diff options
Diffstat (limited to 'arch/arc')
101 files changed, 2701 insertions, 2423 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5917099470e..9596b0ab108 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -8,6 +8,7 @@ config ARC def_bool y + select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS # ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev select DEVTMPFS if !INITRAMFS_SOURCE="" @@ -20,7 +21,6 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_GENERIC_HARDIRQS select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES @@ -34,6 +34,13 @@ config ARC select OF select OF_EARLY_FLATTREE select PERF_USE_VMALLOC + select HAVE_DEBUG_STACKOVERFLOW + +config TRACE_IRQFLAGS_SUPPORT + def_bool y + +config LOCKDEP_SUPPORT + def_bool y config SCHED_OMIT_FRAME_POINTER def_bool y @@ -50,7 +57,7 @@ config ARCH_FLATMEM_ENABLE config MMU def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config GENERIC_CALIBRATE_DELAY @@ -119,28 +126,24 @@ config ARC_PLAT_NEEDS_CPU_TO_DMA config SMP bool "Symmetric Multi-Processing (Incomplete)" default n - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have - a system with only one CPU, like most personal computers, say N. If - you have a system with more than one CPU, say Y. + a system with only one CPU, say N. If you have a system with more + than one CPU, say Y. if SMP config ARC_HAS_COH_CACHES def_bool n -config ARC_HAS_COH_RTSC - def_bool n - config ARC_HAS_REENTRANT_IRQ_LV2 def_bool n endif config NR_CPUS - int "Maximum number of CPUs (2-32)" - range 2 32 + int "Maximum number of CPUs (2-4096)" + range 2 4096 depends on SMP default "2" @@ -184,6 +187,7 @@ config ARC_CACHE_PAGES config ARC_CACHE_VIPT_ALIASING bool "Support VIPT Aliasing D$" + depends on ARC_HAS_DCACHE default n endif #ARC_CACHE @@ -325,8 +329,7 @@ config ARC_HAS_RTSC bool "Insn: RTSC (64-bit r/o cycle counter)" default y depends on ARC_CPU_REL_4_10 - # if SMP, enable RTSC only if counter is coherent across cores - depends on !SMP || ARC_HAS_COH_RTSC + depends on !SMP endmenu # "ARC CPU Configuration" @@ -353,7 +356,6 @@ config ARC_CURR_IN_REG config ARC_MISALIGN_ACCESS bool "Emulate unaligned memory access (userspace only)" - default N select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_ARCH_UNALIGN_ALLOW help @@ -361,13 +363,6 @@ config ARC_MISALIGN_ACCESS Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide potential bugs in code -config ARC_STACK_NONEXEC - bool "Make stack non-executable" - default n - help - To disable the execute permissions of stack/heap of processes - which are enabled by default. - config HZ int "Timer Frequency" default 100 @@ -413,17 +408,6 @@ config ARC_DBG_TLB_MISS_COUNT Counts number of I and D TLB Misses and exports them via Debugfs The counters can be cleared via Debugfs as well -config CMDLINE_UBOOT - bool "Support U-boot kernel command line passing" - default n - help - If you are using U-boot (www.denx.de) and wish to pass the kernel - command line from the U-boot environment to the Linux kernel then - switch this option on. - ARC U-boot will setup the cmdline in RAM/flash and set r2 to point - to it. kernel startup code will append this to DeviceTree - /bootargs provided cmdline args. - config ARC_BUILTIN_DTB_NAME string "Built in DTB" help diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug index 962c6099659..a7fc0da2565 100644 --- a/arch/arc/Kconfig.debug +++ b/arch/arc/Kconfig.debug @@ -15,13 +15,6 @@ config EARLY_PRINTK with klogd/syslogd or the X server. You should normally N here, unless you want to debug such a crash. -config DEBUG_STACKOVERFLOW - bool "Check for stack overflows" - depends on DEBUG_KERNEL - help - This option will cause messages to be printed if free stack space - drops below a certain limit. - config 16KSTACKS bool "Use 16Kb for kernel stacks instead of 8Kb" help diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 183397fd289..8c0b1aa56f7 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -9,25 +9,27 @@ UTS_MACHINE := arc ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := arc-elf32- +CROSS_COMPILE := arc-linux-uclibc- endif KBUILD_DEFCONFIG := fpga_defconfig cflags-y += -mA7 -fno-common -pipe -fno-builtin -D__linux__ -LINUXINCLUDE += -include ${src}/arch/arc/include/asm/defines.h - ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file # We had a customer reported bug where some code built in kernel was NOT using # any kernel headers, and missing the r25 global register -# Can't do unconditionally (like above) because of recursive include issues +# Can't do unconditionally because of recursive include issues # due to <linux/thread_info.h> LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -atleast_gcc44 := $(call cc-ifversion, -gt, 0402, y) +upto_gcc42 := $(call cc-ifversion, -le, 0402, y) +upto_gcc44 := $(call cc-ifversion, -le, 0404, y) +atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) +atleast_gcc48 := $(call cc-ifversion, -ge, 0408, y) + cflags-$(atleast_gcc44) += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock @@ -35,6 +37,11 @@ cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape cflags-$(CONFIG_ARC_HAS_RTSC) += -mrtsc cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables +# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok +ifeq ($(atleast_gcc48),y) +cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 +endif + ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 cflags-y += -O3 @@ -48,11 +55,10 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: +# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) # arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". -# Default arc-elf32-ld is OK -ldflags-y += -marclinux +# --build-id w/o "-marclinux". Default arc-elf32-ld is OK +ldflags-$(upto_gcc44) += -marclinux ARC_LIBGCC := -mA7 cflags-$(CONFIG_ARC_HAS_HW_MPY) += -multcost=16 @@ -66,8 +72,8 @@ ifndef CONFIG_ARC_HAS_HW_MPY # With gcc 4.4.7, -mno-mpy is enough to make any other related adjustments, # e.g. increased cost of MPY. With gcc 4.2.1 this had to be explicitly hinted - ARC_LIBGCC := -marc600 - ifneq ($(atleast_gcc44),y) + ifeq ($(upto_gcc42),y) + ARC_LIBGCC := -marc600 cflags-y += -multcost=30 endif endif diff --git a/arch/arc/boot/.gitignore b/arch/arc/boot/.gitignore new file mode 100644 index 00000000000..5246969a20c --- /dev/null +++ b/arch/arc/boot/.gitignore @@ -0,0 +1,2 @@ +*.dtb* +uImage diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi index 941ad118a7e..3942634f805 100644 --- a/arch/arc/boot/dts/abilis_tb100.dtsi +++ b/arch/arc/boot/dts/abilis_tb100.dtsi @@ -21,10 +21,6 @@ /include/ "abilis_tb10x.dtsi" -/* interrupt specifiers - * -------------------- - * 0: rising, 1: low, 2: high, 3: falling, - */ / { clock-frequency = <500000000>; /* 500 MHZ */ @@ -47,124 +43,124 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -173,168 +169,182 @@ interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts index 0fa0d4abe79..3dd6ed94146 100644 --- a/arch/arc/boot/dts/abilis_tb100_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts @@ -45,81 +45,81 @@ }; i2c0: i2c@FF120000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c1: i2c@FF121000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c2: i2c@FF122000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c3: i2c@FF123000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c4: i2c@FF124000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; leds { compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi index fd25c212049..b0467229a5c 100644 --- a/arch/arc/boot/dts/abilis_tb101.dtsi +++ b/arch/arc/boot/dts/abilis_tb101.dtsi @@ -21,10 +21,6 @@ /include/ "abilis_tb10x.dtsi" -/* interrupt specifiers - * -------------------- - * 0: rising, 1: low, 2: high, 3: falling, - */ / { clock-frequency = <500000000>; /* 500 MHZ */ @@ -47,133 +43,133 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; pctl_stc0: pctl-stc0 { /* Smart card I/F 0 */ - pingrp = "stc0_pins"; + abilis,function = "stc0"; }; pctl_stc1: pctl-stc1 { /* Smart card I/F 1 */ - pingrp = "stc1_pins"; + abilis,function = "stc1"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; pctl_jtag: pctl-jtag { - pingrp = "jtag_pins"; + abilis,function = "jtag"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -182,168 +178,182 @@ interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; interrupt-controller; #interrupt-cells = <1>; interrupt-parent = <&tb10x_ictl>; - interrupts = <27 1>; + interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts index a4d80ce283a..1cf51c280f2 100644 --- a/arch/arc/boot/dts/abilis_tb101_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts @@ -45,81 +45,81 @@ }; i2c0: i2c@FF120000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c1: i2c@FF121000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c2: i2c@FF122000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c3: i2c@FF123000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; i2c4: i2c@FF124000 { - sda-hold-time = <432>; + i2c-sda-hold-time-ns = <432>; }; leds { compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi index b97e3051ba4..a098d7c05e9 100644 --- a/arch/arc/boot/dts/abilis_tb10x.dtsi +++ b/arch/arc/boot/dts/abilis_tb10x.dtsi @@ -19,10 +19,6 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -/* interrupt specifiers - * -------------------- - * 0: rising, 1: low, 2: high, 3: falling, - */ / { compatible = "abilis,arc-tb10x"; @@ -66,9 +62,8 @@ }; iomux: iomux@FF10601c { - #address-cells = <1>; - #size-cells = <1>; compatible = "abilis,tb10x-iomux"; + #gpio-range-cells = <3>; reg = <0xFF10601c 0x4>; }; @@ -78,7 +73,7 @@ #interrupt-cells = <1>; }; tb10x_ictl: pic@fe002000 { - compatible = "abilis,tb10x_ictl"; + compatible = "abilis,tb10x-ictl"; reg = <0xFE002000 0x20>; interrupt-controller; #interrupt-cells = <2>; @@ -91,7 +86,7 @@ compatible = "snps,dw-apb-uart"; reg = <0xFF100000 0x100>; clock-frequency = <166666666>; - interrupts = <25 1>; + interrupts = <25 8>; reg-shift = <2>; reg-io-width = <4>; interrupt-parent = <&tb10x_ictl>; @@ -100,7 +95,7 @@ compatible = "snps,dwmac-3.70a","snps,dwmac"; reg = <0xFE100000 0x1058>; interrupt-parent = <&tb10x_ictl>; - interrupts = <6 1>; + interrupts = <6 8>; interrupt-names = "macirq"; clocks = <&ahb_clk>; clock-names = "stmmaceth"; @@ -109,7 +104,7 @@ compatible = "snps,dma-spear1340"; reg = <0xFE000000 0x400>; interrupt-parent = <&tb10x_ictl>; - interrupts = <14 1>; + interrupts = <14 8>; dma-channels = <6>; dma-requests = <0>; dma-masters = <1>; @@ -128,7 +123,7 @@ compatible = "snps,designware-i2c"; reg = <0xFF120000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <12 1>; + interrupts = <12 8>; clocks = <&ahb_clk>; }; i2c1: i2c@FF121000 { @@ -137,7 +132,7 @@ compatible = "snps,designware-i2c"; reg = <0xFF121000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <12 1>; + interrupts = <12 8>; clocks = <&ahb_clk>; }; i2c2: i2c@FF122000 { @@ -146,7 +141,7 @@ compatible = "snps,designware-i2c"; reg = <0xFF122000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <12 1>; + interrupts = <12 8>; clocks = <&ahb_clk>; }; i2c3: i2c@FF123000 { @@ -155,7 +150,7 @@ compatible = "snps,designware-i2c"; reg = <0xFF123000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <12 1>; + interrupts = <12 8>; clocks = <&ahb_clk>; }; i2c4: i2c@FF124000 { @@ -164,7 +159,7 @@ compatible = "snps,designware-i2c"; reg = <0xFF124000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <12 1>; + interrupts = <12 8>; clocks = <&ahb_clk>; }; @@ -176,7 +171,7 @@ num-cs = <1>; reg = <0xFE010000 0x20>; interrupt-parent = <&tb10x_ictl>; - interrupts = <26 1>; + interrupts = <26 8>; clocks = <&ahb_clk>; }; spi1: spi@0xFE011000 { @@ -187,7 +182,7 @@ num-cs = <2>; reg = <0xFE011000 0x20>; interrupt-parent = <&tb10x_ictl>; - interrupts = <10 1>; + interrupts = <10 8>; clocks = <&ahb_clk>; }; @@ -195,7 +190,7 @@ compatible = "abilis,tb100-tsm"; reg = <0xff316000 0x400>; interrupt-parent = <&tb10x_ictl>; - interrupts = <17 1>; + interrupts = <17 8>; output-clkdiv = <4>; global-packet-delay = <0x21>; port-packet-delay = <0>; @@ -213,7 +208,7 @@ "cpuctrl", "a6it_int_force"; interrupt-parent = <&tb10x_ictl>; - interrupts = <20 1>, <19 1>; + interrupts = <20 2>, <19 2>; interrupt-names = "cmd_irq", "event_irq"; }; tb10x_mdsc0: tb10x-mdscr@FF300000 { @@ -239,7 +234,7 @@ compatible = "abilis,tb100-wfb"; reg = <0xff319000 0x1000>; interrupt-parent = <&tb10x_ictl>; - interrupts = <16 1>; + interrupts = <16 8>; }; }; }; diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/angel4.dts index bae4f936cb0..5bb2fdaca02 100644 --- a/arch/arc/boot/dts/angel4.dts +++ b/arch/arc/boot/dts/angel4.dts @@ -17,7 +17,7 @@ interrupt-parent = <&intc>; chosen { - bootargs = "console=ttyARC0,115200n8"; + bootargs = "console=ttyARC0,115200n8 earlyprintk=ttyARC0"; }; aliases { @@ -51,5 +51,25 @@ current-speed = <115200>; status = "okay"; }; + + ethernet@c0fc2000 { + compatible = "snps,arc-emac"; + reg = <0xc0fc2000 0x3c>; + interrupts = <6>; + mac-address = [ 00 11 22 33 44 55 ]; + clock-frequency = <80000000>; + max-speed = <100>; + phy = <&phy0>; + + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <1>; + }; + }; + + arcpmu0: pmu { + compatible = "snps,arc700-pmu"; + }; }; }; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index ea16d782af5..4f31b2eb5cd 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -11,13 +11,16 @@ / { compatible = "snps,nsimosci"; - clock-frequency = <80000000>; /* 80 MHZ */ + clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&intc>; chosen { - bootargs = "console=tty0 consoleblank=0"; + /* this is for console on PGU */ + /* bootargs = "console=tty0 consoleblank=0"; */ + /* this is for console on serial */ + bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug"; }; aliases { @@ -44,15 +47,14 @@ }; uart0: serial@c0000000 { - compatible = "snps,dw-apb-uart"; + compatible = "ns8250"; reg = <0xc0000000 0x2000>; interrupts = <11>; - #clock-frequency = <80000000>; clock-frequency = <3686400>; baud = <115200>; reg-shift = <2>; reg-io-width = <4>; - status = "okay"; + no-loopback-test = <1>; }; pgu0: pgu@c9000000 { diff --git a/arch/arc/boot/dts/skeleton.dts b/arch/arc/boot/dts/skeleton.dts deleted file mode 100644 index 25a84fb5b3d..00000000000 --- a/arch/arc/boot/dts/skeleton.dts +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Copyright (C) 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. - */ -/dts-v1/; - -/include/ "skeleton.dtsi" diff --git a/arch/arc/configs/fpga_defconfig b/arch/arc/configs/fpga_defconfig index 95350be6ef6..e283aa58693 100644 --- a/arch/arc/configs/fpga_defconfig +++ b/arch/arc/configs/fpga_defconfig @@ -1,7 +1,9 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -38,6 +40,9 @@ CONFIG_INET=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set # CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +CONFIG_ARC_EMAC=y +CONFIG_LXT_PHY=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -59,4 +64,5 @@ CONFIG_TMPFS=y 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/arch/arc/configs/fpga_noramfs_defconfig b/arch/arc/configs/fpga_noramfs_defconfig new file mode 100644 index 00000000000..5276a52f6a2 --- /dev/null +++ b/arch/arc/configs/fpga_noramfs_defconfig @@ -0,0 +1,64 @@ +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +# 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_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_FPGA_LEGACY=y +CONFIG_ARC_BOARD_ML509=y +# CONFIG_ARC_HAS_RTSC is not set +CONFIG_ARC_BUILTIN_DTB_NAME="angel4" +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_NETDEVICES=y +CONFIG_ARC_EMAC=y +CONFIG_LXT_PHY=y +# 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/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 446c96c24ef..c01ba35a4ef 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set @@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 4fa5cd9f220..6be6492442d 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index d8dd660898b..e76fd79f32b 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,16 +1,18 @@ generic-y += auxvec.h -generic-y += bugs.h +generic-y += barrier.h generic-y += bitsperlong.h +generic-y += bugs.h generic-y += clkdev.h generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h generic-y += errno.h -generic-y += fcntl.h generic-y += fb.h +generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -20,6 +22,7 @@ generic-y += kmap_types.h generic-y += kvm_para.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h @@ -28,6 +31,7 @@ generic-y += pci.h generic-y += percpu.h 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 diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 1b907c46566..355cb470c2a 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -20,7 +20,6 @@ #define ARC_REG_PERIBASE_BCR 0x69 #define ARC_REG_FP_BCR 0x6B /* Single-Precision FPU */ #define ARC_REG_DPFP_BCR 0x6C /* Dbl Precision FPU */ -#define ARC_REG_MMU_BCR 0x6f #define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_ICCM_BCR 0x78 @@ -34,22 +33,12 @@ #define ARC_REG_D_UNCACH_BCR 0x6A /* status32 Bits Positions */ -#define STATUS_H_BIT 0 /* CPU Halted */ -#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_DE_BIT 6 /* PC is in delay slot */ #define STATUS_U_BIT 7 /* User/Kernel mode */ #define STATUS_L_BIT 12 /* Loop inhibit */ /* These masks correspond to the status word(STATUS_32) bits */ -#define STATUS_H_MASK (1<<STATUS_H_BIT) -#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_DE_MASK (1<<STATUS_DE_BIT) #define STATUS_U_MASK (1<<STATUS_U_BIT) @@ -71,6 +60,7 @@ #define ECR_V_ITLB_MISS 0x21 #define ECR_V_DTLB_MISS 0x22 #define ECR_V_PROTV 0x23 +#define ECR_V_TRAP 0x25 /* Protection Violation Exception Cause Code Values */ #define ECR_C_PROTV_INST_FETCH 0x00 @@ -79,94 +69,23 @@ #define ECR_C_PROTV_XCHG 0x03 #define ECR_C_PROTV_MISALIG_DATA 0x04 +#define ECR_C_BIT_PROTV_MISALIG_DATA 10 + +/* Machine Check Cause Code Values */ +#define ECR_C_MCHK_DUP_TLB 0x01 + /* DTLB Miss Exception Cause Code Values */ #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_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 - -/* Timer related Aux registers */ -#define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ -#define ARC_REG_TIMER0_CTRL 0x22 /* timer 0 control */ -#define ARC_REG_TIMER0_CNT 0x21 /* timer 0 count */ -#define ARC_REG_TIMER1_LIMIT 0x102 /* timer 1 limit */ -#define ARC_REG_TIMER1_CTRL 0x101 /* timer 1 control */ -#define ARC_REG_TIMER1_CNT 0x100 /* timer 1 count */ - -#define TIMER_CTRL_IE (1 << 0) /* Interupt when Count reachs limit */ -#define TIMER_CTRL_NH (1 << 1) /* Count only when CPU NOT halted */ - -/* MMU Management regs */ -#define ARC_REG_TLBPD0 0x405 -#define ARC_REG_TLBPD1 0x406 -#define ARC_REG_TLBINDEX 0x407 -#define ARC_REG_TLBCOMMAND 0x408 -#define ARC_REG_PID 0x409 -#define ARC_REG_SCRATCH_DATA0 0x418 - -/* Bits in MMU PID register */ -#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ - -/* Error code if probe fails */ -#define TLB_LKUP_ERR 0x80000000 - -/* TLB Commands */ -#define TLBWrite 0x1 -#define TLBRead 0x2 -#define TLBGetIndex 0x3 -#define TLBProbe 0x4 - -#if (CONFIG_ARC_MMU_VER >= 2) -#define TLBWriteNI 0x5 /* write JTLB without inv uTLBs */ -#define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ -#else -#undef TLBWriteNI /* These cmds don't exist on older MMU */ -#undef TLBIVUTLB -#endif -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - -/* MMU Management regs */ -#define ARC_REG_PID 0x409 -#define ARC_REG_SCRATCH_DATA0 0x418 - -/* Bits in MMU PID register */ -#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ /* * Floating Pt Registers @@ -293,24 +212,6 @@ struct bcr_identity { #endif }; -struct bcr_mmu_1_2 { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8; -#else - unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8; -#endif -}; - -struct bcr_mmu_3 { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, 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, - ways:4, ver:8; -#endif -}; - #define EXTN_SWAP_VALID 0x1 #define EXTN_NORM_VALID 0x2 #define EXTN_MINMAX_VALID 0x2 @@ -343,14 +244,6 @@ struct bcr_extn_xymem { #endif }; -struct bcr_cache { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad:12, line_len:4, sz:4, config:4, ver:8; -#else - unsigned int ver:8, config:4, sz:4, line_len:4, pad:12; -#endif -}; - struct bcr_perip { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int start:8, pad2:8, sz:8, pad:8; @@ -403,7 +296,7 @@ struct cpuinfo_arc_mmu { }; struct cpuinfo_arc_cache { - unsigned int has_aliasing, sz, line_len, assoc, ver; + unsigned int sz, line_len, assoc, ver; }; struct cpuinfo_arc_ccm { diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h deleted file mode 100644 index f6cb7c4ffb3..00000000000 --- a/arch/arc/include/asm/barrier.h +++ /dev/null @@ -1,42 +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. - */ - -#ifndef __ASM_BARRIER_H -#define __ASM_BARRIER_H - -#ifndef __ASSEMBLY__ - -/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */ -#define mb() __asm__ __volatile__ ("" : : : "memory") -#define rmb() mb() -#define wmb() mb() -#define set_mb(var, value) do { var = value; mb(); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) -#define read_barrier_depends() mb() - -/* TODO-vineetg verify the correctness of macros here */ -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() rmb() -#define smp_wmb() wmb() -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#endif - -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() - -#define smp_read_barrier_depends() do { } while (0) - -#endif - -#endif diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index 647a83a8e75..ebc0cf3164d 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <asm/barrier.h> /* * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns. @@ -496,10 +497,6 @@ static inline __attribute__ ((const)) int __ffs(unsigned long word) */ #define ffz(x) __ffs(~(x)) -/* TODO does this affect uni-processor code */ -#define smp_mb__before_clear_bit() barrier() -#define smp_mb__after_clear_bit() barrier() - #include <asm-generic/bitops/hweight.h> #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h index 2ad8f9b1c54..5b18e94c667 100644 --- a/arch/arc/include/asm/bug.h +++ b/arch/arc/include/asm/bug.h @@ -18,9 +18,8 @@ struct task_struct; void show_regs(struct pt_regs *regs); void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs); void show_kernel_fault_diag(const char *str, struct pt_regs *regs, - unsigned long address, unsigned long cause_reg); -void die(const char *str, struct pt_regs *regs, unsigned long address, - unsigned long cause_reg); + unsigned long address); +void die(const char *str, struct pt_regs *regs, unsigned long address); #define BUG() do { \ dump_stack(); \ diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index d5555fe4742..b3c750979aa 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -17,22 +17,14 @@ #endif #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) +#define CACHE_LINE_MASK (~(L1_CACHE_BYTES - 1)) -#define ARC_ICACHE_WAYS 2 -#define ARC_DCACHE_WAYS 4 - -/* Helpers */ -#define ARC_ICACHE_LINE_LEN L1_CACHE_BYTES -#define ARC_DCACHE_LINE_LEN L1_CACHE_BYTES - -#define ICACHE_LINE_MASK (~(ARC_ICACHE_LINE_LEN - 1)) -#define DCACHE_LINE_MASK (~(ARC_DCACHE_LINE_LEN - 1)) - -#if ARC_ICACHE_LINE_LEN != ARC_DCACHE_LINE_LEN -#error "Need to fix some code as I/D cache lines not same" -#else -#define is_not_cache_aligned(p) ((unsigned long)p & (~DCACHE_LINE_MASK)) -#endif +/* + * ARC700 doesn't cache any access in top 256M. + * Ideal for wiring memory mapped peripherals as we don't need to do + * explicit uncached accesses (LD.di/ST.di) hence more portable drivers + */ +#define ARC_UNCACHED_ADDR_SPACE 0xc0000000 #ifndef __ASSEMBLY__ @@ -57,16 +49,37 @@ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -/* - * ARC700 doesn't cache any access in top 256M. - * Ideal for wiring memory mapped peripherals as we don't need to do - * explicit uncached accesses (LD.di/ST.di) hence more portable drivers - */ -#define ARC_UNCACHED_ADDR_SPACE 0xc0000000 - extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); -extern void __init read_decode_cache_bcr(void); +extern void read_decode_cache_bcr(void); + +#endif /* !__ASSEMBLY__ */ + +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#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 + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#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 +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index ef62682e8d9..6abc4972bc9 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -81,16 +81,19 @@ void flush_anon_page(struct vm_area_struct *vma, #endif /* CONFIG_ARC_CACHE_VIPT_ALIASING */ /* + * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default + * This works around some PIO based drivers which don't call flush_dcache_page + * to record that they dirtied the dcache + */ +#define PG_dc_clean PG_arch_1 + +/* * Simple wrapper over config option * Bootup code ensures that hardware matches kernel configuration */ static inline int cache_is_vipt_aliasing(void) { -#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING - return 1; -#else - return 0; -#endif + return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); } #define CACHE_COLOR(addr) (((unsigned long)(addr) >> (PAGE_SHIFT)) & 1) diff --git a/arch/arc/include/asm/defines.h b/arch/arc/include/asm/defines.h deleted file mode 100644 index 6097bb439cc..00000000000 --- a/arch/arc/include/asm/defines.h +++ /dev/null @@ -1,56 +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. - */ - -#ifndef __ARC_ASM_DEFINES_H__ -#define __ARC_ASM_DEFINES_H__ - -#if defined(CONFIG_ARC_MMU_V1) -#define CONFIG_ARC_MMU_VER 1 -#elif defined(CONFIG_ARC_MMU_V2) -#define CONFIG_ARC_MMU_VER 2 -#elif defined(CONFIG_ARC_MMU_V3) -#define CONFIG_ARC_MMU_VER 3 -#endif - -#ifdef CONFIG_ARC_HAS_LLSC -#define __CONFIG_ARC_HAS_LLSC_VAL 1 -#else -#define __CONFIG_ARC_HAS_LLSC_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_SWAPE -#define __CONFIG_ARC_HAS_SWAPE_VAL 1 -#else -#define __CONFIG_ARC_HAS_SWAPE_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_RTSC -#define __CONFIG_ARC_HAS_RTSC_VAL 1 -#else -#define __CONFIG_ARC_HAS_RTSC_VAL 0 -#endif - -#ifdef CONFIG_ARC_MMU_SASID -#define __CONFIG_ARC_MMU_SASID_VAL 1 -#else -#define __CONFIG_ARC_MMU_SASID_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_ICACHE -#define __CONFIG_ARC_HAS_ICACHE 1 -#else -#define __CONFIG_ARC_HAS_ICACHE 0 -#endif - -#ifdef CONFIG_ARC_HAS_DCACHE -#define __CONFIG_ARC_HAS_DCACHE 1 -#else -#define __CONFIG_ARC_HAS_DCACHE 0 -#endif - -#endif /* __ARC_ASM_DEFINES_H__ */ diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index 442ce5d0f70..43de3025698 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -53,11 +53,10 @@ static inline void __udelay(unsigned long usecs) { unsigned long loops; - /* (long long) cast ensures 64 bit MPY - real or emulated + /* (u64) cast ensures 64 bit MPY - real or emulated * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops */ - loops = ((long long)(usecs * 4295 * HZ) * - (long long)(loops_per_jiffy)) >> 32; + loops = ((u64) usecs * 4295 * HZ * loops_per_jiffy) >> 32; __delay(loops); } diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index eb2ae53187d..884081099f8 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -38,6 +38,7 @@ #include <asm/ptrace.h> #include <asm/processor.h> /* For VMALLOC_START */ #include <asm/thread_info.h> /* For THREAD_SIZE */ +#include <asm/mmu.h> /* Note on the LD/ST addr modes with addr reg wback * @@ -50,194 +51,177 @@ * Eff Addr for load = [reg2] */ +.macro PUSH reg + st.a \reg, [sp, -4] +.endm + +.macro PUSHAX aux + lr r9, [\aux] + PUSH r9 +.endm + +.macro POP reg + ld.ab \reg, [sp, 4] +.endm + +.macro POPAX aux + POP r9 + sr r9, [\aux] +.endm + /*-------------------------------------------------------------- - * Save caller saved registers (scratch registers) ( r0 - r12 ) - * Registers are pushed / popped in the order defined in struct ptregs - * in asm/ptrace.h + * Helpers to save/restore Scratch Regs: + * used by Interrupt/Exception Prologue/Epilogue *-------------------------------------------------------------*/ -.macro SAVE_CALLER_SAVED - st.a r0, [sp, -4] - st.a r1, [sp, -4] - st.a r2, [sp, -4] - st.a r3, [sp, -4] - st.a r4, [sp, -4] - st.a r5, [sp, -4] - st.a r6, [sp, -4] - st.a r7, [sp, -4] - st.a r8, [sp, -4] - st.a r9, [sp, -4] - st.a r10, [sp, -4] - st.a r11, [sp, -4] - st.a r12, [sp, -4] +.macro SAVE_R0_TO_R12 + PUSH r0 + PUSH r1 + PUSH r2 + PUSH r3 + PUSH r4 + PUSH r5 + PUSH r6 + PUSH r7 + PUSH r8 + PUSH r9 + PUSH r10 + PUSH r11 + PUSH r12 +.endm + +.macro RESTORE_R12_TO_R0 + POP r12 + POP r11 + POP r10 + POP r9 + POP r8 + POP r7 + POP r6 + POP r5 + POP r4 + POP r3 + POP r2 + POP r1 + POP r0 + +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif .endm /*-------------------------------------------------------------- - * Restore caller saved registers (scratch registers) + * Helpers to save/restore callee-saved regs: + * used by several macros below *-------------------------------------------------------------*/ -.macro RESTORE_CALLER_SAVED - ld.ab r12, [sp, 4] - ld.ab r11, [sp, 4] - ld.ab r10, [sp, 4] - ld.ab r9, [sp, 4] - ld.ab r8, [sp, 4] - ld.ab r7, [sp, 4] - ld.ab r6, [sp, 4] - ld.ab r5, [sp, 4] - ld.ab r4, [sp, 4] - ld.ab r3, [sp, 4] - ld.ab r2, [sp, 4] - ld.ab r1, [sp, 4] - ld.ab r0, [sp, 4] +.macro SAVE_R13_TO_R24 + PUSH r13 + PUSH r14 + PUSH r15 + PUSH r16 + PUSH r17 + PUSH r18 + PUSH r19 + PUSH r20 + PUSH r21 + PUSH r22 + PUSH r23 + PUSH r24 +.endm + +.macro RESTORE_R24_TO_R13 + POP r24 + POP r23 + POP r22 + POP r21 + POP r20 + POP r19 + POP r18 + POP r17 + POP r16 + POP r15 + POP r14 + POP r13 .endm +#define OFF_USER_R25_FROM_R24 (SZ_CALLEE_REGS + SZ_PT_REGS - 8)/4 /*-------------------------------------------------------------- - * Save callee saved registers (non scratch registers) ( r13 - r25 ) - * on kernel stack. - * User mode callee regs need to be saved in case of - * -fork and friends for replicating from parent to child - * -before going into do_signal( ) for ptrace/core-dump - * Special case handling is required for r25 in case it is used by kernel - * for caching task ptr. Low level exception/ISR save user mode r25 - * into task->thread.user_r25. So it needs to be retrieved from there and - * saved into kernel stack with rest of callee reg-file + * Collect User Mode callee regs as struct callee_regs - needed by + * fork/do_signal/unaligned-access-emulation. + * (By default only scratch regs are saved on entry to kernel) + * + * Special handling for r25 if used for caching Task Pointer. + * It would have been saved in task->thread.user_r25 already, but to keep + * the interface same it is copied into regular r25 placeholder in + * struct callee_regs. *-------------------------------------------------------------*/ .macro SAVE_CALLEE_SAVED_USER - st.a r13, [sp, -4] - st.a r14, [sp, -4] - st.a r15, [sp, -4] - st.a r16, [sp, -4] - st.a r17, [sp, -4] - st.a r18, [sp, -4] - st.a r19, [sp, -4] - st.a r20, [sp, -4] - st.a r21, [sp, -4] - st.a r22, [sp, -4] - st.a r23, [sp, -4] - st.a r24, [sp, -4] + + SAVE_R13_TO_R24 #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it on stack - ld r12, [r25, TASK_THREAD + THREAD_USER_R25] + ld.as r12, [sp, OFF_USER_R25_FROM_R24] st.a r12, [sp, -4] #else - st.a r25, [sp, -4] + PUSH r25 #endif - /* move up by 1 word to "create" callee_regs->"stack_place_holder" */ - sub sp, sp, 4 .endm /*-------------------------------------------------------------- - * Save callee saved registers (non scratch registers) ( r13 - r25 ) - * kernel mode callee regs needed to be saved in case of context switch - * If r25 is used for caching task pointer then that need not be saved - * as it can be re-created from current task global + * Save kernel Mode callee regs at the time of Contect Switch. + * + * Special handling for r25 if used for caching Task Pointer. + * Kernel simply skips saving it since it will be loaded with + * incoming task pointer anyways *-------------------------------------------------------------*/ .macro SAVE_CALLEE_SAVED_KERNEL - st.a r13, [sp, -4] - st.a r14, [sp, -4] - st.a r15, [sp, -4] - st.a r16, [sp, -4] - st.a r17, [sp, -4] - st.a r18, [sp, -4] - st.a r19, [sp, -4] - st.a r20, [sp, -4] - st.a r21, [sp, -4] - st.a r22, [sp, -4] - st.a r23, [sp, -4] - st.a r24, [sp, -4] + + SAVE_R13_TO_R24 + #ifdef CONFIG_ARC_CURR_IN_REG - sub sp, sp, 8 -#else - st.a r25, [sp, -4] sub sp, sp, 4 +#else + PUSH r25 #endif .endm /*-------------------------------------------------------------- - * RESTORE_CALLEE_SAVED_KERNEL: - * Loads callee (non scratch) Reg File by popping from Kernel mode stack. - * This is reverse of SAVE_CALLEE_SAVED, - * - * NOTE: - * Ideally this shd only be called in switch_to for loading - * switched-IN task's CALLEE Reg File. - * For all other cases RESTORE_CALLEE_SAVED_FAST must be used - * which simply pops the stack w/o touching regs. + * Opposite of SAVE_CALLEE_SAVED_KERNEL *-------------------------------------------------------------*/ .macro RESTORE_CALLEE_SAVED_KERNEL - #ifdef CONFIG_ARC_CURR_IN_REG - add sp, sp, 8 /* skip callee_reg gutter and user r25 placeholder */ + add sp, sp, 4 /* skip usual r25 placeholder */ #else - add sp, sp, 4 /* skip "callee_regs->stack_place_holder" */ - ld.ab r25, [sp, 4] + POP r25 #endif - - ld.ab r24, [sp, 4] - ld.ab r23, [sp, 4] - ld.ab r22, [sp, 4] - ld.ab r21, [sp, 4] - ld.ab r20, [sp, 4] - ld.ab r19, [sp, 4] - ld.ab r18, [sp, 4] - ld.ab r17, [sp, 4] - ld.ab r16, [sp, 4] - ld.ab r15, [sp, 4] - ld.ab r14, [sp, 4] - ld.ab r13, [sp, 4] - + RESTORE_R24_TO_R13 .endm /*-------------------------------------------------------------- - * RESTORE_CALLEE_SAVED_USER: - * This is called after do_signal where tracer might have changed callee regs - * thus we need to restore the reg file. - * Special case handling is required for r25 in case it is used by kernel - * for caching task ptr. Ptrace would have modified on-kernel-stack value of - * r25, which needs to be shoved back into task->thread.user_r25 where from - * Low level exception/ISR return code will retrieve to populate with rest of - * callee reg-file. + * Opposite of SAVE_CALLEE_SAVED_USER + * + * ptrace tracer or unaligned-access fixup might have changed a user mode + * callee reg which is saved back to usual r25 storage location *-------------------------------------------------------------*/ .macro RESTORE_CALLEE_SAVED_USER - add sp, sp, 4 /* skip "callee_regs->stack_place_holder" */ - #ifdef CONFIG_ARC_CURR_IN_REG ld.ab r12, [sp, 4] - st r12, [r25, TASK_THREAD + THREAD_USER_R25] + st.as r12, [sp, OFF_USER_R25_FROM_R24] #else - ld.ab r25, [sp, 4] + POP r25 #endif - - ld.ab r24, [sp, 4] - ld.ab r23, [sp, 4] - ld.ab r22, [sp, 4] - ld.ab r21, [sp, 4] - ld.ab r20, [sp, 4] - ld.ab r19, [sp, 4] - ld.ab r18, [sp, 4] - ld.ab r17, [sp, 4] - ld.ab r16, [sp, 4] - ld.ab r15, [sp, 4] - ld.ab r14, [sp, 4] - ld.ab r13, [sp, 4] + RESTORE_R24_TO_R13 .endm /*-------------------------------------------------------------- * Super FAST Restore callee saved regs by simply re-adjusting SP *-------------------------------------------------------------*/ .macro DISCARD_CALLEE_SAVED_USER - add sp, sp, 14 * 4 -.endm - -/*-------------------------------------------------------------- - * Restore User mode r25 saved in task_struct->thread.user_r25 - *-------------------------------------------------------------*/ -.macro RESTORE_USER_R25 - ld r25, [r25, TASK_THREAD + THREAD_USER_R25] + add sp, sp, SZ_CALLEE_REGS .endm /*------------------------------------------------------------- @@ -252,7 +236,7 @@ ld \out, [\tsk, TASK_THREAD_INFO] /* Go to end of page where stack begins (grows upwards) */ - add2 \out, \out, (THREAD_SIZE - 4)/4 /* one word GUTTER */ + add2 \out, \out, (THREAD_SIZE)/4 .endm @@ -305,33 +289,28 @@ * safe-keeping not really needed, but it keeps the epilogue code * (SP restore) simpler/uniform. */ - b.d 77f - - st.a sp, [sp, -12] ; Make room for orig_r0 and orig_r8 + b.d 66f + mov r9, sp 88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */ GET_CURR_TASK_ON_CPU r9 -#ifdef CONFIG_ARC_CURR_IN_REG - - /* If current task pointer cached in r25, time to - * -safekeep USER r25 in task->thread_struct->user_r25 - * -load r25 with current task ptr - */ - st.as r25, [r9, (TASK_THREAD + THREAD_USER_R25)/4] - mov r25, r9 -#endif - /* With current tsk in r9, get it's kernel mode stack base */ GET_TSK_STACK_BASE r9, r9 -#ifdef PT_REGS_CANARY - st 0xabcdabcd, [r9, 0] +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, -12] ; Make room for orig_r0 and orig_r8 + 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 @@ -342,7 +321,7 @@ /* set SP to point to kernel mode stack */ mov sp, r9 -77: /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */ + /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */ .endm @@ -369,7 +348,7 @@ * @reg [OUT] &thread_info of "current" */ .macro GET_CURR_THR_INFO_FROM_SP reg - and \reg, sp, ~(THREAD_SIZE - 1) + bic \reg, sp, (THREAD_SIZE - 1) .endm /* @@ -386,7 +365,7 @@ * 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 ptregs. + * to be saved again on kernel mode stack, as part of pt_regs. *-------------------------------------------------------------*/ .macro EXCPN_PROLOG_FREEUP_REG reg #ifdef CONFIG_SMP @@ -405,6 +384,28 @@ .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. @@ -413,62 +414,25 @@ * Note that syscalls are implemented via TRAP which is also a exception * from CPU's point of view *-------------------------------------------------------------*/ -.macro SAVE_ALL_EXCEPTION marker +.macro SAVE_ALL_SYS - st \marker, [sp, 8] /* orig_r8 */ + 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_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - lr r9, [eret] - st.a r9, [sp, -4] - lr r9, [erstatus] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [erbta] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbeef - st r9, [sp, -4] -#endif - - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 -.endm - -/*-------------------------------------------------------------- - * Save scratch regs for exceptions - *-------------------------------------------------------------*/ -.macro SAVE_ALL_SYS - SAVE_ALL_EXCEPTION orig_r8_IS_EXCPN -.endm - -/*-------------------------------------------------------------- - * Save scratch regs for sys calls - *-------------------------------------------------------------*/ -.macro SAVE_ALL_TRAP - /* - * Setup pt_regs->orig_r8. - * Encode syscall number (r8) in upper short word of event type (r9) - * N.B. #1: This is already endian safe (see ptrace.h) - * #2: Only r9 can be used as scratch as it is already clobbered - * and it's contents are no longer needed by the latter part - * of exception prologue - */ - lsl r9, r8, 16 - or r9, r9, orig_r8_IS_SCALL - - SAVE_ALL_EXCEPTION 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 /*-------------------------------------------------------------- @@ -483,28 +447,22 @@ * by hardware and that is not good. *-------------------------------------------------------------*/ .macro RESTORE_ALL_SYS + POPAX erbta + POPAX lp_start + POPAX lp_end - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] - sr r9, [erbta] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [erstatus] - ld.ab r9, [sp, 4] - sr r9, [eret] - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + 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 and orig_r8 skipped automatically */ + /* orig_r0, ECR, user_r25 skipped automatically */ .endm @@ -513,9 +471,7 @@ *-------------------------------------------------------------*/ .macro SAVE_ALL_INT1 - /* restore original r9 , saved in int1_saved_reg - * It will be saved on stack in macro: SAVE_CALLER_SAVED - */ + /* restore original r9 to be saved as part of reg-file */ #ifdef CONFIG_SMP lr r9, [ARC_REG_SCRATCH_DATA0] #else @@ -523,29 +479,19 @@ #endif /* now we are ready to save the remaining context :) */ - st orig_r8_IS_IRQ1, [sp, 8] /* Event Type */ + st event_IRQ1, [sp, 8] /* Dummy ECR */ st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - SAVE_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - st.a ilink1, [sp, -4] - lr r9, [status32_l1] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [bta_l1] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbee1 - st r9, [sp, -4] -#endif - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 + + 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 @@ -558,30 +504,19 @@ ld r9, [@int2_saved_reg] /* now we are ready to save the remaining context :) */ - st orig_r8_IS_IRQ2, [sp, 8] /* Event Type */ + st event_IRQ2, [sp, 8] /* Dummy ECR */ st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - SAVE_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - st.a ilink2, [sp, -4] - lr r9, [status32_l2] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [bta_l2] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbee2 - st r9, [sp, -4] -#endif - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 + 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 /*-------------------------------------------------------------- @@ -595,52 +530,41 @@ *-------------------------------------------------------------*/ .macro RESTORE_ALL_INT1 - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] /* Actual reg file */ - sr r9, [bta_l1] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [status32_l1] - ld.ab r9, [sp, 4] - mov ilink1, r9 - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + 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 and orig_r8 skipped automatically */ + /* orig_r0, ECR, user_r25 skipped automatically */ .endm .macro RESTORE_ALL_INT2 - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] - sr r9, [bta_l2] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [status32_l2] - ld.ab r9, [sp, 4] - mov ilink2, r9 - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + POPAX bta_l2 + POPAX lp_start + POPAX lp_end - ld sp, [sp] /* restore original sp */ - /* orig_r0 and orig_r8 skipped automatically */ + 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 diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 473424d7528..334ce7017a1 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -100,6 +100,10 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } +#define readb_relaxed readb +#define readw_relaxed readw +#define readl_relaxed readl + #include <asm-generic/io.h> #endif /* _ASM_ARC_IO_H */ diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 57898a17eb8..fb4efb64897 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -18,9 +18,7 @@ #include <asm-generic/irq.h> -extern void __init arc_init_IRQ(void); -extern int __init get_hw_config_num_irq(void); - -void __cpuinit arc_local_timer_setup(unsigned int cpu); +extern void arc_init_IRQ(void); +void arc_local_timer_setup(void); #endif diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index eac07166820..cb7efc29f16 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -19,6 +19,26 @@ #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__ /****************************************************************** @@ -131,23 +151,38 @@ static inline void arch_unmask_irq(unsigned int irq) #else -.macro IRQ_DISABLE scratch - lr \scratch, [status32] - bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) - flag \scratch +#ifdef CONFIG_TRACE_IRQFLAGS + +.macro TRACE_ASM_IRQ_DISABLE + bl trace_hardirqs_off +.endm + +.macro TRACE_ASM_IRQ_ENABLE + bl trace_hardirqs_on .endm -.macro IRQ_DISABLE_SAVE scratch, save +#else + +.macro TRACE_ASM_IRQ_DISABLE +.endm + +.macro TRACE_ASM_IRQ_ENABLE +.endm + +#endif + +.macro IRQ_DISABLE scratch lr \scratch, [status32] - mov \save, \scratch /* Make a copy */ 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__ */ diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index 4930957ca3d..b65fca7ffeb 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -31,7 +31,7 @@ static inline void arch_kgdb_breakpoint(void) __asm__ __volatile__ ("trap_s 0x4\n"); } -extern void kgdb_trap(struct pt_regs *regs, int param); +extern void kgdb_trap(struct pt_regs *regs); enum arc700_linux_regnums { _R0 = 0, @@ -53,7 +53,7 @@ enum arc700_linux_regnums { }; #else -#define kgdb_trap(regs, param) +#define kgdb_trap(regs) #endif #endif /* __ARC_KGDB_H__ */ diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 4d9c211fce7..944dbedb38b 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -50,11 +50,9 @@ struct kprobe_ctlblk { int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause); void kretprobe_trampoline(void); -void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs); +void trap_is_kprobe(unsigned long address, struct pt_regs *regs); #else -static void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs) +static void trap_is_kprobe(unsigned long address, struct pt_regs *regs) { } #endif diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index 0283e9e44e0..5faad17118b 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -11,19 +11,7 @@ #ifdef __ASSEMBLY__ -/* Can't use the ENTRY macro in linux/linkage.h - * gas considers ';' as comment vs. newline - */ -.macro ARC_ENTRY name - .global \name - .align 4 - \name: -.endm - -.macro ARC_EXIT name -#define ASM_PREV_SYM_ADDR(name) .-##name - .size \ name, ASM_PREV_SYM_ADDR(\name) -.endm +#define ASM_NL ` /* use '`' to mark new line in macro */ /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index 9998dc846eb..e8993a2be6c 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -51,22 +51,12 @@ struct machine_desc { /* * Current machine - only accessible during boot. */ -extern struct machine_desc *machine_desc; +extern const struct machine_desc *machine_desc; /* * Machine type table - also only accessible during boot */ -extern struct machine_desc __arch_info_begin[], __arch_info_end[]; -#define for_each_machine_desc(p) \ - for (p = __arch_info_begin; p < __arch_info_end; p++) - -static inline struct machine_desc *default_machine_desc(void) -{ - /* the default machine is the last one linked in */ - if (__arch_info_end - 1 < __arch_info_begin) - return NULL; - return __arch_info_end - 1; -} +extern const struct machine_desc __arch_info_begin[], __arch_info_end[]; /* * Set of macros to define architecture features. @@ -81,7 +71,6 @@ __attribute__((__section__(".arch.info.init"))) = { \ #define MACHINE_END \ }; -extern struct machine_desc *setup_machine_fdt(void *dt); -extern void __init copy_devtree(void); +extern const struct machine_desc *setup_machine_fdt(void *dt); #endif diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 56b02320f1a..8c84ae98c33 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -9,15 +9,58 @@ #ifndef _ASM_ARC_MMU_H #define _ASM_ARC_MMU_H +#if defined(CONFIG_ARC_MMU_V1) +#define CONFIG_ARC_MMU_VER 1 +#elif defined(CONFIG_ARC_MMU_V2) +#define CONFIG_ARC_MMU_VER 2 +#elif defined(CONFIG_ARC_MMU_V3) +#define CONFIG_ARC_MMU_VER 3 +#endif + +/* MMU Management regs */ +#define ARC_REG_MMU_BCR 0x06f +#define ARC_REG_TLBPD0 0x405 +#define ARC_REG_TLBPD1 0x406 +#define ARC_REG_TLBINDEX 0x407 +#define ARC_REG_TLBCOMMAND 0x408 +#define ARC_REG_PID 0x409 +#define ARC_REG_SCRATCH_DATA0 0x418 + +/* Bits in MMU PID register */ +#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ + +/* Error code if probe fails */ +#define TLB_LKUP_ERR 0x80000000 + +#define TLB_DUP_ERR (TLB_LKUP_ERR | 0x00000001) + +/* TLB Commands */ +#define TLBWrite 0x1 +#define TLBRead 0x2 +#define TLBGetIndex 0x3 +#define TLBProbe 0x4 + +#if (CONFIG_ARC_MMU_VER >= 2) +#define TLBWriteNI 0x5 /* write JTLB without inv uTLBs */ +#define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ +#endif + #ifndef __ASSEMBLY__ typedef struct { - unsigned long asid; /* Pvt Addr-Space ID for mm */ -#ifdef CONFIG_ARC_TLB_DBG - struct task_struct *tsk; -#endif + unsigned long asid[NR_CPUS]; /* 8 bit MMU PID + Generation cycle */ } mm_context_t; +#ifdef CONFIG_ARC_DBG_TLB_PARANOIA +void tlb_paranoid_check(unsigned int mm_asid, unsigned long address); +#else +#define tlb_paranoid_check(a, b) #endif +void arc_mmu_init(void); +extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len); +void read_decode_mmu_bcr(void); + +#endif /* !__ASSEMBLY__ */ + #endif diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 0d71fb11b57..1fd467ef658 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -30,99 +30,72 @@ * "Fast Context Switch" i.e. no TLB flush on ctxt-switch * * Linux assigns each task a unique ASID. A simple round-robin allocation - * of H/w ASID is done using software tracker @asid_cache. + * of H/w ASID is done using software tracker @asid_cpu. * When it reaches max 255, the allocation cycle starts afresh by flushing * the entire TLB and wrapping ASID back to zero. * - * For book-keeping, Linux uses a couple of data-structures: - * -mm_struct has an @asid field to keep a note of task's ASID (needed at the - * time of say switch_mm( ) - * -An array of mm structs @asid_mm_map[] for asid->mm the reverse mapping, - * given an ASID, finding the mm struct associated. - * - * The round-robin allocation algorithm allows for ASID stealing. - * If asid tracker is at "x-1", a new req will allocate "x", even if "x" was - * already assigned to another (switched-out) task. Obviously the prev owner - * is marked with an invalid ASID to make it request for a new ASID when it - * gets scheduled next time. However its TLB entries (with ASID "x") could - * exist, which must be cleared before the same ASID is used by the new owner. - * Flushing them would be plausible but costly solution. Instead we force a - * allocation policy quirk, which ensures that a stolen ASID won't have any - * TLB entries associates, alleviating the need to flush. - * The quirk essentially is not allowing ASID allocated in prev cycle - * to be used past a roll-over in the next cycle. - * When this happens (i.e. task ASID > asid tracker), task needs to refresh - * its ASID, aligning it to current value of tracker. If the task doesn't get - * scheduled past a roll-over, hence its ASID is not yet realigned with - * tracker, such ASID is anyways safely reusable because it is - * gauranteed that TLB entries with that ASID wont exist. + * A new allocation cycle, post rollover, could potentially reassign an ASID + * to a different task. Thus the rule is to refresh the ASID in a new cycle. + * The 32 bit @asid_cpu (and mm->asid) have 8 bits MMU PID and rest 24 bits + * serve as cycle/generation indicator and natural 32 bit unsigned math + * automagically increments the generation when lower 8 bits rollover. */ -#define FIRST_ASID 0 -#define MAX_ASID 255 /* 8 bit PID field in PID Aux reg */ -#define NO_ASID (MAX_ASID + 1) /* ASID Not alloc to mmu ctxt */ -#define NUM_ASID ((MAX_ASID - FIRST_ASID) + 1) +#define MM_CTXT_ASID_MASK 0x000000ff /* MMU PID reg :8 bit PID */ +#define MM_CTXT_CYCLE_MASK (~MM_CTXT_ASID_MASK) + +#define MM_CTXT_FIRST_CYCLE (MM_CTXT_ASID_MASK + 1) +#define MM_CTXT_NO_ASID 0UL -/* ASID to mm struct mapping */ -extern struct mm_struct *asid_mm_map[NUM_ASID + 1]; +#define asid_mm(mm, cpu) mm->context.asid[cpu] +#define hw_pid(mm, cpu) (asid_mm(mm, cpu) & MM_CTXT_ASID_MASK) -extern int asid_cache; +DECLARE_PER_CPU(unsigned int, asid_cache); +#define asid_cpu(cpu) per_cpu(asid_cache, cpu) /* - * Assign a new ASID to task. If the task already has an ASID, it is - * relinquished. + * Get a new ASID if task doesn't have a valid one (unalloc or from prev cycle) + * Also set the MMU PID register to existing/updated ASID */ static inline void get_new_mmu_context(struct mm_struct *mm) { - struct mm_struct *prev_owner; + const unsigned int cpu = smp_processor_id(); unsigned long flags; local_irq_save(flags); /* - * Relinquish the currently owned ASID (if any). - * Doing unconditionally saves a cmp-n-branch; for already unused - * ASID slot, the value was/remains NULL + * Move to new ASID if it was not from current alloc-cycle/generation. + * This is done by ensuring that the generation bits in both mm->ASID + * and cpu's ASID counter are exactly same. + * + * Note: Callers needing new ASID unconditionally, independent of + * generation, e.g. local_flush_tlb_mm() for forking parent, + * first need to destroy the context, setting it to invalid + * value. */ - asid_mm_map[mm->context.asid] = (struct mm_struct *)NULL; + if (!((asid_mm(mm, cpu) ^ asid_cpu(cpu)) & MM_CTXT_CYCLE_MASK)) + goto set_hw; - /* move to new ASID */ - if (++asid_cache > MAX_ASID) { /* ASID roll-over */ - asid_cache = FIRST_ASID; - flush_tlb_all(); - } + /* move to new ASID and handle rollover */ + if (unlikely(!(++asid_cpu(cpu) & MM_CTXT_ASID_MASK))) { - /* - * Is next ASID already owned by some-one else (we are stealing it). - * If so, let the orig owner be aware of this, so when it runs, it - * asks for a brand new ASID. This would only happen for a long-lived - * task with ASID from prev allocation cycle (before ASID roll-over). - * - * This might look wrong - if we are re-using some other task's ASID, - * won't we use it's stale TLB entries too. Actually switch_mm( ) takes - * care of such a case: it ensures that task with ASID from prev alloc - * cycle, when scheduled will refresh it's ASID: see switch_mm( ) below - * The stealing scenario described here will only happen if that task - * didn't get a chance to refresh it's ASID - implying stale entries - * won't exist. - */ - prev_owner = asid_mm_map[asid_cache]; - if (prev_owner) - prev_owner->context.asid = NO_ASID; + local_flush_tlb_all(); + + /* + * Above checke for rollover of 8 bit ASID in 32 bit container. + * If the container itself wrapped around, set it to a non zero + * "generation" to distinguish from no context + */ + if (!asid_cpu(cpu)) + asid_cpu(cpu) = MM_CTXT_FIRST_CYCLE; + } /* Assign new ASID to tsk */ - asid_mm_map[asid_cache] = mm; - mm->context.asid = asid_cache; - -#ifdef CONFIG_ARC_TLB_DBG - pr_info("ARC_TLB_DBG: NewMM=0x%x OldMM=0x%x task_struct=0x%x Task: %s," - " pid:%u, assigned asid:%lu\n", - (unsigned int)mm, (unsigned int)prev_owner, - (unsigned int)(mm->context.tsk), (mm->context.tsk)->comm, - (mm->context.tsk)->pid, mm->context.asid); -#endif + asid_mm(mm, cpu) = asid_cpu(cpu); - write_aux_reg(ARC_REG_PID, asid_cache | MMU_ENABLE); +set_hw: + write_aux_reg(ARC_REG_PID, hw_pid(mm, cpu) | MMU_ENABLE); local_irq_restore(flags); } @@ -134,59 +107,61 @@ static inline void get_new_mmu_context(struct mm_struct *mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { - mm->context.asid = NO_ASID; -#ifdef CONFIG_ARC_TLB_DBG - mm->context.tsk = tsk; -#endif + int i; + + for_each_possible_cpu(i) + asid_mm(mm, i) = MM_CTXT_NO_ASID; + return 0; } +static inline void destroy_context(struct mm_struct *mm) +{ + unsigned long flags; + + /* Needed to elide CONFIG_DEBUG_PREEMPT warning */ + local_irq_save(flags); + asid_mm(mm, smp_processor_id()) = MM_CTXT_NO_ASID; + local_irq_restore(flags); +} + /* Prepare the MMU for task: setup PID reg with allocated ASID If task doesn't have an ASID (never alloc or stolen, get a new ASID) */ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + const int cpu = smp_processor_id(); + + /* + * Note that the mm_cpumask is "aggregating" only, we don't clear it + * for the switched-out task, unlike some other arches. + * It is used to enlist cpus for sending TLB flush IPIs and not sending + * it to CPUs where a task once ran-on, could cause stale TLB entry + * re-use, specially for a multi-threaded task. + * e.g. T1 runs on C1, migrates to C3. T2 running on C2 munmaps. + * For a non-aggregating mm_cpumask, IPI not sent C1, and if T1 + * were to re-migrate to C1, it could access the unmapped region + * via any existing stale TLB entries. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + #ifndef CONFIG_SMP /* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */ write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); #endif - /* - * Get a new ASID if task doesn't have a valid one. Possible when - * -task never had an ASID (fresh after fork) - * -it's ASID was stolen - past an ASID roll-over. - * -There's a third obscure scenario (if this task is running for the - * first time afer an ASID rollover), where despite having a valid - * ASID, we force a get for new ASID - see comments at top. - * - * Both the non-alloc scenario and first-use-after-rollover can be - * detected using the single condition below: NO_ASID = 256 - * while asid_cache is always a valid ASID value (0-255). - */ - if (next->context.asid > asid_cache) { - get_new_mmu_context(next); - } else { - /* - * XXX: This will never happen given the chks above - * BUG_ON(next->context.asid > MAX_ASID); - */ - write_aux_reg(ARC_REG_PID, next->context.asid | MMU_ENABLE); - } - + get_new_mmu_context(next); } -static inline void destroy_context(struct mm_struct *mm) -{ - unsigned long flags; - - local_irq_save(flags); - - asid_mm_map[mm->context.asid] = NULL; - mm->context.asid = NO_ASID; - - local_irq_restore(flags); -} +/* + * Called at the time of execve() to get a new ASID + * Note the subtlety here: get_new_mmu_context() behaves differently here + * vs. in switch_mm(). Here it always returns a new ASID, because mm has + * an unallocated "initial" value, while in latter, it moves to a new ASID, + * only if it was unallocated + */ +#define activate_mm(prev, next) switch_mm(prev, next, NULL) /* it seemed that deactivate_mm( ) is a reasonable place to do book-keeping * for retiring-mm. However destroy_context( ) still needs to do that because @@ -197,17 +172,6 @@ static inline void destroy_context(struct mm_struct *mm) */ #define deactivate_mm(tsk, mm) do { } while (0) -static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) -{ -#ifndef CONFIG_SMP - write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); -#endif - - /* Unconditionally get a new ASID */ - get_new_mmu_context(next); - -} - #define enter_lazy_tlb(mm, tsk) #endif /* __ASM_ARC_MMU_CONTEXT_H */ diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index ab84bf131fe..9c8aa41e45c 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -96,13 +96,8 @@ typedef unsigned long pgtable_t; #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) -/* Default Permissions for page, used in mmap.c */ -#ifdef CONFIG_ARC_STACK_NONEXEC +/* Default Permissions for stack/heaps pages (Non Executable) */ #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE) -#else -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#endif #define WANT_PAGE_VIRTUAL 1 diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 115ad96480e..cbf755e32a0 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -1,5 +1,7 @@ /* - * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com) + * Linux performance counter support for ARC + * + * Copyright (C) 2011-2013 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 @@ -10,4 +12,204 @@ #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 + +#define ARC_REG_CC_BUILD 0xF6 +#define ARC_REG_CC_INDEX 0x240 +#define ARC_REG_CC_NAME0 0x241 +#define ARC_REG_CC_NAME1 0x242 + +#define ARC_REG_PCT_BUILD 0xF5 +#define ARC_REG_PCT_COUNTL 0x250 +#define ARC_REG_PCT_COUNTH 0x251 +#define ARC_REG_PCT_SNAPL 0x252 +#define ARC_REG_PCT_SNAPH 0x253 +#define ARC_REG_PCT_CONFIG 0x254 +#define ARC_REG_PCT_CONTROL 0x255 +#define ARC_REG_PCT_INDEX 0x256 + +#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; +#else + unsigned int v:8, s:2, r:6, c:8, m:8; +#endif +}; + +struct arc_reg_cc_build { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int c:16, r:8, v:8; +#else + unsigned int v:8, r:8, c:16; +#endif +}; + +#define PERF_COUNT_ARC_DCLM (PERF_COUNT_HW_MAX + 0) +#define PERF_COUNT_ARC_DCSM (PERF_COUNT_HW_MAX + 1) +#define PERF_COUNT_ARC_ICM (PERF_COUNT_HW_MAX + 2) +#define PERF_COUNT_ARC_BPOK (PERF_COUNT_HW_MAX + 3) +#define PERF_COUNT_ARC_EDTLB (PERF_COUNT_HW_MAX + 4) +#define PERF_COUNT_ARC_EITLB (PERF_COUNT_HW_MAX + 5) +#define PERF_COUNT_ARC_HW_MAX (PERF_COUNT_HW_MAX + 6) + +/* + * The "generalized" performance events seem to really be a copy + * of the available events on x86 processors; the mapping to ARC + * events is not always possible 1-to-1. Fortunately, there doesn't + * seem to be an exact definition for these events, so we can cheat + * a bit where necessary. + * + * In particular, the following PERF events may behave a bit differently + * compared to other architectures: + * + * PERF_COUNT_HW_CPU_CYCLES + * Cycles not in halted state + * + * PERF_COUNT_HW_REF_CPU_CYCLES + * Reference cycles not in halted state, same as PERF_COUNT_HW_CPU_CYCLES + * for now as we don't do Dynamic Voltage/Frequency Scaling (yet) + * + * PERF_COUNT_HW_BUS_CYCLES + * Unclear what this means, Intel uses 0x013c, which according to + * their datasheet means "unhalted reference cycles". It sounds similar + * to PERF_COUNT_HW_REF_CPU_CYCLES, and we use the same counter for it. + * + * PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * The ARC 700 can either measure stalls per pipeline stage, or all stalls + * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND + * and all pipeline flushes (e.g. caused by mispredicts, etc.) to + * STALLED_CYCLES_FRONTEND. + * + * We could start multiple performance counters and combine everything + * afterwards, but that makes it complicated. + * + * Note that I$ cache misses aren't counted by either of the two! + */ + +static const char * const arc_pmu_ev_hw_map[] = { + [PERF_COUNT_HW_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_BUS_CYCLES] = "crun", + [PERF_COUNT_HW_INSTRUCTIONS] = "iall", + [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", + [PERF_COUNT_ARC_DCLM] = "dclm", + [PERF_COUNT_ARC_DCSM] = "dcsm", + [PERF_COUNT_ARC_ICM] = "icm", + [PERF_COUNT_ARC_BPOK] = "bpok", + [PERF_COUNT_ARC_EDTLB] = "edtlb", + [PERF_COUNT_ARC_EITLB] = "eitlb", +}; + +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xffff + +static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + #endif /* __ASM_PERF_EVENT_H */ diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 36a9f20c21a..81208bfd9dc 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -105,11 +105,16 @@ static inline pgtable_t 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()); - if (pte_pg) { - memzero((void *)pte_pg, PTRS_PER_PTE * 4); - pgtable_page_ctor(virt_to_page(pte_pg)); + if (!pte_pg) + return 0; + memzero((void *)pte_pg, PTRS_PER_PTE * 4); + page = virt_to_page(pte_pg); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return 0; } return pte_pg; diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 95b1522212a..6b0b7f7ef78 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -57,43 +57,31 @@ #define _PAGE_ACCESSED (1<<1) /* Page is accessed (S) */ #define _PAGE_CACHEABLE (1<<2) /* Page is cached (H) */ -#define _PAGE_U_EXECUTE (1<<3) /* Page has user execute perm (H) */ -#define _PAGE_U_WRITE (1<<4) /* Page has user write perm (H) */ -#define _PAGE_U_READ (1<<5) /* Page has user read perm (H) */ -#define _PAGE_K_EXECUTE (1<<6) /* Page has kernel execute perm (H) */ -#define _PAGE_K_WRITE (1<<7) /* Page has kernel write perm (H) */ -#define _PAGE_K_READ (1<<8) /* Page has kernel perm (H) */ -#define _PAGE_GLOBAL (1<<9) /* Page is global (H) */ -#define _PAGE_MODIFIED (1<<10) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<10) /* page cache/ swap (S) */ -#define _PAGE_PRESENT (1<<11) /* TLB entry is valid (H) */ +#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_FILE (1<<7) /* page cache/ swap (S) */ +#define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ +#define _PAGE_PRESENT (1<<10) /* TLB entry is valid (H) */ -#else +#else /* MMU v3 onwards */ -/* PD1 */ #define _PAGE_CACHEABLE (1<<0) /* Page is cached (H) */ -#define _PAGE_U_EXECUTE (1<<1) /* Page has user execute perm (H) */ -#define _PAGE_U_WRITE (1<<2) /* Page has user write perm (H) */ -#define _PAGE_U_READ (1<<3) /* Page has user read perm (H) */ -#define _PAGE_K_EXECUTE (1<<4) /* Page has kernel execute perm (H) */ -#define _PAGE_K_WRITE (1<<5) /* Page has kernel write perm (H) */ -#define _PAGE_K_READ (1<<6) /* Page has kernel perm (H) */ -#define _PAGE_ACCESSED (1<<7) /* Page is accessed (S) */ - -/* PD0 */ +#define _PAGE_EXECUTE (1<<1) /* Page has user execute perm (H) */ +#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_FILE (1<<6) /* page cache/ swap (S) */ #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<9) /* TLB entry is valid (H) */ -#define _PAGE_SHARED_CODE (1<<10) /* Shared Code page with cmn vaddr +#define _PAGE_SHARED_CODE (1<<11) /* Shared Code page with cmn vaddr usable for shared TLB entries (H) */ - -#define _PAGE_MODIFIED (1<<11) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<12) /* page cache/ swap (S) */ - -#define _PAGE_SHARED_CODE_H (1<<31) /* Hardware counterpart of above */ #endif -/* Kernel allowed all permissions for all pages */ -#define _K_PAGE_PERMS (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ | \ +/* vmalloc permissions */ +#define _K_PAGE_PERMS (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \ _PAGE_GLOBAL | _PAGE_PRESENT) #ifdef CONFIG_ARC_CACHE_PAGES @@ -109,10 +97,6 @@ */ #define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE) -#define _PAGE_READ (_PAGE_U_READ | _PAGE_K_READ) -#define _PAGE_WRITE (_PAGE_U_WRITE | _PAGE_K_WRITE) -#define _PAGE_EXECUTE (_PAGE_U_EXECUTE | _PAGE_K_EXECUTE) - /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED) @@ -126,8 +110,8 @@ #define PAGE_SHARED PAGE_U_W_R -/* While kernel runs out of unstrslated space, vmalloc/modules use a chunk of - * kernel vaddr space - visible in all addr spaces, but kernel mode only +/* While kernel runs out of unstranslated space, vmalloc/modules use a chunk of + * 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) @@ -135,6 +119,11 @@ /* 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_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ) +#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) + /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) * @@ -394,9 +383,6 @@ 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' */ -#define io_remap_pfn_range(vma, from, pfn, size, prot) \ - remap_pfn_range(vma, from, pfn, size, prot) - #include <asm-generic/pgtable.h> /* to cope with aliasing VIPT cache */ diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 5f26b2c1cba..d99f9b37cd1 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -18,7 +18,7 @@ #ifndef __ASSEMBLY__ -#include <asm/arcregs.h> /* for STATUS_E1_MASK et all */ +#include <asm/ptrace.h> /* Arch specific stuff which needs to be saved per task. * However these items are not so important so as to earn a place in @@ -28,10 +28,6 @@ struct thread_struct { unsigned long ksp; /* kernel mode stack pointer */ unsigned long callee_reg; /* pointer to callee regs */ unsigned long fault_address; /* dbls as brkpt holder as well */ - unsigned long cause_code; /* Exception Cause Code (ECR) */ -#ifdef CONFIG_ARC_CURR_IN_REG - unsigned long user_r25; -#endif #ifdef CONFIG_ARC_FPU_SAVE_RESTORE struct arc_fpu fpu; #endif @@ -44,15 +40,13 @@ struct thread_struct { /* Forward declaration, a strange C thing */ struct task_struct; -/* - * Return saved PC of a blocked thread. - */ +/* Return saved PC of a blocked thread */ unsigned long thread_saved_pc(struct task_struct *t); #define task_pt_regs(p) \ - ((struct pt_regs *)(THREAD_SIZE - 4 + (void *)task_stack_page(p)) - 1) + ((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1) -/* Free all resources held by a thread. */ +/* Free all resources held by a thread */ #define release_thread(thread) do { } while (0) /* Prepare to copy thread state - unlazy all lazy status */ @@ -75,32 +69,18 @@ unsigned long thread_saved_pc(struct task_struct *t); /* * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. - * These can't be derived from pt_regs as that would give correp user-mode val + * Look in process.c for details of kernel stack layout */ #define KSTK_ESP(tsk) (tsk->thread.ksp) -#define KSTK_BLINK(tsk) (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1+1)*4))) -#define KSTK_FP(tsk) (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1)*4))) -/* - * Do necessary setup to start up a newly executed thread. - * - * E1,E2 so that Interrupts are enabled in user mode - * L set, so Loop inhibited to begin with - * lp_start and lp_end seeded with bogus non-zero values so to easily catch - * the ARC700 sr to lp_start hardware bug - */ -#define start_thread(_regs, _pc, _usp) \ -do { \ - set_fs(USER_DS); /* reads from user space */ \ - (_regs)->ret = (_pc); \ - /* Interrupts enabled in User Mode */ \ - (_regs)->status32 = STATUS_U_MASK | STATUS_L_MASK \ - | STATUS_E1_MASK | STATUS_E2_MASK; \ - (_regs)->sp = (_usp); \ - /* bogus seed values for debugging */ \ - (_regs)->lp_start = 0x10; \ - (_regs)->lp_end = 0x80; \ -} while (0) +#define KSTK_REG(tsk, off) (*((unsigned int *)(KSTK_ESP(tsk) + \ + sizeof(struct callee_regs) + off))) + +#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) +#define KSTK_FP(tsk) KSTK_REG(tsk, 0) + +extern void start_thread(struct pt_regs * regs, unsigned long pc, + unsigned long usp); extern unsigned int get_wchan(struct task_struct *p); diff --git a/arch/arc/include/asm/prom.h b/arch/arc/include/asm/prom.h deleted file mode 100644 index 692d0d0789a..00000000000 --- a/arch/arc/include/asm/prom.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright (C) 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_ARC_PROM_H_ -#define _ASM_ARC_PROM_H_ - -#define HAVE_ARCH_DEVTREE_FIXUPS - -#endif diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 6179de7e07c..1bfeec2c055 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -17,68 +17,50 @@ /* THE pt_regs: Defines how regs are saved during entry into kernel */ struct pt_regs { - /* - * 1 word gutter after reg-file has been saved - * Technically not needed, Since SP always points to a "full" location - * (vs. "empty"). But pt_regs is shared with tools.... - */ - long res; /* Real registers */ long bta; /* bta_l1, bta_l2, erbta */ - long lp_start; - long lp_end; - long lp_count; + + 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 */ - long r12; - long r11; - long r10; - long r9; - long r8; - long r7; - long r6; - long r5; - long r4; - long r3; - long r2; - long r1; - long r0; + + 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; - /*to distinguish bet excp, syscall, irq */ + /* + * To distinguish bet excp, syscall, irq + * For traps and exceptions, Exception Cause Register. + * ECR: <00> <VV> <CC> <PP> + * Last word used by Linux for extra state mgmt (syscall-restart) + * For interrupts, use artificial ECR values to note current prio-level + */ union { + struct { #ifdef CONFIG_CPU_BIG_ENDIAN - /* so that assembly code is same for LE/BE */ - unsigned long orig_r8:16, event:16; + unsigned long state:8, ecr_vec:8, + ecr_cause:8, ecr_param:8; #else - unsigned long event:16, orig_r8:16; + unsigned long ecr_param:8, ecr_cause:8, + ecr_vec:8, state:8; #endif - long orig_r8_word; + }; + unsigned long event; }; + + long user_r25; }; /* Callee saved registers - need to be saved only when you are scheduled out */ struct callee_regs { - long res; /* Again this is not needed */ - long r25; - long r24; - long r23; - long r22; - long r21; - long r20; - long r19; - long r18; - long r17; - long r16; - long r15; - long r14; - long r13; + long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; #define instruction_pointer(regs) ((regs)->ret) @@ -99,18 +81,20 @@ struct callee_regs { /* return 1 if PC in delay slot */ #define delay_mode(regs) ((regs->status32 & STATUS_DE_MASK) == STATUS_DE_MASK) -#define in_syscall(regs) (regs->event & orig_r8_IS_SCALL) -#define in_brkpt_trap(regs) (regs->event & orig_r8_IS_BRKPT) +#define in_syscall(regs) ((regs->ecr_vec == ECR_V_TRAP) && !regs->ecr_param) +#define in_brkpt_trap(regs) ((regs->ecr_vec == ECR_V_TRAP) && regs->ecr_param) -#define syscall_wont_restart(regs) (regs->event |= orig_r8_IS_SCALL_RESTARTED) -#define syscall_restartable(regs) !(regs->event & orig_r8_IS_SCALL_RESTARTED) +#define STATE_SCALL_RESTARTED 0x01 + +#define syscall_wont_restart(reg) (reg->state |= STATE_SCALL_RESTARTED) +#define syscall_restartable(reg) !(reg->state & STATE_SCALL_RESTARTED) #define current_pt_regs() \ ({ \ /* open-coded current_thread_info() */ \ register unsigned long sp asm ("sp"); \ unsigned long pg_start = (sp & ~(THREAD_SIZE - 1)); \ - (struct pt_regs *)(pg_start + THREAD_SIZE - 4) - 1; \ + (struct pt_regs *)(pg_start + THREAD_SIZE) - 1; \ }) static inline long regs_return_value(struct pt_regs *regs) @@ -120,11 +104,4 @@ static inline long regs_return_value(struct pt_regs *regs) #endif /* !__ASSEMBLY__ */ -#define orig_r8_IS_SCALL 0x0001 -#define orig_r8_IS_SCALL_RESTARTED 0x0002 -#define orig_r8_IS_BRKPT 0x0004 -#define orig_r8_IS_EXCPN 0x0008 -#define orig_r8_IS_IRQ1 0x0010 -#define orig_r8_IS_IRQ2 0x0020 - #endif /* __ASM_PTRACE_H */ diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h index 6fc1159dfef..09db952e14b 100644 --- a/arch/arc/include/asm/sections.h +++ b/arch/arc/include/asm/sections.h @@ -11,8 +11,6 @@ #include <asm-generic/sections.h> -extern char _int_vec_base_lds[]; extern char __arc_dccm_base[]; -extern char __dtb_start[]; #endif diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h index 229e5068149..e10f8cef56a 100644 --- a/arch/arc/include/asm/setup.h +++ b/arch/arc/include/asm/setup.h @@ -31,7 +31,7 @@ struct cpuinfo_data { extern int root_mountflags, end_mem; extern int running_on_hw; -void __init setup_processor(void); +void setup_processor(void); void __init setup_arch_memory(void); #endif /* __ASMARC_SETUP_H */ diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index c4fb211dcd2..5d06eee43ea 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -30,7 +30,7 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * APIs provided by arch SMP code to rest of arch code */ extern void __init smp_init_cpus(void); -extern void __init first_lines_of_secondary(void); +extern void first_lines_of_secondary(void); extern const char *arc_platform_smp_cpuinfo(void); /* @@ -46,14 +46,14 @@ extern int smp_ipi_irq_setup(int cpu, int irq); * * @info: SoC SMP specific info for /proc/cpuinfo etc * @cpu_kick: For Master to kickstart a cpu (optionally at a PC) - * @ipi_send: To send IPI to a @cpumask - * @ips_clear: To clear IPI received by @cpu at @irq + * @ipi_send: To send IPI to a @cpu + * @ips_clear: To clear IPI received at @irq */ struct plat_smp_ops { const char *info; void (*cpu_kick)(int cpu, unsigned long pc); - void (*ipi_send)(void *callmap); - void (*ipi_clear)(int cpu, int irq); + void (*ipi_send)(int cpu); + void (*ipi_clear)(int irq); }; /* TBD: stop exporting it for direct population by platform */ diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index f158197ac5b..b6a8c2dfbe6 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__; + + __asm__ __volatile__( + " ex %0, [%1] \n" + : "+r" (tmp) + : "r"(&(lock->slock)) + : "memory"); + smp_mb(); } diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h index 8276bfd6170..662627ced4f 100644 --- a/arch/arc/include/asm/spinlock_types.h +++ b/arch/arc/include/asm/spinlock_types.h @@ -20,9 +20,9 @@ typedef struct { #define __ARCH_SPIN_LOCK_LOCKED { __ARCH_SPIN_LOCK_LOCKED__ } /* - * Unlocked: 0x01_00_00_00 - * Read lock(s): 0x00_FF_00_00 to say 0x01 - * Write lock: 0x0, but only possible if prior value "unlocked" 0x0100_0000 + * Unlocked : 0x0100_0000 + * Read lock(s) : 0x00FF_FFFF to 0x01 (Multiple Readers decrement it) + * Write lock : 0x0, but only if prior value is "unlocked" 0x0100_0000 */ typedef struct { volatile unsigned int counter; diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h index 33ab3048e9b..29de0980430 100644 --- a/arch/arc/include/asm/syscall.h +++ b/arch/arc/include/asm/syscall.h @@ -18,7 +18,7 @@ static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { if (user_mode(regs) && in_syscall(regs)) - return regs->orig_r8; + return regs->r8; else return -1; } @@ -26,8 +26,7 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs) static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - /* XXX: I can't fathom how pt_regs->r8 will be clobbered ? */ - regs->r8 = regs->orig_r8; + regs->r0 = regs->orig_r0; } static inline long diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 2d50a4cdd7f..45be2167201 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -80,8 +80,6 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may need to diff --git a/arch/arc/include/asm/tlb-mmu1.h b/arch/arc/include/asm/tlb-mmu1.h index a5ff961b1ef..8a1ec96012a 100644 --- a/arch/arc/include/asm/tlb-mmu1.h +++ b/arch/arc/include/asm/tlb-mmu1.h @@ -9,9 +9,9 @@ #ifndef __ASM_TLB_MMU_V1_H__ #define __ASM_TLB_MMU_V1_H__ -#if defined(__ASSEMBLY__) && defined(CONFIG_ARC_MMU_VER == 1) +#include <asm/mmu.h> -#include <asm/tlb.h> +#if defined(__ASSEMBLY__) && (CONFIG_ARC_MMU_VER == 1) .macro TLB_WRITE_HEURISTICS diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h index cb0c708ca66..a9db5f62aaf 100644 --- a/arch/arc/include/asm/tlb.h +++ b/arch/arc/include/asm/tlb.h @@ -9,18 +9,6 @@ #ifndef _ASM_ARC_TLB_H #define _ASM_ARC_TLB_H -#ifdef __KERNEL__ - -#include <asm/pgtable.h> - -/* Masks for actual TLB "PD"s */ -#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT) -#define PTE_BITS_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE | \ - _PAGE_U_EXECUTE | _PAGE_U_WRITE | _PAGE_U_READ | \ - _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ) - -#ifndef __ASSEMBLY__ - #define tlb_flush(tlb) \ do { \ if (tlb->fullmm) \ @@ -56,18 +44,4 @@ do { \ #include <linux/pagemap.h> #include <asm-generic/tlb.h> -#ifdef CONFIG_ARC_DBG_TLB_PARANOIA -void tlb_paranoid_check(unsigned int pid_sw, unsigned long address); -#else -#define tlb_paranoid_check(a, b) -#endif - -void arc_mmu_init(void); -extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len); -void __init read_decode_mmu_bcr(void); - -#endif /* __ASSEMBLY__ */ - -#endif /* __KERNEL__ */ - #endif /* _ASM_ARC_TLB_H */ diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h index b2f9bc7f68c..71c7b2e4b87 100644 --- a/arch/arc/include/asm/tlbflush.h +++ b/arch/arc/include/asm/tlbflush.h @@ -18,11 +18,18 @@ 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); -/* XXX: Revisit for SMP */ +#ifndef CONFIG_SMP #define flush_tlb_range(vma, s, e) local_flush_tlb_range(vma, s, e) #define flush_tlb_page(vma, page) local_flush_tlb_page(vma, page) #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) - +#else +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +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); +#endif /* CONFIG_SMP */ #endif diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index 32420824375..30c9baffa96 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -43,7 +43,7 @@ * Because it essentially checks if buffer end is within limit and @len is * non-ngeative, which implies that buffer start will be within limit too. * - * The reason for rewriting being, for majorit yof cases, @len is generally + * The reason for rewriting being, for majority of cases, @len is generally * compile time constant, causing first sub-expression to be compile time * subsumed. * @@ -53,7 +53,7 @@ * */ #define __user_ok(addr, sz) (((sz) <= TASK_SIZE) && \ - (((addr)+(sz)) <= get_fs())) + ((addr) <= (get_fs() - (sz)))) #define __access_ok(addr, sz) (unlikely(__kernel_ok) || \ likely(__user_ok((addr), (sz)))) diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h index 5dbe63f17b6..3e5f071bc00 100644 --- a/arch/arc/include/asm/unaligned.h +++ b/arch/arc/include/asm/unaligned.h @@ -16,13 +16,14 @@ #ifdef CONFIG_ARC_MISALIGN_ACCESS int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs); + struct callee_regs *cregs); #else static inline int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs) + struct callee_regs *cregs) { - return 0; + /* Not fixed */ + return 1; } #endif diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index 18fefaea73f..f50d02df78d 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -2,11 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm header-y += elf.h header-y += page.h -header-y += setup.h -header-y += byteorder.h header-y += cachectl.h -header-y += ptrace.h -header-y += sigcontext.h -header-y += signal.h -header-y += swab.h -header-y += unistd.h diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index 30333cec0fe..76a7739aab1 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -11,6 +11,7 @@ #ifndef _UAPI__ASM_ARC_PTRACE_H #define _UAPI__ASM_ARC_PTRACE_H +#define PTRACE_GET_THREAD_AREA 25 #ifndef __ASSEMBLY__ /* @@ -20,28 +21,31 @@ * * This is to decouple pt_regs from user-space ABI, to be able to change it * w/o affecting the ABI. - * Although the layout (initial padding) is similar to pt_regs to have some - * optimizations when copying pt_regs to/from user_regs_struct. + * + * The intermediate pad,pad2 are relics of initial layout based on pt_regs + * for optimizations when copying pt_regs to/from user_regs_struct. + * We no longer need them, but can't be changed as they are part of ABI now. * * Also, sigcontext only care about the scratch regs as that is what we really - * save/restore for signal handling. + * save/restore for signal handling. However gdb also uses the same struct + * hence callee regs need to be in there too. */ struct user_regs_struct { + long pad; struct { - long pad; 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; } scratch; + long pad2; struct { - long pad; long r25, r24, r23, r22, r21, r20; 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 directly after checking orig_r8 */ + long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h index 6f30484f34b..39e58d1cdf9 100644 --- a/arch/arc/include/uapi/asm/unistd.h +++ b/arch/arc/include/uapi/asm/unistd.h @@ -8,6 +8,13 @@ /******** no-legacy-syscalls-ABI *******/ +/* + * Non-typical guard macro to enable inclusion twice in ARCH sys.c + * That is how the Generic syscall wrapper generator works + */ +#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL) +#define _UAPI_ASM_ARC_UNISTD_H + #define __ARCH_WANT_SYS_EXECVE #define __ARCH_WANT_SYS_CLONE #define __ARCH_WANT_SYS_VFORK @@ -32,3 +39,7 @@ __SYSCALL(__NR_arc_gettls, sys_arc_gettls) /* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */ #define __NR_sysfs (__NR_arch_specific_syscall + 3) __SYSCALL(__NR_sysfs, sys_sysfs) + +#undef __SYSCALL + +#endif diff --git a/arch/arc/kernel/.gitignore b/arch/arc/kernel/.gitignore new file mode 100644 index 00000000000..c5f676c3c22 --- /dev/null +++ b/arch/arc/kernel/.gitignore @@ -0,0 +1 @@ +vmlinux.lds diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile index c242ef07ba7..8004b4fa646 100644 --- a/arch/arc/kernel/Makefile +++ b/arch/arc/kernel/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_ARC_MISALIGN_ACCESS) += unaligned.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_ARC_METAWARE_HLINK) += arc_hostlink.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_ARC_FPU_SAVE_RESTORE) += fpu.o CFLAGS_fpu.o += -mdpfp diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c index 7dcda702524..6c3aa0edb9b 100644 --- a/arch/arc/kernel/asm-offsets.c +++ b/arch/arc/kernel/asm-offsets.c @@ -24,9 +24,6 @@ int main(void) DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg)); -#ifdef CONFIG_ARC_CURR_IN_REG - DEFINE(THREAD_USER_R25, offsetof(struct thread_struct, user_r25)); -#endif DEFINE(THREAD_FAULT_ADDR, offsetof(struct thread_struct, fault_address)); @@ -49,7 +46,7 @@ int main(void) BLANK(); DEFINE(PT_status32, offsetof(struct pt_regs, status32)); - DEFINE(PT_orig_r8, offsetof(struct pt_regs, orig_r8_word)); + DEFINE(PT_event, offsetof(struct pt_regs, event)); DEFINE(PT_sp, offsetof(struct pt_regs, sp)); DEFINE(PT_r0, offsetof(struct pt_regs, r0)); DEFINE(PT_r1, offsetof(struct pt_regs, r1)); @@ -60,5 +57,7 @@ int main(void) DEFINE(PT_r6, offsetof(struct pt_regs, r6)); DEFINE(PT_r7, offsetof(struct pt_regs, r7)); + DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs)); + DEFINE(SZ_PT_REGS, sizeof(struct pt_regs)); return 0; } diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c index 60844dac613..c14a5bea0c7 100644 --- a/arch/arc/kernel/ctx_sw.c +++ b/arch/arc/kernel/ctx_sw.c @@ -17,16 +17,14 @@ #include <asm/asm-offsets.h> #include <linux/sched.h> +#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) + struct task_struct *__sched __switch_to(struct task_struct *prev_task, struct task_struct *next_task) { unsigned int tmp; unsigned int prev = (unsigned int)prev_task; unsigned int next = (unsigned int)next_task; - int num_words_to_skip = 1; -#ifdef CONFIG_ARC_CURR_IN_REG - num_words_to_skip++; -#endif __asm__ __volatile__( /* FP/BLINK save generated by gcc (standard function prologue */ @@ -44,11 +42,21 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) "st.a r24, [sp, -4] \n\t" #ifndef CONFIG_ARC_CURR_IN_REG "st.a r25, [sp, -4] \n\t" +#else + "sub sp, sp, 4 \n\t" /* usual r25 placeholder */ #endif - "sub sp, sp, %4 \n\t" /* create gutter at top */ /* set ksp of outgoing task in tsk->thread.ksp */ +#if KSP_WORD_OFF <= 255 "st.as sp, [%3, %1] \n\t" +#else + /* + * Workaround for NR_CPUS=4k + * %1 is bigger than 255 (S9 offset for st.as) + */ + "add2 r24, %3, %1 \n\t" + "st sp, [r24] \n\t" +#endif "sync \n\t" @@ -76,10 +84,10 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) /* start loading it's CALLEE reg file */ - "add sp, sp, %4 \n\t" /* skip gutter at top */ - #ifndef CONFIG_ARC_CURR_IN_REG "ld.ab r25, [sp, 4] \n\t" +#else + "add sp, sp, 4 \n\t" #endif "ld.ab r24, [sp, 4] \n\t" "ld.ab r23, [sp, 4] \n\t" @@ -100,8 +108,7 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) /* FP/BLINK restore generated by gcc (standard func epilogue */ : "=r"(tmp) - : "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev), - "n"(num_words_to_skip * 4) + : "n"(KSP_WORD_OFF), "r"(next), "r"(prev) : "blink" ); diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index d8972345e4c..e248594097e 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -10,9 +10,11 @@ * -This is the more "natural" hand written assembler */ +#include <linux/linkage.h> #include <asm/entry.h> /* For the SAVE_* macros */ #include <asm/asm-offsets.h> -#include <asm/linkage.h> + +#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) ;################### Low Level Context Switch ########################## @@ -28,8 +30,13 @@ __switch_to: SAVE_CALLEE_SAVED_KERNEL /* Save the now KSP in task->thread.ksp */ - st.as sp, [r0, (TASK_THREAD + THREAD_KSP)/4] - +#if KSP_WORD_OFF <= 255 + st.as sp, [r0, KSP_WORD_OFF] +#else + /* Workaround for NR_CPUS=4k as ST.as can only take s9 offset */ + add2 r24, r0, KSP_WORD_OFF + st sp, [r24] +#endif /* * Return last task in r0 (return reg) * On ARC, Return reg = First Arg reg = r0. @@ -55,4 +62,4 @@ __switch_to: ld.ab blink, [sp, 4] j [blink] -ARC_EXIT __switch_to +END(__switch_to) diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c index bdee3a81205..fffdb5e41b2 100644 --- a/arch/arc/kernel/devtree.c +++ b/arch/arc/kernel/devtree.c @@ -14,14 +14,20 @@ #include <linux/memblock.h> #include <linux/of.h> #include <linux/of_fdt.h> -#include <asm/prom.h> #include <asm/clk.h> #include <asm/mach_desc.h> -/* called from unflatten_device_tree() to bootstrap devicetree itself */ -void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) +static const void * __init arch_get_next_mach(const char *const **match) { - return __va(memblock_alloc(size, align)); + static const struct machine_desc *mdesc = __arch_info_begin; + const struct machine_desc *m = mdesc; + + if (m >= __arch_info_end) + return NULL; + + mdesc++; + *match = m->dt_compat; + return m; } /** @@ -31,93 +37,24 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) * If a dtb was passed to the kernel, then use it to choose the correct * machine_desc and to setup the system. */ -struct machine_desc * __init setup_machine_fdt(void *dt) +const struct machine_desc * __init setup_machine_fdt(void *dt) { - struct boot_param_header *devtree = dt; - struct machine_desc *mdesc = NULL, *mdesc_best = NULL; - unsigned int score, mdesc_score = ~1; + const struct machine_desc *mdesc; unsigned long dt_root; - const char *model, *compat; - void *clk; - char manufacturer[16]; - unsigned long len; + const void *clk; + int len; - /* check device tree validity */ - if (be32_to_cpu(devtree->magic) != OF_DT_HEADER) + if (!early_init_dt_scan(dt)) return NULL; - initial_boot_params = devtree; - dt_root = of_get_flat_dt_root(); - - /* - * The kernel could be multi-platform enabled, thus could have many - * "baked-in" machine descriptors. Search thru all for the best - * "compatible" string match. - */ - for_each_machine_desc(mdesc) { - score = of_flat_dt_match(dt_root, mdesc->dt_compat); - if (score > 0 && score < mdesc_score) { - mdesc_best = mdesc; - mdesc_score = score; - } - } - if (!mdesc_best) { - const char *prop; - long size; - - pr_err("\n unrecognized device tree list:\n[ "); - - prop = of_get_flat_dt_prop(dt_root, "compatible", &size); - if (prop) { - while (size > 0) { - printk("'%s' ", prop); - size -= strlen(prop) + 1; - prop += strlen(prop) + 1; - } - } - printk("]\n\n"); - + mdesc = of_flat_dt_match_machine(NULL, arch_get_next_mach); + if (!mdesc) machine_halt(); - } - - /* compat = "<manufacturer>,<model>" */ - compat = mdesc_best->dt_compat[0]; - - model = strchr(compat, ','); - if (model) - model++; - - strlcpy(manufacturer, compat, model ? model - compat : strlen(compat)); - - pr_info("Board \"%s\" from %s (Manufacturer)\n", model, manufacturer); - - /* Retrieve various information from the /chosen node */ - of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line); - - /* Initialize {size,address}-cells info */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - - /* Setup memory, calling early_init_dt_add_memory_arch */ - of_scan_flat_dt(early_init_dt_scan_memory, NULL); + dt_root = of_get_flat_dt_root(); clk = of_get_flat_dt_prop(dt_root, "clock-frequency", &len); if (clk) arc_set_core_freq(of_read_ulong(clk, len/4)); - return mdesc_best; -} - -/* - * Copy the flattened DT out of .init since unflattening doesn't copy strings - * and the normal DT APIs refs them from orig flat DT - */ -void __init copy_devtree(void) -{ - void *alloc = early_init_dt_alloc_memory_arch( - be32_to_cpu(initial_boot_params->totalsize), 64); - if (alloc) { - memcpy(alloc, initial_boot_params, - be32_to_cpu(initial_boot_params->totalsize)); - initial_boot_params = alloc; - } + return mdesc; } diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 0c6d664d4a8..83a046a7cd0 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -141,8 +141,8 @@ VECTOR EV_Extension ; 0x130, Extn Intruction Excp (0x26) VECTOR reserved ; Reserved Exceptions .endr -#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ -#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */ +#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> @@ -156,7 +156,7 @@ ARCFP_DATA int1_saved_reg int1_saved_reg: .zero 4 -/* Each Interrupt level needs it's own scratch */ +/* Each Interrupt level needs its own scratch */ #ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS ARCFP_DATA int2_saved_reg @@ -184,7 +184,7 @@ reserved: ; processor restart ; --------------------------------------------- ; Level 2 ISR: Can interrupt a Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level2 +ENTRY(handle_interrupt_level2) ; TODO-vineetg for SMP this wont work ; free up r9 as scratchpad @@ -225,14 +225,14 @@ ARC_ENTRY handle_interrupt_level2 b ret_from_exception -ARC_EXIT handle_interrupt_level2 +END(handle_interrupt_level2) #endif ; --------------------------------------------- ; Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level1 +ENTRY(handle_interrupt_level1) /* free up r9 as scratchpad */ #ifdef CONFIG_SMP @@ -250,6 +250,14 @@ ARC_ENTRY handle_interrupt_level1 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 @@ -257,7 +265,7 @@ ARC_ENTRY handle_interrupt_level1 sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg b ret_from_exception -ARC_EXIT handle_interrupt_level1 +END(handle_interrupt_level1) ;################### Non TLB Exception Handling ############################# @@ -265,63 +273,52 @@ ARC_EXIT handle_interrupt_level1 ; Instruction Error Exception Handler ; --------------------------------------------- -ARC_ENTRY instr_service +ENTRY(instr_service) - EXCPN_PROLOG_FREEUP_REG r9 + EXCEPTION_PROLOGUE - lr r9, [erstatus] - - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS - - lr r0, [ecr] - lr r1, [efa] - - mov r2, sp + lr r0, [efa] + mov r1, sp FAKE_RET_FROM_EXCPN r9 bl do_insterror_or_kprobe b ret_from_exception -ARC_EXIT instr_service +END(instr_service) ; --------------------------------------------- ; Memory Error Exception Handler ; --------------------------------------------- -ARC_ENTRY mem_service +ENTRY(mem_service) - EXCPN_PROLOG_FREEUP_REG r9 + EXCEPTION_PROLOGUE - lr r9, [erstatus] + lr r0, [efa] + mov r1, sp - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS + FAKE_RET_FROM_EXCPN r9 - lr r0, [ecr] - lr r1, [efa] - mov r2, sp bl do_memory_error b ret_from_exception -ARC_EXIT mem_service +END(mem_service) ; --------------------------------------------- ; Machine Check Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_MachineCheck +ENTRY(EV_MachineCheck) - EXCPN_PROLOG_FREEUP_REG r9 - lr r9, [erstatus] + EXCEPTION_PROLOGUE - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS + lr r2, [ecr] + lr r0, [efa] + mov r1, sp - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lsr r3, r2, 8 + bmsk r3, r3, 7 + brne r3, ECR_C_MCHK_DUP_TLB, 1f - brne r0, 0x200100, 1f bl do_tlb_overlap_fault b ret_from_exception @@ -334,29 +331,23 @@ ARC_ENTRY EV_MachineCheck j do_machine_check_fault -ARC_EXIT EV_MachineCheck +END(EV_MachineCheck) ; --------------------------------------------- ; Protection Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_TLBProtV - - EXCPN_PROLOG_FREEUP_REG r9 +ENTRY(EV_TLBProtV) - ;Which mode (user/kernel) was the system in when Exception occured - lr r9, [erstatus] - - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS + 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 r3, [ecr] - lr r4, [efa] + + lr r2, [ecr] + lr r0, [efa] ; Faulting Data address ; --------(4) Return from CPU Exception Mode --------- ; Fake a rtie, but rtie to next label @@ -365,87 +356,68 @@ ARC_ENTRY EV_TLBProtV 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 (WRITE to READ ONLY Page) - for linux COW - ; -Unaligned Access (READ/WRITE on odd boundary) + ; -Access Violaton : 00_23_(00|01|02|03)_00 + ; x r w r+w + ; -Unaligned Access : 00_23_04_00 ; - cmp r3, 0x230400 ; Misaligned data access ? - beq 4f + bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f ;========= (6a) Access Violation Processing ======== - cmp r3, 0x230100 - mov r1, 0x0 ; if LD exception ? write = 0 - mov.ne r1, 0x1 ; else write = 1 - - mov r2, r4 ; faulting address - mov r0, sp ; pt_regs bl do_page_fault b ret_from_exception ;========== (6b) Non aligned access ============ 4: - mov r0, r3 ; cause code - mov r1, r4 ; faulting address - mov r2, sp ; pt_regs -#ifdef CONFIG_ARC_MISALIGN_ACCESS SAVE_CALLEE_SAVED_USER - mov r3, sp ; callee_regs + 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 -#else - bl do_misaligned_error -#endif b ret_from_exception -ARC_EXIT EV_TLBProtV +END(EV_TLBProtV) ; --------------------------------------------- ; Privilege Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_PrivilegeV +ENTRY(EV_PrivilegeV) - EXCPN_PROLOG_FREEUP_REG r9 + EXCEPTION_PROLOGUE - lr r9, [erstatus] - - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS - - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp FAKE_RET_FROM_EXCPN r9 bl do_privilege_fault b ret_from_exception -ARC_EXIT EV_PrivilegeV +END(EV_PrivilegeV) ; --------------------------------------------- ; Extension Instruction Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_Extension +ENTRY(EV_Extension) - EXCPN_PROLOG_FREEUP_REG r9 - lr r9, [erstatus] + EXCEPTION_PROLOGUE - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS + lr r0, [efa] + mov r1, sp + + FAKE_RET_FROM_EXCPN r9 - lr r0, [ecr] - lr r1, [efa] - mov r2, sp bl do_extension_fault b ret_from_exception -ARC_EXIT EV_Extension +END(EV_Extension) ;######################### System Call Tracing ######################### @@ -498,13 +470,10 @@ tracesys_exit: trap_with_param: ; stop_pc info by gdb needs this info - stw orig_r8_IS_BRKPT, [sp, PT_orig_r8] - - mov r0, r12 - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp - ; Now that we have read EFA, its safe to do "fake" rtie + ; 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 @@ -535,20 +504,13 @@ trap_with_param: ; (2) Break Points ;------------------------------------------------------------------ -ARC_ENTRY EV_Trap - - ; Need at least 1 reg to code the early exception prolog - EXCPN_PROLOG_FREEUP_REG r9 - - ;Which mode (user/kernel) was the system in when intr occured - lr r9, [erstatus] +ENTRY(EV_Trap) - SWITCH_TO_KERNEL_STK - SAVE_ALL_TRAP + EXCEPTION_PROLOGUE ;------- (4) What caused the Trap -------------- lr r12, [ecr] - and.f 0, r12, ECR_PARAM_MASK + bmsk.f 0, r12, 7 bnz trap_with_param ; ======= (5a) Trap is due to System Call ======== @@ -572,9 +534,9 @@ ARC_ENTRY EV_Trap jl [r9] ; Entry into Sys Call Handler ; fall through to ret_from_system_call -ARC_EXIT EV_Trap +END(EV_Trap) -ARC_ENTRY ret_from_system_call +ENTRY(ret_from_system_call) st r0, [sp, PT_r0] ; sys call return value in pt_regs @@ -584,16 +546,12 @@ ARC_ENTRY ret_from_system_call ; ; If ret to user mode do we need to handle signals, schedule() et al. -ARC_ENTRY ret_from_exception +ENTRY(ret_from_exception) ; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32 ld r8, [sp, PT_status32] ; returning to User/Kernel Mode -#ifdef CONFIG_PREEMPT bbit0 r8, STATUS_U_BIT, resume_kernel_mode -#else - bbit0 r8, STATUS_U_BIT, restore_regs -#endif ; Before returning to User mode check-for-and-complete any pending work ; such as rescheduling/signal-delivery etc. @@ -620,6 +578,7 @@ resume_user_mode_begin: ; --- (Slow Path #2) pending signal --- mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() + GET_CURR_THR_INFO_FLAGS r9 bbit0 r9, TIF_SIGPENDING, .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs @@ -653,10 +612,15 @@ resume_user_mode_begin: b resume_user_mode_begin ; unconditionally back to U mode ret chks ; for single exit point from this block -#ifdef CONFIG_PREEMPT - resume_kernel_mode: + ; Disable Interrupts from this point on + ; CONFIG_PREEMPT: This is a must for preempt_schedule_irq() + ; !CONFIG_PREEMPT: To ensure restore_regs is intr safe + IRQ_DISABLE r9 + +#ifdef CONFIG_PREEMPT + ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 ld r8, [r10, THREAD_INFO_PREEMPT_COUNT] @@ -666,8 +630,6 @@ resume_kernel_mode: ld r9, [r10, THREAD_INFO_FLAGS] bbit0 r9, TIF_NEED_RESCHED, restore_regs - IRQ_DISABLE r9 - ; Invoke PREEMPTION bl preempt_schedule_irq @@ -680,23 +642,13 @@ resume_kernel_mode: ; ; 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 : - ; Disable Interrupts while restoring reg-file back - ; XXX can this be optimised out - IRQ_DISABLE_SAVE r9, r10 ;@r10 has prisitine (pre-disable) copy - -#ifdef CONFIG_ARC_CURR_IN_REG - ; Restore User R25 - ; Earlier this used to be only for returning to user mode - ; However with 2 levels of IRQ this can also happen even if - ; in kernel mode - ld r9, [sp, PT_sp] - brhs r9, VMALLOC_START, 8f - RESTORE_USER_R25 -8: -#endif + 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 @@ -714,28 +666,33 @@ not_exception: #ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS + ; Level 2 interrupt return Path - from hardware standpoint bbit0 r10, STATUS_A2_BIT, not_level2_interrupt ;------------------------------------------------------------------ - ; if L2 IRQ interrupted a L1 ISR, we'd disbaled preemption earlier - ; so that sched doesnt move to new task, causing L1 to be delayed - ; undeterministically. Now that we've achieved that, lets reset + ; 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 ;---------------------------------------------------------------- - ldw r9, [sp, PT_orig_r8] ; get orig_r8 to make sure it is - brne r9, orig_r8_IS_IRQ2, 149f ; infact a L2 ISR ret path - 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 - ; A1 is set in status32_l2 ; 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 beccause we would have incremented it. + ; 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 @@ -771,15 +728,15 @@ not_level1_interrupt: debug_marker_syscall: rtie -ARC_EXIT ret_from_exception +END(ret_from_exception) -ARC_ENTRY ret_from_fork +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 - ; If kernel thread, jump to it's entry-point + ; If kernel thread, jump to its entry-point ld r9, [sp, PT_status32] brne r9, 0, 1f @@ -790,11 +747,11 @@ ARC_ENTRY ret_from_fork ; special case of kernel_thread entry point returning back due to ; kernel_execve() - pretend return from syscall to ret to userland b ret_from_exception -ARC_EXIT ret_from_fork +END(ret_from_fork) ;################### Special Sys Call Wrappers ########################## -ARC_ENTRY sys_clone_wrapper +ENTRY(sys_clone_wrapper) SAVE_CALLEE_SAVED_USER bl @sys_clone DISCARD_CALLEE_SAVED_USER @@ -804,7 +761,7 @@ ARC_ENTRY sys_clone_wrapper bnz tracesys_exit b ret_from_system_call -ARC_EXIT sys_clone_wrapper +END(sys_clone_wrapper) #ifdef CONFIG_ARC_DW2_UNWIND ; Workaround for bug 94179 (STAR ): diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 006dec3fc35..4d2481bd8b9 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -12,10 +12,42 @@ * to skip certain things during boot on simulator */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/entry.h> -#include <linux/linkage.h> #include <asm/arcregs.h> +#include <asm/cache.h> + +.macro CPU_EARLY_SETUP + + ; Setting up Vectror Table (in case exception happens in early boot + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + + ; Disable I-cache/D-cache if kernel so configured + lr r5, [ARC_REG_IC_BCR] + breq r5, 0, 1f ; I$ doesn't exist + lr r5, [ARC_REG_IC_CTRL] +#ifdef CONFIG_ARC_HAS_ICACHE + bclr r5, r5, 0 ; 0 - Enable, 1 is Disable +#else + bset r5, r5, 0 ; I$ exists, but is not used +#endif + sr r5, [ARC_REG_IC_CTRL] + +1: + lr r5, [ARC_REG_DC_BCR] + breq r5, 0, 1f ; D$ doesn't exist + lr r5, [ARC_REG_DC_CTRL] + bclr r5, r5, 6 ; Invalidate (discard w/o wback) +#ifdef CONFIG_ARC_HAS_DCACHE + bclr r5, r5, 0 ; Enable (+Inv) +#else + bset r5, r5, 0 ; Disable (+Inv) +#endif + sr r5, [ARC_REG_DC_CTRL] + +1: +.endm .cpu A7 @@ -24,45 +56,40 @@ .globl stext stext: ;------------------------------------------------------------------- - ; Don't clobber r0-r4 yet. It might have bootloader provided info + ; Don't clobber r0-r2 yet. It might have bootloader provided info ;------------------------------------------------------------------- + CPU_EARLY_SETUP + #ifdef CONFIG_SMP - ; Only Boot (Master) proceeds. Others wait in platform dependent way + ; 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 - jnz arc_platform_smp_wait_to_boot + mov.ne r0, r5 + jne arc_platform_smp_wait_to_boot #endif ; Clear BSS before updating any globals ; XXX: use ZOL here mov r5, __bss_start - mov r6, __bss_stop + sub r6, __bss_stop, r5 + lsr.f lp_count, r6, 2 + lpnz 1f + st.ab 0, [r5, 4] 1: - st.ab 0, [r5,4] - brlt r5, r6, 1b - -#ifdef CONFIG_CMDLINE_UBOOT - ; support for bootloader provided cmdline - ; If cmdline passed by u-boot, then - ; r0 = 1 (because ATAGS parsing, now retired, used to use 0) - ; r1 = magic number (board identity) - ; r2 = addr of cmdline string (somewhere in memory/flash) - brne r0, 1, .Lother_bootup_chores ; u-boot didn't pass cmdline - breq r2, 0, .Lother_bootup_chores ; or cmdline is NULL - - mov r5, @command_line -1: - ldb.ab r6, [r2, 1] - breq r6, 0, .Lother_bootup_chores - b.d 1b - stb.ab r6, [r5, 1] -#endif - -.Lother_bootup_chores: + ; 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 + ; r2 = pointer to uboot provided cmdline or external DTB in mem + ; These are handled later in setup_arch() + st r0, [@uboot_tag] + st r2, [@uboot_arg] ; Identify if running on ISS vs Silicon ; IDENTITY Reg [ 3 2 1 0 ] @@ -90,12 +117,14 @@ stext: ;---------------------------------------------------------------- ; First lines of code run by secondary before jumping to 'C' ;---------------------------------------------------------------- - .section .init.text, "ax",@progbits + .section .text, "ax",@progbits .type first_lines_of_secondary, @function .globl first_lines_of_secondary first_lines_of_secondary: + CPU_EARLY_SETUP + ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] SET_CURR_TASK_ON_CPU r0, r1 diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 8115fa53157..7d653c0d077 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -24,34 +24,29 @@ * -Needed for each CPU (hence not foldable into init_IRQ) * * what it does ? - * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000 * -Disable all IRQs (on CPU side) * -Optionally, setup the High priority Interrupts as Level 2 IRQs */ -void __cpuinit arc_init_IRQ(void) +void arc_init_IRQ(void) { int level_mask = 0; - write_aux_reg(AUX_INTR_VEC_BASE, _int_vec_base_lds); - /* Disable all IRQs: enable them as devices request */ write_aux_reg(AUX_IENABLE, 0); /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ -#ifdef CONFIG_ARC_IRQ3_LV2 - level_mask |= (1 << 3); -#endif -#ifdef CONFIG_ARC_IRQ5_LV2 - level_mask |= (1 << 5); -#endif -#ifdef CONFIG_ARC_IRQ6_LV2 - level_mask |= (1 << 6); -#endif + 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) { + if (level_mask) pr_info("Level-2 interrupts bitset %x\n", level_mask); - write_aux_reg(AUX_IRQ_LEV, level_mask); - } } /* @@ -155,24 +150,6 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } -int __init 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; -} - /* * arch_local_irq_enable - Enable interrupts. * diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index 52bdc83c149..a2ff5c5d145 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -169,7 +169,7 @@ int kgdb_arch_init(void) return 0; } -void kgdb_trap(struct pt_regs *regs, int param) +void kgdb_trap(struct pt_regs *regs) { /* trap_s 3 is used for breakpoints that overwrite existing * instructions, while trap_s 4 is used for compiled breakpoints. @@ -181,7 +181,7 @@ void kgdb_trap(struct pt_regs *regs, int param) * with trap_s 4 (compiled) breakpoints, continuation needs to * start after the breakpoint. */ - if (param == 3) + if (regs->ecr_param == 3) instruction_pointer(regs) -= BREAK_INSTR_SIZE; kgdb_handle_exception(1, SIGTRAP, 0, regs); @@ -196,6 +196,18 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) instruction_pointer(regs) = ip; } +static void kgdb_call_nmi_hook(void *ignored) +{ + kgdb_nmicallback(raw_smp_processor_id(), NULL); +} + +void kgdb_roundup_cpus(unsigned long flags) +{ + local_irq_enable(); + smp_call_function(kgdb_call_nmi_hook, NULL, 0); + local_irq_disable(); +} + struct kgdb_arch arch_kgdb_ops = { /* breakpoint instruction: TRAP_S 0x3 */ #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 5a7b80e2d88..42b05046fad 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -87,13 +87,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } static inline void __kprobes set_current_kprobe(struct kprobe *p) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } static void __kprobes resume_execution(struct kprobe *p, unsigned long addr, @@ -237,7 +237,7 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) return 1; } else if (kprobe_running()) { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { setup_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; @@ -327,7 +327,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr) */ /* We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); @@ -517,8 +517,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) return 0; } -void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void trap_is_kprobe(unsigned long address, struct pt_regs *regs) { - notify_die(DIE_TRAP, "kprobe_trap", regs, address, cause, SIGTRAP); + notify_die(DIE_TRAP, "kprobe_trap", regs, address, 0, SIGTRAP); } diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c new file mode 100644 index 00000000000..63177e4cb66 --- /dev/null +++ b/arch/arc/kernel/perf_event.c @@ -0,0 +1,326 @@ +/* + * Linux performance counter support for ARC700 series + * + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * This code is inspired by the perf support of various other architectures. + * + * 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/errno.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/perf_event.h> +#include <linux/platform_device.h> +#include <asm/arcregs.h> + +struct arc_pmu { + struct pmu pmu; + int counter_size; /* in bits */ + int n_counters; + unsigned long used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)]; + int ev_hw_idx[PERF_COUNT_ARC_HW_MAX]; +}; + +/* read counter #idx; note that counter# != event# on ARC! */ +static uint64_t arc_pmu_read_counter(int idx) +{ + uint32_t tmp; + uint64_t result; + + /* + * ARC supports making 'snapshots' of the counters, so we don't + * need to care about counters wrapping to 0 underneath our feet + */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN); + result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32; + result |= read_aux_reg(ARC_REG_PCT_SNAPL); + + return result; +} + +static void arc_perf_event_update(struct perf_event *event, + struct hw_perf_event *hwc, int idx) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + 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); + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); +} + +static void arc_pmu_read(struct perf_event *event) +{ + arc_perf_event_update(event, &event->hw, event->hw.idx); +} + +static int arc_pmu_cache_event(u64 config) +{ + unsigned int cache_type, cache_op, cache_result; + int ret; + + cache_type = (config >> 0) & 0xff; + cache_op = (config >> 8) & 0xff; + cache_result = (config >> 16) & 0xff; + if (cache_type >= PERF_COUNT_HW_CACHE_MAX) + return -EINVAL; + if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) + return -EINVAL; + if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ret = arc_pmu_cache_map[cache_type][cache_op][cache_result]; + + if (ret == CACHE_OP_UNSUPPORTED) + return -ENOENT; + + return ret; +} + +/* initializes hw_perf_event structure if event is supported */ +static int arc_pmu_event_init(struct perf_event *event) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + struct hw_perf_event *hwc = &event->hw; + int ret; + + /* ARC 700 PMU does not support sampling events */ + if (is_sampling_event(event)) + return -ENOENT; + + 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]; + pr_debug("initializing event %d with cfg %d\n", + (int) event->attr.config, (int) hwc->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]; + return 0; + default: + return -ENOENT; + } +} + +/* starts all counters */ +static void arc_pmu_enable(struct pmu *pmu) +{ + uint32_t tmp; + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1); +} + +/* stops all counters */ +static void arc_pmu_disable(struct pmu *pmu) +{ + uint32_t tmp; + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0); +} + +/* + * Assigns hardware counter to hardware condition. + * Note that there is no separate start/stop mechanism; + * stopping is achieved by assigning the 'never' condition + */ +static void arc_pmu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (WARN_ON_ONCE(idx == -1)) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + event->hw.state = 0; + + /* enable ARC pmu here */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config); +} + +static void arc_pmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (!(event->hw.state & PERF_HES_STOPPED)) { + /* stop ARC pmu here */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + + /* condition code #0 is always "never" */ + write_aux_reg(ARC_REG_PCT_CONFIG, 0); + + event->hw.state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && + !(event->hw.state & PERF_HES_UPTODATE)) { + arc_perf_event_update(event, &event->hw, idx); + event->hw.state |= PERF_HES_UPTODATE; + } +} + +static void arc_pmu_del(struct perf_event *event, int flags) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + + arc_pmu_stop(event, PERF_EF_UPDATE); + __clear_bit(event->hw.idx, arc_pmu->used_mask); + + perf_event_update_userpage(event); +} + +/* allocate hardware counter and optionally start counting */ +static int arc_pmu_add(struct perf_event *event, int flags) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + 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, + arc_pmu->n_counters); + if (idx == arc_pmu->n_counters) + return -EAGAIN; + + __set_bit(idx, arc_pmu->used_mask); + hwc->idx = idx; + } + + write_aux_reg(ARC_REG_PCT_INDEX, idx); + write_aux_reg(ARC_REG_PCT_CONFIG, 0); + write_aux_reg(ARC_REG_PCT_COUNTL, 0); + write_aux_reg(ARC_REG_PCT_COUNTH, 0); + local64_set(&hwc->prev_count, 0); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (flags & PERF_EF_START) + arc_pmu_start(event, PERF_EF_RELOAD); + + perf_event_update_userpage(event); + + return 0; +} + +static int arc_pmu_device_probe(struct platform_device *pdev) +{ + struct arc_pmu *arc_pmu; + struct arc_reg_pct_build pct_bcr; + struct arc_reg_cc_build cc_bcr; + int i, j, ret; + + union cc_name { + struct { + uint32_t word0, word1; + char sentinel; + } indiv; + char str[9]; + } cc_name; + + + READ_BCR(ARC_REG_PCT_BUILD, pct_bcr); + if (!pct_bcr.v) { + pr_err("This core does not have performance counters!\n"); + return -ENODEV; + } + + arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), + GFP_KERNEL); + if (!arc_pmu) + return -ENOMEM; + + arc_pmu->n_counters = pct_bcr.c; + BUG_ON(arc_pmu->n_counters > ARC_PMU_MAX_HWEVENTS); + + arc_pmu->counter_size = 32 + (pct_bcr.s << 4); + pr_info("ARC PMU found with %d counters of size %d bits\n", + arc_pmu->n_counters, arc_pmu->counter_size); + + READ_BCR(ARC_REG_CC_BUILD, cc_bcr); + + if (!cc_bcr.v) + pr_err("Strange! Performance counters exist, but no countable conditions?\n"); + + pr_info("ARC PMU has %d countable conditions\n", cc_bcr.c); + + cc_name.str[8] = 0; + for (i = 0; i < PERF_COUNT_HW_MAX; i++) + arc_pmu->ev_hw_idx[i] = -1; + + for (j = 0; j < cc_bcr.c; j++) { + write_aux_reg(ARC_REG_CC_INDEX, j); + cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); + cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { + if (arc_pmu_ev_hw_map[i] && + !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) && + strlen(arc_pmu_ev_hw_map[i])) { + pr_debug("mapping %d to idx %d with name %s\n", + i, j, cc_name.str); + arc_pmu->ev_hw_idx[i] = j; + } + } + } + + arc_pmu->pmu = (struct pmu) { + .pmu_enable = arc_pmu_enable, + .pmu_disable = arc_pmu_disable, + .event_init = arc_pmu_event_init, + .add = arc_pmu_add, + .del = arc_pmu_del, + .start = arc_pmu_start, + .stop = arc_pmu_stop, + .read = arc_pmu_read, + }; + + ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); + + return ret; +} + +#ifdef CONFIG_OF +static const struct of_device_id arc_pmu_match[] = { + { .compatible = "snps,arc700-pmu" }, + {}, +}; +MODULE_DEVICE_TABLE(of, arc_pmu_match); +#endif + +static struct platform_driver arc_pmu_driver = { + .driver = { + .name = "arc700-pmu", + .of_match_table = of_match_ptr(arc_pmu_match), + }, + .probe = arc_pmu_device_probe, +}; + +module_platform_driver(arc_pmu_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mischa Jonker <mjonker@synopsys.com>"); +MODULE_DESCRIPTION("ARC PMU driver"); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index cad66851e0c..fdd89715d2d 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -55,10 +55,8 @@ asmlinkage void ret_from_fork(void); * | ... | * | unused | * | | - * ------------------ <==== top of Stack (thread.ksp) - * | UNUSED 1 word| * ------------------ - * | r25 | + * | r25 | <==== top of Stack (thread.ksp) * ~ ~ * | --to-- | (CALLEE Regs of user mode) * | r13 | @@ -76,7 +74,10 @@ asmlinkage void ret_from_fork(void); * | --to-- | (scratch Regs of user mode) * | r0 | * ------------------ - * | UNUSED 1 word| + * | SP | + * | orig_r0 | + * | event/ECR | + * | user_r25 | * ------------------ <===== END of PAGE */ int copy_thread(unsigned long clone_flags, @@ -150,6 +151,29 @@ int copy_thread(unsigned long clone_flags, } /* + * Do necessary setup to start up a new user task + */ +void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) +{ + set_fs(USER_DS); /* user space */ + + regs->sp = usp; + regs->ret = pc; + + /* + * [U]ser Mode bit set + * [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; + + /* bogus seed values for debugging */ + regs->lp_start = 0x10; + regs->lp_end = 0x80; +} + +/* * Some archs flush debug and FPU info here */ void flush_thread(void) diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c index c6a81c58d0f..13b3ffb27a3 100644 --- a/arch/arc/kernel/ptrace.c +++ b/arch/arc/kernel/ptrace.c @@ -40,7 +40,15 @@ static int genregs_get(struct task_struct *target, offsetof(struct user_regs_struct, LOC), \ offsetof(struct user_regs_struct, LOC) + 4); +#define REG_O_ZERO(LOC) \ + if (!ret) \ + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, \ + offsetof(struct user_regs_struct, LOC), \ + offsetof(struct user_regs_struct, LOC) + 4); + + REG_O_ZERO(pad); REG_O_CHUNK(scratch, callee, ptregs); + REG_O_ZERO(pad2); REG_O_CHUNK(callee, efa, cregs); REG_O_CHUNK(efa, stop_pc, &target->thread.fault_address); @@ -88,11 +96,13 @@ static int genregs_set(struct task_struct *target, offsetof(struct user_regs_struct, LOC), \ offsetof(struct user_regs_struct, LOC) + 4); - /* TBD: disallow updates to STATUS32, orig_r8 etc*/ - REG_IN_CHUNK(scratch, callee, ptregs); /* pt_regs[bta..orig_r8] */ + REG_IGNORE_ONE(pad); + /* TBD: disallow updates to STATUS32 etc*/ + REG_IN_CHUNK(scratch, pad2, ptregs); /* pt_regs[bta..sp] */ + REG_IGNORE_ONE(pad2); REG_IN_CHUNK(callee, efa, cregs); /* callee_regs[r25..r13] */ REG_IGNORE_ONE(efa); /* efa update invalid */ - REG_IN_ONE(stop_pc, &ptregs->ret); /* stop_pc: PC update */ + REG_IGNORE_ONE(stop_pc); /* PC updated via @ret */ return ret; } @@ -136,6 +146,10 @@ long arch_ptrace(struct task_struct *child, long request, pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data); switch (request) { + case PTRACE_GET_THREAD_AREA: + ret = put_user(task_thread_info(child)->thr_ptr, + (unsigned long __user *)data); + break; default: ret = ptrace_request(child, request, addr, data); break; diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c index e227a2b1c94..2768fa1e39b 100644 --- a/arch/arc/kernel/reset.c +++ b/arch/arc/kernel/reset.c @@ -31,3 +31,4 @@ void machine_power_off(void) } void (*pm_power_off) (void) = NULL; +EXPORT_SYMBOL(pm_power_off); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index b2b3731dd1e..119dddb752b 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -21,7 +21,6 @@ #include <asm/setup.h> #include <asm/page.h> #include <asm/irq.h> -#include <asm/prom.h> #include <asm/unwind.h> #include <asm/clk.h> #include <asm/mach_desc.h> @@ -30,15 +29,17 @@ int running_on_hw = 1; /* vs. on ISS */ -char __initdata command_line[COMMAND_LINE_SIZE]; -struct machine_desc *machine_desc __cpuinitdata; +/* Part of U-boot ABI: see head.S */ +int __initdata uboot_tag; +char __initdata *uboot_arg; + +const struct machine_desc *machine_desc; struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; - -void __cpuinit read_arc_build_cfg_regs(void) +static void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -47,10 +48,7 @@ void __cpuinit read_arc_build_cfg_regs(void) READ_BCR(AUX_IDENTITY, cpu->core); cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR); - cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE); - if (cpu->vec_base == 0) - cpu->vec_base = (unsigned int)_int_vec_base_lds; READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space); cpu->uncached_base = uncached_space.start << 24; @@ -109,7 +107,7 @@ static const struct cpuinfo_data arc_cpu_tbl[] = { { {0x00, NULL } } }; -char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) +static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; @@ -174,7 +172,7 @@ static const struct id_to_str mac_mul_nm[] = { {0x6, "Dual 16x16 and 32x16"} }; -char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) +static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; @@ -182,7 +180,7 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) FIX_PTR(cpu); #define IS_AVAIL1(var, str) ((var) ? str : "") #define IS_AVAIL2(var, str) ((var == 0x2) ? str : "") -#define IS_USED(var) ((var) ? "(in-use)" : "(not used)") +#define IS_USED(cfg) (IS_ENABLED(cfg) ? "(in-use)" : "(not used)") n += scnprintf(buf + n, len - n, "Extn [700-Base]\t: %s %s %s %s %s %s\n", @@ -202,9 +200,9 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) if (cpu->core.family == 0x34) { n += scnprintf(buf + n, len - n, "Extn [700-4.10]\t: LLOCK/SCOND %s, SWAPE %s, RTSC %s\n", - IS_USED(__CONFIG_ARC_HAS_LLSC_VAL), - IS_USED(__CONFIG_ARC_HAS_SWAPE_VAL), - IS_USED(__CONFIG_ARC_HAS_RTSC_VAL)); + IS_USED(CONFIG_ARC_HAS_LLSC), + IS_USED(CONFIG_ARC_HAS_SWAPE), + IS_USED(CONFIG_ARC_HAS_RTSC)); } n += scnprintf(buf + n, len - n, "Extn [CCM]\t: %s", @@ -237,7 +235,7 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) return buf; } -void __cpuinit arc_chk_ccms(void) +static void arc_chk_ccms(void) { #if defined(CONFIG_ARC_HAS_DCCM) || defined(CONFIG_ARC_HAS_ICCM) struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -272,7 +270,7 @@ void __cpuinit arc_chk_ccms(void) * hardware has dedicated regs which need to be saved/restored on ctx-sw * (Single Precision uses core regs), thus kernel is kind of oblivious to it */ -void __cpuinit arc_chk_fpu(void) +static void arc_chk_fpu(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -293,7 +291,7 @@ void __cpuinit arc_chk_fpu(void) * such as only for boot CPU etc */ -void __cpuinit setup_processor(void) +void setup_processor(void) { char str[512]; int cpu_id = smp_processor_id(); @@ -316,19 +314,40 @@ void __cpuinit setup_processor(void) arc_chk_fpu(); } +static inline int is_kernel(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) + return 1; + return 0; +} + void __init setup_arch(char **cmdline_p) { - /* This also populates @boot_command_line from /bootargs */ - machine_desc = setup_machine_fdt(__dtb_start); - if (!machine_desc) - panic("Embedded DT invalid\n"); - - /* Append any u-boot provided cmdline */ -#ifdef CONFIG_CMDLINE_UBOOT - /* Add a whitespace seperator between the 2 cmdlines */ - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, command_line, COMMAND_LINE_SIZE); -#endif + /* 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) { + /* No, so try the embedded one */ + machine_desc = setup_machine_fdt(__dtb_start); + if (!machine_desc) + panic("Embedded DT invalid\n"); + + /* + * If we are here, it is established that @uboot_arg didn't + * point to DT blob. Instead if u-boot says it is cmdline, + * Appent to embedded DT cmdline. + * setup_machine_fdt() would have populated @boot_command_line + */ + if (uboot_tag == 1) { + /* Ensure a whitespace between the 2 cmdlines */ + strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); + strlcat(boot_command_line, uboot_arg, + COMMAND_LINE_SIZE); + } + } /* Save unparsed command line copy for /proc/cmdline */ *cmdline_p = boot_command_line; @@ -349,16 +368,13 @@ void __init setup_arch(char **cmdline_p) setup_arch_memory(); /* copy flat DT out of .init and then unflatten it */ - copy_devtree(); - unflatten_device_tree(); + unflatten_and_copy_device_tree(); /* Can be issue if someone passes cmd line arg "ro" * But that is unlikely so keeping it as it is */ root_mountflags &= ~MS_RDONLY; - console_verbose(); - #if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; #endif diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index ee6ef2f60a2..7e95e1a8651 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -101,7 +101,6 @@ SYSCALL_DEFINE0(rt_sigreturn) { struct rt_sigframe __user *sf; unsigned int magic; - int err; struct pt_regs *regs = current_pt_regs(); /* Always make any pending restarted system calls return -EINTR */ @@ -119,15 +118,16 @@ SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(VERIFY_READ, sf, sizeof(*sf))) goto badframe; - err = restore_usr_regs(regs, sf); - err |= __get_user(magic, &sf->sigret_magic); - if (err) + if (__get_user(magic, &sf->sigret_magic)) goto badframe; if (unlikely(is_do_ss_needed(magic))) if (restore_altstack(&sf->uc.uc_stack)) goto badframe; + if (restore_usr_regs(regs, sf)) + goto badframe; + /* Don't restart from sigreturn */ syscall_wont_restart(regs); @@ -191,6 +191,15 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info, return 1; /* + * w/o SA_SIGINFO, struct ucontext is partially populated (only + * uc_mcontext/uc_sigmask) for kernel's normal user state preservation + * during signal handler execution. This works for SA_SIGINFO as well + * although the semantics are now overloaded (the same reg state can be + * inspected by userland: but are they allowed to fiddle with it ? + */ + err |= stash_usr_regs(sf, regs, set); + + /* * SA_SIGINFO requires 3 args to signal handler: * #1: sig-no (common to any handler) * #2: struct siginfo @@ -213,14 +222,6 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info, magic = MAGIC_SIGALTSTK; } - /* - * w/o SA_SIGINFO, struct ucontext is partially populated (only - * uc_mcontext/uc_sigmask) for kernel's normal user state preservation - * during signal handler execution. This works for SA_SIGINFO as well - * although the semantics are now overloaded (the same reg state can be - * inspected by userland: but are they allowed to fiddle with it ? - */ - err |= stash_usr_regs(sf, regs, set); err |= __put_user(magic, &sf->sigret_magic); if (err) return err; diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 5c7fd603d21..c802bb50060 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -95,7 +95,7 @@ void __init smp_cpus_done(unsigned int max_cpus) * If it turns out to be elaborate, it's better to code it in assembly * */ -void __attribute__((weak)) arc_platform_smp_wait_to_boot(int cpu) +void __weak arc_platform_smp_wait_to_boot(int cpu) { /* * As a hack for debugging - since debugger will single-step over the @@ -117,7 +117,7 @@ const char *arc_platform_smp_cpuinfo(void) * Called from asm stub in head.S * "current"/R25 already setup by low level boot code */ -void __cpuinit start_kernel_secondary(void) +void start_kernel_secondary(void) { struct mm_struct *mm = &init_mm; unsigned int cpu = smp_processor_id(); @@ -128,6 +128,7 @@ void __cpuinit start_kernel_secondary(void) atomic_inc(&mm->mm_users); atomic_inc(&mm->mm_count); current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); notify_cpu_starting(cpu); set_cpu_online(cpu, true); @@ -137,7 +138,7 @@ void __cpuinit start_kernel_secondary(void) if (machine_desc->init_smp) machine_desc->init_smp(smp_processor_id()); - arc_local_timer_setup(cpu); + arc_local_timer_setup(); local_irq_enable(); preempt_disable(); @@ -154,7 +155,7 @@ void __cpuinit start_kernel_secondary(void) * * Essential requirements being where to run from (PC) and stack (SP) */ -int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle) +int __cpu_up(unsigned int cpu, struct task_struct *idle) { unsigned long wait_till; @@ -196,52 +197,65 @@ int __init setup_profiling_timer(unsigned int multiplier) /* Inter Processor Interrupt Handling */ /*****************************************************************************/ -/* - * structures for inter-processor calls - * A Collection of single bit ipi messages - * - */ - -/* - * TODO_rajesh investigate tlb message types. - * IPI Timer not needed because each ARC has an individual Interrupting Timer - */ enum ipi_msg_type { - IPI_NOP = 0, + IPI_EMPTY = 0, IPI_RESCHEDULE = 1, IPI_CALL_FUNC, - IPI_CALL_FUNC_SINGLE, - IPI_CPU_STOP + IPI_CPU_STOP, }; -struct ipi_data { - unsigned long bits; -}; +/* + * In arches with IRQ for each msg type (above), receiver can use IRQ-id to + * figure out what msg was sent. For those which don't (ARC has dedicated IPI + * IRQ), the msg-type needs to be conveyed via per-cpu data + */ -static DEFINE_PER_CPU(struct ipi_data, ipi_data); +static DEFINE_PER_CPU(unsigned long, ipi_data); -static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg) +static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) { + unsigned long __percpu *ipi_data_ptr = per_cpu_ptr(&ipi_data, cpu); + unsigned long old, new; unsigned long flags; - unsigned int cpu; + + pr_debug("%d Sending msg [%d] to %d\n", smp_processor_id(), msg, cpu); local_irq_save(flags); - for_each_cpu(cpu, callmap) { - struct ipi_data *ipi = &per_cpu(ipi_data, cpu); - set_bit(msg, &ipi->bits); - } + /* + * Atomically write new msg bit (in case others are writing too), + * and read back old value + */ + do { + new = old = *ipi_data_ptr; + new |= 1U << msg; + } while (cmpxchg(ipi_data_ptr, old, new) != old); - /* Call the platform specific cross-CPU call function */ - if (plat_smp_ops.ipi_send) - plat_smp_ops.ipi_send((void *)callmap); + /* + * Call the platform specific IPI kick function, but avoid if possible: + * Only do so if there's no pending msg from other concurrent sender(s). + * Otherwise, recevier will see this msg as well when it takes the + * IPI corresponding to that msg. This is true, even if it is already in + * IPI handler, because !@old means it has not yet dequeued the msg(s) + * so @new msg can be a free-loader + */ + if (plat_smp_ops.ipi_send && !old) + plat_smp_ops.ipi_send(cpu); local_irq_restore(flags); } +static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg) +{ + unsigned int cpu; + + for_each_cpu(cpu, callmap) + ipi_send_msg_one(cpu, msg); +} + void smp_send_reschedule(int cpu) { - ipi_send_msg(cpumask_of(cpu), IPI_RESCHEDULE); + ipi_send_msg_one(cpu, IPI_RESCHEDULE); } void smp_send_stop(void) @@ -254,7 +268,7 @@ void smp_send_stop(void) void arch_send_call_function_single_ipi(int cpu) { - ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); + ipi_send_msg_one(cpu, IPI_CALL_FUNC); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -265,37 +279,29 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) /* * ipi_cpu_stop - handle IPI from smp_send_stop() */ -static void ipi_cpu_stop(unsigned int cpu) +static void ipi_cpu_stop(void) { machine_halt(); } -static inline void __do_IPI(unsigned long *ops, struct ipi_data *ipi, int cpu) +static inline void __do_IPI(unsigned long msg) { - unsigned long msg = 0; - - do { - msg = find_next_bit(ops, BITS_PER_LONG, msg+1); + switch (msg) { + case IPI_RESCHEDULE: + scheduler_ipi(); + break; - switch (msg) { - case IPI_RESCHEDULE: - scheduler_ipi(); - break; - - case IPI_CALL_FUNC: - generic_smp_call_function_interrupt(); - break; - - case IPI_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; - case IPI_CPU_STOP: - ipi_cpu_stop(cpu); - break; - } - } while (msg < BITS_PER_LONG); + case IPI_CPU_STOP: + ipi_cpu_stop(); + break; + default: + pr_warn("IPI with unexpected msg %ld\n", msg); + } } /* @@ -304,19 +310,25 @@ static inline void __do_IPI(unsigned long *ops, struct ipi_data *ipi, int cpu) */ irqreturn_t do_IPI(int irq, void *dev_id) { - int cpu = smp_processor_id(); - struct ipi_data *ipi = &per_cpu(ipi_data, cpu); - unsigned long ops; + unsigned long pending; + + pr_debug("IPI [%ld] received on cpu %d\n", + *this_cpu_ptr(&ipi_data), smp_processor_id()); if (plat_smp_ops.ipi_clear) - plat_smp_ops.ipi_clear(cpu, irq); + plat_smp_ops.ipi_clear(irq); /* - * XXX: is this loop really needed - * And do we need to move ipi_clean inside + * "dequeue" the msg corresponding to this IPI (and possibly other + * piggybacked msg from elided IPIs: see ipi_send_msg_one() above) */ - while ((ops = xchg(&ipi->bits, 0)) != 0) - __do_IPI(&ops, ipi, cpu); + pending = xchg(this_cpu_ptr(&ipi_data), 0); + + do { + unsigned long msg = __ffs(pending); + __do_IPI(msg); + pending &= ~(1U << msg); + } while (pending); return IRQ_HANDLED; } @@ -325,8 +337,19 @@ irqreturn_t do_IPI(int irq, void *dev_id) * API called by platform code to hookup arch-common ISR to their IPI IRQ */ static DEFINE_PER_CPU(int, ipi_dev); + +static struct irqaction arc_ipi_irq = { + .name = "IPI Interrupt", + .flags = IRQF_PERCPU, + .handler = do_IPI, +}; + int smp_ipi_irq_setup(int cpu, int irq) { - int *dev_id = &per_cpu(ipi_dev, smp_processor_id()); - return request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev_id); + if (!cpu) + return setup_irq(irq, &arc_ipi_irq); + else + arch_unmask_irq(irq); + + return 0; } diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index ca0207b9d5b..9ce47cfe230 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -79,7 +79,7 @@ static void seed_unwind_frame_info(struct task_struct *tsk, * assembly code */ frame_info->regs.r27 = 0; - frame_info->regs.r28 += 64; + frame_info->regs.r28 += 60; frame_info->call_frame = 0; } else { @@ -237,11 +237,14 @@ unsigned int get_wchan(struct task_struct *tsk) */ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { + /* Assumes @tsk is sleeping so unwinds from __switch_to */ arc_unwind_core(tsk, NULL, __collect_all_but_sched, trace); } void save_stack_trace(struct stack_trace *trace) { - arc_unwind_core(current, NULL, __collect_all, trace); + /* Pass NULL for task so it unwinds the current call frame */ + arc_unwind_core(NULL, NULL, __collect_all, trace); } +EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 09f4309aa2c..36c2aa99436 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -44,17 +44,29 @@ #include <asm/clk.h> #include <asm/mach_desc.h> +/* Timer related Aux registers */ +#define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ +#define ARC_REG_TIMER0_CTRL 0x22 /* timer 0 control */ +#define ARC_REG_TIMER0_CNT 0x21 /* timer 0 count */ +#define ARC_REG_TIMER1_LIMIT 0x102 /* timer 1 limit */ +#define ARC_REG_TIMER1_CTRL 0x101 /* timer 1 control */ +#define ARC_REG_TIMER1_CNT 0x100 /* timer 1 count */ + +#define TIMER_CTRL_IE (1 << 0) /* Interupt when Count reachs limit */ +#define TIMER_CTRL_NH (1 << 1) /* Count only when CPU NOT halted */ + #define ARC_TIMER_MAX 0xFFFFFFFF /********** Clock Source Device *********/ #ifdef CONFIG_ARC_HAS_RTSC -int __cpuinit arc_counter_setup(void) +int arc_counter_setup(void) { - /* RTSC insn taps into cpu clk, needs no setup */ - - /* For SMP, only allowed if cross-core-sync, hence usable as cs */ + /* + * For SMP this needs to be 0. However Kconfig glue doesn't + * enable this option for SMP configs + */ return 1; } @@ -105,7 +117,7 @@ static bool is_usable_as_clocksource(void) /* * set 32bit TIMER1 to keep counting monotonically and wraparound */ -int __cpuinit arc_counter_setup(void) +int arc_counter_setup(void) { write_aux_reg(ARC_REG_TIMER1_LIMIT, ARC_TIMER_MAX); write_aux_reg(ARC_REG_TIMER1_CNT, 0); @@ -143,22 +155,6 @@ static void arc_timer_event_setup(unsigned int limit) write_aux_reg(ARC_REG_TIMER0_CTRL, TIMER_CTRL_IE | TIMER_CTRL_NH); } -/* - * Acknowledge the interrupt (oneshot) and optionally re-arm it (periodic) - * -Any write to CTRL Reg will ack the intr (NH bit: Count when not halted) - * -Rearming is done by setting the IE bit - * - * Small optimisation: Normal code would have been - * if (irq_reenable) - * CTRL_REG = (IE | NH); - * else - * CTRL_REG = NH; - * However since IE is BIT0 we can fold the branch - */ -static void arc_timer_event_ack(unsigned int irq_reenable) -{ - write_aux_reg(ARC_REG_TIMER0_CTRL, irq_reenable | TIMER_CTRL_NH); -} static int arc_clkevent_set_next_event(unsigned long delta, struct clock_event_device *dev) @@ -195,10 +191,22 @@ static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = { static irqreturn_t timer_irq_handler(int irq, void *dev_id) { - struct clock_event_device *clk = &__get_cpu_var(arc_clockevent_device); + /* + * Note that generic IRQ core could have passed @evt for @dev_id if + * 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; + + /* + * Any write to CTRL reg ACks the interrupt, we rewrite the + * Count when [N]ot [H]alted bit. + * And re-arm it if perioid by [I]nterrupt [E]nable bit + */ + write_aux_reg(ARC_REG_TIMER0_CTRL, irq_reenable | TIMER_CTRL_NH); + + evt->event_handler(evt); - arc_timer_event_ack(clk->mode == CLOCK_EVT_MODE_PERIODIC); - clk->event_handler(clk); return IRQ_HANDLED; } @@ -210,18 +218,15 @@ static struct irqaction arc_timer_irq = { /* * Setup the local event timer for @cpu - * N.B. weak so that some exotic ARC SoCs can completely override it */ -void __attribute__((weak)) __cpuinit arc_local_timer_setup(unsigned int cpu) +void arc_local_timer_setup() { - struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu); - - clockevents_calc_mult_shift(clk, arc_get_core_freq(), 5); - - clk->max_delta_ns = clockevent_delta2ns(ARC_TIMER_MAX, clk); - clk->cpumask = cpumask_of(cpu); + struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device); + int cpu = smp_processor_id(); - clockevents_register_device(clk); + evt->cpumask = cpumask_of(cpu); + clockevents_config_and_register(evt, arc_get_core_freq(), + 0, ARC_TIMER_MAX); /* * setup the per-cpu timer IRQ handler - for all cpus @@ -257,7 +262,7 @@ void __init time_init(void) clocksource_register_hz(&arc_counter, arc_get_core_freq()); /* sets up the periodic event timer */ - arc_local_timer_setup(smp_processor_id()); + arc_local_timer_setup(); if (machine_desc->init_time) machine_desc->init_time(); diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index 0471d9c9dd5..3eadfdabc32 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -28,10 +28,9 @@ void __init trap_init(void) return; } -void die(const char *str, struct pt_regs *regs, unsigned long address, - unsigned long cause_reg) +void die(const char *str, struct pt_regs *regs, unsigned long address) { - show_kernel_fault_diag(str, regs, address, cause_reg); + show_kernel_fault_diag(str, regs, address); /* DEAD END */ __asm__("flag 1"); @@ -42,14 +41,13 @@ void die(const char *str, struct pt_regs *regs, unsigned long address, * -for user faults enqueues requested signal * -for kernel, chk if due to copy_(to|from)_user, otherwise die() */ -static noinline int handle_exception(unsigned long cause, char *str, - struct pt_regs *regs, siginfo_t *info) +static noinline int +handle_exception(const char *str, struct pt_regs *regs, siginfo_t *info) { if (user_mode(regs)) { struct task_struct *tsk = current; tsk->thread.fault_address = (__force unsigned int)info->si_addr; - tsk->thread.cause_code = cause; force_sig_info(info->si_signo, info, tsk); @@ -58,14 +56,14 @@ static noinline int handle_exception(unsigned long cause, char *str, if (fixup_exception(regs)) return 0; - die(str, regs, (unsigned long)info->si_addr, cause); + die(str, regs, (unsigned long)info->si_addr); } return 1; } #define DO_ERROR_INFO(signr, str, name, sicode) \ -int name(unsigned long cause, unsigned long address, struct pt_regs *regs) \ +int name(unsigned long address, struct pt_regs *regs) \ { \ siginfo_t info = { \ .si_signo = signr, \ @@ -73,7 +71,7 @@ int name(unsigned long cause, unsigned long address, struct pt_regs *regs) \ .si_code = sicode, \ .si_addr = (void __user *)address, \ }; \ - return handle_exception(cause, str, regs, &info);\ + return handle_exception(str, regs, &info);\ } /* @@ -86,28 +84,26 @@ DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", do_memory_error, BUS_ADRERR) DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT) DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN) -#ifdef CONFIG_ARC_MISALIGN_ACCESS /* * Entry Point for Misaligned Data access Exception, for emulating in software */ -int do_misaligned_access(unsigned long cause, unsigned long address, - struct pt_regs *regs, struct callee_regs *cregs) +int do_misaligned_access(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs) { - if (misaligned_fixup(address, regs, cause, cregs) != 0) - return do_misaligned_error(cause, address, regs); + /* If emulation not enabled, or failed, kill the task */ + if (misaligned_fixup(address, regs, cregs) != 0) + return do_misaligned_error(address, regs); return 0; } -#endif /* * Entry point for miscll errors such as Nested Exceptions * -Duplicate TLB entry is handled seperately though */ -void do_machine_check_fault(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void do_machine_check_fault(unsigned long address, struct pt_regs *regs) { - die("Machine Check Exception", regs, address, cause); + die("Machine Check Exception", regs, address); } @@ -120,23 +116,22 @@ void do_machine_check_fault(unsigned long cause, unsigned long address, * -1 used for software breakpointing (gdb) * -2 used by kprobes */ -void do_non_swi_trap(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void do_non_swi_trap(unsigned long address, struct pt_regs *regs) { - unsigned int param = cause & 0xff; + unsigned int param = regs->ecr_param; switch (param) { case 1: - trap_is_brkpt(cause, address, regs); + trap_is_brkpt(address, regs); break; case 2: - trap_is_kprobe(param, address, regs); + trap_is_kprobe(address, regs); break; case 3: case 4: - kgdb_trap(regs, param); + kgdb_trap(regs); break; default: @@ -149,14 +144,14 @@ void do_non_swi_trap(unsigned long cause, unsigned long address, * -For a corner case, ARC kprobes implementation resorts to using * this exception, hence the check */ -void do_insterror_or_kprobe(unsigned long cause, - unsigned long address, - struct pt_regs *regs) +void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs) { + int rc; + /* Check if this exception is caused by kprobes */ - if (notify_die(DIE_IERR, "kprobe_ierr", regs, address, - cause, SIGILL) == NOTIFY_STOP) + rc = notify_die(DIE_IERR, "kprobe_ierr", regs, address, 0, SIGILL); + if (rc == NOTIFY_STOP) return; - insterror_is_error(cause, address, regs); + insterror_is_error(address, regs); } diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 11c301b81c9..1badf9b84b5 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -86,12 +86,13 @@ static void show_faulting_vma(unsigned long address, char *buf) unsigned long ino = 0; dev_t dev = 0; char *nm = buf; + struct mm_struct *active_mm = current->active_mm; /* can't use print_vma_addr() yet as it doesn't check for * non-inclusive vma */ - - vma = find_vma(current->active_mm, address); + down_read(&active_mm->mmap_sem); + vma = find_vma(active_mm, address); /* check against the find_vma( ) behaviour which returns the next VMA * if the container VMA is not found @@ -101,7 +102,7 @@ static void show_faulting_vma(unsigned long address, char *buf) if (file) { struct path *path = &file->f_path; nm = d_path(path, buf, PAGE_SIZE - 1); - inode = vma->vm_file->f_path.dentry->d_inode; + inode = file_inode(vma->vm_file); dev = inode->i_sb->s_dev; ino = inode->i_ino; } @@ -110,30 +111,30 @@ static void show_faulting_vma(unsigned long address, char *buf) vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); - } else { + } else pr_info(" @No matching VMA found\n"); - } + + up_read(&active_mm->mmap_sem); } static void show_ecr_verbose(struct pt_regs *regs) { - unsigned int vec, cause_code, cause_reg; + unsigned int vec, cause_code; unsigned long address; - cause_reg = current->thread.cause_code; - pr_info("\n[ECR ]: 0x%08x => ", cause_reg); + pr_info("\n[ECR ]: 0x%08lx => ", regs->event); /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; - vec = cause_reg >> 16; - cause_code = (cause_reg >> 8) & 0xFF; + vec = regs->ecr_vec; + cause_code = regs->ecr_cause; /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s 0x%08lx by insn @ 0x%08lx\n", - (cause_code == 0x01) ? "Read From" : - ((cause_code == 0x02) ? "Write to" : "EX"), + pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + (cause_code == 0x01) ? "Read" : + ((cause_code == 0x02) ? "Write" : "EX"), address, regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); @@ -144,14 +145,12 @@ static void show_ecr_verbose(struct pt_regs *regs) } else if (vec == ECR_V_PROTV) { if (cause_code == ECR_C_PROTV_INST_FETCH) pr_cont("Execute from Non-exec Page\n"); - else if (cause_code == ECR_C_PROTV_LOAD) - pr_cont("Read from Non-readable Page\n"); - else if (cause_code == ECR_C_PROTV_STORE) - pr_cont("Write to Non-writable Page\n"); - else if (cause_code == ECR_C_PROTV_XCHG) - pr_cont("Data exchange protection violation\n"); else if (cause_code == ECR_C_PROTV_MISALIG_DATA) pr_cont("Misaligned r/w from 0x%08lx\n", address); + else + pr_cont("%s access not allowed on page\n", + (cause_code == 0x01) ? "Read" : + ((cause_code == 0x02) ? "Write" : "EX")); } else if (vec == ECR_V_INSN_ERR) { pr_cont("Illegal Insn\n"); } else { @@ -176,8 +175,7 @@ void show_regs(struct pt_regs *regs) print_task_path_n_nm(tsk, buf); show_regs_print_info(KERN_INFO); - if (current->thread.cause_code) - show_ecr_verbose(regs); + show_ecr_verbose(regs); pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", current->thread.fault_address, @@ -213,10 +211,9 @@ void show_regs(struct pt_regs *regs) } void show_kernel_fault_diag(const char *str, struct pt_regs *regs, - unsigned long address, unsigned long cause_reg) + unsigned long address) { current->thread.fault_address = address; - current->thread.cause_code = cause_reg; /* Caller and Callee regs */ show_regs(regs); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 4cd81633feb..7ff5b5c183b 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -16,6 +16,16 @@ #include <linux/uaccess.h> #include <asm/disasm.h> +#ifdef CONFIG_CPU_BIG_ENDIAN +#define BE 1 +#define FIRST_BYTE_16 "swap %1, %1\n swape %1, %1\n" +#define FIRST_BYTE_32 "swape %1, %1\n" +#else +#define BE 0 +#define FIRST_BYTE_16 +#define FIRST_BYTE_32 +#endif + #define __get8_unaligned_check(val, addr, err) \ __asm__( \ "1: ldb.ab %1, [%2, 1]\n" \ @@ -36,9 +46,9 @@ do { \ unsigned int err = 0, v, a = addr; \ __get8_unaligned_check(v, a, err); \ - val = v ; \ + val = v << ((BE) ? 8 : 0); \ __get8_unaligned_check(v, a, err); \ - val |= v << 8; \ + val |= v << ((BE) ? 0 : 8); \ if (err) \ goto fault; \ } while (0) @@ -47,13 +57,13 @@ do { \ unsigned int err = 0, v, a = addr; \ __get8_unaligned_check(v, a, err); \ - val = v << 0; \ + val = v << ((BE) ? 24 : 0); \ __get8_unaligned_check(v, a, err); \ - val |= v << 8; \ + val |= v << ((BE) ? 16 : 8); \ __get8_unaligned_check(v, a, err); \ - val |= v << 16; \ + val |= v << ((BE) ? 8 : 16); \ __get8_unaligned_check(v, a, err); \ - val |= v << 24; \ + val |= v << ((BE) ? 0 : 24); \ if (err) \ goto fault; \ } while (0) @@ -63,6 +73,7 @@ unsigned int err = 0, v = val, a = addr;\ \ __asm__( \ + FIRST_BYTE_16 \ "1: stb.ab %1, [%2, 1]\n" \ " lsr %1, %1, 8\n" \ "2: stb %1, [%2]\n" \ @@ -87,8 +98,9 @@ #define put32_unaligned_check(val, addr) \ do { \ unsigned int err = 0, v = val, a = addr;\ - __asm__( \ \ + __asm__( \ + FIRST_BYTE_32 \ "1: stb.ab %1, [%2, 1]\n" \ " lsr %1, %1, 8\n" \ "2: stb.ab %1, [%2, 1]\n" \ @@ -187,7 +199,7 @@ fault: state->fault = 1; * Returns 0 if successfully handled, 1 if some error happened */ int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs) + struct callee_regs *cregs) { struct disasm_state state; char buf[TASK_COMM_LEN]; @@ -233,6 +245,12 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; + + /* handle zero-overhead-loop */ + if ((regs->ret == regs->lp_end) && (regs->lp_count)) { + regs->ret = regs->lp_start; + regs->lp_count--; + } } return 0; diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index a8d02223da4..e550b117ec4 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -289,6 +289,8 @@ static void __init setup_unwind_table(struct unwind_table *table, * instead of the initial loc addr * return; */ + WARN(1, "unwinder: FDE->initial_location NULL %p\n", + (const u8 *)(fde + 1) + *fde); } ++n; } diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index d3c92f52d44..dd35bde39f6 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -116,7 +116,7 @@ SECTIONS _edata = .; - BSS_SECTION(0, 0, 0) + BSS_SECTION(4, 4, 4) #ifdef CONFIG_ARC_DW2_UNWIND . = ALIGN(PAGE_SIZE); @@ -125,6 +125,11 @@ SECTIONS *(.debug_frame) __end_unwind = .; } + /* + * gcc 4.8 generates this for -fasynchonous-unwind-tables, + * while we still use the .debug_frame based unwinder + */ + /DISCARD/ : { *(.eh_frame) } #else /DISCARD/ : { *(.debug_frame) } #endif @@ -142,15 +147,18 @@ SECTIONS *(.arcextmap.*) } +#ifndef CONFIG_DEBUG_INFO /* open-coded because we need .debug_frame seperately for unwinding */ - .debug_aranges 0 : { *(.debug_aranges) } - .debug_pubnames 0 : { *(.debug_pubnames) } - .debug_info 0 : { *(.debug_info) } - .debug_abbrev 0 : { *(.debug_abbrev) } - .debug_line 0 : { *(.debug_line) } - .debug_str 0 : { *(.debug_str) } - .debug_loc 0 : { *(.debug_loc) } - .debug_macinfo 0 : { *(.debug_macinfo) } + /DISCARD/ : { *(.debug_aranges) } + /DISCARD/ : { *(.debug_pubnames) } + /DISCARD/ : { *(.debug_info) } + /DISCARD/ : { *(.debug_abbrev) } + /DISCARD/ : { *(.debug_line) } + /DISCARD/ : { *(.debug_str) } + /DISCARD/ : { *(.debug_loc) } + /DISCARD/ : { *(.debug_macinfo) } + /DISCARD/ : { *(.debug_ranges) } +#endif #ifdef CONFIG_ARC_HAS_DCCM . = CONFIG_ARC_DCCM_BASE; diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S index bc813d55b6c..978bf8314df 100644 --- a/arch/arc/lib/memcmp.S +++ b/arch/arc/lib/memcmp.S @@ -6,7 +6,7 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> #ifdef __LITTLE_ENDIAN__ #define WORD2 r2 @@ -16,7 +16,7 @@ #define SHIFT r2 #endif -ARC_ENTRY memcmp +ENTRY(memcmp) or r12,r0,r1 asl_s r12,r12,30 sub r3,r2,1 @@ -121,4 +121,4 @@ ARC_ENTRY memcmp .Lnil: j_s.d [blink] mov r0,0 -ARC_EXIT memcmp +END(memcmp) diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S index b64cc10ac91..3222573e50d 100644 --- a/arch/arc/lib/memcpy-700.S +++ b/arch/arc/lib/memcpy-700.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY memcpy +ENTRY(memcpy) or r3,r0,r1 asl_s r3,r3,30 mov_s r5,r0 @@ -63,4 +63,4 @@ ARC_ENTRY memcpy .Lendbloop: j_s.d [blink] stb r12,[r5,0] -ARC_EXIT memcpy +END(memcpy) diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S index 9b2d88d2e14..d36bd43fc98 100644 --- a/arch/arc/lib/memset.S +++ b/arch/arc/lib/memset.S @@ -6,11 +6,11 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> #define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ -ARC_ENTRY memset +ENTRY(memset) mov_s r4,r0 or r12,r0,r2 bmsk.f r12,r12,1 @@ -46,14 +46,14 @@ ARC_ENTRY memset stb.ab r1,[r4,1] .Ltiny_end: j_s [blink] -ARC_EXIT memset +END(memset) ; memzero: @r0 = mem, @r1 = size_t ; memset: @r0 = mem, @r1 = char, @r2 = size_t -ARC_ENTRY memzero +ENTRY(memzero) ; adjust bzero args to memset args mov r2, r1 mov r1, 0 b memset ;tail call so need to tinker with blink -ARC_EXIT memzero +END(memzero) diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index 99c10475d47..b725d586210 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -11,9 +11,9 @@ presence of the norm instruction makes it easier to operate on whole words branch-free. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strchr +ENTRY(strchr) extb_s r1,r1 asl r5,r1,8 bmsk r2,r0,1 @@ -39,9 +39,18 @@ ARC_ENTRY strchr ld.a r2,[r0,4] sub r12,r6,r7 bic r12,r12,r6 +#ifdef __LITTLE_ENDIAN__ and r7,r12,r4 breq r7,0,.Loop ; For speed, we want this branch to be unaligned. b .Lfound_char ; Likewise this one. +#else + and r12,r12,r4 + breq r12,0,.Loop ; For speed, we want this branch to be unaligned. + lsr_s r12,r12,7 + bic r2,r7,r6 + b.d .Lfound_char_b + and_s r2,r2,r12 +#endif ; /* We require this code address to be unaligned for speed... */ .Laligned: ld_s r2,[r0] @@ -95,6 +104,7 @@ ARC_ENTRY strchr lsr r7,r7,7 bic r2,r7,r6 +.Lfound_char_b: norm r2,r2 sub_s r0,r0,4 asr_s r2,r2,3 @@ -120,4 +130,4 @@ ARC_ENTRY strchr j_s.d [blink] mov.mi r0,0 #endif /* ENDIAN */ -ARC_EXIT strchr +END(strchr) diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S index 5dc802b45cf..3544600fefe 100644 --- a/arch/arc/lib/strcmp.S +++ b/arch/arc/lib/strcmp.S @@ -13,9 +13,9 @@ source 1; however, that would increase the overhead for loop setup / finish, and strcmp might often terminate early. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strcmp +ENTRY(strcmp) or r2,r0,r1 bmsk_s r2,r2,1 brne r2,0,.Lcharloop @@ -93,4 +93,4 @@ ARC_ENTRY strcmp .Lcmpend: j_s.d [blink] sub r0,r2,r3 -ARC_EXIT strcmp +END(strcmp) diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S index b7ca4ae81d8..8422f38e121 100644 --- a/arch/arc/lib/strcpy-700.S +++ b/arch/arc/lib/strcpy-700.S @@ -16,9 +16,9 @@ there, but the it is not likely to be taken often, and it would also be likey to cost an unaligned mispredict at the next call. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strcpy +ENTRY(strcpy) or r2,r0,r1 bmsk_s r2,r2,1 brne.d r2,0,charloop @@ -67,4 +67,4 @@ charloop: brne.d r3,0,charloop stb.ab r3,[r10,1] j [blink] -ARC_EXIT strcpy +END(strcpy) diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S index 39759e09969..53cfd5685a5 100644 --- a/arch/arc/lib/strlen.S +++ b/arch/arc/lib/strlen.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strlen +ENTRY(strlen) or r3,r0,7 ld r2,[r3,-7] ld.a r6,[r3,-3] @@ -80,4 +80,4 @@ ARC_ENTRY strlen .Learly_end: b.d .Lend sub_s.ne r1,r1,r1 -ARC_EXIT strlen +END(strlen) diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index aedce190544..353b202c37c 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,10 +73,9 @@ #include <asm/cachectl.h> #include <asm/setup.h> -char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) +char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; - unsigned int c = smp_processor_id(); #define PR_CACHE(p, enb, str) \ { \ @@ -89,8 +88,10 @@ char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) enb ? "" : "DISABLED (kernel-build)"); \ } - PR_CACHE(&cpuinfo_arc700[c].icache, __CONFIG_ARC_HAS_ICACHE, "I-Cache"); - PR_CACHE(&cpuinfo_arc700[c].dcache, __CONFIG_ARC_HAS_DCACHE, "D-Cache"); + PR_CACHE(&cpuinfo_arc700[c].icache, IS_ENABLED(CONFIG_ARC_HAS_ICACHE), + "I-Cache"); + PR_CACHE(&cpuinfo_arc700[c].dcache, IS_ENABLED(CONFIG_ARC_HAS_DCACHE), + "D-Cache"); return buf; } @@ -100,17 +101,23 @@ char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) * the cpuinfo structure for later use. * No Validation done here, simply read/convert the BCRs */ -void __cpuinit read_decode_cache_bcr(void) +void read_decode_cache_bcr(void) { - struct bcr_cache ibcr, dbcr; struct cpuinfo_arc_cache *p_ic, *p_dc; unsigned int cpu = smp_processor_id(); + struct bcr_cache { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:12, line_len:4, sz:4, config:4, ver:8; +#else + unsigned int ver:8, config:4, sz:4, line_len:4, pad:12; +#endif + } ibcr, dbcr; p_ic = &cpuinfo_arc700[cpu].icache; READ_BCR(ARC_REG_IC_BCR, ibcr); - if (ibcr.config == 0x3) - p_ic->assoc = 2; + BUG_ON(ibcr.config != 3); + p_ic->assoc = 2; /* Fixed to 2w set assoc */ p_ic->line_len = 8 << ibcr.line_len; p_ic->sz = 0x200 << ibcr.sz; p_ic->ver = ibcr.ver; @@ -118,8 +125,8 @@ void __cpuinit read_decode_cache_bcr(void) p_dc = &cpuinfo_arc700[cpu].dcache; READ_BCR(ARC_REG_DC_BCR, dbcr); - if (dbcr.config == 0x2) - p_dc->assoc = 4; + 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 = 0x200 << dbcr.sz; p_dc->ver = dbcr.ver; @@ -132,93 +139,116 @@ void __cpuinit read_decode_cache_bcr(void) * 3. Enable the Caches, setup default flush mode for D-Cache * 3. Calculate the SHMLBA used by user space */ -void __cpuinit arc_cache_init(void) +void arc_cache_init(void) { - unsigned int temp; - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - int way_pg_ratio = way_pg_ratio; - int dcache_does_alias; + unsigned int __maybe_unused cpu = smp_processor_id(); + struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (!ic->ver) - goto chk_dc; - #ifdef CONFIG_ARC_HAS_ICACHE - /* 1. Confirm some of I-cache params which Linux assumes */ - if ((ic->assoc != ARC_ICACHE_WAYS) || - (ic->line_len != ARC_ICACHE_LINE_LEN)) { - panic("Cache H/W doesn't match kernel Config"); + ic = &cpuinfo_arc700[cpu].icache; + if (ic->ver) { + 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); } -#if (CONFIG_ARC_MMU_VER > 2) - if (ic->ver != 3) { - if (running_on_hw) - panic("Cache ver doesn't match MMU ver\n"); +#endif - /* For ISS - suggest the toggles to use */ - pr_err("Use -prop=icache_version=3,-prop=dcache_version=3\n"); +#ifdef CONFIG_ARC_HAS_DCACHE + dc = &cpuinfo_arc700[cpu].dcache; + if (dc->ver) { + unsigned int dcache_does_alias; - } -#endif -#endif + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); - /* Enable/disable I-Cache */ - temp = read_aux_reg(ARC_REG_IC_CTRL); + /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_ICACHE - temp &= ~IC_CTRL_CACHE_DISABLE; -#else - temp |= IC_CTRL_CACHE_DISABLE; + if (dcache_does_alias && !cache_is_vipt_aliasing()) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dcache_does_alias && cache_is_vipt_aliasing()) + panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } #endif +} - write_aux_reg(ARC_REG_IC_CTRL, temp); +#define OP_INV 0x1 +#define OP_FLUSH 0x2 +#define OP_FLUSH_N_INV 0x3 +#define OP_INV_IC 0x4 -chk_dc: - if (!dc->ver) - return; +/* + * Common Helper for Line Operations on {I,D}-Cache + */ +static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, + unsigned long sz, const int cacheop) +{ + unsigned int aux_cmd, aux_tag; + int num_lines; + const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_DCACHE - if ((dc->assoc != ARC_DCACHE_WAYS) || - (dc->line_len != ARC_DCACHE_LINE_LEN)) { - panic("Cache H/W doesn't match kernel Config"); + if (cacheop == OP_INV_IC) { + aux_cmd = ARC_REG_IC_IVIL; +#if (CONFIG_ARC_MMU_VER > 2) + aux_tag = ARC_REG_IC_PTAG; +#endif } - - dcache_does_alias = (dc->sz / ARC_DCACHE_WAYS) > PAGE_SIZE; - - /* check for D-Cache aliasing */ - if (dcache_does_alias && !cache_is_vipt_aliasing()) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dcache_does_alias && cache_is_vipt_aliasing()) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + 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) + aux_tag = ARC_REG_DC_PTAG; #endif + } - /* Set the default Invalidate Mode to "simpy discard dirty lines" - * as this is more frequent then flush before invalidate - * Ofcourse we toggle this default behviour when desired + /* 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). */ - temp = read_aux_reg(ARC_REG_DC_CTRL); - temp &= ~DC_CTRL_INV_MODE_FLUSH; + if (!full_page_op) { + sz += paddr & ~CACHE_LINE_MASK; + paddr &= CACHE_LINE_MASK; + vaddr &= CACHE_LINE_MASK; + } -#ifdef CONFIG_ARC_HAS_DCACHE - /* Enable D-Cache: Clear Bit 0 */ - write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE); + 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 - /* Flush D cache */ - write_aux_reg(ARC_REG_DC_FLSH, 0x1); - /* Disable D cache */ - write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE); + /* if V-P const for loop, PTAG can be written once outside loop */ + if (full_page_op) + write_aux_reg(aux_tag, paddr); #endif - return; + while (num_lines-- > 0) { +#if (CONFIG_ARC_MMU_VER > 2) + /* MMUv3, cache ops require paddr seperately */ + if (!full_page_op) { + write_aux_reg(aux_tag, paddr); + paddr += L1_CACHE_BYTES; + } + + write_aux_reg(aux_cmd, vaddr); + vaddr += L1_CACHE_BYTES; +#else + write_aux_reg(aux_cmd, paddr); + paddr += L1_CACHE_BYTES; +#endif + } } -#define OP_INV 0x1 -#define OP_FLUSH 0x2 -#define OP_FLUSH_N_INV 0x3 - #ifdef CONFIG_ARC_HAS_DCACHE /*************************************************************** @@ -239,11 +269,9 @@ static inline void wait_for_flush(void) */ static inline void __dc_entire_op(const int cacheop) { - unsigned long flags, tmp = tmp; + unsigned int tmp = tmp; int aux; - local_irq_save(flags); - if (cacheop == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE @@ -267,55 +295,6 @@ static inline void __dc_entire_op(const int cacheop) /* Switch back the DISCARD ONLY Invalidate mode */ if (cacheop == OP_FLUSH_N_INV) write_aux_reg(ARC_REG_DC_CTRL, tmp & ~DC_CTRL_INV_MODE_FLUSH); - - local_irq_restore(flags); -} - -/* - * Per Line Operation on D-Cache - * Doesn't deal with type-of-op/IRQ-disabling/waiting-for-flush-to-complete - * It's sole purpose is to help gcc generate ZOL - * (aliasing VIPT dcache flushing needs both vaddr and paddr) - */ -static inline void __dc_line_loop(unsigned long paddr, unsigned long vaddr, - unsigned long sz, const int aux_reg) -{ - int num_lines; - - /* 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 (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) { - sz += paddr & ~DCACHE_LINE_MASK; - paddr &= DCACHE_LINE_MASK; - vaddr &= DCACHE_LINE_MASK; - } - - num_lines = DIV_ROUND_UP(sz, ARC_DCACHE_LINE_LEN); - -#if (CONFIG_ARC_MMU_VER <= 2) - paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; -#endif - - while (num_lines-- > 0) { -#if (CONFIG_ARC_MMU_VER > 2) - /* - * Just as for I$, in MMU v3, D$ ops also require - * "tag" bits in DC_PTAG, "index" bits in FLDL,IVDL ops - */ - write_aux_reg(ARC_REG_DC_PTAG, paddr); - - write_aux_reg(aux_reg, vaddr); - vaddr += ARC_DCACHE_LINE_LEN; -#else - /* paddr contains stuffed vaddrs bits */ - write_aux_reg(aux_reg, paddr); -#endif - paddr += ARC_DCACHE_LINE_LEN; - } } /* For kernel mappings cache operation: index is same as paddr */ @@ -328,7 +307,6 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, unsigned long sz, const int cacheop) { unsigned long flags, tmp = tmp; - int aux; local_irq_save(flags); @@ -343,12 +321,7 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, write_aux_reg(ARC_REG_DC_CTRL, tmp | DC_CTRL_INV_MODE_FLUSH); } - if (cacheop & OP_INV) /* Inv / flush-n-inv use same cmd reg */ - aux = ARC_REG_DC_IVDL; - else - aux = ARC_REG_DC_FLDL; - - __dc_line_loop(paddr, vaddr, sz, aux); + __cache_line_loop(paddr, vaddr, sz, cacheop); if (cacheop & OP_FLUSH) /* flush / flush-n-inv both wait */ wait_for_flush(); @@ -416,51 +389,42 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, /*********************************************************** * Machine specific helper for per line I-Cache invalidate. */ -static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, +static void __ic_line_inv_vaddr_local(unsigned long paddr, unsigned long vaddr, unsigned long sz) { unsigned long flags; - int num_lines; - - /* - * Ensure we properly floor/ceil the non-line aligned/sized requests: - * However page sized flushes can be compile time optimised. - * -@paddr will be cache-line aligned already (being page aligned) - * -@sz will be integral multiple of line size (being page sized). - */ - if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) { - sz += paddr & ~ICACHE_LINE_MASK; - paddr &= ICACHE_LINE_MASK; - vaddr &= ICACHE_LINE_MASK; - } - num_lines = DIV_ROUND_UP(sz, ARC_ICACHE_LINE_LEN); + local_irq_save(flags); + __cache_line_loop(paddr, vaddr, sz, OP_INV_IC); + local_irq_restore(flags); +} -#if (CONFIG_ARC_MMU_VER <= 2) - /* bits 17:13 of vaddr go as bits 4:0 of paddr */ - paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; -#endif +static inline void __ic_entire_inv(void) +{ + write_aux_reg(ARC_REG_IC_IVIC, 1); + read_aux_reg(ARC_REG_IC_CTRL); /* blocks */ +} - local_irq_save(flags); - while (num_lines-- > 0) { -#if (CONFIG_ARC_MMU_VER > 2) - /* tag comes from phy addr */ - write_aux_reg(ARC_REG_IC_PTAG, paddr); +struct ic_line_inv_vaddr_ipi { + unsigned long paddr, vaddr; + int sz; +}; - /* index bits come from vaddr */ - write_aux_reg(ARC_REG_IC_IVIL, vaddr); - vaddr += ARC_ICACHE_LINE_LEN; -#else - /* paddr contains stuffed vaddrs bits */ - write_aux_reg(ARC_REG_IC_IVIL, paddr); -#endif - paddr += ARC_ICACHE_LINE_LEN; - } - local_irq_restore(flags); +static void __ic_line_inv_vaddr_helper(void *info) +{ + struct ic_line_inv_vaddr_ipi *ic_inv = (struct ic_line_inv_vaddr_ipi*) 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, + unsigned long sz) +{ + struct ic_line_inv_vaddr_ipi ic_inv = { paddr, vaddr , sz}; + on_each_cpu(__ic_line_inv_vaddr_helper, &ic_inv, 1); +} #else +#define __ic_entire_inv() #define __ic_line_inv_vaddr(pstart, vstart, sz) #endif /* CONFIG_ARC_HAS_ICACHE */ @@ -487,7 +451,7 @@ void flush_dcache_page(struct page *page) struct address_space *mapping; if (!cache_is_vipt_aliasing()) { - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); return; } @@ -501,7 +465,7 @@ void flush_dcache_page(struct page *page) * Make a note that K-mapping is dirty */ if (!mapping_mapped(mapping)) { - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); } else if (page_mapped(page)) { /* kernel reading from page with U-mapping */ @@ -597,21 +561,17 @@ void flush_icache_range(unsigned long kstart, unsigned long kend) /* * General purpose helper to make I and D cache lines consistent. * @paddr is phy addr of region - * @vaddr is typically user or kernel vaddr (vmalloc) - * Howver in one instance, flush_icache_range() by kprobe (for a breakpt in + * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc) + * However in one instance, when called by kprobe (for a breakpt in * builtin kernel code) @vaddr will be paddr only, meaning CDU operation will * use a paddr to index the cache (despite VIPT). This is fine since since a - * built-in kernel page will not have any virtual mappings (not even kernel) - * kprobe on loadable module is different as it will have kvaddr. + * 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) { - unsigned long flags; - - local_irq_save(flags); - __ic_line_inv_vaddr(paddr, vaddr, len); __dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV); - local_irq_restore(flags); + __ic_line_inv_vaddr(paddr, vaddr, len); } /* wrapper to compile time eliminate alignment checks in flush loop */ @@ -629,26 +589,13 @@ void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr) __dc_line_op(paddr, vaddr & PAGE_MASK, PAGE_SIZE, OP_FLUSH_N_INV); } -void flush_icache_all(void) -{ - unsigned long flags; - - local_irq_save(flags); - - write_aux_reg(ARC_REG_IC_IVIC, 1); - - /* lr will not complete till the icache inv operation is not over */ - read_aux_reg(ARC_REG_IC_CTRL); - local_irq_restore(flags); -} - noinline void flush_cache_all(void) { unsigned long flags; local_irq_save(flags); - flush_icache_all(); + __ic_entire_inv(); __dc_entire_op(OP_FLUSH_N_INV); local_irq_restore(flags); @@ -667,7 +614,12 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, { unsigned int paddr = pfn << PAGE_SHIFT; - __sync_icache_dcache(paddr, u_vaddr, PAGE_SIZE); + u_vaddr &= PAGE_MASK; + + ___flush_dcache_page(paddr, u_vaddr); + + if (vma->vm_flags & VM_EXEC) + __inv_icache_page(paddr, u_vaddr); } void flush_cache_range(struct vm_area_struct *vma, unsigned long start, @@ -717,7 +669,7 @@ void copy_user_highpage(struct page *to, struct page *from, * non copied user pages (e.g. read faults which wire in pagecache page * directly). */ - set_bit(PG_arch_1, &to->flags); + clear_bit(PG_dc_clean, &to->flags); /* * if SRC was already usermapped and non-congruent to kernel mapping @@ -725,15 +677,16 @@ void copy_user_highpage(struct page *to, struct page *from, */ if (clean_src_k_mappings) { __flush_dcache_page(kfrom, kfrom); + set_bit(PG_dc_clean, &from->flags); } else { - set_bit(PG_arch_1, &from->flags); + clear_bit(PG_dc_clean, &from->flags); } } void clear_user_page(void *to, unsigned long u_vaddr, struct page *page) { clear_page(to); - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); } diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 689ffd86d5e..9c69552350c 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -15,8 +15,9 @@ #include <linux/uaccess.h> #include <linux/kdebug.h> #include <asm/pgalloc.h> +#include <asm/mmu.h> -static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address) +static int handle_vmalloc_fault(unsigned long address) { /* * Synchronize this task's top level page-table @@ -26,7 +27,7 @@ static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address) pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; - pgd = pgd_offset_fast(mm, address); + pgd = pgd_offset_fast(current->active_mm, address); pgd_k = pgd_offset_k(address); if (!pgd_present(*pgd_k)) @@ -51,16 +52,15 @@ bad_area: return 1; } -void do_page_fault(struct pt_regs *regs, int write, unsigned long address, - unsigned long cause_code) +void do_page_fault(unsigned long address, struct pt_regs *regs) { struct vm_area_struct *vma = NULL; struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; siginfo_t info; int fault, ret; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */ + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * We fault-in kernel-space virtual memory on-demand. The @@ -72,7 +72,7 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address, * nothing more. */ if (address >= VMALLOC_START && address <= VMALLOC_END) { - ret = handle_vmalloc_fault(mm, address); + ret = handle_vmalloc_fault(address); if (unlikely(ret)) goto bad_area_nosemaphore; else @@ -88,6 +88,8 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -109,18 +111,19 @@ good_area: /* Handle protection violation, execute on heap or stack */ - if (cause_code == ((ECR_V_PROTV << 16) | ECR_C_PROTV_INST_FETCH)) + if ((regs->ecr_vec == ECR_V_PROTV) && + (regs->ecr_cause == ECR_C_PROTV_INST_FETCH)) goto bad_area; if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } -survive: /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -176,7 +179,6 @@ bad_area_nosemaphore: /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) { tsk->thread.fault_address = address; - tsk->thread.cause_code = cause_code; info.si_signo = SIGSEGV; info.si_errno = 0; /* info.si_code has been set above */ @@ -197,17 +199,15 @@ no_context: if (fixup_exception(regs)) return; - die("Oops", regs, address, cause_code); + die("Oops", regs, address); out_of_memory: - if (is_global_init(tsk)) { - yield(); - goto survive; - } up_read(&mm->mmap_sem); - if (user_mode(regs)) - do_group_exit(SIGKILL); /* This will never return */ + if (user_mode(regs)) { + pagefault_out_of_memory(); + return; + } goto no_context; @@ -218,7 +218,6 @@ do_sigbus: goto no_context; tsk->thread.fault_address = address; - tsk->thread.cause_code = cause_code; info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = BUS_ADRERR; diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 4a177365b2c..523412369f7 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -10,6 +10,9 @@ #include <linux/mm.h> #include <linux/bootmem.h> #include <linux/memblock.h> +#ifdef CONFIG_BLK_DEV_INITRD +#include <linux/initrd.h> +#endif #include <linux/swap.h> #include <linux/module.h> #include <asm/page.h> @@ -42,6 +45,24 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) pr_info("Memory size set via devicetree %ldM\n", TO_MB(arc_mem_sz)); } +#ifdef CONFIG_BLK_DEV_INITRD +static int __init early_initrd(char *p) +{ + unsigned long start, size; + char *endp; + + start = memparse(p, &endp); + if (*endp == ',') { + size = memparse(endp + 1, NULL); + + initrd_start = (unsigned long)__va(start); + initrd_end = (unsigned long)__va(start + size); + } + return 0; +} +early_param("initrd", early_initrd); +#endif + /* * First memory setup routine called from setup_arch() * 1. setup swapper's mm @init_mm @@ -74,17 +95,23 @@ void __init setup_arch_memory(void) /* Last usable page of low mem (no HIGHMEM yet for ARC port) */ max_low_pfn = max_pfn = PFN_DOWN(end_mem); - max_mapnr = num_physpages = max_low_pfn - min_low_pfn; + max_mapnr = max_low_pfn - min_low_pfn; /*------------- reserve kernel image -----------------------*/ memblock_reserve(CONFIG_LINUX_LINK_BASE, __pa(_end) - CONFIG_LINUX_LINK_BASE); +#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 --------------------------------*/ memset(zones_size, 0, sizeof(zones_size)); - zones_size[ZONE_NORMAL] = num_physpages; + zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn; /* * We can't use the helper free_area_init(zones[]) because it uses @@ -106,39 +133,9 @@ void __init setup_arch_memory(void) */ void __init mem_init(void) { - int codesize, datasize, initsize, reserved_pages, free_pages; - int tmp; - high_memory = (void *)(CONFIG_LINUX_LINK_BASE + arc_mem_sz); - - totalram_pages = free_all_bootmem(); - - /* count all reserved pages [kernel code/data/mem_map..] */ - reserved_pages = 0; - for (tmp = 0; tmp < max_mapnr; tmp++) - if (PageReserved(mem_map + tmp)) - reserved_pages++; - - /* XXX: nr_free_pages() is equivalent */ - free_pages = max_mapnr - reserved_pages; - - /* - * For the purpose of display below, split the "reserve mem" - * kernel code/data is already shown explicitly, - * Show any other reservations (mem_map[ ] et al) - */ - reserved_pages -= (((unsigned int)_end - CONFIG_LINUX_LINK_BASE) >> - PAGE_SHIFT); - - codesize = _etext - _text; - datasize = _end - _etext; - initsize = __init_end - __init_begin; - - pr_info("Memory Available: %dM / %ldM (%dK code, %dK data, %dK init, %dK reserv)\n", - PAGES_TO_MB(free_pages), - TO_MB(arc_mem_sz), - TO_KB(codesize), TO_KB(datasize), TO_KB(initsize), - PAGES_TO_KB(reserved_pages)); + free_all_bootmem(); + mem_init_print_info(NULL); } /* @@ -146,20 +143,12 @@ void __init mem_init(void) */ void __init_refok free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif - -#ifdef CONFIG_OF_FLATTREE -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) -{ - pr_err("%s(%lx, %lx)\n", __func__, start, end); -} -#endif /* CONFIG_OF_FLATTREE */ diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index fe1c5a073af..e1acf0ce564 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -52,10 +52,11 @@ */ #include <linux/module.h> +#include <linux/bug.h> #include <asm/arcregs.h> #include <asm/setup.h> #include <asm/mmu_context.h> -#include <asm/tlb.h> +#include <asm/mmu.h> /* Need for ARC MMU v2 * @@ -97,49 +98,47 @@ * J-TLB entry got evicted/replaced. */ -/* A copy of the ASID from the PID reg is kept in asid_cache */ -int asid_cache = FIRST_ASID; -/* ASID to mm struct mapping. We have one extra entry corresponding to - * NO_ASID to save us a compare when clearing the mm entry for old asid - * see get_new_mmu_context (asm-arc/mmu_context.h) - */ -struct mm_struct *asid_mm_map[NUM_ASID + 1]; +/* A copy of the ASID from the PID reg is kept in asid_cache */ +DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE; /* * Utility Routine to erase a J-TLB entry - * The procedure is to look it up in the MMU. If found, ERASE it by - * issuing a TlbWrite CMD with PD0 = PD1 = 0 + * Caller needs to setup Index Reg (manually or via getIndex) */ - -static void __tlb_entry_erase(void) +static inline void __tlb_entry_erase(void) { write_aux_reg(ARC_REG_TLBPD1, 0); write_aux_reg(ARC_REG_TLBPD0, 0); write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); } -static void tlb_entry_erase(unsigned int vaddr_n_asid) +static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid) { unsigned int idx; - /* Locate the TLB entry for this vaddr + ASID */ write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid); + write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe); idx = read_aux_reg(ARC_REG_TLBINDEX); + return idx; +} + +static void tlb_entry_erase(unsigned int vaddr_n_asid) +{ + unsigned int idx; + + /* Locate the TLB entry for this vaddr + ASID */ + idx = tlb_entry_lkup(vaddr_n_asid); + /* No error means entry found, zero it out */ if (likely(!(idx & TLB_LKUP_ERR))) { __tlb_entry_erase(); - } else { /* Some sort of Error */ - + } else { /* Duplicate entry error */ - if (idx & 0x1) { - /* TODO we need to handle this case too */ - pr_emerg("unhandled Duplicate flush for %x\n", - vaddr_n_asid); - } - /* else entry not found so nothing to do */ + WARN(idx == TLB_DUP_ERR, "Probe returned Dup PD for %x\n", + vaddr_n_asid); } } @@ -158,7 +157,7 @@ static void utlb_invalidate(void) { #if (CONFIG_ARC_MMU_VER >= 2) -#if (CONFIG_ARC_MMU_VER < 3) +#if (CONFIG_ARC_MMU_VER == 2) /* MMU v2 introduced the uTLB Flush command. * There was however an obscure hardware bug, where uTLB flush would * fail when a prior probe for J-TLB (both totally unrelated) would @@ -181,6 +180,36 @@ static void utlb_invalidate(void) } +static void tlb_entry_insert(unsigned int pd0, unsigned int pd1) +{ + unsigned int idx; + + /* + * First verify if entry for this vaddr+ASID already exists + * This also sets up PD0 (vaddr, ASID..) for final commit + */ + idx = tlb_entry_lkup(pd0); + + /* + * If Not already present get a free slot from MMU. + * Otherwise, Probe would have located the entry and set INDEX Reg + * with existing location. This will cause Write CMD to over-write + * existing entry with new PD0 and PD1 + */ + if (likely(idx & TLB_LKUP_ERR)) + write_aux_reg(ARC_REG_TLBCOMMAND, TLBGetIndex); + + /* setup the other half of TLB entry (pfn, rwx..) */ + write_aux_reg(ARC_REG_TLBPD1, pd1); + + /* + * Commit the Entry to MMU + * It doesnt sound safe to use the TLBWriteNI cmd here + * which doesn't flush uTLBs. I'd rather be safe than sorry. + */ + write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); +} + /* * Un-conditionally (without lookup) erase the entire MMU contents */ @@ -223,13 +252,14 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) return; /* - * Workaround for Android weirdism: - * A binder VMA could end up in a task such that vma->mm != tsk->mm - * old code would cause h/w - s/w ASID to get out of sync + * - Move to a new ASID, but only if the mm is still wired in + * (Android Binder ended up calling this for vma->mm != tsk->mm, + * causing h/w - s/w ASID to get out of sync) + * - Also get_new_mmu_context() new implementation allocates a new + * ASID only if it is not allocated already - so unallocate first */ - if (current->mm != mm) - destroy_context(mm); - else + destroy_context(mm); + if (current->mm == mm) get_new_mmu_context(mm); } @@ -244,8 +274,8 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { + const unsigned int cpu = smp_processor_id(); unsigned long flags; - unsigned int asid; /* If range @start to @end is more than 32 TLB entries deep, * its better to move to a new ASID rather than searching for @@ -267,11 +297,10 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, start &= PAGE_MASK; local_irq_save(flags); - asid = vma->vm_mm->context.asid; - if (asid != NO_ASID) { + if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) { while (start < end) { - tlb_entry_erase(start | (asid & 0xff)); + tlb_entry_erase(start | hw_pid(vma->vm_mm, cpu)); start += PAGE_SIZE; } } @@ -318,6 +347,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) { + const unsigned int cpu = smp_processor_id(); unsigned long flags; /* Note that it is critical that interrupts are DISABLED between @@ -325,23 +355,95 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) */ local_irq_save(flags); - if (vma->vm_mm->context.asid != NO_ASID) { - tlb_entry_erase((page & PAGE_MASK) | - (vma->vm_mm->context.asid & 0xff)); + if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) { + tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm, cpu)); utlb_invalidate(); } local_irq_restore(flags); } +#ifdef CONFIG_SMP + +struct tlb_args { + struct vm_area_struct *ta_vma; + unsigned long ta_start; + unsigned long ta_end; +}; + +static inline void ipi_flush_tlb_page(void *arg) +{ + struct tlb_args *ta = arg; + + local_flush_tlb_page(ta->ta_vma, ta->ta_start); +} + +static inline void ipi_flush_tlb_range(void *arg) +{ + struct tlb_args *ta = arg; + + local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end); +} + +static inline void ipi_flush_tlb_kernel_range(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + + local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end); +} + +void flush_tlb_all(void) +{ + on_each_cpu((smp_call_func_t)local_flush_tlb_all, NULL, 1); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + on_each_cpu_mask(mm_cpumask(mm), (smp_call_func_t)local_flush_tlb_mm, + mm, 1); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + struct tlb_args ta = { + .ta_vma = vma, + .ta_start = uaddr + }; + + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, &ta, 1); +} + +void flush_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_tlb_range, &ta, 1); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + struct tlb_args ta = { + .ta_start = start, + .ta_end = end + }; + + on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1); +} +#endif + /* * Routine to create a TLB entry */ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { unsigned long flags; - unsigned int idx, asid_or_sasid; - unsigned long pd0_flags; + unsigned int asid_or_sasid, rwx; + unsigned long pd0, pd1; /* * create_tlb() assumes that current->mm == vma->mm, since @@ -373,47 +475,37 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) local_irq_save(flags); - tlb_paranoid_check(vma->vm_mm->context.asid, address); + tlb_paranoid_check(asid_mm(vma->vm_mm, smp_processor_id()), address); address &= PAGE_MASK; /* update this PTE credentials */ pte_val(*ptep) |= (_PAGE_PRESENT | _PAGE_ACCESSED); - /* Create HW TLB entry Flags (in PD0) from PTE Flags */ -#if (CONFIG_ARC_MMU_VER <= 2) - pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0) >> 1); -#else - pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0)); -#endif + /* Create HW TLB(PD0,PD1) from PTE */ /* ASID for this task */ asid_or_sasid = read_aux_reg(ARC_REG_PID) & 0xff; - write_aux_reg(ARC_REG_TLBPD0, address | pd0_flags | asid_or_sasid); - - /* Load remaining info in PD1 (Page Frame Addr and Kx/Kw/Kr Flags) */ - write_aux_reg(ARC_REG_TLBPD1, (pte_val(*ptep) & PTE_BITS_IN_PD1)); - - /* First verify if entry for this vaddr+ASID already exists */ - write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe); - idx = read_aux_reg(ARC_REG_TLBINDEX); + pd0 = address | asid_or_sasid | (pte_val(*ptep) & PTE_BITS_IN_PD0); /* - * If Not already present get a free slot from MMU. - * Otherwise, Probe would have located the entry and set INDEX Reg - * with existing location. This will cause Write CMD to over-write - * existing entry with new PD0 and PD1 + * ARC MMU provides fully orthogonal access bits for K/U mode, + * however Linux only saves 1 set to save PTE real-estate + * Here we convert 3 PTE bits into 6 MMU bits: + * -Kernel only entries have Kr Kw Kx 0 0 0 + * -User entries have mirrored K and U bits */ - if (likely(idx & TLB_LKUP_ERR)) - write_aux_reg(ARC_REG_TLBCOMMAND, TLBGetIndex); + rwx = pte_val(*ptep) & PTE_BITS_RWX; - /* - * Commit the Entry to MMU - * It doesnt sound safe to use the TLBWriteNI cmd here - * which doesn't flush uTLBs. I'd rather be safe than sorry. - */ - write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); + if (pte_val(*ptep) & _PAGE_GLOBAL) + rwx <<= 3; /* r w x => Kr Kw Kx 0 0 0 */ + else + rwx |= (rwx << 3); /* r w x => Kr Kw Kx Ur Uw Ux */ + + pd1 = rwx | (pte_val(*ptep) & PTE_BITS_NON_RWX_IN_PD1); + + tlb_entry_insert(pd0, pd1); local_irq_restore(flags); } @@ -432,9 +524,14 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; unsigned long paddr = pte_val(*ptep) & PAGE_MASK; + struct page *page = pfn_to_page(pte_pfn(*ptep)); create_tlb(vma, vaddr, ptep); + if (page == ZERO_PAGE(0)) { + return; + } + /* * Exec page : Independent of aliasing/page-color considerations, * since icache doesn't snoop dcache on ARC, any dirty @@ -446,9 +543,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, */ if ((vma->vm_flags & VM_EXEC) || addr_not_cache_congruent(paddr, vaddr)) { - struct page *page = pfn_to_page(pte_pfn(*ptep)); - int dirty = test_and_clear_bit(PG_arch_1, &page->flags); + int dirty = !test_and_set_bit(PG_dc_clean, &page->flags); if (dirty) { /* wback + inv dcache lines */ __flush_dcache_page(paddr, paddr); @@ -464,12 +560,27 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ -void __cpuinit read_decode_mmu_bcr(void) +void read_decode_mmu_bcr(void) { - unsigned int tmp; - struct bcr_mmu_1_2 *mmu2; /* encoded MMU2 attr */ - struct bcr_mmu_3 *mmu3; /* encoded MMU3 attr */ struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; + unsigned int tmp; + struct bcr_mmu_1_2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8; +#else + unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8; +#endif + } *mmu2; + + struct bcr_mmu_3 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, 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, + ways:4, ver:8; +#endif + } *mmu3; tmp = read_aux_reg(ARC_REG_MMU_BCR); mmu->ver = (tmp >> 24); @@ -505,12 +616,12 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len) "J-TLB %d (%dx%d), uDTLB %d, uITLB %d, %s\n", p_mmu->num_tlb, p_mmu->sets, p_mmu->ways, p_mmu->u_dtlb, p_mmu->u_itlb, - __CONFIG_ARC_MMU_SASID_VAL ? "SASID" : ""); + IS_ENABLED(CONFIG_ARC_MMU_SASID) ? "SASID" : ""); return buf; } -void __cpuinit arc_mmu_init(void) +void arc_mmu_init(void) { char str[256]; struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; @@ -533,13 +644,6 @@ void __cpuinit arc_mmu_init(void) if (mmu->pg_sz != PAGE_SIZE) panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE)); - /* - * ASID mgmt data structures are compile time init - * asid_cache = FIRST_ASID and asid_mm_map[] all zeroes - */ - - local_flush_tlb_all(); - /* Enable the MMU */ write_aux_reg(ARC_REG_PID, MMU_ENABLE); @@ -581,9 +685,9 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) { int set, way, n; - unsigned int pd0[4], pd1[4]; /* assume max 4 ways */ unsigned long flags, is_valid; struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; + unsigned int pd0[mmu->ways], pd1[mmu->ways]; local_irq_save(flags); @@ -608,7 +712,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, continue; /* Scan the set for duplicate ways: needs a nested loop */ - for (way = 0; way < mmu->ways; way++) { + for (way = 0; way < mmu->ways - 1; way++) { if (!pd0[way]) continue; @@ -651,25 +755,28 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, * Low Level ASM TLB handler calls this if it finds that HW and SW ASIDS * don't match */ -void print_asid_mismatch(int is_fast_path) +void print_asid_mismatch(int mm_asid, int mmu_asid, int is_fast_path) { - int pid_sw, pid_hw; - pid_sw = current->active_mm->context.asid; - pid_hw = read_aux_reg(ARC_REG_PID) & 0xff; - pr_emerg("ASID Mismatch in %s Path Handler: sw-pid=0x%x hw-pid=0x%x\n", - is_fast_path ? "Fast" : "Slow", pid_sw, pid_hw); + is_fast_path ? "Fast" : "Slow", mm_asid, mmu_asid); __asm__ __volatile__("flag 1"); } -void tlb_paranoid_check(unsigned int pid_sw, unsigned long addr) +void tlb_paranoid_check(unsigned int mm_asid, unsigned long addr) { - unsigned int pid_hw; + unsigned int mmu_asid; - pid_hw = read_aux_reg(ARC_REG_PID) & 0xff; + mmu_asid = read_aux_reg(ARC_REG_PID) & 0xff; - if (addr < 0x70000000 && ((pid_hw != pid_sw) || (pid_sw == NO_ASID))) - print_asid_mismatch(0); + /* + * At the time of a TLB miss/installation + * - HW version needs to match SW version + * - SW needs to have a valid ASID + */ + if (addr < 0x70000000 && + ((mm_asid == MM_CTXT_NO_ASID) || + (mmu_asid != (mm_asid & MM_CTXT_ASID_MASK)))) + print_asid_mismatch(mm_asid, mmu_asid, 0); } #endif diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index 3357d26ffe5..79bfc81358c 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -39,22 +39,41 @@ #include <linux/linkage.h> #include <asm/entry.h> -#include <asm/tlb.h> +#include <asm/mmu.h> #include <asm/pgtable.h> #include <asm/arcregs.h> #include <asm/cache.h> #include <asm/processor.h> -#if (CONFIG_ARC_MMU_VER == 1) #include <asm/tlb-mmu1.h> -#endif -;-------------------------------------------------------------------------- -; scratch memory to save the registers (r0-r3) used to code TLB refill Handler -; For details refer to comments before TLBMISS_FREEUP_REGS below +;----------------------------------------------------------------- +; ARC700 Exception Handling doesn't auto-switch stack and it only provides +; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0" +; +; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a +; "global" is used to free-up FIRST core reg to be able to code the rest of +; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe). +; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3 +; need to be saved as well by extending the "global" to be 4 words. Hence +; ".size ex_saved_reg1, 16" +; [All of this dance is to avoid stack switching for each TLB Miss, since we +; only need to save only a handful of regs, as opposed to complete reg file] +; +; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST +; core reg as it will not be SMP safe. +; Thus scratch AUX reg is used (and no longer used to cache task PGD). +; To save the rest of 3 regs - per cpu, the global is made "per-cpu". +; Epilogue thus has to locate the "per-cpu" storage for regs. +; To avoid cache line bouncing the per-cpu global is aligned/sized per +; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence +; ".size ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)" + +; As simple as that.... ;-------------------------------------------------------------------------- +; scratch memory to save [r0-r3] used to code TLB refill Handler ARCFP_DATA ex_saved_reg1 - .align 1 << L1_CACHE_SHIFT ; IMP: Must be Cache Line aligned + .align 1 << L1_CACHE_SHIFT .type ex_saved_reg1, @object #ifdef CONFIG_SMP .size ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT) @@ -66,6 +85,44 @@ ex_saved_reg1: .zero 16 #endif +.macro TLBMISS_FREEUP_REGS +#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 + add r0, @ex_saved_reg1, r0 +#else + st r0, [@ex_saved_reg1] + mov_s r0, @ex_saved_reg1 +#endif + st_s r1, [r0, 4] + st_s r2, [r0, 8] + st_s r3, [r0, 12] + + ; VERIFY if the ASID in MMU-PID Reg is same as + ; one in Linux data structures + + tlb_paranoid_check_asm +.endm + +.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 + add r0, @ex_saved_reg1, r0 + ld_s r3, [r0,12] + ld_s r2, [r0, 8] + ld_s r1, [r0, 4] + lr r0, [ARC_REG_SCRATCH_DATA0] +#else + mov_s r0, @ex_saved_reg1 + ld_s r3, [r0,12] + ld_s r2, [r0, 8] + ld_s r1, [r0, 4] + ld_s r0, [r0] +#endif +.endm + ;============================================================================ ; Troubleshooting Stuff ;============================================================================ @@ -76,34 +133,35 @@ ex_saved_reg1: ; In bizzare scenrios SW and HW ASID can get out-of-sync which is trouble. ; So we try to detect this in TLB Mis shandler - -.macro DBG_ASID_MISMATCH +.macro tlb_paranoid_check_asm #ifdef CONFIG_ARC_DBG_TLB_PARANOIA - ; make sure h/w ASID is same as s/w ASID - GET_CURR_TASK_ON_CPU r3 ld r0, [r3, TASK_ACT_MM] ld r0, [r0, MM_CTXT+MM_CTXT_ASID] + breq r0, 0, 55f ; Error if no ASID allocated lr r1, [ARC_REG_PID] and r1, r1, 0xFF - breq r1, r0, 5f + and r2, r0, 0xFF ; MMU PID bits only for comparison + breq r1, r2, 5f + +55: ; Error if H/w and S/w ASID don't match, but NOT if in kernel mode - lr r0, [erstatus] - bbit0 r0, STATUS_U_BIT, 5f + lr r2, [erstatus] + bbit0 r2, STATUS_U_BIT, 5f ; We sure are in troubled waters, Flag the error, but to do so ; need to switch to kernel mode stack to call error routine GET_TSK_STACK_BASE r3, sp ; Call printk to shoutout aloud - mov r0, 1 + mov r2, 1 j print_asid_mismatch -5: ; ASIDs match so proceed normally +5: ; ASIDs match so proceed normally nop #endif @@ -147,9 +205,9 @@ ex_saved_reg1: #ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT and.f 0, r0, _PAGE_PRESENT bz 1f - ld r2, [num_pte_not_present] - add r2, r2, 1 - st r2, [num_pte_not_present] + ld r3, [num_pte_not_present] + add r3, r3, 1 + st r3, [num_pte_not_present] 1: #endif @@ -161,13 +219,17 @@ ex_saved_reg1: ; IN: r0 = PTE, r1 = ptr to PTE .macro CONV_PTE_TO_TLB - and r3, r0, PTE_BITS_IN_PD1 ; Extract permission flags+PFN from PTE - sr r3, [ARC_REG_TLBPD1] ; these go in PD1 + and r3, r0, PTE_BITS_RWX ; r w x + lsl r2, r3, 3 ; r w x 0 0 0 + and.f 0, r0, _PAGE_GLOBAL + or.z r2, r2, r3 ; r w x r w x + + 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 and r2, r0, PTE_BITS_IN_PD0 ; Extract other PTE flags: (V)alid, (G)lb -#if (CONFIG_ARC_MMU_VER <= 2) /* Neednot be done with v3 onwards */ - lsr r2, r2 ; shift PTE flags to match layout in PD0 -#endif lr r3,[ARC_REG_TLBPD0] ; MMU prepares PD0 with vaddr and asid @@ -191,68 +253,6 @@ ex_saved_reg1: #endif .endm -;----------------------------------------------------------------- -; ARC700 Exception Handling doesn't auto-switch stack and it only provides -; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0" -; -; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a -; "global" is used to free-up FIRST core reg to be able to code the rest of -; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe). -; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3 -; need to be saved as well by extending the "global" to be 4 words. Hence -; ".size ex_saved_reg1, 16" -; [All of this dance is to avoid stack switching for each TLB Miss, since we -; only need to save only a handful of regs, as opposed to complete reg file] -; -; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST -; core reg as it will not be SMP safe. -; Thus scratch AUX reg is used (and no longer used to cache task PGD). -; To save the rest of 3 regs - per cpu, the global is made "per-cpu". -; Epilogue thus has to locate the "per-cpu" storage for regs. -; To avoid cache line bouncing the per-cpu global is aligned/sized per -; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence -; ".size ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)" - -; As simple as that.... - -.macro TLBMISS_FREEUP_REGS -#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 - add r0, @ex_saved_reg1, r0 -#else - st r0, [@ex_saved_reg1] - mov_s r0, @ex_saved_reg1 -#endif - st_s r1, [r0, 4] - st_s r2, [r0, 8] - st_s r3, [r0, 12] - - ; VERIFY if the ASID in MMU-PID Reg is same as - ; one in Linux data structures - - DBG_ASID_MISMATCH -.endm - -;----------------------------------------------------------------- -.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 - add r0, @ex_saved_reg1, r0 - ld_s r3, [r0,12] - ld_s r2, [r0, 8] - ld_s r1, [r0, 4] - lr r0, [ARC_REG_SCRATCH_DATA0] -#else - mov_s r0, @ex_saved_reg1 - ld_s r3, [r0,12] - ld_s r2, [r0, 8] - ld_s r1, [r0, 4] - ld_s r0, [r0] -#endif -.endm ARCFP_CODE ;Fast Path Code, candidate for ICCM @@ -260,7 +260,7 @@ ARCFP_CODE ;Fast Path Code, candidate for ICCM ; I-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissI +ENTRY(EV_TLBMissI) TLBMISS_FREEUP_REGS @@ -271,35 +271,35 @@ ARC_ENTRY EV_TLBMissI #endif ;---------------------------------------------------------------- - ; Get the PTE corresponding to V-addr accessed + ; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA LOAD_FAULT_PTE ;---------------------------------------------------------------- ; VERIFY_PTE: Check if PTE permissions approp for executing code cmp_s r2, VMALLOC_START - mov.lo r2, (_PAGE_PRESENT | _PAGE_U_READ | _PAGE_U_EXECUTE) - mov.hs r2, (_PAGE_PRESENT | _PAGE_K_READ | _PAGE_K_EXECUTE) + mov_s r2, (_PAGE_PRESENT | _PAGE_EXECUTE) + or.hs r2, r2, _PAGE_GLOBAL and r3, r0, r2 ; Mask out NON Flag bits from PTE xor.f r3, r3, r2 ; check ( ( pte & flags_test ) == flags_test ) bnz do_slow_path_pf ; Let Linux VM know that the page was accessed - or r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED) ; set Accessed Bit - st_s r0, [r1] ; Write back PTE + or r0, r0, _PAGE_ACCESSED ; set Accessed Bit + st_s r0, [r1] ; Write back PTE CONV_PTE_TO_TLB COMMIT_ENTRY_TO_MMU TLBMISS_RESTORE_REGS rtie -ARC_EXIT EV_TLBMissI +END(EV_TLBMissI) ;----------------------------------------------------------------------------- ; D-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissD +ENTRY(EV_TLBMissD) TLBMISS_FREEUP_REGS @@ -311,32 +311,27 @@ ARC_ENTRY EV_TLBMissD ;---------------------------------------------------------------- ; Get the PTE corresponding to V-addr accessed - ; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE + ; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA LOAD_FAULT_PTE ;---------------------------------------------------------------- ; VERIFY_PTE: Chk if PTE permissions approp for data access (R/W/R+W) - mov_s r2, 0 + cmp_s r2, VMALLOC_START + mov_s r2, _PAGE_PRESENT ; common bit for K/U PTE + or.hs r2, r2, _PAGE_GLOBAL ; kernel PTE only + + ; Linux PTE [RWX] bits are semantically overloaded: + ; -If PAGE_GLOBAL set, they refer to kernel-only flags (vmalloc) + ; -Otherwise they are user-mode permissions, and those are exactly + ; same for kernel mode as well (e.g. copy_(to|from)_user) + lr r3, [ecr] btst_s r3, ECR_C_BIT_DTLB_LD_MISS ; Read Access - or.nz r2, r2, _PAGE_U_READ ; chk for Read flag in PTE + or.nz r2, r2, _PAGE_READ ; chk for Read flag in PTE btst_s r3, ECR_C_BIT_DTLB_ST_MISS ; Write Access - or.nz r2, r2, _PAGE_U_WRITE ; chk for Write flag in PTE - ; Above laddering takes care of XCHG access - ; which is both Read and Write - - ; If kernel mode access, ; make _PAGE_xx flags as _PAGE_K_xx - ; For copy_(to|from)_user, despite exception taken in kernel mode, - ; this code is not hit, because EFA would still be the user mode - ; address (EFA < 0x6000_0000). - ; This code is for legit kernel mode faults, vmalloc specifically - ; (EFA: 0x7000_0000 to 0x7FFF_FFFF) - - lr r3, [efa] - cmp r3, VMALLOC_START - 1 ; If kernel mode access - asl.hi r2, r2, 3 ; make _PAGE_xx flags as _PAGE_K_xx - or r2, r2, _PAGE_PRESENT ; Common flag for K/U mode + or.nz r2, r2, _PAGE_WRITE ; chk for Write flag in PTE + ; Above laddering takes care of XCHG access (both R and W) ; By now, r2 setup with all the Flags we need to check in PTE and r3, r0, r2 ; Mask out NON Flag bits from PTE @@ -345,7 +340,7 @@ ARC_ENTRY EV_TLBMissD ;---------------------------------------------------------------- ; UPDATE_PTE: Let Linux VM know that page was accessed/dirty lr r3, [ecr] - or r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED) ; Accessed bit always + 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 st_s r0, [r1] ; Write back PTE @@ -371,28 +366,11 @@ do_slow_path_pf: ; Slow path TLB Miss handled as a regular ARC Exception ; (stack switching / save the complete reg-file). - ; That requires freeing up r9 - EXCPN_PROLOG_FREEUP_REG r9 - - lr r9, [erstatus] - - SWITCH_TO_KERNEL_STK - SAVE_ALL_SYS + EXCEPTION_PROLOGUE ; ------- setup args for Linux Page fault Hanlder --------- - mov_s r0, sp - lr r2, [efa] - lr r3, [ecr] - - ; Both st and ex imply WRITE access of some sort, hence do_page_fault( ) - ; invoked with write=1 for DTLB-st/ex Miss and write=0 for ITLB miss or - ; DTLB-ld Miss - ; DTLB Miss Cause code is ld = 0x01 , st = 0x02, ex = 0x03 - ; Following code uses that fact that st/ex have one bit in common - - btst_s r3, ECR_C_BIT_DTLB_ST_MISS - mov.z r1, 0 - mov.nz r1, 1 + 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 @@ -403,6 +381,4 @@ do_slow_path_pf: bl do_page_fault b ret_from_exception -ARC_EXIT EV_TLBMissD - -ARC_ENTRY EV_TLBMissB ; Bogus entry to measure sz of DTLBMiss hdlr +END(EV_TLBMissD) diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig index 295cefeb25d..e27bb5cc3c1 100644 --- a/arch/arc/plat-arcfpga/Kconfig +++ b/arch/arc/plat-arcfpga/Kconfig @@ -33,7 +33,6 @@ config ISS_SMP_EXTN bool "ARC SMP Extensions (ISS Models only)" default n depends on SMP - select ARC_HAS_COH_RTSC help SMP Extensions to ARC700, in a "simulation only" Model, supported in ARC ISS (Instruction Set Simulator). @@ -49,36 +48,4 @@ config ARC_SERIAL_BAUD help Baud rate for the ARC UART -menuconfig ARC_HAS_BVCI_LAT_UNIT - bool "BVCI Bus Latency Unit" - depends on ARC_BOARD_ML509 || ARC_BOARD_ANGEL4 - help - IP to add artificial latency to BVCI Bus Based FPGA builds. - The default latency (even worst case) for FPGA is non-realistic - (~10 SDRAM, ~5 SSRAM). - -config BVCI_LAT_UNITS - hex "Latency Unit(s) Bitmap" - default "0x0" - depends on ARC_HAS_BVCI_LAT_UNIT - help - There are multiple Latency Units corresponding to the many - interfaces of the system bus arbiter (both CPU side as well as - the peripheral side). - To add latency to ALL memory transaction, choose Unit 0, otherwise - for finer grainer - interface wise latency, specify a bitmap (1 bit - per unit) of all units. e.g. 1,2,12 will be 0x1003 - - Unit 0 - System Arb and Mem Controller - Unit 1 - I$ and System Bus - Unit 2 - D$ and System Bus - .. - Unit 12 - IDE Disk controller and System Bus - -config BVCI_LAT_CYCLES - int "Latency Value in cycles" - range 0 63 - default "30" - depends on ARC_HAS_BVCI_LAT_UNIT - endif diff --git a/arch/arc/plat-arcfpga/Makefile b/arch/arc/plat-arcfpga/Makefile index a44e22ebc1b..4d1bddc34b5 100644 --- a/arch/arc/plat-arcfpga/Makefile +++ b/arch/arc/plat-arcfpga/Makefile @@ -9,4 +9,4 @@ KBUILD_CFLAGS += -Iarch/arc/plat-arcfpga/include obj-y := platform.o irq.o -obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_ISS_SMP_EXTN) += smp.o diff --git a/arch/arc/plat-arcfpga/include/plat/irq.h b/arch/arc/plat-arcfpga/include/plat/irq.h index 41e335670f6..6adbc53c3a5 100644 --- a/arch/arc/plat-arcfpga/include/plat/irq.h +++ b/arch/arc/plat-arcfpga/include/plat/irq.h @@ -16,8 +16,6 @@ #define UART1_IRQ 10 #define UART2_IRQ 11 -#define VMAC_IRQ 6 - #define IDE_IRQ 13 #define PCI_IRQ 14 #define PS2_IRQ 15 diff --git a/arch/arc/plat-arcfpga/include/plat/memmap.h b/arch/arc/plat-arcfpga/include/plat/memmap.h index 1663f338808..5c78e6135a1 100644 --- a/arch/arc/plat-arcfpga/include/plat/memmap.h +++ b/arch/arc/plat-arcfpga/include/plat/memmap.h @@ -15,8 +15,6 @@ #define UART0_BASE 0xC0FC1000 #define UART1_BASE 0xC0FC1100 -#define VMAC_REG_BASEADDR 0xC0FC2000 - #define IDE_CONTROLLER_BASE 0xC0FC9000 #define AHB_PCI_HOST_BRG_BASE 0xC0FD0000 diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-arcfpga/platform.c index b3700c064c0..61c7e599738 100644 --- a/arch/arc/plat-arcfpga/platform.c +++ b/arch/arc/plat-arcfpga/platform.c @@ -22,61 +22,9 @@ #include <plat/smp.h> #include <plat/irq.h> -/*-----------------------BVCI Latency Unit -----------------------------*/ - -#ifdef CONFIG_ARC_HAS_BVCI_LAT_UNIT - -int lat_cycles = CONFIG_BVCI_LAT_CYCLES; - -/* BVCI Bus Profiler: Latency Unit */ -static void __init setup_bvci_lat_unit(void) -{ -#define MAX_BVCI_UNITS 12 - - unsigned int i; - unsigned int *base = (unsigned int *)BVCI_LAT_UNIT_BASE; - const unsigned long units_req = CONFIG_BVCI_LAT_UNITS; - const unsigned int REG_UNIT = 21; - const unsigned int REG_VAL = 22; - - /* - * There are multiple Latency Units corresponding to the many - * interfaces of the system bus arbiter (both CPU side as well as - * the peripheral side). - * - * Unit 0 - System Arb and Mem Controller - adds latency to all - * memory trasactions - * Unit 1 - I$ and System Bus - * Unit 2 - D$ and System Bus - * .. - * Unit 12 - IDE Disk controller and System Bus - * - * The programmers model requires writing to lat_unit reg first - * and then the latency value (cycles) to lat_value reg - */ - - if (CONFIG_BVCI_LAT_UNITS == 0) { - writel(0, base + REG_UNIT); - writel(lat_cycles, base + REG_VAL); - pr_info("BVCI Latency for all Memory Transactions %d cycles\n", - lat_cycles); - } else { - for_each_set_bit(i, &units_req, MAX_BVCI_UNITS) { - writel(i + 1, base + REG_UNIT); /* loop is 0 based */ - writel(lat_cycles, base + REG_VAL); - pr_info("BVCI Latency for Unit[%d] = %d cycles\n", - (i + 1), lat_cycles); - } - } -} -#else -static void __init setup_bvci_lat_unit(void) -{ -} -#endif - /*----------------------- Platform Devices -----------------------------*/ +#if IS_ENABLED(CONFIG_SERIAL_ARC) static unsigned long arc_uart_info[] = { 0, /* uart->is_emulated (runtime @running_on_hw) */ 0, /* uart->port.uartclk */ @@ -115,7 +63,7 @@ static struct platform_device arc_uart0_dev = { static struct platform_device *fpga_early_devs[] __initdata = { &arc_uart0_dev, }; -#endif +#endif /* CONFIG_SERIAL_ARC_CONSOLE */ static void arc_fpga_serial_init(void) { @@ -131,16 +79,11 @@ static void arc_fpga_serial_init(void) ARRAY_SIZE(fpga_early_devs)); /* - * ARC console driver registers itself as an early platform driver - * of class "earlyprintk". - * Install it here, followed by probe of devices. - * The installation here doesn't require earlyprintk in command line - * To do so however, replace the lines below with - * parse_early_param(); - * early_platform_driver_probe("earlyprintk", 1, 1); - * ^^ + * ARC console driver registers (build time) as an early platform driver + * of class "earlyprintk". However it needs explicit cmdline toggle + * "earlyprintk=ttyARC0" to be successfuly runtime registered. + * Otherwise the early probe below fails to find the driver */ - early_platform_driver_register_all("earlyprintk"); early_platform_driver_probe("earlyprintk", 1, 0); /* @@ -152,24 +95,27 @@ static void arc_fpga_serial_init(void) * otherwise the early console never gets a chance to run. */ add_preferred_console("ttyARC", 0, "115200"); -#endif +#endif /* CONFIG_SERIAL_ARC_CONSOLE */ } +#else /* !IS_ENABLED(CONFIG_SERIAL_ARC) */ +static void arc_fpga_serial_init(void) +{ +} +#endif static void __init plat_fpga_early_init(void) { pr_info("[plat-arcfpga]: registering early dev resources\n"); - setup_bvci_lat_unit(); - arc_fpga_serial_init(); -#ifdef CONFIG_SMP +#ifdef CONFIG_ISS_SMP_EXTN iss_model_init_early_smp(); #endif } static struct of_dev_auxdata plat_auxdata_lookup[] __initdata = { -#if defined(CONFIG_SERIAL_ARC) || defined(CONFIG_SERIAL_ARC_MODULE) +#if IS_ENABLED(CONFIG_SERIAL_ARC) OF_DEV_AUXDATA("snps,arc-uart", UART0_BASE, "arc-uart", arc_uart_info), #endif {} @@ -195,7 +141,7 @@ static void __init plat_fpga_populate_dev(void) * callback set, by matching the DT compatible name. */ -static const char *aa4_compat[] __initdata = { +static const char *aa4_compat[] __initconst = { "snps,arc-angel4", NULL, }; @@ -205,12 +151,12 @@ MACHINE_START(ANGEL4, "angel4") .init_early = plat_fpga_early_init, .init_machine = plat_fpga_populate_dev, .init_irq = plat_fpga_init_IRQ, -#ifdef CONFIG_SMP +#ifdef CONFIG_ISS_SMP_EXTN .init_smp = iss_model_init_smp, #endif MACHINE_END -static const char *ml509_compat[] __initdata = { +static const char *ml509_compat[] __initconst = { "snps,arc-ml509", NULL, }; @@ -225,7 +171,7 @@ MACHINE_START(ML509, "ml509") #endif MACHINE_END -static const char *nsimosci_compat[] __initdata = { +static const char *nsimosci_compat[] __initconst = { "snps,nsimosci", NULL, }; diff --git a/arch/arc/plat-arcfpga/smp.c b/arch/arc/plat-arcfpga/smp.c index 91b55349a5f..92bad912207 100644 --- a/arch/arc/plat-arcfpga/smp.c +++ b/arch/arc/plat-arcfpga/smp.c @@ -42,6 +42,24 @@ static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc) } +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 @@ -88,18 +106,14 @@ void iss_model_init_smp(unsigned int cpu) smp_ipi_irq_setup(cpu, IDU_INTERRUPT_0 + cpu); } -static void iss_model_ipi_send(void *arg) +static void iss_model_ipi_send(int cpu) { - struct cpumask *callmap = arg; - unsigned int cpu; - - for_each_cpu(cpu, callmap) - idu_irq_assert(cpu); + idu_irq_assert(cpu); } -static void iss_model_ipi_clear(int cpu, int irq) +static void iss_model_ipi_clear(int irq) { - idu_irq_clear(IDU_INTERRUPT_0 + cpu); + idu_irq_clear(IDU_INTERRUPT_0 + smp_processor_id()); } void iss_model_init_early_smp(void) diff --git a/arch/arc/plat-tb10x/Kconfig b/arch/arc/plat-tb10x/Kconfig index 1d3452100f1..6994c188dc8 100644 --- a/arch/arc/plat-tb10x/Kconfig +++ b/arch/arc/plat-tb10x/Kconfig @@ -20,8 +20,11 @@ menuconfig ARC_PLAT_TB10X bool "Abilis TB10x" select COMMON_CLK select PINCTRL + select PINCTRL_TB10X select PINMUX select ARCH_REQUIRE_GPIOLIB + select GPIO_TB10X + select TB10X_IRQC help Support for platforms based on the TB10x home media gateway SOC by Abilis Systems. TB10x is based on the ARC700 CPU architecture. |