diff options
Diffstat (limited to 'kernel/arch/arc')
122 files changed, 8832 insertions, 2522 deletions
diff --git a/kernel/arch/arc/Kconfig b/kernel/arch/arc/Kconfig index df94ac1f7..6312f6079 100644 --- a/kernel/arch/arc/Kconfig +++ b/kernel/arch/arc/Kconfig @@ -8,6 +8,7 @@ config ARC def_bool y + select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC select BUILDTIME_EXTABLE_SORT select COMMON_CLK select CLONE_BACKWARDS @@ -22,6 +23,7 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_FUTEX_CMPXCHG select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES @@ -74,6 +76,10 @@ config STACKTRACE_SUPPORT config HAVE_LATENCYTOP_SUPPORT def_bool y +config HAVE_ARCH_TRANSPARENT_HUGEPAGE + def_bool y + depends on ARC_MMU_V4 + source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -81,26 +87,47 @@ menu "ARC Architecture Configuration" menu "ARC Platform/SoC/Board" -source "arch/arc/plat-arcfpga/Kconfig" +source "arch/arc/plat-sim/Kconfig" source "arch/arc/plat-tb10x/Kconfig" +source "arch/arc/plat-axs10x/Kconfig" #New platform adds here endmenu +choice + prompt "ARC Instruction Set" + default ISA_ARCOMPACT + +config ISA_ARCOMPACT + bool "ARCompact ISA" + help + The original ARC ISA of ARC600/700 cores + +config ISA_ARCV2 + bool "ARC ISA v2" + help + ISA for the Next Generation ARC-HS cores + +endchoice + menu "ARC CPU Configuration" choice prompt "ARC Core" - default ARC_CPU_770 + default ARC_CPU_770 if ISA_ARCOMPACT + default ARC_CPU_HS if ISA_ARCV2 + +if ISA_ARCOMPACT config ARC_CPU_750D bool "ARC750D" + select ARC_CANT_LLSC help Support for ARC750 core config ARC_CPU_770 bool "ARC770" - select ARC_CPU_REL_4_10 + select ARC_HAS_SWAPE help Support for ARC770 core introduced with Rel 4.10 (Summer 2011) This core has a bunch of cool new features: @@ -109,6 +136,27 @@ config ARC_CPU_770 -Caches: New Prog Model, Region Flush -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr +endif #ISA_ARCOMPACT + +config ARC_CPU_HS + bool "ARC-HS" + depends on ISA_ARCV2 + help + Support for ARC HS38x Cores based on ARCv2 ISA + The notable features are: + - SMP configurations of upto 4 core with coherency + - Optional L2 Cache and IO-Coherency + - Revised Interrupt Architecture (multiple priorites, reg banks, + auto stack switch, auto regfile save/restore) + - MMUv4 (PIPT dcache, Huge Pages) + - Instructions for + * 64bit load/store: LDD, STD + * Hardware assisted divide/remainder: DIV, REM + * Function prologue/epilogue: ENTER_S, LEAVE_S + * IRQ enable/disable: CLRI, SETI + * pop count: FFS, FLS + * SETcc, BMSKN, XBFU... + endchoice config CPU_BIG_ENDIAN @@ -117,17 +165,13 @@ config CPU_BIG_ENDIAN help Build kernel for Big Endian Mode of ARC CPU -# If a platform can't work with 0x8000_0000 based dma_addr_t -config ARC_PLAT_NEEDS_CPU_TO_DMA - bool - config SMP - bool "Symmetric Multi-Processing (Incomplete)" + bool "Symmetric Multi-Processing" default n + select ARC_HAS_COH_CACHES if ISA_ARCV2 + select ARC_MCIP if ISA_ARCV2 help - This enables support for systems with more than one CPU. If you have - a system with only one CPU, say N. If you have a system with more - than one CPU, say Y. + This enables support for systems with more than one CPU. if SMP @@ -137,13 +181,30 @@ config ARC_HAS_COH_CACHES config ARC_HAS_REENTRANT_IRQ_LV2 def_bool n -endif +config ARC_MCIP + bool "ARConnect Multicore IP (MCIP) Support " + depends on ISA_ARCV2 + help + This IP block enables SMP in ARC-HS38 cores. + It provides for cross-core interrupts, multi-core debug + hardware semaphores, shared memory,.... config NR_CPUS int "Maximum number of CPUs (2-4096)" range 2 4096 - depends on SMP - default "2" + default "4" + +config ARC_SMP_HALT_ON_RESET + bool "Enable Halt-on-reset boot mode" + default y if ARC_UBOOT_SUPPORT + help + In SMP configuration cores can be configured as Halt-on-reset + or they could all start at same time. For Halt-on-reset, non + masters are parked until Master kicks them so they can start of + at designated entry point. For other case, all jump to common + entry point and spin wait for Master's signal. + +endif #SMP menuconfig ARC_CACHE bool "Enable Cache Support" @@ -185,7 +246,7 @@ config ARC_CACHE_PAGES config ARC_CACHE_VIPT_ALIASING bool "Support VIPT Aliasing D$" - depends on ARC_HAS_DCACHE + depends on ARC_HAS_DCACHE && ISA_ARCOMPACT default n endif #ARC_CACHE @@ -226,9 +287,12 @@ config ARC_HAS_HW_MPY Multipler. Otherwise software multipy lib is used choice - prompt "ARC700 MMU Version" + prompt "MMU Version" default ARC_MMU_V3 if ARC_CPU_770 default ARC_MMU_V2 if ARC_CPU_750D + default ARC_MMU_V4 if ARC_CPU_HS + +if ISA_ARCOMPACT config ARC_MMU_V1 bool "MMU v1" @@ -249,6 +313,12 @@ config ARC_MMU_V3 Variable Page size (1k-16k), var JTLB size 128 x (2 or 4) Shared Address Spaces (SASID) +endif + +config ARC_MMU_V4 + bool "MMU v4" + depends on ISA_ARCV2 + endchoice @@ -263,14 +333,16 @@ config ARC_PAGE_SIZE_8K config ARC_PAGE_SIZE_16K bool "16KB" - depends on ARC_MMU_V3 + depends on ARC_MMU_V3 || ARC_MMU_V4 config ARC_PAGE_SIZE_4K bool "4KB" - depends on ARC_MMU_V3 + depends on ARC_MMU_V3 || ARC_MMU_V4 endchoice +if ISA_ARCOMPACT + config ARC_COMPACT_IRQ_LEVELS bool "ARCompact IRQ Priorities: High(2)/Low(1)" default n @@ -290,7 +362,7 @@ config ARC_IRQ5_LV2 config ARC_IRQ6_LV2 bool -endif +endif #ARC_COMPACT_IRQ_LEVELS config ARC_FPU_SAVE_RESTORE bool "Enable FPU state persistence across context switch" @@ -303,32 +375,62 @@ config ARC_FPU_SAVE_RESTORE based on actual usage of FPU by a task. Thus our implemn does this for all tasks in system. +endif #ISA_ARCOMPACT + config ARC_CANT_LLSC def_bool n -menuconfig ARC_CPU_REL_4_10 - bool "Enable support for Rel 4.10 features" - default n - help - -ARC770 (and dependent features) enabled - -ARC750 also shares some of the new features with 770 - config ARC_HAS_LLSC bool "Insn: LLOCK/SCOND (efficient atomic ops)" default y - depends on ARC_CPU_770 && !ARC_CANT_LLSC + depends on !ARC_CANT_LLSC + +config ARC_STAR_9000923308 + bool "Workaround for llock/scond livelock" + default y + depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC config ARC_HAS_SWAPE bool "Insn: SWAPE (endian-swap)" default y - depends on ARC_CPU_REL_4_10 -config ARC_HAS_RTSC - bool "Insn: RTSC (64-bit r/o cycle counter)" +if ISA_ARCV2 + +config ARC_HAS_LL64 + bool "Insn: 64bit LDD/STD" + help + Enable gcc to generate 64-bit load/store instructions + ISA mandates even/odd registers to allow encoding of two + dest operands with 2 possible source operands. + default y + +config ARC_HAS_DIV_REM + bool "Insn: div, divu, rem, remu" default y - depends on ARC_CPU_REL_4_10 + +config ARC_HAS_RTC + bool "Local 64-bit r/o cycle counter" + default n depends on !SMP +config ARC_HAS_GRTC + bool "SMP synchronized 64-bit cycle counter" + default y + depends on SMP + +config ARC_NUMBER_OF_INTERRUPTS + int "Number of interrupts" + range 8 240 + default 32 + help + This defines the number of interrupts on the ARCv2HS core. + It affects the size of vector table. + The initial 8 IRQs are fixed (Timer, ICI etc) and although configurable + in hardware, it keep things simple for Linux to assume they are always + present. + +endif # ISA_ARCV2 + endmenu # "ARC CPU Configuration" config LINUX_LINK_BASE @@ -343,6 +445,29 @@ config LINUX_LINK_BASE However some customers have peripherals mapped at this addr, so Linux needs to be scooted a bit. If you don't know what the above means, leave this setting alone. + This needs to match memory start address specified in Device Tree + +config HIGHMEM + bool "High Memory Support" + help + With ARC 2G:2G address split, only upper 2G is directly addressable by + kernel. Enable this to potentially allow access to rest of 2G and PAE + in future + +config ARC_HAS_PAE40 + bool "Support for the 40-bit Physical Address Extension" + default n + depends on ISA_ARCV2 + select HIGHMEM + help + Enable access to physical memory beyond 4G, only supported on + ARC cores with 40 bit Physical Addressing support + +config ARCH_PHYS_ADDR_T_64BIT + def_bool ARC_HAS_PAE40 + +config ARCH_DMA_ADDR_T_64BIT + bool config ARC_CURR_IN_REG bool "Dedicate Register r25 for current_task pointer" @@ -354,8 +479,10 @@ config ARC_CURR_IN_REG config ARC_EMUL_UNALIGNED bool "Emulate unaligned memory access (userspace only)" + default N select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_ARCH_UNALIGN_ALLOW + depends on ISA_ARCOMPACT help This enables misaligned 16 & 32 bit memory access from user space. Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide @@ -378,9 +505,10 @@ menuconfig ARC_DBG bool "ARC debugging" default y +if ARC_DBG + config ARC_DW2_UNWIND bool "Enable DWARF specific kernel stack unwind" - depends on ARC_DBG default y select KALLSYMS help @@ -394,18 +522,38 @@ config ARC_DW2_UNWIND config ARC_DBG_TLB_PARANOIA bool "Paranoia Checks in Low Level TLB Handlers" - depends on ARC_DBG default n config ARC_DBG_TLB_MISS_COUNT bool "Profile TLB Misses" default n select DEBUG_FS - depends on ARC_DBG help Counts number of I and D TLB Misses and exports them via Debugfs The counters can be cleared via Debugfs as well +if SMP + +config ARC_IPI_DBG + bool "Debug Inter Core interrupts" + default n + +endif + +endif + +config ARC_UBOOT_SUPPORT + bool "Support uboot arg Handling" + default n + help + ARC Linux by default checks for uboot provided args as pointers to + external cmdline or DTB. This however breaks in absence of uboot, + when booting from Metaware debugger directly, as the registers are + not zeroed out on reset by mdb and/or ARCv2 based cores. The bogus + registers look like uboot args to kernel which then chokes. + So only enable the uboot arg checking/processing if users are sure + of uboot being in play. + config ARC_BUILTIN_DTB_NAME string "Built in DTB" help diff --git a/kernel/arch/arc/Makefile b/kernel/arch/arc/Makefile index 2f21e1e0e..aeb190210 100644 --- a/kernel/arch/arc/Makefile +++ b/kernel/arch/arc/Makefile @@ -9,12 +9,14 @@ UTS_MACHINE := arc ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := arc-linux-uclibc- +CROSS_COMPILE := arc-linux- endif KBUILD_DEFCONFIG := nsim_700_defconfig -cflags-y += -mA7 -fno-common -pipe -fno-builtin -D__linux__ +cflags-y += -fno-common -pipe -fno-builtin -D__linux__ +cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 +cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file @@ -33,7 +35,19 @@ cflags-$(atleast_gcc44) += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape -cflags-$(CONFIG_ARC_HAS_RTSC) += -mrtsc + +ifdef CONFIG_ISA_ARCV2 + +ifndef CONFIG_ARC_HAS_LL64 +cflags-y += -mno-ll64 +endif + +ifndef CONFIG_ARC_HAS_DIV_REM +cflags-y += -mno-div-rem +endif + +endif + cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok @@ -67,7 +81,7 @@ endif LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel -KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls -mno-millicode # Finally dump eveything into kernel build system KBUILD_CFLAGS += $(cflags-y) @@ -82,8 +96,9 @@ core-y += arch/arc/ # w/o this dtb won't embed into kernel binary core-y += arch/arc/boot/dts/ -core-$(CONFIG_ARC_PLAT_FPGA_LEGACY) += arch/arc/plat-arcfpga/ -core-$(CONFIG_ARC_PLAT_TB10X) += arch/arc/plat-tb10x/ +core-$(CONFIG_ARC_PLAT_SIM) += arch/arc/plat-sim/ +core-$(CONFIG_ARC_PLAT_TB10X) += arch/arc/plat-tb10x/ +core-$(CONFIG_ARC_PLAT_AXS10X) += arch/arc/plat-axs10x/ drivers-$(CONFIG_OPROFILE) += arch/arc/oprofile/ @@ -106,7 +121,7 @@ $(boot_targets): vmlinux $(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@ dtbs: scripts - $(Q)$(MAKE) $(build)=$(boot)/dts dtbs + $(Q)$(MAKE) $(build)=$(boot)/dts archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/kernel/arch/arc/boot/dts/Makefile b/kernel/arch/arc/boot/dts/Makefile index faf240e29..a09f11b71 100644 --- a/kernel/arch/arc/boot/dts/Makefile +++ b/kernel/arch/arc/boot/dts/Makefile @@ -1,15 +1,17 @@ # Built-in dtb -builtindtb-y := angel4 +builtindtb-y := nsim_700 ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),"") builtindtb-y := $(patsubst "%",%,$(CONFIG_ARC_BUILTIN_DTB_NAME)) endif obj-y += $(builtindtb-y).dtb.o -targets += $(builtindtb-y).dtb +dtb-y := $(builtindtb-y).dtb .SECONDARY: $(obj)/$(builtindtb-y).dtb.S -dtbs: $(addprefix $(obj)/, $(builtindtb-y).dtb) +dtstree := $(srctree)/$(src) +dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +always := $(dtb-y) clean-files := *.dtb *.dtb.S diff --git a/kernel/arch/arc/boot/dts/axc001.dtsi b/kernel/arch/arc/boot/dts/axc001.dtsi new file mode 100644 index 000000000..420dcfde2 --- /dev/null +++ b/kernel/arch/arc/boot/dts/axc001.dtsi @@ -0,0 +1,100 @@ +/* + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device tree for AXC001 770D/EM6/AS221 CPU card + * Note that this file only supports the 770D CPU + */ + +/ { + compatible = "snps,arc"; + clock-frequency = <750000000>; /* 750 MHZ */ + #address-cells = <1>; + #size-cells = <1>; + + cpu_card { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0x00000000 0xf0000000 0x10000000>; + + cpu_intc: arc700-intc@cpu { + compatible = "snps,arc700-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + /* + * this GPIO block ORs all interrupts on CPU card (creg,..) + * to uplink only 1 IRQ to ARC core intc + */ + dw-apb-gpio@0x2000 { + compatible = "snps,dw-apb-gpio"; + reg = < 0x2000 0x80 >; + #address-cells = <1>; + #size-cells = <0>; + + ictl_intc: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <30>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpu_intc>; + interrupts = <15>; + }; + }; + + debug_uart: dw-apb-uart@0x5000 { + compatible = "snps,dw-apb-uart"; + reg = <0x5000 0x100>; + clock-frequency = <33333000>; + interrupt-parent = <&ictl_intc>; + interrupts = <19 4>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + arcpmu0: pmu { + compatible = "snps,arc700-pct"; + }; + }; + + /* + * This INTC is actually connected to DW APB GPIO + * which acts as a wire between MB INTC and CPU INTC. + * GPIO INTC is configured in platform init code + * and here we mimic direct connection from MB INTC to + * CPU INTC, thus we set "interrupts = <7>" instead of + * "interrupts = <12>" + * + * This intc actually resides on MB, but we move it here to + * avoid duplicating the MB dtsi file given that IRQ from + * this intc to cpu intc are different for axs101 and axs103 + */ + mb_intc: dw-apb-ictl@0xe0012000 { + #interrupt-cells = <1>; + compatible = "snps,dw-apb-ictl"; + reg = < 0xe0012000 0x200 >; + interrupt-controller; + interrupt-parent = <&cpu_intc>; + interrupts = < 7 >; + }; + + memory { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x80000000 0x40000000>; + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512MiB */ + }; +}; diff --git a/kernel/arch/arc/boot/dts/axc003.dtsi b/kernel/arch/arc/boot/dts/axc003.dtsi new file mode 100644 index 000000000..f90fadf7f --- /dev/null +++ b/kernel/arch/arc/boot/dts/axc003.dtsi @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device tree for AXC003 CPU card: HS38x UP configuration + */ + +/ { + compatible = "snps,arc"; + clock-frequency = <90000000>; + #address-cells = <1>; + #size-cells = <1>; + + cpu_card { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0x00000000 0xf0000000 0x10000000>; + + cpu_intc: archs-intc@cpu { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + /* + * this GPIO block ORs all interrupts on CPU card (creg,..) + * to uplink only 1 IRQ to ARC core intc + */ + dw-apb-gpio@0x2000 { + compatible = "snps,dw-apb-gpio"; + reg = < 0x2000 0x80 >; + #address-cells = <1>; + #size-cells = <0>; + + ictl_intc: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <30>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&cpu_intc>; + interrupts = <25>; + }; + }; + + debug_uart: dw-apb-uart@0x5000 { + compatible = "snps,dw-apb-uart"; + reg = <0x5000 0x100>; + clock-frequency = <33333000>; + interrupt-parent = <&ictl_intc>; + interrupts = <2 4>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupt-parent = <&cpu_intc>; + interrupts = <20>; + }; + }; + + /* + * The DW APB ICTL intc on MB is connected to CPU intc via a + * DT "invisible" DW APB GPIO block, configured to simply pass thru + * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) + * + * So here we mimic a direct connection betwen them, ignoring the + * ABPG GPIO. Thus set "interrupts = <24>" (DW APB GPIO to core) + * instead of "interrupts = <12>" (DW APB ICTL to DW APB GPIO) + * + * This intc actually resides on MB, but we move it here to + * avoid duplicating the MB dtsi file given that IRQ from + * this intc to cpu intc are different for axs101 and axs103 + */ + mb_intc: dw-apb-ictl@0xe0012000 { + #interrupt-cells = <1>; + compatible = "snps,dw-apb-ictl"; + reg = < 0xe0012000 0x200 >; + interrupt-controller; + interrupt-parent = <&cpu_intc>; + interrupts = < 24 >; + }; + + memory { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x80000000 0x40000000>; + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512MiB */ + }; +}; diff --git a/kernel/arch/arc/boot/dts/axc003_idu.dtsi b/kernel/arch/arc/boot/dts/axc003_idu.dtsi new file mode 100644 index 000000000..06a9f294a --- /dev/null +++ b/kernel/arch/arc/boot/dts/axc003_idu.dtsi @@ -0,0 +1,126 @@ +/* + * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device tree for AXC003 CPU card: HS38x2 (Dual Core) with IDU intc + */ + +/ { + compatible = "snps,arc"; + clock-frequency = <90000000>; + #address-cells = <1>; + #size-cells = <1>; + + cpu_card { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0x00000000 0xf0000000 0x10000000>; + + cpu_intc: archs-intc@cpu { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + idu_intc: idu-interrupt-controller { + compatible = "snps,archs-idu-intc"; + interrupt-controller; + interrupt-parent = <&cpu_intc>; + + /* + * <hwirq distribution> + * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + */ + #interrupt-cells = <2>; + + /* + * upstream irqs to core intc - downstream these are + * "COMMON" irq 0,1.. + */ + interrupts = <24 25>; + }; + + /* + * this GPIO block ORs all interrupts on CPU card (creg,..) + * to uplink only 1 IRQ to ARC core intc + */ + dw-apb-gpio@0x2000 { + compatible = "snps,dw-apb-gpio"; + reg = < 0x2000 0x80 >; + #address-cells = <1>; + #size-cells = <0>; + + ictl_intc: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <30>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&idu_intc>; + + /* + * cmn irq 1 -> cpu irq 25 + * Distribute to cpu0 only + */ + interrupts = <1 1>; + }; + }; + + debug_uart: dw-apb-uart@0x5000 { + compatible = "snps,dw-apb-uart"; + reg = <0x5000 0x100>; + clock-frequency = <33333000>; + interrupt-parent = <&ictl_intc>; + interrupts = <2 4>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupt-parent = <&cpu_intc>; + interrupts = <20>; + }; + }; + + /* + * This INTC is actually connected to DW APB GPIO + * which acts as a wire between MB INTC and CPU INTC. + * GPIO INTC is configured in platform init code + * and here we mimic direct connection from MB INTC to + * CPU INTC, thus we set "interrupts = <0 1>" instead of + * "interrupts = <12>" + * + * This intc actually resides on MB, but we move it here to + * avoid duplicating the MB dtsi file given that IRQ from + * this intc to cpu intc are different for axs101 and axs103 + */ + mb_intc: dw-apb-ictl@0xe0012000 { + #interrupt-cells = <1>; + compatible = "snps,dw-apb-ictl"; + reg = < 0xe0012000 0x200 >; + interrupt-controller; + interrupt-parent = <&idu_intc>; + interrupts = <0 1>; /* cmn irq 0 -> cpu irq 24 + distribute to cpu0 only */ + }; + + memory { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x80000000 0x40000000>; + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512MiB */ + }; +}; diff --git a/kernel/arch/arc/boot/dts/axs101.dts b/kernel/arch/arc/boot/dts/axs101.dts new file mode 100644 index 000000000..3f9b0582e --- /dev/null +++ b/kernel/arch/arc/boot/dts/axs101.dts @@ -0,0 +1,21 @@ +/* + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * ARC AXS101 S/W development platform + * + * 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. + */ +/dts-v1/; + +/include/ "axc001.dtsi" +/include/ "axs10x_mb.dtsi" + +/ { + compatible = "snps,axs101", "snps,arc-sdp"; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0"; + }; +}; diff --git a/kernel/arch/arc/boot/dts/axs103.dts b/kernel/arch/arc/boot/dts/axs103.dts new file mode 100644 index 000000000..e6d0e31ea --- /dev/null +++ b/kernel/arch/arc/boot/dts/axs103.dts @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device Tree for AXS103 SDP with AXS10X Main Board and + * AXC003 FPGA Card (with UP bitfile) + */ +/dts-v1/; + +/include/ "axc003.dtsi" +/include/ "axs10x_mb.dtsi" + +/ { + compatible = "snps,axs103", "snps,arc-sdp"; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=ttyS3,115200n8 debug print-fatal-signals=1"; + }; +}; diff --git a/kernel/arch/arc/boot/dts/axs103_idu.dts b/kernel/arch/arc/boot/dts/axs103_idu.dts new file mode 100644 index 000000000..f999fef5a --- /dev/null +++ b/kernel/arch/arc/boot/dts/axs103_idu.dts @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device Tree for AXS103 SDP with AXS10X Main Board and + * AXC003 FPGA Card (with SMP bitfile) + */ +/dts-v1/; + +/include/ "axc003_idu.dtsi" +/include/ "axs10x_mb.dtsi" + +/ { + compatible = "snps,axs103", "snps,arc-sdp"; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=ttyS3,115200n8 debug print-fatal-signals=1"; + }; +}; diff --git a/kernel/arch/arc/boot/dts/axs10x_mb.dtsi b/kernel/arch/arc/boot/dts/axs10x_mb.dtsi new file mode 100644 index 000000000..44a578c10 --- /dev/null +++ b/kernel/arch/arc/boot/dts/axs10x_mb.dtsi @@ -0,0 +1,225 @@ +/* + * Support for peripherals on the AXS10x mainboard + * + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/ { + axs10x_mb { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0xe0000000 0x10000000>; + interrupt-parent = <&mb_intc>; + + clocks { + i2cclk: i2cclk { + compatible = "fixed-clock"; + clock-frequency = <50000000>; + #clock-cells = <0>; + }; + + apbclk: apbclk { + compatible = "fixed-clock"; + clock-frequency = <50000000>; + #clock-cells = <0>; + }; + + mmcclk: mmcclk { + compatible = "fixed-clock"; + clock-frequency = <50000000>; + #clock-cells = <0>; + }; + }; + + ethernet@0x18000 { + #interrupt-cells = <1>; + compatible = "snps,dwmac"; + reg = < 0x18000 0x2000 >; + interrupts = < 4 >; + interrupt-names = "macirq"; + phy-mode = "rgmii"; + snps,pbl = < 32 >; + clocks = <&apbclk>; + clock-names = "stmmaceth"; + max-speed = <100>; + }; + + ehci@0x40000 { + compatible = "generic-ehci"; + reg = < 0x40000 0x100 >; + interrupts = < 8 >; + }; + + ohci@0x60000 { + compatible = "generic-ohci"; + reg = < 0x60000 0x100 >; + interrupts = < 8 >; + }; + + /* + * According to DW Mobile Storage databook it is required + * to use "Hold Register" if card is enumerated in SDR12 or + * SDR25 modes. + * + * Utilization of "Hold Register" is already implemented via + * dw_mci_pltfm_prepare_command() which in its turn gets + * used through dw_mci_drv_data->prepare_command call-back. + * This call-back is used in Altera Socfpga platform and so + * we may reuse it saying that we're compatible with their + * "altr,socfpga-dw-mshc". + * + * Most probably "Hold Register" utilization is platform- + * independent requirement which means that single unified + * "snps,dw-mshc" should be enough for all users of DW MMC once + * dw_mci_pltfm_prepare_command() is used in generic platform + * code. + */ + mmc@0x15000 { + compatible = "altr,socfpga-dw-mshc"; + reg = < 0x15000 0x400 >; + num-slots = < 1 >; + fifo-depth = < 16 >; + card-detect-delay = < 200 >; + clocks = <&apbclk>, <&mmcclk>; + clock-names = "biu", "ciu"; + interrupts = < 7 >; + bus-width = < 4 >; + }; + + uart@0x20000 { + compatible = "snps,dw-apb-uart"; + reg = <0x20000 0x100>; + clock-frequency = <33333333>; + interrupts = <17>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + uart@0x21000 { + compatible = "snps,dw-apb-uart"; + reg = <0x21000 0x100>; + clock-frequency = <33333333>; + interrupts = <18>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + /* UART muxed with USB data port (ttyS3) */ + uart@0x22000 { + compatible = "snps,dw-apb-uart"; + reg = <0x22000 0x100>; + clock-frequency = <33333333>; + interrupts = <19>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + i2c@0x1d000 { + compatible = "snps,designware-i2c"; + reg = <0x1d000 0x100>; + clock-frequency = <400000>; + clocks = <&i2cclk>; + interrupts = <14>; + }; + + i2c@0x1e000 { + compatible = "snps,designware-i2c"; + reg = <0x1e000 0x100>; + clock-frequency = <400000>; + clocks = <&i2cclk>; + interrupts = <15>; + }; + + i2c@0x1f000 { + compatible = "snps,designware-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x1f000 0x100>; + clock-frequency = <400000>; + clocks = <&i2cclk>; + interrupts = <16>; + + eeprom@0x54{ + compatible = "24c01"; + reg = <0x54>; + pagesize = <0x8>; + }; + + eeprom@0x57{ + compatible = "24c04"; + reg = <0x57>; + pagesize = <0x8>; + }; + }; + + gpio0:gpio@13000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x13000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + + gpio0_banka: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + }; + + gpio0_bankb: gpio-controller@1 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <8>; + reg = <1>; + }; + + gpio0_bankc: gpio-controller@2 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <8>; + reg = <2>; + }; + }; + + gpio1:gpio@14000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x14000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + + gpio1_banka: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <30>; + reg = <0>; + }; + + gpio1_bankb: gpio-controller@1 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <10>; + reg = <1>; + }; + + gpio1_bankc: gpio-controller@2 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <8>; + reg = <2>; + }; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/angel4.dts b/kernel/arch/arc/boot/dts/nsim_700.dts index 3b076fbd8..105a00170 100644 --- a/kernel/arch/arc/boot/dts/angel4.dts +++ b/kernel/arch/arc/boot/dts/nsim_700.dts @@ -10,7 +10,7 @@ /include/ "skeleton.dtsi" / { - compatible = "snps,arc-angel4"; + compatible = "snps,nsim"; clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; diff --git a/kernel/arch/arc/boot/dts/nsim_hs.dts b/kernel/arch/arc/boot/dts/nsim_hs.dts new file mode 100644 index 000000000..fc81879bc --- /dev/null +++ b/kernel/arch/arc/boot/dts/nsim_hs.dts @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ +/dts-v1/; + +/include/ "skeleton.dtsi" + +/ { + compatible = "snps,nsim_hs"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&core_intc>; + + memory { + device_type = "memory"; + /* CONFIG_LINUX_LINK_BASE needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ + 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ + }; + + chosen { + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + }; + + aliases { + serial0 = &arcuart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* only perip space at end of low mem accessible */ + ranges = <0x80000000 0x0 0x80000000 0x80000000>; + + core_intc: core-interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + arcuart0: serial@c0fc1000 { + compatible = "snps,arc-uart"; + reg = <0xc0fc1000 0x100>; + interrupts = <24>; + clock-frequency = <80000000>; + current-speed = <115200>; + status = "okay"; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/nsim_hs_idu.dts b/kernel/arch/arc/boot/dts/nsim_hs_idu.dts new file mode 100644 index 000000000..46ab31975 --- /dev/null +++ b/kernel/arch/arc/boot/dts/nsim_hs_idu.dts @@ -0,0 +1,72 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ +/dts-v1/; + +/include/ "skeleton.dtsi" + +/ { + compatible = "snps,nsim_hs"; + interrupt-parent = <&core_intc>; + + chosen { + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + }; + + aliases { + serial0 = &arcuart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* child and parent address space 1:1 mapped */ + ranges; + + core_intc: core-interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + idu_intc: idu-interrupt-controller { + compatible = "snps,archs-idu-intc"; + interrupt-controller; + interrupt-parent = <&core_intc>; + + /* + * <hwirq distribution> + * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + */ + #interrupt-cells = <2>; + + /* + * upstream irqs to core intc - downstream these are + * "COMMON" irq 0,1.. + */ + interrupts = <24 25 26 27 28 29 30 31>; + }; + + arcuart0: serial@c0fc1000 { + compatible = "snps,arc-uart"; + reg = <0xc0fc1000 0x100>; + interrupt-parent = <&idu_intc>; + interrupts = <0 0>; + clock-frequency = <80000000>; + current-speed = <115200>; + status = "okay"; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/nsimosci_hs.dts b/kernel/arch/arc/boot/dts/nsimosci_hs.dts new file mode 100644 index 000000000..d64a96f85 --- /dev/null +++ b/kernel/arch/arc/boot/dts/nsimosci_hs.dts @@ -0,0 +1,80 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ +/dts-v1/; + +/include/ "skeleton.dtsi" + +/ { + compatible = "snps,nsimosci_hs"; + clock-frequency = <20000000>; /* 20 MHZ */ + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&core_intc>; + + chosen { + /* this is for console on PGU */ + /* bootargs = "console=tty0 consoleblank=0"; */ + /* this is for console on serial */ + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug"; + }; + + aliases { + serial0 = &uart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* child and parent address space 1:1 mapped */ + ranges; + + core_intc: core-interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + uart0: serial@f0000000 { + compatible = "ns8250"; + reg = <0xf0000000 0x2000>; + interrupts = <24>; + clock-frequency = <3686400>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test = <1>; + }; + + pgu0: pgu@f9000000 { + compatible = "snps,arcpgufb"; + reg = <0xf9000000 0x400>; + }; + + ps2: ps2@f9001000 { + compatible = "snps,arc_ps2"; + reg = <0xf9000400 0x14>; + interrupts = <27>; + interrupt-names = "arc_ps2_irq"; + }; + + eth0: ethernet@f0003000 { + compatible = "snps,oscilan"; + reg = <0xf0003000 0x44>; + interrupts = <25>, <26>; + interrupt-names = "rx", "tx"; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/nsimosci_hs_idu.dts b/kernel/arch/arc/boot/dts/nsimosci_hs_idu.dts new file mode 100644 index 000000000..f6bf0ca95 --- /dev/null +++ b/kernel/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -0,0 +1,101 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ +/dts-v1/; + +/include/ "skeleton.dtsi" + +/ { + compatible = "snps,nsimosci_hs"; + clock-frequency = <5000000>; /* 5 MHZ */ + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&core_intc>; + + chosen { + /* this is for console on serial */ + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug"; + }; + + aliases { + serial0 = &uart0; + }; + + fpga { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + /* child and parent address space 1:1 mapped */ + ranges; + + core_intc: core-interrupt-controller { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; +/* interrupts = <16 17 18 19 20 21 22 23 24 25>; */ + }; + + idu_intc: idu-interrupt-controller { + compatible = "snps,archs-idu-intc"; + interrupt-controller; + interrupt-parent = <&core_intc>; + + /* + * <hwirq distribution> + * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + */ + #interrupt-cells = <2>; + + /* + * upstream irqs to core intc - downstream these are + * "COMMON" irq 0,1.. + */ + interrupts = <24 25 26 27 28 29 30 31>; + }; + + uart0: serial@f0000000 { + compatible = "ns8250"; + reg = <0xf0000000 0x2000>; + interrupt-parent = <&idu_intc>; + interrupts = <0 0>; /* cmn irq 0 -> cpu irq 24 + RR distribute to all cpus */ + clock-frequency = <3686400>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test = <1>; + }; + + pgu0: pgu@f9000000 { + compatible = "snps,arcpgufb"; + reg = <0xf9000000 0x400>; + }; + + ps2: ps2@f9001000 { + compatible = "snps,arc_ps2"; + reg = <0xf9000400 0x14>; + interrupts = <3 0>; + interrupt-parent = <&idu_intc>; + interrupt-names = "arc_ps2_irq"; + }; + + eth0: ethernet@f0003000 { + compatible = "snps,oscilan"; + reg = <0xf0003000 0x44>; + interrupt-parent = <&idu_intc>; + interrupts = <1 2>, <2 2>; + interrupt-names = "rx", "tx"; + }; + + arcpct0: pct { + compatible = "snps,archs-pct"; + #interrupt-cells = <1>; + interrupts = <20>; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/skeleton.dtsi b/kernel/arch/arc/boot/dts/skeleton.dtsi index a870bdd5e..296d371a3 100644 --- a/kernel/arch/arc/boot/dts/skeleton.dtsi +++ b/kernel/arch/arc/boot/dts/skeleton.dtsi @@ -32,6 +32,6 @@ memory { device_type = "memory"; - reg = <0x00000000 0x10000000>; /* 256M */ + reg = <0x80000000 0x10000000>; /* 256M */ }; }; diff --git a/kernel/arch/arc/boot/dts/vdk_axc003.dtsi b/kernel/arch/arc/boot/dts/vdk_axc003.dtsi new file mode 100644 index 000000000..84226bd48 --- /dev/null +++ b/kernel/arch/arc/boot/dts/vdk_axc003.dtsi @@ -0,0 +1,61 @@ +/* + * Copyright (C) 2013, 2014 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device tree for AXC003 CPU card: HS38x UP configuration (VDK version) + */ + +/ { + compatible = "snps,arc"; + clock-frequency = <50000000>; + #address-cells = <1>; + #size-cells = <1>; + + cpu_card { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0x00000000 0xf0000000 0x10000000>; + + cpu_intc: archs-intc@cpu { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + debug_uart: dw-apb-uart@0x5000 { + compatible = "snps,dw-apb-uart"; + reg = <0x5000 0x100>; + clock-frequency = <2403200>; + interrupt-parent = <&cpu_intc>; + interrupts = <19>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + }; + + mb_intc: dw-apb-ictl@0xe0012000 { + #interrupt-cells = <1>; + compatible = "snps,dw-apb-ictl"; + reg = < 0xe0012000 0x200 >; + interrupt-controller; + interrupt-parent = <&cpu_intc>; + interrupts = < 18 >; + }; + + memory { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x80000000 0x40000000>; + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512MiB */ + }; +}; diff --git a/kernel/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/kernel/arch/arc/boot/dts/vdk_axc003_idu.dtsi new file mode 100644 index 000000000..31f0fb5fc --- /dev/null +++ b/kernel/arch/arc/boot/dts/vdk_axc003_idu.dtsi @@ -0,0 +1,76 @@ +/* + * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/* + * Device tree for AXC003 CPU card: + * HS38x2 (Dual Core) with IDU intc (VDK version) + */ + +/ { + compatible = "snps,arc"; + clock-frequency = <50000000>; + #address-cells = <1>; + #size-cells = <1>; + + cpu_card { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0x00000000 0xf0000000 0x10000000>; + + cpu_intc: archs-intc@cpu { + compatible = "snps,archs-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + idu_intc: idu-interrupt-controller { + compatible = "snps,archs-idu-intc"; + interrupt-controller; + interrupt-parent = <&cpu_intc>; + + /* + * <hwirq distribution> + * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + */ + #interrupt-cells = <2>; + + interrupts = <24 25 26 27>; + }; + + debug_uart: dw-apb-uart@0x5000 { + compatible = "snps,dw-apb-uart"; + reg = <0x5000 0x100>; + clock-frequency = <2403200>; + interrupt-parent = <&idu_intc>; + interrupts = <2 0>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + }; + + mb_intc: dw-apb-ictl@0xe0012000 { + #interrupt-cells = <1>; + compatible = "snps,dw-apb-ictl"; + reg = < 0xe0012000 0x200 >; + interrupt-controller; + interrupt-parent = <&idu_intc>; + interrupts = < 0 0 >; + }; + + memory { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x80000000 0x40000000>; + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512MiB */ + }; +}; diff --git a/kernel/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/kernel/arch/arc/boot/dts/vdk_axs10x_mb.dtsi new file mode 100644 index 000000000..45cd665fc --- /dev/null +++ b/kernel/arch/arc/boot/dts/vdk_axs10x_mb.dtsi @@ -0,0 +1,93 @@ +/* + * Support for peripherals on the AXS10x mainboard (VDK version) + * + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * 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. + */ + +/ { + axs10x_mb_vdk { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0xe0000000 0x10000000>; + interrupt-parent = <&mb_intc>; + + clocks { + apbclk: apbclk { + compatible = "fixed-clock"; + clock-frequency = <50000000>; + #clock-cells = <0>; + }; + + }; + + ethernet@0x18000 { + #interrupt-cells = <1>; + compatible = "snps,dwmac"; + reg = < 0x18000 0x2000 >; + interrupts = < 4 >; + interrupt-names = "macirq"; + phy-mode = "rgmii"; + snps,phy-addr = < 0 >; // VDK model phy address is 0 + snps,pbl = < 32 >; + clocks = <&apbclk>; + clock-names = "stmmaceth"; + }; + + ehci@0x40000 { + compatible = "generic-ehci"; + reg = < 0x40000 0x100 >; + interrupts = < 8 >; + }; + + uart@0x20000 { + compatible = "snps,dw-apb-uart"; + reg = <0x20000 0x100>; + clock-frequency = <2403200>; + interrupts = <17>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + uart@0x21000 { + compatible = "snps,dw-apb-uart"; + reg = <0x21000 0x100>; + clock-frequency = <2403200>; + interrupts = <18>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + + uart@0x22000 { + compatible = "snps,dw-apb-uart"; + reg = <0x22000 0x100>; + clock-frequency = <2403200>; + interrupts = <19>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + }; + +/* PGU output directly sent to virtual LCD screen; hdmi controller not modelled */ + pgu@0x17000 { + compatible = "snps,arcpgufb"; + reg = <0x17000 0x400>; + clock-frequency = <51000000>; /* PGU'clock is initated in init function */ + /* interrupts = <5>; PGU interrupts not used, this vector is used for ps2 below */ + }; + +/* VDK has additional ps2 keyboard/mouse interface integrated in LCD screen model */ + ps2: ps2@e0017400 { + compatible = "snps,arc_ps2"; + reg = <0x17400 0x14>; + interrupts = <5>; + interrupt-names = "arc_ps2_irq"; + }; + }; +}; diff --git a/kernel/arch/arc/boot/dts/vdk_hs38.dts b/kernel/arch/arc/boot/dts/vdk_hs38.dts new file mode 100644 index 000000000..5d803dd2d --- /dev/null +++ b/kernel/arch/arc/boot/dts/vdk_hs38.dts @@ -0,0 +1,21 @@ +/* + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * ARC HS38 Virtual Development Kit (VDK) + * + * 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. + */ +/dts-v1/; + +/include/ "vdk_axc003.dtsi" +/include/ "vdk_axs10x_mb.dtsi" + +/ { + compatible = "snps,axs103"; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0"; + }; +}; diff --git a/kernel/arch/arc/boot/dts/vdk_hs38_smp.dts b/kernel/arch/arc/boot/dts/vdk_hs38_smp.dts new file mode 100644 index 000000000..031a5bc79 --- /dev/null +++ b/kernel/arch/arc/boot/dts/vdk_hs38_smp.dts @@ -0,0 +1,21 @@ +/* + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * ARC HS38 Virtual Development Kit, SMP version (VDK) + * + * 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. + */ +/dts-v1/; + +/include/ "vdk_axc003_idu.dtsi" +/include/ "vdk_axs10x_mb.dtsi" + +/ { + compatible = "snps,axs103"; + + chosen { + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0"; + }; +}; diff --git a/kernel/arch/arc/configs/axs101_defconfig b/kernel/arch/arc/configs/axs101_defconfig new file mode 100644 index 000000000..f1ac9818b --- /dev/null +++ b/kernel/arch/arc/configs/axs101_defconfig @@ -0,0 +1,110 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_MODULES=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARC_PLAT_AXS10X=y +CONFIG_AXS101=y +CONFIG_ARC_CACHE_LINE_SHIFT=5 +CONFIG_ARC_BUILTIN_DTB_NAME="axs101" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_STMMAC_ETH=y +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NATIONAL_PHY=y +# CONFIG_USB_NET_DRIVERS is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +CONFIG_MOUSE_SERIAL=y +CONFIG_MOUSE_SYNAPTICS_USB=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +# CONFIG_HWMON is not set +CONFIG_FB=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_DW=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_NFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_FTRACE is not set diff --git a/kernel/arch/arc/configs/axs103_defconfig b/kernel/arch/arc/configs/axs103_defconfig new file mode 100644 index 000000000..323486d6e --- /dev/null +++ b/kernel/arch/arc/configs/axs103_defconfig @@ -0,0 +1,116 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_MODULES=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARC_PLAT_AXS10X=y +CONFIG_AXS103=y +CONFIG_ISA_ARCV2=y +CONFIG_ARC_BUILTIN_DTB_NAME="axs103" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_AXS=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_STMMAC_ETH=y +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NATIONAL_PHY=y +# CONFIG_USB_NET_DRIVERS is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +CONFIG_MOUSE_SERIAL=y +CONFIG_MOUSE_SYNAPTICS_USB=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +# CONFIG_HWMON is not set +CONFIG_FB=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_DW=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_NFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_FTRACE is not set diff --git a/kernel/arch/arc/configs/axs103_smp_defconfig b/kernel/arch/arc/configs/axs103_smp_defconfig new file mode 100644 index 000000000..66191cd04 --- /dev/null +++ b/kernel/arch/arc/configs/axs103_smp_defconfig @@ -0,0 +1,117 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLAB=y +CONFIG_MODULES=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARC_PLAT_AXS10X=y +CONFIG_AXS103=y +CONFIG_ISA_ARCV2=y +CONFIG_SMP=y +CONFIG_ARC_BUILTIN_DTB_NAME="axs103_idu" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_AXS=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_STMMAC_ETH=y +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NATIONAL_PHY=y +# CONFIG_USB_NET_DRIVERS is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +CONFIG_MOUSE_SERIAL=y +CONFIG_MOUSE_SYNAPTICS_USB=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +# CONFIG_HWMON is not set +CONFIG_FB=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_DW=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_NFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_FTRACE is not set diff --git a/kernel/arch/arc/configs/nsim_700_defconfig b/kernel/arch/arc/configs/nsim_700_defconfig index ef4d3bc7b..138f9d887 100644 --- a/kernel/arch/arc/configs/nsim_700_defconfig +++ b/kernel/arch/arc/configs/nsim_700_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set @@ -22,9 +22,8 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_FPGA_LEGACY=y -# CONFIG_ARC_HAS_RTSC is not set -CONFIG_ARC_BUILTIN_DTB_NAME="angel4" +CONFIG_ARC_PLAT_SIM=y +CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set # CONFIG_CROSS_MEMORY_ATTACH is not set diff --git a/kernel/arch/arc/configs/nsim_hs_defconfig b/kernel/arch/arc/configs/nsim_hs_defconfig new file mode 100644 index 000000000..f68838e80 --- /dev/null +++ b/kernel/arch/arc/configs/nsim_hs_defconfig @@ -0,0 +1,64 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ISA_ARCV2=y +CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_ARC=y +CONFIG_SERIAL_ARC_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_CONSOLE is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +# CONFIG_DEBUG_PREEMPT is not set +CONFIG_XZ_DEC=y diff --git a/kernel/arch/arc/configs/nsim_hs_smp_defconfig b/kernel/arch/arc/configs/nsim_hs_smp_defconfig new file mode 100644 index 000000000..96bd1c20f --- /dev/null +++ b/kernel/arch/arc/configs/nsim_hs_smp_defconfig @@ -0,0 +1,63 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ARC_BOARD_ML509=y +CONFIG_ISA_ARCV2=y +CONFIG_SMP=y +CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_ARC=y +CONFIG_SERIAL_ARC_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_CONSOLE is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_XZ_DEC=y diff --git a/kernel/arch/arc/configs/nsimosci_defconfig b/kernel/arch/arc/configs/nsimosci_defconfig index d2ac4e56b..31e1d9576 100644 --- a/kernel/arch/arc/configs/nsimosci_defconfig +++ b/kernel/arch/arc/configs/nsimosci_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set @@ -23,8 +23,7 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_FPGA_LEGACY=y -# CONFIG_ARC_HAS_RTSC is not set +CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/kernel/arch/arc/configs/nsimosci_hs_defconfig b/kernel/arch/arc/configs/nsimosci_hs_defconfig new file mode 100644 index 000000000..fcae66683 --- /dev/null +++ b/kernel/arch/arc/configs/nsimosci_hs_defconfig @@ -0,0 +1,73 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ISA_ARCV2=y +CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" +# CONFIG_COMPACTION is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +CONFIG_NET_OSCI_LAN=y +CONFIG_INPUT_EVDEV=y +# CONFIG_MOUSE_PS2_ALPS is not set +# CONFIG_MOUSE_PS2_LOGIPS2PP is not set +# CONFIG_MOUSE_PS2_SYNAPTICS is not set +# CONFIG_MOUSE_PS2_TRACKPOINT is not set +CONFIG_MOUSE_PS2_TOUCHKIT=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_ARC_PS2=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set diff --git a/kernel/arch/arc/configs/nsimosci_hs_smp_defconfig b/kernel/arch/arc/configs/nsimosci_hs_smp_defconfig new file mode 100644 index 000000000..b01b65916 --- /dev/null +++ b/kernel/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -0,0 +1,93 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +# CONFIG_COMPAT_BRK is not set +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_SIM=y +CONFIG_ARC_BOARD_ML509=y +CONFIG_ISA_ARCV2=y +CONFIG_SMP=y +CONFIG_ARC_HAS_LL64=y +# CONFIG_ARC_HAS_RTSC is not set +CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_IPV6 is not set +# CONFIG_WIRELESS is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NET_OSCI_LAN=y +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_LIBPS2=y +CONFIG_SERIO_ARC_PS2=y +CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +CONFIG_ARCPGU_RGB888=y +CONFIG_ARCPGU_DISPTYPE=0 +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FTRACE=y diff --git a/kernel/arch/arc/configs/tb10x_defconfig b/kernel/arch/arc/configs/tb10x_defconfig index 6be649244..3b4dc9ceb 100644 --- a/kernel/arch/arc/configs/tb10x_defconfig +++ b/kernel/arch/arc/configs/tb10x_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y @@ -26,7 +26,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLOCK is not set CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -# CONFIG_ARC_HAS_RTSC is not set CONFIG_ARC_STACK_NONEXEC=y CONFIG_HZ=250 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" diff --git a/kernel/arch/arc/configs/vdk_hs38_defconfig b/kernel/arch/arc/configs/vdk_hs38_defconfig new file mode 100644 index 000000000..a07f20de2 --- /dev/null +++ b/kernel/arch/arc/configs/vdk_hs38_defconfig @@ -0,0 +1,102 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARC_PLAT_AXS10X=y +CONFIG_AXS103=y +CONFIG_ISA_ARCV2=y +CONFIG_ARC_UBOOT_SUPPORT=y +CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38" +CONFIG_PREEMPT=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_SLRAM=y +CONFIG_BLK_DEV_RAM=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_STMMAC_ETH=y +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NATIONAL_PHY=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +CONFIG_SERIO_ARC_PS2=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +CONFIG_ARCPGU_RGB888=y +CONFIG_ARCPGU_DISPTYPE=0 +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_USB_SERIAL=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_NFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_FTRACE is not set diff --git a/kernel/arch/arc/configs/vdk_hs38_smp_defconfig b/kernel/arch/arc/configs/vdk_hs38_smp_defconfig new file mode 100644 index 000000000..f36c047b3 --- /dev/null +++ b/kernel/arch/arc/configs/vdk_hs38_smp_defconfig @@ -0,0 +1,104 @@ +CONFIG_CROSS_COMPILE="arc-linux-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARC_PLAT_AXS10X=y +CONFIG_AXS103=y +CONFIG_ISA_ARCV2=y +CONFIG_SMP=y +# CONFIG_ARC_HAS_GRTC is not set +CONFIG_ARC_UBOOT_SUPPORT=y +CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp" +CONFIG_PREEMPT=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_SLRAM=y +CONFIG_BLK_DEV_RAM=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_STMMAC_ETH=y +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_NATIONAL_PHY=y +CONFIG_MOUSE_PS2_TOUCHKIT=y +CONFIG_SERIO_ARC_PS2=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_FB=y +CONFIG_ARCPGU_RGB888=y +CONFIG_ARCPGU_DISPTYPE=0 +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_USB_SERIAL=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_NFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_FTRACE is not set diff --git a/kernel/arch/arc/include/asm/Kbuild b/kernel/arch/arc/include/asm/Kbuild index be0c39e76..0b10ef2a4 100644 --- a/kernel/arch/arc/include/asm/Kbuild +++ b/kernel/arch/arc/include/asm/Kbuild @@ -1,5 +1,4 @@ generic-y += auxvec.h -generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h @@ -23,6 +22,7 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h +generic-y += mm-arch-hooks.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h @@ -33,7 +33,6 @@ generic-y += poll.h generic-y += posix_types.h generic-y += preempt.h generic-y += resource.h -generic-y += scatterlist.h generic-y += sembuf.h generic-y += shmbuf.h generic-y += siginfo.h @@ -49,4 +48,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/kernel/arch/arc/include/asm/arcregs.h b/kernel/arch/arc/include/asm/arcregs.h index e2b1b1211..7fac7d85e 100644 --- a/kernel/arch/arc/include/asm/arcregs.h +++ b/kernel/arch/arc/include/asm/arcregs.h @@ -16,6 +16,8 @@ #define ARC_REG_PERIBASE_BCR 0x69 #define ARC_REG_FP_BCR 0x6B /* ARCompact: Single-Precision FPU */ #define ARC_REG_DPFP_BCR 0x6C /* ARCompact: Dbl Precision FPU */ +#define ARC_REG_FP_V2_BCR 0xc8 /* ARCv2 FPU */ +#define ARC_REG_SLC_BCR 0xce #define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_AP_BCR 0x76 @@ -31,7 +33,9 @@ #define ARC_REG_BPU_BCR 0xc0 #define ARC_REG_ISA_CFG_BCR 0xc1 #define ARC_REG_RTT_BCR 0xF2 +#define ARC_REG_IRQ_BCR 0xF3 #define ARC_REG_SMART_BCR 0xFF +#define ARC_REG_CLUSTER_BCR 0xcf /* status32 Bits Positions */ #define STATUS_AE_BIT 5 /* Exception active */ @@ -51,6 +55,7 @@ * [15: 8] = Exception Cause Code * [ 7: 0] = Exception Parameters (for certain types only) */ +#ifdef CONFIG_ISA_ARCOMPACT #define ECR_V_MEM_ERR 0x01 #define ECR_V_INSN_ERR 0x02 #define ECR_V_MACH_CHK 0x20 @@ -58,6 +63,15 @@ #define ECR_V_DTLB_MISS 0x22 #define ECR_V_PROTV 0x23 #define ECR_V_TRAP 0x25 +#else +#define ECR_V_MEM_ERR 0x01 +#define ECR_V_INSN_ERR 0x02 +#define ECR_V_MACH_CHK 0x03 +#define ECR_V_ITLB_MISS 0x04 +#define ECR_V_DTLB_MISS 0x05 +#define ECR_V_PROTV 0x06 +#define ECR_V_TRAP 0x09 +#endif /* DTLB Miss and Protection Violation Cause Codes */ @@ -76,14 +90,10 @@ #define ECR_C_BIT_DTLB_LD_MISS 8 #define ECR_C_BIT_DTLB_ST_MISS 9 -/* Dummy ECR values for Interrupts */ -#define event_IRQ1 0x0031abcd -#define event_IRQ2 0x0032abcd - /* Auxiliary registers */ #define AUX_IDENTITY 4 #define AUX_INTR_VEC_BASE 0x25 - +#define AUX_NON_VOL 0x5e /* * Floating Pt Registers @@ -110,7 +120,7 @@ /* gcc builtin sr needs reg param to be long immediate */ #define write_aux_reg(reg_immed, val) \ - __builtin_arc_sr((unsigned int)val, reg_immed) + __builtin_arc_sr((unsigned int)(val), reg_immed) #else @@ -204,9 +214,11 @@ struct bcr_identity { struct bcr_isa { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad1:23, atomic1:1, ver:8; + unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1, + pad1:11, atomic1:1, ver:8; #else - unsigned int ver:8, atomic1:1, pad1:23; + unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1, + ldd:1, pad2:4, div_rem:4; #endif }; @@ -228,9 +240,9 @@ struct bcr_extn_xymem { struct bcr_perip { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int start:8, pad2:8, sz:8, pad:8; + unsigned int start:8, pad2:8, sz:8, ver:8; #else - unsigned int pad:8, sz:8, pad2:8, start:8; + unsigned int ver:8, sz:8, pad2:8, start:8; #endif }; @@ -269,11 +281,19 @@ struct bcr_fp_arcompact { #endif }; +struct bcr_fp_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad2:15, dp:1, pad1:7, sp:1, ver:8; +#else + unsigned int ver:8, sp:1, pad1:7, dp:1, pad2:15; +#endif +}; + struct bcr_timer { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad2:15, rtsc:1, pad1:6, t1:1, t0:1, ver:8; + unsigned int pad2:15, rtsc:1, pad1:5, rtc:1, t1:1, t0:1, ver:8; #else - unsigned int ver:8, t0:1, t1:1, pad1:6, rtsc:1, pad2:15; + unsigned int ver:8, t0:1, t1:1, rtc:1, pad1:5, rtsc:1, pad2:15; #endif }; @@ -285,6 +305,14 @@ struct bcr_bpu_arcompact { #endif }; +struct bcr_bpu_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:6, fbe:2, tqe:2, ts:4, ft:1, rse:2, pte:3, bce:3, ver:8; +#else + unsigned int ver:8, bce:3, pte:3, rse:2, ft:1, ts:4, tqe:2, fbe:2, pad:6; +#endif +}; + struct bcr_generic { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int pad:24, ver:8; @@ -299,11 +327,12 @@ struct bcr_generic { */ struct cpuinfo_arc_mmu { - unsigned int ver, pg_sz, sets, ways, u_dtlb, u_itlb, num_tlb; + unsigned int ver:4, pg_sz_k:8, s_pg_sz_m:8, pad:10, sasid:1, pae:1; + unsigned int sets:12, ways:4, u_dtlb:8, u_itlb:8; }; struct cpuinfo_arc_cache { - unsigned int sz_k:8, line_len:8, assoc:4, ver:4, alias:1, vipt:1, pad:6; + unsigned int sz_k:14, line_len:8, assoc:4, ver:4, alias:1, vipt:1; }; struct cpuinfo_arc_bpu { @@ -315,14 +344,13 @@ struct cpuinfo_arc_ccm { }; struct cpuinfo_arc { - struct cpuinfo_arc_cache icache, dcache; + struct cpuinfo_arc_cache icache, dcache, slc; struct cpuinfo_arc_mmu mmu; struct cpuinfo_arc_bpu bpu; struct bcr_identity core; struct bcr_isa isa; struct bcr_timer timers; unsigned int vec_base; - unsigned int uncached_base; struct cpuinfo_arc_ccm iccm, dccm; struct { unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3, @@ -336,6 +364,22 @@ struct cpuinfo_arc { extern struct cpuinfo_arc cpuinfo_arc700[]; +static inline int is_isa_arcv2(void) +{ + return IS_ENABLED(CONFIG_ISA_ARCV2); +} + +static inline int is_isa_arcompact(void) +{ + return IS_ENABLED(CONFIG_ISA_ARCOMPACT); +} + +#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7) +#error "Toolchain not configured for ARCompact builds" +#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS) +#error "Toolchain not configured for ARCv2 builds" +#endif + #endif /* __ASEMBLY__ */ #endif /* _ASM_ARC_ARCREGS_H */ diff --git a/kernel/arch/arc/include/asm/atomic.h b/kernel/arch/arc/include/asm/atomic.h index 20b7dc179..7730d302c 100644 --- a/kernel/arch/arc/include/asm/atomic.h +++ b/kernel/arch/arc/include/asm/atomic.h @@ -17,31 +17,66 @@ #include <asm/barrier.h> #include <asm/smp.h> -#define atomic_read(v) ((v)->counter) +#define atomic_read(v) READ_ONCE((v)->counter) #ifdef CONFIG_ARC_HAS_LLSC -#define atomic_set(v, i) (((v)->counter) = (i)) +#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) + +#ifdef CONFIG_ARC_STAR_9000923308 + +#define SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int delay = 1, tmp; \ + +#define SCOND_FAIL_RETRY_ASM \ + " bz 4f \n" \ + " ; --- scond fail delay --- \n" \ + " mov %[tmp], %[delay] \n" /* tmp = delay */ \ + "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ + " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ + " rol %[delay], %[delay] \n" /* delay *= 2 */ \ + " b 1b \n" /* start over */ \ + "4: ; --- success --- \n" \ + +#define SCOND_FAIL_RETRY_VARS \ + ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \ + +#else /* !CONFIG_ARC_STAR_9000923308 */ + +#define SCOND_FAIL_RETRY_VAR_DEF + +#define SCOND_FAIL_RETRY_ASM \ + " bnz 1b \n" \ + +#define SCOND_FAIL_RETRY_VARS + +#endif #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ - unsigned int temp; \ + unsigned int val; \ + SCOND_FAIL_RETRY_VAR_DEF \ \ __asm__ __volatile__( \ - "1: llock %0, [%1] \n" \ - " " #asm_op " %0, %0, %2 \n" \ - " scond %0, [%1] \n" \ - " bnz 1b \n" \ - : "=&r"(temp) /* Early clobber, to prevent reg reuse */ \ - : "r"(&v->counter), "ir"(i) \ + "1: llock %[val], [%[ctr]] \n" \ + " " #asm_op " %[val], %[val], %[i] \n" \ + " scond %[val], [%[ctr]] \n" \ + " \n" \ + SCOND_FAIL_RETRY_ASM \ + \ + : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ + SCOND_FAIL_RETRY_VARS \ + : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ + [i] "ir" (i) \ : "cc"); \ } \ #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ - unsigned int temp; \ + unsigned int val; \ + SCOND_FAIL_RETRY_VAR_DEF \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -50,17 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ smp_mb(); \ \ __asm__ __volatile__( \ - "1: llock %0, [%1] \n" \ - " " #asm_op " %0, %0, %2 \n" \ - " scond %0, [%1] \n" \ - " bnz 1b \n" \ - : "=&r"(temp) \ - : "r"(&v->counter), "ir"(i) \ + "1: llock %[val], [%[ctr]] \n" \ + " " #asm_op " %[val], %[val], %[i] \n" \ + " scond %[val], [%[ctr]] \n" \ + " \n" \ + SCOND_FAIL_RETRY_ASM \ + \ + : [val] "=&r" (val) \ + SCOND_FAIL_RETRY_VARS \ + : [ctr] "r" (&v->counter), \ + [i] "ir" (i) \ : "cc"); \ \ smp_mb(); \ \ - return temp; \ + return val; \ } #else /* !CONFIG_ARC_HAS_LLSC */ @@ -68,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ #ifndef CONFIG_SMP /* violating atomic_xxx API locking protocol in UP for optimization sake */ -#define atomic_set(v, i) (((v)->counter) = (i)) +#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) #else @@ -86,7 +125,7 @@ static inline void atomic_set(atomic_t *v, int i) unsigned long flags; atomic_ops_lock(flags); - v->counter = i; + WRITE_ONCE(v->counter, i); atomic_ops_unlock(flags); } @@ -133,13 +172,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) -ATOMIC_OP(and, &=, and) -#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v)) +#define atomic_andnot atomic_andnot + +ATOMIC_OP(and, &=, and) +ATOMIC_OP(andnot, &= ~, bic) +ATOMIC_OP(or, |=, or) +ATOMIC_OP(xor, ^=, xor) #undef ATOMIC_OPS #undef ATOMIC_OP_RETURN #undef ATOMIC_OP +#undef SCOND_FAIL_RETRY_VAR_DEF +#undef SCOND_FAIL_RETRY_ASM +#undef SCOND_FAIL_RETRY_VARS /** * __atomic_add_unless - add unless the number is a given value diff --git a/kernel/arch/arc/include/asm/barrier.h b/kernel/arch/arc/include/asm/barrier.h new file mode 100644 index 000000000..a7209983e --- /dev/null +++ b/kernel/arch/arc/include/asm/barrier.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#ifdef CONFIG_ISA_ARCV2 + +/* + * ARCv2 based HS38 cores are in-order issue, but still weakly ordered + * due to micro-arch buffering/queuing of load/store, cache hit vs. miss ... + * + * Explicit barrier provided by DMB instruction + * - Operand supports fine grained load/store/load+store semantics + * - Ensures that selected memory operation issued before it will complete + * before any subsequent memory operation of same type + * - DMB guarantees SMP as well as local barrier semantics + * (asm-generic/barrier.h ensures sane smp_*mb if not defined here, i.e. + * UP: barrier(), SMP: smp_*mb == *mb) + * - DSYNC provides DMB+completion_of_cache_bpu_maintenance_ops hence not needed + * in the general case. Plus it only provides full barrier. + */ + +#define mb() asm volatile("dmb 3\n" : : : "memory") +#define rmb() asm volatile("dmb 1\n" : : : "memory") +#define wmb() asm volatile("dmb 2\n" : : : "memory") + +#endif + +#ifdef CONFIG_ISA_ARCOMPACT + +/* + * ARCompact based cores (ARC700) only have SYNC instruction which is super + * heavy weight as it flushes the pipeline as well. + * There are no real SMP implementations of such cores. + */ + +#define mb() asm volatile("sync\n" : : : "memory") +#endif + +#include <asm-generic/barrier.h> + +#endif diff --git a/kernel/arch/arc/include/asm/bitops.h b/kernel/arch/arc/include/asm/bitops.h index dae03e66f..57c1f3384 100644 --- a/kernel/arch/arc/include/asm/bitops.h +++ b/kernel/arch/arc/include/asm/bitops.h @@ -215,6 +215,8 @@ test_bit(unsigned int nr, const volatile unsigned long *addr) return ((mask & *addr) != 0); } +#ifdef CONFIG_ISA_ARCOMPACT + /* * Count the number of zeros, starting from MSB * Helper for fls( ) friends @@ -307,6 +309,75 @@ static inline __attribute__ ((const)) int __ffs(unsigned long word) return ffs(word) - 1; } +#else /* CONFIG_ISA_ARCV2 */ + +/* + * fls = Find Last Set in word + * @result: [1-32] + * fls(1) = 1, fls(0x80000000) = 32, fls(0) = 0 + */ +static inline __attribute__ ((const)) int fls(unsigned long x) +{ + int n; + + asm volatile( + " fls.f %0, %1 \n" /* 0:31; 0(Z) if src 0 */ + " add.nz %0, %0, 1 \n" /* 0:31 -> 1:32 */ + : "=r"(n) /* Early clobber not needed */ + : "r"(x) + : "cc"); + + return n; +} + +/* + * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set + */ +static inline __attribute__ ((const)) int __fls(unsigned long x) +{ + /* FLS insn has exactly same semantics as the API */ + return __builtin_arc_fls(x); +} + +/* + * ffs = Find First Set in word (LSB to MSB) + * @result: [1-32], 0 if all 0's + */ +static inline __attribute__ ((const)) int ffs(unsigned long x) +{ + int n; + + asm volatile( + " ffs.f %0, %1 \n" /* 0:31; 31(Z) if src 0 */ + " add.nz %0, %0, 1 \n" /* 0:31 -> 1:32 */ + " mov.z %0, 0 \n" /* 31(Z)-> 0 */ + : "=r"(n) /* Early clobber not needed */ + : "r"(x) + : "cc"); + + return n; +} + +/* + * __ffs: Similar to ffs, but zero based (0-31) + */ +static inline __attribute__ ((const)) int __ffs(unsigned long x) +{ + int n; + + asm volatile( + " ffs.f %0, %1 \n" /* 0:31; 31(Z) if src 0 */ + " mov.z %0, 0 \n" /* 31(Z)-> 0 */ + : "=r"(n) + : "r"(x) + : "cc"); + + return n; + +} + +#endif /* CONFIG_ISA_ARCOMPACT */ + /* * ffz = Find First Zero in word. * @return:[0-31], 32 if all 1's diff --git a/kernel/arch/arc/include/asm/cache.h b/kernel/arch/arc/include/asm/cache.h index 7861255da..210ef3e72 100644 --- a/kernel/arch/arc/include/asm/cache.h +++ b/kernel/arch/arc/include/asm/cache.h @@ -53,6 +53,8 @@ extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); extern void read_decode_cache_bcr(void); +extern int ioc_exists; + #endif /* !__ASSEMBLY__ */ /* Instruction cache related Auxiliary registers */ @@ -60,9 +62,8 @@ extern void read_decode_cache_bcr(void); #define ARC_REG_IC_IVIC 0x10 #define ARC_REG_IC_CTRL 0x11 #define ARC_REG_IC_IVIL 0x19 -#if defined(CONFIG_ARC_MMU_V3) #define ARC_REG_IC_PTAG 0x1E -#endif +#define ARC_REG_IC_PTAG_HI 0x1F /* Bit val in IC_CTRL */ #define IC_CTRL_CACHE_DISABLE 0x1 @@ -74,12 +75,31 @@ extern void read_decode_cache_bcr(void); #define ARC_REG_DC_IVDL 0x4A #define ARC_REG_DC_FLSH 0x4B #define ARC_REG_DC_FLDL 0x4C -#if defined(CONFIG_ARC_MMU_V3) #define ARC_REG_DC_PTAG 0x5C -#endif +#define ARC_REG_DC_PTAG_HI 0x5F /* Bit val in DC_CTRL */ #define DC_CTRL_INV_MODE_FLUSH 0x40 #define DC_CTRL_FLUSH_STATUS 0x100 +/*System-level cache (L2 cache) related Auxiliary registers */ +#define ARC_REG_SLC_CFG 0x901 +#define ARC_REG_SLC_CTRL 0x903 +#define ARC_REG_SLC_FLUSH 0x904 +#define ARC_REG_SLC_INVALIDATE 0x905 +#define ARC_REG_SLC_RGN_START 0x914 +#define ARC_REG_SLC_RGN_END 0x916 + +/* Bit val in SLC_CONTROL */ +#define SLC_CTRL_IM 0x040 +#define SLC_CTRL_DISABLE 0x001 +#define SLC_CTRL_BUSY 0x100 +#define SLC_CTRL_RGN_OP_INV 0x200 + +/* IO coherency related Auxiliary registers */ +#define ARC_REG_IO_COH_ENABLE 0x500 +#define ARC_REG_IO_COH_PARTIAL 0x501 +#define ARC_REG_IO_COH_AP0_BASE 0x508 +#define ARC_REG_IO_COH_AP0_SIZE 0x509 + #endif /* _ASM_CACHE_H */ diff --git a/kernel/arch/arc/include/asm/cacheflush.h b/kernel/arch/arc/include/asm/cacheflush.h index 6abc4972b..fbe3587c4 100644 --- a/kernel/arch/arc/include/asm/cacheflush.h +++ b/kernel/arch/arc/include/asm/cacheflush.h @@ -31,12 +31,10 @@ void flush_cache_all(void); -void flush_icache_range(unsigned long start, unsigned long end); -void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len); -void __inv_icache_page(unsigned long paddr, unsigned long vaddr); -void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr); -#define __flush_dcache_page(p, v) \ - ___flush_dcache_page((unsigned long)p, (unsigned long)v) +void flush_icache_range(unsigned long kstart, unsigned long kend); +void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len); +void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr); +void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/kernel/arch/arc/include/asm/cmpxchg.h b/kernel/arch/arc/include/asm/cmpxchg.h index 44fd531f4..af7a2db13 100644 --- a/kernel/arch/arc/include/asm/cmpxchg.h +++ b/kernel/arch/arc/include/asm/cmpxchg.h @@ -110,18 +110,18 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, sizeof(*(ptr)))) /* - * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need - * not require any locking. However there's a quirk. - * ARC lacks native CMPXCHG, thus emulated (see above), using external locking - - * incidently it "reuses" the same atomic_ops_lock used by atomic APIs. - * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to - * abide by same serializing rules, thus ends up using atomic_ops_lock as well. + * xchg() maps directly to ARC EX instruction which guarantees atomicity. + * However in !LLSC config, it also needs to be use @atomic_ops_lock spinlock + * due to a subtle reason: + * - For !LLSC, cmpxchg() needs to use that lock (see above) and there is lot + * of kernel code which calls xchg()/cmpxchg() on same data (see llist.h) + * Hence xchg() needs to follow same locking rules. * - * This however is only relevant if SMP and/or ARC lacks LLSC - * if (UP or LLSC) - * xchg doesn't need serialization - * else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC) - * xchg needs serialization + * Technically the lock is also needed for UP (boils down to irq save/restore) + * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to + * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg() + * Other way around, xchg is one instruction anyways, so can't be interrupted + * as such */ #if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP) diff --git a/kernel/arch/arc/include/asm/delay.h b/kernel/arch/arc/include/asm/delay.h index 43de30256..08e7e2a16 100644 --- a/kernel/arch/arc/include/asm/delay.h +++ b/kernel/arch/arc/include/asm/delay.h @@ -22,11 +22,10 @@ static inline void __delay(unsigned long loops) { __asm__ __volatile__( - "1: sub.f %0, %0, 1 \n" - " jpnz 1b \n" - : "+r"(loops) - : - : "cc"); + " lp 1f \n" + " nop \n" + "1: \n" + : "+l"(loops)); } extern void __bad_udelay(void); diff --git a/kernel/arch/arc/include/asm/dma-mapping.h b/kernel/arch/arc/include/asm/dma-mapping.h index 45b8e0cea..2d28ba939 100644 --- a/kernel/arch/arc/include/asm/dma-mapping.h +++ b/kernel/arch/arc/include/asm/dma-mapping.h @@ -14,23 +14,6 @@ #include <asm-generic/dma-coherent.h> #include <asm/cacheflush.h> -#ifndef CONFIG_ARC_PLAT_NEEDS_CPU_TO_DMA -/* - * dma_map_* API take cpu addresses, which is kernel logical address in the - * untranslated address space (0x8000_0000) based. The dma address (bus addr) - * ideally needs to be 0x0000_0000 based hence these glue routines. - * However given that intermediate bus bridges can ignore the high bit, we can - * do with these routines being no-ops. - * If a platform/device comes up which sriclty requires 0 based bus addr - * (e.g. AHB-PCI bridge on Angel4 board), then it can provide it's own versions - */ -#define plat_dma_addr_to_kernel(dev, addr) ((unsigned long)(addr)) -#define plat_kernel_addr_to_dma(dev, ptr) ((dma_addr_t)(ptr)) - -#else -#include <plat/dma_addr.h> -#endif - void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); @@ -94,7 +77,7 @@ dma_map_single(struct device *dev, void *cpu_addr, size_t size, enum dma_data_direction dir) { _dma_cache_sync((unsigned long)cpu_addr, size, dir); - return plat_kernel_addr_to_dma(dev, cpu_addr); + return (dma_addr_t)cpu_addr; } static inline void @@ -147,16 +130,14 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) { - _dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size, - DMA_FROM_DEVICE); + _dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE); } static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) { - _dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size, - DMA_TO_DEVICE); + _dma_cache_sync(dma_handle, size, DMA_TO_DEVICE); } static inline void @@ -164,8 +145,7 @@ dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle, unsigned long offset, size_t size, enum dma_data_direction direction) { - _dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset, - size, DMA_FROM_DEVICE); + _dma_cache_sync(dma_handle + offset, size, DMA_FROM_DEVICE); } static inline void @@ -173,27 +153,28 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle, unsigned long offset, size_t size, enum dma_data_direction direction) { - _dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset, - size, DMA_TO_DEVICE); + _dma_cache_sync(dma_handle + offset, size, DMA_TO_DEVICE); } static inline void -dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, +dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir) { int i; + struct scatterlist *sg; - for (i = 0; i < nelems; i++, sg++) + for_each_sg(sglist, sg, nelems, i) _dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir); } static inline void -dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction dir) +dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction dir) { int i; + struct scatterlist *sg; - for (i = 0; i < nelems; i++, sg++) + for_each_sg(sglist, sg, nelems, i) _dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir); } diff --git a/kernel/arch/arc/include/asm/elf.h b/kernel/arch/arc/include/asm/elf.h index a26282857..51a99e25f 100644 --- a/kernel/arch/arc/include/asm/elf.h +++ b/kernel/arch/arc/include/asm/elf.h @@ -15,6 +15,11 @@ /* These ELF defines belong to uapi but libc elf.h already defines them */ #define EM_ARCOMPACT 93 +#define EM_ARCV2 195 /* ARCv2 Cores */ + +#define EM_ARC_INUSE (IS_ENABLED(CONFIG_ISA_ARCOMPACT) ? \ + EM_ARCOMPACT : EM_ARCV2) + /* ARC Relocations (kernel Modules only) */ #define R_ARC_32 0x4 #define R_ARC_32_ME 0x1B diff --git a/kernel/arch/arc/include/asm/entry-arcv2.h b/kernel/arch/arc/include/asm/entry-arcv2.h new file mode 100644 index 000000000..b5ff87e6f --- /dev/null +++ b/kernel/arch/arc/include/asm/entry-arcv2.h @@ -0,0 +1,190 @@ + +#ifndef __ASM_ARC_ENTRY_ARCV2_H +#define __ASM_ARC_ENTRY_ARCV2_H + +#include <asm/asm-offsets.h> +#include <asm/irqflags-arcv2.h> +#include <asm/thread_info.h> /* For THREAD_SIZE */ + +/*------------------------------------------------------------------------*/ +.macro INTERRUPT_PROLOGUE called_from + + ; Before jumping to Interrupt Vector, hardware micro-ops did following: + ; 1. SP auto-switched to kernel mode stack + ; 2. STATUS32.Z flag set to U mode at time of interrupt (U:1, K:0) + ; 3. Auto saved: r0-r11, blink, LPE,LPS,LPC, JLI,LDI,EI, PC, STAT32 + ; + ; Now manually save: r12, sp, fp, gp, r25 + + PUSH r12 + + ; Saving pt_regs->sp correctly requires some extra work due to the way + ; Auto stack switch works + ; - U mode: retrieve it from AUX_USER_SP + ; - K mode: add the offset from current SP where H/w starts auto push + ; + ; Utilize the fact that Z bit is set if Intr taken in U mode + mov.nz r9, sp + add.nz r9, r9, SZ_PT_REGS - PT_sp - 4 + bnz 1f + + lr r9, [AUX_USER_SP] +1: + PUSH r9 ; SP + + PUSH fp + PUSH gp + +#ifdef CONFIG_ARC_CURR_IN_REG + PUSH r25 ; user_r25 + GET_CURR_TASK_ON_CPU r25 +#else + sub sp, sp, 4 +#endif + +.ifnc \called_from, exception + sub sp, sp, 12 ; BTA/ECR/orig_r0 placeholder per pt_regs +.endif + +.endm + +/*------------------------------------------------------------------------*/ +.macro INTERRUPT_EPILOGUE called_from + +.ifnc \called_from, exception + add sp, sp, 12 ; skip BTA/ECR/orig_r0 placeholderss +.endif + +#ifdef CONFIG_ARC_CURR_IN_REG + POP r25 +#else + add sp, sp, 4 +#endif + + POP gp + POP fp + + ; Don't touch AUX_USER_SP if returning to K mode (Z bit set) + ; (Z bit set on K mode is inverse of INTERRUPT_PROLOGUE) + add.z sp, sp, 4 + bz 1f + + POPAX AUX_USER_SP +1: + POP r12 + +.endm + +/*------------------------------------------------------------------------*/ +.macro EXCEPTION_PROLOGUE + + ; Before jumping to Exception Vector, hardware micro-ops did following: + ; 1. SP auto-switched to kernel mode stack + ; 2. STATUS32.Z flag set to U mode at time of interrupt (U:1,K:0) + ; + ; Now manually save the complete reg file + + PUSH r9 ; freeup a register: slot of erstatus + + PUSHAX eret + sub sp, sp, 12 ; skip JLI, LDI, EI + PUSH lp_count + PUSHAX lp_start + PUSHAX lp_end + PUSH blink + + PUSH r11 + PUSH r10 + + ld.as r9, [sp, 10] ; load stashed r9 (status32 stack slot) + lr r10, [erstatus] + st.as r10, [sp, 10] ; save status32 at it's right stack slot + + PUSH r9 + PUSH r8 + PUSH r7 + PUSH r6 + PUSH r5 + PUSH r4 + PUSH r3 + PUSH r2 + PUSH r1 + PUSH r0 + + ; -- for interrupts, regs above are auto-saved by h/w in that order -- + ; Now do what ISR prologue does (manually save r12, sp, fp, gp, r25) + ; + ; Set Z flag if this was from U mode (expected by INTERRUPT_PROLOGUE) + ; Although H/w exception micro-ops do set Z flag for U mode (just like + ; for interrupts), it could get clobbered in case we soft land here from + ; a TLB Miss exception handler (tlbex.S) + + and r10, r10, STATUS_U_MASK + xor.f 0, r10, STATUS_U_MASK + + INTERRUPT_PROLOGUE exception + + PUSHAX erbta + PUSHAX ecr ; r9 contains ECR, expected by EV_Trap + + PUSH r0 ; orig_r0 +.endm + +/*------------------------------------------------------------------------*/ +.macro EXCEPTION_EPILOGUE + + ; Assumes r0 has PT_status32 + btst r0, STATUS_U_BIT ; Z flag set if K, used in INTERRUPT_EPILOGUE + + add sp, sp, 8 ; orig_r0/ECR don't need restoring + POPAX erbta + + INTERRUPT_EPILOGUE exception + + POP r0 + POP r1 + POP r2 + POP r3 + POP r4 + POP r5 + POP r6 + POP r7 + POP r8 + POP r9 + POP r10 + POP r11 + + POP blink + POPAX lp_end + POPAX lp_start + + POP r9 + mov lp_count, r9 + + add sp, sp, 12 ; skip JLI, LDI, EI + POPAX eret + POPAX erstatus + + ld.as r9, [sp, -12] ; reload r9 which got clobbered +.endm + +.macro FAKE_RET_FROM_EXCPN + lr r9, [status32] + bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK) + or r9, r9, (STATUS_L_MASK|STATUS_IE_MASK) + kflag r9 +.endm + +/* Get thread_info of "current" tsk */ +.macro GET_CURR_THR_INFO_FROM_SP reg + bmskn \reg, sp, THREAD_SHIFT - 1 +.endm + +/* Get CPU-ID of this core */ +.macro GET_CPU_ID reg + lr \reg, [identity] + xbfu \reg, \reg, 0xE8 /* 00111 01000 */ + /* M = 8-1 N = 8 */ +.endm + +#endif diff --git a/kernel/arch/arc/include/asm/entry-compact.h b/kernel/arch/arc/include/asm/entry-compact.h new file mode 100644 index 000000000..1aff3be91 --- /dev/null +++ b/kernel/arch/arc/include/asm/entry-compact.h @@ -0,0 +1,306 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * 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. + * + * Vineetg: March 2009 (Supporting 2 levels of Interrupts) + * Stack switching code can no longer reliably rely on the fact that + * if we are NOT in user mode, stack is switched to kernel mode. + * e.g. L2 IRQ interrupted a L1 ISR which had not yet completed + * it's prologue including stack switching from user mode + * + * Vineetg: Aug 28th 2008: Bug #94984 + * -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap + * Normally CPU does this automatically, however when doing FAKE rtie, + * we also need to explicitly do this. The problem in macros + * FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit + * was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context + * + * Vineetg: May 5th 2008 + * -Modified CALLEE_REG save/restore macros to handle the fact that + * r25 contains the kernel current task ptr + * - Defined Stack Switching Macro to be reused in all intr/excp hdlrs + * - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the + * address Write back load ld.ab instead of seperate ld/add instn + * + * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 + */ + +#ifndef __ASM_ARC_ENTRY_COMPACT_H +#define __ASM_ARC_ENTRY_COMPACT_H + +#include <asm/asm-offsets.h> +#include <asm/irqflags-compact.h> +#include <asm/thread_info.h> /* For THREAD_SIZE */ + +/*-------------------------------------------------------------- + * Switch to Kernel Mode stack if SP points to User Mode stack + * + * Entry : r9 contains pre-IRQ/exception/trap status32 + * Exit : SP set to K mode stack + * SP at the time of entry (K/U) saved @ pt_regs->sp + * Clobbers: r9 + *-------------------------------------------------------------*/ + +.macro SWITCH_TO_KERNEL_STK + + /* User Mode when this happened ? Yes: Proceed to switch stack */ + bbit1 r9, STATUS_U_BIT, 88f + + /* OK we were already in kernel mode when this event happened, thus can + * assume SP is kernel mode SP. _NO_ need to do any stack switching + */ + +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS + /* However.... + * If Level 2 Interrupts enabled, we may end up with a corner case: + * 1. User Task executing + * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode) + * 3. But before it could switch SP from USER to KERNEL stack + * a L2 IRQ "Interrupts" L1 + * Thay way although L2 IRQ happened in Kernel mode, stack is still + * not switched. + * To handle this, we may need to switch stack even if in kernel mode + * provided SP has values in range of USER mode stack ( < 0x7000_0000 ) + */ + brlo sp, VMALLOC_START, 88f + + /* TODO: vineetg: + * We need to be a bit more cautious here. What if a kernel bug in + * L1 ISR, caused SP to go whaco (some small value which looks like + * USER stk) and then we take L2 ISR. + * Above brlo alone would treat it as a valid L1-L2 sceanrio + * instead of shouting alound + * The only feasible way is to make sure this L2 happened in + * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in + * L1 ISR before it switches stack + */ + +#endif + + /*------Intr/Ecxp happened in kernel mode, SP already setup ------ */ + /* save it nevertheless @ pt_regs->sp for uniformity */ + + b.d 66f + st sp, [sp, PT_sp - SZ_PT_REGS] + +88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */ + + GET_CURR_TASK_ON_CPU r9 + + /* With current tsk in r9, get it's kernel mode stack base */ + GET_TSK_STACK_BASE r9, r9 + + /* save U mode SP @ pt_regs->sp */ + st sp, [r9, PT_sp - SZ_PT_REGS] + + /* final SP switch */ + mov sp, r9 +66: +.endm + +/*------------------------------------------------------------ + * "FAKE" a rtie to return from CPU Exception context + * This is to re-enable Exceptions within exception + * Look at EV_ProtV to see how this is actually used + *-------------------------------------------------------------*/ + +.macro FAKE_RET_FROM_EXCPN + + lr r9, [status32] + bclr r9, r9, STATUS_AE_BIT + or r9, r9, (STATUS_E1_MASK|STATUS_E2_MASK) + sr r9, [erstatus] + mov r9, 55f + sr r9, [eret] + rtie +55: +.endm + +/*-------------------------------------------------------------- + * For early Exception/ISR Prologue, a core reg is temporarily needed to + * code the rest of prolog (stack switching). This is done by stashing + * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP). + * + * Before saving the full regfile - this reg is restored back, only + * to be saved again on kernel mode stack, as part of pt_regs. + *-------------------------------------------------------------*/ +.macro PROLOG_FREEUP_REG reg, mem +#ifdef CONFIG_SMP + sr \reg, [ARC_REG_SCRATCH_DATA0] +#else + st \reg, [\mem] +#endif +.endm + +.macro PROLOG_RESTORE_REG reg, mem +#ifdef CONFIG_SMP + lr \reg, [ARC_REG_SCRATCH_DATA0] +#else + ld \reg, [\mem] +#endif +.endm + +/*-------------------------------------------------------------- + * Exception Entry prologue + * -Switches stack to K mode (if not already) + * -Saves the register file + * + * After this it is safe to call the "C" handlers + *-------------------------------------------------------------*/ +.macro EXCEPTION_PROLOGUE + + /* Need at least 1 reg to code the early exception prologue */ + PROLOG_FREEUP_REG r9, @ex_saved_reg1 + + /* U/K mode at time of exception (stack not switched if already K) */ + lr r9, [erstatus] + + /* ARC700 doesn't provide auto-stack switching */ + SWITCH_TO_KERNEL_STK + +#ifdef CONFIG_ARC_CURR_IN_REG + /* Treat r25 as scratch reg (save on stack) and load with "current" */ + PUSH r25 + GET_CURR_TASK_ON_CPU r25 +#else + sub sp, sp, 4 +#endif + + st.a r0, [sp, -8] /* orig_r0 needed for syscall (skip ECR slot) */ + sub sp, sp, 4 /* skip pt_regs->sp, already saved above */ + + /* Restore r9 used to code the early prologue */ + PROLOG_RESTORE_REG r9, @ex_saved_reg1 + + /* now we are ready to save the regfile */ + SAVE_R0_TO_R12 + PUSH gp + PUSH fp + PUSH blink + PUSHAX eret + PUSHAX erstatus + PUSH lp_count + PUSHAX lp_end + PUSHAX lp_start + PUSHAX erbta + + lr r9, [ecr] + st r9, [sp, PT_event] /* EV_Trap expects r9 to have ECR */ +.endm + +/*-------------------------------------------------------------- + * Restore all registers used by system call or Exceptions + * SP should always be pointing to the next free stack element + * when entering this macro. + * + * NOTE: + * + * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg + * for memory load operations. If used in that way interrupts are deffered + * by hardware and that is not good. + *-------------------------------------------------------------*/ +.macro EXCEPTION_EPILOGUE + POPAX erbta + POPAX lp_start + POPAX lp_end + + POP r9 + mov lp_count, r9 ;LD to lp_count is not allowed + + POPAX erstatus + POPAX eret + POP blink + POP fp + POP gp + RESTORE_R12_TO_R0 + + ld sp, [sp] /* restore original sp */ + /* orig_r0, ECR, user_r25 skipped automatically */ +.endm + +/* Dummy ECR values for Interrupts */ +#define event_IRQ1 0x0031abcd +#define event_IRQ2 0x0032abcd + +.macro INTERRUPT_PROLOGUE LVL + + /* free up r9 as scratchpad */ + PROLOG_FREEUP_REG r9, @int\LVL\()_saved_reg + + /* Which mode (user/kernel) was the system in when intr occured */ + lr r9, [status32_l\LVL\()] + + SWITCH_TO_KERNEL_STK + +#ifdef CONFIG_ARC_CURR_IN_REG + /* Treat r25 as scratch reg (save on stack) and load with "current" */ + PUSH r25 + GET_CURR_TASK_ON_CPU r25 +#else + sub sp, sp, 4 +#endif + + PUSH 0x003\LVL\()abcd /* Dummy ECR */ + sub sp, sp, 8 /* skip orig_r0 (not needed) + skip pt_regs->sp, already saved above */ + + /* Restore r9 used to code the early prologue */ + PROLOG_RESTORE_REG r9, @int\LVL\()_saved_reg + + SAVE_R0_TO_R12 + PUSH gp + PUSH fp + PUSH blink + PUSH ilink\LVL\() + PUSHAX status32_l\LVL\() + PUSH lp_count + PUSHAX lp_end + PUSHAX lp_start + PUSHAX bta_l\LVL\() +.endm + +/*-------------------------------------------------------------- + * Restore all registers used by interrupt handlers. + * + * NOTE: + * + * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg + * for memory load operations. If used in that way interrupts are deffered + * by hardware and that is not good. + *-------------------------------------------------------------*/ +.macro INTERRUPT_EPILOGUE LVL + POPAX bta_l\LVL\() + POPAX lp_start + POPAX lp_end + + POP r9 + mov lp_count, r9 ;LD to lp_count is not allowed + + POPAX status32_l\LVL\() + POP ilink\LVL\() + POP blink + POP fp + POP gp + RESTORE_R12_TO_R0 + + ld sp, [sp] /* restore original sp */ + /* orig_r0, ECR, user_r25 skipped automatically */ +.endm + +/* Get thread_info of "current" tsk */ +.macro GET_CURR_THR_INFO_FROM_SP reg + bic \reg, sp, (THREAD_SIZE - 1) +.endm + +/* Get CPU-ID of this core */ +.macro GET_CPU_ID reg + lr \reg, [identity] + lsr \reg, \reg, 8 + bmsk \reg, \reg, 7 +.endm + +#endif /* __ASM_ARC_ENTRY_COMPACT_H */ diff --git a/kernel/arch/arc/include/asm/entry.h b/kernel/arch/arc/include/asm/entry.h index 884081099..ad7860c5c 100644 --- a/kernel/arch/arc/include/asm/entry.h +++ b/kernel/arch/arc/include/asm/entry.h @@ -1,45 +1,27 @@ /* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * 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. - * - * Vineetg: March 2009 (Supporting 2 levels of Interrupts) - * Stack switching code can no longer reliably rely on the fact that - * if we are NOT in user mode, stack is switched to kernel mode. - * e.g. L2 IRQ interrupted a L1 ISR which had not yet completed - * it's prologue including stack switching from user mode - * - * Vineetg: Aug 28th 2008: Bug #94984 - * -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap - * Normally CPU does this automatically, however when doing FAKE rtie, - * we also need to explicitly do this. The problem in macros - * FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit - * was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context - * - * Vineetg: May 5th 2008 - * -Modified CALLEE_REG save/restore macros to handle the fact that - * r25 contains the kernel current task ptr - * - Defined Stack Switching Macro to be reused in all intr/excp hdlrs - * - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the - * address Write back load ld.ab instead of seperate ld/add instn - * - * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 */ #ifndef __ASM_ARC_ENTRY_H #define __ASM_ARC_ENTRY_H -#ifdef __ASSEMBLY__ #include <asm/unistd.h> /* For NR_syscalls defination */ -#include <asm/asm-offsets.h> #include <asm/arcregs.h> #include <asm/ptrace.h> #include <asm/processor.h> /* For VMALLOC_START */ -#include <asm/thread_info.h> /* For THREAD_SIZE */ #include <asm/mmu.h> +#ifdef CONFIG_ISA_ARCOMPACT +#include <asm/entry-compact.h> /* ISA specific bits */ +#else +#include <asm/entry-arcv2.h> +#endif + /* Note on the LD/ST addr modes with addr reg wback * * LD.a same as LD.aw @@ -143,8 +125,6 @@ POP r13 .endm -#define OFF_USER_R25_FROM_R24 (SZ_CALLEE_REGS + SZ_PT_REGS - 8)/4 - /*-------------------------------------------------------------- * Collect User Mode callee regs as struct callee_regs - needed by * fork/do_signal/unaligned-access-emulation. @@ -157,12 +137,13 @@ *-------------------------------------------------------------*/ .macro SAVE_CALLEE_SAVED_USER + mov r12, sp ; save SP as ref to pt_regs SAVE_R13_TO_R24 #ifdef CONFIG_ARC_CURR_IN_REG - ; Retrieve orig r25 and save it on stack - ld.as r12, [sp, OFF_USER_R25_FROM_R24] - st.a r12, [sp, -4] + ; Retrieve orig r25 and save it with rest of callee_regs + ld.as r12, [r12, PT_user_r25] + PUSH r12 #else PUSH r25 #endif @@ -209,12 +190,16 @@ .macro RESTORE_CALLEE_SAVED_USER #ifdef CONFIG_ARC_CURR_IN_REG - ld.ab r12, [sp, 4] - st.as r12, [sp, OFF_USER_R25_FROM_R24] + POP r12 #else POP r25 #endif RESTORE_R24_TO_R13 + + ; SP is back to start of pt_regs +#ifdef CONFIG_ARC_CURR_IN_REG + st.as r12, [sp, PT_user_r25] +#endif .endm /*-------------------------------------------------------------- @@ -240,117 +225,6 @@ .endm -/*-------------------------------------------------------------- - * Switch to Kernel Mode stack if SP points to User Mode stack - * - * Entry : r9 contains pre-IRQ/exception/trap status32 - * Exit : SP is set to kernel mode stack pointer - * If CURR_IN_REG, r25 set to "current" task pointer - * Clobbers: r9 - *-------------------------------------------------------------*/ - -.macro SWITCH_TO_KERNEL_STK - - /* User Mode when this happened ? Yes: Proceed to switch stack */ - bbit1 r9, STATUS_U_BIT, 88f - - /* OK we were already in kernel mode when this event happened, thus can - * assume SP is kernel mode SP. _NO_ need to do any stack switching - */ - -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS - /* However.... - * If Level 2 Interrupts enabled, we may end up with a corner case: - * 1. User Task executing - * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode) - * 3. But before it could switch SP from USER to KERNEL stack - * a L2 IRQ "Interrupts" L1 - * Thay way although L2 IRQ happened in Kernel mode, stack is still - * not switched. - * To handle this, we may need to switch stack even if in kernel mode - * provided SP has values in range of USER mode stack ( < 0x7000_0000 ) - */ - brlo sp, VMALLOC_START, 88f - - /* TODO: vineetg: - * We need to be a bit more cautious here. What if a kernel bug in - * L1 ISR, caused SP to go whaco (some small value which looks like - * USER stk) and then we take L2 ISR. - * Above brlo alone would treat it as a valid L1-L2 sceanrio - * instead of shouting alound - * The only feasible way is to make sure this L2 happened in - * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in - * L1 ISR before it switches stack - */ - -#endif - - /* Save Pre Intr/Exception KERNEL MODE SP on kernel stack - * safe-keeping not really needed, but it keeps the epilogue code - * (SP restore) simpler/uniform. - */ - b.d 66f - mov r9, sp - -88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */ - - GET_CURR_TASK_ON_CPU r9 - - /* With current tsk in r9, get it's kernel mode stack base */ - GET_TSK_STACK_BASE r9, r9 - -66: -#ifdef CONFIG_ARC_CURR_IN_REG - /* - * Treat r25 as scratch reg, save it on stack first - * Load it with current task pointer - */ - st r25, [r9, -4] - GET_CURR_TASK_ON_CPU r25 -#endif - - /* Save Pre Intr/Exception User SP on kernel stack */ - st.a sp, [r9, -16] ; Make room for orig_r0, ECR, user_r25 - - /* CAUTION: - * SP should be set at the very end when we are done with everything - * In case of 2 levels of interrupt we depend on value of SP to assume - * that everything else is done (loading r25 etc) - */ - - /* set SP to point to kernel mode stack */ - mov sp, r9 - - /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */ - -.endm - -/*------------------------------------------------------------ - * "FAKE" a rtie to return from CPU Exception context - * This is to re-enable Exceptions within exception - * Look at EV_ProtV to see how this is actually used - *-------------------------------------------------------------*/ - -.macro FAKE_RET_FROM_EXCPN reg - - ld \reg, [sp, PT_status32] - bic \reg, \reg, (STATUS_U_MASK|STATUS_DE_MASK) - bset \reg, \reg, STATUS_L_BIT - sr \reg, [erstatus] - mov \reg, 55f - sr \reg, [eret] - - rtie -55: -.endm - -/* - * @reg [OUT] &thread_info of "current" - */ -.macro GET_CURR_THR_INFO_FROM_SP reg - bic \reg, sp, (THREAD_SIZE - 1) -.endm - /* * @reg [OUT] thread_info->flags of "current" */ @@ -359,222 +233,6 @@ ld \reg, [\reg, THREAD_INFO_FLAGS] .endm -/*-------------------------------------------------------------- - * For early Exception Prologue, a core reg is temporarily needed to - * code the rest of prolog (stack switching). This is done by stashing - * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP). - * - * Before saving the full regfile - this reg is restored back, only - * to be saved again on kernel mode stack, as part of pt_regs. - *-------------------------------------------------------------*/ -.macro EXCPN_PROLOG_FREEUP_REG reg -#ifdef CONFIG_SMP - sr \reg, [ARC_REG_SCRATCH_DATA0] -#else - st \reg, [@ex_saved_reg1] -#endif -.endm - -.macro EXCPN_PROLOG_RESTORE_REG reg -#ifdef CONFIG_SMP - lr \reg, [ARC_REG_SCRATCH_DATA0] -#else - ld \reg, [@ex_saved_reg1] -#endif -.endm - -/*-------------------------------------------------------------- - * Exception Entry prologue - * -Switches stack to K mode (if not already) - * -Saves the register file - * - * After this it is safe to call the "C" handlers - *-------------------------------------------------------------*/ -.macro EXCEPTION_PROLOGUE - - /* Need at least 1 reg to code the early exception prologue */ - EXCPN_PROLOG_FREEUP_REG r9 - - /* U/K mode at time of exception (stack not switched if already K) */ - lr r9, [erstatus] - - /* ARC700 doesn't provide auto-stack switching */ - SWITCH_TO_KERNEL_STK - - /* save the regfile */ - SAVE_ALL_SYS -.endm - -/*-------------------------------------------------------------- - * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc) - * Requires SP to be already switched to kernel mode Stack - * sp points to the next free element on the stack at exit of this macro. - * Registers are pushed / popped in the order defined in struct ptregs - * in asm/ptrace.h - * Note that syscalls are implemented via TRAP which is also a exception - * from CPU's point of view - *-------------------------------------------------------------*/ -.macro SAVE_ALL_SYS - - lr r9, [ecr] - st r9, [sp, 8] /* ECR */ - st r0, [sp, 4] /* orig_r0, needed only for sys calls */ - - /* Restore r9 used to code the early prologue */ - EXCPN_PROLOG_RESTORE_REG r9 - - SAVE_R0_TO_R12 - PUSH gp - PUSH fp - PUSH blink - PUSHAX eret - PUSHAX erstatus - PUSH lp_count - PUSHAX lp_end - PUSHAX lp_start - PUSHAX erbta -.endm - -/*-------------------------------------------------------------- - * Restore all registers used by system call or Exceptions - * SP should always be pointing to the next free stack element - * when entering this macro. - * - * NOTE: - * - * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg - * for memory load operations. If used in that way interrupts are deffered - * by hardware and that is not good. - *-------------------------------------------------------------*/ -.macro RESTORE_ALL_SYS - POPAX erbta - POPAX lp_start - POPAX lp_end - - POP r9 - mov lp_count, r9 ;LD to lp_count is not allowed - - POPAX erstatus - POPAX eret - POP blink - POP fp - POP gp - RESTORE_R12_TO_R0 - - ld sp, [sp] /* restore original sp */ - /* orig_r0, ECR, user_r25 skipped automatically */ -.endm - - -/*-------------------------------------------------------------- - * Save all registers used by interrupt handlers. - *-------------------------------------------------------------*/ -.macro SAVE_ALL_INT1 - - /* restore original r9 to be saved as part of reg-file */ -#ifdef CONFIG_SMP - lr r9, [ARC_REG_SCRATCH_DATA0] -#else - ld r9, [@int1_saved_reg] -#endif - - /* now we are ready to save the remaining context :) */ - st event_IRQ1, [sp, 8] /* Dummy ECR */ - st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - - SAVE_R0_TO_R12 - PUSH gp - PUSH fp - PUSH blink - PUSH ilink1 - PUSHAX status32_l1 - PUSH lp_count - PUSHAX lp_end - PUSHAX lp_start - PUSHAX bta_l1 -.endm - -.macro SAVE_ALL_INT2 - - /* TODO-vineetg: SMP we can't use global nor can we use - * SCRATCH0 as we do for int1 because while int1 is using - * it, int2 can come - */ - /* retsore original r9 , saved in sys_saved_r9 */ - ld r9, [@int2_saved_reg] - - /* now we are ready to save the remaining context :) */ - st event_IRQ2, [sp, 8] /* Dummy ECR */ - st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - - SAVE_R0_TO_R12 - PUSH gp - PUSH fp - PUSH blink - PUSH ilink2 - PUSHAX status32_l2 - PUSH lp_count - PUSHAX lp_end - PUSHAX lp_start - PUSHAX bta_l2 -.endm - -/*-------------------------------------------------------------- - * Restore all registers used by interrupt handlers. - * - * NOTE: - * - * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg - * for memory load operations. If used in that way interrupts are deffered - * by hardware and that is not good. - *-------------------------------------------------------------*/ - -.macro RESTORE_ALL_INT1 - POPAX bta_l1 - POPAX lp_start - POPAX lp_end - - POP r9 - mov lp_count, r9 ;LD to lp_count is not allowed - - POPAX status32_l1 - POP ilink1 - POP blink - POP fp - POP gp - RESTORE_R12_TO_R0 - - ld sp, [sp] /* restore original sp */ - /* orig_r0, ECR, user_r25 skipped automatically */ -.endm - -.macro RESTORE_ALL_INT2 - POPAX bta_l2 - POPAX lp_start - POPAX lp_end - - POP r9 - mov lp_count, r9 ;LD to lp_count is not allowed - - POPAX status32_l2 - POP ilink2 - POP blink - POP fp - POP gp - RESTORE_R12_TO_R0 - - ld sp, [sp] /* restore original sp */ - /* orig_r0, ECR, user_r25 skipped automatically */ -.endm - - -/* Get CPU-ID of this core */ -.macro GET_CPU_ID reg - lr \reg, [identity] - lsr \reg, \reg, 8 - bmsk \reg, \reg, 7 -.endm - #ifdef CONFIG_SMP /*------------------------------------------------- @@ -643,6 +301,4 @@ #endif /* CONFIG_ARC_CURR_IN_REG */ -#endif /* __ASSEMBLY__ */ - #endif /* __ASM_ARC_ENTRY_H */ diff --git a/kernel/arch/arc/include/asm/futex.h b/kernel/arch/arc/include/asm/futex.h index 05b5aaf5b..11e1b1f3a 100644 --- a/kernel/arch/arc/include/asm/futex.h +++ b/kernel/arch/arc/include/asm/futex.h @@ -16,18 +16,22 @@ #include <linux/uaccess.h> #include <asm/errno.h> +#ifdef CONFIG_ARC_HAS_LLSC + #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\ \ + smp_mb(); \ __asm__ __volatile__( \ - "1: ld %1, [%2] \n" \ + "1: llock %1, [%2] \n" \ insn "\n" \ - "2: st %0, [%2] \n" \ + "2: scond %0, [%2] \n" \ + " bnz 1b \n" \ " mov %0, 0 \n" \ "3: \n" \ " .section .fixup,\"ax\" \n" \ " .align 4 \n" \ "4: mov %0, %4 \n" \ - " b 3b \n" \ + " j 3b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ " .align 4 \n" \ @@ -37,7 +41,37 @@ \ : "=&r" (ret), "=&r" (oldval) \ : "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \ - : "cc", "memory") + : "cc", "memory"); \ + smp_mb() \ + +#else /* !CONFIG_ARC_HAS_LLSC */ + +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\ + \ + smp_mb(); \ + __asm__ __volatile__( \ + "1: ld %1, [%2] \n" \ + insn "\n" \ + "2: st %0, [%2] \n" \ + " mov %0, 0 \n" \ + "3: \n" \ + " .section .fixup,\"ax\" \n" \ + " .align 4 \n" \ + "4: mov %0, %4 \n" \ + " j 3b \n" \ + " .previous \n" \ + " .section __ex_table,\"a\" \n" \ + " .align 4 \n" \ + " .word 1b, 4b \n" \ + " .word 2b, 4b \n" \ + " .previous \n" \ + \ + : "=&r" (ret), "=&r" (oldval) \ + : "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \ + : "cc", "memory"); \ + smp_mb() \ + +#endif static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { @@ -53,6 +87,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) return -EFAULT; +#ifndef CONFIG_ARC_HAS_LLSC + preempt_disable(); /* to guarantee atomic r-m-w of futex op */ +#endif pagefault_disable(); switch (op) { @@ -60,6 +97,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) __futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ADD: + /* oldval = *uaddr; *uaddr += oparg ; ret = *uaddr */ __futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg); break; case FUTEX_OP_OR: @@ -76,6 +114,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) } pagefault_enable(); +#ifndef CONFIG_ARC_HAS_LLSC + preempt_enable(); +#endif if (!ret) { switch (cmp) { @@ -104,48 +145,57 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) return ret; } -/* Compare-xchg with pagefaults disabled. - * Notes: - * -Best-Effort: Exchg happens only if compare succeeds. - * If compare fails, returns; leaving retry/looping to upper layers - * -successful cmp-xchg: return orig value in @addr (same as cmp val) - * -Compare fails: return orig value in @addr - * -user access r/w fails: return -EFAULT +/* + * cmpxchg of futex (pagefaults disabled by caller) + * Return 0 for success, -EFAULT otherwise */ static inline int -futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, - u32 newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 expval, + u32 newval) { - u32 val; + int ret = 0; + u32 existval; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); +#ifndef CONFIG_ARC_HAS_LLSC + preempt_disable(); /* to guarantee atomic r-m-w of futex op */ +#endif + smp_mb(); - /* TBD : can use llock/scond */ __asm__ __volatile__( - "1: ld %0, [%3] \n" - " brne %0, %1, 3f \n" - "2: st %2, [%3] \n" +#ifdef CONFIG_ARC_HAS_LLSC + "1: llock %1, [%4] \n" + " brne %1, %2, 3f \n" + "2: scond %3, [%4] \n" + " bnz 1b \n" +#else + "1: ld %1, [%4] \n" + " brne %1, %2, 3f \n" + "2: st %3, [%4] \n" +#endif "3: \n" " .section .fixup,\"ax\" \n" - "4: mov %0, %4 \n" - " b 3b \n" + "4: mov %0, %5 \n" + " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" " .align 4 \n" " .word 1b, 4b \n" " .word 2b, 4b \n" " .previous\n" - : "=&r"(val) - : "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT) + : "+&r"(ret), "=&r"(existval) + : "r"(expval), "r"(newval), "r"(uaddr), "ir"(-EFAULT) : "cc", "memory"); - pagefault_enable(); + smp_mb(); - *uval = val; - return val; +#ifndef CONFIG_ARC_HAS_LLSC + preempt_enable(); +#endif + *uval = existval; + return ret; } #endif diff --git a/kernel/arch/arc/include/asm/highmem.h b/kernel/arch/arc/include/asm/highmem.h new file mode 100644 index 000000000..b1585c963 --- /dev/null +++ b/kernel/arch/arc/include/asm/highmem.h @@ -0,0 +1,61 @@ +/* + * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef _ASM_HIGHMEM_H +#define _ASM_HIGHMEM_H + +#ifdef CONFIG_HIGHMEM + +#include <uapi/asm/page.h> +#include <asm/kmap_types.h> + +/* start after vmalloc area */ +#define FIXMAP_BASE (PAGE_OFFSET - FIXMAP_SIZE - PKMAP_SIZE) +#define FIXMAP_SIZE PGDIR_SIZE /* only 1 PGD worth */ +#define KM_TYPE_NR ((FIXMAP_SIZE >> PAGE_SHIFT)/NR_CPUS) +#define FIXMAP_ADDR(nr) (FIXMAP_BASE + ((nr) << PAGE_SHIFT)) + +/* start after fixmap area */ +#define PKMAP_BASE (FIXMAP_BASE + FIXMAP_SIZE) +#define PKMAP_SIZE PGDIR_SIZE +#define LAST_PKMAP (PKMAP_SIZE >> PAGE_SHIFT) +#define LAST_PKMAP_MASK (LAST_PKMAP - 1) +#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) +#define PKMAP_NR(virt) (((virt) - PKMAP_BASE) >> PAGE_SHIFT) + +#define kmap_prot PAGE_KERNEL + + +#include <asm/cacheflush.h> + +extern void *kmap(struct page *page); +extern void *kmap_high(struct page *page); +extern void *kmap_atomic(struct page *page); +extern void __kunmap_atomic(void *kvaddr); +extern void kunmap_high(struct page *page); + +extern void kmap_init(void); + +static inline void flush_cache_kmaps(void) +{ + flush_cache_all(); +} + +static inline void kunmap(struct page *page) +{ + BUG_ON(in_interrupt()); + if (!PageHighMem(page)) + return; + kunmap_high(page); +} + + +#endif + +#endif diff --git a/kernel/arch/arc/include/asm/hugepage.h b/kernel/arch/arc/include/asm/hugepage.h new file mode 100644 index 000000000..c5094de86 --- /dev/null +++ b/kernel/arch/arc/include/asm/hugepage.h @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + + +#ifndef _ASM_ARC_HUGEPAGE_H +#define _ASM_ARC_HUGEPAGE_H + +#include <linux/types.h> +#include <asm-generic/pgtable-nopmd.h> + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd(pte_val(pte)); +} + +#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) +#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) +#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) +#define pmd_mkhuge(pmd) pte_pmd(pte_mkhuge(pmd_pte(pmd))) +#define pmd_mknotpresent(pmd) pte_pmd(pte_mknotpresent(pmd_pte(pmd))) +#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) + +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) +#define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) +#define pmd_special(pmd) pte_special(pmd_pte(pmd)) + +#define mk_pmd(page, prot) pte_pmd(mk_pte(page, prot)) + +#define pmd_trans_huge(pmd) (pmd_val(pmd) & _PAGE_HW_SZ) +#define pmd_trans_splitting(pmd) (pmd_trans_huge(pmd) && pmd_special(pmd)) + +#define pfn_pmd(pfn, prot) (__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))) + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + /* + * open-coded pte_modify() with additional retaining of HW_SZ bit + * so that pmd_trans_huge() remains true for this PMD + */ + return __pmd((pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HW_SZ)) | pgprot_val(newprot)); +} + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + *pmdp = pmd; +} + +extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd); + +#define has_transparent_hugepage() 1 + +/* Generic variants assume pgtable_t is struct page *, hence need for these */ +#define __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); + +#define __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); + +#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); + +#endif diff --git a/kernel/arch/arc/include/asm/io.h b/kernel/arch/arc/include/asm/io.h index cabd518cb..694ece8a0 100644 --- a/kernel/arch/arc/include/asm/io.h +++ b/kernel/arch/arc/include/asm/io.h @@ -20,6 +20,7 @@ extern void iounmap(const void __iomem *addr); #define ioremap_nocache(phy, sz) ioremap(phy, sz) #define ioremap_wc(phy, sz) ioremap(phy, sz) +#define ioremap_wt(phy, sz) ioremap(phy, sz) /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -98,9 +99,45 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#define readb_relaxed readb -#define readw_relaxed readw -#define readl_relaxed readl +#ifdef CONFIG_ISA_ARCV2 +#include <asm/barrier.h> +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + +/* + * MMIO can also get buffered/optimized in micro-arch, so barriers needed + * Based on ARM model for the typical use case + * + * <ST [DMA buffer]> + * <writel MMIO "go" reg> + * or: + * <readl MMIO "status" reg> + * <LD [DMA buffer]> + * + * http://lkml.kernel.org/r/20150622133656.GG1583@arm.com + */ +#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(); __v; }) +#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(); __v; }) +#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(); __v; }) + +#define writeb(v,c) ({ __iowmb(); writeb_relaxed(v,c); }) +#define writew(v,c) ({ __iowmb(); writew_relaxed(v,c); }) +#define writel(v,c) ({ __iowmb(); writel_relaxed(v,c); }) + +/* + * Relaxed API for drivers which can handle any ordering themselves + */ +#define readb_relaxed(c) __raw_readb(c) +#define readw_relaxed(c) __raw_readw(c) +#define readl_relaxed(c) __raw_readl(c) + +#define writeb_relaxed(v,c) __raw_writeb(v,c) +#define writew_relaxed(v,c) __raw_writew(v,c) +#define writel_relaxed(v,c) __raw_writel(v,c) #include <asm-generic/io.h> diff --git a/kernel/arch/arc/include/asm/irq.h b/kernel/arch/arc/include/asm/irq.h index f38652fb2..4fd7d62a6 100644 --- a/kernel/arch/arc/include/asm/irq.h +++ b/kernel/arch/arc/include/asm/irq.h @@ -13,8 +13,15 @@ #define NR_IRQS 128 /* allow some CPU external IRQ handling */ /* Platform Independent IRQs */ +#ifdef CONFIG_ISA_ARCOMPACT #define TIMER0_IRQ 3 #define TIMER1_IRQ 4 +#define IPI_IRQ (NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */ +#else +#define TIMER0_IRQ 16 +#define TIMER1_IRQ 17 +#define IPI_IRQ 19 +#endif #include <linux/interrupt.h> #include <asm-generic/irq.h> diff --git a/kernel/arch/arc/include/asm/irqflags-arcv2.h b/kernel/arch/arc/include/asm/irqflags-arcv2.h new file mode 100644 index 000000000..68b609234 --- /dev/null +++ b/kernel/arch/arc/include/asm/irqflags-arcv2.h @@ -0,0 +1,138 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_IRQFLAGS_ARCV2_H +#define __ASM_IRQFLAGS_ARCV2_H + +#include <asm/arcregs.h> + +/* status32 Bits */ +#define STATUS_AD_BIT 19 /* Disable Align chk: core supports non-aligned */ +#define STATUS_IE_BIT 31 + +#define STATUS_AD_MASK (1<<STATUS_AD_BIT) +#define STATUS_IE_MASK (1<<STATUS_IE_BIT) + +#define AUX_USER_SP 0x00D +#define AUX_IRQ_CTRL 0x00E +#define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ +#define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ +#define AUX_IRQ_PRIORITY 0x206 +#define ICAUSE 0x40a +#define AUX_IRQ_SELECT 0x40b +#define AUX_IRQ_ENABLE 0x40c + +/* Was Intr taken in User Mode */ +#define AUX_IRQ_ACT_BIT_U 31 + +/* 0 is highest level, but taken by FIRQs, if present in design */ +#define ARCV2_IRQ_DEF_PRIO 0 + +/* seed value for status register */ +#define ISA_INIT_STATUS_BITS (STATUS_IE_MASK | STATUS_AD_MASK | \ + (ARCV2_IRQ_DEF_PRIO << 1)) + +/* SLEEP needs default irq priority (<=) which can interrupt the doze */ +#define ISA_SLEEP_ARG (0x10 | ARCV2_IRQ_DEF_PRIO) + +#ifndef __ASSEMBLY__ + +/* + * Save IRQ state and disable IRQs + */ +static inline long arch_local_irq_save(void) +{ + unsigned long flags; + + __asm__ __volatile__(" clri %0 \n" : "=r" (flags) : : "memory"); + + return flags; +} + +/* + * restore saved IRQ state + */ +static inline void arch_local_irq_restore(unsigned long flags) +{ + __asm__ __volatile__(" seti %0 \n" : : "r" (flags) : "memory"); +} + +/* + * Unconditionally Enable IRQs + */ +static inline void arch_local_irq_enable(void) +{ + unsigned int irqact = read_aux_reg(AUX_IRQ_ACT); + + if (irqact & 0xffff) + write_aux_reg(AUX_IRQ_ACT, irqact & ~0xffff); + + __asm__ __volatile__(" seti \n" : : : "memory"); +} + +/* + * Unconditionally Disable IRQs + */ +static inline void arch_local_irq_disable(void) +{ + __asm__ __volatile__(" clri \n" : : : "memory"); +} + +/* + * save IRQ state + */ +static inline long arch_local_save_flags(void) +{ + unsigned long temp; + + __asm__ __volatile__( + " lr %0, [status32] \n" + : "=&r"(temp) + : + : "memory"); + + return temp; +} + +/* + * Query IRQ state + */ +static inline int arch_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & (STATUS_IE_MASK)); +} + +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + +#else + +.macro IRQ_DISABLE scratch + clri +.endm + +.macro IRQ_ENABLE scratch + seti +.endm + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/kernel/arch/arc/include/asm/irqflags-compact.h b/kernel/arch/arc/include/asm/irqflags-compact.h new file mode 100644 index 000000000..c1d36458b --- /dev/null +++ b/kernel/arch/arc/include/asm/irqflags-compact.h @@ -0,0 +1,199 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_IRQFLAGS_ARCOMPACT_H +#define __ASM_IRQFLAGS_ARCOMPACT_H + +/* vineetg: March 2010 : local_irq_save( ) optimisation + * -Remove explicit mov of current status32 into reg, that is not needed + * -Use BIC insn instead of INVERTED + AND + * -Conditionally disable interrupts (if they are not enabled, don't disable) +*/ + +#include <asm/arcregs.h> + +/* status32 Reg bits related to Interrupt Handling */ +#define STATUS_E1_BIT 1 /* Int 1 enable */ +#define STATUS_E2_BIT 2 /* Int 2 enable */ +#define STATUS_A1_BIT 3 /* Int 1 active */ +#define STATUS_A2_BIT 4 /* Int 2 active */ +#define STATUS_AE_BIT 5 /* Exception active */ + +#define STATUS_E1_MASK (1<<STATUS_E1_BIT) +#define STATUS_E2_MASK (1<<STATUS_E2_BIT) +#define STATUS_A1_MASK (1<<STATUS_A1_BIT) +#define STATUS_A2_MASK (1<<STATUS_A2_BIT) +#define STATUS_AE_MASK (1<<STATUS_AE_BIT) +#define STATUS_IE_MASK (STATUS_E1_MASK | STATUS_E2_MASK) + +/* Other Interrupt Handling related Aux regs */ +#define AUX_IRQ_LEV 0x200 /* IRQ Priority: L1 or L2 */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ +#define AUX_IRQ_LV12 0x43 /* interrupt level register */ + +#define AUX_IENABLE 0x40c +#define AUX_ITRIGGER 0x40d +#define AUX_IPULSE 0x415 + +#define ISA_INIT_STATUS_BITS STATUS_IE_MASK + +#define ISA_SLEEP_ARG 0x3 + +#ifndef __ASSEMBLY__ + +/****************************************************************** + * IRQ Control Macros + * + * All of them have "memory" clobber (compiler barrier) which is needed to + * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available) + * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register) + * + * Noted at the time of Abilis Timer List corruption + * Orig Bug + Rejected solution : https://lkml.org/lkml/2013/3/29/67 + * Reasoning : https://lkml.org/lkml/2013/4/8/15 + * + ******************************************************************/ + +/* + * Save IRQ state and disable IRQs + */ +static inline long arch_local_irq_save(void) +{ + unsigned long temp, flags; + + __asm__ __volatile__( + " lr %1, [status32] \n" + " bic %0, %1, %2 \n" + " and.f 0, %1, %2 \n" + " flag.nz %0 \n" + : "=r"(temp), "=r"(flags) + : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) + : "memory", "cc"); + + return flags; +} + +/* + * restore saved IRQ state + */ +static inline void arch_local_irq_restore(unsigned long flags) +{ + + __asm__ __volatile__( + " flag %0 \n" + : + : "r"(flags) + : "memory"); +} + +/* + * Unconditionally Enable IRQs + */ +static inline void arch_local_irq_enable(void) +{ + unsigned long temp; + + __asm__ __volatile__( + " lr %0, [status32] \n" + " or %0, %0, %1 \n" + " flag %0 \n" + : "=&r"(temp) + : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) + : "cc", "memory"); +} + + +/* + * Unconditionally Disable IRQs + */ +static inline void arch_local_irq_disable(void) +{ + unsigned long temp; + + __asm__ __volatile__( + " lr %0, [status32] \n" + " and %0, %0, %1 \n" + " flag %0 \n" + : "=&r"(temp) + : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)) + : "memory"); +} + +/* + * save IRQ state + */ +static inline long arch_local_save_flags(void) +{ + unsigned long temp; + + __asm__ __volatile__( + " lr %0, [status32] \n" + : "=&r"(temp) + : + : "memory"); + + return temp; +} + +/* + * Query IRQ state + */ +static inline int arch_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & (STATUS_E1_MASK +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS + | STATUS_E2_MASK +#endif + )); +} + +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + +#else + +#ifdef CONFIG_TRACE_IRQFLAGS + +.macro TRACE_ASM_IRQ_DISABLE + bl trace_hardirqs_off +.endm + +.macro TRACE_ASM_IRQ_ENABLE + bl trace_hardirqs_on +.endm + +#else + +.macro TRACE_ASM_IRQ_DISABLE +.endm + +.macro TRACE_ASM_IRQ_ENABLE +.endm + +#endif + +.macro IRQ_DISABLE scratch + lr \scratch, [status32] + bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) + flag \scratch + TRACE_ASM_IRQ_DISABLE +.endm + +.macro IRQ_ENABLE scratch + lr \scratch, [status32] + or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) + flag \scratch + TRACE_ASM_IRQ_ENABLE +.endm + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/kernel/arch/arc/include/asm/irqflags.h b/kernel/arch/arc/include/asm/irqflags.h index 27ecc6975..59bc6a64f 100644 --- a/kernel/arch/arc/include/asm/irqflags.h +++ b/kernel/arch/arc/include/asm/irqflags.h @@ -1,4 +1,5 @@ /* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * This program is free software; you can redistribute it and/or modify @@ -9,171 +10,10 @@ #ifndef __ASM_ARC_IRQFLAGS_H #define __ASM_ARC_IRQFLAGS_H -/* vineetg: March 2010 : local_irq_save( ) optimisation - * -Remove explicit mov of current status32 into reg, that is not needed - * -Use BIC insn instead of INVERTED + AND - * -Conditionally disable interrupts (if they are not enabled, don't disable) -*/ - -#include <asm/arcregs.h> - -/* status32 Reg bits related to Interrupt Handling */ -#define STATUS_E1_BIT 1 /* Int 1 enable */ -#define STATUS_E2_BIT 2 /* Int 2 enable */ -#define STATUS_A1_BIT 3 /* Int 1 active */ -#define STATUS_A2_BIT 4 /* Int 2 active */ - -#define STATUS_E1_MASK (1<<STATUS_E1_BIT) -#define STATUS_E2_MASK (1<<STATUS_E2_BIT) -#define STATUS_A1_MASK (1<<STATUS_A1_BIT) -#define STATUS_A2_MASK (1<<STATUS_A2_BIT) - -/* Other Interrupt Handling related Aux regs */ -#define AUX_IRQ_LEV 0x200 /* IRQ Priority: L1 or L2 */ -#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ -#define AUX_IRQ_LV12 0x43 /* interrupt level register */ - -#define AUX_IENABLE 0x40c -#define AUX_ITRIGGER 0x40d -#define AUX_IPULSE 0x415 - -#ifndef __ASSEMBLY__ - -/****************************************************************** - * IRQ Control Macros - * - * All of them have "memory" clobber (compiler barrier) which is needed to - * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available) - * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register) - * - * Noted at the time of Abilis Timer List corruption - * Orig Bug + Rejected solution : https://lkml.org/lkml/2013/3/29/67 - * Reasoning : https://lkml.org/lkml/2013/4/8/15 - * - ******************************************************************/ - -/* - * Save IRQ state and disable IRQs - */ -static inline long arch_local_irq_save(void) -{ - unsigned long temp, flags; - - __asm__ __volatile__( - " lr %1, [status32] \n" - " bic %0, %1, %2 \n" - " and.f 0, %1, %2 \n" - " flag.nz %0 \n" - : "=r"(temp), "=r"(flags) - : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) - : "memory", "cc"); - - return flags; -} - -/* - * restore saved IRQ state - */ -static inline void arch_local_irq_restore(unsigned long flags) -{ - - __asm__ __volatile__( - " flag %0 \n" - : - : "r"(flags) - : "memory"); -} - -/* - * Unconditionally Enable IRQs - */ -extern void arch_local_irq_enable(void); - -/* - * Unconditionally Disable IRQs - */ -static inline void arch_local_irq_disable(void) -{ - unsigned long temp; - - __asm__ __volatile__( - " lr %0, [status32] \n" - " and %0, %0, %1 \n" - " flag %0 \n" - : "=&r"(temp) - : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)) - : "memory"); -} - -/* - * save IRQ state - */ -static inline long arch_local_save_flags(void) -{ - unsigned long temp; - - __asm__ __volatile__( - " lr %0, [status32] \n" - : "=&r"(temp) - : - : "memory"); - - return temp; -} - -/* - * Query IRQ state - */ -static inline int arch_irqs_disabled_flags(unsigned long flags) -{ - return !(flags & (STATUS_E1_MASK -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS - | STATUS_E2_MASK -#endif - )); -} - -static inline int arch_irqs_disabled(void) -{ - return arch_irqs_disabled_flags(arch_local_save_flags()); -} - -#else - -#ifdef CONFIG_TRACE_IRQFLAGS - -.macro TRACE_ASM_IRQ_DISABLE - bl trace_hardirqs_off -.endm - -.macro TRACE_ASM_IRQ_ENABLE - bl trace_hardirqs_on -.endm - +#ifdef CONFIG_ISA_ARCOMPACT +#include <asm/irqflags-compact.h> #else - -.macro TRACE_ASM_IRQ_DISABLE -.endm - -.macro TRACE_ASM_IRQ_ENABLE -.endm - +#include <asm/irqflags-arcv2.h> #endif -.macro IRQ_DISABLE scratch - lr \scratch, [status32] - bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) - flag \scratch - TRACE_ASM_IRQ_DISABLE -.endm - -.macro IRQ_ENABLE scratch - lr \scratch, [status32] - or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) - flag \scratch - TRACE_ASM_IRQ_ENABLE -.endm - -#endif /* __ASSEMBLY__ */ - #endif diff --git a/kernel/arch/arc/include/asm/kmap_types.h b/kernel/arch/arc/include/asm/kmap_types.h new file mode 100644 index 000000000..f0d7f6ace --- /dev/null +++ b/kernel/arch/arc/include/asm/kmap_types.h @@ -0,0 +1,18 @@ +/* + * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef _ASM_KMAP_TYPES_H +#define _ASM_KMAP_TYPES_H + +/* + * We primarily need to define KM_TYPE_NR here but that in turn + * is a function of PGDIR_SIZE etc. + * To avoid circular deps issue, put everything in asm/highmem.h + */ +#endif diff --git a/kernel/arch/arc/include/asm/mach_desc.h b/kernel/arch/arc/include/asm/mach_desc.h index e8993a2be..c28e6c347 100644 --- a/kernel/arch/arc/include/asm/mach_desc.h +++ b/kernel/arch/arc/include/asm/mach_desc.h @@ -23,11 +23,8 @@ * @dt_compat: Array of device tree 'compatible' strings * (XXX: although only 1st entry is looked at) * @init_early: Very early callback [called from setup_arch()] - * @init_irq: setup external IRQ controllers [called from init_IRQ()] - * @init_smp: for each CPU (e.g. setup IPI) + * @init_per_cpu: for each CPU as it is coming up (SMP as well as UP) * [(M):init_IRQ(), (o):start_kernel_secondary()] - * @init_time: platform specific clocksource/clockevent registration - * [called from time_init()] * @init_machine: arch initcall level callback (e.g. populate static * platform devices or parse Devicetree) * @init_late: Late initcall level callback @@ -36,13 +33,10 @@ struct machine_desc { const char *name; const char **dt_compat; - void (*init_early)(void); - void (*init_irq)(void); #ifdef CONFIG_SMP - void (*init_smp)(unsigned int); + void (*init_per_cpu)(unsigned int); #endif - void (*init_time)(void); void (*init_machine)(void); void (*init_late)(void); diff --git a/kernel/arch/arc/include/asm/mcip.h b/kernel/arch/arc/include/asm/mcip.h new file mode 100644 index 000000000..46f4e5351 --- /dev/null +++ b/kernel/arch/arc/include/asm/mcip.h @@ -0,0 +1,91 @@ +/* + * ARConnect IP Support (Multi core enabler: Cross core IPI, RTC ...) + * + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_MCIP_H +#define __ASM_MCIP_H + +#ifdef CONFIG_ISA_ARCV2 + +#include <asm/arcregs.h> + +#define ARC_REG_MCIP_BCR 0x0d0 +#define ARC_REG_MCIP_CMD 0x600 +#define ARC_REG_MCIP_WDATA 0x601 +#define ARC_REG_MCIP_READBACK 0x602 + +struct mcip_cmd { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:8, param:16, cmd:8; +#else + unsigned int cmd:8, param:16, pad:8; +#endif + +#define CMD_INTRPT_GENERATE_IRQ 0x01 +#define CMD_INTRPT_GENERATE_ACK 0x02 +#define CMD_INTRPT_READ_STATUS 0x03 +#define CMD_INTRPT_CHECK_SOURCE 0x04 + +/* Semaphore Commands */ +#define CMD_SEMA_CLAIM_AND_READ 0x11 +#define CMD_SEMA_RELEASE 0x12 + +#define CMD_DEBUG_SET_MASK 0x34 +#define CMD_DEBUG_SET_SELECT 0x36 + +#define CMD_GRTC_READ_LO 0x42 +#define CMD_GRTC_READ_HI 0x43 + +#define CMD_IDU_ENABLE 0x71 +#define CMD_IDU_DISABLE 0x72 +#define CMD_IDU_SET_MODE 0x74 +#define CMD_IDU_SET_DEST 0x76 +#define CMD_IDU_SET_MASK 0x7C + +#define IDU_M_TRIG_LEVEL 0x0 +#define IDU_M_TRIG_EDGE 0x1 + +#define IDU_M_DISTRI_RR 0x0 +#define IDU_M_DISTRI_DEST 0x2 +}; + +/* + * MCIP programming model + * + * - Simple commands write {cmd:8,param:16} to MCIP_CMD aux reg + * (param could be irq, common_irq, core_id ...) + * - More involved commands setup MCIP_WDATA with cmd specific data + * before invoking the simple command + */ +static inline void __mcip_cmd(unsigned int cmd, unsigned int param) +{ + struct mcip_cmd buf; + + buf.pad = 0; + buf.cmd = cmd; + buf.param = param; + + WRITE_AUX(ARC_REG_MCIP_CMD, buf); +} + +/* + * Setup additional data for a cmd + * Callers need to lock to ensure atomicity + */ +static inline void __mcip_cmd_data(unsigned int cmd, unsigned int param, + unsigned int data) +{ + write_aux_reg(ARC_REG_MCIP_WDATA, data); + + __mcip_cmd(cmd, param); +} + +#endif + +#endif diff --git a/kernel/arch/arc/include/asm/mmu.h b/kernel/arch/arc/include/asm/mmu.h index 8c84ae98c..b144d7ca7 100644 --- a/kernel/arch/arc/include/asm/mmu.h +++ b/kernel/arch/arc/include/asm/mmu.h @@ -15,24 +15,43 @@ #define CONFIG_ARC_MMU_VER 2 #elif defined(CONFIG_ARC_MMU_V3) #define CONFIG_ARC_MMU_VER 3 +#elif defined(CONFIG_ARC_MMU_V4) +#define CONFIG_ARC_MMU_VER 4 #endif /* MMU Management regs */ #define ARC_REG_MMU_BCR 0x06f +#if (CONFIG_ARC_MMU_VER < 4) #define ARC_REG_TLBPD0 0x405 #define ARC_REG_TLBPD1 0x406 +#define ARC_REG_TLBPD1HI 0 /* Dummy: allows code sharing with ARC700 */ #define ARC_REG_TLBINDEX 0x407 #define ARC_REG_TLBCOMMAND 0x408 #define ARC_REG_PID 0x409 #define ARC_REG_SCRATCH_DATA0 0x418 +#else +#define ARC_REG_TLBPD0 0x460 +#define ARC_REG_TLBPD1 0x461 +#define ARC_REG_TLBPD1HI 0x463 +#define ARC_REG_TLBINDEX 0x464 +#define ARC_REG_TLBCOMMAND 0x465 +#define ARC_REG_PID 0x468 +#define ARC_REG_SCRATCH_DATA0 0x46c +#endif /* Bits in MMU PID register */ -#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ +#define __TLB_ENABLE (1 << 31) +#define __PROG_ENABLE (1 << 30) +#define MMU_ENABLE (__TLB_ENABLE | __PROG_ENABLE) /* Error code if probe fails */ #define TLB_LKUP_ERR 0x80000000 +#if (CONFIG_ARC_MMU_VER < 4) #define TLB_DUP_ERR (TLB_LKUP_ERR | 0x00000001) +#else +#define TLB_DUP_ERR (TLB_LKUP_ERR | 0x40000000) +#endif /* TLB Commands */ #define TLBWrite 0x1 @@ -45,6 +64,11 @@ #define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ #endif +#if (CONFIG_ARC_MMU_VER >= 4) +#define TLBInsertEntry 0x7 +#define TLBDeleteEntry 0x8 +#endif + #ifndef __ASSEMBLY__ typedef struct { @@ -61,6 +85,11 @@ void arc_mmu_init(void); extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len); void read_decode_mmu_bcr(void); +static inline int is_pae40_enabled(void) +{ + return IS_ENABLED(CONFIG_ARC_HAS_PAE40); +} + #endif /* !__ASSEMBLY__ */ #endif diff --git a/kernel/arch/arc/include/asm/page.h b/kernel/arch/arc/include/asm/page.h index 9c8aa41e4..429957f1c 100644 --- a/kernel/arch/arc/include/asm/page.h +++ b/kernel/arch/arc/include/asm/page.h @@ -43,7 +43,6 @@ typedef struct { typedef struct { unsigned long pgprot; } pgprot_t; -typedef unsigned long pgtable_t; #define pte_val(x) ((x).pte) #define pgd_val(x) ((x).pgd) @@ -57,20 +56,26 @@ typedef unsigned long pgtable_t; #else /* !STRICT_MM_TYPECHECKS */ +#ifdef CONFIG_ARC_HAS_PAE40 +typedef unsigned long long pte_t; +#else typedef unsigned long pte_t; +#endif typedef unsigned long pgd_t; typedef unsigned long pgprot_t; -typedef unsigned long pgtable_t; #define pte_val(x) (x) #define pgd_val(x) (x) #define pgprot_val(x) (x) #define __pte(x) (x) +#define __pgd(x) (x) #define __pgprot(x) (x) #define pte_pgprot(x) (x) #endif +typedef pte_t * pgtable_t; + #define ARCH_PFN_OFFSET (CONFIG_LINUX_LINK_BASE >> PAGE_SHIFT) #define pfn_valid(pfn) (((pfn) - ARCH_PFN_OFFSET) < max_mapnr) diff --git a/kernel/arch/arc/include/asm/perf_event.h b/kernel/arch/arc/include/asm/perf_event.h index 2b8880e95..5f071762f 100644 --- a/kernel/arch/arc/include/asm/perf_event.h +++ b/kernel/arch/arc/include/asm/perf_event.h @@ -1,6 +1,7 @@ /* * Linux performance counter support for ARC * + * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com) * * This program is free software; you can redistribute it and/or modify @@ -12,8 +13,8 @@ #ifndef __ASM_PERF_EVENT_H #define __ASM_PERF_EVENT_H -/* real maximum varies per CPU, this is the maximum supported by the driver */ -#define ARC_PMU_MAX_HWEVENTS 64 +/* Max number of counters that PCT block may ever have */ +#define ARC_PERF_MAX_COUNTERS 32 #define ARC_REG_CC_BUILD 0xF6 #define ARC_REG_CC_INDEX 0x240 @@ -28,15 +29,22 @@ #define ARC_REG_PCT_CONFIG 0x254 #define ARC_REG_PCT_CONTROL 0x255 #define ARC_REG_PCT_INDEX 0x256 +#define ARC_REG_PCT_INT_CNTL 0x25C +#define ARC_REG_PCT_INT_CNTH 0x25D +#define ARC_REG_PCT_INT_CTRL 0x25E +#define ARC_REG_PCT_INT_ACT 0x25F + +#define ARC_REG_PCT_CONFIG_USER (1 << 18) /* count in user mode */ +#define ARC_REG_PCT_CONFIG_KERN (1 << 19) /* count in kernel mode */ #define ARC_REG_PCT_CONTROL_CC (1 << 16) /* clear counts */ #define ARC_REG_PCT_CONTROL_SN (1 << 17) /* snapshot */ struct arc_reg_pct_build { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int m:8, c:8, r:6, s:2, v:8; + unsigned int m:8, c:8, r:5, i:1, s:2, v:8; #else - unsigned int v:8, s:2, r:6, c:8, m:8; + unsigned int v:8, s:2, i:1, r:5, c:8, m:8; #endif }; @@ -95,10 +103,13 @@ static const char * const arc_pmu_ev_hw_map[] = { /* counts condition */ [PERF_COUNT_HW_INSTRUCTIONS] = "iall", - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */ [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */ +#ifdef CONFIG_ISA_ARCV2 + [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp", +#else [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */ - +#endif [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */ [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */ diff --git a/kernel/arch/arc/include/asm/pgalloc.h b/kernel/arch/arc/include/asm/pgalloc.h index 81208bfd9..86ed67128 100644 --- a/kernel/arch/arc/include/asm/pgalloc.h +++ b/kernel/arch/arc/include/asm/pgalloc.h @@ -49,7 +49,7 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t ptep) static inline int __get_order_pgd(void) { - return get_order(PTRS_PER_PGD * 4); + return get_order(PTRS_PER_PGD * sizeof(pgd_t)); } static inline pgd_t *pgd_alloc(struct mm_struct *mm) @@ -87,7 +87,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline int __get_order_pte(void) { - return get_order(PTRS_PER_PTE * 4); + return get_order(PTRS_PER_PTE * sizeof(pte_t)); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, @@ -107,10 +107,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address) pgtable_t pte_pg; struct page *page; - pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); + pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); if (!pte_pg) return 0; - memzero((void *)pte_pg, PTRS_PER_PTE * 4); + memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t)); page = virt_to_page(pte_pg); if (!pgtable_page_ctor(page)) { __free_page(page); @@ -128,12 +128,12 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, pgtable_t ptep) { pgtable_page_dtor(virt_to_page(ptep)); - free_pages(ptep, __get_order_pte()); + free_pages((unsigned long)ptep, __get_order_pte()); } #define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte) #define check_pgt_cache() do { } while (0) -#define pmd_pgtable(pmd) pmd_page_vaddr(pmd) +#define pmd_pgtable(pmd) ((pgtable_t) pmd_page_vaddr(pmd)) #endif /* _ASM_ARC_PGALLOC_H */ diff --git a/kernel/arch/arc/include/asm/pgtable.h b/kernel/arch/arc/include/asm/pgtable.h index 9615fe170..57af2f05a 100644 --- a/kernel/arch/arc/include/asm/pgtable.h +++ b/kernel/arch/arc/include/asm/pgtable.h @@ -38,6 +38,7 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm-generic/pgtable-nopmd.h> +#include <linux/const.h> /************************************************************************** * Page Table Flags @@ -60,7 +61,8 @@ #define _PAGE_EXECUTE (1<<3) /* Page has user execute perm (H) */ #define _PAGE_WRITE (1<<4) /* Page has user write perm (H) */ #define _PAGE_READ (1<<5) /* Page has user read perm (H) */ -#define _PAGE_MODIFIED (1<<6) /* Page modified (dirty) (S) */ +#define _PAGE_DIRTY (1<<6) /* Page modified (dirty) (S) */ +#define _PAGE_SPECIAL (1<<7) #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<10) /* TLB entry is valid (H) */ @@ -71,32 +73,44 @@ #define _PAGE_WRITE (1<<2) /* Page has user write perm (H) */ #define _PAGE_READ (1<<3) /* Page has user read perm (H) */ #define _PAGE_ACCESSED (1<<4) /* Page is accessed (S) */ -#define _PAGE_MODIFIED (1<<5) /* Page modified (dirty) (S) */ +#define _PAGE_DIRTY (1<<5) /* Page modified (dirty) (S) */ +#define _PAGE_SPECIAL (1<<6) + +#if (CONFIG_ARC_MMU_VER >= 4) +#define _PAGE_WTHRU (1<<7) /* Page cache mode write-thru (H) */ +#endif + #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<9) /* TLB entry is valid (H) */ + +#if (CONFIG_ARC_MMU_VER >= 4) +#define _PAGE_HW_SZ (1<<10) /* Page Size indicator (H): 0 normal, 1 super */ +#endif + #define _PAGE_SHARED_CODE (1<<11) /* Shared Code page with cmn vaddr usable for shared TLB entries (H) */ + +#define _PAGE_UNUSED_BIT (1<<12) #endif /* vmalloc permissions */ #define _K_PAGE_PERMS (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \ _PAGE_GLOBAL | _PAGE_PRESENT) -#ifdef CONFIG_ARC_CACHE_PAGES -#define _PAGE_DEF_CACHEABLE _PAGE_CACHEABLE -#else -#define _PAGE_DEF_CACHEABLE (0) +#ifndef CONFIG_ARC_CACHE_PAGES +#undef _PAGE_CACHEABLE +#define _PAGE_CACHEABLE 0 #endif -/* Helper for every "user" page - * -kernel can R/W/X - * -by default cached, unless config otherwise - * -present in memory - */ -#define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE) +#ifndef _PAGE_HW_SZ +#define _PAGE_HW_SZ 0 +#endif + +/* Defaults for every user page */ +#define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE) /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED) +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) /* More Abbrevaited helpers */ #define PAGE_U_NONE __pgprot(___DEF) @@ -112,15 +126,20 @@ * user vaddr space - visible in all addr spaces, but kernel mode only * Thus Global, all-kernel-access, no-user-access, cached */ -#define PAGE_KERNEL __pgprot(_K_PAGE_PERMS | _PAGE_DEF_CACHEABLE) +#define PAGE_KERNEL __pgprot(_K_PAGE_PERMS | _PAGE_CACHEABLE) /* ioremap */ #define PAGE_KERNEL_NO_CACHE __pgprot(_K_PAGE_PERMS) /* Masks for actual TLB "PD"s */ -#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT) +#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ) #define PTE_BITS_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ) + +#ifdef CONFIG_ARC_HAS_PAE40 +#define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) +#else #define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) +#endif /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) @@ -181,26 +200,22 @@ /* Optimal Sizing of Pg Tbl - based on MMU page size */ #if defined(CONFIG_ARC_PAGE_SIZE_8K) -#define BITS_FOR_PTE 8 +#define BITS_FOR_PTE 8 /* 11:8:13 */ #elif defined(CONFIG_ARC_PAGE_SIZE_16K) -#define BITS_FOR_PTE 8 +#define BITS_FOR_PTE 8 /* 10:8:14 */ #elif defined(CONFIG_ARC_PAGE_SIZE_4K) -#define BITS_FOR_PTE 9 +#define BITS_FOR_PTE 9 /* 11:9:12 */ #endif #define BITS_FOR_PGD (32 - BITS_FOR_PTE - BITS_IN_PAGE) -#define PGDIR_SHIFT (BITS_FOR_PTE + BITS_IN_PAGE) +#define PGDIR_SHIFT (32 - BITS_FOR_PGD) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) /* vaddr span, not PDG sz */ #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#ifdef __ASSEMBLY__ -#define PTRS_PER_PTE (1 << BITS_FOR_PTE) -#define PTRS_PER_PGD (1 << BITS_FOR_PGD) -#else -#define PTRS_PER_PTE (1UL << BITS_FOR_PTE) -#define PTRS_PER_PGD (1UL << BITS_FOR_PGD) -#endif +#define PTRS_PER_PTE _BITUL(BITS_FOR_PTE) +#define PTRS_PER_PGD _BITUL(BITS_FOR_PGD) + /* * Number of entries a user land program use. * TASK_SIZE is the maximum vaddr that can be used by a userland program. @@ -260,15 +275,10 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) (unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \ PAGE_SHIFT))) -#define mk_pte(page, pgprot) \ -({ \ - pte_t pte; \ - pte_val(pte) = __pa(page_address(page)) + pgprot_val(pgprot); \ - pte; \ -}) - +#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) -#define pfn_pte(pfn, prot) (__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | \ + pgprot_val(prot))) #define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) /* @@ -285,23 +295,26 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) /* Zoo of pte_xxx function */ #define pte_read(pte) (pte_val(pte) & _PAGE_READ) #define pte_write(pte) (pte_val(pte) & _PAGE_WRITE) -#define pte_dirty(pte) (pte_val(pte) & _PAGE_MODIFIED) +#define pte_dirty(pte) (pte_val(pte) & _PAGE_DIRTY) #define pte_young(pte) (pte_val(pte) & _PAGE_ACCESSED) -#define pte_special(pte) (0) +#define pte_special(pte) (pte_val(pte) & _PAGE_SPECIAL) #define PTE_BIT_FUNC(fn, op) \ static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; } +PTE_BIT_FUNC(mknotpresent, &= ~(_PAGE_PRESENT)); PTE_BIT_FUNC(wrprotect, &= ~(_PAGE_WRITE)); PTE_BIT_FUNC(mkwrite, |= (_PAGE_WRITE)); -PTE_BIT_FUNC(mkclean, &= ~(_PAGE_MODIFIED)); -PTE_BIT_FUNC(mkdirty, |= (_PAGE_MODIFIED)); +PTE_BIT_FUNC(mkclean, &= ~(_PAGE_DIRTY)); +PTE_BIT_FUNC(mkdirty, |= (_PAGE_DIRTY)); PTE_BIT_FUNC(mkold, &= ~(_PAGE_ACCESSED)); PTE_BIT_FUNC(mkyoung, |= (_PAGE_ACCESSED)); PTE_BIT_FUNC(exprotect, &= ~(_PAGE_EXECUTE)); PTE_BIT_FUNC(mkexec, |= (_PAGE_EXECUTE)); +PTE_BIT_FUNC(mkspecial, |= (_PAGE_SPECIAL)); +PTE_BIT_FUNC(mkhuge, |= (_PAGE_HW_SZ)); -static inline pte_t pte_mkspecial(pte_t pte) { return pte; } +#define __HAVE_ARCH_PTE_SPECIAL static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { @@ -347,7 +360,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, #define pgd_offset_fast(mm, addr) pgd_offset(mm, addr) #endif -extern void paging_init(void); extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE); void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); @@ -373,6 +385,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, * remap a physical page `pfn' of size `size' with page protection `prot' * into virtual address `from' */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#include <asm/hugepage.h> +#endif + #include <asm-generic/pgtable.h> /* to cope with aliasing VIPT cache */ diff --git a/kernel/arch/arc/include/asm/processor.h b/kernel/arch/arc/include/asm/processor.h index 52312cb5d..1d694c1ef 100644 --- a/kernel/arch/arc/include/asm/processor.h +++ b/kernel/arch/arc/include/asm/processor.h @@ -57,11 +57,7 @@ struct task_struct; * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise * get optimised away by gcc */ -#ifdef CONFIG_SMP #define cpu_relax() __asm__ __volatile__ ("" : : : "memory") -#else -#define cpu_relax() do { } while (0) -#endif #define cpu_relax_lowlatency() cpu_relax() @@ -77,7 +73,7 @@ struct task_struct; */ #define TSK_K_ESP(tsk) (tsk->thread.ksp) -#define TSK_K_REG(tsk, off) (*((unsigned int *)(TSK_K_ESP(tsk) + \ +#define TSK_K_REG(tsk, off) (*((unsigned long *)(TSK_K_ESP(tsk) + \ sizeof(struct callee_regs) + off))) #define TSK_K_BLINK(tsk) TSK_K_REG(tsk, 4) @@ -100,29 +96,31 @@ extern unsigned int get_wchan(struct task_struct *p); #endif /* !__ASSEMBLY__ */ -/* Kernels Virtual memory area. - * Unlike other architectures(MIPS, sh, cris ) ARC 700 does not have a - * "kernel translated" region (like KSEG2 in MIPS). So we use a upper part - * of the translated bottom 2GB for kernel virtual memory and protect - * these pages from user accesses by disabling Ru, Eu and Wu. +/* + * System Memory Map on ARC + * + * ---------------------------- (lower 2G, Translated) ------------------------- + * 0x0000_0000 0x5FFF_FFFF (user vaddr: TASK_SIZE) + * 0x6000_0000 0x6FFF_FFFF (reserved gutter between U/K) + * 0x7000_0000 0x7FFF_FFFF (kvaddr: vmalloc/modules/pkmap..) + * + * PAGE_OFFSET ---------------- (Upper 2G, Untranslated) ----------------------- + * 0x8000_0000 0xBFFF_FFFF (kernel direct mapped) + * 0xC000_0000 0xFFFF_FFFF (peripheral uncached space) + * ----------------------------------------------------------------------------- */ -#define VMALLOC_SIZE (0x10000000) /* 256M */ -#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) -#define VMALLOC_END (PAGE_OFFSET) +#define VMALLOC_START 0x70000000 -/* Most of the architectures seem to be keeping some kind of padding between - * userspace TASK_SIZE and PAGE_OFFSET. i.e TASK_SIZE != PAGE_OFFSET. +/* + * 1 PGDIR_SIZE each for fixmap/pkmap, 2 PGDIR_SIZE gutter + * See asm/highmem.h for details */ +#define VMALLOC_SIZE (PAGE_OFFSET - VMALLOC_START - PGDIR_SIZE * 4) +#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE) + #define USER_KERNEL_GUTTER 0x10000000 -/* User address space: - * On ARC700, CPU allows the entire lower half of 32 bit address space to be - * translated. Thus potentially 2G (0:0x7FFF_FFFF) could be User vaddr space. - * However we steal 256M for kernel addr (0x7000_0000:0x7FFF_FFFF) and another - * 256M (0x6000_0000:0x6FFF_FFFF) is gutter between user/kernel spaces - * Thus total User vaddr space is (0:0x5FFF_FFFF) - */ -#define TASK_SIZE (PAGE_OFFSET - VMALLOC_SIZE - USER_KERNEL_GUTTER) +#define TASK_SIZE (VMALLOC_START - USER_KERNEL_GUTTER) #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP diff --git a/kernel/arch/arc/include/asm/ptrace.h b/kernel/arch/arc/include/asm/ptrace.h index 2a58af7a2..69095da1f 100644 --- a/kernel/arch/arc/include/asm/ptrace.h +++ b/kernel/arch/arc/include/asm/ptrace.h @@ -16,23 +16,24 @@ /* THE pt_regs: Defines how regs are saved during entry into kernel */ +#ifdef CONFIG_ISA_ARCOMPACT struct pt_regs { /* Real registers */ - long bta; /* bta_l1, bta_l2, erbta */ + unsigned long bta; /* bta_l1, bta_l2, erbta */ - long lp_start, lp_end, lp_count; + unsigned long lp_start, lp_end, lp_count; - long status32; /* status32_l1, status32_l2, erstatus */ - long ret; /* ilink1, ilink2 or eret */ - long blink; - long fp; - long r26; /* gp */ + unsigned long status32; /* status32_l1, status32_l2, erstatus */ + unsigned long ret; /* ilink1, ilink2 or eret */ + unsigned long blink; + unsigned long fp; + unsigned long r26; /* gp */ - long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; + unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; - long sp; /* user/kernel sp depending on where we came from */ - long orig_r0; + unsigned long sp; /* User/Kernel depending on where we came from */ + unsigned long orig_r0; /* * To distinguish bet excp, syscall, irq @@ -54,16 +55,58 @@ struct pt_regs { unsigned long event; }; - long user_r25; + unsigned long user_r25; }; +#else + +struct pt_regs { + + unsigned long orig_r0; + + union { + struct { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned long state:8, ecr_vec:8, + ecr_cause:8, ecr_param:8; +#else + unsigned long ecr_param:8, ecr_cause:8, + ecr_vec:8, state:8; +#endif + }; + unsigned long event; + }; + + unsigned long bta; /* bta_l1, bta_l2, erbta */ + + unsigned long user_r25; + + unsigned long r26; /* gp */ + unsigned long fp; + unsigned long sp; /* user/kernel sp depending on where we came from */ + + unsigned long r12; + + /*------- Below list auto saved by h/w -----------*/ + unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11; + + unsigned long blink; + unsigned long lp_end, lp_start, lp_count; + + unsigned long ei, ldi, jli; + + unsigned long ret; + unsigned long status32; +}; + +#endif /* Callee saved registers - need to be saved only when you are scheduled out */ struct callee_regs { - long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; + unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; -#define instruction_pointer(regs) (unsigned long)((regs)->ret) +#define instruction_pointer(regs) ((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) /* return 1 if user mode or 0 if kernel mode */ @@ -99,7 +142,7 @@ struct callee_regs { static inline long regs_return_value(struct pt_regs *regs) { - return regs->r0; + return (long)regs->r0; } #endif /* !__ASSEMBLY__ */ diff --git a/kernel/arch/arc/include/asm/setup.h b/kernel/arch/arc/include/asm/setup.h index 6e3ef5ba4..307846691 100644 --- a/kernel/arch/arc/include/asm/setup.h +++ b/kernel/arch/arc/include/asm/setup.h @@ -33,4 +33,11 @@ extern int root_mountflags, end_mem; void setup_processor(void); void __init setup_arch_memory(void); +/* Helpers used in arc_*_mumbojumbo routines */ +#define IS_AVAIL1(v, s) ((v) ? s : "") +#define IS_DISABLED_RUN(v) ((v) ? "" : "(disabled) ") +#define IS_USED_RUN(v) ((v) ? "" : "(not used) ") +#define IS_USED_CFG(cfg) IS_USED_RUN(IS_ENABLED(cfg)) +#define IS_AVAIL2(v, s, cfg) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg)) + #endif /* __ASMARC_SETUP_H */ diff --git a/kernel/arch/arc/include/asm/smp.h b/kernel/arch/arc/include/asm/smp.h index 3845b9e94..991380438 100644 --- a/kernel/arch/arc/include/asm/smp.h +++ b/kernel/arch/arc/include/asm/smp.h @@ -45,12 +45,19 @@ extern int smp_ipi_irq_setup(int cpu, int irq); * struct plat_smp_ops - SMP callbacks provided by platform to ARC SMP * * @info: SoC SMP specific info for /proc/cpuinfo etc + * @init_early_smp: A SMP specific h/w block can init itself + * Could be common across platforms so not covered by + * mach_desc->init_early() + * @init_per_cpu: Called for each core so SMP h/w block driver can do + * any needed setup per cpu (e.g. IPI request) * @cpu_kick: For Master to kickstart a cpu (optionally at a PC) * @ipi_send: To send IPI to a @cpu * @ips_clear: To clear IPI received at @irq */ struct plat_smp_ops { const char *info; + void (*init_early_smp)(void); + void (*init_per_cpu)(int cpu); void (*cpu_kick)(int cpu, unsigned long pc); void (*ipi_send)(int cpu); void (*ipi_clear)(int irq); diff --git a/kernel/arch/arc/include/asm/spinlock.h b/kernel/arch/arc/include/asm/spinlock.h index e1651df6a..db8c59d1e 100644 --- a/kernel/arch/arc/include/asm/spinlock.h +++ b/kernel/arch/arc/include/asm/spinlock.h @@ -18,9 +18,518 @@ #define arch_spin_unlock_wait(x) \ do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) +#ifdef CONFIG_ARC_HAS_LLSC + +/* + * A normal LLOCK/SCOND based system, w/o need for livelock workaround + */ +#ifndef CONFIG_ARC_STAR_9000923308 + static inline void arch_spin_lock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__; + unsigned int val; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 1b \n" /* spin while LOCKED */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bnz 1b \n" + " mov %[got_it], 1 \n" + "4: \n" + " \n" + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + smp_mb(); + + lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + + smp_mb(); +} + +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) + */ + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * zero means writer holds the lock exclusively, deny Reader. + * Otherwise grant lock to first/subseq reader + * + * if (rw->counter > 0) { + * rw->counter--; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 1b\n" /* <= 0: spin while write locked */ + " sub %[val], %[val], 1 \n" /* reader lock */ + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ + " sub %[val], %[val], 1 \n" /* counter-- */ + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" /* retry if collided with someone */ + " mov %[got_it], 1 \n" + " \n" + "4: ; --- done --- \n" + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), + * deny writer. Otherwise if unlocked grant to writer + * Hence the claim that Linux rwlocks are unfair to writers. + * (can be starved for an indefinite time by readers). + * + * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { + * rw->counter = 0; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 1b \n" /* while !UNLOCKED spin */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" /* retry if collided with someone */ + " mov %[got_it], 1 \n" + " \n" + "4: ; --- done --- \n" + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter++; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " add %[val], %[val], 1 \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)) + : "memory", "cc"); + + smp_mb(); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + smp_mb(); + + rw->counter = __ARCH_RW_LOCK_UNLOCKED__; + + smp_mb(); +} + +#else /* CONFIG_ARC_STAR_9000923308 */ + +/* + * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping + * coherency transactions in the SCU. The exclusive line state keeps rotating + * among contenting cores leading to a never ending cycle. So break the cycle + * by deferring the retry of failed exclusive access (SCOND). The actual delay + * needed is function of number of contending cores as well as the unrelated + * coherency traffic from other cores. To keep the code simple, start off with + * small delay of 1 which would suffice most cases and in case of contention + * double the delay. Eventually the delay is sufficient such that the coherency + * pipeline is drained, thus a subsequent exclusive access would succeed. + */ + +#define SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int delay, tmp; \ + +#define SCOND_FAIL_RETRY_ASM \ + " ; --- scond fail delay --- \n" \ + " mov %[tmp], %[delay] \n" /* tmp = delay */ \ + "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ + " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ + " rol %[delay], %[delay] \n" /* delay *= 2 */ \ + " b 1b \n" /* start over */ \ + " \n" \ + "4: ; --- done --- \n" \ + +#define SCOND_FAIL_RETRY_VARS \ + ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \ + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bz 4f \n" /* done */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + smp_mb(); + + lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + + smp_mb(); +} + +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) + */ + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + /* + * zero means writer holds the lock exclusively, deny Reader. + * Otherwise grant lock to first/subseq reader + * + * if (rw->counter > 0) { + * rw->counter--; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */ + " sub %[val], %[val], 1 \n" /* reader lock */ + " scond %[val], [%[rwlock]] \n" + " bz 4f \n" /* done */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ + " sub %[val], %[val], 1 \n" /* counter-- */ + " scond %[val], [%[rwlock]] \n" + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + /* + * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), + * deny writer. Otherwise if unlocked grant to writer + * Hence the claim that Linux rwlocks are unfair to writers. + * (can be starved for an indefinite time by readers). + * + * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { + * rw->counter = 0; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bz 4f \n" + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter++; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " add %[val], %[val], 1 \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)) + : "memory", "cc"); + + smp_mb(); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter = __ARCH_RW_LOCK_UNLOCKED__; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " scond %[UNLOCKED], [%[rwlock]]\n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +#undef SCOND_FAIL_RETRY_VAR_DEF +#undef SCOND_FAIL_RETRY_ASM +#undef SCOND_FAIL_RETRY_VARS + +#endif /* CONFIG_ARC_STAR_9000923308 */ + +#else /* !CONFIG_ARC_HAS_LLSC */ + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + unsigned int val = __ARCH_SPIN_LOCK_LOCKED__; /* * This smp_mb() is technically superfluous, we only need the one @@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __asm__ __volatile__( "1: ex %0, [%1] \n" " breq %0, %2, 1b \n" - : "+&r" (tmp) + : "+&r" (val) : "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__) : "memory"); @@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) smp_mb(); } +/* 1 - lock taken successfully */ static inline int arch_spin_trylock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__; + unsigned int val = __ARCH_SPIN_LOCK_LOCKED__; smp_mb(); __asm__ __volatile__( "1: ex %0, [%1] \n" - : "+r" (tmp) + : "+r" (val) : "r"(&(lock->slock)) : "memory"); smp_mb(); - return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__); + return (val == __ARCH_SPIN_LOCK_UNLOCKED__); } static inline void arch_spin_unlock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__; + unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__; /* * RELEASE barrier: given the instructions avail on ARCv2, full barrier @@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) __asm__ __volatile__( " ex %0, [%1] \n" - : "+r" (tmp) + : "+r" (val) : "r"(&(lock->slock)) : "memory"); @@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) /* * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) * * The spinlock itself is contained in @counter and access to it is * serialized with @lock_mutex. - * - * Unfair locking as Writers could be starved indefinitely by Reader(s) */ -/* Would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->counter > 0) - -/* Would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__) - /* 1 - lock taken successfully */ static inline int arch_read_trylock(arch_rwlock_t *rw) { @@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) arch_spin_unlock(&(rw->lock_mutex)); } +#endif + +#define arch_read_can_lock(x) ((x)->counter > 0) +#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__) + #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/kernel/arch/arc/include/asm/spinlock_types.h b/kernel/arch/arc/include/asm/spinlock_types.h index 662627ced..4e1ef5f65 100644 --- a/kernel/arch/arc/include/asm/spinlock_types.h +++ b/kernel/arch/arc/include/asm/spinlock_types.h @@ -26,7 +26,9 @@ typedef struct { */ typedef struct { volatile unsigned int counter; +#ifndef CONFIG_ARC_HAS_LLSC arch_spinlock_t lock_mutex; +#endif } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000 diff --git a/kernel/arch/arc/include/asm/thread_info.h b/kernel/arch/arc/include/asm/thread_info.h index aca0d5a45..3af674556 100644 --- a/kernel/arch/arc/include/asm/thread_info.h +++ b/kernel/arch/arc/include/asm/thread_info.h @@ -25,6 +25,7 @@ #endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define THREAD_SHIFT (PAGE_SHIFT << THREAD_SIZE_ORDER) #ifndef __ASSEMBLY__ diff --git a/kernel/arch/arc/include/asm/tlbflush.h b/kernel/arch/arc/include/asm/tlbflush.h index 71c7b2e4b..1fe9c8c80 100644 --- a/kernel/arch/arc/include/asm/tlbflush.h +++ b/kernel/arch/arc/include/asm/tlbflush.h @@ -17,6 +17,8 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page); void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); #ifndef CONFIG_SMP #define flush_tlb_range(vma, s, e) local_flush_tlb_range(vma, s, e) @@ -24,6 +26,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, #define flush_tlb_kernel_range(s, e) local_flush_tlb_kernel_range(s, e) #define flush_tlb_all() local_flush_tlb_all() #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) +#define flush_pmd_tlb_range(vma, s, e) local_flush_pmd_tlb_range(vma, s, e) #else extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -31,5 +34,7 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); extern void flush_tlb_all(void); extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); + #endif /* CONFIG_SMP */ #endif diff --git a/kernel/arch/arc/include/asm/uaccess.h b/kernel/arch/arc/include/asm/uaccess.h index 30c9baffa..d1da6032b 100644 --- a/kernel/arch/arc/include/asm/uaccess.h +++ b/kernel/arch/arc/include/asm/uaccess.h @@ -659,31 +659,30 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n) static inline long __arc_strncpy_from_user(char *dst, const char __user *src, long count) { - long res = count; + long res = 0; char val; - unsigned int hw_count; if (count == 0) return 0; __asm__ __volatile__( - " lp 2f \n" + " lp 3f \n" "1: ldb.ab %3, [%2, 1] \n" - " breq.d %3, 0, 2f \n" + " breq.d %3, 0, 3f \n" " stb.ab %3, [%1, 1] \n" - "2: sub %0, %6, %4 \n" - "3: ;nop \n" + " add %0, %0, 1 # Num of NON NULL bytes copied \n" + "3: \n" " .section .fixup, \"ax\" \n" " .align 4 \n" - "4: mov %0, %5 \n" + "4: mov %0, %4 # sets @res as -EFAULT \n" " j 3b \n" " .previous \n" " .section __ex_table, \"a\" \n" " .align 4 \n" " .word 1b, 4b \n" " .previous \n" - : "=r"(res), "+r"(dst), "+r"(src), "=&r"(val), "=l"(hw_count) - : "g"(-EFAULT), "ir"(count), "4"(count) /* this "4" seeds lp_count */ + : "+r"(res), "+r"(dst), "+r"(src), "=r"(val) + : "g"(-EFAULT), "l"(count) : "memory"); return res; diff --git a/kernel/arch/arc/include/asm/unwind.h b/kernel/arch/arc/include/asm/unwind.h index 7ca628b6e..c11a25bb8 100644 --- a/kernel/arch/arc/include/asm/unwind.h +++ b/kernel/arch/arc/include/asm/unwind.h @@ -112,7 +112,6 @@ struct unwind_frame_info { extern int arc_unwind(struct unwind_frame_info *frame); extern void arc_unwind_init(void); -extern void arc_unwind_setup(void); extern void *unwind_add_table(struct module *module, const void *table_start, unsigned long table_size); extern void unwind_remove_table(void *handle, int init_only); @@ -152,9 +151,6 @@ static inline void arc_unwind_init(void) { } -static inline void arc_unwind_setup(void) -{ -} #define unwind_add_table(a, b, c) #define unwind_remove_table(a, b) diff --git a/kernel/arch/arc/include/uapi/asm/page.h b/kernel/arch/arc/include/uapi/asm/page.h index e5d41e082..059aff38f 100644 --- a/kernel/arch/arc/include/uapi/asm/page.h +++ b/kernel/arch/arc/include/uapi/asm/page.h @@ -9,6 +9,8 @@ #ifndef _UAPI__ASM_ARC_PAGE_H #define _UAPI__ASM_ARC_PAGE_H +#include <linux/const.h> + /* PAGE_SHIFT determines the page size */ #if defined(CONFIG_ARC_PAGE_SIZE_16K) #define PAGE_SHIFT 14 @@ -25,13 +27,8 @@ #define PAGE_SHIFT 13 #endif -#ifdef __ASSEMBLY__ -#define PAGE_SIZE (1 << PAGE_SHIFT) -#define PAGE_OFFSET (0x80000000) -#else -#define PAGE_SIZE (1UL << PAGE_SHIFT) /* Default 8K */ -#define PAGE_OFFSET (0x80000000UL) /* Kernel starts at 2G onwards */ -#endif +#define PAGE_SIZE _BITUL(PAGE_SHIFT) /* Default 8K */ +#define PAGE_OFFSET _AC(0x80000000, UL) /* Kernel starts at 2G onwrds */ #define PAGE_MASK (~(PAGE_SIZE-1)) diff --git a/kernel/arch/arc/include/uapi/asm/ptrace.h b/kernel/arch/arc/include/uapi/asm/ptrace.h index 76a7739aa..0b3ef63d4 100644 --- a/kernel/arch/arc/include/uapi/asm/ptrace.h +++ b/kernel/arch/arc/include/uapi/asm/ptrace.h @@ -32,20 +32,20 @@ */ struct user_regs_struct { - long pad; + unsigned long pad; struct { - long bta, lp_start, lp_end, lp_count; - long status32, ret, blink, fp, gp; - long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; - long sp; + unsigned long bta, lp_start, lp_end, lp_count; + unsigned long status32, ret, blink, fp, gp; + unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; + unsigned long sp; } scratch; - long pad2; + unsigned long pad2; struct { - long r25, r24, r23, r22, r21, r20; - long r19, r18, r17, r16, r15, r14, r13; + unsigned long r25, r24, r23, r22, r21, r20; + unsigned long r19, r18, r17, r16, r15, r14, r13; } callee; - long efa; /* break pt addr, for break points in delay slots */ - long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ + unsigned long efa; /* break pt addr, for break points in delay slots */ + unsigned long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ }; #endif /* !__ASSEMBLY__ */ diff --git a/kernel/arch/arc/kernel/Makefile b/kernel/arch/arc/kernel/Makefile index 113f2033d..e7f3625a1 100644 --- a/kernel/arch/arc/kernel/Makefile +++ b/kernel/arch/arc/kernel/Makefile @@ -8,12 +8,14 @@ # Pass UTS_MACHINE for user_regset definition CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' -obj-y := arcksyms.o setup.o irq.o time.o reset.o ptrace.o entry.o process.o +obj-y := arcksyms.o setup.o irq.o time.o reset.o ptrace.o process.o devtree.o obj-y += signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o clk.o -obj-y += devtree.o +obj-$(CONFIG_ISA_ARCOMPACT) += entry-compact.o intc-compact.o +obj-$(CONFIG_ISA_ARCV2) += entry-arcv2.o intc-arcv2.o obj-$(CONFIG_MODULES) += arcksyms.o module.o obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_ARC_MCIP) += mcip.o obj-$(CONFIG_ARC_DW2_UNWIND) += unwind.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_ARC_EMUL_UNALIGNED) += unaligned.o diff --git a/kernel/arch/arc/kernel/asm-offsets.c b/kernel/arch/arc/kernel/asm-offsets.c index 6c3aa0edb..ecaf34e92 100644 --- a/kernel/arch/arc/kernel/asm-offsets.c +++ b/kernel/arch/arc/kernel/asm-offsets.c @@ -37,6 +37,8 @@ int main(void) DEFINE(TASK_ACT_MM, offsetof(struct task_struct, active_mm)); DEFINE(TASK_TGID, offsetof(struct task_struct, tgid)); + DEFINE(TASK_PID, offsetof(struct task_struct, pid)); + DEFINE(TASK_COMM, offsetof(struct task_struct, comm)); DEFINE(MM_CTXT, offsetof(struct mm_struct, context)); DEFINE(MM_PGD, offsetof(struct mm_struct, pgd)); @@ -56,8 +58,11 @@ int main(void) DEFINE(PT_r5, offsetof(struct pt_regs, r5)); DEFINE(PT_r6, offsetof(struct pt_regs, r6)); DEFINE(PT_r7, offsetof(struct pt_regs, r7)); + DEFINE(PT_ret, offsetof(struct pt_regs, ret)); DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs)); DEFINE(SZ_PT_REGS, sizeof(struct pt_regs)); + DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25)); + return 0; } diff --git a/kernel/arch/arc/kernel/ctx_sw.c b/kernel/arch/arc/kernel/ctx_sw.c index c14a5bea0..5d446df2c 100644 --- a/kernel/arch/arc/kernel/ctx_sw.c +++ b/kernel/arch/arc/kernel/ctx_sw.c @@ -58,8 +58,6 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) "st sp, [r24] \n\t" #endif - "sync \n\t" - /* * setup _current_task with incoming tsk. * optionally, set r25 to that as well diff --git a/kernel/arch/arc/kernel/ctx_sw_asm.S b/kernel/arch/arc/kernel/ctx_sw_asm.S index e24859409..e6890b1f8 100644 --- a/kernel/arch/arc/kernel/ctx_sw_asm.S +++ b/kernel/arch/arc/kernel/ctx_sw_asm.S @@ -44,9 +44,6 @@ __switch_to: * don't need to do anything special to return it */ - /* hardware memory barrier */ - sync - /* * switch to new task, contained in r1 * Temp reg r3 is required to get the ptr to store val diff --git a/kernel/arch/arc/kernel/devtree.c b/kernel/arch/arc/kernel/devtree.c index e32b54abf..7e844fd82 100644 --- a/kernel/arch/arc/kernel/devtree.c +++ b/kernel/arch/arc/kernel/devtree.c @@ -32,6 +32,8 @@ static void __init arc_set_early_base_baud(unsigned long dt_root) if (of_flat_dt_is_compatible(dt_root, "abilis,arc-tb10x")) arc_base_baud = core_clk/3; + else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp")) + arc_base_baud = 33333333; /* Fixed 33MHz clk (AXS10x) */ else arc_base_baud = core_clk; } diff --git a/kernel/arch/arc/kernel/entry-arcv2.S b/kernel/arch/arc/kernel/entry-arcv2.S new file mode 100644 index 000000000..c1264607b --- /dev/null +++ b/kernel/arch/arc/kernel/entry-arcv2.S @@ -0,0 +1,271 @@ +/* + * ARCv2 ISA based core Low Level Intr/Traps/Exceptions(non-TLB) Handling + * + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ +#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */ +#include <asm/errno.h> +#include <asm/arcregs.h> +#include <asm/irqflags.h> + + .cpu HS + +#define VECTOR .word + +;############################ Vector Table ################################# + + .section .vector,"a",@progbits + .align 4 + +# Initial 16 slots are Exception Vectors +VECTOR res_service ; Reset Vector +VECTOR mem_service ; Mem exception +VECTOR instr_service ; Instrn Error +VECTOR EV_MachineCheck ; Fatal Machine check +VECTOR EV_TLBMissI ; Intruction TLB miss +VECTOR EV_TLBMissD ; Data TLB miss +VECTOR EV_TLBProtV ; Protection Violation +VECTOR EV_PrivilegeV ; Privilege Violation +VECTOR EV_SWI ; Software Breakpoint +VECTOR EV_Trap ; Trap exception +VECTOR EV_Extension ; Extn Instruction Exception +VECTOR EV_DivZero ; Divide by Zero +VECTOR EV_DCError ; Data Cache Error +VECTOR EV_Misaligned ; Misaligned Data Access +VECTOR reserved ; Reserved slots +VECTOR reserved ; Reserved slots + +# Begin Interrupt Vectors +VECTOR handle_interrupt ; (16) Timer0 +VECTOR handle_interrupt ; unused (Timer1) +VECTOR handle_interrupt ; unused (WDT) +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs + +.rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 + VECTOR handle_interrupt +.endr + + .section .text, "ax",@progbits + +reserved: + flag 1 ; Unexpected event, halt + +;##################### Interrupt Handling ############################## + +ENTRY(handle_interrupt) + + INTERRUPT_PROLOGUE irq + + clri ; To make status32.IE agree with CPU internal state + + lr r0, [ICAUSE] + + mov blink, ret_from_exception + + b.d arch_do_IRQ + mov r1, sp + +END(handle_interrupt) + +;################### Non TLB Exception Handling ############################# + +ENTRY(EV_SWI) + flag 1 +END(EV_SWI) + +ENTRY(EV_DivZero) + flag 1 +END(EV_DivZero) + +ENTRY(EV_DCError) + flag 1 +END(EV_DCError) + +; --------------------------------------------- +; Memory Error Exception Handler +; - Unlike ARCompact, handles Bus errors for both User/Kernel mode, +; Instruction fetch or Data access, under a single Exception Vector +; --------------------------------------------- + +ENTRY(mem_service) + + EXCEPTION_PROLOGUE + + lr r0, [efa] + mov r1, sp + + FAKE_RET_FROM_EXCPN + + bl do_memory_error + b ret_from_exception +END(mem_service) + +ENTRY(EV_Misaligned) + + EXCEPTION_PROLOGUE + + lr r0, [efa] ; Faulting Data address + mov r1, sp + + FAKE_RET_FROM_EXCPN + + SAVE_CALLEE_SAVED_USER + mov r2, sp ; callee_regs + + bl do_misaligned_access + + ; TBD: optimize - do this only if a callee reg was involved + ; either a dst of emulated LD/ST or src with address-writeback + RESTORE_CALLEE_SAVED_USER + + b ret_from_exception +END(EV_Misaligned) + +; --------------------------------------------- +; Protection Violation Exception Handler +; --------------------------------------------- + +ENTRY(EV_TLBProtV) + + EXCEPTION_PROLOGUE + + lr r0, [efa] ; Faulting Data address + mov r1, sp ; pt_regs + + FAKE_RET_FROM_EXCPN + + mov blink, ret_from_exception + b do_page_fault + +END(EV_TLBProtV) + +; From Linux standpoint Slow Path I/D TLB Miss is same a ProtV as they +; need to call do_page_fault(). +; ECR in pt_regs provides whether access was R/W/X + +.global call_do_page_fault +.set call_do_page_fault, EV_TLBProtV + +;############# Common Handlers for ARCompact and ARCv2 ############## + +#include "entry.S" + +;############# Return from Intr/Excp/Trap (ARCv2 ISA Specifics) ############## +; +; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap) +; IRQ shd definitely not happen between now and rtie +; All 2 entry points to here already disable interrupts + +.Lrestore_regs: + + ld r0, [sp, PT_status32] ; U/K mode at time of entry + lr r10, [AUX_IRQ_ACT] + + bmsk r11, r10, 15 ; AUX_IRQ_ACT.ACTIVE + breq r11, 0, .Lexcept_ret ; No intr active, ret from Exception + +;####### Return from Intr ####### + +debug_marker_l1: + bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot + +.Lisr_ret_fast_path: + ; Handle special case #1: (Entry via Exception, Return via IRQ) + ; + ; Exception in U mode, preempted in kernel, Intr taken (K mode), orig + ; task now returning to U mode (riding the Intr) + ; AUX_IRQ_ACTIVE won't have U bit set (since intr in K mode), hence SP + ; won't be switched to correct U mode value (from AUX_SP) + ; So force AUX_IRQ_ACT.U for such a case + + btst r0, STATUS_U_BIT ; Z flag set if K (Z clear for U) + bset.nz r11, r11, AUX_IRQ_ACT_BIT_U ; NZ means U + sr r11, [AUX_IRQ_ACT] + + INTERRUPT_EPILOGUE irq + rtie + +;####### Return from Exception / pure kernel mode ####### + +.Lexcept_ret: ; Expects r0 has PT_status32 + +debug_marker_syscall: + EXCEPTION_EPILOGUE + rtie + +;####### Return from Intr to insn in delay slot ####### + +; Handle special case #2: (Entry via Exception in Delay Slot, Return via IRQ) +; +; Intr returning to a Delay Slot (DS) insn +; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig +; entry was via Exception in DS which got preempted in kernel). +; +; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround +; +; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline +; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly + +.Lintr_ret_to_delay_slot: +debug_marker_ds: + + ld r2, [@intr_to_DE_cnt] + add r2, r2, 1 + st r2, [@intr_to_DE_cnt] + + ld r2, [sp, PT_ret] + ld r3, [sp, PT_status32] + + ; STAT32 for Int return created from scratch + ; (No delay dlot, disable Further intr in trampoline) + + bic r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK + st r0, [sp, PT_status32] + + mov r1, .Lintr_ret_to_delay_slot_2 + st r1, [sp, PT_ret] + + ; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots + st r2, [sp, 0] + st r3, [sp, 4] + + b .Lisr_ret_fast_path + +.Lintr_ret_to_delay_slot_2: + ; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP + sub sp, sp, SZ_PT_REGS + st r9, [sp, -4] + + ld r9, [sp, 0] + sr r9, [eret] + + ld r9, [sp, 4] + sr r9, [erstatus] + + ; restore AUX_USER_SP if returning to U mode + bbit0 r9, STATUS_U_BIT, 1f + ld r9, [sp, PT_sp] + sr r9, [AUX_USER_SP] + +1: + ld r9, [sp, 8] + sr r9, [erbta] + + ld r9, [sp, -4] + add sp, sp, SZ_PT_REGS + + ; return from pure kernel mode to delay slot + rtie + +END(ret_from_exception) diff --git a/kernel/arch/arc/kernel/entry-compact.S b/kernel/arch/arc/kernel/entry-compact.S new file mode 100644 index 000000000..431433929 --- /dev/null +++ b/kernel/arch/arc/kernel/entry-compact.S @@ -0,0 +1,417 @@ +/* + * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARCompact ISA + * + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * 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. + * + * vineetg: May 2011 + * -Userspace unaligned access emulation + * + * vineetg: Feb 2011 (ptrace low level code fixes) + * -traced syscall return code (r0) was not saved into pt_regs for restoring + * into user reg-file when traded task rets to user space. + * -syscalls needing arch-wrappers (mainly for passing sp as pt_regs) + * were not invoking post-syscall trace hook (jumping directly into + * ret_from_system_call) + * + * vineetg: Nov 2010: + * -Vector table jumps (@8 bytes) converted into branches (@4 bytes) + * -To maintain the slot size of 8 bytes/vector, added nop, which is + * not executed at runtime. + * + * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK) + * -do_signal()invoked upon TIF_RESTORE_SIGMASK as well + * -Wrappers for sys_{,rt_}sigsuspend() nolonger needed as they don't + * need ptregs anymore + * + * Vineetg: Oct 2009 + * -In a rare scenario, Process gets a Priv-V exception and gets scheduled + * out. Since we don't do FAKE RTIE for Priv-V, CPU excpetion state remains + * active (AE bit enabled). This causes a double fault for a subseq valid + * exception. Thus FAKE RTIE needed in low level Priv-Violation handler. + * Instr Error could also cause similar scenario, so same there as well. + * + * Vineetg: March 2009 (Supporting 2 levels of Interrupts) + * + * Vineetg: Aug 28th 2008: Bug #94984 + * -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap + * Normally CPU does this automatically, however when doing FAKE rtie, + * we need to explicitly do this. The problem in macros + * FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit + * was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit, + * setting it and not clearing it clears ZOL context + * + * Vineetg: May 16th, 2008 + * - r25 now contains the Current Task when in kernel + * + * Vineetg: Dec 22, 2007 + * Minor Surgery of Low Level ISR to make it SMP safe + * - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR + * - _current_task is made an array of NR_CPUS + * - Access of _current_task wrapped inside a macro so that if hardware + * team agrees for a dedicated reg, no other code is touched + * + * Amit Bhor, Rahul Trivedi, Kanika Nema, Sameer Dhavale : Codito Tech 2004 + */ + +#include <linux/errno.h> +#include <linux/linkage.h> /* {EXTRY,EXIT} */ +#include <asm/entry.h> +#include <asm/irqflags.h> + + .cpu A7 + +;############################ Vector Table ################################# + +.macro VECTOR lbl +#if 1 /* Just in case, build breaks */ + j \lbl +#else + b \lbl + nop +#endif +.endm + + .section .vector, "ax",@progbits + .align 4 + +/* Each entry in the vector table must occupy 2 words. Since it is a jump + * across sections (.vector to .text) we are gauranteed that 'j somewhere' + * will use the 'j limm' form of the intrsuction as long as somewhere is in + * a section other than .vector. + */ + +; ********* Critical System Events ********************** +VECTOR res_service ; 0x0, Reset Vector (0x0) +VECTOR mem_service ; 0x8, Mem exception (0x1) +VECTOR instr_service ; 0x10, Instrn Error (0x2) + +; ******************** Device ISRs ********************** +#ifdef CONFIG_ARC_IRQ3_LV2 +VECTOR handle_interrupt_level2 +#else +VECTOR handle_interrupt_level1 +#endif + +VECTOR handle_interrupt_level1 + +#ifdef CONFIG_ARC_IRQ5_LV2 +VECTOR handle_interrupt_level2 +#else +VECTOR handle_interrupt_level1 +#endif + +#ifdef CONFIG_ARC_IRQ6_LV2 +VECTOR handle_interrupt_level2 +#else +VECTOR handle_interrupt_level1 +#endif + +.rept 25 +VECTOR handle_interrupt_level1 ; Other devices +.endr + +/* FOR ARC600: timer = 0x3, uart = 0x8, emac = 0x10 */ + +; ******************** Exceptions ********************** +VECTOR EV_MachineCheck ; 0x100, Fatal Machine check (0x20) +VECTOR EV_TLBMissI ; 0x108, Intruction TLB miss (0x21) +VECTOR EV_TLBMissD ; 0x110, Data TLB miss (0x22) +VECTOR EV_TLBProtV ; 0x118, Protection Violation (0x23) + ; or Misaligned Access +VECTOR EV_PrivilegeV ; 0x120, Privilege Violation (0x24) +VECTOR EV_Trap ; 0x128, Trap exception (0x25) +VECTOR EV_Extension ; 0x130, Extn Intruction Excp (0x26) + +.rept 24 +VECTOR reserved ; Reserved Exceptions +.endr + + +;##################### Scratch Mem for IRQ stack switching ############# + +ARCFP_DATA int1_saved_reg + .align 32 + .type int1_saved_reg, @object + .size int1_saved_reg, 4 +int1_saved_reg: + .zero 4 + +/* Each Interrupt level needs its own scratch */ +ARCFP_DATA int2_saved_reg + .type int2_saved_reg, @object + .size int2_saved_reg, 4 +int2_saved_reg: + .zero 4 + +; --------------------------------------------- + .section .text, "ax",@progbits + + +reserved: + flag 1 ; Unexpected event, halt + +;##################### Interrupt Handling ############################## + +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS +; --------------------------------------------- +; Level 2 ISR: Can interrupt a Level 1 ISR +; --------------------------------------------- +ENTRY(handle_interrupt_level2) + + INTERRUPT_PROLOGUE 2 + + ;------------------------------------------------------ + ; if L2 IRQ interrupted a L1 ISR, disable preemption + ; + ; This is to avoid a potential L1-L2-L1 scenario + ; -L1 IRQ taken + ; -L2 interrupts L1 (before L1 ISR could run) + ; -preemption off IRQ, user task in syscall picked to run + ; -RTIE to userspace + ; Returns from L2 context fine + ; But both L1 and L2 re-enabled, so another L1 can be taken + ; while prev L1 is still unserviced + ; + ;------------------------------------------------------ + + ; L2 interrupting L1 implies both L2 and L1 active + ; However both A2 and A1 are NOT set in STATUS32, thus + ; need to check STATUS32_L2 to determine if L1 was active + + ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs) + bbit0 r9, STATUS_A1_BIT, 1f ; L1 not active when L2 IRQ, so normal + + ; bump thread_info->preempt_count (Disable preemption) + GET_CURR_THR_INFO_FROM_SP r10 + ld r9, [r10, THREAD_INFO_PREEMPT_COUNT] + add r9, r9, 1 + st r9, [r10, THREAD_INFO_PREEMPT_COUNT] + +1: + ;------------------------------------------------------ + ; setup params for Linux common ISR and invoke it + ;------------------------------------------------------ + lr r0, [icause2] + and r0, r0, 0x1f + + bl.d @arch_do_IRQ + mov r1, sp + + mov r8,0x2 + sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg + + b ret_from_exception + +END(handle_interrupt_level2) + +#endif + +; --------------------------------------------- +; User Mode Memory Bus Error Interrupt Handler +; (Kernel mode memory errors handled via seperate exception vectors) +; --------------------------------------------- +ENTRY(mem_service) + + INTERRUPT_PROLOGUE 2 + + mov r0, ilink2 + mov r1, sp + + ; User process needs to be killed with SIGBUS, but first need to get + ; out of the L2 interrupt context (drop to pure kernel mode) and jump + ; off to "C" code where SIGBUS in enqueued + lr r3, [status32] + bclr r3, r3, STATUS_A2_BIT + or r3, r3, (STATUS_E1_MASK|STATUS_E2_MASK) + sr r3, [status32_l2] + mov ilink2, 1f + rtie +1: + bl do_memory_error + b ret_from_exception +END(mem_service) + +; --------------------------------------------- +; Level 1 ISR +; --------------------------------------------- +ENTRY(handle_interrupt_level1) + + INTERRUPT_PROLOGUE 1 + + lr r0, [icause1] + and r0, r0, 0x1f + +#ifdef CONFIG_TRACE_IRQFLAGS + ; icause1 needs to be read early, before calling tracing, which + ; can clobber scratch regs, hence use of stack to stash it + push r0 + TRACE_ASM_IRQ_DISABLE + pop r0 +#endif + + bl.d @arch_do_IRQ + mov r1, sp + + mov r8,0x1 + sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg + + b ret_from_exception +END(handle_interrupt_level1) + +;################### Non TLB Exception Handling ############################# + +; --------------------------------------------- +; Protection Violation Exception Handler +; --------------------------------------------- + +ENTRY(EV_TLBProtV) + + EXCEPTION_PROLOGUE + + lr r2, [ecr] + lr r0, [efa] ; Faulting Data address (not part of pt_regs saved above) + + ; Exception auto-disables further Intr/exceptions. + ; Re-enable them by pretending to return from exception + ; (so rest of handler executes in pure K mode) + + FAKE_RET_FROM_EXCPN + + mov r1, sp ; Handle to pt_regs + + ;------ (5) Type of Protection Violation? ---------- + ; + ; ProtV Hardware Exception is triggered for Access Faults of 2 types + ; -Access Violaton : 00_23_(00|01|02|03)_00 + ; x r w r+w + ; -Unaligned Access : 00_23_04_00 + ; + bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f + + ;========= (6a) Access Violation Processing ======== + bl do_page_fault + b ret_from_exception + + ;========== (6b) Non aligned access ============ +4: + + SAVE_CALLEE_SAVED_USER + mov r2, sp ; callee_regs + + bl do_misaligned_access + + ; TBD: optimize - do this only if a callee reg was involved + ; either a dst of emulated LD/ST or src with address-writeback + RESTORE_CALLEE_SAVED_USER + + b ret_from_exception + +END(EV_TLBProtV) + +; Wrapper for Linux page fault handler called from EV_TLBMiss* +; Very similar to ProtV handler case (6a) above, but avoids the extra checks +; for Misaligned access +; +ENTRY(call_do_page_fault) + + EXCEPTION_PROLOGUE + lr r0, [efa] ; Faulting Data address + mov r1, sp + FAKE_RET_FROM_EXCPN + + mov blink, ret_from_exception + b do_page_fault + +END(call_do_page_fault) + +;############# Common Handlers for ARCompact and ARCv2 ############## + +#include "entry.S" + +;############# Return from Intr/Excp/Trap (ARC Specifics) ############## +; +; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap) +; IRQ shd definitely not happen between now and rtie +; All 2 entry points to here already disable interrupts + +.Lrestore_regs: + + TRACE_ASM_IRQ_ENABLE + + lr r10, [status32] + + ; Restore REG File. In case multiple Events outstanding, + ; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None + ; Note that we use realtime STATUS32 (not pt_regs->status32) to + ; decide that. + + and.f 0, r10, (STATUS_A1_MASK|STATUS_A2_MASK) + bz .Lexcep_or_pure_K_ret + + ; Returning from Interrupts (Level 1 or 2) + +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS + + ; Level 2 interrupt return Path - from hardware standpoint + bbit0 r10, STATUS_A2_BIT, not_level2_interrupt + + ;------------------------------------------------------------------ + ; However the context returning might not have taken L2 intr itself + ; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret + ; Special considerations needed for the context which took L2 intr + + ld r9, [sp, PT_event] ; Ensure this is L2 intr context + brne r9, event_IRQ2, 149f + + ;------------------------------------------------------------------ + ; if L2 IRQ interrupted an L1 ISR, we'd disabled preemption earlier + ; so that sched doesn't move to new task, causing L1 to be delayed + ; undeterministically. Now that we've achieved that, let's reset + ; things to what they were, before returning from L2 context + ;---------------------------------------------------------------- + + ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs) + bbit0 r9, STATUS_A1_BIT, 149f ; L1 not active when L2 IRQ, so normal + + ; decrement thread_info->preempt_count (re-enable preemption) + GET_CURR_THR_INFO_FROM_SP r10 + ld r9, [r10, THREAD_INFO_PREEMPT_COUNT] + + ; paranoid check, given A1 was active when A2 happened, preempt count + ; must not be 0 because we would have incremented it. + ; If this does happen we simply HALT as it means a BUG !!! + cmp r9, 0 + bnz 2f + flag 1 + +2: + sub r9, r9, 1 + st r9, [r10, THREAD_INFO_PREEMPT_COUNT] + +149: + INTERRUPT_EPILOGUE 2 ; return from level 2 interrupt +debug_marker_l2: + rtie + +not_level2_interrupt: + +#endif + + INTERRUPT_EPILOGUE 1 ; return from level 1 interrupt +debug_marker_l1: + rtie + +.Lexcep_or_pure_K_ret: + + ;this case is for syscalls or Exceptions or pure kernel mode + + EXCEPTION_EPILOGUE +debug_marker_syscall: + rtie + +END(ret_from_exception) diff --git a/kernel/arch/arc/kernel/entry.S b/kernel/arch/arc/kernel/entry.S index d868289c5..2efb06253 100644 --- a/kernel/arch/arc/kernel/entry.S +++ b/kernel/arch/arc/kernel/entry.S @@ -1,60 +1,13 @@ /* - * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC + * Common Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC + * (included from entry-<isa>.S * + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * 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. - * - * vineetg: May 2011 - * -Userspace unaligned access emulation - * - * vineetg: Feb 2011 (ptrace low level code fixes) - * -traced syscall return code (r0) was not saved into pt_regs for restoring - * into user reg-file when traded task rets to user space. - * -syscalls needing arch-wrappers (mainly for passing sp as pt_regs) - * were not invoking post-syscall trace hook (jumping directly into - * ret_from_system_call) - * - * vineetg: Nov 2010: - * -Vector table jumps (@8 bytes) converted into branches (@4 bytes) - * -To maintain the slot size of 8 bytes/vector, added nop, which is - * not executed at runtime. - * - * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK) - * -do_signal()invoked upon TIF_RESTORE_SIGMASK as well - * -Wrappers for sys_{,rt_}sigsuspend() nolonger needed as they don't - * need ptregs anymore - * - * Vineetg: Oct 2009 - * -In a rare scenario, Process gets a Priv-V exception and gets scheduled - * out. Since we don't do FAKE RTIE for Priv-V, CPU excpetion state remains - * active (AE bit enabled). This causes a double fault for a subseq valid - * exception. Thus FAKE RTIE needed in low level Priv-Violation handler. - * Instr Error could also cause similar scenario, so same there as well. - * - * Vineetg: March 2009 (Supporting 2 levels of Interrupts) - * - * Vineetg: Aug 28th 2008: Bug #94984 - * -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap - * Normally CPU does this automatically, however when doing FAKE rtie, - * we need to explicitly do this. The problem in macros - * FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit - * was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit, - * setting it and not clearing it clears ZOL context - * - * Vineetg: May 16th, 2008 - * - r25 now contains the Current Task when in kernel - * - * Vineetg: Dec 22, 2007 - * Minor Surgery of Low Level ISR to make it SMP safe - * - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR - * - _current_task is made an array of NR_CPUS - * - Access of _current_task wrapped inside a macro so that if hardware - * team agrees for a dedicated reg, no other code is touched - * - * Amit Bhor, Rahul Trivedi, Kanika Nema, Sameer Dhavale : Codito Tech 2004 */ /*------------------------------------------------------------------ @@ -67,206 +20,59 @@ * Global Pointer (gp) r26 * Frame Pointer (fp) r27 * Stack Pointer (sp) r28 - * Interrupt link register (ilink1) r29 - * Interrupt link register (ilink2) r30 * Branch link register (blink) r31 *------------------------------------------------------------------ */ - .cpu A7 - -;############################ Vector Table ################################# - -.macro VECTOR lbl -#if 1 /* Just in case, build breaks */ - j \lbl -#else - b \lbl - nop -#endif -.endm - - .section .vector, "ax",@progbits - .align 4 - -/* Each entry in the vector table must occupy 2 words. Since it is a jump - * across sections (.vector to .text) we are gauranteed that 'j somewhere' - * will use the 'j limm' form of the intrsuction as long as somewhere is in - * a section other than .vector. - */ - -; ********* Critical System Events ********************** -VECTOR res_service ; 0x0, Restart Vector (0x0) -VECTOR mem_service ; 0x8, Mem exception (0x1) -VECTOR instr_service ; 0x10, Instrn Error (0x2) - -; ******************** Device ISRs ********************** -#ifdef CONFIG_ARC_IRQ3_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -VECTOR handle_interrupt_level1 - -#ifdef CONFIG_ARC_IRQ5_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -#ifdef CONFIG_ARC_IRQ6_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -.rept 25 -VECTOR handle_interrupt_level1 ; Other devices -.endr - -/* FOR ARC600: timer = 0x3, uart = 0x8, emac = 0x10 */ - -; ******************** Exceptions ********************** -VECTOR EV_MachineCheck ; 0x100, Fatal Machine check (0x20) -VECTOR EV_TLBMissI ; 0x108, Intruction TLB miss (0x21) -VECTOR EV_TLBMissD ; 0x110, Data TLB miss (0x22) -VECTOR EV_TLBProtV ; 0x118, Protection Violation (0x23) - ; or Misaligned Access -VECTOR EV_PrivilegeV ; 0x120, Privilege Violation (0x24) -VECTOR EV_Trap ; 0x128, Trap exception (0x25) -VECTOR EV_Extension ; 0x130, Extn Intruction Excp (0x26) - -.rept 24 -VECTOR reserved ; Reserved Exceptions -.endr - -#include <linux/linkage.h> /* {EXTRY,EXIT} */ -#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,SYS...} */ -#include <asm/errno.h> -#include <asm/arcregs.h> -#include <asm/irqflags.h> - -;##################### Scratch Mem for IRQ stack switching ############# - -ARCFP_DATA int1_saved_reg - .align 32 - .type int1_saved_reg, @object - .size int1_saved_reg, 4 -int1_saved_reg: - .zero 4 - -/* Each Interrupt level needs its own scratch */ -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS - -ARCFP_DATA int2_saved_reg - .type int2_saved_reg, @object - .size int2_saved_reg, 4 -int2_saved_reg: - .zero 4 - -#endif - -; --------------------------------------------- - .section .text, "ax",@progbits - -res_service: ; processor restart - flag 0x1 ; not implemented - nop - nop - -reserved: ; processor restart - rtie ; jump to processor initializations - -;##################### Interrupt Handling ############################## - -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS -; --------------------------------------------- -; Level 2 ISR: Can interrupt a Level 1 ISR -; --------------------------------------------- -ENTRY(handle_interrupt_level2) +;################### Special Sys Call Wrappers ########################## - ; TODO-vineetg for SMP this wont work - ; free up r9 as scratchpad - st r9, [@int2_saved_reg] +ENTRY(sys_clone_wrapper) + SAVE_CALLEE_SAVED_USER + bl @sys_clone + DISCARD_CALLEE_SAVED_USER - ;Which mode (user/kernel) was the system in when intr occured - lr r9, [status32_l2] + GET_CURR_THR_INFO_FLAGS r10 + btst r10, TIF_SYSCALL_TRACE + bnz tracesys_exit - SWITCH_TO_KERNEL_STK - SAVE_ALL_INT2 + b ret_from_system_call +END(sys_clone_wrapper) - ;------------------------------------------------------ - ; if L2 IRQ interrupted a L1 ISR, disable preemption - ;------------------------------------------------------ +ENTRY(ret_from_fork) + ; when the forked child comes here from the __switch_to function + ; r0 has the last task pointer. + ; put last task in scheduler queue + jl @schedule_tail - ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs) - bbit0 r9, STATUS_A1_BIT, 1f ; L1 not active when L2 IRQ, so normal + ld r9, [sp, PT_status32] + brne r9, 0, 1f - ; A1 is set in status32_l2 - ; bump thread_info->preempt_count (Disable preemption) - GET_CURR_THR_INFO_FROM_SP r10 - ld r9, [r10, THREAD_INFO_PREEMPT_COUNT] - add r9, r9, 1 - st r9, [r10, THREAD_INFO_PREEMPT_COUNT] + jl.d [r14] ; kernel thread entry point + mov r0, r13 ; (see PF_KTHREAD block in copy_thread) 1: - ;------------------------------------------------------ - ; setup params for Linux common ISR and invoke it - ;------------------------------------------------------ - lr r0, [icause2] - and r0, r0, 0x1f - - bl.d @arch_do_IRQ - mov r1, sp - - mov r8,0x2 - sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg - - b ret_from_exception - -END(handle_interrupt_level2) - -#endif - -; --------------------------------------------- -; Level 1 ISR -; --------------------------------------------- -ENTRY(handle_interrupt_level1) - - /* free up r9 as scratchpad */ -#ifdef CONFIG_SMP - sr r9, [ARC_REG_SCRATCH_DATA0] -#else - st r9, [@int1_saved_reg] -#endif - - ;Which mode (user/kernel) was the system in when intr occured - lr r9, [status32_l1] - - SWITCH_TO_KERNEL_STK - SAVE_ALL_INT1 + ; Return to user space + ; 1. Any forked task (Reach here via BRne above) + ; 2. First ever init task (Reach here via return from JL above) + ; This is the historic "kernel_execve" use-case, to return to init + ; user mode, in a round about way since that is always done from + ; a kernel thread which is executed via JL above but always returns + ; out whenever kernel_execve (now inline do_fork()) is involved + b ret_from_exception +END(ret_from_fork) - lr r0, [icause1] - and r0, r0, 0x1f +#ifdef CONFIG_ARC_DW2_UNWIND +; Workaround for bug 94179 (STAR ): +; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder +; section (.debug_frame) as loadable. So we force it here. +; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag) +; would not work after a clean build due to kernel build system dependencies. +.section .debug_frame, "wa",@progbits -#ifdef CONFIG_TRACE_IRQFLAGS - ; icause1 needs to be read early, before calling tracing, which - ; can clobber scratch regs, hence use of stack to stash it - push r0 - TRACE_ASM_IRQ_DISABLE - pop r0 +; Reset to .text as this file is included in entry-<isa>.S +.section .text, "ax",@progbits #endif - bl.d @arch_do_IRQ - mov r1, sp - - mov r8,0x1 - sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg - - b ret_from_exception -END(handle_interrupt_level1) - ;################### Non TLB Exception Handling ############################# ; --------------------------------------------- @@ -280,30 +86,13 @@ ENTRY(instr_service) lr r0, [efa] mov r1, sp - FAKE_RET_FROM_EXCPN r9 + FAKE_RET_FROM_EXCPN bl do_insterror_or_kprobe b ret_from_exception END(instr_service) ; --------------------------------------------- -; Memory Error Exception Handler -; --------------------------------------------- - -ENTRY(mem_service) - - EXCEPTION_PROLOGUE - - lr r0, [efa] - mov r1, sp - - FAKE_RET_FROM_EXCPN r9 - - bl do_memory_error - b ret_from_exception -END(mem_service) - -; --------------------------------------------- ; Machine Check Exception Handler ; --------------------------------------------- @@ -334,60 +123,6 @@ ENTRY(EV_MachineCheck) END(EV_MachineCheck) ; --------------------------------------------- -; Protection Violation Exception Handler -; --------------------------------------------- - -ENTRY(EV_TLBProtV) - - EXCEPTION_PROLOGUE - - ;---------(3) Save some more regs----------------- - ; vineetg: Mar 6th: Random Seg Fault issue #1 - ; ecr and efa were not saved in case an Intr sneaks in - ; after fake rtie - - lr r2, [ecr] - lr r0, [efa] ; Faulting Data address - - ; --------(4) Return from CPU Exception Mode --------- - ; Fake a rtie, but rtie to next label - ; That way, subsequently, do_page_fault ( ) executes in pure kernel - ; mode with further Exceptions enabled - - FAKE_RET_FROM_EXCPN r9 - - mov r1, sp - - ;------ (5) Type of Protection Violation? ---------- - ; - ; ProtV Hardware Exception is triggered for Access Faults of 2 types - ; -Access Violaton : 00_23_(00|01|02|03)_00 - ; x r w r+w - ; -Unaligned Access : 00_23_04_00 - ; - bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f - - ;========= (6a) Access Violation Processing ======== - bl do_page_fault - b ret_from_exception - - ;========== (6b) Non aligned access ============ -4: - - SAVE_CALLEE_SAVED_USER - mov r2, sp ; callee_regs - - bl do_misaligned_access - - ; TBD: optimize - do this only if a callee reg was involved - ; either a dst of emulated LD/ST or src with address-writeback - RESTORE_CALLEE_SAVED_USER - - b ret_from_exception - -END(EV_TLBProtV) - -; --------------------------------------------- ; Privilege Violation Exception Handler ; --------------------------------------------- ENTRY(EV_PrivilegeV) @@ -397,7 +132,7 @@ ENTRY(EV_PrivilegeV) lr r0, [efa] mov r1, sp - FAKE_RET_FROM_EXCPN r9 + FAKE_RET_FROM_EXCPN bl do_privilege_fault b ret_from_exception @@ -413,14 +148,17 @@ ENTRY(EV_Extension) lr r0, [efa] mov r1, sp - FAKE_RET_FROM_EXCPN r9 + FAKE_RET_FROM_EXCPN bl do_extension_fault b ret_from_exception END(EV_Extension) -;######################### System Call Tracing ######################### +;################ Trap Handling (Syscall, Breakpoint) ################## +; --------------------------------------------- +; syscall Tracing +; --------------------------------------------- tracesys: ; save EFA in case tracer wants the PC of traced task ; using ERET won't work since next-PC has already committed @@ -463,10 +201,9 @@ tracesys_exit: b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above -;################### Break Point TRAP ########################## - - ; ======= (5b) Trap is due to Break-Point ========= - +; --------------------------------------------- +; Breakpoint TRAP +; --------------------------------------------- trap_with_param: ; stop_pc info by gdb needs this info @@ -475,7 +212,7 @@ trap_with_param: ; Now that we have read EFA, it is safe to do "fake" rtie ; and get out of CPU exception mode - FAKE_RET_FROM_EXCPN r11 + FAKE_RET_FROM_EXCPN ; Save callee regs in case gdb wants to have a look ; SP will grow up by size of CALLEE Reg-File @@ -494,37 +231,33 @@ trap_with_param: b ret_from_exception -;##################### Trap Handling ############################## -; -; EV_Trap caused by TRAP_S and TRAP0 instructions. -;------------------------------------------------------------------ -; (1) System Calls -; :parameters in r0-r7. -; :r8 has the system call number -; (2) Break Points -;------------------------------------------------------------------ +; --------------------------------------------- +; syscall TRAP +; ABI: (r0-r7) upto 8 args, (r8) syscall number +; --------------------------------------------- ENTRY(EV_Trap) EXCEPTION_PROLOGUE - ;------- (4) What caused the Trap -------------- - lr r12, [ecr] - bmsk.f 0, r12, 7 + ;============ TRAP 1 :breakpoints + ; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR) + bmsk.f 0, r9, 7 bnz trap_with_param - ; ======= (5a) Trap is due to System Call ======== + ;============ TRAP (no param): syscall top level - ; Before doing anything, return from CPU Exception Mode - FAKE_RET_FROM_EXCPN r11 + ; First return from Exception to pure K mode (Exception/IRQs renabled) + FAKE_RET_FROM_EXCPN - ; If syscall tracing ongoing, invoke pre-pos-hooks + ; If syscall tracing ongoing, invoke pre-post-hooks GET_CURR_THR_INFO_FLAGS r10 btst r10, TIF_SYSCALL_TRACE bnz tracesys ; this never comes back - ;============ This is normal System Call case ========== - ; Sys-call num shd not exceed the total system calls avail + ;============ Normal syscall case + + ; syscall num shd not exceed the total system calls avail cmp r8, NR_syscalls mov.hi r0, -ENOSYS bhi ret_from_system_call @@ -565,12 +298,12 @@ resume_user_mode_begin: ; Fast Path return to user mode if no pending work GET_CURR_THR_INFO_FLAGS r9 and.f 0, r9, _TIF_WORK_MASK - bz restore_regs + bz .Lrestore_regs ; --- (Slow Path #1) task preemption --- bbit0 r9, TIF_NEED_RESCHED, .Lchk_pend_signals mov blink, resume_user_mode_begin ; tail-call to U mode ret chks - b @schedule ; BTST+Bnz causes relo error in link + j @schedule ; BTST+Bnz causes relo error in link .Lchk_pend_signals: IRQ_ENABLE r10 @@ -624,154 +357,19 @@ resume_kernel_mode: ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 ld r8, [r10, THREAD_INFO_PREEMPT_COUNT] - brne r8, 0, restore_regs + brne r8, 0, .Lrestore_regs ; check if this task's NEED_RESCHED flag set ld r9, [r10, THREAD_INFO_FLAGS] - bbit0 r9, TIF_NEED_RESCHED, restore_regs + bbit0 r9, TIF_NEED_RESCHED, .Lrestore_regs ; Invoke PREEMPTION - bl preempt_schedule_irq + jl preempt_schedule_irq ; preempt_schedule_irq() always returns with IRQ disabled #endif - ; fall through - -;############# Return from Intr/Excp/Trap (ARC Specifics) ############## -; -; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap) -; IRQ shd definitely not happen between now and rtie -; All 2 entry points to here already disable interrupts - -restore_regs : - - TRACE_ASM_IRQ_ENABLE - - lr r10, [status32] - - ; Restore REG File. In case multiple Events outstanding, - ; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None - ; Note that we use realtime STATUS32 (not pt_regs->status32) to - ; decide that. - - ; if Returning from Exception - bbit0 r10, STATUS_AE_BIT, not_exception - RESTORE_ALL_SYS - rtie - - ; Not Exception so maybe Interrupts (Level 1 or 2) + b .Lrestore_regs -not_exception: +##### DONT ADD CODE HERE - .Lrestore_regs actually follows in entry-<isa>.S -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS - - ; Level 2 interrupt return Path - from hardware standpoint - bbit0 r10, STATUS_A2_BIT, not_level2_interrupt - - ;------------------------------------------------------------------ - ; However the context returning might not have taken L2 intr itself - ; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret - ; Special considerations needed for the context which took L2 intr - - ld r9, [sp, PT_event] ; Ensure this is L2 intr context - brne r9, event_IRQ2, 149f - - ;------------------------------------------------------------------ - ; if L2 IRQ interrupted an L1 ISR, we'd disabled preemption earlier - ; so that sched doesn't move to new task, causing L1 to be delayed - ; undeterministically. Now that we've achieved that, let's reset - ; things to what they were, before returning from L2 context - ;---------------------------------------------------------------- - - ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs) - bbit0 r9, STATUS_A1_BIT, 149f ; L1 not active when L2 IRQ, so normal - - ; decrement thread_info->preempt_count (re-enable preemption) - GET_CURR_THR_INFO_FROM_SP r10 - ld r9, [r10, THREAD_INFO_PREEMPT_COUNT] - - ; paranoid check, given A1 was active when A2 happened, preempt count - ; must not be 0 because we would have incremented it. - ; If this does happen we simply HALT as it means a BUG !!! - cmp r9, 0 - bnz 2f - flag 1 - -2: - sub r9, r9, 1 - st r9, [r10, THREAD_INFO_PREEMPT_COUNT] - -149: - ;return from level 2 - RESTORE_ALL_INT2 -debug_marker_l2: - rtie - -not_level2_interrupt: - -#endif - - bbit0 r10, STATUS_A1_BIT, not_level1_interrupt - - ;return from level 1 - - RESTORE_ALL_INT1 -debug_marker_l1: - rtie - -not_level1_interrupt: - - ;this case is for syscalls or Exceptions (with fake rtie) - - RESTORE_ALL_SYS -debug_marker_syscall: - rtie - -END(ret_from_exception) - -ENTRY(ret_from_fork) - ; when the forked child comes here from the __switch_to function - ; r0 has the last task pointer. - ; put last task in scheduler queue - bl @schedule_tail - - ld r9, [sp, PT_status32] - brne r9, 0, 1f - - jl.d [r14] ; kernel thread entry point - mov r0, r13 ; (see PF_KTHREAD block in copy_thread) - -1: - ; Return to user space - ; 1. Any forked task (Reach here via BRne above) - ; 2. First ever init task (Reach here via return from JL above) - ; This is the historic "kernel_execve" use-case, to return to init - ; user mode, in a round about way since that is always done from - ; a kernel thread which is executed via JL above but always returns - ; out whenever kernel_execve (now inline do_fork()) is involved - b ret_from_exception -END(ret_from_fork) - -;################### Special Sys Call Wrappers ########################## - -ENTRY(sys_clone_wrapper) - SAVE_CALLEE_SAVED_USER - bl @sys_clone - DISCARD_CALLEE_SAVED_USER - - GET_CURR_THR_INFO_FLAGS r10 - btst r10, TIF_SYSCALL_TRACE - bnz tracesys_exit - - b ret_from_system_call -END(sys_clone_wrapper) - -#ifdef CONFIG_ARC_DW2_UNWIND -; Workaround for bug 94179 (STAR ): -; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder -; section (.debug_frame) as loadable. So we force it here. -; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag) -; would not work after a clean build due to kernel build system dependencies. -.section .debug_frame, "wa",@progbits -#endif diff --git a/kernel/arch/arc/kernel/head.S b/kernel/arch/arc/kernel/head.S index b0e8666fd..689dd867f 100644 --- a/kernel/arch/arc/kernel/head.S +++ b/kernel/arch/arc/kernel/head.S @@ -49,31 +49,38 @@ 1: .endm - .cpu A7 - .section .init.text, "ax",@progbits - .type stext, @function - .globl stext -stext: - ;------------------------------------------------------------------- - ; Don't clobber r0-r2 yet. It might have bootloader provided info - ;------------------------------------------------------------------- + +;---------------------------------------------------------------- +; Default Reset Handler (jumped into from Reset vector) +; - Don't clobber r0,r1,r2 as they might have u-boot provided args +; - Platforms can override this weak version if needed +;---------------------------------------------------------------- +WEAK(res_service) + j stext +END(res_service) + +;---------------------------------------------------------------- +; Kernel Entry point +;---------------------------------------------------------------- +ENTRY(stext) CPU_EARLY_SETUP #ifdef CONFIG_SMP - ; Ensure Boot (Master) proceeds. Others wait in platform dependent way - ; IDENTITY Reg [ 3 2 1 0 ] - ; (cpu-id) ^^^ => Zero for UP ARC700 - ; => #Core-ID if SMP (Master 0) - ; Note that non-boot CPUs might not land here if halt-on-reset and - ; instead breath life from @first_lines_of_secondary, but we still - ; need to make sure only boot cpu takes this path. GET_CPU_ID r5 cmp r5, 0 - mov.ne r0, r5 - jne arc_platform_smp_wait_to_boot + mov.nz r0, r5 +#ifdef CONFIG_ARC_SMP_HALT_ON_RESET + ; Non-Master can proceed as system would be booted sufficiently + jnz first_lines_of_secondary +#else + ; Non-Masters wait for Master to boot enough and bring them up + jnz arc_platform_smp_wait_to_boot #endif + ; Master falls thru +#endif + ; Clear BSS before updating any globals ; XXX: use ZOL here mov r5, __bss_start @@ -83,6 +90,7 @@ stext: st.ab 0, [r5, 4] 1: +#ifdef CONFIG_ARC_UBOOT_SUPPORT ; Uboot - kernel ABI ; r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2 ; r1 = magic number (board identity, unused as of now @@ -90,6 +98,7 @@ stext: ; These are handled later in setup_arch() st r0, [@uboot_tag] st r2, [@uboot_arg] +#endif ; setup "current" tsk and optionally cache it in dedicated r25 mov r9, @init_task @@ -102,18 +111,14 @@ stext: GET_TSK_STACK_BASE r9, sp ; r9 = tsk, sp = stack base(output) j start_kernel ; "C" entry point +END(stext) #ifdef CONFIG_SMP ;---------------------------------------------------------------- ; First lines of code run by secondary before jumping to 'C' ;---------------------------------------------------------------- .section .text, "ax",@progbits - .type first_lines_of_secondary, @function - .globl first_lines_of_secondary - -first_lines_of_secondary: - - CPU_EARLY_SETUP +ENTRY(first_lines_of_secondary) ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] @@ -126,5 +131,5 @@ first_lines_of_secondary: GET_TSK_STACK_BASE r0, sp j start_kernel_secondary - +END(first_lines_of_secondary) #endif diff --git a/kernel/arch/arc/kernel/intc-arcv2.c b/kernel/arch/arc/kernel/intc-arcv2.c new file mode 100644 index 000000000..0394f9f61 --- /dev/null +++ b/kernel/arch/arc/kernel/intc-arcv2.c @@ -0,0 +1,153 @@ +/* + * Copyright (C) 2014 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/irqdomain.h> +#include <linux/irqchip.h> +#include <asm/irq.h> + +/* + * Early Hardware specific Interrupt setup + * -Called very early (start_kernel -> setup_arch -> setup_processor) + * -Platform Independent (must for any ARC Core) + * -Needed for each CPU (hence not foldable into init_IRQ) + */ +void arc_init_IRQ(void) +{ + unsigned int tmp; + + struct aux_irq_ctrl { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int res3:18, save_idx_regs:1, res2:1, + save_u_to_u:1, save_lp_regs:1, save_blink:1, + res:4, save_nr_gpr_pairs:5; +#else + unsigned int save_nr_gpr_pairs:5, res:4, + save_blink:1, save_lp_regs:1, save_u_to_u:1, + res2:1, save_idx_regs:1, res3:18; +#endif + } ictrl; + + *(unsigned int *)&ictrl = 0; + + ictrl.save_nr_gpr_pairs = 6; /* r0 to r11 (r12 saved manually) */ + ictrl.save_blink = 1; + ictrl.save_lp_regs = 1; /* LP_COUNT, LP_START, LP_END */ + ictrl.save_u_to_u = 0; /* user ctxt saved on kernel stack */ + ictrl.save_idx_regs = 1; /* JLI, LDI, EI */ + + WRITE_AUX(AUX_IRQ_CTRL, ictrl); + + /* setup status32, don't enable intr yet as kernel doesn't want */ + tmp = read_aux_reg(0xa); + tmp |= ISA_INIT_STATUS_BITS; + tmp &= ~STATUS_IE_MASK; + asm volatile("flag %0 \n"::"r"(tmp)); + + /* + * ARCv2 core intc provides multiple interrupt priorities (upto 16). + * Typical builds though have only two levels (0-high, 1-low) + * Linux by default uses lower prio 1 for most irqs, reserving 0 for + * NMI style interrupts in future (say perf) + * + * Read the intc BCR to confirm that Linux default priority is avail + * in h/w + * + * Note: + * IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level + * is 0 based. + */ + tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF; + if (ARCV2_IRQ_DEF_PRIO > tmp) + panic("Linux default irq prio incorrect\n"); +} + +static void arcv2_irq_mask(struct irq_data *data) +{ + write_aux_reg(AUX_IRQ_SELECT, data->irq); + write_aux_reg(AUX_IRQ_ENABLE, 0); +} + +static void arcv2_irq_unmask(struct irq_data *data) +{ + write_aux_reg(AUX_IRQ_SELECT, data->irq); + write_aux_reg(AUX_IRQ_ENABLE, 1); +} + +void arcv2_irq_enable(struct irq_data *data) +{ + /* set default priority */ + write_aux_reg(AUX_IRQ_SELECT, data->irq); + write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO); + + /* + * hw auto enables (linux unmask) all by default + * So no need to do IRQ_ENABLE here + * XXX: However OSCI LAN need it + */ + write_aux_reg(AUX_IRQ_ENABLE, 1); +} + +static struct irq_chip arcv2_irq_chip = { + .name = "ARCv2 core Intc", + .irq_mask = arcv2_irq_mask, + .irq_unmask = arcv2_irq_unmask, + .irq_enable = arcv2_irq_enable +}; + +static int arcv2_irq_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hw) +{ + /* + * core intc IRQs [16, 23]: + * Statically assigned always private-per-core (Timers, WDT, IPI, PCT) + */ + if (hw < 24) { + /* + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + */ + irq_set_percpu_devid(irq); + irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq); + } else { + irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq); + } + + return 0; +} + +static const struct irq_domain_ops arcv2_irq_ops = { + .xlate = irq_domain_xlate_onecell, + .map = arcv2_irq_map, +}; + +static struct irq_domain *root_domain; + +static int __init +init_onchip_IRQ(struct device_node *intc, struct device_node *parent) +{ + if (parent) + panic("DeviceTree incore intc not a root irq controller\n"); + + root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0, + &arcv2_irq_ops, NULL); + + if (!root_domain) + panic("root irq domain not avail\n"); + + /* with this we don't need to export root_domain */ + irq_set_default_host(root_domain); + + return 0; +} + +IRQCHIP_DECLARE(arc_intc, "snps,archs-intc", init_onchip_IRQ); diff --git a/kernel/arch/arc/kernel/intc-compact.c b/kernel/arch/arc/kernel/intc-compact.c new file mode 100644 index 000000000..06bcedf19 --- /dev/null +++ b/kernel/arch/arc/kernel/intc-compact.c @@ -0,0 +1,161 @@ +/* + * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/irqdomain.h> +#include <linux/irqchip.h> +#include <asm/irq.h> + +/* + * Early Hardware specific Interrupt setup + * -Platform independent, needed for each CPU (not foldable into init_IRQ) + * -Called very early (start_kernel -> setup_arch -> setup_processor) + * + * what it does ? + * -Optionally, setup the High priority Interrupts as Level 2 IRQs + */ +void arc_init_IRQ(void) +{ + int level_mask = 0; + + /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3; + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; + + /* + * Write to register, even if no LV2 IRQs configured to reset it + * in case bootloader had mucked with it + */ + write_aux_reg(AUX_IRQ_LEV, level_mask); + + if (level_mask) + pr_info("Level-2 interrupts bitset %x\n", level_mask); +} + +/* + * ARC700 core includes a simple on-chip intc supporting + * -per IRQ enable/disable + * -2 levels of interrupts (high/low) + * -all interrupts being level triggered + * + * To reduce platform code, we assume all IRQs directly hooked-up into intc. + * Platforms with external intc, hence cascaded IRQs, are free to over-ride + * below, per IRQ. + */ + +static void arc_irq_mask(struct irq_data *data) +{ + unsigned int ienb; + + ienb = read_aux_reg(AUX_IENABLE); + ienb &= ~(1 << data->irq); + write_aux_reg(AUX_IENABLE, ienb); +} + +static void arc_irq_unmask(struct irq_data *data) +{ + unsigned int ienb; + + ienb = read_aux_reg(AUX_IENABLE); + ienb |= (1 << data->irq); + write_aux_reg(AUX_IENABLE, ienb); +} + +static struct irq_chip onchip_intc = { + .name = "ARC In-core Intc", + .irq_mask = arc_irq_mask, + .irq_unmask = arc_irq_unmask, +}; + +static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hw) +{ + switch (irq) { + case TIMER0_IRQ: +#ifdef CONFIG_SMP + case IPI_IRQ: +#endif + irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq); + break; + default: + irq_set_chip_and_handler(irq, &onchip_intc, handle_level_irq); + } + return 0; +} + +static const struct irq_domain_ops arc_intc_domain_ops = { + .xlate = irq_domain_xlate_onecell, + .map = arc_intc_domain_map, +}; + +static struct irq_domain *root_domain; + +static int __init +init_onchip_IRQ(struct device_node *intc, struct device_node *parent) +{ + if (parent) + panic("DeviceTree incore intc not a root irq controller\n"); + + root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0, + &arc_intc_domain_ops, NULL); + + if (!root_domain) + panic("root irq domain not avail\n"); + + /* with this we don't need to export root_domain */ + irq_set_default_host(root_domain); + + return 0; +} + +IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ); + +/* + * arch_local_irq_enable - Enable interrupts. + * + * 1. Explicitly called to re-enable interrupts + * 2. Implicitly called from spin_unlock_irq, write_unlock_irq etc + * which maybe in hard ISR itself + * + * Semantics of this function change depending on where it is called from: + * + * -If called from hard-ISR, it must not invert interrupt priorities + * e.g. suppose TIMER is high priority (Level 2) IRQ + * Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times. + * Here local_irq_enable( ) shd not re-enable lower priority interrupts + * -If called from soft-ISR, it must re-enable all interrupts + * soft ISR are low prioity jobs which can be very slow, thus all IRQs + * must be enabled while they run. + * Now hardware context wise we may still be in L2 ISR (not done rtie) + * still we must re-enable both L1 and L2 IRQs + * Another twist is prev scenario with flow being + * L1 ISR ==> interrupted by L2 ISR ==> L2 soft ISR + * here we must not re-enable Ll as prev Ll Interrupt's h/w context will get + * over-written (this is deficiency in ARC700 Interrupt mechanism) + */ + +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS /* Complex version for 2 IRQ levels */ + +void arch_local_irq_enable(void) +{ + unsigned long flags = arch_local_save_flags(); + + if (flags & STATUS_A2_MASK) + flags |= STATUS_E2_MASK; + else if (flags & STATUS_A1_MASK) + flags |= STATUS_E1_MASK; + + arch_local_irq_restore(flags); +} + +EXPORT_SYMBOL(arch_local_irq_enable); +#endif diff --git a/kernel/arch/arc/kernel/irq.c b/kernel/arch/arc/kernel/irq.c index 620ec2fe3..ba17f8528 100644 --- a/kernel/arch/arc/kernel/irq.c +++ b/kernel/arch/arc/kernel/irq.c @@ -8,114 +8,9 @@ */ #include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/of.h> -#include <linux/irqdomain.h> #include <linux/irqchip.h> -#include "../../drivers/irqchip/irqchip.h" -#include <asm/sections.h> -#include <asm/irq.h> #include <asm/mach_desc.h> - -/* - * Early Hardware specific Interrupt setup - * -Platform independent, needed for each CPU (not foldable into init_IRQ) - * -Called very early (start_kernel -> setup_arch -> setup_processor) - * - * what it does ? - * -Optionally, setup the High priority Interrupts as Level 2 IRQs - */ -void arc_init_IRQ(void) -{ - int level_mask = 0; - - /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; - - /* - * Write to register, even if no LV2 IRQs configured to reset it - * in case bootloader had mucked with it - */ - write_aux_reg(AUX_IRQ_LEV, level_mask); - - if (level_mask) - pr_info("Level-2 interrupts bitset %x\n", level_mask); -} - -/* - * ARC700 core includes a simple on-chip intc supporting - * -per IRQ enable/disable - * -2 levels of interrupts (high/low) - * -all interrupts being level triggered - * - * To reduce platform code, we assume all IRQs directly hooked-up into intc. - * Platforms with external intc, hence cascaded IRQs, are free to over-ride - * below, per IRQ. - */ - -static void arc_irq_mask(struct irq_data *data) -{ - unsigned int ienb; - - ienb = read_aux_reg(AUX_IENABLE); - ienb &= ~(1 << data->irq); - write_aux_reg(AUX_IENABLE, ienb); -} - -static void arc_irq_unmask(struct irq_data *data) -{ - unsigned int ienb; - - ienb = read_aux_reg(AUX_IENABLE); - ienb |= (1 << data->irq); - write_aux_reg(AUX_IENABLE, ienb); -} - -static struct irq_chip onchip_intc = { - .name = "ARC In-core Intc", - .irq_mask = arc_irq_mask, - .irq_unmask = arc_irq_unmask, -}; - -static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq, - irq_hw_number_t hw) -{ - if (irq == TIMER0_IRQ) - irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq); - else - irq_set_chip_and_handler(irq, &onchip_intc, handle_level_irq); - - return 0; -} - -static const struct irq_domain_ops arc_intc_domain_ops = { - .xlate = irq_domain_xlate_onecell, - .map = arc_intc_domain_map, -}; - -static struct irq_domain *root_domain; - -static int __init -init_onchip_IRQ(struct device_node *intc, struct device_node *parent) -{ - if (parent) - panic("DeviceTree incore intc not a root irq controller\n"); - - root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0, - &arc_intc_domain_ops, NULL); - - if (!root_domain) - panic("root irq domain not avail\n"); - - /* with this we don't need to export root_domain */ - irq_set_default_host(root_domain); - - return 0; -} - -IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ); +#include <asm/smp.h> /* * Late Interrupt system init called from start_kernel for Boot CPU only @@ -125,17 +20,20 @@ IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ); */ void __init init_IRQ(void) { - /* Any external intc can be setup here */ - if (machine_desc->init_irq) - machine_desc->init_irq(); - - /* process the entire interrupt tree in one go */ + /* + * process the entire interrupt tree in one go + * Any external intc will be setup provided DT chains them + * properly + */ irqchip_init(); #ifdef CONFIG_SMP - /* Master CPU can initialize it's side of IPI */ - if (machine_desc->init_smp) - machine_desc->init_smp(smp_processor_id()); + /* a SMP H/w block could do IPI IRQ request here */ + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(smp_processor_id()); + + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(smp_processor_id()); #endif } @@ -153,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * API called for requesting percpu interrupts - called by each CPU + * - For boot CPU, actually request the IRQ with genirq core + enables + * - For subsequent callers only enable called locally + * + * Relies on being called by boot cpu first (i.e. request called ahead) of + * any enable as expected by genirq. Hence Suitable only for TIMER, IPI + * which are guaranteed to be setup on boot core first. + * Late probed peripherals such as perf can't use this as there no guarantee + * of being called on boot CPU first. + */ + void arc_request_percpu_irq(int irq, int cpu, irqreturn_t (*isr)(int irq, void *dev), const char *irq_nm, @@ -162,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu, if (!cpu) { int rc; +#ifdef CONFIG_ISA_ARCOMPACT /* - * These 2 calls are essential to making percpu IRQ APIs work - * Ideally these details could be hidden in irq chip map function - * but the issue is IPIs IRQs being static (non-DT) and platform - * specific, so we can't identify them there. + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + * + * For ARCv2, this is done in irq map function since we know + * which irqs are strictly per cpu */ irq_set_percpu_devid(irq); - irq_modify_status(irq, IRQ_NOAUTOEN, 0); /* @irq, @clr, @set */ +#endif rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev); if (rc) @@ -178,107 +91,3 @@ void arc_request_percpu_irq(int irq, int cpu, enable_percpu_irq(irq, 0); } - -/* - * arch_local_irq_enable - Enable interrupts. - * - * 1. Explicitly called to re-enable interrupts - * 2. Implicitly called from spin_unlock_irq, write_unlock_irq etc - * which maybe in hard ISR itself - * - * Semantics of this function change depending on where it is called from: - * - * -If called from hard-ISR, it must not invert interrupt priorities - * e.g. suppose TIMER is high priority (Level 2) IRQ - * Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times. - * Here local_irq_enable( ) shd not re-enable lower priority interrupts - * -If called from soft-ISR, it must re-enable all interrupts - * soft ISR are low prioity jobs which can be very slow, thus all IRQs - * must be enabled while they run. - * Now hardware context wise we may still be in L2 ISR (not done rtie) - * still we must re-enable both L1 and L2 IRQs - * Another twist is prev scenario with flow being - * L1 ISR ==> interrupted by L2 ISR ==> L2 soft ISR - * here we must not re-enable Ll as prev Ll Interrupt's h/w context will get - * over-written (this is deficiency in ARC700 Interrupt mechanism) - */ - -#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS /* Complex version for 2 IRQ levels */ - -void arch_local_irq_enable(void) -{ - - unsigned long flags; - flags = arch_local_save_flags(); - - /* Allow both L1 and L2 at the onset */ - flags |= (STATUS_E1_MASK | STATUS_E2_MASK); - - /* Called from hard ISR (between irq_enter and irq_exit) */ - if (in_irq()) { - - /* If in L2 ISR, don't re-enable any further IRQs as this can - * cause IRQ priorities to get upside down. e.g. it could allow - * L1 be taken while in L2 hard ISR which is wrong not only in - * theory, it can also cause the dreaded L1-L2-L1 scenario - */ - if (flags & STATUS_A2_MASK) - flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK); - - /* Even if in L1 ISR, allowe Higher prio L2 IRQs */ - else if (flags & STATUS_A1_MASK) - flags &= ~(STATUS_E1_MASK); - } - - /* called from soft IRQ, ideally we want to re-enable all levels */ - - else if (in_softirq()) { - - /* However if this is case of L1 interrupted by L2, - * re-enabling both may cause whaco L1-L2-L1 scenario - * because ARC700 allows level 1 to interrupt an active L2 ISR - * Thus we disable both - * However some code, executing in soft ISR wants some IRQs - * to be enabled so we re-enable L2 only - * - * How do we determine L1 intr by L2 - * -A2 is set (means in L2 ISR) - * -E1 is set in this ISR's pt_regs->status32 which is - * saved copy of status32_l2 when l2 ISR happened - */ - struct pt_regs *pt = get_irq_regs(); - if ((flags & STATUS_A2_MASK) && pt && - (pt->status32 & STATUS_A1_MASK)) { - /*flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK); */ - flags &= ~(STATUS_E1_MASK); - } - } - - arch_local_irq_restore(flags); -} - -#else /* ! CONFIG_ARC_COMPACT_IRQ_LEVELS */ - -/* - * Simpler version for only 1 level of interrupt - * Here we only Worry about Level 1 Bits - */ -void arch_local_irq_enable(void) -{ - unsigned long flags; - - /* - * ARC IDE Drivers tries to re-enable interrupts from hard-isr - * context which is simply wrong - */ - if (in_irq()) { - WARN_ONCE(1, "IRQ enabled from hard-isr"); - return; - } - - flags = arch_local_save_flags(); - flags |= (STATUS_E1_MASK | STATUS_E2_MASK); - arch_local_irq_restore(flags); -} -#endif -EXPORT_SYMBOL(arch_local_irq_enable); diff --git a/kernel/arch/arc/kernel/mcip.c b/kernel/arch/arc/kernel/mcip.c new file mode 100644 index 000000000..30d806ce0 --- /dev/null +++ b/kernel/arch/arc/kernel/mcip.c @@ -0,0 +1,348 @@ +/* + * ARC ARConnect (MultiCore IP) support (formerly known as MCIP) + * + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/smp.h> +#include <linux/irq.h> +#include <linux/spinlock.h> +#include <asm/irqflags-arcv2.h> +#include <asm/mcip.h> +#include <asm/setup.h> + +#define SOFTIRQ_IRQ 21 + +static char smp_cpuinfo_buf[128]; +static int idu_detected; + +static DEFINE_RAW_SPINLOCK(mcip_lock); + +static void mcip_setup_per_cpu(int cpu) +{ + smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); +} + +static void mcip_ipi_send(int cpu) +{ + unsigned long flags; + int ipi_was_pending; + + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + + /* + * NOTE: We must spin here if the other cpu hasn't yet + * serviced a previous message. This can burn lots + * of time, but we MUST follows this protocol or + * ipi messages can be lost!!! + * Also, we must release the lock in this loop because + * the other side may get to this same loop and not + * be able to ack -- thus causing deadlock. + */ + + do { + raw_spin_lock_irqsave(&mcip_lock, flags); + __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); + ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); + if (ipi_was_pending == 0) + break; /* break out but keep lock */ + raw_spin_unlock_irqrestore(&mcip_lock, flags); + } while (1); + + __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); + raw_spin_unlock_irqrestore(&mcip_lock, flags); + +#ifdef CONFIG_ARC_IPI_DBG + if (ipi_was_pending) + pr_info("IPI ACK delayed from cpu %d\n", cpu); +#endif +} + +static void mcip_ipi_clear(int irq) +{ + unsigned int cpu, c; + unsigned long flags; + unsigned int __maybe_unused copy; + + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + + raw_spin_lock_irqsave(&mcip_lock, flags); + + /* Who sent the IPI */ + __mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0); + + copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ + + /* + * In rare case, multiple concurrent IPIs sent to same target can + * possibly be coalesced by MCIP into 1 asserted IRQ, so @cpus can be + * "vectored" (multiple bits sets) as opposed to typical single bit + */ + do { + c = __ffs(cpu); /* 0,1,2,3 */ + __mcip_cmd(CMD_INTRPT_GENERATE_ACK, c); + cpu &= ~(1U << c); + } while (cpu); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); + +#ifdef CONFIG_ARC_IPI_DBG + if (c != __ffs(copy)) + pr_info("IPIs from %x coalesced to %x\n", + copy, raw_smp_processor_id()); +#endif +} + +static void mcip_probe_n_setup(void) +{ + struct mcip_bcr { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad3:8, + idu:1, llm:1, num_cores:6, + iocoh:1, grtc:1, dbg:1, pad2:1, + msg:1, sem:1, ipi:1, pad:1, + ver:8; +#else + unsigned int ver:8, + pad:1, ipi:1, sem:1, msg:1, + pad2:1, dbg:1, grtc:1, iocoh:1, + num_cores:6, llm:1, idu:1, + pad3:8; +#endif + } mp; + + READ_BCR(ARC_REG_MCIP_BCR, mp); + + sprintf(smp_cpuinfo_buf, + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", + mp.ver, mp.num_cores, + IS_AVAIL1(mp.ipi, "IPI "), + IS_AVAIL1(mp.idu, "IDU "), + IS_AVAIL1(mp.dbg, "DEBUG "), + IS_AVAIL1(mp.grtc, "GRTC")); + + idu_detected = mp.idu; + + if (mp.dbg) { + __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf); + __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf); + } + + if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc) + panic("kernel trying to use non-existent GRTC\n"); +} + +struct plat_smp_ops plat_smp_ops = { + .info = smp_cpuinfo_buf, + .init_early_smp = mcip_probe_n_setup, + .init_per_cpu = mcip_setup_per_cpu, + .ipi_send = mcip_ipi_send, + .ipi_clear = mcip_ipi_clear, +}; + +/*************************************************************************** + * ARCv2 Interrupt Distribution Unit (IDU) + * + * Connects external "COMMON" IRQs to core intc, providing: + * -dynamic routing (IRQ affinity) + * -load balancing (Round Robin interrupt distribution) + * -1:N distribution + * + * It physically resides in the MCIP hw block + */ + +#include <linux/irqchip.h> +#include <linux/of.h> +#include <linux/of_irq.h> + +/* + * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core) + */ +static void idu_set_dest(unsigned int cmn_irq, unsigned int cpu_mask) +{ + __mcip_cmd_data(CMD_IDU_SET_DEST, cmn_irq, cpu_mask); +} + +static void idu_set_mode(unsigned int cmn_irq, unsigned int lvl, + unsigned int distr) +{ + union { + unsigned int word; + struct { + unsigned int distr:2, pad:2, lvl:1, pad2:27; + }; + } data; + + data.distr = distr; + data.lvl = lvl; + __mcip_cmd_data(CMD_IDU_SET_MODE, cmn_irq, data.word); +} + +static void idu_irq_mask(struct irq_data *data) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + __mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 1); + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + +static void idu_irq_unmask(struct irq_data *data) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + __mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 0); + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + +#ifdef CONFIG_SMP +static int +idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, + bool force) +{ + unsigned long flags; + cpumask_t online; + + /* errout if no online cpu per @cpumask */ + if (!cpumask_and(&online, cpumask, cpu_online_mask)) + return -EINVAL; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + idu_set_dest(data->hwirq, cpumask_bits(&online)[0]); + idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); + + return IRQ_SET_MASK_OK; +} +#endif + +static struct irq_chip idu_irq_chip = { + .name = "MCIP IDU Intc", + .irq_mask = idu_irq_mask, + .irq_unmask = idu_irq_unmask, +#ifdef CONFIG_SMP + .irq_set_affinity = idu_irq_set_affinity, +#endif + +}; + +static int idu_first_irq; + +static void idu_cascade_isr(struct irq_desc *desc) +{ + struct irq_domain *domain = irq_desc_get_handler_data(desc); + unsigned int core_irq = irq_desc_get_irq(desc); + unsigned int idu_irq; + + idu_irq = core_irq - idu_first_irq; + generic_handle_irq(irq_find_mapping(domain, idu_irq)); +} + +static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq); + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + + return 0; +} + +static int idu_irq_xlate(struct irq_domain *d, struct device_node *n, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_type) +{ + irq_hw_number_t hwirq = *out_hwirq = intspec[0]; + int distri = intspec[1]; + unsigned long flags; + + *out_type = IRQ_TYPE_NONE; + + /* XXX: validate distribution scheme again online cpu mask */ + if (distri == 0) { + /* 0 - Round Robin to all cpus, otherwise 1 bit per core */ + raw_spin_lock_irqsave(&mcip_lock, flags); + idu_set_dest(hwirq, BIT(num_online_cpus()) - 1); + idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); + raw_spin_unlock_irqrestore(&mcip_lock, flags); + } else { + /* + * DEST based distribution for Level Triggered intr can only + * have 1 CPU, so generalize it to always contain 1 cpu + */ + int cpu = ffs(distri); + + if (cpu != fls(distri)) + pr_warn("IDU irq %lx distri mode set to cpu %x\n", + hwirq, cpu); + + raw_spin_lock_irqsave(&mcip_lock, flags); + idu_set_dest(hwirq, cpu); + idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST); + raw_spin_unlock_irqrestore(&mcip_lock, flags); + } + + return 0; +} + +static const struct irq_domain_ops idu_irq_ops = { + .xlate = idu_irq_xlate, + .map = idu_irq_map, +}; + +/* + * [16, 23]: Statically assigned always private-per-core (Timers, WDT, IPI) + * [24, 23+C]: If C > 0 then "C" common IRQs + * [24+C, N]: Not statically assigned, private-per-core + */ + + +static int __init +idu_of_init(struct device_node *intc, struct device_node *parent) +{ + struct irq_domain *domain; + /* Read IDU BCR to confirm nr_irqs */ + int nr_irqs = of_irq_count(intc); + int i, irq; + + if (!idu_detected) + panic("IDU not detected, but DeviceTree using it"); + + pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs); + + domain = irq_domain_add_linear(intc, nr_irqs, &idu_irq_ops, NULL); + + /* Parent interrupts (core-intc) are already mapped */ + + for (i = 0; i < nr_irqs; i++) { + /* + * Return parent uplink IRQs (towards core intc) 24,25,..... + * this step has been done before already + * however we need it to get the parent virq and set IDU handler + * as first level isr + */ + irq = irq_of_parse_and_map(intc, i); + if (!i) + idu_first_irq = irq; + + irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain); + } + + __mcip_cmd(CMD_IDU_ENABLE, 0); + + return 0; +} +IRQCHIP_DECLARE(arcv2_idu_intc, "snps,archs-idu-intc", idu_of_init); diff --git a/kernel/arch/arc/kernel/perf_event.c b/kernel/arch/arc/kernel/perf_event.c index 57b58f52d..8b134cfe5 100644 --- a/kernel/arch/arc/kernel/perf_event.c +++ b/kernel/arch/arc/kernel/perf_event.c @@ -1,7 +1,7 @@ /* * Linux performance counter support for ARC700 series * - * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com) * * This code is inspired by the perf support of various other architectures. * @@ -11,6 +11,7 @@ * */ #include <linux/errno.h> +#include <linux/interrupt.h> #include <linux/module.h> #include <linux/of.h> #include <linux/perf_event.h> @@ -20,12 +21,25 @@ struct arc_pmu { struct pmu pmu; - int counter_size; /* in bits */ + unsigned int irq; int n_counters; - unsigned long used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)]; + u64 max_period; int ev_hw_idx[PERF_COUNT_ARC_HW_MAX]; }; +struct arc_pmu_cpu { + /* + * A 1 bit for an index indicates that the counter is being used for + * an event. A 0 means that the counter can be used. + */ + unsigned long used_mask[BITS_TO_LONGS(ARC_PERF_MAX_COUNTERS)]; + + /* + * The events that are active on the PMU for the given index. + */ + struct perf_event *act_counter[ARC_PERF_MAX_COUNTERS]; +}; + struct arc_callchain_trace { int depth; void *perf_stuff; @@ -65,6 +79,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) } static struct arc_pmu *arc_pmu; +static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu); /* read counter #idx; note that counter# != event# on ARC! */ static uint64_t arc_pmu_read_counter(int idx) @@ -88,18 +103,15 @@ static uint64_t arc_pmu_read_counter(int idx) static void arc_perf_event_update(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - uint64_t prev_raw_count, new_raw_count; - int64_t delta; - - do { - prev_raw_count = local64_read(&hwc->prev_count); - new_raw_count = arc_pmu_read_counter(idx); - } while (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count); - - delta = (new_raw_count - prev_raw_count) & - ((1ULL << arc_pmu->counter_size) - 1ULL); + uint64_t prev_raw_count = local64_read(&hwc->prev_count); + uint64_t new_raw_count = arc_pmu_read_counter(idx); + int64_t delta = new_raw_count - prev_raw_count; + /* + * We don't afaraid of hwc->prev_count changing beneath our feet + * because there's no way for us to re-enter this function anytime. + */ + local64_set(&hwc->prev_count, new_raw_count); local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); } @@ -142,22 +154,41 @@ static int arc_pmu_event_init(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int ret; + if (!is_sampling_event(event)) { + hwc->sample_period = arc_pmu->max_period; + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + } + + hwc->config = 0; + + if (is_isa_arcv2()) { + /* "exclude user" means "count only kernel" */ + if (event->attr.exclude_user) + hwc->config |= ARC_REG_PCT_CONFIG_KERN; + + /* "exclude kernel" means "count only user" */ + if (event->attr.exclude_kernel) + hwc->config |= ARC_REG_PCT_CONFIG_USER; + } + switch (event->attr.type) { case PERF_TYPE_HARDWARE: if (event->attr.config >= PERF_COUNT_HW_MAX) return -ENOENT; if (arc_pmu->ev_hw_idx[event->attr.config] < 0) return -ENOENT; - hwc->config = arc_pmu->ev_hw_idx[event->attr.config]; + hwc->config |= arc_pmu->ev_hw_idx[event->attr.config]; pr_debug("init event %d with h/w %d \'%s\'\n", (int) event->attr.config, (int) hwc->config, arc_pmu_ev_hw_map[event->attr.config]); return 0; + case PERF_TYPE_HW_CACHE: ret = arc_pmu_cache_event(event->attr.config); if (ret < 0) return ret; - hwc->config = arc_pmu->ev_hw_idx[ret]; + hwc->config |= arc_pmu->ev_hw_idx[ret]; return 0; default: return -ENOENT; @@ -180,6 +211,47 @@ static void arc_pmu_disable(struct pmu *pmu) write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0); } +static int arc_pmu_event_set_period(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + s64 left = local64_read(&hwc->period_left); + s64 period = hwc->sample_period; + int idx = hwc->idx; + int overflow = 0; + u64 value; + + if (unlikely(left <= -period)) { + /* left underflowed by more than period. */ + left = period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + overflow = 1; + } else if (unlikely(left <= 0)) { + /* left underflowed by less than period. */ + left += period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + overflow = 1; + } + + if (left > arc_pmu->max_period) + left = arc_pmu->max_period; + + value = arc_pmu->max_period - left; + local64_set(&hwc->prev_count, value); + + /* Select counter */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + + /* Write value */ + write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value); + write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32)); + + perf_event_update_userpage(event); + + return overflow; +} + /* * Assigns hardware counter to hardware condition. * Note that there is no separate start/stop mechanism; @@ -194,13 +266,20 @@ static void arc_pmu_start(struct perf_event *event, int flags) return; if (flags & PERF_EF_RELOAD) - WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + + hwc->state = 0; - event->hw.state = 0; + arc_pmu_event_set_period(event); + + /* Enable interrupt for this counter */ + if (is_sampling_event(event)) + write_aux_reg(ARC_REG_PCT_INT_CTRL, + read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx)); /* enable ARC pmu here */ - write_aux_reg(ARC_REG_PCT_INDEX, idx); - write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config); + write_aux_reg(ARC_REG_PCT_INDEX, idx); /* counter # */ + write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config); /* condition */ } static void arc_pmu_stop(struct perf_event *event, int flags) @@ -208,6 +287,17 @@ static void arc_pmu_stop(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + /* Disable interrupt for this counter */ + if (is_sampling_event(event)) { + /* + * Reset interrupt flag by writing of 1. This is required + * to make sure pending interrupt was not left. + */ + write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx); + write_aux_reg(ARC_REG_PCT_INT_CTRL, + read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx)); + } + if (!(event->hw.state & PERF_HES_STOPPED)) { /* stop ARC pmu here */ write_aux_reg(ARC_REG_PCT_INDEX, idx); @@ -227,8 +317,12 @@ static void arc_pmu_stop(struct perf_event *event, int flags) static void arc_pmu_del(struct perf_event *event, int flags) { + struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); + arc_pmu_stop(event, PERF_EF_UPDATE); - __clear_bit(event->hw.idx, arc_pmu->used_mask); + __clear_bit(event->hw.idx, pmu_cpu->used_mask); + + pmu_cpu->act_counter[event->hw.idx] = 0; perf_event_update_userpage(event); } @@ -236,20 +330,31 @@ static void arc_pmu_del(struct perf_event *event, int flags) /* allocate hardware counter and optionally start counting */ static int arc_pmu_add(struct perf_event *event, int flags) { + struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - if (__test_and_set_bit(idx, arc_pmu->used_mask)) { - idx = find_first_zero_bit(arc_pmu->used_mask, + if (__test_and_set_bit(idx, pmu_cpu->used_mask)) { + idx = find_first_zero_bit(pmu_cpu->used_mask, arc_pmu->n_counters); if (idx == arc_pmu->n_counters) return -EAGAIN; - __set_bit(idx, arc_pmu->used_mask); + __set_bit(idx, pmu_cpu->used_mask); hwc->idx = idx; } write_aux_reg(ARC_REG_PCT_INDEX, idx); + + pmu_cpu->act_counter[idx] = event; + + if (is_sampling_event(event)) { + /* Mimic full counter overflow as other arches do */ + write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period); + write_aux_reg(ARC_REG_PCT_INT_CNTH, + (arc_pmu->max_period >> 32)); + } + write_aux_reg(ARC_REG_PCT_CONFIG, 0); write_aux_reg(ARC_REG_PCT_COUNTL, 0); write_aux_reg(ARC_REG_PCT_COUNTH, 0); @@ -264,11 +369,81 @@ static int arc_pmu_add(struct perf_event *event, int flags) return 0; } +#ifdef CONFIG_ISA_ARCV2 +static irqreturn_t arc_pmu_intr(int irq, void *dev) +{ + struct perf_sample_data data; + struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); + struct pt_regs *regs; + int active_ints; + int idx; + + arc_pmu_disable(&arc_pmu->pmu); + + active_ints = read_aux_reg(ARC_REG_PCT_INT_ACT); + + regs = get_irq_regs(); + + for (idx = 0; idx < arc_pmu->n_counters; idx++) { + struct perf_event *event = pmu_cpu->act_counter[idx]; + struct hw_perf_event *hwc; + + if (!(active_ints & (1 << idx))) + continue; + + /* Reset interrupt flag by writing of 1 */ + write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx); + + /* + * On reset of "interrupt active" bit corresponding + * "interrupt enable" bit gets automatically reset as well. + * Now we need to re-enable interrupt for the counter. + */ + write_aux_reg(ARC_REG_PCT_INT_CTRL, + read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx)); + + hwc = &event->hw; + + WARN_ON_ONCE(hwc->idx != idx); + + arc_perf_event_update(event, &event->hw, event->hw.idx); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!arc_pmu_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + arc_pmu_stop(event, 0); + } + + arc_pmu_enable(&arc_pmu->pmu); + + return IRQ_HANDLED; +} +#else + +static irqreturn_t arc_pmu_intr(int irq, void *dev) +{ + return IRQ_NONE; +} + +#endif /* CONFIG_ISA_ARCV2 */ + +static void arc_cpu_pmu_irq_init(void *data) +{ + int irq = *(int *)data; + + enable_percpu_irq(irq, IRQ_TYPE_NONE); + + /* Clear all pending interrupt flags */ + write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); +} + static int arc_pmu_device_probe(struct platform_device *pdev) { struct arc_reg_pct_build pct_bcr; struct arc_reg_cc_build cc_bcr; - int i, j, ret; + int i, j, has_interrupts; + int counter_size; /* in bits */ union cc_name { struct { @@ -284,7 +459,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) pr_err("This core does not have performance counters!\n"); return -ENODEV; } - BUG_ON(pct_bcr.c > ARC_PMU_MAX_HWEVENTS); + BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS); READ_BCR(ARC_REG_CC_BUILD, cc_bcr); BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */ @@ -293,11 +468,16 @@ static int arc_pmu_device_probe(struct platform_device *pdev) if (!arc_pmu) return -ENOMEM; + has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0; + arc_pmu->n_counters = pct_bcr.c; - arc_pmu->counter_size = 32 + (pct_bcr.s << 4); + counter_size = 32 + (pct_bcr.s << 4); + + arc_pmu->max_period = (1ULL << counter_size) / 2 - 1ULL; - pr_info("ARC perf\t: %d counters (%d bits), %d countable conditions\n", - arc_pmu->n_counters, arc_pmu->counter_size, cc_bcr.c); + pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n", + arc_pmu->n_counters, counter_size, cc_bcr.c, + has_interrupts ? ", [overflow IRQ support]":""); cc_name.str[8] = 0; for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++) @@ -332,17 +512,32 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .read = arc_pmu_read, }; - /* ARC 700 PMU does not support sampling events */ - arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + if (has_interrupts) { + int irq = platform_get_irq(pdev, 0); - ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); + if (irq < 0) { + pr_err("Cannot get IRQ number for the platform\n"); + return -ENODEV; + } - return ret; + arc_pmu->irq = irq; + + /* intc map function ensures irq_set_percpu_devid() called */ + request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", + this_cpu_ptr(&arc_pmu_cpu)); + + on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + + } else + arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + + return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); } #ifdef CONFIG_OF static const struct of_device_id arc_pmu_match[] = { { .compatible = "snps,arc700-pct" }, + { .compatible = "snps,archs-pct" }, {}, }; MODULE_DEVICE_TABLE(of, arc_pmu_match); @@ -350,7 +545,7 @@ MODULE_DEVICE_TABLE(of, arc_pmu_match); static struct platform_driver arc_pmu_driver = { .driver = { - .name = "arc700-pct", + .name = "arc-pct", .of_match_table = of_match_ptr(arc_pmu_match), }, .probe = arc_pmu_device_probe, diff --git a/kernel/arch/arc/kernel/process.c b/kernel/arch/arc/kernel/process.c index e095c557a..a3f750e76 100644 --- a/kernel/arch/arc/kernel/process.c +++ b/kernel/arch/arc/kernel/process.c @@ -44,7 +44,10 @@ SYSCALL_DEFINE0(arc_gettls) void arch_cpu_idle(void) { /* sleep, but enable all interrupts before committing */ - __asm__("sleep 0x3"); + __asm__ __volatile__( + "sleep %0 \n" + : + :"I"(ISA_SLEEP_ARG)); /* can't be "r" has to be embedded const */ } asmlinkage void ret_from_fork(void); @@ -61,7 +64,7 @@ asmlinkage void ret_from_fork(void); * ------------------ * | r25 | <==== top of Stack (thread.ksp) * ~ ~ - * | --to-- | (CALLEE Regs of user mode) + * | --to-- | (CALLEE Regs of kernel mode) * | r13 | * ------------------ * | fp | @@ -166,8 +169,7 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) * [L] ZOL loop inhibited to begin with - cleared by a LP insn * Interrupts enabled */ - regs->status32 = STATUS_U_MASK | STATUS_L_MASK | - STATUS_E1_MASK | STATUS_E2_MASK; + regs->status32 = STATUS_U_MASK | STATUS_L_MASK | ISA_INIT_STATUS_BITS; /* bogus seed values for debugging */ regs->lp_start = 0x10; @@ -197,8 +199,11 @@ int elf_check_arch(const struct elf32_hdr *x) { unsigned int eflags; - if (x->e_machine != EM_ARCOMPACT) + if (x->e_machine != EM_ARC_INUSE) { + pr_err("ELF not built for %s ISA\n", + is_isa_arcompact() ? "ARCompact":"ARCv2"); return 0; + } eflags = x->e_flags; if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) { diff --git a/kernel/arch/arc/kernel/ptrace.c b/kernel/arch/arc/kernel/ptrace.c index 13b3ffb27..4442204fe 100644 --- a/kernel/arch/arc/kernel/ptrace.c +++ b/kernel/arch/arc/kernel/ptrace.c @@ -47,10 +47,47 @@ static int genregs_get(struct task_struct *target, offsetof(struct user_regs_struct, LOC) + 4); REG_O_ZERO(pad); - REG_O_CHUNK(scratch, callee, ptregs); + REG_O_ONE(scratch.bta, &ptregs->bta); + REG_O_ONE(scratch.lp_start, &ptregs->lp_start); + REG_O_ONE(scratch.lp_end, &ptregs->lp_end); + REG_O_ONE(scratch.lp_count, &ptregs->lp_count); + REG_O_ONE(scratch.status32, &ptregs->status32); + REG_O_ONE(scratch.ret, &ptregs->ret); + REG_O_ONE(scratch.blink, &ptregs->blink); + REG_O_ONE(scratch.fp, &ptregs->fp); + REG_O_ONE(scratch.gp, &ptregs->r26); + REG_O_ONE(scratch.r12, &ptregs->r12); + REG_O_ONE(scratch.r11, &ptregs->r11); + REG_O_ONE(scratch.r10, &ptregs->r10); + REG_O_ONE(scratch.r9, &ptregs->r9); + REG_O_ONE(scratch.r8, &ptregs->r8); + REG_O_ONE(scratch.r7, &ptregs->r7); + REG_O_ONE(scratch.r6, &ptregs->r6); + REG_O_ONE(scratch.r5, &ptregs->r5); + REG_O_ONE(scratch.r4, &ptregs->r4); + REG_O_ONE(scratch.r3, &ptregs->r3); + REG_O_ONE(scratch.r2, &ptregs->r2); + REG_O_ONE(scratch.r1, &ptregs->r1); + REG_O_ONE(scratch.r0, &ptregs->r0); + REG_O_ONE(scratch.sp, &ptregs->sp); + REG_O_ZERO(pad2); - REG_O_CHUNK(callee, efa, cregs); - REG_O_CHUNK(efa, stop_pc, &target->thread.fault_address); + + REG_O_ONE(callee.r25, &cregs->r25); + REG_O_ONE(callee.r24, &cregs->r24); + REG_O_ONE(callee.r23, &cregs->r23); + REG_O_ONE(callee.r22, &cregs->r22); + REG_O_ONE(callee.r21, &cregs->r21); + REG_O_ONE(callee.r20, &cregs->r20); + REG_O_ONE(callee.r19, &cregs->r19); + REG_O_ONE(callee.r18, &cregs->r18); + REG_O_ONE(callee.r17, &cregs->r17); + REG_O_ONE(callee.r16, &cregs->r16); + REG_O_ONE(callee.r15, &cregs->r15); + REG_O_ONE(callee.r14, &cregs->r14); + REG_O_ONE(callee.r13, &cregs->r13); + + REG_O_ONE(efa, &target->thread.fault_address); if (!ret) { if (in_brkpt_trap(ptregs)) { @@ -97,12 +134,51 @@ static int genregs_set(struct task_struct *target, offsetof(struct user_regs_struct, LOC) + 4); REG_IGNORE_ONE(pad); - /* TBD: disallow updates to STATUS32 etc*/ - REG_IN_CHUNK(scratch, pad2, ptregs); /* pt_regs[bta..sp] */ + + REG_IN_ONE(scratch.bta, &ptregs->bta); + REG_IN_ONE(scratch.lp_start, &ptregs->lp_start); + REG_IN_ONE(scratch.lp_end, &ptregs->lp_end); + REG_IN_ONE(scratch.lp_count, &ptregs->lp_count); + + REG_IGNORE_ONE(scratch.status32); + + REG_IN_ONE(scratch.ret, &ptregs->ret); + REG_IN_ONE(scratch.blink, &ptregs->blink); + REG_IN_ONE(scratch.fp, &ptregs->fp); + REG_IN_ONE(scratch.gp, &ptregs->r26); + REG_IN_ONE(scratch.r12, &ptregs->r12); + REG_IN_ONE(scratch.r11, &ptregs->r11); + REG_IN_ONE(scratch.r10, &ptregs->r10); + REG_IN_ONE(scratch.r9, &ptregs->r9); + REG_IN_ONE(scratch.r8, &ptregs->r8); + REG_IN_ONE(scratch.r7, &ptregs->r7); + REG_IN_ONE(scratch.r6, &ptregs->r6); + REG_IN_ONE(scratch.r5, &ptregs->r5); + REG_IN_ONE(scratch.r4, &ptregs->r4); + REG_IN_ONE(scratch.r3, &ptregs->r3); + REG_IN_ONE(scratch.r2, &ptregs->r2); + REG_IN_ONE(scratch.r1, &ptregs->r1); + REG_IN_ONE(scratch.r0, &ptregs->r0); + REG_IN_ONE(scratch.sp, &ptregs->sp); + REG_IGNORE_ONE(pad2); - REG_IN_CHUNK(callee, efa, cregs); /* callee_regs[r25..r13] */ + + REG_IN_ONE(callee.r25, &cregs->r25); + REG_IN_ONE(callee.r24, &cregs->r24); + REG_IN_ONE(callee.r23, &cregs->r23); + REG_IN_ONE(callee.r22, &cregs->r22); + REG_IN_ONE(callee.r21, &cregs->r21); + REG_IN_ONE(callee.r20, &cregs->r20); + REG_IN_ONE(callee.r19, &cregs->r19); + REG_IN_ONE(callee.r18, &cregs->r18); + REG_IN_ONE(callee.r17, &cregs->r17); + REG_IN_ONE(callee.r16, &cregs->r16); + REG_IN_ONE(callee.r15, &cregs->r15); + REG_IN_ONE(callee.r14, &cregs->r14); + REG_IN_ONE(callee.r13, &cregs->r13); + REG_IGNORE_ONE(efa); /* efa update invalid */ - REG_IGNORE_ONE(stop_pc); /* PC updated via @ret */ + REG_IGNORE_ONE(stop_pc); /* PC updated via @ret */ return ret; } @@ -124,7 +200,7 @@ static const struct user_regset arc_regsets[] = { static const struct user_regset_view user_arc_view = { .name = UTS_MACHINE, - .e_machine = EM_ARCOMPACT, + .e_machine = EM_ARC_INUSE, .regsets = arc_regsets, .n = ARRAY_SIZE(arc_regsets) }; diff --git a/kernel/arch/arc/kernel/setup.c b/kernel/arch/arc/kernel/setup.c index 1d167c6df..e1b87444e 100644 --- a/kernel/arch/arc/kernel/setup.c +++ b/kernel/arch/arc/kernel/setup.c @@ -30,6 +30,8 @@ #define FIX_PTR(x) __asm__ __volatile__(";" : "+r"(x)) +unsigned int intr_to_DE_cnt; + /* Part of U-boot ABI: see head.S */ int __initdata uboot_tag; char __initdata *uboot_arg; @@ -45,6 +47,7 @@ static void read_arc_build_cfg_regs(void) struct bcr_perip uncached_space; struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; + unsigned long perip_space; FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); @@ -54,7 +57,12 @@ static void read_arc_build_cfg_regs(void) cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE); READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space); - cpu->uncached_base = uncached_space.start << 24; + if (uncached_space.ver < 3) + perip_space = uncached_space.start << 24; + else + perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000; + + BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE); READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy); @@ -96,7 +104,7 @@ static void read_arc_build_cfg_regs(void) read_decode_mmu_bcr(); read_decode_cache_bcr(); - { + if (is_isa_arcompact()) { struct bcr_fp_arcompact sp, dp; struct bcr_bpu_arcompact bpu; @@ -112,6 +120,19 @@ static void read_arc_build_cfg_regs(void) cpu->bpu.num_cache = 256 << (bpu.ent - 1); cpu->bpu.num_pred = 256 << (bpu.ent - 1); } + } else { + struct bcr_fp_arcv2 spdp; + struct bcr_bpu_arcv2 bpu; + + READ_BCR(ARC_REG_FP_V2_BCR, spdp); + cpu->extn.fpu_sp = spdp.sp ? 1 : 0; + cpu->extn.fpu_dp = spdp.dp ? 1 : 0; + + READ_BCR(ARC_REG_BPU_BCR, bpu); + cpu->bpu.ver = bpu.ver; + cpu->bpu.full = bpu.ft; + cpu->bpu.num_cache = 256 << bpu.bce; + cpu->bpu.num_pred = 2048 << bpu.pte; } READ_BCR(ARC_REG_AP_BCR, bcr); @@ -127,16 +148,18 @@ static void read_arc_build_cfg_regs(void) } static const struct cpuinfo_data arc_cpu_tbl[] = { +#ifdef CONFIG_ISA_ARCOMPACT { {0x20, "ARC 600" }, 0x2F}, { {0x30, "ARC 700" }, 0x33}, { {0x34, "ARC 700 R4.10"}, 0x34}, { {0x35, "ARC 700 R4.11"}, 0x35}, +#else + { {0x50, "ARC HS38 R2.0"}, 0x51}, + { {0x52, "ARC HS38 R2.1"}, 0x52}, +#endif { {0x00, NULL } } }; -#define IS_AVAIL1(v, str) ((v) ? str : "") -#define IS_USED(cfg) (IS_ENABLED(cfg) ? "" : "(not used) ") -#define IS_AVAIL2(v, str, cfg) IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg)) static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) { @@ -149,13 +172,17 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) FIX_PTR(cpu); - { + if (is_isa_arcompact()) { isa_nm = "ARCompact"; be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); atomic = cpu->isa.atomic1; if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); + } else { + isa_nm = "ARCv2"; + be = cpu->isa.be; + atomic = cpu->isa.atomic; } n += scnprintf(buf + n, len - n, @@ -183,16 +210,34 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ", IS_AVAIL1(cpu->timers.t0, "Timer0 "), IS_AVAIL1(cpu->timers.t1, "Timer1 "), - IS_AVAIL2(cpu->timers.rtsc, "64-bit RTSC ", CONFIG_ARC_HAS_RTSC)); + IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ", + CONFIG_ARC_HAS_RTC)); - n += i = scnprintf(buf + n, len - n, "%s%s", - IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC)); + n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s", + IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC), + IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64), + IS_AVAIL1(cpu->isa.unalign, "unalign (not used)")); if (i) n += scnprintf(buf + n, len - n, "\n\t\t: "); + if (cpu->extn_mpy.ver) { + if (cpu->extn_mpy.ver <= 0x2) { /* ARCompact */ + n += scnprintf(buf + n, len - n, "mpy "); + } else { + int opt = 2; /* stock MPY/MPYH */ + + if (cpu->extn_mpy.dsp) /* OPT 7-9 */ + opt = cpu->extn_mpy.dsp + 6; + + n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); + } + n += scnprintf(buf + n, len - n, "%s", + IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY)); + } + n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", - IS_AVAIL1(cpu->extn_mpy.ver, "mpy "), + IS_AVAIL1(cpu->isa.div_rem, "div_rem "), IS_AVAIL1(cpu->extn.norm, "norm "), IS_AVAIL1(cpu->extn.barrel, "barrel-shift "), IS_AVAIL1(cpu->extn.swap, "swap "), @@ -219,7 +264,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\nUncached Base\t: %#x\n", - cpu->vec_base, cpu->uncached_base); + cpu->vec_base, ARC_UNCACHED_ADDR_SPACE); if (cpu->extn.fpu_sp || cpu->extn.fpu_dp) n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n", @@ -254,8 +299,8 @@ static void arc_chk_core_config(void) if (!cpu->timers.t1) panic("Timer1 is not present!\n"); - if (IS_ENABLED(CONFIG_ARC_HAS_RTSC) && !cpu->timers.rtsc) - panic("RTSC is not present\n"); + if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc) + panic("RTC is not present\n"); #ifdef CONFIG_ARC_HAS_DCCM /* @@ -287,6 +332,10 @@ static void arc_chk_core_config(void) pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n"); else if (!cpu->extn.fpu_dp && fpu_enabled) panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n"); + + if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic && + !IS_ENABLED(CONFIG_ARC_STAR_9000923308)) + panic("llock/scond livelock workaround missing\n"); } /* @@ -323,13 +372,16 @@ static inline int is_kernel(unsigned long addr) void __init setup_arch(char **cmdline_p) { +#ifdef CONFIG_ARC_UBOOT_SUPPORT /* make sure that uboot passed pointer to cmdline/dtb is valid */ if (uboot_tag && is_kernel((unsigned long)uboot_arg)) panic("Invalid uboot arg\n"); /* See if u-boot passed an external Device Tree blob */ machine_desc = setup_machine_fdt(uboot_arg); /* uboot_tag == 2 */ - if (!machine_desc) { + if (!machine_desc) +#endif + { /* No, so try the embedded one */ machine_desc = setup_machine_fdt(__dtb_start); if (!machine_desc) @@ -359,8 +411,9 @@ void __init setup_arch(char **cmdline_p) if (machine_desc->init_early) machine_desc->init_early(); - setup_processor(); smp_init_cpus(); + + setup_processor(); setup_arch_memory(); /* copy flat DT out of .init and then unflatten it */ @@ -376,7 +429,6 @@ void __init setup_arch(char **cmdline_p) #endif arc_unwind_init(); - arc_unwind_setup(); } static int __init customize_machine(void) diff --git a/kernel/arch/arc/kernel/signal.c b/kernel/arch/arc/kernel/signal.c index 2251fb4bb..004b7f0bc 100644 --- a/kernel/arch/arc/kernel/signal.c +++ b/kernel/arch/arc/kernel/signal.c @@ -67,7 +67,33 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int err; - err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs, + struct user_regs_struct uregs; + + uregs.scratch.bta = regs->bta; + uregs.scratch.lp_start = regs->lp_start; + uregs.scratch.lp_end = regs->lp_end; + uregs.scratch.lp_count = regs->lp_count; + uregs.scratch.status32 = regs->status32; + uregs.scratch.ret = regs->ret; + uregs.scratch.blink = regs->blink; + uregs.scratch.fp = regs->fp; + uregs.scratch.gp = regs->r26; + uregs.scratch.r12 = regs->r12; + uregs.scratch.r11 = regs->r11; + uregs.scratch.r10 = regs->r10; + uregs.scratch.r9 = regs->r9; + uregs.scratch.r8 = regs->r8; + uregs.scratch.r7 = regs->r7; + uregs.scratch.r6 = regs->r6; + uregs.scratch.r5 = regs->r5; + uregs.scratch.r4 = regs->r4; + uregs.scratch.r3 = regs->r3; + uregs.scratch.r2 = regs->r2; + uregs.scratch.r1 = regs->r1; + uregs.scratch.r0 = regs->r0; + uregs.scratch.sp = regs->sp; + + err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); @@ -78,14 +104,40 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) { sigset_t set; int err; + struct user_regs_struct uregs; err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); if (!err) set_current_blocked(&set); - err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch), + err |= __copy_from_user(&uregs.scratch, + &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); + regs->bta = uregs.scratch.bta; + regs->lp_start = uregs.scratch.lp_start; + regs->lp_end = uregs.scratch.lp_end; + regs->lp_count = uregs.scratch.lp_count; + regs->status32 = uregs.scratch.status32; + regs->ret = uregs.scratch.ret; + regs->blink = uregs.scratch.blink; + regs->fp = uregs.scratch.fp; + regs->r26 = uregs.scratch.gp; + regs->r12 = uregs.scratch.r12; + regs->r11 = uregs.scratch.r11; + regs->r10 = uregs.scratch.r10; + regs->r9 = uregs.scratch.r9; + regs->r8 = uregs.scratch.r8; + regs->r7 = uregs.scratch.r7; + regs->r6 = uregs.scratch.r6; + regs->r5 = uregs.scratch.r5; + regs->r4 = uregs.scratch.r4; + regs->r3 = uregs.scratch.r3; + regs->r2 = uregs.scratch.r2; + regs->r1 = uregs.scratch.r1; + regs->r0 = uregs.scratch.r0; + regs->sp = uregs.scratch.sp; + return err; } @@ -284,7 +336,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs) * their orig user space value when we ret from kernel */ regs->r0 = regs->orig_r0; - regs->ret -= 4; + regs->ret -= is_isa_arcv2() ? 2 : 4; break; } } @@ -325,10 +377,10 @@ void do_signal(struct pt_regs *regs) if (regs->r0 == -ERESTARTNOHAND || regs->r0 == -ERESTARTSYS || regs->r0 == -ERESTARTNOINTR) { regs->r0 = regs->orig_r0; - regs->ret -= 4; + regs->ret -= is_isa_arcv2() ? 2 : 4; } else if (regs->r0 == -ERESTART_RESTARTBLOCK) { regs->r8 = __NR_restart_syscall; - regs->ret -= 4; + regs->ret -= is_isa_arcv2() ? 2 : 4; } syscall_wont_restart(regs); /* No more restarts */ } diff --git a/kernel/arch/arc/kernel/smp.c b/kernel/arch/arc/kernel/smp.c index 6a400b1b0..ef6e9e15b 100644 --- a/kernel/arch/arc/kernel/smp.c +++ b/kernel/arch/arc/kernel/smp.c @@ -31,7 +31,7 @@ arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED; arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED; #endif -struct plat_smp_ops plat_smp_ops; +struct plat_smp_ops __weak plat_smp_ops; /* XXX: per cpu ? Only needed once in early seconday boot */ struct task_struct *secondary_idle_tsk; @@ -42,8 +42,13 @@ void __init smp_prepare_boot_cpu(void) } /* - * Initialise the CPU possible map early - this describes the CPUs - * which may be present or become present in the system. + * Called from setup_arch() before calling setup_processor() + * + * - Initialise the CPU possible map early - this describes the CPUs + * which may be present or become present in the system. + * - Call early smp init hook. This can initialize a specific multi-core + * IP which is say common to several platforms (hence not part of + * platform specific int_early() hook) */ void __init smp_init_cpus(void) { @@ -51,6 +56,9 @@ void __init smp_init_cpus(void) for (i = 0; i < NR_CPUS; i++) set_cpu_possible(i, true); + + if (plat_smp_ops.init_early_smp) + plat_smp_ops.init_early_smp(); } /* called from init ( ) => process 1 */ @@ -72,35 +80,29 @@ void __init smp_cpus_done(unsigned int max_cpus) } /* - * After power-up, a non Master CPU needs to wait for Master to kick start it - * - * The default implementation halts - * - * This relies on platform specific support allowing Master to directly set - * this CPU's PC (to be @first_lines_of_secondary() and kick start it. - * - * In lack of such h/w assist, platforms can override this function - * - make this function busy-spin on a token, eventually set by Master - * (from arc_platform_smp_wakeup_cpu()) - * - Once token is available, jump to @first_lines_of_secondary - * (using inline asm). - * - * Alert: can NOT use stack here as it has not been determined/setup for CPU. - * If it turns out to be elaborate, it's better to code it in assembly - * + * Default smp boot helper for Run-on-reset case where all cores start off + * together. Non-masters need to wait for Master to start running. + * This is implemented using a flag in memory, which Non-masters spin-wait on. + * Master sets it to cpu-id of core to "ungate" it. */ -void __weak arc_platform_smp_wait_to_boot(int cpu) +static volatile int wake_flag; + +static void arc_default_smp_cpu_kick(int cpu, unsigned long pc) { - /* - * As a hack for debugging - since debugger will single-step over the - * FLAG insn - wrap the halt itself it in a self loop - */ - __asm__ __volatile__( - "1: \n" - " flag 1 \n" - " b 1b \n"); + BUG_ON(cpu == 0); + wake_flag = cpu; } +void arc_platform_smp_wait_to_boot(int cpu) +{ + while (wake_flag != cpu) + ; + + wake_flag = 0; + __asm__ __volatile__("j @first_lines_of_secondary \n"); +} + + const char *arc_platform_smp_cpuinfo(void) { return plat_smp_ops.info ? : ""; @@ -129,8 +131,12 @@ void start_kernel_secondary(void) pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu); - if (machine_desc->init_smp) - machine_desc->init_smp(cpu); + /* Some SMP H/w setup - for each cpu */ + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(cpu); + + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(cpu); arc_local_timer_setup(); @@ -161,6 +167,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) if (plat_smp_ops.cpu_kick) plat_smp_ops.cpu_kick(cpu, (unsigned long)first_lines_of_secondary); + else + arc_default_smp_cpu_kick(cpu, (unsigned long)NULL); /* wait for 1 sec after kicking the secondary */ wait_till = jiffies + HZ; @@ -182,7 +190,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) /* * not supported here */ -int __init setup_profiling_timer(unsigned int multiplier) +int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } @@ -278,8 +286,10 @@ static void ipi_cpu_stop(void) machine_halt(); } -static inline void __do_IPI(unsigned long msg) +static inline int __do_IPI(unsigned long msg) { + int rc = 0; + switch (msg) { case IPI_RESCHEDULE: scheduler_ipi(); @@ -294,8 +304,10 @@ static inline void __do_IPI(unsigned long msg) break; default: - pr_warn("IPI with unexpected msg %ld\n", msg); + rc = 1; } + + return rc; } /* @@ -305,6 +317,7 @@ static inline void __do_IPI(unsigned long msg) irqreturn_t do_IPI(int irq, void *dev_id) { unsigned long pending; + unsigned long __maybe_unused copy; pr_debug("IPI [%ld] received on cpu %d\n", *this_cpu_ptr(&ipi_data), smp_processor_id()); @@ -316,11 +329,18 @@ irqreturn_t do_IPI(int irq, void *dev_id) * "dequeue" the msg corresponding to this IPI (and possibly other * piggybacked msg from elided IPIs: see ipi_send_msg_one() above) */ - pending = xchg(this_cpu_ptr(&ipi_data), 0); + copy = pending = xchg(this_cpu_ptr(&ipi_data), 0); do { unsigned long msg = __ffs(pending); - __do_IPI(msg); + int rc; + + rc = __do_IPI(msg); +#ifdef CONFIG_ARC_IPI_DBG + /* IPI received but no valid @msg */ + if (rc) + pr_info("IPI with bogus msg %ld in %ld\n", msg, copy); +#endif pending &= ~(1U << msg); } while (pending); diff --git a/kernel/arch/arc/kernel/stacktrace.c b/kernel/arch/arc/kernel/stacktrace.c index 92320d6f7..001de4ce7 100644 --- a/kernel/arch/arc/kernel/stacktrace.c +++ b/kernel/arch/arc/kernel/stacktrace.c @@ -122,19 +122,17 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, while (1) { address = UNW_PC(&frame_info); - if (address && __kernel_text_address(address)) { - if (consumer_fn(address, arg) == -1) - break; - } + if (!address || !__kernel_text_address(address)) + break; - ret = arc_unwind(&frame_info); + if (consumer_fn(address, arg) == -1) + break; - if (ret == 0) { - frame_info.regs.r63 = frame_info.regs.r31; - continue; - } else { + ret = arc_unwind(&frame_info); + if (ret) break; - } + + frame_info.regs.r63 = frame_info.regs.r31; } return address; /* return the last address it saw */ diff --git a/kernel/arch/arc/kernel/time.c b/kernel/arch/arc/kernel/time.c index dbe74f418..dfad287f1 100644 --- a/kernel/arch/arc/kernel/time.c +++ b/kernel/arch/arc/kernel/time.c @@ -26,6 +26,7 @@ * while TIMER1 for free running (clocksource) * * Newer ARC700 cores have 64bit clk fetching RTSC insn, preferred over TIMER1 + * which however is currently broken */ #include <linux/spinlock.h> @@ -44,6 +45,8 @@ #include <asm/clk.h> #include <asm/mach_desc.h> +#include <asm/mcip.h> + /* Timer related Aux registers */ #define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ #define ARC_REG_TIMER0_CTRL 0x22 /* timer 0 control */ @@ -59,14 +62,10 @@ /********** Clock Source Device *********/ -#ifdef CONFIG_ARC_HAS_RTSC +#ifdef CONFIG_ARC_HAS_GRTC -int arc_counter_setup(void) +static int arc_counter_setup(void) { - /* - * For SMP this needs to be 0. However Kconfig glue doesn't - * enable this option for SMP configs - */ return 1; } @@ -75,45 +74,84 @@ static cycle_t arc_counter_read(struct clocksource *cs) unsigned long flags; union { #ifdef CONFIG_CPU_BIG_ENDIAN - struct { u32 high, low; }; + struct { u32 h, l; }; #else - struct { u32 low, high; }; + struct { u32 l, h; }; #endif cycle_t full; } stamp; - flags = arch_local_irq_save(); + local_irq_save(flags); - __asm__ __volatile( - " .extCoreRegister tsch, 58, r, cannot_shortcut \n" - " rtsc %0, 0 \n" - " mov %1, 0 \n" - : "=r" (stamp.low), "=r" (stamp.high)); + __mcip_cmd(CMD_GRTC_READ_LO, 0); + stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK); + + __mcip_cmd(CMD_GRTC_READ_HI, 0); + stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK); - arch_local_irq_restore(flags); + local_irq_restore(flags); return stamp.full; } static struct clocksource arc_counter = { - .name = "ARC RTSC", - .rating = 300, + .name = "ARConnect GRTC", + .rating = 400, .read = arc_counter_read, - .mask = CLOCKSOURCE_MASK(32), + .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -#else /* !CONFIG_ARC_HAS_RTSC */ +#else + +#ifdef CONFIG_ARC_HAS_RTC + +#define AUX_RTC_CTRL 0x103 +#define AUX_RTC_LOW 0x104 +#define AUX_RTC_HIGH 0x105 -static bool is_usable_as_clocksource(void) +int arc_counter_setup(void) { -#ifdef CONFIG_SMP - return 0; + write_aux_reg(AUX_RTC_CTRL, 1); + + /* Not usable in SMP */ + return !IS_ENABLED(CONFIG_SMP); +} + +static cycle_t arc_counter_read(struct clocksource *cs) +{ + unsigned long status; + union { +#ifdef CONFIG_CPU_BIG_ENDIAN + struct { u32 high, low; }; #else - return 1; + struct { u32 low, high; }; #endif + cycle_t full; + } stamp; + + + __asm__ __volatile( + "1: \n" + " lr %0, [AUX_RTC_LOW] \n" + " lr %1, [AUX_RTC_HIGH] \n" + " lr %2, [AUX_RTC_CTRL] \n" + " bbit0.nt %2, 31, 1b \n" + : "=r" (stamp.low), "=r" (stamp.high), "=r" (status)); + + return stamp.full; } +static struct clocksource arc_counter = { + .name = "ARCv2 RTC", + .rating = 350, + .read = arc_counter_read, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +#else /* !CONFIG_ARC_HAS_RTC */ + /* * set 32bit TIMER1 to keep counting monotonically and wraparound */ @@ -123,7 +161,8 @@ int arc_counter_setup(void) write_aux_reg(ARC_REG_TIMER1_CNT, 0); write_aux_reg(ARC_REG_TIMER1_CTRL, TIMER_CTRL_NH); - return is_usable_as_clocksource(); + /* Not usable in SMP */ + return !IS_ENABLED(CONFIG_SMP); } static cycle_t arc_counter_read(struct clocksource *cs) @@ -140,6 +179,7 @@ static struct clocksource arc_counter = { }; #endif +#endif /********** Clock Event Device *********/ @@ -163,34 +203,24 @@ static int arc_clkevent_set_next_event(unsigned long delta, return 0; } -static void arc_clkevent_set_mode(enum clock_event_mode mode, - struct clock_event_device *dev) +static int arc_clkevent_set_periodic(struct clock_event_device *dev) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* - * At X Hz, 1 sec = 1000ms -> X cycles; - * 10ms -> X / 100 cycles - */ - arc_timer_event_setup(arc_get_core_freq() / HZ); - break; - case CLOCK_EVT_MODE_ONESHOT: - break; - default: - break; - } - - return; + /* + * At X Hz, 1 sec = 1000ms -> X cycles; + * 10ms -> X / 100 cycles + */ + arc_timer_event_setup(arc_get_core_freq() / HZ); + return 0; } static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = { - .name = "ARC Timer0", - .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC, - .mode = CLOCK_EVT_MODE_UNUSED, - .rating = 300, - .irq = TIMER0_IRQ, /* hardwired, no need for resources */ - .set_next_event = arc_clkevent_set_next_event, - .set_mode = arc_clkevent_set_mode, + .name = "ARC Timer0", + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_PERIODIC, + .rating = 300, + .irq = TIMER0_IRQ, /* hardwired, no need for resources */ + .set_next_event = arc_clkevent_set_next_event, + .set_state_periodic = arc_clkevent_set_periodic, }; static irqreturn_t timer_irq_handler(int irq, void *dev_id) @@ -200,7 +230,7 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id) * irq_set_chip_and_handler() asked for handle_percpu_devid_irq() */ struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device); - int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC; + int irq_reenable = clockevent_state_periodic(evt); /* * Any write to CTRL reg ACks the interrupt, we rewrite the @@ -255,7 +285,4 @@ void __init time_init(void) /* sets up the periodic event timer */ arc_local_timer_setup(); - - if (machine_desc->init_time) - machine_desc->init_time(); } diff --git a/kernel/arch/arc/kernel/troubleshoot.c b/kernel/arch/arc/kernel/troubleshoot.c index e00a01879..a6f91e88c 100644 --- a/kernel/arch/arc/kernel/troubleshoot.c +++ b/kernel/arch/arc/kernel/troubleshoot.c @@ -14,6 +14,7 @@ #include <linux/proc_fs.h> #include <linux/file.h> #include <asm/arcregs.h> +#include <asm/irqflags.h> /* * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25) @@ -34,7 +35,10 @@ static noinline void print_reg_file(long *reg_rev, int start_num) n += scnprintf(buf + n, len - n, "\n"); /* because pt_regs has regs reversed: r12..r0, r25..r13 */ - reg_rev--; + if (is_isa_arcv2() && start_num == 0) + reg_rev++; + else + reg_rev--; } if (start_num != 0) @@ -54,7 +58,6 @@ static void show_callee_regs(struct callee_regs *cregs) static void print_task_path_n_nm(struct task_struct *tsk, char *buf) { - struct path path; char *path_nm = NULL; struct mm_struct *mm; struct file *exe_file; @@ -67,15 +70,12 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf) mmput(mm); if (exe_file) { - path = exe_file->f_path; - path_get(&exe_file->f_path); + path_nm = file_path(exe_file, buf, 255); fput(exe_file); - path_nm = d_path(&path, buf, 255); - path_put(&path); } done: - pr_info("Path: %s\n", path_nm); + pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?"); } static void show_faulting_vma(unsigned long address, char *buf) @@ -99,8 +99,7 @@ static void show_faulting_vma(unsigned long address, char *buf) if (vma && (vma->vm_start <= address)) { struct file *file = vma->vm_file; if (file) { - struct path *path = &file->f_path; - nm = d_path(path, buf, PAGE_SIZE - 1); + nm = file_path(file, buf, PAGE_SIZE - 1); inode = file_inode(vma->vm_file); dev = inode->i_sb->s_dev; ino = inode->i_ino; @@ -152,6 +151,15 @@ static void show_ecr_verbose(struct pt_regs *regs) ((cause_code == 0x02) ? "Write" : "EX")); } else if (vec == ECR_V_INSN_ERR) { pr_cont("Illegal Insn\n"); +#ifdef CONFIG_ISA_ARCV2 + } else if (vec == ECR_V_MEM_ERR) { + if (cause_code == 0x00) + pr_cont("Bus Error from Insn Mem\n"); + else if (cause_code == 0x10) + pr_cont("Bus Error from Data Mem\n"); + else + pr_cont("Bus Error, check PRM\n"); +#endif } else { pr_cont("Check Programmer's Manual\n"); } @@ -185,12 +193,20 @@ void show_regs(struct pt_regs *regs) pr_info("[STAT32]: 0x%08lx", regs->status32); -#define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit : "" - if (!user_mode(regs)) - pr_cont(" : %2s %2s %2s %2s %2s\n", - STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1), - STS_BIT(regs, E2), STS_BIT(regs, E1)); +#define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : "" +#ifdef CONFIG_ISA_ARCOMPACT + pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n", + (regs->status32 & STATUS_U_MASK) ? "U " : "K ", + STS_BIT(regs, DE), STS_BIT(regs, AE), + STS_BIT(regs, A2), STS_BIT(regs, A1), + STS_BIT(regs, E2), STS_BIT(regs, E1)); +#else + pr_cont(" : %2s%2s%2s%2s\n", + STS_BIT(regs, IE), + (regs->status32 & STATUS_U_MASK) ? "U " : "K ", + STS_BIT(regs, DE), STS_BIT(regs, AE)); +#endif pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n", regs->bta, regs->sp, regs->fp); pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", diff --git a/kernel/arch/arc/kernel/unaligned.c b/kernel/arch/arc/kernel/unaligned.c index 74db59b6f..abd961f3e 100644 --- a/kernel/arch/arc/kernel/unaligned.c +++ b/kernel/arch/arc/kernel/unaligned.c @@ -34,7 +34,7 @@ " .section .fixup,\"ax\"\n" \ " .align 4\n" \ "3: mov %0, 1\n" \ - " b 2b\n" \ + " j 2b\n" \ " .previous\n" \ " .section __ex_table,\"a\"\n" \ " .align 4\n" \ @@ -82,7 +82,7 @@ " .section .fixup,\"ax\"\n" \ " .align 4\n" \ "4: mov %0, 1\n" \ - " b 3b\n" \ + " j 3b\n" \ " .previous\n" \ " .section __ex_table,\"a\"\n" \ " .align 4\n" \ @@ -113,7 +113,7 @@ " .section .fixup,\"ax\"\n" \ " .align 4\n" \ "6: mov %0, 1\n" \ - " b 5b\n" \ + " j 5b\n" \ " .previous\n" \ " .section __ex_table,\"a\"\n" \ " .align 4\n" \ diff --git a/kernel/arch/arc/kernel/unwind.c b/kernel/arch/arc/kernel/unwind.c index 93c6ea52b..5eb707640 100644 --- a/kernel/arch/arc/kernel/unwind.c +++ b/kernel/arch/arc/kernel/unwind.c @@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc) static unsigned long read_pointer(const u8 **pLoc, const void *end, signed ptrType); +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)); + +/* + * wrappers for header alloc (vs. calling one vs. other at call site) + * to elide section mismatches warnings + */ +static void *__init unw_hdr_alloc_early(unsigned long sz) +{ + return __alloc_bootmem_nopanic(sz, sizeof(unsigned int), + MAX_DMA_ADDRESS); +} + +static void *unw_hdr_alloc(unsigned long sz) +{ + return kmalloc(sz, GFP_KERNEL); +} static void init_unwind_table(struct unwind_table *table, const char *name, const void *core_start, unsigned long core_size, @@ -209,6 +226,8 @@ void __init arc_unwind_init(void) __start_unwind, __end_unwind - __start_unwind, NULL, 0); /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/ + + init_unwind_hdr(&root_table, unw_hdr_alloc_early); } static const u32 bad_cie, not_fde; @@ -241,8 +260,8 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size) e2->fde = v; } -static void __init setup_unwind_table(struct unwind_table *table, - void *(*alloc) (unsigned long)) +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)) { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; @@ -277,10 +296,10 @@ static void __init setup_unwind_table(struct unwind_table *table, if (cie == ¬_fde) continue; if (cie == NULL || cie == &bad_cie) - return; + goto ret_err; ptrType = fde_pointer_type(cie); if (ptrType < 0) - return; + goto ret_err; ptr = (const u8 *)(fde + 2); if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde, @@ -296,13 +315,15 @@ static void __init setup_unwind_table(struct unwind_table *table, } if (tableSize || !n) - return; + goto ret_err; hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int) + 2 * n * sizeof(unsigned long); + header = alloc(hdrSize); if (!header) - return; + goto ret_err; + header->version = 1; header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native; header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4; @@ -340,18 +361,10 @@ static void __init setup_unwind_table(struct unwind_table *table, table->hdrsz = hdrSize; smp_wmb(); table->header = (const void *)header; -} - -static void *__init balloc(unsigned long sz) -{ - return __alloc_bootmem_nopanic(sz, - sizeof(unsigned int), - __pa(MAX_DMA_ADDRESS)); -} + return; -void __init arc_unwind_setup(void) -{ - setup_unwind_table(&root_table, balloc); +ret_err: + panic("Attention !!! Dwarf FDE parsing errors\n");; } #ifdef CONFIG_MODULES @@ -377,6 +390,8 @@ void *unwind_add_table(struct module *module, const void *table_start, table_start, table_size, NULL, 0); + init_unwind_hdr(table, unw_hdr_alloc); + #ifdef UNWIND_DEBUG unw_debug("Table added for [%s] %lx %lx\n", module->name, table->core.pc, table->core.range); @@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only) info.init_only = init_only; unlink_table(&info); /* XXX: SMP */ + kfree(table->header); kfree(table); } @@ -588,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie) const u8 *ptr = (const u8 *)(cie + 2); unsigned version = *ptr; - if (version != 1) - return -1; /* unsupported */ - if (*++ptr) { const char *aug; const u8 *end = (const u8 *)(cie + 1) + *cie; @@ -986,42 +999,13 @@ int arc_unwind(struct unwind_frame_info *frame) (const u8 *)(fde + 1) + *fde, ptrType); - if (pc >= endLoc) + if (pc >= endLoc) { fde = NULL; - } else - fde = NULL; - } - if (fde == NULL) { - for (fde = table->address, tableSize = table->size; - cie = NULL, tableSize > sizeof(*fde) - && tableSize - sizeof(*fde) >= *fde; - tableSize -= sizeof(*fde) + *fde, - fde += 1 + *fde / sizeof(*fde)) { - cie = cie_for_fde(fde, table); - if (cie == &bad_cie) { cie = NULL; - break; } - if (cie == NULL - || cie == ¬_fde - || (ptrType = fde_pointer_type(cie)) < 0) - continue; - ptr = (const u8 *)(fde + 2); - startLoc = read_pointer(&ptr, - (const u8 *)(fde + 1) + - *fde, ptrType); - if (!startLoc) - continue; - if (!(ptrType & DW_EH_PE_indirect)) - ptrType &= - DW_EH_PE_FORM | DW_EH_PE_signed; - endLoc = - startLoc + read_pointer(&ptr, - (const u8 *)(fde + - 1) + - *fde, ptrType); - if (pc >= startLoc && pc < endLoc) - break; + } else { + fde = NULL; + cie = NULL; } } } @@ -1031,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame) ptr = (const u8 *)(cie + 2); end = (const u8 *)(cie + 1) + *cie; frame->call_frame = 1; - if ((state.version = *ptr) != 1) - cie = NULL; /* unsupported version */ - else if (*++ptr) { + if (*++ptr) { /* check if augmentation size is first (thus present) */ if (*ptr == 'z') { while (++ptr < end && *ptr) { diff --git a/kernel/arch/arc/kernel/vmlinux.lds.S b/kernel/arch/arc/kernel/vmlinux.lds.S index dd35bde39..894e696bd 100644 --- a/kernel/arch/arc/kernel/vmlinux.lds.S +++ b/kernel/arch/arc/kernel/vmlinux.lds.S @@ -12,7 +12,7 @@ #include <asm/thread_info.h> OUTPUT_ARCH(arc) -ENTRY(_stext) +ENTRY(res_service) #ifdef CONFIG_CPU_BIG_ENDIAN jiffies = jiffies_64 + 4; diff --git a/kernel/arch/arc/lib/Makefile b/kernel/arch/arc/lib/Makefile index db46e200b..b1656d156 100644 --- a/kernel/arch/arc/lib/Makefile +++ b/kernel/arch/arc/lib/Makefile @@ -5,5 +5,7 @@ # it under the terms of the GNU General Public License version 2 as # published by the Free Software Foundation. -lib-y := strchr-700.o strcmp.o strcpy-700.o strlen.o -lib-y += memcmp.o memcpy-700.o memset.o +lib-y := strchr-700.o strcpy-700.o strlen.o memcmp.o + +lib-$(CONFIG_ISA_ARCOMPACT) += memcpy-700.o memset.o strcmp.o +lib-$(CONFIG_ISA_ARCV2) += memcpy-archs.o memset-archs.o strcmp-archs.o diff --git a/kernel/arch/arc/lib/memcmp.S b/kernel/arch/arc/lib/memcmp.S index 978bf8314..a4015e7d9 100644 --- a/kernel/arch/arc/lib/memcmp.S +++ b/kernel/arch/arc/lib/memcmp.S @@ -24,14 +24,32 @@ ENTRY(memcmp) ld r4,[r0,0] ld r5,[r1,0] lsr.f lp_count,r3,3 +#ifdef CONFIG_ISA_ARCV2 + /* In ARCv2 a branch can't be the last instruction in a zero overhead + * loop. + * So we move the branch to the start of the loop, duplicate it + * after the end, and set up r12 so that the branch isn't taken + * initially. + */ + mov_s r12,WORD2 + lpne .Loop_end + brne WORD2,r12,.Lodd + ld WORD2,[r0,4] +#else lpne .Loop_end ld_s WORD2,[r0,4] +#endif ld_s r12,[r1,4] brne r4,r5,.Leven ld.a r4,[r0,8] ld.a r5,[r1,8] +#ifdef CONFIG_ISA_ARCV2 +.Loop_end: + brne WORD2,r12,.Lodd +#else brne WORD2,r12,.Lodd .Loop_end: +#endif asl_s SHIFT,SHIFT,3 bhs_s .Last_cmp brne r4,r5,.Leven @@ -89,7 +107,6 @@ ENTRY(memcmp) bset.cs r0,r0,31 .Lodd: cmp_s WORD2,r12 - mov_s r0,1 j_s.d [blink] bset.cs r0,r0,31 @@ -100,14 +117,25 @@ ENTRY(memcmp) ldb r4,[r0,0] ldb r5,[r1,0] lsr.f lp_count,r3 +#ifdef CONFIG_ISA_ARCV2 + mov r12,r3 lpne .Lbyte_end + brne r3,r12,.Lbyte_odd +#else + lpne .Lbyte_end +#endif ldb_s r3,[r0,1] ldb r12,[r1,1] brne r4,r5,.Lbyte_even ldb.a r4,[r0,2] ldb.a r5,[r1,2] +#ifdef CONFIG_ISA_ARCV2 +.Lbyte_end: + brne r3,r12,.Lbyte_odd +#else brne r3,r12,.Lbyte_odd .Lbyte_end: +#endif bcc .Lbyte_even brne r4,r5,.Lbyte_even ldb_s r3,[r0,1] diff --git a/kernel/arch/arc/lib/memcpy-archs.S b/kernel/arch/arc/lib/memcpy-archs.S new file mode 100644 index 000000000..f96c75edf --- /dev/null +++ b/kernel/arch/arc/lib/memcpy-archs.S @@ -0,0 +1,236 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +#ifdef __LITTLE_ENDIAN__ +# define SHIFT_1(RX,RY,IMM) asl RX, RY, IMM ; << +# define SHIFT_2(RX,RY,IMM) lsr RX, RY, IMM ; >> +# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM +# define MERGE_2(RX,RY,IMM) +# define EXTRACT_1(RX,RY,IMM) and RX, RY, 0xFFFF +# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, IMM +#else +# define SHIFT_1(RX,RY,IMM) lsr RX, RY, IMM ; >> +# define SHIFT_2(RX,RY,IMM) asl RX, RY, IMM ; << +# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM ; << +# define MERGE_2(RX,RY,IMM) asl RX, RY, IMM ; << +# define EXTRACT_1(RX,RY,IMM) lsr RX, RY, IMM +# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, 0x08 +#endif + +#ifdef CONFIG_ARC_HAS_LL64 +# define PREFETCH_READ(RX) prefetch [RX, 56] +# define PREFETCH_WRITE(RX) prefetchw [RX, 64] +# define LOADX(DST,RX) ldd.ab DST, [RX, 8] +# define STOREX(SRC,RX) std.ab SRC, [RX, 8] +# define ZOLSHFT 5 +# define ZOLAND 0x1F +#else +# define PREFETCH_READ(RX) prefetch [RX, 28] +# define PREFETCH_WRITE(RX) prefetchw [RX, 32] +# define LOADX(DST,RX) ld.ab DST, [RX, 4] +# define STOREX(SRC,RX) st.ab SRC, [RX, 4] +# define ZOLSHFT 4 +# define ZOLAND 0xF +#endif + +ENTRY(memcpy) + prefetch [r1] ; Prefetch the read location + prefetchw [r0] ; Prefetch the write location + mov.f 0, r2 +;;; if size is zero + jz.d [blink] + mov r3, r0 ; don;t clobber ret val + +;;; if size <= 8 + cmp r2, 8 + bls.d @.Lsmallchunk + mov.f lp_count, r2 + + and.f r4, r0, 0x03 + rsub lp_count, r4, 4 + lpnz @.Laligndestination + ;; LOOP BEGIN + ldb.ab r5, [r1,1] + sub r2, r2, 1 + stb.ab r5, [r3,1] +.Laligndestination: + +;;; Check the alignment of the source + and.f r4, r1, 0x03 + bnz.d @.Lsourceunaligned + +;;; CASE 0: Both source and destination are 32bit aligned +;;; Convert len to Dwords, unfold x4 + lsr.f lp_count, r2, ZOLSHFT + lpnz @.Lcopy32_64bytes + ;; LOOP START + LOADX (r6, r1) + PREFETCH_READ (r1) + PREFETCH_WRITE (r3) + LOADX (r8, r1) + LOADX (r10, r1) + LOADX (r4, r1) + STOREX (r6, r3) + STOREX (r8, r3) + STOREX (r10, r3) + STOREX (r4, r3) +.Lcopy32_64bytes: + + and.f lp_count, r2, ZOLAND ;Last remaining 31 bytes +.Lsmallchunk: + lpnz @.Lcopyremainingbytes + ;; LOOP START + ldb.ab r5, [r1,1] + stb.ab r5, [r3,1] +.Lcopyremainingbytes: + + j [blink] +;;; END CASE 0 + +.Lsourceunaligned: + cmp r4, 2 + beq.d @.LunalignedOffby2 + sub r2, r2, 1 + + bhi.d @.LunalignedOffby3 + ldb.ab r5, [r1, 1] + +;;; CASE 1: The source is unaligned, off by 1 + ;; Hence I need to read 1 byte for a 16bit alignment + ;; and 2bytes to reach 32bit alignment + ldh.ab r6, [r1, 2] + sub r2, r2, 2 + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 + MERGE_1 (r6, r6, 8) + MERGE_2 (r5, r5, 24) + or r5, r5, r6 + + ;; Both src and dst are aligned + lpnz @.Lcopy8bytes_1 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 24) + or r7, r7, r5 + SHIFT_2 (r5, r6, 8) + + SHIFT_1 (r9, r8, 24) + or r9, r9, r5 + SHIFT_2 (r5, r8, 8) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_1: + + ;; Write back the remaining 16bits + EXTRACT_1 (r6, r5, 16) + sth.ab r6, [r3, 2] + ;; Write back the remaining 8bits + EXTRACT_2 (r5, r5, 16) + stb.ab r5, [r3, 1] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_1 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_1: + j [blink] + +.LunalignedOffby2: +;;; CASE 2: The source is unaligned, off by 2 + ldh.ab r5, [r1, 2] + sub r2, r2, 1 + + ;; Both src and dst are aligned + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 +#ifdef __BIG_ENDIAN__ + asl.nz r5, r5, 16 +#endif + lpnz @.Lcopy8bytes_2 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 16) + or r7, r7, r5 + SHIFT_2 (r5, r6, 16) + + SHIFT_1 (r9, r8, 16) + or r9, r9, r5 + SHIFT_2 (r5, r8, 16) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_2: + +#ifdef __BIG_ENDIAN__ + lsr.nz r5, r5, 16 +#endif + sth.ab r5, [r3, 2] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_2 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_2: + j [blink] + +.LunalignedOffby3: +;;; CASE 3: The source is unaligned, off by 3 +;;; Hence, I need to read 1byte for achieve the 32bit alignment + + ;; Both src and dst are aligned + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 +#ifdef __BIG_ENDIAN__ + asl.ne r5, r5, 24 +#endif + lpnz @.Lcopy8bytes_3 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 8) + or r7, r7, r5 + SHIFT_2 (r5, r6, 24) + + SHIFT_1 (r9, r8, 8) + or r9, r9, r5 + SHIFT_2 (r5, r8, 24) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_3: + +#ifdef __BIG_ENDIAN__ + lsr.nz r5, r5, 24 +#endif + stb.ab r5, [r3, 1] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_3 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_3: + j [blink] + +END(memcpy) diff --git a/kernel/arch/arc/lib/memset-archs.S b/kernel/arch/arc/lib/memset-archs.S new file mode 100644 index 000000000..365b18364 --- /dev/null +++ b/kernel/arch/arc/lib/memset-archs.S @@ -0,0 +1,122 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +#undef PREALLOC_NOT_AVAIL + +ENTRY(memset) + prefetchw [r0] ; Prefetch the write location + mov.f 0, r2 +;;; if size is zero + jz.d [blink] + mov r3, r0 ; don't clobber ret val + +;;; if length < 8 + brls.d.nt r2, 8, .Lsmallchunk + mov.f lp_count,r2 + + and.f r4, r0, 0x03 + rsub lp_count, r4, 4 + lpnz @.Laligndestination + ;; LOOP BEGIN + stb.ab r1, [r3,1] + sub r2, r2, 1 +.Laligndestination: + +;;; Destination is aligned + and r1, r1, 0xFF + asl r4, r1, 8 + or r4, r4, r1 + asl r5, r4, 16 + or r5, r5, r4 + mov r4, r5 + + sub3 lp_count, r2, 8 + cmp r2, 64 + bmsk.hi r2, r2, 5 + mov.ls lp_count, 0 + add3.hi r2, r2, 8 + +;;; Convert len to Dwords, unfold x8 + lsr.f lp_count, lp_count, 6 + + lpnz @.Lset64bytes + ;; LOOP START +#ifdef PREALLOC_NOT_AVAIL + prefetchw [r3, 64] ;Prefetch the next write location +#else + prealloc [r3, 64] +#endif +#ifdef CONFIG_ARC_HAS_LL64 + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif +.Lset64bytes: + + lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes + lpnz .Lset32bytes + ;; LOOP START + prefetchw [r3, 32] ;Prefetch the next write location +#ifdef CONFIG_ARC_HAS_LL64 + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif +.Lset32bytes: + + and.f lp_count, r2, 0x1F ;Last remaining 31 bytes +.Lsmallchunk: + lpnz .Lcopy3bytes + ;; LOOP START + stb.ab r1, [r3, 1] +.Lcopy3bytes: + + j [blink] + +END(memset) + +ENTRY(memzero) + ; adjust bzero args to memset args + mov r2, r1 + b.d memset ;tail call so need to tinker with blink + mov r1, 0 +END(memzero) diff --git a/kernel/arch/arc/lib/strcmp-archs.S b/kernel/arch/arc/lib/strcmp-archs.S new file mode 100644 index 000000000..4f338eec3 --- /dev/null +++ b/kernel/arch/arc/lib/strcmp-archs.S @@ -0,0 +1,78 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +ENTRY(strcmp) + or r2, r0, r1 + bmsk_s r2, r2, 1 + brne r2, 0, @.Lcharloop + +;;; s1 and s2 are word aligned + ld.ab r2, [r0, 4] + + mov_s r12, 0x01010101 + ror r11, r12 + .align 4 +.LwordLoop: + ld.ab r3, [r1, 4] + ;; Detect NULL char in str1 + sub r4, r2, r12 + ld.ab r5, [r0, 4] + bic r4, r4, r2 + and r4, r4, r11 + brne.d.nt r4, 0, .LfoundNULL + ;; Check if the read locations are the same + cmp r2, r3 + beq.d .LwordLoop + mov.eq r2, r5 + + ;; A match is found, spot it out +#ifdef __LITTLE_ENDIAN__ + swape r3, r3 + mov_s r0, 1 + swape r2, r2 +#else + mov_s r0, 1 +#endif + cmp_s r2, r3 + j_s.d [blink] + bset.lo r0, r0, 31 + + .align 4 +.LfoundNULL: +#ifdef __BIG_ENDIAN__ + swape r4, r4 + swape r2, r2 + swape r3, r3 +#endif + ;; Find null byte + ffs r0, r4 + bmsk r2, r2, r0 + bmsk r3, r3, r0 + swape r2, r2 + swape r3, r3 + ;; make the return value + sub.f r0, r2, r3 + mov.hi r0, 1 + j_s.d [blink] + bset.lo r0, r0, 31 + + .align 4 +.Lcharloop: + ldb.ab r2, [r0, 1] + ldb.ab r3, [r1, 1] + nop + breq r2, 0, .Lcmpend + breq r2, r3, .Lcharloop + + .align 4 +.Lcmpend: + j_s.d [blink] + sub r0, r2, r3 +END(strcmp) diff --git a/kernel/arch/arc/mm/Makefile b/kernel/arch/arc/mm/Makefile index ac95cc239..3703a4969 100644 --- a/kernel/arch/arc/mm/Makefile +++ b/kernel/arch/arc/mm/Makefile @@ -7,4 +7,5 @@ # obj-y := extable.o ioremap.o dma.o fault.o init.o -obj-y += tlb.o tlbex.o cache_arc700.o mmap.o +obj-y += tlb.o tlbex.o cache.o mmap.o +obj-$(CONFIG_HIGHMEM) += highmem.o diff --git a/kernel/arch/arc/mm/cache_arc700.c b/kernel/arch/arc/mm/cache.c index 12b2100db..ff7ff6cbb 100644 --- a/kernel/arch/arc/mm/cache_arc700.c +++ b/kernel/arch/arc/mm/cache.c @@ -1,64 +1,12 @@ /* - * ARC700 VIPT Cache Management + * ARC Cache Management * + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * 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. - * - * vineetg: May 2011: for Non-aliasing VIPT D-cache following can be NOPs - * -flush_cache_dup_mm (fork) - * -likewise for flush_cache_mm (exit/execve) - * -likewise for flush_cache_range,flush_cache_page (munmap, exit, COW-break) - * - * vineetg: Apr 2011 - * -Now that MMU can support larger pg sz (16K), the determiniation of - * aliasing shd not be based on assumption of 8k pg - * - * vineetg: Mar 2011 - * -optimised version of flush_icache_range( ) for making I/D coherent - * when vaddr is available (agnostic of num of aliases) - * - * vineetg: Mar 2011 - * -Added documentation about I-cache aliasing on ARC700 and the way it - * was handled up until MMU V2. - * -Spotted a three year old bug when killing the 4 aliases, which needs - * bottom 2 bits, so we need to do paddr | {0x00, 0x01, 0x02, 0x03} - * instead of paddr | {0x00, 0x01, 0x10, 0x11} - * (Rajesh you owe me one now) - * - * vineetg: Dec 2010 - * -Off-by-one error when computing num_of_lines to flush - * This broke signal handling with bionic which uses synthetic sigret stub - * - * vineetg: Mar 2010 - * -GCC can't generate ZOL for core cache flush loops. - * Conv them into iterations based as opposed to while (start < end) types - * - * Vineetg: July 2009 - * -In I-cache flush routine we used to chk for aliasing for every line INV. - * Instead now we setup routines per cache geometry and invoke them - * via function pointers. - * - * Vineetg: Jan 2009 - * -Cache Line flush routines used to flush an extra line beyond end addr - * because check was while (end >= start) instead of (end > start) - * =Some call sites had to work around by doing -1, -4 etc to end param - * =Some callers didnt care. This was spec bad in case of INV routines - * which would discard valid data (cause of the horrible ext2 bug - * in ARC IDE driver) - * - * vineetg: June 11th 2008: Fixed flush_icache_range( ) - * -Since ARC700 caches are not coherent (I$ doesnt snoop D$) both need - * to be flushed, which it was not doing. - * -load_module( ) passes vmalloc addr (Kernel Virtual Addr) to the API, - * however ARC cache maintenance OPs require PHY addr. Thus need to do - * vmalloc_to_phy. - * -Also added optimisation there, that for range > PAGE SIZE we flush the - * entire cache in one shot rather than line by line. For e.g. a module - * with Code sz 600k, old code flushed 600k worth of cache (line-by-line), - * while cache is only 16 or 32k. */ #include <linux/module.h> @@ -73,9 +21,21 @@ #include <asm/cachectl.h> #include <asm/setup.h> +static int l2_line_sz; +int ioc_exists; +volatile int slc_enable = 1, ioc_enable = 1; + +void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr, + unsigned long sz, const int cacheop); + +void (*__dma_cache_wback_inv)(unsigned long start, unsigned long sz); +void (*__dma_cache_inv)(unsigned long start, unsigned long sz); +void (*__dma_cache_wback)(unsigned long start, unsigned long sz); + char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; + struct cpuinfo_arc_cache *p; #define PR_CACHE(p, cfg, str) \ if (!(p)->ver) \ @@ -86,11 +46,24 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) (p)->sz_k, (p)->assoc, (p)->line_len, \ (p)->vipt ? "VIPT" : "PIPT", \ (p)->alias ? " aliasing" : "", \ - IS_ENABLED(cfg) ? "" : " (not used)"); + IS_USED_CFG(cfg)); PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache"); PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache"); + if (!is_isa_arcv2()) + return buf; + + p = &cpuinfo_arc700[c].slc; + if (p->ver) + n += scnprintf(buf + n, len - n, + "SLC\t\t: %uK, %uB Line%s\n", + p->sz_k, p->line_len, IS_USED_RUN(slc_enable)); + + if (ioc_exists) + n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n", + IS_DISABLED_RUN(ioc_enable)); + return buf; } @@ -99,6 +72,40 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) * the cpuinfo structure for later use. * No Validation done here, simply read/convert the BCRs */ +static void read_decode_cache_bcr_arcv2(int cpu) +{ + struct cpuinfo_arc_cache *p_slc = &cpuinfo_arc700[cpu].slc; + struct bcr_generic sbcr; + + struct bcr_slc_cfg { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:24, way:2, lsz:2, sz:4; +#else + unsigned int sz:4, lsz:2, way:2, pad:24; +#endif + } slc_cfg; + + struct bcr_clust_cfg { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:7, c:1, num_entries:8, num_cores:8, ver:8; +#else + unsigned int ver:8, num_cores:8, num_entries:8, c:1, pad:7; +#endif + } cbcr; + + READ_BCR(ARC_REG_SLC_BCR, sbcr); + if (sbcr.ver) { + READ_BCR(ARC_REG_SLC_CFG, slc_cfg); + p_slc->ver = sbcr.ver; + p_slc->sz_k = 128 << slc_cfg.sz; + l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64; + } + + READ_BCR(ARC_REG_CLUSTER_BCR, cbcr); + if (cbcr.c && ioc_enable) + ioc_exists = 1; +} + void read_decode_cache_bcr(void) { struct cpuinfo_arc_cache *p_ic, *p_dc; @@ -117,8 +124,13 @@ void read_decode_cache_bcr(void) if (!ibcr.ver) goto dc_chk; - BUG_ON(ibcr.config != 3); - p_ic->assoc = 2; /* Fixed to 2w set assoc */ + if (ibcr.ver <= 3) { + BUG_ON(ibcr.config != 3); + p_ic->assoc = 2; /* Fixed to 2w set assoc */ + } else if (ibcr.ver >= 4) { + p_ic->assoc = 1 << ibcr.config; /* 1,2,4,8 */ + } + p_ic->line_len = 8 << ibcr.line_len; p_ic->sz_k = 1 << (ibcr.sz - 1); p_ic->ver = ibcr.ver; @@ -130,94 +142,135 @@ dc_chk: READ_BCR(ARC_REG_DC_BCR, dbcr); if (!dbcr.ver) - return; + goto slc_chk; + + if (dbcr.ver <= 3) { + BUG_ON(dbcr.config != 2); + p_dc->assoc = 4; /* Fixed to 4w set assoc */ + p_dc->vipt = 1; + p_dc->alias = p_dc->sz_k/p_dc->assoc/TO_KB(PAGE_SIZE) > 1; + } else if (dbcr.ver >= 4) { + p_dc->assoc = 1 << dbcr.config; /* 1,2,4,8 */ + p_dc->vipt = 0; + p_dc->alias = 0; /* PIPT so can't VIPT alias */ + } - BUG_ON(dbcr.config != 2); - p_dc->assoc = 4; /* Fixed to 4w set assoc */ p_dc->line_len = 16 << dbcr.line_len; p_dc->sz_k = 1 << (dbcr.sz - 1); p_dc->ver = dbcr.ver; - p_dc->vipt = 1; - p_dc->alias = p_dc->sz_k/p_dc->assoc/TO_KB(PAGE_SIZE) > 1; + +slc_chk: + if (is_isa_arcv2()) + read_decode_cache_bcr_arcv2(cpu); } /* - * 1. Validate the Cache Geomtery (compile time config matches hardware) - * 2. If I-cache suffers from aliasing, setup work arounds (difft flush rtn) - * (aliasing D-cache configurations are not supported YET) - * 3. Enable the Caches, setup default flush mode for D-Cache - * 3. Calculate the SHMLBA used by user space + * Line Operation on {I,D}-Cache */ -void arc_cache_init(void) -{ - unsigned int __maybe_unused cpu = smp_processor_id(); - char str[256]; - - printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; +#define OP_INV 0x1 +#define OP_FLUSH 0x2 +#define OP_FLUSH_N_INV 0x3 +#define OP_INV_IC 0x4 - if (!ic->ver) - panic("cache support enabled but non-existent cache\n"); +/* + * I-Cache Aliasing in ARC700 VIPT caches (MMU v1-v3) + * + * ARC VIPT I-cache uses vaddr to index into cache and paddr to match the tag. + * The orig Cache Management Module "CDU" only required paddr to invalidate a + * certain line since it sufficed as index in Non-Aliasing VIPT cache-geometry. + * Infact for distinct V1,V2,P: all of {V1-P},{V2-P},{P-P} would end up fetching + * the exact same line. + * + * However for larger Caches (way-size > page-size) - i.e. in Aliasing config, + * paddr alone could not be used to correctly index the cache. + * + * ------------------ + * MMU v1/v2 (Fixed Page Size 8k) + * ------------------ + * The solution was to provide CDU with these additonal vaddr bits. These + * would be bits [x:13], x would depend on cache-geometry, 13 comes from + * standard page size of 8k. + * H/w folks chose [17:13] to be a future safe range, and moreso these 5 bits + * of vaddr could easily be "stuffed" in the paddr as bits [4:0] since the + * orig 5 bits of paddr were anyways ignored by CDU line ops, as they + * represent the offset within cache-line. The adv of using this "clumsy" + * interface for additional info was no new reg was needed in CDU programming + * model. + * + * 17:13 represented the max num of bits passable, actual bits needed were + * fewer, based on the num-of-aliases possible. + * -for 2 alias possibility, only bit 13 needed (32K cache) + * -for 4 alias possibility, bits 14:13 needed (64K cache) + * + * ------------------ + * MMU v3 + * ------------------ + * This ver of MMU supports variable page sizes (1k-16k): although Linux will + * only support 8k (default), 16k and 4k. + * However from hardware perspective, smaller page sizes aggrevate aliasing + * meaning more vaddr bits needed to disambiguate the cache-line-op ; + * the existing scheme of piggybacking won't work for certain configurations. + * Two new registers IC_PTAG and DC_PTAG inttoduced. + * "tag" bits are provided in PTAG, index bits in existing IVIL/IVDL/FLDL regs + */ - if (ic->line_len != L1_CACHE_BYTES) - panic("ICache line [%d] != kernel Config [%d]", - ic->line_len, L1_CACHE_BYTES); +static inline +void __cache_line_loop_v2(phys_addr_t paddr, unsigned long vaddr, + unsigned long sz, const int op) +{ + unsigned int aux_cmd; + int num_lines; + const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE; - if (ic->ver != CONFIG_ARC_MMU_VER) - panic("Cache ver [%d] doesn't match MMU ver [%d]\n", - ic->ver, CONFIG_ARC_MMU_VER); + if (op == OP_INV_IC) { + aux_cmd = ARC_REG_IC_IVIL; + } else { + /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ + aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; } - if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) { - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - int handled; - - if (!dc->ver) - panic("cache support enabled but non-existent cache\n"); + /* Ensure we properly floor/ceil the non-line aligned/sized requests + * and have @paddr - aligned to cache line and integral @num_lines. + * This however can be avoided for page sized since: + * -@paddr will be cache-line aligned already (being page aligned) + * -@sz will be integral multiple of line size (being page sized). + */ + if (!full_page) { + sz += paddr & ~CACHE_LINE_MASK; + paddr &= CACHE_LINE_MASK; + vaddr &= CACHE_LINE_MASK; + } - if (dc->line_len != L1_CACHE_BYTES) - panic("DCache line [%d] != kernel Config [%d]", - dc->line_len, L1_CACHE_BYTES); + num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES); - /* check for D-Cache aliasing */ - handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); + /* MMUv2 and before: paddr contains stuffed vaddrs bits */ + paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; - if (dc->alias && !handled) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dc->alias && handled) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + while (num_lines-- > 0) { + write_aux_reg(aux_cmd, paddr); + paddr += L1_CACHE_BYTES; } } -#define OP_INV 0x1 -#define OP_FLUSH 0x2 -#define OP_FLUSH_N_INV 0x3 -#define OP_INV_IC 0x4 - /* - * Common Helper for Line Operations on {I,D}-Cache + * For ARC700 MMUv3 I-cache and D-cache flushes + * Also reused for HS38 aliasing I-cache configuration */ -static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, - unsigned long sz, const int cacheop) +static inline +void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr, + unsigned long sz, const int op) { unsigned int aux_cmd, aux_tag; int num_lines; - const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE; + const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE; - if (cacheop == OP_INV_IC) { + if (op == OP_INV_IC) { aux_cmd = ARC_REG_IC_IVIL; -#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_IC_PTAG; -#endif - } - else { - /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ - aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; -#if (CONFIG_ARC_MMU_VER > 2) + } else { + aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; aux_tag = ARC_REG_DC_PTAG; -#endif } /* Ensure we properly floor/ceil the non-line aligned/sized requests @@ -226,177 +279,201 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, * -@paddr will be cache-line aligned already (being page aligned) * -@sz will be integral multiple of line size (being page sized). */ - if (!full_page_op) { + if (!full_page) { sz += paddr & ~CACHE_LINE_MASK; paddr &= CACHE_LINE_MASK; vaddr &= CACHE_LINE_MASK; } - num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES); -#if (CONFIG_ARC_MMU_VER <= 2) - /* MMUv2 and before: paddr contains stuffed vaddrs bits */ - paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; -#else - /* if V-P const for loop, PTAG can be written once outside loop */ - if (full_page_op) + /* + * MMUv3, cache ops require paddr in PTAG reg + * if V-P const for loop, PTAG can be written once outside loop + */ + if (full_page) write_aux_reg(aux_tag, paddr); -#endif + + /* + * This is technically for MMU v4, using the MMU v3 programming model + * Special work for HS38 aliasing I-cache configuratino with PAE40 + * - upper 8 bits of paddr need to be written into PTAG_HI + * - (and needs to be written before the lower 32 bits) + * Note that PTAG_HI is hoisted outside the line loop + */ + if (is_pae40_enabled() && op == OP_INV_IC) + write_aux_reg(ARC_REG_IC_PTAG_HI, (u64)paddr >> 32); while (num_lines-- > 0) { -#if (CONFIG_ARC_MMU_VER > 2) - /* MMUv3, cache ops require paddr seperately */ - if (!full_page_op) { + if (!full_page) { write_aux_reg(aux_tag, paddr); paddr += L1_CACHE_BYTES; } write_aux_reg(aux_cmd, vaddr); vaddr += L1_CACHE_BYTES; -#else + } +} + +/* + * In HS38x (MMU v4), I-cache is VIPT (can alias), D-cache is PIPT + * Here's how cache ops are implemented + * + * - D-cache: only paddr needed (in DC_IVDL/DC_FLDL) + * - I-cache Non Aliasing: Despite VIPT, only paddr needed (in IC_IVIL) + * - I-cache Aliasing: Both vaddr and paddr needed (in IC_IVIL, IC_PTAG + * respectively, similar to MMU v3 programming model, hence + * __cache_line_loop_v3() is used) + * + * If PAE40 is enabled, independent of aliasing considerations, the higher bits + * needs to be written into PTAG_HI + */ +static inline +void __cache_line_loop_v4(phys_addr_t paddr, unsigned long vaddr, + unsigned long sz, const int cacheop) +{ + unsigned int aux_cmd; + int num_lines; + const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE; + + if (cacheop == OP_INV_IC) { + aux_cmd = ARC_REG_IC_IVIL; + } else { + /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ + aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; + } + + /* Ensure we properly floor/ceil the non-line aligned/sized requests + * and have @paddr - aligned to cache line and integral @num_lines. + * This however can be avoided for page sized since: + * -@paddr will be cache-line aligned already (being page aligned) + * -@sz will be integral multiple of line size (being page sized). + */ + if (!full_page_op) { + sz += paddr & ~CACHE_LINE_MASK; + paddr &= CACHE_LINE_MASK; + } + + num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES); + + /* + * For HS38 PAE40 configuration + * - upper 8 bits of paddr need to be written into PTAG_HI + * - (and needs to be written before the lower 32 bits) + */ + if (is_pae40_enabled()) { + if (cacheop == OP_INV_IC) + /* + * Non aliasing I-cache in HS38, + * aliasing I-cache handled in __cache_line_loop_v3() + */ + write_aux_reg(ARC_REG_IC_PTAG_HI, (u64)paddr >> 32); + else + write_aux_reg(ARC_REG_DC_PTAG_HI, (u64)paddr >> 32); + } + + while (num_lines-- > 0) { write_aux_reg(aux_cmd, paddr); paddr += L1_CACHE_BYTES; -#endif } } +#if (CONFIG_ARC_MMU_VER < 3) +#define __cache_line_loop __cache_line_loop_v2 +#elif (CONFIG_ARC_MMU_VER == 3) +#define __cache_line_loop __cache_line_loop_v3 +#elif (CONFIG_ARC_MMU_VER > 3) +#define __cache_line_loop __cache_line_loop_v4 +#endif + #ifdef CONFIG_ARC_HAS_DCACHE /*************************************************************** * Machine specific helpers for Entire D-Cache or Per Line ops */ -static inline unsigned int __before_dc_op(const int op) +static inline void __before_dc_op(const int op) { - unsigned int reg = reg; - if (op == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE * flush-n-inv is achieved by INV cmd but with IM=1 * So toggle INV sub-mode depending on op request and default */ - reg = read_aux_reg(ARC_REG_DC_CTRL); - write_aux_reg(ARC_REG_DC_CTRL, reg | DC_CTRL_INV_MODE_FLUSH) - ; + const unsigned int ctl = ARC_REG_DC_CTRL; + write_aux_reg(ctl, read_aux_reg(ctl) | DC_CTRL_INV_MODE_FLUSH); } - - return reg; } -static inline void __after_dc_op(const int op, unsigned int reg) +static inline void __after_dc_op(const int op) { - if (op & OP_FLUSH) /* flush / flush-n-inv both wait */ - while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS); + if (op & OP_FLUSH) { + const unsigned int ctl = ARC_REG_DC_CTRL; + unsigned int reg; + + /* flush / flush-n-inv both wait */ + while ((reg = read_aux_reg(ctl)) & DC_CTRL_FLUSH_STATUS) + ; - /* Switch back to default Invalidate mode */ - if (op == OP_FLUSH_N_INV) - write_aux_reg(ARC_REG_DC_CTRL, reg & ~DC_CTRL_INV_MODE_FLUSH); + /* Switch back to default Invalidate mode */ + if (op == OP_FLUSH_N_INV) + write_aux_reg(ctl, reg & ~DC_CTRL_INV_MODE_FLUSH); + } } /* * Operation on Entire D-Cache - * @cacheop = {OP_INV, OP_FLUSH, OP_FLUSH_N_INV} + * @op = {OP_INV, OP_FLUSH, OP_FLUSH_N_INV} * Note that constant propagation ensures all the checks are gone * in generated code */ -static inline void __dc_entire_op(const int cacheop) +static inline void __dc_entire_op(const int op) { - unsigned int ctrl_reg; int aux; - ctrl_reg = __before_dc_op(cacheop); + __before_dc_op(op); - if (cacheop & OP_INV) /* Inv or flush-n-inv use same cmd reg */ + if (op & OP_INV) /* Inv or flush-n-inv use same cmd reg */ aux = ARC_REG_DC_IVDC; else aux = ARC_REG_DC_FLSH; write_aux_reg(aux, 0x1); - __after_dc_op(cacheop, ctrl_reg); + __after_dc_op(op); } /* For kernel mappings cache operation: index is same as paddr */ #define __dc_line_op_k(p, sz, op) __dc_line_op(p, p, sz, op) /* - * D-Cache : Per Line INV (discard or wback+discard) or FLUSH (wback) + * D-Cache Line ops: Per Line INV (discard or wback+discard) or FLUSH (wback) */ -static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, - unsigned long sz, const int cacheop) +static inline void __dc_line_op(phys_addr_t paddr, unsigned long vaddr, + unsigned long sz, const int op) { unsigned long flags; - unsigned int ctrl_reg; local_irq_save(flags); - ctrl_reg = __before_dc_op(cacheop); + __before_dc_op(op); - __cache_line_loop(paddr, vaddr, sz, cacheop); + __cache_line_loop(paddr, vaddr, sz, op); - __after_dc_op(cacheop, ctrl_reg); + __after_dc_op(op); local_irq_restore(flags); } #else -#define __dc_entire_op(cacheop) -#define __dc_line_op(paddr, vaddr, sz, cacheop) -#define __dc_line_op_k(paddr, sz, cacheop) +#define __dc_entire_op(op) +#define __dc_line_op(paddr, vaddr, sz, op) +#define __dc_line_op_k(paddr, sz, op) #endif /* CONFIG_ARC_HAS_DCACHE */ - #ifdef CONFIG_ARC_HAS_ICACHE -/* - * I-Cache Aliasing in ARC700 VIPT caches - * - * ARC VIPT I-cache uses vaddr to index into cache and paddr to match the tag. - * The orig Cache Management Module "CDU" only required paddr to invalidate a - * certain line since it sufficed as index in Non-Aliasing VIPT cache-geometry. - * Infact for distinct V1,V2,P: all of {V1-P},{V2-P},{P-P} would end up fetching - * the exact same line. - * - * However for larger Caches (way-size > page-size) - i.e. in Aliasing config, - * paddr alone could not be used to correctly index the cache. - * - * ------------------ - * MMU v1/v2 (Fixed Page Size 8k) - * ------------------ - * The solution was to provide CDU with these additonal vaddr bits. These - * would be bits [x:13], x would depend on cache-geometry, 13 comes from - * standard page size of 8k. - * H/w folks chose [17:13] to be a future safe range, and moreso these 5 bits - * of vaddr could easily be "stuffed" in the paddr as bits [4:0] since the - * orig 5 bits of paddr were anyways ignored by CDU line ops, as they - * represent the offset within cache-line. The adv of using this "clumsy" - * interface for additional info was no new reg was needed in CDU programming - * model. - * - * 17:13 represented the max num of bits passable, actual bits needed were - * fewer, based on the num-of-aliases possible. - * -for 2 alias possibility, only bit 13 needed (32K cache) - * -for 4 alias possibility, bits 14:13 needed (64K cache) - * - * ------------------ - * MMU v3 - * ------------------ - * This ver of MMU supports variable page sizes (1k-16k): although Linux will - * only support 8k (default), 16k and 4k. - * However from hardware perspective, smaller page sizes aggrevate aliasing - * meaning more vaddr bits needed to disambiguate the cache-line-op ; - * the existing scheme of piggybacking won't work for certain configurations. - * Two new registers IC_PTAG and DC_PTAG inttoduced. - * "tag" bits are provided in PTAG, index bits in existing IVIL/IVDL/FLDL regs - */ - -/*********************************************************** - * Machine specific helper for per line I-Cache invalidate. - */ - static inline void __ic_entire_inv(void) { write_aux_reg(ARC_REG_IC_IVIC, 1); @@ -404,13 +481,13 @@ static inline void __ic_entire_inv(void) } static inline void -__ic_line_inv_vaddr_local(unsigned long paddr, unsigned long vaddr, +__ic_line_inv_vaddr_local(phys_addr_t paddr, unsigned long vaddr, unsigned long sz) { unsigned long flags; local_irq_save(flags); - __cache_line_loop(paddr, vaddr, sz, OP_INV_IC); + (*_cache_line_loop_ic_fn)(paddr, vaddr, sz, OP_INV_IC); local_irq_restore(flags); } @@ -421,7 +498,7 @@ __ic_line_inv_vaddr_local(unsigned long paddr, unsigned long vaddr, #else struct ic_inv_args { - unsigned long paddr, vaddr; + phys_addr_t paddr, vaddr; int sz; }; @@ -432,7 +509,7 @@ static void __ic_line_inv_vaddr_helper(void *info) __ic_line_inv_vaddr_local(ic_inv->paddr, ic_inv->vaddr, ic_inv->sz); } -static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, +static void __ic_line_inv_vaddr(phys_addr_t paddr, unsigned long vaddr, unsigned long sz) { struct ic_inv_args ic_inv = { @@ -453,6 +530,56 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, #endif /* CONFIG_ARC_HAS_ICACHE */ +noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op) +{ +#ifdef CONFIG_ISA_ARCV2 + /* + * SLC is shared between all cores and concurrent aux operations from + * multiple cores need to be serialized using a spinlock + * A concurrent operation can be silently ignored and/or the old/new + * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop + * below) + */ + static DEFINE_SPINLOCK(lock); + unsigned long flags; + unsigned int ctrl; + + spin_lock_irqsave(&lock, flags); + + /* + * The Region Flush operation is specified by CTRL.RGN_OP[11..9] + * - b'000 (default) is Flush, + * - b'001 is Invalidate if CTRL.IM == 0 + * - b'001 is Flush-n-Invalidate if CTRL.IM == 1 + */ + ctrl = read_aux_reg(ARC_REG_SLC_CTRL); + + /* Don't rely on default value of IM bit */ + if (!(op & OP_FLUSH)) /* i.e. OP_INV */ + ctrl &= ~SLC_CTRL_IM; /* clear IM: Disable flush before Inv */ + else + ctrl |= SLC_CTRL_IM; + + if (op & OP_INV) + ctrl |= SLC_CTRL_RGN_OP_INV; /* Inv or flush-n-inv */ + else + ctrl &= ~SLC_CTRL_RGN_OP_INV; + + write_aux_reg(ARC_REG_SLC_CTRL, ctrl); + + /* + * Lower bits are ignored, no need to clip + * END needs to be setup before START (latter triggers the operation) + * END can't be same as START, so add (l2_line_sz - 1) to sz + */ + write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1)); + write_aux_reg(ARC_REG_SLC_RGN_START, paddr); + + while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY); + + spin_unlock_irqrestore(&lock, flags); +#endif +} /*********************************************************** * Exported APIs @@ -493,7 +620,7 @@ void flush_dcache_page(struct page *page) } else if (page_mapped(page)) { /* kernel reading from page with U-mapping */ - void *paddr = page_address(page); + phys_addr_t paddr = (unsigned long)page_address(page); unsigned long vaddr = page->index << PAGE_CACHE_SHIFT; if (addr_not_cache_congruent(paddr, vaddr)) @@ -502,22 +629,74 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); +/* + * DMA ops for systems with L1 cache only + * Make memory coherent with L1 cache by flushing/invalidating L1 lines + */ +static void __dma_cache_wback_inv_l1(unsigned long start, unsigned long sz) +{ + __dc_line_op_k(start, sz, OP_FLUSH_N_INV); +} -void dma_cache_wback_inv(unsigned long start, unsigned long sz) +static void __dma_cache_inv_l1(unsigned long start, unsigned long sz) +{ + __dc_line_op_k(start, sz, OP_INV); +} + +static void __dma_cache_wback_l1(unsigned long start, unsigned long sz) +{ + __dc_line_op_k(start, sz, OP_FLUSH); +} + +/* + * DMA ops for systems with both L1 and L2 caches, but without IOC + * Both L1 and L2 lines need to be explicity flushed/invalidated + */ +static void __dma_cache_wback_inv_slc(unsigned long start, unsigned long sz) { __dc_line_op_k(start, sz, OP_FLUSH_N_INV); + slc_op(start, sz, OP_FLUSH_N_INV); +} + +static void __dma_cache_inv_slc(unsigned long start, unsigned long sz) +{ + __dc_line_op_k(start, sz, OP_INV); + slc_op(start, sz, OP_INV); +} + +static void __dma_cache_wback_slc(unsigned long start, unsigned long sz) +{ + __dc_line_op_k(start, sz, OP_FLUSH); + slc_op(start, sz, OP_FLUSH); +} + +/* + * DMA ops for systems with IOC + * IOC hardware snoops all DMA traffic keeping the caches consistent with + * memory - eliding need for any explicit cache maintenance of DMA buffers + */ +static void __dma_cache_wback_inv_ioc(unsigned long start, unsigned long sz) {} +static void __dma_cache_inv_ioc(unsigned long start, unsigned long sz) {} +static void __dma_cache_wback_ioc(unsigned long start, unsigned long sz) {} + +/* + * Exported DMA API + */ +void dma_cache_wback_inv(unsigned long start, unsigned long sz) +{ + __dma_cache_wback_inv(start, sz); } EXPORT_SYMBOL(dma_cache_wback_inv); void dma_cache_inv(unsigned long start, unsigned long sz) { - __dc_line_op_k(start, sz, OP_INV); + __dma_cache_inv(start, sz); } EXPORT_SYMBOL(dma_cache_inv); void dma_cache_wback(unsigned long start, unsigned long sz) { - __dc_line_op_k(start, sz, OP_FLUSH); + __dma_cache_wback(start, sz); } EXPORT_SYMBOL(dma_cache_wback); @@ -589,14 +768,14 @@ EXPORT_SYMBOL(flush_icache_range); * builtin kernel page will not have any virtual mappings. * kprobe on loadable module will be kernel vaddr. */ -void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len) +void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len) { __dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV); __ic_line_inv_vaddr(paddr, vaddr, len); } /* wrapper to compile time eliminate alignment checks in flush loop */ -void __inv_icache_page(unsigned long paddr, unsigned long vaddr) +void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr) { __ic_line_inv_vaddr(paddr, vaddr, PAGE_SIZE); } @@ -605,7 +784,7 @@ void __inv_icache_page(unsigned long paddr, unsigned long vaddr) * wrapper to clearout kernel or userspace mappings of a page * For kernel mappings @vaddr == @paddr */ -void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr) +void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr) { __dc_line_op(paddr, vaddr & PAGE_MASK, PAGE_SIZE, OP_FLUSH_N_INV); } @@ -637,7 +816,7 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, u_vaddr &= PAGE_MASK; - ___flush_dcache_page(paddr, u_vaddr); + __flush_dcache_page(paddr, u_vaddr); if (vma->vm_flags & VM_EXEC) __inv_icache_page(paddr, u_vaddr); @@ -663,8 +842,8 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, void copy_user_highpage(struct page *to, struct page *from, unsigned long u_vaddr, struct vm_area_struct *vma) { - void *kfrom = page_address(from); - void *kto = page_address(to); + void *kfrom = kmap_atomic(from); + void *kto = kmap_atomic(to); int clean_src_k_mappings = 0; /* @@ -674,9 +853,12 @@ void copy_user_highpage(struct page *to, struct page *from, * * Note that while @u_vaddr refers to DST page's userspace vaddr, it is * equally valid for SRC page as well + * + * For !VIPT cache, all of this gets compiled out as + * addr_not_cache_congruent() is 0 */ if (page_mapped(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { - __flush_dcache_page(kfrom, u_vaddr); + __flush_dcache_page((unsigned long)kfrom, u_vaddr); clean_src_k_mappings = 1; } @@ -697,11 +879,14 @@ void copy_user_highpage(struct page *to, struct page *from, * sync the kernel mapping back to physical page */ if (clean_src_k_mappings) { - __flush_dcache_page(kfrom, kfrom); + __flush_dcache_page((unsigned long)kfrom, (unsigned long)kfrom); set_bit(PG_dc_clean, &from->flags); } else { clear_bit(PG_dc_clean, &from->flags); } + + kunmap_atomic(kto); + kunmap_atomic(kfrom); } void clear_user_page(void *to, unsigned long u_vaddr, struct page *page) @@ -721,3 +906,93 @@ SYSCALL_DEFINE3(cacheflush, uint32_t, start, uint32_t, sz, uint32_t, flags) flush_cache_all(); return 0; } + +void arc_cache_init(void) +{ + unsigned int __maybe_unused cpu = smp_processor_id(); + char str[256]; + + printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { + struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; + + if (!ic->ver) + panic("cache support enabled but non-existent cache\n"); + + if (ic->line_len != L1_CACHE_BYTES) + panic("ICache line [%d] != kernel Config [%d]", + ic->line_len, L1_CACHE_BYTES); + + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver [%d] doesn't match MMU ver [%d]\n", + ic->ver, CONFIG_ARC_MMU_VER); + + /* + * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG + * pair to provide vaddr/paddr respectively, just as in MMU v3 + */ + if (is_isa_arcv2() && ic->alias) + _cache_line_loop_ic_fn = __cache_line_loop_v3; + else + _cache_line_loop_ic_fn = __cache_line_loop; + } + + if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) { + struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; + + if (!dc->ver) + panic("cache support enabled but non-existent cache\n"); + + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); + + /* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */ + if (is_isa_arcompact()) { + int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); + + if (dc->alias && !handled) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dc->alias && handled) + panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } + } + + if (is_isa_arcv2() && l2_line_sz && !slc_enable) { + + /* IM set : flush before invalidate */ + write_aux_reg(ARC_REG_SLC_CTRL, + read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_IM); + + write_aux_reg(ARC_REG_SLC_INVALIDATE, 1); + + /* Important to wait for flush to complete */ + while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY); + write_aux_reg(ARC_REG_SLC_CTRL, + read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE); + } + + if (is_isa_arcv2() && ioc_exists) { + /* IO coherency base - 0x8z */ + write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000); + /* IO coherency aperture size - 512Mb: 0x8z-0xAz */ + write_aux_reg(ARC_REG_IO_COH_AP0_SIZE, 0x11); + /* Enable partial writes */ + write_aux_reg(ARC_REG_IO_COH_PARTIAL, 1); + /* Enable IO coherency */ + write_aux_reg(ARC_REG_IO_COH_ENABLE, 1); + + __dma_cache_wback_inv = __dma_cache_wback_inv_ioc; + __dma_cache_inv = __dma_cache_inv_ioc; + __dma_cache_wback = __dma_cache_wback_ioc; + } else if (is_isa_arcv2() && l2_line_sz && slc_enable) { + __dma_cache_wback_inv = __dma_cache_wback_inv_slc; + __dma_cache_inv = __dma_cache_inv_slc; + __dma_cache_wback = __dma_cache_wback_slc; + } else { + __dma_cache_wback_inv = __dma_cache_wback_inv_l1; + __dma_cache_inv = __dma_cache_inv_l1; + __dma_cache_wback = __dma_cache_wback_l1; + } +} diff --git a/kernel/arch/arc/mm/dma.c b/kernel/arch/arc/mm/dma.c index 12cc6485b..29a46bb19 100644 --- a/kernel/arch/arc/mm/dma.c +++ b/kernel/arch/arc/mm/dma.c @@ -14,13 +14,12 @@ * Cache bit off in the TLB entry. * * The default DMA address == Phy address which is 0x8000_0000 based. - * A platform/device can make it zero based, by over-riding - * plat_{dma,kernel}_addr_to_{kernel,dma} */ #include <linux/dma-mapping.h> #include <linux/dma-debug.h> #include <linux/export.h> +#include <asm/cache.h> #include <asm/cacheflush.h> /* @@ -37,7 +36,7 @@ void *dma_alloc_noncoherent(struct device *dev, size_t size, return NULL; /* This is bus address, platform dependent */ - *dma_handle = plat_kernel_addr_to_dma(dev, paddr); + *dma_handle = (dma_addr_t)paddr; return paddr; } @@ -46,8 +45,7 @@ EXPORT_SYMBOL(dma_alloc_noncoherent); void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) { - free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle), - size); + free_pages_exact((void *)dma_handle, size); } EXPORT_SYMBOL(dma_free_noncoherent); @@ -56,6 +54,20 @@ void *dma_alloc_coherent(struct device *dev, size_t size, { void *paddr, *kvaddr; + /* + * IOC relies on all data (even coherent DMA data) being in cache + * Thus allocate normal cached memory + * + * The gains with IOC are two pronged: + * -For streaming data, elides needs for cache maintenance, saving + * cycles in flush code, and bus bandwidth as all the lines of a + * buffer need to be flushed out to memory + * -For coherent data, Read/Write to buffers terminate early in cache + * (vs. always going to memory - thus are faster) + */ + if (is_isa_arcv2() && ioc_exists) + return dma_alloc_noncoherent(dev, size, dma_handle, gfp); + /* This is linear addr (0x8000_0000 based) */ paddr = alloc_pages_exact(size, gfp); if (!paddr) @@ -63,11 +75,23 @@ void *dma_alloc_coherent(struct device *dev, size_t size, /* This is kernel Virtual address (0x7000_0000 based) */ kvaddr = ioremap_nocache((unsigned long)paddr, size); - if (kvaddr != NULL) - memset(kvaddr, 0, size); + if (kvaddr == NULL) + return NULL; /* This is bus address, platform dependent */ - *dma_handle = plat_kernel_addr_to_dma(dev, paddr); + *dma_handle = (dma_addr_t)paddr; + + /* + * Evict any existing L1 and/or L2 lines for the backing page + * in case it was used earlier as a normal "cached" page. + * Yeah this bit us - STAR 9000898266 + * + * Although core does call flush_cache_vmap(), it gets kvaddr hence + * can't be used to efficiently flush L1 and/or L2 which need paddr + * Currently flush_cache_vmap nukes the L1 cache completely which + * will be optimized as a separate commit + */ + dma_cache_wback_inv((unsigned long)paddr, size); return kvaddr; } @@ -76,10 +100,12 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *dev, size_t size, void *kvaddr, dma_addr_t dma_handle) { + if (is_isa_arcv2() && ioc_exists) + return dma_free_noncoherent(dev, size, kvaddr, dma_handle); + iounmap((void __force __iomem *)kvaddr); - free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle), - size); + free_pages_exact((void *)dma_handle, size); } EXPORT_SYMBOL(dma_free_coherent); diff --git a/kernel/arch/arc/mm/fault.c b/kernel/arch/arc/mm/fault.c index d948e4e9d..af63f4a13 100644 --- a/kernel/arch/arc/mm/fault.c +++ b/kernel/arch/arc/mm/fault.c @@ -18,7 +18,14 @@ #include <asm/pgalloc.h> #include <asm/mmu.h> -static int handle_vmalloc_fault(unsigned long address) +/* + * kernel virtual address is required to implement vmalloc/pkmap/fixmap + * Refer to asm/processor.h for System Memory Map + * + * It simply copies the PMD entry (pointer to 2nd level page table or hugepage) + * from swapper pgdir to task pgdir. The 2nd level table/page is thus shared + */ +noinline static int handle_kernel_vaddr_fault(unsigned long address) { /* * Synchronize this task's top level page-table @@ -72,8 +79,8 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) * only copy the information from the master page table, * nothing more. */ - if (address >= VMALLOC_START && address <= VMALLOC_END) { - ret = handle_vmalloc_fault(address); + if (address >= VMALLOC_START) { + ret = handle_kernel_vaddr_fault(address); if (unlikely(ret)) goto bad_area_nosemaphore; else diff --git a/kernel/arch/arc/mm/highmem.c b/kernel/arch/arc/mm/highmem.c new file mode 100644 index 000000000..92dd92cad --- /dev/null +++ b/kernel/arch/arc/mm/highmem.c @@ -0,0 +1,140 @@ +/* + * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/bootmem.h> +#include <linux/export.h> +#include <linux/highmem.h> +#include <asm/processor.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> + +/* + * HIGHMEM API: + * + * kmap() API provides sleep semantics hence refered to as "permanent maps" + * It allows mapping LAST_PKMAP pages, using @last_pkmap_nr as the cursor + * for book-keeping + * + * kmap_atomic() can't sleep (calls pagefault_disable()), thus it provides + * shortlived ala "temporary mappings" which historically were implemented as + * fixmaps (compile time addr etc). Their book-keeping is done per cpu. + * + * Both these facts combined (preemption disabled and per-cpu allocation) + * means the total number of concurrent fixmaps will be limited to max + * such allocations in a single control path. Thus KM_TYPE_NR (another + * historic relic) is a small'ish number which caps max percpu fixmaps + * + * ARC HIGHMEM Details + * + * - the kernel vaddr space from 0x7z to 0x8z (currently used by vmalloc/module) + * is now shared between vmalloc and kmap (non overlapping though) + * + * - Both fixmap/pkmap use a dedicated page table each, hooked up to swapper PGD + * This means each only has 1 PGDIR_SIZE worth of kvaddr mappings, which means + * 2M of kvaddr space for typical config (8K page and 11:8:13 traversal split) + * + * - fixmap anyhow needs a limited number of mappings. So 2M kvaddr == 256 PTE + * slots across NR_CPUS would be more than sufficient (generic code defines + * KM_TYPE_NR as 20). + * + * - pkmap being preemptible, in theory could do with more than 256 concurrent + * mappings. However, generic pkmap code: map_new_virtual(), doesn't traverse + * the PGD and only works with a single page table @pkmap_page_table, hence + * sets the limit + */ + +extern pte_t * pkmap_page_table; +static pte_t * fixmap_page_table; + +void *kmap(struct page *page) +{ + BUG_ON(in_interrupt()); + if (!PageHighMem(page)) + return page_address(page); + + return kmap_high(page); +} + +void *kmap_atomic(struct page *page) +{ + int idx, cpu_idx; + unsigned long vaddr; + + preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + + cpu_idx = kmap_atomic_idx_push(); + idx = cpu_idx + KM_TYPE_NR * smp_processor_id(); + vaddr = FIXMAP_ADDR(idx); + + set_pte_at(&init_mm, vaddr, fixmap_page_table + idx, + mk_pte(page, kmap_prot)); + + return (void *)vaddr; +} +EXPORT_SYMBOL(kmap_atomic); + +void __kunmap_atomic(void *kv) +{ + unsigned long kvaddr = (unsigned long)kv; + + if (kvaddr >= FIXMAP_BASE && kvaddr < (FIXMAP_BASE + FIXMAP_SIZE)) { + + /* + * Because preemption is disabled, this vaddr can be associated + * with the current allocated index. + * But in case of multiple live kmap_atomic(), it still relies on + * callers to unmap in right order. + */ + int cpu_idx = kmap_atomic_idx(); + int idx = cpu_idx + KM_TYPE_NR * smp_processor_id(); + + WARN_ON(kvaddr != FIXMAP_ADDR(idx)); + + pte_clear(&init_mm, kvaddr, fixmap_page_table + idx); + local_flush_tlb_kernel_range(kvaddr, kvaddr + PAGE_SIZE); + + kmap_atomic_idx_pop(); + } + + pagefault_enable(); + preempt_enable(); +} +EXPORT_SYMBOL(__kunmap_atomic); + +static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr) +{ + pgd_t *pgd_k; + pud_t *pud_k; + pmd_t *pmd_k; + pte_t *pte_k; + + pgd_k = pgd_offset_k(kvaddr); + pud_k = pud_offset(pgd_k, kvaddr); + pmd_k = pmd_offset(pud_k, kvaddr); + + pte_k = (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); + pmd_populate_kernel(&init_mm, pmd_k, pte_k); + return pte_k; +} + +void __init kmap_init(void) +{ + /* Due to recursive include hell, we can't do this in processor.h */ + BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE)); + + BUILD_BUG_ON(KM_TYPE_NR > PTRS_PER_PTE); + pkmap_page_table = alloc_kmap_pgtable(PKMAP_BASE); + + BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE); + fixmap_page_table = alloc_kmap_pgtable(FIXMAP_BASE); +} diff --git a/kernel/arch/arc/mm/init.c b/kernel/arch/arc/mm/init.c index d44eedd8c..7d2c4fbf4 100644 --- a/kernel/arch/arc/mm/init.c +++ b/kernel/arch/arc/mm/init.c @@ -15,6 +15,7 @@ #endif #include <linux/swap.h> #include <linux/module.h> +#include <linux/highmem.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/sections.h> @@ -24,16 +25,22 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE); char empty_zero_page[PAGE_SIZE] __aligned(PAGE_SIZE); EXPORT_SYMBOL(empty_zero_page); -/* Default tot mem from .config */ -static unsigned long arc_mem_sz = 0x20000000; /* some default */ +static const unsigned long low_mem_start = CONFIG_LINUX_LINK_BASE; +static unsigned long low_mem_sz; + +#ifdef CONFIG_HIGHMEM +static unsigned long min_high_pfn; +static u64 high_mem_start; +static u64 high_mem_sz; +#endif /* User can over-ride above with "mem=nnn[KkMm]" in cmdline */ static int __init setup_mem_sz(char *str) { - arc_mem_sz = memparse(str, NULL) & PAGE_MASK; + low_mem_sz = memparse(str, NULL) & PAGE_MASK; /* early console might not be setup yet - it will show up later */ - pr_info("\"mem=%s\": mem sz set to %ldM\n", str, TO_MB(arc_mem_sz)); + pr_info("\"mem=%s\": mem sz set to %ldM\n", str, TO_MB(low_mem_sz)); return 0; } @@ -41,8 +48,24 @@ early_param("mem", setup_mem_sz); void __init early_init_dt_add_memory_arch(u64 base, u64 size) { - arc_mem_sz = size & PAGE_MASK; - pr_info("Memory size set via devicetree %ldM\n", TO_MB(arc_mem_sz)); + int in_use = 0; + + if (!low_mem_sz) { + if (base != low_mem_start) + panic("CONFIG_LINUX_LINK_BASE != DT memory { }"); + + low_mem_sz = size; + in_use = 1; + } else { +#ifdef CONFIG_HIGHMEM + high_mem_start = base; + high_mem_sz = size; + in_use = 1; +#endif + } + + pr_info("Memory @ %llx [%lldM] %s\n", + base, TO_MB(size), !in_use ? "Not used":""); } #ifdef CONFIG_BLK_DEV_INITRD @@ -72,46 +95,62 @@ early_param("initrd", early_initrd); void __init setup_arch_memory(void) { unsigned long zones_size[MAX_NR_ZONES]; - unsigned long end_mem = CONFIG_LINUX_LINK_BASE + arc_mem_sz; + unsigned long zones_holes[MAX_NR_ZONES]; init_mm.start_code = (unsigned long)_text; init_mm.end_code = (unsigned long)_etext; init_mm.end_data = (unsigned long)_edata; init_mm.brk = (unsigned long)_end; - /* - * We do it here, so that memory is correctly instantiated - * even if "mem=xxx" cmline over-ride is given and/or - * DT has memory node. Each causes an update to @arc_mem_sz - * and we finally add memory one here - */ - memblock_add(CONFIG_LINUX_LINK_BASE, arc_mem_sz); - - /*------------- externs in mm need setting up ---------------*/ - /* first page of system - kernel .vector starts here */ min_low_pfn = ARCH_PFN_OFFSET; - /* Last usable page of low mem (no HIGHMEM yet for ARC port) */ - max_low_pfn = max_pfn = PFN_DOWN(end_mem); + /* Last usable page of low mem */ + max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz); - max_mapnr = max_low_pfn - min_low_pfn; +#ifdef CONFIG_HIGHMEM + min_high_pfn = PFN_DOWN(high_mem_start); + max_pfn = PFN_DOWN(high_mem_start + high_mem_sz); +#endif + + max_mapnr = max_pfn - min_low_pfn; - /*------------- reserve kernel image -----------------------*/ - memblock_reserve(CONFIG_LINUX_LINK_BASE, - __pa(_end) - CONFIG_LINUX_LINK_BASE); + /*------------- bootmem allocator setup -----------------------*/ + + /* + * seed the bootmem allocator after any DT memory node parsing or + * "mem=xxx" cmdline overrides have potentially updated @arc_mem_sz + * + * Only low mem is added, otherwise we have crashes when allocating + * mem_map[] itself. NO_BOOTMEM allocates mem_map[] at the end of + * avail memory, ending in highmem with a > 32-bit address. However + * it then tries to memset it with a truncaed 32-bit handle, causing + * the crash + */ + + memblock_add(low_mem_start, low_mem_sz); + memblock_reserve(low_mem_start, __pa(_end) - low_mem_start); #ifdef CONFIG_BLK_DEV_INITRD - /*------------- reserve initrd image -----------------------*/ if (initrd_start) memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); #endif memblock_dump_all(); - /*-------------- node setup --------------------------------*/ + /*----------------- node/zones setup --------------------------*/ memset(zones_size, 0, sizeof(zones_size)); - zones_size[ZONE_NORMAL] = max_mapnr; + memset(zones_holes, 0, sizeof(zones_holes)); + + zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn; + zones_holes[ZONE_NORMAL] = 0; + +#ifdef CONFIG_HIGHMEM + zones_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn; + + /* This handles the peripheral address space hole */ + zones_holes[ZONE_HIGHMEM] = min_high_pfn - max_low_pfn; +#endif /* * We can't use the helper free_area_init(zones[]) because it uses @@ -122,9 +161,12 @@ void __init setup_arch_memory(void) free_area_init_node(0, /* node-id */ zones_size, /* num pages per zone */ min_low_pfn, /* first pfn of node */ - NULL); /* NO holes */ + zones_holes); /* holes */ - high_memory = (void *)end_mem; +#ifdef CONFIG_HIGHMEM + high_memory = (void *)(min_high_pfn << PAGE_SHIFT); + kmap_init(); +#endif } /* @@ -135,6 +177,14 @@ void __init setup_arch_memory(void) */ void __init mem_init(void) { +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + reset_all_zones_managed_pages(); + for (tmp = min_high_pfn; tmp < max_pfn; tmp++) + free_highmem_page(pfn_to_page(tmp)); +#endif + free_all_bootmem(); mem_init_print_info(NULL); } diff --git a/kernel/arch/arc/mm/tlb.c b/kernel/arch/arc/mm/tlb.c index 7f47d2a56..daf2bf52b 100644 --- a/kernel/arch/arc/mm/tlb.c +++ b/kernel/arch/arc/mm/tlb.c @@ -109,10 +109,16 @@ DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE; static inline void __tlb_entry_erase(void) { write_aux_reg(ARC_REG_TLBPD1, 0); + + if (is_pae40_enabled()) + write_aux_reg(ARC_REG_TLBPD1HI, 0); + write_aux_reg(ARC_REG_TLBPD0, 0); write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); } +#if (CONFIG_ARC_MMU_VER < 4) + static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid) { unsigned int idx; @@ -180,7 +186,7 @@ static void utlb_invalidate(void) } -static void tlb_entry_insert(unsigned int pd0, unsigned int pd1) +static void tlb_entry_insert(unsigned int pd0, pte_t pd1) { unsigned int idx; @@ -210,28 +216,71 @@ static void tlb_entry_insert(unsigned int pd0, unsigned int pd1) write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); } +#else /* CONFIG_ARC_MMU_VER >= 4) */ + +static void utlb_invalidate(void) +{ + /* No need since uTLB is always in sync with JTLB */ +} + +static void tlb_entry_erase(unsigned int vaddr_n_asid) +{ + write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid | _PAGE_PRESENT); + write_aux_reg(ARC_REG_TLBCOMMAND, TLBDeleteEntry); +} + +static void tlb_entry_insert(unsigned int pd0, pte_t pd1) +{ + write_aux_reg(ARC_REG_TLBPD0, pd0); + write_aux_reg(ARC_REG_TLBPD1, pd1); + + if (is_pae40_enabled()) + write_aux_reg(ARC_REG_TLBPD1HI, (u64)pd1 >> 32); + + write_aux_reg(ARC_REG_TLBCOMMAND, TLBInsertEntry); +} + +#endif + /* * Un-conditionally (without lookup) erase the entire MMU contents */ noinline void local_flush_tlb_all(void) { + struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; unsigned long flags; unsigned int entry; - struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; + int num_tlb = mmu->sets * mmu->ways; local_irq_save(flags); /* Load PD0 and PD1 with template for a Blank Entry */ write_aux_reg(ARC_REG_TLBPD1, 0); + + if (is_pae40_enabled()) + write_aux_reg(ARC_REG_TLBPD1HI, 0); + write_aux_reg(ARC_REG_TLBPD0, 0); - for (entry = 0; entry < mmu->num_tlb; entry++) { + for (entry = 0; entry < num_tlb; entry++) { /* write this entry to the TLB */ write_aux_reg(ARC_REG_TLBINDEX, entry); write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); } + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + const int stlb_idx = 0x800; + + /* Blank sTLB entry */ + write_aux_reg(ARC_REG_TLBPD0, _PAGE_HW_SZ); + + for (entry = stlb_idx; entry < stlb_idx + 16; entry++) { + write_aux_reg(ARC_REG_TLBINDEX, entry); + write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); + } + } + utlb_invalidate(); local_irq_restore(flags); @@ -385,6 +434,15 @@ static inline void ipi_flush_tlb_range(void *arg) local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void ipi_flush_pmd_tlb_range(void *arg) +{ + struct tlb_args *ta = arg; + + local_flush_pmd_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end); +} +#endif + static inline void ipi_flush_tlb_kernel_range(void *arg) { struct tlb_args *ta = (struct tlb_args *)arg; @@ -425,6 +483,20 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range, &ta, 1); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + struct tlb_args ta = { + .ta_vma = vma, + .ta_start = start, + .ta_end = end + }; + + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_pmd_tlb_range, &ta, 1); +} +#endif + void flush_tlb_kernel_range(unsigned long start, unsigned long end) { struct tlb_args ta = { @@ -439,11 +511,12 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) /* * Routine to create a TLB entry */ -void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +void create_tlb(struct vm_area_struct *vma, unsigned long vaddr, pte_t *ptep) { unsigned long flags; unsigned int asid_or_sasid, rwx; - unsigned long pd0, pd1; + unsigned long pd0; + pte_t pd1; /* * create_tlb() assumes that current->mm == vma->mm, since @@ -475,9 +548,9 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) local_irq_save(flags); - tlb_paranoid_check(asid_mm(vma->vm_mm, smp_processor_id()), address); + tlb_paranoid_check(asid_mm(vma->vm_mm, smp_processor_id()), vaddr); - address &= PAGE_MASK; + vaddr &= PAGE_MASK; /* update this PTE credentials */ pte_val(*ptep) |= (_PAGE_PRESENT | _PAGE_ACCESSED); @@ -487,7 +560,7 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) /* ASID for this task */ asid_or_sasid = read_aux_reg(ARC_REG_PID) & 0xff; - pd0 = address | asid_or_sasid | (pte_val(*ptep) & PTE_BITS_IN_PD0); + pd0 = vaddr | asid_or_sasid | (pte_val(*ptep) & PTE_BITS_IN_PD0); /* * ARC MMU provides fully orthogonal access bits for K/U mode, @@ -523,7 +596,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, pte_t *ptep) { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; - unsigned long paddr = pte_val(*ptep) & PAGE_MASK; + phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK; struct page *page = pfn_to_page(pte_pfn(*ptep)); create_tlb(vma, vaddr, ptep); @@ -546,16 +619,105 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, int dirty = !test_and_set_bit(PG_dc_clean, &page->flags); if (dirty) { - /* wback + inv dcache lines */ + /* wback + inv dcache lines (K-mapping) */ __flush_dcache_page(paddr, paddr); - /* invalidate any existing icache lines */ + /* invalidate any existing icache lines (U-mapping) */ if (vma->vm_flags & VM_EXEC) __inv_icache_page(paddr, vaddr); } } } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +/* + * MMUv4 in HS38x cores supports Super Pages which are basis for Linux THP + * support. + * + * Normal and Super pages can co-exist (ofcourse not overlap) in TLB with a + * new bit "SZ" in TLB page desciptor to distinguish between them. + * Super Page size is configurable in hardware (4K to 16M), but fixed once + * RTL builds. + * + * The exact THP size a Linx configuration will support is a function of: + * - MMU page size (typical 8K, RTL fixed) + * - software page walker address split between PGD:PTE:PFN (typical + * 11:8:13, but can be changed with 1 line) + * So for above default, THP size supported is 8K * (2^8) = 2M + * + * Default Page Walker is 2 levels, PGD:PTE:PFN, which in THP regime + * reduces to 1 level (as PTE is folded into PGD and canonically referred + * to as PMD). + * Thus THP PMD accessors are implemented in terms of PTE (just like sparc) + */ + +void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd) +{ + pte_t pte = __pte(pmd_val(*pmd)); + update_mmu_cache(vma, addr, &pte); +} + +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) +{ + struct list_head *lh = (struct list_head *) pgtable; + + assert_spin_locked(&mm->page_table_lock); + + /* FIFO */ + if (!pmd_huge_pte(mm, pmdp)) + INIT_LIST_HEAD(lh); + else + list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp)); + pmd_huge_pte(mm, pmdp) = pgtable; +} + +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) +{ + struct list_head *lh; + pgtable_t pgtable; + + assert_spin_locked(&mm->page_table_lock); + + pgtable = pmd_huge_pte(mm, pmdp); + lh = (struct list_head *) pgtable; + if (list_empty(lh)) + pmd_huge_pte(mm, pmdp) = NULL; + else { + pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next; + list_del(lh); + } + + pte_val(pgtable[0]) = 0; + pte_val(pgtable[1]) = 0; + + return pgtable; +} + +void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + unsigned int cpu; + unsigned long flags; + + local_irq_save(flags); + + cpu = smp_processor_id(); + + if (likely(asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID)) { + unsigned int asid = hw_pid(vma->vm_mm, cpu); + + /* No need to loop here: this will always be for 1 Huge Page */ + tlb_entry_erase(start | _PAGE_HW_SZ | asid); + } + + local_irq_restore(flags); +} + +#endif + /* Read the Cache Build Confuration Registers, Decode them and save into * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs @@ -574,47 +736,73 @@ void read_decode_mmu_bcr(void) struct bcr_mmu_3 { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, pg_sz:4, + unsigned int ver:8, ways:4, sets:4, res:3, sasid:1, pg_sz:4, u_itlb:4, u_dtlb:4; #else - unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, reserv:3, osm:1, sets:4, + unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, sasid:1, res:3, sets:4, ways:4, ver:8; #endif } *mmu3; + struct bcr_mmu_4 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int ver:8, sasid:1, sz1:4, sz0:4, res:2, pae:1, + n_ways:2, n_entry:2, n_super:2, u_itlb:3, u_dtlb:3; +#else + /* DTLB ITLB JES JE JA */ + unsigned int u_dtlb:3, u_itlb:3, n_super:2, n_entry:2, n_ways:2, + pae:1, res:2, sz0:4, sz1:4, sasid:1, ver:8; +#endif + } *mmu4; + tmp = read_aux_reg(ARC_REG_MMU_BCR); mmu->ver = (tmp >> 24); if (mmu->ver <= 2) { mmu2 = (struct bcr_mmu_1_2 *)&tmp; - mmu->pg_sz = PAGE_SIZE; + mmu->pg_sz_k = TO_KB(0x2000); mmu->sets = 1 << mmu2->sets; mmu->ways = 1 << mmu2->ways; mmu->u_dtlb = mmu2->u_dtlb; mmu->u_itlb = mmu2->u_itlb; - } else { + } else if (mmu->ver == 3) { mmu3 = (struct bcr_mmu_3 *)&tmp; - mmu->pg_sz = 512 << mmu3->pg_sz; + mmu->pg_sz_k = 1 << (mmu3->pg_sz - 1); mmu->sets = 1 << mmu3->sets; mmu->ways = 1 << mmu3->ways; mmu->u_dtlb = mmu3->u_dtlb; mmu->u_itlb = mmu3->u_itlb; + mmu->sasid = mmu3->sasid; + } else { + mmu4 = (struct bcr_mmu_4 *)&tmp; + mmu->pg_sz_k = 1 << (mmu4->sz0 - 1); + mmu->s_pg_sz_m = 1 << (mmu4->sz1 - 11); + mmu->sets = 64 << mmu4->n_entry; + mmu->ways = mmu4->n_ways * 2; + mmu->u_dtlb = mmu4->u_dtlb * 4; + mmu->u_itlb = mmu4->u_itlb * 4; + mmu->sasid = mmu4->sasid; + mmu->pae = mmu4->pae; } - - mmu->num_tlb = mmu->sets * mmu->ways; } char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; struct cpuinfo_arc_mmu *p_mmu = &cpuinfo_arc700[cpu_id].mmu; + char super_pg[64] = ""; + + if (p_mmu->s_pg_sz_m) + scnprintf(super_pg, 64, "%dM Super Page%s, ", + p_mmu->s_pg_sz_m, + IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE)); n += scnprintf(buf + n, len - n, - "MMU [v%x]\t: %dk PAGE, JTLB %d (%dx%d), uDTLB %d, uITLB %d %s\n", - p_mmu->ver, TO_KB(p_mmu->pg_sz), - p_mmu->num_tlb, p_mmu->sets, p_mmu->ways, + "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n", + p_mmu->ver, p_mmu->pg_sz_k, super_pg, + p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways, p_mmu->u_dtlb, p_mmu->u_itlb, - IS_ENABLED(CONFIG_ARC_MMU_SASID) ? ",SASID" : ""); + IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40)); return buf; } @@ -639,9 +827,17 @@ void arc_mmu_init(void) mmu->ver, CONFIG_ARC_MMU_VER); } - if (mmu->pg_sz != PAGE_SIZE) + if (mmu->pg_sz_k != TO_KB(PAGE_SIZE)) panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE)); + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + mmu->s_pg_sz_m != TO_MB(HPAGE_PMD_SIZE)) + panic("MMU Super pg size != Linux HPAGE_PMD_SIZE (%luM)\n", + (unsigned long)TO_MB(HPAGE_PMD_SIZE)); + + if (IS_ENABLED(CONFIG_ARC_HAS_PAE40) && !mmu->pae) + panic("Hardware doesn't support PAE40\n"); + /* Enable the MMU */ write_aux_reg(ARC_REG_PID, MMU_ENABLE); @@ -677,15 +873,15 @@ void arc_mmu_init(void) * the duplicate one. * -Knob to be verbose abt it.(TODO: hook them up to debugfs) */ -volatile int dup_pd_verbose = 1;/* Be slient abt it or complain (default) */ +volatile int dup_pd_silent; /* Be slient abt it or complain (default) */ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) { - int set, way, n; - unsigned long flags, is_valid; struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; - unsigned int pd0[mmu->ways], pd1[mmu->ways]; + unsigned int pd0[mmu->ways]; + unsigned long flags; + int set; local_irq_save(flags); @@ -695,14 +891,16 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /* loop thru all sets of TLB */ for (set = 0; set < mmu->sets; set++) { + int is_valid, way; + /* read out all the ways of current set */ for (way = 0, is_valid = 0; way < mmu->ways; way++) { write_aux_reg(ARC_REG_TLBINDEX, SET_WAY_TO_IDX(mmu, set, way)); write_aux_reg(ARC_REG_TLBCOMMAND, TLBRead); pd0[way] = read_aux_reg(ARC_REG_TLBPD0); - pd1[way] = read_aux_reg(ARC_REG_TLBPD1); is_valid |= pd0[way] & _PAGE_PRESENT; + pd0[way] &= PAGE_MASK; } /* If all the WAYS in SET are empty, skip to next SET */ @@ -711,30 +909,28 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /* Scan the set for duplicate ways: needs a nested loop */ for (way = 0; way < mmu->ways - 1; way++) { + + int n; + if (!pd0[way]) continue; for (n = way + 1; n < mmu->ways; n++) { - if ((pd0[way] & PAGE_MASK) == - (pd0[n] & PAGE_MASK)) { - - if (dup_pd_verbose) { - pr_info("Duplicate PD's @" - "[%d:%d]/[%d:%d]\n", - set, way, set, n); - pr_info("TLBPD0[%u]: %08x\n", - way, pd0[way]); - } - - /* - * clear entry @way and not @n. This is - * critical to our optimised loop - */ - pd0[way] = pd1[way] = 0; - write_aux_reg(ARC_REG_TLBINDEX, + if (pd0[way] != pd0[n]) + continue; + + if (!dup_pd_silent) + pr_info("Dup TLB PD0 %08x @ set %d ways %d,%d\n", + pd0[way], set, way, n); + + /* + * clear entry @way and not @n. + * This is critical to our optimised loop + */ + pd0[way] = 0; + write_aux_reg(ARC_REG_TLBINDEX, SET_WAY_TO_IDX(mmu, set, way)); - __tlb_entry_erase(); - } + __tlb_entry_erase(); } } } diff --git a/kernel/arch/arc/mm/tlbex.S b/kernel/arch/arc/mm/tlbex.S index d572f1c2c..f1967eeb3 100644 --- a/kernel/arch/arc/mm/tlbex.S +++ b/kernel/arch/arc/mm/tlbex.S @@ -35,8 +35,6 @@ * Rahul Trivedi, Amit Bhor: Codito Technologies 2004 */ - .cpu A7 - #include <linux/linkage.h> #include <asm/entry.h> #include <asm/mmu.h> @@ -46,6 +44,7 @@ #include <asm/processor.h> #include <asm/tlb-mmu1.h> +#ifdef CONFIG_ISA_ARCOMPACT ;----------------------------------------------------------------- ; ARC700 Exception Handling doesn't auto-switch stack and it only provides ; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0" @@ -89,7 +88,7 @@ ex_saved_reg1: #ifdef CONFIG_SMP sr r0, [ARC_REG_SCRATCH_DATA0] ; freeup r0 to code with GET_CPU_ID r0 ; get to per cpu scratch mem, - lsl r0, r0, L1_CACHE_SHIFT ; cache line wide per cpu + asl r0, r0, L1_CACHE_SHIFT ; cache line wide per cpu add r0, @ex_saved_reg1, r0 #else st r0, [@ex_saved_reg1] @@ -108,7 +107,7 @@ ex_saved_reg1: .macro TLBMISS_RESTORE_REGS #ifdef CONFIG_SMP GET_CPU_ID r0 ; get to per cpu scratch mem - lsl r0, r0, L1_CACHE_SHIFT ; each is cache line wide + asl r0, r0, L1_CACHE_SHIFT ; each is cache line wide add r0, @ex_saved_reg1, r0 ld_s r3, [r0,12] ld_s r2, [r0, 8] @@ -123,6 +122,24 @@ ex_saved_reg1: #endif .endm +#else /* ARCv2 */ + +.macro TLBMISS_FREEUP_REGS + PUSH r0 + PUSH r1 + PUSH r2 + PUSH r3 +.endm + +.macro TLBMISS_RESTORE_REGS + POP r3 + POP r2 + POP r1 + POP r0 +.endm + +#endif + ;============================================================================ ; Troubleshooting Stuff ;============================================================================ @@ -188,20 +205,38 @@ ex_saved_reg1: #endif lsr r0, r2, PGDIR_SHIFT ; Bits for indexing into PGD - ld.as r1, [r1, r0] ; PGD entry corresp to faulting addr - and.f r1, r1, PAGE_MASK ; Ignoring protection and other flags - ; contains Ptr to Page Table - bz.d do_slow_path_pf ; if no Page Table, do page fault + ld.as r3, [r1, r0] ; PGD entry corresp to faulting addr + tst r3, r3 + bz do_slow_path_pf ; if no Page Table, do page fault + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + and.f 0, r3, _PAGE_HW_SZ ; Is this Huge PMD (thp) + add2.nz r1, r1, r0 + bnz.d 2f ; YES: PGD == PMD has THP PTE: stop pgd walk + mov.nz r0, r3 + +#endif + and r1, r3, PAGE_MASK ; Get the PTE entry: The idea is ; (1) x = addr >> PAGE_SHIFT -> masks page-off bits from @fault-addr ; (2) y = x & (PTRS_PER_PTE - 1) -> to get index - ; (3) z = pgtbl[y] - ; To avoid the multiply by in end, we do the -2, <<2 below + ; (3) z = (pgtbl + y * 4) + +#ifdef CONFIG_ARC_HAS_PAE40 +#define PTE_SIZE_LOG 3 /* 8 == 2 ^ 3 */ +#else +#define PTE_SIZE_LOG 2 /* 4 == 2 ^ 2 */ +#endif + + ; multiply in step (3) above avoided by shifting lesser in step (1) + lsr r0, r2, ( PAGE_SHIFT - PTE_SIZE_LOG ) + and r0, r0, ( (PTRS_PER_PTE - 1) << PTE_SIZE_LOG ) + ld.aw r0, [r1, r0] ; r0: PTE (lower word only for PAE40) + ; r1: PTE ptr + +2: - lsr r0, r2, (PAGE_SHIFT - 2) - and r0, r0, ( (PTRS_PER_PTE - 1) << 2) - ld.aw r0, [r1, r0] ; get PTE and PTE ptr for fault addr #ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT and.f 0, r0, _PAGE_PRESENT bz 1f @@ -216,18 +251,23 @@ ex_saved_reg1: ;----------------------------------------------------------------- ; Convert Linux PTE entry into TLB entry ; A one-word PTE entry is programmed as two-word TLB Entry [PD0:PD1] in mmu +; (for PAE40, two-words PTE, while three-word TLB Entry [PD0:PD1:PD1HI]) ; IN: r0 = PTE, r1 = ptr to PTE .macro CONV_PTE_TO_TLB - and r3, r0, PTE_BITS_RWX ; r w x - lsl r2, r3, 3 ; r w x 0 0 0 (GLOBAL, kernel only) + and r3, r0, PTE_BITS_RWX ; r w x + asl r2, r3, 3 ; Kr Kw Kx 0 0 0 (GLOBAL, kernel only) and.f 0, r0, _PAGE_GLOBAL - or.z r2, r2, r3 ; r w x r w x (!GLOBAL, user page) + or.z r2, r2, r3 ; Kr Kw Kx Ur Uw Ux (!GLOBAL, user page) and r3, r0, PTE_BITS_NON_RWX_IN_PD1 ; Extract PFN+cache bits from PTE or r3, r3, r2 - sr r3, [ARC_REG_TLBPD1] ; these go in PD1 + sr r3, [ARC_REG_TLBPD1] ; paddr[31..13] | Kr Kw Kx Ur Uw Ux | C +#ifdef CONFIG_ARC_HAS_PAE40 + ld r3, [r1, 4] ; paddr[39..32] + sr r3, [ARC_REG_TLBPD1HI] +#endif and r2, r0, PTE_BITS_IN_PD0 ; Extract other PTE flags: (V)alid, (G)lb @@ -241,6 +281,7 @@ ex_saved_reg1: ; Commit the TLB entry into MMU .macro COMMIT_ENTRY_TO_MMU +#if (CONFIG_ARC_MMU_VER < 4) /* Get free TLB slot: Set = computed from vaddr, way = random */ sr TLBGetIndex, [ARC_REG_TLBCOMMAND] @@ -251,6 +292,10 @@ ex_saved_reg1: #else sr TLBWrite, [ARC_REG_TLBCOMMAND] #endif + +#else + sr TLBInsertEntry, [ARC_REG_TLBCOMMAND] +#endif .endm @@ -291,6 +336,7 @@ ENTRY(EV_TLBMissI) CONV_PTE_TO_TLB COMMIT_ENTRY_TO_MMU TLBMISS_RESTORE_REGS +EV_TLBMissI_fast_ret: ; additional label for VDK OS-kit instrumentation rtie END(EV_TLBMissI) @@ -342,7 +388,7 @@ ENTRY(EV_TLBMissD) lr r3, [ecr] or r0, r0, _PAGE_ACCESSED ; Accessed bit always btst_s r3, ECR_C_BIT_DTLB_ST_MISS ; See if it was a Write Access ? - or.nz r0, r0, _PAGE_MODIFIED ; if Write, set Dirty bit as well + or.nz r0, r0, _PAGE_DIRTY ; if Write, set Dirty bit as well st_s r0, [r1] ; Write back PTE CONV_PTE_TO_TLB @@ -356,6 +402,7 @@ ENTRY(EV_TLBMissD) COMMIT_ENTRY_TO_MMU TLBMISS_RESTORE_REGS +EV_TLBMissD_fast_ret: ; additional label for VDK OS-kit instrumentation rtie ;-------- Common routine to call Linux Page Fault Handler ----------- @@ -366,19 +413,5 @@ do_slow_path_pf: ; Slow path TLB Miss handled as a regular ARC Exception ; (stack switching / save the complete reg-file). - EXCEPTION_PROLOGUE - - ; ------- setup args for Linux Page fault Hanlder --------- - mov_s r1, sp - lr r0, [efa] - - ; We don't want exceptions to be disabled while the fault is handled. - ; Now that we have saved the context we return from exception hence - ; exceptions get re-enable - - FAKE_RET_FROM_EXCPN r9 - - bl do_page_fault - b ret_from_exception - + b call_do_page_fault END(EV_TLBMissD) diff --git a/kernel/arch/arc/plat-arcfpga/Kconfig b/kernel/arch/arc/plat-arcfpga/Kconfig deleted file mode 100644 index 217593a70..000000000 --- a/kernel/arch/arc/plat-arcfpga/Kconfig +++ /dev/null @@ -1,33 +0,0 @@ -# -# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) -# -# 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. -# - -menuconfig ARC_PLAT_FPGA_LEGACY - bool "\"Legacy\" ARC FPGA dev Boards" - select ARC_HAS_COH_CACHES if SMP - help - Support for ARC development boards, provided by Synopsys. - These are based on FPGA or ISS. e.g. - - ARCAngel4 - - ML509 - - MetaWare ISS - -if ARC_PLAT_FPGA_LEGACY - -config ISS_SMP_EXTN - bool "ARC SMP Extensions (ISS Models only)" - default n - depends on SMP - help - SMP Extensions to ARC700, in a "simulation only" Model, supported in - ARC ISS (Instruction Set Simulator). - The SMP extensions include: - -IDU (Interrupt Distribution Unit) - -XTL (To enable CPU start/stop/set-PC for another CPU) - It doesn't provide coherent Caches and/or Atomic Ops (LLOCK/SCOND) - -endif diff --git a/kernel/arch/arc/plat-arcfpga/include/plat/smp.h b/kernel/arch/arc/plat-arcfpga/include/plat/smp.h deleted file mode 100644 index c09eb4cfc..000000000 --- a/kernel/arch/arc/plat-arcfpga/include/plat/smp.h +++ /dev/null @@ -1,118 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * 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. - * - * Rajeshwar Ranga: Interrupt Distribution Unit API's - */ - -#ifndef __PLAT_ARCFPGA_SMP_H -#define __PLAT_ARCFPGA_SMP_H - -#ifdef CONFIG_SMP - -#include <linux/types.h> -#include <asm/arcregs.h> - -#define ARC_AUX_IDU_REG_CMD 0x2000 -#define ARC_AUX_IDU_REG_PARAM 0x2001 - -#define ARC_AUX_XTL_REG_CMD 0x2002 -#define ARC_AUX_XTL_REG_PARAM 0x2003 - -#define ARC_REG_MP_BCR 0x2021 - -#define ARC_XTL_CMD_WRITE_PC 0x04 -#define ARC_XTL_CMD_CLEAR_HALT 0x02 - -/* - * Build Configuration Register which identifies the sub-components - */ -struct bcr_mp { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int mp_arch:16, pad:5, sdu:1, idu:1, scu:1, ver:8; -#else - unsigned int ver:8, scu:1, idu:1, sdu:1, pad:5, mp_arch:16; -#endif -}; - -/* IDU supports 256 common interrupts */ -#define NR_IDU_IRQS 256 - -/* - * The Aux Regs layout is same bit-by-bit in both BE/LE modes. - * However when casted as a bitfield encoded "C" struct, gcc treats it as - * memory, generating different code for BE/LE, requiring strcture adj (see - * include/asm/arcregs.h) - * - * However when manually "carving" the value for a Aux, no special handling - * of BE is needed because of the property discribed above - */ -#define IDU_SET_COMMAND(irq, cmd) \ -do { \ - uint32_t __val; \ - __val = (((irq & 0xFF) << 8) | (cmd & 0xFF)); \ - write_aux_reg(ARC_AUX_IDU_REG_CMD, __val); \ -} while (0) - -#define IDU_SET_PARAM(par) write_aux_reg(ARC_AUX_IDU_REG_PARAM, par) -#define IDU_GET_PARAM() read_aux_reg(ARC_AUX_IDU_REG_PARAM) - -/* IDU Commands */ -#define IDU_DISABLE 0x00 -#define IDU_ENABLE 0x01 -#define IDU_IRQ_CLEAR 0x02 -#define IDU_IRQ_ASSERT 0x03 -#define IDU_IRQ_WMODE 0x04 -#define IDU_IRQ_STATUS 0x05 -#define IDU_IRQ_ACK 0x06 -#define IDU_IRQ_PEND 0x07 -#define IDU_IRQ_RMODE 0x08 -#define IDU_IRQ_WBITMASK 0x09 -#define IDU_IRQ_RBITMASK 0x0A - -#define idu_enable() IDU_SET_COMMAND(0, IDU_ENABLE) -#define idu_disable() IDU_SET_COMMAND(0, IDU_DISABLE) - -#define idu_irq_assert(irq) IDU_SET_COMMAND((irq), IDU_IRQ_ASSERT) -#define idu_irq_clear(irq) IDU_SET_COMMAND((irq), IDU_IRQ_CLEAR) - -/* IDU Interrupt Mode - Destination Encoding */ -#define IDU_IRQ_MOD_DISABLE 0x00 -#define IDU_IRQ_MOD_ROUND_RECP 0x01 -#define IDU_IRQ_MOD_TCPU_FIRSTRECP 0x02 -#define IDU_IRQ_MOD_TCPU_ALLRECP 0x03 - -/* IDU Interrupt Mode - Triggering Mode */ -#define IDU_IRQ_MODE_LEVEL_TRIG 0x00 -#define IDU_IRQ_MODE_PULSE_TRIG 0x01 - -#define IDU_IRQ_MODE_PARAM(dest_mode, trig_mode) \ - (((trig_mode & 0x01) << 15) | (dest_mode & 0xFF)) - -struct idu_irq_config { - uint8_t irq; - uint8_t dest_mode; - uint8_t trig_mode; -}; - -struct idu_irq_status { - uint8_t irq; - bool enabled; - bool status; - bool ack; - bool pend; - uint8_t next_rr; -}; - -extern void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask); -extern void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode); - -extern void iss_model_init_smp(unsigned int cpu); -extern void iss_model_init_early_smp(void); - -#endif /* CONFIG_SMP */ - -#endif diff --git a/kernel/arch/arc/plat-arcfpga/smp.c b/kernel/arch/arc/plat-arcfpga/smp.c deleted file mode 100644 index 64797ba3b..000000000 --- a/kernel/arch/arc/plat-arcfpga/smp.c +++ /dev/null @@ -1,186 +0,0 @@ -/* - * ARC700 Simulation-only Extensions for SMP - * - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * 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. - * - * Vineet Gupta - 2012 : split off arch common and plat specific SMP - * Rajeshwar Ranga - 2007 : Interrupt Distribution Unit API's - */ - -#include <linux/smp.h> -#include <linux/irq.h> -#include <plat/smp.h> - -#define IDU_INTERRUPT_0 16 - -static char smp_cpuinfo_buf[128]; - -/* - *------------------------------------------------------------------- - * Platform specific callbacks expected by arch SMP code - *------------------------------------------------------------------- - */ - -/* - * Master kick starting another CPU - */ -static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc) -{ - /* setup the start PC */ - write_aux_reg(ARC_AUX_XTL_REG_PARAM, pc); - - /* Trigger WRITE_PC cmd for this cpu */ - write_aux_reg(ARC_AUX_XTL_REG_CMD, - (ARC_XTL_CMD_WRITE_PC | (cpu << 8))); - - /* Take the cpu out of Halt */ - write_aux_reg(ARC_AUX_XTL_REG_CMD, - (ARC_XTL_CMD_CLEAR_HALT | (cpu << 8))); - -} - -static inline int get_hw_config_num_irq(void) -{ - uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR); - - switch (val & 0x03) { - case 0: - return 16; - case 1: - return 32; - case 2: - return 8; - default: - return 0; - } - - return 0; -} - -/* - * Any SMP specific init any CPU does when it comes up. - * Here we setup the CPU to enable Inter-Processor-Interrupts - * Called for each CPU - * -Master : init_IRQ() - * -Other(s) : start_kernel_secondary() - */ -void iss_model_init_smp(unsigned int cpu) -{ - /* Check if CPU is configured for more than 16 interrupts */ - if (NR_IRQS <= 16 || get_hw_config_num_irq() <= 16) - panic("[arcfpga] IRQ system can't support IDU IPI\n"); - - idu_disable(); - - /**************************************************************** - * IDU provides a set of Common IRQs, each of which can be dynamically - * attached to (1|many|all) CPUs. - * The Common IRQs [0-15] are mapped as CPU pvt [16-31] - * - * Here we use a simple 1:1 mapping: - * A CPU 'x' is wired to Common IRQ 'x'. - * So an IDU ASSERT on IRQ 'x' will trigger Interupt on CPU 'x', which - * makes up for our simple IPI plumbing. - * - * TBD: Have a dedicated multicast IRQ for sending IPIs to all CPUs - * w/o having to do one-at-a-time - ******************************************************************/ - - /* - * Claim an IRQ which would trigger IPI on this CPU. - * In IDU parlance it involves setting up a cpu bitmask for the IRQ - * The bitmap here contains only 1 CPU (self). - */ - idu_irq_set_tgtcpu(cpu, 0x1 << cpu); - - /* Set the IRQ destination to use the bitmask above */ - idu_irq_set_mode(cpu, 7, /* XXX: IDU_IRQ_MOD_TCPU_ALLRECP: ISS bug */ - IDU_IRQ_MODE_PULSE_TRIG); - - idu_enable(); - - /* Attach the arch-common IPI ISR to our IDU IRQ */ - smp_ipi_irq_setup(cpu, IDU_INTERRUPT_0 + cpu); -} - -static void iss_model_ipi_send(int cpu) -{ - idu_irq_assert(cpu); -} - -static void iss_model_ipi_clear(int irq) -{ - idu_irq_clear(IDU_INTERRUPT_0 + smp_processor_id()); -} - -void iss_model_init_early_smp(void) -{ -#define IS_AVAIL1(var, str) ((var) ? str : "") - - struct bcr_mp mp; - - READ_BCR(ARC_REG_MP_BCR, mp); - - sprintf(smp_cpuinfo_buf, "Extn [ISS-SMP]: v%d, arch(%d) %s %s %s\n", - mp.ver, mp.mp_arch, IS_AVAIL1(mp.scu, "SCU"), - IS_AVAIL1(mp.idu, "IDU"), IS_AVAIL1(mp.sdu, "SDU")); - - plat_smp_ops.info = smp_cpuinfo_buf; - - plat_smp_ops.cpu_kick = iss_model_smp_wakeup_cpu; - plat_smp_ops.ipi_send = iss_model_ipi_send; - plat_smp_ops.ipi_clear = iss_model_ipi_clear; -} - -/* - *------------------------------------------------------------------- - * Low level Platform IPI Providers - *------------------------------------------------------------------- - */ - -/* Set the Mode for the Common IRQ */ -void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode) -{ - uint32_t par = IDU_IRQ_MODE_PARAM(dest_mode, trig_mode); - - IDU_SET_PARAM(par); - IDU_SET_COMMAND(irq, IDU_IRQ_WMODE); -} - -/* Set the target cpu Bitmask for Common IRQ */ -void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask) -{ - IDU_SET_PARAM(mask); - IDU_SET_COMMAND(irq, IDU_IRQ_WBITMASK); -} - -/* Get the Interrupt Acknowledged status for IRQ (as CPU Bitmask) */ -bool idu_irq_get_ack(uint8_t irq) -{ - uint32_t val; - - IDU_SET_COMMAND(irq, IDU_IRQ_ACK); - val = IDU_GET_PARAM(); - - return val & (1 << irq); -} - -/* - * Get the Interrupt Pending status for IRQ (as CPU Bitmask) - * -Pending means CPU has not yet noticed the IRQ (e.g. disabled) - * -After Interrupt has been taken, the IPI expcitily needs to be - * cleared, to be acknowledged. - */ -bool idu_irq_get_pend(uint8_t irq) -{ - uint32_t val; - - IDU_SET_COMMAND(irq, IDU_IRQ_PEND); - val = IDU_GET_PARAM(); - - return val & (1 << irq); -} diff --git a/kernel/arch/arc/plat-axs10x/Kconfig b/kernel/arch/arc/plat-axs10x/Kconfig new file mode 100644 index 000000000..d475f9d48 --- /dev/null +++ b/kernel/arch/arc/plat-axs10x/Kconfig @@ -0,0 +1,46 @@ +# +# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) +# +# 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. +# + +menuconfig ARC_PLAT_AXS10X + bool "Synopsys ARC AXS10x Software Development Platforms" + select DW_APB_ICTL + select GPIO_DWAPB + select OF_GPIO + select GENERIC_IRQ_CHIP + select ARCH_REQUIRE_GPIOLIB + help + Support for the ARC AXS10x Software Development Platforms. + + The AXS10x Platforms consist of a mainboard with peripherals, + on which several daughter cards can be placed. The daughter cards + typically contain a CPU and memory. + +if ARC_PLAT_AXS10X + +config AXS101 + depends on ISA_ARCOMPACT + bool "AXS101 with AXC001 CPU Card (ARC 770D/EM6/AS221)" + help + This adds support for the 770D/EM6/AS221 CPU Card. Only the ARC + 770D is supported in Linux. + + The AXS101 Platform consists of an AXS10x mainboard with + this daughtercard. Please use the axs101.dts device tree + with this configuration. + +config AXS103 + bool "AXS103 with AXC003 CPU Card (ARC HS38x)" + depends on ISA_ARCV2 + help + This adds support for the HS38x CPU Card. + + The AXS103 Platform consists of an AXS10x mainboard with + this daughtercard. Please use the axs103.dts device tree + with this configuration. + +endif diff --git a/kernel/arch/arc/plat-axs10x/Makefile b/kernel/arch/arc/plat-axs10x/Makefile new file mode 100644 index 000000000..d4748f27f --- /dev/null +++ b/kernel/arch/arc/plat-axs10x/Makefile @@ -0,0 +1,9 @@ +# +# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) +# +# 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. +# + +obj-$(CONFIG_ARC_PLAT_AXS10X) += axs10x.o diff --git a/kernel/arch/arc/plat-axs10x/axs10x.c b/kernel/arch/arc/plat-axs10x/axs10x.c new file mode 100644 index 000000000..1b0f0f458 --- /dev/null +++ b/kernel/arch/arc/plat-axs10x/axs10x.c @@ -0,0 +1,493 @@ +/* + * AXS101/AXS103 Software Development Platform + * + * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/of_platform.h> + +#include <asm/asm-offsets.h> +#include <asm/clk.h> +#include <asm/io.h> +#include <asm/mach_desc.h> +#include <asm/mcip.h> + +#define AXS_MB_CGU 0xE0010000 +#define AXS_MB_CREG 0xE0011000 + +#define CREG_MB_IRQ_MUX (AXS_MB_CREG + 0x214) +#define CREG_MB_SW_RESET (AXS_MB_CREG + 0x220) +#define CREG_MB_VER (AXS_MB_CREG + 0x230) +#define CREG_MB_CONFIG (AXS_MB_CREG + 0x234) + +#define AXC001_CREG 0xF0001000 +#define AXC001_GPIO_INTC 0xF0003000 + +static void __init axs10x_enable_gpio_intc_wire(void) +{ + /* + * Peripherals on CPU Card and Mother Board are wired to cpu intc via + * intermediate DW APB GPIO blocks (mainly for debouncing) + * + * --------------------- + * | snps,arc700-intc | + * --------------------- + * | #7 | #15 + * ------------------- ------------------- + * | snps,dw-apb-gpio | | snps,dw-apb-gpio | + * ------------------- ------------------- + * | #12 | + * | [ Debug UART on cpu card ] + * | + * ------------------------ + * | snps,dw-apb-intc (MB)| + * ------------------------ + * | | | | + * [eth] [uart] [... other perip on Main Board] + * + * Current implementation of "irq-dw-apb-ictl" driver doesn't work well + * with stacked INTCs. In particular problem happens if its master INTC + * not yet instantiated. See discussion here - + * https://lkml.org/lkml/2015/3/4/755 + * + * So setup the first gpio block as a passive pass thru and hide it from + * DT hardware topology - connect MB intc directly to cpu intc + * The GPIO "wire" needs to be init nevertheless (here) + * + * One side adv is that peripheral interrupt handling avoids one nested + * intc ISR hop + */ +#define GPIO_INTEN (AXC001_GPIO_INTC + 0x30) +#define GPIO_INTMASK (AXC001_GPIO_INTC + 0x34) +#define GPIO_INTTYPE_LEVEL (AXC001_GPIO_INTC + 0x38) +#define GPIO_INT_POLARITY (AXC001_GPIO_INTC + 0x3c) +#define MB_TO_GPIO_IRQ 12 + + iowrite32(~(1 << MB_TO_GPIO_IRQ), (void __iomem *) GPIO_INTMASK); + iowrite32(0, (void __iomem *) GPIO_INTTYPE_LEVEL); + iowrite32(~0, (void __iomem *) GPIO_INT_POLARITY); + iowrite32(1 << MB_TO_GPIO_IRQ, (void __iomem *) GPIO_INTEN); +} + +static inline void __init +write_cgu_reg(uint32_t value, void __iomem *reg, void __iomem *lock_reg) +{ + unsigned int loops = 128 * 1024, ctr; + + iowrite32(value, reg); + + ctr = loops; + while (((ioread32(lock_reg) & 1) == 1) && ctr--) /* wait for unlock */ + cpu_relax(); + + ctr = loops; + while (((ioread32(lock_reg) & 1) == 0) && ctr--) /* wait for re-lock */ + cpu_relax(); +} + +static void __init axs10x_print_board_ver(unsigned int creg, const char *str) +{ + union ver { + struct { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:11, y:12, m:4, d:5; +#else + unsigned int d:5, m:4, y:12, pad:11; +#endif + }; + unsigned int val; + } board; + + board.val = ioread32((void __iomem *)creg); + pr_info("AXS: %s FPGA Date: %u-%u-%u\n", str, board.d, board.m, + board.y); +} + +static void __init axs10x_early_init(void) +{ + int mb_rev; + char mb[32]; + + /* Determine motherboard version */ + if (ioread32((void __iomem *) CREG_MB_CONFIG) & (1 << 28)) + mb_rev = 3; /* HT-3 (rev3.0) */ + else + mb_rev = 2; /* HT-2 (rev2.0) */ + + axs10x_enable_gpio_intc_wire(); + + scnprintf(mb, 32, "MainBoard v%d", mb_rev); + axs10x_print_board_ver(CREG_MB_VER, mb); +} + +#ifdef CONFIG_AXS101 + +#define CREG_CPU_ADDR_770 (AXC001_CREG + 0x20) +#define CREG_CPU_ADDR_TUNN (AXC001_CREG + 0x60) +#define CREG_CPU_ADDR_770_UPD (AXC001_CREG + 0x34) +#define CREG_CPU_ADDR_TUNN_UPD (AXC001_CREG + 0x74) + +#define CREG_CPU_ARC770_IRQ_MUX (AXC001_CREG + 0x114) +#define CREG_CPU_GPIO_UART_MUX (AXC001_CREG + 0x120) + +/* + * Set up System Memory Map for ARC cpu / peripherals controllers + * + * Each AXI master has a 4GB memory map specified as 16 apertures of 256MB, each + * of which maps to a corresponding 256MB aperture in Target slave memory map. + * + * e.g. ARC cpu AXI Master's aperture 8 (0x8000_0000) is mapped to aperture 0 + * (0x0000_0000) of DDR Port 0 (slave #1) + * + * Access from cpu to MB controllers such as GMAC is setup using AXI Tunnel: + * which has master/slaves on both ends. + * e.g. aperture 14 (0xE000_0000) of ARC cpu is mapped to aperture 14 + * (0xE000_0000) of CPU Card AXI Tunnel slave (slave #3) which is mapped to + * MB AXI Tunnel Master, which also has a mem map setup + * + * In the reverse direction, MB AXI Masters (e.g. GMAC) mem map is setup + * to map to MB AXI Tunnel slave which connects to CPU Card AXI Tunnel Master + */ +struct aperture { + unsigned int slave_sel:4, slave_off:4, pad:24; +}; + +/* CPU Card target slaves */ +#define AXC001_SLV_NONE 0 +#define AXC001_SLV_DDR_PORT0 1 +#define AXC001_SLV_SRAM 2 +#define AXC001_SLV_AXI_TUNNEL 3 +#define AXC001_SLV_AXI2APB 6 +#define AXC001_SLV_DDR_PORT1 7 + +/* MB AXI Target slaves */ +#define AXS_MB_SLV_NONE 0 +#define AXS_MB_SLV_AXI_TUNNEL_CPU 1 +#define AXS_MB_SLV_AXI_TUNNEL_HAPS 2 +#define AXS_MB_SLV_SRAM 3 +#define AXS_MB_SLV_CONTROL 4 + +/* MB AXI masters */ +#define AXS_MB_MST_TUNNEL_CPU 0 +#define AXS_MB_MST_USB_OHCI 10 + +/* + * memmap for ARC core on CPU Card + */ +static const struct aperture axc001_memmap[16] = { + {AXC001_SLV_AXI_TUNNEL, 0x0}, + {AXC001_SLV_AXI_TUNNEL, 0x1}, + {AXC001_SLV_SRAM, 0x0}, /* 0x2000_0000: Local SRAM */ + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_DDR_PORT0, 0x0}, /* 0x8000_0000: DDR 0..256M */ + {AXC001_SLV_DDR_PORT0, 0x1}, /* 0x9000_0000: DDR 256..512M */ + {AXC001_SLV_DDR_PORT0, 0x2}, + {AXC001_SLV_DDR_PORT0, 0x3}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_AXI_TUNNEL, 0xD}, + {AXC001_SLV_AXI_TUNNEL, 0xE}, /* MB: CREG, CGU... */ + {AXC001_SLV_AXI2APB, 0x0}, /* CPU Card local CREG, CGU... */ +}; + +/* + * memmap for CPU Card AXI Tunnel Master (for access by MB controllers) + * GMAC (MB) -> MB AXI Tunnel slave -> CPU Card AXI Tunnel Master -> DDR + */ +static const struct aperture axc001_axi_tunnel_memmap[16] = { + {AXC001_SLV_AXI_TUNNEL, 0x0}, + {AXC001_SLV_AXI_TUNNEL, 0x1}, + {AXC001_SLV_SRAM, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_DDR_PORT1, 0x0}, + {AXC001_SLV_DDR_PORT1, 0x1}, + {AXC001_SLV_DDR_PORT1, 0x2}, + {AXC001_SLV_DDR_PORT1, 0x3}, + {AXC001_SLV_NONE, 0x0}, + {AXC001_SLV_AXI_TUNNEL, 0xD}, + {AXC001_SLV_AXI_TUNNEL, 0xE}, + {AXC001_SLV_AXI2APB, 0x0}, +}; + +/* + * memmap for MB AXI Masters + * Same mem map for all perip controllers as well as MB AXI Tunnel Master + */ +static const struct aperture axs_mb_memmap[16] = { + {AXS_MB_SLV_SRAM, 0x0}, + {AXS_MB_SLV_SRAM, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_AXI_TUNNEL_CPU, 0x8}, /* DDR on CPU Card */ + {AXS_MB_SLV_AXI_TUNNEL_CPU, 0x9}, /* DDR on CPU Card */ + {AXS_MB_SLV_AXI_TUNNEL_CPU, 0xA}, + {AXS_MB_SLV_AXI_TUNNEL_CPU, 0xB}, + {AXS_MB_SLV_NONE, 0x0}, + {AXS_MB_SLV_AXI_TUNNEL_HAPS, 0xD}, + {AXS_MB_SLV_CONTROL, 0x0}, /* MB Local CREG, CGU... */ + {AXS_MB_SLV_AXI_TUNNEL_CPU, 0xF}, +}; + +static noinline void __init +axs101_set_memmap(void __iomem *base, const struct aperture map[16]) +{ + unsigned int slave_select, slave_offset; + int i; + + slave_select = slave_offset = 0; + for (i = 0; i < 8; i++) { + slave_select |= map[i].slave_sel << (i << 2); + slave_offset |= map[i].slave_off << (i << 2); + } + + iowrite32(slave_select, base + 0x0); /* SLV0 */ + iowrite32(slave_offset, base + 0x8); /* OFFSET0 */ + + slave_select = slave_offset = 0; + for (i = 0; i < 8; i++) { + slave_select |= map[i+8].slave_sel << (i << 2); + slave_offset |= map[i+8].slave_off << (i << 2); + } + + iowrite32(slave_select, base + 0x4); /* SLV1 */ + iowrite32(slave_offset, base + 0xC); /* OFFSET1 */ +} + +static void __init axs101_early_init(void) +{ + int i; + + /* ARC 770D memory view */ + axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_770, axc001_memmap); + iowrite32(1, (void __iomem *) CREG_CPU_ADDR_770_UPD); + + /* AXI tunnel memory map (incoming traffic from MB into CPU Card */ + axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_TUNN, + axc001_axi_tunnel_memmap); + iowrite32(1, (void __iomem *) CREG_CPU_ADDR_TUNN_UPD); + + /* MB peripherals memory map */ + for (i = AXS_MB_MST_TUNNEL_CPU; i <= AXS_MB_MST_USB_OHCI; i++) + axs101_set_memmap((void __iomem *) AXS_MB_CREG + (i << 4), + axs_mb_memmap); + + iowrite32(0x3ff, (void __iomem *) AXS_MB_CREG + 0x100); /* Update */ + + /* GPIO pins 18 and 19 are used as UART rx and tx, respectively. */ + iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX); + + /* Set up the MB interrupt system: mux interrupts to GPIO7) */ + iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX); + + /* reset ethernet and ULPI interfaces */ + iowrite32(0x18, (void __iomem *) CREG_MB_SW_RESET); + + /* map GPIO 14:10 to ARC 9:5 (IRQ mux change for MB v2 onwards) */ + iowrite32(0x52, (void __iomem *) CREG_CPU_ARC770_IRQ_MUX); + + axs10x_early_init(); +} + +#endif /* CONFIG_AXS101 */ + +#ifdef CONFIG_AXS103 + +#define AXC003_CGU 0xF0000000 +#define AXC003_CREG 0xF0001000 +#define AXC003_MST_AXI_TUNNEL 0 +#define AXC003_MST_HS38 1 + +#define CREG_CPU_AXI_M0_IRQ_MUX (AXC003_CREG + 0x440) +#define CREG_CPU_GPIO_UART_MUX (AXC003_CREG + 0x480) +#define CREG_CPU_TUN_IO_CTRL (AXC003_CREG + 0x494) + + +union pll_reg { + struct { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:17, noupd:1, bypass:1, edge:1, high:6, low:6; +#else + unsigned int low:6, high:6, edge:1, bypass:1, noupd:1, pad:17; +#endif + }; + unsigned int val; +}; + +static unsigned int __init axs103_get_freq(void) +{ + union pll_reg idiv, fbdiv, odiv; + unsigned int f = 33333333; + + idiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 0); + fbdiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 4); + odiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 8); + + if (idiv.bypass != 1) + f = f / (idiv.low + idiv.high); + + if (fbdiv.bypass != 1) + f = f * (fbdiv.low + fbdiv.high); + + if (odiv.bypass != 1) + f = f / (odiv.low + odiv.high); + + f = (f + 500000) / 1000000; /* Rounding */ + return f; +} + +static inline unsigned int __init encode_div(unsigned int id, int upd) +{ + union pll_reg div; + + div.val = 0; + + div.noupd = !upd; + div.bypass = id == 1 ? 1 : 0; + div.edge = (id%2 == 0) ? 0 : 1; /* 0 = rising */ + div.low = (id%2 == 0) ? id >> 1 : (id >> 1)+1; + div.high = id >> 1; + + return div.val; +} + +noinline static void __init +axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od) +{ + write_cgu_reg(encode_div(id, 0), + (void __iomem *)AXC003_CGU + 0x80 + 0, + (void __iomem *)AXC003_CGU + 0x110); + + write_cgu_reg(encode_div(fd, 0), + (void __iomem *)AXC003_CGU + 0x80 + 4, + (void __iomem *)AXC003_CGU + 0x110); + + write_cgu_reg(encode_div(od, 1), + (void __iomem *)AXC003_CGU + 0x80 + 8, + (void __iomem *)AXC003_CGU + 0x110); +} + +static void __init axs103_early_init(void) +{ + /* + * AXS103 configurations for SMP/QUAD configurations share device tree + * which defaults to 90 MHz. However recent failures of Quad config + * revealed P&R timing violations so clamp it down to safe 50 MHz + * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack + * + * This hack is really hacky as of now. Fix it properly by getting the + * number of cores as return value of platform's early SMP callback + */ +#ifdef CONFIG_ARC_MCIP + unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F; + if (num_cores > 2) + arc_set_core_freq(50 * 1000000); + else if (num_cores == 2) + arc_set_core_freq(75 * 1000000); +#endif + + switch (arc_get_core_freq()/1000000) { + case 33: + axs103_set_freq(1, 1, 1); + break; + case 50: + axs103_set_freq(1, 30, 20); + break; + case 75: + axs103_set_freq(2, 45, 10); + break; + case 90: + axs103_set_freq(2, 54, 10); + break; + case 100: + axs103_set_freq(1, 30, 10); + break; + case 125: + axs103_set_freq(2, 45, 6); + break; + default: + /* + * In this case, core_frequency derived from + * DT "clock-frequency" might not match with board value. + * Hence update it to match the board value. + */ + arc_set_core_freq(axs103_get_freq() * 1000000); + break; + } + + pr_info("Freq is %dMHz\n", axs103_get_freq()); + + /* Memory maps already config in pre-bootloader */ + + /* set GPIO mux to UART */ + iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX); + + iowrite32((0x00100000U | 0x000C0000U | 0x00003322U), + (void __iomem *) CREG_CPU_TUN_IO_CTRL); + + /* Set up the AXS_MB interrupt system.*/ + iowrite32(12, (void __iomem *) (CREG_CPU_AXI_M0_IRQ_MUX + + (AXC003_MST_HS38 << 2))); + + /* connect ICTL - Main Board with GPIO line */ + iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX); + + axs10x_print_board_ver(AXC003_CREG + 4088, "AXC003 CPU Card"); + + axs10x_early_init(); +} +#endif + +#ifdef CONFIG_AXS101 + +static const char *axs101_compat[] __initconst = { + "snps,axs101", + NULL, +}; + +MACHINE_START(AXS101, "axs101") + .dt_compat = axs101_compat, + .init_early = axs101_early_init, +MACHINE_END + +#endif /* CONFIG_AXS101 */ + +#ifdef CONFIG_AXS103 + +static const char *axs103_compat[] __initconst = { + "snps,axs103", + NULL, +}; + +MACHINE_START(AXS103, "axs103") + .dt_compat = axs103_compat, + .init_early = axs103_early_init, +MACHINE_END + +/* + * For the VDK OS-kit, to get the offset to pid and command fields + */ +char coware_swa_pid_offset[TASK_PID]; +char coware_swa_comm_offset[TASK_COMM]; + +#endif /* CONFIG_AXS103 */ diff --git a/kernel/arch/arc/plat-sim/Kconfig b/kernel/arch/arc/plat-sim/Kconfig new file mode 100644 index 000000000..18e39fcc4 --- /dev/null +++ b/kernel/arch/arc/plat-sim/Kconfig @@ -0,0 +1,14 @@ +# +# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) +# +# 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. +# + +menuconfig ARC_PLAT_SIM + bool "ARC nSIM based simulation virtual platforms" + select ARC_HAS_COH_CACHES if SMP + help + Support for nSIM based ARC simulation platforms + This includes the standalone nSIM (uart only) vs. System C OSCI VP diff --git a/kernel/arch/arc/plat-arcfpga/Makefile b/kernel/arch/arc/plat-sim/Makefile index 66fd0ecd6..00b1a958c 100644 --- a/kernel/arch/arc/plat-arcfpga/Makefile +++ b/kernel/arch/arc/plat-sim/Makefile @@ -6,7 +6,4 @@ # published by the Free Software Foundation. # -KBUILD_CFLAGS += -Iarch/arc/plat-arcfpga/include - obj-y := platform.o -obj-$(CONFIG_ISS_SMP_EXTN) += smp.o diff --git a/kernel/arch/arc/plat-arcfpga/platform.c b/kernel/arch/arc/plat-sim/platform.c index afc88254a..e4fe51456 100644 --- a/kernel/arch/arc/plat-arcfpga/platform.c +++ b/kernel/arch/arc/plat-sim/platform.c @@ -1,5 +1,5 @@ /* - * ARC FPGA Platform support code + * ARC simulation Platform support code * * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com) * @@ -10,7 +10,6 @@ #include <linux/init.h> #include <asm/mach_desc.h> -#include <plat/smp.h> /*----------------------- Machine Descriptions ------------------------------ * @@ -20,23 +19,11 @@ * callback set, by matching the DT compatible name. */ -static const char *legacy_fpga_compat[] __initconst = { - "snps,arc-angel4", - "snps,arc-ml509", - NULL, -}; - -MACHINE_START(LEGACY_FPGA, "legacy_fpga") - .dt_compat = legacy_fpga_compat, -#ifdef CONFIG_ISS_SMP_EXTN - .init_early = iss_model_init_early_smp, - .init_smp = iss_model_init_smp, -#endif -MACHINE_END - static const char *simulation_compat[] __initconst = { "snps,nsim", + "snps,nsim_hs", "snps,nsimosci", + "snps,nsimosci_hs", NULL, }; |