diff options
213 files changed, 9427 insertions, 2613 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 8f4d50b0adf..a3128ca0fe1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -193,6 +193,12 @@ config SYS_SUPPORTS_APM_EMULATION default y if PMAC_APM_EMU bool +config EPAPR_BOOT + bool + help + Used to allow a board to specify it wants an ePAPR compliant wrapper. + default n + config DEFAULT_UIMAGE bool help diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 2d38a50e66b..a597dd77b90 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -267,6 +267,11 @@ config PPC_EARLY_DEBUG_USBGECKO Select this to enable early debugging for Nintendo GameCube/Wii consoles via an external USB Gecko adapter. +config PPC_EARLY_DEBUG_WSP + bool "Early debugging via WSP's internal UART" + depends on PPC_WSP + select PPC_UDBG_16550 + endchoice config PPC_EARLY_DEBUG_44x_PHYSLOW diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 89178164af5..c26200b40a4 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -69,7 +69,8 @@ src-wlib := string.S crt0.S crtsavres.S stdio.c main.c \ cpm-serial.c stdlib.c mpc52xx-psc.c planetcore.c uartlite.c \ fsl-soc.c mpc8xx.c pq2.c ugecon.c src-plat := of.c cuboot-52xx.c cuboot-824x.c cuboot-83xx.c cuboot-85xx.c holly.c \ - cuboot-ebony.c cuboot-hotfoot.c treeboot-ebony.c prpmc2800.c \ + cuboot-ebony.c cuboot-hotfoot.c epapr.c treeboot-ebony.c \ + prpmc2800.c \ ps3-head.S ps3-hvcall.S ps3.c treeboot-bamboo.c cuboot-8xx.c \ cuboot-pq2.c cuboot-sequoia.c treeboot-walnut.c \ cuboot-bamboo.c cuboot-mpc7448hpc2.c cuboot-taishan.c \ @@ -127,7 +128,7 @@ quiet_cmd_bootas = BOOTAS $@ cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< quiet_cmd_bootar = BOOTAR $@ - cmd_bootar = $(CROSS32AR) -cr $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ + cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ $(obj-libfdt): $(obj)/%.o: $(srctree)/scripts/dtc/libfdt/%.c FORCE $(call if_changed_dep,bootcc) @@ -182,6 +183,7 @@ image-$(CONFIG_PPC_HOLLY) += dtbImage.holly image-$(CONFIG_PPC_PRPMC2800) += dtbImage.prpmc2800 image-$(CONFIG_PPC_ISERIES) += zImage.iseries image-$(CONFIG_DEFAULT_UIMAGE) += uImage +image-$(CONFIG_EPAPR_BOOT) += zImage.epapr # # Targets which embed a device tree blob diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index f1c4dfc635b..0f7428a37ef 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -6,16 +6,28 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * NOTE: this code runs in 32 bit mode and is packaged as ELF32. + * NOTE: this code runs in 32 bit mode, is position-independent, + * and is packaged as ELF32. */ #include "ppc_asm.h" .text - /* a procedure descriptor used when booting this as a COFF file */ + /* A procedure descriptor used when booting this as a COFF file. + * When making COFF, this comes first in the link and we're + * linked at 0x500000. + */ .globl _zimage_start_opd _zimage_start_opd: - .long _zimage_start, 0, 0, 0 + .long 0x500000, 0, 0, 0 + +p_start: .long _start +p_etext: .long _etext +p_bss_start: .long __bss_start +p_end: .long _end + + .weak _platform_stack_top +p_pstack: .long _platform_stack_top .weak _zimage_start .globl _zimage_start @@ -24,37 +36,65 @@ _zimage_start: _zimage_start_lib: /* Work out the offset between the address we were linked at and the address where we're running. */ - bl 1f -1: mflr r0 - lis r9,1b@ha - addi r9,r9,1b@l - subf. r0,r9,r0 - beq 3f /* if running at same address as linked */ + bl .+4 +p_base: mflr r10 /* r10 now points to runtime addr of p_base */ + /* grab the link address of the dynamic section in r11 */ + addis r11,r10,(_GLOBAL_OFFSET_TABLE_-p_base)@ha + lwz r11,(_GLOBAL_OFFSET_TABLE_-p_base)@l(r11) + cmpwi r11,0 + beq 3f /* if not linked -pie */ + /* get the runtime address of the dynamic section in r12 */ + .weak __dynamic_start + addis r12,r10,(__dynamic_start-p_base)@ha + addi r12,r12,(__dynamic_start-p_base)@l + subf r11,r11,r12 /* runtime - linktime offset */ + + /* The dynamic section contains a series of tagged entries. + * We need the RELA and RELACOUNT entries. */ +RELA = 7 +RELACOUNT = 0x6ffffff9 + li r9,0 + li r0,0 +9: lwz r8,0(r12) /* get tag */ + cmpwi r8,0 + beq 10f /* end of list */ + cmpwi r8,RELA + bne 11f + lwz r9,4(r12) /* get RELA pointer in r9 */ + b 12f +11: addis r8,r8,(-RELACOUNT)@ha + cmpwi r8,RELACOUNT@l + bne 12f + lwz r0,4(r12) /* get RELACOUNT value in r0 */ +12: addi r12,r12,8 + b 9b - /* The .got2 section contains a list of addresses, so add - the address offset onto each entry. */ - lis r9,__got2_start@ha - addi r9,r9,__got2_start@l - lis r8,__got2_end@ha - addi r8,r8,__got2_end@l - subf. r8,r9,r8 + /* The relocation section contains a list of relocations. + * We now do the R_PPC_RELATIVE ones, which point to words + * which need to be initialized with addend + offset. + * The R_PPC_RELATIVE ones come first and there are RELACOUNT + * of them. */ +10: /* skip relocation if we don't have both */ + cmpwi r0,0 beq 3f - srwi. r8,r8,2 - mtctr r8 - add r9,r0,r9 -2: lwz r8,0(r9) - add r8,r8,r0 - stw r8,0(r9) - addi r9,r9,4 + cmpwi r9,0 + beq 3f + + add r9,r9,r11 /* Relocate RELA pointer */ + mtctr r0 +2: lbz r0,4+3(r9) /* ELF32_R_INFO(reloc->r_info) */ + cmpwi r0,22 /* R_PPC_RELATIVE */ + bne 3f + lwz r12,0(r9) /* reloc->r_offset */ + lwz r0,8(r9) /* reloc->r_addend */ + add r0,r0,r11 + stwx r0,r11,r12 + addi r9,r9,12 bdnz 2b /* Do a cache flush for our text, in case the loader didn't */ -3: lis r9,_start@ha - addi r9,r9,_start@l - add r9,r0,r9 - lis r8,_etext@ha - addi r8,r8,_etext@l - add r8,r0,r8 +3: lwz r9,p_start-p_base(r10) /* note: these are relocated now */ + lwz r8,p_etext-p_base(r10) 4: dcbf r0,r9 icbi r0,r9 addi r9,r9,0x20 @@ -64,27 +104,19 @@ _zimage_start_lib: isync /* Clear the BSS */ - lis r9,__bss_start@ha - addi r9,r9,__bss_start@l - add r9,r0,r9 - lis r8,_end@ha - addi r8,r8,_end@l - add r8,r0,r8 - li r10,0 -5: stw r10,0(r9) + lwz r9,p_bss_start-p_base(r10) + lwz r8,p_end-p_base(r10) + li r0,0 +5: stw r0,0(r9) addi r9,r9,4 cmplw cr0,r9,r8 blt 5b /* Possibly set up a custom stack */ -.weak _platform_stack_top - lis r8,_platform_stack_top@ha - addi r8,r8,_platform_stack_top@l + lwz r8,p_pstack-p_base(r10) cmpwi r8,0 beq 6f - add r8,r0,r8 lwz r1,0(r8) - add r1,r0,r1 li r0,0 stwu r0,-16(r1) /* establish a stack frame */ 6: diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c new file mode 100644 index 00000000000..06c1961bd12 --- /dev/null +++ b/arch/powerpc/boot/epapr.c @@ -0,0 +1,66 @@ +/* + * Bootwrapper for ePAPR compliant firmwares + * + * Copyright 2010 David Gibson <david@gibson.dropbear.id.au>, IBM Corporation. + * + * Based on earlier bootwrappers by: + * (c) Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp,\ + * and + * Scott Wood <scottwood@freescale.com> + * Copyright (c) 2007 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include "ops.h" +#include "stdio.h" +#include "io.h" +#include <libfdt.h> + +BSS_STACK(4096); + +#define EPAPR_SMAGIC 0x65504150 +#define EPAPR_EMAGIC 0x45504150 + +static unsigned epapr_magic; +static unsigned long ima_size; +static unsigned long fdt_addr; + +static void platform_fixups(void) +{ + if ((epapr_magic != EPAPR_EMAGIC) + && (epapr_magic != EPAPR_SMAGIC)) + fatal("r6 contained 0x%08x instead of ePAPR magic number\n", + epapr_magic); + + if (ima_size < (unsigned long)_end) + printf("WARNING: Image loaded outside IMA!" + " (_end=%p, ima_size=0x%lx)\n", _end, ima_size); + if (ima_size < fdt_addr) + printf("WARNING: Device tree address is outside IMA!" + "(fdt_addr=0x%lx, ima_size=0x%lx)\n", fdt_addr, + ima_size); + if (ima_size < fdt_addr + fdt_totalsize((void *)fdt_addr)) + printf("WARNING: Device tree extends outside IMA!" + " (fdt_addr=0x%lx, size=0x%x, ima_size=0x%lx\n", + fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size); +} + +void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7) +{ + epapr_magic = r6; + ima_size = r7; + fdt_addr = r3; + + /* FIXME: we should process reserve entries */ + + simple_alloc_init(_end, ima_size - (unsigned long)_end, 32, 64); + + fdt_init((void *)fdt_addr); + + serial_console_init(); + platform_ops.fixups = platform_fixups; +} diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index cb97e7511d7..c74531af72c 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -39,6 +39,7 @@ dts= cacheit= binary= gzip=.gz +pie= # cross-compilation prefix CROSS= @@ -157,9 +158,10 @@ pmac|chrp) platformo=$object/of.o ;; coff) - platformo=$object/of.o + platformo="$object/crt0.o $object/of.o" lds=$object/zImage.coff.lds link_address='0x500000' + pie= ;; miboot|uboot) # miboot and U-boot want just the bare bits, not an ELF binary @@ -208,6 +210,7 @@ ps3) ksection=.kernel:vmlinux.bin isection=.kernel:initrd link_address='' + pie= ;; ep88xc|ep405|ep8248e) platformo="$object/fixed-head.o $object/$platform.o" @@ -244,6 +247,10 @@ gamecube|wii) treeboot-iss4xx-mpic) platformo="$object/treeboot-iss4xx.o" ;; +epapr) + link_address='0x20000000' + pie=-pie + ;; esac vmz="$tmpdir/`basename \"$kernel\"`.$ext" @@ -251,7 +258,7 @@ if [ -z "$cacheit" -o ! -f "$vmz$gzip" -o "$vmz$gzip" -ot "$kernel" ]; then ${CROSS}objcopy $objflags "$kernel" "$vmz.$$" if [ -n "$gzip" ]; then - gzip -f -9 "$vmz.$$" + gzip -n -f -9 "$vmz.$$" fi if [ -n "$cacheit" ]; then @@ -310,9 +317,9 @@ fi if [ "$platform" != "miboot" ]; then if [ -n "$link_address" ] ; then - text_start="-Ttext $link_address --defsym _start=$link_address" + text_start="-Ttext $link_address" fi - ${CROSS}ld -m elf32ppc -T $lds $text_start -o "$ofile" \ + ${CROSS}ld -m elf32ppc -T $lds $text_start $pie -o "$ofile" \ $platformo $tmp $object/wrapper.a rm $tmp fi @@ -336,7 +343,7 @@ coff) $objbin/hack-coff "$ofile" ;; cuboot*) - gzip -f -9 "$ofile" + gzip -n -f -9 "$ofile" ${MKIMAGE} -A ppc -O linux -T kernel -C gzip -a "$base" -e "$entry" \ $uboot_version -d "$ofile".gz "$ofile" ;; @@ -383,6 +390,6 @@ ps3) odir="$(dirname "$ofile.bin")" rm -f "$odir/otheros.bld" - gzip --force -9 --stdout "$ofile.bin" > "$odir/otheros.bld" + gzip -n --force -9 --stdout "$ofile.bin" > "$odir/otheros.bld" ;; esac diff --git a/arch/powerpc/boot/zImage.coff.lds.S b/arch/powerpc/boot/zImage.coff.lds.S index 856dc78b14e..de4c9e3c934 100644 --- a/arch/powerpc/boot/zImage.coff.lds.S +++ b/arch/powerpc/boot/zImage.coff.lds.S @@ -3,13 +3,13 @@ ENTRY(_zimage_start_opd) EXTERN(_zimage_start_opd) SECTIONS { - _start = .; .text : { + _start = .; *(.text) *(.fixup) + _etext = .; } - _etext = .; . = ALIGN(4096); .data : { @@ -17,9 +17,7 @@ SECTIONS *(.data*) *(__builtin_*) *(.sdata*) - __got2_start = .; *(.got2) - __got2_end = .; _dtb_start = .; *(.kernel:dtb) diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S index 0962d62bdb5..2bd8731f136 100644 --- a/arch/powerpc/boot/zImage.lds.S +++ b/arch/powerpc/boot/zImage.lds.S @@ -3,49 +3,64 @@ ENTRY(_zimage_start) EXTERN(_zimage_start) SECTIONS { - _start = .; .text : { + _start = .; *(.text) *(.fixup) + _etext = .; } - _etext = .; . = ALIGN(4096); .data : { *(.rodata*) *(.data*) *(.sdata*) - __got2_start = .; *(.got2) - __got2_end = .; } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .dynamic : + { + __dynamic_start = .; + *(.dynamic) + } + .hash : { *(.hash) } + .interp : { *(.interp) } + .rela.dyn : { *(.rela*) } . = ALIGN(8); - _dtb_start = .; - .kernel:dtb : { *(.kernel:dtb) } - _dtb_end = .; - - . = ALIGN(4096); - _vmlinux_start = .; - .kernel:vmlinux.strip : { *(.kernel:vmlinux.strip) } - _vmlinux_end = .; + .kernel:dtb : + { + _dtb_start = .; + *(.kernel:dtb) + _dtb_end = .; + } . = ALIGN(4096); - _initrd_start = .; - .kernel:initrd : { *(.kernel:initrd) } - _initrd_end = .; + .kernel:vmlinux.strip : + { + _vmlinux_start = .; + *(.kernel:vmlinux.strip) + _vmlinux_end = .; + } . = ALIGN(4096); - _edata = .; + .kernel:initrd : + { + _initrd_start = .; + *(.kernel:initrd) + _initrd_end = .; + } . = ALIGN(4096); - __bss_start = .; .bss : { - *(.sbss) - *(.bss) + _edata = .; + __bss_start = .; + *(.sbss) + *(.bss) + *(COMMON) + _end = . ; } - . = ALIGN(4096); - _end = . ; } diff --git a/arch/powerpc/configs/c2k_defconfig b/arch/powerpc/configs/c2k_defconfig index f9e6a3ea5a6..2a84fd7f631 100644 --- a/arch/powerpc/configs/c2k_defconfig +++ b/arch/powerpc/configs/c2k_defconfig @@ -132,8 +132,8 @@ CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_IND=y CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m +CONFIG_BT_L2CAP=y +CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index ac4fc41035f..f8b394a76ac 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -112,8 +112,8 @@ CONFIG_IRDA_CACHE_LAST_LSAP=y CONFIG_IRDA_FAST_RR=y CONFIG_IRTTY_SIR=m CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m +CONFIG_BT_L2CAP=y +CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 0a10fb009ef..214208924a9 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -351,8 +351,8 @@ CONFIG_VLSI_FIR=m CONFIG_VIA_FIR=m CONFIG_MCS_FIR=m CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m +CONFIG_BT_L2CAP=y +CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index caba919f65d..6472322bf13 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -52,8 +52,8 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_INET_DIAG is not set CONFIG_IPV6=y CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m +CONFIG_BT_L2CAP=y +CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 249ddd0a27c..7de13865508 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -146,12 +146,18 @@ CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_SCSI_SAS_ATTRS=m +CONFIG_SCSI_CXGB3_ISCSI=m +CONFIG_SCSI_CXGB4_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_BE2ISCSI=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m +CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_LPFC=m CONFIG_ATA=y # CONFIG_ATA_SFF is not set @@ -197,6 +203,8 @@ CONFIG_S2IO=m CONFIG_MYRI10GE=m CONFIG_NETXEN_NIC=m CONFIG_MLX4_EN=m +CONFIG_QLGE=m +CONFIG_BE2NET=m CONFIG_PPP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 1833d1a07e7..4efbfb3f325 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -178,22 +178,18 @@ extern const char *powerpc_base_platform; #define LONG_ASM_CONST(x) 0 #endif -#define CPU_FTR_SLB LONG_ASM_CONST(0x0000000100000000) -#define CPU_FTR_16M_PAGE LONG_ASM_CONST(0x0000000200000000) -#define CPU_FTR_TLBIEL LONG_ASM_CONST(0x0000000400000000) + +#define CPU_FTR_HVMODE_206 LONG_ASM_CONST(0x0000000800000000) +#define CPU_FTR_CFAR LONG_ASM_CONST(0x0000001000000000) #define CPU_FTR_IABR LONG_ASM_CONST(0x0000002000000000) #define CPU_FTR_MMCRA LONG_ASM_CONST(0x0000004000000000) #define CPU_FTR_CTRL LONG_ASM_CONST(0x0000008000000000) #define CPU_FTR_SMT LONG_ASM_CONST(0x0000010000000000) -#define CPU_FTR_LOCKLESS_TLBIE LONG_ASM_CONST(0x0000040000000000) -#define CPU_FTR_CI_LARGE_PAGE LONG_ASM_CONST(0x0000100000000000) #define CPU_FTR_PAUSE_ZERO LONG_ASM_CONST(0x0000200000000000) #define CPU_FTR_PURR LONG_ASM_CONST(0x0000400000000000) #define CPU_FTR_CELL_TB_BUG LONG_ASM_CONST(0x0000800000000000) #define CPU_FTR_SPURR LONG_ASM_CONST(0x0001000000000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0002000000000000) -#define CPU_FTR_1T_SEGMENT LONG_ASM_CONST(0x0004000000000000) -#define CPU_FTR_NO_SLBIE_B LONG_ASM_CONST(0x0008000000000000) #define CPU_FTR_VSX LONG_ASM_CONST(0x0010000000000000) #define CPU_FTR_SAO LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0040000000000000) @@ -202,12 +198,14 @@ extern const char *powerpc_base_platform; #define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0200000000000000) #define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0800000000000000) +#define CPU_FTR_ICSWX LONG_ASM_CONST(0x1000000000000000) #ifndef __ASSEMBLY__ -#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_SLB | \ - CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | \ - CPU_FTR_NODSISRALIGN | CPU_FTR_16M_PAGE) +#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN) + +#define MMU_FTR_PPCAS_ARCH_V2 (MMU_FTR_SLB | MMU_FTR_TLBIEL | \ + MMU_FTR_16M_PAGE) /* We only set the altivec features if the kernel was compiled with altivec * support @@ -407,44 +405,45 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_POWER5 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ - CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ - CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS | \ - CPU_FTR_POPCNTB) + CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \ + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB) #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ - CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ + CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \ - CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB) + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_HVMODE_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ - CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ + CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ - CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD) + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ + CPU_FTR_ICSWX | CPU_FTR_CFAR) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ - CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \ - CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \ + CPU_FTR_PAUSE_ZERO | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \ CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_PPCAS_ARCH_V2 | \ - CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \ - CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B) + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \ + CPU_FTR_PURR | CPU_FTR_REAL_LE) #define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2) +#define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \ + CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN) + #ifdef __powerpc64__ #ifdef CONFIG_PPC_BOOK3E -#define CPU_FTRS_POSSIBLE (CPU_FTRS_E5500) +#define CPU_FTRS_POSSIBLE (CPU_FTRS_E5500 | CPU_FTRS_A2) #else #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 | \ CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 | \ CPU_FTRS_POWER7 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \ - CPU_FTR_1T_SEGMENT | CPU_FTR_VSX) + CPU_FTR_VSX) #endif #else enum { @@ -487,7 +486,7 @@ enum { #ifdef __powerpc64__ #ifdef CONFIG_PPC_BOOK3E -#define CPU_FTRS_ALWAYS (CPU_FTRS_E5500) +#define CPU_FTRS_ALWAYS (CPU_FTRS_E5500 & CPU_FTRS_A2) #else #define CPU_FTRS_ALWAYS \ (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 & \ diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index f71bb4c118b..ce516e5eb0d 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -37,16 +37,16 @@ extern cpumask_t threads_core_mask; * This can typically be used for things like IPI for tlb invalidations * since those need to be done only once per core/TLB */ -static inline cpumask_t cpu_thread_mask_to_cores(cpumask_t threads) +static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads) { cpumask_t tmp, res; int i; - res = CPU_MASK_NONE; + cpumask_clear(&res); for (i = 0; i < NR_CPUS; i += threads_per_core) { - cpus_shift_left(tmp, threads_core_mask, i); - if (cpus_intersects(threads, tmp)) - cpu_set(i, res); + cpumask_shift_left(&tmp, &threads_core_mask, i); + if (cpumask_intersects(threads, &tmp)) + cpumask_set_cpu(i, &res); } return res; } @@ -58,7 +58,7 @@ static inline int cpu_nr_cores(void) static inline cpumask_t cpu_online_cores_map(void) { - return cpu_thread_mask_to_cores(cpu_online_map); + return cpu_thread_mask_to_cores(cpu_online_mask); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 0893ab9343a..9c70d0ca96d 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -27,9 +27,8 @@ enum ppc_dbell { PPC_G_DBELL_MC = 4, /* guest mcheck doorbell */ }; -extern void doorbell_message_pass(int target, int msg); +extern void doorbell_cause_ipi(int cpu, unsigned long data); extern void doorbell_exception(struct pt_regs *regs); -extern void doorbell_check_self(void); extern void doorbell_setup_this_cpu(void); static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index f0fb4fc1f6e..45921672b97 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -52,6 +52,10 @@ extern struct ppc_emulated { #ifdef CONFIG_VSX struct ppc_emulated_entry vsx; #endif +#ifdef CONFIG_PPC64 + struct ppc_emulated_entry mfdscr; + struct ppc_emulated_entry mtdscr; +#endif } ppc_emulated; extern u32 ppc_warn_emulated; diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 7778d6f0c87..f5dfe3411f6 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -46,6 +46,7 @@ #define EX_CCR 60 #define EX_R3 64 #define EX_LR 72 +#define EX_CFAR 80 /* * We're short on space and time in the exception prolog, so we can't @@ -56,30 +57,40 @@ #define LOAD_HANDLER(reg, label) \ addi reg,reg,(label)-_stext; /* virt addr of handler ... */ -#define EXCEPTION_PROLOG_1(area) \ - mfspr r13,SPRN_SPRG_PACA; /* get paca address into r13 */ \ +/* Exception register prefixes */ +#define EXC_HV H +#define EXC_STD + +#define EXCEPTION_PROLOG_1(area) \ + GET_PACA(r13); \ std r9,area+EX_R9(r13); /* save r9 - r12 */ \ std r10,area+EX_R10(r13); \ std r11,area+EX_R11(r13); \ std r12,area+EX_R12(r13); \ - mfspr r9,SPRN_SPRG_SCRATCH0; \ + BEGIN_FTR_SECTION_NESTED(66); \ + mfspr r10,SPRN_CFAR; \ + std r10,area+EX_CFAR(r13); \ + END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ + GET_SCRATCH0(r9); \ std r9,area+EX_R13(r13); \ mfcr r9 -#define EXCEPTION_PROLOG_PSERIES_1(label) \ +#define __EXCEPTION_PROLOG_PSERIES_1(label, h) \ ld r12,PACAKBASE(r13); /* get high part of &label */ \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ - mfspr r11,SPRN_SRR0; /* save SRR0 */ \ + mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label) \ - mtspr SPRN_SRR0,r12; \ - mfspr r12,SPRN_SRR1; /* and SRR1 */ \ - mtspr SPRN_SRR1,r10; \ - rfid; \ + mtspr SPRN_##h##SRR0,r12; \ + mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ + mtspr SPRN_##h##SRR1,r10; \ + h##rfid; \ b . /* prevent speculative execution */ +#define EXCEPTION_PROLOG_PSERIES_1(label, h) \ + __EXCEPTION_PROLOG_PSERIES_1(label, h) -#define EXCEPTION_PROLOG_PSERIES(area, label) \ +#define EXCEPTION_PROLOG_PSERIES(area, label, h) \ EXCEPTION_PROLOG_1(area); \ - EXCEPTION_PROLOG_PSERIES_1(label); + EXCEPTION_PROLOG_PSERIES_1(label, h); /* * The common exception prolog is used for all except a few exceptions @@ -98,10 +109,11 @@ beq- 1f; \ ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ 1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ - bge- cr1,2f; /* abort if it is */ \ - b 3f; \ -2: li r1,(n); /* will be reloaded later */ \ + blt+ cr1,3f; /* abort if it is */ \ + li r1,(n); /* will be reloaded later */ \ sth r1,PACA_TRAP_SAVE(r13); \ + std r3,area+EX_R3(r13); \ + addi r3,r13,area; /* r3 -> where regs are saved*/ \ b bad_stack; \ 3: std r9,_CCR(r1); /* save CR in stackframe */ \ std r11,_NIP(r1); /* save SRR0 in stackframe */ \ @@ -123,6 +135,10 @@ std r9,GPR11(r1); \ std r10,GPR12(r1); \ std r11,GPR13(r1); \ + BEGIN_FTR_SECTION_NESTED(66); \ + ld r10,area+EX_CFAR(r13); \ + std r10,ORIG_GPR3(r1); \ + END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ mflr r9; /* save LR in stackframe */ \ std r9,_LINK(r1); \ @@ -143,57 +159,62 @@ /* * Exception vectors. */ -#define STD_EXCEPTION_PSERIES(n, label) \ - . = n; \ +#define STD_EXCEPTION_PSERIES(loc, vec, label) \ + . = loc; \ .globl label##_pSeries; \ label##_pSeries: \ HMT_MEDIUM; \ - DO_KVM n; \ - mtspr SPRN_SPRG_SCRATCH0,r13; /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) + DO_KVM vec; \ + SET_SCRATCH0(r13); /* save r13 */ \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD) -#define HSTD_EXCEPTION_PSERIES(n, label) \ - . = n; \ - .globl label##_pSeries; \ -label##_pSeries: \ +#define STD_EXCEPTION_HV(loc, vec, label) \ + . = loc; \ + .globl label##_hv; \ +label##_hv: \ HMT_MEDIUM; \ - mtspr SPRN_SPRG_SCRATCH0,r20; /* save r20 */ \ - mfspr r20,SPRN_HSRR0; /* copy HSRR0 to SRR0 */ \ - mtspr SPRN_SRR0,r20; \ - mfspr r20,SPRN_HSRR1; /* copy HSRR0 to SRR0 */ \ - mtspr SPRN_SRR1,r20; \ - mfspr r20,SPRN_SPRG_SCRATCH0; /* restore r20 */ \ - mtspr SPRN_SPRG_SCRATCH0,r13; /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) + DO_KVM vec; \ + SET_SCRATCH0(r13); /* save r13 */ \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV) - -#define MASKABLE_EXCEPTION_PSERIES(n, label) \ - . = n; \ - .globl label##_pSeries; \ -label##_pSeries: \ +#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h) \ HMT_MEDIUM; \ - DO_KVM n; \ - mtspr SPRN_SPRG_SCRATCH0,r13; /* save r13 */ \ - mfspr r13,SPRN_SPRG_PACA; /* get paca address into r13 */ \ + DO_KVM vec; \ + SET_SCRATCH0(r13); /* save r13 */ \ + GET_PACA(r13); \ std r9,PACA_EXGEN+EX_R9(r13); /* save r9, r10 */ \ std r10,PACA_EXGEN+EX_R10(r13); \ lbz r10,PACASOFTIRQEN(r13); \ mfcr r9; \ cmpwi r10,0; \ - beq masked_interrupt; \ - mfspr r10,SPRN_SPRG_SCRATCH0; \ + beq masked_##h##interrupt; \ + GET_SCRATCH0(r10); \ std r10,PACA_EXGEN+EX_R13(r13); \ std r11,PACA_EXGEN+EX_R11(r13); \ std r12,PACA_EXGEN+EX_R12(r13); \ ld r12,PACAKBASE(r13); /* get high part of &label */ \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ - mfspr r11,SPRN_SRR0; /* save SRR0 */ \ + mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label##_common) \ - mtspr SPRN_SRR0,r12; \ - mfspr r12,SPRN_SRR1; /* and SRR1 */ \ - mtspr SPRN_SRR1,r10; \ - rfid; \ + mtspr SPRN_##h##SRR0,r12; \ + mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ + mtspr SPRN_##h##SRR1,r10; \ + h##rfid; \ b . /* prevent speculative execution */ +#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h) \ + __MASKABLE_EXCEPTION_PSERIES(vec, label, h) + +#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label) \ + . = loc; \ + .globl label##_pSeries; \ +label##_pSeries: \ + _MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_STD) + +#define MASKABLE_EXCEPTION_HV(loc, vec, label) \ + . = loc; \ + .globl label##_hv; \ +label##_hv: \ + _MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_HV) #ifdef CONFIG_PPC_ISERIES #define DISABLE_INTS \ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 921a8470e18..9a67a38bf7b 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -49,7 +49,7 @@ label##5: \ FTR_ENTRY_OFFSET label##2b-label##5b; \ FTR_ENTRY_OFFSET label##3b-label##5b; \ FTR_ENTRY_OFFSET label##4b-label##5b; \ - .ifgt (label##4b-label##3b)-(label##2b-label##1b); \ + .ifgt (label##4b- label##3b)-(label##2b- label##1b); \ .error "Feature section else case larger than body"; \ .endif; \ .popsection; @@ -146,6 +146,19 @@ label##5: \ #ifndef __ASSEMBLY__ +#define ASM_FTR_IF(section_if, section_else, msk, val) \ + stringify_in_c(BEGIN_FTR_SECTION) \ + section_if "; " \ + stringify_in_c(FTR_SECTION_ELSE) \ + section_else "; " \ + stringify_in_c(ALT_FTR_SECTION_END((msk), (val))) + +#define ASM_FTR_IFSET(section_if, section_else, msk) \ + ASM_FTR_IF(section_if, section_else, (msk), (msk)) + +#define ASM_FTR_IFCLR(section_if, section_else, msk) \ + ASM_FTR_IF(section_if, section_else, (msk), 0) + #define ASM_MMU_FTR_IF(section_if, section_else, msk, val) \ stringify_in_c(BEGIN_MMU_FTR_SECTION) \ section_if "; " \ diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 4ef662e4a31..3a6c586c4e4 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -47,6 +47,7 @@ #define FW_FEATURE_BEAT ASM_CONST(0x0000000001000000) #define FW_FEATURE_CMO ASM_CONST(0x0000000002000000) #define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000) +#define FW_FEATURE_XCMO ASM_CONST(0x0000000008000000) #ifndef __ASSEMBLY__ @@ -60,7 +61,7 @@ enum { FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN | FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | - FW_FEATURE_CMO | FW_FEATURE_VPHN, + FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR, FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR, diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 8edec710cc6..852b8c1c09d 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -102,6 +102,7 @@ #define H_ANDCOND (1UL<<(63-33)) #define H_ICACHE_INVALIDATE (1UL<<(63-40)) /* icbi, etc. (ignored for IO pages) */ #define H_ICACHE_SYNCHRONIZE (1UL<<(63-41)) /* dcbst, icbi, etc (ignored for IO pages */ +#define H_COALESCE_CAND (1UL<<(63-42)) /* page is a good candidate for coalescing */ #define H_ZERO_PAGE (1UL<<(63-48)) /* zero the page before mapping (ignored for IO pages) */ #define H_COPY_PAGE (1UL<<(63-49)) #define H_N (1UL<<(63-61)) @@ -234,6 +235,7 @@ #define H_GET_MPP 0x2D4 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC #define H_BEST_ENERGY 0x2F4 +#define H_GET_MPP_X 0x314 #define MAX_HCALL_OPCODE H_BEST_ENERGY #ifndef __ASSEMBLY__ @@ -312,6 +314,16 @@ struct hvcall_mpp_data { int h_get_mpp(struct hvcall_mpp_data *); +struct hvcall_mpp_x_data { + unsigned long coalesced_bytes; + unsigned long pool_coalesced_bytes; + unsigned long pool_purr_cycles; + unsigned long pool_spurr_cycles; + unsigned long reserved[3]; +}; + +int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data); + #ifdef CONFIG_PPC_PSERIES extern int CMO_PrPSP; extern int CMO_SecPSP; diff --git a/arch/powerpc/platforms/cell/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h index 6efc7782ebf..fbae4928692 100644 --- a/arch/powerpc/platforms/cell/io-workarounds.h +++ b/arch/powerpc/include/asm/io-workarounds.h @@ -31,7 +31,6 @@ struct iowa_bus { void *private; }; -void __devinit io_workaround_init(void); void __devinit iowa_register_bus(struct pci_controller *, struct ppc_pci_io *, int (*)(struct iowa_bus *, void *), void *); struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 001f2f11c19..45698d55cd6 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -2,6 +2,8 @@ #define _ASM_POWERPC_IO_H #ifdef __KERNEL__ +#define ARCH_HAS_IOREMAP_WC + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -481,10 +483,16 @@ __do_out_asm(_rec_outl, "stwbrx") _memcpy_fromio(dst,PCI_FIX_ADDR(src),n) #endif /* !CONFIG_EEH */ -#ifdef CONFIG_PPC_INDIRECT_IO -#define DEF_PCI_HOOK(x) x +#ifdef CONFIG_PPC_INDIRECT_PIO +#define DEF_PCI_HOOK_pio(x) x +#else +#define DEF_PCI_HOOK_pio(x) NULL +#endif + +#ifdef CONFIG_PPC_INDIRECT_MMIO +#define DEF_PCI_HOOK_mem(x) x #else -#define DEF_PCI_HOOK(x) NULL +#define DEF_PCI_HOOK_mem(x) NULL #endif /* Structure containing all the hooks */ @@ -504,7 +512,7 @@ extern struct ppc_pci_io { #define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \ static inline ret name at \ { \ - if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL) \ + if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL) \ return ppc_pci_io.name al; \ return __do_##name al; \ } @@ -512,7 +520,7 @@ static inline ret name at \ #define DEF_PCI_AC_NORET(name, at, al, space, aa) \ static inline void name at \ { \ - if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL) \ + if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL) \ ppc_pci_io.name al; \ else \ __do_##name al; \ @@ -616,12 +624,13 @@ static inline void iosync(void) * * ioremap is the standard one and provides non-cacheable guarded mappings * and can be hooked by the platform via ppc_md * - * * ioremap_flags allows to specify the page flags as an argument and can - * also be hooked by the platform via ppc_md. ioremap_prot is the exact - * same thing as ioremap_flags. + * * ioremap_prot allows to specify the page flags as an argument and can + * also be hooked by the platform via ppc_md. * * * ioremap_nocache is identical to ioremap * + * * ioremap_wc enables write combining + * * * iounmap undoes such a mapping and can be hooked * * * __ioremap_at (and the pending __iounmap_at) are low level functions to @@ -629,7 +638,7 @@ static inline void iosync(void) * currently be hooked. Must be page aligned. * * * __ioremap is the low level implementation used by ioremap and - * ioremap_flags and cannot be hooked (but can be used by a hook on one + * ioremap_prot and cannot be hooked (but can be used by a hook on one * of the previous ones) * * * __ioremap_caller is the same as above but takes an explicit caller @@ -640,10 +649,10 @@ static inline void iosync(void) * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); -extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size, - unsigned long flags); +extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, + unsigned long flags); +extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); #define ioremap_nocache(addr, size) ioremap((addr), (size)) -#define ioremap_prot(addr, size, prot) ioremap_flags((addr), (size), (prot)) extern void iounmap(volatile void __iomem *addr); diff --git a/arch/powerpc/include/asm/io_event_irq.h b/arch/powerpc/include/asm/io_event_irq.h new file mode 100644 index 00000000000..b1a9a1be3c2 --- /dev/null +++ b/arch/powerpc/include/asm/io_event_irq.h @@ -0,0 +1,54 @@ +/* + * Copyright 2010, 2011 Mark Nelson and Tseng-Hui (Frank) Lin, 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. + */ + +#ifndef _ASM_POWERPC_IO_EVENT_IRQ_H +#define _ASM_POWERPC_IO_EVENT_IRQ_H + +#include <linux/types.h> +#include <linux/notifier.h> + +#define PSERIES_IOEI_RPC_MAX_LEN 216 + +#define PSERIES_IOEI_TYPE_ERR_DETECTED 0x01 +#define PSERIES_IOEI_TYPE_ERR_RECOVERED 0x02 +#define PSERIES_IOEI_TYPE_EVENT 0x03 +#define PSERIES_IOEI_TYPE_RPC_PASS_THRU 0x04 + +#define PSERIES_IOEI_SUBTYPE_NOT_APP 0x00 +#define PSERIES_IOEI_SUBTYPE_REBALANCE_REQ 0x01 +#define PSERIES_IOEI_SUBTYPE_NODE_ONLINE 0x03 +#define PSERIES_IOEI_SUBTYPE_NODE_OFFLINE 0x04 +#define PSERIES_IOEI_SUBTYPE_DUMP_SIZE_CHANGE 0x05 +#define PSERIES_IOEI_SUBTYPE_TORRENT_IRV_UPDATE 0x06 +#define PSERIES_IOEI_SUBTYPE_TORRENT_HFI_CFGED 0x07 + +#define PSERIES_IOEI_SCOPE_NOT_APP 0x00 +#define PSERIES_IOEI_SCOPE_RIO_HUB 0x36 +#define PSERIES_IOEI_SCOPE_RIO_BRIDGE 0x37 +#define PSERIES_IOEI_SCOPE_PHB 0x38 +#define PSERIES_IOEI_SCOPE_EADS_GLOBAL 0x39 +#define PSERIES_IOEI_SCOPE_EADS_SLOT 0x3A +#define PSERIES_IOEI_SCOPE_TORRENT_HUB 0x3B +#define PSERIES_IOEI_SCOPE_SERVICE_PROC 0x51 + +/* Platform Event Log Format, Version 6, data portition of IO event section */ +struct pseries_io_event { + uint8_t event_type; /* 0x00 IO-Event Type */ + uint8_t rpc_data_len; /* 0x01 RPC data length */ + uint8_t scope; /* 0x02 Error/Event Scope */ + uint8_t event_subtype; /* 0x03 I/O-Event Sub-Type */ + uint32_t drc_index; /* 0x04 DRC Index */ + uint8_t rpc_data[PSERIES_IOEI_RPC_MAX_LEN]; + /* 0x08 RPC Data (0-216 bytes, */ + /* padded to 4 bytes alignment) */ +}; + +extern struct atomic_notifier_head pseries_ioei_notifier_list; + +#endif /* _ASM_POWERPC_IO_EVENT_IRQ_H */ diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 67ab5fb7d15..1bff591f7f7 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -88,9 +88,6 @@ struct irq_host_ops { /* Dispose of such a mapping */ void (*unmap)(struct irq_host *h, unsigned int virq); - /* Update of such a mapping */ - void (*remap)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw); - /* Translate device-tree interrupt specifier from raw format coming * from the firmware to a irq_hw_number_t (interrupt line number) and * type (sense) that can be passed to set_irq_type(). In the absence @@ -128,19 +125,10 @@ struct irq_host { struct device_node *of_node; }; -/* The main irq map itself is an array of NR_IRQ entries containing the - * associate host and irq number. An entry with a host of NULL is free. - * An entry can be allocated if it's free, the allocator always then sets - * hwirq first to the host's invalid irq number and then fills ops. - */ -struct irq_map_entry { - irq_hw_number_t hwirq; - struct irq_host *host; -}; - -extern struct irq_map_entry irq_map[NR_IRQS]; - +struct irq_data; +extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d); extern irq_hw_number_t virq_to_hw(unsigned int virq); +extern bool virq_is_host(unsigned int virq, struct irq_host *host); /** * irq_alloc_host - Allocate a new irq_host data structure diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index f54408d995b..8a33698c61b 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -76,7 +76,7 @@ extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)); extern cpumask_t cpus_in_sr; static inline int kexec_sr_activated(int cpu) { - return cpu_isset(cpu,cpus_in_sr); + return cpumask_test_cpu(cpu, &cpus_in_sr); } struct kimage; diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 5b750467439..0951b17f4eb 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -59,6 +59,7 @@ #define BOOK3S_INTERRUPT_INST_SEGMENT 0x480 #define BOOK3S_INTERRUPT_EXTERNAL 0x500 #define BOOK3S_INTERRUPT_EXTERNAL_LEVEL 0x501 +#define BOOK3S_INTERRUPT_EXTERNAL_HV 0x502 #define BOOK3S_INTERRUPT_ALIGNMENT 0x600 #define BOOK3S_INTERRUPT_PROGRAM 0x700 #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 36fdb3aff30..d5a8a386163 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -34,6 +34,7 @@ (\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \ (\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \ (\intno == BOOK3S_INTERRUPT_EXTERNAL) || \ + (\intno == BOOK3S_INTERRUPT_EXTERNAL_HV) || \ (\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \ (\intno == BOOK3S_INTERRUPT_PROGRAM) || \ (\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \ diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index a077adc0b35..e0298d26ce5 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -210,6 +210,8 @@ struct dtl_entry { #define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */ #define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry)) +extern struct kmem_cache *dtl_cache; + /* * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls * reading from the dispatch trace log. If other code wants to consume diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index e4f01915fbb..47cacddb14c 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -29,21 +29,6 @@ struct file; struct pci_controller; struct kimage; -#ifdef CONFIG_SMP -struct smp_ops_t { - void (*message_pass)(int target, int msg); - int (*probe)(void); - void (*kick_cpu)(int nr); - void (*setup_cpu)(int nr); - void (*bringup_done)(void); - void (*take_timebase)(void); - void (*give_timebase)(void); - int (*cpu_disable)(void); - void (*cpu_die)(unsigned int nr); - int (*cpu_bootable)(unsigned int nr); -}; -#endif - struct machdep_calls { char *name; #ifdef CONFIG_PPC64 @@ -267,6 +252,7 @@ struct machdep_calls { extern void e500_idle(void); extern void power4_idle(void); +extern void power7_idle(void); extern void ppc6xx_idle(void); extern void book3e_idle(void); @@ -311,12 +297,6 @@ extern sys_ctrler_t sys_ctrler; #endif /* CONFIG_PPC_PMAC */ -#ifdef CONFIG_SMP -/* Poor default implementations */ -extern void __devinit smp_generic_give_timebase(void); -extern void __devinit smp_generic_take_timebase(void); -#endif /* CONFIG_SMP */ - /* Functions to produce codes on the leds. * The SRC code should be unique for the message category and should diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index 17194fcd404..3ea0f9a259d 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -43,6 +43,7 @@ #define MAS0_TLBSEL(x) (((x) << 28) & 0x30000000) #define MAS0_ESEL(x) (((x) << 16) & 0x0FFF0000) #define MAS0_NV(x) ((x) & 0x00000FFF) +#define MAS0_ESEL_MASK 0x0FFF0000 #define MAS0_HES 0x00004000 #define MAS0_WQ_ALLWAYS 0x00000000 #define MAS0_WQ_COND 0x00001000 @@ -137,6 +138,21 @@ #define MMUCSR0_TLB2PS 0x00078000 /* TLB2 Page Size */ #define MMUCSR0_TLB3PS 0x00780000 /* TLB3 Page Size */ +/* MMUCFG bits */ +#define MMUCFG_MAVN_NASK 0x00000003 +#define MMUCFG_MAVN_V1_0 0x00000000 +#define MMUCFG_MAVN_V2_0 0x00000001 +#define MMUCFG_NTLB_MASK 0x0000000c +#define MMUCFG_NTLB_SHIFT 2 +#define MMUCFG_PIDSIZE_MASK 0x000007c0 +#define MMUCFG_PIDSIZE_SHIFT 6 +#define MMUCFG_TWC 0x00008000 +#define MMUCFG_LRAT 0x00010000 +#define MMUCFG_RASIZE_MASK 0x00fe0000 +#define MMUCFG_RASIZE_SHIFT 17 +#define MMUCFG_LPIDSIZE_MASK 0x0f000000 +#define MMUCFG_LPIDSIZE_SHIFT 24 + /* TLBnCFG encoding */ #define TLBnCFG_N_ENTRY 0x00000fff /* number of entries */ #define TLBnCFG_HES 0x00002000 /* HW select supported */ @@ -229,6 +245,10 @@ extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; extern int mmu_linear_psize; extern int mmu_vmemmap_psize; +#ifdef CONFIG_PPC64 +extern unsigned long linear_map_top; +#endif + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */ diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index ae7b3efec8e..d865bd909c7 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -408,6 +408,7 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } #endif /* CONFIG_PPC_SUBPAGE_PROT */ typedef unsigned long mm_context_id_t; +struct spinlock; typedef struct { mm_context_id_t id; @@ -423,6 +424,11 @@ typedef struct { #ifdef CONFIG_PPC_SUBPAGE_PROT struct subpage_prot_table spt; #endif /* CONFIG_PPC_SUBPAGE_PROT */ +#ifdef CONFIG_PPC_ICSWX + struct spinlock *cop_lockp; /* guard acop and cop_pid */ + unsigned long acop; /* mask of enabled coprocessor types */ + unsigned int cop_pid; /* pid value used with coprocessors */ +#endif /* CONFIG_PPC_ICSWX */ } mm_context_t; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index bb40a06d3b7..4138b21ae80 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -56,11 +56,6 @@ */ #define MMU_FTR_NEED_DTLB_SW_LRU ASM_CONST(0x00200000) -/* This indicates that the processor uses the ISA 2.06 server tlbie - * mnemonics - */ -#define MMU_FTR_TLBIE_206 ASM_CONST(0x00400000) - /* Enable use of TLB reservation. Processor should support tlbsrx. * instruction and MAS0[WQ]. */ @@ -70,6 +65,53 @@ */ #define MMU_FTR_USE_PAIRED_MAS ASM_CONST(0x01000000) +/* MMU is SLB-based + */ +#define MMU_FTR_SLB ASM_CONST(0x02000000) + +/* Support 16M large pages + */ +#define MMU_FTR_16M_PAGE ASM_CONST(0x04000000) + +/* Supports TLBIEL variant + */ +#define MMU_FTR_TLBIEL ASM_CONST(0x08000000) + +/* Supports tlbies w/o locking + */ +#define MMU_FTR_LOCKLESS_TLBIE ASM_CONST(0x10000000) + +/* Large pages can be marked CI + */ +#define MMU_FTR_CI_LARGE_PAGE ASM_CONST(0x20000000) + +/* 1T segments available + */ +#define MMU_FTR_1T_SEGMENT ASM_CONST(0x40000000) + +/* Doesn't support the B bit (1T segment) in SLBIE + */ +#define MMU_FTR_NO_SLBIE_B ASM_CONST(0x80000000) + +/* MMU feature bit sets for various CPUs */ +#define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 \ + MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2 +#define MMU_FTRS_POWER4 MMU_FTRS_DEFAULT_HPTE_ARCH_V2 +#define MMU_FTRS_PPC970 MMU_FTRS_POWER4 +#define MMU_FTRS_POWER5 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE +#define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE +#define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE +#define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ + MMU_FTR_CI_LARGE_PAGE +#define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ + MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B +#define MMU_FTRS_A2 MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX | \ + MMU_FTR_USE_TLBIVAX_BCAST | \ + MMU_FTR_LOCK_BCAST_INVAL | \ + MMU_FTR_USE_TLBRSRV | \ + MMU_FTR_USE_PAIRED_MAS | \ + MMU_FTR_TLBIEL | \ + MMU_FTR_16M_PAGE #ifndef __ASSEMBLY__ #include <asm/cputable.h> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 81fb41289d6..a73668a5f30 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -32,6 +32,10 @@ extern void __destroy_context(unsigned long context_id); extern void mmu_context_init(void); #endif +extern void switch_cop(struct mm_struct *next); +extern int use_cop(unsigned long acop, struct mm_struct *mm); +extern void drop_cop(unsigned long acop, struct mm_struct *mm); + /* * switch_mm is the entry point called from the architecture independent * code in kernel/sched.c @@ -55,6 +59,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, if (prev == next) return; +#ifdef CONFIG_PPC_ICSWX + /* Switch coprocessor context only if prev or next uses a coprocessor */ + if (prev->context.acop || next->context.acop) + switch_cop(next); +#endif /* CONFIG_PPC_ICSWX */ + /* We must stop all altivec streams before changing the HW * context */ @@ -67,7 +77,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * sub architectures. */ #ifdef CONFIG_PPC_STD_MMU_64 - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) switch_slb(tsk, next); else switch_stab(tsk, next); diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h index d4b4bfa26fb..89d2f99c1bf 100644 --- a/arch/powerpc/include/asm/pSeries_reconfig.h +++ b/arch/powerpc/include/asm/pSeries_reconfig.h @@ -18,13 +18,18 @@ extern int pSeries_reconfig_notifier_register(struct notifier_block *); extern void pSeries_reconfig_notifier_unregister(struct notifier_block *); extern struct blocking_notifier_head pSeries_reconfig_chain; +/* Not the best place to put this, will be fixed when we move some + * of the rtas suspend-me stuff to pseries */ +extern void pSeries_coalesce_init(void); #else /* !CONFIG_PPC_PSERIES */ static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb) { return 0; } static inline void pSeries_reconfig_notifier_unregister(struct notifier_block *nb) { } +static inline void pSeries_coalesce_init(void) { } #endif /* CONFIG_PPC_PSERIES */ + #endif /* __KERNEL__ */ #endif /* _PPC64_PSERIES_RECONFIG_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index ec57540cd7a..74126765106 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -92,9 +92,9 @@ struct paca_struct { * Now, starting in cacheline 2, the exception save areas */ /* used for most interrupts/exceptions */ - u64 exgen[10] __attribute__((aligned(0x80))); - u64 exmc[10]; /* used for machine checks */ - u64 exslb[10]; /* used for SLB/segment table misses + u64 exgen[11] __attribute__((aligned(0x80))); + u64 exmc[11]; /* used for machine checks */ + u64 exslb[11]; /* used for SLB/segment table misses * on the linear mapping */ /* SLB related definitions */ u16 vmalloc_sllp; @@ -106,7 +106,8 @@ struct paca_struct { pgd_t *pgd; /* Current PGD */ pgd_t *kernel_pgd; /* Kernel PGD */ u64 exgen[8] __attribute__((aligned(0x80))); - u64 extlb[EX_TLB_SIZE*3] __attribute__((aligned(0x80))); + /* We can have up to 3 levels of reentrancy in the TLB miss handler */ + u64 extlb[3][EX_TLB_SIZE / sizeof(u64)] __attribute__((aligned(0x80))); u64 exmc[8]; /* used for machine checks */ u64 excrit[8]; /* used for crit interrupts */ u64 exdbg[8]; /* used for debug interrupts */ @@ -125,7 +126,7 @@ struct paca_struct { struct task_struct *__current; /* Pointer to current */ u64 kstack; /* Saved Kernel stack addr */ u64 stab_rr; /* stab/slb round-robin counter */ - u64 saved_r1; /* r1 save for RTAS calls */ + u64 saved_r1; /* r1 save for RTAS calls or PM */ u64 saved_msr; /* MSR saved here by enter_rtas */ u16 trap_save; /* Used when bad stack is encountered */ u8 soft_enabled; /* irq soft-enable flag */ diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index 812b2cd80ae..9356262fd3c 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -59,24 +59,7 @@ static __inline__ void clear_page(void *addr) : "ctr", "memory"); } -extern void copy_4K_page(void *to, void *from); - -#ifdef CONFIG_PPC_64K_PAGES -static inline void copy_page(void *to, void *from) -{ - unsigned int i; - for (i=0; i < (1 << (PAGE_SHIFT - 12)); i++) { - copy_4K_page(to, from); - to += 4096; - from += 4096; - } -} -#else /* CONFIG_PPC_64K_PAGES */ -static inline void copy_page(void *to, void *from) -{ - copy_4K_page(to, from); -} -#endif /* CONFIG_PPC_64K_PAGES */ +extern void copy_page(void *to, void *from); /* Log 2 of page table size */ extern u64 ppc64_pft_size; @@ -130,7 +113,7 @@ extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize); extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start, unsigned long len, unsigned int psize); -#define slice_mm_new_context(mm) ((mm)->context.id == 0) +#define slice_mm_new_context(mm) ((mm)->context.id == MMU_NO_CONTEXT) #endif /* __ASSEMBLY__ */ #else diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 2b09cd522d3..81576ee0cfb 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -257,21 +257,20 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old; - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - old = pte_update(mm, addr, ptep, _PAGE_RW, 0); + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old; - if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - old = pte_update(mm, addr, ptep, _PAGE_RW, 1); + + pte_update(mm, addr, ptep, _PAGE_RW, 1); } /* diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 1255569387b..e472659d906 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -41,6 +41,10 @@ #define PPC_INST_RFCI 0x4c000066 #define PPC_INST_RFDI 0x4c00004e #define PPC_INST_RFMCI 0x4c00004c +#define PPC_INST_MFSPR_DSCR 0x7c1102a6 +#define PPC_INST_MFSPR_DSCR_MASK 0xfc1fffff +#define PPC_INST_MTSPR_DSCR 0x7c1103a6 +#define PPC_INST_MTSPR_DSCR_MASK 0xfc1fffff #define PPC_INST_STRING 0x7c00042a #define PPC_INST_STRING_MASK 0xfc0007fe @@ -56,6 +60,17 @@ #define PPC_INST_TLBSRX_DOT 0x7c0006a5 #define PPC_INST_XXLOR 0xf0000510 +#define PPC_INST_NAP 0x4c000364 +#define PPC_INST_SLEEP 0x4c0003a4 + +/* A2 specific instructions */ +#define PPC_INST_ERATWE 0x7c0001a6 +#define PPC_INST_ERATRE 0x7c000166 +#define PPC_INST_ERATILX 0x7c000066 +#define PPC_INST_ERATIVAX 0x7c000666 +#define PPC_INST_ERATSX 0x7c000126 +#define PPC_INST_ERATSX_DOT 0x7c000127 + /* macros to insert fields into opcodes */ #define __PPC_RA(a) (((a) & 0x1f) << 16) #define __PPC_RB(b) (((b) & 0x1f) << 11) @@ -67,6 +82,8 @@ #define __PPC_XT(s) __PPC_XS(s) #define __PPC_T_TLB(t) (((t) & 0x3) << 21) #define __PPC_WC(w) (((w) & 0x3) << 21) +#define __PPC_WS(w) (((w) & 0x1f) << 11) + /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a * larx with EH set as an illegal instruction. @@ -113,6 +130,21 @@ #define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \ __PPC_RA(a) | __PPC_RB(b)) +#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_INST_ERATWE | \ + __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_INST_ERATRE | \ + __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_INST_ERATILX | \ + __PPC_T_TLB(t) | __PPC_RA(a) | \ + __PPC_RB(b)) +#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_INST_ERATIVAX | \ + __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_INST_ERATSX | \ + __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \ + __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b)) + + /* * Define what the VSX XX1 form instructions will look like, then add * the 128 bit load store instructions based on that. @@ -126,4 +158,7 @@ #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ VSX_XX3((t), (a), (b))) +#define PPC_NAP stringify_in_c(.long PPC_INST_NAP) +#define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) + #endif /* _ASM_POWERPC_PPC_OPCODE_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 98210067c1c..1b422381fc1 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -170,6 +170,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define HMT_MEDIUM or 2,2,2 #define HMT_MEDIUM_HIGH or 5,5,5 # medium high priority #define HMT_HIGH or 3,3,3 +#define HMT_EXTRA_HIGH or 7,7,7 # power7 only #ifdef __KERNEL__ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index de1967a1ff5..d50c2b6d9bc 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -238,6 +238,10 @@ struct thread_struct { #ifdef CONFIG_KVM_BOOK3S_32_HANDLER void* kvm_shadow_vcpu; /* KVM internal data */ #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */ +#ifdef CONFIG_PPC64 + unsigned long dscr; + int dscr_inherit; +#endif }; #define ARCH_MIN_TASKALIGN 16 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 7e4abebe76c..fdec5933305 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -99,17 +99,23 @@ #define MSR_LE __MASK(MSR_LE_LG) /* Little Endian */ #if defined(CONFIG_PPC_BOOK3S_64) +#define MSR_64BIT MSR_SF + /* Server variant */ #define MSR_ MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV -#define MSR_KERNEL MSR_ | MSR_SF +#define MSR_KERNEL MSR_ | MSR_64BIT #define MSR_USER32 MSR_ | MSR_PR | MSR_EE -#define MSR_USER64 MSR_USER32 | MSR_SF +#define MSR_USER64 MSR_USER32 | MSR_64BIT #elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx) /* Default MSR for kernel mode. */ #define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR) #define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE) #endif +#ifndef MSR_64BIT +#define MSR_64BIT 0 +#endif + /* Floating Point Status and Control Register (FPSCR) Fields */ #define FPSCR_FX 0x80000000 /* FPU exception summary */ #define FPSCR_FEX 0x40000000 /* FPU enabled exception summary */ @@ -182,6 +188,8 @@ #define SPRN_CTR 0x009 /* Count Register */ #define SPRN_DSCR 0x11 +#define SPRN_CFAR 0x1c /* Come From Address Register */ +#define SPRN_ACOP 0x1F /* Available Coprocessor Register */ #define SPRN_CTRLF 0x088 #define SPRN_CTRLT 0x098 #define CTRL_CT 0xc0000000 /* current thread */ @@ -210,8 +218,43 @@ #define SPRN_TBWL 0x11C /* Time Base Lower Register (super, R/W) */ #define SPRN_TBWU 0x11D /* Time Base Upper Register (super, R/W) */ #define SPRN_SPURR 0x134 /* Scaled PURR */ +#define SPRN_HSPRG0 0x130 /* Hypervisor Scratch 0 */ +#define SPRN_HSPRG1 0x131 /* Hypervisor Scratch 1 */ +#define SPRN_HDSISR 0x132 +#define SPRN_HDAR 0x133 +#define SPRN_HDEC 0x136 /* Hypervisor Decrementer */ #define SPRN_HIOR 0x137 /* 970 Hypervisor interrupt offset */ +#define SPRN_RMOR 0x138 /* Real mode offset register */ +#define SPRN_HRMOR 0x139 /* Real mode offset register */ +#define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */ +#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ +#define LPCR_VPM0 (1ul << (63-0)) +#define LPCR_VPM1 (1ul << (63-1)) +#define LPCR_ISL (1ul << (63-2)) +#define LPCR_DPFD_SH (63-11) +#define LPCR_VRMA_L (1ul << (63-12)) +#define LPCR_VRMA_LP0 (1ul << (63-15)) +#define LPCR_VRMA_LP1 (1ul << (63-16)) +#define LPCR_RMLS 0x1C000000 /* impl dependent rmo limit sel */ +#define LPCR_ILE 0x02000000 /* !HV irqs set MSR:LE */ +#define LPCR_PECE 0x00007000 /* powersave exit cause enable */ +#define LPCR_PECE0 0x00004000 /* ext. exceptions can cause exit */ +#define LPCR_PECE1 0x00002000 /* decrementer can cause exit */ +#define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */ +#define LPCR_MER 0x00000800 /* Mediated External Exception */ +#define LPCR_LPES0 0x00000008 /* LPAR Env selector 0 */ +#define LPCR_LPES1 0x00000004 /* LPAR Env selector 1 */ +#define LPCR_RMI 0x00000002 /* real mode is cache inhibit */ +#define LPCR_HDICE 0x00000001 /* Hyp Decr enable (HV,PR,EE) */ +#define SPRN_LPID 0x13F /* Logical Partition Identifier */ +#define SPRN_HMER 0x150 /* Hardware m? error recovery */ +#define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */ +#define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */ +#define SPRN_TLBINDEXR 0x154 /* P7 TLB control register */ +#define SPRN_TLBVPNR 0x155 /* P7 TLB control register */ +#define SPRN_TLBRPNR 0x156 /* P7 TLB control register */ +#define SPRN_TLBLPIDR 0x157 /* P7 TLB control register */ #define SPRN_DBAT0L 0x219 /* Data BAT 0 Lower Register */ #define SPRN_DBAT0U 0x218 /* Data BAT 0 Upper Register */ #define SPRN_DBAT1L 0x21B /* Data BAT 1 Lower Register */ @@ -434,16 +477,23 @@ #define SPRN_SRR0 0x01A /* Save/Restore Register 0 */ #define SPRN_SRR1 0x01B /* Save/Restore Register 1 */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ -#define SRR1_WAKERESET 0x00380000 /* System reset */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ +#define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ #define SRR1_WAKETHERM 0x00100000 /* Thermal management interrupt */ +#define SRR1_WAKERESET 0x00100000 /* System reset */ +#define SRR1_WAKESTATE 0x00030000 /* Powersave exit mask [46:47] */ +#define SRR1_WS_DEEPEST 0x00030000 /* Some resources not maintained, + * may not be recoverable */ +#define SRR1_WS_DEEPER 0x00020000 /* Some resources not maintained */ +#define SRR1_WS_DEEP 0x00010000 /* All resources maintained */ #define SRR1_PROGFPE 0x00100000 /* Floating Point Enabled */ #define SRR1_PROGPRIV 0x00040000 /* Privileged instruction */ #define SRR1_PROGTRAP 0x00020000 /* Trap */ #define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */ + #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ @@ -673,12 +723,15 @@ * SPRG usage: * * All 64-bit: - * - SPRG1 stores PACA pointer + * - SPRG1 stores PACA pointer except 64-bit server in + * HV mode in which case it is HSPRG0 * * 64-bit server: * - SPRG0 unused (reserved for HV on Power4) * - SPRG2 scratch for exception vectors * - SPRG3 unused (user visible) + * - HSPRG0 stores PACA in HV mode + * - HSPRG1 scratch for "HV" exceptions * * 64-bit embedded * - SPRG0 generic exception scratch @@ -741,6 +794,36 @@ #ifdef CONFIG_PPC_BOOK3S_64 #define SPRN_SPRG_SCRATCH0 SPRN_SPRG2 +#define SPRN_SPRG_HPACA SPRN_HSPRG0 +#define SPRN_SPRG_HSCRATCH0 SPRN_HSPRG1 + +#define GET_PACA(rX) \ + BEGIN_FTR_SECTION_NESTED(66); \ + mfspr rX,SPRN_SPRG_PACA; \ + FTR_SECTION_ELSE_NESTED(66); \ + mfspr rX,SPRN_SPRG_HPACA; \ + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + +#define SET_PACA(rX) \ + BEGIN_FTR_SECTION_NESTED(66); \ + mtspr SPRN_SPRG_PACA,rX; \ + FTR_SECTION_ELSE_NESTED(66); \ + mtspr SPRN_SPRG_HPACA,rX; \ + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + +#define GET_SCRATCH0(rX) \ + BEGIN_FTR_SECTION_NESTED(66); \ + mfspr rX,SPRN_SPRG_SCRATCH0; \ + FTR_SECTION_ELSE_NESTED(66); \ + mfspr rX,SPRN_SPRG_HSCRATCH0; \ + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + +#define SET_SCRATCH0(rX) \ + BEGIN_FTR_SECTION_NESTED(66); \ + mtspr SPRN_SPRG_SCRATCH0,rX; \ + FTR_SECTION_ELSE_NESTED(66); \ + mtspr SPRN_SPRG_HSCRATCH0,rX; \ + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) #endif #ifdef CONFIG_PPC_BOOK3E_64 @@ -750,6 +833,10 @@ #define SPRN_SPRG_TLB_EXFRAME SPRN_SPRG2 #define SPRN_SPRG_TLB_SCRATCH SPRN_SPRG6 #define SPRN_SPRG_GEN_SCRATCH SPRN_SPRG0 + +#define SET_PACA(rX) mtspr SPRN_SPRG_PACA,rX +#define GET_PACA(rX) mfspr rX,SPRN_SPRG_PACA + #endif #ifdef CONFIG_PPC_BOOK3S_32 @@ -800,6 +887,8 @@ #define SPRN_SPRG_SCRATCH1 SPRN_SPRG1 #endif + + /* * An mtfsf instruction with the L bit set. On CPUs that support this a * full 64bits of FPSCR is restored and on other CPUs the L bit is ignored. @@ -894,6 +983,8 @@ #define PV_POWER5p 0x003B #define PV_POWER7 0x003F #define PV_970FX 0x003C +#define PV_POWER6 0x003E +#define PV_POWER7 0x003F #define PV_630 0x0040 #define PV_630p 0x0041 #define PV_970MP 0x0044 diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h new file mode 100644 index 00000000000..3d52a1132f3 --- /dev/null +++ b/arch/powerpc/include/asm/reg_a2.h @@ -0,0 +1,165 @@ +/* + * Register definitions specific to the A2 core + * + * Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), 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 __ASM_POWERPC_REG_A2_H__ +#define __ASM_POWERPC_REG_A2_H__ + +#define SPRN_TENSR 0x1b5 +#define SPRN_TENS 0x1b6 /* Thread ENable Set */ +#define SPRN_TENC 0x1b7 /* Thread ENable Clear */ + +#define SPRN_A2_CCR0 0x3f0 /* Core Configuration Register 0 */ +#define SPRN_A2_CCR1 0x3f1 /* Core Configuration Register 1 */ +#define SPRN_A2_CCR2 0x3f2 /* Core Configuration Register 2 */ +#define SPRN_MMUCR0 0x3fc /* MMU Control Register 0 */ +#define SPRN_MMUCR1 0x3fd /* MMU Control Register 1 */ +#define SPRN_MMUCR2 0x3fe /* MMU Control Register 2 */ +#define SPRN_MMUCR3 0x3ff /* MMU Control Register 3 */ + +#define SPRN_IAR 0x372 + +#define SPRN_IUCR0 0x3f3 +#define IUCR0_ICBI_ACK 0x1000 + +#define SPRN_XUCR0 0x3f6 /* Execution Unit Config Register 0 */ + +#define A2_IERAT_SIZE 16 +#define A2_DERAT_SIZE 32 + +/* A2 MMUCR0 bits */ +#define MMUCR0_ECL 0x80000000 /* Extended Class for TLB fills */ +#define MMUCR0_TID_NZ 0x40000000 /* TID is non-zero */ +#define MMUCR0_TS 0x10000000 /* Translation space for TLB fills */ +#define MMUCR0_TGS 0x20000000 /* Guest space for TLB fills */ +#define MMUCR0_TLBSEL 0x0c000000 /* TLB or ERAT target for TLB fills */ +#define MMUCR0_TLBSEL_U 0x00000000 /* TLBSEL = UTLB */ +#define MMUCR0_TLBSEL_I 0x08000000 /* TLBSEL = I-ERAT */ +#define MMUCR0_TLBSEL_D 0x0c000000 /* TLBSEL = D-ERAT */ +#define MMUCR0_LOCKSRSH 0x02000000 /* Use TLB lock on tlbsx. */ +#define MMUCR0_TID_MASK 0x000000ff /* TID field */ + +/* A2 MMUCR1 bits */ +#define MMUCR1_IRRE 0x80000000 /* I-ERAT round robin enable */ +#define MMUCR1_DRRE 0x40000000 /* D-ERAT round robin enable */ +#define MMUCR1_REE 0x20000000 /* Reference Exception Enable*/ +#define MMUCR1_CEE 0x10000000 /* Change exception enable */ +#define MMUCR1_CSINV_ALL 0x00000000 /* Inval ERAT on all CS evts */ +#define MMUCR1_CSINV_NISYNC 0x04000000 /* Inval ERAT on all ex isync*/ +#define MMUCR1_CSINV_NEVER 0x0c000000 /* Don't inval ERAT on CS */ +#define MMUCR1_ICTID 0x00080000 /* IERAT class field as TID */ +#define MMUCR1_ITTID 0x00040000 /* IERAT thdid field as TID */ +#define MMUCR1_DCTID 0x00020000 /* DERAT class field as TID */ +#define MMUCR1_DTTID 0x00010000 /* DERAT thdid field as TID */ +#define MMUCR1_DCCD 0x00008000 /* DERAT class ignore */ +#define MMUCR1_TLBWE_BINV 0x00004000 /* back invalidate on tlbwe */ + +/* A2 MMUCR2 bits */ +#define MMUCR2_PSSEL_SHIFT 4 + +/* A2 MMUCR3 bits */ +#define MMUCR3_THID 0x0000000f /* Thread ID */ + +/* *** ERAT TLB bits definitions */ +#define TLB0_EPN_MASK ASM_CONST(0xfffffffffffff000) +#define TLB0_CLASS_MASK ASM_CONST(0x0000000000000c00) +#define TLB0_CLASS_00 ASM_CONST(0x0000000000000000) +#define TLB0_CLASS_01 ASM_CONST(0x0000000000000400) +#define TLB0_CLASS_10 ASM_CONST(0x0000000000000800) +#define TLB0_CLASS_11 ASM_CONST(0x0000000000000c00) +#define TLB0_V ASM_CONST(0x0000000000000200) +#define TLB0_X ASM_CONST(0x0000000000000100) +#define TLB0_SIZE_MASK ASM_CONST(0x00000000000000f0) +#define TLB0_SIZE_4K ASM_CONST(0x0000000000000010) +#define TLB0_SIZE_64K ASM_CONST(0x0000000000000030) +#define TLB0_SIZE_1M ASM_CONST(0x0000000000000050) +#define TLB0_SIZE_16M ASM_CONST(0x0000000000000070) +#define TLB0_SIZE_1G ASM_CONST(0x00000000000000a0) +#define TLB0_THDID_MASK ASM_CONST(0x000000000000000f) +#define TLB0_THDID_0 ASM_CONST(0x0000000000000001) +#define TLB0_THDID_1 ASM_CONST(0x0000000000000002) +#define TLB0_THDID_2 ASM_CONST(0x0000000000000004) +#define TLB0_THDID_3 ASM_CONST(0x0000000000000008) +#define TLB0_THDID_ALL ASM_CONST(0x000000000000000f) + +#define TLB1_RESVATTR ASM_CONST(0x00f0000000000000) +#define TLB1_U0 ASM_CONST(0x0008000000000000) +#define TLB1_U1 ASM_CONST(0x0004000000000000) +#define TLB1_U2 ASM_CONST(0x0002000000000000) +#define TLB1_U3 ASM_CONST(0x0001000000000000) +#define TLB1_R ASM_CONST(0x0000800000000000) +#define TLB1_C ASM_CONST(0x0000400000000000) +#define TLB1_RPN_MASK ASM_CONST(0x000003fffffff000) +#define TLB1_W ASM_CONST(0x0000000000000800) +#define TLB1_I ASM_CONST(0x0000000000000400) +#define TLB1_M ASM_CONST(0x0000000000000200) +#define TLB1_G ASM_CONST(0x0000000000000100) +#define TLB1_E ASM_CONST(0x0000000000000080) +#define TLB1_VF ASM_CONST(0x0000000000000040) +#define TLB1_UX ASM_CONST(0x0000000000000020) +#define TLB1_SX ASM_CONST(0x0000000000000010) +#define TLB1_UW ASM_CONST(0x0000000000000008) +#define TLB1_SW ASM_CONST(0x0000000000000004) +#define TLB1_UR ASM_CONST(0x0000000000000002) +#define TLB1_SR ASM_CONST(0x0000000000000001) + +#ifdef CONFIG_PPC_EARLY_DEBUG_WSP +#define WSP_UART_PHYS 0xffc000c000 +/* This needs to be careful chosen to hit a !0 congruence class + * in the TLB since we bolt it in way 3, which is already occupied + * by our linear mapping primary bolted entry in CC 0. + */ +#define WSP_UART_VIRT 0xf000000000001000 +#endif + +/* A2 erativax attributes definitions */ +#define ERATIVAX_RS_IS_ALL 0x000 +#define ERATIVAX_RS_IS_TID 0x040 +#define ERATIVAX_RS_IS_CLASS 0x080 +#define ERATIVAX_RS_IS_FULLMATCH 0x0c0 +#define ERATIVAX_CLASS_00 0x000 +#define ERATIVAX_CLASS_01 0x010 +#define ERATIVAX_CLASS_10 0x020 +#define ERATIVAX_CLASS_11 0x030 +#define ERATIVAX_PSIZE_4K (TLB_PSIZE_4K >> 1) +#define ERATIVAX_PSIZE_64K (TLB_PSIZE_64K >> 1) +#define ERATIVAX_PSIZE_1M (TLB_PSIZE_1M >> 1) +#define ERATIVAX_PSIZE_16M (TLB_PSIZE_16M >> 1) +#define ERATIVAX_PSIZE_1G (TLB_PSIZE_1G >> 1) + +/* A2 eratilx attributes definitions */ +#define ERATILX_T_ALL 0 +#define ERATILX_T_TID 1 +#define ERATILX_T_TGS 2 +#define ERATILX_T_FULLMATCH 3 +#define ERATILX_T_CLASS0 4 +#define ERATILX_T_CLASS1 5 +#define ERATILX_T_CLASS2 6 +#define ERATILX_T_CLASS3 7 + +/* XUCR0 bits */ +#define XUCR0_TRACE_UM_T0 0x40000000 /* Thread 0 */ +#define XUCR0_TRACE_UM_T1 0x20000000 /* Thread 1 */ +#define XUCR0_TRACE_UM_T2 0x10000000 /* Thread 2 */ +#define XUCR0_TRACE_UM_T3 0x08000000 /* Thread 3 */ + +/* A2 CCR0 register */ +#define A2_CCR0_PME_DISABLED 0x00000000 +#define A2_CCR0_PME_SLEEP 0x40000000 +#define A2_CCR0_PME_RVW 0x80000000 +#define A2_CCR0_PME_DISABLED2 0xc0000000 + +/* A2 CCR2 register */ +#define A2_CCR2_ERAT_ONLY_MODE 0x00000001 +#define A2_CCR2_ENABLE_ICSWX 0x00000002 +#define A2_CCR2_ENABLE_PC 0x20000000 +#define A2_CCR2_ENABLE_TRACE 0x40000000 + +#endif /* __ASM_POWERPC_REG_A2_H__ */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index b316794aa2b..817bd1ac175 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -27,10 +27,12 @@ #define MSR_CM (1<<31) /* Computation Mode (0=32-bit, 1=64-bit) */ #if defined(CONFIG_PPC_BOOK3E_64) +#define MSR_64BIT MSR_CM + #define MSR_ MSR_ME | MSR_CE -#define MSR_KERNEL MSR_ | MSR_CM +#define MSR_KERNEL MSR_ | MSR_64BIT #define MSR_USER32 MSR_ | MSR_PR | MSR_EE | MSR_DE -#define MSR_USER64 MSR_USER32 | MSR_CM | MSR_DE +#define MSR_USER64 MSR_USER32 | MSR_64BIT #elif defined (CONFIG_40x) #define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE) #define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 9a1193e30f2..58625d1e780 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -158,7 +158,50 @@ struct rtas_error_log { unsigned long target:4; /* Target of failed operation */ unsigned long type:8; /* General event or error*/ unsigned long extended_log_length:32; /* length in bytes */ - unsigned char buffer[1]; + unsigned char buffer[1]; /* Start of extended log */ + /* Variable length. */ +}; + +#define RTAS_V6EXT_LOG_FORMAT_EVENT_LOG 14 + +#define RTAS_V6EXT_COMPANY_ID_IBM (('I' << 24) | ('B' << 16) | ('M' << 8)) + +/* RTAS general extended event log, Version 6. The extended log starts + * from "buffer" field of struct rtas_error_log defined above. + */ +struct rtas_ext_event_log_v6 { + /* Byte 0 */ + uint32_t log_valid:1; /* 1:Log valid */ + uint32_t unrecoverable_error:1; /* 1:Unrecoverable error */ + uint32_t recoverable_error:1; /* 1:recoverable (correctable */ + /* or successfully retried) */ + uint32_t degraded_operation:1; /* 1:Unrecoverable err, bypassed*/ + /* - degraded operation (e.g. */ + /* CPU or mem taken off-line) */ + uint32_t predictive_error:1; + uint32_t new_log:1; /* 1:"New" log (Always 1 for */ + /* data returned from RTAS */ + uint32_t big_endian:1; /* 1: Big endian */ + uint32_t :1; /* reserved */ + /* Byte 1 */ + uint32_t :8; /* reserved */ + /* Byte 2 */ + uint32_t powerpc_format:1; /* Set to 1 (indicating log is */ + /* in PowerPC format */ + uint32_t :3; /* reserved */ + uint32_t log_format:4; /* Log format indicator. Define */ + /* format used for byte 12-2047 */ + /* Byte 3 */ + uint32_t :8; /* reserved */ + /* Byte 4-11 */ + uint8_t reserved[8]; /* reserved */ + /* Byte 12-15 */ + uint32_t company_id; /* Company ID of the company */ + /* that defines the format for */ + /* the vendor specific log type */ + /* Byte 16-end of log */ + uint8_t vendor_log[1]; /* Start of vendor specific log */ + /* Variable length. */ }; /* diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h new file mode 100644 index 00000000000..0cabfd7bc2d --- /dev/null +++ b/arch/powerpc/include/asm/scom.h @@ -0,0 +1,156 @@ +/* + * Copyright 2010 Benjamin Herrenschmidt, IBM Corp + * <benh@kernel.crashing.org> + * and David Gibson, IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_POWERPC_SCOM_H +#define _ASM_POWERPC_SCOM_H + +#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ +#ifdef CONFIG_PPC_SCOM + +/* + * The SCOM bus is a sideband bus used for accessing various internal + * registers of the processor or the chipset. The implementation details + * differ between processors and platforms, and the access method as + * well. + * + * This API allows to "map" ranges of SCOM register numbers associated + * with a given SCOM controller. The later must be represented by a + * device node, though some implementations might support NULL if there + * is no possible ambiguity + * + * Then, scom_read/scom_write can be used to accesses registers inside + * that range. The argument passed is a register number relative to + * the beginning of the range mapped. + */ + +typedef void *scom_map_t; + +/* Value for an invalid SCOM map */ +#define SCOM_MAP_INVALID (NULL) + +/* The scom_controller data structure is what the platform passes + * to the core code in scom_init, it provides the actual implementation + * of all the SCOM functions + */ +struct scom_controller { + scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count); + void (*unmap)(scom_map_t map); + + u64 (*read)(scom_map_t map, u32 reg); + void (*write)(scom_map_t map, u32 reg, u64 value); +}; + +extern const struct scom_controller *scom_controller; + +/** + * scom_init - Initialize the SCOM backend, called by the platform + * @controller: The platform SCOM controller + */ +static inline void scom_init(const struct scom_controller *controller) +{ + scom_controller = controller; +} + +/** + * scom_map_ok - Test is a SCOM mapping is successful + * @map: The result of scom_map to test + */ +static inline int scom_map_ok(scom_map_t map) +{ + return map != SCOM_MAP_INVALID; +} + +/** + * scom_map - Map a block of SCOM registers + * @ctrl_dev: Device node of the SCOM controller + * some implementations allow NULL here + * @reg: first SCOM register to map + * @count: Number of SCOM registers to map + */ + +static inline scom_map_t scom_map(struct device_node *ctrl_dev, + u64 reg, u64 count) +{ + return scom_controller->map(ctrl_dev, reg, count); +} + +/** + * scom_find_parent - Find the SCOM controller for a device + * @dev: OF node of the device + * + * This is not meant for general usage, but in combination with + * scom_map() allows to map registers not represented by the + * device own scom-reg property. Useful for applying HW workarounds + * on things not properly represented in the device-tree for example. + */ +struct device_node *scom_find_parent(struct device_node *dev); + + +/** + * scom_map_device - Map a device's block of SCOM registers + * @dev: OF node of the device + * @index: Register bank index (index in "scom-reg" property) + * + * This function will use the device-tree binding for SCOM which + * is to follow "scom-parent" properties until it finds a node with + * a "scom-controller" property to find the controller. It will then + * use the "scom-reg" property which is made of reg/count pairs, + * each of them having a size defined by the controller's #scom-cells + * property + */ +extern scom_map_t scom_map_device(struct device_node *dev, int index); + + +/** + * scom_unmap - Unmap a block of SCOM registers + * @map: Result of scom_map is to be unmapped + */ +static inline void scom_unmap(scom_map_t map) +{ + if (scom_map_ok(map)) + scom_controller->unmap(map); +} + +/** + * scom_read - Read a SCOM register + * @map: Result of scom_map + * @reg: Register index within that map + */ +static inline u64 scom_read(scom_map_t map, u32 reg) +{ + return scom_controller->read(map, reg); +} + +/** + * scom_write - Write to a SCOM register + * @map: Result of scom_map + * @reg: Register index within that map + * @value: Value to write + */ +static inline void scom_write(scom_map_t map, u32 reg, u64 value) +{ + scom_controller->write(map, reg, value); +} + +#endif /* CONFIG_PPC_SCOM */ +#endif /* __ASSEMBLY__ */ +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_SCOM_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index a902a0d3ae0..880b8c1e6e5 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -20,6 +20,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/kernel.h> +#include <linux/irqreturn.h> #ifndef __ASSEMBLY__ @@ -29,14 +30,32 @@ #include <asm/percpu.h> extern int boot_cpuid; +extern int boot_cpu_count; extern void cpu_die(void); #ifdef CONFIG_SMP -extern void smp_send_debugger_break(int cpu); -extern void smp_message_recv(int); +struct smp_ops_t { + void (*message_pass)(int cpu, int msg); +#ifdef CONFIG_PPC_SMP_MUXED_IPI + void (*cause_ipi)(int cpu, unsigned long data); +#endif + int (*probe)(void); + int (*kick_cpu)(int nr); + void (*setup_cpu)(int nr); + void (*bringup_done)(void); + void (*take_timebase)(void); + void (*give_timebase)(void); + int (*cpu_disable)(void); + void (*cpu_die)(unsigned int nr); + int (*cpu_bootable)(unsigned int nr); +}; + +extern void smp_send_debugger_break(void); extern void start_secondary_resume(void); +extern void __devinit smp_generic_give_timebase(void); +extern void __devinit smp_generic_take_timebase(void); DECLARE_PER_CPU(unsigned int, cpu_pvr); @@ -93,13 +112,16 @@ extern int cpu_to_core_id(int cpu); #define PPC_MSG_CALL_FUNC_SINGLE 2 #define PPC_MSG_DEBUGGER_BREAK 3 -/* - * irq controllers that have dedicated ipis per message and don't - * need additional code in the action handler may use this - */ +/* for irq controllers that have dedicated ipis per message (4) */ extern int smp_request_message_ipi(int virq, int message); extern const char *smp_ipi_name[]; +/* for irq controllers with only a single ipi */ +extern void smp_muxed_ipi_set_data(int cpu, unsigned long data); +extern void smp_muxed_ipi_message_pass(int cpu, int msg); +extern void smp_muxed_ipi_resend(void); +extern irqreturn_t smp_ipi_demux(void); + void smp_init_iSeries(void); void smp_init_pSeries(void); void smp_init_cell(void); @@ -149,7 +171,7 @@ extern int smt_enabled_at_boot; extern int smp_mpic_probe(void); extern void smp_mpic_setup_cpu(int cpu); -extern void smp_generic_kick_cpu(int nr); +extern int smp_generic_kick_cpu(int nr); extern void smp_generic_give_timebase(void); extern void smp_generic_take_timebase(void); @@ -169,6 +191,8 @@ extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; +extern irqreturn_t debug_ipi_action(int irq, void *data); + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h index 5e474ddd227..2dc595dda03 100644 --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -219,8 +219,6 @@ extern int mem_init_done; /* set on boot once kmalloc can be called */ extern int init_bootmem_done; /* set once bootmem is available */ extern phys_addr_t memory_limit; extern unsigned long klimit; - -extern void *alloc_maybe_bootmem(size_t size, gfp_t mask); extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); extern int powersave_nap; /* set if nap mode can be used in idle loop */ diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index d50a380b2b6..81143fcbd11 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -79,6 +79,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) #elif defined(CONFIG_PPC_STD_MMU_64) +#define MMU_NO_CONTEXT 0 + /* * TLB flushing for 64-bit hash-MMU CPUs */ diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h index 11ae699135b..58580e94a2b 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -52,6 +52,7 @@ extern void __init udbg_init_44x_as1(void); extern void __init udbg_init_40x_realmode(void); extern void __init udbg_init_cpm(void); extern void __init udbg_init_usbgecko(void); +extern void __init udbg_init_wsp(void); #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_UDBG_H */ diff --git a/arch/powerpc/include/asm/wsp.h b/arch/powerpc/include/asm/wsp.h new file mode 100644 index 00000000000..c7dc83088a3 --- /dev/null +++ b/arch/powerpc/include/asm/wsp.h @@ -0,0 +1,14 @@ +/* + * Copyright 2011 Michael Ellerman, 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 __ASM_POWERPC_WSP_H +#define __ASM_POWERPC_WSP_H + +extern int wsp_get_chip_id(struct device_node *dn); + +#endif /* __ASM_POWERPC_WSP_H */ diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h new file mode 100644 index 00000000000..b183a406201 --- /dev/null +++ b/arch/powerpc/include/asm/xics.h @@ -0,0 +1,142 @@ +/* + * Common definitions accross all variants of ICP and ICS interrupt + * controllers. + */ + +#ifndef _XICS_H +#define _XICS_H + +#include <linux/interrupt.h> + +#define XICS_IPI 2 +#define XICS_IRQ_SPURIOUS 0 + +/* Want a priority other than 0. Various HW issues require this. */ +#define DEFAULT_PRIORITY 5 + +/* + * Mark IPIs as higher priority so we can take them inside interrupts that + * arent marked IRQF_DISABLED + */ +#define IPI_PRIORITY 4 + +/* The least favored priority */ +#define LOWEST_PRIORITY 0xFF + +/* The number of priorities defined above */ +#define MAX_NUM_PRIORITIES 3 + +/* Native ICP */ +extern int icp_native_init(void); + +/* PAPR ICP */ +extern int icp_hv_init(void); + +/* ICP ops */ +struct icp_ops { + unsigned int (*get_irq)(void); + void (*eoi)(struct irq_data *d); + void (*set_priority)(unsigned char prio); + void (*teardown_cpu)(void); + void (*flush_ipi)(void); +#ifdef CONFIG_SMP + void (*cause_ipi)(int cpu, unsigned long data); + irq_handler_t ipi_action; +#endif +}; + +extern const struct icp_ops *icp_ops; + +/* Native ICS */ +extern int ics_native_init(void); + +/* RTAS ICS */ +extern int ics_rtas_init(void); + +/* ICS instance, hooked up to chip_data of an irq */ +struct ics { + struct list_head link; + int (*map)(struct ics *ics, unsigned int virq); + void (*mask_unknown)(struct ics *ics, unsigned long vec); + long (*get_server)(struct ics *ics, unsigned long vec); + int (*host_match)(struct ics *ics, struct device_node *node); + char data[]; +}; + +/* Commons */ +extern unsigned int xics_default_server; +extern unsigned int xics_default_distrib_server; +extern unsigned int xics_interrupt_server_size; +extern struct irq_host *xics_host; + +struct xics_cppr { + unsigned char stack[MAX_NUM_PRIORITIES]; + int index; +}; + +DECLARE_PER_CPU(struct xics_cppr, xics_cppr); + +static inline void xics_push_cppr(unsigned int vec) +{ + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + + if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1)) + return; + + if (vec == XICS_IPI) + os_cppr->stack[++os_cppr->index] = IPI_PRIORITY; + else + os_cppr->stack[++os_cppr->index] = DEFAULT_PRIORITY; +} + +static inline unsigned char xics_pop_cppr(void) +{ + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + + if (WARN_ON(os_cppr->index < 1)) + return LOWEST_PRIORITY; + + return os_cppr->stack[--os_cppr->index]; +} + +static inline void xics_set_base_cppr(unsigned char cppr) +{ + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + + /* we only really want to set the priority when there's + * just one cppr value on the stack + */ + WARN_ON(os_cppr->index != 0); + + os_cppr->stack[0] = cppr; +} + +static inline unsigned char xics_cppr_top(void) +{ + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + + return os_cppr->stack[os_cppr->index]; +} + +DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message); + +extern void xics_init(void); +extern void xics_setup_cpu(void); +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_register_ics(struct ics *ics); +extern void xics_teardown_cpu(void); +extern void xics_kexec_teardown_cpu(int secondary); +extern void xics_migrate_irqs_away(void); +#ifdef CONFIG_SMP +extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, + unsigned int strict_check); +#else +#define xics_get_irq_server(virq, cpumask, strict_check) (xics_default_server) +#endif + + +#endif /* _XICS_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 3bb2a3e6a33..9aab3631257 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,11 +38,14 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ paca.o nvram_64.o firmware.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power7.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o obj-$(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 obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-y := proc_powerpc.o @@ -75,7 +78,6 @@ obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o extra-y := head_$(CONFIG_WORD_SIZE).o -extra-$(CONFIG_PPC_BOOK3E_32) := head_new_booke.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o @@ -103,6 +105,8 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o + obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 23e6a93145a..6887661ac07 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -74,6 +74,7 @@ int main(void) DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); DEFINE(SIGSEGV, SIGSEGV); DEFINE(NMI_MASK, NMI_MASK); + DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S new file mode 100644 index 00000000000..7f818feaa7a --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_a2.S @@ -0,0 +1,114 @@ +/* + * A2 specific assembly support code + * + * Copyright 2009 Ben Herrenschmidt, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/asm-offsets.h> +#include <asm/ppc_asm.h> +#include <asm/ppc-opcode.h> +#include <asm/processor.h> +#include <asm/reg_a2.h> +#include <asm/reg.h> +#include <asm/thread_info.h> + +/* + * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity. + * This also prevents external LPID accesses but that isn't a problem when not a + * guest. Under PV, this setting will be ignored and MMUCR will return the right + * number of PID bits we can use. + */ +#define MMUCR1_EXTEND_PID \ + (MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \ + MMUCR1_DTTID | MMUCR1_DCCD) + +/* + * Use extended PIDs if enabled. + * Don't clear the ERATs on context sync events and enable I & D LRU. + * Enable ERAT back invalidate when tlbwe overwrites an entry. + */ +#define INITIAL_MMUCR1 \ + (MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \ + MMUCR1_DRRE | MMUCR1_TLBWE_BINV) + +_GLOBAL(__setup_cpu_a2) + /* Some of these are actually thread local and some are + * core local but doing it always won't hurt + */ + +#ifdef CONFIG_PPC_WSP_COPRO + /* Make sure ACOP starts out as zero */ + li r3,0 + mtspr SPRN_ACOP,r3 + + /* Enable icswx instruction */ + mfspr r3,SPRN_A2_CCR2 + ori r3,r3,A2_CCR2_ENABLE_ICSWX + mtspr SPRN_A2_CCR2,r3 + + /* Unmask all CTs in HACOP */ + li r3,-1 + mtspr SPRN_HACOP,r3 +#endif /* CONFIG_PPC_WSP_COPRO */ + + /* Enable doorbell */ + mfspr r3,SPRN_A2_CCR2 + oris r3,r3,A2_CCR2_ENABLE_PC@h + mtspr SPRN_A2_CCR2,r3 + isync + + /* Setup CCR0 to disable power saving for now as it's busted + * in the current implementations. Setup CCR1 to wake on + * interrupts normally (we write the default value but who + * knows what FW may have clobbered...) + */ + li r3,0 + mtspr SPRN_A2_CCR0, r3 + LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f) + mtspr SPRN_A2_CCR1, r3 + + /* Initialise MMUCR1 */ + lis r3,INITIAL_MMUCR1@h + ori r3,r3,INITIAL_MMUCR1@l + mtspr SPRN_MMUCR1,r3 + + /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ + LOAD_REG_IMMEDIATE(r3, 0x000a7531) + mtspr SPRN_MMUCR2,r3 + + /* Set MMUCR3 to write all thids bit to the TLB */ + LOAD_REG_IMMEDIATE(r3, 0x0000000f) + mtspr SPRN_MMUCR3,r3 + + /* Don't do ERAT stuff if running guest mode */ + mfmsr r3 + andis. r0,r3,MSR_GS@h + bne 1f + + /* Now set the I-ERAT watermark to 15 */ + lis r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h + mtspr SPRN_MMUCR0, r4 + li r4,A2_IERAT_SIZE-1 + PPC_ERATWE(r4,r4,3) + + /* Now set the D-ERAT watermark to 31 */ + lis r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h + mtspr SPRN_MMUCR0, r4 + li r4,A2_DERAT_SIZE-1 + PPC_ERATWE(r4,r4,3) + + /* And invalidate the beast just in case. That won't get rid of + * a bolted entry though it will be in LRU and so will go away eventually + * but let's not bother for now + */ + PPC_ERATILX(0,0,0) +1: + blr + +_GLOBAL(__restore_cpu_a2) + b __setup_cpu_a2 diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S new file mode 100644 index 00000000000..4f9a93fcfe0 --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_power7.S @@ -0,0 +1,91 @@ +/* + * This file contains low level CPU setup functions. + * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/cache.h> + +/* Entry: r3 = crap, r4 = ptr to cputable entry + * + * Note that we can be called twice for pseudo-PVRs + */ +_GLOBAL(__setup_cpu_power7) + mflr r11 + bl __init_hvmode_206 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + bl __init_LPCR + bl __init_TLB + mtlr r11 + blr + +_GLOBAL(__restore_cpu_power7) + mflr r11 + mfmsr r3 + rldicl. r0,r3,4,63 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + bl __init_LPCR + bl __init_TLB + mtlr r11 + blr + +__init_hvmode_206: + /* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */ + mfmsr r3 + rldicl. r0,r3,4,63 + bnelr + ld r5,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206) + xor r5,r5,r6 + std r5,CPU_SPEC_FEATURES(r4) + blr + +__init_LPCR: + /* Setup a sane LPCR: + * + * LPES = 0b01 (HSRR0/1 used for 0x500) + * PECE = 0b111 + * DPFD = 4 + * + * Other bits untouched for now + */ + mfspr r3,SPRN_LPCR + ori r3,r3,(LPCR_LPES0|LPCR_LPES1) + xori r3,r3, LPCR_LPES0 + ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2) + li r5,7 + sldi r5,r5,LPCR_DPFD_SH + andc r3,r3,r5 + li r5,4 + sldi r5,r5,LPCR_DPFD_SH + or r3,r3,r5 + mtspr SPRN_LPCR,r3 + isync + blr + +__init_TLB: + /* Clear the TLB */ + li r6,128 + mtctr r6 + li r7,0xc00 /* IS field = 0b11 */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b9602ee06de..34d2722b945 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -62,10 +62,12 @@ extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_a2(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_pa6t(void); extern void __restore_cpu_ppc970(void); extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power7(void); +extern void __restore_cpu_a2(void); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -199,7 +201,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (gp)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -214,7 +216,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4+ (gq)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -230,7 +232,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -248,7 +250,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -284,7 +286,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -302,7 +304,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -318,7 +320,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5 (gr)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -338,7 +340,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -354,7 +356,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -371,7 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_cpu_type = "ppc64/ibm-compat-v1", @@ -385,7 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -404,7 +406,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER6 (architected)", .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_cpu_type = "ppc64/ibm-compat-v1", @@ -417,12 +419,13 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (architected)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_type = PPC_OPROFILE_POWER4, .oprofile_cpu_type = "ppc64/ibm-compat-v1", + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7", }, { /* Power7 */ @@ -431,14 +434,15 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7", }, { /* Power7+ */ @@ -447,14 +451,15 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7+ (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7+", }, { /* Cell Broadband Engine */ @@ -465,7 +470,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_CELL, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 4, @@ -480,7 +485,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "PA6T", .cpu_features = CPU_FTRS_PA6T, .cpu_user_features = COMMON_USER_PA6T, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PA6T, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, @@ -497,7 +502,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (compatible)", .cpu_features = CPU_FTRS_COMPATIBLE, .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_DEFAULT_HPTE_ARCH_V2, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -2005,7 +2010,22 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC32 */ #endif /* CONFIG_E500 */ -#ifdef CONFIG_PPC_BOOK3E_64 +#ifdef CONFIG_PPC_A2 + { /* Standard A2 (>= DD2) + FPU core */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00480000, + .cpu_name = "A2 (>= DD2)", + .cpu_features = CPU_FTRS_A2, + .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTRS_A2, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 0, + .cpu_setup = __setup_cpu_a2, + .cpu_restore = __restore_cpu_a2, + .machine_check = machine_check_generic, + .platform = "ppca2", + }, { /* This is a default entry to get going, to be replaced by * a real one at some stage */ @@ -2026,7 +2046,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "power6", }, -#endif +#endif /* CONFIG_PPC_A2 */ }; static struct cpu_spec the_cpu_spec; diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 5eb0ee37f6c..4e6ee944495 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -64,9 +64,9 @@ void crash_ipi_callback(struct pt_regs *regs) return; hard_irq_disable(); - if (!cpu_isset(cpu, cpus_in_crash)) + if (!cpumask_test_cpu(cpu, &cpus_in_crash)) crash_save_cpu(regs, cpu); - cpu_set(cpu, cpus_in_crash); + cpumask_set_cpu(cpu, &cpus_in_crash); /* * Entered via soft-reset - could be the kdump @@ -77,8 +77,8 @@ void crash_ipi_callback(struct pt_regs *regs) * Tell the kexec CPU that entered via soft-reset and ready * to go down. */ - if (cpu_isset(cpu, cpus_in_sr)) { - cpu_clear(cpu, cpus_in_sr); + if (cpumask_test_cpu(cpu, &cpus_in_sr)) { + cpumask_clear_cpu(cpu, &cpus_in_sr); atomic_inc(&enter_on_soft_reset); } @@ -87,7 +87,7 @@ void crash_ipi_callback(struct pt_regs *regs) * This barrier is needed to make sure that all CPUs are stopped. * If not, soft-reset will be invoked to bring other CPUs. */ - while (!cpu_isset(crashing_cpu, cpus_in_crash)) + while (!cpumask_test_cpu(crashing_cpu, &cpus_in_crash)) cpu_relax(); if (ppc_md.kexec_cpu_down) @@ -109,7 +109,7 @@ static void crash_soft_reset_check(int cpu) { unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ - cpu_clear(cpu, cpus_in_sr); + cpumask_clear_cpu(cpu, &cpus_in_sr); while (atomic_read(&enter_on_soft_reset) != ncpus) cpu_relax(); } @@ -132,7 +132,7 @@ static void crash_kexec_prepare_cpus(int cpu) */ printk(KERN_EMERG "Sending IPI to other cpus...\n"); msecs = 10000; - while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) { + while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) { cpu_relax(); mdelay(1); } @@ -144,20 +144,20 @@ static void crash_kexec_prepare_cpus(int cpu) * user to do soft reset such that we get all. * Soft-reset will be used until better mechanism is implemented. */ - if (cpus_weight(cpus_in_crash) < ncpus) { + if (cpumask_weight(&cpus_in_crash) < ncpus) { printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n", - ncpus - cpus_weight(cpus_in_crash)); + ncpus - cpumask_weight(&cpus_in_crash)); printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n"); - cpus_in_sr = CPU_MASK_NONE; + cpumask_clear(&cpus_in_sr); atomic_set(&enter_on_soft_reset, 0); - while (cpus_weight(cpus_in_crash) < ncpus) + while (cpumask_weight(&cpus_in_crash) < ncpus) cpu_relax(); } /* * Make sure all CPUs are entered via soft-reset if the kdump is * invoked using soft-reset. */ - if (cpu_isset(cpu, cpus_in_sr)) + if (cpumask_test_cpu(cpu, &cpus_in_sr)) crash_soft_reset_check(cpu); /* Leave the IPI callback set */ } @@ -182,7 +182,7 @@ void crash_kexec_secondary(struct pt_regs *regs) * exited using 'x'(exit and recover) or * kexec_should_crash() failed for all running tasks. */ - cpu_clear(cpu, cpus_in_sr); + cpumask_clear_cpu(cpu, &cpus_in_sr); local_irq_restore(flags); return; } @@ -196,7 +196,7 @@ void crash_kexec_secondary(struct pt_regs *regs) * then start kexec boot. */ crash_soft_reset_check(cpu); - cpu_set(crashing_cpu, cpus_in_crash); + cpumask_set_cpu(crashing_cpu, &cpus_in_crash); if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); machine_kexec(kexec_crash_image); @@ -224,7 +224,7 @@ static void crash_kexec_prepare_cpus(int cpu) void crash_kexec_secondary(struct pt_regs *regs) { - cpus_in_sr = CPU_MASK_NONE; + cpumask_clear(&cpus_in_sr); } #endif /* CONFIG_SMP */ @@ -236,7 +236,7 @@ static void crash_kexec_wait_realmode(int cpu) int i; msecs = 10000; - for (i=0; i < NR_CPUS && msecs > 0; i++) { + for (i=0; i < nr_cpu_ids && msecs > 0; i++) { if (i == cpu) continue; @@ -346,7 +346,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crashing_cpu = smp_processor_id(); crash_save_cpu(regs, crashing_cpu); crash_kexec_prepare_cpus(crashing_cpu); - cpu_set(crashing_cpu, cpus_in_crash); + cpumask_set_cpu(crashing_cpu, &cpus_in_crash); crash_kexec_wait_realmode(crashing_cpu); machine_kexec_mask_interrupts(); diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 3307a52d797..2cc451aaaca 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -13,84 +13,35 @@ #include <linux/kernel.h> #include <linux/smp.h> #include <linux/threads.h> -#include <linux/percpu.h> +#include <linux/hardirq.h> #include <asm/dbell.h> #include <asm/irq_regs.h> #ifdef CONFIG_SMP -struct doorbell_cpu_info { - unsigned long messages; /* current messages bits */ - unsigned int tag; /* tag value */ -}; - -static DEFINE_PER_CPU(struct doorbell_cpu_info, doorbell_cpu_info); - void doorbell_setup_this_cpu(void) { - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); + unsigned long tag = mfspr(SPRN_PIR) & 0x3fff; - info->messages = 0; - info->tag = mfspr(SPRN_PIR) & 0x3fff; + smp_muxed_ipi_set_data(smp_processor_id(), tag); } -void doorbell_message_pass(int target, int msg) +void doorbell_cause_ipi(int cpu, unsigned long data) { - struct doorbell_cpu_info *info; - int i; - - if (target < NR_CPUS) { - info = &per_cpu(doorbell_cpu_info, target); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - else if (target == MSG_ALL_BUT_SELF) { - for_each_online_cpu(i) { - if (i == smp_processor_id()) - continue; - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - } - else { /* target == MSG_ALL */ - for_each_online_cpu(i) { - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - } - ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0); - } + ppc_msgsnd(PPC_DBELL, 0, data); } void doorbell_exception(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - int msg; - /* Warning: regs can be NULL when called from irq enable */ + irq_enter(); - if (!info->messages || (num_online_cpus() < 2)) - goto out; + smp_ipi_demux(); - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &info->messages)) - smp_message_recv(msg); - -out: + irq_exit(); set_irq_regs(old_regs); } - -void doorbell_check_self(void) -{ - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - - if (!info->messages) - return; - - ppc_msgsnd(PPC_DBELL, 0, info->tag); -} - #else /* CONFIG_SMP */ void doorbell_exception(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d82878c4daa..d834425186a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -421,6 +421,12 @@ BEGIN_FTR_SECTION std r24,THREAD_VRSAVE(r3) END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_PPC64 +BEGIN_FTR_SECTION + mfspr r25,SPRN_DSCR + std r25,THREAD_DSCR(r3) +END_FTR_SECTION_IFSET(CPU_FTR_DSCR) +#endif and. r0,r0,r22 beq+ 1f andc r22,r22,r0 @@ -462,10 +468,10 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE_NESTED(95) clrrdi r6,r8,40 /* get its 1T ESID */ clrrdi r9,r1,40 /* get current sp 1T ESID */ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_1T_SEGMENT, 95) + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_1T_SEGMENT, 95) FTR_SECTION_ELSE b 2f -ALT_FTR_SECTION_END_IFSET(CPU_FTR_SLB) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_SLB) clrldi. r0,r6,2 /* is new ESID c00000000? */ cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */ cror eq,4*cr1+eq,eq @@ -479,7 +485,7 @@ BEGIN_FTR_SECTION li r9,MMU_SEGSIZE_1T /* insert B field */ oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0 -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* Update the last bolted SLB. No write barriers are needed * here, provided we only update the current CPU's SLB shadow @@ -491,7 +497,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */ std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */ - /* No need to check for CPU_FTR_NO_SLBIE_B here, since when + /* No need to check for MMU_FTR_NO_SLBIE_B here, since when * we have 1TB segments, the only CPUs known to have the errata * only support less than 1TB of system memory and we'll never * actually hit this code path. @@ -522,6 +528,15 @@ BEGIN_FTR_SECTION mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_PPC64 +BEGIN_FTR_SECTION + ld r0,THREAD_DSCR(r4) + cmpd r0,r25 + beq 1f + mtspr SPRN_DSCR,r0 +1: +END_FTR_SECTION_IFSET(CPU_FTR_DSCR) +#endif /* r3-r13 are destroyed -- Cort */ REST_8GPRS(14, r1) @@ -838,7 +853,7 @@ _GLOBAL(enter_rtas) _STATIC(rtas_return_loc) /* relocation is off at this point */ - mfspr r4,SPRN_SPRG_PACA /* Get PACA */ + GET_PACA(r4) clrldi r4,r4,2 /* convert to realmode address */ bcl 20,31,$+4 @@ -869,7 +884,7 @@ _STATIC(rtas_restore_regs) REST_8GPRS(14, r1) /* Restore the non-volatiles */ REST_10GPRS(22, r1) /* ditto */ - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) ld r4,_CCR(r1) mtcr r4 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 9651acc3504..4d0abb4930a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -17,6 +17,7 @@ #include <asm/cputable.h> #include <asm/setup.h> #include <asm/thread_info.h> +#include <asm/reg_a2.h> #include <asm/exception-64e.h> #include <asm/bug.h> #include <asm/irqflags.h> @@ -864,8 +865,23 @@ have_hes: * that will have to be made dependent on whether we are running under * a hypervisor I suppose. */ - ori r3,r3,MAS0_HES | MAS0_WQ_ALLWAYS - mtspr SPRN_MAS0,r3 + + /* BEWARE, MAGIC + * This code is called as an ordinary function on the boot CPU. But to + * avoid duplication, this code is also used in SCOM bringup of + * secondary CPUs. We read the code between the initial_tlb_code_start + * and initial_tlb_code_end labels one instruction at a time and RAM it + * into the new core via SCOM. That doesn't process branches, so there + * must be none between those two labels. It also means if this code + * ever takes any parameters, the SCOM code must also be updated to + * provide them. + */ + .globl a2_tlbinit_code_start +a2_tlbinit_code_start: + + ori r11,r3,MAS0_WQ_ALLWAYS + oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */ + mtspr SPRN_MAS0,r11 lis r3,(MAS1_VALID | MAS1_IPROT)@h ori r3,r3,BOOK3E_PAGESZ_1GB << MAS1_TSIZE_SHIFT mtspr SPRN_MAS1,r3 @@ -879,18 +895,86 @@ have_hes: /* Write the TLB entry */ tlbwe + .globl a2_tlbinit_after_linear_map +a2_tlbinit_after_linear_map: + /* Now we branch the new virtual address mapped by this entry */ LOAD_REG_IMMEDIATE(r3,1f) mtctr r3 bctr 1: /* We are now running at PAGE_OFFSET, clean the TLB of everything - * else (XXX we should scan for bolted crap from the firmware too) + * else (including IPROTed things left by firmware) + * r4 = TLBnCFG + * r3 = current address (more or less) */ + + li r5,0 + mtspr SPRN_MAS6,r5 + tlbsx 0,r3 + + rlwinm r9,r4,0,TLBnCFG_N_ENTRY + rlwinm r10,r4,8,0xff + addi r10,r10,-1 /* Get inner loop mask */ + + li r3,1 + + mfspr r5,SPRN_MAS1 + rlwinm r5,r5,0,(~(MAS1_VALID|MAS1_IPROT)) + + mfspr r6,SPRN_MAS2 + rldicr r6,r6,0,51 /* Extract EPN */ + + mfspr r7,SPRN_MAS0 + rlwinm r7,r7,0,0xffff0fff /* Clear HES and WQ */ + + rlwinm r8,r7,16,0xfff /* Extract ESEL */ + +2: add r4,r3,r8 + and r4,r4,r10 + + rlwimi r7,r4,16,MAS0_ESEL_MASK + + mtspr SPRN_MAS0,r7 + mtspr SPRN_MAS1,r5 + mtspr SPRN_MAS2,r6 + tlbwe + + addi r3,r3,1 + and. r4,r3,r10 + + bne 3f + addis r6,r6,(1<<30)@h +3: + cmpw r3,r9 + blt 2b + + .globl a2_tlbinit_after_iprot_flush +a2_tlbinit_after_iprot_flush: + +#ifdef CONFIG_PPC_EARLY_DEBUG_WSP + /* Now establish early debug mappings if applicable */ + /* Restore the MAS0 we used for linear mapping load */ + mtspr SPRN_MAS0,r11 + + lis r3,(MAS1_VALID | MAS1_IPROT)@h + ori r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT) + mtspr SPRN_MAS1,r3 + LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G) + mtspr SPRN_MAS2,r3 + LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW) + mtspr SPRN_MAS7_MAS3,r3 + /* re-use the MAS8 value from the linear mapping */ + tlbwe +#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ + PPC_TLBILX(0,0,0) sync isync + .globl a2_tlbinit_code_end +a2_tlbinit_code_end: + /* We translate LR and return */ mflr r3 tovirt(r3,r3) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index aeb739e1876..a85f4874cba 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -37,23 +37,51 @@ .globl __start_interrupts __start_interrupts: - STD_EXCEPTION_PSERIES(0x100, system_reset) + .globl system_reset_pSeries; +system_reset_pSeries: + HMT_MEDIUM; + DO_KVM 0x100; + SET_SCRATCH0(r13) +#ifdef CONFIG_PPC_P7_NAP +BEGIN_FTR_SECTION + /* Running native on arch 2.06 or later, check if we are + * waking up from nap. We only handle no state loss and + * supervisor state loss. We do -not- handle hypervisor + * state loss at this time. + */ + mfspr r13,SPRN_SRR1 + rlwinm r13,r13,47-31,30,31 + cmpwi cr0,r13,1 + bne 1f + b .power7_wakeup_noloss +1: cmpwi cr0,r13,2 + bne 1f + b .power7_wakeup_loss + /* Total loss of HV state is fatal, we could try to use the + * PIR to locate a PACA, then use an emergency stack etc... + * but for now, let's just stay stuck here + */ +1: cmpwi cr0,r13,3 + beq . +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206) +#endif /* CONFIG_PPC_P7_NAP */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) . = 0x200 _machine_check_pSeries: HMT_MEDIUM DO_KVM 0x200 - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) . = 0x300 .globl data_access_pSeries data_access_pSeries: HMT_MEDIUM DO_KVM 0x300 - mtspr SPRN_SPRG_SCRATCH0,r13 + SET_SCRATCH0(r13) BEGIN_FTR_SECTION - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) std r9,PACA_EXSLB+EX_R9(r13) std r10,PACA_EXSLB+EX_R10(r13) mfspr r10,SPRN_DAR @@ -67,22 +95,22 @@ BEGIN_FTR_SECTION std r11,PACA_EXGEN+EX_R11(r13) ld r11,PACA_EXSLB+EX_R9(r13) std r12,PACA_EXGEN+EX_R12(r13) - mfspr r12,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r12) std r10,PACA_EXGEN+EX_R10(r13) std r11,PACA_EXGEN+EX_R9(r13) std r12,PACA_EXGEN+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(data_access_common) + EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD) FTR_SECTION_ELSE - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common) -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) . = 0x380 .globl data_access_slb_pSeries data_access_slb_pSeries: HMT_MEDIUM DO_KVM 0x380 - mtspr SPRN_SPRG_SCRATCH0,r13 - mfspr r13,SPRN_SPRG_PACA /* get paca address into r13 */ + SET_SCRATCH0(r13) + GET_PACA(r13) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_DAR std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ @@ -95,7 +123,7 @@ data_access_slb_pSeries: std r10,PACA_EXSLB+EX_R10(r13) std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ #ifndef CONFIG_RELOCATABLE @@ -113,15 +141,15 @@ data_access_slb_pSeries: bctr #endif - STD_EXCEPTION_PSERIES(0x400, instruction_access) + STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access) . = 0x480 .globl instruction_access_slb_pSeries instruction_access_slb_pSeries: HMT_MEDIUM DO_KVM 0x480 - mtspr SPRN_SPRG_SCRATCH0,r13 - mfspr r13,SPRN_SPRG_PACA /* get paca address into r13 */ + SET_SCRATCH0(r13) + GET_PACA(r13) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ @@ -134,7 +162,7 @@ instruction_access_slb_pSeries: std r10,PACA_EXSLB+EX_R10(r13) std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ #ifndef CONFIG_RELOCATABLE @@ -147,13 +175,29 @@ instruction_access_slb_pSeries: bctr #endif - MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt) - STD_EXCEPTION_PSERIES(0x600, alignment) - STD_EXCEPTION_PSERIES(0x700, program_check) - STD_EXCEPTION_PSERIES(0x800, fp_unavailable) - MASKABLE_EXCEPTION_PSERIES(0x900, decrementer) - STD_EXCEPTION_PSERIES(0xa00, trap_0a) - STD_EXCEPTION_PSERIES(0xb00, trap_0b) + /* We open code these as we can't have a ". = x" (even with + * x = "." within a feature section + */ + . = 0x500; + .globl hardware_interrupt_pSeries; + .globl hardware_interrupt_hv; +hardware_interrupt_pSeries: +hardware_interrupt_hv: + BEGIN_FTR_SECTION + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD) + FTR_SECTION_ELSE + _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV) + ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206) + + STD_EXCEPTION_PSERIES(0x600, 0x600, alignment) + STD_EXCEPTION_PSERIES(0x700, 0x700, program_check) + STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) + + MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) + MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer) + + STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) + STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b) . = 0xc00 .globl system_call_pSeries @@ -165,13 +209,13 @@ BEGIN_FTR_SECTION beq- 1f END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) mr r9,r13 - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) mfspr r11,SPRN_SRR0 - ld r12,PACAKBASE(r13) - ld r10,PACAKMSR(r13) - LOAD_HANDLER(r12, system_call_entry) - mtspr SPRN_SRR0,r12 mfspr r12,SPRN_SRR1 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10, system_call_entry) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 rfid b . /* prevent speculative execution */ @@ -183,8 +227,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) rfid /* return to userspace */ b . - STD_EXCEPTION_PSERIES(0xd00, single_step) - STD_EXCEPTION_PSERIES(0xe00, trap_0e) + STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step) + + /* At 0xe??? we have a bunch of hypervisor exceptions, we branch + * out of line to handle them + */ + . = 0xe00 + b h_data_storage_hv + . = 0xe20 + b h_instr_storage_hv + . = 0xe40 + b emulation_assist_hv + . = 0xe50 + b hmi_exception_hv + . = 0xe60 + b hmi_exception_hv /* We need to deal with the Altivec unavailable exception * here which is at 0xf20, thus in the middle of the @@ -193,39 +250,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) */ performance_monitor_pSeries_1: . = 0xf00 - DO_KVM 0xf00 b performance_monitor_pSeries altivec_unavailable_pSeries_1: . = 0xf20 - DO_KVM 0xf20 b altivec_unavailable_pSeries vsx_unavailable_pSeries_1: . = 0xf40 - DO_KVM 0xf40 b vsx_unavailable_pSeries #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error) + STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) + STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance) + STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1700, altivec_assist) + STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal) + STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) #endif /* CONFIG_CBE_RAS */ . = 0x3000 -/*** pSeries interrupt support ***/ +/*** Out of line interrupts support ***/ + + /* moved from 0xe00 */ + STD_EXCEPTION_HV(., 0xe00, h_data_storage) + STD_EXCEPTION_HV(., 0xe20, h_instr_storage) + STD_EXCEPTION_HV(., 0xe40, emulation_assist) + STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */ /* moved from 0xf00 */ - STD_EXCEPTION_PSERIES(., performance_monitor) - STD_EXCEPTION_PSERIES(., altivec_unavailable) - STD_EXCEPTION_PSERIES(., vsx_unavailable) + STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor) + STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable) + STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable) /* * An interrupt came in while soft-disabled; clear EE in SRR1, @@ -240,17 +300,30 @@ masked_interrupt: rotldi r10,r10,16 mtspr SPRN_SRR1,r10 ld r10,PACA_EXGEN+EX_R10(r13) - mfspr r13,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r13) rfid b . +masked_Hinterrupt: + stb r10,PACAHARDIRQEN(r13) + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + mfspr r10,SPRN_HSRR1 + rldicl r10,r10,48,1 /* clear MSR_EE */ + rotldi r10,r10,16 + mtspr SPRN_HSRR1,r10 + ld r10,PACA_EXGEN+EX_R10(r13) + GET_SCRATCH0(r13) + hrfid + b . + .align 7 do_stab_bolted_pSeries: std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted) + EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) #ifdef CONFIG_PPC_PSERIES /* @@ -260,15 +333,15 @@ do_stab_bolted_pSeries: .align 7 system_reset_fwnmi: HMT_MEDIUM - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) .globl machine_check_fwnmi .align 7 machine_check_fwnmi: HMT_MEDIUM - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) #endif /* CONFIG_PPC_PSERIES */ @@ -282,7 +355,7 @@ slb_miss_user_pseries: std r10,PACA_EXGEN+EX_R10(r13) std r11,PACA_EXGEN+EX_R11(r13) std r12,PACA_EXGEN+EX_R12(r13) - mfspr r10,SPRG_SCRATCH0 + GET_SCRATCH0(r10) ld r11,PACA_EXSLB+EX_R9(r13) ld r12,PACA_EXSLB+EX_R3(r13) std r10,PACA_EXGEN+EX_R13(r13) @@ -342,6 +415,8 @@ machine_check_common: STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) + STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception) + STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) #ifdef CONFIG_ALTIVEC @@ -386,9 +461,24 @@ bad_stack: std r12,_XER(r1) SAVE_GPR(0,r1) SAVE_GPR(2,r1) - SAVE_4GPRS(3,r1) - SAVE_2GPRS(7,r1) - SAVE_10GPRS(12,r1) + ld r10,EX_R3(r3) + std r10,GPR3(r1) + SAVE_GPR(4,r1) + SAVE_4GPRS(5,r1) + ld r9,EX_R9(r3) + ld r10,EX_R10(r3) + SAVE_2GPRS(9,r1) + ld r9,EX_R11(r3) + ld r10,EX_R12(r3) + ld r11,EX_R13(r3) + std r9,GPR11(r1) + std r10,GPR12(r1) + std r11,GPR13(r1) +BEGIN_FTR_SECTION + ld r10,EX_CFAR(r3) + std r10,ORIG_GPR3(r1) +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + SAVE_8GPRS(14,r1) SAVE_10GPRS(22,r1) lhz r12,PACA_TRAP_SAVE(r13) std r12,_TRAP(r1) @@ -397,6 +487,9 @@ bad_stack: li r12,0 std r12,0(r11) ld r2,PACATOC(r13) + ld r11,exception_marker@toc(r2) + std r12,RESULT(r1) + std r11,STACK_FRAME_OVERHEAD-16(r1) 1: addi r3,r1,STACK_FRAME_OVERHEAD bl .kernel_bad_stack b 1b @@ -419,6 +512,19 @@ data_access_common: li r5,0x300 b .do_hash_page /* Try to handle as hpte fault */ + .align 7 + .globl h_data_storage_common +h_data_storage_common: + mfspr r10,SPRN_HDAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_HDSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .unknown_exception + b .ret_from_except + .align 7 .globl instruction_access_common instruction_access_common: @@ -428,6 +534,8 @@ instruction_access_common: li r5,0x400 b .do_hash_page /* Try to handle as hpte fault */ + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) + /* * Here is the common SLB miss user that is used when going to virtual * mode for SLB misses, that is currently not used @@ -750,7 +858,7 @@ _STATIC(do_hash_page) BEGIN_FTR_SECTION andis. r0,r4,0x0020 /* Is it a segment table fault? */ bne- do_ste_alloc /* If so handle it */ -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) clrrdi r11,r1,THREAD_SHIFT lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 3a319f9c9d3..ba504099844 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -147,6 +147,8 @@ __secondary_hold: mtctr r4 mr r3,r24 li r4,0 + /* Make sure that patched code is visible */ + isync bctr #else BUG_OPCODE @@ -216,19 +218,25 @@ generic_secondary_common_init: */ LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ ld r13,0(r13) /* Get base vaddr of paca array */ +#ifndef CONFIG_SMP + addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ + b .kexec_wait /* wait for next kernel if !SMP */ +#else + LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ + lwz r7,0(r7) /* also the max paca allocated */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ beq 2f addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ addi r5,r5,1 - cmpwi r5,NR_CPUS + cmpw r5,r7 /* Check if more pacas exist */ blt 1b mr r3,r24 /* not found, copy phys to r3 */ b .kexec_wait /* next kernel might do better */ -2: mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG */ +2: SET_PACA(r13) #ifdef CONFIG_PPC_BOOK3E addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */ mtspr SPRN_SPRG_TLB_EXFRAME,r12 @@ -236,34 +244,39 @@ generic_secondary_common_init: /* From now on, r24 is expected to be logical cpuid */ mr r24,r5 -3: HMT_LOW - lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ - /* start. */ - -#ifndef CONFIG_SMP - b 3b /* Never go on non-SMP */ -#else - cmpwi 0,r23,0 - beq 3b /* Loop until told to go */ - - sync /* order paca.run and cur_cpu_spec */ /* See if we need to call a cpu state restore handler */ LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) ld r23,CPU_SPEC_RESTORE(r23) cmpdi 0,r23,0 - beq 4f + beq 3f ld r23,0(r23) mtctr r23 bctrl -4: /* Create a temp kernel stack for use before relocation is on. */ +3: LOAD_REG_ADDR(r3, boot_cpu_count) /* Decrement boot_cpu_count */ + lwarx r4,0,r3 + subi r4,r4,1 + stwcx. r4,0,r3 + bne 3b + isync + +4: HMT_LOW + lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ + /* start. */ + cmpwi 0,r23,0 + beq 4b /* Loop until told to go */ + + sync /* order paca.run and cur_cpu_spec */ + isync /* In case code patching happened */ + + /* Create a temp kernel stack for use before relocation is on. */ ld r1,PACAEMERGSP(r13) subi r1,r1,STACK_FRAME_OVERHEAD b __secondary_start -#endif +#endif /* SMP */ /* * Turn the MMU off. @@ -534,7 +547,7 @@ _GLOBAL(pmac_secondary_start) ld r4,0(r4) /* Get base vaddr of paca array */ mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r4 /* for this processor. */ - mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG*/ + SET_PACA(r13) /* Save vaddr of paca in an SPRG*/ /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) @@ -645,7 +658,7 @@ _GLOBAL(enable_64b_mode) oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ mtmsr r11 #else /* CONFIG_PPC_BOOK3E */ - li r12,(MSR_SF | MSR_ISF)@highest + li r12,(MSR_64BIT | MSR_ISF)@highest sldi r12,r12,48 or r11,r11,r12 mtmsrd r11 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S new file mode 100644 index 00000000000..f8f0bc7f1d4 --- /dev/null +++ b/arch/powerpc/kernel/idle_power7.S @@ -0,0 +1,97 @@ +/* + * This file contains the power_save function for 970-family CPUs. + * + * 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/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/ppc-opcode.h> + +#undef DEBUG + + .text + +_GLOBAL(power7_idle) + /* Now check if user or arch enabled NAP mode */ + LOAD_REG_ADDRBASE(r3,powersave_nap) + lwz r4,ADDROFF(powersave_nap)(r3) + cmpwi 0,r4,0 + beqlr + + /* NAP is a state loss, we create a regs frame on the + * stack, fill it up with the state we care about and + * stick a pointer to it in PACAR1. We really only + * need to save PC, some CR bits and the NV GPRs, + * but for now an interrupt frame will do. + */ + mflr r0 + std r0,16(r1) + stdu r1,-INT_FRAME_SIZE(r1) + std r0,_LINK(r1) + std r0,_NIP(r1) + +#ifndef CONFIG_SMP + /* Make sure FPU, VSX etc... are flushed as we may lose + * state when going to nap mode + */ + bl .discard_lazy_cpu_state +#endif /* CONFIG_SMP */ + + /* Hard disable interrupts */ + mfmsr r9 + rldicl r9,r9,48,1 + rotldi r9,r9,16 + mtmsrd r9,1 /* hard-disable interrupts */ + li r0,0 + stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */ + stb r0,PACAHARDIRQEN(r13) + + /* Continue saving state */ + SAVE_GPR(2, r1) + SAVE_NVGPRS(r1) + mfcr r3 + std r3,_CCR(r1) + std r9,_MSR(r1) + std r1,PACAR1(r13) + + /* Magic NAP mode enter sequence */ + std r0,0(r1) + ptesync + ld r0,0(r1) +1: cmp cr0,r0,r0 + bne 1b + PPC_NAP + b . + +_GLOBAL(power7_wakeup_loss) + GET_PACA(r13) + ld r1,PACAR1(r13) + REST_NVGPRS(r1) + REST_GPR(2, r1) + ld r3,_CCR(r1) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtcr r3 + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid + +_GLOBAL(power7_wakeup_noloss) + GET_PACA(r13) + ld r1,PACAR1(r13) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid diff --git a/arch/powerpc/platforms/cell/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index 5c1118e3194..ffafaea3d26 100644 --- a/arch/powerpc/platforms/cell/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -17,8 +17,7 @@ #include <asm/machdep.h> #include <asm/pgtable.h> #include <asm/ppc-pci.h> - -#include "io-workarounds.h" +#include <asm/io-workarounds.h> #define IOWA_MAX_BUS 8 @@ -145,7 +144,19 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, return res; } -/* Regist new bus to support workaround */ +/* Enable IO workaround */ +static void __devinit io_workaround_init(void) +{ + static int io_workaround_inited; + + if (io_workaround_inited) + return; + ppc_pci_io = iowa_pci_io; + ppc_md.ioremap = iowa_ioremap; + io_workaround_inited = 1; +} + +/* Register new bus to support workaround */ void __devinit iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops, int (*initfunc)(struct iowa_bus *, void *), void *data) @@ -153,6 +164,8 @@ void __devinit iowa_register_bus(struct pci_controller *phb, struct iowa_bus *bus; struct device_node *np = phb->dn; + io_workaround_init(); + if (iowa_bus_count >= IOWA_MAX_BUS) { pr_err("IOWA:Too many pci bridges, " "workarounds disabled for %s\n", np->full_name); @@ -162,6 +175,7 @@ void __devinit iowa_register_bus(struct pci_controller *phb, bus = &iowa_busses[iowa_bus_count]; bus->phb = phb; bus->ops = ops; + bus->private = data; if (initfunc) if ((*initfunc)(bus, data)) @@ -172,14 +186,3 @@ void __devinit iowa_register_bus(struct pci_controller *phb, pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name); } -/* enable IO workaround */ -void __devinit io_workaround_init(void) -{ - static int io_workaround_inited; - - if (io_workaround_inited) - return; - ppc_pci_io = iowa_pci_io; - ppc_md.ioremap = iowa_ioremap; - io_workaround_inited = 1; -} diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index f621b7d2d86..a24d37d4cf5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -66,7 +66,6 @@ #include <asm/ptrace.h> #include <asm/machdep.h> #include <asm/udbg.h> -#include <asm/dbell.h> #include <asm/smp.h> #ifdef CONFIG_PPC64 @@ -160,7 +159,8 @@ notrace void arch_local_irq_restore(unsigned long en) #if defined(CONFIG_BOOKE) && defined(CONFIG_SMP) /* Check for pending doorbell interrupts and resend to ourself */ - doorbell_check_self(); + if (cpu_has_feature(CPU_FTR_DBELL)) + smp_muxed_ipi_resend(); #endif /* @@ -397,24 +397,28 @@ struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly; void exc_lvl_ctx_init(void) { struct thread_info *tp; - int i, hw_cpu; + int i, cpu_nr; for_each_possible_cpu(i) { - hw_cpu = get_hard_smp_processor_id(i); - memset((void *)critirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = critirq_ctx[hw_cpu]; - tp->cpu = i; +#ifdef CONFIG_PPC64 + cpu_nr = i; +#else + cpu_nr = get_hard_smp_processor_id(i); +#endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = critirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = 0; #ifdef CONFIG_BOOKE - memset((void *)dbgirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = dbgirq_ctx[hw_cpu]; - tp->cpu = i; + memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = dbgirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = 0; - memset((void *)mcheckirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = mcheckirq_ctx[hw_cpu]; - tp->cpu = i; + memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = mcheckirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = HARDIRQ_OFFSET; #endif } @@ -477,20 +481,41 @@ void do_softirq(void) * IRQ controller and virtual interrupts */ +/* The main irq map itself is an array of NR_IRQ entries containing the + * associate host and irq number. An entry with a host of NULL is free. + * An entry can be allocated if it's free, the allocator always then sets + * hwirq first to the host's invalid irq number and then fills ops. + */ +struct irq_map_entry { + irq_hw_number_t hwirq; + struct irq_host *host; +}; + static LIST_HEAD(irq_hosts); static DEFINE_RAW_SPINLOCK(irq_big_lock); -static unsigned int revmap_trees_allocated; static DEFINE_MUTEX(revmap_trees_mutex); -struct irq_map_entry irq_map[NR_IRQS]; +static struct irq_map_entry irq_map[NR_IRQS]; static unsigned int irq_virq_count = NR_IRQS; static struct irq_host *irq_default_host; +irq_hw_number_t irqd_to_hwirq(struct irq_data *d) +{ + return irq_map[d->irq].hwirq; +} +EXPORT_SYMBOL_GPL(irqd_to_hwirq); + irq_hw_number_t virq_to_hw(unsigned int virq) { return irq_map[virq].hwirq; } EXPORT_SYMBOL_GPL(virq_to_hw); +bool virq_is_host(unsigned int virq, struct irq_host *host) +{ + return irq_map[virq].host == host; +} +EXPORT_SYMBOL_GPL(virq_is_host); + static int default_irq_host_match(struct irq_host *h, struct device_node *np) { return h->of_node != NULL && h->of_node == np; @@ -511,7 +536,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, /* Allocate structure and revmap table if using linear mapping */ if (revmap_type == IRQ_HOST_MAP_LINEAR) size += revmap_arg * sizeof(unsigned int); - host = zalloc_maybe_bootmem(size, GFP_KERNEL); + host = kzalloc(size, GFP_KERNEL); if (host == NULL) return NULL; @@ -561,14 +586,14 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, irq_map[i].host = host; smp_wmb(); - /* Clear norequest flags */ - irq_clear_status_flags(i, IRQ_NOREQUEST); - /* Legacy flags are left to default at this point, * one can then use irq_create_mapping() to * explicitly change them */ ops->map(host, i, i); + + /* Clear norequest flags */ + irq_clear_status_flags(i, IRQ_NOREQUEST); } break; case IRQ_HOST_MAP_LINEAR: @@ -579,6 +604,9 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, smp_wmb(); host->revmap_data.linear.revmap = rmap; break; + case IRQ_HOST_MAP_TREE: + INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL); + break; default: break; } @@ -636,8 +664,6 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto error; } - irq_clear_status_flags(virq, IRQ_NOREQUEST); - /* map it */ smp_wmb(); irq_map[virq].hwirq = hwirq; @@ -648,6 +674,8 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto errdesc; } + irq_clear_status_flags(virq, IRQ_NOREQUEST); + return 0; errdesc: @@ -704,8 +732,6 @@ unsigned int irq_create_mapping(struct irq_host *host, */ virq = irq_find_mapping(host, hwirq); if (virq != NO_IRQ) { - if (host->ops->remap) - host->ops->remap(host, virq, hwirq); pr_debug("irq: -> existing mapping on virq %d\n", virq); return virq; } @@ -786,14 +812,15 @@ void irq_dispose_mapping(unsigned int virq) return; host = irq_map[virq].host; - WARN_ON (host == NULL); - if (host == NULL) + if (WARN_ON(host == NULL)) return; /* Never unmap legacy interrupts */ if (host->revmap_type == IRQ_HOST_MAP_LEGACY) return; + irq_set_status_flags(virq, IRQ_NOREQUEST); + /* remove chip and handler */ irq_set_chip_and_handler(virq, NULL, NULL); @@ -813,13 +840,6 @@ void irq_dispose_mapping(unsigned int virq) host->revmap_data.linear.revmap[hwirq] = NO_IRQ; break; case IRQ_HOST_MAP_TREE: - /* - * Check if radix tree allocated yet, if not then nothing to - * remove. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) - break; mutex_lock(&revmap_trees_mutex); radix_tree_delete(&host->revmap_data.tree, hwirq); mutex_unlock(&revmap_trees_mutex); @@ -830,8 +850,6 @@ void irq_dispose_mapping(unsigned int virq) smp_mb(); irq_map[virq].hwirq = host->inval_irq; - irq_set_status_flags(virq, IRQ_NOREQUEST); - irq_free_descs(virq, 1); /* Free it */ irq_free_virt(virq, 1); @@ -877,16 +895,9 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, struct irq_map_entry *ptr; unsigned int virq; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists and has bee initialized. - * If not, we fallback to slow mode - */ - if (revmap_trees_allocated < 2) + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE)) return irq_find_mapping(host, hwirq); - /* Now try to resolve */ /* * No rcu_read_lock(ing) needed, the ptr returned can't go under us * as it's referencing an entry in the static irq_map table. @@ -909,16 +920,7 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq, irq_hw_number_t hwirq) { - - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists yet. - * If not, then the irq will be inserted into the tree when it gets - * initialized. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) + if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE)) return; if (virq != NO_IRQ) { @@ -934,7 +936,8 @@ unsigned int irq_linear_revmap(struct irq_host *host, { unsigned int *revmap; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_LINEAR); + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR)) + return irq_find_mapping(host, hwirq); /* Check revmap bounds */ if (unlikely(hwirq >= host->revmap_data.linear.size)) @@ -1028,53 +1031,6 @@ int arch_early_irq_init(void) return 0; } -/* We need to create the radix trees late */ -static int irq_late_init(void) -{ - struct irq_host *h; - unsigned int i; - - /* - * No mutual exclusion with respect to accessors of the tree is needed - * here as the synchronization is done via the state variable - * revmap_trees_allocated. - */ - list_for_each_entry(h, &irq_hosts, link) { - if (h->revmap_type == IRQ_HOST_MAP_TREE) - INIT_RADIX_TREE(&h->revmap_data.tree, GFP_KERNEL); - } - - /* - * Make sure the radix trees inits are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 1; - - /* - * Insert the reverse mapping for those interrupts already present - * in irq_map[]. - */ - mutex_lock(&revmap_trees_mutex); - for (i = 0; i < irq_virq_count; i++) { - if (irq_map[i].host && - (irq_map[i].host->revmap_type == IRQ_HOST_MAP_TREE)) - radix_tree_insert(&irq_map[i].host->revmap_data.tree, - irq_map[i].hwirq, &irq_map[i]); - } - mutex_unlock(&revmap_trees_mutex); - - /* - * Make sure the radix trees insertions are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 2; - - return 0; -} -arch_initcall(irq_late_init); - #ifdef CONFIG_VIRQ_DEBUG static int virq_debug_show(struct seq_file *m, void *private) { @@ -1082,10 +1038,11 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; const char *p; static const char none[] = "none"; + void *data; int i; - seq_printf(m, "%-5s %-7s %-15s %s\n", "virq", "hwirq", - "chip name", "host name"); + seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq", + "chip name", "chip data", "host name"); for (i = 1; i < nr_irqs; i++) { desc = irq_to_desc(i); @@ -1098,7 +1055,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_chip *chip; seq_printf(m, "%5d ", i); - seq_printf(m, "0x%05lx ", virq_to_hw(i)); + seq_printf(m, "0x%05lx ", irq_map[i].hwirq); chip = irq_desc_get_chip(desc); if (chip && chip->name) @@ -1107,6 +1064,9 @@ static int virq_debug_show(struct seq_file *m, void *private) p = none; seq_printf(m, "%-15s ", p); + data = irq_desc_get_chip_data(desc); + seq_printf(m, "0x%16p ", data); + if (irq_map[i].host && irq_map[i].host->of_node) p = irq_map[i].host->of_node->full_name; else diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 42850ee00ad..bd9d35f59cf 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -109,7 +109,7 @@ static int kgdb_call_nmi_hook(struct pt_regs *regs) #ifdef CONFIG_SMP void kgdb_roundup_cpus(unsigned long flags) { - smp_send_debugger_break(MSG_ALL_BUT_SELF); + smp_send_debugger_break(); } #endif diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 301db65f05a..84daabe2fcb 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -132,34 +132,6 @@ static int iseries_lparcfg_data(struct seq_file *m, void *v) /* * Methods used to fetch LPAR data when running on a pSeries platform. */ -/** - * h_get_mpp - * H_GET_MPP hcall returns info in 7 parms - */ -int h_get_mpp(struct hvcall_mpp_data *mpp_data) -{ - int rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; - - rc = plpar_hcall9(H_GET_MPP, retbuf); - - mpp_data->entitled_mem = retbuf[0]; - mpp_data->mapped_mem = retbuf[1]; - - mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff; - mpp_data->pool_num = retbuf[2] & 0xffff; - - mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff; - mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff; - mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff; - - mpp_data->pool_size = retbuf[4]; - mpp_data->loan_request = retbuf[5]; - mpp_data->backing_mem = retbuf[6]; - - return rc; -} -EXPORT_SYMBOL(h_get_mpp); struct hvcall_ppp_data { u64 entitlement; @@ -345,6 +317,30 @@ static void parse_mpp_data(struct seq_file *m) seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem); } +/** + * parse_mpp_x_data + * Parse out data returned from h_get_mpp_x + */ +static void parse_mpp_x_data(struct seq_file *m) +{ + struct hvcall_mpp_x_data mpp_x_data; + + if (!firmware_has_feature(FW_FEATURE_XCMO)) + return; + if (h_get_mpp_x(&mpp_x_data)) + return; + + seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes); + + if (mpp_x_data.pool_coalesced_bytes) + seq_printf(m, "pool_coalesced_bytes=%ld\n", + mpp_x_data.pool_coalesced_bytes); + if (mpp_x_data.pool_purr_cycles) + seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles); + if (mpp_x_data.pool_spurr_cycles) + seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles); +} + #define SPLPAR_CHARACTERISTICS_TOKEN 20 #define SPLPAR_MAXLENGTH 1026*(sizeof(char)) @@ -520,6 +516,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) parse_system_parameter_string(m); parse_ppp_data(m); parse_mpp_data(m); + parse_mpp_x_data(m); pseries_cmo_data(m); splpar_dispatch_data(m); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 206a321a71d..e89df59cdc5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -462,7 +462,8 @@ _GLOBAL(disable_kernel_fp) * wait for the flag to change, indicating this kernel is going away but * the slave code for the next one is at addresses 0 to 100. * - * This is used by all slaves. + * This is used by all slaves, even those that did not find a matching + * paca in the secondary startup code. * * Physical (hardware) cpu id should be in r3. */ @@ -471,10 +472,6 @@ _GLOBAL(kexec_wait) 1: mflr r5 addi r5,r5,kexec_flag-1b - li r4,KEXEC_STATE_REAL_MODE - stb r4,PACAKEXECSTATE(r13) - SYNC - 99: HMT_LOW #ifdef CONFIG_KEXEC /* use no memory without kexec */ lwz r4,0(r5) @@ -499,11 +496,17 @@ kexec_flag: * * get phys id from paca * switch to real mode + * mark the paca as no longer used * join other cpus in kexec_wait(phys_id) */ _GLOBAL(kexec_smp_wait) lhz r3,PACAHWCPUID(r13) bl real_mode + + li r4,KEXEC_STATE_REAL_MODE + stb r4,PACAKEXECSTATE(r13) + SYNC + b .kexec_wait /* diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 10f0aadee95..efeb8818418 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/threads.h> +#include <linux/smp.h> #include <linux/module.h> #include <linux/memblock.h> @@ -156,18 +156,29 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) /* Put the paca pointer into r13 and SPRG_PACA */ void setup_paca(struct paca_struct *new_paca) { + /* Setup r13 */ local_paca = new_paca; - mtspr(SPRN_SPRG_PACA, local_paca); + #ifdef CONFIG_PPC_BOOK3E + /* On Book3E, initialize the TLB miss exception frames */ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); +#else + /* In HV mode, we setup both HPACA and PACA to avoid problems + * if we do a GET_PACA() before the feature fixups have been + * applied + */ + if (cpu_has_feature(CPU_FTR_HVMODE_206)) + mtspr(SPRN_SPRG_HPACA, local_paca); #endif + mtspr(SPRN_SPRG_PACA, local_paca); + } static int __initdata paca_size; void __init allocate_pacas(void) { - int nr_cpus, cpu, limit; + int cpu, limit; /* * We can't take SLB misses on the paca, and we want to access them @@ -179,23 +190,18 @@ void __init allocate_pacas(void) if (firmware_has_feature(FW_FEATURE_ISERIES)) limit = min(limit, HvPagesToMap * HVPAGESIZE); - nr_cpus = NR_CPUS; - /* On iSeries we know we can never have more than 64 cpus */ - if (firmware_has_feature(FW_FEATURE_ISERIES)) - nr_cpus = min(64, nr_cpus); - - paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); memset(paca, 0, paca_size); printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", - paca_size, nr_cpus, paca); + paca_size, nr_cpu_ids, paca); - allocate_lppacas(nr_cpus, limit); + allocate_lppacas(nr_cpu_ids, limit); /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < nr_cpus; cpu++) + for (cpu = 0; cpu < nr_cpu_ids; cpu++) initialise_paca(&paca[cpu], cpu); } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index d225d99fe39..6baabc13306 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -43,10 +43,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data) const u32 *regs; struct pci_dn *pdn; - pdn = alloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); + pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); if (pdn == NULL) return NULL; - memset(pdn, 0, sizeof(*pdn)); dn->data = pdn; pdn->node = dn; pdn->phb = phb; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ef3ef566235..7d28f540200 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -54,7 +54,6 @@ extern void single_step_exception(struct pt_regs *regs); extern int sys_sigreturn(struct pt_regs *regs); EXPORT_SYMBOL(clear_pages); -EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); @@ -88,9 +87,7 @@ EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__strncpy_from_user); EXPORT_SYMBOL(__strnlen_user); -#ifdef CONFIG_PPC64 -EXPORT_SYMBOL(copy_4K_page); -#endif +EXPORT_SYMBOL(copy_page); #if defined(CONFIG_PCI) && defined(CONFIG_PPC32) EXPORT_SYMBOL(isa_io_base); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index f74f355a961..095043d7994 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -702,6 +702,8 @@ void prepare_to_copy(struct task_struct *tsk) /* * Copy a thread.. */ +extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ + int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) @@ -755,11 +757,11 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, _ALIGN_UP(sizeof(struct thread_info), 16); #ifdef CONFIG_PPC_STD_MMU_64 - if (cpu_has_feature(CPU_FTR_SLB)) { + if (mmu_has_feature(MMU_FTR_SLB)) { unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) << SLB_VSID_SHIFT_1T; else @@ -769,6 +771,20 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.ksp_vsid = sp_vsid; } #endif /* CONFIG_PPC_STD_MMU_64 */ +#ifdef CONFIG_PPC64 + if (cpu_has_feature(CPU_FTR_DSCR)) { + if (current->thread.dscr_inherit) { + p->thread.dscr_inherit = 1; + p->thread.dscr = current->thread.dscr; + } else if (0 != dscr_default) { + p->thread.dscr_inherit = 1; + p->thread.dscr = dscr_default; + } else { + p->thread.dscr_inherit = 0; + p->thread.dscr = 0; + } + } +#endif /* * The PPC64 ABI makes use of a TOC to contain function diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index e74fa12afc8..5f5e6aed2b7 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -123,18 +123,19 @@ static void __init move_device_tree(void) */ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ + unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_SLB, 0, 0, 2, 0}, - {CPU_FTR_CTRL, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 1, 1, 1}, - {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, + {0, MMU_FTR_SLB, 0, 0, 2, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; @@ -166,9 +167,11 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } } @@ -268,13 +271,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) { - static int logical_cpuid = 0; char *type = of_get_flat_dt_prop(node, "device_type", NULL); const u32 *prop; const u32 *intserv; int i, nthreads; unsigned long len; - int found = 0; + int found = -1; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -299,11 +301,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * booted proc. */ if (initial_boot_params && initial_boot_params->version >= 2) { - if (intserv[i] == - initial_boot_params->boot_cpuid_phys) { - found = 1; - break; - } + if (intserv[i] == initial_boot_params->boot_cpuid_phys) + found = boot_cpu_count; } else { /* * Check if it's the boot-cpu, set it's hw index now, @@ -311,23 +310,20 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * off secondary threads. */ if (of_get_flat_dt_prop(node, - "linux,boot-cpu", NULL) != NULL) { - found = 1; - break; - } + "linux,boot-cpu", NULL) != NULL) + found = boot_cpu_count; } - #ifdef CONFIG_SMP /* logical cpu id is always 0 on UP kernels */ - logical_cpuid++; + boot_cpu_count++; #endif } - if (found) { - DBG("boot cpu: logical %d physical %d\n", logical_cpuid, + if (found >= 0) { + DBG("boot cpu: logical %d physical %d\n", found, intserv[i]); - boot_cpuid = logical_cpuid; - set_hard_smp_processor_id(boot_cpuid, intserv[i]); + boot_cpuid = found; + set_hard_smp_processor_id(found, intserv[i]); /* * PAPR defines "logical" PVR values for cpus that diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 941ff4dbc56..c016033ba78 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -335,6 +335,7 @@ static void __init prom_printf(const char *format, ...) const char *p, *q, *s; va_list args; unsigned long v; + long vs; struct prom_t *_prom = &RELOC(prom); va_start(args, format); @@ -368,12 +369,35 @@ static void __init prom_printf(const char *format, ...) v = va_arg(args, unsigned long); prom_print_hex(v); break; + case 'd': + ++q; + vs = va_arg(args, int); + if (vs < 0) { + prom_print(RELOC("-")); + vs = -vs; + } + prom_print_dec(vs); + break; case 'l': ++q; - if (*q == 'u') { /* '%lu' */ + if (*q == 0) + break; + else if (*q == 'x') { + ++q; + v = va_arg(args, unsigned long); + prom_print_hex(v); + } else if (*q == 'u') { /* '%lu' */ ++q; v = va_arg(args, unsigned long); prom_print_dec(v); + } else if (*q == 'd') { /* %ld */ + ++q; + vs = va_arg(args, long); + if (vs < 0) { + prom_print(RELOC("-")); + vs = -vs; + } + prom_print_dec(vs); } break; } @@ -676,8 +700,10 @@ static void __init early_cmdline_parse(void) #endif /* CONFIG_PCI_MSI */ #ifdef CONFIG_PPC_SMLPAR #define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */ +#define OV5_XCMO 0x40 /* Page Coalescing */ #else #define OV5_CMO 0x00 +#define OV5_XCMO 0x00 #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ @@ -732,7 +758,7 @@ static unsigned char ibm_architecture_vec[] = { OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | OV5_DONATE_DEDICATE_CPU | OV5_MSI, 0, - OV5_CMO, + OV5_CMO | OV5_XCMO, OV5_TYPE1_AFFINITY, 0, 0, diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 2097f2b3cba..271ff6318ed 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -42,6 +42,7 @@ #include <asm/time.h> #include <asm/mmu.h> #include <asm/topology.h> +#include <asm/pSeries_reconfig.h> struct rtas_t rtas = { .lock = __ARCH_SPIN_LOCK_UNLOCKED @@ -494,7 +495,7 @@ unsigned int rtas_busy_delay(int status) might_sleep(); ms = rtas_busy_delay_time(status); - if (ms) + if (ms && need_resched()) msleep(ms); return ms; @@ -731,6 +732,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w atomic_set(&data->error, rc); start_topology_update(); + pSeries_coalesce_init(); if (wake_when_done) { atomic_set(&data->done, 1); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 21f30cb6807..ef33a084fcf 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -381,7 +381,7 @@ static void __init cpu_init_thread_core_maps(int tpc) int i; threads_per_core = tpc; - threads_core_mask = CPU_MASK_NONE; + cpumask_clear(&threads_core_mask); /* This implementation only supports power of 2 number of threads * for simplicity and performance @@ -390,7 +390,7 @@ static void __init cpu_init_thread_core_maps(int tpc) BUG_ON(tpc != (1 << threads_shift)); for (i = 0; i < tpc; i++) - cpu_set(i, threads_core_mask); + cpumask_set_cpu(i, &threads_core_mask); printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n", tpc, tpc > 1 ? "s" : ""); @@ -404,7 +404,7 @@ static void __init cpu_init_thread_core_maps(int tpc) * cpu_present_mask * * Having the possible map set up early allows us to restrict allocations - * of things like irqstacks to num_possible_cpus() rather than NR_CPUS. + * of things like irqstacks to nr_cpu_ids rather than NR_CPUS. * * We do not initialize the online map here; cpus set their own bits in * cpu_online_mask as they come up. @@ -424,7 +424,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) { + while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) { const int *intserv; int j, len; @@ -443,7 +443,7 @@ void __init smp_setup_cpu_maps(void) intserv = &cpu; /* assume logical == phys */ } - for (j = 0; j < nthreads && cpu < NR_CPUS; j++) { + for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, intserv[j]); set_cpu_present(cpu, true); @@ -483,12 +483,12 @@ void __init smp_setup_cpu_maps(void) if (cpu_has_feature(CPU_FTR_SMT)) maxcpus *= nthreads; - if (maxcpus > NR_CPUS) { + if (maxcpus > nr_cpu_ids) { printk(KERN_WARNING "Partition configured for %d cpus, " "operating system maximum is %d.\n", - maxcpus, NR_CPUS); - maxcpus = NR_CPUS; + maxcpus, nr_cpu_ids); + maxcpus = nr_cpu_ids; } else printk(KERN_INFO "Partition configured for %d cpus.\n", maxcpus); @@ -510,7 +510,7 @@ void __init smp_setup_cpu_maps(void) cpu_init_thread_core_maps(nthreads); /* Now that possible cpus are set, set nr_cpu_ids for later use */ - nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; + setup_nr_cpu_ids(); free_unused_pacas(); } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1d2fbc90530..620d792b52e 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -48,6 +48,7 @@ extern void bootx_init(unsigned long r4, unsigned long phys); int boot_cpuid = -1; EXPORT_SYMBOL_GPL(boot_cpuid); +int __initdata boot_cpu_count; int boot_cpuid_phys; int smp_hw_index[NR_CPUS]; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5a0401fcaeb..c2ec0a12e14 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -72,6 +72,7 @@ #endif int boot_cpuid = 0; +int __initdata boot_cpu_count; u64 ppc64_pft_size; /* Pick defaults since we might want to patch instructions @@ -233,6 +234,7 @@ void early_setup_secondary(void) void smp_release_cpus(void) { unsigned long *ptr; + int i; DBG(" -> smp_release_cpus()\n"); @@ -245,7 +247,16 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); *ptr = __pa(generic_secondary_smp_init); - mb(); + + /* And wait a bit for them to catch up */ + for (i = 0; i < 100000; i++) { + mb(); + HMT_low(); + if (boot_cpu_count == 0) + break; + udelay(1); + } + DBG("boot_cpu_count = %d\n", boot_cpu_count); DBG(" <- smp_release_cpus()\n"); } @@ -423,17 +434,30 @@ void __init setup_system(void) DBG(" <- setup_system()\n"); } -static u64 slb0_limit(void) +/* This returns the limit below which memory accesses to the linear + * mapping are guarnateed not to cause a TLB or SLB miss. This is + * used to allocate interrupt or emergency stacks for which our + * exception entry path doesn't deal with being interrupted. + */ +static u64 safe_stack_limit(void) { - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { +#ifdef CONFIG_PPC_BOOK3E + /* Freescale BookE bolts the entire linear mapping */ + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + return linear_map_top; + /* Other BookE, we assume the first GB is bolted */ + return 1ul << 30; +#else + /* BookS, the first segment is bolted */ + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) return 1UL << SID_SHIFT_1T; - } return 1UL << SID_SHIFT; +#endif } static void __init irqstack_early_init(void) { - u64 limit = slb0_limit(); + u64 limit = safe_stack_limit(); unsigned int i; /* @@ -486,7 +510,7 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(slb0_limit(), ppc64_rma_size); + limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { unsigned long sp; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 27c4a4584f8..da989fff19c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -381,7 +381,7 @@ badframe: regs, uc, &uc->uc_mcontext); #endif if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_SF ? fmt64 : fmt32, + printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "rt_sigreturn", (long)uc, regs->nip, regs->link); @@ -469,7 +469,7 @@ badframe: regs, frame, newsp); #endif if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_SF ? fmt64 : fmt32, + printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "setup_rt_frame", (long)frame, regs->nip, regs->link); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index f2dcab7aadc..dd1973fed30 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -95,7 +95,7 @@ int smt_enabled_at_boot = 1; static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL; #ifdef CONFIG_PPC64 -void __devinit smp_generic_kick_cpu(int nr) +int __devinit smp_generic_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); @@ -106,37 +106,10 @@ void __devinit smp_generic_kick_cpu(int nr) */ paca[nr].cpu_start = 1; smp_mb(); -} -#endif -void smp_message_recv(int msg) -{ - switch(msg) { - case PPC_MSG_CALL_FUNCTION: - generic_smp_call_function_interrupt(); - break; - case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ - break; - case PPC_MSG_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; - case PPC_MSG_DEBUGGER_BREAK: - if (crash_ipi_function_ptr) { - crash_ipi_function_ptr(get_irq_regs()); - break; - } -#ifdef CONFIG_DEBUGGER - debugger_ipi(get_irq_regs()); - break; -#endif /* CONFIG_DEBUGGER */ - /* FALLTHROUGH */ - default: - printk("SMP %d: smp_message_recv(): unknown msg %d\n", - smp_processor_id(), msg); - break; - } + return 0; } +#endif static irqreturn_t call_function_action(int irq, void *data) { @@ -156,9 +129,17 @@ static irqreturn_t call_function_single_action(int irq, void *data) return IRQ_HANDLED; } -static irqreturn_t debug_ipi_action(int irq, void *data) +irqreturn_t debug_ipi_action(int irq, void *data) { - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + if (crash_ipi_function_ptr) { + crash_ipi_function_ptr(get_irq_regs()); + return IRQ_HANDLED; + } + +#ifdef CONFIG_DEBUGGER + debugger_ipi(get_irq_regs()); +#endif /* CONFIG_DEBUGGER */ + return IRQ_HANDLED; } @@ -197,6 +178,66 @@ int smp_request_message_ipi(int virq, int msg) return err; } +#ifdef CONFIG_PPC_SMP_MUXED_IPI +struct cpu_messages { + int messages; /* current messages */ + unsigned long data; /* data for cause ipi */ +}; +static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message); + +void smp_muxed_ipi_set_data(int cpu, unsigned long data) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + + info->data = data; +} + +void smp_muxed_ipi_message_pass(int cpu, int msg) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + char *message = (char *)&info->messages; + + message[msg] = 1; + mb(); + smp_ops->cause_ipi(cpu, info->data); +} + +void smp_muxed_ipi_resend(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + + if (info->messages) + smp_ops->cause_ipi(smp_processor_id(), info->data); +} + +irqreturn_t smp_ipi_demux(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + unsigned int all; + + mb(); /* order any irq clear */ + + do { + all = xchg_local(&info->messages, 0); + +#ifdef __BIG_ENDIAN + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) + generic_smp_call_function_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE))) + reschedule_action(0, NULL); /* upcoming sched hook */ + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE))) + generic_smp_call_function_single_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK))) + debug_ipi_action(0, NULL); +#else +#error Unsupported ENDIAN +#endif + } while (info->messages); + + return IRQ_HANDLED; +} +#endif /* CONFIG_PPC_SMP_MUXED_IPI */ + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) @@ -216,11 +257,18 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION); } -#ifdef CONFIG_DEBUGGER -void smp_send_debugger_break(int cpu) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +void smp_send_debugger_break(void) { - if (likely(smp_ops)) - smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); + int cpu; + int me = raw_smp_processor_id(); + + if (unlikely(!smp_ops)) + return; + + for_each_online_cpu(cpu) + if (cpu != me) + smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); } #endif @@ -228,9 +276,9 @@ void smp_send_debugger_break(int cpu) void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; - if (crash_ipi_callback && smp_ops) { + if (crash_ipi_callback) { mb(); - smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK); + smp_send_debugger_break(); } } #endif @@ -434,7 +482,11 @@ int __cpuinit __cpu_up(unsigned int cpu) /* wake up cpus */ DBG("smp: kicking cpu %d\n", cpu); - smp_ops->kick_cpu(cpu); + rc = smp_ops->kick_cpu(cpu); + if (rc) { + pr_err("smp: failed starting cpu %d (rc %d)\n", cpu, rc); + return rc; + } /* * wait to see if the cpu made a callin (is actually up). @@ -507,7 +559,7 @@ int cpu_first_thread_of_core(int core) } EXPORT_SYMBOL_GPL(cpu_first_thread_of_core); -/* Must be called when no change can occur to cpu_present_map, +/* Must be called when no change can occur to cpu_present_mask, * i.e. during cpu online or offline. */ static struct device_node *cpu_to_l2cache(int cpu) @@ -608,7 +660,7 @@ void __init smp_cpus_done(unsigned int max_cpus) * se we pin us down to CPU 0 for a short while */ alloc_cpumask_var(&old_mask, GFP_NOWAIT); - cpumask_copy(old_mask, ¤t->cpus_allowed); + cpumask_copy(old_mask, tsk_cpus_allowed(current)); set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid)); if (smp_ops && smp_ops->setup_cpu) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index c0d8c2006bf..f0f2199e64e 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -182,6 +182,41 @@ static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr); static SYSDEV_ATTR(purr, 0600, show_purr, store_purr); + +unsigned long dscr_default = 0; +EXPORT_SYMBOL(dscr_default); + +static ssize_t show_dscr_default(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) +{ + return sprintf(buf, "%lx\n", dscr_default); +} + +static ssize_t __used store_dscr_default(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, + size_t count) +{ + unsigned long val; + int ret = 0; + + ret = sscanf(buf, "%lx", &val); + if (ret != 1) + return -EINVAL; + dscr_default = val; + + return count; +} + +static SYSDEV_CLASS_ATTR(dscr_default, 0600, + show_dscr_default, store_dscr_default); + +static void sysfs_create_dscr_default(void) +{ + int err = 0; + if (cpu_has_feature(CPU_FTR_DSCR)) + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_dscr_default.attr); +} #endif /* CONFIG_PPC64 */ #ifdef HAS_PPC_PMC_PA6T @@ -617,6 +652,9 @@ static int __init topology_init(void) if (cpu_online(cpu)) register_cpu_online(cpu); } +#ifdef CONFIG_PPC64 + sysfs_create_dscr_default(); +#endif /* CONFIG_PPC64 */ return 0; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 5ddb801bc15..06b9d457d0a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -199,7 +199,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) } else if (show_unhandled_signals && unhandled_signal(current, signr) && printk_ratelimit()) { - printk(regs->msr & MSR_SF ? fmt64 : fmt32, + printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, signr, addr, regs->nip, regs->link, code); } @@ -221,7 +221,7 @@ void system_reset_exception(struct pt_regs *regs) } #ifdef CONFIG_KEXEC - cpu_set(smp_processor_id(), cpus_in_sr); + cpumask_set_cpu(smp_processor_id(), &cpus_in_sr); #endif die("System Reset", regs, SIGABRT); @@ -909,6 +909,26 @@ static int emulate_instruction(struct pt_regs *regs) return emulate_isel(regs, instword); } +#ifdef CONFIG_PPC64 + /* Emulate the mfspr rD, DSCR. */ + if (((instword & PPC_INST_MFSPR_DSCR_MASK) == PPC_INST_MFSPR_DSCR) && + cpu_has_feature(CPU_FTR_DSCR)) { + PPC_WARN_EMULATED(mfdscr, regs); + rd = (instword >> 21) & 0x1f; + regs->gpr[rd] = mfspr(SPRN_DSCR); + return 0; + } + /* Emulate the mtspr DSCR, rD. */ + if (((instword & PPC_INST_MTSPR_DSCR_MASK) == PPC_INST_MTSPR_DSCR) && + cpu_has_feature(CPU_FTR_DSCR)) { + PPC_WARN_EMULATED(mtdscr, regs); + rd = (instword >> 21) & 0x1f; + mtspr(SPRN_DSCR, regs->gpr[rd]); + current->thread.dscr_inherit = 1; + return 0; + } +#endif + return -EINVAL; } @@ -1506,6 +1526,10 @@ struct ppc_emulated ppc_emulated = { #ifdef CONFIG_VSX WARN_EMULATED_SETUP(vsx), #endif +#ifdef CONFIG_PPC64 + WARN_EMULATED_SETUP(mfdscr), + WARN_EMULATED_SETUP(mtdscr), +#endif }; u32 ppc_warn_emulated; diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index e39cad83c88..23d65abbedc 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -62,6 +62,8 @@ void __init udbg_early_init(void) udbg_init_cpm(); #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO) udbg_init_usbgecko(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) + udbg_init_wsp(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index baa33a7517b..6837f839ab7 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <asm/udbg.h> #include <asm/io.h> +#include <asm/reg_a2.h> extern u8 real_readb(volatile u8 __iomem *addr); extern void real_writeb(u8 data, volatile u8 __iomem *addr); @@ -298,3 +299,53 @@ void __init udbg_init_40x_realmode(void) udbg_getc_poll = NULL; } #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ + +#ifdef CONFIG_PPC_EARLY_DEBUG_WSP +static void udbg_wsp_flush(void) +{ + if (udbg_comport) { + while ((readb(&udbg_comport->lsr) & LSR_THRE) == 0) + /* wait for idle */; + } +} + +static void udbg_wsp_putc(char c) +{ + if (udbg_comport) { + if (c == '\n') + udbg_wsp_putc('\r'); + udbg_wsp_flush(); + writeb(c, &udbg_comport->thr); eieio(); + } +} + +static int udbg_wsp_getc(void) +{ + if (udbg_comport) { + while ((readb(&udbg_comport->lsr) & LSR_DR) == 0) + ; /* wait for char */ + return readb(&udbg_comport->rbr); + } + return -1; +} + +static int udbg_wsp_getc_poll(void) +{ + if (udbg_comport) + if (readb(&udbg_comport->lsr) & LSR_DR) + return readb(&udbg_comport->rbr); + return -1; +} + +void __init udbg_init_wsp(void) +{ + udbg_comport = (struct NS16550 __iomem *)WSP_UART_VIRT; + + udbg_init_uart(udbg_comport, 57600, 50000000); + + udbg_putc = udbg_wsp_putc; + udbg_flush = udbg_wsp_flush; + udbg_getc = udbg_wsp_getc; + udbg_getc_poll = udbg_wsp_getc_poll; +} +#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 9de6f396cf8..4d5a3edff49 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -102,7 +102,7 @@ _GLOBAL(giveup_altivec) MTMSRD(r5) /* enable use of VMX now */ isync PPC_LCMPI 0,r3,0 - beqlr- /* if no previous owner, done */ + beqlr /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r5,0 diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 2b9c9088d00..ae99af66ca3 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -35,9 +35,7 @@ #if defined(CONFIG_PPC_BOOK3S_64) -#define LOAD_SHADOW_VCPU(reg) \ - mfspr reg, SPRN_SPRG_PACA - +#define LOAD_SHADOW_VCPU(reg) GET_PACA(reg) #define SHADOW_VCPU_OFF PACA_KVM_SVCPU #define MSR_NOIRQ MSR_KERNEL & ~(MSR_IR | MSR_DR) #define FUNC(name) GLUE(.,name) @@ -72,7 +70,7 @@ .global kvmppc_trampoline_\intno kvmppc_trampoline_\intno: - mtspr SPRN_SPRG_SCRATCH0, r13 /* Save r13 */ + SET_SCRATCH0(r13) /* Save r13 */ /* * First thing to do is to find out if we're coming @@ -91,7 +89,7 @@ kvmppc_trampoline_\intno: lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) - mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ + GET_SCRATCH0(r13) /* r13 = original r13 */ b kvmppc_resume_\intno /* Get back original handler */ /* Now we know we're handling a KVM guest */ @@ -114,6 +112,7 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_MACHINE_CHECK INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL +INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL_HV INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALIGNMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PROGRAM INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_FP_UNAVAIL @@ -158,7 +157,7 @@ kvmppc_handler_skip_ins: lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) - mfspr r13, SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r13) /* And get back into the code */ RFI diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 7c52ed0b705..451264274b8 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -155,14 +155,20 @@ kvmppc_handler_trampoline_exit: PPC_LL r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13) /* Save guest PC and MSR */ - mfsrr0 r3 + andi. r0,r12,0x2 + beq 1f + mfspr r3,SPRN_HSRR0 + mfspr r4,SPRN_HSRR1 + andi. r12,r12,0x3ffd + b 2f +1: mfsrr0 r3 mfsrr1 r4 - +2: PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13) PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13) /* Get scratch'ed off registers */ - mfspr r9, SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r9) PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) lwz r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index f53e09c7dac..13b676c20d1 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -6,14 +6,6 @@ #include <asm/system.h> -void * __init_refok alloc_maybe_bootmem(size_t size, gfp_t mask) -{ - if (mem_init_done) - return kmalloc(size, mask); - else - return alloc_bootmem(size); -} - void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask) { void *p; diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 4d4eeb90048..53dcb6b1b70 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -6,6 +6,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include <asm/page.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> @@ -15,9 +16,9 @@ PPC64_CACHES: .tc ppc64_caches[TC],ppc64_caches .section ".text" - -_GLOBAL(copy_4K_page) - li r5,4096 /* 4K page size */ +_GLOBAL(copy_page) + lis r5,PAGE_SIZE@h + ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION ld r10,PPC64_CACHES@toc(r2) lwz r11,DCACHEL1LOGLINESIZE(r10) /* log2 of cache line size */ diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c index deac4d30daf..e91615abae6 100644 --- a/arch/powerpc/lib/devres.c +++ b/arch/powerpc/lib/devres.c @@ -9,11 +9,11 @@ #include <linux/device.h> /* devres_*(), devm_ioremap_release() */ #include <linux/gfp.h> -#include <linux/io.h> /* ioremap_flags() */ +#include <linux/io.h> /* ioremap_prot() */ #include <linux/module.h> /* EXPORT_SYMBOL() */ /** - * devm_ioremap_prot - Managed ioremap_flags() + * devm_ioremap_prot - Managed ioremap_prot() * @dev: Generic device to remap IO address for * @offset: BUS offset to map * @size: Size of map @@ -31,7 +31,7 @@ void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset, if (!ptr) return NULL; - addr = ioremap_flags(offset, size, flags); + addr = ioremap_prot(offset, size, flags); if (addr) { *ptr = addr; devres_add(dev, ptr); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index ae5189ab004..0e5e540c777 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -45,6 +45,18 @@ extern int do_stxvd2x(int rn, unsigned long ea); #endif /* + * Emulate the truncation of 64 bit values in 32-bit mode. + */ +static unsigned long truncate_if_32bit(unsigned long msr, unsigned long val) +{ +#ifdef __powerpc64__ + if ((msr & MSR_64BIT) == 0) + val &= 0xffffffffUL; +#endif + return val; +} + +/* * Determine whether a conditional branch instruction would branch. */ static int __kprobes branch_taken(unsigned int instr, struct pt_regs *regs) @@ -90,11 +102,8 @@ static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs if (instr & 0x04000000) /* update forms */ regs->gpr[ra] = ea; } -#ifdef __powerpc64__ - if (!(regs->msr & MSR_SF)) - ea &= 0xffffffffUL; -#endif - return ea; + + return truncate_if_32bit(regs->msr, ea); } #ifdef __powerpc64__ @@ -113,9 +122,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg if ((instr & 3) == 1) /* update forms */ regs->gpr[ra] = ea; } - if (!(regs->msr & MSR_SF)) - ea &= 0xffffffffUL; - return ea; + + return truncate_if_32bit(regs->msr, ea); } #endif /* __powerpc64 */ @@ -136,11 +144,8 @@ static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs if (do_update) /* update forms */ regs->gpr[ra] = ea; } -#ifdef __powerpc64__ - if (!(regs->msr & MSR_SF)) - ea &= 0xffffffffUL; -#endif - return ea; + + return truncate_if_32bit(regs->msr, ea); } /* @@ -466,7 +471,7 @@ static void __kprobes set_cr0(struct pt_regs *regs, int rd) regs->ccr = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000); #ifdef __powerpc64__ - if (!(regs->msr & MSR_SF)) + if (!(regs->msr & MSR_64BIT)) val = (int) val; #endif if (val < 0) @@ -487,7 +492,7 @@ static void __kprobes add_with_carry(struct pt_regs *regs, int rd, ++val; regs->gpr[rd] = val; #ifdef __powerpc64__ - if (!(regs->msr & MSR_SF)) { + if (!(regs->msr & MSR_64BIT)) { val = (unsigned int) val; val1 = (unsigned int) val1; } @@ -570,8 +575,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) if ((instr & 2) == 0) imm += regs->nip; regs->nip += 4; - if ((regs->msr & MSR_SF) == 0) - regs->nip &= 0xffffffffUL; + regs->nip = truncate_if_32bit(regs->msr, regs->nip); if (instr & 1) regs->link = regs->nip; if (branch_taken(instr, regs)) @@ -604,13 +608,9 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) imm -= 0x04000000; if ((instr & 2) == 0) imm += regs->nip; - if (instr & 1) { - regs->link = regs->nip + 4; - if ((regs->msr & MSR_SF) == 0) - regs->link &= 0xffffffffUL; - } - if ((regs->msr & MSR_SF) == 0) - imm &= 0xffffffffUL; + if (instr & 1) + regs->link = truncate_if_32bit(regs->msr, regs->nip + 4); + imm = truncate_if_32bit(regs->msr, imm); regs->nip = imm; return 1; case 19: @@ -618,11 +618,8 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) case 16: /* bclr */ case 528: /* bcctr */ imm = (instr & 0x400)? regs->ctr: regs->link; - regs->nip += 4; - if ((regs->msr & MSR_SF) == 0) { - regs->nip &= 0xffffffffUL; - imm &= 0xffffffffUL; - } + regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4); + imm = truncate_if_32bit(regs->msr, imm); if (instr & 1) regs->link = regs->nip; if (branch_taken(instr, regs)) @@ -1616,11 +1613,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) return 0; /* invoke DSI if -EFAULT? */ } instr_done: - regs->nip += 4; -#ifdef __powerpc64__ - if ((regs->msr & MSR_SF) == 0) - regs->nip &= 0xffffffffUL; -#endif + regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4); return 1; logical_done: diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 5b7dd4ea02b..a242b5d7cbe 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -118,7 +118,7 @@ _GLOBAL(__hash_page_4K) BEGIN_FTR_SECTION cmpdi r9,0 /* check segment size */ bne 3f -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* Calc va and put it in r29 */ rldicr r29,r5,28,63-28 rldicl r3,r3,0,36 @@ -401,7 +401,7 @@ _GLOBAL(__hash_page_4K) BEGIN_FTR_SECTION cmpdi r9,0 /* check segment size */ bne 3f -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* Calc va and put it in r29 */ rldicr r29,r5,28,63-28 /* r29 = (vsid << 28) */ rldicl r3,r3,0,36 /* r3 = (ea & 0x0fffffff) */ @@ -715,7 +715,7 @@ BEGIN_FTR_SECTION andi. r0,r31,_PAGE_NO_CACHE /* If so, bail out and refault as a 4k page */ bne- ht64_bail_ok -END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_CI_LARGE_PAGE) /* Prepare new PTE value (turn access RW into DIRTY, then * add BUSY and ACCESSED) */ @@ -736,7 +736,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) BEGIN_FTR_SECTION cmpdi r9,0 /* check segment size */ bne 3f -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* Calc va and put it in r29 */ rldicr r29,r5,28,63-28 rldicl r3,r3,0,36 diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 784a400e078..dfd764896db 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -50,9 +50,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize) case MMU_PAGE_4K: va &= ~0xffful; va |= ssize << 8; - asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), - %2) - : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206) + asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) + : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206) : "memory"); break; default: @@ -61,9 +60,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize) va |= penc << 12; va |= ssize << 8; va |= 1; /* L */ - asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), - %2) - : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206) + asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) + : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206) : "memory"); break; } @@ -98,8 +96,8 @@ static inline void __tlbiel(unsigned long va, int psize, int ssize) static inline void tlbie(unsigned long va, int psize, int ssize, int local) { - unsigned int use_local = local && cpu_has_feature(CPU_FTR_TLBIEL); - int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE); + unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL); + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); if (use_local) use_local = mmu_psize_defs[psize].tlbiel; @@ -503,7 +501,7 @@ static void native_flush_hash_range(unsigned long number, int local) } pte_iterate_hashed_end(); } - if (cpu_has_feature(CPU_FTR_TLBIEL) && + if (mmu_has_feature(MMU_FTR_TLBIEL) && mmu_psize_defs[psize].tlbiel && local) { asm volatile("ptesync":::"memory"); for (i = 0; i < number; i++) { @@ -517,7 +515,7 @@ static void native_flush_hash_range(unsigned long number, int local) } asm volatile("ptesync":::"memory"); } else { - int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE); + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 58a022d0f46..26b2872b3d0 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -53,6 +53,7 @@ #include <asm/sections.h> #include <asm/spu.h> #include <asm/udbg.h> +#include <asm/code-patching.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -258,11 +259,11 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, for (; size >= 4; size -= 4, ++prop) { if (prop[0] == 40) { DBG("1T segment support detected\n"); - cur_cpu_spec->cpu_features |= CPU_FTR_1T_SEGMENT; + cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT; return 1; } } - cur_cpu_spec->cpu_features &= ~CPU_FTR_NO_SLBIE_B; + cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B; return 0; } @@ -288,7 +289,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, if (prop != NULL) { DBG("Page sizes from device-tree:\n"); size /= 4; - cur_cpu_spec->cpu_features &= ~(CPU_FTR_16M_PAGE); + cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE); while(size > 0) { unsigned int shift = prop[0]; unsigned int slbenc = prop[1]; @@ -316,7 +317,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, break; case 0x18: idx = MMU_PAGE_16M; - cur_cpu_spec->cpu_features |= CPU_FTR_16M_PAGE; + cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE; break; case 0x22: idx = MMU_PAGE_16G; @@ -411,7 +412,7 @@ static void __init htab_init_page_sizes(void) * Not in the device-tree, let's fallback on known size * list for 16M capable GP & GR */ - if (cpu_has_feature(CPU_FTR_16M_PAGE)) + if (mmu_has_feature(MMU_FTR_16M_PAGE)) memcpy(mmu_psize_defs, mmu_psize_defaults_gp, sizeof(mmu_psize_defaults_gp)); found: @@ -441,7 +442,7 @@ static void __init htab_init_page_sizes(void) mmu_vmalloc_psize = MMU_PAGE_64K; if (mmu_linear_psize == MMU_PAGE_4K) mmu_linear_psize = MMU_PAGE_64K; - if (cpu_has_feature(CPU_FTR_CI_LARGE_PAGE)) { + if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) { /* * Don't use 64k pages for ioremap on pSeries, since * that would stop us accessing the HEA ethernet. @@ -547,15 +548,7 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ -static inline void make_bl(unsigned int *insn_addr, void *func) -{ - unsigned long funcp = *((unsigned long *)func); - int offset = funcp - (unsigned long)insn_addr; - - *insn_addr = (unsigned int)(0x48000001 | (offset & 0x03fffffc)); - flush_icache_range((unsigned long)insn_addr, 4+ - (unsigned long)insn_addr); -} +#define FUNCTION_TEXT(A) ((*(unsigned long *)(A))) static void __init htab_finish_init(void) { @@ -570,16 +563,33 @@ static void __init htab_finish_init(void) extern unsigned int *ht64_call_hpte_remove; extern unsigned int *ht64_call_hpte_updatepp; - make_bl(ht64_call_hpte_insert1, ppc_md.hpte_insert); - make_bl(ht64_call_hpte_insert2, ppc_md.hpte_insert); - make_bl(ht64_call_hpte_remove, ppc_md.hpte_remove); - make_bl(ht64_call_hpte_updatepp, ppc_md.hpte_updatepp); + patch_branch(ht64_call_hpte_insert1, + FUNCTION_TEXT(ppc_md.hpte_insert), + BRANCH_SET_LINK); + patch_branch(ht64_call_hpte_insert2, + FUNCTION_TEXT(ppc_md.hpte_insert), + BRANCH_SET_LINK); + patch_branch(ht64_call_hpte_remove, + FUNCTION_TEXT(ppc_md.hpte_remove), + BRANCH_SET_LINK); + patch_branch(ht64_call_hpte_updatepp, + FUNCTION_TEXT(ppc_md.hpte_updatepp), + BRANCH_SET_LINK); + #endif /* CONFIG_PPC_HAS_HASH_64K */ - make_bl(htab_call_hpte_insert1, ppc_md.hpte_insert); - make_bl(htab_call_hpte_insert2, ppc_md.hpte_insert); - make_bl(htab_call_hpte_remove, ppc_md.hpte_remove); - make_bl(htab_call_hpte_updatepp, ppc_md.hpte_updatepp); + patch_branch(htab_call_hpte_insert1, + FUNCTION_TEXT(ppc_md.hpte_insert), + BRANCH_SET_LINK); + patch_branch(htab_call_hpte_insert2, + FUNCTION_TEXT(ppc_md.hpte_insert), + BRANCH_SET_LINK); + patch_branch(htab_call_hpte_remove, + FUNCTION_TEXT(ppc_md.hpte_remove), + BRANCH_SET_LINK); + patch_branch(htab_call_hpte_updatepp, + FUNCTION_TEXT(ppc_md.hpte_updatepp), + BRANCH_SET_LINK); } static void __init htab_initialize(void) @@ -598,7 +608,7 @@ static void __init htab_initialize(void) /* Initialize page sizes */ htab_init_page_sizes(); - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) { mmu_kernel_ssize = MMU_SEGSIZE_1T; mmu_highuser_ssize = MMU_SEGSIZE_1T; printk(KERN_INFO "Using 1TB segments\n"); @@ -739,7 +749,7 @@ void __init early_init_mmu(void) /* Initialize stab / SLB management except on iSeries */ - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) slb_initialize(); else if (!firmware_has_feature(FW_FEATURE_ISERIES)) stab_initialize(get_paca()->stab_real); @@ -756,7 +766,7 @@ void __cpuinit early_init_mmu_secondary(void) * in real mode on pSeries and we want a virtual address on * iSeries anyway */ - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) slb_initialize(); else stab_initialize(get_paca()->stab_addr); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9bb249c3046..0b9a5c1901b 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -529,7 +529,7 @@ static int __init hugetlbpage_init(void) { int psize; - if (!cpu_has_feature(CPU_FTR_16M_PAGE)) + if (!mmu_has_feature(MMU_FTR_16M_PAGE)) return -ENODEV; for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 2535828aa84..3bafc3deca6 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -20,9 +20,205 @@ #include <linux/idr.h> #include <linux/module.h> #include <linux/gfp.h> +#include <linux/slab.h> #include <asm/mmu_context.h> +#ifdef CONFIG_PPC_ICSWX +/* + * The processor and its L2 cache cause the icswx instruction to + * generate a COP_REQ transaction on PowerBus. The transaction has + * no address, and the processor does not perform an MMU access + * to authenticate the transaction. The command portion of the + * PowerBus COP_REQ transaction includes the LPAR_ID (LPID) and + * the coprocessor Process ID (PID), which the coprocessor compares + * to the authorized LPID and PID held in the coprocessor, to determine + * if the process is authorized to generate the transaction. + * The data of the COP_REQ transaction is 128-byte or less and is + * placed in cacheable memory on a 128-byte cache line boundary. + * + * The task to use a coprocessor should use use_cop() to allocate + * a coprocessor PID before executing icswx instruction. use_cop() + * also enables the coprocessor context switching. Drop_cop() is + * used to free the coprocessor PID. + * + * Example: + * Host Fabric Interface (HFI) is a PowerPC network coprocessor. + * Each HFI have multiple windows. Each HFI window serves as a + * network device sending to and receiving from HFI network. + * HFI immediate send function uses icswx instruction. The immediate + * send function allows small (single cache-line) packets be sent + * without using the regular HFI send FIFO and doorbell, which are + * much slower than immediate send. + * + * For each task intending to use HFI immediate send, the HFI driver + * calls use_cop() to obtain a coprocessor PID for the task. + * The HFI driver then allocate a free HFI window and save the + * coprocessor PID to the HFI window to allow the task to use the + * HFI window. + * + * The HFI driver repeatedly creates immediate send packets and + * issues icswx instruction to send data through the HFI window. + * The HFI compares the coprocessor PID in the CPU PID register + * to the PID held in the HFI window to determine if the transaction + * is allowed. + * + * When the task to release the HFI window, the HFI driver calls + * drop_cop() to release the coprocessor PID. + */ + +#define COP_PID_NONE 0 +#define COP_PID_MIN (COP_PID_NONE + 1) +#define COP_PID_MAX (0xFFFF) + +static DEFINE_SPINLOCK(mmu_context_acop_lock); +static DEFINE_IDA(cop_ida); + +void switch_cop(struct mm_struct *next) +{ + mtspr(SPRN_PID, next->context.cop_pid); + mtspr(SPRN_ACOP, next->context.acop); +} + +static int new_cop_pid(struct ida *ida, int min_id, int max_id, + spinlock_t *lock) +{ + int index; + int err; + +again: + if (!ida_pre_get(ida, GFP_KERNEL)) + return -ENOMEM; + + spin_lock(lock); + err = ida_get_new_above(ida, min_id, &index); + spin_unlock(lock); + + if (err == -EAGAIN) + goto again; + else if (err) + return err; + + if (index > max_id) { + spin_lock(lock); + ida_remove(ida, index); + spin_unlock(lock); + return -ENOMEM; + } + + return index; +} + +static void sync_cop(void *arg) +{ + struct mm_struct *mm = arg; + + if (mm == current->active_mm) + switch_cop(current->active_mm); +} + +/** + * Start using a coprocessor. + * @acop: mask of coprocessor to be used. + * @mm: The mm the coprocessor to associate with. Most likely current mm. + * + * Return a positive PID if successful. Negative errno otherwise. + * The returned PID will be fed to the coprocessor to determine if an + * icswx transaction is authenticated. + */ +int use_cop(unsigned long acop, struct mm_struct *mm) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_ICSWX)) + return -ENODEV; + + if (!mm || !acop) + return -EINVAL; + + /* We need to make sure mm_users doesn't change */ + down_read(&mm->mmap_sem); + spin_lock(mm->context.cop_lockp); + + if (mm->context.cop_pid == COP_PID_NONE) { + ret = new_cop_pid(&cop_ida, COP_PID_MIN, COP_PID_MAX, + &mmu_context_acop_lock); + if (ret < 0) + goto out; + + mm->context.cop_pid = ret; + } + mm->context.acop |= acop; + + sync_cop(mm); + + /* + * If this is a threaded process then there might be other threads + * running. We need to send an IPI to force them to pick up any + * change in PID and ACOP. + */ + if (atomic_read(&mm->mm_users) > 1) + smp_call_function(sync_cop, mm, 1); + + ret = mm->context.cop_pid; + +out: + spin_unlock(mm->context.cop_lockp); + up_read(&mm->mmap_sem); + + return ret; +} +EXPORT_SYMBOL_GPL(use_cop); + +/** + * Stop using a coprocessor. + * @acop: mask of coprocessor to be stopped. + * @mm: The mm the coprocessor associated with. + */ +void drop_cop(unsigned long acop, struct mm_struct *mm) +{ + int free_pid = COP_PID_NONE; + + if (!cpu_has_feature(CPU_FTR_ICSWX)) + return; + + if (WARN_ON_ONCE(!mm)) + return; + + /* We need to make sure mm_users doesn't change */ + down_read(&mm->mmap_sem); + spin_lock(mm->context.cop_lockp); + + mm->context.acop &= ~acop; + + if ((!mm->context.acop) && (mm->context.cop_pid != COP_PID_NONE)) { + free_pid = mm->context.cop_pid; + mm->context.cop_pid = COP_PID_NONE; + } + + sync_cop(mm); + + /* + * If this is a threaded process then there might be other threads + * running. We need to send an IPI to force them to pick up any + * change in PID and ACOP. + */ + if (atomic_read(&mm->mm_users) > 1) + smp_call_function(sync_cop, mm, 1); + + if (free_pid != COP_PID_NONE) { + spin_lock(&mmu_context_acop_lock); + ida_remove(&cop_ida, free_pid); + spin_unlock(&mmu_context_acop_lock); + } + + spin_unlock(mm->context.cop_lockp); + up_read(&mm->mmap_sem); +} +EXPORT_SYMBOL_GPL(drop_cop); + +#endif /* CONFIG_PPC_ICSWX */ + static DEFINE_SPINLOCK(mmu_context_lock); static DEFINE_IDA(mmu_context_ida); @@ -31,7 +227,6 @@ static DEFINE_IDA(mmu_context_ida); * Each segment contains 2^28 bytes. Each context maps 2^44 bytes, * so we can support 2^19-1 contexts (19 == 35 + 28 - 44). */ -#define NO_CONTEXT 0 #define MAX_CONTEXT ((1UL << 19) - 1) int __init_new_context(void) @@ -79,6 +274,16 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) slice_set_user_psize(mm, mmu_virtual_psize); subpage_prot_init_new_context(mm); mm->context.id = index; +#ifdef CONFIG_PPC_ICSWX + mm->context.cop_lockp = kmalloc(sizeof(spinlock_t), GFP_KERNEL); + if (!mm->context.cop_lockp) { + __destroy_context(index); + subpage_prot_free(mm); + mm->context.id = MMU_NO_CONTEXT; + return -ENOMEM; + } + spin_lock_init(mm->context.cop_lockp); +#endif /* CONFIG_PPC_ICSWX */ return 0; } @@ -93,7 +298,12 @@ EXPORT_SYMBOL_GPL(__destroy_context); void destroy_context(struct mm_struct *mm) { +#ifdef CONFIG_PPC_ICSWX + drop_cop(mm->context.acop, mm); + kfree(mm->context.cop_lockp); + mm->context.cop_lockp = NULL; +#endif /* CONFIG_PPC_ICSWX */ __destroy_context(mm->context.id); subpage_prot_free(mm); - mm->context.id = NO_CONTEXT; + mm->context.id = MMU_NO_CONTEXT; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index c0aab52da3a..336807de550 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -338,12 +338,14 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self, return NOTIFY_OK; switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu); stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu); @@ -407,7 +409,17 @@ void __init mmu_context_init(void) } else if (mmu_has_feature(MMU_FTR_TYPE_47x)) { first_context = 1; last_context = 65535; - } else { + } else +#ifdef CONFIG_PPC_BOOK3E_MMU + if (mmu_has_feature(MMU_FTR_TYPE_3E)) { + u32 mmucfg = mfspr(SPRN_MMUCFG); + u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK) + >> MMUCFG_PIDSIZE_SHIFT; + first_context = 1; + last_context = (1UL << (pid_bits + 1)) - 1; + } else +#endif + { first_context = 1; last_context = 255; } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 5ec1dad2a19..2164006fe17 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -311,14 +311,13 @@ EXPORT_SYMBOL_GPL(of_node_to_nid); static int __init find_min_common_depth(void) { int depth; - struct device_node *rtas_root; struct device_node *chosen; + struct device_node *root; const char *vec5; - rtas_root = of_find_node_by_path("/rtas"); - - if (!rtas_root) - return -1; + root = of_find_node_by_path("/rtas"); + if (!root) + root = of_find_node_by_path("/"); /* * This property is a set of 32-bit integers, each representing @@ -332,7 +331,7 @@ static int __init find_min_common_depth(void) * NUMA boundary and the following are progressively less significant * boundaries. There can be more than one level of NUMA. */ - distance_ref_points = of_get_property(rtas_root, + distance_ref_points = of_get_property(root, "ibm,associativity-reference-points", &distance_ref_points_depth); @@ -376,11 +375,11 @@ static int __init find_min_common_depth(void) distance_ref_points_depth = MAX_DISTANCE_REF_POINTS; } - of_node_put(rtas_root); + of_node_put(root); return depth; err: - of_node_put(rtas_root); + of_node_put(root); return -1; } @@ -1453,7 +1452,7 @@ int arch_update_cpu_topology(void) unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; struct sys_device *sysdev; - for_each_cpu_mask(cpu, cpu_associativity_changes_mask) { + for_each_cpu(cpu,&cpu_associativity_changes_mask) { vphn_get_associativity(cpu, associativity); nid = associativity_to_nid(associativity); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 8dc41c0157f..51f87956f8f 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -133,7 +133,15 @@ ioremap(phys_addr_t addr, unsigned long size) EXPORT_SYMBOL(ioremap); void __iomem * -ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags) +ioremap_wc(phys_addr_t addr, unsigned long size) +{ + return __ioremap_caller(addr, size, _PAGE_NO_CACHE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wc); + +void __iomem * +ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) { /* writeable implies dirty for kernel addresses */ if (flags & _PAGE_RW) @@ -152,7 +160,7 @@ ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags) return __ioremap_caller(addr, size, flags, __builtin_return_address(0)); } -EXPORT_SYMBOL(ioremap_flags); +EXPORT_SYMBOL(ioremap_prot); void __iomem * __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 88927a05cdc..6e595f6496d 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -255,7 +255,17 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, flags, caller); } -void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size, +void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size) +{ + unsigned long flags = _PAGE_NO_CACHE; + void *caller = __builtin_return_address(0); + + if (ppc_md.ioremap) + return ppc_md.ioremap(addr, size, flags, caller); + return __ioremap_caller(addr, size, flags, caller); +} + +void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) { void *caller = __builtin_return_address(0); @@ -311,7 +321,8 @@ void iounmap(volatile void __iomem *token) } EXPORT_SYMBOL(ioremap); -EXPORT_SYMBOL(ioremap_flags); +EXPORT_SYMBOL(ioremap_wc); +EXPORT_SYMBOL(ioremap_prot); EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(__ioremap_at); EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 1d98ecc8eec..e22276cb67a 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -24,6 +24,7 @@ #include <asm/firmware.h> #include <linux/compiler.h> #include <asm/udbg.h> +#include <asm/code-patching.h> extern void slb_allocate_realmode(unsigned long ea); @@ -166,7 +167,7 @@ static inline int esids_match(unsigned long addr1, unsigned long addr2) int esid_1t_count; /* System is not 1T segment size capable. */ - if (!cpu_has_feature(CPU_FTR_1T_SEGMENT)) + if (!mmu_has_feature(MMU_FTR_1T_SEGMENT)) return (GET_ESID(addr1) == GET_ESID(addr2)); esid_1t_count = (((addr1 >> SID_SHIFT_1T) != 0) + @@ -201,7 +202,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) */ hard_irq_disable(); offset = get_paca()->slb_cache_ptr; - if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B) && + if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) && offset <= SLB_CACHE_ENTRIES) { int i; asm volatile("isync" : : : "memory"); @@ -249,9 +250,8 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) static inline void patch_slb_encoding(unsigned int *insn_addr, unsigned int immed) { - *insn_addr = (*insn_addr & 0xffff0000) | immed; - flush_icache_range((unsigned long)insn_addr, 4+ - (unsigned long)insn_addr); + int insn = (*insn_addr & 0xffff0000) | immed; + patch_instruction(insn_addr, insn); } void slb_set_size(u16 size) diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 95ce3558169..ef653dc95b6 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -58,7 +58,7 @@ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 BEGIN_FTR_SECTION b slb_finish_load -END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T 1: @@ -87,7 +87,7 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) 6: BEGIN_FTR_SECTION b slb_finish_load -END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T 0: /* user address: proto-VSID = context << 15 | ESID. First check @@ -138,11 +138,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) ld r9,PACACONTEXTID(r13) BEGIN_FTR_SECTION cmpldi r10,0x1000 -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) rldimi r10,r9,USER_ESID_BITS,0 BEGIN_FTR_SECTION bge slb_finish_load_1T -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c index 446a01842a7..41e31642a86 100644 --- a/arch/powerpc/mm/stab.c +++ b/arch/powerpc/mm/stab.c @@ -243,7 +243,7 @@ void __init stabs_alloc(void) { int cpu; - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) return; for_each_possible_cpu(cpu) { diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c index aa46e9d1e77..19395f18b1d 100644 --- a/arch/powerpc/platforms/44x/iss4xx.c +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -87,7 +87,7 @@ static void __cpuinit smp_iss4xx_setup_cpu(int cpu) mpic_setup_this_cpu(); } -static void __cpuinit smp_iss4xx_kick_cpu(int cpu) +static int __cpuinit smp_iss4xx_kick_cpu(int cpu) { struct device_node *cpunode = of_get_cpu_node(cpu, NULL); const u64 *spin_table_addr_prop; @@ -104,7 +104,7 @@ static void __cpuinit smp_iss4xx_kick_cpu(int cpu) NULL); if (spin_table_addr_prop == NULL) { pr_err("CPU%d: Can't start, missing cpu-release-addr !\n", cpu); - return; + return -ENOENT; } /* Assume it's mapped as part of the linear mapping. This is a bit @@ -117,6 +117,8 @@ static void __cpuinit smp_iss4xx_kick_cpu(int cpu) smp_wmb(); spin_table[1] = __pa(start_secondary_47x); mb(); + + return 0; } static struct smp_ops_t iss_smp_ops = { diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c index cfc4b200998..9f09319352c 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c @@ -61,7 +61,7 @@ irq_to_pic_bit(unsigned int irq) static void cpld_mask_irq(struct irq_data *d) { - unsigned int cpld_irq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int cpld_irq = (unsigned int)irqd_to_hwirq(d); void __iomem *pic_mask = irq_to_pic_mask(cpld_irq); out_8(pic_mask, @@ -71,7 +71,7 @@ cpld_mask_irq(struct irq_data *d) static void cpld_unmask_irq(struct irq_data *d) { - unsigned int cpld_irq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int cpld_irq = (unsigned int)irqd_to_hwirq(d); void __iomem *pic_mask = irq_to_pic_mask(cpld_irq); out_8(pic_mask, @@ -97,7 +97,7 @@ cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp, status |= (ignore | mask); if (status == 0xff) - return NO_IRQ_IGNORE; + return NO_IRQ; cpld_irq = ffz(status) + offset; @@ -109,14 +109,14 @@ cpld_pic_cascade(unsigned int irq, struct irq_desc *desc) { irq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status, &cpld_regs->pci_mask); - if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { + if (irq != NO_IRQ) { generic_handle_irq(irq); return; } irq = cpld_pic_get_irq(8, MISC_IGNORE, &cpld_regs->misc_status, &cpld_regs->misc_mask); - if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { + if (irq != NO_IRQ) { generic_handle_irq(irq); return; } diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index 57a6a349e93..96f85e5e0cd 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -56,7 +56,7 @@ static void media5200_irq_unmask(struct irq_data *d) spin_lock_irqsave(&media5200_irq.lock, flags); val = in_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE); - val |= 1 << (MEDIA5200_IRQ_SHIFT + irq_map[d->irq].hwirq); + val |= 1 << (MEDIA5200_IRQ_SHIFT + irqd_to_hwirq(d)); out_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE, val); spin_unlock_irqrestore(&media5200_irq.lock, flags); } @@ -68,7 +68,7 @@ static void media5200_irq_mask(struct irq_data *d) spin_lock_irqsave(&media5200_irq.lock, flags); val = in_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE); - val &= ~(1 << (MEDIA5200_IRQ_SHIFT + irq_map[d->irq].hwirq)); + val &= ~(1 << (MEDIA5200_IRQ_SHIFT + irqd_to_hwirq(d))); out_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE, val); spin_unlock_irqrestore(&media5200_irq.lock, flags); } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c index 1dd15400f6f..1a9a4957057 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c @@ -157,48 +157,30 @@ static inline void io_be_clrbit(u32 __iomem *addr, int bitno) */ static void mpc52xx_extirq_mask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_clrbit(&intr->ctrl, 11 - l2irq); } static void mpc52xx_extirq_unmask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_setbit(&intr->ctrl, 11 - l2irq); } static void mpc52xx_extirq_ack(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_setbit(&intr->ctrl, 27-l2irq); } static int mpc52xx_extirq_set_type(struct irq_data *d, unsigned int flow_type) { u32 ctrl_reg, type; - int irq; - int l2irq; + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; void *handler = handle_level_irq; - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - - pr_debug("%s: irq=%x. l2=%d flow_type=%d\n", __func__, irq, l2irq, flow_type); + pr_debug("%s: irq=%x. l2=%d flow_type=%d\n", __func__, + (int) irqd_to_hwirq(d), l2irq, flow_type); switch (flow_type) { case IRQF_TRIGGER_HIGH: type = 0; break; @@ -237,23 +219,13 @@ static int mpc52xx_null_set_type(struct irq_data *d, unsigned int flow_type) static void mpc52xx_main_mask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_setbit(&intr->main_mask, 16 - l2irq); } static void mpc52xx_main_unmask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_clrbit(&intr->main_mask, 16 - l2irq); } @@ -270,23 +242,13 @@ static struct irq_chip mpc52xx_main_irqchip = { */ static void mpc52xx_periph_mask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_setbit(&intr->per_mask, 31 - l2irq); } static void mpc52xx_periph_unmask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_clrbit(&intr->per_mask, 31 - l2irq); } @@ -303,34 +265,19 @@ static struct irq_chip mpc52xx_periph_irqchip = { */ static void mpc52xx_sdma_mask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_setbit(&sdma->IntMask, l2irq); } static void mpc52xx_sdma_unmask(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; io_be_clrbit(&sdma->IntMask, l2irq); } static void mpc52xx_sdma_ack(struct irq_data *d) { - int irq; - int l2irq; - - irq = irq_map[d->irq].hwirq; - l2irq = irq & MPC52xx_IRQ_L2_MASK; - + int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK; out_be32(&sdma->IntPend, 1 << l2irq); } @@ -539,7 +486,7 @@ void __init mpc52xx_init_irq(void) unsigned int mpc52xx_get_irq(void) { u32 status; - int irq = NO_IRQ_IGNORE; + int irq; status = in_be32(&intr->enc_status); if (status & 0x00000400) { /* critical */ @@ -562,6 +509,8 @@ unsigned int mpc52xx_get_irq(void) } else { irq |= (MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET); } + } else { + return NO_IRQ; } return irq_linear_revmap(mpc52xx_irqhost, irq); diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 4a4eb6ffa12..8ccf9ed62fe 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -42,7 +42,7 @@ struct pq2ads_pci_pic { static void pq2ads_pci_mask_irq(struct irq_data *d) { struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d); - int irq = NUM_IRQS - virq_to_hw(d->irq) - 1; + int irq = NUM_IRQS - irqd_to_hwirq(d) - 1; if (irq != -1) { unsigned long flags; @@ -58,7 +58,7 @@ static void pq2ads_pci_mask_irq(struct irq_data *d) static void pq2ads_pci_unmask_irq(struct irq_data *d) { struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d); - int irq = NUM_IRQS - virq_to_hw(d->irq) - 1; + int irq = NUM_IRQS - irqd_to_hwirq(d) - 1; if (irq != -1) { unsigned long flags; @@ -112,16 +112,8 @@ static int pci_pic_host_map(struct irq_host *h, unsigned int virq, return 0; } -static void pci_host_unmap(struct irq_host *h, unsigned int virq) -{ - /* remove chip and handler */ - irq_set_chip_data(virq, NULL); - irq_set_chip(virq, NULL); -} - static struct irq_host_ops pci_pic_host_ops = { .map = pci_pic_host_map, - .unmap = pci_host_unmap, }; int __init pq2ads_pci_init_irq(void) diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 0d00ff9d05a..d6a93a10c0f 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -41,7 +41,7 @@ extern void __early_start(void); #define NUM_BOOT_ENTRY 8 #define SIZE_BOOT_ENTRY (NUM_BOOT_ENTRY * sizeof(u32)) -static void __init +static int __init smp_85xx_kick_cpu(int nr) { unsigned long flags; @@ -60,7 +60,7 @@ smp_85xx_kick_cpu(int nr) if (cpu_rel_addr == NULL) { printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr); - return; + return -ENOENT; } /* @@ -107,6 +107,8 @@ smp_85xx_kick_cpu(int nr) iounmap(bptr_vaddr); pr_debug("waited %d msecs for CPU #%d.\n", n, nr); + + return 0; } static void __init @@ -233,8 +235,10 @@ void __init mpc85xx_smp_init(void) smp_85xx_ops.message_pass = smp_mpic_message_pass; } - if (cpu_has_feature(CPU_FTR_DBELL)) - smp_85xx_ops.message_pass = doorbell_message_pass; + if (cpu_has_feature(CPU_FTR_DBELL)) { + smp_85xx_ops.message_pass = smp_muxed_ipi_message_pass; + smp_85xx_ops.cause_ipi = doorbell_cause_ipi; + } BUG_ON(!smp_85xx_ops.message_pass); diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index db864623b4a..12cb9bb2cc6 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -48,8 +48,6 @@ static struct socrates_fpga_irq_info fpga_irqs[SOCRATES_FPGA_NUM_IRQS] = { [8] = {0, IRQ_TYPE_LEVEL_HIGH}, }; -#define socrates_fpga_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) - static DEFINE_RAW_SPINLOCK(socrates_fpga_pic_lock); static void __iomem *socrates_fpga_pic_iobase; @@ -110,11 +108,9 @@ void socrates_fpga_pic_cascade(unsigned int irq, struct irq_desc *desc) static void socrates_fpga_pic_ack(struct irq_data *d) { unsigned long flags; - unsigned int hwirq, irq_line; + unsigned int irq_line, hwirq = irqd_to_hwirq(d); uint32_t mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - irq_line = fpga_irqs[hwirq].irq_line; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) @@ -127,12 +123,10 @@ static void socrates_fpga_pic_ack(struct irq_data *d) static void socrates_fpga_pic_mask(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); int irq_line; u32 mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - irq_line = fpga_irqs[hwirq].irq_line; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) @@ -145,12 +139,10 @@ static void socrates_fpga_pic_mask(struct irq_data *d) static void socrates_fpga_pic_mask_ack(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); int irq_line; u32 mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - irq_line = fpga_irqs[hwirq].irq_line; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) @@ -164,12 +156,10 @@ static void socrates_fpga_pic_mask_ack(struct irq_data *d) static void socrates_fpga_pic_unmask(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); int irq_line; u32 mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - irq_line = fpga_irqs[hwirq].irq_line; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) @@ -182,12 +172,10 @@ static void socrates_fpga_pic_unmask(struct irq_data *d) static void socrates_fpga_pic_eoi(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); int irq_line; u32 mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - irq_line = fpga_irqs[hwirq].irq_line; raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) @@ -201,12 +189,10 @@ static int socrates_fpga_pic_set_type(struct irq_data *d, unsigned int flow_type) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); int polarity; u32 mask; - hwirq = socrates_fpga_irq_to_hw(d->irq); - if (fpga_irqs[hwirq].type != IRQ_TYPE_NONE) return -EINVAL; diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c index 0beec7d5566..94594e58594 100644 --- a/arch/powerpc/platforms/86xx/gef_pic.c +++ b/arch/powerpc/platforms/86xx/gef_pic.c @@ -46,8 +46,6 @@ #define GEF_PIC_CPU0_MCP_MASK GEF_PIC_MCP_MASK(0) #define GEF_PIC_CPU1_MCP_MASK GEF_PIC_MCP_MASK(1) -#define gef_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) - static DEFINE_RAW_SPINLOCK(gef_pic_lock); @@ -113,11 +111,9 @@ void gef_pic_cascade(unsigned int irq, struct irq_desc *desc) static void gef_pic_mask(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); u32 mask; - hwirq = gef_irq_to_hw(d->irq); - raw_spin_lock_irqsave(&gef_pic_lock, flags); mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0)); mask &= ~(1 << hwirq); @@ -136,11 +132,9 @@ static void gef_pic_mask_ack(struct irq_data *d) static void gef_pic_unmask(struct irq_data *d) { unsigned long flags; - unsigned int hwirq; + unsigned int hwirq = irqd_to_hwirq(d); u32 mask; - hwirq = gef_irq_to_hw(d->irq); - raw_spin_lock_irqsave(&gef_pic_lock, flags); mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0)); mask |= (1 << hwirq); diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c index eacea0e3fcc..af09baee22c 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c @@ -56,7 +56,7 @@ smp_86xx_release_core(int nr) } -static void __init +static int __init smp_86xx_kick_cpu(int nr) { unsigned int save_vector; @@ -65,7 +65,7 @@ smp_86xx_kick_cpu(int nr) unsigned int *vector = (unsigned int *)(KERNELBASE + 0x100); if (nr < 0 || nr >= NR_CPUS) - return; + return -ENOENT; pr_debug("smp_86xx_kick_cpu: kick CPU #%d\n", nr); @@ -92,6 +92,8 @@ smp_86xx_kick_cpu(int nr) local_irq_restore(flags); pr_debug("wait CPU #%d for %d msecs.\n", nr, n); + + return 0; } diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index 9ecce995dd4..1e121088826 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -150,7 +150,7 @@ void __init mpc8xx_calibrate_decr(void) */ cpu = of_find_node_by_type(NULL, "cpu"); virq= irq_of_parse_and_map(cpu, 0); - irq = irq_map[virq].hwirq; + irq = virq_to_hw(virq); sys_tmr2 = immr_map(im_sit); out_be16(&sys_tmr2->sit_tbscr, ((1 << (7 - (irq/2))) << 8) | diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index f7b07720aa3..f970ca2b180 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -20,6 +20,7 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig" source "arch/powerpc/platforms/44x/Kconfig" source "arch/powerpc/platforms/40x/Kconfig" source "arch/powerpc/platforms/amigaone/Kconfig" +source "arch/powerpc/platforms/wsp/Kconfig" config KVM_GUEST bool "KVM Guest support" @@ -56,16 +57,19 @@ config UDBG_RTAS_CONSOLE depends on PPC_RTAS default n +config PPC_SMP_MUXED_IPI + bool + help + Select this opton if your platform supports SMP and your + interrupt controller provides less than 4 interrupts to each + 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 XICS - depends on PPC_PSERIES - bool - default y - config IPIC bool default n @@ -147,14 +151,27 @@ config PPC_970_NAP bool default n +config PPC_P7_NAP + bool + default n + config PPC_INDIRECT_IO bool select GENERIC_IOMAP - default n + +config PPC_INDIRECT_PIO + bool + select PPC_INDIRECT_IO + +config PPC_INDIRECT_MMIO + bool + select PPC_INDIRECT_IO + +config PPC_IO_WORKAROUNDS + bool config GENERIC_IOMAP bool - default n source "drivers/cpufreq/Kconfig" diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 111138c55f9..2165b65876f 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -73,6 +73,7 @@ config PPC_BOOK3S_64 config PPC_BOOK3E_64 bool "Embedded processors" select PPC_FPU # Make it a choice ? + select PPC_SMP_MUXED_IPI endchoice @@ -107,6 +108,10 @@ config POWER4 depends on PPC64 && PPC_BOOK3S def_bool y +config PPC_A2 + bool + depends on PPC_BOOK3E_64 + config TUNE_CELL bool "Optimize for Cell Broadband Engine" depends on PPC64 && PPC_BOOK3S @@ -174,6 +179,7 @@ config FSL_BOOKE config PPC_FSL_BOOK3E bool select FSL_EMB_PERFMON + select PPC_SMP_MUXED_IPI default y if FSL_BOOKE config PTE_64BIT @@ -226,6 +232,24 @@ config VSX If in doubt, say Y here. +config PPC_ICSWX + bool "Support for PowerPC icswx coprocessor instruction" + depends on POWER4 + default n + ---help--- + + This option enables kernel support for the PowerPC Initiate + Coprocessor Store Word (icswx) coprocessor instruction on POWER7 + or newer processors. + + This option is only useful if you have a processor that supports + the icswx coprocessor instruction. It does not have any effect + on processors without the icswx coprocessor instruction. + + This option slightly increases kernel memory usage. + + If in doubt, say N here. + config SPE bool "SPE Support" depends on E200 || (E500 && !PPC_E500MC) diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index fdb9f0b0d7a..73e2116cfee 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_PPC_CELL) += cell/ obj-$(CONFIG_PPC_PS3) += ps3/ obj-$(CONFIG_EMBEDDED6xx) += embedded6xx/ obj-$(CONFIG_AMIGAONE) += amigaone/ +obj-$(CONFIG_PPC_WSP) += wsp/ diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 81239ebed83..67d5009b4e8 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -6,7 +6,8 @@ config PPC_CELL_COMMON bool select PPC_CELL select PPC_DCR_MMIO - select PPC_INDIRECT_IO + select PPC_INDIRECT_PIO + select PPC_INDIRECT_MMIO select PPC_NATIVE select PPC_RTAS select IRQ_EDGE_EOI_HANDLER @@ -15,6 +16,7 @@ config PPC_CELL_NATIVE bool select PPC_CELL_COMMON select MPIC + select PPC_IO_WORKAROUNDS select IBM_NEW_EMAC_EMAC4 select IBM_NEW_EMAC_RGMII select IBM_NEW_EMAC_ZMII #test only diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 83fafe92264..a4a89350bcf 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -1,7 +1,7 @@ obj-$(CONFIG_PPC_CELL_COMMON) += cbe_regs.o interrupt.o pervasive.o obj-$(CONFIG_PPC_CELL_NATIVE) += iommu.o setup.o spider-pic.o \ - pmu.o io-workarounds.o spider-pci.o + pmu.o spider-pci.o obj-$(CONFIG_CBE_RAS) += ras.o obj-$(CONFIG_CBE_THERM) += cbe_thermal.o @@ -39,11 +39,10 @@ obj-y += celleb_setup.o \ celleb_pci.o celleb_scc_epci.o \ celleb_scc_pciex.o \ celleb_scc_uhc.o \ - io-workarounds.o spider-pci.o \ - beat.o beat_htab.o beat_hvCall.o \ - beat_interrupt.o beat_iommu.o + spider-pci.o beat.o beat_htab.o \ + beat_hvCall.o beat_interrupt.o \ + beat_iommu.o -obj-$(CONFIG_SMP) += beat_smp.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 diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index bb5ebf8fa80..ac06903e136 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -113,7 +113,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc) pr_devel("axon_msi: woff %x roff %x msi %x\n", write_offset, msic->read_offset, msi); - if (msi < NR_IRQS && irq_map[msi].host == msic->irq_host) { + if (msi < NR_IRQS && irq_get_chip_data(msi) == msic) { generic_handle_irq(msi); msic->fifo_virt[idx] = cpu_to_le32(0xffffffff); } else { @@ -320,6 +320,7 @@ static struct irq_chip msic_irq_chip = { static int msic_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hw) { + irq_set_chip_data(virq, h->host_data); irq_set_chip_and_handler(virq, &msic_irq_chip, handle_simple_irq); return 0; diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c index 4cb9e147c30..55015e1f693 100644 --- a/arch/powerpc/platforms/cell/beat_interrupt.c +++ b/arch/powerpc/platforms/cell/beat_interrupt.c @@ -148,16 +148,6 @@ static int beatic_pic_host_map(struct irq_host *h, unsigned int virq, } /* - * Update binding hardware IRQ number (hw) and Virtuql - * IRQ number (virq). This is called only once for a given mapping. - */ -static void beatic_pic_host_remap(struct irq_host *h, unsigned int virq, - irq_hw_number_t hw) -{ - beat_construct_and_connect_irq_plug(virq, hw); -} - -/* * Translate device-tree interrupt spec to irq_hw_number_t style (ulong), * to pass away to irq_create_mapping(). * @@ -184,7 +174,6 @@ static int beatic_pic_host_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops beatic_pic_host_ops = { .map = beatic_pic_host_map, - .remap = beatic_pic_host_remap, .unmap = beatic_pic_host_unmap, .xlate = beatic_pic_host_xlate, .match = beatic_pic_host_match, @@ -257,22 +246,6 @@ void __init beatic_init_IRQ(void) irq_set_default_host(beatic_host); } -#ifdef CONFIG_SMP - -/* Nullified to compile with SMP mode */ -void beatic_setup_cpu(int cpu) -{ -} - -void beatic_cause_IPI(int cpu, int mesg) -{ -} - -void beatic_request_IPIs(void) -{ -} -#endif /* CONFIG_SMP */ - void beatic_deinit_IRQ(void) { int i; diff --git a/arch/powerpc/platforms/cell/beat_interrupt.h b/arch/powerpc/platforms/cell/beat_interrupt.h index b470fd0051f..a7e52f91a07 100644 --- a/arch/powerpc/platforms/cell/beat_interrupt.h +++ b/arch/powerpc/platforms/cell/beat_interrupt.h @@ -24,9 +24,6 @@ extern void beatic_init_IRQ(void); extern unsigned int beatic_get_irq(void); -extern void beatic_cause_IPI(int cpu, int mesg); -extern void beatic_request_IPIs(void); -extern void beatic_setup_cpu(int); extern void beatic_deinit_IRQ(void); #endif diff --git a/arch/powerpc/platforms/cell/beat_smp.c b/arch/powerpc/platforms/cell/beat_smp.c deleted file mode 100644 index 26efc204c47..00000000000 --- a/arch/powerpc/platforms/cell/beat_smp.c +++ /dev/null @@ -1,124 +0,0 @@ -/* - * SMP support for Celleb platform. (Incomplete) - * - * (C) Copyright 2006 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/cell/smp.c: - * Dave Engebretsen, Peter Bergner, and - * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com - * Plus various changes from other IBM teams... - * - * 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/smp.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/threads.h> -#include <linux/cpu.h> - -#include <asm/irq.h> -#include <asm/smp.h> -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "beat_interrupt.h" - -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -/* - * The primary thread of each non-boot processor is recorded here before - * smp init. - */ -/* static cpumask_t of_spin_map; */ - -/** - * smp_startup_cpu() - start the given cpu - * - * At boot time, there is nothing to do for primary threads which were - * started from Open Firmware. For anything else, call RTAS with the - * appropriate start location. - * - * Returns: - * 0 - failure - * 1 - success - */ -static inline int __devinit smp_startup_cpu(unsigned int lcpu) -{ - return 0; -} - -static void smp_beatic_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - beatic_cause_IPI(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - beatic_cause_IPI(i, msg); - } - } -} - -static int __init smp_beatic_probe(void) -{ - return cpus_weight(cpu_possible_map); -} - -static void __devinit smp_beatic_setup_cpu(int cpu) -{ - beatic_setup_cpu(cpu); -} - -static void __devinit smp_celleb_kick_cpu(int nr) -{ - BUG_ON(nr < 0 || nr >= NR_CPUS); - - if (!smp_startup_cpu(nr)) - return; -} - -static int smp_celleb_cpu_bootable(unsigned int nr) -{ - return 1; -} -static struct smp_ops_t bpa_beatic_smp_ops = { - .message_pass = smp_beatic_message_pass, - .probe = smp_beatic_probe, - .kick_cpu = smp_celleb_kick_cpu, - .setup_cpu = smp_beatic_setup_cpu, - .cpu_bootable = smp_celleb_cpu_bootable, -}; - -/* This is called very early */ -void __init smp_init_celleb(void) -{ - DBG(" -> smp_init_celleb()\n"); - - smp_ops = &bpa_beatic_smp_ops; - - DBG(" <- smp_init_celleb()\n"); -} diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c index dbc338f187a..f3917e7a5b4 100644 --- a/arch/powerpc/platforms/cell/cbe_regs.c +++ b/arch/powerpc/platforms/cell/cbe_regs.c @@ -45,8 +45,8 @@ static struct cbe_thread_map unsigned int cbe_id; } cbe_thread_map[NR_CPUS]; -static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = CPU_MASK_NONE }; -static cpumask_t cbe_first_online_cpu = CPU_MASK_NONE; +static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = {CPU_BITS_NONE} }; +static cpumask_t cbe_first_online_cpu = { CPU_BITS_NONE }; static struct cbe_regs_map *cbe_find_map(struct device_node *np) { @@ -159,7 +159,8 @@ EXPORT_SYMBOL_GPL(cbe_cpu_to_node); u32 cbe_node_to_cpu(int node) { - return find_first_bit( (unsigned long *) &cbe_local_mask[node], sizeof(cpumask_t)); + return cpumask_first(&cbe_local_mask[node]); + } EXPORT_SYMBOL_GPL(cbe_node_to_cpu); @@ -268,9 +269,9 @@ void __init cbe_regs_init(void) thread->regs = map; thread->cbe_id = cbe_id; map->be_node = thread->be_node; - cpu_set(i, cbe_local_mask[cbe_id]); + cpumask_set_cpu(i, &cbe_local_mask[cbe_id]); if(thread->thread_id == 0) - cpu_set(i, cbe_first_online_cpu); + cpumask_set_cpu(i, &cbe_first_online_cpu); } } diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c index 404d1fc04d5..5822141aa63 100644 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ b/arch/powerpc/platforms/cell/celleb_pci.c @@ -41,7 +41,6 @@ #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> -#include "io-workarounds.h" #include "celleb_pci.h" #define MAX_PCI_DEVICES 32 @@ -320,7 +319,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node, size = 256; config = &private->fake_config[devno][fn]; - *config = alloc_maybe_bootmem(size, GFP_KERNEL); + *config = zalloc_maybe_bootmem(size, GFP_KERNEL); if (*config == NULL) { printk(KERN_ERR "PCI: " "not enough memory for fake configuration space\n"); @@ -331,7 +330,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node, size = sizeof(struct celleb_pci_resource); res = &private->res[devno][fn]; - *res = alloc_maybe_bootmem(size, GFP_KERNEL); + *res = zalloc_maybe_bootmem(size, GFP_KERNEL); if (*res == NULL) { printk(KERN_ERR "PCI: not enough memory for resource data space\n"); @@ -432,7 +431,7 @@ static int __init phb_set_bus_ranges(struct device_node *dev, static void __init celleb_alloc_private_mem(struct pci_controller *hose) { hose->private_data = - alloc_maybe_bootmem(sizeof(struct celleb_pci_private), + zalloc_maybe_bootmem(sizeof(struct celleb_pci_private), GFP_KERNEL); } @@ -469,18 +468,6 @@ static struct of_device_id celleb_phb_match[] __initdata = { }, }; -static int __init celleb_io_workaround_init(struct pci_controller *phb, - struct celleb_phb_spec *phb_spec) -{ - if (phb_spec->ops) { - iowa_register_bus(phb, phb_spec->ops, phb_spec->iowa_init, - phb_spec->iowa_data); - io_workaround_init(); - } - - return 0; -} - int __init celleb_setup_phb(struct pci_controller *phb) { struct device_node *dev = phb->dn; @@ -500,7 +487,11 @@ int __init celleb_setup_phb(struct pci_controller *phb) if (rc) return 1; - return celleb_io_workaround_init(phb, phb_spec); + 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) diff --git a/arch/powerpc/platforms/cell/celleb_pci.h b/arch/powerpc/platforms/cell/celleb_pci.h index 4cba1523ec5..a801fcc5f38 100644 --- a/arch/powerpc/platforms/cell/celleb_pci.h +++ b/arch/powerpc/platforms/cell/celleb_pci.h @@ -26,8 +26,9 @@ #include <asm/pci-bridge.h> #include <asm/prom.h> #include <asm/ppc-pci.h> +#include <asm/io-workarounds.h> -#include "io-workarounds.h" +struct iowa_bus; struct celleb_phb_spec { int (*setup)(struct device_node *, struct pci_controller *); diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c index e5384557977..d58d9bae4b9 100644 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ b/arch/powerpc/platforms/cell/celleb_setup.c @@ -128,10 +128,6 @@ static void __init celleb_setup_arch_beat(void) spu_management_ops = &spu_management_of_ops; #endif -#ifdef CONFIG_SMP - smp_init_celleb(); -#endif - celleb_setup_arch_common(); } diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 44cfd1bef89..6a58744d66c 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -196,8 +196,20 @@ static irqreturn_t iic_ipi_action(int irq, void *dev_id) { int ipi = (int)(long)dev_id; - smp_message_recv(ipi); - + switch(ipi) { + case PPC_MSG_CALL_FUNCTION: + generic_smp_call_function_interrupt(); + break; + case PPC_MSG_RESCHEDULE: + /* Upcoming sched hook */ + break; + case PPC_MSG_CALL_FUNC_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + case PPC_MSG_DEBUGGER_BREAK: + debug_ipi_action(0, NULL); + break; + } return IRQ_HANDLED; } static void iic_request_ipi(int ipi, const char *name) diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c index d31c594cfdf..51e290126bc 100644 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ b/arch/powerpc/platforms/cell/qpace_setup.c @@ -42,7 +42,6 @@ #include "interrupt.h" #include "pervasive.h" #include "ras.h" -#include "io-workarounds.h" static void qpace_show_cpuinfo(struct seq_file *m) { diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index fd57bfe00ed..c73cf4c43fc 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -51,11 +51,11 @@ #include <asm/udbg.h> #include <asm/mpic.h> #include <asm/cell-regs.h> +#include <asm/io-workarounds.h> #include "interrupt.h" #include "pervasive.h" #include "ras.h" -#include "io-workarounds.h" #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -136,8 +136,6 @@ static int __devinit cell_setup_phb(struct pci_controller *phb) iowa_register_bus(phb, &spiderpci_ops, &spiderpci_iowa_init, (void *)SPIDER_PCI_REG_BASE); - io_workaround_init(); - return 0; } diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index f774530075b..d176e6148e3 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -77,7 +77,7 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu) unsigned int pcpu; int start_cpu; - if (cpu_isset(lcpu, of_spin_map)) + if (cpumask_test_cpu(lcpu, &of_spin_map)) /* Already started by OF and sitting in spin loop */ return 1; @@ -103,27 +103,11 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu) return 1; } -static void smp_iic_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - iic_cause_IPI(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - iic_cause_IPI(i, msg); - } - } -} - static int __init smp_iic_probe(void) { iic_request_IPIs(); - return cpus_weight(cpu_possible_map); + return cpumask_weight(cpu_possible_mask); } static void __devinit smp_cell_setup_cpu(int cpu) @@ -137,12 +121,12 @@ static void __devinit smp_cell_setup_cpu(int cpu) mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER); } -static void __devinit smp_cell_kick_cpu(int nr) +static int __devinit smp_cell_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); if (!smp_startup_cpu(nr)) - return; + return -ENOENT; /* * The processor is currently spinning, waiting for the @@ -150,6 +134,8 @@ static void __devinit smp_cell_kick_cpu(int nr) * the processor will continue on to secondary_start */ paca[nr].cpu_start = 1; + + return 0; } static int smp_cell_cpu_bootable(unsigned int nr) @@ -166,7 +152,7 @@ static int smp_cell_cpu_bootable(unsigned int nr) return 1; } static struct smp_ops_t bpa_iic_smp_ops = { - .message_pass = smp_iic_message_pass, + .message_pass = iic_cause_IPI, .probe = smp_iic_probe, .kick_cpu = smp_cell_kick_cpu, .setup_cpu = smp_cell_setup_cpu, @@ -186,13 +172,12 @@ void __init smp_init_cell(void) if (cpu_has_feature(CPU_FTR_SMT)) { for_each_present_cpu(i) { if (cpu_thread_in_core(i) == 0) - cpu_set(i, of_spin_map); + cpumask_set_cpu(i, &of_spin_map); } - } else { - of_spin_map = cpu_present_map; - } + } else + cpumask_copy(&of_spin_map, cpu_present_mask); - cpu_clear(boot_cpuid, of_spin_map); + cpumask_clear_cpu(boot_cpuid, &of_spin_map); /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c index ca7731c0b59..f1f7878893f 100644 --- a/arch/powerpc/platforms/cell/spider-pci.c +++ b/arch/powerpc/platforms/cell/spider-pci.c @@ -27,8 +27,7 @@ #include <asm/ppc-pci.h> #include <asm/pci-bridge.h> - -#include "io-workarounds.h" +#include <asm/io-workarounds.h> #define SPIDER_PCI_DISABLE_PREFETCH diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index c5cf50e6b45..442c28c00f8 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -68,9 +68,9 @@ struct spider_pic { }; static struct spider_pic spider_pics[SPIDER_CHIP_COUNT]; -static struct spider_pic *spider_virq_to_pic(unsigned int virq) +static struct spider_pic *spider_irq_data_to_pic(struct irq_data *d) { - return irq_map[virq].host->host_data; + return irq_data_get_irq_chip_data(d); } static void __iomem *spider_get_irq_config(struct spider_pic *pic, @@ -81,24 +81,24 @@ static void __iomem *spider_get_irq_config(struct spider_pic *pic, static void spider_unmask_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); - void __iomem *cfg = spider_get_irq_config(pic, irq_map[d->irq].hwirq); + struct spider_pic *pic = spider_irq_data_to_pic(d); + void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d)); out_be32(cfg, in_be32(cfg) | 0x30000000u); } static void spider_mask_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); - void __iomem *cfg = spider_get_irq_config(pic, irq_map[d->irq].hwirq); + struct spider_pic *pic = spider_irq_data_to_pic(d); + void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d)); out_be32(cfg, in_be32(cfg) & ~0x30000000u); } static void spider_ack_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); - unsigned int src = irq_map[d->irq].hwirq; + struct spider_pic *pic = spider_irq_data_to_pic(d); + unsigned int src = irqd_to_hwirq(d); /* Reset edge detection logic if necessary */ @@ -116,8 +116,8 @@ static void spider_ack_irq(struct irq_data *d) static int spider_set_irq_type(struct irq_data *d, unsigned int type) { unsigned int sense = type & IRQ_TYPE_SENSE_MASK; - struct spider_pic *pic = spider_virq_to_pic(d->irq); - unsigned int hw = irq_map[d->irq].hwirq; + struct spider_pic *pic = spider_irq_data_to_pic(d); + unsigned int hw = irqd_to_hwirq(d); void __iomem *cfg = spider_get_irq_config(pic, hw); u32 old_mask; u32 ic; @@ -171,6 +171,7 @@ static struct irq_chip spider_pic = { static int spider_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hw) { + irq_set_chip_data(virq, h->host_data); irq_set_chip_and_handler(virq, &spider_pic, handle_level_irq); /* Set default irq type */ diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 65203857b0c..32cb4e66d2c 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx) * runqueue. The context will be rescheduled on the proper node * if it is timesliced or preempted. */ - ctx->cpus_allowed = current->cpus_allowed; + cpumask_copy(&ctx->cpus_allowed, tsk_cpus_allowed(current)); /* Save the current cpu id for spu interrupt routing. */ ctx->last_ran = raw_smp_processor_id(); diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c index 02cafecc90e..a800122e4dd 100644 --- a/arch/powerpc/platforms/chrp/smp.c +++ b/arch/powerpc/platforms/chrp/smp.c @@ -30,10 +30,12 @@ #include <asm/mpic.h> #include <asm/rtas.h> -static void __devinit smp_chrp_kick_cpu(int nr) +static int __devinit smp_chrp_kick_cpu(int nr) { *(unsigned long *)KERNELBASE = nr; asm volatile("dcbf 0,%0"::"r"(KERNELBASE):"memory"); + + return 0; } static void __devinit smp_chrp_setup_cpu(int cpu_nr) diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index 12aa62b6f22..f61a2dd96b9 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -48,7 +48,7 @@ static void flipper_pic_mask_and_ack(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); u32 mask = 1 << irq; @@ -59,7 +59,7 @@ static void flipper_pic_mask_and_ack(struct irq_data *d) static void flipper_pic_ack(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); /* this is at least needed for RSW */ @@ -68,7 +68,7 @@ static void flipper_pic_ack(struct irq_data *d) static void flipper_pic_mask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); clrbits32(io_base + FLIPPER_IMR, 1 << irq); @@ -76,7 +76,7 @@ static void flipper_pic_mask(struct irq_data *d) static void flipper_pic_unmask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); setbits32(io_base + FLIPPER_IMR, 1 << irq); @@ -107,12 +107,6 @@ static int flipper_pic_map(struct irq_host *h, unsigned int virq, return 0; } -static void flipper_pic_unmap(struct irq_host *h, unsigned int irq) -{ - irq_set_chip_data(irq, NULL); - irq_set_chip(irq, NULL); -} - static int flipper_pic_match(struct irq_host *h, struct device_node *np) { return 1; @@ -121,7 +115,6 @@ static int flipper_pic_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops flipper_irq_host_ops = { .map = flipper_pic_map, - .unmap = flipper_pic_unmap, .match = flipper_pic_match, }; diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 2bdddfc9d52..e4919170c6b 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -43,7 +43,7 @@ static void hlwd_pic_mask_and_ack(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); u32 mask = 1 << irq; @@ -53,7 +53,7 @@ static void hlwd_pic_mask_and_ack(struct irq_data *d) static void hlwd_pic_ack(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); out_be32(io_base + HW_BROADWAY_ICR, 1 << irq); @@ -61,7 +61,7 @@ static void hlwd_pic_ack(struct irq_data *d) static void hlwd_pic_mask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); clrbits32(io_base + HW_BROADWAY_IMR, 1 << irq); @@ -69,7 +69,7 @@ static void hlwd_pic_mask(struct irq_data *d) static void hlwd_pic_unmask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void __iomem *io_base = irq_data_get_irq_chip_data(d); setbits32(io_base + HW_BROADWAY_IMR, 1 << irq); @@ -100,15 +100,8 @@ static int hlwd_pic_map(struct irq_host *h, unsigned int virq, return 0; } -static void hlwd_pic_unmap(struct irq_host *h, unsigned int irq) -{ - irq_set_chip_data(irq, NULL); - irq_set_chip(irq, NULL); -} - static struct irq_host_ops hlwd_irq_host_ops = { .map = hlwd_pic_map, - .unmap = hlwd_pic_unmap, }; static unsigned int __hlwd_pic_get_irq(struct irq_host *h) diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig index e5bc9f75d47..b57cda3a081 100644 --- a/arch/powerpc/platforms/iseries/Kconfig +++ b/arch/powerpc/platforms/iseries/Kconfig @@ -1,7 +1,9 @@ config PPC_ISERIES bool "IBM Legacy iSeries" depends on PPC64 && PPC_BOOK3S - select PPC_INDIRECT_IO + select PPC_SMP_MUXED_IPI + select PPC_INDIRECT_PIO + select PPC_INDIRECT_MMIO select PPC_PCI_CHOICE if EXPERT menu "iSeries device drivers" diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index 32a56c6dfa7..29c02f36b32 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -31,6 +31,7 @@ #include <asm/thread_info.h> #include <asm/ptrace.h> #include <asm/cputable.h> +#include <asm/mmu.h> #include "exception.h" @@ -60,29 +61,31 @@ system_reset_iSeries: /* Spin on __secondary_hold_spinloop until it is updated by the boot cpu. */ /* In the UP case we'll yield() later, and we will not access the paca anyway */ #ifdef CONFIG_SMP -1: +iSeries_secondary_wait_paca: HMT_LOW LOAD_REG_ADDR(r23, __secondary_hold_spinloop) ld r23,0(r23) - sync - LOAD_REG_ADDR(r3,current_set) - sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r3,r3,r28 - addi r1,r3,THREAD_SIZE - subi r1,r1,STACK_FRAME_OVERHEAD - cmpwi 0,r23,0 /* Keep poking the Hypervisor until */ - bne 2f /* we're released */ - /* Let the Hypervisor know we are alive */ + cmpdi 0,r23,0 + bne 2f /* go on when the master is ready */ + + /* Keep poking the Hypervisor until we're released */ /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ lis r3,0x8002 rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ li r0,-1 /* r0=-1 indicates a Hypervisor call */ sc /* Invoke the hypervisor via a system call */ - b 1b -#endif + b iSeries_secondary_wait_paca 2: + HMT_MEDIUM + sync + + LOAD_REG_ADDR(r3, nr_cpu_ids) /* get number of pacas allocated */ + lwz r3,0(r3) /* nr_cpus= or NR_CPUS can limit */ + cmpld 0,r24,r3 /* is our cpu number allocated? */ + bge iSeries_secondary_yield /* no, yield forever */ + /* Load our paca now that it's been allocated */ LOAD_REG_ADDR(r13, paca) ld r13,0(r13) @@ -93,10 +96,24 @@ system_reset_iSeries: ori r23,r23,MSR_RI mtmsrd r23 /* RI on */ - HMT_LOW -#ifdef CONFIG_SMP +iSeries_secondary_smp_loop: lbz r23,PACAPROCSTART(r13) /* Test if this processor * should start */ + cmpwi 0,r23,0 + bne 3f /* go on when we are told */ + + HMT_LOW + /* Let the Hypervisor know we are alive */ + /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ + lis r3,0x8002 + rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ + li r0,-1 /* r0=-1 indicates a Hypervisor call */ + sc /* Invoke the hypervisor via a system call */ + mfspr r13,SPRN_SPRG_PACA /* Put r13 back ???? */ + b iSeries_secondary_smp_loop /* wait for signal to start */ + +3: + HMT_MEDIUM sync LOAD_REG_ADDR(r3,current_set) sldi r28,r24,3 /* get current_set[cpu#] */ @@ -104,27 +121,22 @@ system_reset_iSeries: addi r1,r3,THREAD_SIZE subi r1,r1,STACK_FRAME_OVERHEAD - cmpwi 0,r23,0 - beq iSeries_secondary_smp_loop /* Loop until told to go */ b __secondary_start /* Loop until told to go */ -iSeries_secondary_smp_loop: - /* Let the Hypervisor know we are alive */ - /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ - lis r3,0x8002 - rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ -#else /* CONFIG_SMP */ +#endif /* CONFIG_SMP */ + +iSeries_secondary_yield: /* Yield the processor. This is required for non-SMP kernels which are running on multi-threaded machines. */ + HMT_LOW lis r3,0x8000 rldicr r3,r3,32,15 /* r3 = (r3 << 32) & 0xffff000000000000 */ addi r3,r3,18 /* r3 = 0x8000000000000012 which is "yield" */ li r4,0 /* "yield timed" */ li r5,-1 /* "yield forever" */ -#endif /* CONFIG_SMP */ li r0,-1 /* r0=-1 indicates a Hypervisor call */ sc /* Invoke the hypervisor via a system call */ mfspr r13,SPRN_SPRG_PACA /* Put r13 back ???? */ - b 2b /* If SMP not configured, secondaries + b iSeries_secondary_yield /* If SMP not configured, secondaries * loop forever */ /*** ISeries-LPAR interrupt handlers ***/ @@ -157,7 +169,7 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE EXCEPTION_PROLOG_1(PACA_EXGEN) EXCEPTION_PROLOG_ISERIES_1 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) b data_access_common .do_stab_bolted_iSeries: diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c index 52a6889832c..b2103453eb0 100644 --- a/arch/powerpc/platforms/iseries/irq.c +++ b/arch/powerpc/platforms/iseries/irq.c @@ -42,7 +42,6 @@ #include "irq.h" #include "pci.h" #include "call_pci.h" -#include "smp.h" #ifdef CONFIG_PCI @@ -171,7 +170,7 @@ static void iseries_enable_IRQ(struct irq_data *d) { u32 bus, dev_id, function, mask; const u32 sub_bus = 0; - unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int rirq = (unsigned int)irqd_to_hwirq(d); /* The IRQ has already been locked by the caller */ bus = REAL_IRQ_TO_BUS(rirq); @@ -188,7 +187,7 @@ static unsigned int iseries_startup_IRQ(struct irq_data *d) { u32 bus, dev_id, function, mask; const u32 sub_bus = 0; - unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int rirq = (unsigned int)irqd_to_hwirq(d); bus = REAL_IRQ_TO_BUS(rirq); function = REAL_IRQ_TO_FUNC(rirq); @@ -234,7 +233,7 @@ static void iseries_shutdown_IRQ(struct irq_data *d) { u32 bus, dev_id, function, mask; const u32 sub_bus = 0; - unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int rirq = (unsigned int)irqd_to_hwirq(d); /* irq should be locked by the caller */ bus = REAL_IRQ_TO_BUS(rirq); @@ -257,7 +256,7 @@ static void iseries_disable_IRQ(struct irq_data *d) { u32 bus, dev_id, function, mask; const u32 sub_bus = 0; - unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int rirq = (unsigned int)irqd_to_hwirq(d); /* The IRQ has already been locked by the caller */ bus = REAL_IRQ_TO_BUS(rirq); @@ -271,7 +270,7 @@ static void iseries_disable_IRQ(struct irq_data *d) static void iseries_end_IRQ(struct irq_data *d) { - unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq; + unsigned int rirq = (unsigned int)irqd_to_hwirq(d); HvCallPci_eoi(REAL_IRQ_TO_BUS(rirq), REAL_IRQ_TO_SUBBUS(rirq), (REAL_IRQ_TO_IDSEL(rirq) << 4) + REAL_IRQ_TO_FUNC(rirq)); @@ -316,7 +315,7 @@ unsigned int iSeries_get_irq(void) #ifdef CONFIG_SMP if (get_lppaca()->int_dword.fields.ipi_cnt) { get_lppaca()->int_dword.fields.ipi_cnt = 0; - iSeries_smp_message_recv(); + smp_ipi_demux(); } #endif /* CONFIG_SMP */ if (hvlpevent_is_pending()) diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 2946ae10fbf..c25a0815c26 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -249,7 +249,7 @@ static unsigned long iSeries_process_mainstore_vpd(struct MemoryBlock *mb_array, unsigned long i; unsigned long mem_blocks = 0; - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) mem_blocks = iSeries_process_Regatta_mainstore_vpd(mb_array, max_entries); else @@ -634,7 +634,7 @@ static int __init iseries_probe(void) hpte_init_iSeries(); /* iSeries does not support 16M pages */ - cur_cpu_spec->cpu_features &= ~CPU_FTR_16M_PAGE; + cur_cpu_spec->mmu_features &= ~MMU_FTR_16M_PAGE; return 1; } @@ -685,6 +685,11 @@ void * __init iSeries_early_setup(void) powerpc_firmware_features |= FW_FEATURE_ISERIES; powerpc_firmware_features |= FW_FEATURE_LPAR; +#ifdef CONFIG_SMP + /* On iSeries we know we can never have more than 64 cpus */ + nr_cpu_ids = max(nr_cpu_ids, 64); +#endif + iSeries_fixup_klimit(); /* diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c index 6c6029914db..e3265adde5d 100644 --- a/arch/powerpc/platforms/iseries/smp.c +++ b/arch/powerpc/platforms/iseries/smp.c @@ -42,57 +42,23 @@ #include <asm/cputable.h> #include <asm/system.h> -#include "smp.h" - -static unsigned long iSeries_smp_message[NR_CPUS]; - -void iSeries_smp_message_recv(void) -{ - int cpu = smp_processor_id(); - int msg; - - if (num_online_cpus() < 2) - return; - - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &iSeries_smp_message[cpu])) - smp_message_recv(msg); -} - -static inline void smp_iSeries_do_message(int cpu, int msg) +static void smp_iSeries_cause_ipi(int cpu, unsigned long data) { - set_bit(msg, &iSeries_smp_message[cpu]); HvCall_sendIPI(&(paca[cpu])); } -static void smp_iSeries_message_pass(int target, int msg) -{ - int i; - - if (target < NR_CPUS) - smp_iSeries_do_message(target, msg); - else { - for_each_online_cpu(i) { - if ((target == MSG_ALL_BUT_SELF) && - (i == smp_processor_id())) - continue; - smp_iSeries_do_message(i, msg); - } - } -} - static int smp_iSeries_probe(void) { return cpumask_weight(cpu_possible_mask); } -static void smp_iSeries_kick_cpu(int nr) +static int smp_iSeries_kick_cpu(int nr) { BUG_ON((nr < 0) || (nr >= NR_CPUS)); /* Verify that our partition has a processor nr */ if (lppaca_of(nr).dyn_proc_status >= 2) - return; + return -ENOENT; /* The processor is currently spinning, waiting * for the cpu_start field to become non-zero @@ -100,6 +66,8 @@ static void smp_iSeries_kick_cpu(int nr) * continue on to secondary_start in iSeries_head.S */ paca[nr].cpu_start = 1; + + return 0; } static void __devinit smp_iSeries_setup_cpu(int nr) @@ -107,7 +75,8 @@ static void __devinit smp_iSeries_setup_cpu(int nr) } static struct smp_ops_t iSeries_smp_ops = { - .message_pass = smp_iSeries_message_pass, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = smp_iSeries_cause_ipi, .probe = smp_iSeries_probe, .kick_cpu = smp_iSeries_kick_cpu, .setup_cpu = smp_iSeries_setup_cpu, diff --git a/arch/powerpc/platforms/iseries/smp.h b/arch/powerpc/platforms/iseries/smp.h deleted file mode 100644 index d501f7de01e..00000000000 --- a/arch/powerpc/platforms/iseries/smp.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _PLATFORMS_ISERIES_SMP_H -#define _PLATFORMS_ISERIES_SMP_H - -extern void iSeries_smp_message_recv(void); - -#endif /* _PLATFORMS_ISERIES_SMP_H */ diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index 1e1a0873e1d..1afd10f6785 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -18,4 +18,13 @@ config PPC_PMAC64 select PPC_970_NAP default y - +config PPC_PMAC32_PSURGE + bool "Support for powersurge upgrade cards" if EXPERT + depends on SMP && PPC32 && PPC_PMAC + select PPC_SMP_MUXED_IPI + default y + help + The powersurge cpu boards can be used in the generation + of powermacs that have a socket for an upgradeable cpu card, + including the 7500, 8500, 9500, 9600. Support exists for + both dual and quad socket upgrade cards. diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 023f24086a0..360260d1352 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -84,7 +84,7 @@ static void __pmac_retrigger(unsigned int irq_nr) static void pmac_mask_and_ack_irq(struct irq_data *d) { - unsigned int src = irq_map[d->irq].hwirq; + unsigned int src = irqd_to_hwirq(d); unsigned long bit = 1UL << (src & 0x1f); int i = src >> 5; unsigned long flags; @@ -106,7 +106,7 @@ static void pmac_mask_and_ack_irq(struct irq_data *d) static void pmac_ack_irq(struct irq_data *d) { - unsigned int src = irq_map[d->irq].hwirq; + unsigned int src = irqd_to_hwirq(d); unsigned long bit = 1UL << (src & 0x1f); int i = src >> 5; unsigned long flags; @@ -152,7 +152,7 @@ static void __pmac_set_irq_mask(unsigned int irq_nr, int nokicklost) static unsigned int pmac_startup_irq(struct irq_data *d) { unsigned long flags; - unsigned int src = irq_map[d->irq].hwirq; + unsigned int src = irqd_to_hwirq(d); unsigned long bit = 1UL << (src & 0x1f); int i = src >> 5; @@ -169,7 +169,7 @@ static unsigned int pmac_startup_irq(struct irq_data *d) static void pmac_mask_irq(struct irq_data *d) { unsigned long flags; - unsigned int src = irq_map[d->irq].hwirq; + unsigned int src = irqd_to_hwirq(d); raw_spin_lock_irqsave(&pmac_pic_lock, flags); __clear_bit(src, ppc_cached_irq_mask); @@ -180,7 +180,7 @@ static void pmac_mask_irq(struct irq_data *d) static void pmac_unmask_irq(struct irq_data *d) { unsigned long flags; - unsigned int src = irq_map[d->irq].hwirq; + unsigned int src = irqd_to_hwirq(d); raw_spin_lock_irqsave(&pmac_pic_lock, flags); __set_bit(src, ppc_cached_irq_mask); @@ -193,7 +193,7 @@ static int pmac_retrigger(struct irq_data *d) unsigned long flags; raw_spin_lock_irqsave(&pmac_pic_lock, flags); - __pmac_retrigger(irq_map[d->irq].hwirq); + __pmac_retrigger(irqd_to_hwirq(d)); raw_spin_unlock_irqrestore(&pmac_pic_lock, flags); return 1; } @@ -239,15 +239,12 @@ static unsigned int pmac_pic_get_irq(void) unsigned long bits = 0; unsigned long flags; -#ifdef CONFIG_SMP - void psurge_smp_message_recv(void); - - /* IPI's are a hack on the powersurge -- Cort */ - if ( smp_processor_id() != 0 ) { - psurge_smp_message_recv(); - return NO_IRQ_IGNORE; /* ignore, already handled */ +#ifdef CONFIG_PPC_PMAC32_PSURGE + /* IPI's are a hack on the powersurge -- Cort */ + if (smp_processor_id() != 0) { + return psurge_secondary_virq; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ raw_spin_lock_irqsave(&pmac_pic_lock, flags); for (irq = max_real_irqs; (irq -= 32) >= 0; ) { int i = irq >> 5; diff --git a/arch/powerpc/platforms/powermac/pic.h b/arch/powerpc/platforms/powermac/pic.h deleted file mode 100644 index d622a8345aa..00000000000 --- a/arch/powerpc/platforms/powermac/pic.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __PPC_PLATFORMS_PMAC_PIC_H -#define __PPC_PLATFORMS_PMAC_PIC_H - -#include <linux/irq.h> - -extern struct irq_chip pmac_pic; - -extern void pmac_pic_init(void); -extern int pmac_get_irq(void); - -#endif /* __PPC_PLATFORMS_PMAC_PIC_H */ diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 20468f49aec..8327cce2bdb 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -33,6 +33,7 @@ extern void pmac_setup_pci_dma(void); extern void pmac_check_ht_link(void); extern void pmac_setup_smp(void); +extern int psurge_secondary_virq; extern void low_cpu_die(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index bc5f0dc6ae1..db092d7c4c5 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -70,7 +70,7 @@ static void (*pmac_tb_freeze)(int freeze); static u64 timebase; static int tb_req; -#ifdef CONFIG_PPC32 +#ifdef CONFIG_PPC_PMAC32_PSURGE /* * Powersurge (old powermac SMP) support. @@ -124,6 +124,10 @@ static volatile u32 __iomem *psurge_start; /* what sort of powersurge board we have */ static int psurge_type = PSURGE_NONE; +/* irq for secondary cpus to report */ +static struct irq_host *psurge_host; +int psurge_secondary_virq; + /* * Set and clear IPIs for powersurge. */ @@ -156,51 +160,52 @@ static inline void psurge_clr_ipi(int cpu) /* * On powersurge (old SMP powermac architecture) we don't have * separate IPIs for separate messages like openpic does. Instead - * we have a bitmap for each processor, where a 1 bit means that - * the corresponding message is pending for that processor. - * Ideally each cpu's entry would be in a different cache line. + * use the generic demux helpers * -- paulus. */ -static unsigned long psurge_smp_message[NR_CPUS]; - -void psurge_smp_message_recv(void) +static irqreturn_t psurge_ipi_intr(int irq, void *d) { - int cpu = smp_processor_id(); - int msg; + psurge_clr_ipi(smp_processor_id()); + smp_ipi_demux(); - /* clear interrupt */ - psurge_clr_ipi(cpu); - - if (num_online_cpus() < 2) - return; + return IRQ_HANDLED; +} - /* make sure there is a message there */ - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &psurge_smp_message[cpu])) - smp_message_recv(msg); +static void smp_psurge_cause_ipi(int cpu, unsigned long data) +{ + psurge_set_ipi(cpu); } -irqreturn_t psurge_primary_intr(int irq, void *d) +static int psurge_host_map(struct irq_host *h, unsigned int virq, + irq_hw_number_t hw) { - psurge_smp_message_recv(); - return IRQ_HANDLED; + irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_percpu_irq); + + return 0; } -static void smp_psurge_message_pass(int target, int msg) +struct irq_host_ops psurge_host_ops = { + .map = psurge_host_map, +}; + +static int psurge_secondary_ipi_init(void) { - int i; + int rc = -ENOMEM; - if (num_online_cpus() < 2) - return; + psurge_host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0, + &psurge_host_ops, 0); - for_each_online_cpu(i) { - if (target == MSG_ALL - || (target == MSG_ALL_BUT_SELF && i != smp_processor_id()) - || target == i) { - set_bit(msg, &psurge_smp_message[i]); - psurge_set_ipi(i); - } - } + if (psurge_host) + psurge_secondary_virq = irq_create_direct_mapping(psurge_host); + + if (psurge_secondary_virq) + rc = request_irq(psurge_secondary_virq, psurge_ipi_intr, + IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); + + if (rc) + pr_err("Failed to setup secondary cpu IPI\n"); + + return rc; } /* @@ -311,6 +316,9 @@ static int __init smp_psurge_probe(void) ncpus = 2; } + if (psurge_secondary_ipi_init()) + return 1; + psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); @@ -329,7 +337,7 @@ static int __init smp_psurge_probe(void) return ncpus; } -static void __init smp_psurge_kick_cpu(int nr) +static int __init smp_psurge_kick_cpu(int nr) { unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8; unsigned long a, flags; @@ -394,11 +402,13 @@ static void __init smp_psurge_kick_cpu(int nr) psurge_set_ipi(1); if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354); + + return 0; } static struct irqaction psurge_irqaction = { - .handler = psurge_primary_intr, - .flags = IRQF_DISABLED, + .handler = psurge_ipi_intr, + .flags = IRQF_DISABLED|IRQF_PERCPU, .name = "primary IPI", }; @@ -437,14 +447,15 @@ void __init smp_psurge_give_timebase(void) /* PowerSurge-style Macs */ struct smp_ops_t psurge_smp_ops = { - .message_pass = smp_psurge_message_pass, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = smp_psurge_cause_ipi, .probe = smp_psurge_probe, .kick_cpu = smp_psurge_kick_cpu, .setup_cpu = smp_psurge_setup_cpu, .give_timebase = smp_psurge_give_timebase, .take_timebase = smp_psurge_take_timebase, }; -#endif /* CONFIG_PPC32 - actually powersurge support */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ /* * Core 99 and later support @@ -791,14 +802,14 @@ static int __init smp_core99_probe(void) return ncpus; } -static void __devinit smp_core99_kick_cpu(int nr) +static int __devinit smp_core99_kick_cpu(int nr) { unsigned int save_vector; unsigned long target, flags; unsigned int *vector = (unsigned int *)(PAGE_OFFSET+0x100); if (nr < 0 || nr > 3) - return; + return -ENOENT; if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu", 0x346); @@ -830,6 +841,8 @@ static void __devinit smp_core99_kick_cpu(int nr) local_irq_restore(flags); if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347); + + return 0; } static void __devinit smp_core99_setup_cpu(int cpu_nr) @@ -1002,7 +1015,7 @@ void __init pmac_setup_smp(void) of_node_put(np); smp_ops = &core99_smp_ops; } -#ifdef CONFIG_PPC32 +#ifdef CONFIG_PPC_PMAC32_PSURGE else { /* We have to set bits in cpu_possible_mask here since the * secondary CPU(s) aren't in the device tree. Various @@ -1015,7 +1028,7 @@ void __init pmac_setup_smp(void) set_cpu_possible(cpu, true); smp_ops = &psurge_smp_ops; } -#endif /* CONFIG_PPC32 */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ #ifdef CONFIG_HOTPLUG_CPU ppc_md.cpu_die = pmac_cpu_die; diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index f2f6413b81d..600ed2c0ed5 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -197,7 +197,7 @@ static int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, result = irq_set_chip_data(*virq, pd); if (result) { - pr_debug("%s:%d: set_irq_chip_data failed\n", + pr_debug("%s:%d: irq_set_chip_data failed\n", __func__, __LINE__); goto fail_set; } @@ -659,11 +659,6 @@ static void __maybe_unused _dump_mask(struct ps3_private *pd, static void dump_bmp(struct ps3_private* pd) {}; #endif /* defined(DEBUG) */ -static void ps3_host_unmap(struct irq_host *h, unsigned int virq) -{ - irq_set_chip_data(virq, NULL); -} - static int ps3_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hwirq) { @@ -683,7 +678,6 @@ static int ps3_host_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops ps3_host_ops = { .map = ps3_host_map, - .unmap = ps3_host_unmap, .match = ps3_host_match, }; diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index 51ffde40af2..4c44794faac 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -39,7 +39,7 @@ #define MSG_COUNT 4 static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs); -static void do_message_pass(int target, int msg) +static void ps3_smp_message_pass(int cpu, int msg) { int result; unsigned int virq; @@ -49,28 +49,12 @@ static void do_message_pass(int target, int msg) return; } - virq = per_cpu(ps3_ipi_virqs, target)[msg]; + virq = per_cpu(ps3_ipi_virqs, cpu)[msg]; result = ps3_send_event_locally(virq); if (result) DBG("%s:%d: ps3_send_event_locally(%d, %d) failed" - " (%d)\n", __func__, __LINE__, target, msg, result); -} - -static void ps3_smp_message_pass(int target, int msg) -{ - int cpu; - - if (target < NR_CPUS) - do_message_pass(target, msg); - else if (target == MSG_ALL_BUT_SELF) { - for_each_online_cpu(cpu) - if (cpu != smp_processor_id()) - do_message_pass(cpu, msg); - } else { - for_each_online_cpu(cpu) - do_message_pass(cpu, msg); - } + " (%d)\n", __func__, __LINE__, cpu, msg, result); } static int ps3_smp_probe(void) diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 39a472e9e80..375a9f92158 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -197,7 +197,7 @@ static void spu_unmap(struct spu *spu) * The current HV requires the spu shadow regs to be mapped with the * PTE page protection bits set as read-only (PP=3). This implementation * uses the low level __ioremap() to bypass the page protection settings - * inforced by ioremap_flags() to get the needed PTE bits set for the + * inforced by ioremap_prot() to get the needed PTE bits set for the * shadow regs. */ @@ -214,7 +214,7 @@ static int __init setup_areas(struct spu *spu) goto fail_ioremap; } - spu->local_store = (__force void *)ioremap_flags(spu->local_store_phys, + spu->local_store = (__force void *)ioremap_prot(spu->local_store_phys, LS_SIZE, _PAGE_NO_CACHE); if (!spu->local_store) { diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 5b3da4b4ea7..71af4c5d6c0 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -3,7 +3,10 @@ config PPC_PSERIES bool "IBM pSeries & new (POWER5-based) iSeries" select MPIC select PCI_MSI - select XICS + select PPC_XICS + select PPC_ICP_NATIVE + select PPC_ICP_HV + select PPC_ICS_RTAS select PPC_I8259 select PPC_RTAS select PPC_RTAS_DAEMON @@ -47,6 +50,24 @@ config SCANLOG tristate "Scanlog dump interface" depends on RTAS_PROC && PPC_PSERIES +config IO_EVENT_IRQ + bool "IO Event Interrupt support" + depends on PPC_PSERIES + default y + help + Select this option, if you want to enable support for IO Event + interrupts. IO event interrupt is a mechanism provided by RTAS + to return information about hardware error and non-error events + which may need OS attention. RTAS returns events for multiple + event types and scopes. Device drivers can register their handlers + to receive events. + + This option will only enable the IO event platform code. You + will still need to enable or compile the actual drivers + that use this infrastruture to handle IO event interrupts. + + Say Y if you are unsure. + config LPARCFG bool "LPAR Configuration Data" depends on PPC_PSERIES || PPC_ISERIES diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index fc5237810ec..3556e402cbf 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -5,7 +5,6 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o mobility.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_XICS) += xics.o obj-$(CONFIG_SCANLOG) += scanlog.o obj-$(CONFIG_EEH) += eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_KEXEC) += kexec.o @@ -22,6 +21,7 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DTL) += dtl.o +obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o ifeq ($(CONFIG_PPC_PSERIES),y) obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index c371bc06434..e9190073bb9 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -52,10 +52,10 @@ static u8 dtl_event_mask = 0x7; /* - * Size of per-cpu log buffers. Default is just under 16 pages worth. + * Size of per-cpu log buffers. Firmware requires that the buffer does + * not cross a 4k boundary. */ -static int dtl_buf_entries = (16 * 85); - +static int dtl_buf_entries = N_DISPATCH_LOG; #ifdef CONFIG_VIRT_CPU_ACCOUNTING struct dtl_ring { @@ -151,7 +151,7 @@ static int dtl_start(struct dtl *dtl) /* Register our dtl buffer with the hypervisor. The HV expects the * buffer size to be passed in the second word of the buffer */ - ((u32 *)dtl->buf)[1] = dtl->buf_entries * sizeof(struct dtl_entry); + ((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES; hwcpu = get_hard_smp_processor_id(dtl->cpu); addr = __pa(dtl->buf); @@ -196,13 +196,15 @@ static int dtl_enable(struct dtl *dtl) long int rc; struct dtl_entry *buf = NULL; + if (!dtl_cache) + return -ENOMEM; + /* only allow one reader */ if (dtl->buf) return -EBUSY; n_entries = dtl_buf_entries; - buf = kmalloc_node(n_entries * sizeof(struct dtl_entry), - GFP_KERNEL, cpu_to_node(dtl->cpu)); + buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu)); if (!buf) { printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n", __func__, dtl->cpu); @@ -223,7 +225,7 @@ static int dtl_enable(struct dtl *dtl) spin_unlock(&dtl->lock); if (rc) - kfree(buf); + kmem_cache_free(dtl_cache, buf); return rc; } @@ -231,7 +233,7 @@ static void dtl_disable(struct dtl *dtl) { spin_lock(&dtl->lock); dtl_stop(dtl); - kfree(dtl->buf); + kmem_cache_free(dtl_cache, dtl->buf); dtl->buf = NULL; dtl->buf_entries = 0; spin_unlock(&dtl->lock); @@ -365,7 +367,7 @@ static int dtl_init(void) event_mask_file = debugfs_create_x8("dtl_event_mask", 0600, dtl_dir, &dtl_event_mask); - buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0600, + buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0400, dtl_dir, &dtl_buf_entries); if (!event_mask_file || !buf_entries_file) { diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 89649173d3a..46b55cf563e 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -93,6 +93,7 @@ static int ibm_slot_error_detail; static int ibm_get_config_addr_info; static int ibm_get_config_addr_info2; static int ibm_configure_bridge; +static int ibm_configure_pe; int eeh_subsystem_enabled; EXPORT_SYMBOL(eeh_subsystem_enabled); @@ -261,6 +262,8 @@ void eeh_slot_error_detail(struct pci_dn *pdn, int severity) pci_regs_buf[0] = 0; rtas_pci_enable(pdn, EEH_THAW_MMIO); + rtas_configure_bridge(pdn); + eeh_restore_bars(pdn); loglen = gather_pci_data(pdn, pci_regs_buf, EEH_PCI_REGS_LOG_LEN); rtas_slot_error_detail(pdn, severity, pci_regs_buf, loglen); @@ -448,6 +451,39 @@ void eeh_clear_slot (struct device_node *dn, int mode_flag) raw_spin_unlock_irqrestore(&confirm_error_lock, flags); } +void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset) +{ + struct device_node *dn; + + for_each_child_of_node(parent, dn) { + if (PCI_DN(dn)) { + + struct pci_dev *dev = PCI_DN(dn)->pcidev; + + if (dev && dev->driver) + *freset |= dev->needs_freset; + + __eeh_set_pe_freset(dn, freset); + } + } +} + +void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset) +{ + struct pci_dev *dev; + dn = find_device_pe(dn); + + /* Back up one, since config addrs might be shared */ + if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent)) + dn = dn->parent; + + dev = PCI_DN(dn)->pcidev; + if (dev) + *freset |= dev->needs_freset; + + __eeh_set_pe_freset(dn, freset); +} + /** * eeh_dn_check_failure - check if all 1's data is due to EEH slot freeze * @dn device node @@ -692,15 +728,24 @@ rtas_pci_slot_reset(struct pci_dn *pdn, int state) if (pdn->eeh_pe_config_addr) config_addr = pdn->eeh_pe_config_addr; - rc = rtas_call(ibm_set_slot_reset,4,1, NULL, + rc = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid), state); - if (rc) - printk (KERN_WARNING "EEH: Unable to reset the failed slot," - " (%d) #RST=%d dn=%s\n", - rc, state, pdn->node->full_name); + + /* Fundamental-reset not supported on this PE, try hot-reset */ + if (rc == -8 && state == 3) { + rc = rtas_call(ibm_set_slot_reset, 4, 1, NULL, + config_addr, + BUID_HI(pdn->phb->buid), + BUID_LO(pdn->phb->buid), 1); + if (rc) + printk(KERN_WARNING + "EEH: Unable to reset the failed slot," + " #RST=%d dn=%s\n", + rc, pdn->node->full_name); + } } /** @@ -736,18 +781,21 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat /** * rtas_set_slot_reset -- assert the pci #RST line for 1/4 second * @pdn: pci device node to be reset. - * - * Return 0 if success, else a non-zero value. */ static void __rtas_set_slot_reset(struct pci_dn *pdn) { - struct pci_dev *dev = pdn->pcidev; + unsigned int freset = 0; - /* Determine type of EEH reset required by device, - * default hot reset or fundamental reset - */ - if (dev && dev->needs_freset) + /* Determine type of EEH reset required for + * Partitionable Endpoint, a hot-reset (1) + * or a fundamental reset (3). + * A fundamental reset required by any device under + * Partitionable Endpoint trumps hot-reset. + */ + eeh_set_pe_freset(pdn->node, &freset); + + if (freset) rtas_pci_slot_reset(pdn, 3); else rtas_pci_slot_reset(pdn, 1); @@ -895,13 +943,20 @@ rtas_configure_bridge(struct pci_dn *pdn) { int config_addr; int rc; + int token; /* Use PE configuration address, if present */ config_addr = pdn->eeh_config_addr; if (pdn->eeh_pe_config_addr) config_addr = pdn->eeh_pe_config_addr; - rc = rtas_call(ibm_configure_bridge,3,1, NULL, + /* Use new configure-pe function, if supported */ + if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) + token = ibm_configure_pe; + else + token = ibm_configure_bridge; + + rc = rtas_call(token, 3, 1, NULL, config_addr, BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid)); @@ -1077,6 +1132,7 @@ void __init eeh_init(void) ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); ibm_configure_bridge = rtas_token ("ibm,configure-bridge"); + ibm_configure_pe = rtas_token("ibm,configure-pe"); if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) return; diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c index b8d70f5d9aa..1b6cb10589e 100644 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ b/arch/powerpc/platforms/pseries/eeh_driver.c @@ -328,7 +328,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event) struct pci_bus *frozen_bus; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; - const char *location, *pci_str, *drv_str; + const char *location, *pci_str, *drv_str, *bus_pci_str, *bus_drv_str; frozen_dn = find_device_pe(event->dn); if (!frozen_dn) { @@ -364,13 +364,8 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event) frozen_pdn = PCI_DN(frozen_dn); frozen_pdn->eeh_freeze_count++; - if (frozen_pdn->pcidev) { - pci_str = pci_name (frozen_pdn->pcidev); - drv_str = pcid_name (frozen_pdn->pcidev); - } else { - pci_str = eeh_pci_name(event->dev); - drv_str = pcid_name (event->dev); - } + pci_str = eeh_pci_name(event->dev); + drv_str = pcid_name(event->dev); if (frozen_pdn->eeh_freeze_count > EEH_MAX_ALLOWED_FREEZES) goto excess_failures; @@ -378,8 +373,17 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event) printk(KERN_WARNING "EEH: This PCI device has failed %d times in the last hour:\n", frozen_pdn->eeh_freeze_count); + + if (frozen_pdn->pcidev) { + bus_pci_str = pci_name(frozen_pdn->pcidev); + bus_drv_str = pcid_name(frozen_pdn->pcidev); + printk(KERN_WARNING + "EEH: Bus location=%s driver=%s pci addr=%s\n", + location, bus_drv_str, bus_pci_str); + } + printk(KERN_WARNING - "EEH: location=%s driver=%s pci addr=%s\n", + "EEH: Device location=%s driver=%s pci addr=%s\n", location, drv_str, pci_str); /* Walk the various device drivers attached to this slot through diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index ef8c45489e2..46f13a3c5d0 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -19,6 +19,7 @@ */ #include <linux/kernel.h> +#include <linux/interrupt.h> #include <linux/delay.h> #include <linux/cpu.h> #include <asm/system.h> @@ -28,7 +29,7 @@ #include <asm/machdep.h> #include <asm/vdso_datapage.h> #include <asm/pSeries_reconfig.h> -#include "xics.h" +#include <asm/xics.h> #include "plpar_wrappers.h" #include "offline_states.h" @@ -280,7 +281,7 @@ static int pseries_add_processor(struct device_node *np) } for_each_cpu(cpu, tmp) { - BUG_ON(cpumask_test_cpu(cpu, cpu_present_mask)); + BUG_ON(cpu_present(cpu)); set_cpu_present(cpu, true); set_hard_smp_processor_id(cpu, *intserv++); } diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c new file mode 100644 index 00000000000..c829e6067d5 --- /dev/null +++ b/arch/powerpc/platforms/pseries/io_event_irq.c @@ -0,0 +1,231 @@ +/* + * Copyright 2010 2011 Mark Nelson and Tseng-Hui (Frank) Lin, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/of.h> +#include <linux/list.h> +#include <linux/notifier.h> + +#include <asm/machdep.h> +#include <asm/rtas.h> +#include <asm/irq.h> +#include <asm/io_event_irq.h> + +#include "pseries.h" + +/* + * IO event interrupt is a mechanism provided by RTAS to return + * information about hardware error and non-error events. Device + * drivers can register their event handlers to receive events. + * Device drivers are expected to use atomic_notifier_chain_register() + * and atomic_notifier_chain_unregister() to register and unregister + * their event handlers. Since multiple IO event types and scopes + * share an IO event interrupt, the event handlers are called one + * by one until the IO event is claimed by one of the handlers. + * The event handlers are expected to return NOTIFY_OK if the + * event is handled by the event handler or NOTIFY_DONE if the + * event does not belong to the handler. + * + * Usage: + * + * Notifier function: + * #include <asm/io_event_irq.h> + * int event_handler(struct notifier_block *nb, unsigned long val, void *data) { + * p = (struct pseries_io_event_sect_data *) data; + * if (! is_my_event(p->scope, p->event_type)) return NOTIFY_DONE; + * : + * : + * return NOTIFY_OK; + * } + * struct notifier_block event_nb = { + * .notifier_call = event_handler, + * } + * + * Registration: + * atomic_notifier_chain_register(&pseries_ioei_notifier_list, &event_nb); + * + * Unregistration: + * atomic_notifier_chain_unregister(&pseries_ioei_notifier_list, &event_nb); + */ + +ATOMIC_NOTIFIER_HEAD(pseries_ioei_notifier_list); +EXPORT_SYMBOL_GPL(pseries_ioei_notifier_list); + +static int ioei_check_exception_token; + +/* pSeries event log format */ + +/* Two bytes ASCII section IDs */ +#define PSERIES_ELOG_SECT_ID_PRIV_HDR (('P' << 8) | 'H') +#define PSERIES_ELOG_SECT_ID_USER_HDR (('U' << 8) | 'H') +#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC (('P' << 8) | 'S') +#define PSERIES_ELOG_SECT_ID_EXTENDED_UH (('E' << 8) | 'H') +#define PSERIES_ELOG_SECT_ID_FAILING_MTMS (('M' << 8) | 'T') +#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC (('S' << 8) | 'S') +#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR (('D' << 8) | 'H') +#define PSERIES_ELOG_SECT_ID_FW_ERROR (('S' << 8) | 'W') +#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID (('L' << 8) | 'P') +#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID (('L' << 8) | 'R') +#define PSERIES_ELOG_SECT_ID_HMC_ID (('H' << 8) | 'M') +#define PSERIES_ELOG_SECT_ID_EPOW (('E' << 8) | 'P') +#define PSERIES_ELOG_SECT_ID_IO_EVENT (('I' << 8) | 'E') +#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') + +/* Vendor specific Platform Event Log Format, Version 6, section header */ +struct pseries_elog_section { + uint16_t id; /* 0x00 2-byte ASCII section ID */ + uint16_t length; /* 0x02 Section length in bytes */ + uint8_t version; /* 0x04 Section version */ + uint8_t subtype; /* 0x05 Section subtype */ + uint16_t creator_component; /* 0x06 Creator component ID */ + uint8_t data[]; /* 0x08 Start of section data */ +}; + +static char ioei_rtas_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; + +/** + * Find data portion of a specific section in RTAS extended event log. + * @elog: RTAS error/event log. + * @sect_id: secsion ID. + * + * Return: + * pointer to the section data of the specified section + * NULL if not found + */ +static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *elog, + uint16_t sect_id) +{ + struct rtas_ext_event_log_v6 *xelog = + (struct rtas_ext_event_log_v6 *) elog->buffer; + struct pseries_elog_section *sect; + unsigned char *p, *log_end; + + /* Check that we understand the format */ + if (elog->extended_log_length < sizeof(struct rtas_ext_event_log_v6) || + xelog->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG || + xelog->company_id != RTAS_V6EXT_COMPANY_ID_IBM) + return NULL; + + log_end = elog->buffer + elog->extended_log_length; + p = xelog->vendor_log; + while (p < log_end) { + sect = (struct pseries_elog_section *)p; + if (sect->id == sect_id) + return sect; + p += sect->length; + } + return NULL; +} + +/** + * Find the data portion of an IO Event section from event log. + * @elog: RTAS error/event log. + * + * Return: + * pointer to a valid IO event section data. NULL if not found. + */ +static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) +{ + struct pseries_elog_section *sect; + + /* We should only ever get called for io-event interrupts, but if + * we do get called for another type then something went wrong so + * make some noise about it. + * RTAS_TYPE_IO only exists in extended event log version 6 or later. + * No need to check event log version. + */ + if (unlikely(elog->type != RTAS_TYPE_IO)) { + printk_once(KERN_WARNING "io_event_irq: Unexpected event type %d", + elog->type); + return NULL; + } + + sect = find_xelog_section(elog, PSERIES_ELOG_SECT_ID_IO_EVENT); + if (unlikely(!sect)) { + printk_once(KERN_WARNING "io_event_irq: RTAS extended event " + "log does not contain an IO Event section. " + "Could be a bug in system firmware!\n"); + return NULL; + } + return (struct pseries_io_event *) §->data; +} + +/* + * PAPR: + * - check-exception returns the first found error or event and clear that + * error or event so it is reported once. + * - Each interrupt returns one event. If a plateform chooses to report + * multiple events through a single interrupt, it must ensure that the + * interrupt remains asserted until check-exception has been used to + * process all out-standing events for that interrupt. + * + * Implementation notes: + * - Events must be processed in the order they are returned. Hence, + * sequential in nature. + * - The owner of an event is determined by combinations of scope, + * event type, and sub-type. There is no easy way to pre-sort clients + * by scope or event type alone. For example, Torrent ISR route change + * event is reported with scope 0x00 (Not Applicatable) rather than + * 0x3B (Torrent-hub). It is better to let the clients to identify + * who owns the the event. + */ + +static irqreturn_t ioei_interrupt(int irq, void *dev_id) +{ + struct pseries_io_event *event; + int rtas_rc; + + for (;;) { + rtas_rc = rtas_call(ioei_check_exception_token, 6, 1, NULL, + RTAS_VECTOR_EXTERNAL_INTERRUPT, + virq_to_hw(irq), + RTAS_IO_EVENTS, 1 /* Time Critical */, + __pa(ioei_rtas_buf), + RTAS_DATA_BUF_SIZE); + if (rtas_rc != 0) + break; + + event = ioei_find_event((struct rtas_error_log *)ioei_rtas_buf); + if (!event) + continue; + + atomic_notifier_call_chain(&pseries_ioei_notifier_list, + 0, event); + } + return IRQ_HANDLED; +} + +static int __init ioei_init(void) +{ + struct device_node *np; + + ioei_check_exception_token = rtas_token("check-exception"); + if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE) { + pr_warning("IO Event IRQ not supported on this system !\n"); + return -ENODEV; + } + np = of_find_node_by_path("/event-sources/ibm,io-events"); + if (np) { + request_event_sources_irqs(np, ioei_interrupt, "IO_EVENT"); + of_node_put(np); + } else { + pr_err("io_event_irq: No ibm,io-events on system! " + "IO Event interrupt disabled.\n"); + return -ENODEV; + } + return 0; +} +machine_subsys_initcall(pseries, ioei_init); + diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 6d5412a18b2..48eec3b8702 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -730,16 +730,20 @@ static u64 dupe_ddw_if_kexec(struct pci_dev *dev, struct device_node *pdn) pcidn = PCI_DN(dn); direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); if (direct64) { - window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window) { + if (len < sizeof(struct dynamic_dma_window_prop)) { remove_ddw(pdn); } else { - window->device = pdn; - window->prop = direct64; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); - dma_addr = direct64->dma_base; + window = kzalloc(sizeof(*window), GFP_KERNEL); + if (!window) { + remove_ddw(pdn); + } else { + window->device = pdn; + window->prop = direct64; + spin_lock(&direct_window_list_lock); + list_add(&window->list, &direct_window_list); + spin_unlock(&direct_window_list_lock); + dma_addr = direct64->dma_base; + } } } @@ -833,7 +837,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct device_node *dn; const u32 *uninitialized_var(ddr_avail); struct direct_window *window; - struct property *uninitialized_var(win64); + struct property *win64; struct dynamic_dma_window_prop *ddwprop; mutex_lock(&direct_window_init_mutex); @@ -907,6 +911,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); + win64->length = sizeof(*ddwprop); if (!win64->name || !win64->value) { dev_info(&dev->dev, "couldn't allocate property name and value\n"); @@ -1024,10 +1029,10 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) if (!dev->dma_mask || !dma_supported(dev, dma_mask)) return -EIO; + pdev = to_pci_dev(dev); + /* only attempt to use a new window if 64-bit DMA is requested */ if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) { - pdev = to_pci_dev(dev); - dn = pci_device_to_OF_node(pdev); dev_dbg(dev, "node is %s\n", dn->full_name); @@ -1058,6 +1063,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) if (!ddw_enabled) { dev_info(dev, "Using 32-bit DMA via iommu\n"); set_dma_ops(dev, &dma_iommu_ops); + pci_dma_dev_setup_pSeriesLP(pdev); } *dev->dma_mask = dma_mask; diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 77d38a5e2ff..54cf3a4aa16 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -7,15 +7,18 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/kernel.h> +#include <linux/interrupt.h> + #include <asm/machdep.h> #include <asm/page.h> #include <asm/firmware.h> #include <asm/kexec.h> #include <asm/mpic.h> +#include <asm/xics.h> #include <asm/smp.h> #include "pseries.h" -#include "xics.h" #include "plpar_wrappers.h" static void pseries_kexec_cpu_down(int crash_shutdown, int secondary) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index ca5d5898d32..39e6e0a7b2f 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -329,6 +329,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, /* Make pHyp happy */ if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU)) hpte_r &= ~_PAGE_COHERENT; + if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N)) + flags |= H_COALESCE_CAND; lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot); if (unlikely(lpar_rc == H_PTEG_FULL)) { @@ -573,7 +575,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) unsigned long i, pix, rc; unsigned long flags = 0; struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); - int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE); + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); unsigned long param[9]; unsigned long va; unsigned long hash, index, shift, hidx, slot; @@ -771,3 +773,47 @@ out: local_irq_restore(flags); } #endif + +/** + * h_get_mpp + * H_GET_MPP hcall returns info in 7 parms + */ +int h_get_mpp(struct hvcall_mpp_data *mpp_data) +{ + int rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + rc = plpar_hcall9(H_GET_MPP, retbuf); + + mpp_data->entitled_mem = retbuf[0]; + mpp_data->mapped_mem = retbuf[1]; + + mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff; + mpp_data->pool_num = retbuf[2] & 0xffff; + + mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff; + mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff; + mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff; + + mpp_data->pool_size = retbuf[4]; + mpp_data->loan_request = retbuf[5]; + mpp_data->backing_mem = retbuf[6]; + + return rc; +} +EXPORT_SYMBOL(h_get_mpp); + +int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data) +{ + int rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = { 0 }; + + rc = plpar_hcall9(H_GET_MPP_X, retbuf); + + mpp_x_data->coalesced_bytes = retbuf[0]; + mpp_x_data->pool_coalesced_bytes = retbuf[1]; + mpp_x_data->pool_purr_cycles = retbuf[2]; + mpp_x_data->pool_spurr_cycles = retbuf[3]; + + return rc; +} diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index d9801117124..4bf21207d7d 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -270,31 +270,4 @@ static inline long plpar_put_term_char(unsigned long termno, unsigned long len, lbuf[1]); } -static inline long plpar_eoi(unsigned long xirr) -{ - return plpar_hcall_norets(H_EOI, xirr); -} - -static inline long plpar_cppr(unsigned long cppr) -{ - return plpar_hcall_norets(H_CPPR, cppr); -} - -static inline long plpar_ipi(unsigned long servernum, unsigned long mfrr) -{ - return plpar_hcall_norets(H_IPI, servernum, mfrr); -} - -static inline long plpar_xirr(unsigned long *xirr_ret, unsigned char cppr) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_XIRR, retbuf, cppr); - - *xirr_ret = retbuf[0]; - - return rc; -} - #endif /* _PSERIES_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index c55d7ad9c64..086d2ae4e06 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -122,7 +122,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) status = rtas_call(ras_check_exception_token, 6, 1, NULL, RTAS_VECTOR_EXTERNAL_INTERRUPT, - irq_map[irq].hwirq, + virq_to_hw(irq), RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS, critical, __pa(&ras_log_buf), rtas_get_error_log_max()); @@ -157,7 +157,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) status = rtas_call(ras_check_exception_token, 6, 1, NULL, RTAS_VECTOR_EXTERNAL_INTERRUPT, - irq_map[irq].hwirq, + virq_to_hw(irq), RTAS_INTERNAL_ERROR, 1 /*Time Critical */, __pa(&ras_log_buf), rtas_get_error_log_max()); @@ -227,7 +227,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) struct rtas_error_log *h, *errhdr = NULL; if (!VALID_FWNMI_BUFFER(regs->gpr[3])) { - printk(KERN_ERR "FWNMI: corrupt r3\n"); + printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]); return NULL; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6c42cfde841..593acceeff9 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -53,9 +53,9 @@ #include <asm/irq.h> #include <asm/time.h> #include <asm/nvram.h> -#include "xics.h" #include <asm/pmc.h> #include <asm/mpic.h> +#include <asm/xics.h> #include <asm/ppc-pci.h> #include <asm/i8259.h> #include <asm/udbg.h> @@ -205,6 +205,9 @@ static void __init pseries_mpic_init_IRQ(void) mpic_assign_isu(mpic, n, isuaddr); } + /* Setup top-level get_irq */ + ppc_md.get_irq = mpic_get_irq; + /* All ISUs are setup, complete initialization */ mpic_init(mpic); @@ -214,7 +217,7 @@ static void __init pseries_mpic_init_IRQ(void) static void __init pseries_xics_init_IRQ(void) { - xics_init_IRQ(); + xics_init(); pseries_setup_i8259_cascade(); } @@ -238,7 +241,6 @@ static void __init pseries_discover_pic(void) if (strstr(typep, "open-pic")) { pSeries_mpic_node = of_node_get(np); ppc_md.init_IRQ = pseries_mpic_init_IRQ; - ppc_md.get_irq = mpic_get_irq; setup_kexec_cpu_down_mpic(); smp_init_pseries_mpic(); return; @@ -276,6 +278,8 @@ static struct notifier_block pci_dn_reconfig_nb = { .notifier_call = pci_dn_reconfig_notifier, }; +struct kmem_cache *dtl_cache; + #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Allocate space for the dispatch trace log for all possible cpus @@ -287,18 +291,12 @@ static int alloc_dispatch_logs(void) int cpu, ret; struct paca_struct *pp; struct dtl_entry *dtl; - struct kmem_cache *dtl_cache; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; - dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, NULL); - if (!dtl_cache) { - pr_warn("Failed to create dispatch trace log buffer cache\n"); - pr_warn("Stolen time statistics will be unreliable\n"); + if (!dtl_cache) return 0; - } for_each_possible_cpu(cpu) { pp = &paca[cpu]; @@ -332,10 +330,27 @@ static int alloc_dispatch_logs(void) return 0; } - -early_initcall(alloc_dispatch_logs); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static inline int alloc_dispatch_logs(void) +{ + return 0; +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +static int alloc_dispatch_log_kmem_cache(void) +{ + dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, NULL); + if (!dtl_cache) { + pr_warn("Failed to create dispatch trace log buffer cache\n"); + pr_warn("Stolen time statistics will be unreliable\n"); + return 0; + } + + return alloc_dispatch_logs(); +} +early_initcall(alloc_dispatch_log_kmem_cache); + static void __init pSeries_setup_arch(void) { /* Discover PIC type and setup ppc_md accordingly */ @@ -403,6 +418,16 @@ static int pseries_set_xdabr(unsigned long dabr) #define CMO_CHARACTERISTICS_TOKEN 44 #define CMO_MAXLENGTH 1026 +void pSeries_coalesce_init(void) +{ + struct hvcall_mpp_x_data mpp_x_data; + + if (firmware_has_feature(FW_FEATURE_CMO) && !h_get_mpp_x(&mpp_x_data)) + powerpc_firmware_features |= FW_FEATURE_XCMO; + else + powerpc_firmware_features &= ~FW_FEATURE_XCMO; +} + /** * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions, * handle that here. (Stolen from parse_system_parameter_string) @@ -472,6 +497,7 @@ void pSeries_cmo_feature_init(void) pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP, CMO_SecPSP); powerpc_firmware_features |= FW_FEATURE_CMO; + pSeries_coalesce_init(); } else pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP, CMO_SecPSP); diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index a509c5292a6..fbffd7e47ab 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,10 +44,11 @@ #include <asm/mpic.h> #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> +#include <asm/mpic.h> +#include <asm/xics.h> #include "plpar_wrappers.h" #include "pseries.h" -#include "xics.h" #include "offline_states.h" @@ -136,7 +137,6 @@ out: return 1; } -#ifdef CONFIG_XICS static void __devinit smp_xics_setup_cpu(int cpu) { if (cpu != boot_cpuid) @@ -151,14 +151,13 @@ static void __devinit smp_xics_setup_cpu(int cpu) set_default_offline_state(cpu); #endif } -#endif /* CONFIG_XICS */ -static void __devinit smp_pSeries_kick_cpu(int nr) +static int __devinit smp_pSeries_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); if (!smp_startup_cpu(nr)) - return; + return -ENOENT; /* * The processor is currently spinning, waiting for the @@ -180,6 +179,8 @@ static void __devinit smp_pSeries_kick_cpu(int nr) "Ret= %ld\n", nr, rc); } #endif + + return 0; } static int smp_pSeries_cpu_bootable(unsigned int nr) @@ -197,23 +198,22 @@ static int smp_pSeries_cpu_bootable(unsigned int nr) return 1; } -#ifdef CONFIG_MPIC + static struct smp_ops_t pSeries_mpic_smp_ops = { .message_pass = smp_mpic_message_pass, .probe = smp_mpic_probe, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_mpic_setup_cpu, }; -#endif -#ifdef CONFIG_XICS + static struct smp_ops_t pSeries_xics_smp_ops = { - .message_pass = smp_xics_message_pass, - .probe = smp_xics_probe, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */ + .probe = xics_smp_probe, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_xics_setup_cpu, .cpu_bootable = smp_pSeries_cpu_bootable, }; -#endif /* This is called very early */ static void __init smp_init_pseries(void) @@ -245,14 +245,12 @@ static void __init smp_init_pseries(void) pr_debug(" <- smp_init_pSeries()\n"); } -#ifdef CONFIG_MPIC void __init smp_init_pseries_mpic(void) { smp_ops = &pSeries_mpic_smp_ops; smp_init_pseries(); } -#endif void __init smp_init_pseries_xics(void) { diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c deleted file mode 100644 index d6901334d66..00000000000 --- a/arch/powerpc/platforms/pseries/xics.c +++ /dev/null @@ -1,949 +0,0 @@ -/* - * arch/powerpc/platforms/pseries/xics.c - * - * Copyright 2000 IBM Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/types.h> -#include <linux/threads.h> -#include <linux/kernel.h> -#include <linux/irq.h> -#include <linux/smp.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/radix-tree.h> -#include <linux/cpu.h> -#include <linux/msi.h> -#include <linux/of.h> -#include <linux/percpu.h> - -#include <asm/firmware.h> -#include <asm/io.h> -#include <asm/pgtable.h> -#include <asm/smp.h> -#include <asm/rtas.h> -#include <asm/hvcall.h> -#include <asm/machdep.h> - -#include "xics.h" -#include "plpar_wrappers.h" - -static struct irq_host *xics_host; - -#define XICS_IPI 2 -#define XICS_IRQ_SPURIOUS 0 - -/* Want a priority other than 0. Various HW issues require this. */ -#define DEFAULT_PRIORITY 5 - -/* - * Mark IPIs as higher priority so we can take them inside interrupts that - * arent marked IRQF_DISABLED - */ -#define IPI_PRIORITY 4 - -/* The least favored priority */ -#define LOWEST_PRIORITY 0xFF - -/* The number of priorities defined above */ -#define MAX_NUM_PRIORITIES 3 - -static unsigned int default_server = 0xFF; -static unsigned int default_distrib_server = 0; -static unsigned int interrupt_server_size = 8; - -/* RTAS service tokens */ -static int ibm_get_xive; -static int ibm_set_xive; -static int ibm_int_on; -static int ibm_int_off; - -struct xics_cppr { - unsigned char stack[MAX_NUM_PRIORITIES]; - int index; -}; - -static DEFINE_PER_CPU(struct xics_cppr, xics_cppr); - -/* Direct hardware low level accessors */ - -/* The part of the interrupt presentation layer that we care about */ -struct xics_ipl { - union { - u32 word; - u8 bytes[4]; - } xirr_poll; - union { - u32 word; - u8 bytes[4]; - } xirr; - u32 dummy; - union { - u32 word; - u8 bytes[4]; - } qirr; -}; - -static struct xics_ipl __iomem *xics_per_cpu[NR_CPUS]; - -static inline unsigned int direct_xirr_info_get(void) -{ - int cpu = smp_processor_id(); - - return in_be32(&xics_per_cpu[cpu]->xirr.word); -} - -static inline void direct_xirr_info_set(unsigned int value) -{ - int cpu = smp_processor_id(); - - out_be32(&xics_per_cpu[cpu]->xirr.word, value); -} - -static inline void direct_cppr_info(u8 value) -{ - int cpu = smp_processor_id(); - - out_8(&xics_per_cpu[cpu]->xirr.bytes[0], value); -} - -static inline void direct_qirr_info(int n_cpu, u8 value) -{ - out_8(&xics_per_cpu[n_cpu]->qirr.bytes[0], value); -} - - -/* LPAR low level accessors */ - -static inline unsigned int lpar_xirr_info_get(unsigned char cppr) -{ - unsigned long lpar_rc; - unsigned long return_value; - - lpar_rc = plpar_xirr(&return_value, cppr); - if (lpar_rc != H_SUCCESS) - panic(" bad return code xirr - rc = %lx\n", lpar_rc); - return (unsigned int)return_value; -} - -static inline void lpar_xirr_info_set(unsigned int value) -{ - unsigned long lpar_rc; - - lpar_rc = plpar_eoi(value); - if (lpar_rc != H_SUCCESS) - panic("bad return code EOI - rc = %ld, value=%x\n", lpar_rc, - value); -} - -static inline void lpar_cppr_info(u8 value) -{ - unsigned long lpar_rc; - - lpar_rc = plpar_cppr(value); - if (lpar_rc != H_SUCCESS) - panic("bad return code cppr - rc = %lx\n", lpar_rc); -} - -static inline void lpar_qirr_info(int n_cpu , u8 value) -{ - unsigned long lpar_rc; - - lpar_rc = plpar_ipi(get_hard_smp_processor_id(n_cpu), value); - if (lpar_rc != H_SUCCESS) - panic("bad return code qirr - rc = %lx\n", lpar_rc); -} - - -/* Interface to generic irq subsystem */ - -#ifdef CONFIG_SMP -/* - * For the moment we only implement delivery to all cpus or one cpu. - * - * If the requested affinity is cpu_all_mask, we set global affinity. - * If not we set it to the first cpu in the mask, even if multiple cpus - * are set. This is so things like irqbalance (which set core and package - * wide affinities) do the right thing. - */ -static int get_irq_server(unsigned int virq, const struct cpumask *cpumask, - unsigned int strict_check) -{ - - if (!distribute_irqs) - return default_server; - - if (!cpumask_subset(cpu_possible_mask, cpumask)) { - int server = cpumask_first_and(cpu_online_mask, cpumask); - - if (server < nr_cpu_ids) - return get_hard_smp_processor_id(server); - - if (strict_check) - return -1; - } - - /* - * Workaround issue with some versions of JS20 firmware that - * deliver interrupts to cpus which haven't been started. This - * happens when using the maxcpus= boot option. - */ - if (cpumask_equal(cpu_online_mask, cpu_present_mask)) - return default_distrib_server; - - return default_server; -} -#else -#define get_irq_server(virq, cpumask, strict_check) (default_server) -#endif - -static void xics_unmask_irq(struct irq_data *d) -{ - unsigned int hwirq; - int call_status; - int server; - - pr_devel("xics: unmask virq %d\n", d->irq); - - hwirq = (unsigned int)irq_map[d->irq].hwirq; - pr_devel(" -> map to hwirq 0x%x\n", hwirq); - if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS) - return; - - server = get_irq_server(d->irq, d->affinity, 0); - - call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hwirq, server, - DEFAULT_PRIORITY); - if (call_status != 0) { - printk(KERN_ERR - "%s: ibm_set_xive irq %u server %x returned %d\n", - __func__, hwirq, server, call_status); - return; - } - - /* Now unmask the interrupt (often a no-op) */ - call_status = rtas_call(ibm_int_on, 1, 1, NULL, hwirq); - if (call_status != 0) { - printk(KERN_ERR "%s: ibm_int_on irq=%u returned %d\n", - __func__, hwirq, call_status); - return; - } -} - -static unsigned int xics_startup(struct irq_data *d) -{ - /* - * The generic MSI code returns with the interrupt disabled on the - * card, using the MSI mask bits. Firmware doesn't appear to unmask - * at that level, so we do it here by hand. - */ - if (d->msi_desc) - unmask_msi_irq(d); - - /* unmask it */ - xics_unmask_irq(d); - return 0; -} - -static void xics_mask_real_irq(unsigned int hwirq) -{ - int call_status; - - if (hwirq == XICS_IPI) - return; - - call_status = rtas_call(ibm_int_off, 1, 1, NULL, hwirq); - if (call_status != 0) { - printk(KERN_ERR "%s: ibm_int_off irq=%u returned %d\n", - __func__, hwirq, call_status); - return; - } - - /* Have to set XIVE to 0xff to be able to remove a slot */ - call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hwirq, - default_server, 0xff); - if (call_status != 0) { - printk(KERN_ERR "%s: ibm_set_xive(0xff) irq=%u returned %d\n", - __func__, hwirq, call_status); - return; - } -} - -static void xics_mask_irq(struct irq_data *d) -{ - unsigned int hwirq; - - pr_devel("xics: mask virq %d\n", d->irq); - - hwirq = (unsigned int)irq_map[d->irq].hwirq; - if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS) - return; - xics_mask_real_irq(hwirq); -} - -static void xics_mask_unknown_vec(unsigned int vec) -{ - printk(KERN_ERR "Interrupt %u (real) is invalid, disabling it.\n", vec); - xics_mask_real_irq(vec); -} - -static inline unsigned int xics_xirr_vector(unsigned int xirr) -{ - /* - * The top byte is the old cppr, to be restored on EOI. - * The remaining 24 bits are the vector. - */ - return xirr & 0x00ffffff; -} - -static void push_cppr(unsigned int vec) -{ - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - - if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1)) - return; - - if (vec == XICS_IPI) - os_cppr->stack[++os_cppr->index] = IPI_PRIORITY; - else - os_cppr->stack[++os_cppr->index] = DEFAULT_PRIORITY; -} - -static unsigned int xics_get_irq_direct(void) -{ - unsigned int xirr = direct_xirr_info_get(); - unsigned int vec = xics_xirr_vector(xirr); - unsigned int irq; - - if (vec == XICS_IRQ_SPURIOUS) - return NO_IRQ; - - irq = irq_radix_revmap_lookup(xics_host, vec); - if (likely(irq != NO_IRQ)) { - push_cppr(vec); - return irq; - } - - /* We don't have a linux mapping, so have rtas mask it. */ - xics_mask_unknown_vec(vec); - - /* We might learn about it later, so EOI it */ - direct_xirr_info_set(xirr); - return NO_IRQ; -} - -static unsigned int xics_get_irq_lpar(void) -{ - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - unsigned int xirr = lpar_xirr_info_get(os_cppr->stack[os_cppr->index]); - unsigned int vec = xics_xirr_vector(xirr); - unsigned int irq; - - if (vec == XICS_IRQ_SPURIOUS) - return NO_IRQ; - - irq = irq_radix_revmap_lookup(xics_host, vec); - if (likely(irq != NO_IRQ)) { - push_cppr(vec); - return irq; - } - - /* We don't have a linux mapping, so have RTAS mask it. */ - xics_mask_unknown_vec(vec); - - /* We might learn about it later, so EOI it */ - lpar_xirr_info_set(xirr); - return NO_IRQ; -} - -static unsigned char pop_cppr(void) -{ - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - - if (WARN_ON(os_cppr->index < 1)) - return LOWEST_PRIORITY; - - return os_cppr->stack[--os_cppr->index]; -} - -static void xics_eoi_direct(struct irq_data *d) -{ - unsigned int hwirq = (unsigned int)irq_map[d->irq].hwirq; - - iosync(); - direct_xirr_info_set((pop_cppr() << 24) | hwirq); -} - -static void xics_eoi_lpar(struct irq_data *d) -{ - unsigned int hwirq = (unsigned int)irq_map[d->irq].hwirq; - - iosync(); - lpar_xirr_info_set((pop_cppr() << 24) | hwirq); -} - -static int -xics_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool force) -{ - unsigned int hwirq; - int status; - int xics_status[2]; - int irq_server; - - hwirq = (unsigned int)irq_map[d->irq].hwirq; - if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS) - return -1; - - status = rtas_call(ibm_get_xive, 1, 3, xics_status, hwirq); - - if (status) { - printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", - __func__, hwirq, status); - return -1; - } - - irq_server = get_irq_server(d->irq, cpumask, 1); - if (irq_server == -1) { - char cpulist[128]; - cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); - printk(KERN_WARNING - "%s: No online cpus in the mask %s for irq %d\n", - __func__, cpulist, d->irq); - return -1; - } - - status = rtas_call(ibm_set_xive, 3, 1, NULL, - hwirq, irq_server, xics_status[1]); - - if (status) { - printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", - __func__, hwirq, status); - return -1; - } - - return 0; -} - -static struct irq_chip xics_pic_direct = { - .name = "XICS", - .irq_startup = xics_startup, - .irq_mask = xics_mask_irq, - .irq_unmask = xics_unmask_irq, - .irq_eoi = xics_eoi_direct, - .irq_set_affinity = xics_set_affinity -}; - -static struct irq_chip xics_pic_lpar = { - .name = "XICS", - .irq_startup = xics_startup, - .irq_mask = xics_mask_irq, - .irq_unmask = xics_unmask_irq, - .irq_eoi = xics_eoi_lpar, - .irq_set_affinity = xics_set_affinity -}; - - -/* Interface to arch irq controller subsystem layer */ - -/* Points to the irq_chip we're actually using */ -static struct irq_chip *xics_irq_chip; - -static int xics_host_match(struct irq_host *h, struct device_node *node) -{ - /* IBM machines have interrupt parents of various funky types for things - * like vdevices, events, etc... The trick we use here is to match - * everything here except the legacy 8259 which is compatible "chrp,iic" - */ - return !of_device_is_compatible(node, "chrp,iic"); -} - -static int xics_host_map(struct irq_host *h, unsigned int virq, - irq_hw_number_t hw) -{ - pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); - - /* Insert the interrupt mapping into the radix tree for fast lookup */ - irq_radix_revmap_insert(xics_host, virq, hw); - - irq_set_status_flags(virq, IRQ_LEVEL); - irq_set_chip_and_handler(virq, xics_irq_chip, handle_fasteoi_irq); - return 0; -} - -static int xics_host_xlate(struct irq_host *h, struct device_node *ct, - const u32 *intspec, unsigned int intsize, - irq_hw_number_t *out_hwirq, unsigned int *out_flags) - -{ - /* Current xics implementation translates everything - * to level. It is not technically right for MSIs but this - * is irrelevant at this point. We might get smarter in the future - */ - *out_hwirq = intspec[0]; - *out_flags = IRQ_TYPE_LEVEL_LOW; - - return 0; -} - -static struct irq_host_ops xics_host_ops = { - .match = xics_host_match, - .map = xics_host_map, - .xlate = xics_host_xlate, -}; - -static void __init xics_init_host(void) -{ - if (firmware_has_feature(FW_FEATURE_LPAR)) - xics_irq_chip = &xics_pic_lpar; - else - xics_irq_chip = &xics_pic_direct; - - xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, &xics_host_ops, - XICS_IRQ_SPURIOUS); - BUG_ON(xics_host == NULL); - irq_set_default_host(xics_host); -} - - -/* Inter-processor interrupt support */ - -#ifdef CONFIG_SMP -/* - * XICS only has a single IPI, so encode the messages per CPU - */ -static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message); - -static inline void smp_xics_do_message(int cpu, int msg) -{ - unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - - set_bit(msg, tgt); - mb(); - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_qirr_info(cpu, IPI_PRIORITY); - else - direct_qirr_info(cpu, IPI_PRIORITY); -} - -void smp_xics_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - smp_xics_do_message(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - smp_xics_do_message(i, msg); - } - } -} - -static irqreturn_t xics_ipi_dispatch(int cpu) -{ - unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - - mb(); /* order mmio clearing qirr */ - while (*tgt) { - if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt)) { - smp_message_recv(PPC_MSG_CALL_FUNCTION); - } - if (test_and_clear_bit(PPC_MSG_RESCHEDULE, tgt)) { - smp_message_recv(PPC_MSG_RESCHEDULE); - } - if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, tgt)) { - smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE); - } -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) - if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, tgt)) { - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); - } -#endif - } - return IRQ_HANDLED; -} - -static irqreturn_t xics_ipi_action_direct(int irq, void *dev_id) -{ - int cpu = smp_processor_id(); - - direct_qirr_info(cpu, 0xff); - - return xics_ipi_dispatch(cpu); -} - -static irqreturn_t xics_ipi_action_lpar(int irq, void *dev_id) -{ - int cpu = smp_processor_id(); - - lpar_qirr_info(cpu, 0xff); - - return xics_ipi_dispatch(cpu); -} - -static void xics_request_ipi(void) -{ - unsigned int ipi; - int rc; - - ipi = irq_create_mapping(xics_host, XICS_IPI); - BUG_ON(ipi == NO_IRQ); - - /* - * IPIs are marked IRQF_DISABLED as they must run with irqs - * disabled - */ - irq_set_handler(ipi, handle_percpu_irq); - if (firmware_has_feature(FW_FEATURE_LPAR)) - rc = request_irq(ipi, xics_ipi_action_lpar, - IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); - else - rc = request_irq(ipi, xics_ipi_action_direct, - IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); - BUG_ON(rc); -} - -int __init smp_xics_probe(void) -{ - xics_request_ipi(); - - return cpumask_weight(cpu_possible_mask); -} - -#endif /* CONFIG_SMP */ - - -/* Initialization */ - -static void xics_update_irq_servers(void) -{ - int i, j; - struct device_node *np; - u32 ilen; - const u32 *ireg; - u32 hcpuid; - - /* Find the server numbers for the boot cpu. */ - np = of_get_cpu_node(boot_cpuid, NULL); - BUG_ON(!np); - - ireg = of_get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen); - if (!ireg) { - of_node_put(np); - return; - } - - i = ilen / sizeof(int); - hcpuid = get_hard_smp_processor_id(boot_cpuid); - - /* Global interrupt distribution server is specified in the last - * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last - * entry fom this property for current boot cpu id and use it as - * default distribution server - */ - for (j = 0; j < i; j += 2) { - if (ireg[j] == hcpuid) { - default_server = hcpuid; - default_distrib_server = ireg[j+1]; - } - } - - of_node_put(np); -} - -static void __init xics_map_one_cpu(int hw_id, unsigned long addr, - unsigned long size) -{ - int i; - - /* This may look gross but it's good enough for now, we don't quite - * have a hard -> linux processor id matching. - */ - for_each_possible_cpu(i) { - if (!cpu_present(i)) - continue; - if (hw_id == get_hard_smp_processor_id(i)) { - xics_per_cpu[i] = ioremap(addr, size); - return; - } - } -} - -static void __init xics_init_one_node(struct device_node *np, - unsigned int *indx) -{ - unsigned int ilen; - const u32 *ireg; - - /* This code does the theorically broken assumption that the interrupt - * server numbers are the same as the hard CPU numbers. - * This happens to be the case so far but we are playing with fire... - * should be fixed one of these days. -BenH. - */ - ireg = of_get_property(np, "ibm,interrupt-server-ranges", NULL); - - /* Do that ever happen ? we'll know soon enough... but even good'old - * f80 does have that property .. - */ - WARN_ON(ireg == NULL); - if (ireg) { - /* - * set node starting index for this node - */ - *indx = *ireg; - } - ireg = of_get_property(np, "reg", &ilen); - if (!ireg) - panic("xics_init_IRQ: can't find interrupt reg property"); - - while (ilen >= (4 * sizeof(u32))) { - unsigned long addr, size; - - /* XXX Use proper OF parsing code here !!! */ - addr = (unsigned long)*ireg++ << 32; - ilen -= sizeof(u32); - addr |= *ireg++; - ilen -= sizeof(u32); - size = (unsigned long)*ireg++ << 32; - ilen -= sizeof(u32); - size |= *ireg++; - ilen -= sizeof(u32); - xics_map_one_cpu(*indx, addr, size); - (*indx)++; - } -} - -void __init xics_init_IRQ(void) -{ - struct device_node *np; - u32 indx = 0; - int found = 0; - const u32 *isize; - - ppc64_boot_msg(0x20, "XICS Init"); - - ibm_get_xive = rtas_token("ibm,get-xive"); - ibm_set_xive = rtas_token("ibm,set-xive"); - ibm_int_on = rtas_token("ibm,int-on"); - ibm_int_off = rtas_token("ibm,int-off"); - - for_each_node_by_type(np, "PowerPC-External-Interrupt-Presentation") { - found = 1; - if (firmware_has_feature(FW_FEATURE_LPAR)) { - of_node_put(np); - break; - } - xics_init_one_node(np, &indx); - } - if (found == 0) - return; - - /* get the bit size of server numbers */ - found = 0; - - for_each_compatible_node(np, NULL, "ibm,ppc-xics") { - isize = of_get_property(np, "ibm,interrupt-server#-size", NULL); - - if (!isize) - continue; - - if (!found) { - interrupt_server_size = *isize; - found = 1; - } else if (*isize != interrupt_server_size) { - printk(KERN_WARNING "XICS: " - "mismatched ibm,interrupt-server#-size\n"); - interrupt_server_size = max(*isize, - interrupt_server_size); - } - } - - xics_update_irq_servers(); - xics_init_host(); - - if (firmware_has_feature(FW_FEATURE_LPAR)) - ppc_md.get_irq = xics_get_irq_lpar; - else - ppc_md.get_irq = xics_get_irq_direct; - - xics_setup_cpu(); - - ppc64_boot_msg(0x21, "XICS Done"); -} - -/* Cpu startup, shutdown, and hotplug */ - -static void xics_set_cpu_priority(unsigned char cppr) -{ - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - - /* - * we only really want to set the priority when there's - * just one cppr value on the stack - */ - WARN_ON(os_cppr->index != 0); - - os_cppr->stack[0] = cppr; - - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_cppr_info(cppr); - else - direct_cppr_info(cppr); - iosync(); -} - -/* Have the calling processor join or leave the specified global queue */ -static void xics_set_cpu_giq(unsigned int gserver, unsigned int join) -{ - int index; - int status; - - if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL)) - return; - - index = (1UL << interrupt_server_size) - 1 - gserver; - - status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join); - - WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n", - GLOBAL_INTERRUPT_QUEUE, index, join, status); -} - -void xics_setup_cpu(void) -{ - xics_set_cpu_priority(LOWEST_PRIORITY); - - xics_set_cpu_giq(default_distrib_server, 1); -} - -void xics_teardown_cpu(void) -{ - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); - int cpu = smp_processor_id(); - - /* - * we have to reset the cppr index to 0 because we're - * not going to return from the IPI - */ - os_cppr->index = 0; - xics_set_cpu_priority(0); - - /* Clear any pending IPI request */ - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_qirr_info(cpu, 0xff); - else - direct_qirr_info(cpu, 0xff); -} - -void xics_kexec_teardown_cpu(int secondary) -{ - xics_teardown_cpu(); - - /* - * we take the ipi irq but and never return so we - * need to EOI the IPI, but want to leave our priority 0 - * - * should we check all the other interrupts too? - * should we be flagging idle loop instead? - * or creating some task to be scheduled? - */ - - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_xirr_info_set((0x00 << 24) | XICS_IPI); - else - direct_xirr_info_set((0x00 << 24) | XICS_IPI); - - /* - * Some machines need to have at least one cpu in the GIQ, - * so leave the master cpu in the group. - */ - if (secondary) - xics_set_cpu_giq(default_distrib_server, 0); -} - -#ifdef CONFIG_HOTPLUG_CPU - -/* Interrupts are disabled. */ -void xics_migrate_irqs_away(void) -{ - int cpu = smp_processor_id(), hw_cpu = hard_smp_processor_id(); - int virq; - - /* If we used to be the default server, move to the new "boot_cpuid" */ - if (hw_cpu == default_server) - xics_update_irq_servers(); - - /* Reject any interrupt that was queued to us... */ - xics_set_cpu_priority(0); - - /* Remove ourselves from the global interrupt queue */ - xics_set_cpu_giq(default_distrib_server, 0); - - /* Allow IPIs again... */ - xics_set_cpu_priority(DEFAULT_PRIORITY); - - for_each_irq(virq) { - struct irq_desc *desc; - struct irq_chip *chip; - unsigned int hwirq; - int xics_status[2]; - int status; - unsigned long flags; - - /* We can't set affinity on ISA interrupts */ - if (virq < NUM_ISA_INTERRUPTS) - continue; - if (irq_map[virq].host != xics_host) - continue; - hwirq = (unsigned int)irq_map[virq].hwirq; - /* We need to get IPIs still. */ - if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS) - continue; - - desc = irq_to_desc(virq); - - /* We only need to migrate enabled IRQS */ - if (desc == NULL || desc->action == NULL) - continue; - - chip = irq_desc_get_chip(desc); - if (chip == NULL || chip->irq_set_affinity == NULL) - continue; - - raw_spin_lock_irqsave(&desc->lock, flags); - - status = rtas_call(ibm_get_xive, 1, 3, xics_status, hwirq); - if (status) { - printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", - __func__, hwirq, status); - goto unlock; - } - - /* - * We only support delivery to all cpus or to one cpu. - * The irq has to be migrated only in the single cpu - * case. - */ - if (xics_status[0] != hw_cpu) - goto unlock; - - /* This is expected during cpu offline. */ - if (cpu_online(cpu)) - printk(KERN_WARNING "IRQ %u affinity broken off cpu %u\n", - virq, cpu); - - /* Reset affinity to all cpus */ - cpumask_setall(desc->irq_data.affinity); - chip->irq_set_affinity(&desc->irq_data, cpu_all_mask, true); -unlock: - raw_spin_unlock_irqrestore(&desc->lock, flags); - } -} -#endif diff --git a/arch/powerpc/platforms/pseries/xics.h b/arch/powerpc/platforms/pseries/xics.h deleted file mode 100644 index d1d5a83039a..00000000000 --- a/arch/powerpc/platforms/pseries/xics.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * arch/powerpc/platforms/pseries/xics.h - * - * Copyright 2000 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. - */ - -#ifndef _POWERPC_KERNEL_XICS_H -#define _POWERPC_KERNEL_XICS_H - -extern void xics_init_IRQ(void); -extern void xics_setup_cpu(void); -extern void xics_teardown_cpu(void); -extern void xics_kexec_teardown_cpu(int secondary); -extern void xics_migrate_irqs_away(void); -extern int smp_xics_probe(void); -extern void smp_xics_message_pass(int target, int msg); - -#endif /* _POWERPC_KERNEL_XICS_H */ diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig new file mode 100644 index 00000000000..c3c48eb62cc --- /dev/null +++ b/arch/powerpc/platforms/wsp/Kconfig @@ -0,0 +1,28 @@ +config PPC_WSP + bool + default n + +menu "WSP platform selection" + depends on PPC_BOOK3E_64 + +config PPC_PSR2 + bool "PSR-2 platform" + select PPC_A2 + select GENERIC_TBSYNC + select PPC_SCOM + select EPAPR_BOOT + select PPC_WSP + select PPC_XICS + select PPC_ICP_NATIVE + default y + +endmenu + +config PPC_A2_DD2 + bool "Support for DD2 based A2/WSP systems" + depends on PPC_A2 + +config WORKAROUND_ERRATUM_463 + depends on PPC_A2_DD2 + bool "Workaround erratum 463" + default y diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile new file mode 100644 index 00000000000..095be73d6cd --- /dev/null +++ b/arch/powerpc/platforms/wsp/Makefile @@ -0,0 +1,6 @@ +ccflags-y += -mno-minimal-toc + +obj-y += setup.o ics.o +obj-$(CONFIG_PPC_PSR2) += psr2.o opb_pic.o +obj-$(CONFIG_PPC_WSP) += scom_wsp.o +obj-$(CONFIG_SMP) += smp.o scom_smp.o diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c new file mode 100644 index 00000000000..e53bd9e7b12 --- /dev/null +++ b/arch/powerpc/platforms/wsp/ics.c @@ -0,0 +1,712 @@ +/* + * Copyright 2008-2011 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/cpu.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/msi.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/xics.h> + +#include "wsp.h" +#include "ics.h" + + +/* WSP ICS */ + +struct wsp_ics { + struct ics ics; + struct device_node *dn; + void __iomem *regs; + spinlock_t lock; + unsigned long *bitmap; + u32 chip_id; + u32 lsi_base; + u32 lsi_count; + u64 hwirq_start; + u64 count; +#ifdef CONFIG_SMP + int *hwirq_cpu_map; +#endif +}; + +#define to_wsp_ics(ics) container_of(ics, struct wsp_ics, ics) + +#define INT_SRC_LAYER_BUID_REG(base) ((base) + 0x00) +#define IODA_TBL_ADDR_REG(base) ((base) + 0x18) +#define IODA_TBL_DATA_REG(base) ((base) + 0x20) +#define XIVE_UPDATE_REG(base) ((base) + 0x28) +#define ICS_INT_CAPS_REG(base) ((base) + 0x30) + +#define TBL_AUTO_INCREMENT ((1UL << 63) | (1UL << 15)) +#define TBL_SELECT_XIST (1UL << 48) +#define TBL_SELECT_XIVT (1UL << 49) + +#define IODA_IRQ(irq) ((irq) & (0x7FFULL)) /* HRM 5.1.3.4 */ + +#define XIST_REQUIRED 0x8 +#define XIST_REJECTED 0x4 +#define XIST_PRESENTED 0x2 +#define XIST_PENDING 0x1 + +#define XIVE_SERVER_SHIFT 42 +#define XIVE_SERVER_MASK 0xFFFFULL +#define XIVE_PRIORITY_MASK 0xFFULL +#define XIVE_PRIORITY_SHIFT 32 +#define XIVE_WRITE_ENABLE (1ULL << 63) + +/* + * The docs refer to a 6 bit field called ChipID, which consists of a + * 3 bit NodeID and a 3 bit ChipID. On WSP the ChipID is always zero + * so we ignore it, and every where we use "chip id" in this code we + * mean the NodeID. + */ +#define WSP_ICS_CHIP_SHIFT 17 + + +static struct wsp_ics *ics_list; +static int num_ics; + +/* ICS Source controller accessors */ + +static u64 wsp_ics_get_xive(struct wsp_ics *ics, unsigned int irq) +{ + unsigned long flags; + u64 xive; + + spin_lock_irqsave(&ics->lock, flags); + out_be64(IODA_TBL_ADDR_REG(ics->regs), TBL_SELECT_XIVT | IODA_IRQ(irq)); + xive = in_be64(IODA_TBL_DATA_REG(ics->regs)); + spin_unlock_irqrestore(&ics->lock, flags); + + return xive; +} + +static void wsp_ics_set_xive(struct wsp_ics *ics, unsigned int irq, u64 xive) +{ + xive &= ~XIVE_ADDR_MASK; + xive |= (irq & XIVE_ADDR_MASK); + xive |= XIVE_WRITE_ENABLE; + + out_be64(XIVE_UPDATE_REG(ics->regs), xive); +} + +static u64 xive_set_server(u64 xive, unsigned int server) +{ + u64 mask = ~(XIVE_SERVER_MASK << XIVE_SERVER_SHIFT); + + xive &= mask; + xive |= (server & XIVE_SERVER_MASK) << XIVE_SERVER_SHIFT; + + return xive; +} + +static u64 xive_set_priority(u64 xive, unsigned int priority) +{ + u64 mask = ~(XIVE_PRIORITY_MASK << XIVE_PRIORITY_SHIFT); + + xive &= mask; + xive |= (priority & XIVE_PRIORITY_MASK) << XIVE_PRIORITY_SHIFT; + + return xive; +} + + +#ifdef CONFIG_SMP +/* Find logical CPUs within mask on a given chip and store result in ret */ +void cpus_on_chip(int chip_id, cpumask_t *mask, cpumask_t *ret) +{ + int cpu, chip; + struct device_node *cpu_dn, *dn; + const u32 *prop; + + cpumask_clear(ret); + for_each_cpu(cpu, mask) { + cpu_dn = of_get_cpu_node(cpu, NULL); + if (!cpu_dn) + continue; + + prop = of_get_property(cpu_dn, "at-node", NULL); + if (!prop) { + of_node_put(cpu_dn); + continue; + } + + dn = of_find_node_by_phandle(*prop); + of_node_put(cpu_dn); + + chip = wsp_get_chip_id(dn); + if (chip == chip_id) + cpumask_set_cpu(cpu, ret); + + of_node_put(dn); + } +} + +/* Store a suitable CPU to handle a hwirq in the ics->hwirq_cpu_map cache */ +static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, + const cpumask_t *affinity) +{ + cpumask_var_t avail, newmask; + int ret = -ENOMEM, cpu, cpu_rover = 0, target; + int index = hwirq - ics->hwirq_start; + unsigned int nodeid; + + BUG_ON(index < 0 || index >= ics->count); + + if (!ics->hwirq_cpu_map) + return -ENOMEM; + + if (!distribute_irqs) { + ics->hwirq_cpu_map[hwirq - ics->hwirq_start] = xics_default_server; + return 0; + } + + /* Allocate needed CPU masks */ + if (!alloc_cpumask_var(&avail, GFP_KERNEL)) + goto ret; + if (!alloc_cpumask_var(&newmask, GFP_KERNEL)) + goto freeavail; + + /* Find PBus attached to the source of this IRQ */ + nodeid = (hwirq >> WSP_ICS_CHIP_SHIFT) & 0x3; /* 12:14 */ + + /* Find CPUs that could handle this IRQ */ + if (affinity) + cpumask_and(avail, cpu_online_mask, affinity); + else + cpumask_copy(avail, cpu_online_mask); + + /* Narrow selection down to logical CPUs on the same chip */ + cpus_on_chip(nodeid, avail, newmask); + + /* Ensure we haven't narrowed it down to 0 */ + if (unlikely(cpumask_empty(newmask))) { + if (unlikely(cpumask_empty(avail))) { + ret = -1; + goto out; + } + cpumask_copy(newmask, avail); + } + + /* Choose a CPU out of those we narrowed it down to in round robin */ + target = hwirq % cpumask_weight(newmask); + for_each_cpu(cpu, newmask) { + if (cpu_rover++ >= target) { + ics->hwirq_cpu_map[index] = get_hard_smp_processor_id(cpu); + ret = 0; + goto out; + } + } + + /* Shouldn't happen */ + WARN_ON(1); + +out: + free_cpumask_var(newmask); +freeavail: + free_cpumask_var(avail); +ret: + if (ret < 0) { + ics->hwirq_cpu_map[index] = cpumask_first(cpu_online_mask); + pr_warning("Error, falling hwirq 0x%x routing back to CPU %i\n", + hwirq, ics->hwirq_cpu_map[index]); + } + return ret; +} + +static void alloc_irq_map(struct wsp_ics *ics) +{ + int i; + + ics->hwirq_cpu_map = kmalloc(sizeof(int) * ics->count, GFP_KERNEL); + if (!ics->hwirq_cpu_map) { + pr_warning("Allocate hwirq_cpu_map failed, " + "IRQ balancing disabled\n"); + return; + } + + for (i=0; i < ics->count; i++) + ics->hwirq_cpu_map[i] = xics_default_server; +} + +static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) +{ + int index = hwirq - ics->hwirq_start; + + BUG_ON(index < 0 || index >= ics->count); + + if (!ics->hwirq_cpu_map) + return xics_default_server; + + return ics->hwirq_cpu_map[index]; +} +#else /* !CONFIG_SMP */ +static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, + const cpumask_t *affinity) +{ + return 0; +} + +static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) +{ + return xics_default_server; +} + +static void alloc_irq_map(struct wsp_ics *ics) { } +#endif + +static void wsp_chip_unmask_irq(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct wsp_ics *ics; + int server; + u64 xive; + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return; + + ics = d->chip_data; + if (WARN_ON(!ics)) + return; + + server = get_irq_server(ics, hw_irq); + + xive = wsp_ics_get_xive(ics, hw_irq); + xive = xive_set_server(xive, server); + xive = xive_set_priority(xive, DEFAULT_PRIORITY); + wsp_ics_set_xive(ics, hw_irq, xive); +} + +static unsigned int wsp_chip_startup(struct irq_data *d) +{ + /* unmask it */ + wsp_chip_unmask_irq(d); + return 0; +} + +static void wsp_mask_real_irq(unsigned int hw_irq, struct wsp_ics *ics) +{ + u64 xive; + + if (hw_irq == XICS_IPI) + return; + + if (WARN_ON(!ics)) + return; + xive = wsp_ics_get_xive(ics, hw_irq); + xive = xive_set_server(xive, xics_default_server); + xive = xive_set_priority(xive, LOWEST_PRIORITY); + wsp_ics_set_xive(ics, hw_irq, xive); +} + +static void wsp_chip_mask_irq(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct wsp_ics *ics = d->chip_data; + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return; + + wsp_mask_real_irq(hw_irq, ics); +} + +static int wsp_chip_set_affinity(struct irq_data *d, + const struct cpumask *cpumask, bool force) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct wsp_ics *ics; + int ret; + u64 xive; + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return -1; + + ics = d->chip_data; + if (WARN_ON(!ics)) + return -1; + xive = wsp_ics_get_xive(ics, hw_irq); + + /* + * For the moment only implement delivery to all cpus or one cpu. + * Get current irq_server for the given irq + */ + ret = cache_hwirq_map(ics, d->irq, cpumask); + if (ret == -1) { + char cpulist[128]; + cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); + pr_warning("%s: No online cpus in the mask %s for irq %d\n", + __func__, cpulist, d->irq); + return -1; + } else if (ret == -ENOMEM) { + pr_warning("%s: Out of memory\n", __func__); + return -1; + } + + xive = xive_set_server(xive, get_irq_server(ics, hw_irq)); + wsp_ics_set_xive(ics, hw_irq, xive); + + return 0; +} + +static struct irq_chip wsp_irq_chip = { + .name = "WSP ICS", + .irq_startup = wsp_chip_startup, + .irq_mask = wsp_chip_mask_irq, + .irq_unmask = wsp_chip_unmask_irq, + .irq_set_affinity = wsp_chip_set_affinity +}; + +static int wsp_ics_host_match(struct ics *ics, struct device_node *dn) +{ + /* All ICSs in the system implement a global irq number space, + * so match against them all. */ + return of_device_is_compatible(dn, "ibm,ppc-xics"); +} + +static int wsp_ics_match_hwirq(struct wsp_ics *wsp_ics, unsigned int hwirq) +{ + if (hwirq >= wsp_ics->hwirq_start && + hwirq < wsp_ics->hwirq_start + wsp_ics->count) + return 1; + + return 0; +} + +static int wsp_ics_map(struct ics *ics, unsigned int virq) +{ + struct wsp_ics *wsp_ics = to_wsp_ics(ics); + unsigned int hw_irq = virq_to_hw(virq); + unsigned long flags; + + if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) + return -ENOENT; + + irq_set_chip_and_handler(virq, &wsp_irq_chip, handle_fasteoi_irq); + + irq_set_chip_data(virq, wsp_ics); + + spin_lock_irqsave(&wsp_ics->lock, flags); + bitmap_allocate_region(wsp_ics->bitmap, hw_irq - wsp_ics->hwirq_start, 0); + spin_unlock_irqrestore(&wsp_ics->lock, flags); + + return 0; +} + +static void wsp_ics_mask_unknown(struct ics *ics, unsigned long hw_irq) +{ + struct wsp_ics *wsp_ics = to_wsp_ics(ics); + + if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) + return; + + pr_err("%s: IRQ %lu (real) is invalid, disabling it.\n", __func__, hw_irq); + wsp_mask_real_irq(hw_irq, wsp_ics); +} + +static long wsp_ics_get_server(struct ics *ics, unsigned long hw_irq) +{ + struct wsp_ics *wsp_ics = to_wsp_ics(ics); + + if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) + return -ENOENT; + + return get_irq_server(wsp_ics, hw_irq); +} + +/* HW Number allocation API */ + +static struct wsp_ics *wsp_ics_find_dn_ics(struct device_node *dn) +{ + struct device_node *iparent; + int i; + + iparent = of_irq_find_parent(dn); + if (!iparent) { + pr_err("wsp_ics: Failed to find interrupt parent!\n"); + return NULL; + } + + for(i = 0; i < num_ics; i++) { + if(ics_list[i].dn == iparent) + break; + } + + if (i >= num_ics) { + pr_err("wsp_ics: Unable to find parent bitmap!\n"); + return NULL; + } + + return &ics_list[i]; +} + +int wsp_ics_alloc_irq(struct device_node *dn, int num) +{ + struct wsp_ics *ics; + int order, offset; + + ics = wsp_ics_find_dn_ics(dn); + if (!ics) + return -ENODEV; + + /* Fast, but overly strict if num isn't a power of two */ + order = get_count_order(num); + + spin_lock_irq(&ics->lock); + offset = bitmap_find_free_region(ics->bitmap, ics->count, order); + spin_unlock_irq(&ics->lock); + + if (offset < 0) + return offset; + + return offset + ics->hwirq_start; +} + +void wsp_ics_free_irq(struct device_node *dn, unsigned int irq) +{ + struct wsp_ics *ics; + + ics = wsp_ics_find_dn_ics(dn); + if (WARN_ON(!ics)) + return; + + spin_lock_irq(&ics->lock); + bitmap_release_region(ics->bitmap, irq, 0); + spin_unlock_irq(&ics->lock); +} + +/* Initialisation */ + +static int __init wsp_ics_bitmap_setup(struct wsp_ics *ics, + struct device_node *dn) +{ + int len, i, j, size; + u32 start, count; + const u32 *p; + + size = BITS_TO_LONGS(ics->count) * sizeof(long); + ics->bitmap = kzalloc(size, GFP_KERNEL); + if (!ics->bitmap) { + pr_err("wsp_ics: ENOMEM allocating IRQ bitmap!\n"); + return -ENOMEM; + } + + spin_lock_init(&ics->lock); + + p = of_get_property(dn, "available-ranges", &len); + if (!p || !len) { + /* FIXME this should be a WARN() once mambo is updated */ + pr_err("wsp_ics: No available-ranges defined for %s\n", + dn->full_name); + return 0; + } + + if (len % (2 * sizeof(u32)) != 0) { + /* FIXME this should be a WARN() once mambo is updated */ + pr_err("wsp_ics: Invalid available-ranges for %s\n", + dn->full_name); + return 0; + } + + bitmap_fill(ics->bitmap, ics->count); + + for (i = 0; i < len / sizeof(u32); i += 2) { + start = of_read_number(p + i, 1); + count = of_read_number(p + i + 1, 1); + + pr_devel("%s: start: %d count: %d\n", __func__, start, count); + + if ((start + count) > (ics->hwirq_start + ics->count) || + start < ics->hwirq_start) { + pr_err("wsp_ics: Invalid range! -> %d to %d\n", + start, start + count); + break; + } + + for (j = 0; j < count; j++) + bitmap_release_region(ics->bitmap, + (start + j) - ics->hwirq_start, 0); + } + + /* Ensure LSIs are not available for allocation */ + bitmap_allocate_region(ics->bitmap, ics->lsi_base, + get_count_order(ics->lsi_count)); + + return 0; +} + +static int __init wsp_ics_setup(struct wsp_ics *ics, struct device_node *dn) +{ + u32 lsi_buid, msi_buid, msi_base, msi_count; + void __iomem *regs; + const u32 *p; + int rc, len, i; + u64 caps, buid; + + p = of_get_property(dn, "interrupt-ranges", &len); + if (!p || len < (2 * sizeof(u32))) { + pr_err("wsp_ics: No/bad interrupt-ranges found on %s\n", + dn->full_name); + return -ENOENT; + } + + if (len > (2 * sizeof(u32))) { + pr_err("wsp_ics: Multiple ics ranges not supported.\n"); + return -EINVAL; + } + + regs = of_iomap(dn, 0); + if (!regs) { + pr_err("wsp_ics: of_iomap(%s) failed\n", dn->full_name); + return -ENXIO; + } + + ics->hwirq_start = of_read_number(p, 1); + ics->count = of_read_number(p + 1, 1); + ics->regs = regs; + + ics->chip_id = wsp_get_chip_id(dn); + if (WARN_ON(ics->chip_id < 0)) + ics->chip_id = 0; + + /* Get some informations about the critter */ + caps = in_be64(ICS_INT_CAPS_REG(ics->regs)); + buid = in_be64(INT_SRC_LAYER_BUID_REG(ics->regs)); + ics->lsi_count = caps >> 56; + msi_count = (caps >> 44) & 0x7ff; + + /* Note: LSI BUID is 9 bits, but really only 3 are BUID and the + * rest is mixed in the interrupt number. We store the whole + * thing though + */ + lsi_buid = (buid >> 48) & 0x1ff; + ics->lsi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | lsi_buid << 5; + msi_buid = (buid >> 37) & 0x7; + msi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | msi_buid << 11; + + pr_info("wsp_ics: Found %s\n", dn->full_name); + pr_info("wsp_ics: irq range : 0x%06llx..0x%06llx\n", + ics->hwirq_start, ics->hwirq_start + ics->count - 1); + pr_info("wsp_ics: %4d LSIs : 0x%06x..0x%06x\n", + ics->lsi_count, ics->lsi_base, + ics->lsi_base + ics->lsi_count - 1); + pr_info("wsp_ics: %4d MSIs : 0x%06x..0x%06x\n", + msi_count, msi_base, + msi_base + msi_count - 1); + + /* Let's check the HW config is sane */ + if (ics->lsi_base < ics->hwirq_start || + (ics->lsi_base + ics->lsi_count) > (ics->hwirq_start + ics->count)) + pr_warning("wsp_ics: WARNING ! LSIs out of interrupt-ranges !\n"); + if (msi_base < ics->hwirq_start || + (msi_base + msi_count) > (ics->hwirq_start + ics->count)) + pr_warning("wsp_ics: WARNING ! MSIs out of interrupt-ranges !\n"); + + /* We don't check for overlap between LSI and MSI, which will happen + * if we use the same BUID, I'm not sure yet how legit that is. + */ + + rc = wsp_ics_bitmap_setup(ics, dn); + if (rc) { + iounmap(regs); + return rc; + } + + ics->dn = of_node_get(dn); + alloc_irq_map(ics); + + for(i = 0; i < ics->count; i++) + wsp_mask_real_irq(ics->hwirq_start + i, ics); + + ics->ics.map = wsp_ics_map; + ics->ics.mask_unknown = wsp_ics_mask_unknown; + ics->ics.get_server = wsp_ics_get_server; + ics->ics.host_match = wsp_ics_host_match; + + xics_register_ics(&ics->ics); + + return 0; +} + +static void __init wsp_ics_set_default_server(void) +{ + struct device_node *np; + u32 hwid; + + /* Find the server number for the boot cpu. */ + np = of_get_cpu_node(boot_cpuid, NULL); + BUG_ON(!np); + + hwid = get_hard_smp_processor_id(boot_cpuid); + + pr_info("wsp_ics: default server is %#x, CPU %s\n", hwid, np->full_name); + xics_default_server = hwid; + + of_node_put(np); +} + +static int __init wsp_ics_init(void) +{ + struct device_node *dn; + struct wsp_ics *ics; + int rc, found; + + wsp_ics_set_default_server(); + + found = 0; + for_each_compatible_node(dn, NULL, "ibm,ppc-xics") + found++; + + if (found == 0) { + pr_err("wsp_ics: No ICS's found!\n"); + return -ENODEV; + } + + ics_list = kmalloc(sizeof(*ics) * found, GFP_KERNEL); + if (!ics_list) { + pr_err("wsp_ics: No memory for structs.\n"); + return -ENOMEM; + } + + num_ics = 0; + ics = ics_list; + for_each_compatible_node(dn, NULL, "ibm,wsp-xics") { + rc = wsp_ics_setup(ics, dn); + if (rc == 0) { + ics++; + num_ics++; + } + } + + if (found != num_ics) { + pr_err("wsp_ics: Failed setting up %d ICS's\n", + found - num_ics); + return -1; + } + + return 0; +} + +void __init wsp_init_irq(void) +{ + wsp_ics_init(); + xics_init(); + + /* We need to patch our irq chip's EOI to point to the right ICP */ + wsp_irq_chip.irq_eoi = icp_ops->eoi; +} diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h new file mode 100644 index 00000000000..e34d5310264 --- /dev/null +++ b/arch/powerpc/platforms/wsp/ics.h @@ -0,0 +1,20 @@ +/* + * 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. + */ + +#ifndef __ICS_H +#define __ICS_H + +#define XIVE_ADDR_MASK 0x7FFULL + +extern void wsp_init_irq(void); + +extern int wsp_ics_alloc_irq(struct device_node *dn, int num); +extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq); + +#endif /* __ICS_H */ diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c new file mode 100644 index 00000000000..be05631a3c1 --- /dev/null +++ b/arch/powerpc/platforms/wsp/opb_pic.c @@ -0,0 +1,332 @@ +/* + * IBM Onboard Peripheral Bus Interrupt Controller + * + * Copyright 2010 Jack Miller, IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/time.h> + +#include <asm/reg_a2.h> +#include <asm/irq.h> + +#define OPB_NR_IRQS 32 + +#define OPB_MLSASIER 0x04 /* MLS Accumulated Status IER */ +#define OPB_MLSIR 0x50 /* MLS Interrupt Register */ +#define OPB_MLSIER 0x54 /* MLS Interrupt Enable Register */ +#define OPB_MLSIPR 0x58 /* MLS Interrupt Polarity Register */ +#define OPB_MLSIIR 0x5c /* MLS Interrupt Inputs Register */ + +static int opb_index = 0; + +struct opb_pic { + struct irq_host *host; + void *regs; + int index; + spinlock_t lock; +}; + +static u32 opb_in(struct opb_pic *opb, int offset) +{ + return in_be32(opb->regs + offset); +} + +static void opb_out(struct opb_pic *opb, int offset, u32 val) +{ + out_be32(opb->regs + offset, val); +} + +static void opb_unmask_irq(struct irq_data *d) +{ + struct opb_pic *opb; + unsigned long flags; + u32 ier, bitset; + + opb = d->chip_data; + bitset = (1 << (31 - irqd_to_hwirq(d))); + + spin_lock_irqsave(&opb->lock, flags); + + ier = opb_in(opb, OPB_MLSIER); + opb_out(opb, OPB_MLSIER, ier | bitset); + ier = opb_in(opb, OPB_MLSIER); + + spin_unlock_irqrestore(&opb->lock, flags); +} + +static void opb_mask_irq(struct irq_data *d) +{ + struct opb_pic *opb; + unsigned long flags; + u32 ier, mask; + + opb = d->chip_data; + mask = ~(1 << (31 - irqd_to_hwirq(d))); + + spin_lock_irqsave(&opb->lock, flags); + + ier = opb_in(opb, OPB_MLSIER); + opb_out(opb, OPB_MLSIER, ier & mask); + ier = opb_in(opb, OPB_MLSIER); // Flush posted writes + + spin_unlock_irqrestore(&opb->lock, flags); +} + +static void opb_ack_irq(struct irq_data *d) +{ + struct opb_pic *opb; + unsigned long flags; + u32 bitset; + + opb = d->chip_data; + bitset = (1 << (31 - irqd_to_hwirq(d))); + + spin_lock_irqsave(&opb->lock, flags); + + opb_out(opb, OPB_MLSIR, bitset); + opb_in(opb, OPB_MLSIR); // Flush posted writes + + spin_unlock_irqrestore(&opb->lock, flags); +} + +static void opb_mask_ack_irq(struct irq_data *d) +{ + struct opb_pic *opb; + unsigned long flags; + u32 bitset; + u32 ier, ir; + + opb = d->chip_data; + bitset = (1 << (31 - irqd_to_hwirq(d))); + + spin_lock_irqsave(&opb->lock, flags); + + ier = opb_in(opb, OPB_MLSIER); + opb_out(opb, OPB_MLSIER, ier & ~bitset); + ier = opb_in(opb, OPB_MLSIER); // Flush posted writes + + opb_out(opb, OPB_MLSIR, bitset); + ir = opb_in(opb, OPB_MLSIR); // Flush posted writes + + spin_unlock_irqrestore(&opb->lock, flags); +} + +static int opb_set_irq_type(struct irq_data *d, unsigned int flow) +{ + struct opb_pic *opb; + unsigned long flags; + int invert, ipr, mask, bit; + + opb = d->chip_data; + + /* The only information we're interested in in the type is whether it's + * a high or low trigger. For high triggered interrupts, the polarity + * set for it in the MLS Interrupt Polarity Register is 0, for low + * interrupts it's 1 so that the proper input in the MLS Interrupt Input + * Register is interrupted as asserting the interrupt. */ + + switch (flow) { + case IRQ_TYPE_NONE: + opb_mask_irq(d); + return 0; + + case IRQ_TYPE_LEVEL_HIGH: + invert = 0; + break; + + case IRQ_TYPE_LEVEL_LOW: + invert = 1; + break; + + default: + return -EINVAL; + } + + bit = (1 << (31 - irqd_to_hwirq(d))); + mask = ~bit; + + spin_lock_irqsave(&opb->lock, flags); + + ipr = opb_in(opb, OPB_MLSIPR); + ipr = (ipr & mask) | (invert ? bit : 0); + opb_out(opb, OPB_MLSIPR, ipr); + ipr = opb_in(opb, OPB_MLSIPR); // Flush posted writes + + spin_unlock_irqrestore(&opb->lock, flags); + + /* Record the type in the interrupt descriptor */ + irqd_set_trigger_type(d, flow); + + return 0; +} + +static struct irq_chip opb_irq_chip = { + .name = "OPB", + .irq_mask = opb_mask_irq, + .irq_unmask = opb_unmask_irq, + .irq_mask_ack = opb_mask_ack_irq, + .irq_ack = opb_ack_irq, + .irq_set_type = opb_set_irq_type +}; + +static int opb_host_map(struct irq_host *host, unsigned int virq, + irq_hw_number_t hwirq) +{ + struct opb_pic *opb; + + opb = host->host_data; + + /* Most of the important stuff is handled by the generic host code, like + * the lookup, so just attach some info to the virtual irq */ + + irq_set_chip_data(virq, opb); + irq_set_chip_and_handler(virq, &opb_irq_chip, handle_level_irq); + irq_set_irq_type(virq, IRQ_TYPE_NONE); + + return 0; +} + +static int opb_host_xlate(struct irq_host *host, struct device_node *dn, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_type) +{ + /* Interrupt size must == 2 */ + BUG_ON(intsize != 2); + *out_hwirq = intspec[0]; + *out_type = intspec[1]; + return 0; +} + +static struct irq_host_ops opb_host_ops = { + .map = opb_host_map, + .xlate = opb_host_xlate, +}; + +irqreturn_t opb_irq_handler(int irq, void *private) +{ + struct opb_pic *opb; + u32 ir, src, subvirq; + + opb = (struct opb_pic *) private; + + /* Read the OPB MLS Interrupt Register for + * asserted interrupts */ + ir = opb_in(opb, OPB_MLSIR); + if (!ir) + return IRQ_NONE; + + do { + /* Get 1 - 32 source, *NOT* bit */ + src = 32 - ffs(ir); + + /* Translate from the OPB's conception of interrupt number to + * Linux's virtual IRQ */ + + subvirq = irq_linear_revmap(opb->host, src); + + generic_handle_irq(subvirq); + } while ((ir = opb_in(opb, OPB_MLSIR))); + + return IRQ_HANDLED; +} + +struct opb_pic *opb_pic_init_one(struct device_node *dn) +{ + struct opb_pic *opb; + struct resource res; + + if (of_address_to_resource(dn, 0, &res)) { + printk(KERN_ERR "opb: Couldn't translate resource\n"); + return NULL; + } + + opb = kzalloc(sizeof(struct opb_pic), GFP_KERNEL); + if (!opb) { + printk(KERN_ERR "opb: Failed to allocate opb struct!\n"); + return NULL; + } + + /* Get access to the OPB MMIO registers */ + opb->regs = ioremap(res.start + 0x10000, 0x1000); + if (!opb->regs) { + printk(KERN_ERR "opb: Failed to allocate register space!\n"); + goto free_opb; + } + + /* Allocate an irq host so that Linux knows that despite only + * having one interrupt to issue, we're the controller for multiple + * hardware IRQs, so later we can lookup their virtual IRQs. */ + + opb->host = irq_alloc_host(dn, IRQ_HOST_MAP_LINEAR, + OPB_NR_IRQS, &opb_host_ops, -1); + + if (!opb->host) { + printk(KERN_ERR "opb: Failed to allocate IRQ host!\n"); + goto free_regs; + } + + opb->index = opb_index++; + spin_lock_init(&opb->lock); + opb->host->host_data = opb; + + /* Disable all interrupts by default */ + opb_out(opb, OPB_MLSASIER, 0); + opb_out(opb, OPB_MLSIER, 0); + + /* ACK any interrupts left by FW */ + opb_out(opb, OPB_MLSIR, 0xFFFFFFFF); + + return opb; + +free_regs: + iounmap(opb->regs); +free_opb: + kfree(opb); + return NULL; +} + +void __init opb_pic_init(void) +{ + struct device_node *dn; + struct opb_pic *opb; + int virq; + int rc; + + /* Call init_one for each OPB device */ + for_each_compatible_node(dn, NULL, "ibm,opb") { + + /* Fill in an OPB struct */ + opb = opb_pic_init_one(dn); + if (!opb) { + printk(KERN_WARNING "opb: Failed to init node, skipped!\n"); + continue; + } + + /* Map / get opb's hardware virtual irq */ + virq = irq_of_parse_and_map(dn, 0); + if (virq <= 0) { + printk("opb: irq_op_parse_and_map failed!\n"); + continue; + } + + /* Attach opb interrupt handler to new virtual IRQ */ + rc = request_irq(virq, opb_irq_handler, 0, "OPB LS Cascade", opb); + if (rc) { + printk("opb: request_irq failed: %d\n", rc); + continue; + } + + printk("OPB%d init with %d IRQs at %p\n", opb->index, + OPB_NR_IRQS, opb->regs); + } +} diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c new file mode 100644 index 00000000000..40f28916ff6 --- /dev/null +++ b/arch/powerpc/platforms/wsp/psr2.c @@ -0,0 +1,95 @@ +/* + * Copyright 2008-2011, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/of.h> +#include <linux/smp.h> + +#include <asm/machdep.h> +#include <asm/system.h> +#include <asm/time.h> +#include <asm/udbg.h> + +#include "ics.h" +#include "wsp.h" + + +static void psr2_spin(void) +{ + hard_irq_disable(); + for (;;) ; +} + +static void psr2_restart(char *cmd) +{ + psr2_spin(); +} + +static int psr2_probe_devices(void) +{ + struct device_node *np; + + /* Our RTC is a ds1500. It seems to be programatically compatible + * with the ds1511 for which we have a driver so let's use that + */ + np = of_find_compatible_node(NULL, NULL, "dallas,ds1500"); + if (np != NULL) { + struct resource res; + if (of_address_to_resource(np, 0, &res) == 0) + platform_device_register_simple("ds1511", 0, &res, 1); + } + return 0; +} +machine_arch_initcall(psr2_md, psr2_probe_devices); + +static void __init psr2_setup_arch(void) +{ + /* init to some ~sane value until calibrate_delay() runs */ + loops_per_jiffy = 50000000; + + scom_init_wsp(); + + /* Setup SMP callback */ +#ifdef CONFIG_SMP + a2_setup_smp(); +#endif +} + +static int __init psr2_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (!of_flat_dt_is_compatible(root, "ibm,psr2")) + return 0; + + return 1; +} + +static void __init psr2_init_irq(void) +{ + wsp_init_irq(); + opb_pic_init(); +} + +define_machine(psr2_md) { + .name = "PSR2 A2", + .probe = psr2_probe, + .setup_arch = psr2_setup_arch, + .restart = psr2_restart, + .power_off = psr2_spin, + .halt = psr2_spin, + .calibrate_decr = generic_calibrate_decr, + .init_IRQ = psr2_init_irq, + .progress = udbg_progress, + .power_save = book3e_idle, +}; diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c new file mode 100644 index 00000000000..141e7803209 --- /dev/null +++ b/arch/powerpc/platforms/wsp/scom_smp.c @@ -0,0 +1,427 @@ +/* + * SCOM support for A2 platforms + * + * Copyright 2007-2011 Benjamin Herrenschmidt, David Gibson, + * Michael Ellerman, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/cpumask.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <asm/cputhreads.h> +#include <asm/reg_a2.h> +#include <asm/scom.h> +#include <asm/udbg.h> + +#include "wsp.h" + +#define SCOM_RAMC 0x2a /* Ram Command */ +#define SCOM_RAMC_TGT1_EXT 0x80000000 +#define SCOM_RAMC_SRC1_EXT 0x40000000 +#define SCOM_RAMC_SRC2_EXT 0x20000000 +#define SCOM_RAMC_SRC3_EXT 0x10000000 +#define SCOM_RAMC_ENABLE 0x00080000 +#define SCOM_RAMC_THREADSEL 0x00060000 +#define SCOM_RAMC_EXECUTE 0x00010000 +#define SCOM_RAMC_MSR_OVERRIDE 0x00008000 +#define SCOM_RAMC_MSR_PR 0x00004000 +#define SCOM_RAMC_MSR_GS 0x00002000 +#define SCOM_RAMC_FORCE 0x00001000 +#define SCOM_RAMC_FLUSH 0x00000800 +#define SCOM_RAMC_INTERRUPT 0x00000004 +#define SCOM_RAMC_ERROR 0x00000002 +#define SCOM_RAMC_DONE 0x00000001 +#define SCOM_RAMI 0x29 /* Ram Instruction */ +#define SCOM_RAMIC 0x28 /* Ram Instruction and Command */ +#define SCOM_RAMIC_INSN 0xffffffff00000000 +#define SCOM_RAMD 0x2d /* Ram Data */ +#define SCOM_RAMDH 0x2e /* Ram Data High */ +#define SCOM_RAMDL 0x2f /* Ram Data Low */ +#define SCOM_PCCR0 0x33 /* PC Configuration Register 0 */ +#define SCOM_PCCR0_ENABLE_DEBUG 0x80000000 +#define SCOM_PCCR0_ENABLE_RAM 0x40000000 +#define SCOM_THRCTL 0x30 /* Thread Control and Status */ +#define SCOM_THRCTL_T0_STOP 0x80000000 +#define SCOM_THRCTL_T1_STOP 0x40000000 +#define SCOM_THRCTL_T2_STOP 0x20000000 +#define SCOM_THRCTL_T3_STOP 0x10000000 +#define SCOM_THRCTL_T0_STEP 0x08000000 +#define SCOM_THRCTL_T1_STEP 0x04000000 +#define SCOM_THRCTL_T2_STEP 0x02000000 +#define SCOM_THRCTL_T3_STEP 0x01000000 +#define SCOM_THRCTL_T0_RUN 0x00800000 +#define SCOM_THRCTL_T1_RUN 0x00400000 +#define SCOM_THRCTL_T2_RUN 0x00200000 +#define SCOM_THRCTL_T3_RUN 0x00100000 +#define SCOM_THRCTL_T0_PM 0x00080000 +#define SCOM_THRCTL_T1_PM 0x00040000 +#define SCOM_THRCTL_T2_PM 0x00020000 +#define SCOM_THRCTL_T3_PM 0x00010000 +#define SCOM_THRCTL_T0_UDE 0x00008000 +#define SCOM_THRCTL_T1_UDE 0x00004000 +#define SCOM_THRCTL_T2_UDE 0x00002000 +#define SCOM_THRCTL_T3_UDE 0x00001000 +#define SCOM_THRCTL_ASYNC_DIS 0x00000800 +#define SCOM_THRCTL_TB_DIS 0x00000400 +#define SCOM_THRCTL_DEC_DIS 0x00000200 +#define SCOM_THRCTL_AND 0x31 /* Thread Control and Status */ +#define SCOM_THRCTL_OR 0x32 /* Thread Control and Status */ + + +static DEFINE_PER_CPU(scom_map_t, scom_ptrs); + +static scom_map_t get_scom(int cpu, struct device_node *np, int *first_thread) +{ + scom_map_t scom = per_cpu(scom_ptrs, cpu); + int tcpu; + + if (scom_map_ok(scom)) { + *first_thread = 0; + return scom; + } + + *first_thread = 1; + + scom = scom_map_device(np, 0); + + for (tcpu = cpu_first_thread_sibling(cpu); + tcpu <= cpu_last_thread_sibling(cpu); tcpu++) + per_cpu(scom_ptrs, tcpu) = scom; + + /* Hack: for the boot core, this will actually get called on + * the second thread up, not the first so our test above will + * set first_thread incorrectly. */ + if (cpu_first_thread_sibling(cpu) == 0) + *first_thread = 0; + + return scom; +} + +static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask) +{ + u64 cmd, mask, val; + int n = 0; + + cmd = ((u64)insn << 32) | (((u64)extmask & 0xf) << 28) + | ((u64)thread << 17) | SCOM_RAMC_ENABLE | SCOM_RAMC_EXECUTE; + mask = SCOM_RAMC_DONE | SCOM_RAMC_INTERRUPT | SCOM_RAMC_ERROR; + + scom_write(scom, SCOM_RAMIC, cmd); + + while (!((val = scom_read(scom, SCOM_RAMC)) & mask)) { + pr_devel("Waiting on RAMC = 0x%llx\n", val); + if (++n == 3) { + pr_err("RAMC timeout on instruction 0x%08x, thread %d\n", + insn, thread); + return -1; + } + } + + if (val & SCOM_RAMC_INTERRUPT) { + pr_err("RAMC interrupt on instruction 0x%08x, thread %d\n", + insn, thread); + return -SCOM_RAMC_INTERRUPT; + } + + if (val & SCOM_RAMC_ERROR) { + pr_err("RAMC error on instruction 0x%08x, thread %d\n", + insn, thread); + return -SCOM_RAMC_ERROR; + } + + return 0; +} + +static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt, + u64 *out_gpr) +{ + int rc; + + /* or rN, rN, rN */ + u32 insn = 0x7c000378 | (gpr << 21) | (gpr << 16) | (gpr << 11); + rc = a2_scom_ram(scom, thread, insn, alt ? 0xf : 0x0); + if (rc) + return rc; + + *out_gpr = scom_read(scom, SCOM_RAMD); + + return 0; +} + +static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr) +{ + int rc, sprhi, sprlo; + u32 insn; + + sprhi = spr >> 5; + sprlo = spr & 0x1f; + insn = 0x7c2002a6 | (sprlo << 16) | (sprhi << 11); /* mfspr r1,spr */ + + if (spr == 0x0ff0) + insn = 0x7c2000a6; /* mfmsr r1 */ + + rc = a2_scom_ram(scom, thread, insn, 0xf); + if (rc) + return rc; + return a2_scom_getgpr(scom, thread, 1, 1, out_spr); +} + +static int a2_scom_setgpr(scom_map_t scom, int thread, int gpr, + int alt, u64 val) +{ + u32 lis = 0x3c000000 | (gpr << 21); + u32 li = 0x38000000 | (gpr << 21); + u32 oris = 0x64000000 | (gpr << 21) | (gpr << 16); + u32 ori = 0x60000000 | (gpr << 21) | (gpr << 16); + u32 rldicr32 = 0x780007c6 | (gpr << 21) | (gpr << 16); + u32 highest = val >> 48; + u32 higher = (val >> 32) & 0xffff; + u32 high = (val >> 16) & 0xffff; + u32 low = val & 0xffff; + int lext = alt ? 0x8 : 0x0; + int oext = alt ? 0xf : 0x0; + int rc = 0; + + if (highest) + rc |= a2_scom_ram(scom, thread, lis | highest, lext); + + if (higher) { + if (highest) + rc |= a2_scom_ram(scom, thread, oris | higher, oext); + else + rc |= a2_scom_ram(scom, thread, li | higher, lext); + } + + if (highest || higher) + rc |= a2_scom_ram(scom, thread, rldicr32, oext); + + if (high) { + if (highest || higher) + rc |= a2_scom_ram(scom, thread, oris | high, oext); + else + rc |= a2_scom_ram(scom, thread, lis | high, lext); + } + + if (highest || higher || high) + rc |= a2_scom_ram(scom, thread, ori | low, oext); + else + rc |= a2_scom_ram(scom, thread, li | low, lext); + + return rc; +} + +static int a2_scom_setspr(scom_map_t scom, int thread, int spr, u64 val) +{ + int sprhi = spr >> 5; + int sprlo = spr & 0x1f; + /* mtspr spr, r1 */ + u32 insn = 0x7c2003a6 | (sprlo << 16) | (sprhi << 11); + + if (spr == 0x0ff0) + insn = 0x7c200124; /* mtmsr r1 */ + + if (a2_scom_setgpr(scom, thread, 1, 1, val)) + return -1; + + return a2_scom_ram(scom, thread, insn, 0xf); +} + +static int a2_scom_initial_tlb(scom_map_t scom, int thread) +{ + extern u32 a2_tlbinit_code_start[], a2_tlbinit_code_end[]; + extern u32 a2_tlbinit_after_iprot_flush[]; + extern u32 a2_tlbinit_after_linear_map[]; + u32 assoc, entries, i; + u64 epn, tlbcfg; + u32 *p; + int rc; + + /* Invalidate all entries (including iprot) */ + + rc = a2_scom_getspr(scom, thread, SPRN_TLB0CFG, &tlbcfg); + if (rc) + goto scom_fail; + entries = tlbcfg & TLBnCFG_N_ENTRY; + assoc = (tlbcfg & TLBnCFG_ASSOC) >> 24; + epn = 0; + + /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ + a2_scom_setspr(scom, thread, SPRN_MMUCR2, 0x000a7531); + /* Set MMUCR3 to write all thids bit to the TLB */ + a2_scom_setspr(scom, thread, SPRN_MMUCR3, 0x0000000f); + + /* Set MAS1 for 1G page size, and MAS2 to our initial EPN */ + a2_scom_setspr(scom, thread, SPRN_MAS1, MAS1_TSIZE(BOOK3E_PAGESZ_1GB)); + a2_scom_setspr(scom, thread, SPRN_MAS2, epn); + for (i = 0; i < entries; i++) { + + a2_scom_setspr(scom, thread, SPRN_MAS0, MAS0_ESEL(i % assoc)); + + /* tlbwe */ + rc = a2_scom_ram(scom, thread, 0x7c0007a4, 0); + if (rc) + goto scom_fail; + + /* Next entry is new address? */ + if((i + 1) % assoc == 0) { + epn += (1 << 30); + a2_scom_setspr(scom, thread, SPRN_MAS2, epn); + } + } + + /* Setup args for linear mapping */ + rc = a2_scom_setgpr(scom, thread, 3, 0, MAS0_TLBSEL(0)); + if (rc) + goto scom_fail; + + /* Linear mapping */ + for (p = a2_tlbinit_code_start; p < a2_tlbinit_after_linear_map; p++) { + rc = a2_scom_ram(scom, thread, *p, 0); + if (rc) + goto scom_fail; + } + + /* + * For the boot thread, between the linear mapping and the debug + * mappings there is a loop to flush iprot mappings. Ramming doesn't do + * branches, but the secondary threads don't need to be nearly as smart + * (i.e. we don't need to worry about invalidating the mapping we're + * standing on). + */ + + /* Debug mappings. Expects r11 = MAS0 from linear map (set above) */ + for (p = a2_tlbinit_after_iprot_flush; p < a2_tlbinit_code_end; p++) { + rc = a2_scom_ram(scom, thread, *p, 0); + if (rc) + goto scom_fail; + } + +scom_fail: + if (rc) + pr_err("Setting up initial TLB failed, err %d\n", rc); + + if (rc == -SCOM_RAMC_INTERRUPT) { + /* Interrupt, dump some status */ + int rc[10]; + u64 iar, srr0, srr1, esr, mas0, mas1, mas2, mas7_3, mas8, ccr2; + rc[0] = a2_scom_getspr(scom, thread, SPRN_IAR, &iar); + rc[1] = a2_scom_getspr(scom, thread, SPRN_SRR0, &srr0); + rc[2] = a2_scom_getspr(scom, thread, SPRN_SRR1, &srr1); + rc[3] = a2_scom_getspr(scom, thread, SPRN_ESR, &esr); + rc[4] = a2_scom_getspr(scom, thread, SPRN_MAS0, &mas0); + rc[5] = a2_scom_getspr(scom, thread, SPRN_MAS1, &mas1); + rc[6] = a2_scom_getspr(scom, thread, SPRN_MAS2, &mas2); + rc[7] = a2_scom_getspr(scom, thread, SPRN_MAS7_MAS3, &mas7_3); + rc[8] = a2_scom_getspr(scom, thread, SPRN_MAS8, &mas8); + rc[9] = a2_scom_getspr(scom, thread, SPRN_A2_CCR2, &ccr2); + pr_err(" -> retreived IAR =0x%llx (err %d)\n", iar, rc[0]); + pr_err(" retreived SRR0=0x%llx (err %d)\n", srr0, rc[1]); + pr_err(" retreived SRR1=0x%llx (err %d)\n", srr1, rc[2]); + pr_err(" retreived ESR =0x%llx (err %d)\n", esr, rc[3]); + pr_err(" retreived MAS0=0x%llx (err %d)\n", mas0, rc[4]); + pr_err(" retreived MAS1=0x%llx (err %d)\n", mas1, rc[5]); + pr_err(" retreived MAS2=0x%llx (err %d)\n", mas2, rc[6]); + pr_err(" retreived MS73=0x%llx (err %d)\n", mas7_3, rc[7]); + pr_err(" retreived MAS8=0x%llx (err %d)\n", mas8, rc[8]); + pr_err(" retreived CCR2=0x%llx (err %d)\n", ccr2, rc[9]); + } + + return rc; +} + +int __devinit a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, + struct device_node *np) +{ + u64 init_iar, init_msr, init_ccr2; + unsigned long start_here; + int rc, core_setup; + scom_map_t scom; + u64 pccr0; + + scom = get_scom(lcpu, np, &core_setup); + if (!scom) { + printk(KERN_ERR "Couldn't map SCOM for CPU%d\n", lcpu); + return -1; + } + + pr_devel("Bringing up CPU%d using SCOM...\n", lcpu); + + pccr0 = scom_read(scom, SCOM_PCCR0); + scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG | + SCOM_PCCR0_ENABLE_RAM); + + /* Stop the thead with THRCTL. If we are setting up the TLB we stop all + * threads. We also disable asynchronous interrupts while RAMing. + */ + if (core_setup) + scom_write(scom, SCOM_THRCTL_OR, + SCOM_THRCTL_T0_STOP | + SCOM_THRCTL_T1_STOP | + SCOM_THRCTL_T2_STOP | + SCOM_THRCTL_T3_STOP | + SCOM_THRCTL_ASYNC_DIS); + else + scom_write(scom, SCOM_THRCTL_OR, SCOM_THRCTL_T0_STOP >> thr_idx); + + /* Flush its pipeline just in case */ + scom_write(scom, SCOM_RAMC, ((u64)thr_idx << 17) | + SCOM_RAMC_FLUSH | SCOM_RAMC_ENABLE); + + a2_scom_getspr(scom, thr_idx, SPRN_IAR, &init_iar); + a2_scom_getspr(scom, thr_idx, 0x0ff0, &init_msr); + a2_scom_getspr(scom, thr_idx, SPRN_A2_CCR2, &init_ccr2); + + /* Set MSR to MSR_CM (0x0ff0 is magic value for MSR_CM) */ + rc = a2_scom_setspr(scom, thr_idx, 0x0ff0, MSR_CM); + if (rc) { + pr_err("Failed to set MSR ! err %d\n", rc); + return rc; + } + + /* RAM in an sync/isync for the sake of it */ + a2_scom_ram(scom, thr_idx, 0x7c0004ac, 0); + a2_scom_ram(scom, thr_idx, 0x4c00012c, 0); + + if (core_setup) { + pr_devel("CPU%d is first thread in core, initializing TLB...\n", + lcpu); + rc = a2_scom_initial_tlb(scom, thr_idx); + if (rc) + goto fail; + } + + start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init + : generic_secondary_thread_init); + pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here); + + rc |= a2_scom_setspr(scom, thr_idx, SPRN_IAR, start_here); + rc |= a2_scom_setgpr(scom, thr_idx, 3, 0, + get_hard_smp_processor_id(lcpu)); + /* + * Tell book3e_secondary_core_init not to set up the TLB, we've + * already done that. + */ + rc |= a2_scom_setgpr(scom, thr_idx, 4, 0, 1); + + rc |= a2_scom_setspr(scom, thr_idx, SPRN_TENS, 0x1 << thr_idx); + + scom_write(scom, SCOM_RAMC, 0); + scom_write(scom, SCOM_THRCTL_AND, ~(SCOM_THRCTL_T0_STOP >> thr_idx)); + scom_write(scom, SCOM_PCCR0, pccr0); +fail: + pr_devel(" SCOM initialization %s\n", rc ? "failed" : "succeeded"); + if (rc) { + pr_err("Old IAR=0x%08llx MSR=0x%08llx CCR2=0x%08llx\n", + init_iar, init_msr, init_ccr2); + } + + return rc; +} diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c new file mode 100644 index 00000000000..4052e2259f3 --- /dev/null +++ b/arch/powerpc/platforms/wsp/scom_wsp.c @@ -0,0 +1,77 @@ +/* + * SCOM backend for WSP + * + * Copyright 2010 Benjamin Herrenschmidt, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/cpumask.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <asm/cputhreads.h> +#include <asm/reg_a2.h> +#include <asm/scom.h> +#include <asm/udbg.h> + +#include "wsp.h" + + +static scom_map_t wsp_scom_map(struct device_node *dev, u64 reg, u64 count) +{ + struct resource r; + u64 xscom_addr; + + if (!of_get_property(dev, "scom-controller", NULL)) { + pr_err("%s: device %s is not a SCOM controller\n", + __func__, dev->full_name); + return SCOM_MAP_INVALID; + } + + if (of_address_to_resource(dev, 0, &r)) { + pr_debug("Failed to find SCOM controller address\n"); + return 0; + } + + /* Transform the SCOM address into an XSCOM offset */ + xscom_addr = ((reg & 0x7f000000) >> 1) | ((reg & 0xfffff) << 3); + + return (scom_map_t)ioremap(r.start + xscom_addr, count << 3); +} + +static void wsp_scom_unmap(scom_map_t map) +{ + iounmap((void *)map); +} + +static u64 wsp_scom_read(scom_map_t map, u32 reg) +{ + u64 __iomem *addr = (u64 __iomem *)map; + + return in_be64(addr + reg); +} + +static void wsp_scom_write(scom_map_t map, u32 reg, u64 value) +{ + u64 __iomem *addr = (u64 __iomem *)map; + + return out_be64(addr + reg, value); +} + +static const struct scom_controller wsp_scom_controller = { + .map = wsp_scom_map, + .unmap = wsp_scom_unmap, + .read = wsp_scom_read, + .write = wsp_scom_write +}; + +void scom_init_wsp(void) +{ + scom_init(&wsp_scom_controller); +} diff --git a/arch/powerpc/platforms/wsp/setup.c b/arch/powerpc/platforms/wsp/setup.c new file mode 100644 index 00000000000..11ac2f05e01 --- /dev/null +++ b/arch/powerpc/platforms/wsp/setup.c @@ -0,0 +1,36 @@ +/* + * Copyright 2010 Michael Ellerman, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/of_platform.h> + +#include "wsp.h" + +/* + * Find chip-id by walking up device tree looking for ibm,wsp-chip-id property. + * Won't work for nodes that are not a descendant of a wsp node. + */ +int wsp_get_chip_id(struct device_node *dn) +{ + const u32 *p; + int rc; + + /* Start looking at the specified node, not its parent */ + dn = of_node_get(dn); + while (dn && !(p = of_get_property(dn, "ibm,wsp-chip-id", NULL))) + dn = of_get_next_parent(dn); + + if (!dn) + return -1; + + rc = *p; + of_node_put(dn); + + return rc; +} diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c new file mode 100644 index 00000000000..9d20fa9d371 --- /dev/null +++ b/arch/powerpc/platforms/wsp/smp.c @@ -0,0 +1,88 @@ +/* + * SMP Support for A2 platforms + * + * Copyright 2007 Benjamin Herrenschmidt, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/smp.h> + +#include <asm/dbell.h> +#include <asm/machdep.h> +#include <asm/xics.h> + +#include "ics.h" +#include "wsp.h" + +static void __devinit smp_a2_setup_cpu(int cpu) +{ + doorbell_setup_this_cpu(); + + if (cpu != boot_cpuid) + xics_setup_cpu(); +} + +int __devinit smp_a2_kick_cpu(int nr) +{ + const char *enable_method; + struct device_node *np; + int thr_idx; + + if (nr < 0 || nr >= NR_CPUS) + return -ENOENT; + + np = of_get_cpu_node(nr, &thr_idx); + if (!np) + return -ENODEV; + + enable_method = of_get_property(np, "enable-method", NULL); + pr_devel("CPU%d has enable-method: \"%s\"\n", nr, enable_method); + + if (!enable_method) { + printk(KERN_ERR "CPU%d has no enable-method\n", nr); + return -ENOENT; + } else if (strcmp(enable_method, "ibm,a2-scom") == 0) { + if (a2_scom_startup_cpu(nr, thr_idx, np)) + return -1; + } else { + printk(KERN_ERR "CPU%d: Don't understand enable-method \"%s\"\n", + nr, enable_method); + return -EINVAL; + } + + /* + * The processor is currently spinning, waiting for the + * cpu_start field to become non-zero After we set cpu_start, + * the processor will continue on to secondary_start + */ + paca[nr].cpu_start = 1; + + return 0; +} + +static int __init smp_a2_probe(void) +{ + return cpus_weight(cpu_possible_map); +} + +static struct smp_ops_t a2_smp_ops = { + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = doorbell_cause_ipi, + .probe = smp_a2_probe, + .kick_cpu = smp_a2_kick_cpu, + .setup_cpu = smp_a2_setup_cpu, +}; + +void __init a2_setup_smp(void) +{ + smp_ops = &a2_smp_ops; +} diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h new file mode 100644 index 00000000000..7c3e087fd2f --- /dev/null +++ b/arch/powerpc/platforms/wsp/wsp.h @@ -0,0 +1,17 @@ +#ifndef __WSP_H +#define __WSP_H + +#include <asm/wsp.h> + +extern void wsp_setup_pci(void); +extern void scom_init_wsp(void); + +extern void a2_setup_smp(void); +extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, + struct device_node *np); +int smp_a2_cpu_bootable(unsigned int nr); +int __devinit smp_a2_kick_cpu(int nr); + +void opb_pic_init(void); + +#endif /* __WSP_H */ diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index 396582835cb..d775fd148d1 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -12,3 +12,13 @@ config PPC_MSI_BITMAP depends on PCI_MSI default y if MPIC default y if FSL_PCI + +source "arch/powerpc/sysdev/xics/Kconfig" + +config PPC_SCOM + bool + +config SCOM_DEBUGFS + bool "Expose SCOM controllers via debugfs" + depends on PPC_SCOM + default n diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 1e0c933ef77..6076e0074a8 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -57,3 +57,9 @@ obj-$(CONFIG_PPC_MPC52xx) += mpc5xxx_clocks.o ifeq ($(CONFIG_SUSPEND),y) obj-$(CONFIG_6xx) += 6xx-suspend.o endif + +obj-$(CONFIG_PPC_SCOM) += scom.o + +subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror + +obj-$(CONFIG_PPC_XICS) += xics/ diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 1636dd89670..bd0d54060b9 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -216,7 +216,7 @@ static int axon_ram_probe(struct platform_device *device) AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20); bank->ph_addr = resource.start; - bank->io_addr = (unsigned long) ioremap_flags( + bank->io_addr = (unsigned long) ioremap_prot( bank->ph_addr, bank->size, _PAGE_NO_CACHE); if (bank->io_addr == 0) { dev_err(&device->dev, "ioremap() failed\n"); diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index e0bc944eb23..350787c83e2 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -58,21 +58,21 @@ static struct irq_host *cpm_pic_host; static void cpm_mask_irq(struct irq_data *d) { - unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq; + unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d); clrbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec)); } static void cpm_unmask_irq(struct irq_data *d) { - unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq; + unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d); setbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec)); } static void cpm_end_irq(struct irq_data *d) { - unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq; + unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d); out_be32(&cpic_reg->cpic_cisr, (1 << cpm_vec)); } @@ -157,7 +157,7 @@ unsigned int cpm_pic_init(void) goto end; /* Initialize the CPM interrupt controller. */ - hwirq = (unsigned int)irq_map[sirq].hwirq; + hwirq = (unsigned int)virq_to_hw(sirq); out_be32(&cpic_reg->cpic_cicr, (CICR_SCD_SCC4 | CICR_SCC_SCC3 | CICR_SCB_SCC2 | CICR_SCA_SCC1) | ((hwirq/2) << 13) | CICR_HP_MASK); diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c index 5495c1be472..bcab50e2a9e 100644 --- a/arch/powerpc/sysdev/cpm2_pic.c +++ b/arch/powerpc/sysdev/cpm2_pic.c @@ -81,7 +81,7 @@ static const u_char irq_to_siubit[] = { static void cpm2_mask_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = virq_to_hw(d->irq); + unsigned int irq_nr = irqd_to_hwirq(d); bit = irq_to_siubit[irq_nr]; word = irq_to_siureg[irq_nr]; @@ -93,7 +93,7 @@ static void cpm2_mask_irq(struct irq_data *d) static void cpm2_unmask_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = virq_to_hw(d->irq); + unsigned int irq_nr = irqd_to_hwirq(d); bit = irq_to_siubit[irq_nr]; word = irq_to_siureg[irq_nr]; @@ -105,7 +105,7 @@ static void cpm2_unmask_irq(struct irq_data *d) static void cpm2_ack(struct irq_data *d) { int bit, word; - unsigned int irq_nr = virq_to_hw(d->irq); + unsigned int irq_nr = irqd_to_hwirq(d); bit = irq_to_siubit[irq_nr]; word = irq_to_siureg[irq_nr]; @@ -116,7 +116,7 @@ static void cpm2_ack(struct irq_data *d) static void cpm2_end_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = virq_to_hw(d->irq); + unsigned int irq_nr = irqd_to_hwirq(d); bit = irq_to_siubit[irq_nr]; word = irq_to_siureg[irq_nr]; @@ -133,7 +133,7 @@ static void cpm2_end_irq(struct irq_data *d) static int cpm2_set_irq_type(struct irq_data *d, unsigned int flow_type) { - unsigned int src = virq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned int vold, vnew, edibit; /* Port C interrupts are either IRQ_TYPE_EDGE_FALLING or diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c index 54fb1922fe3..11641589917 100644 --- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c +++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c @@ -106,10 +106,10 @@ int __init instantiate_cache_sram(struct platform_device *dev, goto out_free; } - cache_sram->base_virt = ioremap_flags(cache_sram->base_phys, + cache_sram->base_virt = ioremap_prot(cache_sram->base_phys, cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL); if (!cache_sram->base_virt) { - dev_err(&dev->dev, "%s: ioremap_flags failed\n", + dev_err(&dev->dev, "%s: ioremap_prot failed\n", dev->dev.of_node->full_name); ret = -ENOMEM; goto out_release; diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 01cd2f08951..92e78333c47 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -110,7 +110,7 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev) list_for_each_entry(entry, &pdev->msi_list, list) { if (entry->irq == NO_IRQ) continue; - msi_data = irq_get_handler_data(entry->irq); + msi_data = irq_get_chip_data(entry->irq); irq_set_msi_desc(entry->irq, NULL); msi_bitmap_free_hwirqs(&msi_data->bitmap, virq_to_hw(entry->irq), 1); @@ -168,7 +168,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) rc = -ENOSPC; goto out_free; } - irq_set_handler_data(virq, msi_data); + /* chip_data is msi_data via host->hostdata in host->map() */ irq_set_msi_desc(virq, entry); fsl_compose_msi_msg(pdev, hwirq, &msg, msi_data); @@ -193,7 +193,7 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc) u32 have_shift = 0; struct fsl_msi_cascade_data *cascade_data; - cascade_data = (struct fsl_msi_cascade_data *)irq_get_handler_data(irq); + cascade_data = irq_get_handler_data(irq); msi_data = cascade_data->msi_data; raw_spin_lock(&desc->lock); @@ -253,7 +253,7 @@ unlock: static int fsl_of_msi_remove(struct platform_device *ofdev) { - struct fsl_msi *msi = ofdev->dev.platform_data; + struct fsl_msi *msi = platform_get_drvdata(ofdev); int virq, i; struct fsl_msi_cascade_data *cascade_data; @@ -330,7 +330,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev) dev_err(&dev->dev, "No memory for MSI structure\n"); return -ENOMEM; } - dev->dev.platform_data = msi; + platform_set_drvdata(dev, msi); msi->irqhost = irq_alloc_host(dev->dev.of_node, IRQ_HOST_MAP_LINEAR, NR_MSI_IRQS, &fsl_msi_host_ops, 0); diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c index 142770cb84b..d18bb27e4df 100644 --- a/arch/powerpc/sysdev/i8259.c +++ b/arch/powerpc/sysdev/i8259.c @@ -185,18 +185,6 @@ static int i8259_host_map(struct irq_host *h, unsigned int virq, return 0; } -static void i8259_host_unmap(struct irq_host *h, unsigned int virq) -{ - /* Make sure irq is masked in hardware */ - i8259_mask_irq(irq_get_irq_data(virq)); - - /* remove chip and handler */ - irq_set_chip_and_handler(virq, NULL, NULL); - - /* Make sure it's completed */ - synchronize_irq(virq); -} - static int i8259_host_xlate(struct irq_host *h, struct device_node *ct, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_flags) @@ -220,7 +208,6 @@ static int i8259_host_xlate(struct irq_host *h, struct device_node *ct, static struct irq_host_ops i8259_host_ops = { .match = i8259_host_match, .map = i8259_host_map, - .unmap = i8259_host_unmap, .xlate = i8259_host_xlate, }; diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index fa438be962b..f0ece79f9be 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -521,12 +521,10 @@ static inline struct ipic * ipic_from_irq(unsigned int virq) return primary_ipic; } -#define ipic_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) - static void ipic_unmask_irq(struct irq_data *d) { struct ipic *ipic = ipic_from_irq(d->irq); - unsigned int src = ipic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; @@ -542,7 +540,7 @@ static void ipic_unmask_irq(struct irq_data *d) static void ipic_mask_irq(struct irq_data *d) { struct ipic *ipic = ipic_from_irq(d->irq); - unsigned int src = ipic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; @@ -562,7 +560,7 @@ static void ipic_mask_irq(struct irq_data *d) static void ipic_ack_irq(struct irq_data *d) { struct ipic *ipic = ipic_from_irq(d->irq); - unsigned int src = ipic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; @@ -581,7 +579,7 @@ static void ipic_ack_irq(struct irq_data *d) static void ipic_mask_irq_and_ack(struct irq_data *d) { struct ipic *ipic = ipic_from_irq(d->irq); - unsigned int src = ipic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; @@ -604,7 +602,7 @@ static void ipic_mask_irq_and_ack(struct irq_data *d) static int ipic_set_irq_type(struct irq_data *d, unsigned int flow_type) { struct ipic *ipic = ipic_from_irq(d->irq); - unsigned int src = ipic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned int vold, vnew, edibit; if (flow_type == IRQ_TYPE_NONE) @@ -793,7 +791,7 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags) int ipic_set_priority(unsigned int virq, unsigned int priority) { struct ipic *ipic = ipic_from_irq(virq); - unsigned int src = ipic_irq_to_hw(virq); + unsigned int src = virq_to_hw(virq); u32 temp; if (priority > 7) @@ -821,7 +819,7 @@ int ipic_set_priority(unsigned int virq, unsigned int priority) void ipic_set_highest_priority(unsigned int virq) { struct ipic *ipic = ipic_from_irq(virq); - unsigned int src = ipic_irq_to_hw(virq); + unsigned int src = virq_to_hw(virq); u32 temp; temp = ipic_read(ipic->regs, IPIC_SICFR); diff --git a/arch/powerpc/sysdev/mmio_nvram.c b/arch/powerpc/sysdev/mmio_nvram.c index 20732420906..ddc877a3a23 100644 --- a/arch/powerpc/sysdev/mmio_nvram.c +++ b/arch/powerpc/sysdev/mmio_nvram.c @@ -115,6 +115,8 @@ int __init mmio_nvram_init(void) int ret; nvram_node = of_find_node_by_type(NULL, "nvram"); + if (!nvram_node) + nvram_node = of_find_compatible_node(NULL, NULL, "nvram"); if (!nvram_node) { printk(KERN_WARNING "nvram: no node found in device-tree\n"); return -ENODEV; diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c index a88800ff4d0..20924f2246f 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.c +++ b/arch/powerpc/sysdev/mpc8xx_pic.c @@ -28,7 +28,7 @@ int cpm_get_irq(struct pt_regs *regs); static void mpc8xx_unmask_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq; + unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d); bit = irq_nr & 0x1f; word = irq_nr >> 5; @@ -40,7 +40,7 @@ static void mpc8xx_unmask_irq(struct irq_data *d) static void mpc8xx_mask_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq; + unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d); bit = irq_nr & 0x1f; word = irq_nr >> 5; @@ -52,7 +52,7 @@ static void mpc8xx_mask_irq(struct irq_data *d) static void mpc8xx_ack(struct irq_data *d) { int bit; - unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq; + unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d); bit = irq_nr & 0x1f; out_be32(&siu_reg->sc_sipend, 1 << (31-bit)); @@ -61,7 +61,7 @@ static void mpc8xx_ack(struct irq_data *d) static void mpc8xx_end_irq(struct irq_data *d) { int bit, word; - unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq; + unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d); bit = irq_nr & 0x1f; word = irq_nr >> 5; @@ -73,7 +73,7 @@ static void mpc8xx_end_irq(struct irq_data *d) static int mpc8xx_set_irq_type(struct irq_data *d, unsigned int flow_type) { if (flow_type & IRQ_TYPE_EDGE_FALLING) { - irq_hw_number_t hw = (unsigned int)irq_map[d->irq].hwirq; + irq_hw_number_t hw = (unsigned int)irqd_to_hwirq(d); unsigned int siel = in_be32(&siu_reg->sc_siel); /* only external IRQ senses are programmable */ diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c index 0892a2841c2..fb4963abdf5 100644 --- a/arch/powerpc/sysdev/mpc8xxx_gpio.c +++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c @@ -163,7 +163,7 @@ static void mpc8xxx_irq_unmask(struct irq_data *d) spin_lock_irqsave(&mpc8xxx_gc->lock, flags); - setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(d->irq))); + setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d))); spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); } @@ -176,7 +176,7 @@ static void mpc8xxx_irq_mask(struct irq_data *d) spin_lock_irqsave(&mpc8xxx_gc->lock, flags); - clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(d->irq))); + clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d))); spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); } @@ -186,7 +186,7 @@ static void mpc8xxx_irq_ack(struct irq_data *d) struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d); struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; - out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(virq_to_hw(d->irq))); + out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(irqd_to_hwirq(d))); } static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type) @@ -199,14 +199,14 @@ static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type) case IRQ_TYPE_EDGE_FALLING: spin_lock_irqsave(&mpc8xxx_gc->lock, flags); setbits32(mm->regs + GPIO_ICR, - mpc8xxx_gpio2mask(virq_to_hw(d->irq))); + mpc8xxx_gpio2mask(irqd_to_hwirq(d))); spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); break; case IRQ_TYPE_EDGE_BOTH: spin_lock_irqsave(&mpc8xxx_gc->lock, flags); clrbits32(mm->regs + GPIO_ICR, - mpc8xxx_gpio2mask(virq_to_hw(d->irq))); + mpc8xxx_gpio2mask(irqd_to_hwirq(d))); spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags); break; @@ -221,7 +221,7 @@ static int mpc512x_irq_set_type(struct irq_data *d, unsigned int flow_type) { struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d); struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc; - unsigned long gpio = virq_to_hw(d->irq); + unsigned long gpio = irqd_to_hwirq(d); void __iomem *reg; unsigned int shift; unsigned long flags; diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index f91c065bed5..53121f62506 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -607,8 +607,6 @@ static int irq_choose_cpu(const struct cpumask *mask) } #endif -#define mpic_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) - /* Find an mpic associated with a given linux interrupt */ static struct mpic *mpic_find(unsigned int irq) { @@ -621,7 +619,7 @@ static struct mpic *mpic_find(unsigned int irq) /* Determine if the linux irq is an IPI */ static unsigned int mpic_is_ipi(struct mpic *mpic, unsigned int irq) { - unsigned int src = mpic_irq_to_hw(irq); + unsigned int src = virq_to_hw(irq); return (src >= mpic->ipi_vecs[0] && src <= mpic->ipi_vecs[3]); } @@ -633,7 +631,7 @@ static inline u32 mpic_physmask(u32 cpumask) int i; u32 mask = 0; - for (i = 0; i < NR_CPUS; ++i, cpumask >>= 1) + for (i = 0; i < min(32, NR_CPUS); ++i, cpumask >>= 1) mask |= (cpumask & 1) << get_hard_smp_processor_id(i); return mask; } @@ -674,7 +672,7 @@ void mpic_unmask_irq(struct irq_data *d) { unsigned int loops = 100000; struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); DBG("%p: %s: enable_irq: %d (src %d)\n", mpic, mpic->name, d->irq, src); @@ -695,7 +693,7 @@ void mpic_mask_irq(struct irq_data *d) { unsigned int loops = 100000; struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); DBG("%s: disable_irq: %d (src %d)\n", mpic->name, d->irq, src); @@ -733,7 +731,7 @@ void mpic_end_irq(struct irq_data *d) static void mpic_unmask_ht_irq(struct irq_data *d) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); mpic_unmask_irq(d); @@ -744,7 +742,7 @@ static void mpic_unmask_ht_irq(struct irq_data *d) static unsigned int mpic_startup_ht_irq(struct irq_data *d) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); mpic_unmask_irq(d); mpic_startup_ht_interrupt(mpic, src, irqd_is_level_type(d)); @@ -755,7 +753,7 @@ static unsigned int mpic_startup_ht_irq(struct irq_data *d) static void mpic_shutdown_ht_irq(struct irq_data *d) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); mpic_shutdown_ht_interrupt(mpic, src); mpic_mask_irq(d); @@ -764,7 +762,7 @@ static void mpic_shutdown_ht_irq(struct irq_data *d) static void mpic_end_ht_irq(struct irq_data *d) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); #ifdef DEBUG_IRQ DBG("%s: end_irq: %d\n", mpic->name, d->irq); @@ -785,7 +783,7 @@ static void mpic_end_ht_irq(struct irq_data *d) static void mpic_unmask_ipi(struct irq_data *d) { struct mpic *mpic = mpic_from_ipi(d); - unsigned int src = mpic_irq_to_hw(d->irq) - mpic->ipi_vecs[0]; + unsigned int src = virq_to_hw(d->irq) - mpic->ipi_vecs[0]; DBG("%s: enable_ipi: %d (ipi %d)\n", mpic->name, d->irq, src); mpic_ipi_write(src, mpic_ipi_read(src) & ~MPIC_VECPRI_MASK); @@ -816,23 +814,19 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool force) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); if (mpic->flags & MPIC_SINGLE_DEST_CPU) { int cpuid = irq_choose_cpu(cpumask); mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), 1 << cpuid); } else { - cpumask_var_t tmp; - - alloc_cpumask_var(&tmp, GFP_KERNEL); + u32 mask = cpumask_bits(cpumask)[0]; - cpumask_and(tmp, cpumask, cpu_online_mask); + mask &= cpumask_bits(cpu_online_mask)[0]; mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), - mpic_physmask(cpumask_bits(tmp)[0])); - - free_cpumask_var(tmp); + mpic_physmask(mask)); } return 0; @@ -862,7 +856,7 @@ static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type) int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type) { struct mpic *mpic = mpic_from_irq_data(d); - unsigned int src = mpic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned int vecpri, vold, vnew; DBG("mpic: set_irq_type(mpic:@%p,virq:%d,src:0x%x,type:0x%x)\n", @@ -898,7 +892,7 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type) void mpic_set_vector(unsigned int virq, unsigned int vector) { struct mpic *mpic = mpic_from_irq(virq); - unsigned int src = mpic_irq_to_hw(virq); + unsigned int src = virq_to_hw(virq); unsigned int vecpri; DBG("mpic: set_vector(mpic:@%p,virq:%d,src:%d,vector:0x%x)\n", @@ -916,7 +910,7 @@ void mpic_set_vector(unsigned int virq, unsigned int vector) void mpic_set_destination(unsigned int virq, unsigned int cpuid) { struct mpic *mpic = mpic_from_irq(virq); - unsigned int src = mpic_irq_to_hw(virq); + unsigned int src = virq_to_hw(virq); DBG("mpic: set_destination(mpic:@%p,virq:%d,src:%d,cpuid:0x%x)\n", mpic, virq, src, cpuid); @@ -1427,7 +1421,7 @@ void __init mpic_set_serial_int(struct mpic *mpic, int enable) void mpic_irq_set_priority(unsigned int irq, unsigned int pri) { struct mpic *mpic = mpic_find(irq); - unsigned int src = mpic_irq_to_hw(irq); + unsigned int src = virq_to_hw(irq); unsigned long flags; u32 reg; @@ -1619,46 +1613,28 @@ void mpic_request_ipis(void) } } -static void mpic_send_ipi(unsigned int ipi_no, const struct cpumask *cpu_mask) +void smp_mpic_message_pass(int cpu, int msg) { struct mpic *mpic = mpic_primary; + u32 physmask; BUG_ON(mpic == NULL); -#ifdef DEBUG_IPI - DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, ipi_no); -#endif - - mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + - ipi_no * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), - mpic_physmask(cpumask_bits(cpu_mask)[0])); -} - -void smp_mpic_message_pass(int target, int msg) -{ - cpumask_var_t tmp; - /* make sure we're sending something that translates to an IPI */ if ((unsigned int)msg > 3) { printk("SMP %d: smp_message_pass: unknown msg %d\n", smp_processor_id(), msg); return; } - switch (target) { - case MSG_ALL: - mpic_send_ipi(msg, cpu_online_mask); - break; - case MSG_ALL_BUT_SELF: - alloc_cpumask_var(&tmp, GFP_NOWAIT); - cpumask_andnot(tmp, cpu_online_mask, - cpumask_of(smp_processor_id())); - mpic_send_ipi(msg, tmp); - free_cpumask_var(tmp); - break; - default: - mpic_send_ipi(msg, cpumask_of(target)); - break; - } + +#ifdef DEBUG_IPI + DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, msg); +#endif + + physmask = 1 << get_hard_smp_processor_id(cpu); + + mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + + msg * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), physmask); } int __init smp_mpic_probe(void) diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c index e9c633c7c08..14d130268e7 100644 --- a/arch/powerpc/sysdev/mv64x60_pic.c +++ b/arch/powerpc/sysdev/mv64x60_pic.c @@ -78,7 +78,7 @@ static struct irq_host *mv64x60_irq_host; static void mv64x60_mask_low(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -91,7 +91,7 @@ static void mv64x60_mask_low(struct irq_data *d) static void mv64x60_unmask_low(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -115,7 +115,7 @@ static struct irq_chip mv64x60_chip_low = { static void mv64x60_mask_high(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -128,7 +128,7 @@ static void mv64x60_mask_high(struct irq_data *d) static void mv64x60_unmask_high(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -152,7 +152,7 @@ static struct irq_chip mv64x60_chip_high = { static void mv64x60_mask_gpp(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -165,7 +165,7 @@ static void mv64x60_mask_gpp(struct irq_data *d) static void mv64x60_mask_ack_gpp(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); @@ -180,7 +180,7 @@ static void mv64x60_mask_ack_gpp(struct irq_data *d) static void mv64x60_unmask_gpp(struct irq_data *d) { - int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK; + int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK; unsigned long flags; spin_lock_irqsave(&mv64x60_lock, flags); diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c index 832d6924ad1..b2acda07220 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c @@ -197,12 +197,10 @@ static inline struct qe_ic *qe_ic_from_irq_data(struct irq_data *d) return irq_data_get_irq_chip_data(d); } -#define virq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) - static void qe_ic_unmask_irq(struct irq_data *d) { struct qe_ic *qe_ic = qe_ic_from_irq_data(d); - unsigned int src = virq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; @@ -218,7 +216,7 @@ static void qe_ic_unmask_irq(struct irq_data *d) static void qe_ic_mask_irq(struct irq_data *d) { struct qe_ic *qe_ic = qe_ic_from_irq_data(d); - unsigned int src = virq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 temp; diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c new file mode 100644 index 00000000000..b2593ce30c9 --- /dev/null +++ b/arch/powerpc/sysdev/scom.c @@ -0,0 +1,192 @@ +/* + * Copyright 2010 Benjamin Herrenschmidt, IBM Corp + * <benh@kernel.crashing.org> + * and David Gibson, IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/kernel.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <asm/prom.h> +#include <asm/scom.h> + +const struct scom_controller *scom_controller; +EXPORT_SYMBOL_GPL(scom_controller); + +struct device_node *scom_find_parent(struct device_node *node) +{ + struct device_node *par, *tmp; + const u32 *p; + + for (par = of_node_get(node); par;) { + if (of_get_property(par, "scom-controller", NULL)) + break; + p = of_get_property(par, "scom-parent", NULL); + tmp = par; + if (p == NULL) + par = of_get_parent(par); + else + par = of_find_node_by_phandle(*p); + of_node_put(tmp); + } + return par; +} +EXPORT_SYMBOL_GPL(scom_find_parent); + +scom_map_t scom_map_device(struct device_node *dev, int index) +{ + struct device_node *parent; + unsigned int cells, size; + const u32 *prop; + u64 reg, cnt; + scom_map_t ret; + + parent = scom_find_parent(dev); + + if (parent == NULL) + return 0; + + prop = of_get_property(parent, "#scom-cells", NULL); + cells = prop ? *prop : 1; + + prop = of_get_property(dev, "scom-reg", &size); + if (!prop) + return 0; + size >>= 2; + + if (index >= (size / (2*cells))) + return 0; + + reg = of_read_number(&prop[index * cells * 2], cells); + cnt = of_read_number(&prop[index * cells * 2 + cells], cells); + + ret = scom_map(parent, reg, cnt); + of_node_put(parent); + + return ret; +} +EXPORT_SYMBOL_GPL(scom_map_device); + +#ifdef CONFIG_SCOM_DEBUGFS +struct scom_debug_entry { + struct device_node *dn; + unsigned long addr; + scom_map_t map; + spinlock_t lock; + char name[8]; + struct debugfs_blob_wrapper blob; +}; + +static int scom_addr_set(void *data, u64 val) +{ + struct scom_debug_entry *ent = data; + + ent->addr = 0; + scom_unmap(ent->map); + + ent->map = scom_map(ent->dn, val, 1); + if (scom_map_ok(ent->map)) + ent->addr = val; + else + return -EFAULT; + + return 0; +} + +static int scom_addr_get(void *data, u64 *val) +{ + struct scom_debug_entry *ent = data; + *val = ent->addr; + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(scom_addr_fops, scom_addr_get, scom_addr_set, + "0x%llx\n"); + +static int scom_val_set(void *data, u64 val) +{ + struct scom_debug_entry *ent = data; + + if (!scom_map_ok(ent->map)) + return -EFAULT; + + scom_write(ent->map, 0, val); + + return 0; +} + +static int scom_val_get(void *data, u64 *val) +{ + struct scom_debug_entry *ent = data; + + if (!scom_map_ok(ent->map)) + return -EFAULT; + + *val = scom_read(ent->map, 0); + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(scom_val_fops, scom_val_get, scom_val_set, + "0x%llx\n"); + +static int scom_debug_init_one(struct dentry *root, struct device_node *dn, + int i) +{ + struct scom_debug_entry *ent; + struct dentry *dir; + + ent = kzalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + + ent->dn = of_node_get(dn); + ent->map = SCOM_MAP_INVALID; + spin_lock_init(&ent->lock); + snprintf(ent->name, 8, "scom%d", i); + ent->blob.data = dn->full_name; + ent->blob.size = strlen(dn->full_name); + + dir = debugfs_create_dir(ent->name, root); + if (!dir) { + of_node_put(dn); + kfree(ent); + return -1; + } + + debugfs_create_file("addr", 0600, dir, ent, &scom_addr_fops); + debugfs_create_file("value", 0600, dir, ent, &scom_val_fops); + debugfs_create_blob("path", 0400, dir, &ent->blob); + + return 0; +} + +static int scom_debug_init(void) +{ + struct device_node *dn; + struct dentry *root; + int i, rc; + + root = debugfs_create_dir("scom", powerpc_debugfs_root); + if (!root) + return -1; + + i = rc = 0; + for_each_node_with_property(dn, "scom-controller") + rc |= scom_debug_init_one(root, dn, i++); + + return rc; +} +device_initcall(scom_debug_init); +#endif /* CONFIG_SCOM_DEBUGFS */ diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index 5d913851662..984cd202915 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -41,8 +41,6 @@ #define UIC_VR 0x7 #define UIC_VCR 0x8 -#define uic_irq_to_hw(virq) (irq_map[virq].hwirq) - struct uic *primary_uic; struct uic { @@ -58,7 +56,7 @@ struct uic { static void uic_unmask_irq(struct irq_data *d) { struct uic *uic = irq_data_get_irq_chip_data(d); - unsigned int src = uic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 er, sr; @@ -76,7 +74,7 @@ static void uic_unmask_irq(struct irq_data *d) static void uic_mask_irq(struct irq_data *d) { struct uic *uic = irq_data_get_irq_chip_data(d); - unsigned int src = uic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 er; @@ -90,7 +88,7 @@ static void uic_mask_irq(struct irq_data *d) static void uic_ack_irq(struct irq_data *d) { struct uic *uic = irq_data_get_irq_chip_data(d); - unsigned int src = uic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; spin_lock_irqsave(&uic->lock, flags); @@ -101,7 +99,7 @@ static void uic_ack_irq(struct irq_data *d) static void uic_mask_ack_irq(struct irq_data *d) { struct uic *uic = irq_data_get_irq_chip_data(d); - unsigned int src = uic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; u32 er, sr; @@ -126,7 +124,7 @@ static void uic_mask_ack_irq(struct irq_data *d) static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) { struct uic *uic = irq_data_get_irq_chip_data(d); - unsigned int src = uic_irq_to_hw(d->irq); + unsigned int src = irqd_to_hwirq(d); unsigned long flags; int trigger, polarity; u32 tr, pr, mask; diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig new file mode 100644 index 00000000000..0031eda320c --- /dev/null +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -0,0 +1,13 @@ +config PPC_XICS + def_bool n + select PPC_SMP_MUXED_IPI + +config PPC_ICP_NATIVE + def_bool n + +config PPC_ICP_HV + def_bool n + +config PPC_ICS_RTAS + def_bool n + diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile new file mode 100644 index 00000000000..b75a6059337 --- /dev/null +++ b/arch/powerpc/sysdev/xics/Makefile @@ -0,0 +1,6 @@ +subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror + +obj-y += xics-common.o +obj-$(CONFIG_PPC_ICP_NATIVE) += icp-native.o +obj-$(CONFIG_PPC_ICP_HV) += icp-hv.o +obj-$(CONFIG_PPC_ICS_RTAS) += ics-rtas.o diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c new file mode 100644 index 00000000000..9518d367a64 --- /dev/null +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -0,0 +1,164 @@ +/* + * Copyright 2011 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/of.h> + +#include <asm/smp.h> +#include <asm/irq.h> +#include <asm/errno.h> +#include <asm/xics.h> +#include <asm/io.h> +#include <asm/hvcall.h> + +static inline unsigned int icp_hv_get_xirr(unsigned char cppr) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_XIRR, retbuf, cppr); + if (rc != H_SUCCESS) + panic(" bad return code xirr - rc = %lx\n", rc); + return (unsigned int)retbuf[0]; +} + +static inline void icp_hv_set_xirr(unsigned int value) +{ + long rc = plpar_hcall_norets(H_EOI, value); + if (rc != H_SUCCESS) + panic("bad return code EOI - rc = %ld, value=%x\n", rc, value); +} + +static inline void icp_hv_set_cppr(u8 value) +{ + long rc = plpar_hcall_norets(H_CPPR, value); + if (rc != H_SUCCESS) + panic("bad return code cppr - rc = %lx\n", rc); +} + +static inline void icp_hv_set_qirr(int n_cpu , u8 value) +{ + long rc = plpar_hcall_norets(H_IPI, get_hard_smp_processor_id(n_cpu), + value); + if (rc != H_SUCCESS) + panic("bad return code qirr - rc = %lx\n", rc); +} + +static void icp_hv_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + + iosync(); + icp_hv_set_xirr((xics_pop_cppr() << 24) | hw_irq); +} + +static void icp_hv_teardown_cpu(void) +{ + int cpu = smp_processor_id(); + + /* Clear any pending IPI */ + icp_hv_set_qirr(cpu, 0xff); +} + +static void icp_hv_flush_ipi(void) +{ + /* We take the ipi irq but and never return so we + * need to EOI the IPI, but want to leave our priority 0 + * + * should we check all the other interrupts too? + * should we be flagging idle loop instead? + * or creating some task to be scheduled? + */ + + icp_hv_set_xirr((0x00 << 24) | XICS_IPI); +} + +static unsigned int icp_hv_get_irq(void) +{ + unsigned int xirr = icp_hv_get_xirr(xics_cppr_top()); + unsigned int vec = xirr & 0x00ffffff; + unsigned int irq; + + if (vec == XICS_IRQ_SPURIOUS) + return NO_IRQ; + + irq = irq_radix_revmap_lookup(xics_host, vec); + if (likely(irq != NO_IRQ)) { + xics_push_cppr(vec); + return irq; + } + + /* We don't have a linux mapping, so have rtas mask it. */ + xics_mask_unknown_vec(vec); + + /* We might learn about it later, so EOI it */ + icp_hv_set_xirr(xirr); + + return NO_IRQ; +} + +static void icp_hv_set_cpu_priority(unsigned char cppr) +{ + xics_set_base_cppr(cppr); + icp_hv_set_cppr(cppr); + iosync(); +} + +#ifdef CONFIG_SMP + +static void icp_hv_cause_ipi(int cpu, unsigned long data) +{ + icp_hv_set_qirr(cpu, IPI_PRIORITY); +} + +static irqreturn_t icp_hv_ipi_action(int irq, void *dev_id) +{ + int cpu = smp_processor_id(); + + icp_hv_set_qirr(cpu, 0xff); + + return smp_ipi_demux(); +} + +#endif /* CONFIG_SMP */ + +static const struct icp_ops icp_hv_ops = { + .get_irq = icp_hv_get_irq, + .eoi = icp_hv_eoi, + .set_priority = icp_hv_set_cpu_priority, + .teardown_cpu = icp_hv_teardown_cpu, + .flush_ipi = icp_hv_flush_ipi, +#ifdef CONFIG_SMP + .ipi_action = icp_hv_ipi_action, + .cause_ipi = icp_hv_cause_ipi, +#endif +}; + +int icp_hv_init(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, "ibm,ppc-xicp"); + if (!np) + np = of_find_node_by_type(NULL, + "PowerPC-External-Interrupt-Presentation"); + if (!np) + return -ENODEV; + + icp_ops = &icp_hv_ops; + + return 0; +} + diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c new file mode 100644 index 00000000000..1f15ad43614 --- /dev/null +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -0,0 +1,293 @@ +/* + * Copyright 2011 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <linux/spinlock.h> + +#include <asm/prom.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/irq.h> +#include <asm/errno.h> +#include <asm/xics.h> + +struct icp_ipl { + union { + u32 word; + u8 bytes[4]; + } xirr_poll; + union { + u32 word; + u8 bytes[4]; + } xirr; + u32 dummy; + union { + u32 word; + u8 bytes[4]; + } qirr; + u32 link_a; + u32 link_b; + u32 link_c; +}; + +static struct icp_ipl __iomem *icp_native_regs[NR_CPUS]; + +static inline unsigned int icp_native_get_xirr(void) +{ + int cpu = smp_processor_id(); + + return in_be32(&icp_native_regs[cpu]->xirr.word); +} + +static inline void icp_native_set_xirr(unsigned int value) +{ + int cpu = smp_processor_id(); + + out_be32(&icp_native_regs[cpu]->xirr.word, value); +} + +static inline void icp_native_set_cppr(u8 value) +{ + int cpu = smp_processor_id(); + + out_8(&icp_native_regs[cpu]->xirr.bytes[0], value); +} + +static inline void icp_native_set_qirr(int n_cpu, u8 value) +{ + out_8(&icp_native_regs[n_cpu]->qirr.bytes[0], value); +} + +static void icp_native_set_cpu_priority(unsigned char cppr) +{ + xics_set_base_cppr(cppr); + icp_native_set_cppr(cppr); + iosync(); +} + +static void icp_native_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + + iosync(); + icp_native_set_xirr((xics_pop_cppr() << 24) | hw_irq); +} + +static void icp_native_teardown_cpu(void) +{ + int cpu = smp_processor_id(); + + /* Clear any pending IPI */ + icp_native_set_qirr(cpu, 0xff); +} + +static void icp_native_flush_ipi(void) +{ + /* We take the ipi irq but and never return so we + * need to EOI the IPI, but want to leave our priority 0 + * + * should we check all the other interrupts too? + * should we be flagging idle loop instead? + * or creating some task to be scheduled? + */ + + icp_native_set_xirr((0x00 << 24) | XICS_IPI); +} + +static unsigned int icp_native_get_irq(void) +{ + unsigned int xirr = icp_native_get_xirr(); + unsigned int vec = xirr & 0x00ffffff; + unsigned int irq; + + if (vec == XICS_IRQ_SPURIOUS) + return NO_IRQ; + + irq = irq_radix_revmap_lookup(xics_host, vec); + if (likely(irq != NO_IRQ)) { + xics_push_cppr(vec); + return irq; + } + + /* We don't have a linux mapping, so have rtas mask it. */ + xics_mask_unknown_vec(vec); + + /* We might learn about it later, so EOI it */ + icp_native_set_xirr(xirr); + + return NO_IRQ; +} + +#ifdef CONFIG_SMP + +static void icp_native_cause_ipi(int cpu, unsigned long data) +{ + icp_native_set_qirr(cpu, IPI_PRIORITY); +} + +static irqreturn_t icp_native_ipi_action(int irq, void *dev_id) +{ + int cpu = smp_processor_id(); + + icp_native_set_qirr(cpu, 0xff); + + return smp_ipi_demux(); +} + +#endif /* CONFIG_SMP */ + +static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr, + unsigned long size) +{ + char *rname; + int i, cpu = -1; + + /* This may look gross but it's good enough for now, we don't quite + * have a hard -> linux processor id matching. + */ + for_each_possible_cpu(i) { + if (!cpu_present(i)) + continue; + if (hw_id == get_hard_smp_processor_id(i)) { + cpu = i; + break; + } + } + + /* Fail, skip that CPU. Don't print, it's normal, some XICS come up + * with way more entries in there than you have CPUs + */ + if (cpu == -1) + return 0; + + rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation", + cpu, hw_id); + + if (!request_mem_region(addr, size, rname)) { + pr_warning("icp_native: Could not reserve ICP MMIO" + " for CPU %d, interrupt server #0x%x\n", + cpu, hw_id); + return -EBUSY; + } + + icp_native_regs[cpu] = ioremap(addr, size); + if (!icp_native_regs[cpu]) { + pr_warning("icp_native: Failed ioremap for CPU %d, " + "interrupt server #0x%x, addr %#lx\n", + cpu, hw_id, addr); + release_mem_region(addr, size); + return -ENOMEM; + } + return 0; +} + +static int __init icp_native_init_one_node(struct device_node *np, + unsigned int *indx) +{ + unsigned int ilen; + const u32 *ireg; + int i; + int reg_tuple_size; + int num_servers = 0; + + /* This code does the theorically broken assumption that the interrupt + * server numbers are the same as the hard CPU numbers. + * This happens to be the case so far but we are playing with fire... + * should be fixed one of these days. -BenH. + */ + ireg = of_get_property(np, "ibm,interrupt-server-ranges", &ilen); + + /* Do that ever happen ? we'll know soon enough... but even good'old + * f80 does have that property .. + */ + WARN_ON((ireg == NULL) || (ilen != 2*sizeof(u32))); + + if (ireg) { + *indx = of_read_number(ireg, 1); + if (ilen >= 2*sizeof(u32)) + num_servers = of_read_number(ireg + 1, 1); + } + + ireg = of_get_property(np, "reg", &ilen); + if (!ireg) { + pr_err("icp_native: Can't find interrupt reg property"); + return -1; + } + + reg_tuple_size = (of_n_addr_cells(np) + of_n_size_cells(np)) * 4; + if (((ilen % reg_tuple_size) != 0) + || (num_servers && (num_servers != (ilen / reg_tuple_size)))) { + pr_err("icp_native: ICP reg len (%d) != num servers (%d)", + ilen / reg_tuple_size, num_servers); + return -1; + } + + for (i = 0; i < (ilen / reg_tuple_size); i++) { + struct resource r; + int err; + + err = of_address_to_resource(np, i, &r); + if (err) { + pr_err("icp_native: Could not translate ICP MMIO" + " for interrupt server 0x%x (%d)\n", *indx, err); + return -1; + } + + if (icp_native_map_one_cpu(*indx, r.start, r.end - r.start)) + return -1; + + (*indx)++; + } + return 0; +} + +static const struct icp_ops icp_native_ops = { + .get_irq = icp_native_get_irq, + .eoi = icp_native_eoi, + .set_priority = icp_native_set_cpu_priority, + .teardown_cpu = icp_native_teardown_cpu, + .flush_ipi = icp_native_flush_ipi, +#ifdef CONFIG_SMP + .ipi_action = icp_native_ipi_action, + .cause_ipi = icp_native_cause_ipi, +#endif +}; + +int icp_native_init(void) +{ + struct device_node *np; + u32 indx = 0; + int found = 0; + + for_each_compatible_node(np, NULL, "ibm,ppc-xicp") + if (icp_native_init_one_node(np, &indx) == 0) + found = 1; + if (!found) { + for_each_node_by_type(np, + "PowerPC-External-Interrupt-Presentation") { + if (icp_native_init_one_node(np, &indx) == 0) + found = 1; + } + } + + if (found == 0) + return -ENODEV; + + icp_ops = &icp_native_ops; + + return 0; +} diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c new file mode 100644 index 00000000000..c782f85cf7e --- /dev/null +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -0,0 +1,240 @@ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <linux/spinlock.h> +#include <linux/msi.h> + +#include <asm/prom.h> +#include <asm/smp.h> +#include <asm/machdep.h> +#include <asm/irq.h> +#include <asm/errno.h> +#include <asm/xics.h> +#include <asm/rtas.h> + +/* RTAS service tokens */ +static int ibm_get_xive; +static int ibm_set_xive; +static int ibm_int_on; +static int ibm_int_off; + +static int ics_rtas_map(struct ics *ics, unsigned int virq); +static void ics_rtas_mask_unknown(struct ics *ics, unsigned long vec); +static long ics_rtas_get_server(struct ics *ics, unsigned long vec); +static int ics_rtas_host_match(struct ics *ics, struct device_node *node); + +/* Only one global & state struct ics */ +static struct ics ics_rtas = { + .map = ics_rtas_map, + .mask_unknown = ics_rtas_mask_unknown, + .get_server = ics_rtas_get_server, + .host_match = ics_rtas_host_match, +}; + +static void ics_rtas_unmask_irq(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + int call_status; + int server; + + pr_devel("xics: unmask virq %d [hw 0x%x]\n", d->irq, hw_irq); + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return; + + server = xics_get_irq_server(d->irq, d->affinity, 0); + + call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hw_irq, server, + DEFAULT_PRIORITY); + if (call_status != 0) { + printk(KERN_ERR + "%s: ibm_set_xive irq %u server %x returned %d\n", + __func__, hw_irq, server, call_status); + return; + } + + /* Now unmask the interrupt (often a no-op) */ + call_status = rtas_call(ibm_int_on, 1, 1, NULL, hw_irq); + if (call_status != 0) { + printk(KERN_ERR "%s: ibm_int_on irq=%u returned %d\n", + __func__, hw_irq, call_status); + return; + } +} + +static unsigned int ics_rtas_startup(struct irq_data *d) +{ +#ifdef CONFIG_PCI_MSI + /* + * The generic MSI code returns with the interrupt disabled on the + * card, using the MSI mask bits. Firmware doesn't appear to unmask + * at that level, so we do it here by hand. + */ + if (d->msi_desc) + unmask_msi_irq(d); +#endif + /* unmask it */ + ics_rtas_unmask_irq(d); + return 0; +} + +static void ics_rtas_mask_real_irq(unsigned int hw_irq) +{ + int call_status; + + if (hw_irq == XICS_IPI) + return; + + call_status = rtas_call(ibm_int_off, 1, 1, NULL, hw_irq); + if (call_status != 0) { + printk(KERN_ERR "%s: ibm_int_off irq=%u returned %d\n", + __func__, hw_irq, call_status); + return; + } + + /* Have to set XIVE to 0xff to be able to remove a slot */ + call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hw_irq, + xics_default_server, 0xff); + if (call_status != 0) { + printk(KERN_ERR "%s: ibm_set_xive(0xff) irq=%u returned %d\n", + __func__, hw_irq, call_status); + return; + } +} + +static void ics_rtas_mask_irq(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + + pr_devel("xics: mask virq %d [hw 0x%x]\n", d->irq, hw_irq); + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return; + ics_rtas_mask_real_irq(hw_irq); +} + +static int ics_rtas_set_affinity(struct irq_data *d, + const struct cpumask *cpumask, + bool force) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + int status; + int xics_status[2]; + int irq_server; + + if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) + return -1; + + status = rtas_call(ibm_get_xive, 1, 3, xics_status, hw_irq); + + if (status) { + printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", + __func__, hw_irq, status); + return -1; + } + + irq_server = xics_get_irq_server(d->irq, cpumask, 1); + if (irq_server == -1) { + char cpulist[128]; + cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); + printk(KERN_WARNING + "%s: No online cpus in the mask %s for irq %d\n", + __func__, cpulist, d->irq); + return -1; + } + + status = rtas_call(ibm_set_xive, 3, 1, NULL, + hw_irq, irq_server, xics_status[1]); + + if (status) { + printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", + __func__, hw_irq, status); + return -1; + } + + return IRQ_SET_MASK_OK; +} + +static struct irq_chip ics_rtas_irq_chip = { + .name = "XICS", + .irq_startup = ics_rtas_startup, + .irq_mask = ics_rtas_mask_irq, + .irq_unmask = ics_rtas_unmask_irq, + .irq_eoi = NULL, /* Patched at init time */ + .irq_set_affinity = ics_rtas_set_affinity +}; + +static int ics_rtas_map(struct ics *ics, unsigned int virq) +{ + unsigned int hw_irq = (unsigned int)virq_to_hw(virq); + int status[2]; + int rc; + + if (WARN_ON(hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)) + return -EINVAL; + + /* Check if RTAS knows about this interrupt */ + rc = rtas_call(ibm_get_xive, 1, 3, status, hw_irq); + if (rc) + return -ENXIO; + + irq_set_chip_and_handler(virq, &ics_rtas_irq_chip, handle_fasteoi_irq); + irq_set_chip_data(virq, &ics_rtas); + + return 0; +} + +static void ics_rtas_mask_unknown(struct ics *ics, unsigned long vec) +{ + ics_rtas_mask_real_irq(vec); +} + +static long ics_rtas_get_server(struct ics *ics, unsigned long vec) +{ + int rc, status[2]; + + rc = rtas_call(ibm_get_xive, 1, 3, status, vec); + if (rc) + return -1; + return status[0]; +} + +static int ics_rtas_host_match(struct ics *ics, struct device_node *node) +{ + /* IBM machines have interrupt parents of various funky types for things + * like vdevices, events, etc... The trick we use here is to match + * everything here except the legacy 8259 which is compatible "chrp,iic" + */ + return !of_device_is_compatible(node, "chrp,iic"); +} + +int ics_rtas_init(void) +{ + ibm_get_xive = rtas_token("ibm,get-xive"); + ibm_set_xive = rtas_token("ibm,set-xive"); + ibm_int_on = rtas_token("ibm,int-on"); + ibm_int_off = rtas_token("ibm,int-off"); + + /* We enable the RTAS "ICS" if RTAS is present with the + * appropriate tokens + */ + if (ibm_get_xive == RTAS_UNKNOWN_SERVICE || + ibm_set_xive == RTAS_UNKNOWN_SERVICE) + return -ENODEV; + + /* We need to patch our irq chip's EOI to point to the + * right ICP + */ + ics_rtas_irq_chip.irq_eoi = icp_ops->eoi; + + /* Register ourselves */ + xics_register_ics(&ics_rtas); + + return 0; +} + diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c new file mode 100644 index 00000000000..445c5a01b76 --- /dev/null +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -0,0 +1,443 @@ +/* + * Copyright 2011 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include <linux/types.h> +#include <linux/threads.h> +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/debugfs.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include <asm/prom.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/machdep.h> +#include <asm/irq.h> +#include <asm/errno.h> +#include <asm/rtas.h> +#include <asm/xics.h> +#include <asm/firmware.h> + +/* Globals common to all ICP/ICS implementations */ +const struct icp_ops *icp_ops; + +unsigned int xics_default_server = 0xff; +unsigned int xics_default_distrib_server = 0; +unsigned int xics_interrupt_server_size = 8; + +DEFINE_PER_CPU(struct xics_cppr, xics_cppr); + +struct irq_host *xics_host; + +static LIST_HEAD(ics_list); + +void xics_update_irq_servers(void) +{ + int i, j; + struct device_node *np; + u32 ilen; + const u32 *ireg; + u32 hcpuid; + + /* Find the server numbers for the boot cpu. */ + np = of_get_cpu_node(boot_cpuid, NULL); + BUG_ON(!np); + + hcpuid = get_hard_smp_processor_id(boot_cpuid); + xics_default_server = xics_default_distrib_server = hcpuid; + + pr_devel("xics: xics_default_server = 0x%x\n", xics_default_server); + + ireg = of_get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen); + if (!ireg) { + of_node_put(np); + return; + } + + i = ilen / sizeof(int); + + /* Global interrupt distribution server is specified in the last + * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last + * entry fom this property for current boot cpu id and use it as + * default distribution server + */ + for (j = 0; j < i; j += 2) { + if (ireg[j] == hcpuid) { + xics_default_distrib_server = ireg[j+1]; + break; + } + } + pr_devel("xics: xics_default_distrib_server = 0x%x\n", + xics_default_distrib_server); + of_node_put(np); +} + +/* GIQ stuff, currently only supported on RTAS setups, will have + * to be sorted properly for bare metal + */ +void xics_set_cpu_giq(unsigned int gserver, unsigned int join) +{ +#ifdef CONFIG_PPC_RTAS + int index; + int status; + + if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL)) + return; + + index = (1UL << xics_interrupt_server_size) - 1 - gserver; + + status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join); + + WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n", + GLOBAL_INTERRUPT_QUEUE, index, join, status); +#endif +} + +void xics_setup_cpu(void) +{ + icp_ops->set_priority(LOWEST_PRIORITY); + + xics_set_cpu_giq(xics_default_distrib_server, 1); +} + +void xics_mask_unknown_vec(unsigned int vec) +{ + struct ics *ics; + + pr_err("Interrupt 0x%x (real) is invalid, disabling it.\n", vec); + + list_for_each_entry(ics, &ics_list, link) + ics->mask_unknown(ics, vec); +} + + +#ifdef CONFIG_SMP + +static void xics_request_ipi(void) +{ + unsigned int ipi; + + ipi = irq_create_mapping(xics_host, XICS_IPI); + BUG_ON(ipi == NO_IRQ); + + /* + * IPIs are marked IRQF_DISABLED as they must run with irqs + * disabled, and PERCPU. The handler was set in map. + */ + BUG_ON(request_irq(ipi, icp_ops->ipi_action, + IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL)); +} + +int __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 cpumask_weight(cpu_possible_mask); +} + +#endif /* CONFIG_SMP */ + +void xics_teardown_cpu(void) +{ + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + + /* + * we have to reset the cppr index to 0 because we're + * not going to return from the IPI + */ + os_cppr->index = 0; + icp_ops->set_priority(0); + icp_ops->teardown_cpu(); +} + +void xics_kexec_teardown_cpu(int secondary) +{ + xics_teardown_cpu(); + + icp_ops->flush_ipi(); + + /* + * Some machines need to have at least one cpu in the GIQ, + * so leave the master cpu in the group. + */ + if (secondary) + xics_set_cpu_giq(xics_default_distrib_server, 0); +} + + +#ifdef CONFIG_HOTPLUG_CPU + +/* Interrupts are disabled. */ +void xics_migrate_irqs_away(void) +{ + int cpu = smp_processor_id(), hw_cpu = hard_smp_processor_id(); + unsigned int irq, virq; + + /* If we used to be the default server, move to the new "boot_cpuid" */ + if (hw_cpu == xics_default_server) + xics_update_irq_servers(); + + /* Reject any interrupt that was queued to us... */ + icp_ops->set_priority(0); + + /* Remove ourselves from the global interrupt queue */ + xics_set_cpu_giq(xics_default_distrib_server, 0); + + /* Allow IPIs again... */ + icp_ops->set_priority(DEFAULT_PRIORITY); + + for_each_irq(virq) { + struct irq_desc *desc; + struct irq_chip *chip; + long server; + unsigned long flags; + struct ics *ics; + + /* We can't set affinity on ISA interrupts */ + if (virq < NUM_ISA_INTERRUPTS) + continue; + if (!virq_is_host(virq, xics_host)) + continue; + irq = (unsigned int)virq_to_hw(virq); + /* We need to get IPIs still. */ + if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS) + continue; + desc = irq_to_desc(virq); + /* We only need to migrate enabled IRQS */ + if (!desc || !desc->action) + continue; + chip = irq_desc_get_chip(desc); + if (!chip || !chip->irq_set_affinity) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + + /* Locate interrupt server */ + server = -1; + ics = irq_get_chip_data(virq); + if (ics) + server = ics->get_server(ics, irq); + if (server < 0) { + printk(KERN_ERR "%s: Can't find server for irq %d\n", + __func__, irq); + goto unlock; + } + + /* We only support delivery to all cpus or to one cpu. + * The irq has to be migrated only in the single cpu + * case. + */ + if (server != hw_cpu) + goto unlock; + + /* This is expected during cpu offline. */ + if (cpu_online(cpu)) + pr_warning("IRQ %u affinity broken off cpu %u\n", + virq, cpu); + + /* Reset affinity to all cpus */ + raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_set_affinity(virq, cpu_all_mask); + continue; +unlock: + raw_spin_unlock_irqrestore(&desc->lock, flags); + } +} +#endif /* CONFIG_HOTPLUG_CPU */ + +#ifdef CONFIG_SMP +/* + * For the moment we only implement delivery to all cpus or one cpu. + * + * If the requested affinity is cpu_all_mask, we set global affinity. + * If not we set it to the first cpu in the mask, even if multiple cpus + * are set. This is so things like irqbalance (which set core and package + * wide affinities) do the right thing. + * + * We need to fix this to implement support for the links + */ +int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, + unsigned int strict_check) +{ + + if (!distribute_irqs) + return xics_default_server; + + if (!cpumask_subset(cpu_possible_mask, cpumask)) { + int server = cpumask_first_and(cpu_online_mask, cpumask); + + if (server < nr_cpu_ids) + return get_hard_smp_processor_id(server); + + if (strict_check) + return -1; + } + + /* + * Workaround issue with some versions of JS20 firmware that + * deliver interrupts to cpus which haven't been started. This + * happens when using the maxcpus= boot option. + */ + if (cpumask_equal(cpu_online_mask, cpu_present_mask)) + return xics_default_distrib_server; + + return xics_default_server; +} +#endif /* CONFIG_SMP */ + +static int xics_host_match(struct irq_host *h, struct device_node *node) +{ + struct ics *ics; + + list_for_each_entry(ics, &ics_list, link) + if (ics->host_match(ics, node)) + return 1; + + return 0; +} + +/* Dummies */ +static void xics_ipi_unmask(struct irq_data *d) { } +static void xics_ipi_mask(struct irq_data *d) { } + +static struct irq_chip xics_ipi_chip = { + .name = "XICS", + .irq_eoi = NULL, /* Patched at init time */ + .irq_mask = xics_ipi_mask, + .irq_unmask = xics_ipi_unmask, +}; + +static int xics_host_map(struct irq_host *h, unsigned int virq, + irq_hw_number_t hw) +{ + struct ics *ics; + + pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); + + /* Insert the interrupt mapping into the radix tree for fast lookup */ + irq_radix_revmap_insert(xics_host, virq, hw); + + /* They aren't all level sensitive but we just don't really know */ + irq_set_status_flags(virq, IRQ_LEVEL); + + /* Don't call into ICS for IPIs */ + if (hw == XICS_IPI) { + irq_set_chip_and_handler(virq, &xics_ipi_chip, + handle_percpu_irq); + return 0; + } + + /* Let the ICS setup the chip data */ + list_for_each_entry(ics, &ics_list, link) + if (ics->map(ics, virq) == 0) + return 0; + + return -EINVAL; +} + +static int xics_host_xlate(struct irq_host *h, struct device_node *ct, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_flags) + +{ + /* Current xics implementation translates everything + * to level. It is not technically right for MSIs but this + * is irrelevant at this point. We might get smarter in the future + */ + *out_hwirq = intspec[0]; + *out_flags = IRQ_TYPE_LEVEL_LOW; + + return 0; +} + +static struct irq_host_ops xics_host_ops = { + .match = xics_host_match, + .map = xics_host_map, + .xlate = xics_host_xlate, +}; + +static void __init xics_init_host(void) +{ + xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, &xics_host_ops, + XICS_IRQ_SPURIOUS); + BUG_ON(xics_host == NULL); + irq_set_default_host(xics_host); +} + +void __init xics_register_ics(struct ics *ics) +{ + list_add(&ics->link, &ics_list); +} + +static void __init xics_get_server_size(void) +{ + struct device_node *np; + const u32 *isize; + + /* We fetch the interrupt server size from the first ICS node + * we find if any + */ + np = of_find_compatible_node(NULL, NULL, "ibm,ppc-xics"); + if (!np) + return; + isize = of_get_property(np, "ibm,interrupt-server#-size", NULL); + if (!isize) + return; + xics_interrupt_server_size = *isize; + of_node_put(np); +} + +void __init xics_init(void) +{ + int rc = -1; + + /* Fist locate ICP */ +#ifdef CONFIG_PPC_ICP_HV + if (firmware_has_feature(FW_FEATURE_LPAR)) + rc = icp_hv_init(); +#endif +#ifdef CONFIG_PPC_ICP_NATIVE + if (rc < 0) + rc = icp_native_init(); +#endif + if (rc < 0) { + pr_warning("XICS: Cannot find a Presentation Controller !\n"); + return; + } + + /* Copy get_irq callback over to ppc_md */ + ppc_md.get_irq = icp_ops->get_irq; + + /* Patch up IPI chip EOI */ + xics_ipi_chip.irq_eoi = icp_ops->eoi; + + /* Now locate ICS */ +#ifdef CONFIG_PPC_ICS_RTAS + rc = ics_rtas_init(); +#endif + if (rc < 0) + pr_warning("XICS: Cannot find a Source Controller !\n"); + + /* Initialize common bits */ + xics_get_server_size(); + xics_update_irq_servers(); + xics_init_host(); + xics_setup_cpu(); +} diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c index 0a13fc19e28..6183799754a 100644 --- a/arch/powerpc/sysdev/xilinx_intc.c +++ b/arch/powerpc/sysdev/xilinx_intc.c @@ -71,7 +71,7 @@ static unsigned char xilinx_intc_map_senses[] = { */ static void xilinx_intc_mask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void * regs = irq_data_get_irq_chip_data(d); pr_debug("mask: %d\n", irq); out_be32(regs + XINTC_CIE, 1 << irq); @@ -87,7 +87,7 @@ static int xilinx_intc_set_type(struct irq_data *d, unsigned int flow_type) */ static void xilinx_intc_level_unmask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void * regs = irq_data_get_irq_chip_data(d); pr_debug("unmask: %d\n", irq); out_be32(regs + XINTC_SIE, 1 << irq); @@ -112,7 +112,7 @@ static struct irq_chip xilinx_intc_level_irqchip = { */ static void xilinx_intc_edge_unmask(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void *regs = irq_data_get_irq_chip_data(d); pr_debug("unmask: %d\n", irq); out_be32(regs + XINTC_SIE, 1 << irq); @@ -120,7 +120,7 @@ static void xilinx_intc_edge_unmask(struct irq_data *d) static void xilinx_intc_edge_ack(struct irq_data *d) { - int irq = virq_to_hw(d->irq); + int irq = irqd_to_hwirq(d); void * regs = irq_data_get_irq_chip_data(d); pr_debug("ack: %d\n", irq); out_be32(regs + XINTC_IAR, 1 << irq); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 33794c1d92c..42541bbcc7f 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -334,7 +334,7 @@ static void release_output_lock(void) int cpus_are_in_xmon(void) { - return !cpus_empty(cpus_in_xmon); + return !cpumask_empty(&cpus_in_xmon); } #endif @@ -373,7 +373,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) #ifdef CONFIG_SMP cpu = smp_processor_id(); - if (cpu_isset(cpu, cpus_in_xmon)) { + if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { get_output_lock(); excprint(regs); printf("cpu 0x%x: Exception %lx %s in xmon, " @@ -396,10 +396,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } xmon_fault_jmp[cpu] = recurse_jmp; - cpu_set(cpu, cpus_in_xmon); + cpumask_set_cpu(cpu, &cpus_in_xmon); bp = NULL; - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) == (MSR_IR|MSR_SF)) + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) bp = at_breakpoint(regs->nip); if (bp || unrecoverable_excp(regs)) fromipi = 0; @@ -437,10 +437,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) xmon_owner = cpu; mb(); if (ncpus > 1) { - smp_send_debugger_break(MSG_ALL_BUT_SELF); + smp_send_debugger_break(); /* wait for other cpus to come in */ for (timeout = 100000000; timeout != 0; --timeout) { - if (cpus_weight(cpus_in_xmon) >= ncpus) + if (cpumask_weight(&cpus_in_xmon) >= ncpus) break; barrier(); } @@ -484,7 +484,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } } leave: - cpu_clear(cpu, cpus_in_xmon); + cpumask_clear_cpu(cpu, &cpus_in_xmon); xmon_fault_jmp[cpu] = NULL; #else /* UP is simple... */ @@ -529,7 +529,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } } #else - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) == (MSR_IR|MSR_SF)) { + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) { bp = at_breakpoint(regs->nip); if (bp != NULL) { int stepped = emulate_step(regs, bp->instr[0]); @@ -578,7 +578,7 @@ static int xmon_bpt(struct pt_regs *regs) struct bpt *bp; unsigned long offset; - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) != (MSR_IR|MSR_SF)) + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) != (MSR_IR|MSR_64BIT)) return 0; /* Are we at the trap at bp->instr[1] for some bp? */ @@ -609,7 +609,7 @@ static int xmon_sstep(struct pt_regs *regs) static int xmon_dabr_match(struct pt_regs *regs) { - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) != (MSR_IR|MSR_SF)) + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) != (MSR_IR|MSR_64BIT)) return 0; if (dabr.enabled == 0) return 0; @@ -619,7 +619,7 @@ static int xmon_dabr_match(struct pt_regs *regs) static int xmon_iabr_match(struct pt_regs *regs) { - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) != (MSR_IR|MSR_SF)) + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) != (MSR_IR|MSR_64BIT)) return 0; if (iabr == NULL) return 0; @@ -630,7 +630,7 @@ static int xmon_iabr_match(struct pt_regs *regs) static int xmon_ipi(struct pt_regs *regs) { #ifdef CONFIG_SMP - if (in_xmon && !cpu_isset(smp_processor_id(), cpus_in_xmon)) + if (in_xmon && !cpumask_test_cpu(smp_processor_id(), &cpus_in_xmon)) xmon_core(regs, 1); #endif return 0; @@ -644,7 +644,7 @@ static int xmon_fault_handler(struct pt_regs *regs) if (in_xmon && catch_memory_errors) handle_fault(regs); /* doesn't return */ - if ((regs->msr & (MSR_IR|MSR_PR|MSR_SF)) == (MSR_IR|MSR_SF)) { + if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) { bp = in_breakpoint_table(regs->nip, &offset); if (bp != NULL) { regs->nip = bp->address + offset; @@ -929,7 +929,7 @@ static int do_step(struct pt_regs *regs) int stepped; /* check we are in 64-bit kernel mode, translation enabled */ - if ((regs->msr & (MSR_SF|MSR_PR|MSR_IR)) == (MSR_SF|MSR_IR)) { + if ((regs->msr & (MSR_64BIT|MSR_PR|MSR_IR)) == (MSR_64BIT|MSR_IR)) { if (mread(regs->nip, &instr, 4) == 4) { stepped = emulate_step(regs, instr); if (stepped < 0) { @@ -976,7 +976,7 @@ static int cpu_cmd(void) printf("cpus stopped:"); count = 0; for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu_isset(cpu, cpus_in_xmon)) { + if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); ++count; @@ -992,7 +992,7 @@ static int cpu_cmd(void) return 0; } /* try to switch to cpu specified */ - if (!cpu_isset(cpu, cpus_in_xmon)) { + if (!cpumask_test_cpu(cpu, &cpus_in_xmon)) { printf("cpu 0x%x isn't in xmon\n", cpu); return 0; } @@ -1497,6 +1497,10 @@ static void prregs(struct pt_regs *fp) #endif printf("pc = "); xmon_print_symbol(fp->nip, " ", "\n"); + if (TRAP(fp) != 0xc00 && cpu_has_feature(CPU_FTR_CFAR)) { + printf("cfar= "); + xmon_print_symbol(fp->orig_gpr3, " ", "\n"); + } printf("lr = "); xmon_print_symbol(fp->link, " ", "\n"); printf("msr = "REG" cr = %.8lx\n", fp->msr, fp->ccr); @@ -2663,7 +2667,7 @@ static void dump_stab(void) void dump_segments(void) { - if (cpu_has_feature(CPU_FTR_SLB)) + if (mmu_has_feature(MMU_FTR_SLB)) dump_slb(); else dump_stab(); diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index a4a6c2f044b..cf39bc08ce0 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -295,7 +295,7 @@ static int bsr_create_devs(struct device_node *bn) static int __init bsr_init(void) { struct device_node *np; - dev_t bsr_dev = MKDEV(bsr_major, 0); + dev_t bsr_dev; int ret = -ENODEV; int result; diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 24af12fc822..c0221eec881 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -269,11 +269,8 @@ struct t4_swsqe { static inline pgprot_t t4_pgprot_wc(pgprot_t prot) { -#if defined(__i386__) || defined(__x86_64__) +#if defined(__i386__) || defined(__x86_64__) || defined(CONFIG_PPC64) return pgprot_writecombine(prot); -#elif defined(CONFIG_PPC64) - return __pgprot((pgprot_val(prot) | _PAGE_NO_CACHE) & - ~(pgprot_t)_PAGE_GUARDED); #else return pgprot_noncached(prot); #endif diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 4e007c6a4b4..d80dcdee88f 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -481,5 +481,6 @@ source "drivers/misc/cb710/Kconfig" source "drivers/misc/iwmc3200top/Kconfig" source "drivers/misc/ti-st/Kconfig" source "drivers/misc/lis3lv02d/Kconfig" +source "drivers/misc/carma/Kconfig" endif # MISC_DEVICES diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index f5468602961..848e8464faa 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -44,3 +44,4 @@ obj-$(CONFIG_PCH_PHUB) += pch_phub.o obj-y += ti-st/ obj-$(CONFIG_AB8500_PWM) += ab8500-pwm.o obj-y += lis3lv02d/ +obj-y += carma/ diff --git a/drivers/misc/carma/Kconfig b/drivers/misc/carma/Kconfig new file mode 100644 index 00000000000..c90370ed712 --- /dev/null +++ b/drivers/misc/carma/Kconfig @@ -0,0 +1,17 @@ +config CARMA_FPGA + tristate "CARMA DATA-FPGA Access Driver" + depends on FSL_SOC && PPC_83xx && MEDIA_SUPPORT && HAS_DMA && FSL_DMA + select VIDEOBUF_DMA_SG + default n + help + Say Y here to include support for communicating with the data + processing FPGAs on the OVRO CARMA board. + +config CARMA_FPGA_PROGRAM + tristate "CARMA DATA-FPGA Programmer" + depends on FSL_SOC && PPC_83xx && MEDIA_SUPPORT && HAS_DMA && FSL_DMA + select VIDEOBUF_DMA_SG + default n + help + Say Y here to include support for programming the data processing + FPGAs on the OVRO CARMA board. diff --git a/drivers/misc/carma/Makefile b/drivers/misc/carma/Makefile new file mode 100644 index 00000000000..ff36ac2ce53 --- /dev/null +++ b/drivers/misc/carma/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_CARMA_FPGA) += carma-fpga.o +obj-$(CONFIG_CARMA_FPGA_PROGRAM) += carma-fpga-program.o diff --git a/drivers/misc/carma/carma-fpga-program.c b/drivers/misc/carma/carma-fpga-program.c new file mode 100644 index 00000000000..7ce6065dc20 --- /dev/null +++ b/drivers/misc/carma/carma-fpga-program.c @@ -0,0 +1,1141 @@ +/* + * CARMA Board DATA-FPGA Programmer + * + * Copyright (c) 2009-2011 Ira W. Snyder <iws@ovro.caltech.edu> + * + * 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/dma-mapping.h> +#include <linux/of_platform.h> +#include <linux/completion.h> +#include <linux/miscdevice.h> +#include <linux/dmaengine.h> +#include <linux/interrupt.h> +#include <linux/highmem.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/leds.h> +#include <linux/slab.h> +#include <linux/kref.h> +#include <linux/fs.h> +#include <linux/io.h> + +#include <media/videobuf-dma-sg.h> + +/* MPC8349EMDS specific get_immrbase() */ +#include <sysdev/fsl_soc.h> + +static const char drv_name[] = "carma-fpga-program"; + +/* + * Firmware images are always this exact size + * + * 12849552 bytes for a CARMA Digitizer Board (EP2S90 FPGAs) + * 18662880 bytes for a CARMA Correlator Board (EP2S130 FPGAs) + */ +#define FW_SIZE_EP2S90 12849552 +#define FW_SIZE_EP2S130 18662880 + +struct fpga_dev { + struct miscdevice miscdev; + + /* Reference count */ + struct kref ref; + + /* Device Registers */ + struct device *dev; + void __iomem *regs; + void __iomem *immr; + + /* Freescale DMA Device */ + struct dma_chan *chan; + + /* Interrupts */ + int irq, status; + struct completion completion; + + /* FPGA Bitfile */ + struct mutex lock; + + struct videobuf_dmabuf vb; + bool vb_allocated; + + /* max size and written bytes */ + size_t fw_size; + size_t bytes; +}; + +/* + * FPGA Bitfile Helpers + */ + +/** + * fpga_drop_firmware_data() - drop the bitfile image from memory + * @priv: the driver's private data structure + * + * LOCKING: must hold priv->lock + */ +static void fpga_drop_firmware_data(struct fpga_dev *priv) +{ + videobuf_dma_free(&priv->vb); + priv->vb_allocated = false; + priv->bytes = 0; +} + +/* + * Private Data Reference Count + */ + +static void fpga_dev_remove(struct kref *ref) +{ + struct fpga_dev *priv = container_of(ref, struct fpga_dev, ref); + + /* free any firmware image that was not programmed */ + fpga_drop_firmware_data(priv); + + mutex_destroy(&priv->lock); + kfree(priv); +} + +/* + * LED Trigger (could be a seperate module) + */ + +/* + * NOTE: this whole thing does have the problem that whenever the led's are + * NOTE: first set to use the fpga trigger, they could be in the wrong state + */ + +DEFINE_LED_TRIGGER(ledtrig_fpga); + +static void ledtrig_fpga_programmed(bool enabled) +{ + if (enabled) + led_trigger_event(ledtrig_fpga, LED_FULL); + else + led_trigger_event(ledtrig_fpga, LED_OFF); +} + +/* + * FPGA Register Helpers + */ + +/* Register Definitions */ +#define FPGA_CONFIG_CONTROL 0x40 +#define FPGA_CONFIG_STATUS 0x44 +#define FPGA_CONFIG_FIFO_SIZE 0x48 +#define FPGA_CONFIG_FIFO_USED 0x4C +#define FPGA_CONFIG_TOTAL_BYTE_COUNT 0x50 +#define FPGA_CONFIG_CUR_BYTE_COUNT 0x54 + +#define FPGA_FIFO_ADDRESS 0x3000 + +static int fpga_fifo_size(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_FIFO_SIZE); +} + +#define CFG_STATUS_ERR_MASK 0xfffe + +static int fpga_config_error(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_STATUS) & CFG_STATUS_ERR_MASK; +} + +static int fpga_fifo_empty(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_FIFO_USED) == 0; +} + +static void fpga_fifo_write(void __iomem *regs, u32 val) +{ + iowrite32be(val, regs + FPGA_FIFO_ADDRESS); +} + +static void fpga_set_byte_count(void __iomem *regs, u32 count) +{ + iowrite32be(count, regs + FPGA_CONFIG_TOTAL_BYTE_COUNT); +} + +#define CFG_CTL_ENABLE (1 << 0) +#define CFG_CTL_RESET (1 << 1) +#define CFG_CTL_DMA (1 << 2) + +static void fpga_programmer_enable(struct fpga_dev *priv, bool dma) +{ + u32 val; + + val = (dma) ? (CFG_CTL_ENABLE | CFG_CTL_DMA) : CFG_CTL_ENABLE; + iowrite32be(val, priv->regs + FPGA_CONFIG_CONTROL); +} + +static void fpga_programmer_disable(struct fpga_dev *priv) +{ + iowrite32be(0x0, priv->regs + FPGA_CONFIG_CONTROL); +} + +static void fpga_dump_registers(struct fpga_dev *priv) +{ + u32 control, status, size, used, total, curr; + + /* good status: do nothing */ + if (priv->status == 0) + return; + + /* Dump all status registers */ + control = ioread32be(priv->regs + FPGA_CONFIG_CONTROL); + status = ioread32be(priv->regs + FPGA_CONFIG_STATUS); + size = ioread32be(priv->regs + FPGA_CONFIG_FIFO_SIZE); + used = ioread32be(priv->regs + FPGA_CONFIG_FIFO_USED); + total = ioread32be(priv->regs + FPGA_CONFIG_TOTAL_BYTE_COUNT); + curr = ioread32be(priv->regs + FPGA_CONFIG_CUR_BYTE_COUNT); + + dev_err(priv->dev, "Configuration failed, dumping status registers\n"); + dev_err(priv->dev, "Control: 0x%.8x\n", control); + dev_err(priv->dev, "Status: 0x%.8x\n", status); + dev_err(priv->dev, "FIFO Size: 0x%.8x\n", size); + dev_err(priv->dev, "FIFO Used: 0x%.8x\n", used); + dev_err(priv->dev, "FIFO Total: 0x%.8x\n", total); + dev_err(priv->dev, "FIFO Curr: 0x%.8x\n", curr); +} + +/* + * FPGA Power Supply Code + */ + +#define CTL_PWR_CONTROL 0x2006 +#define CTL_PWR_STATUS 0x200A +#define CTL_PWR_FAIL 0x200B + +#define PWR_CONTROL_ENABLE 0x01 + +#define PWR_STATUS_ERROR_MASK 0x10 +#define PWR_STATUS_GOOD 0x0f + +/* + * Determine if the FPGA power is good for all supplies + */ +static bool fpga_power_good(struct fpga_dev *priv) +{ + u8 val; + + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (val & PWR_STATUS_ERROR_MASK) + return false; + + return val == PWR_STATUS_GOOD; +} + +/* + * Disable the FPGA power supplies + */ +static void fpga_disable_power_supplies(struct fpga_dev *priv) +{ + unsigned long start; + u8 val; + + iowrite8(0x0, priv->regs + CTL_PWR_CONTROL); + + /* + * Wait 500ms for the power rails to discharge + * + * Without this delay, the CTL-CPLD state machine can get into a + * state where it is waiting for the power-goods to assert, but they + * never do. This only happens when enabling and disabling the + * power sequencer very rapidly. + * + * The loop below will also wait for the power goods to de-assert, + * but testing has shown that they are always disabled by the time + * the sleep completes. However, omitting the sleep and only waiting + * for the power-goods to de-assert was not sufficient to ensure + * that the power sequencer would not wedge itself. + */ + msleep(500); + + start = jiffies; + while (time_before(jiffies, start + HZ)) { + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (!(val & PWR_STATUS_GOOD)) + break; + + usleep_range(5000, 10000); + } + + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (val & PWR_STATUS_GOOD) { + dev_err(priv->dev, "power disable failed: " + "power goods: status 0x%.2x\n", val); + } + + if (val & PWR_STATUS_ERROR_MASK) { + dev_err(priv->dev, "power disable failed: " + "alarm bit set: status 0x%.2x\n", val); + } +} + +/** + * fpga_enable_power_supplies() - enable the DATA-FPGA power supplies + * @priv: the driver's private data structure + * + * Enable the DATA-FPGA power supplies, waiting up to 1 second for + * them to enable successfully. + * + * Returns 0 on success, -ERRNO otherwise + */ +static int fpga_enable_power_supplies(struct fpga_dev *priv) +{ + unsigned long start = jiffies; + + if (fpga_power_good(priv)) { + dev_dbg(priv->dev, "power was already good\n"); + return 0; + } + + iowrite8(PWR_CONTROL_ENABLE, priv->regs + CTL_PWR_CONTROL); + while (time_before(jiffies, start + HZ)) { + if (fpga_power_good(priv)) + return 0; + + usleep_range(5000, 10000); + } + + return fpga_power_good(priv) ? 0 : -ETIMEDOUT; +} + +/* + * Determine if the FPGA power supplies are all enabled + */ +static bool fpga_power_enabled(struct fpga_dev *priv) +{ + u8 val; + + val = ioread8(priv->regs + CTL_PWR_CONTROL); + if (val & PWR_CONTROL_ENABLE) + return true; + + return false; +} + +/* + * Determine if the FPGA's are programmed and running correctly + */ +static bool fpga_running(struct fpga_dev *priv) +{ + if (!fpga_power_good(priv)) + return false; + + /* Check the config done bit */ + return ioread32be(priv->regs + FPGA_CONFIG_STATUS) & (1 << 18); +} + +/* + * FPGA Programming Code + */ + +/** + * fpga_program_block() - put a block of data into the programmer's FIFO + * @priv: the driver's private data structure + * @buf: the data to program + * @count: the length of data to program (must be a multiple of 4 bytes) + * + * Returns 0 on success, -ERRNO otherwise + */ +static int fpga_program_block(struct fpga_dev *priv, void *buf, size_t count) +{ + u32 *data = buf; + int size = fpga_fifo_size(priv->regs); + int i, len; + unsigned long timeout; + + /* enforce correct data length for the FIFO */ + BUG_ON(count % 4 != 0); + + while (count > 0) { + + /* Get the size of the block to write (maximum is FIFO_SIZE) */ + len = min_t(size_t, count, size); + timeout = jiffies + HZ / 4; + + /* Write the block */ + for (i = 0; i < len / 4; i++) + fpga_fifo_write(priv->regs, data[i]); + + /* Update the amounts left */ + count -= len; + data += len / 4; + + /* Wait for the fifo to empty */ + while (true) { + + if (fpga_fifo_empty(priv->regs)) { + break; + } else { + dev_dbg(priv->dev, "Fifo not empty\n"); + cpu_relax(); + } + + if (fpga_config_error(priv->regs)) { + dev_err(priv->dev, "Error detected\n"); + return -EIO; + } + + if (time_after(jiffies, timeout)) { + dev_err(priv->dev, "Fifo drain timeout\n"); + return -ETIMEDOUT; + } + + usleep_range(5000, 10000); + } + } + + return 0; +} + +/** + * fpga_program_cpu() - program the DATA-FPGA's using the CPU + * @priv: the driver's private data structure + * + * This is useful when the DMA programming method fails. It is possible to + * wedge the Freescale DMA controller such that the DMA programming method + * always fails. This method has always succeeded. + * + * Returns 0 on success, -ERRNO otherwise + */ +static noinline int fpga_program_cpu(struct fpga_dev *priv) +{ + int ret; + + /* Disable the programmer */ + fpga_programmer_disable(priv); + + /* Set the total byte count */ + fpga_set_byte_count(priv->regs, priv->bytes); + dev_dbg(priv->dev, "total byte count %u bytes\n", priv->bytes); + + /* Enable the controller for programming */ + fpga_programmer_enable(priv, false); + dev_dbg(priv->dev, "enabled the controller\n"); + + /* Write each chunk of the FPGA bitfile to FPGA programmer */ + ret = fpga_program_block(priv, priv->vb.vaddr, priv->bytes); + if (ret) + goto out_disable_controller; + + /* Wait for the interrupt handler to signal that programming finished */ + ret = wait_for_completion_timeout(&priv->completion, 2 * HZ); + if (!ret) { + dev_err(priv->dev, "Timed out waiting for completion\n"); + ret = -ETIMEDOUT; + goto out_disable_controller; + } + + /* Retrieve the status from the interrupt handler */ + ret = priv->status; + +out_disable_controller: + fpga_programmer_disable(priv); + return ret; +} + +#define FIFO_DMA_ADDRESS 0xf0003000 +#define FIFO_MAX_LEN 4096 + +/** + * fpga_program_dma() - program the DATA-FPGA's using the DMA engine + * @priv: the driver's private data structure + * + * Program the DATA-FPGA's using the Freescale DMA engine. This requires that + * the engine is programmed such that the hardware DMA request lines can + * control the entire DMA transaction. The system controller FPGA then + * completely offloads the programming from the CPU. + * + * Returns 0 on success, -ERRNO otherwise + */ +static noinline int fpga_program_dma(struct fpga_dev *priv) +{ + struct videobuf_dmabuf *vb = &priv->vb; + struct dma_chan *chan = priv->chan; + struct dma_async_tx_descriptor *tx; + size_t num_pages, len, avail = 0; + struct dma_slave_config config; + struct scatterlist *sg; + struct sg_table table; + dma_cookie_t cookie; + int ret, i; + + /* Disable the programmer */ + fpga_programmer_disable(priv); + + /* Allocate a scatterlist for the DMA destination */ + num_pages = DIV_ROUND_UP(priv->bytes, FIFO_MAX_LEN); + ret = sg_alloc_table(&table, num_pages, GFP_KERNEL); + if (ret) { + dev_err(priv->dev, "Unable to allocate dst scatterlist\n"); + ret = -ENOMEM; + goto out_return; + } + + /* + * This is an ugly hack + * + * We fill in a scatterlist as if it were mapped for DMA. This is + * necessary because there exists no better structure for this + * inside the kernel code. + * + * As an added bonus, we can use the DMAEngine API for all of this, + * rather than inventing another extremely similar API. + */ + avail = priv->bytes; + for_each_sg(table.sgl, sg, num_pages, i) { + len = min_t(size_t, avail, FIFO_MAX_LEN); + sg_dma_address(sg) = FIFO_DMA_ADDRESS; + sg_dma_len(sg) = len; + + avail -= len; + } + + /* Map the buffer for DMA */ + ret = videobuf_dma_map(priv->dev, &priv->vb); + if (ret) { + dev_err(priv->dev, "Unable to map buffer for DMA\n"); + goto out_free_table; + } + + /* + * Configure the DMA channel to transfer FIFO_SIZE / 2 bytes per + * transaction, and then put it under external control + */ + memset(&config, 0, sizeof(config)); + config.direction = DMA_TO_DEVICE; + config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; + config.dst_maxburst = fpga_fifo_size(priv->regs) / 2 / 4; + ret = chan->device->device_control(chan, DMA_SLAVE_CONFIG, + (unsigned long)&config); + if (ret) { + dev_err(priv->dev, "DMA slave configuration failed\n"); + goto out_dma_unmap; + } + + ret = chan->device->device_control(chan, FSLDMA_EXTERNAL_START, 1); + if (ret) { + dev_err(priv->dev, "DMA external control setup failed\n"); + goto out_dma_unmap; + } + + /* setup and submit the DMA transaction */ + tx = chan->device->device_prep_dma_sg(chan, + table.sgl, num_pages, + vb->sglist, vb->sglen, 0); + if (!tx) { + dev_err(priv->dev, "Unable to prep DMA transaction\n"); + ret = -ENOMEM; + goto out_dma_unmap; + } + + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "Unable to submit DMA transaction\n"); + ret = -ENOMEM; + goto out_dma_unmap; + } + + dma_async_memcpy_issue_pending(chan); + + /* Set the total byte count */ + fpga_set_byte_count(priv->regs, priv->bytes); + dev_dbg(priv->dev, "total byte count %u bytes\n", priv->bytes); + + /* Enable the controller for DMA programming */ + fpga_programmer_enable(priv, true); + dev_dbg(priv->dev, "enabled the controller\n"); + + /* Wait for the interrupt handler to signal that programming finished */ + ret = wait_for_completion_timeout(&priv->completion, 2 * HZ); + if (!ret) { + dev_err(priv->dev, "Timed out waiting for completion\n"); + ret = -ETIMEDOUT; + goto out_disable_controller; + } + + /* Retrieve the status from the interrupt handler */ + ret = priv->status; + +out_disable_controller: + fpga_programmer_disable(priv); +out_dma_unmap: + videobuf_dma_unmap(priv->dev, vb); +out_free_table: + sg_free_table(&table); +out_return: + return ret; +} + +/* + * Interrupt Handling + */ + +static irqreturn_t fpga_irq(int irq, void *dev_id) +{ + struct fpga_dev *priv = dev_id; + + /* Save the status */ + priv->status = fpga_config_error(priv->regs) ? -EIO : 0; + dev_dbg(priv->dev, "INTERRUPT status %d\n", priv->status); + fpga_dump_registers(priv); + + /* Disabling the programmer clears the interrupt */ + fpga_programmer_disable(priv); + + /* Notify any waiters */ + complete(&priv->completion); + + return IRQ_HANDLED; +} + +/* + * SYSFS Helpers + */ + +/** + * fpga_do_stop() - deconfigure (reset) the DATA-FPGA's + * @priv: the driver's private data structure + * + * LOCKING: must hold priv->lock + */ +static int fpga_do_stop(struct fpga_dev *priv) +{ + u32 val; + + /* Set the led to unprogrammed */ + ledtrig_fpga_programmed(false); + + /* Pulse the config line to reset the FPGA's */ + val = CFG_CTL_ENABLE | CFG_CTL_RESET; + iowrite32be(val, priv->regs + FPGA_CONFIG_CONTROL); + iowrite32be(0x0, priv->regs + FPGA_CONFIG_CONTROL); + + return 0; +} + +static noinline int fpga_do_program(struct fpga_dev *priv) +{ + int ret; + + if (priv->bytes != priv->fw_size) { + dev_err(priv->dev, "Incorrect bitfile size: got %zu bytes, " + "should be %zu bytes\n", + priv->bytes, priv->fw_size); + return -EINVAL; + } + + if (!fpga_power_enabled(priv)) { + dev_err(priv->dev, "Power not enabled\n"); + return -EINVAL; + } + + if (!fpga_power_good(priv)) { + dev_err(priv->dev, "Power not good\n"); + return -EINVAL; + } + + /* Set the LED to unprogrammed */ + ledtrig_fpga_programmed(false); + + /* Try to program the FPGA's using DMA */ + ret = fpga_program_dma(priv); + + /* If DMA failed or doesn't exist, try with CPU */ + if (ret) { + dev_warn(priv->dev, "Falling back to CPU programming\n"); + ret = fpga_program_cpu(priv); + } + + if (ret) { + dev_err(priv->dev, "Unable to program FPGA's\n"); + return ret; + } + + /* Drop the firmware bitfile from memory */ + fpga_drop_firmware_data(priv); + + dev_dbg(priv->dev, "FPGA programming successful\n"); + ledtrig_fpga_programmed(true); + + return 0; +} + +/* + * File Operations + */ + +static int fpga_open(struct inode *inode, struct file *filp) +{ + /* + * The miscdevice layer puts our struct miscdevice into the + * filp->private_data field. We use this to find our private + * data and then overwrite it with our own private structure. + */ + struct fpga_dev *priv = container_of(filp->private_data, + struct fpga_dev, miscdev); + unsigned int nr_pages; + int ret; + + /* We only allow one process at a time */ + ret = mutex_lock_interruptible(&priv->lock); + if (ret) + return ret; + + filp->private_data = priv; + kref_get(&priv->ref); + + /* Truncation: drop any existing data */ + if (filp->f_flags & O_TRUNC) + priv->bytes = 0; + + /* Check if we have already allocated a buffer */ + if (priv->vb_allocated) + return 0; + + /* Allocate a buffer to hold enough data for the bitfile */ + nr_pages = DIV_ROUND_UP(priv->fw_size, PAGE_SIZE); + ret = videobuf_dma_init_kernel(&priv->vb, DMA_TO_DEVICE, nr_pages); + if (ret) { + dev_err(priv->dev, "unable to allocate data buffer\n"); + mutex_unlock(&priv->lock); + kref_put(&priv->ref, fpga_dev_remove); + return ret; + } + + priv->vb_allocated = true; + return 0; +} + +static int fpga_release(struct inode *inode, struct file *filp) +{ + struct fpga_dev *priv = filp->private_data; + + mutex_unlock(&priv->lock); + kref_put(&priv->ref, fpga_dev_remove); + return 0; +} + +static ssize_t fpga_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos) +{ + struct fpga_dev *priv = filp->private_data; + + /* FPGA bitfiles have an exact size: disallow anything else */ + if (priv->bytes >= priv->fw_size) + return -ENOSPC; + + count = min_t(size_t, priv->fw_size - priv->bytes, count); + if (copy_from_user(priv->vb.vaddr + priv->bytes, buf, count)) + return -EFAULT; + + priv->bytes += count; + return count; +} + +static ssize_t fpga_read(struct file *filp, char __user *buf, size_t count, + loff_t *f_pos) +{ + struct fpga_dev *priv = filp->private_data; + + count = min_t(size_t, priv->bytes - *f_pos, count); + if (copy_to_user(buf, priv->vb.vaddr + *f_pos, count)) + return -EFAULT; + + *f_pos += count; + return count; +} + +static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin) +{ + struct fpga_dev *priv = filp->private_data; + loff_t newpos; + + /* only read-only opens are allowed to seek */ + if ((filp->f_flags & O_ACCMODE) != O_RDONLY) + return -EINVAL; + + switch (origin) { + case SEEK_SET: /* seek relative to the beginning of the file */ + newpos = offset; + break; + case SEEK_CUR: /* seek relative to current position in the file */ + newpos = filp->f_pos + offset; + break; + case SEEK_END: /* seek relative to the end of the file */ + newpos = priv->fw_size - offset; + break; + default: + return -EINVAL; + } + + /* check for sanity */ + if (newpos > priv->fw_size) + return -EINVAL; + + filp->f_pos = newpos; + return newpos; +} + +static const struct file_operations fpga_fops = { + .open = fpga_open, + .release = fpga_release, + .write = fpga_write, + .read = fpga_read, + .llseek = fpga_llseek, +}; + +/* + * Device Attributes + */ + +static ssize_t pfail_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + u8 val; + + val = ioread8(priv->regs + CTL_PWR_FAIL); + return snprintf(buf, PAGE_SIZE, "0x%.2x\n", val); +} + +static ssize_t pgood_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_power_good(priv)); +} + +static ssize_t penable_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_power_enabled(priv)); +} + +static ssize_t penable_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + unsigned long val; + int ret; + + if (strict_strtoul(buf, 0, &val)) + return -EINVAL; + + if (val) { + ret = fpga_enable_power_supplies(priv); + if (ret) + return ret; + } else { + fpga_do_stop(priv); + fpga_disable_power_supplies(priv); + } + + return count; +} + +static ssize_t program_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_running(priv)); +} + +static ssize_t program_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + unsigned long val; + int ret; + + if (strict_strtoul(buf, 0, &val)) + return -EINVAL; + + /* We can't have an image writer and be programming simultaneously */ + if (mutex_lock_interruptible(&priv->lock)) + return -ERESTARTSYS; + + /* Program or Reset the FPGA's */ + ret = val ? fpga_do_program(priv) : fpga_do_stop(priv); + if (ret) + goto out_unlock; + + /* Success */ + ret = count; + +out_unlock: + mutex_unlock(&priv->lock); + return ret; +} + +static DEVICE_ATTR(power_fail, S_IRUGO, pfail_show, NULL); +static DEVICE_ATTR(power_good, S_IRUGO, pgood_show, NULL); +static DEVICE_ATTR(power_enable, S_IRUGO | S_IWUSR, + penable_show, penable_store); + +static DEVICE_ATTR(program, S_IRUGO | S_IWUSR, + program_show, program_store); + +static struct attribute *fpga_attributes[] = { + &dev_attr_power_fail.attr, + &dev_attr_power_good.attr, + &dev_attr_power_enable.attr, + &dev_attr_program.attr, + NULL, +}; + +static const struct attribute_group fpga_attr_group = { + .attrs = fpga_attributes, +}; + +/* + * OpenFirmware Device Subsystem + */ + +#define SYS_REG_VERSION 0x00 +#define SYS_REG_GEOGRAPHIC 0x10 + +static bool dma_filter(struct dma_chan *chan, void *data) +{ + /* + * DMA Channel #0 is the only acceptable device + * + * This probably won't survive an unload/load cycle of the Freescale + * DMAEngine driver, but that won't be a problem + */ + return chan->chan_id == 0 && chan->device->dev_id == 0; +} + +static int fpga_of_remove(struct platform_device *op) +{ + struct fpga_dev *priv = dev_get_drvdata(&op->dev); + struct device *this_device = priv->miscdev.this_device; + + sysfs_remove_group(&this_device->kobj, &fpga_attr_group); + misc_deregister(&priv->miscdev); + + free_irq(priv->irq, priv); + irq_dispose_mapping(priv->irq); + + /* make sure the power supplies are off */ + fpga_disable_power_supplies(priv); + + /* unmap registers */ + iounmap(priv->immr); + iounmap(priv->regs); + + dma_release_channel(priv->chan); + + /* drop our reference to the private data structure */ + kref_put(&priv->ref, fpga_dev_remove); + return 0; +} + +/* CTL-CPLD Version Register */ +#define CTL_CPLD_VERSION 0x2000 + +static int fpga_of_probe(struct platform_device *op, + const struct of_device_id *match) +{ + struct device_node *of_node = op->dev.of_node; + struct device *this_device; + struct fpga_dev *priv; + dma_cap_mask_t mask; + u32 ver; + int ret; + + /* Allocate private data */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + dev_err(&op->dev, "Unable to allocate private data\n"); + ret = -ENOMEM; + goto out_return; + } + + /* Setup the miscdevice */ + priv->miscdev.minor = MISC_DYNAMIC_MINOR; + priv->miscdev.name = drv_name; + priv->miscdev.fops = &fpga_fops; + + kref_init(&priv->ref); + + dev_set_drvdata(&op->dev, priv); + priv->dev = &op->dev; + mutex_init(&priv->lock); + init_completion(&priv->completion); + videobuf_dma_init(&priv->vb); + + dev_set_drvdata(priv->dev, priv); + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + dma_cap_set(DMA_INTERRUPT, mask); + dma_cap_set(DMA_SLAVE, mask); + dma_cap_set(DMA_SG, mask); + + /* Get control of DMA channel #0 */ + priv->chan = dma_request_channel(mask, dma_filter, NULL); + if (!priv->chan) { + dev_err(&op->dev, "Unable to acquire DMA channel #0\n"); + ret = -ENODEV; + goto out_free_priv; + } + + /* Remap the registers for use */ + priv->regs = of_iomap(of_node, 0); + if (!priv->regs) { + dev_err(&op->dev, "Unable to ioremap registers\n"); + ret = -ENOMEM; + goto out_dma_release_channel; + } + + /* Remap the IMMR for use */ + priv->immr = ioremap(get_immrbase(), 0x100000); + if (!priv->immr) { + dev_err(&op->dev, "Unable to ioremap IMMR\n"); + ret = -ENOMEM; + goto out_unmap_regs; + } + + /* + * Check that external DMA is configured + * + * U-Boot does this for us, but we should check it and bail out if + * there is a problem. Failing to have this register setup correctly + * will cause the DMA controller to transfer a single cacheline + * worth of data, then wedge itself. + */ + if ((ioread32be(priv->immr + 0x114) & 0xE00) != 0xE00) { + dev_err(&op->dev, "External DMA control not configured\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* + * Check the CTL-CPLD version + * + * This driver uses the CTL-CPLD DATA-FPGA power sequencer, and we + * don't want to run on any version of the CTL-CPLD that does not use + * a compatible register layout. + * + * v2: changed register layout, added power sequencer + * v3: added glitch filter on the i2c overcurrent/overtemp outputs + */ + ver = ioread8(priv->regs + CTL_CPLD_VERSION); + if (ver != 0x02 && ver != 0x03) { + dev_err(&op->dev, "CTL-CPLD is not version 0x02 or 0x03!\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* Set the exact size that the firmware image should be */ + ver = ioread32be(priv->regs + SYS_REG_VERSION); + priv->fw_size = (ver & (1 << 18)) ? FW_SIZE_EP2S130 : FW_SIZE_EP2S90; + + /* Find the correct IRQ number */ + priv->irq = irq_of_parse_and_map(of_node, 0); + if (priv->irq == NO_IRQ) { + dev_err(&op->dev, "Unable to find IRQ line\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* Request the IRQ */ + ret = request_irq(priv->irq, fpga_irq, IRQF_SHARED, drv_name, priv); + if (ret) { + dev_err(&op->dev, "Unable to request IRQ %d\n", priv->irq); + ret = -ENODEV; + goto out_irq_dispose_mapping; + } + + /* Reset and stop the FPGA's, just in case */ + fpga_do_stop(priv); + + /* Register the miscdevice */ + ret = misc_register(&priv->miscdev); + if (ret) { + dev_err(&op->dev, "Unable to register miscdevice\n"); + goto out_free_irq; + } + + /* Create the sysfs files */ + this_device = priv->miscdev.this_device; + dev_set_drvdata(this_device, priv); + ret = sysfs_create_group(&this_device->kobj, &fpga_attr_group); + if (ret) { + dev_err(&op->dev, "Unable to create sysfs files\n"); + goto out_misc_deregister; + } + + dev_info(priv->dev, "CARMA FPGA Programmer: %s rev%s with %s FPGAs\n", + (ver & (1 << 17)) ? "Correlator" : "Digitizer", + (ver & (1 << 16)) ? "B" : "A", + (ver & (1 << 18)) ? "EP2S130" : "EP2S90"); + + return 0; + +out_misc_deregister: + misc_deregister(&priv->miscdev); +out_free_irq: + free_irq(priv->irq, priv); +out_irq_dispose_mapping: + irq_dispose_mapping(priv->irq); +out_unmap_immr: + iounmap(priv->immr); +out_unmap_regs: + iounmap(priv->regs); +out_dma_release_channel: + dma_release_channel(priv->chan); +out_free_priv: + kref_put(&priv->ref, fpga_dev_remove); +out_return: + return ret; +} + +static struct of_device_id fpga_of_match[] = { + { .compatible = "carma,fpga-programmer", }, + {}, +}; + +static struct of_platform_driver fpga_of_driver = { + .probe = fpga_of_probe, + .remove = fpga_of_remove, + .driver = { + .name = drv_name, + .of_match_table = fpga_of_match, + .owner = THIS_MODULE, + }, +}; + +/* + * Module Init / Exit + */ + +static int __init fpga_init(void) +{ + led_trigger_register_simple("fpga", &ledtrig_fpga); + return of_register_platform_driver(&fpga_of_driver); +} + +static void __exit fpga_exit(void) +{ + of_unregister_platform_driver(&fpga_of_driver); + led_trigger_unregister_simple(ledtrig_fpga); +} + +MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>"); +MODULE_DESCRIPTION("CARMA Board DATA-FPGA Programmer"); +MODULE_LICENSE("GPL"); + +module_init(fpga_init); +module_exit(fpga_exit); diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c new file mode 100644 index 00000000000..3965821fef1 --- /dev/null +++ b/drivers/misc/carma/carma-fpga.c @@ -0,0 +1,1433 @@ +/* + * CARMA DATA-FPGA Access Driver + * + * Copyright (c) 2009-2011 Ira W. Snyder <iws@ovro.caltech.edu> + * + * 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. + */ + +/* + * FPGA Memory Dump Format + * + * FPGA #0 control registers (32 x 32-bit words) + * FPGA #1 control registers (32 x 32-bit words) + * FPGA #2 control registers (32 x 32-bit words) + * FPGA #3 control registers (32 x 32-bit words) + * SYSFPGA control registers (32 x 32-bit words) + * FPGA #0 correlation array (NUM_CORL0 correlation blocks) + * FPGA #1 correlation array (NUM_CORL1 correlation blocks) + * FPGA #2 correlation array (NUM_CORL2 correlation blocks) + * FPGA #3 correlation array (NUM_CORL3 correlation blocks) + * + * Each correlation array consists of: + * + * Correlation Data (2 x NUM_LAGSn x 32-bit words) + * Pipeline Metadata (2 x NUM_METAn x 32-bit words) + * Quantization Counters (2 x NUM_QCNTn x 32-bit words) + * + * The NUM_CORLn, NUM_LAGSn, NUM_METAn, and NUM_QCNTn values come from + * the FPGA configuration registers. They do not change once the FPGA's + * have been programmed, they only change on re-programming. + */ + +/* + * Basic Description: + * + * This driver is used to capture correlation spectra off of the four data + * processing FPGAs. The FPGAs are often reprogrammed at runtime, therefore + * this driver supports dynamic enable/disable of capture while the device + * remains open. + * + * The nominal capture rate is 64Hz (every 15.625ms). To facilitate this fast + * capture rate, all buffers are pre-allocated to avoid any potentially long + * running memory allocations while capturing. + * + * There are two lists and one pointer which are used to keep track of the + * different states of data buffers. + * + * 1) free list + * This list holds all empty data buffers which are ready to receive data. + * + * 2) inflight pointer + * This pointer holds the currently inflight data buffer. This buffer is having + * data copied into it by the DMA engine. + * + * 3) used list + * This list holds data buffers which have been filled, and are waiting to be + * read by userspace. + * + * All buffers start life on the free list, then move successively to the + * inflight pointer, and then to the used list. After they have been read by + * userspace, they are moved back to the free list. The cycle repeats as long + * as necessary. + * + * It should be noted that all buffers are mapped and ready for DMA when they + * are on any of the three lists. They are only unmapped when they are in the + * process of being read by userspace. + */ + +/* + * Notes on the IRQ masking scheme: + * + * The IRQ masking scheme here is different than most other hardware. The only + * way for the DATA-FPGAs to detect if the kernel has taken too long to copy + * the data is if the status registers are not cleared before the next + * correlation data dump is ready. + * + * The interrupt line is connected to the status registers, such that when they + * are cleared, the interrupt is de-asserted. Therein lies our problem. We need + * to schedule a long-running DMA operation and return from the interrupt + * handler quickly, but we cannot clear the status registers. + * + * To handle this, the system controller FPGA has the capability to connect the + * interrupt line to a user-controlled GPIO pin. This pin is driven high + * (unasserted) and left that way. To mask the interrupt, we change the + * interrupt source to the GPIO pin. Tada, we hid the interrupt. :) + */ + +#include <linux/of_platform.h> +#include <linux/dma-mapping.h> +#include <linux/miscdevice.h> +#include <linux/interrupt.h> +#include <linux/dmaengine.h> +#include <linux/seq_file.h> +#include <linux/highmem.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/kref.h> +#include <linux/io.h> + +#include <media/videobuf-dma-sg.h> + +/* system controller registers */ +#define SYS_IRQ_SOURCE_CTL 0x24 +#define SYS_IRQ_OUTPUT_EN 0x28 +#define SYS_IRQ_OUTPUT_DATA 0x2C +#define SYS_IRQ_INPUT_DATA 0x30 +#define SYS_FPGA_CONFIG_STATUS 0x44 + +/* GPIO IRQ line assignment */ +#define IRQ_CORL_DONE 0x10 + +/* FPGA registers */ +#define MMAP_REG_VERSION 0x00 +#define MMAP_REG_CORL_CONF1 0x08 +#define MMAP_REG_CORL_CONF2 0x0C +#define MMAP_REG_STATUS 0x48 + +#define SYS_FPGA_BLOCK 0xF0000000 + +#define DATA_FPGA_START 0x400000 +#define DATA_FPGA_SIZE 0x80000 + +static const char drv_name[] = "carma-fpga"; + +#define NUM_FPGA 4 + +#define MIN_DATA_BUFS 8 +#define MAX_DATA_BUFS 64 + +struct fpga_info { + unsigned int num_lag_ram; + unsigned int blk_size; +}; + +struct data_buf { + struct list_head entry; + struct videobuf_dmabuf vb; + size_t size; +}; + +struct fpga_device { + /* character device */ + struct miscdevice miscdev; + struct device *dev; + struct mutex mutex; + + /* reference count */ + struct kref ref; + + /* FPGA registers and information */ + struct fpga_info info[NUM_FPGA]; + void __iomem *regs; + int irq; + + /* FPGA Physical Address/Size Information */ + resource_size_t phys_addr; + size_t phys_size; + + /* DMA structures */ + struct sg_table corl_table; + unsigned int corl_nents; + struct dma_chan *chan; + + /* Protection for all members below */ + spinlock_t lock; + + /* Device enable/disable flag */ + bool enabled; + + /* Correlation data buffers */ + wait_queue_head_t wait; + struct list_head free; + struct list_head used; + struct data_buf *inflight; + + /* Information about data buffers */ + unsigned int num_dropped; + unsigned int num_buffers; + size_t bufsize; + struct dentry *dbg_entry; +}; + +struct fpga_reader { + struct fpga_device *priv; + struct data_buf *buf; + off_t buf_start; +}; + +static void fpga_device_release(struct kref *ref) +{ + struct fpga_device *priv = container_of(ref, struct fpga_device, ref); + + /* the last reader has exited, cleanup the last bits */ + mutex_destroy(&priv->mutex); + kfree(priv); +} + +/* + * Data Buffer Allocation Helpers + */ + +/** + * data_free_buffer() - free a single data buffer and all allocated memory + * @buf: the buffer to free + * + * This will free all of the pages allocated to the given data buffer, and + * then free the structure itself + */ +static void data_free_buffer(struct data_buf *buf) +{ + /* It is ok to free a NULL buffer */ + if (!buf) + return; + + /* free all memory */ + videobuf_dma_free(&buf->vb); + kfree(buf); +} + +/** + * data_alloc_buffer() - allocate and fill a data buffer with pages + * @bytes: the number of bytes required + * + * This allocates all space needed for a data buffer. It must be mapped before + * use in a DMA transaction using videobuf_dma_map(). + * + * Returns NULL on failure + */ +static struct data_buf *data_alloc_buffer(const size_t bytes) +{ + unsigned int nr_pages; + struct data_buf *buf; + int ret; + + /* calculate the number of pages necessary */ + nr_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); + + /* allocate the buffer structure */ + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) + goto out_return; + + /* initialize internal fields */ + INIT_LIST_HEAD(&buf->entry); + buf->size = bytes; + + /* allocate the videobuf */ + videobuf_dma_init(&buf->vb); + ret = videobuf_dma_init_kernel(&buf->vb, DMA_FROM_DEVICE, nr_pages); + if (ret) + goto out_free_buf; + + return buf; + +out_free_buf: + kfree(buf); +out_return: + return NULL; +} + +/** + * data_free_buffers() - free all allocated buffers + * @priv: the driver's private data structure + * + * Free all buffers allocated by the driver (except those currently in the + * process of being read by userspace). + * + * LOCKING: must hold dev->mutex + * CONTEXT: user + */ +static void data_free_buffers(struct fpga_device *priv) +{ + struct data_buf *buf, *tmp; + + /* the device should be stopped, no DMA in progress */ + BUG_ON(priv->inflight != NULL); + + list_for_each_entry_safe(buf, tmp, &priv->free, entry) { + list_del_init(&buf->entry); + videobuf_dma_unmap(priv->dev, &buf->vb); + data_free_buffer(buf); + } + + list_for_each_entry_safe(buf, tmp, &priv->used, entry) { + list_del_init(&buf->entry); + videobuf_dma_unmap(priv->dev, &buf->vb); + data_free_buffer(buf); + } + + priv->num_buffers = 0; + priv->bufsize = 0; +} + +/** + * data_alloc_buffers() - allocate 1 seconds worth of data buffers + * @priv: the driver's private data structure + * + * Allocate enough buffers for a whole second worth of data + * + * This routine will attempt to degrade nicely by succeeding even if a full + * second worth of data buffers could not be allocated, as long as a minimum + * number were allocated. In this case, it will print a message to the kernel + * log. + * + * The device must not be modifying any lists when this is called. + * + * CONTEXT: user + * LOCKING: must hold dev->mutex + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_alloc_buffers(struct fpga_device *priv) +{ + struct data_buf *buf; + int i, ret; + + for (i = 0; i < MAX_DATA_BUFS; i++) { + + /* allocate a buffer */ + buf = data_alloc_buffer(priv->bufsize); + if (!buf) + break; + + /* map it for DMA */ + ret = videobuf_dma_map(priv->dev, &buf->vb); + if (ret) { + data_free_buffer(buf); + break; + } + + /* add it to the list of free buffers */ + list_add_tail(&buf->entry, &priv->free); + priv->num_buffers++; + } + + /* Make sure we allocated the minimum required number of buffers */ + if (priv->num_buffers < MIN_DATA_BUFS) { + dev_err(priv->dev, "Unable to allocate enough data buffers\n"); + data_free_buffers(priv); + return -ENOMEM; + } + + /* Warn if we are running in a degraded state, but do not fail */ + if (priv->num_buffers < MAX_DATA_BUFS) { + dev_warn(priv->dev, + "Unable to allocate %d buffers, using %d buffers instead\n", + MAX_DATA_BUFS, i); + } + + return 0; +} + +/* + * DMA Operations Helpers + */ + +/** + * fpga_start_addr() - get the physical address a DATA-FPGA + * @priv: the driver's private data structure + * @fpga: the DATA-FPGA number (zero based) + */ +static dma_addr_t fpga_start_addr(struct fpga_device *priv, unsigned int fpga) +{ + return priv->phys_addr + 0x400000 + (0x80000 * fpga); +} + +/** + * fpga_block_addr() - get the physical address of a correlation data block + * @priv: the driver's private data structure + * @fpga: the DATA-FPGA number (zero based) + * @blknum: the correlation block number (zero based) + */ +static dma_addr_t fpga_block_addr(struct fpga_device *priv, unsigned int fpga, + unsigned int blknum) +{ + return fpga_start_addr(priv, fpga) + (0x10000 * (1 + blknum)); +} + +#define REG_BLOCK_SIZE (32 * 4) + +/** + * data_setup_corl_table() - create the scatterlist for correlation dumps + * @priv: the driver's private data structure + * + * Create the scatterlist for transferring a correlation dump from the + * DATA FPGAs. This structure will be reused for each buffer than needs + * to be filled with correlation data. + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_setup_corl_table(struct fpga_device *priv) +{ + struct sg_table *table = &priv->corl_table; + struct scatterlist *sg; + struct fpga_info *info; + int i, j, ret; + + /* Calculate the number of entries needed */ + priv->corl_nents = (1 + NUM_FPGA) * REG_BLOCK_SIZE; + for (i = 0; i < NUM_FPGA; i++) + priv->corl_nents += priv->info[i].num_lag_ram; + + /* Allocate the scatterlist table */ + ret = sg_alloc_table(table, priv->corl_nents, GFP_KERNEL); + if (ret) { + dev_err(priv->dev, "unable to allocate DMA table\n"); + return ret; + } + + /* Add the DATA FPGA registers to the scatterlist */ + sg = table->sgl; + for (i = 0; i < NUM_FPGA; i++) { + sg_dma_address(sg) = fpga_start_addr(priv, i); + sg_dma_len(sg) = REG_BLOCK_SIZE; + sg = sg_next(sg); + } + + /* Add the SYS-FPGA registers to the scatterlist */ + sg_dma_address(sg) = SYS_FPGA_BLOCK; + sg_dma_len(sg) = REG_BLOCK_SIZE; + sg = sg_next(sg); + + /* Add the FPGA correlation data blocks to the scatterlist */ + for (i = 0; i < NUM_FPGA; i++) { + info = &priv->info[i]; + for (j = 0; j < info->num_lag_ram; j++) { + sg_dma_address(sg) = fpga_block_addr(priv, i, j); + sg_dma_len(sg) = info->blk_size; + sg = sg_next(sg); + } + } + + /* + * All physical addresses and lengths are present in the structure + * now. It can be reused for every FPGA DATA interrupt + */ + return 0; +} + +/* + * FPGA Register Access Helpers + */ + +static void fpga_write_reg(struct fpga_device *priv, unsigned int fpga, + unsigned int reg, u32 val) +{ + const int fpga_start = DATA_FPGA_START + (fpga * DATA_FPGA_SIZE); + iowrite32be(val, priv->regs + fpga_start + reg); +} + +static u32 fpga_read_reg(struct fpga_device *priv, unsigned int fpga, + unsigned int reg) +{ + const int fpga_start = DATA_FPGA_START + (fpga * DATA_FPGA_SIZE); + return ioread32be(priv->regs + fpga_start + reg); +} + +/** + * data_calculate_bufsize() - calculate the data buffer size required + * @priv: the driver's private data structure + * + * Calculate the total buffer size needed to hold a single block + * of correlation data + * + * CONTEXT: user + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_calculate_bufsize(struct fpga_device *priv) +{ + u32 num_corl, num_lags, num_meta, num_qcnt, num_pack; + u32 conf1, conf2, version; + u32 num_lag_ram, blk_size; + int i; + + /* Each buffer starts with the 5 FPGA register areas */ + priv->bufsize = (1 + NUM_FPGA) * REG_BLOCK_SIZE; + + /* Read and store the configuration data for each FPGA */ + for (i = 0; i < NUM_FPGA; i++) { + version = fpga_read_reg(priv, i, MMAP_REG_VERSION); + conf1 = fpga_read_reg(priv, i, MMAP_REG_CORL_CONF1); + conf2 = fpga_read_reg(priv, i, MMAP_REG_CORL_CONF2); + + /* minor version 2 and later */ + if ((version & 0x000000FF) >= 2) { + num_corl = (conf1 & 0x000000F0) >> 4; + num_pack = (conf1 & 0x00000F00) >> 8; + num_lags = (conf1 & 0x00FFF000) >> 12; + num_meta = (conf1 & 0x7F000000) >> 24; + num_qcnt = (conf2 & 0x00000FFF) >> 0; + } else { + num_corl = (conf1 & 0x000000F0) >> 4; + num_pack = 1; /* implied */ + num_lags = (conf1 & 0x000FFF00) >> 8; + num_meta = (conf1 & 0x7FF00000) >> 20; + num_qcnt = (conf2 & 0x00000FFF) >> 0; + } + + num_lag_ram = (num_corl + num_pack - 1) / num_pack; + blk_size = ((num_pack * num_lags) + num_meta + num_qcnt) * 8; + + priv->info[i].num_lag_ram = num_lag_ram; + priv->info[i].blk_size = blk_size; + priv->bufsize += num_lag_ram * blk_size; + + dev_dbg(priv->dev, "FPGA %d NUM_CORL: %d\n", i, num_corl); + dev_dbg(priv->dev, "FPGA %d NUM_PACK: %d\n", i, num_pack); + dev_dbg(priv->dev, "FPGA %d NUM_LAGS: %d\n", i, num_lags); + dev_dbg(priv->dev, "FPGA %d NUM_META: %d\n", i, num_meta); + dev_dbg(priv->dev, "FPGA %d NUM_QCNT: %d\n", i, num_qcnt); + dev_dbg(priv->dev, "FPGA %d BLK_SIZE: %d\n", i, blk_size); + } + + dev_dbg(priv->dev, "TOTAL BUFFER SIZE: %zu bytes\n", priv->bufsize); + return 0; +} + +/* + * Interrupt Handling + */ + +/** + * data_disable_interrupts() - stop the device from generating interrupts + * @priv: the driver's private data structure + * + * Hide interrupts by switching to GPIO interrupt source + * + * LOCKING: must hold dev->lock + */ +static void data_disable_interrupts(struct fpga_device *priv) +{ + /* hide the interrupt by switching the IRQ driver to GPIO */ + iowrite32be(0x2F, priv->regs + SYS_IRQ_SOURCE_CTL); +} + +/** + * data_enable_interrupts() - allow the device to generate interrupts + * @priv: the driver's private data structure + * + * Unhide interrupts by switching to the FPGA interrupt source. At the + * same time, clear the DATA-FPGA status registers. + * + * LOCKING: must hold dev->lock + */ +static void data_enable_interrupts(struct fpga_device *priv) +{ + /* clear the actual FPGA corl_done interrupt */ + fpga_write_reg(priv, 0, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 1, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 2, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 3, MMAP_REG_STATUS, 0x0); + + /* flush the writes */ + fpga_read_reg(priv, 0, MMAP_REG_STATUS); + + /* switch back to the external interrupt source */ + iowrite32be(0x3F, priv->regs + SYS_IRQ_SOURCE_CTL); +} + +/** + * data_dma_cb() - DMAEngine callback for DMA completion + * @data: the driver's private data structure + * + * Complete a DMA transfer from the DATA-FPGA's + * + * This is called via the DMA callback mechanism, and will handle moving the + * completed DMA transaction to the used list, and then wake any processes + * waiting for new data + * + * CONTEXT: any, softirq expected + */ +static void data_dma_cb(void *data) +{ + struct fpga_device *priv = data; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* If there is no inflight buffer, we've got a bug */ + BUG_ON(priv->inflight == NULL); + + /* Move the inflight buffer onto the used list */ + list_move_tail(&priv->inflight->entry, &priv->used); + priv->inflight = NULL; + + /* clear the FPGA status and re-enable interrupts */ + data_enable_interrupts(priv); + + spin_unlock_irqrestore(&priv->lock, flags); + + /* + * We've changed both the inflight and used lists, so we need + * to wake up any processes that are blocking for those events + */ + wake_up(&priv->wait); +} + +/** + * data_submit_dma() - prepare and submit the required DMA to fill a buffer + * @priv: the driver's private data structure + * @buf: the data buffer + * + * Prepare and submit the necessary DMA transactions to fill a correlation + * data buffer. + * + * LOCKING: must hold dev->lock + * CONTEXT: hardirq only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_submit_dma(struct fpga_device *priv, struct data_buf *buf) +{ + struct scatterlist *dst_sg, *src_sg; + unsigned int dst_nents, src_nents; + struct dma_chan *chan = priv->chan; + struct dma_async_tx_descriptor *tx; + dma_cookie_t cookie; + dma_addr_t dst, src; + + dst_sg = buf->vb.sglist; + dst_nents = buf->vb.sglen; + + src_sg = priv->corl_table.sgl; + src_nents = priv->corl_nents; + + /* + * All buffers passed to this function should be ready and mapped + * for DMA already. Therefore, we don't need to do anything except + * submit it to the Freescale DMA Engine for processing + */ + + /* setup the scatterlist to scatterlist transfer */ + tx = chan->device->device_prep_dma_sg(chan, + dst_sg, dst_nents, + src_sg, src_nents, + 0); + if (!tx) { + dev_err(priv->dev, "unable to prep scatterlist DMA\n"); + return -ENOMEM; + } + + /* submit the transaction to the DMA controller */ + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "unable to submit scatterlist DMA\n"); + return -ENOMEM; + } + + /* Prepare the re-read of the SYS-FPGA block */ + dst = sg_dma_address(dst_sg) + (NUM_FPGA * REG_BLOCK_SIZE); + src = SYS_FPGA_BLOCK; + tx = chan->device->device_prep_dma_memcpy(chan, dst, src, + REG_BLOCK_SIZE, + DMA_PREP_INTERRUPT); + if (!tx) { + dev_err(priv->dev, "unable to prep SYS-FPGA DMA\n"); + return -ENOMEM; + } + + /* Setup the callback */ + tx->callback = data_dma_cb; + tx->callback_param = priv; + + /* submit the transaction to the DMA controller */ + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "unable to submit SYS-FPGA DMA\n"); + return -ENOMEM; + } + + return 0; +} + +#define CORL_DONE 0x1 +#define CORL_ERR 0x2 + +static irqreturn_t data_irq(int irq, void *dev_id) +{ + struct fpga_device *priv = dev_id; + bool submitted = false; + struct data_buf *buf; + u32 status; + int i; + + /* detect spurious interrupts via FPGA status */ + for (i = 0; i < 4; i++) { + status = fpga_read_reg(priv, i, MMAP_REG_STATUS); + if (!(status & (CORL_DONE | CORL_ERR))) { + dev_err(priv->dev, "spurious irq detected (FPGA)\n"); + return IRQ_NONE; + } + } + + /* detect spurious interrupts via raw IRQ pin readback */ + status = ioread32be(priv->regs + SYS_IRQ_INPUT_DATA); + if (status & IRQ_CORL_DONE) { + dev_err(priv->dev, "spurious irq detected (IRQ)\n"); + return IRQ_NONE; + } + + spin_lock(&priv->lock); + + /* hide the interrupt by switching the IRQ driver to GPIO */ + data_disable_interrupts(priv); + + /* If there are no free buffers, drop this data */ + if (list_empty(&priv->free)) { + priv->num_dropped++; + goto out; + } + + buf = list_first_entry(&priv->free, struct data_buf, entry); + list_del_init(&buf->entry); + BUG_ON(buf->size != priv->bufsize); + + /* Submit a DMA transfer to get the correlation data */ + if (data_submit_dma(priv, buf)) { + dev_err(priv->dev, "Unable to setup DMA transfer\n"); + list_move_tail(&buf->entry, &priv->free); + goto out; + } + + /* Save the buffer for the DMA callback */ + priv->inflight = buf; + submitted = true; + + /* Start the DMA Engine */ + dma_async_memcpy_issue_pending(priv->chan); + +out: + /* If no DMA was submitted, re-enable interrupts */ + if (!submitted) + data_enable_interrupts(priv); + + spin_unlock(&priv->lock); + return IRQ_HANDLED; +} + +/* + * Realtime Device Enable Helpers + */ + +/** + * data_device_enable() - enable the device for buffered dumping + * @priv: the driver's private data structure + * + * Enable the device for buffered dumping. Allocates buffers and hooks up + * the interrupt handler. When this finishes, data will come pouring in. + * + * LOCKING: must hold dev->mutex + * CONTEXT: user context only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_device_enable(struct fpga_device *priv) +{ + u32 val; + int ret; + + /* multiple enables are safe: they do nothing */ + if (priv->enabled) + return 0; + + /* check that the FPGAs are programmed */ + val = ioread32be(priv->regs + SYS_FPGA_CONFIG_STATUS); + if (!(val & (1 << 18))) { + dev_err(priv->dev, "DATA-FPGAs are not enabled\n"); + return -ENODATA; + } + + /* read the FPGAs to calculate the buffer size */ + ret = data_calculate_bufsize(priv); + if (ret) { + dev_err(priv->dev, "unable to calculate buffer size\n"); + goto out_error; + } + + /* allocate the correlation data buffers */ + ret = data_alloc_buffers(priv); + if (ret) { + dev_err(priv->dev, "unable to allocate buffers\n"); + goto out_error; + } + + /* setup the source scatterlist for dumping correlation data */ + ret = data_setup_corl_table(priv); + if (ret) { + dev_err(priv->dev, "unable to setup correlation DMA table\n"); + goto out_error; + } + + /* hookup the irq handler */ + ret = request_irq(priv->irq, data_irq, IRQF_SHARED, drv_name, priv); + if (ret) { + dev_err(priv->dev, "unable to request IRQ handler\n"); + goto out_error; + } + + /* switch to the external FPGA IRQ line */ + data_enable_interrupts(priv); + + /* success, we're enabled */ + priv->enabled = true; + return 0; + +out_error: + sg_free_table(&priv->corl_table); + priv->corl_nents = 0; + + data_free_buffers(priv); + return ret; +} + +/** + * data_device_disable() - disable the device for buffered dumping + * @priv: the driver's private data structure + * + * Disable the device for buffered dumping. Stops new DMA transactions from + * being generated, waits for all outstanding DMA to complete, and then frees + * all buffers. + * + * LOCKING: must hold dev->mutex + * CONTEXT: user only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_device_disable(struct fpga_device *priv) +{ + int ret; + + /* allow multiple disable */ + if (!priv->enabled) + return 0; + + /* switch to the internal GPIO IRQ line */ + data_disable_interrupts(priv); + + /* unhook the irq handler */ + free_irq(priv->irq, priv); + + /* + * wait for all outstanding DMA to complete + * + * Device interrupts are disabled, therefore another buffer cannot + * be marked inflight. + */ + ret = wait_event_interruptible(priv->wait, priv->inflight == NULL); + if (ret) + return ret; + + /* free the correlation table */ + sg_free_table(&priv->corl_table); + priv->corl_nents = 0; + + /* + * We are taking the spinlock not to protect priv->enabled, but instead + * to make sure that there are no readers in the process of altering + * the free or used lists while we are setting this flag. + */ + spin_lock_irq(&priv->lock); + priv->enabled = false; + spin_unlock_irq(&priv->lock); + + /* free all buffers: the free and used lists are not being changed */ + data_free_buffers(priv); + return 0; +} + +/* + * DEBUGFS Interface + */ +#ifdef CONFIG_DEBUG_FS + +/* + * Count the number of entries in the given list + */ +static unsigned int list_num_entries(struct list_head *list) +{ + struct list_head *entry; + unsigned int ret = 0; + + list_for_each(entry, list) + ret++; + + return ret; +} + +static int data_debug_show(struct seq_file *f, void *offset) +{ + struct fpga_device *priv = f->private; + int ret; + + /* + * Lock the mutex first, so that we get an accurate value for enable + * Lock the spinlock next, to get accurate list counts + */ + ret = mutex_lock_interruptible(&priv->mutex); + if (ret) + return ret; + + spin_lock_irq(&priv->lock); + + seq_printf(f, "enabled: %d\n", priv->enabled); + seq_printf(f, "bufsize: %d\n", priv->bufsize); + seq_printf(f, "num_buffers: %d\n", priv->num_buffers); + seq_printf(f, "num_free: %d\n", list_num_entries(&priv->free)); + seq_printf(f, "inflight: %d\n", priv->inflight != NULL); + seq_printf(f, "num_used: %d\n", list_num_entries(&priv->used)); + seq_printf(f, "num_dropped: %d\n", priv->num_dropped); + + spin_unlock_irq(&priv->lock); + mutex_unlock(&priv->mutex); + return 0; +} + +static int data_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, data_debug_show, inode->i_private); +} + +static const struct file_operations data_debug_fops = { + .owner = THIS_MODULE, + .open = data_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int data_debugfs_init(struct fpga_device *priv) +{ + priv->dbg_entry = debugfs_create_file(drv_name, S_IRUGO, NULL, priv, + &data_debug_fops); + if (IS_ERR(priv->dbg_entry)) + return PTR_ERR(priv->dbg_entry); + + return 0; +} + +static void data_debugfs_exit(struct fpga_device *priv) +{ + debugfs_remove(priv->dbg_entry); +} + +#else + +static inline int data_debugfs_init(struct fpga_device *priv) +{ + return 0; +} + +static inline void data_debugfs_exit(struct fpga_device *priv) +{ +} + +#endif /* CONFIG_DEBUG_FS */ + +/* + * SYSFS Attributes + */ + +static ssize_t data_en_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_device *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%u\n", priv->enabled); +} + +static ssize_t data_en_set(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_device *priv = dev_get_drvdata(dev); + unsigned long enable; + int ret; + + ret = strict_strtoul(buf, 0, &enable); + if (ret) { + dev_err(priv->dev, "unable to parse enable input\n"); + return -EINVAL; + } + + ret = mutex_lock_interruptible(&priv->mutex); + if (ret) + return ret; + + if (enable) + ret = data_device_enable(priv); + else + ret = data_device_disable(priv); + + if (ret) { + dev_err(priv->dev, "device %s failed\n", + enable ? "enable" : "disable"); + count = ret; + goto out_unlock; + } + +out_unlock: + mutex_unlock(&priv->mutex); + return count; +} + +static DEVICE_ATTR(enable, S_IWUSR | S_IRUGO, data_en_show, data_en_set); + +static struct attribute *data_sysfs_attrs[] = { + &dev_attr_enable.attr, + NULL, +}; + +static const struct attribute_group rt_sysfs_attr_group = { + .attrs = data_sysfs_attrs, +}; + +/* + * FPGA Realtime Data Character Device + */ + +static int data_open(struct inode *inode, struct file *filp) +{ + /* + * The miscdevice layer puts our struct miscdevice into the + * filp->private_data field. We use this to find our private + * data and then overwrite it with our own private structure. + */ + struct fpga_device *priv = container_of(filp->private_data, + struct fpga_device, miscdev); + struct fpga_reader *reader; + int ret; + + /* allocate private data */ + reader = kzalloc(sizeof(*reader), GFP_KERNEL); + if (!reader) + return -ENOMEM; + + reader->priv = priv; + reader->buf = NULL; + + filp->private_data = reader; + ret = nonseekable_open(inode, filp); + if (ret) { + dev_err(priv->dev, "nonseekable-open failed\n"); + kfree(reader); + return ret; + } + + /* + * success, increase the reference count of the private data structure + * so that it doesn't disappear if the device is unbound + */ + kref_get(&priv->ref); + return 0; +} + +static int data_release(struct inode *inode, struct file *filp) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + + /* free the per-reader structure */ + data_free_buffer(reader->buf); + kfree(reader); + filp->private_data = NULL; + + /* decrement our reference count to the private data */ + kref_put(&priv->ref, fpga_device_release); + return 0; +} + +static ssize_t data_read(struct file *filp, char __user *ubuf, size_t count, + loff_t *f_pos) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + struct list_head *used = &priv->used; + struct data_buf *dbuf; + size_t avail; + void *data; + int ret; + + /* check if we already have a partial buffer */ + if (reader->buf) { + dbuf = reader->buf; + goto have_buffer; + } + + spin_lock_irq(&priv->lock); + + /* Block until there is at least one buffer on the used list */ + while (list_empty(used)) { + spin_unlock_irq(&priv->lock); + + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + ret = wait_event_interruptible(priv->wait, !list_empty(used)); + if (ret) + return ret; + + spin_lock_irq(&priv->lock); + } + + /* Grab the first buffer off of the used list */ + dbuf = list_first_entry(used, struct data_buf, entry); + list_del_init(&dbuf->entry); + + spin_unlock_irq(&priv->lock); + + /* Buffers are always mapped: unmap it */ + videobuf_dma_unmap(priv->dev, &dbuf->vb); + + /* save the buffer for later */ + reader->buf = dbuf; + reader->buf_start = 0; + +have_buffer: + /* Get the number of bytes available */ + avail = dbuf->size - reader->buf_start; + data = dbuf->vb.vaddr + reader->buf_start; + + /* Get the number of bytes we can transfer */ + count = min(count, avail); + + /* Copy the data to the userspace buffer */ + if (copy_to_user(ubuf, data, count)) + return -EFAULT; + + /* Update the amount of available space */ + avail -= count; + + /* + * If there is still some data available, save the buffer for the + * next userspace call to read() and return + */ + if (avail > 0) { + reader->buf_start += count; + reader->buf = dbuf; + return count; + } + + /* + * Get the buffer ready to be reused for DMA + * + * If it fails, we pretend that the read never happed and return + * -EFAULT to userspace. The read will be retried. + */ + ret = videobuf_dma_map(priv->dev, &dbuf->vb); + if (ret) { + dev_err(priv->dev, "unable to remap buffer for DMA\n"); + return -EFAULT; + } + + /* Lock against concurrent enable/disable */ + spin_lock_irq(&priv->lock); + + /* the reader is finished with this buffer */ + reader->buf = NULL; + + /* + * One of two things has happened, the device is disabled, or the + * device has been reconfigured underneath us. In either case, we + * should just throw away the buffer. + */ + if (!priv->enabled || dbuf->size != priv->bufsize) { + videobuf_dma_unmap(priv->dev, &dbuf->vb); + data_free_buffer(dbuf); + goto out_unlock; + } + + /* The buffer is safe to reuse, so add it back to the free list */ + list_add_tail(&dbuf->entry, &priv->free); + +out_unlock: + spin_unlock_irq(&priv->lock); + return count; +} + +static unsigned int data_poll(struct file *filp, struct poll_table_struct *tbl) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + unsigned int mask = 0; + + poll_wait(filp, &priv->wait, tbl); + + if (!list_empty(&priv->used)) + mask |= POLLIN | POLLRDNORM; + + return mask; +} + +static int data_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + unsigned long offset, vsize, psize, addr; + + /* VMA properties */ + offset = vma->vm_pgoff << PAGE_SHIFT; + vsize = vma->vm_end - vma->vm_start; + psize = priv->phys_size - offset; + addr = (priv->phys_addr + offset) >> PAGE_SHIFT; + + /* Check against the FPGA region's physical memory size */ + if (vsize > psize) { + dev_err(priv->dev, "requested mmap mapping too large\n"); + return -EINVAL; + } + + /* IO memory (stop cacheing) */ + vma->vm_flags |= VM_IO | VM_RESERVED; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + return io_remap_pfn_range(vma, vma->vm_start, addr, vsize, + vma->vm_page_prot); +} + +static const struct file_operations data_fops = { + .owner = THIS_MODULE, + .open = data_open, + .release = data_release, + .read = data_read, + .poll = data_poll, + .mmap = data_mmap, + .llseek = no_llseek, +}; + +/* + * OpenFirmware Device Subsystem + */ + +static bool dma_filter(struct dma_chan *chan, void *data) +{ + /* + * DMA Channel #0 is used for the FPGA Programmer, so ignore it + * + * This probably won't survive an unload/load cycle of the Freescale + * DMAEngine driver, but that won't be a problem + */ + if (chan->chan_id == 0 && chan->device->dev_id == 0) + return false; + + return true; +} + +static int data_of_probe(struct platform_device *op, + const struct of_device_id *match) +{ + struct device_node *of_node = op->dev.of_node; + struct device *this_device; + struct fpga_device *priv; + struct resource res; + dma_cap_mask_t mask; + int ret; + + /* Allocate private data */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + dev_err(&op->dev, "Unable to allocate device private data\n"); + ret = -ENOMEM; + goto out_return; + } + + dev_set_drvdata(&op->dev, priv); + priv->dev = &op->dev; + kref_init(&priv->ref); + mutex_init(&priv->mutex); + + dev_set_drvdata(priv->dev, priv); + spin_lock_init(&priv->lock); + INIT_LIST_HEAD(&priv->free); + INIT_LIST_HEAD(&priv->used); + init_waitqueue_head(&priv->wait); + + /* Setup the misc device */ + priv->miscdev.minor = MISC_DYNAMIC_MINOR; + priv->miscdev.name = drv_name; + priv->miscdev.fops = &data_fops; + + /* Get the physical address of the FPGA registers */ + ret = of_address_to_resource(of_node, 0, &res); + if (ret) { + dev_err(&op->dev, "Unable to find FPGA physical address\n"); + ret = -ENODEV; + goto out_free_priv; + } + + priv->phys_addr = res.start; + priv->phys_size = resource_size(&res); + + /* ioremap the registers for use */ + priv->regs = of_iomap(of_node, 0); + if (!priv->regs) { + dev_err(&op->dev, "Unable to ioremap registers\n"); + ret = -ENOMEM; + goto out_free_priv; + } + + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + dma_cap_set(DMA_INTERRUPT, mask); + dma_cap_set(DMA_SLAVE, mask); + dma_cap_set(DMA_SG, mask); + + /* Request a DMA channel */ + priv->chan = dma_request_channel(mask, dma_filter, NULL); + if (!priv->chan) { + dev_err(&op->dev, "Unable to request DMA channel\n"); + ret = -ENODEV; + goto out_unmap_regs; + } + + /* Find the correct IRQ number */ + priv->irq = irq_of_parse_and_map(of_node, 0); + if (priv->irq == NO_IRQ) { + dev_err(&op->dev, "Unable to find IRQ line\n"); + ret = -ENODEV; + goto out_release_dma; + } + + /* Drive the GPIO for FPGA IRQ high (no interrupt) */ + iowrite32be(IRQ_CORL_DONE, priv->regs + SYS_IRQ_OUTPUT_DATA); + + /* Register the miscdevice */ + ret = misc_register(&priv->miscdev); + if (ret) { + dev_err(&op->dev, "Unable to register miscdevice\n"); + goto out_irq_dispose_mapping; + } + + /* Create the debugfs files */ + ret = data_debugfs_init(priv); + if (ret) { + dev_err(&op->dev, "Unable to create debugfs files\n"); + goto out_misc_deregister; + } + + /* Create the sysfs files */ + this_device = priv->miscdev.this_device; + dev_set_drvdata(this_device, priv); + ret = sysfs_create_group(&this_device->kobj, &rt_sysfs_attr_group); + if (ret) { + dev_err(&op->dev, "Unable to create sysfs files\n"); + goto out_data_debugfs_exit; + } + + dev_info(&op->dev, "CARMA FPGA Realtime Data Driver Loaded\n"); + return 0; + +out_data_debugfs_exit: + data_debugfs_exit(priv); +out_misc_deregister: + misc_deregister(&priv->miscdev); +out_irq_dispose_mapping: + irq_dispose_mapping(priv->irq); +out_release_dma: + dma_release_channel(priv->chan); +out_unmap_regs: + iounmap(priv->regs); +out_free_priv: + kref_put(&priv->ref, fpga_device_release); +out_return: + return ret; +} + +static int data_of_remove(struct platform_device *op) +{ + struct fpga_device *priv = dev_get_drvdata(&op->dev); + struct device *this_device = priv->miscdev.this_device; + + /* remove all sysfs files, now the device cannot be re-enabled */ + sysfs_remove_group(&this_device->kobj, &rt_sysfs_attr_group); + + /* remove all debugfs files */ + data_debugfs_exit(priv); + + /* disable the device from generating data */ + data_device_disable(priv); + + /* remove the character device to stop new readers from appearing */ + misc_deregister(&priv->miscdev); + + /* cleanup everything not needed by readers */ + irq_dispose_mapping(priv->irq); + dma_release_channel(priv->chan); + iounmap(priv->regs); + + /* release our reference */ + kref_put(&priv->ref, fpga_device_release); + return 0; +} + +static struct of_device_id data_of_match[] = { + { .compatible = "carma,carma-fpga", }, + {}, +}; + +static struct of_platform_driver data_of_driver = { + .probe = data_of_probe, + .remove = data_of_remove, + .driver = { + .name = drv_name, + .of_match_table = data_of_match, + .owner = THIS_MODULE, + }, +}; + +/* + * Module Init / Exit + */ + +static int __init data_init(void) +{ + return of_register_platform_driver(&data_of_driver); +} + +static void __exit data_exit(void) +{ + of_unregister_platform_driver(&data_of_driver); +} + +MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>"); +MODULE_DESCRIPTION("CARMA DATA-FPGA Access Driver"); +MODULE_LICENSE("GPL"); + +module_init(data_init); +module_exit(data_exit); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 75b0d3cb767..9f689f1da0f 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map); * Returns a pointer to the interrupt parent node, or NULL if the interrupt * parent could not be determined. */ -static struct device_node *of_irq_find_parent(struct device_node *child) +struct device_node *of_irq_find_parent(struct device_node *child) { struct device_node *p; const __be32 *parp; diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 109e013b177..e6955f5d1f0 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -68,6 +68,7 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern int of_irq_count(struct device_node *dev); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); +extern struct device_node *of_irq_find_parent(struct device_node *child); #endif /* CONFIG_OF_IRQ */ #endif /* CONFIG_OF */ |