC_EPCI_STATUS; - out_be32(reg, 0xffffffff); - reg = epci_base + SCC_EPCI_VISTAT; - out_be32(reg, 0xffffffff); - - /* disable PCI->IB address translation */ - reg = epci_base + SCC_EPCI_VCSR; - val = in_be32(reg); - val &= ~(SCC_EPCI_VCSR_DR | SCC_EPCI_VCSR_AT); - out_be32(reg, val); - - /* set base addresses. (no need to set?) */ - - /* memory space, bus master enable */ - reg = epci_base + PCI_COMMAND; - val = PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; - out_be32(reg, val); - - /* endian mode setup */ - reg = epci_base + SCC_EPCI_ECMODE; - val = 0x00550155; - out_be32(reg, val); - - /* set control option */ - reg = epci_base + SCC_EPCI_CNTOPT; - val = in_be32(reg); - val |= SCC_EPCI_CNTOPT_O2PMB; - out_be32(reg, val); - - /* XXX: temporay: set registers for address conversion setup */ - reg = epci_base + SCC_EPCI_CNF10_REG; - out_be32(reg, 0x80000008); - reg = epci_base + SCC_EPCI_CNF14_REG; - out_be32(reg, 0x40000008); - - reg = epci_base + SCC_EPCI_BAM0; - out_be32(reg, 0x80000000); - reg = epci_base + SCC_EPCI_BAM1; - out_be32(reg, 0xe0000000); - - reg = epci_base + SCC_EPCI_PVBAT; - out_be32(reg, 0x80000000); - - if (!hwres) { - /* release external PCI reset */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_PCIRST; - out_be32(reg, val); - } - - return 0; -} - -static int __init celleb_setup_epci(struct device_node *node, - struct pci_controller *hose) -{ - struct resource r; - - pr_debug("PCI: celleb_setup_epci()\n"); - - /* - * Note: - * Celleb epci uses cfg_addr and cfg_data member of - * pci_controller structure in irregular way. - * - * cfg_addr is used to map for control registers of - * celleb epci. - * - * cfg_data is used for configuration area of devices - * on Celleb epci buses. - */ - - if (of_address_to_resource(node, 0, &r)) - goto error; - hose->cfg_addr = ioremap(r.start, resource_size(&r)); - if (!hose->cfg_addr) - goto error; - pr_debug("EPCI: cfg_addr map 0x%016llx->0x%016lx + 0x%016llx\n", - r.start, (unsigned long)hose->cfg_addr, resource_size(&r)); - - if (of_address_to_resource(node, 2, &r)) - goto error; - hose->cfg_data = ioremap(r.start, resource_size(&r)); - if (!hose->cfg_data) - goto error; - pr_debug("EPCI: cfg_data map 0x%016llx->0x%016lx + 0x%016llx\n", - r.start, (unsigned long)hose->cfg_data, resource_size(&r)); - - hose->ops = &celleb_epci_ops; - celleb_epci_init(hose); - - return 0; - -error: - if (hose->cfg_addr) - iounmap(hose->cfg_addr); - - if (hose->cfg_data) - iounmap(hose->cfg_data); - return 1; -} - -struct celleb_phb_spec celleb_epci_spec __initdata = { - .setup = celleb_setup_epci, - .ops = &spiderpci_ops, - .iowa_init = &spiderpci_iowa_init, - .iowa_data = (void *)0, -}; diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c deleted file mode 100644 index 94170e4f2ce7..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ /dev/null @@ -1,538 +0,0 @@ -/* - * Support for Celleb PCI-Express. - * - * (C) Copyright 2007-2008 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/string.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/interrupt.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/iommu.h> -#include <asm/byteorder.h> - -#include "celleb_scc.h" -#include "celleb_pci.h" - -#define PEX_IN(base, off) in_be32((void __iomem *)(base) + (off)) -#define PEX_OUT(base, off, data) out_be32((void __iomem *)(base) + (off), (data)) - -static void scc_pciex_io_flush(struct iowa_bus *bus) -{ - (void)PEX_IN(bus->phb->cfg_addr, PEXDMRDEN0); -} - -/* - * Memory space access to device on PCIEX - */ -#define PCIEX_MMIO_READ(name, ret) \ -static ret scc_pciex_##name(const PCI_IO_ADDR addr) \ -{ \ - ret val = __do_##name(addr); \ - scc_pciex_io_flush(iowa_mem_find_bus(addr)); \ - return val; \ -} - -#define PCIEX_MMIO_READ_STR(name) \ -static void scc_pciex_##name(const PCI_IO_ADDR addr, void *buf, \ - unsigned long count) \ -{ \ - __do_##name(addr, buf, count); \ - scc_pciex_io_flush(iowa_mem_find_bus(addr)); \ -} - -PCIEX_MMIO_READ(readb, u8) -PCIEX_MMIO_READ(readw, u16) -PCIEX_MMIO_READ(readl, u32) -PCIEX_MMIO_READ(readq, u64) -PCIEX_MMIO_READ(readw_be, u16) -PCIEX_MMIO_READ(readl_be, u32) -PCIEX_MMIO_READ(readq_be, u64) -PCIEX_MMIO_READ_STR(readsb) -PCIEX_MMIO_READ_STR(readsw) -PCIEX_MMIO_READ_STR(readsl) - -static void scc_pciex_memcpy_fromio(void *dest, const PCI_IO_ADDR src, - unsigned long n) -{ - __do_memcpy_fromio(dest, src, n); - scc_pciex_io_flush(iowa_mem_find_bus(src)); -} - -/* - * I/O port access to devices on PCIEX. - */ - -static inline unsigned long get_bus_address(struct pci_controller *phb, - unsigned long port) -{ - return port - ((unsigned long)(phb->io_base_virt) - _IO_BASE); -} - -static u32 scc_pciex_read_port(struct pci_controller *phb, - unsigned long port, int size) -{ - unsigned int byte_enable; - unsigned int cmd, shift; - unsigned long addr; - u32 data, ret; - - BUG_ON(((port & 0x3ul) + size) > 4); - - addr = get_bus_address(phb, port); - shift = addr & 0x3ul; - byte_enable = ((1 << size) - 1) << shift; - cmd = PEXDCMND_IO_READ | (byte_enable << PEXDCMND_BYTE_EN_SHIFT); - PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul)); - PEX_OUT(phb->cfg_addr, PEXDCMND, cmd); - data = PEX_IN(phb->cfg_addr, PEXDRDATA); - ret = (data >> (shift * 8)) & (0xFFFFFFFF >> ((4 - size) * 8)); - - pr_debug("PCIEX:PIO READ:port=0x%lx, addr=0x%lx, size=%d, be=%x," - " cmd=%x, data=%x, ret=%x\n", port, addr, size, byte_enable, - cmd, data, ret); - - return ret; -} - -static void scc_pciex_write_port(struct pci_controller *phb, - unsigned long port, int size, u32 val) -{ - unsigned int byte_enable; - unsigned int cmd, shift; - unsigned long addr; - u32 data; - - BUG_ON(((port & 0x3ul) + size) > 4); - - addr = get_bus_address(phb, port); - shift = addr & 0x3ul; - byte_enable = ((1 << size) - 1) << shift; - cmd = PEXDCMND_IO_WRITE | (byte_enable << PEXDCMND_BYTE_EN_SHIFT); - data = (val & (0xFFFFFFFF >> (4 - size) * 8)) << (shift * 8); - PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul)); - PEX_OUT(phb->cfg_addr, PEXDCMND, cmd); - PEX_OUT(phb->cfg_addr, PEXDWDATA, data); - - pr_debug("PCIEX:PIO WRITE:port=0x%lx, addr=%lx, size=%d, val=%x," - " be=%x, cmd=%x, data=%x\n", port, addr, size, val, - byte_enable, cmd, data); -} - -static u8 __scc_pciex_inb(struct pci_controller *phb, unsigned long port) -{ - return (u8)scc_pciex_read_port(phb, port, 1); -} - -static u16 __scc_pciex_inw(struct pci_controller *phb, unsigned long port) -{ - u32 data; - if ((port & 0x3ul) < 3) - data = scc_pciex_read_port(phb, port, 2); - else { - u32 d1 = scc_pciex_read_port(phb, port, 1); - u32 d2 = scc_pciex_read_port(phb, port + 1, 1); - data = d1 | (d2 << 8); - } - return (u16)data; -} - -static u32 __scc_pciex_inl(struct pci_controller *phb, unsigned long port) -{ - unsigned int mod = port & 0x3ul; - u32 data; - if (mod == 0) - data = scc_pciex_read_port(phb, port, 4); - else { - u32 d1 = scc_pciex_read_port(phb, port, 4 - mod); - u32 d2 = scc_pciex_read_port(phb, port + 1, mod); - data = d1 | (d2 << (mod * 8)); - } - return data; -} - -static void __scc_pciex_outb(struct pci_controller *phb, - u8 val, unsigned long port) -{ - scc_pciex_write_port(phb, port, 1, (u32)val); -} - -static void __scc_pciex_outw(struct pci_controller *phb, - u16 val, unsigned long port) -{ - if ((port & 0x3ul) < 3) - scc_pciex_write_port(phb, port, 2, (u32)val); - else { - u32 d1 = val & 0x000000FF; - u32 d2 = (val & 0x0000FF00) >> 8; - scc_pciex_write_port(phb, port, 1, d1); - scc_pciex_write_port(phb, port + 1, 1, d2); - } -} - -static void __scc_pciex_outl(struct pci_controller *phb, - u32 val, unsigned long port) -{ - unsigned int mod = port & 0x3ul; - if (mod == 0) - scc_pciex_write_port(phb, port, 4, val); - else { - u32 d1 = val & (0xFFFFFFFFul >> (mod * 8)); - u32 d2 = val >> ((4 - mod) * 8); - scc_pciex_write_port(phb, port, 4 - mod, d1); - scc_pciex_write_port(phb, port + 1, mod, d2); - } -} - -#define PCIEX_PIO_FUNC(size, name) \ -static u##size scc_pciex_in##name(unsigned long port) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(port); \ - u##size data = __scc_pciex_in##name(bus->phb, port); \ - scc_pciex_io_flush(bus); \ - return data; \ -} \ -static void scc_pciex_ins##name(unsigned long p, void *b, unsigned long c) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(p); \ - __le##size *dst = b; \ - for (; c != 0; c--, dst++) \ - *dst = cpu_to_le##size(__scc_pciex_in##name(bus->phb, p)); \ - scc_pciex_io_flush(bus); \ -} \ -static void scc_pciex_out##name(u##size val, unsigned long port) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(port); \ - __scc_pciex_out##name(bus->phb, val, port); \ -} \ -static void scc_pciex_outs##name(unsigned long p, const void *b, \ - unsigned long c) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(p); \ - const __le##size *src = b; \ - for (; c != 0; c--, src++) \ - __scc_pciex_out##name(bus->phb, le##size##_to_cpu(*src), p); \ -} -#define __le8 u8 -#define cpu_to_le8(x) (x) -#define le8_to_cpu(x) (x) -PCIEX_PIO_FUNC(8, b) -PCIEX_PIO_FUNC(16, w) -PCIEX_PIO_FUNC(32, l) - -static struct ppc_pci_io scc_pciex_ops = { - .readb = scc_pciex_readb, - .readw = scc_pciex_readw, - .readl = scc_pciex_readl, - .readq = scc_pciex_readq, - .readw_be = scc_pciex_readw_be, - .readl_be = scc_pciex_readl_be, - .readq_be = scc_pciex_readq_be, - .readsb = scc_pciex_readsb, - .readsw = scc_pciex_readsw, - .readsl = scc_pciex_readsl, - .memcpy_fromio = scc_pciex_memcpy_fromio, - .inb = scc_pciex_inb, - .inw = scc_pciex_inw, - .inl = scc_pciex_inl, - .outb = scc_pciex_outb, - .outw = scc_pciex_outw, - .outl = scc_pciex_outl, - .insb = scc_pciex_insb, - .insw = scc_pciex_insw, - .insl = scc_pciex_insl, - .outsb = scc_pciex_outsb, - .outsw = scc_pciex_outsw, - .outsl = scc_pciex_outsl, -}; - -static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data) -{ - dma_addr_t dummy_page_da; - void *dummy_page_va; - - dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!dummy_page_va) { - pr_err("PCIEX:Alloc dummy_page_va failed\n"); - return -1; - } - - dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va, - PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(bus->phb->parent, dummy_page_da)) { - pr_err("PCIEX:Map dummy page failed.\n"); - kfree(dummy_page_va); - return -1; - } - - PEX_OUT(bus->phb->cfg_addr, PEXDMRDADR0, dummy_page_da); - - return 0; -} - -/* - * config space access - */ -#define MK_PEXDADRS(bus_no, dev_no, func_no, addr) \ - ((uint32_t)(((addr) & ~0x3UL) | \ - ((bus_no) << PEXDADRS_BUSNO_SHIFT) | \ - ((dev_no) << PEXDADRS_DEVNO_SHIFT) | \ - ((func_no) << PEXDADRS_FUNCNO_SHIFT))) - -#define MK_PEXDCMND_BYTE_EN(addr, size) \ - ((((0x1 << (size))-1) << ((addr) & 0x3)) << PEXDCMND_BYTE_EN_SHIFT) -#define MK_PEXDCMND(cmd, addr, size) ((cmd) | MK_PEXDCMND_BYTE_EN(addr, size)) - -static uint32_t config_read_pciex_dev(unsigned int __iomem *base, - uint64_t bus_no, uint64_t dev_no, uint64_t func_no, - uint64_t off, uint64_t size) -{ - uint32_t ret; - uint32_t addr, cmd; - - addr = MK_PEXDADRS(bus_no, dev_no, func_no, off); - cmd = MK_PEXDCMND(PEXDCMND_CONFIG_READ, off, size); - PEX_OUT(base, PEXDADRS, addr); - PEX_OUT(base, PEXDCMND, cmd); - ret = (PEX_IN(base, PEXDRDATA) - >> ((off & (4-size)) * 8)) & ((0x1 << (size * 8)) - 1); - return ret; -} - -static void config_write_pciex_dev(unsigned int __iomem *base, uint64_t bus_no, - uint64_t dev_no, uint64_t func_no, uint64_t off, uint64_t size, - uint32_t data) -{ - uint32_t addr, cmd; - - addr = MK_PEXDADRS(bus_no, dev_no, func_no, off); - cmd = MK_PEXDCMND(PEXDCMND_CONFIG_WRITE, off, size); - PEX_OUT(base, PEXDADRS, addr); - PEX_OUT(base, PEXDCMND, cmd); - PEX_OUT(base, PEXDWDATA, - (data & ((0x1 << (size * 8)) - 1)) << ((off & (4-size)) * 8)); -} - -#define MK_PEXCADRS_BYTE_EN(off, len) \ - ((((0x1 << (len)) - 1) << ((off) & 0x3)) << PEXCADRS_BYTE_EN_SHIFT) -#define MK_PEXCADRS(cmd, addr, size) \ - ((cmd) | MK_PEXCADRS_BYTE_EN(addr, size) | ((addr) & ~0x3)) -static uint32_t config_read_pciex_rc(unsigned int __iomem *base, - uint32_t where, uint32_t size) -{ - PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_READ, where, size)); - return (PEX_IN(base, PEXCRDATA) - >> ((where & (4 - size)) * 8)) & ((0x1 << (size * 8)) - 1); -} - -static void config_write_pciex_rc(unsigned int __iomem *base, uint32_t where, - uint32_t size, uint32_t val) -{ - uint32_t data; - - data = (val & ((0x1 << (size * 8)) - 1)) << ((where & (4 - size)) * 8); - PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_WRITE, where, size)); - PEX_OUT(base, PEXCWDATA, data); -} - -/* Interfaces */ -/* Note: Work-around - * On SCC PCIEXC, one device is seen on all 32 dev_no. - * As SCC PCIEXC can have only one device on the bus, we look only one dev_no. - * (dev_no = 1) - */ -static int scc_pciex_read_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, unsigned int *val) -{ - struct pci_controller *phb = pci_bus_to_host(bus); - - if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1) { - *val = ~0; - return PCIBIOS_DEVICE_NOT_FOUND; - } - - if (bus->number == 0 && PCI_SLOT(devfn) == 0) - *val = config_read_pciex_rc(phb->cfg_addr, where, size); - else - *val = config_read_pciex_dev(phb->cfg_addr, bus->number, - PCI_SLOT(devfn), PCI_FUNC(devfn), where, size); - - return PCIBIOS_SUCCESSFUL; -} - -static int scc_pciex_write_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, unsigned int val) -{ - struct pci_controller *phb = pci_bus_to_host(bus); - - if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == 0 && PCI_SLOT(devfn) == 0) - config_write_pciex_rc(phb->cfg_addr, where, size, val); - else - config_write_pciex_dev(phb->cfg_addr, bus->number, - PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val); - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops scc_pciex_pci_ops = { - .read = scc_pciex_read_config, - .write = scc_pciex_write_config, -}; - -static void pciex_clear_intr_all(unsigned int __iomem *base) -{ - PEX_OUT(base, PEXAERRSTS, 0xffffffff); - PEX_OUT(base, PEXPRERRSTS, 0xffffffff); - PEX_OUT(base, PEXINTSTS, 0xffffffff); -} - -#if 0 -static void pciex_disable_intr_all(unsigned int *base) -{ - PEX_OUT(base, PEXINTMASK, 0x0); - PEX_OUT(base, PEXAERRMASK, 0x0); - PEX_OUT(base, PEXPRERRMASK, 0x0); - PEX_OUT(base, PEXVDMASK, 0x0); -} -#endif - -static void pciex_enable_intr_all(unsigned int __iomem *base) -{ - PEX_OUT(base, PEXINTMASK, 0x0000e7f1); - PEX_OUT(base, PEXAERRMASK, 0x03ff01ff); - PEX_OUT(base, PEXPRERRMASK, 0x0001010f); - PEX_OUT(base, PEXVDMASK, 0x00000001); -} - -static void pciex_check_status(unsigned int __iomem *base) -{ - uint32_t err = 0; - uint32_t intsts, aerr, prerr, rcvcp, lenerr; - uint32_t maea, maec; - - intsts = PEX_IN(base, PEXINTSTS); - aerr = PEX_IN(base, PEXAERRSTS); - prerr = PEX_IN(base, PEXPRERRSTS); - rcvcp = PEX_IN(base, PEXRCVCPLIDA); - lenerr = PEX_IN(base, PEXLENERRIDA); - - if (intsts || aerr || prerr || rcvcp || lenerr) - err = 1; - - pr_info("PCEXC interrupt!!\n"); - pr_info("PEXINTSTS :0x%08x\n", intsts); - pr_info("PEXAERRSTS :0x%08x\n", aerr); - pr_info("PEXPRERRSTS :0x%08x\n", prerr); - pr_info("PEXRCVCPLIDA :0x%08x\n", rcvcp); - pr_info("PEXLENERRIDA :0x%08x\n", lenerr); - - /* print detail of Protection Error */ - if (intsts & 0x00004000) { - uint32_t i, n; - for (i = 0; i < 4; i++) { - n = 1 << i; - if (prerr & n) { - maea = PEX_IN(base, PEXMAEA(i)); - maec = PEX_IN(base, PEXMAEC(i)); - pr_info("PEXMAEC%d :0x%08x\n", i, maec); - pr_info("PEXMAEA%d :0x%08x\n", i, maea); - } - } - } - - if (err) - pciex_clear_intr_all(base); -} - -static irqreturn_t pciex_handle_internal_irq(int irq, void *dev_id) -{ - struct pci_controller *phb = dev_id; - - pr_debug("PCIEX:pciex_handle_internal_irq(irq=%d)\n", irq); - - BUG_ON(phb->cfg_addr == NULL); - - pciex_check_status(phb->cfg_addr); - - return IRQ_HANDLED; -} - -static __init int celleb_setup_pciex(struct device_node *node, - struct pci_controller *phb) -{ - struct resource r; - int virq; - - /* SMMIO registers; used inside this file */ - if (of_address_to_resource(node, 0, &r)) { - pr_err("PCIEXC:Failed to get config resource.\n"); - return 1; - } - phb->cfg_addr = ioremap(r.start, resource_size(&r)); - if (!phb->cfg_addr) { - pr_err("PCIEXC:Failed to remap SMMIO region.\n"); - return 1; - } - - /* Not use cfg_data, cmd and data regs are near address reg */ - phb->cfg_data = NULL; - - /* set pci_ops */ - phb->ops = &scc_pciex_pci_ops; - - /* internal interrupt handler */ - virq = irq_of_parse_and_map(node, 1); - if (!virq) { - pr_err("PCIEXC:Failed to map irq\n"); - goto error; - } - if (request_irq(virq, pciex_handle_internal_irq, - 0, "pciex", (void *)phb)) { - pr_err("PCIEXC:Failed to request irq\n"); - goto error; - } - - /* enable all interrupts */ - pciex_clear_intr_all(phb->cfg_addr); - pciex_enable_intr_all(phb->cfg_addr); - /* MSI: TBD */ - - return 0; - -error: - phb->cfg_data = NULL; - if (phb->cfg_addr) - iounmap(phb->cfg_addr); - phb->cfg_addr = NULL; - return 1; -} - -struct celleb_phb_spec celleb_pciex_spec __initdata = { - .setup = celleb_setup_pciex, - .ops = &scc_pciex_ops, - .iowa_init = &scc_pciex_iowa_init, -}; diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c deleted file mode 100644 index c8eb57193826..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_sio.c +++ /dev/null @@ -1,99 +0,0 @@ -/* - * setup serial port in SCC - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/tty.h> -#include <linux/serial.h> -#include <linux/serial_core.h> -#include <linux/console.h> - -#include <asm/io.h> -#include <asm/prom.h> - -/* sio irq0=0xb00010022 irq0=0xb00010023 irq2=0xb00010024 - mmio=0xfff000-0x1000,0xff2000-0x1000 */ -static int txx9_serial_bitmap __initdata; - -static struct { - uint32_t offset; - uint32_t index; -} txx9_scc_tab[3] __initdata = { - { 0x300, 0 }, /* 0xFFF300 */ - { 0x400, 0 }, /* 0xFFF400 */ - { 0x800, 1 } /* 0xFF2800 */ -}; - -static int __init txx9_serial_init(void) -{ - extern int early_serial_txx9_setup(struct uart_port *port); - struct device_node *node; - int i; - struct uart_port req; - struct of_phandle_args irq; - struct resource res; - - for_each_compatible_node(node, "serial", "toshiba,sio-scc") { - for (i = 0; i < ARRAY_SIZE(txx9_scc_tab); i++) { - if (!(txx9_serial_bitmap & (1<<i))) - continue; - - if (of_irq_parse_one(node, i, &irq)) - continue; - if (of_address_to_resource(node, - txx9_scc_tab[i].index, &res)) - continue; - - memset(&req, 0, sizeof(req)); - req.line = i; - req.iotype = UPIO_MEM; - req.mapbase = res.start + txx9_scc_tab[i].offset; -#ifdef CONFIG_SERIAL_TXX9_CONSOLE - req.membase = ioremap(req.mapbase, 0x24); -#endif - req.irq = irq_create_of_mapping(&irq); - req.flags |= UPF_IOREMAP | UPF_BUGGY_UART - /*HAVE_CTS_LINE*/; - req.uartclk = 83300000; - early_serial_txx9_setup(&req); - } - } - - return 0; -} - -static int __init txx9_serial_config(char *ptr) -{ - int i; - - for (;;) { - switch (get_option(&ptr, &i)) { - default: - return 0; - case 2: - txx9_serial_bitmap |= 1 << i; - break; - case 1: - txx9_serial_bitmap |= 1 << i; - return 0; - } - } -} -__setup("txx9_serial=", txx9_serial_config); - -console_initcall(txx9_serial_init); diff --git a/arch/powerpc/platforms/cell/celleb_scc_uhc.c b/arch/powerpc/platforms/cell/celleb_scc_uhc.c deleted file mode 100644 index d63b720bfe3a..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_uhc.c +++ /dev/null @@ -1,95 +0,0 @@ -/* - * SCC (Super Companion Chip) UHC setup - * - * (C) Copyright 2006-2007 TOSHIBA 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> - -#include <asm/delay.h> -#include <asm/io.h> -#include <asm/machdep.h> - -#include "celleb_scc.h" - -#define UHC_RESET_WAIT_MAX 10000 - -static inline int uhc_clkctrl_ready(u32 val) -{ - const u32 mask = SCC_UHC_USBCEN | SCC_UHC_USBCEN; - return((val & mask) == mask); -} - -/* - * UHC(usb host controller) enable function. - * affect to both of OHCI and EHCI core module. - */ -static void enable_scc_uhc(struct pci_dev *dev) -{ - void __iomem *uhc_base; - u32 __iomem *uhc_clkctrl; - u32 __iomem *uhc_ecmode; - u32 val = 0; - int i; - - if (!machine_is(celleb_beat) && - !machine_is(celleb_native)) - return; - - uhc_base = ioremap(pci_resource_start(dev, 0), - pci_resource_len(dev, 0)); - if (!uhc_base) { - printk(KERN_ERR "failed to map UHC register base.\n"); - return; - } - uhc_clkctrl = uhc_base + SCC_UHC_CKRCTRL; - uhc_ecmode = uhc_base + SCC_UHC_ECMODE; - - /* setup for normal mode */ - val |= SCC_UHC_F48MCKLEN; - out_be32(uhc_clkctrl, val); - val |= SCC_UHC_PHY_SUSPEND_SEL; - out_be32(uhc_clkctrl, val); - udelay(10); - val |= SCC_UHC_PHYEN; - out_be32(uhc_clkctrl, val); - udelay(50); - - /* disable reset */ - val |= SCC_UHC_HCLKEN; - out_be32(uhc_clkctrl, val); - val |= (SCC_UHC_USBCEN | SCC_UHC_USBEN); - out_be32(uhc_clkctrl, val); - i = 0; - while (!uhc_clkctrl_ready(in_be32(uhc_clkctrl))) { - udelay(10); - if (i++ > UHC_RESET_WAIT_MAX) { - printk(KERN_ERR "Failed to disable UHC reset %x\n", - in_be32(uhc_clkctrl)); - break; - } - } - - /* Endian Conversion Mode for Master ALL area */ - out_be32(uhc_ecmode, SCC_UHC_ECMODE_BY_BYTE); - - iounmap(uhc_base); -} - -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA_2, - PCI_DEVICE_ID_TOSHIBA_SCC_USB, enable_scc_uhc); diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c deleted file mode 100644 index 90be8ec51686..000000000000 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ /dev/null @@ -1,243 +0,0 @@ -/* - * Celleb setup code - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/cell/setup.c: - * Copyright (C) 1995 Linus Torvalds - * Adapted from 'alpha' version by Gary Thomas - * Modified by Cort Dougan (cort@cs.nmt.edu) - * Modified by PPC64 Team, IBM Corp - * Modified by Cell Team, IBM Deutschland Entwicklung GmbH - * - * 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., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/reboot.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/irq.h> -#include <linux/seq_file.h> -#include <linux/root_dev.h> -#include <linux/console.h> -#include <linux/of_platform.h> - -#include <asm/mmu.h> -#include <asm/processor.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/cputable.h> -#include <asm/irq.h> -#include <asm/time.h> -#include <asm/spu_priv1.h> -#include <asm/firmware.h> -#include <asm/rtas.h> -#include <asm/cell-regs.h> - -#include "beat_interrupt.h" -#include "beat_wrapper.h" -#include "beat.h" -#include "celleb_pci.h" -#include "interrupt.h" -#include "pervasive.h" -#include "ras.h" - -static char celleb_machine_type[128] = "Celleb"; - -static void celleb_show_cpuinfo(struct seq_file *m) -{ - struct device_node *root; - const char *model = ""; - - root = of_find_node_by_path("/"); - if (root) - model = of_get_property(root, "model", NULL); - /* using "CHRP" is to trick anaconda into installing FCx into Celleb */ - seq_printf(m, "machine\t\t: %s %s\n", celleb_machine_type, model); - of_node_put(root); -} - -static int __init celleb_machine_type_hack(char *ptr) -{ - strlcpy(celleb_machine_type, ptr, sizeof(celleb_machine_type)); - return 0; -} - -__setup("celleb_machine_type_hack=", celleb_machine_type_hack); - -static void celleb_progress(char *s, unsigned short hex) -{ - printk("*** %04x : %s\n", hex, s ? s : ""); -} - -static void __init celleb_setup_arch_common(void) -{ - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif -} - -static const struct of_device_id celleb_bus_ids[] __initconst = { - { .type = "scc", }, - { .type = "ioif", }, /* old style */ - {}, -}; - -static int __init celleb_publish_devices(void) -{ - /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, celleb_bus_ids, NULL); - - return 0; -} -machine_device_initcall(celleb_beat, celleb_publish_devices); -machine_device_initcall(celleb_native, celleb_publish_devices); - - -/* - * functions for Celleb-Beat - */ -static void __init celleb_setup_arch_beat(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_beat_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - celleb_setup_arch_common(); -} - -static int __init celleb_probe_beat(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "Beat")) - return 0; - - powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS - | FW_FEATURE_BEAT | FW_FEATURE_LPAR; - hpte_init_beat_v3(); - pm_power_off = beat_power_off; - - return 1; -} - - -/* - * functions for Celleb-native - */ -static void __init celleb_init_IRQ_native(void) -{ - iic_init_IRQ(); - spider_init_IRQ(); -} - -static void __init celleb_setup_arch_native(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_mmio_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - cbe_regs_init(); - -#ifdef CONFIG_CBE_RAS - cbe_ras_init(); -#endif - -#ifdef CONFIG_SMP - smp_init_cell(); -#endif - - cbe_pervasive_init(); - - /* XXX: nvram initialization should be added */ - - celleb_setup_arch_common(); -} - -static int __init celleb_probe_native(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (of_flat_dt_is_compatible(root, "Beat") || - !of_flat_dt_is_compatible(root, "TOSHIBA,Celleb")) - return 0; - - powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS; - hpte_init_native(); - pm_power_off = rtas_power_off; - - return 1; -} - - -/* - * machine definitions - */ -define_machine(celleb_beat) { - .name = "Cell Reference Set (Beat)", - .probe = celleb_probe_beat, - .setup_arch = celleb_setup_arch_beat, - .show_cpuinfo = celleb_show_cpuinfo, - .restart = beat_restart, - .halt = beat_halt, - .get_rtc_time = beat_get_rtc_time, - .set_rtc_time = beat_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = celleb_progress, - .power_save = beat_power_save, - .nvram_size = beat_nvram_get_size, - .nvram_read = beat_nvram_read, - .nvram_write = beat_nvram_write, - .set_dabr = beat_set_xdabr, - .init_IRQ = beatic_init_IRQ, - .get_irq = beatic_get_irq, - .pci_probe_mode = celleb_pci_probe_mode, - .pci_setup_phb = celleb_setup_phb, -#ifdef CONFIG_KEXEC - .kexec_cpu_down = beat_kexec_cpu_down, -#endif -}; - -define_machine(celleb_native) { - .name = "Cell Reference Set (native)", - .probe = celleb_probe_native, - .setup_arch = celleb_setup_arch_native, - .show_cpuinfo = celleb_show_cpuinfo, - .restart = rtas_restart, - .halt = rtas_halt, - .get_boot_time = rtas_get_boot_time, - .get_rtc_time = rtas_get_rtc_time, - .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = celleb_progress, - .pci_probe_mode = celleb_pci_probe_mode, - .pci_setup_phb = celleb_setup_phb, - .init_IRQ = celleb_init_IRQ_native, -}; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 4c11421847be..3af8324c122e 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) void iic_setup_cpu(void) { - out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff); + out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff); } u8 iic_get_target_id(int cpu) diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index c7c8720aa39f..21b502398bf3 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -39,6 +39,7 @@ #include <asm/firmware.h> #include <asm/cell-regs.h> +#include "cell.h" #include "interrupt.h" /* Define CELL_IOMMU_REAL_UNMAP to actually unmap non-used pages @@ -197,7 +198,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) + for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift)) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -857,7 +858,7 @@ static int __init cell_iommu_init_disabled(void) cell_dma_direct_offset += base; if (cell_dma_direct_offset != 0) - ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup; + cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup; printk("iommu: disabled, direct DMA offset is 0x%lx\n", cell_dma_direct_offset); @@ -1197,8 +1198,8 @@ static int __init cell_iommu_init(void) if (cell_iommu_init_disabled() == 0) goto bail; - /* Setup various ppc_md. callbacks */ - ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup; + /* Setup various callbacks */ + cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup; ppc_md.dma_get_required_mask = cell_dma_get_required_mask; ppc_md.tce_build = tce_build_cell; ppc_md.tce_free = tce_free_cell; @@ -1234,5 +1235,3 @@ static int __init cell_iommu_init(void) return 0; } machine_arch_initcall(cell, cell_iommu_init); -machine_arch_initcall(celleb_native, cell_iommu_init); - diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index d62aa982d530..36cff28d0293 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -54,6 +54,7 @@ #include <asm/cell-regs.h> #include <asm/io-workarounds.h> +#include "cell.h" #include "interrupt.h" #include "pervasive.h" #include "ras.h" @@ -126,6 +127,8 @@ static int cell_setup_phb(struct pci_controller *phb) if (rc) return rc; + phb->controller_ops = cell_pci_controller_ops; + np = phb->dn; model = of_get_property(np, "model", NULL); if (model == NULL || strcmp(np->name, "pci")) @@ -279,3 +282,5 @@ define_machine(cell) { .init_IRQ = cell_init_irq, .pci_setup_phb = cell_setup_phb, }; + +struct pci_controller_ops cell_pci_controller_ops; diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index b64e7ead752f..895560f4be69 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -102,13 +102,6 @@ static inline int smp_startup_cpu(unsigned int lcpu) return 1; } -static int __init smp_iic_probe(void) -{ - iic_request_IPIs(); - - return num_possible_cpus(); -} - static void smp_cell_setup_cpu(int cpu) { if (cpu != boot_cpuid) @@ -139,7 +132,7 @@ static int smp_cell_kick_cpu(int nr) static struct smp_ops_t bpa_iic_smp_ops = { .message_pass = iic_message_pass, - .probe = smp_iic_probe, + .probe = iic_request_IPIs, .kick_cpu = smp_cell_kick_cpu, .setup_cpu = smp_cell_setup_cpu, .cpu_bootable = smp_generic_cpu_bootable, diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index b0ec78e8ad68..a494028b2cdf 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -39,6 +39,7 @@ static void *spu_syscall_table[] = { #define PPC_SYS(func) sys_ni_syscall, #define OLDSYS(func) sys_ni_syscall, #define SYS32ONLY(func) sys_ni_syscall, +#define PPC64ONLY(func) sys_ni_syscall, #define SYSX(f, f3264, f32) sys_ni_syscall, #define SYSCALL_SPU(func) sys_##func, diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 1a3429e1ccb5..1ba6307be4db 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -111,7 +111,7 @@ out: static int spufs_setattr(struct dentry *dentry, struct iattr *attr) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); if ((attr->ia_valid & ATTR_SIZE) && (attr->ia_size != inode->i_size)) @@ -163,14 +163,14 @@ static void spufs_prune_dir(struct dentry *dir) { struct dentry *dentry, *tmp; - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock(&d_inode(dir)->i_mutex); list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); - if (!(d_unhashed(dentry)) && dentry->d_inode) { + if (!(d_unhashed(dentry)) && d_really_is_positive(dentry)) { dget_dlock(dentry); __d_drop(dentry); spin_unlock(&dentry->d_lock); - simple_unlink(dir->d_inode, dentry); + simple_unlink(d_inode(dir), dentry); /* XXX: what was dcache_lock protecting here? Other * filesystems (IB, configfs) release dcache_lock * before unlink */ @@ -180,7 +180,7 @@ static void spufs_prune_dir(struct dentry *dir) } } shrink_dcache_parent(dir); - mutex_unlock(&dir->d_inode->i_mutex); + mutex_unlock(&d_inode(dir)->i_mutex); } /* Caller must hold parent->i_mutex */ @@ -192,7 +192,7 @@ static int spufs_rmdir(struct inode *parent, struct dentry *dir) d_drop(dir); res = simple_rmdir(parent, dir); /* We have to give up the mm_struct */ - spu_forget(SPUFS_I(dir->d_inode)->i_ctx); + spu_forget(SPUFS_I(d_inode(dir))->i_ctx); return res; } @@ -222,8 +222,8 @@ static int spufs_dir_close(struct inode *inode, struct file *file) int ret; dir = file->f_path.dentry; - parent = dir->d_parent->d_inode; - ctx = SPUFS_I(dir->d_inode)->i_ctx; + parent = d_inode(dir->d_parent); + ctx = SPUFS_I(d_inode(dir))->i_ctx; mutex_lock_nested(&parent->i_mutex, I_MUTEX_PARENT); ret = spufs_rmdir(parent, dir); @@ -460,7 +460,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry, goto out_aff_unlock; if (affinity) { - spufs_set_affinity(flags, SPUFS_I(dentry->d_inode)->i_ctx, + spufs_set_affinity(flags, SPUFS_I(d_inode(dentry))->i_ctx, neighbor); if (neighbor) put_spu_context(neighbor); @@ -504,7 +504,7 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) d_instantiate(dentry, inode); inc_nlink(dir); - inc_nlink(dentry->d_inode); + inc_nlink(d_inode(dentry)); return ret; out_iput: @@ -561,7 +561,7 @@ static struct file_system_type spufs_type; long spufs_create(struct path *path, struct dentry *dentry, unsigned int flags, umode_t mode, struct file *filp) { - struct inode *dir = path->dentry->d_inode; + struct inode *dir = d_inode(path->dentry); int ret; /* check if we are on spufs */ diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 860a59eb8ea2..15ebc4e8a151 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -253,7 +253,7 @@ static void briq_restart(char *cmd) * But unfortunately, the firmware does not connect /chosen/{stdin,stdout} * the the built-in serial node. Instead, a /failsafe node is created. */ -static void chrp_init_early(void) +static __init void chrp_init_early(void) { struct device_node *node; const char *property; diff --git a/arch/powerpc/platforms/maple/maple.h b/arch/powerpc/platforms/maple/maple.h index c6911ddc479f..eecfa182b06e 100644 --- a/arch/powerpc/platforms/maple/maple.h +++ b/arch/powerpc/platforms/maple/maple.h @@ -10,3 +10,5 @@ extern void maple_calibrate_decr(void); extern void maple_pci_init(void); extern void maple_pci_irq_fixup(struct pci_dev *dev); extern int maple_pci_get_legacy_ide_irq(struct pci_dev *dev, int channel); + +extern struct pci_controller_ops maple_pci_controller_ops; diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index d3a13067ec42..a923230e575b 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -510,6 +510,7 @@ static int __init maple_add_bridge(struct device_node *dev) return -ENOMEM; hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; + hose->controller_ops = maple_pci_controller_ops; disp_name = NULL; if (of_device_is_compatible(dev, "u3-agp")) { @@ -660,3 +661,6 @@ static void quirk_ipr_msi(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN, quirk_ipr_msi); + +struct pci_controller_ops maple_pci_controller_ops = { +}; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 56b85cd61aaf..a837188544c8 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -203,7 +203,7 @@ static void __init maple_init_early(void) { DBG(" -> maple_init_early\n"); - iommu_init_early_dart(); + iommu_init_early_dart(&maple_pci_controller_ops); DBG(" <- maple_init_early\n"); } diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 2e576f2ae442..b8f567b2ea19 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -27,6 +27,8 @@ #include <asm/machdep.h> #include <asm/firmware.h> +#include "pasemi.h" + #define IOBMAP_PAGE_SHIFT 12 #define IOBMAP_PAGE_SIZE (1 << IOBMAP_PAGE_SHIFT) #define IOBMAP_PAGE_MASK (IOBMAP_PAGE_SIZE - 1) @@ -248,8 +250,8 @@ void __init iommu_init_early_pasemi(void) iob_init(NULL); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pasemi; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pasemi; + pasemi_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pasemi; + pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi; ppc_md.tce_build = iobmap_build; ppc_md.tce_free = iobmap_free; set_pci_dma_ops(&dma_iommu_ops); diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h index ea65bf0eb897..11f230a48227 100644 --- a/arch/powerpc/platforms/pasemi/pasemi.h +++ b/arch/powerpc/platforms/pasemi/pasemi.h @@ -30,5 +30,6 @@ static inline void restore_astate(int cpu) } #endif +extern struct pci_controller_ops pasemi_pci_controller_ops; #endif /* _PASEMI_PASEMI_H */ diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index aa862713258c..f3a68a0fef23 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -31,6 +31,8 @@ #include <asm/ppc-pci.h> +#include "pasemi.h" + #define PA_PXP_CFA(bus, devfn, off) (((bus) << 20) | ((devfn) << 12) | (off)) static inline int pa_pxp_offset_valid(u8 bus, u8 devfn, int offset) @@ -199,6 +201,7 @@ static int __init pas_add_bridge(struct device_node *dev) hose->first_busno = 0; hose->last_busno = 0xff; + hose->controller_ops = pasemi_pci_controller_ops; setup_pa_pxp(hose); @@ -239,3 +242,5 @@ void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset) return (void __iomem *)pa_pxp_cfg_addr(hose, dev->bus->number, dev->devfn, offset); } + +struct pci_controller_ops pasemi_pci_controller_ops; diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c index 3e91ef538114..76f5013c35e5 100644 --- a/arch/powerpc/platforms/powermac/bootx_init.c +++ b/arch/powerpc/platforms/powermac/bootx_init.c @@ -246,7 +246,7 @@ static void __init bootx_scan_dt_build_strings(unsigned long base, DBG(" detected display ! adding properties names !\n"); bootx_dt_add_string("linux,boot-display", mem_end); bootx_dt_add_string("linux,opened", mem_end); - strncpy(bootx_disp_path, namep, 255); + strlcpy(bootx_disp_path, namep, sizeof(bootx_disp_path)); } /* get and store all property names */ diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index f4071a67ad00..59ab16fa600f 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -27,6 +27,8 @@ #include <asm/grackle.h> #include <asm/ppc-pci.h> +#include "pmac.h" + #undef DEBUG #ifdef DEBUG @@ -798,6 +800,7 @@ static int __init pmac_add_bridge(struct device_node *dev) return -ENOMEM; hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; + hose->controller_ops = pmac_pci_controller_ops; disp_name = NULL; @@ -942,7 +945,7 @@ void __init pmac_pci_init(void) } #ifdef CONFIG_PPC32 -int pmac_pci_enable_device_hook(struct pci_dev *dev) +static bool pmac_pci_enable_device_hook(struct pci_dev *dev) { struct device_node* node; int updatecfg = 0; @@ -958,11 +961,11 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev) && !node) { printk(KERN_INFO "Apple USB OHCI %s disabled by firmware\n", pci_name(dev)); - return -EINVAL; + return false; } if (!node) - return 0; + return true; uninorth_child = node->parent && of_device_is_compatible(node->parent, "uni-north"); @@ -1003,7 +1006,7 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev) L1_CACHE_BYTES >> 2); } - return 0; + return true; } void pmac_pci_fixup_ohci(struct pci_dev *dev) @@ -1223,3 +1226,30 @@ static void fixup_u4_pcie(struct pci_dev* dev) pci_write_config_dword(dev, PCI_PREF_MEMORY_BASE, 0); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_U4_PCIE, fixup_u4_pcie); + +#ifdef CONFIG_PPC64 +static int pmac_pci_probe_mode(struct pci_bus *bus) +{ + struct device_node *node = pci_bus_to_OF_node(bus); + + /* We need to use normal PCI probing for the AGP bus, + * since the device for the AGP bridge isn't in the tree. + * Same for the PCIe host on U4 and the HT host bridge. + */ + if (bus->self == NULL && (of_device_is_compatible(node, "u3-agp") || + of_device_is_compatible(node, "u4-pcie") || + of_device_is_compatible(node, "u3-ht"))) + return PCI_PROBE_NORMAL; + return PCI_PROBE_DEVTREE; +} +#endif /* CONFIG_PPC64 */ + +struct pci_controller_ops pmac_pci_controller_ops = { +#ifdef CONFIG_PPC64 + .probe_mode = pmac_pci_probe_mode, +#endif +#ifdef CONFIG_PPC32 + .enable_device_hook = pmac_pci_enable_device_hook, +#endif +}; + diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 4c24bf60d39d..59cfc9d63c2d 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -321,6 +321,9 @@ static void __init pmac_pic_probe_oldstyle(void) max_irqs = max_real_irqs = 64; /* We might have a second cascaded heathrow */ + + /* Compensate for of_node_put() in of_find_node_by_name() */ + of_node_get(master); slave = of_find_node_by_name(master, "mac-io"); /* Check ordering of master & slave */ diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 8327cce2bdb0..e7f8163d6769 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -25,7 +25,6 @@ extern void pmac_pci_init(void); extern void pmac_nvram_update(void); extern unsigned char pmac_nvram_read_byte(int addr); extern void pmac_nvram_write_byte(int addr, unsigned char val); -extern int pmac_pci_enable_device_hook(struct pci_dev *dev); extern void pmac_pcibios_after_init(void); extern int of_show_percpuinfo(struct seq_file *m, int i); @@ -39,4 +38,6 @@ extern void low_cpu_die(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); extern void pmac_pic_init(void); +extern struct pci_controller_ops pmac_pci_controller_ops; + #endif /* __PMAC_H__ */ diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 713d36d45d1d..8dd78f4e1af4 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -473,7 +473,7 @@ static void __init pmac_init_early(void) udbg_adb_init(!!strstr(boot_command_line, "btextdbg")); #ifdef CONFIG_PPC64 - iommu_init_early_dart(); + iommu_init_early_dart(&pmac_pci_controller_ops); #endif /* SMP Init has to be done early as we need to patch up @@ -637,24 +637,6 @@ static int __init pmac_probe(void) return 1; } -#ifdef CONFIG_PPC64 -/* Move that to pci.c */ -static int pmac_pci_probe_mode(struct pci_bus *bus) -{ - struct device_node *node = pci_bus_to_OF_node(bus); - - /* We need to use normal PCI probing for the AGP bus, - * since the device for the AGP bridge isn't in the tree. - * Same for the PCIe host on U4 and the HT host bridge. - */ - if (bus->self == NULL && (of_device_is_compatible(node, "u3-agp") || - of_device_is_compatible(node, "u4-pcie") || - of_device_is_compatible(node, "u3-ht"))) - return PCI_PROBE_NORMAL; - return PCI_PROBE_DEVTREE; -} -#endif /* CONFIG_PPC64 */ - define_machine(powermac) { .name = "PowerMac", .probe = pmac_probe, @@ -674,12 +656,10 @@ define_machine(powermac) { .feature_call = pmac_do_feature_call, .progress = udbg_progress, #ifdef CONFIG_PPC64 - .pci_probe_mode = pmac_pci_probe_mode, .power_save = power4_idle, .enable_pmcs = power4_enable_pmcs, #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC32 - .pcibios_enable_device_hook = pmac_pci_enable_device_hook, .pcibios_after_init = pmac_pcibios_after_init, .phys_mem_access_prot = pci_phys_mem_access_prot, #endif diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index af094ae03dbb..28a147ca32ba 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -268,14 +268,14 @@ static void __init psurge_quad_init(void) mdelay(33); } -static int __init smp_psurge_probe(void) +static void __init smp_psurge_probe(void) { int i, ncpus; struct device_node *dn; /* We don't do SMP on the PPC601 -- paulus */ if (PVR_VER(mfspr(SPRN_PVR)) == 1) - return 1; + return; /* * The powersurge cpu board can be used in the generation @@ -289,7 +289,7 @@ static int __init smp_psurge_probe(void) */ dn = of_find_node_by_name(NULL, "hammerhead"); if (dn == NULL) - return 1; + return; of_node_put(dn); hhead_base = ioremap(HAMMERHEAD_BASE, 0x800); @@ -310,13 +310,13 @@ static int __init smp_psurge_probe(void) /* not a dual-cpu card */ iounmap(hhead_base); psurge_type = PSURGE_NONE; - return 1; + return; } ncpus = 2; } if (psurge_secondary_ipi_init()) - return 1; + return; psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); @@ -332,8 +332,6 @@ static int __init smp_psurge_probe(void) set_cpu_present(i, true); if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352); - - return ncpus; } static int __init smp_psurge_kick_cpu(int nr) @@ -766,7 +764,7 @@ static void __init smp_core99_setup(int ncpus) powersave_nap = 0; } -static int __init smp_core99_probe(void) +static void __init smp_core99_probe(void) { struct device_node *cpus; int ncpus = 0; @@ -781,7 +779,7 @@ static int __init smp_core99_probe(void) /* Nothing more to do if less than 2 of them */ if (ncpus <= 1) - return 1; + return; /* We need to perform some early initialisations before we can start * setting up SMP as we are running before initcalls @@ -797,8 +795,6 @@ static int __init smp_core99_probe(void) /* Collect l2cr and l3cr values from CPU 0 */ core99_init_caches(0); - - return ncpus; } static int smp_core99_kick_cpu(int nr) diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 45a8ed0585cd..4b044d8cb49a 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -19,10 +19,3 @@ config PPC_POWERNV select CPU_FREQ_GOV_CONSERVATIVE select PPC_DOORBELL default y - -config PPC_POWERNV_RTAS - depends on PPC_POWERNV - bool "Support for RTAS based PowerNV platforms such as BML" - default y - select PPC_ICS_RTAS - select PPC_RTAS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 6f3c5d33c3af..33e44f37212f 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -5,7 +5,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o -obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o +obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c deleted file mode 100644 index 2809c9895288..000000000000 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ /dev/null @@ -1,1149 +0,0 @@ -/* - * The file intends to implement the functions needed by EEH, which is - * built on IODA compliant chip. Actually, lots of functions related - * to EEH would be built based on the OPAL APIs. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013. - * - * 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/debugfs.h> -#include <linux/delay.h> -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/msi.h> -#include <linux/notifier.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/eeh.h> -#include <asm/eeh_event.h> -#include <asm/io.h> -#include <asm/iommu.h> -#include <asm/msi_bitmap.h> -#include <asm/opal.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> -#include <asm/tce.h> - -#include "powernv.h" -#include "pci.h" - -static int ioda_eeh_nb_init = 0; - -static int ioda_eeh_event(struct notifier_block *nb, - unsigned long events, void *change) -{ - uint64_t changed_evts = (uint64_t)change; - - /* - * We simply send special EEH event if EEH has - * been enabled, or clear pending events in - * case that we enable EEH soon - */ - if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || - !(events & OPAL_EVENT_PCI_ERROR)) - return 0; - - if (eeh_enabled()) - eeh_send_failure_event(NULL); - else - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - return 0; -} - -static struct notifier_block ioda_eeh_nb = { - .notifier_call = ioda_eeh_event, - .next = NULL, - .priority = 0 -}; - -#ifdef CONFIG_DEBUG_FS -static ssize_t ioda_eeh_ei_write(struct file *filp, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct pci_controller *hose = filp->private_data; - struct pnv_phb *phb = hose->private_data; - struct eeh_dev *edev; - struct eeh_pe *pe; - int pe_no, type, func; - unsigned long addr, mask; - char buf[50]; - int ret; - - if (!phb->eeh_ops || !phb->eeh_ops->err_inject) - return -ENXIO; - - ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); - if (!ret) - return -EFAULT; - - /* Retrieve parameters */ - ret = sscanf(buf, "%x:%x:%x:%lx:%lx", - &pe_no, &type, &func, &addr, &mask); - if (ret != 5) - return -EINVAL; - - /* Retrieve PE */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return -ENOMEM; - edev->phb = hose; - edev->pe_config_addr = pe_no; - pe = eeh_pe_get(edev); - kfree(edev); - if (!pe) - return -ENODEV; - - /* Do error injection */ - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); - return ret < 0 ? ret : count; -} - -static const struct file_operations ioda_eeh_ei_fops = { - .open = simple_open, - .llseek = no_llseek, - .write = ioda_eeh_ei_write, -}; - -static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - out_be64(phb->regs + offset, val); - return 0; -} - -static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - *val = in_be64(phb->regs + offset); - return 0; -} - -static int ioda_eeh_outb_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD10, val); -} - -static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD10, val); -} - -static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD90, val); -} - -static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD90, val); -} - -static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xE10, val); -} - -static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xE10, val); -} - -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get, - ioda_eeh_outb_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get, - ioda_eeh_inbA_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, - ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); -#endif /* CONFIG_DEBUG_FS */ - - -/** - * ioda_eeh_post_init - Chip dependent post initialization - * @hose: PCI controller - * - * The function will be called after eeh PEs and devices - * have been built. That means the EEH is ready to supply - * service with I/O cache. - */ -static int ioda_eeh_post_init(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - int ret; - - /* Register OPAL event notifier */ - if (!ioda_eeh_nb_init) { - ret = opal_notifier_register(&ioda_eeh_nb); - if (ret) { - pr_err("%s: Can't register OPAL event notifier (%d)\n", - __func__, ret); - return ret; - } - - ioda_eeh_nb_init = 1; - } - -#ifdef CONFIG_DEBUG_FS - if (!phb->has_dbgfs && phb->dbgfs) { - phb->has_dbgfs = 1; - - debugfs_create_file("err_injct", 0200, - phb->dbgfs, hose, - &ioda_eeh_ei_fops); - - debugfs_create_file("err_injct_outbound", 0600, - phb->dbgfs, hose, - &ioda_eeh_outb_dbgfs_ops); - debugfs_create_file("err_injct_inboundA", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbA_dbgfs_ops); - debugfs_create_file("err_injct_inboundB", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbB_dbgfs_ops); - } -#endif - - /* If EEH is enabled, we're going to rely on that. - * Otherwise, we restore to conventional mechanism - * to clear frozen PE during PCI config access. - */ - if (eeh_enabled()) - phb->flags |= PNV_PHB_FLAG_EEH; - else - phb->flags &= ~PNV_PHB_FLAG_EEH; - - return 0; -} - -/** - * ioda_eeh_set_option - Set EEH operation or I/O setting - * @pe: EEH PE - * @option: options - * - * Enable or disable EEH option for the indicated PE. The - * function also can be used to enable I/O or DMA for the - * PE. - */ -static int ioda_eeh_set_option(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - bool freeze_pe = false; - int enable, ret = 0; - s64 rc; - - /* Check on PE number */ - if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) { - pr_err("%s: PE address %x out of range [0, %x] " - "on PHB#%x\n", - __func__, pe->addr, phb->ioda.total_pe, - hose->global_number); - return -EINVAL; - } - - switch (option) { - case EEH_OPT_DISABLE: - return -EPERM; - case EEH_OPT_ENABLE: - return 0; - case EEH_OPT_THAW_MMIO: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; - break; - case EEH_OPT_THAW_DMA: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; - break; - case EEH_OPT_FREEZE_PE: - freeze_pe = true; - enable = OPAL_EEH_ACTION_SET_FREEZE_ALL; - break; - default: - pr_warn("%s: Invalid option %d\n", - __func__, option); - return -EINVAL; - } - - /* If PHB supports compound PE, to handle it */ - if (freeze_pe) { - if (phb->freeze_pe) { - phb->freeze_pe(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_set(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld freezing " - "PHB#%x-PE#%x\n", - __func__, rc, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } else { - if (phb->unfreeze_pe) { - ret = phb->unfreeze_pe(phb, pe->addr, enable); - } else { - rc = opal_pci_eeh_freeze_clear(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld enable %d " - "for PHB#%x-PE#%x\n", - __func__, rc, option, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } - - return ret; -} - -static void ioda_eeh_phb_diag(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) - pr_warn("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, pe->phb->global_number, rc); -} - -static int ioda_eeh_get_phb_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result = 0; - - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x state\n", - __func__, rc, phb->hose->global_number); - return EEH_STATE_NOT_SUPPORT; - } - - /* - * Check PHB state. If the PHB is frozen for the - * first time, to dump the PHB diag-data. - */ - if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - } else if (!(pe->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -static int ioda_eeh_get_pe_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result; - - /* - * We don't clobber hardware frozen state until PE - * reset is completed. In order to keep EEH core - * moving forward, we have to return operational - * state during PE reset. - */ - if (pe->state & EEH_PE_RESET) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - return result; - } - - /* - * Fetch PE state from hardware. If the PHB - * supports compound PE, let it handle that. - */ - if (phb->get_pe_state) { - fstate = phb->get_pe_state(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", - __func__, rc, phb->hose->global_number, pe->addr); - return EEH_STATE_NOT_SUPPORT; - } - } - - /* Figure out state */ - switch (fstate) { - case OPAL_EEH_STOPPED_NOT_FROZEN: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_FREEZE: - result = (EEH_STATE_DMA_ACTIVE | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_DMA_FREEZE: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_MMIO_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: - result = 0; - break; - case OPAL_EEH_STOPPED_RESET: - result = EEH_STATE_RESET_ACTIVE; - break; - case OPAL_EEH_STOPPED_TEMP_UNAVAIL: - result = EEH_STATE_UNAVAILABLE; - break; - case OPAL_EEH_STOPPED_PERM_UNAVAIL: - result = EEH_STATE_NOT_SUPPORT; - break; - default: - result = EEH_STATE_NOT_SUPPORT; - pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", - __func__, phb->hose->global_number, - pe->addr, fstate); - } - - /* - * If PHB supports compound PE, to freeze all - * slave PEs for consistency. - * - * If the PE is switching to frozen state for the - * first time, to dump the PHB diag-data. - */ - if (!(result & EEH_STATE_NOT_SUPPORT) && - !(result & EEH_STATE_UNAVAILABLE) && - !(result & EEH_STATE_MMIO_ACTIVE) && - !(result & EEH_STATE_DMA_ACTIVE) && - !(pe->state & EEH_PE_ISOLATED)) { - if (phb->freeze_pe) - phb->freeze_pe(phb, pe->addr); - - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -/** - * ioda_eeh_get_state - Retrieve the state of PE - * @pe: EEH PE - * - * The PE's state should be retrieved from the PEEV, PEST - * IODA tables. Since the OPAL has exported the function - * to do it, it'd better to use that. - */ -static int ioda_eeh_get_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - - /* Sanity check on PE number. PHB PE should have 0 */ - if (pe->addr < 0 || - pe->addr >= phb->ioda.total_pe) { - pr_warn("%s: PHB#%x-PE#%x out of range [0, %x]\n", - __func__, phb->hose->global_number, - pe->addr, phb->ioda.total_pe); - return EEH_STATE_NOT_SUPPORT; - } - - if (pe->type & EEH_PE_PHB) - return ioda_eeh_get_phb_state(pe); - - return ioda_eeh_get_pe_state(pe); -} - -static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) -{ - s64 rc = OPAL_HARDWARE; - - while (1) { - rc = opal_pci_poll(phb->opal_id); - if (rc <= 0) - break; - - if (system_state < SYSTEM_RUNNING) - udelay(1000 * rc); - else - msleep(rc); - } - - return rc; -} - -int ioda_eeh_phb_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_HARDWARE; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* Issue PHB complete reset request */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* - * Poll state of the PHB until the request is done - * successfully. The PHB reset is usually PHB complete - * reset followed by hot reset on root bus. So we also - * need the PCI bus settlement delay. - */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) { - if (system_state < SYSTEM_RUNNING) - udelay(1000 * EEH_PE_RST_SETTLE_TIME); - else - msleep(EEH_PE_RST_SETTLE_TIME); - } -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_root_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_SUCCESS; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* - * During the reset deassert time, we needn't care - * the reset scope because the firmware does nothing - * for fundamental or hot reset during deassert phase. - */ - if (option == EEH_RESET_FUNDAMENTAL) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_FUNDAMENTAL, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* Poll state of the PHB until the request is done */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) - msleep(EEH_PE_RST_SETTLE_TIME); -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) - -{ - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); - int aer = edev ? edev->aer_cap : 0; - u32 ctrl; - - pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", - __func__, pci_domain_nr(dev->bus), - dev->bus->number, option); - - switch (option) { - case EEH_RESET_FUNDAMENTAL: - case EEH_RESET_HOT: - /* Don't report linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl |= PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_HOLD_TIME); - - break; - case EEH_RESET_DEACTIVATE: - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_SETTLE_TIME); - - /* Continue reporting linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl &= ~PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - break; - } - - return 0; -} - -void pnv_pci_reset_secondary_bus(struct pci_dev *dev) -{ - struct pci_controller *hose; - - if (pci_is_root_bus(dev->bus)) { - hose = pci_bus_to_host(dev->bus); - ioda_eeh_root_reset(hose, EEH_RESET_HOT); - ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); - } else { - ioda_eeh_bridge_reset(dev, EEH_RESET_HOT); - ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); - } -} - -/** - * ioda_eeh_reset - Reset the indicated PE - * @pe: EEH PE - * @option: reset option - * - * Do reset on the indicated PE. For PCI bus sensitive PE, - * we need to reset the parent p2p bridge. The PHB has to - * be reinitialized if the p2p bridge is root bridge. For - * PCI device sensitive PE, we will try to reset the device - * through FLR. For now, we don't have OPAL APIs to do HARD - * reset yet, so all reset would be SOFT (HOT) reset. - */ -static int ioda_eeh_reset(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pci_bus *bus; - int ret; - - /* - * For PHB reset, we always have complete reset. For those PEs whose - * primary bus derived from root complex (root bus) or root port - * (usually bus#1), we apply hot or fundamental reset on the root port. - * For other PEs, we always have hot reset on the PE primary bus. - * - * Here, we have different design to pHyp, which always clear the - * frozen state during PE reset. However, the good idea here from - * benh is to keep frozen state before we get PE reset done completely - * (until BAR restore). With the frozen state, HW drops illegal IO - * or MMIO access, which can incur recrusive frozen PE during PE - * reset. The side effect is that EEH core has to clear the frozen - * state explicitly after BAR restore. - */ - if (pe->type & EEH_PE_PHB) { - ret = ioda_eeh_phb_reset(hose, option); - } else { - struct pnv_phb *phb; - s64 rc; - - /* - * The frozen PE might be caused by PAPR error injection - * registers, which are expected to be cleared after hitting - * frozen PE as stated in the hardware spec. Unfortunately, - * that's not true on P7IOC. So we have to clear it manually - * to avoid recursive EEH errors during recovery. - */ - phb = hose->private_data; - if (phb->model == PNV_PHB_MODEL_P7IOC && - (option == EEH_RESET_HOT || - option == EEH_RESET_FUNDAMENTAL)) { - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_ERROR, - OPAL_ASSERT_RESET); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld clearing " - "error injection registers\n", - __func__, rc); - return -EIO; - } - } - - bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus) || - pci_is_root_bus(bus->parent)) - ret = ioda_eeh_root_reset(hose, option); - else - ret = ioda_eeh_bridge_reset(bus->self, option); - } - - return ret; -} - -/** - * ioda_eeh_get_log - Retrieve error log - * @pe: frozen PE - * @severity: permanent or temporary error - * @drv_log: device driver log - * @len: length of device driver log - * - * Retrieve error log, which contains log from device driver - * and firmware. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - - return 0; -} - -/** - * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE - * @pe: EEH PE - * - * For particular PE, it might have included PCI bridges. In order - * to make the PE work properly, those PCI bridges should be configured - * correctly. However, we need do nothing on P7IOC since the reset - * function will do everything that should be covered by the function. - */ -static int ioda_eeh_configure_bridge(struct eeh_pe *pe) -{ - return 0; -} - -static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - s64 ret; - - /* Sanity check on error type */ - if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && - type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { - pr_warn("%s: Invalid error type %d\n", - __func__, type); - return -ERANGE; - } - - if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || - func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { - pr_warn("%s: Invalid error function %d\n", - __func__, func); - return -ERANGE; - } - - /* Firmware supports error injection ? */ - if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { - pr_warn("%s: Firmware doesn't support error injection\n", - __func__); - return -ENXIO; - } - - /* Do error injection */ - ret = opal_pci_err_inject(phb->opal_id, pe->addr, - type, func, addr, mask); - if (ret != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld injecting error " - "%d-%d to PHB#%x-PE#%x\n", - __func__, ret, type, func, - hose->global_number, pe->addr); - return -EIO; - } - - return 0; -} - -static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data) -{ - /* GEM */ - if (data->gemXfir || data->gemRfir || - data->gemRirqfir || data->gemMask || data->gemRwof) - pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->gemXfir), - be64_to_cpu(data->gemRfir), - be64_to_cpu(data->gemRirqfir), - be64_to_cpu(data->gemMask), - be64_to_cpu(data->gemRwof)); - - /* LEM */ - if (data->lemFir || data->lemErrMask || - data->lemAction0 || data->lemAction1 || data->lemWof) - pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->lemFir), - be64_to_cpu(data->lemErrMask), - be64_to_cpu(data->lemAction0), - be64_to_cpu(data->lemAction1), - be64_to_cpu(data->lemWof)); -} - -static void ioda_eeh_hub_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; - long rc; - - rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", - __func__, phb->hub_id, rc); - return; - } - - switch (data->type) { - case OPAL_P7IOC_DIAG_TYPE_RGC: - pr_info("P7IOC diag-data for RGC\n\n"); - ioda_eeh_hub_diag_common(data); - if (data->rgc.rgcStatus || data->rgc.rgcLdcp) - pr_info(" RGC: %016llx %016llx\n", - be64_to_cpu(data->rgc.rgcStatus), - be64_to_cpu(data->rgc.rgcLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_BI: - pr_info("P7IOC diag-data for BI %s\n\n", - data->bi.biDownbound ? "Downbound" : "Upbound"); - ioda_eeh_hub_diag_common(data); - if (data->bi.biLdcp0 || data->bi.biLdcp1 || - data->bi.biLdcp2 || data->bi.biFenceStatus) - pr_info(" BI: %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->bi.biLdcp0), - be64_to_cpu(data->bi.biLdcp1), - be64_to_cpu(data->bi.biLdcp2), - be64_to_cpu(data->bi.biFenceStatus)); - break; - case OPAL_P7IOC_DIAG_TYPE_CI: - pr_info("P7IOC diag-data for CI Port %d\n\n", - data->ci.ciPort); - ioda_eeh_hub_diag_common(data); - if (data->ci.ciPortStatus || data->ci.ciPortLdcp) - pr_info(" CI: %016llx %016llx\n", - be64_to_cpu(data->ci.ciPortStatus), - be64_to_cpu(data->ci.ciPortLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_MISC: - pr_info("P7IOC diag-data for MISC\n\n"); - ioda_eeh_hub_diag_common(data); - break; - case OPAL_P7IOC_DIAG_TYPE_I2C: - pr_info("P7IOC diag-data for I2C\n\n"); - ioda_eeh_hub_diag_common(data); - break; - default: - pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", - __func__, phb->hub_id, data->type); - } -} - -static int ioda_eeh_get_pe(struct pci_controller *hose, - u16 pe_no, struct eeh_pe **pe) -{ - struct pnv_phb *phb = hose->private_data; - struct pnv_ioda_pe *pnv_pe; - struct eeh_pe *dev_pe; - struct eeh_dev edev; - - /* - * If PHB supports compound PE, to fetch - * the master PE because slave PE is invisible - * to EEH core. - */ - pnv_pe = &phb->ioda.pe_array[pe_no]; - if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { - pnv_pe = pnv_pe->master; - WARN_ON(!pnv_pe || - !(pnv_pe->flags & PNV_IODA_PE_MASTER)); - pe_no = pnv_pe->pe_number; - } - - /* Find the PE according to PE# */ - memset(&edev, 0, sizeof(struct eeh_dev)); - edev.phb = hose; - edev.pe_config_addr = pe_no; - dev_pe = eeh_pe_get(&edev); - if (!dev_pe) - return -EEXIST; - - /* Freeze the (compound) PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, pe_no); - - /* - * At this point, we're sure the (compound) PE should - * have been frozen. However, we still need poke until - * hitting the frozen PE on top level. - */ - dev_pe = dev_pe->parent; - while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { - int ret; - int active_flags = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE); - - ret = eeh_ops->get_state(dev_pe, NULL); - if (ret <= 0 || (ret & active_flags) == active_flags) { - dev_pe = dev_pe->parent; - continue; - } - - /* Frozen parent PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, dev_pe->addr); - - /* Next one */ - dev_pe = dev_pe->parent; - } - - return 0; -} - -/** - * ioda_eeh_next_error - Retrieve next error for EEH core to handle - * @pe: The affected PE - * - * The function is expected to be called by EEH core while it gets - * special EEH event (without binding PE). The function calls to - * OPAL APIs for next error to handle. The informational error is - * handled internally by platform. However, the dead IOC, dead PHB, - * fenced PHB and frozen PE should be handled by EEH core eventually. - */ -static int ioda_eeh_next_error(struct eeh_pe **pe) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - struct eeh_pe *phb_pe, *parent_pe; - __be64 frozen_pe_no; - __be16 err_type, severity; - int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); - long rc; - int state, ret = EEH_NEXT_ERR_NONE; - - /* - * While running here, it's safe to purge the event queue. - * And we should keep the cached OPAL notifier event sychronized - * between the kernel and firmware. - */ - eeh_remove_event(NULL, false); - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - list_for_each_entry(hose, &hose_list, list_node) { - /* - * If the subordinate PCI buses of the PHB has been - * removed or is exactly under error recovery, we - * needn't take care of it any more. - */ - phb = hose->private_data; - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) - continue; - - rc = opal_pci_next_error(phb->opal_id, - &frozen_pe_no, &err_type, &severity); - - /* If OPAL API returns error, we needn't proceed */ - if (rc != OPAL_SUCCESS) { - pr_devel("%s: Invalid return value on " - "PHB#%x (0x%lx) from opal_pci_next_error", - __func__, hose->global_number, rc); - continue; - } - - /* If the PHB doesn't have error, stop processing */ - if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || - be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { - pr_devel("%s: No error found on PHB#%x\n", - __func__, hose->global_number); - continue; - } - - /* - * Processing the error. We're expecting the error with - * highest priority reported upon multiple errors on the - * specific PHB. - */ - pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", - __func__, be16_to_cpu(err_type), be16_to_cpu(severity), - be64_to_cpu(frozen_pe_no), hose->global_number); - switch (be16_to_cpu(err_type)) { - case OPAL_EEH_IOC_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { - pr_err("EEH: dead IOC detected\n"); - ret = EEH_NEXT_ERR_DEAD_IOC; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: IOC informative error " - "detected\n"); - ioda_eeh_hub_diag(hose); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PHB_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { - *pe = phb_pe; - pr_err("EEH: dead PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_DEAD_PHB; - } else if (be16_to_cpu(severity) == - OPAL_EEH_SEV_PHB_FENCED) { - *pe = phb_pe; - pr_err("EEH: Fenced PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FENCED_PHB; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: PHB#%x informative error " - "detected, location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ioda_eeh_phb_diag(phb_pe); - pnv_pci_dump_phb_diag_data(hose, phb_pe->data); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PE_ERROR: - /* - * If we can't find the corresponding PE, we - * just try to unfreeze. - */ - if (ioda_eeh_get_pe(hose, - be64_to_cpu(frozen_pe_no), pe)) { - /* Try best to clear it */ - pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", - hose->global_number, frozen_pe_no); - pr_info("EEH: PHB location: %s\n", - eeh_pe_loc_get(phb_pe)); - opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no, - OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); - ret = EEH_NEXT_ERR_NONE; - } else if ((*pe)->state & EEH_PE_ISOLATED || - eeh_pe_passed(*pe)) { - ret = EEH_NEXT_ERR_NONE; - } else { - pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", - (*pe)->addr, (*pe)->phb->global_number); - pr_err("EEH: PE location: %s, PHB location: %s\n", - eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FROZEN_PE; - } - - break; - default: - pr_warn("%s: Unexpected error type %d\n", - __func__, be16_to_cpu(err_type)); - } - - /* - * EEH core will try recover from fenced PHB or - * frozen PE. In the time for frozen PE, EEH core - * enable IO path for that before collecting logs, - * but it ruins the site. So we have to dump the - * log in advance here. - */ - if ((ret == EEH_NEXT_ERR_FROZEN_PE || - ret == EEH_NEXT_ERR_FENCED_PHB) && - !((*pe)->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(*pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data((*pe)->phb, - (*pe)->data); - } - - /* - * We probably have the frozen parent PE out there and - * we need have to handle frozen parent PE firstly. - */ - if (ret == EEH_NEXT_ERR_FROZEN_PE) { - parent_pe = (*pe)->parent; - while (parent_pe) { - /* Hit the ceiling ? */ - if (parent_pe->type & EEH_PE_PHB) - break; - - /* Frozen parent PE ? */ - state = ioda_eeh_get_state(parent_pe); - if (state > 0 && - (state & active_flags) != active_flags) - *pe = parent_pe; - - /* Next parent level */ - parent_pe = parent_pe->parent; - } - - /* We possibly migrate to another PE */ - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - } - - /* - * If we have no errors on the specific PHB or only - * informative error there, we continue poking it. - * Otherwise, we need actions to be taken by upper - * layer. - */ - if (ret > EEH_NEXT_ERR_INF) - break; - } - - return ret; -} - -struct pnv_eeh_ops ioda_eeh_ops = { - .post_init = ioda_eeh_post_init, - .set_option = ioda_eeh_set_option, - .get_state = ioda_eeh_get_state, - .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, - .configure_bridge = ioda_eeh_configure_bridge, - .err_inject = ioda_eeh_err_inject, - .next_error = ioda_eeh_next_error -}; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e261869adc86..ce738ab3d5a9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -12,6 +12,7 @@ */ #include <linux/atomic.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -38,12 +39,14 @@ #include "powernv.h" #include "pci.h" +static bool pnv_eeh_nb_init = false; + /** - * powernv_eeh_init - EEH platform dependent initialization + * pnv_eeh_init - EEH platform dependent initialization * * EEH platform dependent initialization on powernv */ -static int powernv_eeh_init(void) +static int pnv_eeh_init(void) { struct pci_controller *hose; struct pnv_phb *phb; @@ -85,37 +88,280 @@ static int powernv_eeh_init(void) return 0; } +static int pnv_eeh_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + uint64_t changed_evts = (uint64_t)change; + + /* + * We simply send special EEH event if EEH has + * been enabled, or clear pending events in + * case that we enable EEH soon + */ + if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || + !(events & OPAL_EVENT_PCI_ERROR)) + return 0; + + if (eeh_enabled()) + eeh_send_failure_event(NULL); + else + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); + + return 0; +} + +static struct notifier_block pnv_eeh_nb = { + .notifier_call = pnv_eeh_event, + .next = NULL, + .priority = 0 +}; + +#ifdef CONFIG_DEBUG_FS +static ssize_t pnv_eeh_ei_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct pci_controller *hose = filp->private_data; + struct eeh_dev *edev; + struct eeh_pe *pe; + int pe_no, type, func; + unsigned long addr, mask; + char buf[50]; + int ret; + + if (!eeh_ops || !eeh_ops->err_inject) + return -ENXIO; + + /* Copy over argument buffer */ + ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); + if (!ret) + return -EFAULT; + + /* Retrieve parameters */ + ret = sscanf(buf, "%x:%x:%x:%lx:%lx", + &pe_no, &type, &func, &addr, &mask); + if (ret != 5) + return -EINVAL; + + /* Retrieve PE */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + return -ENOMEM; + edev->phb = hose; + edev->pe_config_addr = pe_no; + pe = eeh_pe_get(edev); + kfree(edev); + if (!pe) + return -ENODEV; + + /* Do error injection */ + ret = eeh_ops->err_inject(pe, type, func, addr, mask); + return ret < 0 ? ret : count; +} + +static const struct file_operations pnv_eeh_ei_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = pnv_eeh_ei_write, +}; + +static int pnv_eeh_dbgfs_set(void *data, int offset, u64 val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + out_be64(phb->regs + offset, val); + return 0; +} + +static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + *val = in_be64(phb->regs + offset); + return 0; +} + +static int pnv_eeh_outb_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD10, val); +} + +static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD10, val); +} + +static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD90, val); +} + +static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD90, val); +} + +static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xE10, val); +} + +static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xE10, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get, + pnv_eeh_outb_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get, + pnv_eeh_inbA_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get, + pnv_eeh_inbB_dbgfs_set, "0x%llx\n"); +#endif /* CONFIG_DEBUG_FS */ + /** - * powernv_eeh_post_init - EEH platform dependent post initialization + * pnv_eeh_post_init - EEH platform dependent post initialization * * EEH platform dependent post initialization on powernv. When * the function is called, the EEH PEs and devices should have * been built. If the I/O cache staff has been built, EEH is * ready to supply service. */ -static int powernv_eeh_post_init(void) +static int pnv_eeh_post_init(void) { struct pci_controller *hose; struct pnv_phb *phb; int ret = 0; + /* Register OPAL event notifier */ + if (!pnv_eeh_nb_init) { + ret = opal_notifier_register(&pnv_eeh_nb); + if (ret) { + pr_warn("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + + pnv_eeh_nb_init = true; + } + list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; - if (phb->eeh_ops && phb->eeh_ops->post_init) { - ret = phb->eeh_ops->post_init(hose); - if (ret) - break; - } + /* + * If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; + + /* Create debugfs entries */ +#ifdef CONFIG_DEBUG_FS + if (phb->has_dbgfs || !phb->dbgfs) + continue; + + phb->has_dbgfs = 1; + debugfs_create_file("err_injct", 0200, + phb->dbgfs, hose, + &pnv_eeh_ei_fops); + + debugfs_create_file("err_injct_outbound", 0600, + phb->dbgfs, hose, + &pnv_eeh_outb_dbgfs_ops); + debugfs_create_file("err_injct_inboundA", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbA_dbgfs_ops); + debugfs_create_file("err_injct_inboundB", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbB_dbgfs_ops); +#endif /* CONFIG_DEBUG_FS */ } + return ret; } +static int pnv_eeh_cap_start(struct pci_dn *pdn) +{ + u32 status; + + if (!pdn) + return 0; + + pnv_pci_cfg_read(pdn, PCI_STATUS, 2, &status); + if (!(status & PCI_STATUS_CAP_LIST)) + return 0; + + return PCI_CAPABILITY_LIST; +} + +static int pnv_eeh_find_cap(struct pci_dn *pdn, int cap) +{ + int pos = pnv_eeh_cap_start(pdn); + int cnt = 48; /* Maximal number of capabilities */ + u32 id; + + if (!pos) + return 0; + + while (cnt--) { + pnv_pci_cfg_read(pdn, pos, 1, &pos); + if (pos < 0x40) + break; + + pos &= ~3; + pnv_pci_cfg_read(pdn, pos + PCI_CAP_LIST_ID, 1, &id); + if (id == 0xff) + break; + + /* Found */ + if (id == cap) + return pos; + + /* Next one */ + pos += PCI_CAP_LIST_NEXT; + } + + return 0; +} + +static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 header; + int pos = 256, ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + return 0; + else if (!header) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < 256) + break; + + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** - * powernv_eeh_dev_probe - Do probe on PCI device - * @dev: PCI device - * @flag: unused + * pnv_eeh_probe - Do probe on PCI device + * @pdn: PCI device node + * @data: unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function @@ -129,12 +375,12 @@ static int powernv_eeh_post_init(void) * was possiblly triggered by EEH core, the binding between EEH device * and the PCI device isn't built yet. */ -static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) +static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); + struct pci_controller *hose = pdn->phb; struct pnv_phb *phb = hose->private_data; - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + uint32_t pcie_flags; int ret; /* @@ -143,40 +389,42 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * the root bridge. So it's not reasonable to continue * the probing. */ - if (!dn || !edev || edev->pe) - return 0; + if (!edev || edev->pe) + return NULL; /* Skip for PCI-ISA bridge */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA) - return 0; + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* Initialize eeh device */ - edev->class_code = dev->class; + edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); + if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; - edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (pci_is_pcie(dev)) { - edev->pcie_cap = pci_pcie_cap(dev); - - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - edev->mode |= EEH_DEV_ROOT_PORT; - else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) - edev->mode |= EEH_DEV_DS_PORT; - - edev->aer_cap = pci_find_ext_capability(dev, - PCI_EXT_CAP_ID_ERR); + if (edev->pcie_cap) { + pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS, + 2, &pcie_flags); + pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4; + if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT) + edev->mode |= EEH_DEV_ROOT_PORT; + else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM) + edev->mode |= EEH_DEV_DS_PORT; + } } - edev->config_addr = ((dev->bus->number << 8) | dev->devfn); - edev->pe_config_addr = phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff); + edev->config_addr = (pdn->busno << 8) | (pdn->devfn); + edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr]; /* Create PE */ ret = eeh_add_to_parent_pe(edev); if (ret) { - pr_warn("%s: Can't add PCI dev %s to parent PE (%d)\n", - __func__, pci_name(dev), ret); - return ret; + pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%d)\n", + __func__, hose->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret); + return NULL; } /* @@ -195,8 +443,10 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Broadcom Austin 4-ports NICs (14e4:1657) * Broadcom Shiner 2-ports 10G NICs (14e4:168e) */ - if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) || - (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e)) + if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x1657) || + (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x168e)) edev->pe->state |= EEH_PE_CFG_RESTRICTED; /* @@ -206,7 +456,8 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * to PE reset. */ if (!edev->pe->bus) - edev->pe->bus = dev->bus; + edev->pe->bus = pci_find_bus(hose->global_number, + pdn->busno); /* * Enable EEH explicitly so that we will do EEH check @@ -217,11 +468,11 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) /* Save memory bars */ eeh_save_bars(edev); - return 0; + return NULL; } /** - * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable + * pnv_eeh_set_option - Initialize EEH or MMIO/DMA reenable * @pe: EEH PE * @option: operation to be issued * @@ -229,36 +480,236 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Currently, following options are support according to PAPR: * Enable EEH, Disable EEH, Enable MMIO and Enable DMA */ -static int powernv_eeh_set_option(struct eeh_pe *pe, int option) +static int pnv_eeh_set_option(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + bool freeze_pe = false; + int opt, ret = 0; + s64 rc; + + /* Sanity check on option */ + switch (option) { + case EEH_OPT_DISABLE: + return -EPERM; + case EEH_OPT_ENABLE: + return 0; + case EEH_OPT_THAW_MMIO: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; + break; + case EEH_OPT_THAW_DMA: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; + break; + case EEH_OPT_FREEZE_PE: + freeze_pe = true; + opt = OPAL_EEH_ACTION_SET_FREEZE_ALL; + break; + default: + pr_warn("%s: Invalid option %d\n", __func__, option); + return -EINVAL; + } - /* - * What we need do is pass it down for hardware - * implementation to handle it. - */ - if (phb->eeh_ops && phb->eeh_ops->set_option) - ret = phb->eeh_ops->set_option(pe, option); + /* If PHB supports compound PE, to handle it */ + if (freeze_pe) { + if (phb->freeze_pe) { + phb->freeze_pe(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_set(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld freezing " + "PHB#%x-PE#%x\n", + __func__, rc, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } else { + if (phb->unfreeze_pe) { + ret = phb->unfreeze_pe(phb, pe->addr, opt); + } else { + rc = opal_pci_eeh_freeze_clear(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld enable %d " + "for PHB#%x-PE#%x\n", + __func__, rc, option, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } return ret; } /** - * powernv_eeh_get_pe_addr - Retrieve PE address + * pnv_eeh_get_pe_addr - Retrieve PE address * @pe: EEH PE * * Retrieve the PE address according to the given tranditional * PCI BDF (Bus/Device/Function) address. */ -static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) +static int pnv_eeh_get_pe_addr(struct eeh_pe *pe) { return pe->addr; } +static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + s64 rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Failure %lld getting PHB#%x diag-data\n", + __func__, rc, pe->phb->global_number); +} + +static int pnv_eeh_get_phb_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result = 0; + + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x state\n", + __func__, rc, phb->hose->global_number); + return EEH_STATE_NOT_SUPPORT; + } + + /* + * Check PHB state. If the PHB is frozen for the + * first time, to dump the PHB diag-data. + */ + if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + +static int pnv_eeh_get_pe_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result; + + /* + * We don't clobber hardware frozen state until PE + * reset is completed. In order to keep EEH core + * moving forward, we have to return operational + * state during PE reset. + */ + if (pe->state & EEH_PE_RESET) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + + /* + * Fetch PE state from hardware. If the PHB + * supports compound PE, let it handle that. + */ + if (phb->get_pe_state) { + fstate = phb->get_pe_state(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", + __func__, rc, phb->hose->global_number, + pe->addr); + return EEH_STATE_NOT_SUPPORT; + } + } + + /* Figure out state */ + switch (fstate) { + case OPAL_EEH_STOPPED_NOT_FROZEN: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_FREEZE: + result = (EEH_STATE_DMA_ACTIVE | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_DMA_FREEZE: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_MMIO_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: + result = 0; + break; + case OPAL_EEH_STOPPED_RESET: + result = EEH_STATE_RESET_ACTIVE; + break; + case OPAL_EEH_STOPPED_TEMP_UNAVAIL: + result = EEH_STATE_UNAVAILABLE; + break; + case OPAL_EEH_STOPPED_PERM_UNAVAIL: + result = EEH_STATE_NOT_SUPPORT; + break; + default: + result = EEH_STATE_NOT_SUPPORT; + pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", + __func__, phb->hose->global_number, + pe->addr, fstate); + } + + /* + * If PHB supports compound PE, to freeze all + * slave PEs for consistency. + * + * If the PE is switching to frozen state for the + * first time, to dump the PHB diag-data. + */ + if (!(result & EEH_STATE_NOT_SUPPORT) && + !(result & EEH_STATE_UNAVAILABLE) && + !(result & EEH_STATE_MMIO_ACTIVE) && + !(result & EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + if (phb->freeze_pe) + phb->freeze_pe(phb, pe->addr); + + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + /** - * powernv_eeh_get_state - Retrieve PE state + * pnv_eeh_get_state - Retrieve PE state * @pe: EEH PE * @delay: delay while PE state is temporarily unavailable * @@ -267,64 +718,279 @@ static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) * we prefer passing down to hardware implementation to handle * it. */ -static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay) +static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay) +{ + int ret; + + if (pe->type & EEH_PE_PHB) + ret = pnv_eeh_get_phb_state(pe); + else + ret = pnv_eeh_get_pe_state(pe); + + if (!delay) + return ret; + + /* + * If the PE state is temporarily unavailable, + * to inform the EEH core delay for default + * period (1 second) + */ + *delay = 0; + if (ret & EEH_STATE_UNAVAILABLE) + *delay = 1000; + + return ret; +} + +static s64 pnv_eeh_phb_poll(struct pnv_phb *phb) +{ + s64 rc = OPAL_HARDWARE; + + while (1) { + rc = opal_pci_poll(phb->opal_id); + if (rc <= 0) + break; + + if (system_state < SYSTEM_RUNNING) + udelay(1000 * rc); + else + msleep(rc); + } + + return rc; +} + +int pnv_eeh_phb_reset(struct pci_controller *hose, int option) { - struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = EEH_STATE_NOT_SUPPORT; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* Issue PHB complete reset request */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; - if (phb->eeh_ops && phb->eeh_ops->get_state) { - ret = phb->eeh_ops->get_state(pe); + /* + * Poll state of the PHB until the request is done + * successfully. The PHB reset is usually PHB complete + * reset followed by hot reset on root bus. So we also + * need the PCI bus settlement delay. + */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) { + if (system_state < SYSTEM_RUNNING) + udelay(1000 * EEH_PE_RST_SETTLE_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + } +out: + if (rc != OPAL_SUCCESS) + return -EIO; - /* - * If the PE state is temporarily unavailable, - * to inform the EEH core delay for default - * period (1 second) - */ - if (delay) { - *delay = 0; - if (ret & EEH_STATE_UNAVAILABLE) - *delay = 1000; + return 0; +} + +static int pnv_eeh_root_reset(struct pci_controller *hose, int option) +{ + struct pnv_phb *phb = hose->private_data; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* + * During the reset deassert time, we needn't care + * the reset scope because the firmware does nothing + * for fundamental or hot reset during deassert phase. + */ + if (option == EEH_RESET_FUNDAMENTAL) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_FUNDAMENTAL, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; + + /* Poll state of the PHB until the request is done */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); +out: + if (rc != OPAL_SUCCESS) + return -EIO; + + return 0; +} + +static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option) +{ + struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + int aer = edev ? edev->aer_cap : 0; + u32 ctrl; + + pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", + __func__, pci_domain_nr(dev->bus), + dev->bus->number, option); + + switch (option) { + case EEH_RESET_FUNDAMENTAL: + case EEH_RESET_HOT: + /* Don't report linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl |= PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); } + + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_HOLD_TIME); + break; + case EEH_RESET_DEACTIVATE: + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_SETTLE_TIME); + + /* Continue reporting linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl &= ~PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + + break; } - return ret; + return 0; +} + +void pnv_pci_reset_secondary_bus(struct pci_dev *dev) +{ + struct pci_controller *hose; + + if (pci_is_root_bus(dev->bus)) { + hose = pci_bus_to_host(dev->bus); + pnv_eeh_root_reset(hose, EEH_RESET_HOT); + pnv_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); + } else { + pnv_eeh_bridge_reset(dev, EEH_RESET_HOT); + pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); + } } /** - * powernv_eeh_reset - Reset the specified PE + * pnv_eeh_reset - Reset the specified PE * @pe: EEH PE * @option: reset option * - * Reset the specified PE + * Do reset on the indicated PE. For PCI bus sensitive PE, + * we need to reset the parent p2p bridge. The PHB has to + * be reinitialized if the p2p bridge is root bridge. For + * PCI device sensitive PE, we will try to reset the device + * through FLR. For now, we don't have OPAL APIs to do HARD + * reset yet, so all reset would be SOFT (HOT) reset. */ -static int powernv_eeh_reset(struct eeh_pe *pe, int option) +static int pnv_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + struct pci_bus *bus; + int ret; + + /* + * For PHB reset, we always have complete reset. For those PEs whose + * primary bus derived from root complex (root bus) or root port + * (usually bus#1), we apply hot or fundamental reset on the root port. + * For other PEs, we always have hot reset on the PE primary bus. + * + * Here, we have different design to pHyp, which always clear the + * frozen state during PE reset. However, the good idea here from + * benh is to keep frozen state before we get PE reset done completely + * (until BAR restore). With the frozen state, HW drops illegal IO + * or MMIO access, which can incur recrusive frozen PE during PE + * reset. The side effect is that EEH core has to clear the frozen + * state explicitly after BAR restore. + */ + if (pe->type & EEH_PE_PHB) { + ret = pnv_eeh_phb_reset(hose, option); + } else { + struct pnv_phb *phb; + s64 rc; - if (phb->eeh_ops && phb->eeh_ops->reset) - ret = phb->eeh_ops->reset(pe, option); + /* + * The frozen PE might be caused by PAPR error injection + * registers, which are expected to be cleared after hitting + * frozen PE as stated in the hardware spec. Unfortunately, + * that's not true on P7IOC. So we have to clear it manually + * to avoid recursive EEH errors during recovery. + */ + phb = hose->private_data; + if (phb->model == PNV_PHB_MODEL_P7IOC && + (option == EEH_RESET_HOT || + option == EEH_RESET_FUNDAMENTAL)) { + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_ERROR, + OPAL_ASSERT_RESET); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld clearing " + "error injection registers\n", + __func__, rc); + return -EIO; + } + } + + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus) || + pci_is_root_bus(bus->parent)) + ret = pnv_eeh_root_reset(hose, option); + else + ret = pnv_eeh_bridge_reset(bus->self, option); + } return ret; } /** - * powernv_eeh_wait_state - Wait for PE state + * pnv_eeh_wait_state - Wait for PE state * @pe: EEH PE * @max_wait: maximal period in microsecond * * Wait for the state of associated PE. It might take some time * to retrieve the PE's state. */ -static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) +static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait) { int ret; int mwait; while (1) { - ret = powernv_eeh_get_state(pe, &mwait); + ret = pnv_eeh_get_state(pe, &mwait); /* * If the PE's state is temporarily unavailable, @@ -348,7 +1014,7 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) } /** - * powernv_eeh_get_log - Retrieve error log + * pnv_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: temporary or permanent error log * @drv_log: driver log to be combined with retrieved error log @@ -356,41 +1022,30 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) * * Retrieve the temporary or permanent error from the PE. */ -static int powernv_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) +static int pnv_eeh_get_log(struct eeh_pe *pe, int severity, + char *drv_log, unsigned long len) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - if (phb->eeh_ops && phb->eeh_ops->get_log) - ret = phb->eeh_ops->get_log(pe, severity, drv_log, len); - - return ret; + return 0; } /** - * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE + * pnv_eeh_configure_bridge - Configure PCI bridges in the indicated PE * @pe: EEH PE * * The function will be called to reconfigure the bridges included * in the specified PE so that the mulfunctional PE would be recovered * again. */ -static int powernv_eeh_configure_bridge(struct eeh_pe *pe) +static int pnv_eeh_configure_bridge(struct eeh_pe *pe) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = 0; - - if (phb->eeh_ops && phb->eeh_ops->configure_bridge) - ret = phb->eeh_ops->configure_bridge(pe); - - return ret; + return 0; } /** - * powernv_pe_err_inject - Inject specified error to the indicated PE + * pnv_pe_err_inject - Inject specified error to the indicated PE * @pe: the indicated PE * @type: error type * @func: specific error type @@ -401,22 +1056,52 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe) * determined by @type and @func, to the indicated PE for * testing purpose. */ -static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) +static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func, + unsigned long addr, unsigned long mask) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + s64 rc; + + /* Sanity check on error type */ + if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && + type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { + pr_warn("%s: Invalid error type %d\n", + __func__, type); + return -ERANGE; + } - if (phb->eeh_ops && phb->eeh_ops->err_inject) - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); + if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || + func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { + pr_warn("%s: Invalid error function %d\n", + __func__, func); + return -ERANGE; + } - return ret; + /* Firmware supports error injection ? */ + if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { + pr_warn("%s: Firmware doesn't support error injection\n", + __func__); + return -ENXIO; + } + + /* Do error injection */ + rc = opal_pci_err_inject(phb->opal_id, pe->addr, + type, func, addr, mask); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld injecting error " + "%d-%d to PHB#%x-PE#%x\n", + __func__, rc, type, func, + hose->global_number, pe->addr); + return -EIO; + } + + return 0; } -static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) +static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); if (!edev || !edev->pe) return false; @@ -427,51 +1112,377 @@ static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) return false; } -static int powernv_eeh_read_config(struct device_node *dn, - int where, int size, u32 *val) +static int pnv_eeh_read_config(struct pci_dn *pdn, + int where, int size, u32 *val) { - if (powernv_eeh_cfg_blocked(dn)) { + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) { *val = 0xFFFFFFFF; return PCIBIOS_SET_FAILED; } - return pnv_pci_cfg_read(dn, where, size, val); + return pnv_pci_cfg_read(pdn, where, size, val); } -static int powernv_eeh_write_config(struct device_node *dn, - int where, int size, u32 val) +static int pnv_eeh_write_config(struct pci_dn *pdn, + int where, int size, u32 val) { - if (powernv_eeh_cfg_blocked(dn)) + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) return PCIBIOS_SET_FAILED; - return pnv_pci_cfg_write(dn, where, size, val); + return pnv_pci_cfg_write(pdn, where, size, val); +} + +static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data) +{ + /* GEM */ + if (data->gemXfir || data->gemRfir || + data->gemRirqfir || data->gemMask || data->gemRwof) + pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->gemXfir), + be64_to_cpu(data->gemRfir), + be64_to_cpu(data->gemRirqfir), + be64_to_cpu(data->gemMask), + be64_to_cpu(data->gemRwof)); + + /* LEM */ + if (data->lemFir || data->lemErrMask || + data->lemAction0 || data->lemAction1 || data->lemWof) + pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->lemFir), + be64_to_cpu(data->lemErrMask), + be64_to_cpu(data->lemAction0), + be64_to_cpu(data->lemAction1), + be64_to_cpu(data->lemWof)); +} + +static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; + long rc; + + rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", + __func__, phb->hub_id, rc); + return; + } + + switch (data->type) { + case OPAL_P7IOC_DIAG_TYPE_RGC: + pr_info("P7IOC diag-data for RGC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + if (data->rgc.rgcStatus || data->rgc.rgcLdcp) + pr_info(" RGC: %016llx %016llx\n", + be64_to_cpu(data->rgc.rgcStatus), + be64_to_cpu(data->rgc.rgcLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_BI: + pr_info("P7IOC diag-data for BI %s\n\n", + data->bi.biDownbound ? "Downbound" : "Upbound"); + pnv_eeh_dump_hub_diag_common(data); + if (data->bi.biLdcp0 || data->bi.biLdcp1 || + data->bi.biLdcp2 || data->bi.biFenceStatus) + pr_info(" BI: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->bi.biLdcp0), + be64_to_cpu(data->bi.biLdcp1), + be64_to_cpu(data->bi.biLdcp2), + be64_to_cpu(data->bi.biFenceStatus)); + break; + case OPAL_P7IOC_DIAG_TYPE_CI: + pr_info("P7IOC diag-data for CI Port %d\n\n", + data->ci.ciPort); + pnv_eeh_dump_hub_diag_common(data); + if (data->ci.ciPortStatus || data->ci.ciPortLdcp) + pr_info(" CI: %016llx %016llx\n", + be64_to_cpu(data->ci.ciPortStatus), + be64_to_cpu(data->ci.ciPortLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_MISC: + pr_info("P7IOC diag-data for MISC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + case OPAL_P7IOC_DIAG_TYPE_I2C: + pr_info("P7IOC diag-data for I2C\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + default: + pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", + __func__, phb->hub_id, data->type); + } +} + +static int pnv_eeh_get_pe(struct pci_controller *hose, + u16 pe_no, struct eeh_pe **pe) +{ + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pnv_pe; + struct eeh_pe *dev_pe; + struct eeh_dev edev; + + /* + * If PHB supports compound PE, to fetch + * the master PE because slave PE is invisible + * to EEH core. + */ + pnv_pe = &phb->ioda.pe_array[pe_no]; + if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { + pnv_pe = pnv_pe->master; + WARN_ON(!pnv_pe || + !(pnv_pe->flags & PNV_IODA_PE_MASTER)); + pe_no = pnv_pe->pe_number; + } + + /* Find the PE according to PE# */ + memset(&edev, 0, sizeof(struct eeh_dev)); + edev.phb = hose; + edev.pe_config_addr = pe_no; + dev_pe = eeh_pe_get(&edev); + if (!dev_pe) + return -EEXIST; + + /* Freeze the (compound) PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, pe_no); + + /* + * At this point, we're sure the (compound) PE should + * have been frozen. However, we still need poke until + * hitting the frozen PE on top level. + */ + dev_pe = dev_pe->parent; + while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { + int ret; + int active_flags = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE); + + ret = eeh_ops->get_state(dev_pe, NULL); + if (ret <= 0 || (ret & active_flags) == active_flags) { + dev_pe = dev_pe->parent; + continue; + } + + /* Frozen parent PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, dev_pe->addr); + + /* Next one */ + dev_pe = dev_pe->parent; + } + + return 0; } /** - * powernv_eeh_next_error - Retrieve next EEH error to handle + * pnv_eeh_next_error - Retrieve next EEH error to handle * @pe: Affected PE * - * Using OPAL API, to retrieve next EEH error for EEH core to handle + * The function is expected to be called by EEH core while it gets + * special EEH event (without binding PE). The function calls to + * OPAL APIs for next error to handle. The informational error is + * handled internally by platform. However, the dead IOC, dead PHB, + * fenced PHB and frozen PE should be handled by EEH core eventually. */ -static int powernv_eeh_next_error(struct eeh_pe **pe) +static int pnv_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose; - struct pnv_phb *phb = NULL; + struct pnv_phb *phb; + struct eeh_pe *phb_pe, *parent_pe; + __be64 frozen_pe_no; + __be16 err_type, severity; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + long rc; + int state, ret = EEH_NEXT_ERR_NONE; + + /* + * While running here, it's safe to purge the event queue. + * And we should keep the cached OPAL notifier event sychronized + * between the kernel and firmware. + */ + eeh_remove_event(NULL, false); + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry(hose, &hose_list, list_node) { + /* + * If the subordinate PCI buses of the PHB has been + * removed or is exactly under error recovery, we + * needn't take care of it any more. + */ phb = hose->private_data; - break; - } + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) + continue; + + rc = opal_pci_next_error(phb->opal_id, + &frozen_pe_no, &err_type, &severity); + if (rc != OPAL_SUCCESS) { + pr_devel("%s: Invalid return value on " + "PHB#%x (0x%lx) from opal_pci_next_error", + __func__, hose->global_number, rc); + continue; + } + + /* If the PHB doesn't have error, stop processing */ + if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || + be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { + pr_devel("%s: No error found on PHB#%x\n", + __func__, hose->global_number); + continue; + } + + /* + * Processing the error. We're expecting the error with + * highest priority reported upon multiple errors on the + * specific PHB. + */ + pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", + __func__, be16_to_cpu(err_type), + be16_to_cpu(severity), be64_to_cpu(frozen_pe_no), + hose->global_number); + switch (be16_to_cpu(err_type)) { + case OPAL_EEH_IOC_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { + pr_err("EEH: dead IOC detected\n"); + ret = EEH_NEXT_ERR_DEAD_IOC; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: IOC informative error " + "detected\n"); + pnv_eeh_get_and_dump_hub_diag(hose); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PHB_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { + *pe = phb_pe; + pr_err("EEH: dead PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_DEAD_PHB; + } else if (be16_to_cpu(severity) == + OPAL_EEH_SEV_PHB_FENCED) { + *pe = phb_pe; + pr_err("EEH: Fenced PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FENCED_PHB; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: PHB#%x informative error " + "detected, location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + pnv_eeh_get_phb_diag(phb_pe); + pnv_pci_dump_phb_diag_data(hose, phb_pe->data); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PE_ERROR: + /* + * If we can't find the corresponding PE, we + * just try to unfreeze. + */ + if (pnv_eeh_get_pe(hose, + be64_to_cpu(frozen_pe_no), pe)) { + /* Try best to clear it */ + pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", + hose->global_number, frozen_pe_no); + pr_info("EEH: PHB location: %s\n", + eeh_pe_loc_get(phb_pe)); + opal_pci_eeh_freeze_clear(phb->opal_id, + frozen_pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + ret = EEH_NEXT_ERR_NONE; + } else if ((*pe)->state & EEH_PE_ISOLATED || + eeh_pe_passed(*pe)) { + ret = EEH_NEXT_ERR_NONE; + } else { + pr_err("EEH: Frozen PE#%x " + "on PHB#%x detected\n", + (*pe)->addr, + (*pe)->phb->global_number); + pr_err("EEH: PE location: %s, " + "PHB location: %s\n", + eeh_pe_loc_get(*pe), + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FROZEN_PE; + } + + break; + default: + pr_warn("%s: Unexpected error type %d\n", + __func__, be16_to_cpu(err_type)); + } - if (phb && phb->eeh_ops->next_error) - return phb->eeh_ops->next_error(pe); + /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(*pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data((*pe)->phb, + (*pe)->data); + } - return -EEXIST; + /* + * We probably have the frozen parent PE out there and + * we need have to handle frozen parent PE firstly. + */ + if (ret == EEH_NEXT_ERR_FROZEN_PE) { + parent_pe = (*pe)->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + state = eeh_ops->get_state(parent_pe, NULL); + if (state > 0 && + (state & active_flags) != active_flags) + *pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + + /* We possibly migrate to another PE */ + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + } + + /* + * If we have no errors on the specific PHB or only + * informative error there, we continue poking it. + * Otherwise, we need actions to be taken by upper + * layer. + */ + if (ret > EEH_NEXT_ERR_INF) + break; + } + + return ret; } -static int powernv_eeh_restore_config(struct device_node *dn) +static int pnv_eeh_restore_config(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); struct pnv_phb *phb; s64 ret; @@ -490,24 +1501,23 @@ static int powernv_eeh_restore_config(struct device_node *dn) return 0; } -static struct eeh_ops powernv_eeh_ops = { +static struct eeh_ops pnv_eeh_ops = { .name = "powernv", - .init = powernv_eeh_init, - .post_init = powernv_eeh_post_init, - .of_probe = NULL, - .dev_probe = powernv_eeh_dev_probe, - .set_option = powernv_eeh_set_option, - .get_pe_addr = powernv_eeh_get_pe_addr, - .get_state = powernv_eeh_get_state, - .reset = powernv_eeh_reset, - .wait_state = powernv_eeh_wait_state, - .get_log = powernv_eeh_get_log, - .configure_bridge = powernv_eeh_configure_bridge, - .err_inject = powernv_eeh_err_inject, - .read_config = powernv_eeh_read_config, - .write_config = powernv_eeh_write_config, - .next_error = powernv_eeh_next_error, - .restore_config = powernv_eeh_restore_config + .init = pnv_eeh_init, + .post_init = pnv_eeh_post_init, + .probe = pnv_eeh_probe, + .set_option = pnv_eeh_set_option, + .get_pe_addr = pnv_eeh_get_pe_addr, + .get_state = pnv_eeh_get_state, + .reset = pnv_eeh_reset, + .wait_state = pnv_eeh_wait_state, + .get_log = pnv_eeh_get_log, + .configure_bridge = pnv_eeh_configure_bridge, + .err_inject = pnv_eeh_err_inject, + .read_config = pnv_eeh_read_config, + .write_config = pnv_eeh_write_config, + .next_error = pnv_eeh_next_error, + .restore_config = pnv_eeh_restore_config }; /** @@ -521,7 +1531,7 @@ static int __init eeh_powernv_init(void) int ret = -EINVAL; eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE); - ret = eeh_ops_register(&powernv_eeh_ops); + ret = eeh_ops_register(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); else diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 23260f7dfa7a..5aa9c1ce4de3 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -452,5 +452,6 @@ void __init opal_platform_dump_init(void) return; } - opal_dump_resend_notification(); + if (opal_check_token(OPAL_DUMP_RESEND)) + opal_dump_resend_notification(); } diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 518fe95dbf24..38ce757e5e2a 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -313,7 +313,8 @@ int __init opal_elog_init(void) } /* We are now ready to pull error logs from opal. */ - opal_resend_pending_logs(); + if (opal_check_token(OPAL_ELOG_RESEND)) + opal_resend_pending_logs(); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 5c21d9c07f45..4ec6219287fc 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -120,7 +120,11 @@ static struct image_header_t image_header; static struct image_data_t image_data; static struct validate_flash_t validate_flash_data; static struct manage_flash_t manage_flash_data; -static struct update_flash_t update_flash_data; + +/* Initialize update_flash_data status to No Operation */ +static struct update_flash_t update_flash_data = { + .status = FLASH_NO_OP, +}; static DEFINE_MUTEX(image_data_mutex); @@ -542,7 +546,7 @@ static struct attribute_group image_op_attr_group = { .attrs = image_op_attrs, }; -void __init opal_flash_init(void) +void __init opal_flash_update_init(void) { int ret; diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index f9896fd5d04a..9db4398ded5d 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <asm/opal.h> +#include <asm/nvram.h> #include <asm/machdep.h> static unsigned int nvram_size; @@ -62,6 +63,15 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) return count; } +static int __init opal_nvram_init_log_partitions(void) +{ + /* Scan nvram for partitions */ + nvram_scan_partitions(); + nvram_init_oops_partition(0); + return 0; +} +machine_arch_initcall(powernv, opal_nvram_init_log_partitions); + void __init opal_nvram_init(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c index 4ab67ef7abc9..655250499d18 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor.c +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -46,18 +46,28 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data) mutex_lock(&opal_sensor_mutex); ret = opal_sensor_read(sensor_hndl, token, &data); - if (ret != OPAL_ASYNC_COMPLETION) - goto out_token; + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_err("%s: Failed to wait for the async response, %d\n", + __func__, ret); + goto out_token; + } - ret = opal_async_wait_response(token, &msg); - if (ret) { - pr_err("%s: Failed to wait for the async response, %d\n", - __func__, ret); - goto out_token; - } + ret = opal_error_code(be64_to_cpu(msg.params[1])); + *sensor_data = be32_to_cpu(data); + break; + + case OPAL_SUCCESS: + ret = 0; + *sensor_data = be32_to_cpu(data); + break; - *sensor_data = be32_to_cpu(data); - ret = be64_to_cpu(msg.params[1]); + default: + ret = opal_error_code(ret); + break; + } out_token: mutex_unlock(&opal_sensor_mutex); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index fcbe899fe299..a7ade94cdf87 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -286,9 +286,12 @@ OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); -OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CXL_MODE); +OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CAPI_MODE); OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST); +OPAL_CALL(opal_flash_read, OPAL_FLASH_READ); +OPAL_CALL(opal_flash_write, OPAL_FLASH_WRITE); +OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 18fd4e71c9c1..2241565b0739 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -23,6 +23,8 @@ #include <linux/kobject.h> #include <linux/delay.h> #include <linux/memblock.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <asm/machdep.h> #include <asm/opal.h> @@ -58,6 +60,7 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); +static uint32_t opal_heartbeat; static void opal_reinit_cores(void) { @@ -302,23 +305,26 @@ void opal_notifier_disable(void) * Opal message notifier based on message type. Allow subscribers to get * notified for specific messgae type. */ -int opal_message_notifier_register(enum OpalMessageType msg_type, +int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb) { - if (!nb) { - pr_warning("%s: Invalid argument (%p)\n", - __func__, nb); - return -EINVAL; - } - if (msg_type > OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Invalid message type argument (%d)\n", + if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Invalid arguments, msg_type:%d\n", __func__, msg_type); return -EINVAL; } + return atomic_notifier_chain_register( &opal_msg_notifier_head[msg_type], nb); } +int opal_message_notifier_unregister(enum opal_msg_type msg_type, + struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister( + &opal_msg_notifier_head[msg_type], nb); +} + static void opal_message_do_notify(uint32_t msg_type, void *msg) { /* notify subscribers */ @@ -351,7 +357,7 @@ static void opal_handle_message(void) type = be32_to_cpu(msg.msg_type); /* Sanity check */ - if (type > OPAL_MSG_TYPE_MAX) { + if (type >= OPAL_MSG_TYPE_MAX) { pr_warning("%s: Unknown message type: %u\n", __func__, type); return; } @@ -665,6 +671,9 @@ static void __init opal_dump_region_init(void) uint64_t size; int rc; + if (!opal_check_token(OPAL_REGISTER_DUMP_REGION)) + return; + /* Register kernel log buffer */ addr = log_buf_addr_get(); if (addr == NULL) @@ -684,6 +693,15 @@ static void __init opal_dump_region_init(void) "rc = %d\n", rc); } +static void opal_flash_init(struct device_node *opal_node) +{ + struct device_node *np; + + for_each_child_of_node(opal_node, np) + if (of_device_is_compatible(np, "ibm,opal-flash")) + of_platform_device_create(np, NULL, NULL); +} + static void opal_ipmi_init(struct device_node *opal_node) { struct device_node *np; @@ -741,6 +759,29 @@ static void __init opal_irq_init(struct device_node *dn) } } +static int kopald(void *unused) +{ + set_freezable(); + do { + try_to_freeze(); + opal_poll_events(NULL); + msleep_interruptible(opal_heartbeat); + } while (!kthread_should_stop()); + + return 0; +} + +static void opal_init_heartbeat(void) +{ + /* Old firwmware, we assume the HVC heartbeat is sufficient */ + if (of_property_read_u32(opal_node, "ibm,heartbeat-ms", + &opal_heartbeat) != 0) + opal_heartbeat = 0; + + if (opal_heartbeat) + kthread_run(kopald, NULL, "kopald"); +} + static int __init opal_init(void) { struct device_node *np, *consoles; @@ -769,6 +810,9 @@ static int __init opal_init(void) /* Create i2c platform devices */ opal_i2c_create_devs(); + /* Setup a heatbeat thread if requested by OPAL */ + opal_init_heartbeat(); + /* Find all OPAL interrupts and request them */ opal_irq_init(opal_node); @@ -782,7 +826,7 @@ static int __init opal_init(void) /* Setup error log interface */ rc = opal_elog_init(); /* Setup code update interface */ - opal_flash_init(); + opal_flash_update_init(); /* Setup platform dump extract interface */ opal_platform_dump_init(); /* Setup system parameters interface */ @@ -791,8 +835,11 @@ static int __init opal_init(void) opal_msglog_init(); } + /* Initialize OPAL IPMI backend */ opal_ipmi_init(opal_node); + opal_flash_init(opal_node); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -823,13 +870,17 @@ void opal_shutdown(void) } /* Unregister memory dump region */ - opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); + if (opal_check_token(OPAL_UNREGISTER_DUMP_REGION)) + opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); } /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); EXPORT_SYMBOL_GPL(opal_ipmi_send); EXPORT_SYMBOL_GPL(opal_ipmi_recv); +EXPORT_SYMBOL_GPL(opal_flash_read); +EXPORT_SYMBOL_GPL(opal_flash_write); +EXPORT_SYMBOL_GPL(opal_flash_erase); /* Convert a region of vmalloc memory to an opal sg list */ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, @@ -894,6 +945,25 @@ void opal_free_sg_list(struct opal_sg_list *sg) } } +int opal_error_code(int rc) +{ + switch (rc) { + case OPAL_SUCCESS: return 0; + + case OPAL_PARAMETER: return -EINVAL; + case OPAL_ASYNC_COMPLETION: return -EINPROGRESS; + case OPAL_BUSY_EVENT: return -EBUSY; + case OPAL_NO_MEM: return -ENOMEM; + + case OPAL_UNSUPPORTED: return -EIO; + case OPAL_HARDWARE: return -EIO; + case OPAL_INTERNAL_ERROR: return -EIO; + default: + pr_err("%s: unexpected OPAL error %d\n", __func__, rc); + return -EIO; + } +} + EXPORT_SYMBOL_GPL(opal_poll_events); EXPORT_SYMBOL_GPL(opal_rtc_read); EXPORT_SYMBOL_GPL(opal_rtc_write); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6c9ff2b95119..920c252d1f49 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -44,6 +44,9 @@ #include "powernv.h" #include "pci.h" +/* 256M DMA window, 4K TCE pages, 8 bytes TCE */ +#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) + static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...) { @@ -56,11 +59,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, vaf.fmt = fmt; vaf.va = &args; - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix)); - else + else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) sprintf(pfix, "%04x:%02x ", pci_domain_nr(pe->pbus), pe->pbus->number); +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + sprintf(pfix, "%04x:%02x:%2x.%d", + pci_domain_nr(pe->parent_dev->bus), + (pe->rid & 0xff00) >> 8, + PCI_SLOT(pe->rid), PCI_FUNC(pe->rid)); +#endif /* CONFIG_PCI_IOV*/ printk("%spci %s: [PE# %.3d] %pV", level, pfix, pe->pe_number, &vaf); @@ -591,7 +601,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, bool is_add) { struct pnv_ioda_pe *slave; - struct pci_dev *pdev; + struct pci_dev *pdev = NULL; int ret; /* @@ -630,8 +640,12 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS)) pdev = pe->pbus->self; - else + else if (pe->flags & PNV_IODA_PE_DEV) pdev = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + pdev = pe->parent_dev->bus->self; +#endif /* CONFIG_PCI_IOV */ while (pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *parent; @@ -649,6 +663,87 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, return 0; } +#ifdef CONFIG_PCI_IOV +static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) +{ + struct pci_dev *parent; + uint8_t bcomp, dcomp, fcomp; + int64_t rc; + long rid_end, rid; + + /* Currently, we just deconfigure VF PE. Bus PE will always there.*/ + if (pe->pbus) { + int count; + + dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; + fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; + parent = pe->pbus->self; + if (pe->flags & PNV_IODA_PE_BUS_ALL) + count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1; + else + count = 1; + + switch(count) { + case 1: bcomp = OpalPciBusAll; break; + case 2: bcomp = OpalPciBus7Bits; break; + case 4: bcomp = OpalPciBus6Bits; break; + case 8: bcomp = OpalPciBus5Bits; break; + case 16: bcomp = OpalPciBus4Bits; break; + case 32: bcomp = OpalPciBus3Bits; break; + default: + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); + /* Do an exact match only */ + bcomp = OpalPciBusAll; + } + rid_end = pe->rid + (count << 8); + } else { + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else + parent = pe->pdev->bus->self; + bcomp = OpalPciBusAll; + dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; + fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; + rid_end = pe->rid + 1; + } + + /* Clear the reverse map */ + for (rid = pe->rid; rid < rid_end; rid++) + phb->ioda.pe_rmap[rid] = 0; + + /* Release from all parents PELT-V */ + while (parent) { + struct pci_dn *pdn = pci_get_pdn(parent); + if (pdn && pdn->pe_number != IODA_INVALID_PE) { + rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + /* XXX What to do in case of error ? */ + } + parent = parent->bus->self; + } + + opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + + /* Disassociate PE in PELT */ + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc); + rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, + bcomp, dcomp, fcomp, OPAL_UNMAP_PE); + if (rc) + pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); + + pe->pbus = NULL; + pe->pdev = NULL; + pe->parent_dev = NULL; + + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; @@ -675,15 +770,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) case 16: bcomp = OpalPciBus4Bits; break; case 32: bcomp = OpalPciBus3Bits; break; default: - pr_err("%s: Number of subordinate busses %d" - " unsupported\n", - pci_name(pe->pbus->self), count); + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); /* Do an exact match only */ bcomp = OpalPciBusAll; } rid_end = pe->rid + (count << 8); } else { - parent = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else +#endif /* CONFIG_PCI_IOV */ + parent = pe->pdev->bus->self; bcomp = OpalPciBusAll; dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; @@ -774,6 +873,78 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev) return 10; } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) +{ + struct pci_dn *pdn = pci_get_pdn(dev); + int i; + struct resource *res, res2; + resource_size_t size; + u16 num_vfs; + + if (!dev->is_physfn) + return -EINVAL; + + /* + * "offset" is in VFs. The M64 windows are sized so that when they + * are segmented, each segment is the same size as the IOV BAR. + * Each segment is in a separate PE, and the high order bits of the + * address are the PE number. Therefore, each VF's BAR is in a + * separate PE, and changing the IOV BAR start address changes the + * range of PEs the VFs are in. + */ + num_vfs = pdn->num_vfs; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + /* + * The actual IOV BAR range is determined by the start address + * and the actual size for num_vfs VFs BAR. This check is to + * make sure that after shifting, the range will not overlap + * with another device. + */ + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2.flags = res->flags; + res2.start = res->start + (size * offset); + res2.end = res2.start + (size * num_vfs) - 1; + + if (res2.end > res->end) { + dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + return -EBUSY; + } + } + + /* + * After doing so, there would be a "hole" in the /proc/iomem when + * offset is a positive value. It looks like the device return some + * mmio back to the system, which actually no one could use it. + */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2 = *res; + res->start += size * offset; + + dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (enabling %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + pci_update_resource(dev, i + PCI_IOV_RESOURCES); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + #if 0 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { @@ -857,7 +1028,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } - pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) @@ -916,6 +1086,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all) return; } + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + /* Associate it with all child devices */ pnv_ioda_setup_same_PE(bus, pe); @@ -974,6 +1148,441 @@ static void pnv_pci_ioda_setup_PEs(void) } } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_release_m64(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int i, j; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) { + if (pdn->m64_wins[i][j] == IODA_INVALID_M64) + continue; + opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0); + clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc); + pdn->m64_wins[i][j] = IODA_INVALID_M64; + } + + return 0; +} + +static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + unsigned int win; + struct resource *res; + int i, j; + int64_t rc; + int total_vfs; + resource_size_t size, start; + int pe_num; + int vf_groups; + int vf_per_group; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + total_vfs = pci_sriov_get_totalvfs(pdev); + + /* Initialize the m64_wins to IODA_INVALID_M64 */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) + pdn->m64_wins[i][j] = IODA_INVALID_M64; + + if (pdn->m64_per_iov == M64_PER_IOV) { + vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV; + vf_per_group = (num_vfs <= M64_PER_IOV)? 1: + roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + } else { + vf_groups = 1; + vf_per_group = 1; + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + for (j = 0; j < vf_groups; j++) { + do { + win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, + phb->ioda.m64_bar_idx + 1, 0); + + if (win >= phb->ioda.m64_bar_idx + 1) + goto m64_failed; + } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); + + pdn->m64_wins[i][j] = win; + + if (pdn->m64_per_iov == M64_PER_IOV) { + size = pci_iov_resource_size(pdev, + PCI_IOV_RESOURCES + i); + size = size * vf_per_group; + start = res->start + size * j; + } else { + size = resource_size(res); + start = res->start; + } + + /* Map the M64 here */ + if (pdn->m64_per_iov == M64_PER_IOV) { + pe_num = pdn->offset + j; + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + pe_num, OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], 0); + } + + rc = opal_pci_set_phb_mem_window(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], + start, + 0, /* unused */ + size); + + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n", + win, rc); + goto m64_failed; + } + + if (pdn->m64_per_iov == M64_PER_IOV) + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2); + else + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1); + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n", + win, rc); + goto m64_failed; + } + } + } + return 0; + +m64_failed: + pnv_pci_vf_release_m64(pdev); + return -EBUSY; +} + +static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct iommu_table *tbl; + unsigned long addr; + int64_t rc; + + bus = dev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + tbl = pe->tce32_table; + addr = tbl->it_base; + + opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + 0, 0x1000); + + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + (pe->pe_number << 1) + 1, + pe->tce_bypass_base, + 0); + if (rc) + pe_warn(pe, "OPAL error %ld release DMA window\n", rc); + + iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); + free_pages(addr, get_order(TCE32_TABLE_SIZE)); + pe->tce32_table = NULL; +} + +static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe, *pe_n; + struct pci_dn *pdn; + u16 vf_index; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++){ + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_REMOVE_PE_FROM_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + + list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { + if (pe->parent_dev != pdev) + continue; + + pnv_pci_ioda2_release_dma_pe(pdev, pe); + + /* Remove from list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_del(&pe->list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_ioda_deconfigure_pe(phb, pe); + + pnv_ioda_free_pe(phb, pe->pe_number); + } +} + +void pnv_pci_sriov_disable(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + struct pci_sriov *iov; + u16 num_vfs; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + iov = pdev->sriov; + num_vfs = pdn->num_vfs; + + /* Release VF PEs */ + pnv_ioda_release_vf_PE(pdev, num_vfs); + + if (phb->type == PNV_PHB_IODA2) { + if (pdn->m64_per_iov == 1) + pnv_pci_vf_resource_shift(pdev, -pdn->offset); + + /* Release M64 windows */ + pnv_pci_vf_release_m64(pdev); + + /* Release PE numbers */ + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + } +} + +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe); +static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + int pe_num; + u16 vf_index; + struct pci_dn *pdn; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + /* Reserve PE for each VF */ + for (vf_index = 0; vf_index < num_vfs; vf_index++) { + pe_num = pdn->offset + vf_index; + + pe = &phb->ioda.pe_array[pe_num]; + pe->pe_number = pe_num; + pe->phb = phb; + pe->flags = PNV_IODA_PE_VF; + pe->pbus = NULL; + pe->parent_dev = pdev; + pe->tce32_seg = -1; + pe->mve_number = -1; + pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) | + pci_iov_virtfn_devfn(pdev, vf_index); + + pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n", + hose->global_number, pdev->bus->number, + PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)), + PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num); + + if (pnv_ioda_configure_pe(phb, pe)) { + /* XXX What do we do here ? */ + if (pe_num) + pnv_ioda_free_pe(phb, pe_num); + pe->pdev = NULL; + continue; + } + + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + + /* Put PE to the list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_add_tail(&pe->list, &phb->ioda.pe_list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) { + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) { + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++) { + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_ADD_PE_TO_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + } + } +} + +int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int ret; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (phb->type == PNV_PHB_IODA2) { + /* Calculate available PE for required VFs */ + mutex_lock(&phb->ioda.pe_alloc_mutex); + pdn->offset = bitmap_find_next_zero_area( + phb->ioda.pe_alloc, phb->ioda.total_pe, + 0, num_vfs, 0); + if (pdn->offset >= phb->ioda.total_pe) { + mutex_unlock(&phb->ioda.pe_alloc_mutex); + dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); + pdn->offset = 0; + return -EBUSY; + } + bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->num_vfs = num_vfs; + mutex_unlock(&phb->ioda.pe_alloc_mutex); + + /* Assign M64 window accordingly */ + ret = pnv_pci_vf_assign_m64(pdev, num_vfs); + if (ret) { + dev_info(&pdev->dev, "Not enough M64 window resources\n"); + goto m64_failed; + } + + /* + * When using one M64 BAR to map one IOV BAR, we need to shift + * the IOV BAR according to the PE# allocated to the VFs. + * Otherwise, the PE# for the VF will conflict with others. + */ + if (pdn->m64_per_iov == 1) { + ret = pnv_pci_vf_resource_shift(pdev, pdn->offset); + if (ret) + goto m64_failed; + } + } + + /* Setup VF PEs */ + pnv_ioda_setup_vf_PE(pdev, num_vfs); + + return 0; + +m64_failed: + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + + return ret; +} + +int pcibios_sriov_disable(struct pci_dev *pdev) +{ + pnv_pci_sriov_disable(pdev); + + /* Release PCI data */ + remove_dev_pci_data(pdev); + return 0; +} + +int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + /* Allocate PCI data */ + add_dev_pci_data(pdev); + + pnv_pci_sriov_enable(pdev, num_vfs); + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); @@ -989,7 +1598,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev pe = &phb->ioda.pe_array[pdn->pe_number]; WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); - set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table); } static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, @@ -1016,7 +1625,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, } else { dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); set_dma_ops(&pdev->dev, &dma_iommu_ops); - set_iommu_table_base(&pdev->dev, &pe->tce32_table); + set_iommu_table_base(&pdev->dev, pe->tce32_table); } *pdev->dev.dma_mask = dma_mask; return 0; @@ -1053,9 +1662,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, list_for_each_entry(dev, &bus->devices, bus_list) { if (add_to_iommu_group) set_iommu_table_base_and_group(&dev->dev, - &pe->tce32_table); + pe->tce32_table); else - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base(&dev->dev, pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate, @@ -1145,8 +1754,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; struct pnv_phb *phb = pe->phb; if (phb->type == PNV_PHB_IODA1) @@ -1167,9 +1775,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, int64_t rc; void *addr; - /* 256M DMA window, 4K TCE pages, 8 bytes TCE */ -#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) - /* XXX FIXME: Handle 64-bit only DMA devices */ /* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */ /* XXX FIXME: Allocate multi-level tables on PHB3 */ @@ -1212,7 +1817,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs, base << 28, IOMMU_PAGE_SHIFT_4K); @@ -1232,12 +1837,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } return; fail: @@ -1250,8 +1862,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -1296,10 +1907,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, pe->tce_bypass_base = 1ull << 59; /* Install set_bypass callback for VFIO */ - pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass; /* Enable bypass by default */ - pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); + pnv_pci_ioda2_set_bypass(pe->tce32_table, true); } static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, @@ -1347,7 +1958,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0, IOMMU_PAGE_SHIFT_4K); @@ -1365,12 +1976,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } /* Also create a bypass window */ if (!pnv_iommu_bypass_disabled) @@ -1731,6 +2349,73 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } #endif /* CONFIG_PCI_MSI */ +#ifdef CONFIG_PCI_IOV +static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + struct resource *res; + int i; + resource_size_t size; + struct pci_dn *pdn; + int mul, total_vfs; + + if (!pdev->is_physfn || pdev->is_added) + return; + + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + + pdn = pci_get_pdn(pdev); + pdn->vfs_expanded = 0; + + total_vfs = pci_sriov_get_totalvfs(pdev); + pdn->m64_per_iov = 1; + mul = phb->ioda.total_pe; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n", + i, res); + continue; + } + + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + + /* bigger than 64M */ + if (size > (1 << 26)) { + dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n", + i, res); + pdn->m64_per_iov = M64_PER_IOV; + mul = roundup_pow_of_two(total_vfs); + break; + } + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n", + i, res); + continue; + } + + dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + res->end = res->start + size * mul - 1; + dev_dbg(&pdev->dev, " %pR\n", res); + dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", + i, res, mul); + } + pdn->vfs_expanded = mul; +} +#endif /* CONFIG_PCI_IOV */ + /* * This function is supposed to be called on basis of PE from top * to bottom style. So the the I/O or MMIO segment assigned to @@ -1777,7 +2462,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, region.start += phb->ioda.io_segsize; index++; } - } else if (res->flags & IORESOURCE_MEM) { + } else if ((res->flags & IORESOURCE_MEM) && + !pnv_pci_is_mem_pref_64(res->flags)) { region.start = res->start - hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -1907,10 +2593,29 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, return phb->ioda.io_segsize; } +#ifdef CONFIG_PCI_IOV +static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, + int resno) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + resource_size_t align, iov_align; + + iov_align = resource_size(&pdev->resource[resno]); + if (iov_align) + return iov_align; + + align = pci_iov_resource_size(pdev, resno); + if (pdn->vfs_expanded) + return pdn->vfs_expanded * align; + + return align; +} +#endif /* CONFIG_PCI_IOV */ + /* Prevent enabling devices for which we couldn't properly * assign a PE */ -static int pnv_pci_enable_device_hook(struct pci_dev *dev) +static bool pnv_pci_enable_device_hook(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; @@ -1922,13 +2627,13 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) * PEs isn't ready. */ if (!phb->initialized) - return 0; + return true; pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) - return -EINVAL; + return false; - return 0; + return true; } static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, @@ -1988,9 +2693,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->last_busno = 0xff; } hose->private_data = phb; + hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = ioda_type; + mutex_init(&phb->ioda.pe_alloc_mutex); /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) @@ -2050,6 +2757,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, INIT_LIST_HEAD(&phb->ioda.pe_dma_list); INIT_LIST_HEAD(&phb->ioda.pe_list); + mutex_init(&phb->ioda.pe_list_mutex); /* Calculate how many 32-bit TCE segments we have */ phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28; @@ -2078,9 +2786,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->get_pe_state = pnv_ioda_get_pe_state; phb->freeze_pe = pnv_ioda_freeze_pe; phb->unfreeze_pe = pnv_ioda_unfreeze_pe; -#ifdef CONFIG_EEH - phb->eeh_ops = &ioda_eeh_ops; -#endif /* Setup RID -> PE mapping function */ phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe; @@ -2104,9 +2809,15 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * the child P2P bridges) can form individual PE. */ ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; - ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; - ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; - ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus; + pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook; + pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment; + pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus; + +#ifdef CONFIG_PCI_IOV + ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; + ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment; +#endif + pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ @@ -2121,8 +2832,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, */ if (is_kdump_kernel()) { pr_info(" Issue PHB reset ...\n"); - ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); - ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); + pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); + pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); } /* Remove M64 resource if we can't configure it successfully */ diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 6ef6d4d8e7e2..4729ca793813 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -133,6 +133,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, phb->hose->first_busno = 0; phb->hose->last_busno = 0xff; phb->hose->private_data = phb; + phb->hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = PNV_PHB_P5IOC2; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 54323d6b5166..bca2aeb6e4b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -366,9 +366,9 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) spin_unlock_irqrestore(&phb->lock, flags); } -static void pnv_pci_config_check_eeh(struct pnv_phb *phb, - struct device_node *dn) +static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { + struct pnv_phb *phb = pdn->phb->private_data; u8 fstate; __be16 pcierr; int pe_no; @@ -379,7 +379,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, * setup that yet. So all ER errors should be mapped to * reserved PE. */ - pe_no = PCI_DN(dn)->pe_number; + pe_no = pdn->pe_number; if (pe_no == IODA_INVALID_PE) { if (phb->type == PNV_PHB_P5IOC2) pe_no = 0; @@ -407,8 +407,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n", - (PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn), - pe_no, fstate); + (pdn->busno << 8) | (pdn->devfn), pe_no, fstate); /* Clear the frozen state if applicable */ if (fstate == OPAL_EEH_STOPPED_MMIO_FREEZE || @@ -425,10 +424,9 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } } -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; s64 rc; @@ -462,10 +460,9 @@ int pnv_pci_cfg_read(struct device_node *dn, return PCIBIOS_SUCCESSFUL; } -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; @@ -489,18 +486,17 @@ int pnv_pci_cfg_write(struct device_node *dn, } #if CONFIG_EEH -static bool pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static bool pnv_pci_cfg_check(struct pci_dn *pdn) { struct eeh_dev *edev = NULL; - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pdn->phb->private_data; /* EEH not enabled ? */ if (!(phb->flags & PNV_PHB_FLAG_EEH)) return true; /* PE reset or device removed ? */ - edev = of_node_to_eeh_dev(dn); + edev = pdn->edev; if (edev) { if (edev->pe && (edev->pe->state & EEH_PE_CFG_BLOCKED)) @@ -513,8 +509,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose, return true; } #else -static inline pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static inline pnv_pci_cfg_check(struct pci_dn *pdn) { return true; } @@ -524,32 +519,26 @@ static int pnv_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; *val = 0xFFFFFFFF; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_read(dn, where, size, val); - if (phb->flags & PNV_PHB_FLAG_EEH) { + ret = pnv_pci_cfg_read(pdn, where, size, val); + phb = pdn->phb->private_data; + if (phb->flags & PNV_PHB_FLAG_EEH && pdn->edev) { if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + eeh_dev_check_failure(pdn->edev)) return PCIBIOS_DEVICE_NOT_FOUND; } else { - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); } return ret; @@ -559,27 +548,21 @@ static int pnv_pci_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_write(dn, where, size, val); + ret = pnv_pci_cfg_write(pdn, where, size, val); + phb = pdn->phb->private_data; if (!(phb->flags & PNV_PHB_FLAG_EEH)) - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); return ret; } @@ -679,66 +662,31 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, tbl->it_type = TCE_PCI; } -static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose) -{ - struct iommu_table *tbl; - const __be64 *basep, *swinvp; - const __be32 *sizep; - - basep = of_get_property(hose->dn, "linux,tce-base", NULL); - sizep = of_get_property(hose->dn, "linux,tce-size", NULL); - if (basep == NULL || sizep == NULL) { - pr_err("PCI: %s has missing tce entries !\n", - hose->dn->full_name); - return NULL; - } - tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node); - if (WARN_ON(!tbl)) - return NULL; - pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)), - be32_to_cpup(sizep), 0, IOMMU_PAGE_SHIFT_4K); - iommu_init_table(tbl, hose->node); - iommu_register_group(tbl, pci_domain_nr(hose->bus), 0); - - /* Deal with SW invalidated TCEs when needed (BML way) */ - swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info", - NULL); - if (swinvp) { - tbl->it_busno = be64_to_cpu(swinvp[1]); - tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; - } - return tbl; -} - -static void pnv_pci_dma_fallback_setup(struct pci_controller *hose, - struct pci_dev *pdev) -{ - struct device_node *np = pci_bus_to_OF_node(hose->bus); - struct pci_dn *pdn; - - if (np == NULL) - return; - pdn = PCI_DN(np); - if (!pdn->iommu_table) - pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); - if (!pdn->iommu_table) - return; - set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table); -} - static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; +#ifdef CONFIG_PCI_IOV + struct pnv_ioda_pe *pe; + struct pci_dn *pdn; + + /* Fix the VF pdn PE number */ + if (pdev->is_virtfn) { + pdn = pci_get_pdn(pdev); + WARN_ON(pdn->pe_number != IODA_INVALID_PE); + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (pe->rid == ((pdev->bus->number << 8) | + (pdev->devfn & 0xff))) { + pdn->pe_number = pe->pe_number; + pe->pdev = pdev; + break; + } + } + } +#endif /* CONFIG_PCI_IOV */ - /* If we have no phb structure, try to setup a fallback based on - * the device-tree (RTAS PCI for example) - */ if (phb && phb->dma_dev_setup) phb->dma_dev_setup(phb, pdev); - else - pnv_pci_dma_fallback_setup(hose, pdev); } int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) @@ -784,44 +732,36 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk); void __init pnv_pci_init(void) { struct device_node *np; + bool found_ioda = false; pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN); - /* OPAL absent, try POPAL first then RTAS detection of PHBs */ - if (!firmware_has_feature(FW_FEATURE_OPAL)) { -#ifdef CONFIG_PPC_POWERNV_RTAS - init_pci_config_tokens(); - find_and_init_phbs(); -#endif /* CONFIG_PPC_POWERNV_RTAS */ - } - /* OPAL is here, do our normal stuff */ - else { - int found_ioda = 0; + /* If we don't have OPAL, eg. in sim, just skip PCI probe */ + if (!firmware_has_feature(FW_FEATURE_OPAL)) + return; - /* Look for IODA IO-Hubs. We don't support mixing IODA - * and p5ioc2 due to the need to change some global - * probing flags - */ - for_each_compatible_node(np, NULL, "ibm,ioda-hub") { - pnv_pci_init_ioda_hub(np); - found_ioda = 1; - } + /* Look for IODA IO-Hubs. We don't support mixing IODA + * and p5ioc2 due to the need to change some global + * probing flags + */ + for_each_compatible_node(np, NULL, "ibm,ioda-hub") { + pnv_pci_init_ioda_hub(np); + found_ioda = true; + } - /* Look for p5ioc2 IO-Hubs */ - if (!found_ioda) - for_each_compatible_node(np, NULL, "ibm,p5ioc2") - pnv_pci_init_p5ioc2_hub(np); + /* Look for p5ioc2 IO-Hubs */ + if (!found_ioda) + for_each_compatible_node(np, NULL, "ibm,p5ioc2") + pnv_pci_init_p5ioc2_hub(np); - /* Look for ioda2 built-in PHB3's */ - for_each_compatible_node(np, NULL, "ibm,ioda2-phb") - pnv_pci_init_ioda2_phb(np); - } + /* Look for ioda2 built-in PHB3's */ + for_each_compatible_node(np, NULL, "ibm,ioda2-phb") + pnv_pci_init_ioda2_phb(np); /* Setup the linkage between OF nodes and PHBs */ pci_devs_phb_init(); /* Configure IOMMU DMA hooks */ - ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup; ppc_md.tce_build = pnv_tce_build_vm; ppc_md.tce_free = pnv_tce_free_vm; ppc_md.tce_build_rm = pnv_tce_build_rm; @@ -837,3 +777,7 @@ void __init pnv_pci_init(void) } machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); + +struct pci_controller_ops pnv_pci_controller_ops = { + .dma_dev_setup = pnv_pci_dma_dev_setup, +}; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 6c02ff8dd69f..070ee888fc95 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -23,6 +23,7 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ #define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */ #define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */ +#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */ /* Data associated with a PE, including IOMMU tracking etc.. */ struct pnv_phb; @@ -34,6 +35,9 @@ struct pnv_ioda_pe { * entire bus (& children). In the former case, pdev * is populated, in the later case, pbus is. */ +#ifdef CONFIG_PCI_IOV + struct pci_dev *parent_dev; +#endif struct pci_dev *pdev; struct pci_bus *pbus; @@ -53,7 +57,7 @@ struct pnv_ioda_pe { /* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */ int tce32_seg; int tce32_segcount; - struct iommu_table tce32_table; + struct iommu_table *tce32_table; phys_addr_t tce_inval_reg_phys; /* 64-bit TCE bypass region */ @@ -75,22 +79,6 @@ struct pnv_ioda_pe { struct list_head list; }; -/* IOC dependent EEH operations */ -#ifdef CONFIG_EEH -struct pnv_eeh_ops { - int (*post_init)(struct pci_controller *hose); - int (*set_option)(struct eeh_pe *pe, int option); - int (*get_state)(struct eeh_pe *pe); - int (*reset)(struct eeh_pe *pe, int option); - int (*get_log)(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len); - int (*configure_bridge)(struct eeh_pe *pe); - int (*err_inject)(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask); - int (*next_error)(struct eeh_pe **pe); -}; -#endif /* CONFIG_EEH */ - #define PNV_PHB_FLAG_EEH (1 << 0) struct pnv_phb { @@ -104,10 +92,6 @@ struct pnv_phb { int initialized; spinlock_t lock; -#ifdef CONFIG_EEH - struct pnv_eeh_ops *eeh_ops; -#endif - #ifdef CONFIG_DEBUG_FS int has_dbgfs; struct dentry *dbgfs; @@ -165,6 +149,8 @@ struct pnv_phb { /* PE allocation bitmap */ unsigned long *pe_alloc; + /* PE allocation mutex */ + struct mutex pe_alloc_mutex; /* M32 & IO segment maps */ unsigned int *m32_segmap; @@ -179,6 +165,7 @@ struct pnv_phb { * on the sequence of creation */ struct list_head pe_list; + struct mutex pe_list_mutex; /* Reverse map of PEs, will have to extend if * we are to support more than 256 PEs, indexed @@ -213,15 +200,12 @@ struct pnv_phb { }; extern struct pci_ops pnv_pci_ops; -#ifdef CONFIG_EEH -extern struct pnv_eeh_ops ioda_eeh_ops; -#endif void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, unsigned char *log_buff); -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val); -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val); extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, @@ -232,6 +216,6 @@ extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); -extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option); +extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 604c48e7879a..826d2c9bea56 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev) } #endif +extern struct pci_controller_ops pnv_pci_controller_ops; + extern u32 pnv_get_supported_cpuidle_states(void); extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 80db43944afe..6eb808ff637e 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -24,12 +24,22 @@ struct powernv_rng { void __iomem *regs; + void __iomem *regs_real; unsigned long mask; }; static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng); +int powernv_hwrng_present(void) +{ + struct powernv_rng *rng; + + rng = get_cpu_var(powernv_rng); + put_cpu_var(rng); + return rng != NULL; +} + static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) { unsigned long parity; @@ -46,6 +56,17 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) return val; } +int powernv_get_random_real_mode(unsigned long *v) +{ + struct powernv_rng *rng; + + rng = raw_cpu_read(powernv_rng); + + *v = rng_whiten(rng, in_rm64(rng->regs_real)); + + return 1; +} + int powernv_get_random_long(unsigned long *v) { struct powernv_rng *rng; @@ -80,12 +101,20 @@ static __init void rng_init_per_cpu(struct powernv_rng *rng, static __init int rng_create(struct device_node *dn) { struct powernv_rng *rng; + struct resource res; unsigned long val; rng = kzalloc(sizeof(*rng), GFP_KERNEL); if (!rng) return -ENOMEM; + if (of_address_to_resource(dn, 0, &res)) { + kfree(rng); + return -ENXIO; + } + + rng->regs_real = (void __iomem *)res.start; + rng->regs = of_iomap(dn, 0); if (!rng->regs) { kfree(rng); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index d2de7d5d7574..16fdcb23f4c3 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -32,7 +32,6 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/xics.h> -#include <asm/rtas.h> #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> @@ -278,20 +277,6 @@ static void __init pnv_setup_machdep_opal(void) ppc_md.handle_hmi_exception = opal_handle_hmi_exception; } -#ifdef CONFIG_PPC_POWERNV_RTAS -static void __init pnv_setup_machdep_rtas(void) -{ - if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) { - ppc_md.get_boot_time = rtas_get_boot_time; - ppc_md.get_rtc_time = rtas_get_rtc_time; - ppc_md.set_rtc_time = rtas_set_rtc_time; - } - ppc_md.restart = rtas_restart; - pm_power_off = rtas_power_off; - ppc_md.halt = rtas_halt; -} -#endif /* CONFIG_PPC_POWERNV_RTAS */ - static u32 supported_cpuidle_states; int pnv_save_sprs_for_winkle(void) @@ -409,37 +394,39 @@ static int __init pnv_init_idle_states(void) { struct device_node *power_mgt; int dt_idle_states; - const __be32 *idle_state_flags; - u32 len_flags, flags; + u32 *flags; int i; supported_cpuidle_states = 0; if (cpuidle_disable != IDLE_NO_OVERRIDE) - return 0; + goto out; if (!firmware_has_feature(FW_FEATURE_OPALv3)) - return 0; + goto out; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { pr_warn("opal: PowerMgmt Node not found\n"); - return 0; + goto out; + } + dt_idle_states = of_property_count_u32_elems(power_mgt, + "ibm,cpu-idle-state-flags"); + if (dt_idle_states < 0) { + pr_warn("cpuidle-powernv: no idle states found in the DT\n"); + goto out; } - idle_state_flags = of_get_property(power_mgt, - "ibm,cpu-idle-state-flags", &len_flags); - if (!idle_state_flags) { - pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n"); - return 0; + flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL); + if (of_property_read_u32_array(power_mgt, + "ibm,cpu-idle-state-flags", flags, dt_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n"); + goto out_free; } - dt_idle_states = len_flags / sizeof(u32); + for (i = 0; i < dt_idle_states; i++) + supported_cpuidle_states |= flags[i]; - for (i = 0; i < dt_idle_states; i++) { - flags = be32_to_cpu(idle_state_flags[i]); - supported_cpuidle_states |= flags; - } if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { patch_instruction( (unsigned int *)pnv_fastsleep_workaround_at_entry, @@ -449,6 +436,9 @@ static int __init pnv_init_idle_states(void) PPC_INST_NOP); } pnv_alloc_idle_core_states(); +out_free: + kfree(flags); +out: return 0; } @@ -465,10 +455,6 @@ static int __init pnv_probe(void) if (firmware_has_feature(FW_FEATURE_OPAL)) pnv_setup_machdep_opal(); -#ifdef CONFIG_PPC_POWERNV_RTAS - else if (rtas.base) - pnv_setup_machdep_rtas(); -#endif /* CONFIG_PPC_POWERNV_RTAS */ pr_debug("PowerNV detected !\n"); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 38a45088f633..8f70ba681a78 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -25,7 +25,6 @@ #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/firmware.h> -#include <asm/rtas.h> #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> #include <asm/xics.h> @@ -251,18 +250,6 @@ void __init pnv_smp_init(void) { smp_ops = &pnv_smp_ops; - /* XXX We don't yet have a proper entry point from HAL, for - * now we rely on kexec-style entry from BML - */ - -#ifdef CONFIG_PPC_RTAS - /* Non-lpar has additional take/give timebase */ - if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { - smp_ops->give_timebase = rtas_give_timebase; - smp_ops->take_timebase = rtas_take_timebase; - } -#endif /* CONFIG_PPC_RTAS */ - #ifdef CONFIG_HOTPLUG_CPU ppc_md.cpu_die = pnv_smp_cpu_kill_self; #endif diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index b358bec6c8cb..3c7707af3384 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -57,7 +57,7 @@ static void ps3_smp_message_pass(int cpu, int msg) " (%d)\n", __func__, __LINE__, cpu, msg, result); } -static int __init ps3_smp_probe(void) +static void __init ps3_smp_probe(void) { int cpu; @@ -100,8 +100,6 @@ static int __init ps3_smp_probe(void) DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu); } - - return 2; } void ps3_smp_cleanup_cpu(int cpu) diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index a758a9c3bbba..54c87d5d349d 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -16,7 +16,6 @@ config PPC_PSERIES select PPC_UDBG_16550 select PPC_NATIVE select PPC_PCI_CHOICE if EXPERT - select ZLIB_DEFLATE select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index c22bb1b4beb8..b4b11096ea8b 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -10,6 +10,8 @@ * 2 as published by the Free Software Foundation. */ +#define pr_fmt(fmt) "dlpar: " fmt + #include <linux/kernel.h> #include <linux/notifier.h> #include <linux/spinlock.h> @@ -535,13 +537,125 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return count; } +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + +static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) +{ + int rc; + + /* pseries error logs are in BE format, convert to cpu type */ + switch (hp_elog->id_type) { + case PSERIES_HP_ELOG_ID_DRC_COUNT: + hp_elog->_drc_u.drc_count = + be32_to_cpu(hp_elog->_drc_u.drc_count); + break; + case PSERIES_HP_ELOG_ID_DRC_INDEX: + hp_elog->_drc_u.drc_index = + be32_to_cpu(hp_elog->_drc_u.drc_index); + } + + switch (hp_elog->resource) { + case PSERIES_HP_ELOG_RESOURCE_MEM: + rc = dlpar_memory(hp_elog); + break; + default: + pr_warn_ratelimited("Invalid resource (%d) specified\n", + hp_elog->resource); + rc = -EINVAL; + } + + return rc; +} + +static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) +{ + struct pseries_hp_errorlog *hp_elog; + const char *arg; + int rc; + + hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL); + if (!hp_elog) { + rc = -ENOMEM; + goto dlpar_store_out; + } + + /* Parse out the request from the user, this will be in the form + * <resource> <action> <id_type> <id> + */ + arg = buf; + if (!strncmp(arg, "memory", 6)) { + hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; + arg += strlen("memory "); + } else { + pr_err("Invalid resource specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "add", 3)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD; + arg += strlen("add "); + } else if (!strncmp(arg, "remove", 6)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE; + arg += strlen("remove "); + } else { + pr_err("Invalid action specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "index", 5)) { + u32 index; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; + arg += strlen("index "); + if (kstrtou32(arg, 0, &index)) { + rc = -EINVAL; + pr_err("Invalid drc_index specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_index = cpu_to_be32(index); + } else if (!strncmp(arg, "count", 5)) { + u32 count; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT; + arg += strlen("count "); + if (kstrtou32(arg, 0, &count)) { + rc = -EINVAL; + pr_err("Invalid count specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_count = cpu_to_be32(count); + } else { + pr_err("Invalid id_type specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + rc = handle_dlpar_errorlog(hp_elog); + +dlpar_store_out: + kfree(hp_elog); + return rc ? rc : count; +} + +static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store); + static int __init pseries_dlpar_init(void) { + int rc; + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE ppc_md.cpu_probe = dlpar_cpu_probe; ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - return 0; + rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); + + return rc; } machine_device_initcall(pseries, pseries_dlpar_init); -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index a6c7e19f5eb3..2039397cc75d 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -118,9 +118,8 @@ static int pseries_eeh_init(void) return 0; } -static int pseries_eeh_cap_start(struct device_node *dn) +static int pseries_eeh_cap_start(struct pci_dn *pdn) { - struct pci_dn *pdn = PCI_DN(dn); u32 status; if (!pdn) @@ -134,10 +133,9 @@ static int pseries_eeh_cap_start(struct device_node *dn) } -static int pseries_eeh_find_cap(struct device_node *dn, int cap) +static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - int pos = pseries_eeh_cap_start(dn); + int pos = pseries_eeh_cap_start(pdn); int cnt = 48; /* Maximal number of capabilities */ u32 id; @@ -160,10 +158,9 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } -static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); u32 header; int pos = 256; int ttl = (4096 - 256) / 8; @@ -191,53 +188,44 @@ static int pseries_eeh_find_ecap(struct device_node *dn, int cap) } /** - * pseries_eeh_of_probe - EEH probe on the given device - * @dn: OF node - * @flag: Unused + * pseries_eeh_probe - EEH probe on the given device + * @pdn: PCI device node + * @data: Unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function * is introduced for the purpose. */ -static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) +static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) { struct eeh_dev *edev; struct eeh_pe pe; - struct pci_dn *pdn = PCI_DN(dn); - const __be32 *classp, *vendorp, *devicep; - u32 class_code; - const __be32 *regs; u32 pcie_flags; int enable = 0; int ret; /* Retrieve OF node and eeh device */ - edev = of_node_to_eeh_dev(dn); - if (edev->pe || !of_device_is_available(dn)) + edev = pdn_to_eeh_dev(pdn); + if (!edev || edev->pe) return NULL; - /* Retrieve class/vendor/device IDs */ - classp = of_get_property(dn, "class-code", NULL); - vendorp = of_get_property(dn, "vendor-id", NULL); - devicep = of_get_property(dn, "device-id", NULL); - - /* Skip for bad OF node or PCI-ISA bridge */ - if (!classp || !vendorp || !devicep) - return NULL; - if (dn->type && !strcmp(dn->type, "isa")) + /* Check class/vendor/device IDs */ + if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code) return NULL; - class_code = of_read_number(classp, 1); + /* Skip for PCI-ISA bridge */ + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* * Update class code and mode of eeh device. We need * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = class_code; - edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); - edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); - edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); + edev->class_code = pdn->class_code; + edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -252,24 +240,16 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) } } - /* Retrieve the device address */ - regs = of_get_property(dn, "reg", NULL); - if (!regs) { - pr_warn("%s: OF node property %s::reg not found\n", - __func__, dn->full_name); - return NULL; - } - /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = of_read_number(regs, 1); + pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ + edev->config_addr = (pdn->busno << 16) | (pdn->devfn << 8); edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -285,16 +265,17 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) eeh_add_flag(EEH_ENABLED); eeh_add_to_parent_pe(edev); - pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", - __func__, dn->full_name, pe.phb->global_number, - pe.addr, pe.config_addr); - } else if (dn->parent && of_node_to_eeh_dev(dn->parent) && - (of_node_to_eeh_dev(dn->parent))->pe) { + pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%d-PE#%x\n", + __func__, pdn->busno, PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), pe.phb->global_number, + pe.addr); + } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && + (pdn_to_eeh_dev(pdn->parent))->pe) { /* This device doesn't support EEH, but it may have an * EEH parent, in which case we mark it as supported. */ - edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; - edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr; + edev->config_addr = pdn_to_eeh_dev(pdn->parent)->config_addr; + edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; eeh_add_to_parent_pe(edev); } } @@ -670,45 +651,36 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) /** * pseries_eeh_read_config - Read PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to read * @val: return value * * Read config space from the speicifed device */ -static int pseries_eeh_read_config(struct device_node *dn, int where, int size, u32 *val) +static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_read_config(pdn, where, size, val); } /** * pseries_eeh_write_config - Write PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to write * @val: value to be written * * Write config space to the specified device */ -static int pseries_eeh_write_config(struct device_node *dn, int where, int size, u32 val) +static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_write_config(pdn, where, size, val); } static struct eeh_ops pseries_eeh_ops = { .name = "pseries", .init = pseries_eeh_init, - .of_probe = pseries_eeh_of_probe, - .dev_probe = NULL, + .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index fa41f0da5b6f..0ced387e1463 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -9,11 +9,14 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "pseries-hotplug-mem: " fmt + #include <linux/of.h> #include <linux/of_address.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/slab.h> #include <asm/firmware.h> #include <asm/machdep.h> @@ -21,6 +24,8 @@ #include <asm/sparsemem.h> #include "pseries.h" +static bool rtas_hp_event; + unsigned long pseries_memory_block_size(void) { struct device_node *np; @@ -64,6 +69,67 @@ unsigned long pseries_memory_block_size(void) return memblock_size; } +static void dlpar_free_drconf_property(struct property *prop) +{ + kfree(prop->name); + kfree(prop->value); + kfree(prop); +} + +static struct property *dlpar_clone_drconf_property(struct device_node *dn) +{ + struct property *prop, *new_prop; + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + prop = of_find_property(dn, "ibm,dynamic-memory", NULL); + if (!prop) + return NULL; + + new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL); + if (!new_prop) + return NULL; + + new_prop->name = kstrdup(prop->name, GFP_KERNEL); + new_prop->value = kmalloc(prop->length, GFP_KERNEL); + if (!new_prop->name || !new_prop->value) { + dlpar_free_drconf_property(new_prop); + return NULL; + } + + memcpy(new_prop->value, prop->value, prop->length); + new_prop->length = prop->length; + + /* Convert the property to cpu endian-ness */ + p = new_prop->value; + *p = be32_to_cpu(*p); + + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + for (i = 0; i < num_lmbs; i++) { + lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); + lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].flags = be32_to_cpu(lmbs[i].flags); + } + + return new_prop; +} + +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -122,6 +188,173 @@ static int pseries_remove_mem_node(struct device_node *np) pseries_remove_memblock(base, lmb_size); return 0; } + +static bool lmb_is_removable(struct of_drconf_cell *lmb) +{ + int i, scns_per_block; + int rc = 1; + unsigned long pfn, block_sz; + u64 phys_addr; + + if (!(lmb->flags & DRCONF_MEM_ASSIGNED)) + return false; + + block_sz = memory_block_size_bytes(); + scns_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + phys_addr = lmb->base_addr; + + for (i = 0; i < scns_per_block; i++) { + pfn = PFN_DOWN(phys_addr); + if (!pfn_present(pfn)) + continue; + + rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION); + phys_addr += MIN_MEMORY_BLOCK_SIZE; + } + + return rc ? true : false; +} + +static int dlpar_add_lmb(struct of_drconf_cell *); + +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (!lmb_is_removable(lmb)) + return -EINVAL; + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) + return -EINVAL; + + rc = device_offline(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) + return rc; + + block_sz = pseries_memory_block_size(); + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + remove_memory(nid, lmb->base_addr, block_sz); + + /* Update memory regions for memory remove */ + memblock_remove(lmb->base_addr, block_sz); + + dlpar_release_drc(lmb->drc_index); + + lmb->flags &= ~DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + int lmbs_removed = 0; + int lmbs_available = 0; + u32 num_lmbs, *p; + int i, rc; + + pr_info("Attempting to hot-remove %d LMB(s)\n", lmbs_to_remove); + + if (lmbs_to_remove == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].flags & DRCONF_MEM_ASSIGNED) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_remove) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) { + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_removed++; + + /* Mark this lmb so we can add it later if all of the + * requested LMBs cannot be removed. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_removed != lmbs_to_remove) { + pr_err("Memory hot-remove failed, adding LMB's back\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to add LMB back, drc index %x\n", + lmbs[i].drc_index); + + lmbs[i].reserved = 0; + } + + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx was hot-removed\n", + lmbs[i].base_addr); + + lmbs[i].reserved = 0; + } + rc = 0; + } + + return rc; +} + +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmb_found; + int i, rc; + + pr_info("Attempting to hot-remove LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_remove_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-remove memory at %llx\n", + lmbs[i].base_addr); + else + pr_info("Memory at %llx was hot-removed\n", lmbs[i].base_addr); + + return rc; +} + #else static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) @@ -132,8 +365,261 @@ static inline int pseries_remove_mem_node(struct device_node *np) { return 0; } +static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_MEMORY_HOTREMOVE */ +static int dlpar_add_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (lmb->flags & DRCONF_MEM_ASSIGNED) + return -EINVAL; + + block_sz = memory_block_size_bytes(); + + rc = dlpar_acquire_drc(lmb->drc_index); + if (rc) + return rc; + + /* Find the node id for this address */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + /* Add the memory */ + rc = add_memory(nid, lmb->base_addr, block_sz); + if (rc) { + dlpar_release_drc(lmb->drc_index); + return rc; + } + + /* Register this block of memory */ + rc = memblock_add(lmb->base_addr, block_sz); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return -EINVAL; + } + + rc = device_online(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + lmb->flags |= DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmbs_available = 0; + int lmbs_added = 0; + int i, rc; + + pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add); + + if (lmbs_to_add == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED)) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_add) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) { + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_added++; + + /* Mark this lmb so we can remove it later if all of the + * requested LMBs cannot be added. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_added != lmbs_to_add) { + pr_err("Memory hot-add failed, removing any added LMBs\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to remove LMB, drc index %x\n", + be32_to_cpu(lmbs[i].drc_index)); + } + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, lmbs[i].drc_index); + lmbs[i].reserved = 0; + } + } + + return rc; +} + +static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i, lmb_found; + int rc; + + pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_add_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-add memory, drc index %x\n", drc_index); + else + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, drc_index); + + return rc; +} + +static void dlpar_update_drconf_property(struct device_node *dn, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + /* Convert the property back to BE */ + p = prop->value; + num_lmbs = *p; + *p = cpu_to_be32(*p); + p++; + + lmbs = (struct of_drconf_cell *)p; + for (i = 0; i < num_lmbs; i++) { + lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); + lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].flags = cpu_to_be32(lmbs[i].flags); + } + + rtas_hp_event = true; + of_update_property(dn, prop); + rtas_hp_event = false; +} + +int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + struct device_node *dn; + struct property *prop; + u32 count, drc_index; + int rc; + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (!dn) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + prop = dlpar_clone_drconf_property(dn); + if (!prop) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + switch (hp_elog->action) { + case PSERIES_HP_ELOG_ACTION_ADD: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_add_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_add_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + case PSERIES_HP_ELOG_ACTION_REMOVE: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_remove_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_remove_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + default: + pr_err("Invalid action (%d) specified\n", hp_elog->action); + rc = -EINVAL; + break; + } + + if (rc) + dlpar_free_drconf_property(prop); + else + dlpar_update_drconf_property(dn, prop); + +dlpar_memory_out: + of_node_put(dn); + unlock_device_hotplug(); + return rc; +} + static int pseries_add_mem_node(struct device_node *np) { const char *type; @@ -174,6 +660,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr) __be32 *p; int i, rc = -EINVAL; + if (rtas_hp_event) + return 0; + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7803a19adb31..61d5a17f45c0 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -49,6 +49,7 @@ #include <asm/mmzone.h> #include <asm/plpar_wrappers.h> +#include "pseries.h" static void tce_invalidate_pSeries_sw(struct iommu_table *tbl, __be64 *startp, __be64 *endp) @@ -1307,16 +1308,16 @@ void iommu_init_early_pSeries(void) ppc_md.tce_free = tce_free_pSeriesLP; } ppc_md.tce_get = tce_get_pSeriesLP; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP; ppc_md.dma_set_mask = dma_set_mask_pSeriesLP; ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP; } else { ppc_md.tce_build = tce_build_pSeries; ppc_md.tce_free = tce_free_pSeries; ppc_md.tce_get = tce_get_pseries; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeries; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeries; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries; } diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 8f35d525cede..ceb18d349459 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -320,28 +320,34 @@ static ssize_t migrate_store(struct class *class, struct class_attribute *attr, { u64 streamid; int rc; - int vasi_rc = 0; rc = kstrtou64(buf, 0, &streamid); if (rc) return rc; do { - rc = rtas_ibm_suspend_me(streamid, &vasi_rc); - if (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE) + rc = rtas_ibm_suspend_me(streamid); + if (rc == -EAGAIN) ssleep(1); - } while (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE); + } while (rc == -EAGAIN); if (rc) return rc; - if (vasi_rc) - return vasi_rc; post_mobility_fixup(); return count; } +/* + * Used by drmgr to determine the kernel behavior of the migration interface. + * + * Version 1: Performs all PAPR requirements for migration including + * firmware activation and device tree update. + */ +#define MIGRATION_API_VERSION 1 + static CLASS_ATTR(migration, S_IWUSR, NULL, migrate_store); +static CLASS_ATTR_STRING(api_version, S_IRUGO, __stringify(MIGRATION_API_VERSION)); static int __init mobility_sysfs_init(void) { @@ -352,7 +358,13 @@ static int __init mobility_sysfs_init(void) return -ENOMEM; rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr); + if (rc) + pr_err("mobility: unable to create migration sysfs file (%d)\n", rc); - return rc; + rc = sysfs_create_file(mobility_kobj, &class_attr_api_version.attr.attr); + if (rc) + pr_err("mobility: unable to create api_version sysfs file (%d)\n", rc); + + return 0; } machine_device_initcall(pseries, mobility_sysfs_init); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 691a154c286d..c8d24f9a6948 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -195,6 +195,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; /* Found our PE and assume 8 at that point. */ @@ -204,10 +205,11 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) return NULL; /* Get the top level device in the PE */ - edev = of_node_to_eeh_dev(dn); + edev = pdn_to_eeh_dev(PCI_DN(dn)); if (edev->pe) edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); - dn = eeh_dev_to_of_node(edev); + pdn = eeh_dev_to_pdn(edev); + dn = pdn ? pdn->node : NULL; if (!dn) return NULL; diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 054a0ed5c7ee..9f8184175c86 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -20,7 +20,6 @@ #include <linux/kmsg_dump.h> #include <linux/pstore.h> #include <linux/ctype.h> -#include <linux/zlib.h> #include <asm/uaccess.h> #include <asm/nvram.h> #include <asm/rtas.h> @@ -30,129 +29,17 @@ /* Max bytes to read/write in one go */ #define NVRW_CNT 0x20 -/* - * Set oops header version to distinguish between old and new format header. - * lnx,oops-log partition max size is 4000, header version > 4000 will - * help in identifying new header. - */ -#define OOPS_HDR_VERSION 5000 - static unsigned int nvram_size; static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); -struct err_log_info { - __be32 error_type; - __be32 seq_num; -}; - -struct nvram_os_partition { - const char *name; - int req_size; /* desired size, in bytes */ - int min_size; /* minimum acceptable size (0 means req_size) */ - long size; /* size of data portion (excluding err_log_info) */ - long index; /* offset of data portion of partition */ - bool os_partition; /* partition initialized by OS, not FW */ -}; - -static struct nvram_os_partition rtas_log_partition = { - .name = "ibm,rtas-log", - .req_size = 2079, - .min_size = 1055, - .index = -1, - .os_partition = true -}; - -static struct nvram_os_partition oops_log_partition = { - .name = "lnx,oops-log", - .req_size = 4000, - .min_size = 2000, - .index = -1, - .os_partition = true -}; - -static const char *pseries_nvram_os_partitions[] = { - "ibm,rtas-log", - "lnx,oops-log", - NULL -}; - -struct oops_log_info { - __be16 version; - __be16 report_length; - __be64 timestamp; -} __attribute__((packed)); - -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason); - -static struct kmsg_dumper nvram_kmsg_dumper = { - .dump = oops_to_nvram -}; - /* See clobbering_unread_rtas_event() */ #define NVRAM_RTAS_READ_TIMEOUT 5 /* seconds */ -static unsigned long last_unread_rtas_event; /* timestamp */ - -/* - * For capturing and compressing an oops or panic report... - - * big_oops_buf[] holds the uncompressed text we're capturing. - * - * oops_buf[] holds the compressed text, preceded by a oops header. - * oops header has u16 holding the version of oops header (to differentiate - * between old and new format header) followed by u16 holding the length of - * the compressed* text (*Or uncompressed, if compression fails.) and u64 - * holding the timestamp. oops_buf[] gets written to NVRAM. - * - * oops_log_info points to the header. oops_data points to the compressed text. - * - * +- oops_buf - * | +- oops_data - * v v - * +-----------+-----------+-----------+------------------------+ - * | version | length | timestamp | text | - * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | - * +-----------+-----------+-----------+------------------------+ - * ^ - * +- oops_log_info - * - * We preallocate these buffers during init to avoid kmalloc during oops/panic. - */ -static size_t big_oops_buf_sz; -static char *big_oops_buf, *oops_buf; -static char *oops_data; -static size_t oops_data_sz; - -/* Compression parameters */ -#define COMPR_LEVEL 6 -#define WINDOW_BITS 12 -#define MEM_LEVEL 4 -static struct z_stream_s stream; +static time64_t last_unread_rtas_event; /* timestamp */ #ifdef CONFIG_PSTORE -static struct nvram_os_partition of_config_partition = { - .name = "of-config", - .index = -1, - .os_partition = false -}; - -static struct nvram_os_partition common_partition = { - .name = "common", - .index = -1, - .os_partition = false -}; - -static enum pstore_type_id nvram_type_ids[] = { - PSTORE_TYPE_DMESG, - PSTORE_TYPE_PPC_RTAS, - PSTORE_TYPE_PPC_OF, - PSTORE_TYPE_PPC_COMMON, - -1 -}; -static int read_type; -static unsigned long last_rtas_event; +time64_t last_rtas_event; #endif static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) @@ -246,132 +133,26 @@ static ssize_t pSeries_nvram_get_size(void) return nvram_size ? nvram_size : -ENODEV; } - -/* nvram_write_os_partition, nvram_write_error_log +/* nvram_write_error_log * * We need to buffer the error logs into nvram to ensure that we have - * the failure information to decode. If we have a severe error there - * is no way to guarantee that the OS or the machine is in a state to - * get back to user land and write the error to disk. For example if - * the SCSI device driver causes a Machine Check by writing to a bad - * IO address, there is no way of guaranteeing that the device driver - * is in any state that is would also be able to write the error data - * captured to disk, thus we buffer it in NVRAM for analysis on the - * next boot. - * - * In NVRAM the partition containing the error log buffer will looks like: - * Header (in bytes): - * +-----------+----------+--------+------------+------------------+ - * | signature | checksum | length | name | data | - * |0 |1 |2 3|4 15|16 length-1| - * +-----------+----------+--------+------------+------------------+ - * - * The 'data' section would look like (in bytes): - * +--------------+------------+-----------------------------------+ - * | event_logged | sequence # | error log | - * |0 3|4 7|8 error_log_size-1| - * +--------------+------------+-----------------------------------+ - * - * event_logged: 0 if event has not been logged to syslog, 1 if it has - * sequence #: The unique sequence # for each event. (until it wraps) - * error log: The error log from event_scan + * the failure information to decode. */ -static int nvram_write_os_partition(struct nvram_os_partition *part, - char *buff, int length, - unsigned int err_type, - unsigned int error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) { - return -ESPIPE; - } - - if (length > part->size) { - length = part->size; - } - - info.error_type = cpu_to_be32(err_type); - info.seq_num = cpu_to_be32(error_log_cnt); - - tmp_index = part->index; - - rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - rc = ppc_md.nvram_write(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - return 0; -} - int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int error_log_cnt) { int rc = nvram_write_os_partition(&rtas_log_partition, buff, length, err_type, error_log_cnt); if (!rc) { - last_unread_rtas_event = get_seconds(); + last_unread_rtas_event = ktime_get_real_seconds(); #ifdef CONFIG_PSTORE - last_rtas_event = get_seconds(); + last_rtas_event = ktime_get_real_seconds(); #endif } return rc; } -/* nvram_read_partition - * - * Reads nvram partition for at most 'length' - */ -static int nvram_read_partition(struct nvram_os_partition *part, char *buff, - int length, unsigned int *err_type, - unsigned int *error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) - return -1; - - if (length > part->size) - length = part->size; - - tmp_index = part->index; - - if (part->os_partition) { - rc = ppc_md.nvram_read((char *)&info, - sizeof(struct err_log_info), - &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - } - - rc = ppc_md.nvram_read(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - - if (part->os_partition) { - *error_log_cnt = be32_to_cpu(info.seq_num); - *err_type = be32_to_cpu(info.error_type); - } - - return 0; -} - /* nvram_read_error_log * * Reads nvram for error log for at most 'length' @@ -407,67 +188,6 @@ int nvram_clear_error_log(void) return 0; } -/* pseries_nvram_init_os_partition - * - * This sets up a partition with an "OS" signature. - * - * The general strategy is the following: - * 1.) If a partition with the indicated name already exists... - * - If it's large enough, use it. - * - Otherwise, recycle it and keep going. - * 2.) Search for a free partition that is large enough. - * 3.) If there's not a free partition large enough, recycle any obsolete - * OS partitions and try again. - * 4.) Will first try getting a chunk that will satisfy the requested size. - * 5.) If a chunk of the requested size cannot be allocated, then try finding - * a chunk that will satisfy the minum needed. - * - * Returns 0 on success, else -1. - */ -static int __init pseries_nvram_init_os_partition(struct nvram_os_partition - *part) -{ - loff_t p; - int size; - - /* Look for ours */ - p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); - - /* Found one but too small, remove it */ - if (p && size < part->min_size) { - pr_info("nvram: Found too small %s partition," - " removing it...\n", part->name); - nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL); - p = 0; - } - - /* Create one if we didn't find */ - if (!p) { - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - if (p == -ENOSPC) { - pr_info("nvram: No room to create %s partition, " - "deleting any obsolete OS partitions...\n", - part->name); - nvram_remove_partition(NULL, NVRAM_SIG_OS, - pseries_nvram_os_partitions); - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - } - } - - if (p <= 0) { - pr_err("nvram: Failed to find or create %s" - " partition, err %d\n", part->name, (int)p); - return -1; - } - - part->index = p; - part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info); - - return 0; -} - /* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd @@ -476,321 +196,14 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition * We assume that if rtas_errd hasn't read the RTAS event in * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to. */ -static int clobbering_unread_rtas_event(void) +int clobbering_unread_rtas_event(void) { return (oops_log_partition.index == rtas_log_partition.index && last_unread_rtas_event - && get_seconds() - last_unread_rtas_event <= + && ktime_get_real_seconds() - last_unread_rtas_event <= NVRAM_RTAS_READ_TIMEOUT); } -/* Derived from logfs_compress() */ -static int nvram_compress(const void *in, void *out, size_t inlen, - size_t outlen) -{ - int err, ret; - - ret = -EIO; - err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, - MEM_LEVEL, Z_DEFAULT_STRATEGY); - if (err != Z_OK) - goto error; - - stream.next_in = in; - stream.avail_in = inlen; - stream.total_in = 0; - stream.next_out = out; - stream.avail_out = outlen; - stream.total_out = 0; - - err = zlib_deflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) - goto error; - - err = zlib_deflateEnd(&stream); - if (err != Z_OK) - goto error; - - if (stream.total_out >= stream.total_in) - goto error; - - ret = stream.total_out; -error: - return ret; -} - -/* Compress the text from big_oops_buf into oops_buf. */ -static int zip_oops(size_t text_len) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len, - oops_data_sz); - if (zipped_len < 0) { - pr_err("nvram: compression failed; returned %d\n", zipped_len); - pr_err("nvram: logging uncompressed oops/panic report\n"); - return -1; - } - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(zipped_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - return 0; -} - -#ifdef CONFIG_PSTORE -static int nvram_pstore_open(struct pstore_info *psi) -{ - /* Reset the iterator to start reading partitions again */ - read_type = -1; - return 0; -} - -/** - * nvram_pstore_write - pstore write callback for nvram - * @type: Type of message logged - * @reason: reason behind dump (oops/panic) - * @id: identifier to indicate the write performed - * @part: pstore writes data to registered buffer in parts, - * part number will indicate the same. - * @count: Indicates oops count - * @compressed: Flag to indicate the log is compressed - * @size: number of bytes written to the registered buffer - * @psi: registered pstore_info structure - * - * Called by pstore_dump() when an oops or panic report is logged in the - * printk buffer. - * Returns 0 on successful write. - */ -static int nvram_pstore_write(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, - bool compressed, size_t size, - struct pstore_info *psi) -{ - int rc; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC; - struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; - - /* part 1 has the recent messages from printk buffer */ - if (part > 1 || type != PSTORE_TYPE_DMESG || - clobbering_unread_rtas_event()) - return -1; - - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(size); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - - if (compressed) - err_type = ERR_TYPE_KERNEL_PANIC_GZ; - - rc = nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + size), err_type, count); - - if (rc != 0) - return rc; - - *id = part; - return 0; -} - -/* - * Reads the oops/panic report, rtas, of-config and common partition. - * Returns the length of the data we read from each partition. - * Returns 0 if we've been called before. - */ -static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, - int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi) -{ - struct oops_log_info *oops_hdr; - unsigned int err_type, id_no, size = 0; - struct nvram_os_partition *part = NULL; - char *buff = NULL; - int sig = 0; - loff_t p; - - read_type++; - - switch (nvram_type_ids[read_type]) { - case PSTORE_TYPE_DMESG: - part = &oops_log_partition; - *type = PSTORE_TYPE_DMESG; - break; - case PSTORE_TYPE_PPC_RTAS: - part = &rtas_log_partition; - *type = PSTORE_TYPE_PPC_RTAS; - time->tv_sec = last_rtas_event; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_OF: - sig = NVRAM_SIG_OF; - part = &of_config_partition; - *type = PSTORE_TYPE_PPC_OF; - *id = PSTORE_TYPE_PPC_OF; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_COMMON: - sig = NVRAM_SIG_SYS; - part = &common_partition; - *type = PSTORE_TYPE_PPC_COMMON; - *id = PSTORE_TYPE_PPC_COMMON; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - default: - return 0; - } - - if (!part->os_partition) { - p = nvram_find_partition(part->name, sig, &size); - if (p <= 0) { - pr_err("nvram: Failed to find partition %s, " - "err %d\n", part->name, (int)p); - return 0; - } - part->index = p; - part->size = size; - } - - buff = kmalloc(part->size, GFP_KERNEL); - - if (!buff) - return -ENOMEM; - - if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) { - kfree(buff); - return 0; - } - - *count = 0; - - if (part->os_partition) - *id = id_no; - - if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { - size_t length, hdr_size; - - oops_hdr = (struct oops_log_info *)buff; - if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { - /* Old format oops header had 2-byte record size */ - hdr_size = sizeof(u16); - length = be16_to_cpu(oops_hdr->version); - time->tv_sec = 0; - time->tv_nsec = 0; - } else { - hdr_size = sizeof(*oops_hdr); - length = be16_to_cpu(oops_hdr->report_length); - time->tv_sec = be64_to_cpu(oops_hdr->timestamp); - time->tv_nsec = 0; - } - *buf = kmalloc(length, GFP_KERNEL); - if (*buf == NULL) - return -ENOMEM; - memcpy(*buf, buff + hdr_size, length); - kfree(buff); - - if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) - *compressed = true; - else - *compressed = false; - return length; - } - - *buf = buff; - return part->size; -} - -static struct pstore_info nvram_pstore_info = { - .owner = THIS_MODULE, - .name = "nvram", - .open = nvram_pstore_open, - .read = nvram_pstore_read, - .write = nvram_pstore_write, -}; - -static int nvram_pstore_init(void) -{ - int rc = 0; - - nvram_pstore_info.buf = oops_data; - nvram_pstore_info.bufsize = oops_data_sz; - - spin_lock_init(&nvram_pstore_info.buf_lock); - - rc = pstore_register(&nvram_pstore_info); - if (rc != 0) - pr_err("nvram: pstore_register() failed, defaults to " - "kmsg_dump; returned %d\n", rc); - - return rc; -} -#else -static int nvram_pstore_init(void) -{ - return -1; -} -#endif - -static void __init nvram_init_oops_partition(int rtas_partition_exists) -{ - int rc; - - rc = pseries_nvram_init_os_partition(&oops_log_partition); - if (rc != 0) { - if (!rtas_partition_exists) - return; - pr_notice("nvram: Using %s partition to log both" - " RTAS errors and oops/panic reports\n", - rtas_log_partition.name); - memcpy(&oops_log_partition, &rtas_log_partition, - sizeof(rtas_log_partition)); - } - oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL); - if (!oops_buf) { - pr_err("nvram: No memory for %s partition\n", - oops_log_partition.name); - return; - } - oops_data = oops_buf + sizeof(struct oops_log_info); - oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); - - rc = nvram_pstore_init(); - - if (!rc) - return; - - /* - * Figure compression (preceded by elimination of each line's <n> - * severity prefix) will reduce the oops/panic report to at most - * 45% of its original size. - */ - big_oops_buf_sz = (oops_data_sz * 100) / 45; - big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); - if (big_oops_buf) { - stream.workspace = kmalloc(zlib_deflate_workspacesize( - WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); - if (!stream.workspace) { - pr_err("nvram: No memory for compression workspace; " - "skipping compression of %s partition data\n", - oops_log_partition.name); - kfree(big_oops_buf); - big_oops_buf = NULL; - } - } else { - pr_err("No memory for uncompressed %s data; " - "skipping compression\n", oops_log_partition.name); - stream.workspace = NULL; - } - - rc = kmsg_dump_register(&nvram_kmsg_dumper); - if (rc != 0) { - pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); - kfree(oops_buf); - kfree(big_oops_buf); - kfree(stream.workspace); - } -} - static int __init pseries_nvram_init_log_partitions(void) { int rc; @@ -798,7 +211,7 @@ static int __init pseries_nvram_init_log_partitions(void) /* Scan nvram for partitions */ nvram_scan_partitions(); - rc = pseries_nvram_init_os_partition(&rtas_log_partition); + rc = nvram_init_os_partition(&rtas_log_partition); nvram_init_oops_partition(rc == 0); return 0; } @@ -834,72 +247,3 @@ int __init pSeries_nvram_init(void) return 0; } - -/* - * This is our kmsg_dump callback, called after an oops or panic report - * has been written to the printk buffer. We want to capture as much - * of the printk buffer as possible. First, capture as much as we can - * that we think will compress sufficiently to fit in the lnx,oops-log - * partition. If that's too much, go back and capture uncompressed text. - */ -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - static unsigned int oops_count = 0; - static bool panicking = false; - static DEFINE_SPINLOCK(lock); - unsigned long flags; - size_t text_len; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; - int rc = -1; - - switch (reason) { - case KMSG_DUMP_RESTART: - case KMSG_DUMP_HALT: - case KMSG_DUMP_POWEROFF: - /* These are almost always orderly shutdowns. */ - return; - case KMSG_DUMP_OOPS: - break; - case KMSG_DUMP_PANIC: - panicking = true; - break; - case KMSG_DUMP_EMERG: - if (panicking) - /* Panic report already captured. */ - return; - break; - default: - pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __func__, (int) reason); - return; - } - - if (clobbering_unread_rtas_event()) - return; - - if (!spin_trylock_irqsave(&lock, flags)) - return; - - if (big_oops_buf) { - kmsg_dump_get_buffer(dumper, false, - big_oops_buf, big_oops_buf_sz, &text_len); - rc = zip_oops(text_len); - } - if (rc != 0) { - kmsg_dump_rewind(dumper); - kmsg_dump_get_buffer(dumper, false, - oops_data, oops_data_sz, &text_len); - err_type = ERR_TYPE_KERNEL_PANIC; - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(text_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - } - - (void) nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + text_len), err_type, - ++oops_count); - - spin_unlock_irqrestore(&lock, flags); -} diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 89e23811199c..5d4a3df59d0c 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -32,6 +32,8 @@ #include <asm/firmware.h> #include <asm/eeh.h> +#include "pseries.h" + static struct pci_bus * find_bus_among_children(struct pci_bus *bus, struct device_node *dn) @@ -75,6 +77,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) return NULL; rtas_setup_phb(phb); pci_process_bridge_OF_ranges(phb, dn, 0); + phb->controller_ops = pseries_pci_controller_ops; pci_devs_phb_init_dynamic(phb); @@ -82,7 +85,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) eeh_dev_phb_init_dynamic(phb); if (dn->child) - eeh_add_device_tree_early(dn); + eeh_add_device_tree_early(PCI_DN(dn)); pcibios_scan_phb(phb); pcibios_finish_adding_to_bus(phb->bus); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1796c5438cc6..8411c27293e4 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -11,6 +11,7 @@ #define _PSERIES_PSERIES_H #include <linux/interrupt.h> +#include <asm/rtas.h> struct device_node; @@ -60,11 +61,24 @@ extern struct device_node *dlpar_configure_connector(__be32, struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); +extern int dlpar_acquire_drc(u32 drc_index); +extern int dlpar_release_drc(u32 drc_index); + +#ifdef CONFIG_MEMORY_HOTPLUG +int dlpar_memory(struct pseries_hp_errorlog *hp_elog); +#else +static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +#endif /* PCI root bridge prepare function override for pseries */ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +extern struct pci_controller_ops pseries_pci_controller_ops; + unsigned long pseries_memory_block_size(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e445b6701f50..df6a7041922b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -265,7 +265,7 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act update_dn_pci_info(np, pci->phb); /* Create EEH device for the OF node */ - eeh_dev_init(np, pci->phb); + eeh_dev_init(PCI_DN(np), pci->phb); } break; default: @@ -461,6 +461,47 @@ static long pseries_little_endian_exceptions(void) } #endif +static void __init find_and_init_phbs(void) +{ + struct device_node *node; + struct pci_controller *phb; + struct device_node *root = of_find_node_by_path("/"); + + for_each_child_of_node(root, node) { + if (node->type == NULL || (strcmp(node->type, "pci") != 0 && + strcmp(node->type, "pciex") != 0)) + continue; + + phb = pcibios_alloc_controller(node); + if (!phb) + continue; + rtas_setup_phb(phb); + pci_process_bridge_OF_ranges(phb, node, 0); + isa_bridge_find_early(phb); + phb->controller_ops = pseries_pci_controller_ops; + } + + of_node_put(root); + pci_devs_phb_init(); + + /* + * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties + * in chosen. + */ + if (of_chosen) { + const int *prop; + + prop = of_get_property(of_chosen, + "linux,pci-probe-only", NULL); + if (prop) { + if (*prop) + pci_add_flags(PCI_PROBE_ONLY); + else + pci_clear_flags(PCI_PROBE_ONLY); + } + } +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -793,6 +834,10 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) void pSeries_final_fixup(void) { } #endif +struct pci_controller_ops pseries_pci_controller_ops = { + .probe_mode = pSeries_pci_probe_mode, +}; + define_machine(pseries) { .name = "pSeries", .probe = pSeries_probe, @@ -801,7 +846,6 @@ define_machine(pseries) { .show_cpuinfo = pSeries_show_cpuinfo, .log_error = pSeries_log_error, .pcibios_fixup = pSeries_final_fixup, - .pci_probe_mode = pSeries_pci_probe_mode, .restart = rtas_restart, .halt = rtas_halt, .panic = rtas_os_term, diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index a3555b10c1a5..6932ea803e33 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -197,16 +197,14 @@ static void pSeries_cause_ipi_mux(int cpu, unsigned long data) xics_cause_ipi(cpu, data); } -static __init int pSeries_smp_probe(void) +static __init void pSeries_smp_probe(void) { - int ret = xics_smp_probe(); + xics_smp_probe(); if (cpu_has_feature(CPU_FTR_DBELL)) { xics_cause_ipi = smp_ops->cause_ipi; smp_ops->cause_ipi = pSeries_cause_ipi_mux; } - - return ret; } static struct smp_ops_t pSeries_mpic_smp_ops = { diff --git a/arch/powerpc/relocs_check.pl b/arch/powerpc/relocs_check.pl deleted file mode 100755 index 3f46e8b9c56d..000000000000 --- a/arch/powerpc/relocs_check.pl +++ /dev/null @@ -1,66 +0,0 @@ -#!/usr/bin/perl - -# Copyright © 2009 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 script checks the relocations of a vmlinux for "suspicious" -# relocations. - -use strict; -use warnings; - -if ($#ARGV != 1) { - die "$0 [path to objdump] [path to vmlinux]\n"; -} - -# Have Kbuild supply the path to objdump so we handle cross compilation. -my $objdump = shift; -my $vmlinux = shift; -my $bad_relocs_count = 0; -my $bad_relocs = ""; -my $old_binutils = 0; - -open(FD, "$objdump -R $vmlinux|") or die; -while (<FD>) { - study $_; - - # Only look at relocation lines. - next if (!/\s+R_/); - - # These relocations are okay - # On PPC64: - # R_PPC64_RELATIVE, R_PPC64_NONE, R_PPC64_ADDR64 - # On PPC: - # R_PPC_RELATIVE, R_PPC_ADDR16_HI, - # R_PPC_ADDR16_HA,R_PPC_ADDR16_LO, - # R_PPC_NONE - - next if (/\bR_PPC64_RELATIVE\b/ or /\bR_PPC64_NONE\b/ or - /\bR_PPC64_ADDR64\s+mach_/); - next if (/\bR_PPC_ADDR16_LO\b/ or /\bR_PPC_ADDR16_HI\b/ or - /\bR_PPC_ADDR16_HA\b/ or /\bR_PPC_RELATIVE\b/ or - /\bR_PPC_NONE\b/); - - # If we see this type of relocation it's an idication that - # we /may/ be using an old version of binutils. - if (/R_PPC64_UADDR64/) { - $old_binutils++; - } - - $bad_relocs_count++; - $bad_relocs .= $_; -} - -if ($bad_relocs_count) { - print "WARNING: $bad_relocs_count bad relocations\n"; - print $bad_relocs; -} - -if ($old_binutils) { - print "WARNING: You need at least binutils >= 2.19 to build a ". - "CONFIG_RELOCATABLE kernel\n"; -} diff --git a/arch/powerpc/relocs_check.sh b/arch/powerpc/relocs_check.sh new file mode 100755 index 000000000000..2e4ebd0e25b3 --- /dev/null +++ b/arch/powerpc/relocs_check.sh @@ -0,0 +1,59 @@ +#!/bin/sh + +# Copyright © 2015 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 script checks the relocations of a vmlinux for "suspicious" +# relocations. + +# based on relocs_check.pl +# Copyright © 2009 IBM Corporation + +if [ $# -lt 2 ]; then + echo "$0 [path to objdump] [path to vmlinux]" 1>&2 + exit 1 +fi + +# Have Kbuild supply the path to objdump so we handle cross compilation. +objdump="$1" +vmlinux="$2" + +bad_relocs=$( +"$objdump" -R "$vmlinux" | + # Only look at relocation lines. + grep -E '\<R_' | + # These relocations are okay + # On PPC64: + # R_PPC64_RELATIVE, R_PPC64_NONE + # R_PPC64_ADDR64 mach_<name> + # On PPC: + # R_PPC_RELATIVE, R_PPC_ADDR16_HI, + # R_PPC_ADDR16_HA,R_PPC_ADDR16_LO, + # R_PPC_NONE + grep -F -w -v 'R_PPC64_RELATIVE +R_PPC64_NONE +R_PPC_ADDR16_LO +R_PPC_ADDR16_HI +R_PPC_ADDR16_HA +R_PPC_RELATIVE +R_PPC_NONE' | + grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' +) + +if [ -z "$bad_relocs" ]; then + exit 0 +fi + +num_bad=$(echo "$bad_relocs" | wc -l) +echo "WARNING: $num_bad bad relocations" +echo "$bad_relocs" + +# If we see this type of relocation it's an idication that +# we /may/ be using an old version of binutils. +if echo "$bad_relocs" | grep -q -F -w R_PPC64_UADDR64; then + echo "WARNING: You need at least binutils >= 2.19 to build a CONFIG_RELOCATABLE kernel" +fi diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 9e5353ff6d1b..d00a5663e312 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -369,7 +369,7 @@ static int dart_dma_set_mask(struct device *dev, u64 dma_mask) return 0; } -void __init iommu_init_early_dart(void) +void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops) { struct device_node *dn; @@ -395,8 +395,8 @@ void __init iommu_init_early_dart(void) if (dart_is_u4) ppc_md.dma_set_mask = dart_dma_set_mask; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart; + controller_ops->dma_dev_setup = pci_dma_dev_setup_dart; + controller_ops->dma_bus_setup = pci_dma_bus_setup_dart; /* Setup pci_dma ops */ set_pci_dma_ops(&dma_iommu_ops); @@ -404,8 +404,8 @@ void __init iommu_init_early_dart(void) bail: /* If init failed, use direct iommu and null setup functions */ - ppc_md.pci_dma_dev_setup = NULL; - ppc_md.pci_dma_bus_setup = NULL; + controller_ops->dma_dev_setup = NULL; + controller_ops->dma_bus_setup = NULL; /* Setup pci_dma ops */ set_pci_dma_ops(&dma_direct_ops); diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c index 2d8a101b6b9e..121e26fffd50 100644 --- a/arch/powerpc/sysdev/dcr.c +++ b/arch/powerpc/sysdev/dcr.c @@ -54,7 +54,7 @@ bool dcr_map_ok_generic(dcr_host_t host) else if (host.type == DCR_HOST_MMIO) return dcr_map_ok_mmio(host.host.mmio); else - return 0; + return false; } EXPORT_SYMBOL_GPL(dcr_map_ok_generic); diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 4bbb4b8dfd09..f086c6f22dc9 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -162,7 +162,17 @@ static void fsl_compose_msi_msg(struct pci_dev *pdev, int hwirq, msg->address_lo = lower_32_bits(address); msg->address_hi = upper_32_bits(address); - msg->data = hwirq; + /* + * MPIC version 2.0 has erratum PIC1. It causes + * that neither MSI nor MSI-X can work fine. + * This is a workaround to allow MSI-X to function + * properly. It only works for MSI-X, we prevent + * MSI on buggy chips in fsl_setup_msi_irqs(). + */ + if (msi_data->feature & MSI_HW_ERRATA_ENDIAN) + msg->data = __swab32(hwirq); + else + msg->data = hwirq; pr_debug("%s: allocated srs: %d, ibs: %d\n", __func__, (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK, @@ -180,8 +190,16 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct msi_msg msg; struct fsl_msi *msi_data; - if (type == PCI_CAP_ID_MSIX) - pr_debug("fslmsi: MSI-X untested, trying anyway.\n"); + if (type == PCI_CAP_ID_MSI) { + /* + * MPIC version 2.0 has erratum PIC1. For now MSI + * could not work. So check to prevent MSI from + * being used on the board with this erratum. + */ + list_for_each_entry(msi_data, &msi_head, list) + if (msi_data->feature & MSI_HW_ERRATA_ENDIAN) + return -EINVAL; + } /* * If the PCI node has an fsl,msi property, then we need to use it @@ -446,6 +464,11 @@ static int fsl_of_msi_probe(struct platform_device *dev) msi->feature = features->fsl_pic_ip; + /* For erratum PIC1 on MPIC version 2.0*/ + if ((features->fsl_pic_ip & FSL_PIC_IP_MASK) == FSL_PIC_IP_MPIC + && (fsl_mpic_primary_get_version() == 0x0200)) + msi->feature |= MSI_HW_ERRATA_ENDIAN; + /* * Remember the phandle, so that we can match with any PCI nodes * that have an "fsl,msi" property. diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h index 420cfcbdac01..a67359d993e5 100644 --- a/arch/powerpc/sysdev/fsl_msi.h +++ b/arch/powerpc/sysdev/fsl_msi.h @@ -27,6 +27,8 @@ #define FSL_PIC_IP_IPIC 0x00000002 #define FSL_PIC_IP_VMPIC 0x00000003 +#define MSI_HW_ERRATA_ENDIAN 0x00000010 + struct fsl_msi_cascade_data; struct fsl_msi { diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 4b74c276e427..9a8fcf0d79d7 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -111,6 +111,18 @@ static struct pci_ops fsl_indirect_pcie_ops = #define MAX_PHYS_ADDR_BITS 40 static u64 pci64_dma_offset = 1ull << MAX_PHYS_ADDR_BITS; +#ifdef CONFIG_SWIOTLB +static void setup_swiotlb_ops(struct pci_controller *hose) +{ + if (ppc_swiotlb_enable) { + hose->controller_ops.dma_dev_setup = pci_dma_dev_setup_swiotlb; + set_pci_dma_ops(&swiotlb_dma_ops); + } +} +#else +static inline void setup_swiotlb_ops(struct pci_controller *hose) {} +#endif + static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask) { if (!dev->dma_mask || !dma_supported(dev, dma_mask)) @@ -548,6 +560,9 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary) /* Setup PEX window registers */ setup_pci_atmu(hose); + /* Set up controller operations */ + setup_swiotlb_ops(hose); + return 0; no_bridge: diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index bbfbbf2025fd..b2b8447a227a 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -655,7 +655,6 @@ static inline struct mpic * mpic_from_irq_data(struct irq_data *d) static inline void mpic_eoi(struct mpic *mpic) { mpic_cpu_write(MPIC_INFO(CPU_EOI), 0); - (void)mpic_cpu_read(MPIC_INFO(CPU_WHOAMI)); } /* @@ -1676,31 +1675,6 @@ void __init mpic_init(struct mpic *mpic) mpic_err_int_init(mpic, MPIC_FSL_ERR_INT); } -void __init mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio) -{ - u32 v; - - v = mpic_read(mpic->gregs, MPIC_GREG_GLOBAL_CONF_1); - v &= ~MPIC_GREG_GLOBAL_CONF_1_CLK_RATIO_MASK; - v |= MPIC_GREG_GLOBAL_CONF_1_CLK_RATIO(clock_ratio); - mpic_write(mpic->gregs, MPIC_GREG_GLOBAL_CONF_1, v); -} - -void __init mpic_set_serial_int(struct mpic *mpic, int enable) -{ - unsigned long flags; - u32 v; - - raw_spin_lock_irqsave(&mpic_lock, flags); - v = mpic_read(mpic->gregs, MPIC_GREG_GLOBAL_CONF_1); - if (enable) - v |= MPIC_GREG_GLOBAL_CONF_1_SIE; - else - v &= ~MPIC_GREG_GLOBAL_CONF_1_SIE; - mpic_write(mpic->gregs, MPIC_GREG_GLOBAL_CONF_1, v); - raw_spin_unlock_irqrestore(&mpic_lock, flags); -} - void mpic_irq_set_priority(unsigned int irq, unsigned int pri) { struct mpic *mpic = mpic_find(irq); @@ -1923,7 +1897,7 @@ void smp_mpic_message_pass(int cpu, int msg) msg * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), physmask); } -int __init smp_mpic_probe(void) +void __init smp_mpic_probe(void) { int nr_cpus; @@ -1935,8 +1909,6 @@ int __init smp_mpic_probe(void) if (nr_cpus > 1) mpic_request_ipis(); - - return nr_cpus; } void smp_mpic_setup_cpu(int cpu) diff --git a/arch/powerpc/sysdev/qe_lib/qe_io.c b/arch/powerpc/sysdev/qe_lib/qe_io.c index d09994164daf..7ea0174f6d3d 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_io.c +++ b/arch/powerpc/sysdev/qe_lib/qe_io.c @@ -190,28 +190,3 @@ int par_io_of_config(struct device_node *np) return 0; } EXPORT_SYMBOL(par_io_of_config); - -#ifdef DEBUG -static void dump_par_io(void) -{ - unsigned int i; - - printk(KERN_INFO "%s: par_io=%p\n", __func__, par_io); - for (i = 0; i < num_par_io_ports; i++) { - printk(KERN_INFO " cpodr[%u]=%08x\n", i, - in_be32(&par_io[i].cpodr)); - printk(KERN_INFO " cpdata[%u]=%08x\n", i, - in_be32(&par_io[i].cpdata)); - printk(KERN_INFO " cpdir1[%u]=%08x\n", i, - in_be32(&par_io[i].cpdir1)); - printk(KERN_INFO " cpdir2[%u]=%08x\n", i, - in_be32(&par_io[i].cpdir2)); - printk(KERN_INFO " cppar1[%u]=%08x\n", i, - in_be32(&par_io[i].cppar1)); - printk(KERN_INFO " cppar2[%u]=%08x\n", i, - in_be32(&par_io[i].cppar2)); - } - -} -EXPORT_SYMBOL(dump_par_io); -#endif /* DEBUG */ diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/arch/powerpc/sysdev/qe_lib/ucc_slow.c index befaf1123f7f..5f91628209eb 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c +++ b/arch/powerpc/sysdev/qe_lib/ucc_slow.c @@ -43,11 +43,6 @@ u32 ucc_slow_get_qe_cr_subblock(int uccs_num) } EXPORT_SYMBOL(ucc_slow_get_qe_cr_subblock); -void ucc_slow_poll_transmitter_now(struct ucc_slow_private * uccs) -{ - out_be16(&uccs->us_regs->utodr, UCC_SLOW_TOD); -} - void ucc_slow_graceful_stop_tx(struct ucc_slow_private * uccs) { struct ucc_slow_info *us_info = uccs->us_info; diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 125743b58c70..878a54036a25 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -140,15 +140,13 @@ static void xics_request_ipi(void) IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL)); } -int __init xics_smp_probe(void) +void __init xics_smp_probe(void) { /* Setup cause_ipi callback based on which ICP is used */ smp_ops->cause_ipi = icp_ops->cause_ipi; /* Register all the IPIs */ xics_request_ipi(); - - return num_possible_cpus(); } #endif /* CONFIG_SMP */ |
