diff options
Diffstat (limited to 'arch')
406 files changed, 8360 insertions, 5089 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 8bf0fa652eb6..f78c2be4242b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -175,4 +175,7 @@ config HAVE_PERF_EVENTS_NMI config HAVE_ARCH_JUMP_LABEL bool +config HAVE_ARCH_MUTEX_CPU_RELAX + bool + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h index fe792ca818f6..5996e7a6757e 100644 --- a/arch/alpha/include/asm/perf_event.h +++ b/arch/alpha/include/asm/perf_event.h @@ -1,10 +1,4 @@ #ifndef __ASM_ALPHA_PERF_EVENT_H #define __ASM_ALPHA_PERF_EVENT_H -#ifdef CONFIG_PERF_EVENTS -extern void init_hw_perf_events(void); -#else -static inline void init_hw_perf_events(void) { } -#endif - #endif /* __ASM_ALPHA_PERF_EVENT_H */ diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 5f77afb88e89..4c8bb374eb0a 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -112,8 +112,6 @@ init_IRQ(void) wrent(entInt, 0); alpha_mv.init_irq(); - - init_hw_perf_events(); } /* diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index 1cc49683fb69..90561c45e7d8 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/kdebug.h> #include <linux/mutex.h> +#include <linux/init.h> #include <asm/hwrpb.h> #include <asm/atomic.h> @@ -863,13 +864,13 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, /* * Init call to initialise performance events at kernel startup. */ -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { pr_info("Performance events: "); if (!supported_cpu()) { pr_cont("No support for your CPU.\n"); - return; + return 0; } pr_cont("Supported CPU type!\n"); @@ -881,6 +882,8 @@ void __init init_hw_perf_events(void) /* And set up PMU specification */ alpha_pmu = &ev67_pmu; - perf_pmu_register(&pmu); -} + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); + return 0; +} +early_initcall(init_hw_perf_events); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index db524e75c4a2..d56d21c0573b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -9,7 +9,7 @@ config ARM select GENERIC_ATOMIC64 if (!CPU_32v6K || !AEABI) select HAVE_OPROFILE if (HAVE_PERF_EVENTS) select HAVE_ARCH_KGDB - select HAVE_KPROBES if (!XIP_KERNEL) + select HAVE_KPROBES if (!XIP_KERNEL && !THUMB2_KERNEL) select HAVE_KRETPROBES if (HAVE_KPROBES) select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) @@ -1311,7 +1311,7 @@ config HZ config THUMB2_KERNEL bool "Compile the kernel in Thumb-2 mode" - depends on CPU_V7 && EXPERIMENTAL + depends on CPU_V7 && !CPU_V6 && EXPERIMENTAL select AEABI select ARM_ASM_UNIFIED help @@ -1759,7 +1759,7 @@ comment "At least one emulation must be selected" config FPE_NWFPE bool "NWFPE math emulation" - depends on !AEABI || OABI_COMPAT + depends on (!AEABI || OABI_COMPAT) && !THUMB2_KERNEL ---help--- Say Y to include the NWFPE floating point emulator in the kernel. This is necessary to run most binaries. Linux does not currently diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index 4a590f4113e2..4d26f2c52a75 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -70,12 +70,7 @@ else $(obj)/uImage: LOADADDR=$(ZRELADDR) endif -ifeq ($(CONFIG_THUMB2_KERNEL),y) -# Set bit 0 to 1 so that "mov pc, rx" switches to Thumb-2 mode -$(obj)/uImage: STARTADDR=$(shell echo $(LOADADDR) | sed -e "s/.$$/1/") -else $(obj)/uImage: STARTADDR=$(LOADADDR) -endif $(obj)/uImage: $(obj)/zImage FORCE $(call if_changed,uimage) diff --git a/arch/arm/boot/bootp/init.S b/arch/arm/boot/bootp/init.S index 8b0de41c3dcb..78b508075161 100644 --- a/arch/arm/boot/bootp/init.S +++ b/arch/arm/boot/bootp/init.S @@ -73,6 +73,8 @@ move: ldmia r4!, {r7 - r10} @ move 32-bytes at a time .size _start, . - _start + .align + .type data,#object data: .word initrd_start @ source initrd address .word initrd_phys @ destination initrd address diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 6825c34646d4..7193884ed8b0 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -125,9 +125,13 @@ wait: mrc p14, 0, pc, c0, c1, 0 * sort out different calling conventions */ .align + .arm @ Always enter in ARM state start: .type start,#function - .rept 8 + THUMB( adr r12, BSYM(1f) ) + THUMB( bx r12 ) + THUMB( .rept 6 ) + ARM( .rept 8 ) mov r0, r0 .endr @@ -135,6 +139,7 @@ start: .word 0x016f2818 @ Magic numbers to help the loader .word start @ absolute load/run zImage address .word _edata @ zImage end address + THUMB( .thumb ) 1: mov r7, r1 @ save architecture ID mov r8, r2 @ save atags pointer @@ -174,7 +179,8 @@ not_angel: ldr sp, [r0, #28] #ifdef CONFIG_AUTO_ZRELADDR @ determine final kernel image address - and r4, pc, #0xf8000000 + mov r4, pc + and r4, r4, #0xf8000000 add r4, r4, #TEXT_OFFSET #else ldr r4, =zreladdr @@ -445,7 +451,8 @@ __setup_mmu: sub r3, r4, #16384 @ Page directory size */ mov r1, #0x1e orr r1, r1, #3 << 10 - mov r2, pc, lsr #20 + mov r2, pc + mov r2, r2, lsr #20 orr r1, r1, r2, lsl #20 add r0, r3, r2, lsl #2 str r1, [r0], #4 @@ -1084,6 +1091,6 @@ memdump: mov r12, r0 reloc_end: .align - .section ".stack", "w" + .section ".stack", "aw", %nobits user_stack: .space 4096 user_stack_end: diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in index d08168941bd6..366a924019ac 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.in +++ b/arch/arm/boot/compressed/vmlinux.lds.in @@ -57,7 +57,7 @@ SECTIONS .bss : { *(.bss) } _end = .; - .stack (NOLOAD) : { *(.stack) } + .stack : { *(.stack) } .stab 0 : { *(.stab) } .stabstr 0 : { *(.stabstr) } diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 772f95f1aecd..e6388dcd8cfa 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -146,9 +146,15 @@ static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) unsigned int shift = (irq % 4) * 8; unsigned int cpu = cpumask_first(mask_val); u32 val; + struct irq_desc *desc; spin_lock(&irq_controller_lock); - irq_desc[irq].node = cpu; + desc = irq_to_desc(irq); + if (desc == NULL) { + spin_unlock(&irq_controller_lock); + return -EINVAL; + } + desc->node = cpu; val = readl(reg) & ~(0xff << shift); val |= 1 << (cpu + shift); writel(val, reg); @@ -210,7 +216,7 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq) void __init gic_dist_init(unsigned int gic_nr, void __iomem *base, unsigned int irq_start) { - unsigned int max_irq, i; + unsigned int gic_irqs, irq_limit, i; u32 cpumask = 1 << smp_processor_id(); if (gic_nr >= MAX_GIC_NR) @@ -226,47 +232,49 @@ void __init gic_dist_init(unsigned int gic_nr, void __iomem *base, /* * Find out how many interrupts are supported. - */ - max_irq = readl(base + GIC_DIST_CTR) & 0x1f; - max_irq = (max_irq + 1) * 32; - - /* * The GIC only supports up to 1020 interrupt sources. - * Limit this to either the architected maximum, or the - * platform maximum. */ - if (max_irq > max(1020, NR_IRQS)) - max_irq = max(1020, NR_IRQS); + gic_irqs = readl(base + GIC_DIST_CTR) & 0x1f; + gic_irqs = (gic_irqs + 1) * 32; + if (gic_irqs > 1020) + gic_irqs = 1020; /* * Set all global interrupts to be level triggered, active low. */ - for (i = 32; i < max_irq; i += 16) + for (i = 32; i < gic_irqs; i += 16) writel(0, base + GIC_DIST_CONFIG + i * 4 / 16); /* * Set all global interrupts to this CPU only. */ - for (i = 32; i < max_irq; i += 4) + for (i = 32; i < gic_irqs; i += 4) writel(cpumask, base + GIC_DIST_TARGET + i * 4 / 4); /* * Set priority on all global interrupts. */ - for (i = 32; i < max_irq; i += 4) + for (i = 32; i < gic_irqs; i += 4) writel(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4); /* * Disable all interrupts. Leave the PPI and SGIs alone * as these enables are banked registers. */ - for (i = 32; i < max_irq; i += 32) + for (i = 32; i < gic_irqs; i += 32) writel(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32); /* + * Limit number of interrupts registered to the platform maximum + */ + irq_limit = gic_data[gic_nr].irq_offset + gic_irqs; + if (WARN_ON(irq_limit > NR_IRQS)) + irq_limit = NR_IRQS; + + /* * Setup the Linux IRQ subsystem. */ - for (i = irq_start; i < gic_data[gic_nr].irq_offset + max_irq; i++) { + for (i = irq_start; i < irq_limit; i++) { set_irq_chip(i, &gic_chip); set_irq_chip_data(i, &gic_data[gic_nr]); set_irq_handler(i, handle_level_irq); diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 1bec96e85196..42ff90b46dfb 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -352,3 +352,4 @@ struct pci_bus * __init it8152_pci_scan_bus(int nr, struct pci_sys_data *sys) return pci_scan_bus(nr, &it8152_ops, sys); } +EXPORT_SYMBOL(dma_set_coherent_mask); diff --git a/arch/arm/configs/at91rm9200_defconfig b/arch/arm/configs/at91rm9200_defconfig new file mode 100644 index 000000000000..38cb7c985426 --- /dev/null +++ b/arch/arm/configs/at91rm9200_defconfig @@ -0,0 +1,341 @@ +CONFIG_EXPERIMENTAL=y +# CONFIG_LOCALVERSION_AUTO is not set +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_SYSFS_DEPRECATED_V2=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARCH_AT91=y +CONFIG_MACH_ONEARM=y +CONFIG_ARCH_AT91RM9200DK=y +CONFIG_MACH_AT91RM9200EK=y +CONFIG_MACH_CSB337=y +CONFIG_MACH_CSB637=y +CONFIG_MACH_CARMEVA=y +CONFIG_MACH_ATEB9200=y +CONFIG_MACH_KB9200=y +CONFIG_MACH_PICOTUX2XX=y +CONFIG_MACH_KAFA=y +CONFIG_MACH_ECBAT91=y +CONFIG_MACH_YL9200=y +CONFIG_MACH_CPUAT91=y +CONFIG_MACH_ECO920=y +CONFIG_MTD_AT91_DATAFLASH_CARD=y +CONFIG_AT91_PROGRAMMABLE_CLOCKS=y +CONFIG_AT91_TIMER_HZ=100 +# CONFIG_ARM_THUMB is not set +CONFIG_PCCARD=y +CONFIG_AT91_CF=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y +CONFIG_AEABI=y +CONFIG_LEDS=y +CONFIG_LEDS_CPU=y +CONFIG_ZBOOT_ROM_TEXT=0x10000000 +CONFIG_ZBOOT_ROM_BSS=0x20040000 +CONFIG_KEXEC=y +CONFIG_FPE_NWFPE=y +CONFIG_BINFMT_MISC=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE=m +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_XFRM_MODE_TRANSPORT=m +CONFIG_INET_XFRM_MODE_TUNNEL=m +CONFIG_INET_XFRM_MODE_BEET=m +CONFIG_IPV6_PRIVACY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MIP6=m +CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m +CONFIG_IPV6_TUNNEL=m +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_BT=m +CONFIG_BT_L2CAP=m +CONFIG_BT_SCO=m +CONFIG_BT_RFCOMM=m +CONFIG_BT_RFCOMM_TTY=y +CONFIG_BT_BNEP=m +CONFIG_BT_BNEP_MC_FILTER=y +CONFIG_BT_BNEP_PROTO_FILTER=y +CONFIG_BT_HIDP=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_MTD=y +CONFIG_MTD_CONCAT=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_AFS_PARTS=y +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_COMPLEX_MAPPINGS=y +CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_PLATRAM=y +CONFIG_MTD_DATAFLASH=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_ATMEL=y +CONFIG_MTD_NAND_PLATFORM=y +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_GLUEBI=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_ATMEL_TCLIB=y +CONFIG_EEPROM_LEGACY=m +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=m +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=m +CONFIG_SCSI_MULTI_LUN=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_NETDEVICES=y +CONFIG_TUN=m +CONFIG_PHYLIB=y +CONFIG_DAVICOM_PHY=y +CONFIG_SMSC_PHY=y +CONFIG_MICREL_PHY=y +CONFIG_NET_ETHERNET=y +CONFIG_ARM_AT91_ETHER=y +# CONFIG_NETDEV_1000 is not set +# CONFIG_NETDEV_10000 is not set +CONFIG_USB_CATC=m +CONFIG_USB_KAWETH=m +CONFIG_USB_PEGASUS=m +CONFIG_USB_RTL8150=m +CONFIG_USB_USBNET=m +CONFIG_USB_NET_DM9601=m +CONFIG_USB_NET_GL620A=m +CONFIG_USB_NET_PLUSB=m +CONFIG_USB_NET_RNDIS_HOST=m +CONFIG_USB_ALI_M5632=y +CONFIG_USB_AN2720=y +CONFIG_USB_EPSON2888=y +CONFIG_PPP=y +CONFIG_PPP_MULTILINK=y +CONFIG_PPP_FILTER=y +CONFIG_PPP_ASYNC=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_MPPE=m +CONFIG_PPPOE=m +CONFIG_SLIP=m +CONFIG_SLIP_COMPRESSED=y +CONFIG_SLIP_SMART=y +CONFIG_SLIP_MODE_SLIP6=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_MOUSEDEV_SCREEN_X=640 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480 +CONFIG_INPUT_EVDEV=y +CONFIG_KEYBOARD_GPIO=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_SERIAL_ATMEL=y +CONFIG_SERIAL_ATMEL_CONSOLE=y +CONFIG_LEGACY_PTY_COUNT=32 +CONFIG_HW_RANDOM=y +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_GPIO=y +CONFIG_SPI=y +CONFIG_SPI_ATMEL=y +CONFIG_SPI_BITBANG=y +CONFIG_GPIO_SYSFS=y +CONFIG_HWMON=m +CONFIG_SENSORS_ADM1021=m +CONFIG_SENSORS_ADM1025=m +CONFIG_SENSORS_ADM1026=m +CONFIG_SENSORS_ADM1029=m +CONFIG_SENSORS_ADM1031=m +CONFIG_SENSORS_ADM9240=m +CONFIG_SENSORS_DS1621=m +CONFIG_SENSORS_GL518SM=m +CONFIG_SENSORS_GL520SM=m +CONFIG_SENSORS_IT87=m +CONFIG_SENSORS_LM63=m +CONFIG_SENSORS_LM73=m +CONFIG_SENSORS_LM75=m +CONFIG_SENSORS_LM77=m +CONFIG_SENSORS_LM78=m +CONFIG_SENSORS_LM80=m +CONFIG_SENSORS_LM83=m +CONFIG_SENSORS_LM85=m +CONFIG_SENSORS_LM87=m +CONFIG_SENSORS_LM90=m +CONFIG_SENSORS_LM92=m +CONFIG_SENSORS_MAX1619=m +CONFIG_SENSORS_PCF8591=m +CONFIG_SENSORS_SMSC47B397=m +CONFIG_SENSORS_W83781D=m +CONFIG_SENSORS_W83791D=m +CONFIG_SENSORS_W83792D=m +CONFIG_SENSORS_W83793=m +CONFIG_SENSORS_W83L785TS=m +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_NOWAYOUT=y +CONFIG_AT91RM9200_WATCHDOG=y +CONFIG_FB=y +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_S1D13XXX=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_LCD_CLASS_DEVICE=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y +# CONFIG_BACKLIGHT_GENERIC is not set +CONFIG_DISPLAY_SUPPORT=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FONTS=y +CONFIG_FONT_MINI_4x6=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_USB=y +CONFIG_USB_DEVICEFS=y +# CONFIG_USB_DEVICE_CLASS is not set +CONFIG_USB_MON=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_ACM=m +CONFIG_USB_PRINTER=m +CONFIG_USB_STORAGE=y +CONFIG_USB_SERIAL=y +CONFIG_USB_SERIAL_CONSOLE=y +CONFIG_USB_SERIAL_GENERIC=y +CONFIG_USB_SERIAL_FTDI_SIO=y +CONFIG_USB_SERIAL_KEYSPAN=y +CONFIG_USB_SERIAL_KEYSPAN_MPR=y +CONFIG_USB_SERIAL_KEYSPAN_USA28=y +CONFIG_USB_SERIAL_KEYSPAN_USA28X=y +CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y +CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y +CONFIG_USB_SERIAL_KEYSPAN_USA19=y +CONFIG_USB_SERIAL_KEYSPAN_USA18X=y +CONFIG_USB_SERIAL_KEYSPAN_USA19W=y +CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y +CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y +CONFIG_USB_SERIAL_KEYSPAN_USA49W=y +CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y +CONFIG_USB_SERIAL_MCT_U232=y +CONFIG_USB_SERIAL_PL2303=y +CONFIG_USB_GADGET=y +CONFIG_USB_ETH=m +CONFIG_USB_MASS_STORAGE=m +CONFIG_MMC=y +CONFIG_MMC_AT91=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_LEDS_TRIGGER_TIMER=y +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +CONFIG_LEDS_TRIGGER_GPIO=y +CONFIG_LEDS_TRIGGER_DEFAULT_ON=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_HCTOSYS is not set +CONFIG_RTC_DRV_DS1307=y +CONFIG_RTC_DRV_PCF8563=y +CONFIG_RTC_DRV_AT91RM9200=y +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_FS_XATTR is not set +CONFIG_REISERFS_FS=y +CONFIG_AUTOFS4_FS=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=m +CONFIG_TMPFS=y +CONFIG_CONFIGFS_FS=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_SUMMARY=y +CONFIG_JFFS2_COMPRESSION_OPTIONS=y +CONFIG_JFFS2_LZO=y +CONFIG_JFFS2_RUBIN=y +CONFIG_CRAMFS=y +CONFIG_MINIX_FS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_ROOT_NFS=y +CONFIG_NFSD=y +CONFIG_SMB_FS=m +CONFIG_CIFS=m +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_CODEPAGE_737=m +CONFIG_NLS_CODEPAGE_775=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_CODEPAGE_852=m +CONFIG_NLS_CODEPAGE_855=m +CONFIG_NLS_CODEPAGE_857=m +CONFIG_NLS_CODEPAGE_860=m +CONFIG_NLS_CODEPAGE_861=m +CONFIG_NLS_CODEPAGE_862=m +CONFIG_NLS_CODEPAGE_863=m +CONFIG_NLS_CODEPAGE_864=m +CONFIG_NLS_CODEPAGE_865=m +CONFIG_NLS_CODEPAGE_866=m +CONFIG_NLS_CODEPAGE_869=m +CONFIG_NLS_CODEPAGE_936=m +CONFIG_NLS_CODEPAGE_950=m +CONFIG_NLS_CODEPAGE_932=m +CONFIG_NLS_CODEPAGE_949=m +CONFIG_NLS_CODEPAGE_874=m +CONFIG_NLS_ISO8859_8=m +CONFIG_NLS_CODEPAGE_1250=m +CONFIG_NLS_CODEPAGE_1251=m +CONFIG_NLS_ASCII=m +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_ISO8859_2=m +CONFIG_NLS_ISO8859_3=m +CONFIG_NLS_ISO8859_4=m +CONFIG_NLS_ISO8859_5=m +CONFIG_NLS_ISO8859_6=m +CONFIG_NLS_ISO8859_7=m +CONFIG_NLS_ISO8859_9=m +CONFIG_NLS_ISO8859_13=m +CONFIG_NLS_ISO8859_14=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_KOI8_R=m +CONFIG_NLS_KOI8_U=m +CONFIG_NLS_UTF8=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_KERNEL=y +# CONFIG_RCU_CPU_STALL_DETECTOR is not set +# CONFIG_FTRACE is not set +CONFIG_CRYPTO_PCBC=y +CONFIG_CRYPTO_SHA1=y diff --git a/arch/arm/configs/at91rm9200dk_defconfig b/arch/arm/configs/at91rm9200dk_defconfig deleted file mode 100644 index 4438e64f3bfb..000000000000 --- a/arch/arm/configs/at91rm9200dk_defconfig +++ /dev/null @@ -1,72 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_ARCH_AT91RM9200DK=y -CONFIG_MACH_ECO920=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -# CONFIG_ARM_THUMB is not set -CONFIG_PCCARD=y -CONFIG_AT91_CF=y -CONFIG_LEDS=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,115200 initrd=0x20410000,3145728 root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_GPIO=y -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_MMC=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/configs/at91rm9200ek_defconfig b/arch/arm/configs/at91rm9200ek_defconfig deleted file mode 100644 index ccd517c64bc7..000000000000 --- a/arch/arm/configs/at91rm9200ek_defconfig +++ /dev/null @@ -1,73 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_AT91RM9200EK=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -# CONFIG_ARM_THUMB is not set -CONFIG_LEDS=y -CONFIG_LEDS_CPU=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,115200 initrd=0x20410000,3145728 root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_GPIO=y -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -CONFIG_FB=y -CONFIG_FB_S1D13XXX=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_MMC=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/configs/ateb9200_defconfig b/arch/arm/configs/ateb9200_defconfig deleted file mode 100644 index 1b0e9a1689bb..000000000000 --- a/arch/arm/configs/ateb9200_defconfig +++ /dev/null @@ -1,131 +0,0 @@ -CONFIG_EXPERIMENTAL=y -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_EMBEDDED=y -CONFIG_SLAB=y -CONFIG_PROFILING=y -CONFIG_OPROFILE=m -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_ARCH_AT91=y -CONFIG_MACH_ATEB9200=y -CONFIG_PCCARD=m -CONFIG_AT91_CF=m -CONFIG_PREEMPT=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_FPE_NWFPE=y -CONFIG_PM=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_NET_KEY=y -CONFIG_INET=y -# CONFIG_IPV6 is not set -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK_RO=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_SCSI=m -CONFIG_BLK_DEV_SD=m -CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=m -CONFIG_SCSI_MULTI_LUN=y -CONFIG_NETDEVICES=y -CONFIG_DUMMY=m -CONFIG_TUN=m -CONFIG_PHYLIB=y -CONFIG_DAVICOM_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -CONFIG_USB_USBNET=y -CONFIG_USB_NET_GL620A=y -CONFIG_USB_NET_PLUSB=y -CONFIG_USB_NET_RNDIS_HOST=y -CONFIG_USB_ALI_M5632=y -CONFIG_USB_AN2720=y -CONFIG_USB_EPSON2888=y -CONFIG_PPP=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPPOE=m -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_I2C=m -CONFIG_I2C_CHARDEV=m -CONFIG_I2C_GPIO=m -# CONFIG_VGA_CONSOLE is not set -CONFIG_SOUND=y -CONFIG_USB_HID=m -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y -CONFIG_USB=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_ACM=m -CONFIG_USB_PRINTER=m -CONFIG_USB_STORAGE=m -CONFIG_USB_STORAGE_DATAFAB=m -CONFIG_USB_STORAGE_FREECOM=m -CONFIG_USB_STORAGE_USBAT=m -CONFIG_USB_STORAGE_SDDR09=m -CONFIG_USB_STORAGE_SDDR55=m -CONFIG_USB_STORAGE_JUMPSHOT=m -CONFIG_USB_SERIAL=m -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_FTDI_SIO=m -CONFIG_USB_SERIAL_PL2303=m -CONFIG_USB_GADGET=m -CONFIG_USB_ETH=m -CONFIG_USB_GADGETFS=m -CONFIG_USB_FILE_STORAGE=m -CONFIG_USB_G_SERIAL=m -CONFIG_MMC=m -CONFIG_MMC_DEBUG=y -CONFIG_RTC_CLASS=y -# CONFIG_RTC_HCTOSYS is not set -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=m -CONFIG_EXT3_FS=m -CONFIG_REISERFS_FS=m -CONFIG_INOTIFY=y -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=m -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=y -CONFIG_NFSD=m -CONFIG_NFSD_V4=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_UTF8=m -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRC16=m -CONFIG_LIBCRC32C=m diff --git a/arch/arm/configs/carmeva_defconfig b/arch/arm/configs/carmeva_defconfig deleted file mode 100644 index ac64dbd8a49c..000000000000 --- a/arch/arm/configs/carmeva_defconfig +++ /dev/null @@ -1,47 +0,0 @@ -CONFIG_EXPERIMENTAL=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EMBEDDED=y -# CONFIG_HOTPLUG is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_ARCH_AT91=y -CONFIG_MACH_CARMEVA=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -# CONFIG_IPV6 is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_BLK_DEV_RAM=y -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -CONFIG_SERIO=m -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_MMC=m -CONFIG_MMC_DEBUG=y -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -# CONFIG_DNOTIFY is not set -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_NFSD=y diff --git a/arch/arm/configs/cpuat91_defconfig b/arch/arm/configs/cpuat91_defconfig deleted file mode 100644 index 022aeb55b676..000000000000 --- a/arch/arm/configs/cpuat91_defconfig +++ /dev/null @@ -1,112 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_CPUAT91=y -CONFIG_AT91_TIMER_HZ=100 -# CONFIG_ARM_THUMB is not set -CONFIG_PREEMPT=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_PLATRAM=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_NBD=y -CONFIG_BLK_DEV_RAM=y -# CONFIG_MISC_DEVICES is not set -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_SCSI_MULTI_LUN=y -# CONFIG_SCSI_LOWLEVEL is not set -CONFIG_NETDEVICES=y -CONFIG_PHYLIB=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set -CONFIG_PPP=y -CONFIG_PPP_ASYNC=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_BSDCOMP=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=32 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_GPIO=y -CONFIG_GPIO_SYSFS=y -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set -CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_USB_GADGET=y -CONFIG_USB_ETH=m -CONFIG_MMC=y -CONFIG_MMC_AT91=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_GPIO=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_GPIO=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -# CONFIG_RTC_HCTOSYS is not set -CONFIG_RTC_DRV_DS1307=y -CONFIG_RTC_DRV_PCF8563=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_FS_XATTR is not set -CONFIG_INOTIFY=y -CONFIG_AUTOFS4_FS=y -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_CRAMFS=y -CONFIG_MINIX_FS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_UTF8=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set diff --git a/arch/arm/configs/csb337_defconfig b/arch/arm/configs/csb337_defconfig deleted file mode 100644 index a24c448840c4..000000000000 --- a/arch/arm/configs/csb337_defconfig +++ /dev/null @@ -1,104 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_CSB337=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -# CONFIG_ARM_THUMB is not set -CONFIG_PCCARD=y -CONFIG_AT91_CF=y -CONFIG_LEDS=y -CONFIG_LEDS_CPU=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,38400 initrd=0x20410000,3145728 root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_LRO is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_ATMEL_SSC=y -CONFIG_SCSI=y -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_GPIO=y -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_USB_SERIAL=y -CONFIG_USB_SERIAL_CONSOLE=y -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_FTDI_SIO=y -CONFIG_USB_SERIAL_KEYSPAN=y -CONFIG_USB_SERIAL_KEYSPAN_MPR=y -CONFIG_USB_SERIAL_KEYSPAN_USA28=y -CONFIG_USB_SERIAL_KEYSPAN_USA28X=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y -CONFIG_USB_SERIAL_KEYSPAN_USA19=y -CONFIG_USB_SERIAL_KEYSPAN_USA18X=y -CONFIG_USB_SERIAL_KEYSPAN_USA19W=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y -CONFIG_USB_SERIAL_KEYSPAN_USA49W=y -CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y -CONFIG_USB_SERIAL_MCT_U232=y -CONFIG_USB_GADGET=y -CONFIG_MMC=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_HCTOSYS_DEVICE="rtc1" -# CONFIG_RTC_INTF_SYSFS is not set -CONFIG_RTC_DRV_DS1307=y -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/configs/csb637_defconfig b/arch/arm/configs/csb637_defconfig deleted file mode 100644 index 98552adac5fb..000000000000 --- a/arch/arm/configs/csb637_defconfig +++ /dev/null @@ -1,98 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_CSB637=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -# CONFIG_ARM_THUMB is not set -CONFIG_PCCARD=y -CONFIG_AT91_CF=y -CONFIG_LEDS=y -CONFIG_LEDS_CPU=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,38400 initrd=0x20410000,3145728 root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_LRO is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_SCSI=y -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_USB_SERIAL=y -CONFIG_USB_SERIAL_CONSOLE=y -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_FTDI_SIO=y -CONFIG_USB_SERIAL_KEYSPAN=y -CONFIG_USB_SERIAL_KEYSPAN_MPR=y -CONFIG_USB_SERIAL_KEYSPAN_USA28=y -CONFIG_USB_SERIAL_KEYSPAN_USA28X=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y -CONFIG_USB_SERIAL_KEYSPAN_USA19=y -CONFIG_USB_SERIAL_KEYSPAN_USA18X=y -CONFIG_USB_SERIAL_KEYSPAN_USA19W=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y -CONFIG_USB_SERIAL_KEYSPAN_USA49W=y -CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y -CONFIG_USB_SERIAL_MCT_U232=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_GPIO=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_EXT2_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/configs/ecbat91_defconfig b/arch/arm/configs/ecbat91_defconfig deleted file mode 100644 index 6bb6abdcea8c..000000000000 --- a/arch/arm/configs/ecbat91_defconfig +++ /dev/null @@ -1,99 +0,0 @@ -CONFIG_EXPERIMENTAL=y -CONFIG_SYSVIPC=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_ECBAT91=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -CONFIG_PCCARD=y -CONFIG_AT91_CF=y -CONFIG_PREEMPT=y -CONFIG_LEDS=y -CONFIG_LEDS_CPU=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="rootfstype=reiserfs root=/dev/mmcblk0p1 console=ttyS0,115200n8 rootdelay=1" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IPV6 is not set -CONFIG_CFG80211=y -CONFIG_MAC80211=y -# CONFIG_STANDALONE is not set -# CONFIG_PREVENT_FIRMWARE_BUILD is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_AFS_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_DATAFLASH=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_SG=y -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set -CONFIG_PPP=y -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_HW_RANDOM=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_SPI=y -CONFIG_SPI_BITBANG=y -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_PRINTER=y -CONFIG_USB_STORAGE=y -CONFIG_USB_GADGET=y -CONFIG_MMC=y -CONFIG_MMC_DEBUG=y -CONFIG_MMC_AT91=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_RTC_CLASS=y -# CONFIG_RTC_HCTOSYS is not set -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -CONFIG_REISERFS_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CONFIGFS_FS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_DEBUG_USER=y -CONFIG_CRYPTO_PCBC=y -CONFIG_CRYPTO_SHA1=y diff --git a/arch/arm/configs/kafa_defconfig b/arch/arm/configs/kafa_defconfig deleted file mode 100644 index 896dbe00dc6e..000000000000 --- a/arch/arm/configs/kafa_defconfig +++ /dev/null @@ -1,61 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_KAFA=y -# CONFIG_ARM_THUMB is not set -CONFIG_PREEMPT=y -CONFIG_LEDS=y -CONFIG_LEDS_CPU=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,115200 initrd=0x20800000,10M root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_MISC=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -# CONFIG_INET_DIAG is not set -# CONFIG_IPV6 is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK_RO=y -CONFIG_NETDEVICES=y -CONFIG_PHYLIB=y -CONFIG_DAVICOM_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=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_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=32 -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_GPIO=y -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_RTC_CLASS=y -# CONFIG_RTC_HCTOSYS is not set -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_FS_XATTR is not set -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=m -CONFIG_NFS_V3=y -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_DES=y diff --git a/arch/arm/configs/kb9202_defconfig b/arch/arm/configs/kb9202_defconfig deleted file mode 100644 index 9f906a85f5c2..000000000000 --- a/arch/arm/configs/kb9202_defconfig +++ /dev/null @@ -1,127 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y -CONFIG_AUDIT=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_KALLSYMS_EXTRA_PASS=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_KB9200=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x10000000 -CONFIG_ZBOOT_ROM_BSS=0x20040000 -CONFIG_CMDLINE="noinitrd root=/dev/mtdblock0 rootfstype=jffs2 mem=64M" -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_MISC=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set -# CONFIG_INET_DIAG is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -# CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CONCAT=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_COMPLEX_MAPPINGS=y -CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_ATMEL=y -CONFIG_MTD_UBI=y -CONFIG_MTD_UBI_GLUEBI=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_ATMEL_TCLIB=y -CONFIG_ATMEL_SSC=y -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_SG=y -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y -CONFIG_SCSI_SPI_ATTRS=m -# CONFIG_SCSI_LOWLEVEL is not set -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_LEGACY_PTYS is not set -# CONFIG_HW_RANDOM is not set -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -CONFIG_AT91RM9200_WATCHDOG=y -CONFIG_FB=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_TILEBLITTING=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -# CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_BACKLIGHT_GENERIC is not set -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_MINI_4x6=y -# CONFIG_HID_SUPPORT is not set -CONFIG_USB=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_USB_LIBUSUAL=y -CONFIG_MMC=y -CONFIG_MMC_AT91=m -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_DNOTIFY is not set -CONFIG_INOTIFY=y -CONFIG_VFAT_FS=y -CONFIG_TMPFS=y -CONFIG_CONFIGFS_FS=y -CONFIG_JFFS2_FS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_ROOT_NFS=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_UTF8=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -# CONFIG_SCHED_DEBUG is not set -# CONFIG_DEBUG_PREEMPT is not set -# CONFIG_RCU_CPU_STALL_DETECTOR is not set diff --git a/arch/arm/configs/onearm_defconfig b/arch/arm/configs/onearm_defconfig deleted file mode 100644 index 1579857aeeaa..000000000000 --- a/arch/arm/configs/onearm_defconfig +++ /dev/null @@ -1,80 +0,0 @@ -CONFIG_EXPERIMENTAL=y -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EMBEDDED=y -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_ONEARM=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -# CONFIG_ARM_THUMB is not set -CONFIG_PCCARD=y -CONFIG_AT91_CF=y -CONFIG_LEDS=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="console=ttyS0,115200 root=/dev/nfs ip=bootp mem=64M" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IPV6=y -# CONFIG_INET6_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET6_XFRM_MODE_TUNNEL is not set -# CONFIG_INET6_XFRM_MODE_BEET is not set -# CONFIG_IPV6_SIT is not set -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_NBD=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=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_VT is not set -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_MMC=y -CONFIG_EXT2_FS=y -CONFIG_INOTIFY=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_ROOT_NFS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/configs/picotux200_defconfig b/arch/arm/configs/picotux200_defconfig deleted file mode 100644 index 4c9afa478d57..000000000000 --- a/arch/arm/configs/picotux200_defconfig +++ /dev/null @@ -1,242 +0,0 @@ -CONFIG_EXPERIMENTAL=y -CONFIG_SYSVIPC=y -CONFIG_IKCONFIG=m -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_EMBEDDED=y -# CONFIG_KALLSYMS is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_MACH_PICOTUX2XX=y -CONFIG_AT91_PROGRAMMABLE_CLOCKS=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_MISC=m -CONFIG_NET=y -CONFIG_PACKET=m -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_NET_IPIP=m -CONFIG_NET_IPGRE=m -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m -CONFIG_INET_DIAG=m -CONFIG_IPV6_PRIVACY=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m -CONFIG_IPV6_TUNNEL=m -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m -CONFIG_BT_RFCOMM=m -CONFIG_BT_RFCOMM_TTY=y -CONFIG_BT_BNEP=m -CONFIG_BT_BNEP_MC_FILTER=y -CONFIG_BT_BNEP_PROTO_FILTER=y -CONFIG_BT_HIDP=m -CONFIG_FW_LOADER=m -CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_EEPROM_LEGACY=m -CONFIG_SCSI=m -CONFIG_BLK_DEV_SD=m -CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=m -CONFIG_NETDEVICES=y -CONFIG_TUN=m -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -CONFIG_USB_CATC=m -CONFIG_USB_KAWETH=m -CONFIG_USB_PEGASUS=m -CONFIG_USB_RTL8150=m -CONFIG_USB_USBNET=m -CONFIG_USB_NET_DM9601=m -CONFIG_USB_NET_GL620A=m -CONFIG_USB_NET_PLUSB=m -CONFIG_USB_NET_MCS7830=m -CONFIG_USB_NET_RNDIS_HOST=m -CONFIG_USB_ALI_M5632=y -CONFIG_USB_AN2720=y -CONFIG_USB_EPSON2888=y -CONFIG_USB_KC2190=y -CONFIG_PPP=m -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPP_MPPE=m -CONFIG_PPPOE=m -CONFIG_SLIP=m -CONFIG_SLIP_COMPRESSED=y -CONFIG_SLIP_SMART=y -CONFIG_SLIP_MODE_SLIP6=y -# CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_LEGACY_PTYS is not set -CONFIG_I2C=m -CONFIG_I2C_CHARDEV=m -CONFIG_I2C_GPIO=m -CONFIG_HWMON=m -CONFIG_SENSORS_ADM1021=m -CONFIG_SENSORS_ADM1025=m -CONFIG_SENSORS_ADM1026=m -CONFIG_SENSORS_ADM1029=m -CONFIG_SENSORS_ADM1031=m -CONFIG_SENSORS_ADM9240=m -CONFIG_SENSORS_DS1621=m -CONFIG_SENSORS_GL518SM=m -CONFIG_SENSORS_GL520SM=m -CONFIG_SENSORS_IT87=m -CONFIG_SENSORS_LM63=m -CONFIG_SENSORS_LM75=m -CONFIG_SENSORS_LM77=m -CONFIG_SENSORS_LM78=m -CONFIG_SENSORS_LM80=m -CONFIG_SENSORS_LM83=m -CONFIG_SENSORS_LM85=m -CONFIG_SENSORS_LM87=m -CONFIG_SENSORS_LM90=m -CONFIG_SENSORS_LM92=m -CONFIG_SENSORS_MAX1619=m -CONFIG_SENSORS_PCF8591=m -CONFIG_SENSORS_SMSC47B397=m -CONFIG_SENSORS_W83781D=m -CONFIG_SENSORS_W83791D=m -CONFIG_SENSORS_W83792D=m -CONFIG_SENSORS_W83793=m -CONFIG_SENSORS_W83L785TS=m -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_AT91RM9200_WATCHDOG=m -CONFIG_HID=m -CONFIG_USB=m -CONFIG_USB_DEVICEFS=y -CONFIG_USB_OHCI_HCD=m -CONFIG_USB_ACM=m -CONFIG_USB_PRINTER=m -CONFIG_USB_STORAGE=m -CONFIG_USB_SERIAL=m -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_PL2303=m -CONFIG_MMC=m -CONFIG_MMC_AT91=m -CONFIG_RTC_CLASS=m -CONFIG_RTC_DRV_AT91RM9200=m -CONFIG_EXT2_FS=m -CONFIG_EXT3_FS=m -# CONFIG_EXT3_FS_XATTR is not set -CONFIG_INOTIFY=y -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_NTFS_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_NFS_FS=m -CONFIG_SMB_FS=m -CONFIG_CIFS=m -CONFIG_PARTITION_ADVANCED=y -CONFIG_AMIGA_PARTITION=y -CONFIG_NLS_DEFAULT="utf-8" -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_BUGVERBOSE is not set -CONFIG_DEBUG_LL=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_LIBCRC32C=m diff --git a/arch/arm/configs/yl9200_defconfig b/arch/arm/configs/yl9200_defconfig deleted file mode 100644 index 30c537f61089..000000000000 --- a/arch/arm/configs/yl9200_defconfig +++ /dev/null @@ -1,137 +0,0 @@ -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARCH_AT91=y -CONFIG_ARCH_AT91RM9200DK=y -CONFIG_MACH_YL9200=y -# CONFIG_ARM_THUMB is not set -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="mem=32M console=ttyS0,115200 initrd=0x20410000,3145728 root=/dev/ram0 rw" -CONFIG_FPE_NWFPE=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set -# CONFIG_INET_DIAG is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_MTD=y -CONFIG_MTD_CONCAT=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_COMPLEX_MAPPINGS=y -CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_PLATRAM=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_ATMEL=y -CONFIG_MTD_NAND_PLATFORM=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=3 -CONFIG_BLK_DEV_RAM_SIZE=8192 -# CONFIG_MISC_DEVICES is not set -CONFIG_BLK_DEV_SD=y -CONFIG_ATA=y -CONFIG_NETDEVICES=y -CONFIG_PHYLIB=y -CONFIG_DAVICOM_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_ARM_AT91_ETHER=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=640 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480 -CONFIG_INPUT_EVDEV=y -# CONFIG_KEYBOARD_ATKBD is not set -CONFIG_KEYBOARD_GPIO=y -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_TOUCHSCREEN_ADS7846=y -# CONFIG_SERIO_SERPORT is not set -CONFIG_SERIAL_ATMEL=y -CONFIG_SERIAL_ATMEL_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_SPI=y -CONFIG_SPI_DEBUG=y -CONFIG_SPI_ATMEL=y -CONFIG_FB=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -CONFIG_LCD_CLASS_DEVICE=y -CONFIG_BACKLIGHT_CLASS_DEVICE=y -CONFIG_DISPLAY_SUPPORT=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set -CONFIG_USB=y -CONFIG_USB_DEBUG=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set -CONFIG_USB_MON=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_USB_GADGET=y -CONFIG_USB_GADGET_M66592=y -CONFIG_USB_FILE_STORAGE=m -CONFIG_MMC=y -CONFIG_MMC_DEBUG=y -# CONFIG_MMC_BLOCK_BOUNCE is not set -CONFIG_MMC_AT91=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_GPIO=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_AT91RM9200=y -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT3_FS=y -CONFIG_REISERFS_FS=y -CONFIG_INOTIFY=y -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_UDF_FS=y -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_FS_DEBUG=1 -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_JFFS2_RUBIN=y -CONFIG_CRAMFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_SLUB_DEBUG_ON=y -CONFIG_DEBUG_KOBJECT=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_ERRORS=y -CONFIG_DEBUG_LL=y diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 062b58c029ab..749bb6622404 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -238,7 +238,7 @@ @ Slightly optimised to avoid incrementing the pointer twice usraccoff \instr, \reg, \ptr, \inc, 0, \cond, \abort .if \rept == 2 - usraccoff \instr, \reg, \ptr, \inc, 4, \cond, \abort + usraccoff \instr, \reg, \ptr, \inc, \inc, \cond, \abort .endif add\cond \ptr, #\rept * \inc diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h index 21fa272301f8..b2f95c72287c 100644 --- a/arch/arm/include/asm/hardware/it8152.h +++ b/arch/arm/include/asm/hardware/it8152.h @@ -76,6 +76,7 @@ extern unsigned long it8152_base_address; IT8152_PD_IRQ(0) Audio controller (ACR) */ #define IT8152_IRQ(x) (IRQ_BOARD_START + (x)) +#define IT8152_LAST_IRQ (IRQ_BOARD_START + 40) /* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */ #define IT8152_LD_IRQ_COUNT 9 diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 1fc684e70ab6..7080e2c8fa62 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -25,9 +25,6 @@ extern void *kmap_high(struct page *page); extern void *kmap_high_get(struct page *page); extern void kunmap_high(struct page *page); -extern void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte); -extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte); - /* * The following functions are already defined by <linux/highmem.h> * when CONFIG_HIGHMEM is not set. diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 68870c776671..b4ffe9d5b526 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -13,6 +13,10 @@ typedef struct { #ifdef CONFIG_CPU_HAS_ASID #define ASID(mm) ((mm)->context.id & 255) + +/* init_mm.context.id_lock should be initialized. */ +#define INIT_MM_CONTEXT(name) \ + .context.id_lock = __SPIN_LOCK_UNLOCKED(name.context.id_lock), #else #define ASID(mm) (0) #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index b155414192da..53d1d5deb111 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -374,6 +374,9 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd))) +/* we don't need complex calculations here as the pmd is folded into the pgd */ +#define pmd_addr_end(addr,end) (end) + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. diff --git a/arch/arm/include/asm/sizes.h b/arch/arm/include/asm/sizes.h index 4fc1565e4f93..316bb2b2be3d 100644 --- a/arch/arm/include/asm/sizes.h +++ b/arch/arm/include/asm/sizes.h @@ -13,9 +13,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -/* DO NOT EDIT!! - this file automatically generated - * from .s file by awk -f s2h.awk - */ /* Size definitions * Copyright (C) ARM Limited 1998. All rights reserved. */ @@ -25,6 +22,9 @@ /* handy sizes */ #define SZ_16 0x00000010 +#define SZ_32 0x00000020 +#define SZ_64 0x00000040 +#define SZ_128 0x00000080 #define SZ_256 0x00000100 #define SZ_512 0x00000200 diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 1120f18a6b17..80025948b8ad 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -150,6 +150,7 @@ extern unsigned int user_debug; #define rmb() dmb() #define wmb() mb() #else +#include <asm/memory.h> #define mb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) #define rmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) #define wmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index c09e3573c5de..bb96a7d4bbf5 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -911,7 +911,7 @@ __kuser_cmpxchg: @ 0xffff0fc0 * A special ghost syscall is used for that (see traps.c). */ stmfd sp!, {r7, lr} - ldr r7, =1f @ it's 20 bits + ldr r7, 1f @ it's 20 bits swi __ARM_NR_cmpxchg ldmfd sp!, {r7, pc} 1: .word __ARM_NR_cmpxchg diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 8bfa98757cd2..80bf8cd88d7c 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -29,6 +29,9 @@ ret_fast_syscall: ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne fast_work_pending +#if defined(CONFIG_IRQSOFF_TRACER) + asm_trace_hardirqs_on +#endif /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr @@ -65,6 +68,9 @@ ret_slow_syscall: tst r1, #_TIF_WORK_MASK bne work_pending no_work_pending: +#if defined(CONFIG_IRQSOFF_TRACER) + asm_trace_hardirqs_on +#endif /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index dd6b369ac69c..6bd82d25683c 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -85,9 +85,11 @@ ENTRY(stext) mrc p15, 0, r9, c0, c0 @ get processor id bl __lookup_processor_type @ r5=procinfo r9=cpuid movs r10, r5 @ invalid processor (r5=0)? + THUMB( it eq ) @ force fixup-able long branch encoding beq __error_p @ yes, error 'p' bl __lookup_machine_type @ r5=machinfo movs r8, r5 @ invalid machine (r5=0)? + THUMB( it eq ) @ force fixup-able long branch encoding beq __error_a @ yes, error 'a' bl __vet_atags #ifdef CONFIG_SMP_ON_UP @@ -262,6 +264,7 @@ __create_page_tables: mov pc, lr ENDPROC(__create_page_tables) .ltorg + .align __enable_mmu_loc: .long . .long __enable_mmu @@ -282,6 +285,7 @@ ENTRY(secondary_startup) bl __lookup_processor_type movs r10, r5 @ invalid processor? moveq r0, #'p' @ yes, error 'p' + THUMB( it eq ) @ force fixup-able long branch encoding beq __error_p /* @@ -308,6 +312,8 @@ ENTRY(__secondary_switched) b secondary_start_kernel ENDPROC(__secondary_switched) + .align + .type __secondary_data, %object __secondary_data: .long . @@ -413,6 +419,7 @@ __fixup_smp_on_up: mov pc, lr ENDPROC(__fixup_smp) + .align 1: .word . .word __smpalt_begin .word __smpalt_end diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 07a50357492a..fdfa4976b0bf 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -3034,11 +3034,11 @@ init_hw_perf_events(void) pr_info("no hardware support available\n"); } - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); return 0; } -arch_initcall(init_hw_perf_events); +early_initcall(init_hw_perf_events); /* * Callchain handling code. diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index fd26f8d65151..9cf4cbf8f95b 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -59,6 +59,8 @@ relocate_new_kernel: ldr r2,kexec_boot_atags mov pc,lr + .align + .globl kexec_start_address kexec_start_address: .long 0x0 diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8c1959590252..9066473c0ebc 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -310,7 +310,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void) * All kernel threads share the same mm context; grab a * reference and switch to it. */ - atomic_inc(&mm->mm_users); atomic_inc(&mm->mm_count); current->active_mm = mm; cpumask_set_cpu(cpu, mm_cpumask(mm)); diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S index 1e4cbd4e7be9..64f6bc1a9132 100644 --- a/arch/arm/lib/findbit.S +++ b/arch/arm/lib/findbit.S @@ -174,8 +174,8 @@ ENDPROC(_find_next_bit_be) */ .L_found: #if __LINUX_ARM_ARCH__ >= 5 - rsb r1, r3, #0 - and r3, r3, r1 + rsb r0, r3, #0 + and r3, r3, r0 clz r3, r3 rsb r3, r3, #31 add r0, r2, r3 @@ -190,5 +190,7 @@ ENDPROC(_find_next_bit_be) addeq r2, r2, #1 mov r0, r2 #endif + cmp r1, r0 @ Clamp to maxbit + movlo r0, r1 mov pc, lr diff --git a/arch/arm/mach-aaec2000/include/mach/vmalloc.h b/arch/arm/mach-aaec2000/include/mach/vmalloc.h index cff4e0a996ce..a6299e8321bd 100644 --- a/arch/arm/mach-aaec2000/include/mach/vmalloc.h +++ b/arch/arm/mach-aaec2000/include/mach/vmalloc.h @@ -11,6 +11,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile index 821eb842795f..d13add71f72a 100644 --- a/arch/arm/mach-at91/Makefile +++ b/arch/arm/mach-at91/Makefile @@ -24,8 +24,8 @@ obj-$(CONFIG_ARCH_AT91X40) += at91x40.o at91x40_time.o # AT91RM9200 board-specific support obj-$(CONFIG_MACH_ONEARM) += board-1arm.o -obj-$(CONFIG_ARCH_AT91RM9200DK) += board-dk.o -obj-$(CONFIG_MACH_AT91RM9200EK) += board-ek.o +obj-$(CONFIG_ARCH_AT91RM9200DK) += board-rm9200dk.o +obj-$(CONFIG_MACH_AT91RM9200EK) += board-rm9200ek.o obj-$(CONFIG_MACH_CSB337) += board-csb337.o obj-$(CONFIG_MACH_CSB637) += board-csb637.o obj-$(CONFIG_MACH_CARMEVA) += board-carmeva.o @@ -65,7 +65,7 @@ obj-$(CONFIG_MACH_AT91SAM9G20EK) += board-sam9g20ek.o obj-$(CONFIG_MACH_CPU9G20) += board-cpu9krea.o obj-$(CONFIG_MACH_STAMP9G20) += board-stamp9g20.o obj-$(CONFIG_MACH_PORTUXG20) += board-stamp9g20.o -obj-$(CONFIG_MACH_PCONTROL_G20) += board-pcontrol-g20.o +obj-$(CONFIG_MACH_PCONTROL_G20) += board-pcontrol-g20.o board-stamp9g20.o # AT91SAM9260/AT91SAM9G20 board-specific support obj-$(CONFIG_MACH_SNAPPER_9260) += board-snapper9260.o diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c index 9338825cfcd7..7b539228e0ef 100644 --- a/arch/arm/mach-at91/at91rm9200_devices.c +++ b/arch/arm/mach-at91/at91rm9200_devices.c @@ -1106,51 +1106,6 @@ static inline void configure_usart3_pins(unsigned pins) static struct platform_device *__initdata at91_uarts[ATMEL_MAX_UART]; /* the UARTs to use */ struct platform_device *atmel_default_console_device; /* the serial console device */ -void __init __deprecated at91_init_serial(struct at91_uart_config *config) -{ - int i; - - /* Fill in list of supported UARTs */ - for (i = 0; i < config->nr_tty; i++) { - switch (config->tty_map[i]) { - case 0: - configure_usart0_pins(ATMEL_UART_CTS | ATMEL_UART_RTS); - at91_uarts[i] = &at91rm9200_uart0_device; - at91_clock_associate("usart0_clk", &at91rm9200_uart0_device.dev, "usart"); - break; - case 1: - configure_usart1_pins(ATMEL_UART_CTS | ATMEL_UART_RTS | ATMEL_UART_DSR | ATMEL_UART_DTR | ATMEL_UART_DCD | ATMEL_UART_RI); - at91_uarts[i] = &at91rm9200_uart1_device; - at91_clock_associate("usart1_clk", &at91rm9200_uart1_device.dev, "usart"); - break; - case 2: - configure_usart2_pins(0); - at91_uarts[i] = &at91rm9200_uart2_device; - at91_clock_associate("usart2_clk", &at91rm9200_uart2_device.dev, "usart"); - break; - case 3: - configure_usart3_pins(0); - at91_uarts[i] = &at91rm9200_uart3_device; - at91_clock_associate("usart3_clk", &at91rm9200_uart3_device.dev, "usart"); - break; - case 4: - configure_dbgu_pins(); - at91_uarts[i] = &at91rm9200_dbgu_device; - at91_clock_associate("mck", &at91rm9200_dbgu_device.dev, "usart"); - break; - default: - continue; - } - at91_uarts[i]->id = i; /* update ID number to mapped ID */ - } - - /* Set serial console device */ - if (config->console_tty < ATMEL_MAX_UART) - atmel_default_console_device = at91_uarts[config->console_tty]; - if (!atmel_default_console_device) - printk(KERN_INFO "AT91: No default serial console defined.\n"); -} - void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins) { struct platform_device *pdev; diff --git a/arch/arm/mach-at91/board-1arm.c b/arch/arm/mach-at91/board-1arm.c index 46bdc82d3fbf..8a3fc84847c1 100644 --- a/arch/arm/mach-at91/board-1arm.c +++ b/arch/arm/mach-at91/board-1arm.c @@ -39,24 +39,24 @@ #include "generic.h" -/* - * Serial port configuration. - * 0 .. 3 = USART0 .. USART3 - * 4 = DBGU - */ -static struct at91_uart_config __initdata onearm_uart_config = { - .console_tty = 0, /* ttyS0 */ - .nr_tty = 3, - .tty_map = { 4, 0, 1, -1, -1 }, /* ttyS0, ..., ttyS4 */ -}; - static void __init onearm_map_io(void) { /* Initialize processor: 18.432 MHz crystal */ at91rm9200_initialize(18432000, AT91RM9200_PQFP); - /* Setup the serial ports and console */ - at91_init_serial(&onearm_uart_config); + /* DBGU on ttyS0. (Rx & Tx only) */ + at91_register_uart(0, 0, 0); + + /* USART0 on ttyS1 (Rx, Tx, CTS, RTS) */ + at91_register_uart(AT91RM9200_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS); + + /* USART1 on ttyS2 (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */ + at91_register_uart(AT91RM9200_ID_US1, 2, ATMEL_UART_CTS | ATMEL_UART_RTS + | ATMEL_UART_DTR | ATMEL_UART_DSR | ATMEL_UART_DCD + | ATMEL_UART_RI); + + /* set serial console to ttyS0 (ie, DBGU) */ + at91_set_serial_console(0); } static void __init onearm_init_irq(void) diff --git a/arch/arm/mach-at91/board-kafa.c b/arch/arm/mach-at91/board-kafa.c index c0ce79d431a0..d2e1f4ec1fcc 100644 --- a/arch/arm/mach-at91/board-kafa.c +++ b/arch/arm/mach-at91/board-kafa.c @@ -39,17 +39,6 @@ #include "generic.h" -/* - * Serial port configuration. - * 0 .. 3 = USART0 .. USART3 - * 4 = DBGU - */ -static struct at91_uart_config __initdata kafa_uart_config = { - .console_tty = 0, /* ttyS0 */ - .nr_tty = 2, - .tty_map = { 4, 0, -1, -1, -1 } /* ttyS0, ..., ttyS4 */ -}; - static void __init kafa_map_io(void) { /* Initialize processor: 18.432 MHz crystal */ @@ -58,8 +47,14 @@ static void __init kafa_map_io(void) /* Set up the LEDs */ at91_init_leds(AT91_PIN_PB4, AT91_PIN_PB4); - /* Setup the serial ports and console */ - at91_init_serial(&kafa_uart_config); + /* DBGU on ttyS0. (Rx & Tx only) */ + at91_register_uart(0, 0, 0); + + /* USART0 on ttyS1 (Rx, Tx, CTS, RTS) */ + at91_register_uart(AT91RM9200_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS); + + /* set serial console to ttyS0 (ie, DBGU) */ + at91_set_serial_console(0); } static void __init kafa_init_irq(void) diff --git a/arch/arm/mach-at91/board-pcontrol-g20.c b/arch/arm/mach-at91/board-pcontrol-g20.c index bba5a560e02b..feb65787c30b 100644 --- a/arch/arm/mach-at91/board-pcontrol-g20.c +++ b/arch/arm/mach-at91/board-pcontrol-g20.c @@ -31,6 +31,7 @@ #include <mach/board.h> #include <mach/at91sam9_smc.h> +#include <mach/stamp9g20.h> #include "sam9_smc.h" #include "generic.h" @@ -38,11 +39,7 @@ static void __init pcontrol_g20_map_io(void) { - /* Initialize processor: 18.432 MHz crystal */ - at91sam9260_initialize(18432000); - - /* DGBU on ttyS0. (Rx, Tx) only TTL -> JTAG connector X7 17,19 ) */ - at91_register_uart(0, 0, 0); + stamp9g20_map_io(); /* USART0 on ttyS1. (Rx, Tx, CTS, RTS) piggyback A2 */ at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS @@ -54,9 +51,6 @@ static void __init pcontrol_g20_map_io(void) /* USART2 on ttyS3. (Rx, Tx) 9bit-Bus Multidrop-mode X4 */ at91_register_uart(AT91SAM9260_ID_US4, 3, 0); - - /* set serial console to ttyS0 (ie, DBGU) */ - at91_set_serial_console(0); } @@ -66,38 +60,6 @@ static void __init init_irq(void) } -/* - * NAND flash 512MiB 1,8V 8-bit, sector size 128 KiB - */ -static struct atmel_nand_data __initdata nand_data = { - .ale = 21, - .cle = 22, - .rdy_pin = AT91_PIN_PC13, - .enable_pin = AT91_PIN_PC14, -}; - -/* - * Bus timings; unit = 7.57ns - */ -static struct sam9_smc_config __initdata nand_smc_config = { - .ncs_read_setup = 0, - .nrd_setup = 2, - .ncs_write_setup = 0, - .nwe_setup = 2, - - .ncs_read_pulse = 4, - .nrd_pulse = 4, - .ncs_write_pulse = 4, - .nwe_pulse = 4, - - .read_cycle = 7, - .write_cycle = 7, - - .mode = AT91_SMC_READMODE | AT91_SMC_WRITEMODE - | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8, - .tdf_cycles = 3, -}; - static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { { .ncs_read_setup = 16, .nrd_setup = 18, @@ -138,14 +100,6 @@ static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { { .tdf_cycles = 1, } }; -static void __init add_device_nand(void) -{ - /* configure chip-select 3 (NAND) */ - sam9_smc_configure(3, &nand_smc_config); - at91_add_device_nand(&nand_data); -} - - static void __init add_device_pcontrol(void) { /* configure chip-select 4 (IO compatible to 8051 X4 ) */ @@ -156,23 +110,6 @@ static void __init add_device_pcontrol(void) /* - * MCI (SD/MMC) - * det_pin, wp_pin and vcc_pin are not connected - */ -#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE) -static struct mci_platform_data __initdata mmc_data = { - .slot[0] = { - .bus_width = 4, - }, -}; -#else -static struct at91_mmc_data __initdata mmc_data = { - .wire4 = 1, -}; -#endif - - -/* * USB Host port */ static struct at91_usbh_data __initdata usbh_data = { @@ -265,42 +202,13 @@ static struct spi_board_info pcontrol_g20_spi_devices[] = { }; -/* - * Dallas 1-Wire DS2431 - */ -static struct w1_gpio_platform_data w1_gpio_pdata = { - .pin = AT91_PIN_PA29, - .is_open_drain = 1, -}; - -static struct platform_device w1_device = { - .name = "w1-gpio", - .id = -1, - .dev.platform_data = &w1_gpio_pdata, -}; - -static void add_wire1(void) -{ - at91_set_GPIO_periph(w1_gpio_pdata.pin, 1); - at91_set_multi_drive(w1_gpio_pdata.pin, 1); - platform_device_register(&w1_device); -} - - static void __init pcontrol_g20_board_init(void) { - at91_add_device_serial(); - add_device_nand(); -#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE) - at91_add_device_mci(0, &mmc_data); -#else - at91_add_device_mmc(0, &mmc_data); -#endif + stamp9g20_board_init(); at91_add_device_usbh(&usbh_data); at91_add_device_eth(&macb_data); at91_add_device_i2c(pcontrol_g20_i2c_devices, ARRAY_SIZE(pcontrol_g20_i2c_devices)); - add_wire1(); add_device_pcontrol(); at91_add_device_spi(pcontrol_g20_spi_devices, ARRAY_SIZE(pcontrol_g20_spi_devices)); diff --git a/arch/arm/mach-at91/board-picotux200.c b/arch/arm/mach-at91/board-picotux200.c index 9d833bbc592d..55dad3a46547 100644 --- a/arch/arm/mach-at91/board-picotux200.c +++ b/arch/arm/mach-at91/board-picotux200.c @@ -43,24 +43,21 @@ #include "generic.h" -/* - * Serial port configuration. - * 0 .. 3 = USART0 .. USART3 - * 4 = DBGU - */ -static struct at91_uart_config __initdata picotux200_uart_config = { - .console_tty = 0, /* ttyS0 */ - .nr_tty = 2, - .tty_map = { 4, 1, -1, -1, -1 } /* ttyS0, ..., ttyS4 */ -}; - static void __init picotux200_map_io(void) { /* Initialize processor: 18.432 MHz crystal */ at91rm9200_initialize(18432000, AT91RM9200_BGA); - /* Setup the serial ports and console */ - at91_init_serial(&picotux200_uart_config); + /* DBGU on ttyS0. (Rx & Tx only) */ + at91_register_uart(0, 0, 0); + + /* USART1 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */ + at91_register_uart(AT91RM9200_ID_US1, 1, ATMEL_UART_CTS | ATMEL_UART_RTS + | ATMEL_UART_DTR | ATMEL_UART_DSR | ATMEL_UART_DCD + | ATMEL_UART_RI); + + /* set serial console to ttyS0 (ie, DBGU) */ + at91_set_serial_console(0); } static void __init picotux200_init_irq(void) @@ -77,11 +74,6 @@ static struct at91_usbh_data __initdata picotux200_usbh_data = { .ports = 1, }; -// static struct at91_udc_data __initdata picotux200_udc_data = { -// .vbus_pin = AT91_PIN_PD4, -// .pullup_pin = AT91_PIN_PD5, -// }; - static struct at91_mmc_data __initdata picotux200_mmc_data = { .det_pin = AT91_PIN_PB27, .slot_b = 0, @@ -89,21 +81,6 @@ static struct at91_mmc_data __initdata picotux200_mmc_data = { .wp_pin = AT91_PIN_PA17, }; -// static struct spi_board_info picotux200_spi_devices[] = { -// { /* DataFlash chip */ -// .modalias = "mtd_dataflash", -// .chip_select = 0, -// .max_speed_hz = 15 * 1000 * 1000, -// }, -// #ifdef CONFIG_MTD_AT91_DATAFLASH_CARD -// { /* DataFlash card */ -// .modalias = "mtd_dataflash", -// .chip_select = 3, -// .max_speed_hz = 15 * 1000 * 1000, -// }, -// #endif -// }; - #define PICOTUX200_FLASH_BASE AT91_CHIPSELECT_0 #define PICOTUX200_FLASH_SIZE SZ_4M @@ -135,21 +112,11 @@ static void __init picotux200_board_init(void) at91_add_device_eth(&picotux200_eth_data); /* USB Host */ at91_add_device_usbh(&picotux200_usbh_data); - /* USB Device */ - // at91_add_device_udc(&picotux200_udc_data); - // at91_set_multi_drive(picotux200_udc_data.pullup_pin, 1); /* pullup_pin is connected to reset */ /* I2C */ at91_add_device_i2c(NULL, 0); - /* SPI */ - // at91_add_device_spi(picotux200_spi_devices, ARRAY_SIZE(picotux200_spi_devices)); -#ifdef CONFIG_MTD_AT91_DATAFLASH_CARD - /* DataFlash card */ - at91_set_gpio_output(AT91_PIN_PB22, 0); -#else /* MMC */ at91_set_gpio_output(AT91_PIN_PB22, 1); /* this MMC card slot can optionally use SPI signaling (CS3). */ at91_add_device_mmc(0, &picotux200_mmc_data); -#endif /* NOR Flash */ platform_device_register(&picotux200_flash); } diff --git a/arch/arm/mach-at91/board-dk.c b/arch/arm/mach-at91/board-rm9200dk.c index e14f0e165680..4c1047c8200d 100644 --- a/arch/arm/mach-at91/board-dk.c +++ b/arch/arm/mach-at91/board-rm9200dk.c @@ -1,5 +1,5 @@ /* - * linux/arch/arm/mach-at91/board-dk.c + * linux/arch/arm/mach-at91/board-rm9200dk.c * * Copyright (C) 2005 SAN People * @@ -91,10 +91,12 @@ static struct at91_cf_data __initdata dk_cf_data = { // .vcc_pin = ... always powered }; +#ifndef CONFIG_MTD_AT91_DATAFLASH_CARD static struct at91_mmc_data __initdata dk_mmc_data = { .slot_b = 0, .wire4 = 1, }; +#endif static struct spi_board_info dk_spi_devices[] = { { /* DataFlash chip */ diff --git a/arch/arm/mach-at91/board-ek.c b/arch/arm/mach-at91/board-rm9200ek.c index 56e92c4bbc2a..9df1be8818c0 100644 --- a/arch/arm/mach-at91/board-ek.c +++ b/arch/arm/mach-at91/board-rm9200ek.c @@ -1,5 +1,5 @@ /* - * linux/arch/arm/mach-at91/board-ek.c + * linux/arch/arm/mach-at91/board-rm9200ek.c * * Copyright (C) 2005 SAN People * @@ -84,12 +84,14 @@ static struct at91_udc_data __initdata ek_udc_data = { .pullup_pin = AT91_PIN_PD5, }; +#ifndef CONFIG_MTD_AT91_DATAFLASH_CARD static struct at91_mmc_data __initdata ek_mmc_data = { .det_pin = AT91_PIN_PB27, .slot_b = 0, .wire4 = 1, .wp_pin = AT91_PIN_PA17, }; +#endif static struct spi_board_info ek_spi_devices[] = { { /* DataFlash chip */ diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c index 5206eef4a67e..f8902b118960 100644 --- a/arch/arm/mach-at91/board-stamp9g20.c +++ b/arch/arm/mach-at91/board-stamp9g20.c @@ -32,7 +32,7 @@ #include "generic.h" -static void __init portuxg20_map_io(void) +void __init stamp9g20_map_io(void) { /* Initialize processor: 18.432 MHz crystal */ at91sam9260_initialize(18432000); @@ -40,6 +40,24 @@ static void __init portuxg20_map_io(void) /* DGBU on ttyS0. (Rx & Tx only) */ at91_register_uart(0, 0, 0); + /* set serial console to ttyS0 (ie, DBGU) */ + at91_set_serial_console(0); +} + +static void __init stamp9g20evb_map_io(void) +{ + stamp9g20_map_io(); + + /* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */ + at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS + | ATMEL_UART_DTR | ATMEL_UART_DSR + | ATMEL_UART_DCD | ATMEL_UART_RI); +} + +static void __init portuxg20_map_io(void) +{ + stamp9g20_map_io(); + /* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */ at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS | ATMEL_UART_DTR | ATMEL_UART_DSR @@ -56,26 +74,6 @@ static void __init portuxg20_map_io(void) /* USART5 on ttyS6. (Rx, Tx only) */ at91_register_uart(AT91SAM9260_ID_US5, 6, 0); - - /* set serial console to ttyS0 (ie, DBGU) */ - at91_set_serial_console(0); -} - -static void __init stamp9g20_map_io(void) -{ - /* Initialize processor: 18.432 MHz crystal */ - at91sam9260_initialize(18432000); - - /* DGBU on ttyS0. (Rx & Tx only) */ - at91_register_uart(0, 0, 0); - - /* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */ - at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS - | ATMEL_UART_DTR | ATMEL_UART_DSR - | ATMEL_UART_DCD | ATMEL_UART_RI); - - /* set serial console to ttyS0 (ie, DBGU) */ - at91_set_serial_console(0); } static void __init init_irq(void) @@ -156,7 +154,7 @@ static struct at91_udc_data __initdata portuxg20_udc_data = { .pullup_pin = 0, /* pull-up driven by UDC */ }; -static struct at91_udc_data __initdata stamp9g20_udc_data = { +static struct at91_udc_data __initdata stamp9g20evb_udc_data = { .vbus_pin = AT91_PIN_PA22, .pullup_pin = 0, /* pull-up driven by UDC */ }; @@ -190,7 +188,7 @@ static struct gpio_led portuxg20_leds[] = { } }; -static struct gpio_led stamp9g20_leds[] = { +static struct gpio_led stamp9g20evb_leds[] = { { .name = "D8", .gpio = AT91_PIN_PB18, @@ -250,7 +248,7 @@ void add_w1(void) } -static void __init generic_board_init(void) +void __init stamp9g20_board_init(void) { /* Serial */ at91_add_device_serial(); @@ -262,34 +260,40 @@ static void __init generic_board_init(void) #else at91_add_device_mmc(0, &mmc_data); #endif - /* USB Host */ - at91_add_device_usbh(&usbh_data); - /* Ethernet */ - at91_add_device_eth(&macb_data); - /* I2C */ - at91_add_device_i2c(NULL, 0); /* W1 */ add_w1(); } static void __init portuxg20_board_init(void) { - generic_board_init(); - /* SPI */ - at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices)); + stamp9g20_board_init(); + /* USB Host */ + at91_add_device_usbh(&usbh_data); /* USB Device */ at91_add_device_udc(&portuxg20_udc_data); + /* Ethernet */ + at91_add_device_eth(&macb_data); + /* I2C */ + at91_add_device_i2c(NULL, 0); + /* SPI */ + at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices)); /* LEDs */ at91_gpio_leds(portuxg20_leds, ARRAY_SIZE(portuxg20_leds)); } -static void __init stamp9g20_board_init(void) +static void __init stamp9g20evb_board_init(void) { - generic_board_init(); + stamp9g20_board_init(); + /* USB Host */ + at91_add_device_usbh(&usbh_data); /* USB Device */ - at91_add_device_udc(&stamp9g20_udc_data); + at91_add_device_udc(&stamp9g20evb_udc_data); + /* Ethernet */ + at91_add_device_eth(&macb_data); + /* I2C */ + at91_add_device_i2c(NULL, 0); /* LEDs */ - at91_gpio_leds(stamp9g20_leds, ARRAY_SIZE(stamp9g20_leds)); + at91_gpio_leds(stamp9g20evb_leds, ARRAY_SIZE(stamp9g20evb_leds)); } MACHINE_START(PORTUXG20, "taskit PortuxG20") @@ -305,7 +309,7 @@ MACHINE_START(STAMP9G20, "taskit Stamp9G20") /* Maintainer: taskit GmbH */ .boot_params = AT91_SDRAM_BASE + 0x100, .timer = &at91sam926x_timer, - .map_io = stamp9g20_map_io, + .map_io = stamp9g20evb_map_io, .init_irq = init_irq, - .init_machine = stamp9g20_board_init, + .init_machine = stamp9g20evb_board_init, MACHINE_END diff --git a/arch/arm/mach-at91/board-yl-9200.c b/arch/arm/mach-at91/board-yl-9200.c index 89df00a9d2f7..e0f0080eb639 100644 --- a/arch/arm/mach-at91/board-yl-9200.c +++ b/arch/arm/mach-at91/board-yl-9200.c @@ -387,7 +387,7 @@ static struct spi_board_info yl9200_spi_devices[] = { * EPSON S1D13806 FB (discontinued chip) * EPSON S1D13506 FB */ -#if defined(CONFIG_FB_S1D135XX) || defined(CONFIG_FB_S1D13XXX_MODULE) +#if defined(CONFIG_FB_S1D13XXX) || defined(CONFIG_FB_S1D13XXX_MODULE) #include <video/s1d13xxxfb.h> diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index 7525cee3983f..9113da6845f1 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -658,7 +658,7 @@ static void __init at91_upll_usbfs_clock_init(unsigned long main_clock) /* Now set uhpck values */ uhpck.parent = &utmi_clk; uhpck.pmc_mask = AT91SAM926x_PMC_UHP; - uhpck.rate_hz = utmi_clk.parent->rate_hz; + uhpck.rate_hz = utmi_clk.rate_hz; uhpck.rate_hz /= 1 + ((at91_sys_read(AT91_PMC_USB) & AT91_PMC_OHCIUSBDIV) >> 8); } diff --git a/arch/arm/mach-at91/include/mach/at91_mci.h b/arch/arm/mach-at91/include/mach/at91_mci.h index 57f8ee154943..27ac6f550fe3 100644 --- a/arch/arm/mach-at91/include/mach/at91_mci.h +++ b/arch/arm/mach-at91/include/mach/at91_mci.h @@ -74,6 +74,8 @@ #define AT91_MCI_TRTYP_BLOCK (0 << 19) #define AT91_MCI_TRTYP_MULTIPLE (1 << 19) #define AT91_MCI_TRTYP_STREAM (2 << 19) +#define AT91_MCI_TRTYP_SDIO_BYTE (4 << 19) +#define AT91_MCI_TRTYP_SDIO_BLOCK (5 << 19) #define AT91_MCI_BLKR 0x18 /* Block Register */ #define AT91_MCI_BLKR_BCNT(n) ((0xffff & (n)) << 0) /* Block count */ diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h index 58528aa9c8a8..2b499eb343a1 100644 --- a/arch/arm/mach-at91/include/mach/board.h +++ b/arch/arm/mach-at91/include/mach/board.h @@ -137,13 +137,7 @@ extern void __init at91_add_device_spi(struct spi_board_info *devices, int nr_de extern void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins); extern void __init at91_set_serial_console(unsigned portnr); -struct at91_uart_config { - unsigned short console_tty; /* tty number of serial console */ - unsigned short nr_tty; /* number of serial tty's */ - short tty_map[]; /* map UART to tty number */ -}; extern struct platform_device *atmel_default_console_device; -extern void __init __deprecated at91_init_serial(struct at91_uart_config *config); struct atmel_uart_data { short use_dma_tx; /* use transmit DMA? */ diff --git a/arch/arm/mach-at91/include/mach/stamp9g20.h b/arch/arm/mach-at91/include/mach/stamp9g20.h new file mode 100644 index 000000000000..6120f9c46d59 --- /dev/null +++ b/arch/arm/mach-at91/include/mach/stamp9g20.h @@ -0,0 +1,7 @@ +#ifndef __MACH_STAMP9G20_H +#define __MACH_STAMP9G20_H + +void stamp9g20_map_io(void); +void stamp9g20_board_init(void); + +#endif diff --git a/arch/arm/mach-bcmring/include/mach/vmalloc.h b/arch/arm/mach-bcmring/include/mach/vmalloc.h index 3db3a09fd398..7397bd7817d9 100644 --- a/arch/arm/mach-bcmring/include/mach/vmalloc.h +++ b/arch/arm/mach-bcmring/include/mach/vmalloc.h @@ -22,4 +22,4 @@ * 0xe0000000 to 0xefffffff. This gives us 256 MB of vm space and handles * larger physical memory designs better. */ -#define VMALLOC_END 0xf0000000 +#define VMALLOC_END 0xf0000000UL diff --git a/arch/arm/mach-clps711x/include/mach/vmalloc.h b/arch/arm/mach-clps711x/include/mach/vmalloc.h index 30b3a287ed88..467b96137e47 100644 --- a/arch/arm/mach-clps711x/include/mach/vmalloc.h +++ b/arch/arm/mach-clps711x/include/mach/vmalloc.h @@ -17,4 +17,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 38088c36936c..78defd71a829 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -369,7 +369,7 @@ static int __init cns3xxx_pcie_init(void) { int i; - hook_fault_code(16 + 6, cns3xxx_pcie_abort_handler, SIGBUS, + hook_fault_code(16 + 6, cns3xxx_pcie_abort_handler, SIGBUS, 0, "imprecise external abort"); for (i = 0; i < ARRAY_SIZE(cns3xxx_pcie); i++) { diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c index 9be261beae7d..2652af124acd 100644 --- a/arch/arm/mach-davinci/dm355.c +++ b/arch/arm/mach-davinci/dm355.c @@ -359,8 +359,8 @@ static struct clk_lookup dm355_clks[] = { CLK(NULL, "uart1", &uart1_clk), CLK(NULL, "uart2", &uart2_clk), CLK("i2c_davinci.1", NULL, &i2c_clk), - CLK("davinci-asp.0", NULL, &asp0_clk), - CLK("davinci-asp.1", NULL, &asp1_clk), + CLK("davinci-mcbsp.0", NULL, &asp0_clk), + CLK("davinci-mcbsp.1", NULL, &asp1_clk), CLK("davinci_mmc.0", NULL, &mmcsd0_clk), CLK("davinci_mmc.1", NULL, &mmcsd1_clk), CLK("spi_davinci.0", NULL, &spi0_clk), @@ -664,7 +664,7 @@ static struct resource dm355_asp1_resources[] = { }; static struct platform_device dm355_asp1_device = { - .name = "davinci-asp", + .name = "davinci-mcbsp", .id = 1, .num_resources = ARRAY_SIZE(dm355_asp1_resources), .resource = dm355_asp1_resources, diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index a12065e87266..c466d710d3c1 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -459,7 +459,7 @@ static struct clk_lookup dm365_clks[] = { CLK(NULL, "usb", &usb_clk), CLK("davinci_emac.1", NULL, &emac_clk), CLK("davinci_voicecodec", NULL, &voicecodec_clk), - CLK("davinci-asp.0", NULL, &asp0_clk), + CLK("davinci-mcbsp", NULL, &asp0_clk), CLK(NULL, "rto", &rto_clk), CLK(NULL, "mjcp", &mjcp_clk), CLK(NULL, NULL, NULL), @@ -922,8 +922,8 @@ static struct resource dm365_asp_resources[] = { }; static struct platform_device dm365_asp_device = { - .name = "davinci-asp", - .id = 0, + .name = "davinci-mcbsp", + .id = -1, .num_resources = ARRAY_SIZE(dm365_asp_resources), .resource = dm365_asp_resources, }; diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c index 0608dd776a16..9a2376b3137c 100644 --- a/arch/arm/mach-davinci/dm644x.c +++ b/arch/arm/mach-davinci/dm644x.c @@ -302,7 +302,7 @@ static struct clk_lookup dm644x_clks[] = { CLK("davinci_emac.1", NULL, &emac_clk), CLK("i2c_davinci.1", NULL, &i2c_clk), CLK("palm_bk3710", NULL, &ide_clk), - CLK("davinci-asp", NULL, &asp_clk), + CLK("davinci-mcbsp", NULL, &asp_clk), CLK("davinci_mmc.0", NULL, &mmcsd_clk), CLK(NULL, "spi", &spi_clk), CLK(NULL, "gpio", &gpio_clk), @@ -580,7 +580,7 @@ static struct resource dm644x_asp_resources[] = { }; static struct platform_device dm644x_asp_device = { - .name = "davinci-asp", + .name = "davinci-mcbsp", .id = -1, .num_resources = ARRAY_SIZE(dm644x_asp_resources), .resource = dm644x_asp_resources, diff --git a/arch/arm/mach-ebsa110/include/mach/vmalloc.h b/arch/arm/mach-ebsa110/include/mach/vmalloc.h index 60bde56fba4c..ea141b7a3e03 100644 --- a/arch/arm/mach-ebsa110/include/mach/vmalloc.h +++ b/arch/arm/mach-ebsa110/include/mach/vmalloc.h @@ -7,4 +7,4 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#define VMALLOC_END 0xdf000000 +#define VMALLOC_END 0xdf000000UL diff --git a/arch/arm/mach-footbridge/include/mach/vmalloc.h b/arch/arm/mach-footbridge/include/mach/vmalloc.h index 0ffbb7c85e59..40ba78e5782b 100644 --- a/arch/arm/mach-footbridge/include/mach/vmalloc.h +++ b/arch/arm/mach-footbridge/include/mach/vmalloc.h @@ -7,4 +7,4 @@ */ -#define VMALLOC_END 0xf0000000 +#define VMALLOC_END 0xf0000000UL diff --git a/arch/arm/mach-h720x/include/mach/vmalloc.h b/arch/arm/mach-h720x/include/mach/vmalloc.h index a45915b88756..8520b4a4d4e6 100644 --- a/arch/arm/mach-h720x/include/mach/vmalloc.h +++ b/arch/arm/mach-h720x/include/mach/vmalloc.h @@ -5,6 +5,6 @@ #ifndef __ARCH_ARM_VMALLOC_H #define __ARCH_ARM_VMALLOC_H -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL #endif diff --git a/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c b/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c index 026263c665ca..7e1e9dc2c8fc 100644 --- a/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c +++ b/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c @@ -250,9 +250,6 @@ static const struct imxuart_platform_data uart_pdata __initconst = { .flags = IMXUART_HAVE_RTSCTS, }; -#if defined(CONFIG_TOUCHSCREEN_ADS7846) \ - || defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE) - #define ADS7846_PENDOWN (GPIO_PORTD | 25) static void ads7846_dev_init(void) @@ -273,9 +270,7 @@ static struct ads7846_platform_data ads7846_config __initdata = { .get_pendown_state = ads7846_get_pendown_state, .keep_vref_on = 1, }; -#endif -#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE) static struct spi_board_info eukrea_mbimx27_spi_board_info[] __initdata = { [0] = { .modalias = "ads7846", @@ -294,7 +289,6 @@ static const struct spi_imx_master eukrea_mbimx27_spi0_data __initconst = { .chipselect = eukrea_mbimx27_spi_cs, .num_chipselect = ARRAY_SIZE(eukrea_mbimx27_spi_cs), }; -#endif static struct i2c_board_info eukrea_mbimx27_i2c_devices[] = { { diff --git a/arch/arm/mach-integrator/include/mach/vmalloc.h b/arch/arm/mach-integrator/include/mach/vmalloc.h index e056e7cf5645..2f5a2bafb11f 100644 --- a/arch/arm/mach-integrator/include/mach/vmalloc.h +++ b/arch/arm/mach-integrator/include/mach/vmalloc.h @@ -17,4 +17,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 24498a932ba6..a54b3db80366 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -513,4 +513,4 @@ int dma_set_coherent_mask(struct device *dev, u64 mask) EXPORT_SYMBOL(ixp4xx_pci_read); EXPORT_SYMBOL(ixp4xx_pci_write); - +EXPORT_SYMBOL(dma_set_coherent_mask); diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c index daf3993349f8..2e3dd08ccc3f 100644 --- a/arch/arm/mach-mmp/mmp2.c +++ b/arch/arm/mach-mmp/mmp2.c @@ -126,7 +126,6 @@ static APBC_CLK(twsi3, MMP2_TWSI3, 0, 26000000); static APBC_CLK(twsi4, MMP2_TWSI4, 0, 26000000); static APBC_CLK(twsi5, MMP2_TWSI5, 0, 26000000); static APBC_CLK(twsi6, MMP2_TWSI6, 0, 26000000); -static APBC_CLK(rtc, MMP2_RTC, 0, 32768); static APMU_CLK(nand, NAND, 0xbf, 100000000); diff --git a/arch/arm/mach-msm/include/mach/vmalloc.h b/arch/arm/mach-msm/include/mach/vmalloc.h index 31a32ad062dc..d138448eff16 100644 --- a/arch/arm/mach-msm/include/mach/vmalloc.h +++ b/arch/arm/mach-msm/include/mach/vmalloc.h @@ -16,7 +16,7 @@ #ifndef __ASM_ARCH_MSM_VMALLOC_H #define __ASM_ARCH_MSM_VMALLOC_H -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL #endif diff --git a/arch/arm/mach-mx25/devices-imx25.h b/arch/arm/mach-mx25/devices-imx25.h index 93afa10b13cf..d94d282fa676 100644 --- a/arch/arm/mach-mx25/devices-imx25.h +++ b/arch/arm/mach-mx25/devices-imx25.h @@ -42,9 +42,9 @@ extern const struct imx_mxc_nand_data imx25_mxc_nand_data __initconst; #define imx25_add_mxc_nand(pdata) \ imx_add_mxc_nand(&imx25_mxc_nand_data, pdata) -extern const struct imx_spi_imx_data imx25_spi_imx_data[] __initconst; +extern const struct imx_spi_imx_data imx25_cspi_data[] __initconst; #define imx25_add_spi_imx(id, pdata) \ - imx_add_spi_imx(&imx25_spi_imx_data[id], pdata) + imx_add_spi_imx(&imx25_cspi_data[id], pdata) #define imx25_add_spi_imx0(pdata) imx25_add_spi_imx(0, pdata) #define imx25_add_spi_imx1(pdata) imx25_add_spi_imx(1, pdata) #define imx25_add_spi_imx2(pdata) imx25_add_spi_imx(2, pdata) diff --git a/arch/arm/mach-mx3/mach-pcm037_eet.c b/arch/arm/mach-mx3/mach-pcm037_eet.c index 99e0894e07db..fda56545d2fd 100644 --- a/arch/arm/mach-mx3/mach-pcm037_eet.c +++ b/arch/arm/mach-mx3/mach-pcm037_eet.c @@ -14,6 +14,7 @@ #include <mach/common.h> #include <mach/iomux-mx3.h> +#include <mach/spi.h> #include <asm/mach-types.h> @@ -59,14 +60,12 @@ static struct spi_board_info pcm037_spi_dev[] = { }; /* Platform Data for MXC CSPI */ -#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE) static int pcm037_spi1_cs[] = {MXC_SPI_CS(1), IOMUX_TO_GPIO(MX31_PIN_KEY_COL7)}; static const struct spi_imx_master pcm037_spi1_pdata __initconst = { .chipselect = pcm037_spi1_cs, .num_chipselect = ARRAY_SIZE(pcm037_spi1_cs), }; -#endif /* GPIO-keys input device */ static struct gpio_keys_button pcm037_gpio_keys[] = { @@ -171,7 +170,7 @@ static struct platform_device pcm037_gpio_keys_device = { }, }; -static int eet_init_devices(void) +static int __init eet_init_devices(void) { if (!machine_is_pcm037() || pcm037_variant() != PCM037_EET) return 0; diff --git a/arch/arm/mach-netx/include/mach/vmalloc.h b/arch/arm/mach-netx/include/mach/vmalloc.h index 7cca3574308f..871f1ef7bff5 100644 --- a/arch/arm/mach-netx/include/mach/vmalloc.h +++ b/arch/arm/mach-netx/include/mach/vmalloc.h @@ -16,4 +16,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL diff --git a/arch/arm/mach-omap1/include/mach/vmalloc.h b/arch/arm/mach-omap1/include/mach/vmalloc.h index b001f67d695b..22ec4a479577 100644 --- a/arch/arm/mach-omap1/include/mach/vmalloc.h +++ b/arch/arm/mach-omap1/include/mach/vmalloc.h @@ -17,4 +17,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xd8000000 +#define VMALLOC_END 0xd8000000UL diff --git a/arch/arm/mach-omap2/board-zoom-peripherals.c b/arch/arm/mach-omap2/board-zoom-peripherals.c index 86c9b2102952..9db9203667df 100644 --- a/arch/arm/mach-omap2/board-zoom-peripherals.c +++ b/arch/arm/mach-omap2/board-zoom-peripherals.c @@ -216,7 +216,7 @@ static struct omap2_hsmmc_info mmc[] __initdata = { { .name = "wl1271", .mmc = 3, - .caps = MMC_CAP_4_BIT_DATA, + .caps = MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD, .gpio_wp = -EINVAL, .gpio_cd = -EINVAL, .nonremovable = true, diff --git a/arch/arm/mach-omap2/include/mach/vmalloc.h b/arch/arm/mach-omap2/include/mach/vmalloc.h index 4da31e997efe..866319947760 100644 --- a/arch/arm/mach-omap2/include/mach/vmalloc.h +++ b/arch/arm/mach-omap2/include/mach/vmalloc.h @@ -17,4 +17,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xf8000000 +#define VMALLOC_END 0xf8000000UL diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 40562ddd3ee4..a1939b1e6f82 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -297,7 +297,7 @@ static int __init _omap2_init_reprogram_sdrc(void) return 0; dpll3_m2_ck = clk_get(NULL, "dpll3_m2_ck"); - if (!dpll3_m2_ck) + if (IS_ERR(dpll3_m2_ck)) return -EINVAL; rate = clk_get_rate(dpll3_m2_ck); diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c index 5e81517a7af2..a8afb610c7d8 100644 --- a/arch/arm/mach-omap2/pm-debug.c +++ b/arch/arm/mach-omap2/pm-debug.c @@ -161,6 +161,23 @@ void omap2_pm_dump(int mode, int resume, unsigned int us) printk(KERN_INFO "%-20s: 0x%08x\n", regs[i].name, regs[i].val); } +void omap2_pm_wakeup_on_timer(u32 seconds, u32 milliseconds) +{ + u32 tick_rate, cycles; + + if (!seconds && !milliseconds) + return; + + tick_rate = clk_get_rate(omap_dm_timer_get_fclk(gptimer_wakeup)); + cycles = tick_rate * seconds + tick_rate * milliseconds / 1000; + omap_dm_timer_stop(gptimer_wakeup); + omap_dm_timer_set_load_start(gptimer_wakeup, 0, 0xffffffff - cycles); + + pr_info("PM: Resume timer in %u.%03u secs" + " (%d ticks at %d ticks/sec.)\n", + seconds, milliseconds, cycles, tick_rate); +} + #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -354,23 +371,6 @@ void pm_dbg_update_time(struct powerdomain *pwrdm, int prev) pwrdm->timer = t; } -void omap2_pm_wakeup_on_timer(u32 seconds, u32 milliseconds) -{ - u32 tick_rate, cycles; - - if (!seconds && !milliseconds) - return; - - tick_rate = clk_get_rate(omap_dm_timer_get_fclk(gptimer_wakeup)); - cycles = tick_rate * seconds + tick_rate * milliseconds / 1000; - omap_dm_timer_stop(gptimer_wakeup); - omap_dm_timer_set_load_start(gptimer_wakeup, 0, 0xffffffff - cycles); - - pr_info("PM: Resume timer in %u.%03u secs" - " (%d ticks at %d ticks/sec.)\n", - seconds, milliseconds, cycles, tick_rate); -} - static int clkdm_dbg_show_counter(struct clockdomain *clkdm, void *user) { struct seq_file *s = (struct seq_file *)user; diff --git a/arch/arm/mach-omap2/pm24xx.c b/arch/arm/mach-omap2/pm24xx.c index a40457d81927..aaeea49b9bdd 100644 --- a/arch/arm/mach-omap2/pm24xx.c +++ b/arch/arm/mach-omap2/pm24xx.c @@ -30,6 +30,7 @@ #include <linux/irq.h> #include <linux/time.h> #include <linux/gpio.h> +#include <linux/console.h> #include <asm/mach/time.h> #include <asm/mach/irq.h> @@ -52,6 +53,19 @@ #include <plat/powerdomain.h> #include <plat/clockdomain.h> +#ifdef CONFIG_SUSPEND +static suspend_state_t suspend_state = PM_SUSPEND_ON; +static inline bool is_suspending(void) +{ + return (suspend_state != PM_SUSPEND_ON); +} +#else +static inline bool is_suspending(void) +{ + return false; +} +#endif + static void (*omap2_sram_idle)(void); static void (*omap2_sram_suspend)(u32 dllctrl, void __iomem *sdrc_dlla_ctrl, void __iomem *sdrc_power); @@ -118,6 +132,11 @@ static void omap2_enter_full_retention(void) if (omap_irq_pending()) goto no_sleep; + /* Block console output in case it is on one of the OMAP UARTs */ + if (!is_suspending()) + if (try_acquire_console_sem()) + goto no_sleep; + omap_uart_prepare_idle(0); omap_uart_prepare_idle(1); omap_uart_prepare_idle(2); @@ -131,6 +150,9 @@ static void omap2_enter_full_retention(void) omap_uart_resume_idle(1); omap_uart_resume_idle(0); + if (!is_suspending()) + release_console_sem(); + no_sleep: if (omap2_pm_debug) { unsigned long long tmp; @@ -277,6 +299,12 @@ out: local_irq_enable(); } +static int omap2_pm_begin(suspend_state_t state) +{ + suspend_state = state; + return 0; +} + static int omap2_pm_prepare(void) { /* We cannot sleep in idle until we have resumed */ @@ -326,10 +354,17 @@ static void omap2_pm_finish(void) enable_hlt(); } +static void omap2_pm_end(void) +{ + suspend_state = PM_SUSPEND_ON; +} + static struct platform_suspend_ops omap_pm_ops = { + .begin = omap2_pm_begin, .prepare = omap2_pm_prepare, .enter = omap2_pm_enter, .finish = omap2_pm_finish, + .end = omap2_pm_end, .valid = suspend_valid_only_mem, }; diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 75c0cd13ad8e..648b8c50d024 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -28,6 +28,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/slab.h> +#include <linux/console.h> #include <plat/sram.h> #include <plat/clockdomain.h> @@ -49,6 +50,19 @@ #include "sdrc.h" #include "control.h" +#ifdef CONFIG_SUSPEND +static suspend_state_t suspend_state = PM_SUSPEND_ON; +static inline bool is_suspending(void) +{ + return (suspend_state != PM_SUSPEND_ON); +} +#else +static inline bool is_suspending(void) +{ + return false; +} +#endif + /* Scratchpad offsets */ #define OMAP343X_TABLE_ADDRESS_OFFSET 0xc4 #define OMAP343X_TABLE_VALUE_OFFSET 0xc0 @@ -385,6 +399,13 @@ void omap_sram_idle(void) omap3_enable_io_chain(); } + /* Block console output in case it is on one of the OMAP UARTs */ + if (!is_suspending()) + if (per_next_state < PWRDM_POWER_ON || + core_next_state < PWRDM_POWER_ON) + if (try_acquire_console_sem()) + goto console_still_active; + /* PER */ if (per_next_state < PWRDM_POWER_ON) { omap_uart_prepare_idle(2); @@ -463,6 +484,10 @@ void omap_sram_idle(void) omap_uart_resume_idle(3); } + if (!is_suspending()) + release_console_sem(); + +console_still_active: /* Disable IO-PAD and IO-CHAIN wakeup */ if (omap3_has_io_wakeup() && (per_next_state < PWRDM_POWER_ON || @@ -504,8 +529,6 @@ out: } #ifdef CONFIG_SUSPEND -static suspend_state_t suspend_state; - static int omap3_pm_prepare(void) { disable_hlt(); diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h index 298a22a754e2..f81acee4738d 100644 --- a/arch/arm/mach-omap2/prcm-common.h +++ b/arch/arm/mach-omap2/prcm-common.h @@ -243,13 +243,14 @@ #define OMAP24XX_EN_GPT1_MASK (1 << 0) /* PM_WKST_WKUP, CM_IDLEST_WKUP shared bits */ -#define OMAP24XX_ST_GPIOS_SHIFT (1 << 2) -#define OMAP24XX_ST_GPIOS_MASK 2 -#define OMAP24XX_ST_GPT1_SHIFT (1 << 0) -#define OMAP24XX_ST_GPT1_MASK 0 +#define OMAP24XX_ST_GPIOS_SHIFT 2 +#define OMAP24XX_ST_GPIOS_MASK (1 << 2) +#define OMAP24XX_ST_GPT1_SHIFT 0 +#define OMAP24XX_ST_GPT1_MASK (1 << 0) /* CM_IDLEST_MDM and PM_WKST_MDM shared bits */ -#define OMAP2430_ST_MDM_SHIFT (1 << 0) +#define OMAP2430_ST_MDM_SHIFT 0 +#define OMAP2430_ST_MDM_MASK (1 << 0) /* 3430 register bits shared between CM & PRM registers */ diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c index becf0e38ef7e..d17960a1be25 100644 --- a/arch/arm/mach-omap2/serial.c +++ b/arch/arm/mach-omap2/serial.c @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/serial_8250.h> #include <linux/pm_runtime.h> +#include <linux/console.h> #ifdef CONFIG_SERIAL_OMAP #include <plat/omap-serial.h> @@ -406,7 +407,7 @@ void omap_uart_resume_idle(int num) struct omap_uart_state *uart; list_for_each_entry(uart, &uart_list, node) { - if (num == uart->num) { + if (num == uart->num && uart->can_sleep) { omap_uart_enable_clocks(uart); /* Check for IO pad wakeup */ @@ -807,6 +808,8 @@ void __init omap_serial_init_port(int port) oh->dev_attr = uart; + acquire_console_sem(); /* in case the earlycon is on the UART */ + /* * Because of early UART probing, UART did not get idled * on init. Now that omap_device is ready, ensure full idle @@ -831,6 +834,8 @@ void __init omap_serial_init_port(int port) omap_uart_block_sleep(uart); uart->timeout = DEFAULT_TIMEOUT; + release_console_sem(); + if ((cpu_is_omap34xx() && uart->padconf) || (uart->wk_en && uart->wk_mask)) { device_init_wakeup(&od->pdev.dev, true); diff --git a/arch/arm/mach-pnx4008/include/mach/vmalloc.h b/arch/arm/mach-pnx4008/include/mach/vmalloc.h index 31b65ee07b0b..184913c71141 100644 --- a/arch/arm/mach-pnx4008/include/mach/vmalloc.h +++ b/arch/arm/mach-pnx4008/include/mach/vmalloc.h @@ -17,4 +17,4 @@ * The vmalloc() routines leaves a hole of 4kB between each vmalloced * area for the same reason. ;) */ -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index dd235ecc9d6c..c93e73d54dd1 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -540,6 +540,7 @@ config MACH_ICONTROL config ARCH_PXA_ESERIES bool "PXA based Toshiba e-series PDAs" select PXA25x + select FB_W100 config MACH_E330 bool "Toshiba e330" diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c index d2060a1d1d68..e5c9932b7588 100644 --- a/arch/arm/mach-pxa/palmtx.c +++ b/arch/arm/mach-pxa/palmtx.c @@ -241,7 +241,8 @@ static inline void palmtx_keys_init(void) {} /****************************************************************************** * NAND Flash ******************************************************************************/ -#if defined(CONFIG_MTD_NAND_GPIO) || defined(CONFIG_MTD_NAND_GPIO_MODULE) +#if defined(CONFIG_MTD_NAND_PLATFORM) || \ + defined(CONFIG_MTD_NAND_PLATFORM_MODULE) static void palmtx_nand_cmd_ctl(struct mtd_info *mtd, int cmd, unsigned int ctrl) { diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S index 52c30b01a671..ae008110db4e 100644 --- a/arch/arm/mach-pxa/sleep.S +++ b/arch/arm/mach-pxa/sleep.S @@ -353,8 +353,8 @@ resume_turn_on_mmu: @ Let us ensure we jump to resume_after_mmu only when the mcr above @ actually took effect. They call it the "cpwait" operation. - mrc p15, 0, r1, c2, c0, 0 @ queue a dependency on CP15 - sub pc, r2, r1, lsr #32 @ jump to virtual addr + mrc p15, 0, r0, c2, c0, 0 @ queue a dependency on CP15 + sub pc, r2, r0, lsr #32 @ jump to virtual addr nop nop nop diff --git a/arch/arm/mach-realview/headsmp.S b/arch/arm/mach-realview/headsmp.S index 4075473cf68a..b34be4554d40 100644 --- a/arch/arm/mach-realview/headsmp.S +++ b/arch/arm/mach-realview/headsmp.S @@ -35,5 +35,6 @@ pen: ldr r7, [r6] */ b secondary_startup + .align 1: .long . .long pen_release diff --git a/arch/arm/mach-rpc/include/mach/vmalloc.h b/arch/arm/mach-rpc/include/mach/vmalloc.h index 3bcd86fadb81..fb700228637a 100644 --- a/arch/arm/mach-rpc/include/mach/vmalloc.h +++ b/arch/arm/mach-rpc/include/mach/vmalloc.h @@ -7,4 +7,4 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#define VMALLOC_END 0xdc000000 +#define VMALLOC_END 0xdc000000UL diff --git a/arch/arm/mach-s3c2410/h1940-bluetooth.c b/arch/arm/mach-s3c2410/h1940-bluetooth.c index 8aa2f1902a94..6b86a722a7db 100644 --- a/arch/arm/mach-s3c2410/h1940-bluetooth.c +++ b/arch/arm/mach-s3c2410/h1940-bluetooth.c @@ -77,13 +77,13 @@ static int __devinit h1940bt_probe(struct platform_device *pdev) /* Configures BT serial port GPIOs */ s3c_gpio_cfgpin(S3C2410_GPH(0), S3C2410_GPH0_nCTS0); - s3c_gpio_cfgpull(S3C2410_GPH(0), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPH(0), S3C_GPIO_PULL_NONE); s3c_gpio_cfgpin(S3C2410_GPH(1), S3C2410_GPIO_OUTPUT); - s3c_gpio_cfgpull(S3C2410_GPH(1), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPH(1), S3C_GPIO_PULL_NONE); s3c_gpio_cfgpin(S3C2410_GPH(2), S3C2410_GPH2_TXD0); - s3c_gpio_cfgpull(S3C2410_GPH(2), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPH(2), S3C_GPIO_PULL_NONE); s3c_gpio_cfgpin(S3C2410_GPH(3), S3C2410_GPH3_RXD0); - s3c_gpio_cfgpull(S3C2410_GPH(3), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPH(3), S3C_GPIO_PULL_NONE); rfk = rfkill_alloc(DRV_NAME, &pdev->dev, RFKILL_TYPE_BLUETOOTH, diff --git a/arch/arm/mach-s3c2412/Kconfig b/arch/arm/mach-s3c2412/Kconfig index cef6a65637bd..6983cb4d4cae 100644 --- a/arch/arm/mach-s3c2412/Kconfig +++ b/arch/arm/mach-s3c2412/Kconfig @@ -16,7 +16,7 @@ config CPU_S3C2412 config CPU_S3C2412_ONLY bool depends on ARCH_S3C2410 && !CPU_S3C2400 && !CPU_S3C2410 && \ - !CPU_2416 && !CPU_S3C2440 && !CPU_S3C2442 && \ + !CPU_S3C2416 && !CPU_S3C2440 && !CPU_S3C2442 && \ !CPU_S3C2443 && CPU_S3C2412 default y if CPU_S3C2412 @@ -28,9 +28,16 @@ config S3C2412_DMA config S3C2412_PM bool + select S3C2412_PM_SLEEP help Internal config node to apply S3C2412 power management +config S3C2412_PM_SLEEP + bool + help + Internal config node to apply sleep for S3C2412 power management. + Can be selected by another SoCs with similar sleep procedure. + # Note, the S3C2412 IOtiming support is in plat-s3c24xx config S3C2412_CPUFREQ diff --git a/arch/arm/mach-s3c2412/Makefile b/arch/arm/mach-s3c2412/Makefile index 530ec46cbaea..6c48a91ea39e 100644 --- a/arch/arm/mach-s3c2412/Makefile +++ b/arch/arm/mach-s3c2412/Makefile @@ -14,7 +14,8 @@ obj-$(CONFIG_CPU_S3C2412) += irq.o obj-$(CONFIG_CPU_S3C2412) += clock.o obj-$(CONFIG_CPU_S3C2412) += gpio.o obj-$(CONFIG_S3C2412_DMA) += dma.o -obj-$(CONFIG_S3C2412_PM) += pm.o sleep.o +obj-$(CONFIG_S3C2412_PM) += pm.o +obj-$(CONFIG_S3C2412_PM_SLEEP) += sleep.o obj-$(CONFIG_S3C2412_CPUFREQ) += cpu-freq.o # Machine support diff --git a/arch/arm/mach-s3c2416/Kconfig b/arch/arm/mach-s3c2416/Kconfig index 87b9c9f003bd..df8d14974c90 100644 --- a/arch/arm/mach-s3c2416/Kconfig +++ b/arch/arm/mach-s3c2416/Kconfig @@ -27,6 +27,7 @@ config S3C2416_DMA config S3C2416_PM bool + select S3C2412_PM_SLEEP help Internal config node to apply S3C2416 power management @@ -35,9 +36,12 @@ menu "S3C2416 Machines" config MACH_SMDK2416 bool "SMDK2416" select CPU_S3C2416 + select MACH_SMDK select S3C_DEV_FB select S3C_DEV_HSMMC select S3C_DEV_HSMMC1 + select S3C_DEV_NAND + select S3C_DEV_USB_HOST select S3C2416_PM if PM help Say Y here if you are using an SMDK2416 diff --git a/arch/arm/mach-s3c2416/irq.c b/arch/arm/mach-s3c2416/irq.c index 084d121f368c..00174daf1526 100644 --- a/arch/arm/mach-s3c2416/irq.c +++ b/arch/arm/mach-s3c2416/irq.c @@ -168,12 +168,11 @@ static struct irq_chip s3c2416_irq_dma = { static void s3c2416_irq_demux_uart3(unsigned int irq, struct irq_desc *desc) { - s3c2416_irq_demux(IRQ_S3C2443_UART3, 3); + s3c2416_irq_demux(IRQ_S3C2443_RX3, 3); } #define INTMSK_UART3 (1UL << (IRQ_S3C2443_UART3 - IRQ_EINT0)) -#define SUBMSK_UART3 (0xf << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0))) - +#define SUBMSK_UART3 (0x7 << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0))) static void s3c2416_irq_uart3_mask(unsigned int irqno) { diff --git a/arch/arm/mach-s3c2440/Kconfig b/arch/arm/mach-s3c2440/Kconfig index ff024a6c0f85..a0cb2581894f 100644 --- a/arch/arm/mach-s3c2440/Kconfig +++ b/arch/arm/mach-s3c2440/Kconfig @@ -18,6 +18,7 @@ config CPU_S3C2440 config CPU_S3C2442 bool select CPU_ARM920T + select S3C_GPIO_PULL_DOWN select S3C2410_CLOCK select S3C2410_GPIO select S3C2410_PM if PM @@ -178,6 +179,9 @@ config MACH_MINI2440 bool "MINI2440 development board" select CPU_S3C2440 select EEPROM_AT24 + select NEW_LEDS + select LEDS_CLASS + select LEDS_TRIGGER select LEDS_TRIGGER_BACKLIGHT select S3C_DEV_NAND select S3C_DEV_USB_HOST diff --git a/arch/arm/mach-s3c2440/s3c2440.c b/arch/arm/mach-s3c2440/s3c2440.c index d50f3ae6173d..f7663f731ea0 100644 --- a/arch/arm/mach-s3c2440/s3c2440.c +++ b/arch/arm/mach-s3c2440/s3c2440.c @@ -46,9 +46,6 @@ int __init s3c2440_init(void) { printk("S3C2440: Initialising architecture\n"); - s3c24xx_gpiocfg_default.set_pull = s3c_gpio_setpull_1up; - s3c24xx_gpiocfg_default.get_pull = s3c_gpio_getpull_1up; - /* change irq for watchdog */ s3c_device_wdt.resource[1].start = IRQ_S3C2440_WDT; @@ -58,3 +55,11 @@ int __init s3c2440_init(void) return sysdev_register(&s3c2440_sysdev); } + +void __init s3c2440_map_io(void) +{ + s3c244x_map_io(); + + s3c24xx_gpiocfg_default.set_pull = s3c_gpio_setpull_1up; + s3c24xx_gpiocfg_default.get_pull = s3c_gpio_getpull_1up; +} diff --git a/arch/arm/mach-s3c2440/s3c2442.c b/arch/arm/mach-s3c2440/s3c2442.c index 188ad1e57dc0..ecf813546554 100644 --- a/arch/arm/mach-s3c2440/s3c2442.c +++ b/arch/arm/mach-s3c2440/s3c2442.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/mutex.h> +#include <linux/gpio.h> #include <linux/clk.h> #include <linux/io.h> @@ -43,6 +44,11 @@ #include <plat/clock.h> #include <plat/cpu.h> +#include <plat/s3c244x.h> + +#include <plat/gpio-core.h> +#include <plat/gpio-cfg.h> +#include <plat/gpio-cfg-helpers.h> /* S3C2442 extended clock support */ @@ -163,3 +169,11 @@ int __init s3c2442_init(void) return sysdev_register(&s3c2442_sysdev); } + +void __init s3c2442_map_io(void) +{ + s3c244x_map_io(); + + s3c24xx_gpiocfg_default.set_pull = s3c_gpio_setpull_1down; + s3c24xx_gpiocfg_default.get_pull = s3c_gpio_getpull_1down; +} diff --git a/arch/arm/mach-s3c2443/Kconfig b/arch/arm/mach-s3c2443/Kconfig index 4fef723126fa..31babec90cec 100644 --- a/arch/arm/mach-s3c2443/Kconfig +++ b/arch/arm/mach-s3c2443/Kconfig @@ -5,6 +5,7 @@ config CPU_S3C2443 bool depends on ARCH_S3C2410 + select CPU_ARM920T select S3C2443_DMA if S3C2410_DMA select CPU_LLSERIAL_S3C2440 select SAMSUNG_CLKSRC diff --git a/arch/arm/mach-s3c2443/irq.c b/arch/arm/mach-s3c2443/irq.c index 0e0d693f3974..893424767ce1 100644 --- a/arch/arm/mach-s3c2443/irq.c +++ b/arch/arm/mach-s3c2443/irq.c @@ -166,12 +166,11 @@ static struct irq_chip s3c2443_irq_dma = { static void s3c2443_irq_demux_uart3(unsigned int irq, struct irq_desc *desc) { - s3c2443_irq_demux(IRQ_S3C2443_UART3, 3); + s3c2443_irq_demux(IRQ_S3C2443_RX3, 3); } #define INTMSK_UART3 (1UL << (IRQ_S3C2443_UART3 - IRQ_EINT0)) -#define SUBMSK_UART3 (0xf << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0))) - +#define SUBMSK_UART3 (0x7 << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0))) static void s3c2443_irq_uart3_mask(unsigned int irqno) { diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c index 249c62956471..89f35e02e883 100644 --- a/arch/arm/mach-s3c64xx/mach-mini6410.c +++ b/arch/arm/mach-s3c64xx/mach-mini6410.c @@ -45,7 +45,7 @@ #include <video/platform_lcd.h> -#define UCON (S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK) +#define UCON S3C2410_UCON_DEFAULT #define ULCON (S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB) #define UFCON (S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE) diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c index f9ef9b5c5f5a..4957ab0a0d4a 100644 --- a/arch/arm/mach-s3c64xx/mach-real6410.c +++ b/arch/arm/mach-s3c64xx/mach-real6410.c @@ -46,7 +46,7 @@ #include <video/platform_lcd.h> -#define UCON (S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK) +#define UCON S3C2410_UCON_DEFAULT #define ULCON (S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB) #define UFCON (S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE) diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c index 28677caf3613..461aa035afc0 100644 --- a/arch/arm/mach-s5pv210/mach-aquila.c +++ b/arch/arm/mach-s5pv210/mach-aquila.c @@ -378,6 +378,12 @@ static struct max8998_regulator_data aquila_regulators[] = { static struct max8998_platform_data aquila_max8998_pdata = { .num_regulators = ARRAY_SIZE(aquila_regulators), .regulators = aquila_regulators, + .buck1_set1 = S5PV210_GPH0(3), + .buck1_set2 = S5PV210_GPH0(4), + .buck2_set3 = S5PV210_GPH0(5), + .buck1_max_voltage1 = 1200000, + .buck1_max_voltage2 = 1200000, + .buck2_max_voltage = 1200000, }; #endif diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c index b1dcf964a768..e22d5112fd44 100644 --- a/arch/arm/mach-s5pv210/mach-goni.c +++ b/arch/arm/mach-s5pv210/mach-goni.c @@ -518,6 +518,12 @@ static struct max8998_regulator_data goni_regulators[] = { static struct max8998_platform_data goni_max8998_pdata = { .num_regulators = ARRAY_SIZE(goni_regulators), .regulators = goni_regulators, + .buck1_set1 = S5PV210_GPH0(3), + .buck1_set2 = S5PV210_GPH0(4), + .buck2_set3 = S5PV210_GPH0(5), + .buck1_max_voltage1 = 1200000, + .buck1_max_voltage2 = 1200000, + .buck2_max_voltage = 1200000, }; #endif diff --git a/arch/arm/mach-s5pv210/mach-smdkc110.c b/arch/arm/mach-s5pv210/mach-smdkc110.c index 0ad7924fe62e..5dd1681c069e 100644 --- a/arch/arm/mach-s5pv210/mach-smdkc110.c +++ b/arch/arm/mach-s5pv210/mach-smdkc110.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/serial_core.h> #include <linux/i2c.h> +#include <linux/sysdev.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c index bcd7a5d53401..1fbc45b2a432 100644 --- a/arch/arm/mach-s5pv210/mach-smdkv210.c +++ b/arch/arm/mach-s5pv210/mach-smdkv210.c @@ -13,6 +13,7 @@ #include <linux/i2c.h> #include <linux/init.h> #include <linux/serial_core.h> +#include <linux/sysdev.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-shark/include/mach/vmalloc.h b/arch/arm/mach-shark/include/mach/vmalloc.h index 8e845b6a7cb5..b10df988526d 100644 --- a/arch/arm/mach-shark/include/mach/vmalloc.h +++ b/arch/arm/mach-shark/include/mach/vmalloc.h @@ -1,4 +1,4 @@ /* * arch/arm/mach-shark/include/mach/vmalloc.h */ -#define VMALLOC_END 0xd0000000 +#define VMALLOC_END 0xd0000000UL diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index d3260542b943..d440e5f456ad 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -567,38 +567,127 @@ static struct platform_device *qhd_devices[] __initdata = { /* FSI */ #define IRQ_FSI evt2irq(0x1840) +static int __fsi_set_rate(struct clk *clk, long rate, int enable) +{ + int ret = 0; + + if (rate <= 0) + return ret; + + if (enable) { + ret = clk_set_rate(clk, rate); + if (0 == ret) + ret = clk_enable(clk); + } else { + clk_disable(clk); + } + + return ret; +} + +static int __fsi_set_round_rate(struct clk *clk, long rate, int enable) +{ + return __fsi_set_rate(clk, clk_round_rate(clk, rate), enable); +} -static int fsi_set_rate(int is_porta, int rate) +static int fsi_ak4642_set_rate(struct device *dev, int rate, int enable) +{ + struct clk *fsia_ick; + struct clk *fsiack; + int ret = -EIO; + + fsia_ick = clk_get(dev, "icka"); + if (IS_ERR(fsia_ick)) + return PTR_ERR(fsia_ick); + + /* + * FSIACK is connected to AK4642, + * and use external clock pin from it. + * it is parent of fsia_ick now. + */ + fsiack = clk_get_parent(fsia_ick); + if (!fsiack) + goto fsia_ick_out; + + /* + * we get 1/1 divided clock by setting same rate to fsiack and fsia_ick + * + ** FIXME ** + * Because the freq_table of external clk (fsiack) are all 0, + * the return value of clk_round_rate became 0. + * So, it use __fsi_set_rate here. + */ + ret = __fsi_set_rate(fsiack, rate, enable); + if (ret < 0) + goto fsiack_out; + + ret = __fsi_set_round_rate(fsia_ick, rate, enable); + if ((ret < 0) && enable) + __fsi_set_round_rate(fsiack, rate, 0); /* disable FSI ACK */ + +fsiack_out: + clk_put(fsiack); + +fsia_ick_out: + clk_put(fsia_ick); + + return 0; +} + +static int fsi_hdmi_set_rate(struct device *dev, int rate, int enable) { struct clk *fsib_clk; struct clk *fdiv_clk = &sh7372_fsidivb_clk; + long fsib_rate = 0; + long fdiv_rate = 0; + int ackmd_bpfmd; int ret; - /* set_rate is not needed if port A */ - if (is_porta) - return 0; - - fsib_clk = clk_get(NULL, "fsib_clk"); - if (IS_ERR(fsib_clk)) - return -EINVAL; - switch (rate) { case 44100: - clk_set_rate(fsib_clk, clk_round_rate(fsib_clk, 11283000)); - ret = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64; + fsib_rate = rate * 256; + ackmd_bpfmd = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64; break; case 48000: - clk_set_rate(fsib_clk, clk_round_rate(fsib_clk, 85428000)); - clk_set_rate(fdiv_clk, clk_round_rate(fdiv_clk, 12204000)); - ret = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64; + fsib_rate = 85428000; /* around 48kHz x 256 x 7 */ + fdiv_rate = rate * 256; + ackmd_bpfmd = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64; break; default: pr_err("unsupported rate in FSI2 port B\n"); - ret = -EINVAL; - break; + return -EINVAL; } + /* FSI B setting */ + fsib_clk = clk_get(dev, "ickb"); + if (IS_ERR(fsib_clk)) + return -EIO; + + ret = __fsi_set_round_rate(fsib_clk, fsib_rate, enable); clk_put(fsib_clk); + if (ret < 0) + return ret; + + /* FSI DIV setting */ + ret = __fsi_set_round_rate(fdiv_clk, fdiv_rate, enable); + if (ret < 0) { + /* disable FSI B */ + if (enable) + __fsi_set_round_rate(fsib_clk, fsib_rate, 0); + return ret; + } + + return ackmd_bpfmd; +} + +static int fsi_set_rate(struct device *dev, int is_porta, int rate, int enable) +{ + int ret; + + if (is_porta) + ret = fsi_ak4642_set_rate(dev, rate, enable); + else + ret = fsi_hdmi_set_rate(dev, rate, enable); return ret; } @@ -880,6 +969,11 @@ static int __init hdmi_init_pm_clock(void) goto out; } + ret = clk_enable(&sh7372_pllc2_clk); + if (ret < 0) { + pr_err("Cannot enable pllc2 clock\n"); + goto out; + } pr_debug("PLLC2 set frequency %lu\n", rate); ret = clk_set_parent(hdmi_ick, &sh7372_pllc2_clk); @@ -896,23 +990,11 @@ out: device_initcall(hdmi_init_pm_clock); -#define FSIACK_DUMMY_RATE 48000 static int __init fsi_init_pm_clock(void) { struct clk *fsia_ick; int ret; - /* - * FSIACK is connected to AK4642, - * and the rate is depend on playing sound rate. - * So, set dummy rate (= 48k) here - */ - ret = clk_set_rate(&sh7372_fsiack_clk, FSIACK_DUMMY_RATE); - if (ret < 0) { - pr_err("Cannot set FSIACK dummy rate: %d\n", ret); - return ret; - } - fsia_ick = clk_get(&fsi_device.dev, "icka"); if (IS_ERR(fsia_ick)) { ret = PTR_ERR(fsia_ick); @@ -921,16 +1003,9 @@ static int __init fsi_init_pm_clock(void) } ret = clk_set_parent(fsia_ick, &sh7372_fsiack_clk); - if (ret < 0) { - pr_err("Cannot set FSI-A parent: %d\n", ret); - goto out; - } - - ret = clk_set_rate(fsia_ick, FSIACK_DUMMY_RATE); if (ret < 0) - pr_err("Cannot set FSI-A rate: %d\n", ret); + pr_err("Cannot set FSI-A parent: %d\n", ret); -out: clk_put(fsia_ick); return ret; diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index 7db31e6c6bf2..3aa026069435 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -220,8 +220,7 @@ static void pllc2_disable(struct clk *clk) __raw_writel(__raw_readl(PLLC2CR) & ~0x80000000, PLLC2CR); } -static int pllc2_set_rate(struct clk *clk, - unsigned long rate, int algo_id) +static int pllc2_set_rate(struct clk *clk, unsigned long rate) { unsigned long value; int idx; @@ -230,21 +229,13 @@ static int pllc2_set_rate(struct clk *clk, if (idx < 0) return idx; - if (rate == clk->parent->rate) { - pllc2_disable(clk); - return 0; - } + if (rate == clk->parent->rate) + return -EINVAL; value = __raw_readl(PLLC2CR) & ~(0x3f << 24); - if (value & 0x80000000) - pllc2_disable(clk); - __raw_writel((value & ~0x80000000) | ((idx + 19) << 24), PLLC2CR); - if (value & 0x80000000) - return pllc2_enable(clk); - return 0; } @@ -453,32 +444,24 @@ static int fsidiv_enable(struct clk *clk) unsigned long value; value = __raw_readl(clk->mapping->base) >> 16; - if (value < 2) { - fsidiv_disable(clk); - return -ENOENT; - } + if (value < 2) + return -EIO; __raw_writel((value << 16) | 0x3, clk->mapping->base); return 0; } -static int fsidiv_set_rate(struct clk *clk, - unsigned long rate, int algo_id) +static int fsidiv_set_rate(struct clk *clk, unsigned long rate) { int idx; - if (clk->parent->rate == rate) { - fsidiv_disable(clk); - return 0; - } - idx = (clk->parent->rate / rate) & 0xffff; if (idx < 2) - return -ENOENT; + return -EINVAL; __raw_writel(idx << 16, clk->mapping->base); - return fsidiv_enable(clk); + return 0; } static struct clk_ops fsidiv_clk_ops = { @@ -609,8 +592,6 @@ static struct clk_lookup lookups[] = { CLKDEV_CON_ID("vck3_clk", &div6_clks[DIV6_VCK3]), CLKDEV_CON_ID("fmsi_clk", &div6_clks[DIV6_FMSI]), CLKDEV_CON_ID("fmso_clk", &div6_clks[DIV6_FMSO]), - CLKDEV_CON_ID("fsia_clk", &div6_reparent_clks[DIV6_FSIA]), - CLKDEV_CON_ID("fsib_clk", &div6_reparent_clks[DIV6_FSIB]), CLKDEV_CON_ID("sub_clk", &div6_clks[DIV6_SUB]), CLKDEV_CON_ID("spu_clk", &div6_clks[DIV6_SPU]), CLKDEV_CON_ID("vou_clk", &div6_clks[DIV6_VOU]), @@ -647,8 +628,8 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */ CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI2 */ CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* IIC1 */ - CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP323]), /* USB0 */ - CLKDEV_DEV_ID("r8a66597_udc.0", &mstp_clks[MSTP323]), /* USB0 */ + CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */ + CLKDEV_DEV_ID("r8a66597_udc.0", &mstp_clks[MSTP322]), /* USB0 */ CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */ CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */ CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMC */ diff --git a/arch/arm/mach-shmobile/include/mach/entry-macro.S b/arch/arm/mach-shmobile/include/mach/entry-macro.S index a285d13c7416..f428c4db2b60 100644 --- a/arch/arm/mach-shmobile/include/mach/entry-macro.S +++ b/arch/arm/mach-shmobile/include/mach/entry-macro.S @@ -1,4 +1,5 @@ /* + * Copyright (C) 2010 Magnus Damm * Copyright (C) 2008 Renesas Solutions Corp. * * This program is free software; you can redistribute it and/or modify @@ -14,24 +15,45 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -#include <mach/hardware.h> #include <mach/irqs.h> +#define INTCA_BASE 0xe6980000 +#define INTFLGA_OFFS 0x00000018 /* accept pending interrupt */ +#define INTEVTA_OFFS 0x00000020 /* vector number of accepted interrupt */ +#define INTLVLA_OFFS 0x00000030 /* priority level of accepted interrupt */ +#define INTLVLB_OFFS 0x00000034 /* previous priority level */ + .macro disable_fiq .endm .macro get_irqnr_preamble, base, tmp - ldr \base, =INTFLGA + ldr \base, =INTCA_BASE .endm .macro arch_ret_to_user, tmp1, tmp2 .endm .macro get_irqnr_and_base, irqnr, irqstat, base, tmp - ldr \irqnr, [\base] + /* The single INTFLGA read access below results in the following: + * + * 1. INTLVLB is updated with old priority value from INTLVLA + * 2. Highest priority interrupt is accepted + * 3. INTLVLA is updated to contain priority of accepted interrupt + * 4. Accepted interrupt vector is stored in INTFLGA and INTEVTA + */ + ldr \irqnr, [\base, #INTFLGA_OFFS] + + /* Restore INTLVLA with the value saved in INTLVLB. + * This is required to support interrupt priorities properly. + */ + ldrb \tmp, [\base, #INTLVLB_OFFS] + strb \tmp, [\base, #INTLVLA_OFFS] + + /* Handle invalid vector number case */ cmp \irqnr, #0 beq 1000f - /* intevt to irq number */ + + /* Convert vector to irq number, same as the evt2irq() macro */ lsr \irqnr, \irqnr, #0x5 subs \irqnr, \irqnr, #16 diff --git a/arch/arm/mach-shmobile/include/mach/vmalloc.h b/arch/arm/mach-shmobile/include/mach/vmalloc.h index 4aecf6e3a859..2b8fd8b942fe 100644 --- a/arch/arm/mach-shmobile/include/mach/vmalloc.h +++ b/arch/arm/mach-shmobile/include/mach/vmalloc.h @@ -2,6 +2,6 @@ #define __ASM_MACH_VMALLOC_H /* Vmalloc at ... - 0xe5ffffff */ -#define VMALLOC_END 0xe6000000 +#define VMALLOC_END 0xe6000000UL #endif /* __ASM_MACH_VMALLOC_H */ diff --git a/arch/arm/mach-tegra/include/mach/debug-macro.S b/arch/arm/mach-tegra/include/mach/debug-macro.S index 8ea3bffb4e00..a0e7c12868bd 100644 --- a/arch/arm/mach-tegra/include/mach/debug-macro.S +++ b/arch/arm/mach-tegra/include/mach/debug-macro.S @@ -21,8 +21,8 @@ #include <mach/io.h> .macro addruart, rp, rv - ldreq \rp, =IO_APB_PHYS @ physical - ldrne \rv, =IO_APB_VIRT @ virtual + ldr \rp, =IO_APB_PHYS @ physical + ldr \rv, =IO_APB_VIRT @ virtual #if defined(CONFIG_TEGRA_DEBUG_UART_NONE) #error "A debug UART must be selected in the kernel config to use DEBUG_LL" #elif defined(CONFIG_TEGRA_DEBUG_UARTA) diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c index 73fb1a551ec6..608a1372b172 100644 --- a/arch/arm/mach-ux500/cpu.c +++ b/arch/arm/mach-ux500/cpu.c @@ -75,14 +75,14 @@ void __init ux500_init_irq(void) static inline void ux500_cache_wait(void __iomem *reg, unsigned long mask) { /* wait for the operation to complete */ - while (readl(reg) & mask) + while (readl_relaxed(reg) & mask) ; } static inline void ux500_cache_sync(void) { void __iomem *base = __io_address(UX500_L2CC_BASE); - writel(0, base + L2X0_CACHE_SYNC); + writel_relaxed(0, base + L2X0_CACHE_SYNC); ux500_cache_wait(base + L2X0_CACHE_SYNC, 1); } @@ -107,7 +107,7 @@ static void ux500_l2x0_inv_all(void) uint32_t l2x0_way_mask = (1<<16) - 1; /* Bitmask of active ways */ /* invalidate all ways */ - writel(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); + writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); ux500_cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); ux500_cache_sync(); } diff --git a/arch/arm/mach-versatile/include/mach/vmalloc.h b/arch/arm/mach-versatile/include/mach/vmalloc.h index ebd8a2543d3b..7d8e069ad51b 100644 --- a/arch/arm/mach-versatile/include/mach/vmalloc.h +++ b/arch/arm/mach-versatile/include/mach/vmalloc.h @@ -18,4 +18,4 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#define VMALLOC_END 0xd8000000 +#define VMALLOC_END 0xd8000000UL diff --git a/arch/arm/mach-vexpress/headsmp.S b/arch/arm/mach-vexpress/headsmp.S index 8a78ff68e1ee..7a3f0632947c 100644 --- a/arch/arm/mach-vexpress/headsmp.S +++ b/arch/arm/mach-vexpress/headsmp.S @@ -35,5 +35,6 @@ pen: ldr r7, [r6] */ b secondary_startup + .align 1: .long . .long pen_release diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index 6e77c042d8e9..e0b0e7a4ec68 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -13,13 +13,9 @@ */ #include <linux/init.h> +#include <linux/highmem.h> #include <asm/cacheflush.h> -#include <asm/kmap_types.h> -#include <asm/fixmap.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> #include <plat/cache-feroceon-l2.h> -#include "mm.h" /* * Low-level cache maintenance operations. @@ -39,27 +35,30 @@ * between which we don't want to be preempted. */ -static inline unsigned long l2_start_va(unsigned long paddr) +static inline unsigned long l2_get_va(unsigned long paddr) { #ifdef CONFIG_HIGHMEM /* - * Let's do our own fixmap stuff in a minimal way here. * Because range ops can't be done on physical addresses, * we simply install a virtual mapping for it only for the * TLB lookup to occur, hence no need to flush the untouched - * memory mapping. This is protected with the disabling of - * interrupts by the caller. + * memory mapping afterwards (note: a cache flush may happen + * in some circumstances depending on the path taken in kunmap_atomic). */ - unsigned long idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id(); - unsigned long vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte_ext(TOP_PTE(vaddr), pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL), 0); - local_flush_tlb_kernel_page(vaddr); - return vaddr + (paddr & ~PAGE_MASK); + void *vaddr = kmap_atomic_pfn(paddr >> PAGE_SHIFT); + return (unsigned long)vaddr + (paddr & ~PAGE_MASK); #else return __phys_to_virt(paddr); #endif } +static inline void l2_put_va(unsigned long vaddr) +{ +#ifdef CONFIG_HIGHMEM + kunmap_atomic((void *)vaddr); +#endif +} + static inline void l2_clean_pa(unsigned long addr) { __asm__("mcr p15, 1, %0, c15, c9, 3" : : "r" (addr)); @@ -76,13 +75,14 @@ static inline void l2_clean_pa_range(unsigned long start, unsigned long end) */ BUG_ON((start ^ end) >> PAGE_SHIFT); - raw_local_irq_save(flags); - va_start = l2_start_va(start); + va_start = l2_get_va(start); va_end = va_start + (end - start); + raw_local_irq_save(flags); __asm__("mcr p15, 1, %0, c15, c9, 4\n\t" "mcr p15, 1, %1, c15, c9, 5" : : "r" (va_start), "r" (va_end)); raw_local_irq_restore(flags); + l2_put_va(va_start); } static inline void l2_clean_inv_pa(unsigned long addr) @@ -106,13 +106,14 @@ static inline void l2_inv_pa_range(unsigned long start, unsigned long end) */ BUG_ON((start ^ end) >> PAGE_SHIFT); - raw_local_irq_save(flags); - va_start = l2_start_va(start); + va_start = l2_get_va(start); va_end = va_start + (end - start); + raw_local_irq_save(flags); __asm__("mcr p15, 1, %0, c15, c11, 4\n\t" "mcr p15, 1, %1, c15, c11, 5" : : "r" (va_start), "r" (va_end)); raw_local_irq_restore(flags); + l2_put_va(va_start); } static inline void l2_inv_all(void) diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 99fa688dfadd..c96fa1b3f49f 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -203,6 +203,10 @@ ENTRY(v6_flush_kern_dcache_area) * - end - virtual end address of region */ v6_dma_inv_range: +#ifdef CONFIG_DMA_CACHE_RWFO + ldrb r2, [r0] @ read for ownership + strb r2, [r0] @ write for ownership +#endif tst r0, #D_CACHE_LINE_SIZE - 1 bic r0, r0, #D_CACHE_LINE_SIZE - 1 #ifdef HARVARD_CACHE @@ -211,6 +215,10 @@ v6_dma_inv_range: mcrne p15, 0, r0, c7, c11, 1 @ clean unified line #endif tst r1, #D_CACHE_LINE_SIZE - 1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrneb r2, [r1, #-1] @ read for ownership + strneb r2, [r1, #-1] @ write for ownership +#endif bic r1, r1, #D_CACHE_LINE_SIZE - 1 #ifdef HARVARD_CACHE mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D line @@ -218,10 +226,6 @@ v6_dma_inv_range: mcrne p15, 0, r1, c7, c15, 1 @ clean & invalidate unified line #endif 1: -#ifdef CONFIG_DMA_CACHE_RWFO - ldr r2, [r0] @ read for ownership - str r2, [r0] @ write for ownership -#endif #ifdef HARVARD_CACHE mcr p15, 0, r0, c7, c6, 1 @ invalidate D line #else @@ -229,6 +233,10 @@ v6_dma_inv_range: #endif add r0, r0, #D_CACHE_LINE_SIZE cmp r0, r1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrlo r2, [r0] @ read for ownership + strlo r2, [r0] @ write for ownership +#endif blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer @@ -263,12 +271,12 @@ v6_dma_clean_range: * - end - virtual end address of region */ ENTRY(v6_dma_flush_range) - bic r0, r0, #D_CACHE_LINE_SIZE - 1 -1: #ifdef CONFIG_DMA_CACHE_RWFO - ldr r2, [r0] @ read for ownership - str r2, [r0] @ write for ownership + ldrb r2, [r0] @ read for ownership + strb r2, [r0] @ write for ownership #endif + bic r0, r0, #D_CACHE_LINE_SIZE - 1 +1: #ifdef HARVARD_CACHE mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line #else @@ -276,6 +284,10 @@ ENTRY(v6_dma_flush_range) #endif add r0, r0, #D_CACHE_LINE_SIZE cmp r0, r1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrlob r2, [r0] @ read for ownership + strlob r2, [r0] @ write for ownership +#endif blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index a3ebf7a4f49b..6136e68ce953 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -173,15 +173,22 @@ ENTRY(v7_coherent_user_range) UNWIND(.fnstart ) dcache_line_size r2, r3 sub r3, r2, #1 - bic r0, r0, r3 + bic r12, r0, r3 1: - USER( mcr p15, 0, r0, c7, c11, 1 ) @ clean D line to the point of unification + USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification + add r12, r12, r2 + cmp r12, r1 + blo 1b dsb - USER( mcr p15, 0, r0, c7, c5, 1 ) @ invalidate I line - add r0, r0, r2 + icache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 2: - cmp r0, r1 - blo 1b + USER( mcr p15, 0, r12, c7, c5, 1 ) @ invalidate I line + add r12, r12, r2 + cmp r12, r1 + blo 2b +3: mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB @@ -194,10 +201,10 @@ ENTRY(v7_coherent_user_range) * isn't mapped, just try the next page. */ 9001: - mov r0, r0, lsr #12 - mov r0, r0, lsl #12 - add r0, r0, #4096 - b 2b + mov r12, r12, lsr #12 + mov r12, r12, lsl #12 + add r12, r12, #4096 + b 3b UNWIND(.fnend ) ENDPROC(v7_coherent_kern_range) ENDPROC(v7_coherent_user_range) diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c index c3154928bccd..5a32020471e3 100644 --- a/arch/arm/mm/cache-xsc3l2.c +++ b/arch/arm/mm/cache-xsc3l2.c @@ -17,14 +17,10 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/init.h> +#include <linux/highmem.h> #include <asm/system.h> #include <asm/cputype.h> #include <asm/cacheflush.h> -#include <asm/kmap_types.h> -#include <asm/fixmap.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> -#include "mm.h" #define CR_L2 (1 << 26) @@ -71,16 +67,15 @@ static inline void xsc3_l2_inv_all(void) dsb(); } +static inline void l2_unmap_va(unsigned long va) +{ #ifdef CONFIG_HIGHMEM -#define l2_map_save_flags(x) raw_local_save_flags(x) -#define l2_map_restore_flags(x) raw_local_irq_restore(x) -#else -#define l2_map_save_flags(x) ((x) = 0) -#define l2_map_restore_flags(x) ((void)(x)) + if (va != -1) + kunmap_atomic((void *)va); #endif +} -static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, - unsigned long flags) +static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va) { #ifdef CONFIG_HIGHMEM unsigned long va = prev_va & PAGE_MASK; @@ -89,17 +84,10 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, /* * Switching to a new page. Because cache ops are * using virtual addresses only, we must put a mapping - * in place for it. We also enable interrupts for a - * short while and disable them again to protect this - * mapping. + * in place for it. */ - unsigned long idx; - raw_local_irq_restore(flags); - idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id(); - va = __fix_to_virt(FIX_KMAP_BEGIN + idx); - raw_local_irq_restore(flags | PSR_I_BIT); - set_pte_ext(TOP_PTE(va), pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL), 0); - local_flush_tlb_kernel_page(va); + l2_unmap_va(prev_va); + va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT); } return va + (pa_offset >> (32 - PAGE_SHIFT)); #else @@ -109,7 +97,7 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, static void xsc3_l2_inv_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; if (start == 0 && end == -1ul) { xsc3_l2_inv_all(); @@ -117,13 +105,12 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) } vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); /* * Clean and invalidate partial first cache line. */ if (start & (CACHE_LINE_SIZE - 1)) { - vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr, flags); + vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); start = (start | (CACHE_LINE_SIZE - 1)) + 1; @@ -133,7 +120,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) * Invalidate all full cache lines between 'start' and 'end'. */ while (start < (end & ~(CACHE_LINE_SIZE - 1))) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_inv_mva(vaddr); start += CACHE_LINE_SIZE; } @@ -142,31 +129,30 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) * Clean and invalidate partial last cache line. */ if (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } static void xsc3_l2_clean_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); start += CACHE_LINE_SIZE; } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } @@ -193,7 +179,7 @@ static inline void xsc3_l2_flush_all(void) static void xsc3_l2_flush_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; if (start == 0 && end == -1ul) { xsc3_l2_flush_all(); @@ -201,17 +187,16 @@ static void xsc3_l2_flush_range(unsigned long start, unsigned long end) } vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); start += CACHE_LINE_SIZE; } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ac6a36142fcd..809f1bf9fa29 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/highmem.h> #include <asm/memory.h> #include <asm/highmem.h> @@ -480,10 +481,10 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, op(vaddr, len, dir); kunmap_high(page); } else if (cache_is_vipt()) { - pte_t saved_pte; - vaddr = kmap_high_l1_vipt(page, &saved_pte); + /* unmapped pages might still be cached */ + vaddr = kmap_atomic(page); op(vaddr + offset, len, dir); - kunmap_high_l1_vipt(page, saved_pte); + kunmap_atomic(vaddr); } } else { vaddr = page_address(page) + offset; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 391ffae75098..c29f2839f1d2 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/mm.h> #include <linux/pagemap.h> +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/cachetype.h> @@ -180,10 +181,10 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_high(page); } else if (cache_is_vipt()) { - pte_t saved_pte; - addr = kmap_high_l1_vipt(page, &saved_pte); + /* unmapped pages might still be cached */ + addr = kmap_atomic(page); __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high_l1_vipt(page, saved_pte); + kunmap_atomic(addr); } } diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index c435fd9e1da9..807c0573abbe 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -140,90 +140,3 @@ struct page *kmap_atomic_to_page(const void *ptr) pte = TOP_PTE(vaddr); return pte_page(*pte); } - -#ifdef CONFIG_CPU_CACHE_VIPT - -#include <linux/percpu.h> - -/* - * The VIVT cache of a highmem page is always flushed before the page - * is unmapped. Hence unmapped highmem pages need no cache maintenance - * in that case. - * - * However unmapped pages may still be cached with a VIPT cache, and - * it is not possible to perform cache maintenance on them using physical - * addresses unfortunately. So we have no choice but to set up a temporary - * virtual mapping for that purpose. - * - * Yet this VIPT cache maintenance may be triggered from DMA support - * functions which are possibly called from interrupt context. As we don't - * want to keep interrupt disabled all the time when such maintenance is - * taking place, we therefore allow for some reentrancy by preserving and - * restoring the previous fixmap entry before the interrupted context is - * resumed. If the reentrancy depth is 0 then there is no need to restore - * the previous fixmap, and leaving the current one in place allow it to - * be reused the next time without a TLB flush (common with DMA). - */ - -static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth); - -void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte) -{ - unsigned int idx, cpu; - int *depth; - unsigned long vaddr, flags; - pte_t pte, *ptep; - - if (!in_interrupt()) - preempt_disable(); - - cpu = smp_processor_id(); - depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); - - idx = KM_L1_CACHE + KM_TYPE_NR * cpu; - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - ptep = TOP_PTE(vaddr); - pte = mk_pte(page, kmap_prot); - - raw_local_irq_save(flags); - (*depth)++; - if (pte_val(*ptep) == pte_val(pte)) { - *saved_pte = pte; - } else { - *saved_pte = *ptep; - set_pte_ext(ptep, pte, 0); - local_flush_tlb_kernel_page(vaddr); - } - raw_local_irq_restore(flags); - - return (void *)vaddr; -} - -void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte) -{ - unsigned int idx, cpu = smp_processor_id(); - int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); - unsigned long vaddr, flags; - pte_t pte, *ptep; - - idx = KM_L1_CACHE + KM_TYPE_NR * cpu; - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - ptep = TOP_PTE(vaddr); - pte = mk_pte(page, kmap_prot); - - BUG_ON(pte_val(*ptep) != pte_val(pte)); - BUG_ON(*depth <= 0); - - raw_local_irq_save(flags); - (*depth)--; - if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) { - set_pte_ext(ptep, saved_pte, 0); - local_flush_tlb_kernel_page(vaddr); - } - raw_local_irq_restore(flags); - - if (!in_interrupt()) - preempt_enable(); -} - -#endif /* CONFIG_CPU_CACHE_VIPT */ diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 17e7b0b57e49..55c17a6fb22f 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -206,8 +206,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, */ if (pfn_valid(pfn)) { printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory. This leads\n" - KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n" - KERN_WARNING "will fail in the next kernel release. Please fix your driver.\n"); + "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n" + "will fail in the next kernel release. Please fix your driver.\n"); WARN_ON(1); } diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 7d63beaf9745..b795afd0a2c6 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -61,17 +61,27 @@ .endm /* - * cache_line_size - get the cache line size from the CSIDR register - * (available on ARMv7+). It assumes that the CSSR register was configured - * to access the L1 data cache CSIDR. + * dcache_line_size - get the minimum D-cache line size from the CTR register + * on ARMv7. */ .macro dcache_line_size, reg, tmp - mrc p15, 1, \tmp, c0, c0, 0 @ read CSIDR - and \tmp, \tmp, #7 @ cache line size encoding - mov \reg, #16 @ size offset + mrc p15, 0, \tmp, c0, c0, 1 @ read ctr + lsr \tmp, \tmp, #16 + and \tmp, \tmp, #0xf @ cache line size encoding + mov \reg, #4 @ bytes per word mov \reg, \reg, lsl \tmp @ actual cache line size .endm +/* + * icache_line_size - get the minimum I-cache line size from the CTR register + * on ARMv7. + */ + .macro icache_line_size, reg, tmp + mrc p15, 0, \tmp, c0, c0, 1 @ read ctr + and \tmp, \tmp, #0xf @ cache line size encoding + mov \reg, #4 @ bytes per word + mov \reg, \reg, lsl \tmp @ actual cache line size + .endm /* * Sanity check the PTE configuration for the code below - which makes diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 53cbe2225153..9b9ff5d949fd 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -381,7 +381,7 @@ __v7_ca9mp_proc_info: PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __v7_ca9mp_setup + W(b) __v7_ca9mp_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS @@ -413,7 +413,7 @@ __v7_proc_info: PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __v7_setup + W(b) __v7_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c index 85d3e55ca4a9..558cdfaf76b6 100644 --- a/arch/arm/plat-iop/time.c +++ b/arch/arm/plat-iop/time.c @@ -18,6 +18,7 @@ #include <linux/time.h> #include <linux/init.h> #include <linux/timex.h> +#include <linux/sched.h> #include <linux/io.h> #include <linux/clocksource.h> #include <linux/clockchips.h> @@ -36,7 +37,7 @@ /* * IOP clocksource (free-running timer 1). */ -static cycle_t iop_clocksource_read(struct clocksource *unused) +static cycle_t notrace iop_clocksource_read(struct clocksource *unused) { return 0xffffffffu - read_tcr1(); } diff --git a/arch/arm/plat-mxc/devices/platform-imx-dma.c b/arch/arm/plat-mxc/devices/platform-imx-dma.c index 02d989018059..3a705c7877dd 100644 --- a/arch/arm/plat-mxc/devices/platform-imx-dma.c +++ b/arch/arm/plat-mxc/devices/platform-imx-dma.c @@ -12,15 +12,7 @@ #include <mach/hardware.h> #include <mach/devices-common.h> -#ifdef SDMA_IS_MERGED #include <mach/sdma.h> -#else -struct sdma_platform_data { - int sdma_version; - char *cpu_name; - int to_version; -}; -#endif struct imx_imx_sdma_data { resource_size_t iobase; diff --git a/arch/arm/plat-mxc/devices/platform-spi_imx.c b/arch/arm/plat-mxc/devices/platform-spi_imx.c index e48340ec331e..17f724c9452d 100644 --- a/arch/arm/plat-mxc/devices/platform-spi_imx.c +++ b/arch/arm/plat-mxc/devices/platform-spi_imx.c @@ -27,6 +27,7 @@ const struct imx_spi_imx_data imx21_cspi_data[] __initconst = { imx_spi_imx_data_entry(MX21, CSPI, "imx21-cspi", _id, _hwid, SZ_4K) imx21_cspi_data_entry(0, 1), imx21_cspi_data_entry(1, 2), +}; #endif #ifdef CONFIG_ARCH_MX25 diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c index aedf9c1d645e..63cdc6025bd7 100644 --- a/arch/arm/plat-nomadik/timer.c +++ b/arch/arm/plat-nomadik/timer.c @@ -3,6 +3,7 @@ * * Copyright (C) 2008 STMicroelectronics * Copyright (C) 2010 Alessandro Rubini + * Copyright (C) 2010 Linus Walleij for ST-Ericsson * * 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 @@ -16,11 +17,13 @@ #include <linux/clk.h> #include <linux/jiffies.h> #include <linux/err.h> +#include <linux/cnt32_to_63.h> +#include <linux/timer.h> #include <asm/mach/time.h> #include <plat/mtu.h> -void __iomem *mtu_base; /* ssigned by machine code */ +void __iomem *mtu_base; /* Assigned by machine code */ /* * Kernel assumes that sched_clock can be called early @@ -48,16 +51,82 @@ static struct clocksource nmdk_clksrc = { /* * Override the global weak sched_clock symbol with this * local implementation which uses the clocksource to get some - * better resolution when scheduling the kernel. We accept that - * this wraps around for now, since it is just a relative time - * stamp. (Inspired by OMAP implementation.) + * better resolution when scheduling the kernel. + * + * Because the hardware timer period may be quite short + * (32.3 secs on the 133 MHz MTU timer selection on ux500) + * and because cnt32_to_63() needs to be called at least once per + * half period to work properly, a kernel keepwarm() timer is set up + * to ensure this requirement is always met. + * + * Also the sched_clock timer will wrap around at some point, + * here we set it to run continously for a year. */ +#define SCHED_CLOCK_MIN_WRAP 3600*24*365 +static struct timer_list cnt32_to_63_keepwarm_timer; +static u32 sched_mult; +static u32 sched_shift; + unsigned long long notrace sched_clock(void) { - return clocksource_cyc2ns(nmdk_clksrc.read( - &nmdk_clksrc), - nmdk_clksrc.mult, - nmdk_clksrc.shift); + u64 cycles; + + if (unlikely(!mtu_base)) + return 0; + + cycles = cnt32_to_63(-readl(mtu_base + MTU_VAL(0))); + /* + * sched_mult is guaranteed to be even so will + * shift out bit 63 + */ + return (cycles * sched_mult) >> sched_shift; +} + +/* Just kick sched_clock every so often */ +static void cnt32_to_63_keepwarm(unsigned long data) +{ + mod_timer(&cnt32_to_63_keepwarm_timer, round_jiffies(jiffies + data)); + (void) sched_clock(); +} + +/* + * Set up a timer to keep sched_clock():s 32_to_63 algorithm warm + * once in half a 32bit timer wrap interval. + */ +static void __init nmdk_sched_clock_init(unsigned long rate) +{ + u32 v; + unsigned long delta; + u64 days; + + /* Find the apropriate mult and shift factors */ + clocks_calc_mult_shift(&sched_mult, &sched_shift, + rate, NSEC_PER_SEC, SCHED_CLOCK_MIN_WRAP); + /* We need to multiply by an even number to get rid of bit 63 */ + if (sched_mult & 1) + sched_mult++; + + /* Let's see what we get, take max counter and scale it */ + days = (0xFFFFFFFFFFFFFFFFLLU * sched_mult) >> sched_shift; + do_div(days, NSEC_PER_SEC); + do_div(days, (3600*24)); + + pr_info("sched_clock: using %d bits @ %lu Hz wrap in %lu days\n", + (64 - sched_shift), rate, (unsigned long) days); + + /* + * Program a timer to kick us at half 32bit wraparound + * Formula: seconds per wrap = (2^32) / f + */ + v = 0xFFFFFFFFUL / rate; + /* We want half of the wrap time to keep cnt32_to_63 warm */ + v /= 2; + pr_debug("sched_clock: prescaled timer rate: %lu Hz, " + "initialize keepwarm timer every %d seconds\n", rate, v); + /* Convert seconds to jiffies */ + delta = msecs_to_jiffies(v*1000); + setup_timer(&cnt32_to_63_keepwarm_timer, cnt32_to_63_keepwarm, delta); + mod_timer(&cnt32_to_63_keepwarm_timer, round_jiffies(jiffies + delta)); } /* Clockevent device: use one-shot mode */ @@ -161,13 +230,15 @@ void __init nmdk_timer_init(void) writel(0, mtu_base + MTU_BGLR(0)); writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(0)); - /* Now the scheduling clock is ready */ + /* Now the clock source is ready */ nmdk_clksrc.read = nmdk_read_timer; if (clocksource_register(&nmdk_clksrc)) pr_err("timer: failed to initialize clock source %s\n", nmdk_clksrc.name); + nmdk_sched_clock_init(rate); + /* Timer 1 is used for events */ clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE); diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c index 155fe43a672b..8722a136f3a5 100644 --- a/arch/arm/plat-omap/counter_32k.c +++ b/arch/arm/plat-omap/counter_32k.c @@ -16,6 +16,7 @@ #include <linux/init.h> #include <linux/clk.h> #include <linux/io.h> +#include <linux/err.h> #include <plat/common.h> #include <plat/board.h> @@ -164,7 +165,7 @@ static int __init omap_init_clocksource_32k(void) return -ENODEV; sync_32k_ick = clk_get(NULL, "omap_32ksync_ick"); - if (sync_32k_ick) + if (!IS_ERR(sync_32k_ick)) clk_enable(sync_32k_ick); clocksource_32k.mult = clocksource_hz2mult(32768, diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index e2c8eebe6b3a..74dac419d328 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -166,7 +166,7 @@ static void __init omap_detect_sram(void) cpu_is_omap1710()) omap_sram_size = 0x4000; /* 16K */ else if (cpu_is_omap1611()) - omap_sram_size = 0x3e800; /* 250K */ + omap_sram_size = SZ_256K; else { printk(KERN_ERR "Could not detect SRAM size\n"); omap_sram_size = 0x4000; diff --git a/arch/arm/plat-pxa/include/plat/sdhci.h b/arch/arm/plat-pxa/include/plat/sdhci.h index e49c5b6fc4e2..1ab332e37d7d 100644 --- a/arch/arm/plat-pxa/include/plat/sdhci.h +++ b/arch/arm/plat-pxa/include/plat/sdhci.h @@ -17,6 +17,9 @@ /* Require clock free running */ #define PXA_FLAG_DISABLE_CLOCK_GATING (1<<0) +/* Board design supports 8-bit data on SD/SDIO BUS */ +#define PXA_FLAG_SD_8_BIT_CAPABLE_SLOT (1<<2) + /* * struct pxa_sdhci_platdata() - Platform device data for PXA SDHCI * @max_speed: the maximum speed supported diff --git a/arch/arm/plat-s3c24xx/Kconfig b/arch/arm/plat-s3c24xx/Kconfig index 5a27b1b538f2..eb105e61c746 100644 --- a/arch/arm/plat-s3c24xx/Kconfig +++ b/arch/arm/plat-s3c24xx/Kconfig @@ -8,7 +8,7 @@ config PLAT_S3C24XX default y select NO_IOPORT select ARCH_REQUIRE_GPIOLIB - select S3C_DEVICE_NAND + select S3C_DEV_NAND select S3C_GPIO_CFG_S3C24XX help Base platform code for any Samsung S3C24XX device diff --git a/arch/arm/plat-s3c24xx/cpu.c b/arch/arm/plat-s3c24xx/cpu.c index 76d0858c3cbb..4a10c0f684b2 100644 --- a/arch/arm/plat-s3c24xx/cpu.c +++ b/arch/arm/plat-s3c24xx/cpu.c @@ -88,7 +88,7 @@ static struct cpu_table cpu_ids[] __initdata = { { .idcode = 0x32440000, .idmask = 0xffffffff, - .map_io = s3c244x_map_io, + .map_io = s3c2440_map_io, .init_clocks = s3c244x_init_clocks, .init_uarts = s3c244x_init_uarts, .init = s3c2440_init, @@ -97,7 +97,7 @@ static struct cpu_table cpu_ids[] __initdata = { { .idcode = 0x32440001, .idmask = 0xffffffff, - .map_io = s3c244x_map_io, + .map_io = s3c2440_map_io, .init_clocks = s3c244x_init_clocks, .init_uarts = s3c244x_init_uarts, .init = s3c2440_init, @@ -106,7 +106,7 @@ static struct cpu_table cpu_ids[] __initdata = { { .idcode = 0x32440aaa, .idmask = 0xffffffff, - .map_io = s3c244x_map_io, + .map_io = s3c2442_map_io, .init_clocks = s3c244x_init_clocks, .init_uarts = s3c244x_init_uarts, .init = s3c2442_init, @@ -115,7 +115,7 @@ static struct cpu_table cpu_ids[] __initdata = { { .idcode = 0x32440aab, .idmask = 0xffffffff, - .map_io = s3c244x_map_io, + .map_io = s3c2442_map_io, .init_clocks = s3c244x_init_clocks, .init_uarts = s3c244x_init_uarts, .init = s3c2442_init, diff --git a/arch/arm/plat-s3c24xx/gpiolib.c b/arch/arm/plat-s3c24xx/gpiolib.c index 24c6f5a30596..243b6411050d 100644 --- a/arch/arm/plat-s3c24xx/gpiolib.c +++ b/arch/arm/plat-s3c24xx/gpiolib.c @@ -82,8 +82,6 @@ static struct s3c_gpio_cfg s3c24xx_gpiocfg_banka = { struct s3c_gpio_cfg s3c24xx_gpiocfg_default = { .set_config = s3c_gpio_setcfg_s3c24xx, .get_config = s3c_gpio_getcfg_s3c24xx, - .set_pull = s3c_gpio_setpull_1up, - .get_pull = s3c_gpio_getpull_1up, }; struct s3c_gpio_chip s3c24xx_gpios[] = { diff --git a/arch/arm/plat-s3c24xx/include/plat/s3c244x.h b/arch/arm/plat-s3c24xx/include/plat/s3c244x.h index 307248d1ccbb..89e8d0a25f87 100644 --- a/arch/arm/plat-s3c24xx/include/plat/s3c244x.h +++ b/arch/arm/plat-s3c24xx/include/plat/s3c244x.h @@ -21,17 +21,22 @@ extern void s3c244x_init_clocks(int xtal); #else #define s3c244x_init_clocks NULL #define s3c244x_init_uarts NULL -#define s3c244x_map_io NULL #endif #ifdef CONFIG_CPU_S3C2440 extern int s3c2440_init(void); + +extern void s3c2440_map_io(void); #else #define s3c2440_init NULL +#define s3c2440_map_io NULL #endif #ifdef CONFIG_CPU_S3C2442 extern int s3c2442_init(void); + +extern void s3c2442_map_io(void); #else #define s3c2442_init NULL +#define s3c2442_map_io NULL #endif diff --git a/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c b/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c index 9793544a6ace..704175b0573f 100644 --- a/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c +++ b/arch/arm/plat-s3c24xx/spi-bus0-gpe11_12_13.c @@ -29,8 +29,8 @@ void s3c24xx_spi_gpiocfg_bus0_gpe11_12_13(struct s3c2410_spi_info *spi, } else { s3c_gpio_cfgpin(S3C2410_GPE(13), S3C2410_GPIO_INPUT); s3c_gpio_cfgpin(S3C2410_GPE(11), S3C2410_GPIO_INPUT); - s3c_gpio_cfgpull(S3C2410_GPE(11), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPE(12), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPE(13), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPE(11), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPE(12), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPE(13), S3C_GPIO_PULL_NONE); } } diff --git a/arch/arm/plat-s3c24xx/spi-bus1-gpd8_9_10.c b/arch/arm/plat-s3c24xx/spi-bus1-gpd8_9_10.c index db9e9e477ec1..72457afd6255 100644 --- a/arch/arm/plat-s3c24xx/spi-bus1-gpd8_9_10.c +++ b/arch/arm/plat-s3c24xx/spi-bus1-gpd8_9_10.c @@ -31,8 +31,8 @@ void s3c24xx_spi_gpiocfg_bus1_gpd8_9_10(struct s3c2410_spi_info *spi, } else { s3c_gpio_cfgpin(S3C2410_GPD(8), S3C2410_GPIO_INPUT); s3c_gpio_cfgpin(S3C2410_GPD(9), S3C2410_GPIO_INPUT); - s3c_gpio_cfgpull(S3C2410_GPD(10), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPD(9), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPD(8), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPD(10), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPD(9), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPD(8), S3C_GPIO_PULL_NONE); } } diff --git a/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c b/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c index 8ea663a438bb..c3972b645d13 100644 --- a/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c +++ b/arch/arm/plat-s3c24xx/spi-bus1-gpg5_6_7.c @@ -29,8 +29,8 @@ void s3c24xx_spi_gpiocfg_bus1_gpg5_6_7(struct s3c2410_spi_info *spi, } else { s3c_gpio_cfgpin(S3C2410_GPG(7), S3C2410_GPIO_INPUT); s3c_gpio_cfgpin(S3C2410_GPG(5), S3C2410_GPIO_INPUT); - s3c_gpio_cfgpull(S3C2410_GPG(5), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPG(6), S3C_GPIO_PULL_NONE); - s3c_gpio_cfgpull(S3C2410_GPG(7), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPG(5), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPG(6), S3C_GPIO_PULL_NONE); + s3c_gpio_setpull(S3C2410_GPG(7), S3C_GPIO_PULL_NONE); } } diff --git a/arch/arm/plat-samsung/gpio-config.c b/arch/arm/plat-samsung/gpio-config.c index b732b773b9af..0aa32f242ee4 100644 --- a/arch/arm/plat-samsung/gpio-config.c +++ b/arch/arm/plat-samsung/gpio-config.c @@ -280,18 +280,17 @@ s3c_gpio_pull_t s3c_gpio_getpull_updown(struct s3c_gpio_chip *chip, } #endif -#ifdef CONFIG_S3C_GPIO_PULL_UP -int s3c_gpio_setpull_1up(struct s3c_gpio_chip *chip, - unsigned int off, s3c_gpio_pull_t pull) +#if defined(CONFIG_S3C_GPIO_PULL_UP) || defined(CONFIG_S3C_GPIO_PULL_DOWN) +static int s3c_gpio_setpull_1(struct s3c_gpio_chip *chip, + unsigned int off, s3c_gpio_pull_t pull, + s3c_gpio_pull_t updown) { void __iomem *reg = chip->base + 0x08; u32 pup = __raw_readl(reg); - pup = __raw_readl(reg); - - if (pup == S3C_GPIO_PULL_UP) + if (pull == updown) pup &= ~(1 << off); - else if (pup == S3C_GPIO_PULL_NONE) + else if (pull == S3C_GPIO_PULL_NONE) pup |= (1 << off); else return -EINVAL; @@ -300,17 +299,45 @@ int s3c_gpio_setpull_1up(struct s3c_gpio_chip *chip, return 0; } -s3c_gpio_pull_t s3c_gpio_getpull_1up(struct s3c_gpio_chip *chip, - unsigned int off) +static s3c_gpio_pull_t s3c_gpio_getpull_1(struct s3c_gpio_chip *chip, + unsigned int off, s3c_gpio_pull_t updown) { void __iomem *reg = chip->base + 0x08; u32 pup = __raw_readl(reg); pup &= (1 << off); - return pup ? S3C_GPIO_PULL_NONE : S3C_GPIO_PULL_UP; + return pup ? S3C_GPIO_PULL_NONE : updown; +} +#endif /* CONFIG_S3C_GPIO_PULL_UP || CONFIG_S3C_GPIO_PULL_DOWN */ + +#ifdef CONFIG_S3C_GPIO_PULL_UP +s3c_gpio_pull_t s3c_gpio_getpull_1up(struct s3c_gpio_chip *chip, + unsigned int off) +{ + return s3c_gpio_getpull_1(chip, off, S3C_GPIO_PULL_UP); +} + +int s3c_gpio_setpull_1up(struct s3c_gpio_chip *chip, + unsigned int off, s3c_gpio_pull_t pull) +{ + return s3c_gpio_setpull_1(chip, off, pull, S3C_GPIO_PULL_UP); } #endif /* CONFIG_S3C_GPIO_PULL_UP */ +#ifdef CONFIG_S3C_GPIO_PULL_DOWN +s3c_gpio_pull_t s3c_gpio_getpull_1down(struct s3c_gpio_chip *chip, + unsigned int off) +{ + return s3c_gpio_getpull_1(chip, off, S3C_GPIO_PULL_DOWN); +} + +int s3c_gpio_setpull_1down(struct s3c_gpio_chip *chip, + unsigned int off, s3c_gpio_pull_t pull) +{ + return s3c_gpio_setpull_1(chip, off, pull, S3C_GPIO_PULL_DOWN); +} +#endif /* CONFIG_S3C_GPIO_PULL_DOWN */ + #ifdef CONFIG_S5P_GPIO_DRVSTR s5p_gpio_drvstr_t s5p_gpio_get_drvstr(unsigned int pin) { diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h b/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h index 8fd65d8b5863..0d2c5703f1ee 100644 --- a/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h +++ b/arch/arm/plat-samsung/include/plat/gpio-cfg-helpers.h @@ -210,6 +210,17 @@ extern s3c_gpio_pull_t s3c_gpio_getpull_1up(struct s3c_gpio_chip *chip, unsigned int off); /** + * s3c_gpio_getpull_1down() - Get configuration for choice of down or none + * @chip: The gpio chip that the GPIO pin belongs to + * @off: The offset to the pin to get the configuration of. + * + * This helper function reads the state of the pull-down resistor for the + * given GPIO in the same case as s3c_gpio_setpull_1down. +*/ +extern s3c_gpio_pull_t s3c_gpio_getpull_1down(struct s3c_gpio_chip *chip, + unsigned int off); + +/** * s3c_gpio_setpull_s3c2443() - Pull configuration for s3c2443. * @chip: The gpio chip that is being configured. * @off: The offset for the GPIO being configured. diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 55590a4d87c9..2fea897ebeb1 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Thu Sep 9 22:43:01 2010 +# Last update: Sun Dec 12 23:24:27 2010 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -2321,7 +2321,7 @@ mx31txtr MACH_MX31TXTR MX31TXTR 2332 u380 MACH_U380 U380 2333 oamp3_hualu MACH_HUALU_BOARD HUALU_BOARD 2334 npcmx50 MACH_NPCMX50 NPCMX50 2335 -mx51_lange51 MACH_MX51_LANGE51 MX51_LANGE51 2336 +mx51_efikamx MACH_MX51_EFIKAMX MX51_EFIKAMX 2336 mx51_lange52 MACH_MX51_LANGE52 MX51_LANGE52 2337 riom MACH_RIOM RIOM 2338 comcas MACH_COMCAS COMCAS 2339 @@ -2355,7 +2355,7 @@ at91sam9263cs MACH_AT91SAM9263CS AT91SAM9263CS 2366 csb732 MACH_CSB732 CSB732 2367 u8500 MACH_U8500 U8500 2368 huqiu MACH_HUQIU HUQIU 2369 -mx51_kunlun MACH_MX51_KUNLUN MX51_KUNLUN 2370 +mx51_efikasb MACH_MX51_EFIKASB MX51_EFIKASB 2370 pmt1g MACH_PMT1G PMT1G 2371 htcelf MACH_HTCELF HTCELF 2372 armadillo420 MACH_ARMADILLO420 ARMADILLO420 2373 @@ -2971,7 +2971,7 @@ premierwave_en MACH_PREMIERWAVE_EN PREMIERWAVE_EN 2985 wasabi MACH_WASABI WASABI 2986 vivow MACH_VIVOW VIVOW 2987 mx50_rdp MACH_MX50_RDP MX50_RDP 2988 -universal MACH_UNIVERSAL UNIVERSAL 2989 +universal_c210 MACH_UNIVERSAL_C210 UNIVERSAL_C210 2989 real6410 MACH_REAL6410 REAL6410 2990 spx_sakura MACH_SPX_SAKURA SPX_SAKURA 2991 ij3k_2440 MACH_IJ3K_2440 IJ3K_2440 2992 @@ -3044,3 +3044,178 @@ harvest_desoto MACH_HARVEST_DESOTO HARVEST_DESOTO 3059 msm8x60_qrdc MACH_MSM8X60_QRDC MSM8X60_QRDC 3060 spear900 MACH_SPEAR900 SPEAR900 3061 pcontrol_g20 MACH_PCONTROL_G20 PCONTROL_G20 3062 +rdstor MACH_RDSTOR RDSTOR 3063 +usdloader MACH_USDLOADER USDLOADER 3064 +tsoploader MACH_TSOPLOADER TSOPLOADER 3065 +kronos MACH_KRONOS KRONOS 3066 +ffcore MACH_FFCORE FFCORE 3067 +mone MACH_MONE MONE 3068 +unit2s MACH_UNIT2S UNIT2S 3069 +acer_a5 MACH_ACER_A5 ACER_A5 3070 +etherpro_isp MACH_ETHERPRO_ISP ETHERPRO_ISP 3071 +stretchs7000 MACH_STRETCHS7000 STRETCHS7000 3072 +p87_smartsim MACH_P87_SMARTSIM P87_SMARTSIM 3073 +tulip MACH_TULIP TULIP 3074 +sunflower MACH_SUNFLOWER SUNFLOWER 3075 +rib MACH_RIB RIB 3076 +clod MACH_CLOD CLOD 3077 +rump MACH_RUMP RUMP 3078 +tenderloin MACH_TENDERLOIN TENDERLOIN 3079 +shortloin MACH_SHORTLOIN SHORTLOIN 3080 +crespo MACH_CRESPO CRESPO 3081 +antares MACH_ANTARES ANTARES 3082 +wb40n MACH_WB40N WB40N 3083 +herring MACH_HERRING HERRING 3084 +naxy400 MACH_NAXY400 NAXY400 3085 +naxy1200 MACH_NAXY1200 NAXY1200 3086 +vpr200 MACH_VPR200 VPR200 3087 +bug20 MACH_BUG20 BUG20 3088 +goflexnet MACH_GOFLEXNET GOFLEXNET 3089 +torbreck MACH_TORBRECK TORBRECK 3090 +saarb_mg1 MACH_SAARB_MG1 SAARB_MG1 3091 +callisto MACH_CALLISTO CALLISTO 3092 +multhsu MACH_MULTHSU MULTHSU 3093 +saluda MACH_SALUDA SALUDA 3094 +pemp_omap3_apollo MACH_PEMP_OMAP3_APOLLO PEMP_OMAP3_APOLLO 3095 +vc0718 MACH_VC0718 VC0718 3096 +mvblx MACH_MVBLX MVBLX 3097 +inhand_apeiron MACH_INHAND_APEIRON INHAND_APEIRON 3098 +inhand_fury MACH_INHAND_FURY INHAND_FURY 3099 +inhand_siren MACH_INHAND_SIREN INHAND_SIREN 3100 +hdnvp MACH_HDNVP HDNVP 3101 +softwinner MACH_SOFTWINNER SOFTWINNER 3102 +prima2_evb MACH_PRIMA2_EVB PRIMA2_EVB 3103 +nas6210 MACH_NAS6210 NAS6210 3104 +unisdev MACH_UNISDEV UNISDEV 3105 +sbca11 MACH_SBCA11 SBCA11 3106 +saga MACH_SAGA SAGA 3107 +ns_k330 MACH_NS_K330 NS_K330 3108 +tanna MACH_TANNA TANNA 3109 +imate8502 MACH_IMATE8502 IMATE8502 3110 +aspen MACH_ASPEN ASPEN 3111 +daintree_cwac MACH_DAINTREE_CWAC DAINTREE_CWAC 3112 +zmx25 MACH_ZMX25 ZMX25 3113 +maple1 MACH_MAPLE1 MAPLE1 3114 +qsd8x72_surf MACH_QSD8X72_SURF QSD8X72_SURF 3115 +qsd8x72_ffa MACH_QSD8X72_FFA QSD8X72_FFA 3116 +abilene MACH_ABILENE ABILENE 3117 +eigen_ttr MACH_EIGEN_TTR EIGEN_TTR 3118 +iomega_ix2_200 MACH_IOMEGA_IX2_200 IOMEGA_IX2_200 3119 +coretec_vcx7400 MACH_CORETEC_VCX7400 CORETEC_VCX7400 3120 +santiago MACH_SANTIAGO SANTIAGO 3121 +mx257sol MACH_MX257SOL MX257SOL 3122 +strasbourg MACH_STRASBOURG STRASBOURG 3123 +msm8x60_fluid MACH_MSM8X60_FLUID MSM8X60_FLUID 3124 +smartqv5 MACH_SMARTQV5 SMARTQV5 3125 +smartqv3 MACH_SMARTQV3 SMARTQV3 3126 +smartqv7 MACH_SMARTQV7 SMARTQV7 3127 +paz00 MACH_PAZ00 PAZ00 3128 +acmenetusfoxg20 MACH_ACMENETUSFOXG20 ACMENETUSFOXG20 3129 +htcwillow MACH_HTCWILLOW HTCWILLOW 3130 +fwbd_0404 MACH_FWBD_0404 FWBD_0404 3131 +hdgu MACH_HDGU HDGU 3132 +pyramid MACH_PYRAMID PYRAMID 3133 +epiphan MACH_EPIPHAN EPIPHAN 3134 +omap_bender MACH_OMAP_BENDER OMAP_BENDER 3135 +gurnard MACH_GURNARD GURNARD 3136 +gtl_it5100 MACH_GTL_IT5100 GTL_IT5100 3137 +bcm2708 MACH_BCM2708 BCM2708 3138 +mx51_ggc MACH_MX51_GGC MX51_GGC 3139 +sharespace MACH_SHARESPACE SHARESPACE 3140 +haba_knx_explorer MACH_HABA_KNX_EXPLORER HABA_KNX_EXPLORER 3141 +simtec_kirkmod MACH_SIMTEC_KIRKMOD SIMTEC_KIRKMOD 3142 +crux MACH_CRUX CRUX 3143 +mx51_bravo MACH_MX51_BRAVO MX51_BRAVO 3144 +charon MACH_CHARON CHARON 3145 +picocom3 MACH_PICOCOM3 PICOCOM3 3146 +picocom4 MACH_PICOCOM4 PICOCOM4 3147 +serrano MACH_SERRANO SERRANO 3148 +doubleshot MACH_DOUBLESHOT DOUBLESHOT 3149 +evsy MACH_EVSY EVSY 3150 +huashan MACH_HUASHAN HUASHAN 3151 +lausanne MACH_LAUSANNE LAUSANNE 3152 +emerald MACH_EMERALD EMERALD 3153 +tqma35 MACH_TQMA35 TQMA35 3154 +marvel MACH_MARVEL MARVEL 3155 +manuae MACH_MANUAE MANUAE 3156 +chacha MACH_CHACHA CHACHA 3157 +lemon MACH_LEMON LEMON 3158 +csc MACH_CSC CSC 3159 +gira_knxip_router MACH_GIRA_KNXIP_ROUTER GIRA_KNXIP_ROUTER 3160 +t20 MACH_T20 T20 3161 +hdmini MACH_HDMINI HDMINI 3162 +sciphone_g2 MACH_SCIPHONE_G2 SCIPHONE_G2 3163 +express MACH_EXPRESS EXPRESS 3164 +express_kt MACH_EXPRESS_KT EXPRESS_KT 3165 +maximasp MACH_MAXIMASP MAXIMASP 3166 +nitrogen_imx51 MACH_NITROGEN_IMX51 NITROGEN_IMX51 3167 +nitrogen_imx53 MACH_NITROGEN_IMX53 NITROGEN_IMX53 3168 +sunfire MACH_SUNFIRE SUNFIRE 3169 +arowana MACH_AROWANA AROWANA 3170 +tegra_daytona MACH_TEGRA_DAYTONA TEGRA_DAYTONA 3171 +tegra_swordfish MACH_TEGRA_SWORDFISH TEGRA_SWORDFISH 3172 +edison MACH_EDISON EDISON 3173 +svp8500v1 MACH_SVP8500V1 SVP8500V1 3174 +svp8500v2 MACH_SVP8500V2 SVP8500V2 3175 +svp5500 MACH_SVP5500 SVP5500 3176 +b5500 MACH_B5500 B5500 3177 +s5500 MACH_S5500 S5500 3178 +icon MACH_ICON ICON 3179 +elephant MACH_ELEPHANT ELEPHANT 3180 +msm8x60_fusion MACH_MSM8X60_FUSION MSM8X60_FUSION 3181 +shooter MACH_SHOOTER SHOOTER 3182 +spade_lte MACH_SPADE_LTE SPADE_LTE 3183 +philhwani MACH_PHILHWANI PHILHWANI 3184 +gsncomm MACH_GSNCOMM GSNCOMM 3185 +strasbourg_a2 MACH_STRASBOURG_A2 STRASBOURG_A2 3186 +mmm MACH_MMM MMM 3187 +davinci_dm365_bv MACH_DAVINCI_DM365_BV DAVINCI_DM365_BV 3188 +ag5evm MACH_AG5EVM AG5EVM 3189 +sc575plc MACH_SC575PLC SC575PLC 3190 +sc575hmi MACH_SC575IPC SC575IPC 3191 +omap3_tdm3730 MACH_OMAP3_TDM3730 OMAP3_TDM3730 3192 +g7 MACH_G7 G7 3193 +top9000_eval MACH_TOP9000_EVAL TOP9000_EVAL 3194 +top9000_su MACH_TOP9000_SU TOP9000_SU 3195 +utm300 MACH_UTM300 UTM300 3196 +tsunagi MACH_TSUNAGI TSUNAGI 3197 +ts75xx MACH_TS75XX TS75XX 3198 +msm8x60_fusn_ffa MACH_MSM8X60_FUSN_FFA MSM8X60_FUSN_FFA 3199 +ts47xx MACH_TS47XX TS47XX 3200 +da850_k5 MACH_DA850_K5 DA850_K5 3201 +ax502 MACH_AX502 AX502 3202 +igep0032 MACH_IGEP0032 IGEP0032 3203 +antero MACH_ANTERO ANTERO 3204 +synergy MACH_SYNERGY SYNERGY 3205 +ics_if_voip MACH_ICS_IF_VOIP ICS_IF_VOIP 3206 +wlf_cragg_6410 MACH_WLF_CRAGG_6410 WLF_CRAGG_6410 3207 +punica MACH_PUNICA PUNICA 3208 +sbc_nt250 MACH_SBC_NT250 SBC_NT250 3209 +mx27_wmultra MACH_MX27_WMULTRA MX27_WMULTRA 3210 +mackerel MACH_MACKEREL MACKEREL 3211 +fa9x27 MACH_FA9X27 FA9X27 3213 +ns2816tb MACH_NS2816TB NS2816TB 3214 +ns2816_ntpad MACH_NS2816_NTPAD NS2816_NTPAD 3215 +ns2816_ntnb MACH_NS2816_NTNB NS2816_NTNB 3216 +kaen MACH_KAEN KAEN 3217 +nv1000 MACH_NV1000 NV1000 3218 +nuc950ts MACH_NUC950TS NUC950TS 3219 +nokia_rm680 MACH_NOKIA_RM680 NOKIA_RM680 3220 +ast2200 MACH_AST2200 AST2200 3221 +lead MACH_LEAD LEAD 3222 +unino1 MACH_UNINO1 UNINO1 3223 +greeco MACH_GREECO GREECO 3224 +verdi MACH_VERDI VERDI 3225 +dm6446_adbox MACH_DM6446_ADBOX DM6446_ADBOX 3226 +quad_salsa MACH_QUAD_SALSA QUAD_SALSA 3227 +abb_gma_1_1 MACH_ABB_GMA_1_1 ABB_GMA_1_1 3228 +svcid MACH_SVCID SVCID 3229 +msm8960_sim MACH_MSM8960_SIM MSM8960_SIM 3230 +msm8960_rumi3 MACH_MSM8960_RUMI3 MSM8960_RUMI3 3231 +icon_g MACH_ICON_G ICON_G 3232 +mb3 MACH_MB3 MB3 3233 +gsia18s MACH_GSIA18S GSIA18S 3234 +pivicc MACH_PIVICC PIVICC 3235 +pcm048 MACH_PCM048 PCM048 3236 +dds MACH_DDS DDS 3237 +chalten_xa1 MACH_CHALTEN_XA1 CHALTEN_XA1 3238 diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index d66cead97d28..9897dcfc16d6 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -206,6 +206,7 @@ ENTRY(vfp_save_state) mov pc, lr ENDPROC(vfp_save_state) + .align last_VFP_context_address: .word last_VFP_context diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index cd0c090ebc54..b407bc8ad918 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -7,7 +7,6 @@ */ #include <linux/module.h> -#include <linux/smp_lock.h> #include <linux/unistd.h> #include <linux/user.h> #include <linux/uaccess.h> diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 2b63b0191f52..efad12071c2e 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -16,7 +16,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 97478138e361..933bd388efb2 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -28,7 +28,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c index 3a078ad3aa44..331de723c676 100644 --- a/arch/ia64/hp/sim/simscsi.c +++ b/arch/ia64/hp/sim/simscsi.c @@ -202,7 +202,7 @@ simscsi_readwrite10 (struct scsi_cmnd *sc, int mode) } static int -simscsi_queuecommand (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)) +simscsi_queuecommand_lck (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)) { unsigned int target_id = sc->device->id; char fname[MAX_ROOT_LEN+16]; @@ -326,6 +326,8 @@ simscsi_queuecommand (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)) return 0; } +static DEF_SCSI_QCMD(simscsi_queuecommand) + static int simscsi_host_reset (struct scsi_cmnd *sc) { diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 18732ab23292..c2a1fc23dd75 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -18,7 +18,6 @@ #include <linux/slab.h> #include <linux/fs.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c index 6d3390590e5b..e2a63af5d517 100644 --- a/arch/m68knommu/kernel/process.c +++ b/arch/m68knommu/kernel/process.c @@ -19,7 +19,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 67a2fa2caa49..0a9b5b8b2a19 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -19,6 +19,8 @@ config MIPS select GENERIC_ATOMIC64 if !64BIT select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG + select HAVE_GENERIC_HARDIRQS + select GENERIC_IRQ_PROBE menu "Machine selection" @@ -1664,6 +1666,28 @@ config PAGE_SIZE_64KB endchoice +config FORCE_MAX_ZONEORDER + int "Maximum zone order" + range 13 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB + default "13" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB + range 12 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB + default "12" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB + range 11 64 + default "11" + help + The kernel memory allocator divides physically contiguous memory + blocks into "zones", where each zone is a power of two number of + pages. This option selects the largest power of two that the kernel + keeps in the memory allocator. If you need to allocate very large + blocks of physically contiguous memory, then you may need to + increase this value. + + This config option is actually maximum order plus one. For example, + a value of 11 means that the largest free memory block is 2^10 pages. + + The page size is not necessarily 4KB. Keep this in mind + when choosing a value for this option. + config BOARD_SCACHE bool @@ -1922,20 +1946,6 @@ config CPU_R4400_WORKAROUNDS bool # -# Use the generic interrupt handling code in kernel/irq/: -# -config GENERIC_HARDIRQS - bool - default y - -config GENERIC_IRQ_PROBE - bool - default y - -config IRQ_PER_CPU - bool - -# # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed # caches such as R3000, SB1, R7000 or those that look like they're virtually diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c index 3691630931d6..9e7814db3d03 100644 --- a/arch/mips/alchemy/common/platform.c +++ b/arch/mips/alchemy/common/platform.c @@ -27,6 +27,7 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state, unsigned int old_state) { +#ifdef CONFIG_SERIAL_8250 switch (state) { case 0: if ((__raw_readl(port->membase + UART_MOD_CNTRL) & 3) != 3) { @@ -49,6 +50,7 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state, serial8250_do_pm(port, state, old_state); break; } +#endif } #define PORT(_base, _irq) \ diff --git a/arch/mips/alchemy/devboards/prom.c b/arch/mips/alchemy/devboards/prom.c index b30df5c97ad3..baeb21385058 100644 --- a/arch/mips/alchemy/devboards/prom.c +++ b/arch/mips/alchemy/devboards/prom.c @@ -54,10 +54,9 @@ void __init prom_init(void) prom_init_cmdline(); memsize_str = prom_getenv("memsize"); - if (!memsize_str) + if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize)) memsize = ALCHEMY_BOARD_DEFAULT_MEMSIZE; - else - strict_strtoul(memsize_str, 0, &memsize); + add_memory_region(0, memsize, BOOT_MEM_RAM); } diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c index fc0e7154e8d6..2ca4ada1c291 100644 --- a/arch/mips/ar7/clock.c +++ b/arch/mips/ar7/clock.c @@ -239,12 +239,12 @@ static void tnetd7300_set_clock(u32 shift, struct tnetd7300_clock *clock, calculate(base_clock, frequency, &prediv, &postdiv, &mul); writel(((prediv - 1) << PREDIV_SHIFT) | (postdiv - 1), &clock->ctrl); - msleep(1); + mdelay(1); writel(4, &clock->pll); while (readl(&clock->pll) & PLL_STATUS) ; writel(((mul - 1) << MUL_SHIFT) | (0xff << 3) | 0x0e, &clock->pll); - msleep(75); + mdelay(75); } static void __init tnetd7300_init_clocks(void) @@ -456,7 +456,7 @@ void clk_put(struct clk *clk) } EXPORT_SYMBOL(clk_put); -int __init ar7_init_clocks(void) +void __init ar7_init_clocks(void) { switch (ar7_chip_id()) { case AR7_CHIP_7100: @@ -472,7 +472,4 @@ int __init ar7_init_clocks(void) } /* adjust vbus clock rate */ vbus_clk.rate = bus_clk.rate / 2; - - return 0; } -arch_initcall(ar7_init_clocks); diff --git a/arch/mips/ar7/time.c b/arch/mips/ar7/time.c index 5fb8a0134085..22c93213b233 100644 --- a/arch/mips/ar7/time.c +++ b/arch/mips/ar7/time.c @@ -30,6 +30,9 @@ void __init plat_time_init(void) { struct clk *cpu_clk; + /* Initialize ar7 clocks so the CPU clock frequency is correct */ + ar7_init_clocks(); + cpu_clk = clk_get(NULL, "cpu"); if (IS_ERR(cpu_clk)) { printk(KERN_ERR "unable to get cpu clock\n"); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index b1aee33efd11..c95f90bf734c 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -32,7 +32,6 @@ #include <asm/reboot.h> #include <asm/time.h> #include <bcm47xx.h> -#include <asm/fw/cfe/cfe_api.h> #include <asm/mach-bcm47xx/nvram.h> struct ssb_bus ssb_bcm47xx; @@ -57,68 +56,112 @@ static void bcm47xx_machine_halt(void) cpu_relax(); } -static void str2eaddr(char *str, char *dest) -{ - int i = 0; +#define READ_FROM_NVRAM(_outvar, name, buf) \ + if (nvram_getenv(name, buf, sizeof(buf)) >= 0)\ + sprom->_outvar = simple_strtoul(buf, NULL, 0); - if (str == NULL) { - memset(dest, 0, 6); - return; +static void bcm47xx_fill_sprom(struct ssb_sprom *sprom) +{ + char buf[100]; + u32 boardflags; + + memset(sprom, 0, sizeof(struct ssb_sprom)); + + sprom->revision = 1; /* Fallback: Old hardware does not define this. */ + READ_FROM_NVRAM(revision, "sromrev", buf); + if (nvram_getenv("il0macaddr", buf, sizeof(buf)) >= 0) + nvram_parse_macaddr(buf, sprom->il0mac); + if (nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0) + nvram_parse_macaddr(buf, sprom->et0mac); + if (nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0) + nvram_parse_macaddr(buf, sprom->et1mac); + READ_FROM_NVRAM(et0phyaddr, "et0phyaddr", buf); + READ_FROM_NVRAM(et1phyaddr, "et1phyaddr", buf); + READ_FROM_NVRAM(et0mdcport, "et0mdcport", buf); + READ_FROM_NVRAM(et1mdcport, "et1mdcport", buf); + READ_FROM_NVRAM(board_rev, "boardrev", buf); + READ_FROM_NVRAM(country_code, "ccode", buf); + READ_FROM_NVRAM(ant_available_a, "aa5g", buf); + READ_FROM_NVRAM(ant_available_bg, "aa2g", buf); + READ_FROM_NVRAM(pa0b0, "pa0b0", buf); + READ_FROM_NVRAM(pa0b1, "pa0b1", buf); + READ_FROM_NVRAM(pa0b2, "pa0b2", buf); + READ_FROM_NVRAM(pa1b0, "pa1b0", buf); + READ_FROM_NVRAM(pa1b1, "pa1b1", buf); + READ_FROM_NVRAM(pa1b2, "pa1b2", buf); + READ_FROM_NVRAM(pa1lob0, "pa1lob0", buf); + READ_FROM_NVRAM(pa1lob2, "pa1lob1", buf); + READ_FROM_NVRAM(pa1lob1, "pa1lob2", buf); + READ_FROM_NVRAM(pa1hib0, "pa1hib0", buf); + READ_FROM_NVRAM(pa1hib2, "pa1hib1", buf); + READ_FROM_NVRAM(pa1hib1, "pa1hib2", buf); + READ_FROM_NVRAM(gpio0, "wl0gpio0", buf); + READ_FROM_NVRAM(gpio1, "wl0gpio1", buf); + READ_FROM_NVRAM(gpio2, "wl0gpio2", buf); + READ_FROM_NVRAM(gpio3, "wl0gpio3", buf); + READ_FROM_NVRAM(maxpwr_bg, "pa0maxpwr", buf); + READ_FROM_NVRAM(maxpwr_al, "pa1lomaxpwr", buf); + READ_FROM_NVRAM(maxpwr_a, "pa1maxpwr", buf); + READ_FROM_NVRAM(maxpwr_ah, "pa1himaxpwr", buf); + READ_FROM_NVRAM(itssi_a, "pa1itssit", buf); + READ_FROM_NVRAM(itssi_bg, "pa0itssit", buf); + READ_FROM_NVRAM(tri2g, "tri2g", buf); + READ_FROM_NVRAM(tri5gl, "tri5gl", buf); + READ_FROM_NVRAM(tri5g, "tri5g", buf); + READ_FROM_NVRAM(tri5gh, "tri5gh", buf); + READ_FROM_NVRAM(rxpo2g, "rxpo2g", buf); + READ_FROM_NVRAM(rxpo5g, "rxpo5g", buf); + READ_FROM_NVRAM(rssisav2g, "rssisav2g", buf); + READ_FROM_NVRAM(rssismc2g, "rssismc2g", buf); + READ_FROM_NVRAM(rssismf2g, "rssismf2g", buf); + READ_FROM_NVRAM(bxa2g, "bxa2g", buf); + READ_FROM_NVRAM(rssisav5g, "rssisav5g", buf); + READ_FROM_NVRAM(rssismc5g, "rssismc5g", buf); + READ_FROM_NVRAM(rssismf5g, "rssismf5g", buf); + READ_FROM_NVRAM(bxa5g, "bxa5g", buf); + READ_FROM_NVRAM(cck2gpo, "cck2gpo", buf); + READ_FROM_NVRAM(ofdm2gpo, "ofdm2gpo", buf); + READ_FROM_NVRAM(ofdm5glpo, "ofdm5glpo", buf); + READ_FROM_NVRAM(ofdm5gpo, "ofdm5gpo", buf); + READ_FROM_NVRAM(ofdm5ghpo, "ofdm5ghpo", buf); + + if (nvram_getenv("boardflags", buf, sizeof(buf)) >= 0) { + boardflags = simple_strtoul(buf, NULL, 0); + if (boardflags) { + sprom->boardflags_lo = (boardflags & 0x0000FFFFU); + sprom->boardflags_hi = (boardflags & 0xFFFF0000U) >> 16; + } } - - for (;;) { - dest[i++] = (char) simple_strtoul(str, NULL, 16); - str += 2; - if (!*str++ || i == 6) - break; + if (nvram_getenv("boardflags2", buf, sizeof(buf)) >= 0) { + boardflags = simple_strtoul(buf, NULL, 0); + if (boardflags) { + sprom->boardflags2_lo = (boardflags & 0x0000FFFFU); + sprom->boardflags2_hi = (boardflags & 0xFFFF0000U) >> 16; + } } } static int bcm47xx_get_invariants(struct ssb_bus *bus, struct ssb_init_invariants *iv) { - char buf[100]; + char buf[20]; /* Fill boardinfo structure */ memset(&(iv->boardinfo), 0 , sizeof(struct ssb_boardinfo)); - if (cfe_getenv("boardvendor", buf, sizeof(buf)) >= 0 || - nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0) - iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0); - if (cfe_getenv("boardtype", buf, sizeof(buf)) >= 0 || - nvram_getenv("boardtype", buf, sizeof(buf)) >= 0) + if (nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0) + iv->boardinfo.vendor = (u16)simple_strtoul(buf, NULL, 0); + else + iv->boardinfo.vendor = SSB_BOARDVENDOR_BCM; + if (nvram_getenv("boardtype", buf, sizeof(buf)) >= 0) iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0); - if (cfe_getenv("boardrev", buf, sizeof(buf)) >= 0 || - nvram_getenv("boardrev", buf, sizeof(buf)) >= 0) + if (nvram_getenv("boardrev", buf, sizeof(buf)) >= 0) iv->boardinfo.rev = (u16)simple_strtoul(buf, NULL, 0); - /* Fill sprom structure */ - memset(&(iv->sprom), 0, sizeof(struct ssb_sprom)); - iv->sprom.revision = 3; - - if (cfe_getenv("et0macaddr", buf, sizeof(buf)) >= 0 || - nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0) - str2eaddr(buf, iv->sprom.et0mac); + bcm47xx_fill_sprom(&iv->sprom); - if (cfe_getenv("et1macaddr", buf, sizeof(buf)) >= 0 || - nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0) - str2eaddr(buf, iv->sprom.et1mac); - - if (cfe_getenv("et0phyaddr", buf, sizeof(buf)) >= 0 || - nvram_getenv("et0phyaddr", buf, sizeof(buf)) >= 0) - iv->sprom.et0phyaddr = simple_strtoul(buf, NULL, 0); - - if (cfe_getenv("et1phyaddr", buf, sizeof(buf)) >= 0 || - nvram_getenv("et1phyaddr", buf, sizeof(buf)) >= 0) - iv->sprom.et1phyaddr = simple_strtoul(buf, NULL, 0); - - if (cfe_getenv("et0mdcport", buf, sizeof(buf)) >= 0 || - nvram_getenv("et0mdcport", buf, sizeof(buf)) >= 0) - iv->sprom.et0mdcport = simple_strtoul(buf, NULL, 10); - - if (cfe_getenv("et1mdcport", buf, sizeof(buf)) >= 0 || - nvram_getenv("et1mdcport", buf, sizeof(buf)) >= 0) - iv->sprom.et1mdcport = simple_strtoul(buf, NULL, 10); + if (nvram_getenv("cardbus", buf, sizeof(buf)) >= 0) + iv->has_cardbus_slot = !!simple_strtoul(buf, NULL, 10); return 0; } @@ -126,12 +169,28 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus, void __init plat_mem_setup(void) { int err; + char buf[100]; + struct ssb_mipscore *mcore; err = ssb_bus_ssbbus_register(&ssb_bcm47xx, SSB_ENUM_BASE, bcm47xx_get_invariants); if (err) panic("Failed to initialize SSB bus (err %d)\n", err); + mcore = &ssb_bcm47xx.mipscore; + if (nvram_getenv("kernel_args", buf, sizeof(buf)) >= 0) { + if (strstr(buf, "console=ttyS1")) { + struct ssb_serial_port port; + + printk(KERN_DEBUG "Swapping serial ports!\n"); + /* swap serial ports */ + memcpy(&port, &mcore->serial_ports[0], sizeof(port)); + memcpy(&mcore->serial_ports[0], &mcore->serial_ports[1], + sizeof(port)); + memcpy(&mcore->serial_ports[1], &port, sizeof(port)); + } + } + _machine_restart = bcm47xx_machine_restart; _machine_halt = bcm47xx_machine_halt; pm_power_off = bcm47xx_machine_halt; diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 06d59dcbe243..86877539c6e8 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -111,8 +111,8 @@ * These are the PRID's for when 23:16 == PRID_COMP_BROADCOM */ -#define PRID_IMP_BMIPS4KC 0x4000 -#define PRID_IMP_BMIPS32 0x8000 +#define PRID_IMP_BMIPS32_REV4 0x4000 +#define PRID_IMP_BMIPS32_REV8 0x8000 #define PRID_IMP_BMIPS3300 0x9000 #define PRID_IMP_BMIPS3300_ALT 0x9100 #define PRID_IMP_BMIPS3300_BUG 0x0000 diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index fd1d39eb7431..455c0ac7d4ea 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -249,7 +249,8 @@ extern struct mips_abi mips_abi_n32; #define SET_PERSONALITY(ex) \ do { \ - set_personality(PER_LINUX); \ + if (personality(current->personality) != PER_LINUX) \ + set_personality(PER_LINUX); \ \ current->thread.abi = &mips_abi; \ } while (0) @@ -296,6 +297,8 @@ do { \ #define SET_PERSONALITY(ex) \ do { \ + unsigned int p; \ + \ clear_thread_flag(TIF_32BIT_REGS); \ clear_thread_flag(TIF_32BIT_ADDR); \ \ @@ -304,7 +307,8 @@ do { \ else \ current->thread.abi = &mips_abi; \ \ - if (current->personality != PER_LINUX32) \ + p = personality(current->personality); \ + if (p != PER_LINUX32 && p != PER_LINUX) \ set_personality(PER_LINUX); \ } while (0) diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index c98bf514ec7d..5b017f23e243 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -329,10 +329,14 @@ static inline void pfx##write##bwlq(type val, \ "dsrl32 %L0, %L0, 0" "\n\t" \ "dsll32 %M0, %M0, 0" "\n\t" \ "or %L0, %L0, %M0" "\n\t" \ + ".set push" "\n\t" \ + ".set noreorder" "\n\t" \ + ".set nomacro" "\n\t" \ "sd %L0, %2" "\n\t" \ + ".set pop" "\n\t" \ ".set mips0" "\n" \ : "=r" (__tmp) \ - : "0" (__val), "m" (*__mem)); \ + : "0" (__val), "R" (*__mem)); \ if (irq) \ local_irq_restore(__flags); \ } else \ @@ -355,12 +359,16 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem) \ local_irq_save(__flags); \ __asm__ __volatile__( \ ".set mips3" "\t\t# __readq" "\n\t" \ + ".set push" "\n\t" \ + ".set noreorder" "\n\t" \ + ".set nomacro" "\n\t" \ "ld %L0, %1" "\n\t" \ + ".set pop" "\n\t" \ "dsra32 %M0, %L0, 0" "\n\t" \ "sll %L0, %L0, 0" "\n\t" \ ".set mips0" "\n" \ : "=r" (__val) \ - : "m" (*__mem)); \ + : "R" (*__mem)); \ if (irq) \ local_irq_restore(__flags); \ } else { \ diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h index 7919d76186bf..07d3fadb2443 100644 --- a/arch/mips/include/asm/mach-ar7/ar7.h +++ b/arch/mips/include/asm/mach-ar7/ar7.h @@ -201,7 +201,6 @@ static inline void ar7_device_off(u32 bit) } int __init ar7_gpio_init(void); - -int __init ar7_gpio_init(void); +void __init ar7_init_clocks(void); #endif /* __AR7_H__ */ diff --git a/arch/mips/include/asm/mach-bcm47xx/nvram.h b/arch/mips/include/asm/mach-bcm47xx/nvram.h index c58ebd8bc155..9759588ba3cf 100644 --- a/arch/mips/include/asm/mach-bcm47xx/nvram.h +++ b/arch/mips/include/asm/mach-bcm47xx/nvram.h @@ -12,6 +12,7 @@ #define __NVRAM_H #include <linux/types.h> +#include <linux/kernel.h> struct nvram_header { u32 magic; @@ -36,4 +37,10 @@ struct nvram_header { extern int nvram_getenv(char *name, char *val, size_t val_len); +static inline void nvram_parse_macaddr(char *buf, u8 *macaddr) +{ + sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &macaddr[0], &macaddr[1], + &macaddr[2], &macaddr[3], &macaddr[4], &macaddr[5]); +} + #endif diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 5742bb4d78f4..5c0a3575877c 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -5,7 +5,7 @@ * * Copyright (c) 2009 Qi Hardware inc., * Author: Xiangfu Liu <xiangfu@qi-hardware.com> - * Copyright 2010, Lars-Petrer Clausen <lars@metafoo.de> + * Copyright 2010, Lars-Peter Clausen <lars@metafoo.de> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 or later @@ -235,7 +235,7 @@ static const unsigned int qi_lb60_keypad_rows[] = { QI_LB60_GPIO_KEYIN(3), QI_LB60_GPIO_KEYIN(4), QI_LB60_GPIO_KEYIN(5), - QI_LB60_GPIO_KEYIN(7), + QI_LB60_GPIO_KEYIN(6), QI_LB60_GPIO_KEYIN8, }; diff --git a/arch/mips/jz4740/platform.c b/arch/mips/jz4740/platform.c index 95bc2b5b14f1..1cc9e544d16b 100644 --- a/arch/mips/jz4740/platform.c +++ b/arch/mips/jz4740/platform.c @@ -208,7 +208,7 @@ struct platform_device jz4740_i2s_device = { /* PCM */ struct platform_device jz4740_pcm_device = { - .name = "jz4740-pcm", + .name = "jz4740-pcm-audio", .id = -1, }; diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c index cfeac15eb2e4..4a70407f55bb 100644 --- a/arch/mips/jz4740/prom.c +++ b/arch/mips/jz4740/prom.c @@ -23,7 +23,7 @@ #include <asm/bootinfo.h> #include <asm/mach-jz4740/base.h> -void jz4740_init_cmdline(int argc, char *argv[]) +static __init void jz4740_init_cmdline(int argc, char *argv[]) { unsigned int count = COMMAND_LINE_SIZE - 1; int i; diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 2f4d7a99bcc2..98c5a9737c14 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -32,7 +32,7 @@ static int mips_next_event(unsigned long delta, cnt = read_c0_count(); cnt += delta; write_c0_compare(cnt); - res = ((int)(read_c0_count() - cnt) > 0) ? -ETIME : 0; + res = ((int)(read_c0_count() - cnt) >= 0) ? -ETIME : 0; return res; } diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 71620e19827a..68dae7b6b5db 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -905,7 +905,8 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu) { decode_configs(c); switch (c->processor_id & 0xff00) { - case PRID_IMP_BMIPS32: + case PRID_IMP_BMIPS32_REV4: + case PRID_IMP_BMIPS32_REV8: c->cputype = CPU_BMIPS32; __cpu_name[cpu] = "Broadcom BMIPS32"; break; @@ -933,10 +934,6 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu) __cpu_name[cpu] = "Broadcom BMIPS5000"; c->options |= MIPS_CPU_ULRI; break; - case PRID_IMP_BMIPS4KC: - c->cputype = CPU_4KC; - __cpu_name[cpu] = "MIPS 4Kc"; - break; } } diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 6343b4a5b835..876a75cc376f 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -251,14 +251,15 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz, SYSCALL_DEFINE1(32_personality, unsigned long, personality) { + unsigned int p = personality & 0xffffffff; int ret; - personality &= 0xffffffff; + if (personality(current->personality) == PER_LINUX32 && - personality == PER_LINUX) - personality = PER_LINUX32; - ret = sys_personality(personality); - if (ret == PER_LINUX32) - ret = PER_LINUX; + personality(p) == PER_LINUX) + p = (p & ~PER_MASK) | PER_LINUX32; + ret = sys_personality(p); + if (ret != -1 && personality(ret) == PER_LINUX32) + ret = (ret & ~PER_MASK) | PER_LINUX; return ret; } diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 5c7c6fc07565..183e0d226669 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1047,6 +1047,6 @@ init_hw_perf_events(void) return 0; } -arch_initcall(init_hw_perf_events); +early_initcall(init_hw_perf_events); #endif /* defined(CONFIG_CPU_MIPS32)... */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 99960940d4a4..ae167df73ddd 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -142,7 +142,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs->regs[7] = 0; /* Clear error flag */ childregs->regs[2] = 0; /* Child gets zero as return value */ - regs->regs[2] = p->pid; if (childregs->cp0_status & ST0_CU0) { childregs->regs[28] = (unsigned long) ti; diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index e000b278f024..9dbe58368953 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -100,7 +100,7 @@ void __init device_tree_init(void) return; base = virt_to_phys((void *)initial_boot_params); - size = initial_boot_params->totalsize; + size = be32_to_cpu(initial_boot_params->totalsize); /* Before we do anything, lets reserve the dt blob */ reserve_mem_mach(base, size); diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index 43e7cdc5ded2..c0e81418ba21 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -153,7 +153,7 @@ static void __cpuinit vsmp_init_secondary(void) { extern int gic_present; - /* This is Malta specific: IPI,performance and timer inetrrupts */ + /* This is Malta specific: IPI,performance and timer interrupts */ if (gic_present) change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 | STATUSF_IP7); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 8e9fbe75894e..e97104302541 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -83,7 +83,8 @@ extern asmlinkage void handle_mcheck(void); extern asmlinkage void handle_reserved(void); extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, - struct mips_fpu_struct *ctx, int has_fpu); + struct mips_fpu_struct *ctx, int has_fpu, + void *__user *fault_addr); void (*board_be_init)(void); int (*board_be_handler)(struct pt_regs *regs, int is_fixup); @@ -661,12 +662,36 @@ asmlinkage void do_ov(struct pt_regs *regs) force_sig_info(SIGFPE, &info, current); } +static int process_fpemu_return(int sig, void __user *fault_addr) +{ + if (sig == SIGSEGV || sig == SIGBUS) { + struct siginfo si = {0}; + si.si_addr = fault_addr; + si.si_signo = sig; + if (sig == SIGSEGV) { + if (find_vma(current->mm, (unsigned long)fault_addr)) + si.si_code = SEGV_ACCERR; + else + si.si_code = SEGV_MAPERR; + } else { + si.si_code = BUS_ADRERR; + } + force_sig_info(sig, &si, current); + return 1; + } else if (sig) { + force_sig(sig, current); + return 1; + } else { + return 0; + } +} + /* * XXX Delayed fp exceptions when doing a lazy ctx switch XXX */ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) { - siginfo_t info; + siginfo_t info = {0}; if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) @@ -675,6 +700,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) if (fcr31 & FPU_CSR_UNI_X) { int sig; + void __user *fault_addr = NULL; /* * Unimplemented operation exception. If we've got the full @@ -690,7 +716,8 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) lose_fpu(1); /* Run the emulator */ - sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1); + sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, + &fault_addr); /* * We can't allow the emulated instruction to leave any of @@ -702,8 +729,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) own_fpu(1); /* Using the FPU again. */ /* If something went wrong, signal */ - if (sig) - force_sig(sig, current); + process_fpemu_return(sig, fault_addr); return; } else if (fcr31 & FPU_CSR_INV_X) @@ -996,11 +1022,11 @@ asmlinkage void do_cpu(struct pt_regs *regs) if (!raw_cpu_has_fpu) { int sig; + void __user *fault_addr = NULL; sig = fpu_emulator_cop1Handler(regs, - ¤t->thread.fpu, 0); - if (sig) - force_sig(sig, current); - else + ¤t->thread.fpu, + 0, &fault_addr); + if (!process_fpemu_return(sig, fault_addr)) mt_ase_fp_affinity(); } diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 3eb3cde2f661..6a1fdfef8fde 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -1092,6 +1092,10 @@ static int vpe_open(struct inode *inode, struct file *filp) /* this of-course trashes what was there before... */ v->pbuffer = vmalloc(P_SIZE); + if (!v->pbuffer) { + pr_warning("VPE loader: unable to allocate memory\n"); + return -ENOMEM; + } v->plen = P_SIZE; v->load_addr = NULL; v->len = 0; @@ -1149,10 +1153,9 @@ static int vpe_release(struct inode *inode, struct file *filp) if (ret < 0) v->shared_ptr = NULL; - // cleanup any temp buffers - if (v->pbuffer) - vfree(v->pbuffer); + vfree(v->pbuffer); v->plen = 0; + return ret; } @@ -1169,11 +1172,6 @@ static ssize_t vpe_write(struct file *file, const char __user * buffer, if (v == NULL) return -ENODEV; - if (v->pbuffer == NULL) { - printk(KERN_ERR "VPE loader: no buffer for program\n"); - return -ENOMEM; - } - if ((count + v->len) > v->plen) { printk(KERN_WARNING "VPE loader: elf size too big. Perhaps strip uneeded symbols\n"); diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index 77dc3b20110a..606c8a9efe3b 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -161,16 +161,16 @@ FEXPORT(__bzero) .Lfwd_fixup: PTR_L t0, TI_TASK($28) - LONG_L t0, THREAD_BUADDR(t0) andi a2, 0x3f + LONG_L t0, THREAD_BUADDR(t0) LONG_ADDU a2, t1 jr ra LONG_SUBU a2, t0 .Lpartial_fixup: PTR_L t0, TI_TASK($28) - LONG_L t0, THREAD_BUADDR(t0) andi a2, LONGMASK + LONG_L t0, THREAD_BUADDR(t0) LONG_ADDU a2, t1 jr ra LONG_SUBU a2, t0 diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c index ae4cff97a56c..11b193f848f8 100644 --- a/arch/mips/loongson/common/env.c +++ b/arch/mips/loongson/common/env.c @@ -29,9 +29,9 @@ unsigned long memsize, highmemsize; #define parse_even_earlier(res, option, p) \ do { \ + int ret; \ if (strncmp(option, (char *)p, strlen(option)) == 0) \ - strict_strtol((char *)p + strlen(option"="), \ - 10, &res); \ + ret = strict_strtol((char *)p + strlen(option"="), 10, &res); \ } while (0) void __init prom_init_env(void) diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index b2ad1b0910ff..d32cb0503110 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -64,7 +64,7 @@ static int fpu_emu(struct pt_regs *, struct mips_fpu_struct *, #if __mips >= 4 && __mips != 32 static int fpux_emu(struct pt_regs *, - struct mips_fpu_struct *, mips_instruction); + struct mips_fpu_struct *, mips_instruction, void *__user *); #endif /* Further private data for which no space exists in mips_fpu_struct */ @@ -208,16 +208,23 @@ static inline int cop1_64bit(struct pt_regs *xcp) * Two instructions if the instruction is in a branch delay slot. */ -static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) +static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, + void *__user *fault_addr) { mips_instruction ir; unsigned long emulpc, contpc; unsigned int cond; - if (get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) { + if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; return SIGBUS; } + if (__get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; + return SIGSEGV; + } /* XXX NEC Vr54xx bug workaround */ if ((xcp->cp0_cause & CAUSEF_BD) && !isBranchInstr(&ir)) @@ -245,10 +252,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) #endif return SIGILL; } - if (get_user(ir, (mips_instruction __user *) emulpc)) { + if (!access_ok(VERIFY_READ, emulpc, sizeof(mips_instruction))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)emulpc; return SIGBUS; } + if (__get_user(ir, (mips_instruction __user *) emulpc)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)emulpc; + return SIGSEGV; + } /* __compute_return_epc() will have updated cp0_epc */ contpc = xcp->cp0_epc; /* In order not to confuse ptrace() et al, tweak context */ @@ -269,10 +282,17 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) u64 val; MIPS_FPU_EMU_INC_STATS(loads); - if (get_user(val, va)) { + + if (!access_ok(VERIFY_READ, va, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__get_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } DITOREG(val, MIPSInst_RT(ir)); break; } @@ -284,10 +304,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) MIPS_FPU_EMU_INC_STATS(stores); DIFROMREG(val, MIPSInst_RT(ir)); - if (put_user(val, va)) { + if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__put_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } break; } @@ -297,10 +323,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) u32 val; MIPS_FPU_EMU_INC_STATS(loads); - if (get_user(val, va)) { + if (!access_ok(VERIFY_READ, va, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__get_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } SITOREG(val, MIPSInst_RT(ir)); break; } @@ -312,10 +344,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) MIPS_FPU_EMU_INC_STATS(stores); SIFROMREG(val, MIPSInst_RT(ir)); - if (put_user(val, va)) { + if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__put_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } break; } @@ -440,11 +478,18 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) contpc = (xcp->cp0_epc + (MIPSInst_SIMM(ir) << 2)); - if (get_user(ir, - (mips_instruction __user *) xcp->cp0_epc)) { + if (!access_ok(VERIFY_READ, xcp->cp0_epc, + sizeof(mips_instruction))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; return SIGBUS; } + if (__get_user(ir, + (mips_instruction __user *) xcp->cp0_epc)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; + return SIGSEGV; + } switch (MIPSInst_OPCODE(ir)) { case lwc1_op: @@ -506,9 +551,8 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx) #if __mips >= 4 && __mips != 32 case cop1x_op:{ - int sig; - - if ((sig = fpux_emu(xcp, ctx, ir))) + int sig = fpux_emu(xcp, ctx, ir, fault_addr); + if (sig) return sig; break; } @@ -604,7 +648,7 @@ DEF3OP(nmadd, dp, ieee754dp_mul, ieee754dp_add, ieee754dp_neg); DEF3OP(nmsub, dp, ieee754dp_mul, ieee754dp_sub, ieee754dp_neg); static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, - mips_instruction ir) + mips_instruction ir, void *__user *fault_addr) { unsigned rcsr = 0; /* resulting csr */ @@ -624,10 +668,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, xcp->regs[MIPSInst_FT(ir)]); MIPS_FPU_EMU_INC_STATS(loads); - if (get_user(val, va)) { + if (!access_ok(VERIFY_READ, va, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__get_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } SITOREG(val, MIPSInst_FD(ir)); break; @@ -638,10 +688,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, MIPS_FPU_EMU_INC_STATS(stores); SIFROMREG(val, MIPSInst_FS(ir)); - if (put_user(val, va)) { + if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (put_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } break; case madd_s_op: @@ -701,10 +757,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, xcp->regs[MIPSInst_FT(ir)]); MIPS_FPU_EMU_INC_STATS(loads); - if (get_user(val, va)) { + if (!access_ok(VERIFY_READ, va, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__get_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } DITOREG(val, MIPSInst_FD(ir)); break; @@ -714,10 +776,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, MIPS_FPU_EMU_INC_STATS(stores); DIFROMREG(val, MIPSInst_FS(ir)); - if (put_user(val, va)) { + if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; return SIGBUS; } + if (__put_user(val, va)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = va; + return SIGSEGV; + } break; case madd_d_op: @@ -1242,7 +1310,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, } int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, - int has_fpu) + int has_fpu, void *__user *fault_addr) { unsigned long oldepc, prevepc; mips_instruction insn; @@ -1252,10 +1320,16 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, do { prevepc = xcp->cp0_epc; - if (get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) { + if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) { MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; return SIGBUS; } + if (__get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) { + MIPS_FPU_EMU_INC_STATS(errors); + *fault_addr = (mips_instruction __user *)xcp->cp0_epc; + return SIGSEGV; + } if (insn == 0) xcp->cp0_epc += 4; /* skip nops */ else { @@ -1267,7 +1341,7 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, */ /* convert to ieee library modes */ ieee754_csr.rm = ieee_rm[ieee754_csr.rm]; - sig = cop1Emulate(xcp, ctx); + sig = cop1Emulate(xcp, ctx, fault_addr); /* revert to mips rounding mode */ ieee754_csr.rm = mips_rm[ieee754_csr.rm]; } diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index 4fc1a0fbe007..21ea14efb837 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -288,7 +288,7 @@ int mips_dma_supported(struct device *dev, u64 mask) return plat_dma_supported(dev, mask); } -void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size, +void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { BUG_ON(direction == DMA_NONE); @@ -298,6 +298,8 @@ void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size, __dma_sync((unsigned long)vaddr, size, direction); } +EXPORT_SYMBOL(dma_cache_sync); + static struct dma_map_ops mips_default_dma_map_ops = { .alloc_coherent = mips_dma_alloc_coherent, .free_coherent = mips_dma_free_coherent, diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 505fecad4684..9cca8de00545 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -68,6 +68,9 @@ static struct bcache_ops mips_sc_ops = { */ static inline int mips_sc_is_activated(struct cpuinfo_mips *c) { + unsigned int config2 = read_c0_config2(); + unsigned int tmp; + /* Check the bypass bit (L2B) */ switch (c->cputype) { case CPU_34K: @@ -83,6 +86,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c) c->scache.linesz = 2 << tmp; else return 0; + return 1; } static inline int __init mips_sc_probe(void) diff --git a/arch/mips/pmc-sierra/yosemite/py-console.c b/arch/mips/pmc-sierra/yosemite/py-console.c index b7f1d9c4a8a3..434d7b1a8c6a 100644 --- a/arch/mips/pmc-sierra/yosemite/py-console.c +++ b/arch/mips/pmc-sierra/yosemite/py-console.c @@ -65,11 +65,15 @@ static unsigned char readb_outer_space(unsigned long long phys) __asm__ __volatile__ ( " .set mips3 \n" + " .set push \n" + " .set noreorder \n" + " .set nomacro \n" " ld %0, %1 \n" + " .set pop \n" " lbu %0, (%0) \n" " .set mips0 \n" : "=r" (res) - : "m" (vaddr)); + : "R" (vaddr)); write_c0_status(sr); ssnop_4(); @@ -89,11 +93,15 @@ static void writeb_outer_space(unsigned long long phys, unsigned char c) __asm__ __volatile__ ( " .set mips3 \n" + " .set push \n" + " .set noreorder \n" + " .set nomacro \n" " ld %0, %1 \n" + " .set pop \n" " sb %2, (%0) \n" " .set mips0 \n" : "=&r" (tmp) - : "m" (vaddr), "r" (c)); + : "R" (vaddr), "r" (c)); write_c0_status(sr); ssnop_4(); diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index c308989fc464..41707a245dea 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -82,7 +82,7 @@ int swarm_be_handler(struct pt_regs *regs, int is_fixup) enum swarm_rtc_type { RTC_NONE, RTC_XICOR, - RTC_M4LT81 + RTC_M41T81, }; enum swarm_rtc_type swarm_rtc_type; @@ -96,7 +96,7 @@ void read_persistent_clock(struct timespec *ts) sec = xicor_get_time(); break; - case RTC_M4LT81: + case RTC_M41T81: sec = m41t81_get_time(); break; @@ -115,7 +115,7 @@ int rtc_mips_set_time(unsigned long sec) case RTC_XICOR: return xicor_set_time(sec); - case RTC_M4LT81: + case RTC_M41T81: return m41t81_set_time(sec); case RTC_NONE: @@ -141,7 +141,7 @@ void __init plat_mem_setup(void) if (xicor_probe()) swarm_rtc_type = RTC_XICOR; if (m41t81_probe()) - swarm_rtc_type = RTC_M4LT81; + swarm_rtc_type = RTC_M41T81; #ifdef CONFIG_VT screen_info = (struct screen_info) { diff --git a/arch/mn10300/include/asm/syscall.h b/arch/mn10300/include/asm/syscall.h new file mode 100644 index 000000000000..b44b0bb75a01 --- /dev/null +++ b/arch/mn10300/include/asm/syscall.h @@ -0,0 +1,117 @@ +/* Access to user system call parameters and results + * + * See asm-generic/syscall.h for function descriptions. + * + * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _ASM_SYSCALL_H +#define _ASM_SYSCALL_H + +#include <linux/sched.h> +#include <linux/err.h> + +extern const unsigned long sys_call_table[]; + +static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) +{ + return regs->orig_d0; +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + regs->d0 = regs->orig_d0; +} + +static inline long syscall_get_error(struct task_struct *task, + struct pt_regs *regs) +{ + unsigned long error = regs->d0; + return IS_ERR_VALUE(error) ? error : 0; +} + +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->d0; +} + +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + regs->d0 = (long) error ?: val; +} + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + unsigned long *args) +{ + switch (i) { + case 0: + if (!n--) break; + *args++ = regs->a0; + case 1: + if (!n--) break; + *args++ = regs->d1; + case 2: + if (!n--) break; + *args++ = regs->a3; + case 3: + if (!n--) break; + *args++ = regs->a2; + case 4: + if (!n--) break; + *args++ = regs->d3; + case 5: + if (!n--) break; + *args++ = regs->d2; + case 6: + if (!n--) break; + default: + BUG(); + break; + } +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + const unsigned long *args) +{ + switch (i) { + case 0: + if (!n--) break; + regs->a0 = *args++; + case 1: + if (!n--) break; + regs->d1 = *args++; + case 2: + if (!n--) break; + regs->a3 = *args++; + case 3: + if (!n--) break; + regs->a2 = *args++; + case 4: + if (!n--) break; + regs->d3 = *args++; + case 5: + if (!n--) break; + regs->d2 = *args++; + case 6: + if (!n--) break; + default: + BUG(); + break; + } +} + +#endif /* _ASM_SYSCALL_H */ diff --git a/arch/mn10300/kernel/gdb-io-serial.c b/arch/mn10300/kernel/gdb-io-serial.c index 0d5d63c91dc3..f28dc99c6f72 100644 --- a/arch/mn10300/kernel/gdb-io-serial.c +++ b/arch/mn10300/kernel/gdb-io-serial.c @@ -73,7 +73,8 @@ void gdbstub_io_init(void) GDBPORT_SERIAL_IER = UART_IER_RDI | UART_IER_RLSI; /* permit level 0 IRQs to take place */ - local_change_intr_mask_level(NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); + arch_local_change_intr_mask_level( + NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); } /* diff --git a/arch/mn10300/kernel/gdb-io-ttysm.c b/arch/mn10300/kernel/gdb-io-ttysm.c index 97dfda23342c..abdeea153c89 100644 --- a/arch/mn10300/kernel/gdb-io-ttysm.c +++ b/arch/mn10300/kernel/gdb-io-ttysm.c @@ -87,7 +87,8 @@ void __init gdbstub_io_init(void) tmp = *gdbstub_port->_control; /* permit level 0 IRQs only */ - local_change_intr_mask_level(NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); + arch_local_change_intr_mask_level( + NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); } /* diff --git a/arch/mn10300/kernel/gdb-stub.c b/arch/mn10300/kernel/gdb-stub.c index a5fc3f05309b..b169d99d9f20 100644 --- a/arch/mn10300/kernel/gdb-stub.c +++ b/arch/mn10300/kernel/gdb-stub.c @@ -1194,7 +1194,8 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) asm volatile("mov mdr,%0" : "=d"(mdr)); local_save_flags(epsw); - local_change_intr_mask_level(NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); + arch_local_change_intr_mask_level( + NUM2EPSW_IM(CONFIG_GDBSTUB_IRQ_LEVEL + 1)); gdbstub_store_fpu(); diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c index c2e44597c22b..ac11754ecec5 100644 --- a/arch/mn10300/kernel/irq.c +++ b/arch/mn10300/kernel/irq.c @@ -459,7 +459,7 @@ void migrate_irqs(void) tmp = CROSS_GxICR(irq, new); x &= GxICR_LEVEL | GxICR_ENABLE; - if (GxICR(irq) & GxICR_REQUEST) { + if (GxICR(irq) & GxICR_REQUEST) x |= GxICR_REQUEST | GxICR_DETECT; CROSS_GxICR(irq, new) = x; tmp = CROSS_GxICR(irq, new); diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 0d0f8049a17b..e1b14a6ed544 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -14,7 +14,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c index f860a340acc9..75da468090b9 100644 --- a/arch/mn10300/kernel/time.c +++ b/arch/mn10300/kernel/time.c @@ -40,21 +40,17 @@ unsigned long long sched_clock(void) unsigned long long ll; unsigned l[2]; } tsc64, result; - unsigned long tsc, tmp; + unsigned long tmp; unsigned product[3]; /* 96-bit intermediate value */ /* cnt32_to_63() is not safe with preemption */ preempt_disable(); - /* read the TSC value - */ - tsc = get_cycles(); - - /* expand to 64-bits. + /* expand the tsc to 64-bits. * - sched_clock() must be called once a minute or better or the * following will go horribly wrong - see cnt32_to_63() */ - tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL; + tsc64.ll = cnt32_to_63(get_cycles()) & 0x7fffffffffffffffULL; preempt_enable(); diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c index ba430a03bc7a..30394081d9b6 100644 --- a/arch/parisc/hpux/sys_hpux.c +++ b/arch/parisc/hpux/sys_hpux.c @@ -28,7 +28,6 @@ #include <linux/namei.h> #include <linux/sched.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/utsname.h> #include <linux/vfs.h> diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 5024f643b3b1..d7d94b845dc2 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -75,9 +75,6 @@ static void cpu_unmask_irq(unsigned int irq) smp_send_all_nop(); } -void no_ack_irq(unsigned int irq) { } -void no_end_irq(unsigned int irq) { } - void cpu_ack_irq(unsigned int irq) { unsigned long mask = EIEM_MASK(irq); @@ -241,7 +238,7 @@ int cpu_claim_irq(unsigned int irq, struct irq_chip *type, void *data) /* for iosapic interrupts */ if (type) { - set_irq_chip_and_handler(irq, type, handle_level_irq); + set_irq_chip_and_handler(irq, type, handle_percpu_irq); set_irq_chip_data(irq, data); cpu_unmask_irq(irq); } @@ -392,7 +389,7 @@ static void claim_cpu_irqs(void) int i; for (i = CPU_IRQ_BASE; i <= CPU_IRQ_MAX; i++) { set_irq_chip_and_handler(i, &cpu_interrupt_type, - handle_level_irq); + handle_percpu_irq); } set_irq_handler(TIMER_IRQ, handle_percpu_irq); diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 35c827e94e31..609a331878e7 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -98,7 +98,6 @@ void sys_rt_sigreturn(struct pt_regs *regs, int in_syscall) { struct rt_sigframe __user *frame; - struct siginfo si; sigset_t set; unsigned long usp = (regs->gr[30] & ~(0x01UL)); unsigned long sigframe_size = PARISC_RT_SIGFRAME_SIZE; @@ -178,13 +177,7 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall) give_sigsegv: DBG(1,"sys_rt_sigreturn: Sending SIGSEGV\n"); - si.si_signo = SIGSEGV; - si.si_errno = 0; - si.si_code = SI_KERNEL; - si.si_pid = task_pid_vnr(current); - si.si_uid = current_uid(); - si.si_addr = &frame->uc; - force_sig_info(SIGSEGV, &si, current); + force_sig(SIGSEGV, current); return; } diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 9779ece2b070..88a0ad14a9c9 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -20,7 +20,6 @@ #include <linux/times.h> #include <linux/time.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/sem.h> #include <linux/msg.h> #include <linux/shm.h> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b6447190e1a2..e625e9e034ae 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -4,6 +4,10 @@ config PPC32 bool default y if !PPC64 +config 32BIT + bool + default y if PPC32 + config 64BIT bool default y if PPC64 diff --git a/arch/powerpc/boot/div64.S b/arch/powerpc/boot/div64.S index 722f360a32a9..d271ab542673 100644 --- a/arch/powerpc/boot/div64.S +++ b/arch/powerpc/boot/div64.S @@ -33,9 +33,10 @@ __div64_32: cntlzw r0,r5 # we are shifting the dividend right li r10,-1 # to make it < 2^32, and shifting srw r10,r10,r0 # the divisor right the same amount, - add r9,r4,r10 # rounding up (so the estimate cannot + addc r9,r4,r10 # rounding up (so the estimate cannot andc r11,r6,r10 # ever be too large, only too small) andc r9,r9,r10 + addze r9,r9 or r11,r5,r11 rotlw r9,r9,r0 rotlw r11,r11,r0 diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c index 7c07de0d8943..b150b510510f 100644 --- a/arch/powerpc/kernel/e500-pmu.c +++ b/arch/powerpc/kernel/e500-pmu.c @@ -126,4 +126,4 @@ static int init_e500_pmu(void) return register_fsl_emb_pmu(&e500_pmu); } -arch_initcall(init_e500_pmu); +early_initcall(init_e500_pmu); diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 7a9db64f3f04..42850ee00ada 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -337,7 +337,7 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) /* FP registers 32 -> 63 */ #if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) if (current) - memcpy(mem, current->thread.evr[regno-32], + memcpy(mem, ¤t->thread.evr[regno-32], dbg_reg_def[regno].size); #else /* fp registers not used by kernel, leave zero */ @@ -362,7 +362,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) if (regno >= 32 && regno < 64) { /* FP registers 32 -> 63 */ #if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) - memcpy(current->thread.evr[regno-32], mem, + memcpy(¤t->thread.evr[regno-32], mem, dbg_reg_def[regno].size); #else /* fp registers not used by kernel, leave zero */ diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index 09d72028f317..2cc5e0301d0b 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -414,4 +414,4 @@ static int init_mpc7450_pmu(void) return register_power_pmu(&mpc7450_pmu); } -arch_initcall(init_mpc7450_pmu); +early_initcall(init_mpc7450_pmu); diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 3129c855933c..567480705789 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1379,7 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ - perf_pmu_register(&power_pmu); + perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(power_pmu_notifier); return 0; diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index 7ecca59ddf77..4dcf5f831e9d 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -681,7 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pr_info("%s performance monitor hardware support registered\n", pmu->name); - perf_pmu_register(&fsl_emb_pmu); + perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW); return 0; } diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index 2a361cdda635..ead8b3c2649e 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -613,4 +613,4 @@ static int init_power4_pmu(void) return register_power_pmu(&power4_pmu); } -arch_initcall(init_power4_pmu); +early_initcall(init_power4_pmu); diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index 199de527d411..eca0ac595cb6 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -682,4 +682,4 @@ static int init_power5p_pmu(void) return register_power_pmu(&power5p_pmu); } -arch_initcall(init_power5p_pmu); +early_initcall(init_power5p_pmu); diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index 98b6a729a9dd..d5ff0f64a5e6 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -621,4 +621,4 @@ static int init_power5_pmu(void) return register_power_pmu(&power5_pmu); } -arch_initcall(init_power5_pmu); +early_initcall(init_power5_pmu); diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 84a607bda8fb..31603927e376 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -544,4 +544,4 @@ static int init_power6_pmu(void) return register_power_pmu(&power6_pmu); } -arch_initcall(init_power6_pmu); +early_initcall(init_power6_pmu); diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 852f7b7f6b40..593740fcb799 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -369,4 +369,4 @@ static int init_power7_pmu(void) return register_power_pmu(&power7_pmu); } -arch_initcall(init_power7_pmu); +early_initcall(init_power7_pmu); diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 3fee685de4df..9a6e093858fe 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -494,4 +494,4 @@ static int init_ppc970_pmu(void) return register_power_pmu(&ppc970_pmu); } -arch_initcall(init_ppc970_pmu); +early_initcall(init_ppc970_pmu); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2a178b0ebcdf..ce6f61c6f871 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -497,9 +497,8 @@ static void __init emergency_stack_init(void) } /* - * Called into from start_kernel, after lock_kernel has been called. - * Initializes bootmem, which is unsed to manage page allocation until - * mem_init is called. + * Called into from start_kernel this initializes bootmem, which is used + * to manage page allocation until mem_init is called. */ void __init setup_arch(char **cmdline_p) { diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index b1b6043a56c4..4e5bf1edc0f2 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -23,7 +23,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/sem.h> #include <linux/msg.h> #include <linux/shm.h> diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 83f534d862db..5e9584405c45 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1123,7 +1123,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, else #endif /* CONFIG_PPC_HAS_HASH_64K */ rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize, - subpage_protection(pgdir, ea)); + subpage_protection(mm, ea)); /* Dump some info in case of hash insertion failure, they should * never happen so it is really useful to know if/when they do diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 2c7e801ab20b..6a3997f98dfb 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -92,7 +92,7 @@ static void pte_free_rcu_callback(struct rcu_head *head) static void pte_free_submit(struct pte_freelist_batch *batch) { - call_rcu(&batch->rcu, pte_free_rcu_callback); + call_rcu_sched(&batch->rcu, pte_free_rcu_callback); } void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift) diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index 8b04c54e596f..8526bd9d2aa3 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -138,8 +138,11 @@ cmpldi cr0,r15,0 /* Check for user region */ std r14,EX_TLB_ESR(r12) /* write crazy -1 to frame */ beq normal_tlb_miss + + li r11,_PAGE_PRESENT|_PAGE_BAP_SX /* Base perm */ + oris r11,r11,_PAGE_ACCESSED@h /* XXX replace the RMW cycles with immediate loads + writes */ -1: mfspr r10,SPRN_MAS1 + mfspr r10,SPRN_MAS1 cmpldi cr0,r15,8 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 36c0c449a899..2a030d89bbc6 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -585,6 +585,6 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); /* Finally limit subsequent allocations */ - memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size); + memblock_set_current_limit(first_memblock_base + ppc64_rma_size); } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index fea833e18ad5..e0d703c7fdf7 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -63,6 +63,7 @@ #include <linux/of_gpio.h> #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/fs.h> #include <linux/watchdog.h> #include <linux/miscdevice.h> #include <linux/uaccess.h> diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index c667f0f02c34..3139814f6439 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -47,6 +47,12 @@ config LPARCFG config PPC_PSERIES_DEBUG depends on PPC_PSERIES && PPC_EARLY_DEBUG bool "Enable extra debug logging in platforms/pseries" + help + Say Y here if you want the pseries core to produce a bunch of + debug messages to the system log. Select this if you are having a + problem with the pseries core and want to see more of what is + going on. This does not enable debugging in lpar.c, which must + be manually done due to its verbosity. default y config PPC_SMLPAR diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 34b7dc12e731..17a11c82e6f8 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -21,8 +21,6 @@ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ -#undef DEBUG - #include <linux/delay.h> #include <linux/init.h> #include <linux/list.h> diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4b7a062dee15..5fcc92a12d3e 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -25,8 +25,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#undef DEBUG - #include <linux/pci.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e0b98e71ff47..6c6d7b339aae 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -99,6 +99,7 @@ config S390 select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO select HAVE_GET_USER_PAGES_FAST + select HAVE_ARCH_MUTEX_CPU_RELAX select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index 45e0c6199f36..05221b13ffb1 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -6,6 +6,18 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" +config STRICT_DEVMEM + def_bool y + prompt "Filter access to /dev/mem" + ---help--- + This option restricts access to /dev/mem. If this option is + disabled, you allow userspace access to all memory, including + kernel and userspace memory. Accidental memory access is likely + to be disastrous. + Memory access is required for experts who want to debug the kernel. + + If you are unsure, say Y. + config DEBUG_STRICT_USER_COPY_CHECKS bool "Strict user copy size checks" ---help--- diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 458c1f7fbc18..688271f5f2e4 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,3 +7,5 @@ */ #include <asm-generic/mutex-dec.h> + +#define arch_mutex_cpu_relax() barrier() diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a8729ea7e9ac..3c987e9ec8d6 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -130,6 +130,11 @@ struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); +static inline int devmem_is_allowed(unsigned long pfn) +{ + return 0; +} + #define HAVE_ARCH_FREE_PAGE #define HAVE_ARCH_ALLOC_PAGE diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 1e6449c79ab6..53acaa86dd94 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -25,7 +25,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/sem.h> #include <linux/msg.h> #include <linux/shm.h> diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d60fc4398516..2564793ec2b6 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -30,6 +30,7 @@ #include <asm/sections.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/hardirq.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -212,7 +213,7 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) /* Set the PER control regs, turns on single step for this address */ __ctl_load(kprobe_per_regs, 9, 11); regs->psw.mask |= PSW_MASK_PER; - regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK); + regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); } static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) @@ -239,7 +240,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, __get_cpu_var(current_kprobe) = p; /* Save the interrupt and per flags */ kcb->kprobe_saved_imask = regs->psw.mask & - (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK); + (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT); /* Save the control regs that govern PER */ __ctl_store(kcb->kprobe_saved_ctl, 9, 11); } @@ -316,8 +317,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 1; ss_probe: - if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO)) - local_irq_disable(); prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -350,6 +349,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, struct hlist_node *node, *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; + kprobe_opcode_t *correct_ret_addr = NULL; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -372,10 +372,32 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, /* another task is sharing our hash bucket */ continue; - if (ri->rp && ri->rp->handler) - ri->rp->handler(ri, regs); + orig_ret_address = (unsigned long)ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; orig_ret_address = (unsigned long)ri->ret_addr; + + if (ri->rp && ri->rp->handler) { + ri->ret_addr = correct_ret_addr; + ri->rp->handler(ri, regs); + } + recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) { @@ -387,7 +409,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, break; } } - kretprobe_assert(ri, orig_ret_address, trampoline_address); + regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE; reset_current_kprobe(); @@ -465,8 +487,6 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) goto out; } reset_current_kprobe(); - if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO)) - local_irq_enable(); out: preempt_enable_no_resched(); @@ -482,7 +502,7 @@ out: return 1; } -int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -508,8 +528,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) restore_previous_kprobe(kcb); else { reset_current_kprobe(); - if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO)) - local_irq_enable(); } preempt_enable_no_resched(); break; @@ -553,6 +571,18 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) return 0; } +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + int ret; + + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_disable(); + ret = kprobe_trap_handler(regs, trapnr); + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_restore(regs->psw.mask & ~PSW_MASK_PER); + return ret; +} + /* * Wrapper routine to for handling exceptions. */ @@ -560,8 +590,12 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; + struct pt_regs *regs = args->regs; int ret = NOTIFY_DONE; + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_disable(); + switch (val) { case DIE_BPT: if (kprobe_handler(args->regs)) @@ -572,16 +606,17 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; break; case DIE_TRAP: - /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && - kprobe_fault_handler(args->regs, args->trapnr)) + if (!preemptible() && kprobe_running() && + kprobe_trap_handler(args->regs, args->trapnr)) ret = NOTIFY_STOP; - preempt_enable(); break; default: break; } + + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_restore(regs->psw.mask & ~PSW_MASK_PER); + return ret; } @@ -595,6 +630,7 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) /* setup return addr to the jprobe handler routine */ regs->psw.addr = (unsigned long)(jp->entry) | PSW_ADDR_AMODE; + regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); /* r14 is the function return address */ kcb->jprobe_saved_r14 = (unsigned long)regs->gprs[14]; diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index ac151399ef34..1995c1712fc8 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -95,7 +95,6 @@ EXPORT_SYMBOL_GPL(s390_handle_mcck); static int notrace s390_revalidate_registers(struct mci *mci) { int kill_task; - u64 tmpclock; u64 zero; void *fpt_save_area, *fpt_creg_save_area; @@ -214,11 +213,10 @@ static int notrace s390_revalidate_registers(struct mci *mci) : "0", "cc"); #endif /* Revalidate clock comparator register */ - asm volatile( - " stck 0(%1)\n" - " sckc 0(%1)" - : "=m" (tmpclock) : "a" (&(tmpclock)) : "cc", "memory"); - + if (S390_lowcore.clock_comparator == -1) + set_clock_comparator(S390_lowcore.mcck_clock); + else + set_clock_comparator(S390_lowcore.clock_comparator); /* Check if old PSW is valid */ if (!mci->wp) /* diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 56c8687b29b3..7eff9b7347c0 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include <linux/kernel_stat.h> #include <linux/rcupdate.h> #include <linux/posix-timers.h> +#include <linux/cpu.h> #include <asm/s390_ext.h> #include <asm/timer.h> @@ -566,6 +567,23 @@ void init_cpu_vtimer(void) __ctl_set_bit(0,10); } +static int __cpuinit s390_nohz_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + struct s390_idle_data *idle; + long cpu = (long) hcpu; + + idle = &per_cpu(s390_idle, cpu); + switch (action) { + case CPU_DYING: + case CPU_DYING_FROZEN: + idle->nohz_delay = 0; + default: + break; + } + return NOTIFY_OK; +} + void __init vtime_init(void) { /* request the cpu timer external interrupt */ @@ -574,5 +592,6 @@ void __init vtime_init(void) /* Enable cpu timer interrupts on the boot cpu. */ init_cpu_vtimer(); + cpu_notifier(s390_nohz_notify, 0); } diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 752b362bf651..7c37ec359ec2 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -29,17 +29,21 @@ static void __udelay_disabled(unsigned long long usecs) { unsigned long mask, cr0, cr0_saved; u64 clock_saved; + u64 end; + mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; + end = get_clock() + (usecs << 12); clock_saved = local_tick_disable(); - set_clock_comparator(get_clock() + (usecs << 12)); __ctl_store(cr0_saved, 0, 0); cr0 = (cr0_saved & 0xffff00e0) | 0x00000800; __ctl_load(cr0 , 0, 0); - mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; lockdep_off(); - trace_hardirqs_on(); - __load_psw_mask(mask); - local_irq_disable(); + do { + set_clock_comparator(end); + trace_hardirqs_on(); + __load_psw_mask(mask); + local_irq_disable(); + } while (get_clock() < end); lockdep_on(); __ctl_load(cr0_saved, 0, 0); local_tick_enable(clock_saved); diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 38e641cdd977..45b405ca2567 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -20,18 +20,17 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - unsigned long mask, result; + unsigned long mask; pte_t *ptep, pte; struct page *page; - result = write ? 0 : _PAGE_RO; - mask = result | _PAGE_INVALID | _PAGE_SPECIAL; + mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL; ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr); do { pte = *ptep; barrier(); - if ((pte_val(pte) & mask) != result) + if ((pte_val(pte) & mask) != 0) return 0; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 7f217b3a50a8..2e9d78d21fd3 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -22,7 +22,8 @@ config SUPERH select HAVE_SPARSE_IRQ select RTC_LIB select GENERIC_ATOMIC64 - select GENERIC_HARDIRQS_NO_DEPRECATED + # Support the deprecated APIs until MFD and GPIOLIB catch up. + select GENERIC_HARDIRQS_NO_DEPRECATED if !MFD_SUPPORT && !GPIOLIB help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 2eaeb9e59585..f48c492a68d3 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -720,32 +720,6 @@ static struct platform_device camera_devices[] = { }; /* FSI */ -/* - * FSI-B use external clock which came from da7210. - * So, we should change parent of fsi - */ -#define FCLKBCR 0xa415000c -static void fsimck_init(struct clk *clk) -{ - u32 status = __raw_readl(clk->enable_reg); - - /* use external clock */ - status &= ~0x000000ff; - status |= 0x00000080; - - __raw_writel(status, clk->enable_reg); -} - -static struct clk_ops fsimck_clk_ops = { - .init = fsimck_init, -}; - -static struct clk fsimckb_clk = { - .ops = &fsimck_clk_ops, - .enable_reg = (void __iomem *)FCLKBCR, - .rate = 0, /* unknown */ -}; - static struct sh_fsi_platform_info fsi_info = { .portb_flags = SH_FSI_BRS_INV | SH_FSI_OUT_SLAVE_MODE | @@ -1264,10 +1238,10 @@ static int __init arch_setup(void) /* change parent of FSI B */ clk = clk_get(NULL, "fsib_clk"); if (!IS_ERR(clk)) { - clk_register(&fsimckb_clk); - clk_set_parent(clk, &fsimckb_clk); - clk_set_rate(clk, 11000); - clk_set_rate(&fsimckb_clk, 11000); + /* 48kHz dummy clock was used to make sure 1/1 divide */ + clk_set_rate(&sh7724_fsimckb_clk, 48000); + clk_set_parent(clk, &sh7724_fsimckb_clk); + clk_set_rate(clk, 48000); clk_put(clk); } diff --git a/arch/sh/boards/mach-se/7206/irq.c b/arch/sh/boards/mach-se/7206/irq.c index d961949600fd..9070d7e60704 100644 --- a/arch/sh/boards/mach-se/7206/irq.c +++ b/arch/sh/boards/mach-se/7206/irq.c @@ -140,7 +140,7 @@ void __init init_se7206_IRQ(void) make_se7206_irq(IRQ1_IRQ); /* ATA */ make_se7206_irq(IRQ3_IRQ); /* SLOT / PCM */ - __raw_writew(__raw_readw(INTC_ICR1) | 0x000b, INTC_ICR); /* ICR1 */ + __raw_writew(__raw_readw(INTC_ICR1) | 0x000b, INTC_ICR1); /* ICR1 */ /* FPGA System register setup*/ __raw_writew(0x0000,INTSTS0); /* Clear INTSTS0 */ diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index c31d228fdfc6..527a0cd956b5 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -283,31 +283,6 @@ static struct platform_device ceu1_device = { }; /* FSI */ -/* - * FSI-A use external clock which came from ak464x. - * So, we should change parent of fsi - */ -#define FCLKACR 0xa4150008 -static void fsimck_init(struct clk *clk) -{ - u32 status = __raw_readl(clk->enable_reg); - - /* use external clock */ - status &= ~0x000000ff; - status |= 0x00000080; - __raw_writel(status, clk->enable_reg); -} - -static struct clk_ops fsimck_clk_ops = { - .init = fsimck_init, -}; - -static struct clk fsimcka_clk = { - .ops = &fsimck_clk_ops, - .enable_reg = (void __iomem *)FCLKACR, - .rate = 0, /* unknown */ -}; - /* change J20, J21, J22 pin to 1-2 connection to use slave mode */ static struct sh_fsi_platform_info fsi_info = { .porta_flags = SH_FSI_BRS_INV | @@ -852,37 +827,29 @@ static int __init devices_setup(void) gpio_request(GPIO_FN_KEYOUT0, NULL); /* enable FSI */ - gpio_request(GPIO_FN_FSIMCKB, NULL); gpio_request(GPIO_FN_FSIMCKA, NULL); + gpio_request(GPIO_FN_FSIIASD, NULL); gpio_request(GPIO_FN_FSIOASD, NULL); gpio_request(GPIO_FN_FSIIABCK, NULL); gpio_request(GPIO_FN_FSIIALRCK, NULL); gpio_request(GPIO_FN_FSIOABCK, NULL); gpio_request(GPIO_FN_FSIOALRCK, NULL); gpio_request(GPIO_FN_CLKAUDIOAO, NULL); - gpio_request(GPIO_FN_FSIIBSD, NULL); - gpio_request(GPIO_FN_FSIOBSD, NULL); - gpio_request(GPIO_FN_FSIIBBCK, NULL); - gpio_request(GPIO_FN_FSIIBLRCK, NULL); - gpio_request(GPIO_FN_FSIOBBCK, NULL); - gpio_request(GPIO_FN_FSIOBLRCK, NULL); - gpio_request(GPIO_FN_CLKAUDIOBO, NULL); - gpio_request(GPIO_FN_FSIIASD, NULL); /* set SPU2 clock to 83.4 MHz */ clk = clk_get(NULL, "spu_clk"); - if (clk) { + if (!IS_ERR(clk)) { clk_set_rate(clk, clk_round_rate(clk, 83333333)); clk_put(clk); } /* change parent of FSI A */ clk = clk_get(NULL, "fsia_clk"); - if (clk) { - clk_register(&fsimcka_clk); - clk_set_parent(clk, &fsimcka_clk); - clk_set_rate(clk, 11000); - clk_set_rate(&fsimcka_clk, 11000); + if (!IS_ERR(clk)) { + /* 48kHz dummy clock was used to make sure 1/1 divide */ + clk_set_rate(&sh7724_fsimcka_clk, 48000); + clk_set_parent(clk, &sh7724_fsimcka_clk); + clk_set_rate(clk, 48000); clk_put(clk); } diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 1f4e562c5e8c..82e1eabeac98 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -96,7 +96,7 @@ void kmap_coherent_init(void); void *kmap_coherent(struct page *page, unsigned long addr); void kunmap_coherent(void *kvaddr); -#define PG_dcache_dirty PG_arch_1 +#define PG_dcache_clean PG_arch_1 void cpu_cache_init(void); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 46d5179c9f49..e3c73cdd8c90 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -199,10 +199,13 @@ extern unsigned long get_wchan(struct task_struct *p); #define ARCH_HAS_PREFETCHW static inline void prefetch(void *x) { - __asm__ __volatile__ ("pref @%0\n\t" : : "r" (x) : "memory"); + __builtin_prefetch(x, 0, 3); } -#define prefetchw(x) prefetch(x) +static inline void prefetchw(void *x) +{ + __builtin_prefetch(x, 1, 3); +} #endif #endif /* __KERNEL__ */ diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index 903cd618eb74..d6741fca89a4 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -368,8 +368,9 @@ #define __NR_sendmsg 355 #define __NR_recvmsg 356 #define __NR_recvmmsg 357 +#define __NR_accept4 358 -#define NR_syscalls 358 +#define NR_syscalls 359 #ifdef __KERNEL__ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h index 4c27b68789b3..7eb435999426 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7724.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h @@ -303,4 +303,7 @@ enum { SHDMA_SLAVE_SDHI1_RX, }; +extern struct clk sh7724_fsimcka_clk; +extern struct clk sh7724_fsimckb_clk; + #endif /* __ASM_SH7724_H__ */ diff --git a/arch/sh/kernel/cpu/sh2a/clock-sh7201.c b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c index b26264dc2aef..c509c40cba4b 100644 --- a/arch/sh/kernel/cpu/sh2a/clock-sh7201.c +++ b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c @@ -34,7 +34,7 @@ static const int pfc_divisors[]={1,2,3,4,6,8,12}; static void master_clk_init(struct clk *clk) { - return 10000000 * PLL2 * pll1rate[(__raw_readw(FREQCR) >> 8) & 0x0007]; + clk->rate = 10000000 * PLL2 * pll1rate[(__raw_readw(FREQCR) >> 8) & 0x0007]; } static struct clk_ops sh7201_master_clk_ops = { diff --git a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c index 4eabc68cd753..6282a839e08e 100644 --- a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c @@ -81,8 +81,7 @@ static void shoc_clk_init(struct clk *clk) for (i = 0; i < ARRAY_SIZE(frqcr3_divisors); i++) { int divisor = frqcr3_divisors[i]; - if (clk->ops->set_rate(clk, clk->parent->rate / - divisor, 0) == 0) + if (clk->ops->set_rate(clk, clk->parent->rate / divisor) == 0) break; } @@ -110,7 +109,7 @@ static int shoc_clk_verify_rate(struct clk *clk, unsigned long rate) return 0; } -static int shoc_clk_set_rate(struct clk *clk, unsigned long rate, int algo_id) +static int shoc_clk_set_rate(struct clk *clk, unsigned long rate) { unsigned long frqcr3; unsigned int tmp; diff --git a/arch/sh/kernel/cpu/sh4/perf_event.c b/arch/sh/kernel/cpu/sh4/perf_event.c index dbf3b4bb71fe..748955df018d 100644 --- a/arch/sh/kernel/cpu/sh4/perf_event.c +++ b/arch/sh/kernel/cpu/sh4/perf_event.c @@ -250,4 +250,4 @@ static int __init sh7750_pmu_init(void) return register_sh_pmu(&sh7750_pmu); } -arch_initcall(sh7750_pmu_init); +early_initcall(sh7750_pmu_init); diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c index 0fe2e9329cb2..271c0b325a9a 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c @@ -111,12 +111,21 @@ static struct clk div3_clk = { .parent = &pll_clk, }; +/* External input clock (pin name: FSIMCKA/FSIMCKB ) */ +struct clk sh7724_fsimcka_clk = { +}; + +struct clk sh7724_fsimckb_clk = { +}; + static struct clk *main_clks[] = { &r_clk, &extal_clk, &fll_clk, &pll_clk, &div3_clk, + &sh7724_fsimcka_clk, + &sh7724_fsimckb_clk, }; static void div4_kick(struct clk *clk) @@ -154,16 +163,38 @@ struct clk div4_clks[DIV4_NR] = { [DIV4_M1] = DIV4(FRQCRB, 4, 0x2f7c, CLK_ENABLE_ON_INIT), }; -enum { DIV6_V, DIV6_FA, DIV6_FB, DIV6_I, DIV6_S, DIV6_NR }; +enum { DIV6_V, DIV6_I, DIV6_S, DIV6_NR }; static struct clk div6_clks[DIV6_NR] = { [DIV6_V] = SH_CLK_DIV6(&div3_clk, VCLKCR, 0), - [DIV6_FA] = SH_CLK_DIV6(&div3_clk, FCLKACR, 0), - [DIV6_FB] = SH_CLK_DIV6(&div3_clk, FCLKBCR, 0), [DIV6_I] = SH_CLK_DIV6(&div3_clk, IRDACLKCR, 0), [DIV6_S] = SH_CLK_DIV6(&div3_clk, SPUCLKCR, CLK_ENABLE_ON_INIT), }; +enum { DIV6_FA, DIV6_FB, DIV6_REPARENT_NR }; + +/* Indices are important - they are the actual src selecting values */ +static struct clk *fclkacr_parent[] = { + [0] = &div3_clk, + [1] = NULL, + [2] = &sh7724_fsimcka_clk, + [3] = NULL, +}; + +static struct clk *fclkbcr_parent[] = { + [0] = &div3_clk, + [1] = NULL, + [2] = &sh7724_fsimckb_clk, + [3] = NULL, +}; + +static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = { + [DIV6_FA] = SH_CLK_DIV6_EXT(&div3_clk, FCLKACR, 0, + fclkacr_parent, ARRAY_SIZE(fclkacr_parent), 6, 2), + [DIV6_FB] = SH_CLK_DIV6_EXT(&div3_clk, FCLKBCR, 0, + fclkbcr_parent, ARRAY_SIZE(fclkbcr_parent), 6, 2), +}; + static struct clk mstp_clks[HWBLK_NR] = { SH_HWBLK_CLK(HWBLK_TLB, &div4_clks[DIV4_I], CLK_ENABLE_ON_INIT), SH_HWBLK_CLK(HWBLK_IC, &div4_clks[DIV4_I], CLK_ENABLE_ON_INIT), @@ -240,8 +271,8 @@ static struct clk_lookup lookups[] = { /* DIV6 clocks */ CLKDEV_CON_ID("video_clk", &div6_clks[DIV6_V]), - CLKDEV_CON_ID("fsia_clk", &div6_clks[DIV6_FA]), - CLKDEV_CON_ID("fsib_clk", &div6_clks[DIV6_FB]), + CLKDEV_CON_ID("fsia_clk", &div6_reparent_clks[DIV6_FA]), + CLKDEV_CON_ID("fsib_clk", &div6_reparent_clks[DIV6_FB]), CLKDEV_CON_ID("irda_clk", &div6_clks[DIV6_I]), CLKDEV_CON_ID("spu_clk", &div6_clks[DIV6_S]), @@ -376,6 +407,9 @@ int __init arch_clk_init(void) ret = sh_clk_div6_register(div6_clks, DIV6_NR); if (!ret) + ret = sh_clk_div6_reparent_register(div6_reparent_clks, DIV6_REPARENT_NR); + + if (!ret) ret = sh_hwblk_clk_register(mstp_clks, HWBLK_NR); return ret; diff --git a/arch/sh/kernel/cpu/sh4a/perf_event.c b/arch/sh/kernel/cpu/sh4a/perf_event.c index 580276525731..17e6bebfede0 100644 --- a/arch/sh/kernel/cpu/sh4a/perf_event.c +++ b/arch/sh/kernel/cpu/sh4a/perf_event.c @@ -284,4 +284,4 @@ static int __init sh4a_pmu_init(void) return register_sh_pmu(&sh4a_pmu); } -arch_initcall(sh4a_pmu_init); +early_initcall(sh4a_pmu_init); diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 5a4b33435650..2ee21a47b5af 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -389,7 +389,7 @@ int __cpuinit register_sh_pmu(struct sh_pmu *_pmu) WARN_ON(_pmu->num_events > MAX_HWEVENTS); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(sh_pmu_notifier); return 0; } diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 81f58371613d..8c6a350df751 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -88,7 +88,7 @@ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, int op) } if (op & CACHEFLUSH_I) - flush_cache_all(); + flush_icache_range(addr, addr+len); up_read(¤t->mm->mmap_sem); return 0; diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S index e872e81add8a..6fc347ebe59d 100644 --- a/arch/sh/kernel/syscalls_32.S +++ b/arch/sh/kernel/syscalls_32.S @@ -375,3 +375,4 @@ ENTRY(sys_call_table) .long sys_sendmsg /* 355 */ .long sys_recvmsg .long sys_recvmmsg + .long sys_accept4 diff --git a/arch/sh/kernel/vsyscall/vsyscall-trapa.S b/arch/sh/kernel/vsyscall/vsyscall-trapa.S index 3b6eb34c43fa..3e70f851cdc6 100644 --- a/arch/sh/kernel/vsyscall/vsyscall-trapa.S +++ b/arch/sh/kernel/vsyscall/vsyscall-trapa.S @@ -8,9 +8,9 @@ __kernel_vsyscall: * fill out .eh_frame -- PFM. */ .LEND_vsyscall: .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous .section .eh_frame,"a",@progbits + .previous .LCIE: .ualong .LCIE_end - .LCIE_start .LCIE_start: diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 2cfae81914aa..92eb98633ab0 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -114,7 +114,7 @@ static void sh4_flush_dcache_page(void *arg) struct address_space *mapping = page_mapping(page); if (mapping && !mapping_mapped(mapping)) - set_bit(PG_dcache_dirty, &page->flags); + clear_bit(PG_dcache_clean, &page->flags); else #endif flush_cache_one(CACHE_OC_ADDRESS_ARRAY | @@ -239,7 +239,7 @@ static void sh4_flush_cache_page(void *args) * another ASID than the current one. */ map_coherent = (current_cpu_data.dcache.n_aliases && - !test_bit(PG_dcache_dirty, &page->flags) && + test_bit(PG_dcache_clean, &page->flags) && page_mapped(page)); if (map_coherent) vaddr = kmap_coherent(page, address); diff --git a/arch/sh/mm/cache-sh7705.c b/arch/sh/mm/cache-sh7705.c index f498da1cce7a..7729cca727eb 100644 --- a/arch/sh/mm/cache-sh7705.c +++ b/arch/sh/mm/cache-sh7705.c @@ -139,7 +139,7 @@ static void sh7705_flush_dcache_page(void *arg) struct address_space *mapping = page_mapping(page); if (mapping && !mapping_mapped(mapping)) - set_bit(PG_dcache_dirty, &page->flags); + clear_bit(PG_dcache_clean, &page->flags); else __flush_dcache_page(__pa(page_address(page))); } diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index ba401d137bb9..88d3dc3d30d5 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -60,14 +60,14 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long len) { if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && - !test_bit(PG_dcache_dirty, &page->flags)) { + test_bit(PG_dcache_clean, &page->flags)) { void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(vto, src, len); kunmap_coherent(vto); } else { memcpy(dst, src, len); if (boot_cpu_data.dcache.n_aliases) - set_bit(PG_dcache_dirty, &page->flags); + clear_bit(PG_dcache_clean, &page->flags); } if (vma->vm_flags & VM_EXEC) @@ -79,14 +79,14 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long len) { if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && - !test_bit(PG_dcache_dirty, &page->flags)) { + test_bit(PG_dcache_clean, &page->flags)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); kunmap_coherent(vfrom); } else { memcpy(dst, src, len); if (boot_cpu_data.dcache.n_aliases) - set_bit(PG_dcache_dirty, &page->flags); + clear_bit(PG_dcache_clean, &page->flags); } } @@ -98,7 +98,7 @@ void copy_user_highpage(struct page *to, struct page *from, vto = kmap_atomic(to, KM_USER1); if (boot_cpu_data.dcache.n_aliases && page_mapped(from) && - !test_bit(PG_dcache_dirty, &from->flags)) { + test_bit(PG_dcache_clean, &from->flags)) { vfrom = kmap_coherent(from, vaddr); copy_page(vto, vfrom); kunmap_coherent(vfrom); @@ -141,7 +141,7 @@ void __update_cache(struct vm_area_struct *vma, page = pfn_to_page(pfn); if (pfn_valid(pfn)) { - int dirty = test_and_clear_bit(PG_dcache_dirty, &page->flags); + int dirty = !test_and_set_bit(PG_dcache_clean, &page->flags); if (dirty) __flush_purge_region(page_address(page), PAGE_SIZE); } @@ -153,7 +153,7 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) if (pages_do_alias(addr, vmaddr)) { if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && - !test_bit(PG_dcache_dirty, &page->flags)) { + test_bit(PG_dcache_clean, &page->flags)) { void *kaddr; kaddr = kmap_coherent(page, vmaddr); diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c index 15d74ea42094..ec29e14ec5a8 100644 --- a/arch/sh/mm/kmap.c +++ b/arch/sh/mm/kmap.c @@ -34,7 +34,7 @@ void *kmap_coherent(struct page *page, unsigned long addr) enum fixed_addresses idx; unsigned long vaddr; - BUG_ON(test_bit(PG_dcache_dirty, &page->flags)); + BUG_ON(!test_bit(PG_dcache_clean, &page->flags)); pagefault_disable(); diff --git a/arch/sparc/include/asm/openprom.h b/arch/sparc/include/asm/openprom.h index 81cd43432dc0..47eaafad15ce 100644 --- a/arch/sparc/include/asm/openprom.h +++ b/arch/sparc/include/asm/openprom.h @@ -39,7 +39,7 @@ struct linux_dev_v2_funcs { int (*v2_dev_open)(char *devpath); void (*v2_dev_close)(int d); int (*v2_dev_read)(int d, char *buf, int nbytes); - int (*v2_dev_write)(int d, char *buf, int nbytes); + int (*v2_dev_write)(int d, const char *buf, int nbytes); int (*v2_dev_seek)(int d, int hi, int lo); /* Never issued (multistage load support) */ diff --git a/arch/sparc/include/asm/oplib_32.h b/arch/sparc/include/asm/oplib_32.h index 51296a6f5005..9e5c64084b86 100644 --- a/arch/sparc/include/asm/oplib_32.h +++ b/arch/sparc/include/asm/oplib_32.h @@ -60,25 +60,6 @@ extern char *prom_getbootargs(void); extern char *prom_mapio(char *virt_hint, int io_space, unsigned int phys_addr, unsigned int num_bytes); extern void prom_unmapio(char *virt_addr, unsigned int num_bytes); -/* Device operations. */ - -/* Open the device described by the passed string. Note, that the format - * of the string is different on V0 vs. V2->higher proms. The caller must - * know what he/she is doing! Returns the device descriptor, an int. - */ -extern int prom_devopen(char *device_string); - -/* Close a previously opened device described by the passed integer - * descriptor. - */ -extern int prom_devclose(int device_handle); - -/* Do a seek operation on the device described by the passed integer - * descriptor. - */ -extern void prom_seek(int device_handle, unsigned int seek_hival, - unsigned int seek_lowval); - /* Miscellaneous routines, don't really fit in any category per se. */ /* Reboot the machine with the command line passed. */ @@ -121,19 +102,8 @@ extern int prom_getrev(void); /* Get the prom firmware revision. */ extern int prom_getprev(void); -/* Character operations to/from the console.... */ - -/* Non-blocking get character from console. */ -extern int prom_nbgetchar(void); - -/* Non-blocking put character to console. */ -extern int prom_nbputchar(char character); - -/* Blocking get character from console. */ -extern char prom_getchar(void); - -/* Blocking put character to console. */ -extern void prom_putchar(char character); +/* Write a buffer of characters to the console. */ +extern void prom_console_write_buf(const char *buf, int len); /* Prom's internal routines, don't use in kernel/boot code. */ extern void prom_printf(const char *fmt, ...); @@ -238,7 +208,6 @@ extern int prom_node_has_property(phandle node, char *property); extern int prom_setprop(phandle node, const char *prop_name, char *prop_value, int value_size); -extern phandle prom_pathtoinode(char *path); extern phandle prom_inst2pkg(int); /* Dorking with Bus ranges... */ diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index c9cc078e3e31..8cd0df34e82b 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -67,27 +67,6 @@ extern void prom_init(void *cif_handler, void *cif_stack); /* Boot argument acquisition, returns the boot command line string. */ extern char *prom_getbootargs(void); -/* Device utilities. */ - -/* Device operations. */ - -/* Open the device described by the passed string. Note, that the format - * of the string is different on V0 vs. V2->higher proms. The caller must - * know what he/she is doing! Returns the device descriptor, an int. - */ -extern int prom_devopen(const char *device_string); - -/* Close a previously opened device described by the passed integer - * descriptor. - */ -extern int prom_devclose(int device_handle); - -/* Do a seek operation on the device described by the passed integer - * descriptor. - */ -extern void prom_seek(int device_handle, unsigned int seek_hival, - unsigned int seek_lowval); - /* Miscellaneous routines, don't really fit in any category per se. */ /* Reboot the machine with the command line passed. */ @@ -109,33 +88,14 @@ extern void prom_halt(void) __attribute__ ((noreturn)); /* Halt and power-off the machine. */ extern void prom_halt_power_off(void) __attribute__ ((noreturn)); -/* Set the PROM 'sync' callback function to the passed function pointer. - * When the user gives the 'sync' command at the prom prompt while the - * kernel is still active, the prom will call this routine. - * - */ -typedef int (*callback_func_t)(long *cmd); -extern void prom_setcallback(callback_func_t func_ptr); - /* Acquire the IDPROM of the root node in the prom device tree. This * gets passed a buffer where you would like it stuffed. The return value * is the format type of this idprom or 0xff on error. */ extern unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size); -/* Character operations to/from the console.... */ - -/* Non-blocking get character from console. */ -extern int prom_nbgetchar(void); - -/* Non-blocking put character to console. */ -extern int prom_nbputchar(char character); - -/* Blocking get character from console. */ -extern char prom_getchar(void); - -/* Blocking put character to console. */ -extern void prom_putchar(char character); +/* Write a buffer of characters to the console. */ +extern void prom_console_write_buf(const char *buf, int len); /* Prom's internal routines, don't use in kernel/boot code. */ extern void prom_printf(const char *fmt, ...); @@ -279,9 +239,7 @@ extern phandle prom_finddevice(const char *name); extern int prom_setprop(phandle node, const char *prop_name, char *prop_value, int value_size); -extern phandle prom_pathtoinode(const char *path); extern phandle prom_inst2pkg(int); -extern int prom_service_exists(const char *service_name); extern void prom_sun4v_guest_soft_state(void); extern int prom_ihandle2path(int handle, char *buffer, int bufsize); diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 6e8bfa1786da..4d3dbe3703e9 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -4,8 +4,6 @@ #ifdef CONFIG_PERF_EVENTS #include <asm/ptrace.h> -extern void init_hw_perf_events(void); - #define perf_arch_fetch_caller_regs(regs, ip) \ do { \ unsigned long _pstate, _asi, _pil, _i7, _fp; \ @@ -26,8 +24,6 @@ do { \ (regs)->u_regs[UREG_I6] = _fp; \ (regs)->u_regs[UREG_I7] = _i7; \ } while (0) -#else -static inline void init_hw_perf_events(void) { } #endif #endif diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index 2d51527d810f..f01c42661ee5 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -114,7 +114,7 @@ void __init leon_init_timers(irq_handler_t counter_fn) if (leon3_gptimer_regs && leon3_irqctrl_regs) { LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].val, 0); LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].rld, - (((1000000 / 100) - 1))); + (((1000000 / HZ) - 1))); LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].ctrl, 0); #ifdef CONFIG_SMP @@ -128,7 +128,7 @@ void __init leon_init_timers(irq_handler_t counter_fn) } LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[1].val, 0); - LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[1].rld, (((1000000/100) - 1))); + LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[1].rld, (((1000000/HZ) - 1))); LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[1].ctrl, 0); # endif diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c index 7524689b03d2..16582d85368a 100644 --- a/arch/sparc/kernel/leon_smp.c +++ b/arch/sparc/kernel/leon_smp.c @@ -12,7 +12,6 @@ #include <linux/sched.h> #include <linux/threads.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/init.h> diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index a4bd7ba74c89..300f810142f5 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -270,8 +270,6 @@ int __init nmi_init(void) atomic_set(&nmi_active, -1); } } - if (!err) - init_hw_perf_events(); return err; } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 0d6deb55a2ae..760578687e7c 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1307,20 +1307,23 @@ static bool __init supported_pmu(void) return false; } -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { pr_info("Performance events: "); if (!supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); - return; + return 0; } pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); register_die_notifier(&perf_event_nmi_notifier); + + return 0; } +early_initcall(init_hw_perf_events); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index e6375a750d9a..6db18c6927fb 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -17,7 +17,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/sem.h> #include <linux/msg.h> #include <linux/shm.h> diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 675c9e11ada5..42b282fa6112 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -19,7 +19,6 @@ #include <linux/mman.h> #include <linux/utsname.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/ipc.h> #include <asm/uaccess.h> diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index 12b9f352595f..4491f4cb2695 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -16,7 +16,6 @@ #include <asm/system.h> #include <asm/uaccess.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/perf_event.h> enum direction { diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index b351770cbdd6..3107381e576d 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -9,7 +9,6 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <asm/uaccess.h> diff --git a/arch/sparc/prom/Makefile b/arch/sparc/prom/Makefile index 1b8c073adb44..816c0fa12dc0 100644 --- a/arch/sparc/prom/Makefile +++ b/arch/sparc/prom/Makefile @@ -6,7 +6,6 @@ ccflags := -Werror lib-y := bootstr_$(BITS).o lib-$(CONFIG_SPARC32) += devmap.o -lib-y += devops_$(BITS).o lib-y += init_$(BITS).o lib-$(CONFIG_SPARC32) += memory.o lib-y += misc_$(BITS).o diff --git a/arch/sparc/prom/console_32.c b/arch/sparc/prom/console_32.c index 5340264b78f5..48863108a44c 100644 --- a/arch/sparc/prom/console_32.c +++ b/arch/sparc/prom/console_32.c @@ -16,63 +16,26 @@ extern void restore_current(void); -/* Non blocking get character from console input device, returns -1 - * if no input was taken. This can be used for polling. - */ -int -prom_nbgetchar(void) -{ - static char inc; - int i = -1; - unsigned long flags; - - spin_lock_irqsave(&prom_lock, flags); - switch(prom_vers) { - case PROM_V0: - i = (*(romvec->pv_nbgetchar))(); - break; - case PROM_V2: - case PROM_V3: - if( (*(romvec->pv_v2devops).v2_dev_read)(*romvec->pv_v2bootargs.fd_stdin , &inc, 0x1) == 1) { - i = inc; - } else { - i = -1; - } - break; - default: - i = -1; - break; - }; - restore_current(); - spin_unlock_irqrestore(&prom_lock, flags); - return i; /* Ugh, we could spin forever on unsupported proms ;( */ -} - /* Non blocking put character to console device, returns -1 if * unsuccessful. */ -int -prom_nbputchar(char c) +static int prom_nbputchar(const char *buf) { - static char outc; unsigned long flags; int i = -1; spin_lock_irqsave(&prom_lock, flags); switch(prom_vers) { case PROM_V0: - i = (*(romvec->pv_nbputchar))(c); + i = (*(romvec->pv_nbputchar))(*buf); break; case PROM_V2: case PROM_V3: - outc = c; - if( (*(romvec->pv_v2devops).v2_dev_write)(*romvec->pv_v2bootargs.fd_stdout, &outc, 0x1) == 1) + if ((*(romvec->pv_v2devops).v2_dev_write)(*romvec->pv_v2bootargs.fd_stdout, + buf, 0x1) == 1) i = 0; - else - i = -1; break; default: - i = -1; break; }; restore_current(); @@ -80,18 +43,14 @@ prom_nbputchar(char c) return i; /* Ugh, we could spin forever on unsupported proms ;( */ } -/* Blocking version of get character routine above. */ -char -prom_getchar(void) +void prom_console_write_buf(const char *buf, int len) { - int character; - while((character = prom_nbgetchar()) == -1) ; - return (char) character; + while (len) { + int n = prom_nbputchar(buf); + if (n) + continue; + len--; + buf++; + } } -/* Blocking version of put character routine above. */ -void -prom_putchar(char c) -{ - while(prom_nbputchar(c) == -1) ; -} diff --git a/arch/sparc/prom/console_64.c b/arch/sparc/prom/console_64.c index 10322dc2f557..ed39e75828bd 100644 --- a/arch/sparc/prom/console_64.c +++ b/arch/sparc/prom/console_64.c @@ -15,85 +15,34 @@ extern int prom_stdin, prom_stdout; -/* Non blocking get character from console input device, returns -1 - * if no input was taken. This can be used for polling. - */ -inline int -prom_nbgetchar(void) -{ - unsigned long args[7]; - char inc; - - args[0] = (unsigned long) "read"; - args[1] = 3; - args[2] = 1; - args[3] = (unsigned int) prom_stdin; - args[4] = (unsigned long) &inc; - args[5] = 1; - args[6] = (unsigned long) -1; - - p1275_cmd_direct(args); - - if (args[6] == 1) - return inc; - return -1; -} - -/* Non blocking put character to console device, returns -1 if - * unsuccessful. - */ -inline int -prom_nbputchar(char c) +static int __prom_console_write_buf(const char *buf, int len) { unsigned long args[7]; - char outc; - - outc = c; + int ret; args[0] = (unsigned long) "write"; args[1] = 3; args[2] = 1; args[3] = (unsigned int) prom_stdout; - args[4] = (unsigned long) &outc; - args[5] = 1; + args[4] = (unsigned long) buf; + args[5] = (unsigned int) len; args[6] = (unsigned long) -1; p1275_cmd_direct(args); - if (args[6] == 1) - return 0; - else + ret = (int) args[6]; + if (ret < 0) return -1; + return ret; } -/* Blocking version of get character routine above. */ -char -prom_getchar(void) -{ - int character; - while((character = prom_nbgetchar()) == -1) ; - return (char) character; -} - -/* Blocking version of put character routine above. */ -void -prom_putchar(char c) +void prom_console_write_buf(const char *buf, int len) { - prom_nbputchar(c); -} - -void -prom_puts(const char *s, int len) -{ - unsigned long args[7]; - - args[0] = (unsigned long) "write"; - args[1] = 3; - args[2] = 1; - args[3] = (unsigned int) prom_stdout; - args[4] = (unsigned long) s; - args[5] = len; - args[6] = (unsigned long) -1; - - p1275_cmd_direct(args); + while (len) { + int n = __prom_console_write_buf(buf, len); + if (n < 0) + continue; + len -= n; + buf += len; + } } diff --git a/arch/sparc/prom/devops_32.c b/arch/sparc/prom/devops_32.c deleted file mode 100644 index 9c5d4687242a..000000000000 --- a/arch/sparc/prom/devops_32.c +++ /dev/null @@ -1,87 +0,0 @@ -/* - * devops.c: Device operations using the PROM. - * - * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu) - */ -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/sched.h> - -#include <asm/openprom.h> -#include <asm/oplib.h> - -extern void restore_current(void); - -/* Open the device described by the string 'dstr'. Returns the handle - * to that device used for subsequent operations on that device. - * Returns -1 on failure. - */ -int -prom_devopen(char *dstr) -{ - int handle; - unsigned long flags; - spin_lock_irqsave(&prom_lock, flags); - switch(prom_vers) { - case PROM_V0: - handle = (*(romvec->pv_v0devops.v0_devopen))(dstr); - if(handle == 0) handle = -1; - break; - case PROM_V2: - case PROM_V3: - handle = (*(romvec->pv_v2devops.v2_dev_open))(dstr); - break; - default: - handle = -1; - break; - }; - restore_current(); - spin_unlock_irqrestore(&prom_lock, flags); - - return handle; -} - -/* Close the device described by device handle 'dhandle'. */ -int -prom_devclose(int dhandle) -{ - unsigned long flags; - spin_lock_irqsave(&prom_lock, flags); - switch(prom_vers) { - case PROM_V0: - (*(romvec->pv_v0devops.v0_devclose))(dhandle); - break; - case PROM_V2: - case PROM_V3: - (*(romvec->pv_v2devops.v2_dev_close))(dhandle); - break; - default: - break; - }; - restore_current(); - spin_unlock_irqrestore(&prom_lock, flags); - return 0; -} - -/* Seek to specified location described by 'seekhi' and 'seeklo' - * for device 'dhandle'. - */ -void -prom_seek(int dhandle, unsigned int seekhi, unsigned int seeklo) -{ - unsigned long flags; - spin_lock_irqsave(&prom_lock, flags); - switch(prom_vers) { - case PROM_V0: - (*(romvec->pv_v0devops.v0_seekdev))(dhandle, seekhi, seeklo); - break; - case PROM_V2: - case PROM_V3: - (*(romvec->pv_v2devops.v2_dev_seek))(dhandle, seekhi, seeklo); - break; - default: - break; - }; - restore_current(); - spin_unlock_irqrestore(&prom_lock, flags); -} diff --git a/arch/sparc/prom/devops_64.c b/arch/sparc/prom/devops_64.c deleted file mode 100644 index a017119e7ef1..000000000000 --- a/arch/sparc/prom/devops_64.c +++ /dev/null @@ -1,67 +0,0 @@ -/* - * devops.c: Device operations using the PROM. - * - * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz) - */ -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/sched.h> - -#include <asm/openprom.h> -#include <asm/oplib.h> - -/* Open the device described by the string 'dstr'. Returns the handle - * to that device used for subsequent operations on that device. - * Returns 0 on failure. - */ -int -prom_devopen(const char *dstr) -{ - unsigned long args[5]; - - args[0] = (unsigned long) "open"; - args[1] = 1; - args[2] = 1; - args[3] = (unsigned long) dstr; - args[4] = (unsigned long) -1; - - p1275_cmd_direct(args); - - return (int) args[4]; -} - -/* Close the device described by device handle 'dhandle'. */ -int -prom_devclose(int dhandle) -{ - unsigned long args[4]; - - args[0] = (unsigned long) "close"; - args[1] = 1; - args[2] = 0; - args[3] = (unsigned int) dhandle; - - p1275_cmd_direct(args); - - return 0; -} - -/* Seek to specified location described by 'seekhi' and 'seeklo' - * for device 'dhandle'. - */ -void -prom_seek(int dhandle, unsigned int seekhi, unsigned int seeklo) -{ - unsigned long args[7]; - - args[0] = (unsigned long) "seek"; - args[1] = 3; - args[2] = 1; - args[3] = (unsigned int) dhandle; - args[4] = seekhi; - args[5] = seeklo; - args[6] = (unsigned long) -1; - - p1275_cmd_direct(args); -} diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c index d24bc44e361e..e4f31d4d3715 100644 --- a/arch/sparc/prom/misc_64.c +++ b/arch/sparc/prom/misc_64.c @@ -18,7 +18,7 @@ #include <asm/system.h> #include <asm/ldc.h> -int prom_service_exists(const char *service_name) +static int prom_service_exists(const char *service_name) { unsigned long args[5]; @@ -150,20 +150,6 @@ void prom_halt_power_off(void) prom_halt(); } -/* Set prom sync handler to call function 'funcp'. */ -void prom_setcallback(callback_func_t funcp) -{ - unsigned long args[5]; - if (!funcp) - return; - args[0] = (unsigned long) "set-callback"; - args[1] = 1; - args[2] = 1; - args[3] = (unsigned long) funcp; - args[4] = (unsigned long) -1; - p1275_cmd_direct(args); -} - /* Get the idprom and stuff it into buffer 'idbuf'. Returns the * format type. 'num_bytes' is the number of bytes that your idbuf * has space for. Returns 0xff on error. diff --git a/arch/sparc/prom/printf.c b/arch/sparc/prom/printf.c index ca869266b9f3..d9682f06b3b0 100644 --- a/arch/sparc/prom/printf.c +++ b/arch/sparc/prom/printf.c @@ -15,22 +15,45 @@ #include <linux/kernel.h> #include <linux/compiler.h> +#include <linux/spinlock.h> #include <asm/openprom.h> #include <asm/oplib.h> +#define CONSOLE_WRITE_BUF_SIZE 1024 + static char ppbuf[1024]; +static char console_write_buf[CONSOLE_WRITE_BUF_SIZE]; +static DEFINE_RAW_SPINLOCK(console_write_lock); void notrace prom_write(const char *buf, unsigned int n) { - char ch; + unsigned int dest_len; + unsigned long flags; + char *dest; + + dest = console_write_buf; + raw_spin_lock_irqsave(&console_write_lock, flags); - while (n != 0) { - --n; - if ((ch = *buf++) == '\n') - prom_putchar('\r'); - prom_putchar(ch); + dest_len = 0; + while (n-- != 0) { + char ch = *buf++; + if (ch == '\n') { + *dest++ = '\r'; + dest_len++; + } + *dest++ = ch; + dest_len++; + if (dest_len >= CONSOLE_WRITE_BUF_SIZE - 1) { + prom_console_write_buf(console_write_buf, dest_len); + dest = console_write_buf; + dest_len = 0; + } } + if (dest_len) + prom_console_write_buf(console_write_buf, dest_len); + + raw_spin_unlock_irqrestore(&console_write_lock, flags); } void notrace prom_printf(const char *fmt, ...) diff --git a/arch/sparc/prom/tree_32.c b/arch/sparc/prom/tree_32.c index 63e08e149774..535e2e69ac1d 100644 --- a/arch/sparc/prom/tree_32.c +++ b/arch/sparc/prom/tree_32.c @@ -342,19 +342,3 @@ phandle prom_inst2pkg(int inst) if (node == -1) return 0; return node; } - -/* Return 'node' assigned to a particular prom 'path' - * FIXME: Should work for v0 as well - */ -phandle prom_pathtoinode(char *path) -{ - phandle node; - int inst; - - inst = prom_devopen (path); - if (inst == -1) return 0; - node = prom_inst2pkg (inst); - prom_devclose (inst); - if (node == -1) return 0; - return node; -} diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c index 691be68932f8..d93660048376 100644 --- a/arch/sparc/prom/tree_64.c +++ b/arch/sparc/prom/tree_64.c @@ -374,24 +374,6 @@ inline phandle prom_inst2pkg(int inst) return node; } -/* Return 'node' assigned to a particular prom 'path' - * FIXME: Should work for v0 as well - */ -phandle prom_pathtoinode(const char *path) -{ - phandle node; - int inst; - - inst = prom_devopen (path); - if (inst == 0) - return 0; - node = prom_inst2pkg(inst); - prom_devclose(inst); - if (node == -1) - return 0; - return node; -} - int prom_ihandle2path(int handle, char *buffer, int bufsize) { unsigned long args[7]; diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 07ec8a865c1d..e11b5fcb70eb 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -329,6 +329,18 @@ endmenu # Tilera-specific configuration menu "Bus options" +config PCI + bool "PCI support" + default y + select PCI_DOMAINS + ---help--- + Enable PCI root complex support, so PCIe endpoint devices can + be attached to the Tile chip. Many, but not all, PCI devices + are supported under Tilera's root complex driver. + +config PCI_DOMAINS + bool + config NO_IOMEM def_bool !PCI diff --git a/arch/tile/include/asm/cacheflush.h b/arch/tile/include/asm/cacheflush.h index c5741da4eeac..14a3f8556ace 100644 --- a/arch/tile/include/asm/cacheflush.h +++ b/arch/tile/include/asm/cacheflush.h @@ -137,4 +137,56 @@ static inline void finv_buffer(void *buffer, size_t size) mb_incoherent(); } +/* + * Flush & invalidate a VA range that is homed remotely on a single core, + * waiting until the memory controller holds the flushed values. + */ +static inline void finv_buffer_remote(void *buffer, size_t size) +{ + char *p; + int i; + + /* + * Flush and invalidate the buffer out of the local L1/L2 + * and request the home cache to flush and invalidate as well. + */ + __finv_buffer(buffer, size); + + /* + * Wait for the home cache to acknowledge that it has processed + * all the flush-and-invalidate requests. This does not mean + * that the flushed data has reached the memory controller yet, + * but it does mean the home cache is processing the flushes. + */ + __insn_mf(); + + /* + * Issue a load to the last cache line, which can't complete + * until all the previously-issued flushes to the same memory + * controller have also completed. If we weren't striping + * memory, that one load would be sufficient, but since we may + * be, we also need to back up to the last load issued to + * another memory controller, which would be the point where + * we crossed an 8KB boundary (the granularity of striping + * across memory controllers). Keep backing up and doing this + * until we are before the beginning of the buffer, or have + * hit all the controllers. + */ + for (i = 0, p = (char *)buffer + size - 1; + i < (1 << CHIP_LOG_NUM_MSHIMS()) && p >= (char *)buffer; + ++i) { + const unsigned long STRIPE_WIDTH = 8192; + + /* Force a load instruction to issue. */ + *(volatile char *)p; + + /* Jump to end of previous stripe. */ + p -= STRIPE_WIDTH; + p = (char *)((unsigned long)p | (STRIPE_WIDTH - 1)); + } + + /* Wait for the loads (and thus flushes) to have completed. */ + __insn_mf(); +} + #endif /* _ASM_TILE_CACHEFLUSH_H */ diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h index ee43328713ab..d3cbb9b14cbe 100644 --- a/arch/tile/include/asm/io.h +++ b/arch/tile/include/asm/io.h @@ -55,9 +55,6 @@ extern void iounmap(volatile void __iomem *addr); #define ioremap_writethrough(physaddr, size) ioremap(physaddr, size) #define ioremap_fullcache(physaddr, size) ioremap(physaddr, size) -void __iomem *ioport_map(unsigned long port, unsigned int len); -extern inline void ioport_unmap(void __iomem *addr) {} - #define mmiowb() /* Conversion between virtual and physical mappings. */ @@ -189,12 +186,22 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, * we never run, uses them unconditionally. */ -static inline int ioport_panic(void) +static inline long ioport_panic(void) { panic("inb/outb and friends do not exist on tile"); return 0; } +static inline void __iomem *ioport_map(unsigned long port, unsigned int len) +{ + return (void __iomem *) ioport_panic(); +} + +static inline void ioport_unmap(void __iomem *addr) +{ + ioport_panic(); +} + static inline u8 inb(unsigned long addr) { return ioport_panic(); diff --git a/arch/tile/include/asm/pci-bridge.h b/arch/tile/include/asm/pci-bridge.h deleted file mode 100644 index e853b0e2793b..000000000000 --- a/arch/tile/include/asm/pci-bridge.h +++ /dev/null @@ -1,117 +0,0 @@ -/* - * Copyright 2010 Tilera Corporation. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for - * more details. - */ - -#ifndef _ASM_TILE_PCI_BRIDGE_H -#define _ASM_TILE_PCI_BRIDGE_H - -#include <linux/ioport.h> -#include <linux/pci.h> - -struct device_node; -struct pci_controller; - -/* - * pci_io_base returns the memory address at which you can access - * the I/O space for PCI bus number `bus' (or NULL on error). - */ -extern void __iomem *pci_bus_io_base(unsigned int bus); -extern unsigned long pci_bus_io_base_phys(unsigned int bus); -extern unsigned long pci_bus_mem_base_phys(unsigned int bus); - -/* Allocate a new PCI host bridge structure */ -extern struct pci_controller *pcibios_alloc_controller(void); - -/* Helper function for setting up resources */ -extern void pci_init_resource(struct resource *res, unsigned long start, - unsigned long end, int flags, char *name); - -/* Get the PCI host controller for a bus */ -extern struct pci_controller *pci_bus_to_hose(int bus); - -/* - * Structure of a PCI controller (host bridge) - */ -struct pci_controller { - int index; /* PCI domain number */ - struct pci_bus *root_bus; - - int first_busno; - int last_busno; - - int hv_cfg_fd[2]; /* config{0,1} fds for this PCIe controller */ - int hv_mem_fd; /* fd to Hypervisor for MMIO operations */ - - struct pci_ops *ops; - - int irq_base; /* Base IRQ from the Hypervisor */ - int plx_gen1; /* flag for PLX Gen 1 configuration */ - - /* Address ranges that are routed to this controller/bridge. */ - struct resource mem_resources[3]; -}; - -static inline struct pci_controller *pci_bus_to_host(struct pci_bus *bus) -{ - return bus->sysdata; -} - -extern void setup_indirect_pci_nomap(struct pci_controller *hose, - void __iomem *cfg_addr, void __iomem *cfg_data); -extern void setup_indirect_pci(struct pci_controller *hose, - u32 cfg_addr, u32 cfg_data); -extern void setup_grackle(struct pci_controller *hose); - -extern unsigned char common_swizzle(struct pci_dev *, unsigned char *); - -/* - * The following code swizzles for exactly one bridge. The routine - * common_swizzle below handles multiple bridges. But there are a - * some boards that don't follow the PCI spec's suggestion so we - * break this piece out separately. - */ -static inline unsigned char bridge_swizzle(unsigned char pin, - unsigned char idsel) -{ - return (((pin-1) + idsel) % 4) + 1; -} - -/* - * The following macro is used to lookup irqs in a standard table - * format for those PPC systems that do not already have PCI - * interrupts properly routed. - */ -/* FIXME - double check this */ -#define PCI_IRQ_TABLE_LOOKUP ({ \ - long _ctl_ = -1; \ - if (idsel >= min_idsel && idsel <= max_idsel && pin <= irqs_per_slot) \ - _ctl_ = pci_irq_table[idsel - min_idsel][pin-1]; \ - _ctl_; \ -}) - -/* - * Scan the buses below a given PCI host bridge and assign suitable - * resources to all devices found. - */ -extern int pciauto_bus_scan(struct pci_controller *, int); - -#ifdef CONFIG_PCI -extern unsigned long pci_address_to_pio(phys_addr_t address); -#else -static inline unsigned long pci_address_to_pio(phys_addr_t address) -{ - return (unsigned long)-1; -} -#endif - -#endif /* _ASM_TILE_PCI_BRIDGE_H */ diff --git a/arch/tile/include/asm/pci.h b/arch/tile/include/asm/pci.h index b0c15da2d5d5..c3fc458a0d32 100644 --- a/arch/tile/include/asm/pci.h +++ b/arch/tile/include/asm/pci.h @@ -15,7 +15,29 @@ #ifndef _ASM_TILE_PCI_H #define _ASM_TILE_PCI_H -#include <asm/pci-bridge.h> +#include <linux/pci.h> + +/* + * Structure of a PCI controller (host bridge) + */ +struct pci_controller { + int index; /* PCI domain number */ + struct pci_bus *root_bus; + + int first_busno; + int last_busno; + + int hv_cfg_fd[2]; /* config{0,1} fds for this PCIe controller */ + int hv_mem_fd; /* fd to Hypervisor for MMIO operations */ + + struct pci_ops *ops; + + int irq_base; /* Base IRQ from the Hypervisor */ + int plx_gen1; /* flag for PLX Gen 1 configuration */ + + /* Address ranges that are routed to this controller/bridge. */ + struct resource mem_resources[3]; +}; /* * The hypervisor maps the entirety of CPA-space as bus addresses, so @@ -24,56 +46,12 @@ */ #define PCI_DMA_BUS_IS_PHYS 1 -struct pci_controller *pci_bus_to_hose(int bus); -unsigned char __init common_swizzle(struct pci_dev *dev, unsigned char *pinp); int __init tile_pci_init(void); -void pci_iounmap(struct pci_dev *dev, void __iomem *addr); -void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); -void __devinit pcibios_fixup_bus(struct pci_bus *bus); -int __devinit _tile_cfg_read(struct pci_controller *hose, - int bus, - int slot, - int function, - int offset, - int size, - u32 *val); -int __devinit _tile_cfg_write(struct pci_controller *hose, - int bus, - int slot, - int function, - int offset, - int size, - u32 val); +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {} -/* - * These are used to to config reads and writes in the early stages of - * setup before the driver infrastructure has been set up enough to be - * able to do config reads and writes. - */ -#define early_cfg_read(where, size, value) \ - _tile_cfg_read(controller, \ - current_bus, \ - pci_slot, \ - pci_fn, \ - where, \ - size, \ - value) - -#define early_cfg_write(where, size, value) \ - _tile_cfg_write(controller, \ - current_bus, \ - pci_slot, \ - pci_fn, \ - where, \ - size, \ - value) - - - -#define PCICFG_BYTE 1 -#define PCICFG_WORD 2 -#define PCICFG_DWORD 4 +void __devinit pcibios_fixup_bus(struct pci_bus *bus); #define TILE_NUM_PCIE 2 @@ -88,33 +66,33 @@ static inline int pci_proc_domain(struct pci_bus *bus) } /* - * I/O space is currently not supported. + * pcibios_assign_all_busses() tells whether or not the bus numbers + * should be reassigned, in case the BIOS didn't do it correctly, or + * in case we don't have a BIOS and we want to let Linux do it. */ +static inline int pcibios_assign_all_busses(void) +{ + return 1; +} -#define TILE_PCIE_LOWER_IO 0x0 -#define TILE_PCIE_UPPER_IO 0x10000 -#define TILE_PCIE_PCIE_IO_SIZE 0x0000FFFF - -#define _PAGE_NO_CACHE 0 -#define _PAGE_GUARDED 0 - - -#define pcibios_assign_all_busses() pci_assign_all_buses -extern int pci_assign_all_buses; - +/* + * No special bus mastering setup handling. + */ static inline void pcibios_set_master(struct pci_dev *dev) { - /* No special bus mastering setup handling */ } #define PCIBIOS_MIN_MEM 0 -#define PCIBIOS_MIN_IO TILE_PCIE_LOWER_IO +#define PCIBIOS_MIN_IO 0 /* * This flag tells if the platform is TILEmpower that needs * special configuration for the PLX switch chip. */ -extern int blade_pci; +extern int tile_plx_gen1; + +/* Use any cpu for PCI. */ +#define cpumask_of_pcibus(bus) cpu_online_mask /* implement the pci_ DMA API in terms of the generic device dma_ one */ #include <asm-generic/pci-dma-compat.h> @@ -122,7 +100,4 @@ extern int blade_pci; /* generic pci stuff */ #include <asm-generic/pci.h> -/* Use any cpu for PCI. */ -#define cpumask_of_pcibus(bus) cpu_online_mask - #endif /* _ASM_TILE_PCI_H */ diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h index 1747ff3946b2..a9e7c8760334 100644 --- a/arch/tile/include/asm/processor.h +++ b/arch/tile/include/asm/processor.h @@ -292,8 +292,18 @@ extern int kstack_hash; /* Are we using huge pages in the TLB for kernel data? */ extern int kdata_huge; +/* Support standard Linux prefetching. */ +#define ARCH_HAS_PREFETCH +#define prefetch(x) __builtin_prefetch(x) #define PREFETCH_STRIDE CHIP_L2_LINE_SIZE() +/* Bring a value into the L1D, faulting the TLB if necessary. */ +#ifdef __tilegx__ +#define prefetch_L1(x) __insn_prefetch_l1_fault((void *)(x)) +#else +#define prefetch_L1(x) __insn_prefetch_L1((void *)(x)) +#endif + #else /* __ASSEMBLY__ */ /* Do some slow action (e.g. read a slow SPR). */ diff --git a/arch/tile/include/asm/signal.h b/arch/tile/include/asm/signal.h index c1ee1d61d44c..81d92a45cd4b 100644 --- a/arch/tile/include/asm/signal.h +++ b/arch/tile/include/asm/signal.h @@ -25,7 +25,7 @@ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) struct pt_regs; -int restore_sigcontext(struct pt_regs *, struct sigcontext __user *, long *); +int restore_sigcontext(struct pt_regs *, struct sigcontext __user *); int setup_sigcontext(struct sigcontext __user *, struct pt_regs *); void do_signal(struct pt_regs *regs); #endif diff --git a/arch/tile/include/hv/drv_xgbe_impl.h b/arch/tile/include/hv/drv_xgbe_impl.h new file mode 100644 index 000000000000..3a73b2b44913 --- /dev/null +++ b/arch/tile/include/hv/drv_xgbe_impl.h @@ -0,0 +1,300 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * @file drivers/xgbe/impl.h + * Implementation details for the NetIO library. + */ + +#ifndef __DRV_XGBE_IMPL_H__ +#define __DRV_XGBE_IMPL_H__ + +#include <hv/netio_errors.h> +#include <hv/netio_intf.h> +#include <hv/drv_xgbe_intf.h> + + +/** How many groups we have (log2). */ +#define LOG2_NUM_GROUPS (12) +/** How many groups we have. */ +#define NUM_GROUPS (1 << LOG2_NUM_GROUPS) + +/** Number of output requests we'll buffer per tile. */ +#define EPP_REQS_PER_TILE (32) + +/** Words used in an eDMA command without checksum acceleration. */ +#define EDMA_WDS_NO_CSUM 8 +/** Words used in an eDMA command with checksum acceleration. */ +#define EDMA_WDS_CSUM 10 +/** Total available words in the eDMA command FIFO. */ +#define EDMA_WDS_TOTAL 128 + + +/* + * FIXME: These definitions are internal and should have underscores! + * NOTE: The actual numeric values here are intentional and allow us to + * optimize the concept "if small ... else if large ... else ...", by + * checking for the low bit being set, and then for non-zero. + * These are used as array indices, so they must have the values (0, 1, 2) + * in some order. + */ +#define SIZE_SMALL (1) /**< Small packet queue. */ +#define SIZE_LARGE (2) /**< Large packet queue. */ +#define SIZE_JUMBO (0) /**< Jumbo packet queue. */ + +/** The number of "SIZE_xxx" values. */ +#define NETIO_NUM_SIZES 3 + + +/* + * Default numbers of packets for IPP drivers. These values are chosen + * such that CIPP1 will not overflow its L2 cache. + */ + +/** The default number of small packets. */ +#define NETIO_DEFAULT_SMALL_PACKETS 2750 +/** The default number of large packets. */ +#define NETIO_DEFAULT_LARGE_PACKETS 2500 +/** The default number of jumbo packets. */ +#define NETIO_DEFAULT_JUMBO_PACKETS 250 + + +/** Log2 of the size of a memory arena. */ +#define NETIO_ARENA_SHIFT 24 /* 16 MB */ +/** Size of a memory arena. */ +#define NETIO_ARENA_SIZE (1 << NETIO_ARENA_SHIFT) + + +/** A queue of packets. + * + * This structure partially defines a queue of packets waiting to be + * processed. The queue as a whole is written to by an interrupt handler and + * read by non-interrupt code; this data structure is what's touched by the + * interrupt handler. The other part of the queue state, the read offset, is + * kept in user space, not in hypervisor space, so it is in a separate data + * structure. + * + * The read offset (__packet_receive_read in the user part of the queue + * structure) points to the next packet to be read. When the read offset is + * equal to the write offset, the queue is empty; therefore the queue must + * contain one more slot than the required maximum queue size. + * + * Here's an example of all 3 state variables and what they mean. All + * pointers move left to right. + * + * @code + * I I V V V V I I I I + * 0 1 2 3 4 5 6 7 8 9 10 + * ^ ^ ^ ^ + * | | | + * | | __last_packet_plus_one + * | __buffer_write + * __packet_receive_read + * @endcode + * + * This queue has 10 slots, and thus can hold 9 packets (_last_packet_plus_one + * = 10). The read pointer is at 2, and the write pointer is at 6; thus, + * there are valid, unread packets in slots 2, 3, 4, and 5. The remaining + * slots are invalid (do not contain a packet). + */ +typedef struct { + /** Byte offset of the next notify packet to be written: zero for the first + * packet on the queue, sizeof (netio_pkt_t) for the second packet on the + * queue, etc. */ + volatile uint32_t __packet_write; + + /** Offset of the packet after the last valid packet (i.e., when any + * pointer is incremented to this value, it wraps back to zero). */ + uint32_t __last_packet_plus_one; +} +__netio_packet_queue_t; + + +/** A queue of buffers. + * + * This structure partially defines a queue of empty buffers which have been + * obtained via requests to the IPP. (The elements of the queue are packet + * handles, which are transformed into a full netio_pkt_t when the buffer is + * retrieved.) The queue as a whole is written to by an interrupt handler and + * read by non-interrupt code; this data structure is what's touched by the + * interrupt handler. The other parts of the queue state, the read offset and + * requested write offset, are kept in user space, not in hypervisor space, so + * they are in a separate data structure. + * + * The read offset (__buffer_read in the user part of the queue structure) + * points to the next buffer to be read. When the read offset is equal to the + * write offset, the queue is empty; therefore the queue must contain one more + * slot than the required maximum queue size. + * + * The requested write offset (__buffer_requested_write in the user part of + * the queue structure) points to the slot which will hold the next buffer we + * request from the IPP, once we get around to sending such a request. When + * the requested write offset is equal to the write offset, no requests for + * new buffers are outstanding; when the requested write offset is one greater + * than the read offset, no more requests may be sent. + * + * Note that, unlike the packet_queue, the buffer_queue places incoming + * buffers at decreasing addresses. This makes the check for "is it time to + * wrap the buffer pointer" cheaper in the assembly code which receives new + * buffers, and means that the value which defines the queue size, + * __last_buffer, is different than in the packet queue. Also, the offset + * used in the packet_queue is already scaled by the size of a packet; here we + * use unscaled slot indices for the offsets. (These differences are + * historical, and in the future it's possible that the packet_queue will look + * more like this queue.) + * + * @code + * Here's an example of all 4 state variables and what they mean. Remember: + * all pointers move right to left. + * + * V V V I I R R V V V + * 0 1 2 3 4 5 6 7 8 9 + * ^ ^ ^ ^ + * | | | | + * | | | __last_buffer + * | | __buffer_write + * | __buffer_requested_write + * __buffer_read + * @endcode + * + * This queue has 10 slots, and thus can hold 9 buffers (_last_buffer = 9). + * The read pointer is at 2, and the write pointer is at 6; thus, there are + * valid, unread buffers in slots 2, 1, 0, 9, 8, and 7. The requested write + * pointer is at 4; thus, requests have been made to the IPP for buffers which + * will be placed in slots 6 and 5 when they arrive. Finally, the remaining + * slots are invalid (do not contain a buffer). + */ +typedef struct +{ + /** Ordinal number of the next buffer to be written: 0 for the first slot in + * the queue, 1 for the second slot in the queue, etc. */ + volatile uint32_t __buffer_write; + + /** Ordinal number of the last buffer (i.e., when any pointer is decremented + * below zero, it is reloaded with this value). */ + uint32_t __last_buffer; +} +__netio_buffer_queue_t; + + +/** + * An object for providing Ethernet packets to a process. + */ +typedef struct __netio_queue_impl_t +{ + /** The queue of packets waiting to be received. */ + __netio_packet_queue_t __packet_receive_queue; + /** The intr bit mask that IDs this device. */ + unsigned int __intr_id; + /** Offset to queues of empty buffers, one per size. */ + uint32_t __buffer_queue[NETIO_NUM_SIZES]; + /** The address of the first EPP tile, or -1 if no EPP. */ + /* ISSUE: Actually this is always "0" or "~0". */ + uint32_t __epp_location; + /** The queue ID that this queue represents. */ + unsigned int __queue_id; + /** Number of acknowledgements received. */ + volatile uint32_t __acks_received; + /** Last completion number received for packet_sendv. */ + volatile uint32_t __last_completion_rcv; + /** Number of packets allowed to be outstanding. */ + uint32_t __max_outstanding; + /** First VA available for packets. */ + void* __va_0; + /** First VA in second range available for packets. */ + void* __va_1; + /** Padding to align the "__packets" field to the size of a netio_pkt_t. */ + uint32_t __padding[3]; + /** The packets themselves. */ + netio_pkt_t __packets[0]; +} +netio_queue_impl_t; + + +/** + * An object for managing the user end of a NetIO queue. + */ +typedef struct __netio_queue_user_impl_t +{ + /** The next incoming packet to be read. */ + uint32_t __packet_receive_read; + /** The next empty buffers to be read, one index per size. */ + uint8_t __buffer_read[NETIO_NUM_SIZES]; + /** Where the empty buffer we next request from the IPP will go, one index + * per size. */ + uint8_t __buffer_requested_write[NETIO_NUM_SIZES]; + /** PCIe interface flag. */ + uint8_t __pcie; + /** Number of packets left to be received before we send a credit update. */ + uint32_t __receive_credit_remaining; + /** Value placed in __receive_credit_remaining when it reaches zero. */ + uint32_t __receive_credit_interval; + /** First fast I/O routine index. */ + uint32_t __fastio_index; + /** Number of acknowledgements expected. */ + uint32_t __acks_outstanding; + /** Last completion number requested. */ + uint32_t __last_completion_req; + /** File descriptor for driver. */ + int __fd; +} +netio_queue_user_impl_t; + + +#define NETIO_GROUP_CHUNK_SIZE 64 /**< Max # groups in one IPP request */ +#define NETIO_BUCKET_CHUNK_SIZE 64 /**< Max # buckets in one IPP request */ + + +/** Internal structure used to convey packet send information to the + * hypervisor. FIXME: Actually, it's not used for that anymore, but + * netio_packet_send() still uses it internally. + */ +typedef struct +{ + uint16_t flags; /**< Packet flags (__NETIO_SEND_FLG_xxx) */ + uint16_t transfer_size; /**< Size of packet */ + uint32_t va; /**< VA of start of packet */ + __netio_pkt_handle_t handle; /**< Packet handle */ + uint32_t csum0; /**< First checksum word */ + uint32_t csum1; /**< Second checksum word */ +} +__netio_send_cmd_t; + + +/** Flags used in two contexts: + * - As the "flags" member in the __netio_send_cmd_t, above; used only + * for netio_pkt_send_{prepare,commit}. + * - As part of the flags passed to the various send packet fast I/O calls. + */ + +/** Need acknowledgement on this packet. Note that some code in the + * normal send_pkt fast I/O handler assumes that this is equal to 1. */ +#define __NETIO_SEND_FLG_ACK 0x1 + +/** Do checksum on this packet. (Only used with the __netio_send_cmd_t; + * normal packet sends use a special fast I/O index to denote checksumming, + * and multi-segment sends test the checksum descriptor.) */ +#define __NETIO_SEND_FLG_CSUM 0x2 + +/** Get a completion on this packet. Only used with multi-segment sends. */ +#define __NETIO_SEND_FLG_COMPLETION 0x4 + +/** Position of the number-of-extra-segments value in the flags word. + Only used with multi-segment sends. */ +#define __NETIO_SEND_FLG_XSEG_SHIFT 3 + +/** Width of the number-of-extra-segments value in the flags word. */ +#define __NETIO_SEND_FLG_XSEG_WIDTH 2 + +#endif /* __DRV_XGBE_IMPL_H__ */ diff --git a/arch/tile/include/hv/drv_xgbe_intf.h b/arch/tile/include/hv/drv_xgbe_intf.h new file mode 100644 index 000000000000..146e47d5334b --- /dev/null +++ b/arch/tile/include/hv/drv_xgbe_intf.h @@ -0,0 +1,615 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * @file drv_xgbe_intf.h + * Interface to the hypervisor XGBE driver. + */ + +#ifndef __DRV_XGBE_INTF_H__ +#define __DRV_XGBE_INTF_H__ + +/** + * An object for forwarding VAs and PAs to the hypervisor. + * @ingroup types + * + * This allows the supervisor to specify a number of areas of memory to + * store packet buffers. + */ +typedef struct +{ + /** The physical address of the memory. */ + HV_PhysAddr pa; + /** Page table entry for the memory. This is only used to derive the + * memory's caching mode; the PA bits are ignored. */ + HV_PTE pte; + /** The virtual address of the memory. */ + HV_VirtAddr va; + /** Size (in bytes) of the memory area. */ + int size; + +} +netio_ipp_address_t; + +/** The various pread/pwrite offsets into the hypervisor-level driver. + * @ingroup types + */ +typedef enum +{ + /** Inform the Linux driver of the address of the NetIO arena memory. + * This offset is actually only used to convey information from netio + * to the Linux driver; it never makes it from there to the hypervisor. + * Write-only; takes a uint32_t specifying the VA address. */ + NETIO_FIXED_ADDR = 0x5000000000000000ULL, + + /** Inform the Linux driver of the size of the NetIO arena memory. + * This offset is actually only used to convey information from netio + * to the Linux driver; it never makes it from there to the hypervisor. + * Write-only; takes a uint32_t specifying the VA size. */ + NETIO_FIXED_SIZE = 0x5100000000000000ULL, + + /** Register current tile with IPP. Write then read: write, takes a + * netio_input_config_t, read returns a pointer to a netio_queue_impl_t. */ + NETIO_IPP_INPUT_REGISTER_OFF = 0x6000000000000000ULL, + + /** Unregister current tile from IPP. Write-only, takes a dummy argument. */ + NETIO_IPP_INPUT_UNREGISTER_OFF = 0x6100000000000000ULL, + + /** Start packets flowing. Write-only, takes a dummy argument. */ + NETIO_IPP_INPUT_INIT_OFF = 0x6200000000000000ULL, + + /** Stop packets flowing. Write-only, takes a dummy argument. */ + NETIO_IPP_INPUT_UNINIT_OFF = 0x6300000000000000ULL, + + /** Configure group (typically we group on VLAN). Write-only: takes an + * array of netio_group_t's, low 24 bits of the offset is the base group + * number times the size of a netio_group_t. */ + NETIO_IPP_INPUT_GROUP_CFG_OFF = 0x6400000000000000ULL, + + /** Configure bucket. Write-only: takes an array of netio_bucket_t's, low + * 24 bits of the offset is the base bucket number times the size of a + * netio_bucket_t. */ + NETIO_IPP_INPUT_BUCKET_CFG_OFF = 0x6500000000000000ULL, + + /** Get/set a parameter. Read or write: read or write data is the parameter + * value, low 32 bits of the offset is a __netio_getset_offset_t. */ + NETIO_IPP_PARAM_OFF = 0x6600000000000000ULL, + + /** Get fast I/O index. Read-only; returns a 4-byte base index value. */ + NETIO_IPP_GET_FASTIO_OFF = 0x6700000000000000ULL, + + /** Configure hijack IP address. Packets with this IPv4 dest address + * go to bucket NETIO_NUM_BUCKETS - 1. Write-only: takes an IP address + * in some standard form. FIXME: Define the form! */ + NETIO_IPP_INPUT_HIJACK_CFG_OFF = 0x6800000000000000ULL, + + /** + * Offsets beyond this point are reserved for the supervisor (although that + * enforcement must be done by the supervisor driver itself). + */ + NETIO_IPP_USER_MAX_OFF = 0x6FFFFFFFFFFFFFFFULL, + + /** Register I/O memory. Write-only, takes a netio_ipp_address_t. */ + NETIO_IPP_IOMEM_REGISTER_OFF = 0x7000000000000000ULL, + + /** Unregister I/O memory. Write-only, takes a netio_ipp_address_t. */ + NETIO_IPP_IOMEM_UNREGISTER_OFF = 0x7100000000000000ULL, + + /* Offsets greater than 0x7FFFFFFF can't be used directly from Linux + * userspace code due to limitations in the pread/pwrite syscalls. */ + + /** Drain LIPP buffers. */ + NETIO_IPP_DRAIN_OFF = 0xFA00000000000000ULL, + + /** Supply a netio_ipp_address_t to be used as shared memory for the + * LEPP command queue. */ + NETIO_EPP_SHM_OFF = 0xFB00000000000000ULL, + + /* 0xFC... is currently unused. */ + + /** Stop IPP/EPP tiles. Write-only, takes a dummy argument. */ + NETIO_IPP_STOP_SHIM_OFF = 0xFD00000000000000ULL, + + /** Start IPP/EPP tiles. Write-only, takes a dummy argument. */ + NETIO_IPP_START_SHIM_OFF = 0xFE00000000000000ULL, + + /** Supply packet arena. Write-only, takes an array of + * netio_ipp_address_t values. */ + NETIO_IPP_ADDRESS_OFF = 0xFF00000000000000ULL, +} netio_hv_offset_t; + +/** Extract the base offset from an offset */ +#define NETIO_BASE_OFFSET(off) ((off) & 0xFF00000000000000ULL) +/** Extract the local offset from an offset */ +#define NETIO_LOCAL_OFFSET(off) ((off) & 0x00FFFFFFFFFFFFFFULL) + + +/** + * Get/set offset. + */ +typedef union +{ + struct + { + uint64_t addr:48; /**< Class-specific address */ + unsigned int class:8; /**< Class (e.g., NETIO_PARAM) */ + unsigned int opcode:8; /**< High 8 bits of NETIO_IPP_PARAM_OFF */ + } + bits; /**< Bitfields */ + uint64_t word; /**< Aggregated value to use as the offset */ +} +__netio_getset_offset_t; + +/** + * Fast I/O index offsets (must be contiguous). + */ +typedef enum +{ + NETIO_FASTIO_ALLOCATE = 0, /**< Get empty packet buffer */ + NETIO_FASTIO_FREE_BUFFER = 1, /**< Give buffer back to IPP */ + NETIO_FASTIO_RETURN_CREDITS = 2, /**< Give credits to IPP */ + NETIO_FASTIO_SEND_PKT_NOCK = 3, /**< Send a packet, no checksum */ + NETIO_FASTIO_SEND_PKT_CK = 4, /**< Send a packet, with checksum */ + NETIO_FASTIO_SEND_PKT_VEC = 5, /**< Send a vector of packets */ + NETIO_FASTIO_SENDV_PKT = 6, /**< Sendv one packet */ + NETIO_FASTIO_NUM_INDEX = 7, /**< Total number of fast I/O indices */ +} netio_fastio_index_t; + +/** 3-word return type for Fast I/O call. */ +typedef struct +{ + int err; /**< Error code. */ + uint32_t val0; /**< Value. Meaning depends upon the specific call. */ + uint32_t val1; /**< Value. Meaning depends upon the specific call. */ +} netio_fastio_rv3_t; + +/** 0-argument fast I/O call */ +int __netio_fastio0(uint32_t fastio_index); +/** 1-argument fast I/O call */ +int __netio_fastio1(uint32_t fastio_index, uint32_t arg0); +/** 3-argument fast I/O call, 2-word return value */ +netio_fastio_rv3_t __netio_fastio3_rv3(uint32_t fastio_index, uint32_t arg0, + uint32_t arg1, uint32_t arg2); +/** 4-argument fast I/O call */ +int __netio_fastio4(uint32_t fastio_index, uint32_t arg0, uint32_t arg1, + uint32_t arg2, uint32_t arg3); +/** 6-argument fast I/O call */ +int __netio_fastio6(uint32_t fastio_index, uint32_t arg0, uint32_t arg1, + uint32_t arg2, uint32_t arg3, uint32_t arg4, uint32_t arg5); +/** 9-argument fast I/O call */ +int __netio_fastio9(uint32_t fastio_index, uint32_t arg0, uint32_t arg1, + uint32_t arg2, uint32_t arg3, uint32_t arg4, uint32_t arg5, + uint32_t arg6, uint32_t arg7, uint32_t arg8); + +/** Allocate an empty packet. + * @param fastio_index Fast I/O index. + * @param size Size of the packet to allocate. + */ +#define __netio_fastio_allocate(fastio_index, size) \ + __netio_fastio1((fastio_index) + NETIO_FASTIO_ALLOCATE, size) + +/** Free a buffer. + * @param fastio_index Fast I/O index. + * @param handle Handle for the packet to free. + */ +#define __netio_fastio_free_buffer(fastio_index, handle) \ + __netio_fastio1((fastio_index) + NETIO_FASTIO_FREE_BUFFER, handle) + +/** Increment our receive credits. + * @param fastio_index Fast I/O index. + * @param credits Number of credits to add. + */ +#define __netio_fastio_return_credits(fastio_index, credits) \ + __netio_fastio1((fastio_index) + NETIO_FASTIO_RETURN_CREDITS, credits) + +/** Send packet, no checksum. + * @param fastio_index Fast I/O index. + * @param ackflag Nonzero if we want an ack. + * @param size Size of the packet. + * @param va Virtual address of start of packet. + * @param handle Packet handle. + */ +#define __netio_fastio_send_pkt_nock(fastio_index, ackflag, size, va, handle) \ + __netio_fastio4((fastio_index) + NETIO_FASTIO_SEND_PKT_NOCK, ackflag, \ + size, va, handle) + +/** Send packet, calculate checksum. + * @param fastio_index Fast I/O index. + * @param ackflag Nonzero if we want an ack. + * @param size Size of the packet. + * @param va Virtual address of start of packet. + * @param handle Packet handle. + * @param csum0 Shim checksum header. + * @param csum1 Checksum seed. + */ +#define __netio_fastio_send_pkt_ck(fastio_index, ackflag, size, va, handle, \ + csum0, csum1) \ + __netio_fastio6((fastio_index) + NETIO_FASTIO_SEND_PKT_CK, ackflag, \ + size, va, handle, csum0, csum1) + + +/** Format for the "csum0" argument to the __netio_fastio_send routines + * and LEPP. Note that this is currently exactly identical to the + * ShimProtocolOffloadHeader. + */ +typedef union +{ + struct + { + unsigned int start_byte:7; /**< The first byte to be checksummed */ + unsigned int count:14; /**< Number of bytes to be checksummed. */ + unsigned int destination_byte:7; /**< The byte to write the checksum to. */ + unsigned int reserved:4; /**< Reserved. */ + } bits; /**< Decomposed method of access. */ + unsigned int word; /**< To send out the IDN. */ +} __netio_checksum_header_t; + + +/** Sendv packet with 1 or 2 segments. + * @param fastio_index Fast I/O index. + * @param flags Ack/csum/notify flags in low 3 bits; number of segments minus + * 1 in next 2 bits; expected checksum in high 16 bits. + * @param confno Confirmation number to request, if notify flag set. + * @param csum0 Checksum descriptor; if zero, no checksum. + * @param va_F Virtual address of first segment. + * @param va_L Virtual address of last segment, if 2 segments. + * @param len_F_L Length of first segment in low 16 bits; length of last + * segment, if 2 segments, in high 16 bits. + */ +#define __netio_fastio_sendv_pkt_1_2(fastio_index, flags, confno, csum0, \ + va_F, va_L, len_F_L) \ + __netio_fastio6((fastio_index) + NETIO_FASTIO_SENDV_PKT, flags, confno, \ + csum0, va_F, va_L, len_F_L) + +/** Send packet on PCIe interface. + * @param fastio_index Fast I/O index. + * @param flags Ack/csum/notify flags in low 3 bits. + * @param confno Confirmation number to request, if notify flag set. + * @param csum0 Checksum descriptor; Hard wired 0, not needed for PCIe. + * @param va_F Virtual address of the packet buffer. + * @param va_L Virtual address of last segment, if 2 segments. Hard wired 0. + * @param len_F_L Length of the packet buffer in low 16 bits. + */ +#define __netio_fastio_send_pcie_pkt(fastio_index, flags, confno, csum0, \ + va_F, va_L, len_F_L) \ + __netio_fastio6((fastio_index) + PCIE_FASTIO_SENDV_PKT, flags, confno, \ + csum0, va_F, va_L, len_F_L) + +/** Sendv packet with 3 or 4 segments. + * @param fastio_index Fast I/O index. + * @param flags Ack/csum/notify flags in low 3 bits; number of segments minus + * 1 in next 2 bits; expected checksum in high 16 bits. + * @param confno Confirmation number to request, if notify flag set. + * @param csum0 Checksum descriptor; if zero, no checksum. + * @param va_F Virtual address of first segment. + * @param va_L Virtual address of last segment (third segment if 3 segments, + * fourth segment if 4 segments). + * @param len_F_L Length of first segment in low 16 bits; length of last + * segment in high 16 bits. + * @param va_M0 Virtual address of "middle 0" segment; this segment is sent + * second when there are three segments, and third if there are four. + * @param va_M1 Virtual address of "middle 1" segment; this segment is sent + * second when there are four segments. + * @param len_M0_M1 Length of middle 0 segment in low 16 bits; length of middle + * 1 segment, if 4 segments, in high 16 bits. + */ +#define __netio_fastio_sendv_pkt_3_4(fastio_index, flags, confno, csum0, va_F, \ + va_L, len_F_L, va_M0, va_M1, len_M0_M1) \ + __netio_fastio9((fastio_index) + NETIO_FASTIO_SENDV_PKT, flags, confno, \ + csum0, va_F, va_L, len_F_L, va_M0, va_M1, len_M0_M1) + +/** Send vector of packets. + * @param fastio_index Fast I/O index. + * @param seqno Number of packets transmitted so far on this interface; + * used to decide which packets should be acknowledged. + * @param nentries Number of entries in vector. + * @param va Virtual address of start of vector entry array. + * @return 3-word netio_fastio_rv3_t structure. The structure's err member + * is an error code, or zero if no error. The val0 member is the + * updated value of seqno; it has been incremented by 1 for each + * packet sent. That increment may be less than nentries if an + * error occured, or if some of the entries in the vector contain + * handles equal to NETIO_PKT_HANDLE_NONE. The val1 member is the + * updated value of nentries; it has been decremented by 1 for each + * vector entry processed. Again, that decrement may be less than + * nentries (leaving the returned value positive) if an error + * occurred. + */ +#define __netio_fastio_send_pkt_vec(fastio_index, seqno, nentries, va) \ + __netio_fastio3_rv3((fastio_index) + NETIO_FASTIO_SEND_PKT_VEC, seqno, \ + nentries, va) + + +/** An egress DMA command for LEPP. */ +typedef struct +{ + /** Is this a TSO transfer? + * + * NOTE: This field is always 0, to distinguish it from + * lepp_tso_cmd_t. It must come first! + */ + uint8_t tso : 1; + + /** Unused padding bits. */ + uint8_t _unused : 3; + + /** Should this packet be sent directly from caches instead of DRAM, + * using hash-for-home to locate the packet data? + */ + uint8_t hash_for_home : 1; + + /** Should we compute a checksum? */ + uint8_t compute_checksum : 1; + + /** Is this the final buffer for this packet? + * + * A single packet can be split over several input buffers (a "gather" + * operation). This flag indicates that this is the last buffer + * in a packet. + */ + uint8_t end_of_packet : 1; + + /** Should LEPP advance 'comp_busy' when this DMA is fully finished? */ + uint8_t send_completion : 1; + + /** High bits of Client Physical Address of the start of the buffer + * to be egressed. + * + * NOTE: Only 6 bits are actually needed here, as CPAs are + * currently 38 bits. So two bits could be scavenged from this. + */ + uint8_t cpa_hi; + + /** The number of bytes to be egressed. */ + uint16_t length; + + /** Low 32 bits of Client Physical Address of the start of the buffer + * to be egressed. + */ + uint32_t cpa_lo; + + /** Checksum information (only used if 'compute_checksum'). */ + __netio_checksum_header_t checksum_data; + +} lepp_cmd_t; + + +/** A chunk of physical memory for a TSO egress. */ +typedef struct +{ + /** The low bits of the CPA. */ + uint32_t cpa_lo; + /** The high bits of the CPA. */ + uint16_t cpa_hi : 15; + /** Should this packet be sent directly from caches instead of DRAM, + * using hash-for-home to locate the packet data? + */ + uint16_t hash_for_home : 1; + /** The length in bytes. */ + uint16_t length; +} lepp_frag_t; + + +/** An LEPP command that handles TSO. */ +typedef struct +{ + /** Is this a TSO transfer? + * + * NOTE: This field is always 1, to distinguish it from + * lepp_cmd_t. It must come first! + */ + uint8_t tso : 1; + + /** Unused padding bits. */ + uint8_t _unused : 7; + + /** Size of the header[] array in bytes. It must be in the range + * [40, 127], which are the smallest header for a TCP packet over + * Ethernet and the maximum possible prepend size supported by + * hardware, respectively. Note that the array storage must be + * padded out to a multiple of four bytes so that the following + * LEPP command is aligned properly. + */ + uint8_t header_size; + + /** Byte offset of the IP header in header[]. */ + uint8_t ip_offset; + + /** Byte offset of the TCP header in header[]. */ + uint8_t tcp_offset; + + /** The number of bytes to use for the payload of each packet, + * except of course the last one, which may not have enough bytes. + * This means that each Ethernet packet except the last will have a + * size of header_size + payload_size. + */ + uint16_t payload_size; + + /** The length of the 'frags' array that follows this struct. */ + uint16_t num_frags; + + /** The actual frags. */ + lepp_frag_t frags[0 /* Variable-sized; num_frags entries. */]; + + /* + * The packet header template logically follows frags[], + * but you can't declare that in C. + * + * uint32_t header[header_size_in_words_rounded_up]; + */ + +} lepp_tso_cmd_t; + + +/** An LEPP completion ring entry. */ +typedef void* lepp_comp_t; + + +/** Maximum number of frags for one TSO command. This is adapted from + * linux's "MAX_SKB_FRAGS", and presumably over-estimates by one, for + * our page size of exactly 65536. We add one for a "body" fragment. + */ +#define LEPP_MAX_FRAGS (65536 / HV_PAGE_SIZE_SMALL + 2 + 1) + +/** Total number of bytes needed for an lepp_tso_cmd_t. */ +#define LEPP_TSO_CMD_SIZE(num_frags, header_size) \ + (sizeof(lepp_tso_cmd_t) + \ + (num_frags) * sizeof(lepp_frag_t) + \ + (((header_size) + 3) & -4)) + +/** The size of the lepp "cmd" queue. */ +#define LEPP_CMD_QUEUE_BYTES \ + (((CHIP_L2_CACHE_SIZE() - 2 * CHIP_L2_LINE_SIZE()) / \ + (sizeof(lepp_cmd_t) + sizeof(lepp_comp_t))) * sizeof(lepp_cmd_t)) + +/** The largest possible command that can go in lepp_queue_t::cmds[]. */ +#define LEPP_MAX_CMD_SIZE LEPP_TSO_CMD_SIZE(LEPP_MAX_FRAGS, 128) + +/** The largest possible value of lepp_queue_t::cmd_{head, tail} (inclusive). + */ +#define LEPP_CMD_LIMIT \ + (LEPP_CMD_QUEUE_BYTES - LEPP_MAX_CMD_SIZE) + +/** The maximum number of completions in an LEPP queue. */ +#define LEPP_COMP_QUEUE_SIZE \ + ((LEPP_CMD_LIMIT + sizeof(lepp_cmd_t) - 1) / sizeof(lepp_cmd_t)) + +/** Increment an index modulo the queue size. */ +#define LEPP_QINC(var) \ + (var = __insn_mnz(var - (LEPP_COMP_QUEUE_SIZE - 1), var + 1)) + +/** A queue used to convey egress commands from the client to LEPP. */ +typedef struct +{ + /** Index of first completion not yet processed by user code. + * If this is equal to comp_busy, there are no such completions. + * + * NOTE: This is only read/written by the user. + */ + unsigned int comp_head; + + /** Index of first completion record not yet completed. + * If this is equal to comp_tail, there are no such completions. + * This index gets advanced (modulo LEPP_QUEUE_SIZE) whenever + * a command with the 'completion' bit set is finished. + * + * NOTE: This is only written by LEPP, only read by the user. + */ + volatile unsigned int comp_busy; + + /** Index of the first empty slot in the completion ring. + * Entries from this up to but not including comp_head (in ring order) + * can be filled in with completion data. + * + * NOTE: This is only read/written by the user. + */ + unsigned int comp_tail; + + /** Byte index of first command enqueued for LEPP but not yet processed. + * + * This is always divisible by sizeof(void*) and always <= LEPP_CMD_LIMIT. + * + * NOTE: LEPP advances this counter as soon as it no longer needs + * the cmds[] storage for this entry, but the transfer is not actually + * complete (i.e. the buffer pointed to by the command is no longer + * needed) until comp_busy advances. + * + * If this is equal to cmd_tail, the ring is empty. + * + * NOTE: This is only written by LEPP, only read by the user. + */ + volatile unsigned int cmd_head; + + /** Byte index of first empty slot in the command ring. This field can + * be incremented up to but not equal to cmd_head (because that would + * mean the ring is empty). + * + * This is always divisible by sizeof(void*) and always <= LEPP_CMD_LIMIT. + * + * NOTE: This is read/written by the user, only read by LEPP. + */ + volatile unsigned int cmd_tail; + + /** A ring of variable-sized egress DMA commands. + * + * NOTE: Only written by the user, only read by LEPP. + */ + char cmds[LEPP_CMD_QUEUE_BYTES] + __attribute__((aligned(CHIP_L2_LINE_SIZE()))); + + /** A ring of user completion data. + * NOTE: Only read/written by the user. + */ + lepp_comp_t comps[LEPP_COMP_QUEUE_SIZE] + __attribute__((aligned(CHIP_L2_LINE_SIZE()))); +} lepp_queue_t; + + +/** An internal helper function for determining the number of entries + * available in a ring buffer, given that there is one sentinel. + */ +static inline unsigned int +_lepp_num_free_slots(unsigned int head, unsigned int tail) +{ + /* + * One entry is reserved for use as a sentinel, to distinguish + * "empty" from "full". So we compute + * (head - tail - 1) % LEPP_QUEUE_SIZE, but without using a slow % operation. + */ + return (head - tail - 1) + ((head <= tail) ? LEPP_COMP_QUEUE_SIZE : 0); +} + + +/** Returns how many new comp entries can be enqueued. */ +static inline unsigned int +lepp_num_free_comp_slots(const lepp_queue_t* q) +{ + return _lepp_num_free_slots(q->comp_head, q->comp_tail); +} + +static inline int +lepp_qsub(int v1, int v2) +{ + int delta = v1 - v2; + return delta + ((delta >> 31) & LEPP_COMP_QUEUE_SIZE); +} + + +/** FIXME: Check this from linux, via a new "pwrite()" call. */ +#define LIPP_VERSION 1 + + +/** We use exactly two bytes of alignment padding. */ +#define LIPP_PACKET_PADDING 2 + +/** The minimum size of a "small" buffer (including the padding). */ +#define LIPP_SMALL_PACKET_SIZE 128 + +/* + * NOTE: The following two values should total to less than around + * 13582, to keep the total size used for "lipp_state_t" below 64K. + */ + +/** The maximum number of "small" buffers. + * This is enough for 53 network cpus with 128 credits. Note that + * if these are exhausted, we will fall back to using large buffers. + */ +#define LIPP_SMALL_BUFFERS 6785 + +/** The maximum number of "large" buffers. + * This is enough for 53 network cpus with 128 credits. + */ +#define LIPP_LARGE_BUFFERS 6785 + +#endif /* __DRV_XGBE_INTF_H__ */ diff --git a/arch/tile/include/hv/netio_errors.h b/arch/tile/include/hv/netio_errors.h new file mode 100644 index 000000000000..e1591bff61b5 --- /dev/null +++ b/arch/tile/include/hv/netio_errors.h @@ -0,0 +1,122 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * Error codes returned from NetIO routines. + */ + +#ifndef __NETIO_ERRORS_H__ +#define __NETIO_ERRORS_H__ + +/** + * @addtogroup error + * + * @brief The error codes returned by NetIO functions. + * + * NetIO functions return 0 (defined as ::NETIO_NO_ERROR) on success, and + * a negative value if an error occurs. + * + * In cases where a NetIO function failed due to a error reported by + * system libraries, the error code will be the negation of the + * system errno at the time of failure. The @ref netio_strerror() + * function will deliver error strings for both NetIO and system error + * codes. + * + * @{ + */ + +/** The set of all NetIO errors. */ +typedef enum +{ + /** Operation successfully completed. */ + NETIO_NO_ERROR = 0, + + /** A packet was successfully retrieved from an input queue. */ + NETIO_PKT = 0, + + /** Largest NetIO error number. */ + NETIO_ERR_MAX = -701, + + /** The tile is not registered with the IPP. */ + NETIO_NOT_REGISTERED = -701, + + /** No packet was available to retrieve from the input queue. */ + NETIO_NOPKT = -702, + + /** The requested function is not implemented. */ + NETIO_NOT_IMPLEMENTED = -703, + + /** On a registration operation, the target queue already has the maximum + * number of tiles registered for it, and no more may be added. On a + * packet send operation, the output queue is full and nothing more can + * be queued until some of the queued packets are actually transmitted. */ + NETIO_QUEUE_FULL = -704, + + /** The calling process or thread is not bound to exactly one CPU. */ + NETIO_BAD_AFFINITY = -705, + + /** Cannot allocate memory on requested controllers. */ + NETIO_CANNOT_HOME = -706, + + /** On a registration operation, the IPP specified is not configured + * to support the options requested; for instance, the application + * wants a specific type of tagged headers which the configured IPP + * doesn't support. Or, the supplied configuration information is + * not self-consistent, or is out of range; for instance, specifying + * both NETIO_RECV and NETIO_NO_RECV, or asking for more than + * NETIO_MAX_SEND_BUFFERS to be preallocated. On a VLAN or bucket + * configure operation, the number of items, or the base item, was + * out of range. + */ + NETIO_BAD_CONFIG = -707, + + /** Too many tiles have registered to transmit packets. */ + NETIO_TOOMANY_XMIT = -708, + + /** Packet transmission was attempted on a queue which was registered + with transmit disabled. */ + NETIO_UNREG_XMIT = -709, + + /** This tile is already registered with the IPP. */ + NETIO_ALREADY_REGISTERED = -710, + + /** The Ethernet link is down. The application should try again later. */ + NETIO_LINK_DOWN = -711, + + /** An invalid memory buffer has been specified. This may be an unmapped + * virtual address, or one which does not meet alignment requirements. + * For netio_input_register(), this error may be returned when multiple + * processes specify different memory regions to be used for NetIO + * buffers. That can happen if these processes specify explicit memory + * regions with the ::NETIO_FIXED_BUFFER_VA flag, or if tmc_cmem_init() + * has not been called by a common ancestor of the processes. + */ + NETIO_FAULT = -712, + + /** Cannot combine user-managed shared memory and cache coherence. */ + NETIO_BAD_CACHE_CONFIG = -713, + + /** Smallest NetIO error number. */ + NETIO_ERR_MIN = -713, + +#ifndef __DOXYGEN__ + /** Used internally to mean that no response is needed; never returned to + * an application. */ + NETIO_NO_RESPONSE = 1 +#endif +} netio_error_t; + +/** @} */ + +#endif /* __NETIO_ERRORS_H__ */ diff --git a/arch/tile/include/hv/netio_intf.h b/arch/tile/include/hv/netio_intf.h new file mode 100644 index 000000000000..8d20972aba2c --- /dev/null +++ b/arch/tile/include/hv/netio_intf.h @@ -0,0 +1,2975 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * NetIO interface structures and macros. + */ + +#ifndef __NETIO_INTF_H__ +#define __NETIO_INTF_H__ + +#include <hv/netio_errors.h> + +#ifdef __KERNEL__ +#include <linux/types.h> +#else +#include <stdint.h> +#endif + +#if !defined(__HV__) && !defined(__BOGUX__) && !defined(__KERNEL__) +#include <assert.h> +#define netio_assert assert /**< Enable assertions from macros */ +#else +#define netio_assert(...) ((void)(0)) /**< Disable assertions from macros */ +#endif + +/* + * If none of these symbols are defined, we're building libnetio in an + * environment where we have pthreads, so we'll enable locking. + */ +#if !defined(__HV__) && !defined(__BOGUX__) && !defined(__KERNEL__) && \ + !defined(__NEWLIB__) +#define _NETIO_PTHREAD /**< Include a mutex in netio_queue_t below */ + +/* + * If NETIO_UNLOCKED is defined, we don't do use per-cpu locks on + * per-packet NetIO operations. We still do pthread locking on things + * like netio_input_register, though. This is used for building + * libnetio_unlocked. + */ +#ifndef NETIO_UNLOCKED + +/* Avoid PLT overhead by using our own inlined per-cpu lock. */ +#include <sched.h> +typedef int _netio_percpu_mutex_t; + +static __inline int +_netio_percpu_mutex_init(_netio_percpu_mutex_t* lock) +{ + *lock = 0; + return 0; +} + +static __inline int +_netio_percpu_mutex_lock(_netio_percpu_mutex_t* lock) +{ + while (__builtin_expect(__insn_tns(lock), 0)) + sched_yield(); + return 0; +} + +static __inline int +_netio_percpu_mutex_unlock(_netio_percpu_mutex_t* lock) +{ + *lock = 0; + return 0; +} + +#else /* NETIO_UNLOCKED */ + +/* Don't do any locking for per-packet NetIO operations. */ +typedef int _netio_percpu_mutex_t; +#define _netio_percpu_mutex_init(L) +#define _netio_percpu_mutex_lock(L) +#define _netio_percpu_mutex_unlock(L) + +#endif /* NETIO_UNLOCKED */ +#endif /* !__HV__, !__BOGUX, !__KERNEL__, !__NEWLIB__ */ + +/** How many tiles can register for a given queue. + * @ingroup setup */ +#define NETIO_MAX_TILES_PER_QUEUE 64 + + +/** Largest permissible queue identifier. + * @ingroup setup */ +#define NETIO_MAX_QUEUE_ID 255 + + +#ifndef __DOXYGEN__ + +/* Metadata packet checksum/ethertype flags. */ + +/** The L4 checksum has not been calculated. */ +#define _NETIO_PKT_NO_L4_CSUM_SHIFT 0 +#define _NETIO_PKT_NO_L4_CSUM_RMASK 1 +#define _NETIO_PKT_NO_L4_CSUM_MASK \ + (_NETIO_PKT_NO_L4_CSUM_RMASK << _NETIO_PKT_NO_L4_CSUM_SHIFT) + +/** The L3 checksum has not been calculated. */ +#define _NETIO_PKT_NO_L3_CSUM_SHIFT 1 +#define _NETIO_PKT_NO_L3_CSUM_RMASK 1 +#define _NETIO_PKT_NO_L3_CSUM_MASK \ + (_NETIO_PKT_NO_L3_CSUM_RMASK << _NETIO_PKT_NO_L3_CSUM_SHIFT) + +/** The L3 checksum is incorrect (or perhaps has not been calculated). */ +#define _NETIO_PKT_BAD_L3_CSUM_SHIFT 2 +#define _NETIO_PKT_BAD_L3_CSUM_RMASK 1 +#define _NETIO_PKT_BAD_L3_CSUM_MASK \ + (_NETIO_PKT_BAD_L3_CSUM_RMASK << _NETIO_PKT_BAD_L3_CSUM_SHIFT) + +/** The Ethernet packet type is unrecognized. */ +#define _NETIO_PKT_TYPE_UNRECOGNIZED_SHIFT 3 +#define _NETIO_PKT_TYPE_UNRECOGNIZED_RMASK 1 +#define _NETIO_PKT_TYPE_UNRECOGNIZED_MASK \ + (_NETIO_PKT_TYPE_UNRECOGNIZED_RMASK << \ + _NETIO_PKT_TYPE_UNRECOGNIZED_SHIFT) + +/* Metadata packet type flags. */ + +/** Where the packet type bits are; this field is the index into + * _netio_pkt_info. */ +#define _NETIO_PKT_TYPE_SHIFT 4 +#define _NETIO_PKT_TYPE_RMASK 0x3F + +/** How many VLAN tags the packet has, and, if we have two, which one we + * actually grouped on. A VLAN within a proprietary (Marvell or Broadcom) + * tag is counted here. */ +#define _NETIO_PKT_VLAN_SHIFT 4 +#define _NETIO_PKT_VLAN_RMASK 0x3 +#define _NETIO_PKT_VLAN_MASK \ + (_NETIO_PKT_VLAN_RMASK << _NETIO_PKT_VLAN_SHIFT) +#define _NETIO_PKT_VLAN_NONE 0 /* No VLAN tag. */ +#define _NETIO_PKT_VLAN_ONE 1 /* One VLAN tag. */ +#define _NETIO_PKT_VLAN_TWO_OUTER 2 /* Two VLAN tags, outer one used. */ +#define _NETIO_PKT_VLAN_TWO_INNER 3 /* Two VLAN tags, inner one used. */ + +/** Which proprietary tags the packet has. */ +#define _NETIO_PKT_TAG_SHIFT 6 +#define _NETIO_PKT_TAG_RMASK 0x3 +#define _NETIO_PKT_TAG_MASK \ + (_NETIO_PKT_TAG_RMASK << _NETIO_PKT_TAG_SHIFT) +#define _NETIO_PKT_TAG_NONE 0 /* No proprietary tags. */ +#define _NETIO_PKT_TAG_MRVL 1 /* Marvell HyperG.Stack tags. */ +#define _NETIO_PKT_TAG_MRVL_EXT 2 /* HyperG.Stack extended tags. */ +#define _NETIO_PKT_TAG_BRCM 3 /* Broadcom HiGig tags. */ + +/** Whether a packet has an LLC + SNAP header. */ +#define _NETIO_PKT_SNAP_SHIFT 8 +#define _NETIO_PKT_SNAP_RMASK 0x1 +#define _NETIO_PKT_SNAP_MASK \ + (_NETIO_PKT_SNAP_RMASK << _NETIO_PKT_SNAP_SHIFT) + +/* NOTE: Bits 9 and 10 are unused. */ + +/** Length of any custom data before the L2 header, in words. */ +#define _NETIO_PKT_CUSTOM_LEN_SHIFT 11 +#define _NETIO_PKT_CUSTOM_LEN_RMASK 0x1F +#define _NETIO_PKT_CUSTOM_LEN_MASK \ + (_NETIO_PKT_CUSTOM_LEN_RMASK << _NETIO_PKT_CUSTOM_LEN_SHIFT) + +/** The L4 checksum is incorrect (or perhaps has not been calculated). */ +#define _NETIO_PKT_BAD_L4_CSUM_SHIFT 16 +#define _NETIO_PKT_BAD_L4_CSUM_RMASK 0x1 +#define _NETIO_PKT_BAD_L4_CSUM_MASK \ + (_NETIO_PKT_BAD_L4_CSUM_RMASK << _NETIO_PKT_BAD_L4_CSUM_SHIFT) + +/** Length of the L2 header, in words. */ +#define _NETIO_PKT_L2_LEN_SHIFT 17 +#define _NETIO_PKT_L2_LEN_RMASK 0x1F +#define _NETIO_PKT_L2_LEN_MASK \ + (_NETIO_PKT_L2_LEN_RMASK << _NETIO_PKT_L2_LEN_SHIFT) + + +/* Flags in minimal packet metadata. */ + +/** We need an eDMA checksum on this packet. */ +#define _NETIO_PKT_NEED_EDMA_CSUM_SHIFT 0 +#define _NETIO_PKT_NEED_EDMA_CSUM_RMASK 1 +#define _NETIO_PKT_NEED_EDMA_CSUM_MASK \ + (_NETIO_PKT_NEED_EDMA_CSUM_RMASK << _NETIO_PKT_NEED_EDMA_CSUM_SHIFT) + +/* Data within the packet information table. */ + +/* Note that, for efficiency, code which uses these fields assumes that none + * of the shift values below are zero. See uses below for an explanation. */ + +/** Offset within the L2 header of the innermost ethertype (in halfwords). */ +#define _NETIO_PKT_INFO_ETYPE_SHIFT 6 +#define _NETIO_PKT_INFO_ETYPE_RMASK 0x1F + +/** Offset within the L2 header of the VLAN tag (in halfwords). */ +#define _NETIO_PKT_INFO_VLAN_SHIFT 11 +#define _NETIO_PKT_INFO_VLAN_RMASK 0x1F + +#endif + + +/** The size of a memory buffer representing a small packet. + * @ingroup egress */ +#define SMALL_PACKET_SIZE 256 + +/** The size of a memory buffer representing a large packet. + * @ingroup egress */ +#define LARGE_PACKET_SIZE 2048 + +/** The size of a memory buffer representing a jumbo packet. + * @ingroup egress */ +#define JUMBO_PACKET_SIZE (12 * 1024) + + +/* Common ethertypes. + * @ingroup ingress */ +/** @{ */ +/** The ethertype of IPv4. */ +#define ETHERTYPE_IPv4 (0x0800) +/** The ethertype of ARP. */ +#define ETHERTYPE_ARP (0x0806) +/** The ethertype of VLANs. */ +#define ETHERTYPE_VLAN (0x8100) +/** The ethertype of a Q-in-Q header. */ +#define ETHERTYPE_Q_IN_Q (0x9100) +/** The ethertype of IPv6. */ +#define ETHERTYPE_IPv6 (0x86DD) +/** The ethertype of MPLS. */ +#define ETHERTYPE_MPLS (0x8847) +/** @} */ + + +/** The possible return values of NETIO_PKT_STATUS. + * @ingroup ingress + */ +typedef enum +{ + /** No problems were detected with this packet. */ + NETIO_PKT_STATUS_OK, + /** The packet is undersized; this is expected behavior if the packet's + * ethertype is unrecognized, but otherwise the packet is likely corrupt. */ + NETIO_PKT_STATUS_UNDERSIZE, + /** The packet is oversized and some trailing bytes have been discarded. + This is expected behavior for short packets, since it's impossible to + precisely determine the amount of padding which may have been added to + them to make them meet the minimum Ethernet packet size. */ + NETIO_PKT_STATUS_OVERSIZE, + /** The packet was judged to be corrupt by hardware (for instance, it had + a bad CRC, or part of it was discarded due to lack of buffer space in + the I/O shim) and should be discarded. */ + NETIO_PKT_STATUS_BAD +} netio_pkt_status_t; + + +/** Log2 of how many buckets we have. */ +#define NETIO_LOG2_NUM_BUCKETS (10) + +/** How many buckets we have. + * @ingroup ingress */ +#define NETIO_NUM_BUCKETS (1 << NETIO_LOG2_NUM_BUCKETS) + + +/** + * @brief A group-to-bucket identifier. + * + * @ingroup setup + * + * This tells us what to do with a given group. + */ +typedef union { + /** The header broken down into bits. */ + struct { + /** Whether we should balance on L4, if available */ + unsigned int __balance_on_l4:1; + /** Whether we should balance on L3, if available */ + unsigned int __balance_on_l3:1; + /** Whether we should balance on L2, if available */ + unsigned int __balance_on_l2:1; + /** Reserved for future use */ + unsigned int __reserved:1; + /** The base bucket to use to send traffic */ + unsigned int __bucket_base:NETIO_LOG2_NUM_BUCKETS; + /** The mask to apply to the balancing value. This must be one less + * than a power of two, e.g. 0x3 or 0xFF. + */ + unsigned int __bucket_mask:NETIO_LOG2_NUM_BUCKETS; + /** Pad to 32 bits */ + unsigned int __padding:(32 - 4 - 2 * NETIO_LOG2_NUM_BUCKETS); + } bits; + /** To send out the IDN. */ + unsigned int word; +} +netio_group_t; + + +/** + * @brief A VLAN-to-bucket identifier. + * + * @ingroup setup + * + * This tells us what to do with a given VLAN. + */ +typedef netio_group_t netio_vlan_t; + + +/** + * A bucket-to-queue mapping. + * @ingroup setup + */ +typedef unsigned char netio_bucket_t; + + +/** + * A packet size can always fit in a netio_size_t. + * @ingroup setup + */ +typedef unsigned int netio_size_t; + + +/** + * @brief Ethernet standard (ingress) packet metadata. + * + * @ingroup ingress + * + * This is additional data associated with each packet. + * This structure is opaque and accessed through the @ref ingress. + * + * Also, the buffer population operation currently assumes that standard + * metadata is at least as large as minimal metadata, and will need to be + * modified if that is no longer the case. + */ +typedef struct +{ +#ifdef __DOXYGEN__ + /** This structure is opaque. */ + unsigned char opaque[24]; +#else + /** The overall ordinal of the packet */ + unsigned int __packet_ordinal; + /** The ordinal of the packet within the group */ + unsigned int __group_ordinal; + /** The best flow hash IPP could compute. */ + unsigned int __flow_hash; + /** Flags pertaining to checksum calculation, packet type, etc. */ + unsigned int __flags; + /** The first word of "user data". */ + unsigned int __user_data_0; + /** The second word of "user data". */ + unsigned int __user_data_1; +#endif +} +netio_pkt_metadata_t; + + +/** To ensure that the L3 header is aligned mod 4, the L2 header should be + * aligned mod 4 plus 2, since every supported L2 header is 4n + 2 bytes + * long. The standard way to do this is to simply add 2 bytes of padding + * before the L2 header. + */ +#define NETIO_PACKET_PADDING 2 + + + +/** + * @brief Ethernet minimal (egress) packet metadata. + * + * @ingroup egress + * + * This structure represents information about packets which have + * been processed by @ref netio_populate_buffer() or + * @ref netio_populate_prepend_buffer(). This structure is opaque + * and accessed through the @ref egress. + * + * @internal This structure is actually copied into the memory used by + * standard metadata, which is assumed to be large enough. + */ +typedef struct +{ +#ifdef __DOXYGEN__ + /** This structure is opaque. */ + unsigned char opaque[14]; +#else + /** The offset of the L2 header from the start of the packet data. */ + unsigned short l2_offset; + /** The offset of the L3 header from the start of the packet data. */ + unsigned short l3_offset; + /** Where to write the checksum. */ + unsigned char csum_location; + /** Where to start checksumming from. */ + unsigned char csum_start; + /** Flags pertaining to checksum calculation etc. */ + unsigned short flags; + /** The L2 length of the packet. */ + unsigned short l2_length; + /** The checksum with which to seed the checksum generator. */ + unsigned short csum_seed; + /** How much to checksum. */ + unsigned short csum_length; +#endif +} +netio_pkt_minimal_metadata_t; + + +#ifndef __DOXYGEN__ + +/** + * @brief An I/O notification header. + * + * This is the first word of data received from an I/O shim in a notification + * packet. It contains framing and status information. + */ +typedef union +{ + unsigned int word; /**< The whole word. */ + /** The various fields. */ + struct + { + unsigned int __channel:7; /**< Resource channel. */ + unsigned int __type:4; /**< Type. */ + unsigned int __ack:1; /**< Whether an acknowledgement is needed. */ + unsigned int __reserved:1; /**< Reserved. */ + unsigned int __protocol:1; /**< A protocol-specific word is added. */ + unsigned int __status:2; /**< Status of the transfer. */ + unsigned int __framing:2; /**< Framing of the transfer. */ + unsigned int __transfer_size:14; /**< Transfer size in bytes (total). */ + } bits; +} +__netio_pkt_notif_t; + + +/** + * Returns the base address of the packet. + */ +#define _NETIO_PKT_HANDLE_BASE(p) \ + ((unsigned char*)((p).word & 0xFFFFFFC0)) + +/** + * Returns the base address of the packet. + */ +#define _NETIO_PKT_BASE(p) \ + _NETIO_PKT_HANDLE_BASE(p->__packet) + +/** + * @brief An I/O notification packet (second word) + * + * This is the second word of data received from an I/O shim in a notification + * packet. This is the virtual address of the packet buffer, plus some flag + * bits. (The virtual address of the packet is always 256-byte aligned so we + * have room for 8 bits' worth of flags in the low 8 bits.) + * + * @internal + * NOTE: The low two bits must contain "__queue", so the "packet size" + * (SIZE_SMALL, SIZE_LARGE, or SIZE_JUMBO) can be determined quickly. + * + * If __addr or __offset are moved, _NETIO_PKT_BASE + * (defined right below this) must be changed. + */ +typedef union +{ + unsigned int word; /**< The whole word. */ + /** The various fields. */ + struct + { + /** Which queue the packet will be returned to once it is sent back to + the IPP. This is one of the SIZE_xxx values. */ + unsigned int __queue:2; + + /** The IPP handle of the sending IPP. */ + unsigned int __ipp_handle:2; + + /** Reserved for future use. */ + unsigned int __reserved:1; + + /** If 1, this packet has minimal (egress) metadata; otherwise, it + has standard (ingress) metadata. */ + unsigned int __minimal:1; + + /** Offset of the metadata within the packet. This value is multiplied + * by 64 and added to the base packet address to get the metadata + * address. Note that this field is aligned within the word such that + * you can easily extract the metadata address with a 26-bit mask. */ + unsigned int __offset:2; + + /** The top 24 bits of the packet's virtual address. */ + unsigned int __addr:24; + } bits; +} +__netio_pkt_handle_t; + +#endif /* !__DOXYGEN__ */ + + +/** + * @brief A handle for an I/O packet's storage. + * @ingroup ingress + * + * netio_pkt_handle_t encodes the concept of a ::netio_pkt_t with its + * packet metadata removed. It is a much smaller type that exists to + * facilitate applications where the full ::netio_pkt_t type is too + * large, such as those that cache enormous numbers of packets or wish + * to transmit packet descriptors over the UDN. + * + * Because there is no metadata, most ::netio_pkt_t operations cannot be + * performed on a netio_pkt_handle_t. It supports only + * netio_free_handle() (to free the buffer) and + * NETIO_PKT_CUSTOM_DATA_H() (to access a pointer to its contents). + * The application must acquire any additional metadata it wants from the + * original ::netio_pkt_t and record it separately. + * + * A netio_pkt_handle_t can be extracted from a ::netio_pkt_t by calling + * NETIO_PKT_HANDLE(). An invalid handle (analogous to NULL) can be + * created by assigning the value ::NETIO_PKT_HANDLE_NONE. A handle can + * be tested for validity with NETIO_PKT_HANDLE_IS_VALID(). + */ +typedef struct +{ + unsigned int word; /**< Opaque bits. */ +} netio_pkt_handle_t; + +/** + * @brief A packet descriptor. + * + * @ingroup ingress + * @ingroup egress + * + * This data structure represents a packet. The structure is manipulated + * through the @ref ingress and the @ref egress. + * + * While the contents of a netio_pkt_t are opaque, the structure itself is + * portable. This means that it may be shared between all tiles which have + * done a netio_input_register() call for the interface on which the pkt_t + * was initially received (via netio_get_packet()) or retrieved (via + * netio_get_buffer()). The contents of a netio_pkt_t can be transmitted to + * another tile via shared memory, or via a UDN message, or by other means. + * The destination tile may then use the pkt_t as if it had originally been + * received locally; it may read or write the packet's data, read its + * metadata, free the packet, send the packet, transfer the netio_pkt_t to + * yet another tile, and so forth. + * + * Once a netio_pkt_t has been transferred to a second tile, the first tile + * should not reference the original copy; in particular, if more than one + * tile frees or sends the same netio_pkt_t, the IPP's packet free lists will + * become corrupted. Note also that each tile which reads or modifies + * packet data must obey the memory coherency rules outlined in @ref input. + */ +typedef struct +{ +#ifdef __DOXYGEN__ + /** This structure is opaque. */ + unsigned char opaque[32]; +#else + /** For an ingress packet (one with standard metadata), this is the + * notification header we got from the I/O shim. For an egress packet + * (one with minimal metadata), this word is zero if the packet has not + * been populated, and nonzero if it has. */ + __netio_pkt_notif_t __notif_header; + + /** Virtual address of the packet buffer, plus state flags. */ + __netio_pkt_handle_t __packet; + + /** Metadata associated with the packet. */ + netio_pkt_metadata_t __metadata; +#endif +} +netio_pkt_t; + + +#ifndef __DOXYGEN__ + +#define __NETIO_PKT_NOTIF_HEADER(pkt) ((pkt)->__notif_header) +#define __NETIO_PKT_IPP_HANDLE(pkt) ((pkt)->__packet.bits.__ipp_handle) +#define __NETIO_PKT_QUEUE(pkt) ((pkt)->__packet.bits.__queue) +#define __NETIO_PKT_NOTIF_HEADER_M(mda, pkt) ((pkt)->__notif_header) +#define __NETIO_PKT_IPP_HANDLE_M(mda, pkt) ((pkt)->__packet.bits.__ipp_handle) +#define __NETIO_PKT_MINIMAL(pkt) ((pkt)->__packet.bits.__minimal) +#define __NETIO_PKT_QUEUE_M(mda, pkt) ((pkt)->__packet.bits.__queue) +#define __NETIO_PKT_FLAGS_M(mda, pkt) ((mda)->__flags) + +/* Packet information table, used by the attribute access functions below. */ +extern const uint16_t _netio_pkt_info[]; + +#endif /* __DOXYGEN__ */ + + +#ifndef __DOXYGEN__ +/* These macros are deprecated and will disappear in a future MDE release. */ +#define NETIO_PKT_GOOD_CHECKSUM(pkt) \ + NETIO_PKT_L4_CSUM_CORRECT(pkt) +#define NETIO_PKT_GOOD_CHECKSUM_M(mda, pkt) \ + NETIO_PKT_L4_CSUM_CORRECT_M(mda, pkt) +#endif /* __DOXYGEN__ */ + + +/* Packet attribute access functions. */ + +/** Return a pointer to the metadata for a packet. + * @ingroup ingress + * + * Calling this function once and passing the result to other retrieval + * functions with a "_M" suffix usually improves performance. This + * function must be called on an 'ingress' packet (i.e. one retrieved + * by @ref netio_get_packet(), on which @ref netio_populate_buffer() or + * @ref netio_populate_prepend_buffer have not been called). Use of this + * function on an 'egress' packet will cause an assertion failure. + * + * @param[in] pkt Packet on which to operate. + * @return A pointer to the packet's standard metadata. + */ +static __inline netio_pkt_metadata_t* +NETIO_PKT_METADATA(netio_pkt_t* pkt) +{ + netio_assert(!pkt->__packet.bits.__minimal); + return &pkt->__metadata; +} + + +/** Return a pointer to the minimal metadata for a packet. + * @ingroup egress + * + * Calling this function once and passing the result to other retrieval + * functions with a "_MM" suffix usually improves performance. This + * function must be called on an 'egress' packet (i.e. one on which + * @ref netio_populate_buffer() or @ref netio_populate_prepend_buffer() + * have been called, or one retrieved by @ref netio_get_buffer()). Use of + * this function on an 'ingress' packet will cause an assertion failure. + * + * @param[in] pkt Packet on which to operate. + * @return A pointer to the packet's standard metadata. + */ +static __inline netio_pkt_minimal_metadata_t* +NETIO_PKT_MINIMAL_METADATA(netio_pkt_t* pkt) +{ + netio_assert(pkt->__packet.bits.__minimal); + return (netio_pkt_minimal_metadata_t*) &pkt->__metadata; +} + + +/** Determine whether a packet has 'minimal' metadata. + * @ingroup pktfuncs + * + * This function will return nonzero if the packet is an 'egress' + * packet (i.e. one on which @ref netio_populate_buffer() or + * @ref netio_populate_prepend_buffer() have been called, or one + * retrieved by @ref netio_get_buffer()), and zero if the packet + * is an 'ingress' packet (i.e. one retrieved by @ref netio_get_packet(), + * which has not been converted into an 'egress' packet). + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the packet has minimal metadata. + */ +static __inline unsigned int +NETIO_PKT_IS_MINIMAL(netio_pkt_t* pkt) +{ + return pkt->__packet.bits.__minimal; +} + + +/** Return a handle for a packet's storage. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return A handle for the packet's storage. + */ +static __inline netio_pkt_handle_t +NETIO_PKT_HANDLE(netio_pkt_t* pkt) +{ + netio_pkt_handle_t h; + h.word = pkt->__packet.word; + return h; +} + + +/** A special reserved value indicating the absence of a packet handle. + * + * @ingroup pktfuncs + */ +#define NETIO_PKT_HANDLE_NONE ((netio_pkt_handle_t) { 0 }) + + +/** Test whether a packet handle is valid. + * + * Applications may wish to use the reserved value NETIO_PKT_HANDLE_NONE + * to indicate no packet at all. This function tests to see if a packet + * handle is a real handle, not this special reserved value. + * + * @ingroup pktfuncs + * + * @param[in] handle Handle on which to operate. + * @return One if the packet handle is valid, else zero. + */ +static __inline unsigned int +NETIO_PKT_HANDLE_IS_VALID(netio_pkt_handle_t handle) +{ + return handle.word != 0; +} + + + +/** Return a pointer to the start of the packet's custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup ingress + * + * @param[in] handle Handle on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_CUSTOM_DATA_H(netio_pkt_handle_t handle) +{ + return _NETIO_PKT_HANDLE_BASE(handle) + NETIO_PACKET_PADDING; +} + + +/** Return the length of the packet's custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet's custom header, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_CUSTOM_HEADER_LENGTH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + /* + * Note that we effectively need to extract a quantity from the flags word + * which is measured in words, and then turn it into bytes by shifting + * it left by 2. We do this all at once by just shifting right two less + * bits, and shifting the mask up two bits. + */ + return ((mda->__flags >> (_NETIO_PKT_CUSTOM_LEN_SHIFT - 2)) & + (_NETIO_PKT_CUSTOM_LEN_RMASK << 2)); +} + + +/** Return the length of the packet, starting with the custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_CUSTOM_LENGTH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (__NETIO_PKT_NOTIF_HEADER(pkt).bits.__transfer_size - + NETIO_PACKET_PADDING); +} + + +/** Return a pointer to the start of the packet's custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_CUSTOM_DATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return NETIO_PKT_CUSTOM_DATA_H(NETIO_PKT_HANDLE(pkt)); +} + + +/** Return the length of the packet's L2 (Ethernet plus VLAN or SNAP) header. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet's L2 header, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_HEADER_LENGTH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + /* + * Note that we effectively need to extract a quantity from the flags word + * which is measured in words, and then turn it into bytes by shifting + * it left by 2. We do this all at once by just shifting right two less + * bits, and shifting the mask up two bits. We then add two bytes. + */ + return ((mda->__flags >> (_NETIO_PKT_L2_LEN_SHIFT - 2)) & + (_NETIO_PKT_L2_LEN_RMASK << 2)) + 2; +} + + +/** Return the length of the packet, starting with the L2 (Ethernet) header. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_LENGTH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (NETIO_PKT_CUSTOM_LENGTH_M(mda, pkt) - + NETIO_PKT_CUSTOM_HEADER_LENGTH_M(mda,pkt)); +} + + +/** Return a pointer to the start of the packet's L2 (Ethernet) header. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_L2_DATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (NETIO_PKT_CUSTOM_DATA_M(mda, pkt) + + NETIO_PKT_CUSTOM_HEADER_LENGTH_M(mda, pkt)); +} + + +/** Retrieve the length of the packet, starting with the L3 (generally, + * the IP) header. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Length of the packet's L3 header and data, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L3_LENGTH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (NETIO_PKT_L2_LENGTH_M(mda, pkt) - + NETIO_PKT_L2_HEADER_LENGTH_M(mda,pkt)); +} + + +/** Return a pointer to the packet's L3 (generally, the IP) header. + * @ingroup ingress + * + * Note that we guarantee word alignment of the L3 header. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return A pointer to the packet's L3 header. + */ +static __inline unsigned char* +NETIO_PKT_L3_DATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (NETIO_PKT_L2_DATA_M(mda, pkt) + + NETIO_PKT_L2_HEADER_LENGTH_M(mda, pkt)); +} + + +/** Return the ordinal of the packet. + * @ingroup ingress + * + * Each packet is given an ordinal number when it is delivered by the IPP. + * In the medium term, the ordinal is unique and monotonically increasing, + * being incremented by 1 for each packet; the ordinal of the first packet + * delivered after the IPP starts is zero. (Since the ordinal is of finite + * size, given enough input packets, it will eventually wrap around to zero; + * in the long term, therefore, ordinals are not unique.) The ordinals + * handed out by different IPPs are not disjoint, so two packets from + * different IPPs may have identical ordinals. Packets dropped by the + * IPP or by the I/O shim are not assigned ordinals. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's per-IPP packet ordinal. + */ +static __inline unsigned int +NETIO_PKT_ORDINAL_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return mda->__packet_ordinal; +} + + +/** Return the per-group ordinal of the packet. + * @ingroup ingress + * + * Each packet is given a per-group ordinal number when it is + * delivered by the IPP. By default, the group is the packet's VLAN, + * although IPP can be recompiled to use different values. In + * the medium term, the ordinal is unique and monotonically + * increasing, being incremented by 1 for each packet; the ordinal of + * the first packet distributed to a particular group is zero. + * (Since the ordinal is of finite size, given enough input packets, + * it will eventually wrap around to zero; in the long term, + * therefore, ordinals are not unique.) The ordinals handed out by + * different IPPs are not disjoint, so two packets from different IPPs + * may have identical ordinals; similarly, packets distributed to + * different groups may have identical ordinals. Packets dropped by + * the IPP or by the I/O shim are not assigned ordinals. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's per-IPP, per-group ordinal. + */ +static __inline unsigned int +NETIO_PKT_GROUP_ORDINAL_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return mda->__group_ordinal; +} + + +/** Return the VLAN ID assigned to the packet. + * @ingroup ingress + * + * This value is usually contained within the packet header. + * + * This value will be zero if the packet does not have a VLAN tag, or if + * this value was not extracted from the packet. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's VLAN ID. + */ +static __inline unsigned short +NETIO_PKT_VLAN_ID_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + int vl = (mda->__flags >> _NETIO_PKT_VLAN_SHIFT) & _NETIO_PKT_VLAN_RMASK; + unsigned short* pkt_p; + int index; + unsigned short val; + + if (vl == _NETIO_PKT_VLAN_NONE) + return 0; + + pkt_p = (unsigned short*) NETIO_PKT_L2_DATA_M(mda, pkt); + index = (mda->__flags >> _NETIO_PKT_TYPE_SHIFT) & _NETIO_PKT_TYPE_RMASK; + + val = pkt_p[(_netio_pkt_info[index] >> _NETIO_PKT_INFO_VLAN_SHIFT) & + _NETIO_PKT_INFO_VLAN_RMASK]; + +#ifdef __TILECC__ + return (__insn_bytex(val) >> 16) & 0xFFF; +#else + return (__builtin_bswap32(val) >> 16) & 0xFFF; +#endif +} + + +/** Return the ethertype of the packet. + * @ingroup ingress + * + * This value is usually contained within the packet header. + * + * This value is reliable if @ref NETIO_PKT_ETHERTYPE_RECOGNIZED_M() + * returns true, and otherwise, may not be well defined. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's ethertype. + */ +static __inline unsigned short +NETIO_PKT_ETHERTYPE_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + unsigned short* pkt_p = (unsigned short*) NETIO_PKT_L2_DATA_M(mda, pkt); + int index = (mda->__flags >> _NETIO_PKT_TYPE_SHIFT) & _NETIO_PKT_TYPE_RMASK; + + unsigned short val = + pkt_p[(_netio_pkt_info[index] >> _NETIO_PKT_INFO_ETYPE_SHIFT) & + _NETIO_PKT_INFO_ETYPE_RMASK]; + + return __builtin_bswap32(val) >> 16; +} + + +/** Return the flow hash computed on the packet. + * @ingroup ingress + * + * For TCP and UDP packets, this hash is calculated by hashing together + * the "5-tuple" values, specifically the source IP address, destination + * IP address, protocol type, source port and destination port. + * The hash value is intended to be helpful for millions of distinct + * flows. + * + * For IPv4 or IPv6 packets which are neither TCP nor UDP, the flow hash is + * derived by hashing together the source and destination IP addresses. + * + * For MPLS-encapsulated packets, the flow hash is derived by hashing + * the first MPLS label. + * + * For all other packets the flow hash is computed from the source + * and destination Ethernet addresses. + * + * The hash is symmetric, meaning it produces the same value if the + * source and destination are swapped. The only exceptions are + * tunneling protocols 0x04 (IP in IP Encapsulation), 0x29 (Simple + * Internet Protocol), 0x2F (General Routing Encapsulation) and 0x32 + * (Encap Security Payload), which use only the destination address + * since the source address is not meaningful. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's 32-bit flow hash. + */ +static __inline unsigned int +NETIO_PKT_FLOW_HASH_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return mda->__flow_hash; +} + + +/** Return the first word of "user data" for the packet. + * + * The contents of the user data words depend on the IPP. + * + * When using the standard ipp1, ipp2, or ipp4 sub-drivers, the first + * word of user data contains the least significant bits of the 64-bit + * arrival cycle count (see @c get_cycle_count_low()). + * + * See the <em>System Programmer's Guide</em> for details. + * + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's first word of "user data". + */ +static __inline unsigned int +NETIO_PKT_USER_DATA_0_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return mda->__user_data_0; +} + + +/** Return the second word of "user data" for the packet. + * + * The contents of the user data words depend on the IPP. + * + * When using the standard ipp1, ipp2, or ipp4 sub-drivers, the second + * word of user data contains the most significant bits of the 64-bit + * arrival cycle count (see @c get_cycle_count_high()). + * + * See the <em>System Programmer's Guide</em> for details. + * + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's second word of "user data". + */ +static __inline unsigned int +NETIO_PKT_USER_DATA_1_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return mda->__user_data_1; +} + + +/** Determine whether the L4 (TCP/UDP) checksum was calculated. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the L4 checksum was calculated. + */ +static __inline unsigned int +NETIO_PKT_L4_CSUM_CALCULATED_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return !(mda->__flags & _NETIO_PKT_NO_L4_CSUM_MASK); +} + + +/** Determine whether the L4 (TCP/UDP) checksum was calculated and found to + * be correct. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the checksum was calculated and is correct. + */ +static __inline unsigned int +NETIO_PKT_L4_CSUM_CORRECT_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return !(mda->__flags & + (_NETIO_PKT_BAD_L4_CSUM_MASK | _NETIO_PKT_NO_L4_CSUM_MASK)); +} + + +/** Determine whether the L3 (IP) checksum was calculated. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the L3 (IP) checksum was calculated. +*/ +static __inline unsigned int +NETIO_PKT_L3_CSUM_CALCULATED_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return !(mda->__flags & _NETIO_PKT_NO_L3_CSUM_MASK); +} + + +/** Determine whether the L3 (IP) checksum was calculated and found to be + * correct. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the checksum was calculated and is correct. + */ +static __inline unsigned int +NETIO_PKT_L3_CSUM_CORRECT_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return !(mda->__flags & + (_NETIO_PKT_BAD_L3_CSUM_MASK | _NETIO_PKT_NO_L3_CSUM_MASK)); +} + + +/** Determine whether the ethertype was recognized and L3 packet data was + * processed. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the ethertype was recognized and L3 packet data was + * processed. + */ +static __inline unsigned int +NETIO_PKT_ETHERTYPE_RECOGNIZED_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return !(mda->__flags & _NETIO_PKT_TYPE_UNRECOGNIZED_MASK); +} + + +/** Retrieve the status of a packet and any errors that may have occurred + * during ingress processing (length mismatches, CRC errors, etc.). + * @ingroup ingress + * + * Note that packets for which @ref NETIO_PKT_ETHERTYPE_RECOGNIZED() + * returns zero are always reported as underlength, as there is no a priori + * means to determine their length. Normally, applications should use + * @ref NETIO_PKT_BAD_M() instead of explicitly checking status with this + * function. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return The packet's status. + */ +static __inline netio_pkt_status_t +NETIO_PKT_STATUS_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (netio_pkt_status_t) __NETIO_PKT_NOTIF_HEADER(pkt).bits.__status; +} + + +/** Report whether a packet is bad (i.e., was shorter than expected based on + * its headers, or had a bad CRC). + * @ingroup ingress + * + * Note that this function does not verify L3 or L4 checksums. + * + * @param[in] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the packet is bad and should be discarded. + */ +static __inline unsigned int +NETIO_PKT_BAD_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return ((NETIO_PKT_STATUS_M(mda, pkt) & 1) && + (NETIO_PKT_ETHERTYPE_RECOGNIZED_M(mda, pkt) || + NETIO_PKT_STATUS_M(mda, pkt) == NETIO_PKT_STATUS_BAD)); +} + + +/** Return the length of the packet, starting with the L2 (Ethernet) header. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_LENGTH_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt) +{ + return mmd->l2_length; +} + + +/** Return the length of the L2 (Ethernet) header. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @return The length of the packet's L2 header, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_HEADER_LENGTH_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt) +{ + return mmd->l3_offset - mmd->l2_offset; +} + + +/** Return the length of the packet, starting with the L3 (IP) header. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @return Length of the packet's L3 header and data, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L3_LENGTH_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt) +{ + return (NETIO_PKT_L2_LENGTH_MM(mmd, pkt) - + NETIO_PKT_L2_HEADER_LENGTH_MM(mmd, pkt)); +} + + +/** Return a pointer to the packet's L3 (generally, the IP) header. + * @ingroup egress + * + * Note that we guarantee word alignment of the L3 header. + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @return A pointer to the packet's L3 header. + */ +static __inline unsigned char* +NETIO_PKT_L3_DATA_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt) +{ + return _NETIO_PKT_BASE(pkt) + mmd->l3_offset; +} + + +/** Return a pointer to the packet's L2 (Ethernet) header. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_L2_DATA_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt) +{ + return _NETIO_PKT_BASE(pkt) + mmd->l2_offset; +} + + +/** Retrieve the status of a packet and any errors that may have occurred + * during ingress processing (length mismatches, CRC errors, etc.). + * @ingroup ingress + * + * Note that packets for which @ref NETIO_PKT_ETHERTYPE_RECOGNIZED() + * returns zero are always reported as underlength, as there is no a priori + * means to determine their length. Normally, applications should use + * @ref NETIO_PKT_BAD() instead of explicitly checking status with this + * function. + * + * @param[in] pkt Packet on which to operate. + * @return The packet's status. + */ +static __inline netio_pkt_status_t +NETIO_PKT_STATUS(netio_pkt_t* pkt) +{ + netio_assert(!pkt->__packet.bits.__minimal); + + return (netio_pkt_status_t) __NETIO_PKT_NOTIF_HEADER(pkt).bits.__status; +} + + +/** Report whether a packet is bad (i.e., was shorter than expected based on + * its headers, or had a bad CRC). + * @ingroup ingress + * + * Note that this function does not verify L3 or L4 checksums. + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the packet is bad and should be discarded. + */ +static __inline unsigned int +NETIO_PKT_BAD(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_BAD_M(mda, pkt); +} + + +/** Return the length of the packet's custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return The length of the packet's custom header, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_CUSTOM_HEADER_LENGTH(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_CUSTOM_HEADER_LENGTH_M(mda, pkt); +} + + +/** Return the length of the packet, starting with the custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return The length of the packet, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_CUSTOM_LENGTH(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_CUSTOM_LENGTH_M(mda, pkt); +} + + +/** Return a pointer to the packet's custom header. + * A custom header may or may not be present, depending upon the IPP; its + * contents and alignment are also IPP-dependent. Currently, none of the + * standard IPPs supplied by Tilera produce a custom header. If present, + * the custom header precedes the L2 header in the packet buffer. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_CUSTOM_DATA(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_CUSTOM_DATA_M(mda, pkt); +} + + +/** Return the length of the packet's L2 (Ethernet plus VLAN or SNAP) header. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return The length of the packet's L2 header, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_HEADER_LENGTH(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_L2_HEADER_LENGTH_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L2_HEADER_LENGTH_M(mda, pkt); + } +} + + +/** Return the length of the packet, starting with the L2 (Ethernet) header. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return The length of the packet, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L2_LENGTH(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_L2_LENGTH_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L2_LENGTH_M(mda, pkt); + } +} + + +/** Return a pointer to the packet's L2 (Ethernet) header. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return A pointer to start of the packet. + */ +static __inline unsigned char* +NETIO_PKT_L2_DATA(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_L2_DATA_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L2_DATA_M(mda, pkt); + } +} + + +/** Retrieve the length of the packet, starting with the L3 (generally, the IP) + * header. + * @ingroup pktfuncs + * + * @param[in] pkt Packet on which to operate. + * @return Length of the packet's L3 header and data, in bytes. + */ +static __inline netio_size_t +NETIO_PKT_L3_LENGTH(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_L3_LENGTH_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L3_LENGTH_M(mda, pkt); + } +} + + +/** Return a pointer to the packet's L3 (generally, the IP) header. + * @ingroup pktfuncs + * + * Note that we guarantee word alignment of the L3 header. + * + * @param[in] pkt Packet on which to operate. + * @return A pointer to the packet's L3 header. + */ +static __inline unsigned char* +NETIO_PKT_L3_DATA(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_L3_DATA_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L3_DATA_M(mda, pkt); + } +} + + +/** Return the ordinal of the packet. + * @ingroup ingress + * + * Each packet is given an ordinal number when it is delivered by the IPP. + * In the medium term, the ordinal is unique and monotonically increasing, + * being incremented by 1 for each packet; the ordinal of the first packet + * delivered after the IPP starts is zero. (Since the ordinal is of finite + * size, given enough input packets, it will eventually wrap around to zero; + * in the long term, therefore, ordinals are not unique.) The ordinals + * handed out by different IPPs are not disjoint, so two packets from + * different IPPs may have identical ordinals. Packets dropped by the + * IPP or by the I/O shim are not assigned ordinals. + * + * + * @param[in] pkt Packet on which to operate. + * @return The packet's per-IPP packet ordinal. + */ +static __inline unsigned int +NETIO_PKT_ORDINAL(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_ORDINAL_M(mda, pkt); +} + + +/** Return the per-group ordinal of the packet. + * @ingroup ingress + * + * Each packet is given a per-group ordinal number when it is + * delivered by the IPP. By default, the group is the packet's VLAN, + * although IPP can be recompiled to use different values. In + * the medium term, the ordinal is unique and monotonically + * increasing, being incremented by 1 for each packet; the ordinal of + * the first packet distributed to a particular group is zero. + * (Since the ordinal is of finite size, given enough input packets, + * it will eventually wrap around to zero; in the long term, + * therefore, ordinals are not unique.) The ordinals handed out by + * different IPPs are not disjoint, so two packets from different IPPs + * may have identical ordinals; similarly, packets distributed to + * different groups may have identical ordinals. Packets dropped by + * the IPP or by the I/O shim are not assigned ordinals. + * + * @param[in] pkt Packet on which to operate. + * @return The packet's per-IPP, per-group ordinal. + */ +static __inline unsigned int +NETIO_PKT_GROUP_ORDINAL(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_GROUP_ORDINAL_M(mda, pkt); +} + + +/** Return the VLAN ID assigned to the packet. + * @ingroup ingress + * + * This is usually also contained within the packet header. If the packet + * does not have a VLAN tag, the VLAN ID returned by this function is zero. + * + * @param[in] pkt Packet on which to operate. + * @return The packet's VLAN ID. + */ +static __inline unsigned short +NETIO_PKT_VLAN_ID(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_VLAN_ID_M(mda, pkt); +} + + +/** Return the ethertype of the packet. + * @ingroup ingress + * + * This value is reliable if @ref NETIO_PKT_ETHERTYPE_RECOGNIZED() + * returns true, and otherwise, may not be well defined. + * + * @param[in] pkt Packet on which to operate. + * @return The packet's ethertype. + */ +static __inline unsigned short +NETIO_PKT_ETHERTYPE(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_ETHERTYPE_M(mda, pkt); +} + + +/** Return the flow hash computed on the packet. + * @ingroup ingress + * + * For TCP and UDP packets, this hash is calculated by hashing together + * the "5-tuple" values, specifically the source IP address, destination + * IP address, protocol type, source port and destination port. + * The hash value is intended to be helpful for millions of distinct + * flows. + * + * For IPv4 or IPv6 packets which are neither TCP nor UDP, the flow hash is + * derived by hashing together the source and destination IP addresses. + * + * For MPLS-encapsulated packets, the flow hash is derived by hashing + * the first MPLS label. + * + * For all other packets the flow hash is computed from the source + * and destination Ethernet addresses. + * + * The hash is symmetric, meaning it produces the same value if the + * source and destination are swapped. The only exceptions are + * tunneling protocols 0x04 (IP in IP Encapsulation), 0x29 (Simple + * Internet Protocol), 0x2F (General Routing Encapsulation) and 0x32 + * (Encap Security Payload), which use only the destination address + * since the source address is not meaningful. + * + * @param[in] pkt Packet on which to operate. + * @return The packet's 32-bit flow hash. + */ +static __inline unsigned int +NETIO_PKT_FLOW_HASH(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_FLOW_HASH_M(mda, pkt); +} + + +/** Return the first word of "user data" for the packet. + * + * The contents of the user data words depend on the IPP. + * + * When using the standard ipp1, ipp2, or ipp4 sub-drivers, the first + * word of user data contains the least significant bits of the 64-bit + * arrival cycle count (see @c get_cycle_count_low()). + * + * See the <em>System Programmer's Guide</em> for details. + * + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return The packet's first word of "user data". + */ +static __inline unsigned int +NETIO_PKT_USER_DATA_0(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_USER_DATA_0_M(mda, pkt); +} + + +/** Return the second word of "user data" for the packet. + * + * The contents of the user data words depend on the IPP. + * + * When using the standard ipp1, ipp2, or ipp4 sub-drivers, the second + * word of user data contains the most significant bits of the 64-bit + * arrival cycle count (see @c get_cycle_count_high()). + * + * See the <em>System Programmer's Guide</em> for details. + * + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return The packet's second word of "user data". + */ +static __inline unsigned int +NETIO_PKT_USER_DATA_1(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_USER_DATA_1_M(mda, pkt); +} + + +/** Determine whether the L4 (TCP/UDP) checksum was calculated. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the L4 checksum was calculated. + */ +static __inline unsigned int +NETIO_PKT_L4_CSUM_CALCULATED(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L4_CSUM_CALCULATED_M(mda, pkt); +} + + +/** Determine whether the L4 (TCP/UDP) checksum was calculated and found to + * be correct. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the checksum was calculated and is correct. + */ +static __inline unsigned int +NETIO_PKT_L4_CSUM_CORRECT(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L4_CSUM_CORRECT_M(mda, pkt); +} + + +/** Determine whether the L3 (IP) checksum was calculated. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the L3 (IP) checksum was calculated. +*/ +static __inline unsigned int +NETIO_PKT_L3_CSUM_CALCULATED(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L3_CSUM_CALCULATED_M(mda, pkt); +} + + +/** Determine whether the L3 (IP) checksum was calculated and found to be + * correct. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the checksum was calculated and is correct. + */ +static __inline unsigned int +NETIO_PKT_L3_CSUM_CORRECT(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_L3_CSUM_CORRECT_M(mda, pkt); +} + + +/** Determine whether the Ethertype was recognized and L3 packet data was + * processed. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + * @return Nonzero if the Ethertype was recognized and L3 packet data was + * processed. + */ +static __inline unsigned int +NETIO_PKT_ETHERTYPE_RECOGNIZED(netio_pkt_t* pkt) +{ + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_ETHERTYPE_RECOGNIZED_M(mda, pkt); +} + + +/** Set an egress packet's L2 length, using a metadata pointer to speed the + * computation. + * @ingroup egress + * + * @param[in,out] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @param[in] len Packet L2 length, in bytes. + */ +static __inline void +NETIO_PKT_SET_L2_LENGTH_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt, + int len) +{ + mmd->l2_length = len; +} + + +/** Set an egress packet's L2 length. + * @ingroup egress + * + * @param[in,out] pkt Packet on which to operate. + * @param[in] len Packet L2 length, in bytes. + */ +static __inline void +NETIO_PKT_SET_L2_LENGTH(netio_pkt_t* pkt, int len) +{ + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + NETIO_PKT_SET_L2_LENGTH_MM(mmd, pkt, len); +} + + +/** Set an egress packet's L2 header length, using a metadata pointer to + * speed the computation. + * @ingroup egress + * + * It is not normally necessary to call this routine; only the L2 length, + * not the header length, is needed to transmit a packet. It may be useful if + * the egress packet will later be processed by code which expects to use + * functions like @ref NETIO_PKT_L3_DATA() to get a pointer to the L3 payload. + * + * @param[in,out] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @param[in] len Packet L2 header length, in bytes. + */ +static __inline void +NETIO_PKT_SET_L2_HEADER_LENGTH_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt, int len) +{ + mmd->l3_offset = mmd->l2_offset + len; +} + + +/** Set an egress packet's L2 header length. + * @ingroup egress + * + * It is not normally necessary to call this routine; only the L2 length, + * not the header length, is needed to transmit a packet. It may be useful if + * the egress packet will later be processed by code which expects to use + * functions like @ref NETIO_PKT_L3_DATA() to get a pointer to the L3 payload. + * + * @param[in,out] pkt Packet on which to operate. + * @param[in] len Packet L2 header length, in bytes. + */ +static __inline void +NETIO_PKT_SET_L2_HEADER_LENGTH(netio_pkt_t* pkt, int len) +{ + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + NETIO_PKT_SET_L2_HEADER_LENGTH_MM(mmd, pkt, len); +} + + +/** Set up an egress packet for hardware checksum computation, using a + * metadata pointer to speed the operation. + * @ingroup egress + * + * NetIO provides the ability to automatically calculate a standard + * 16-bit Internet checksum on transmitted packets. The application + * may specify the point in the packet where the checksum starts, the + * number of bytes to be checksummed, and the two bytes in the packet + * which will be replaced with the completed checksum. (If the range + * of bytes to be checksummed includes the bytes to be replaced, the + * initial values of those bytes will be included in the checksum.) + * + * For some protocols, the packet checksum covers data which is not present + * in the packet, or is at least not contiguous to the main data payload. + * For instance, the TCP checksum includes a "pseudo-header" which includes + * the source and destination IP addresses of the packet. To accommodate + * this, the checksum engine may be "seeded" with an initial value, which + * the application would need to compute based on the specific protocol's + * requirements. Note that the seed is given in host byte order (little- + * endian), not network byte order (big-endian); code written to compute a + * pseudo-header checksum in network byte order will need to byte-swap it + * before use as the seed. + * + * Note that the checksum is computed as part of the transmission process, + * so it will not be present in the packet upon completion of this routine. + * + * @param[in,out] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + * @param[in] start Offset within L2 packet of the first byte to include in + * the checksum. + * @param[in] length Number of bytes to include in the checksum. + * the checksum. + * @param[in] location Offset within L2 packet of the first of the two bytes + * to be replaced with the calculated checksum. + * @param[in] seed Initial value of the running checksum before any of the + * packet data is added. + */ +static __inline void +NETIO_PKT_DO_EGRESS_CSUM_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt, int start, int length, + int location, uint16_t seed) +{ + mmd->csum_start = start; + mmd->csum_length = length; + mmd->csum_location = location; + mmd->csum_seed = seed; + mmd->flags |= _NETIO_PKT_NEED_EDMA_CSUM_MASK; +} + + +/** Set up an egress packet for hardware checksum computation. + * @ingroup egress + * + * NetIO provides the ability to automatically calculate a standard + * 16-bit Internet checksum on transmitted packets. The application + * may specify the point in the packet where the checksum starts, the + * number of bytes to be checksummed, and the two bytes in the packet + * which will be replaced with the completed checksum. (If the range + * of bytes to be checksummed includes the bytes to be replaced, the + * initial values of those bytes will be included in the checksum.) + * + * For some protocols, the packet checksum covers data which is not present + * in the packet, or is at least not contiguous to the main data payload. + * For instance, the TCP checksum includes a "pseudo-header" which includes + * the source and destination IP addresses of the packet. To accommodate + * this, the checksum engine may be "seeded" with an initial value, which + * the application would need to compute based on the specific protocol's + * requirements. Note that the seed is given in host byte order (little- + * endian), not network byte order (big-endian); code written to compute a + * pseudo-header checksum in network byte order will need to byte-swap it + * before use as the seed. + * + * Note that the checksum is computed as part of the transmission process, + * so it will not be present in the packet upon completion of this routine. + * + * @param[in,out] pkt Packet on which to operate. + * @param[in] start Offset within L2 packet of the first byte to include in + * the checksum. + * @param[in] length Number of bytes to include in the checksum. + * the checksum. + * @param[in] location Offset within L2 packet of the first of the two bytes + * to be replaced with the calculated checksum. + * @param[in] seed Initial value of the running checksum before any of the + * packet data is added. + */ +static __inline void +NETIO_PKT_DO_EGRESS_CSUM(netio_pkt_t* pkt, int start, int length, + int location, uint16_t seed) +{ + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + NETIO_PKT_DO_EGRESS_CSUM_MM(mmd, pkt, start, length, location, seed); +} + + +/** Return the number of bytes which could be prepended to a packet, using a + * metadata pointer to speed the operation. + * See @ref netio_populate_prepend_buffer() to get a full description of + * prepending. + * + * @param[in,out] mda Pointer to packet's standard metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline int +NETIO_PKT_PREPEND_AVAIL_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ + return (pkt->__packet.bits.__offset << 6) + + NETIO_PKT_CUSTOM_HEADER_LENGTH_M(mda, pkt); +} + + +/** Return the number of bytes which could be prepended to a packet, using a + * metadata pointer to speed the operation. + * See @ref netio_populate_prepend_buffer() to get a full description of + * prepending. + * @ingroup egress + * + * @param[in,out] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline int +NETIO_PKT_PREPEND_AVAIL_MM(netio_pkt_minimal_metadata_t* mmd, netio_pkt_t* pkt) +{ + return (pkt->__packet.bits.__offset << 6) + mmd->l2_offset; +} + + +/** Return the number of bytes which could be prepended to a packet. + * See @ref netio_populate_prepend_buffer() to get a full description of + * prepending. + * @ingroup egress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline int +NETIO_PKT_PREPEND_AVAIL(netio_pkt_t* pkt) +{ + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = NETIO_PKT_MINIMAL_METADATA(pkt); + + return NETIO_PKT_PREPEND_AVAIL_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = NETIO_PKT_METADATA(pkt); + + return NETIO_PKT_PREPEND_AVAIL_M(mda, pkt); + } +} + + +/** Flush a packet's minimal metadata from the cache, using a metadata pointer + * to speed the operation. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_MINIMAL_METADATA_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt) +{ +} + + +/** Invalidate a packet's minimal metadata from the cache, using a metadata + * pointer to speed the operation. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_INV_MINIMAL_METADATA_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt) +{ +} + + +/** Flush and then invalidate a packet's minimal metadata from the cache, + * using a metadata pointer to speed the operation. + * @ingroup egress + * + * @param[in] mmd Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_INV_MINIMAL_METADATA_MM(netio_pkt_minimal_metadata_t* mmd, + netio_pkt_t* pkt) +{ +} + + +/** Flush a packet's metadata from the cache, using a metadata pointer + * to speed the operation. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's minimal metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_METADATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ +} + + +/** Invalidate a packet's metadata from the cache, using a metadata + * pointer to speed the operation. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_INV_METADATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ +} + + +/** Flush and then invalidate a packet's metadata from the cache, + * using a metadata pointer to speed the operation. + * @ingroup ingress + * + * @param[in] mda Pointer to packet's metadata. + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_INV_METADATA_M(netio_pkt_metadata_t* mda, netio_pkt_t* pkt) +{ +} + + +/** Flush a packet's minimal metadata from the cache. + * @ingroup egress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_MINIMAL_METADATA(netio_pkt_t* pkt) +{ +} + + +/** Invalidate a packet's minimal metadata from the cache. + * @ingroup egress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_INV_MINIMAL_METADATA(netio_pkt_t* pkt) +{ +} + + +/** Flush and then invalidate a packet's minimal metadata from the cache. + * @ingroup egress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_INV_MINIMAL_METADATA(netio_pkt_t* pkt) +{ +} + + +/** Flush a packet's metadata from the cache. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_METADATA(netio_pkt_t* pkt) +{ +} + + +/** Invalidate a packet's metadata from the cache. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_INV_METADATA(netio_pkt_t* pkt) +{ +} + + +/** Flush and then invalidate a packet's metadata from the cache. + * @ingroup ingress + * + * @param[in] pkt Packet on which to operate. + */ +static __inline void +NETIO_PKT_FLUSH_INV_METADATA(netio_pkt_t* pkt) +{ +} + +/** Number of NUMA nodes we can distribute buffers to. + * @ingroup setup */ +#define NETIO_NUM_NODE_WEIGHTS 16 + +/** + * @brief An object for specifying the characteristics of NetIO communication + * endpoint. + * + * @ingroup setup + * + * The @ref netio_input_register() function uses this structure to define + * how an application tile will communicate with an IPP. + * + * + * Future updates to NetIO may add new members to this structure, + * which can affect the success of the registration operation. Thus, + * if dynamically initializing the structure, applications are urged to + * zero it out first, for example: + * + * @code + * netio_input_config_t config; + * memset(&config, 0, sizeof (config)); + * config.flags = NETIO_RECV | NETIO_XMIT_CSUM | NETIO_TAG_NONE; + * config.num_receive_packets = NETIO_MAX_RECEIVE_PKTS; + * config.queue_id = 0; + * . + * . + * . + * @endcode + * + * since that guarantees that any unused structure members, including + * members which did not exist when the application was first developed, + * will not have unexpected values. + * + * If statically initializing the structure, we strongly recommend use of + * C99-style named initializers, for example: + * + * @code + * netio_input_config_t config = { + * .flags = NETIO_RECV | NETIO_XMIT_CSUM | NETIO_TAG_NONE, + * .num_receive_packets = NETIO_MAX_RECEIVE_PKTS, + * .queue_id = 0, + * }, + * @endcode + * + * instead of the old-style structure initialization: + * + * @code + * // Bad example! Currently equivalent to the above, but don't do this. + * netio_input_config_t config = { + * NETIO_RECV | NETIO_XMIT_CSUM | NETIO_TAG_NONE, NETIO_MAX_RECEIVE_PKTS, 0 + * }, + * @endcode + * + * since the C99 style requires no changes to the code if elements of the + * config structure are rearranged. (It also makes the initialization much + * easier to understand.) + * + * Except for items which address a particular tile's transmit or receive + * characteristics, such as the ::NETIO_RECV flag, applications are advised + * to specify the same set of configuration data on all registrations. + * This prevents differing results if multiple tiles happen to do their + * registration operations in a different order on different invocations of + * the application. This is particularly important for things like link + * management flags, and buffer size and homing specifications. + * + * Unless the ::NETIO_FIXED_BUFFER_VA flag is specified in flags, the NetIO + * buffer pool is automatically created and mapped into the application's + * virtual address space at an address chosen by the operating system, + * using the common memory (cmem) facility in the Tilera Multicore + * Components library. The cmem facility allows multiple processes to gain + * access to shared memory which is mapped into each process at an + * identical virtual address. In order for this to work, the processes + * must have a common ancestor, which must create the common memory using + * tmc_cmem_init(). + * + * In programs using the iLib process creation API, or in programs which use + * only one process (which include programs using the pthreads library), + * tmc_cmem_init() is called automatically. All other applications + * must call it explicitly, before any child processes which might call + * netio_input_register() are created. + */ +typedef struct +{ + /** Registration characteristics. + + This value determines several characteristics of the registration; + flags for different types of behavior are ORed together to make the + final flag value. Generally applications should specify exactly + one flag from each of the following categories: + + - Whether the application will be receiving packets on this queue + (::NETIO_RECV or ::NETIO_NO_RECV). + + - Whether the application will be transmitting packets on this queue, + and if so, whether it will request egress checksum calculation + (::NETIO_XMIT, ::NETIO_XMIT_CSUM, or ::NETIO_NO_XMIT). It is + legal to call netio_get_buffer() without one of the XMIT flags, + as long as ::NETIO_RECV is specified; in this case, the retrieved + buffers must be passed to another tile for transmission. + + - Whether the application expects any vendor-specific tags in + its packets' L2 headers (::NETIO_TAG_NONE, ::NETIO_TAG_BRCM, + or ::NETIO_TAG_MRVL). This must match the configuration of the + target IPP. + + To accommodate applications written to previous versions of the NetIO + interface, none of the flags above are currently required; if omitted, + NetIO behaves more or less as if ::NETIO_RECV | ::NETIO_XMIT_CSUM | + ::NETIO_TAG_NONE were used. However, explicit specification of + the relevant flags allows NetIO to do a better job of resource + allocation, allows earlier detection of certain configuration errors, + and may enable advanced features or higher performance in the future, + so their use is strongly recommended. + + Note that specifying ::NETIO_NO_RECV along with ::NETIO_NO_XMIT + is a special case, intended primarily for use by programs which + retrieve network statistics or do link management operations. + When these flags are both specified, the resulting queue may not + be used with NetIO routines other than netio_get(), netio_set(), + and netio_input_unregister(). See @ref link for more information + on link management. + + Other flags are optional; their use is described below. + */ + int flags; + + /** Interface name. This is a string which identifies the specific + Ethernet controller hardware to be used. The format of the string + is a device type and a device index, separated by a slash; so, + the first 10 Gigabit Ethernet controller is named "xgbe/0", while + the second 10/100/1000 Megabit Ethernet controller is named "gbe/1". + */ + const char* interface; + + /** Receive packet queue size. This specifies the maximum number + of ingress packets that can be received on this queue without + being retrieved by @ref netio_get_packet(). If the IPP's distribution + algorithm calls for a packet to be sent to this queue, and this + number of packets are already pending there, the new packet + will either be discarded, or sent to another tile registered + for the same queue_id (see @ref drops). This value must + be at least ::NETIO_MIN_RECEIVE_PKTS, can always be at least + ::NETIO_MAX_RECEIVE_PKTS, and may be larger than that on certain + interfaces. + */ + int num_receive_packets; + + /** The queue ID being requested. Legal values for this range from 0 + to ::NETIO_MAX_QUEUE_ID, inclusive. ::NETIO_MAX_QUEUE_ID is always + greater than or equal to the number of tiles; this allows one queue + for each tile, plus at least one additional queue. Some applications + may wish to use the additional queue as a destination for unwanted + packets, since packets delivered to queues for which no tiles have + registered are discarded. + */ + unsigned int queue_id; + + /** Maximum number of small send buffers to be held in the local empty + buffer cache. This specifies the size of the area which holds + empty small egress buffers requested from the IPP but not yet + retrieved via @ref netio_get_buffer(). This value must be greater + than zero if the application will ever use @ref netio_get_buffer() + to allocate empty small egress buffers; it may be no larger than + ::NETIO_MAX_SEND_BUFFERS. See @ref epp for more details on empty + buffer caching. + */ + int num_send_buffers_small_total; + + /** Number of small send buffers to be preallocated at registration. + If this value is nonzero, the specified number of empty small egress + buffers will be requested from the IPP during the netio_input_register + operation; this may speed the execution of @ref netio_get_buffer(). + This may be no larger than @ref num_send_buffers_small_total. See @ref + epp for more details on empty buffer caching. + */ + int num_send_buffers_small_prealloc; + + /** Maximum number of large send buffers to be held in the local empty + buffer cache. This specifies the size of the area which holds empty + large egress buffers requested from the IPP but not yet retrieved via + @ref netio_get_buffer(). This value must be greater than zero if the + application will ever use @ref netio_get_buffer() to allocate empty + large egress buffers; it may be no larger than ::NETIO_MAX_SEND_BUFFERS. + See @ref epp for more details on empty buffer caching. + */ + int num_send_buffers_large_total; + + /** Number of large send buffers to be preallocated at registration. + If this value is nonzero, the specified number of empty large egress + buffers will be requested from the IPP during the netio_input_register + operation; this may speed the execution of @ref netio_get_buffer(). + This may be no larger than @ref num_send_buffers_large_total. See @ref + epp for more details on empty buffer caching. + */ + int num_send_buffers_large_prealloc; + + /** Maximum number of jumbo send buffers to be held in the local empty + buffer cache. This specifies the size of the area which holds empty + jumbo egress buffers requested from the IPP but not yet retrieved via + @ref netio_get_buffer(). This value must be greater than zero if the + application will ever use @ref netio_get_buffer() to allocate empty + jumbo egress buffers; it may be no larger than ::NETIO_MAX_SEND_BUFFERS. + See @ref epp for more details on empty buffer caching. + */ + int num_send_buffers_jumbo_total; + + /** Number of jumbo send buffers to be preallocated at registration. + If this value is nonzero, the specified number of empty jumbo egress + buffers will be requested from the IPP during the netio_input_register + operation; this may speed the execution of @ref netio_get_buffer(). + This may be no larger than @ref num_send_buffers_jumbo_total. See @ref + epp for more details on empty buffer caching. + */ + int num_send_buffers_jumbo_prealloc; + + /** Total packet buffer size. This determines the total size, in bytes, + of the NetIO buffer pool. Note that the maximum number of available + buffers of each size is determined during hypervisor configuration + (see the <em>System Programmer's Guide</em> for details); this just + influences how much host memory is allocated for those buffers. + + The buffer pool is allocated from common memory, which will be + automatically initialized if needed. If your buffer pool is larger + than 240 MB, you might need to explicitly call @c tmc_cmem_init(), + as described in the Application Libraries Reference Manual (UG227). + + Packet buffers are currently allocated in chunks of 16 MB; this + value will be rounded up to the next larger multiple of 16 MB. + If this value is zero, a default of 32 MB will be used; this was + the value used by previous versions of NetIO. Note that taking this + default also affects the placement of buffers on Linux NUMA nodes. + See @ref buffer_node_weights for an explanation of buffer placement. + + In order to successfully allocate packet buffers, Linux must have + available huge pages on the relevant Linux NUMA nodes. See the + <em>System Programmer's Guide</em> for information on configuring + huge page support in Linux. + */ + uint64_t total_buffer_size; + + /** Buffer placement weighting factors. + + This array specifies the relative amount of buffering to place + on each of the available Linux NUMA nodes. This array is + indexed by the NUMA node, and the values in the array are + proportional to the amount of buffer space to allocate on that + node. + + If memory striping is enabled in the Hypervisor, then there is + only one logical NUMA node (node 0). In that case, NetIO will by + default ignore the suggested buffer node weights, and buffers + will be striped across the physical memory controllers. See + UG209 System Programmer's Guide for a description of the + hypervisor option that controls memory striping. + + If memory striping is disabled, then there are up to four NUMA + nodes, corresponding to the four DDRAM controllers in the TILE + processor architecture. See UG100 Tile Processor Architecture + Overview for a diagram showing the location of each of the DDRAM + controllers relative to the tile array. + + For instance, if memory striping is disabled, the following + configuration strucure: + + @code + netio_input_config_t config = { + . + . + . + .total_buffer_size = 4 * 16 * 1024 * 1024; + .buffer_node_weights = { 1, 0, 1, 0 }, + }, + @endcode + + would result in 32 MB of buffers being placed on controller 0, and + 32 MB on controller 2. (Since buffers are allocated in units of + 16 MB, some sets of weights will not be able to be matched exactly.) + + For the weights to be effective, @ref total_buffer_size must be + nonzero. If @ref total_buffer_size is zero, causing the default + 32 MB of buffer space to be used, then any specified weights will + be ignored, and buffers will positioned as they were in previous + versions of NetIO: + + - For xgbe/0 and gbe/0, 16 MB of buffers will be placed on controller 1, + and the other 16 MB will be placed on controller 2. + + - For xgbe/1 and gbe/1, 16 MB of buffers will be placed on controller 2, + and the other 16 MB will be placed on controller 3. + + If @ref total_buffer_size is nonzero, but all weights are zero, + then all buffer space will be allocated on Linux NUMA node zero. + + By default, the specified buffer placement is treated as a hint; + if sufficient free memory is not available on the specified + controllers, the buffers will be allocated elsewhere. However, + if the ::NETIO_STRICT_HOMING flag is specified in @ref flags, then a + failure to allocate buffer space exactly as requested will cause the + registration operation to fail with an error of ::NETIO_CANNOT_HOME. + + Note that maximal network performance cannot be achieved with + only one memory controller. + */ + uint8_t buffer_node_weights[NETIO_NUM_NODE_WEIGHTS]; + + /** Fixed virtual address for packet buffers. Only valid when + ::NETIO_FIXED_BUFFER_VA is specified in @ref flags; see the + description of that flag for details. + */ + void* fixed_buffer_va; + + /** + Maximum number of outstanding send packet requests. This value is + only relevant when an EPP is in use; it determines the number of + slots in the EPP's outgoing packet queue which this tile is allowed + to consume, and thus the number of packets which may be sent before + the sending tile must wait for an acknowledgment from the EPP. + Modifying this value is generally only helpful when using @ref + netio_send_packet_vector(), where it can help improve performance by + allowing a single vector send operation to process more packets. + Typically it is not specified, and the default, which divides the + outgoing packet slots evenly between all tiles on the chip, is used. + + If a registration asks for more outgoing packet queue slots than are + available, ::NETIO_TOOMANY_XMIT will be returned. The total number + of packet queue slots which are available for all tiles for each EPP + is subject to change, but is currently ::NETIO_TOTAL_SENDS_OUTSTANDING. + + + This value is ignored if ::NETIO_XMIT is not specified in flags. + If you want to specify a large value here for a specific tile, you are + advised to specify NETIO_NO_XMIT on other, non-transmitting tiles so + that they do not consume a default number of packet slots. Any tile + transmitting is required to have at least ::NETIO_MIN_SENDS_OUTSTANDING + slots allocated to it; values less than that will be silently + increased by the NetIO library. + */ + int num_sends_outstanding; +} +netio_input_config_t; + + +/** Registration flags; used in the @ref netio_input_config_t structure. + * @addtogroup setup + */ +/** @{ */ + +/** Fail a registration request if we can't put packet buffers + on the specified memory controllers. */ +#define NETIO_STRICT_HOMING 0x00000002 + +/** This application expects no tags on its L2 headers. */ +#define NETIO_TAG_NONE 0x00000004 + +/** This application expects Marvell extended tags on its L2 headers. */ +#define NETIO_TAG_MRVL 0x00000008 + +/** This application expects Broadcom tags on its L2 headers. */ +#define NETIO_TAG_BRCM 0x00000010 + +/** This registration may call routines which receive packets. */ +#define NETIO_RECV 0x00000020 + +/** This registration may not call routines which receive packets. */ +#define NETIO_NO_RECV 0x00000040 + +/** This registration may call routines which transmit packets. */ +#define NETIO_XMIT 0x00000080 + +/** This registration may call routines which transmit packets with + checksum acceleration. */ +#define NETIO_XMIT_CSUM 0x00000100 + +/** This registration may not call routines which transmit packets. */ +#define NETIO_NO_XMIT 0x00000200 + +/** This registration wants NetIO buffers mapped at an application-specified + virtual address. + + NetIO buffers are by default created by the TMC common memory facility, + which must be configured by a common ancestor of all processes sharing + a network interface. When this flag is specified, NetIO buffers are + instead mapped at an address chosen by the application (and specified + in @ref netio_input_config_t::fixed_buffer_va). This allows multiple + unrelated but cooperating processes to share a NetIO interface. + All processes sharing the same interface must specify this flag, + and all must specify the same fixed virtual address. + + @ref netio_input_config_t::fixed_buffer_va must be a + multiple of 16 MB, and the packet buffers will occupy @ref + netio_input_config_t::total_buffer_size bytes of virtual address + space, beginning at that address. If any of those virtual addresses + are currently occupied by other memory objects, like application or + shared library code or data, @ref netio_input_register() will return + ::NETIO_FAULT. While it is impossible to provide a fixed_buffer_va + which will work for all applications, a good first guess might be to + use 0xb0000000 minus @ref netio_input_config_t::total_buffer_size. + If that fails, it might be helpful to consult the running application's + virtual address description file (/proc/<em>pid</em>/maps) to see + which regions of virtual address space are available. + */ +#define NETIO_FIXED_BUFFER_VA 0x00000400 + +/** This registration call will not complete unless the network link + is up. The process will wait several seconds for this to happen (the + precise interval is link-dependent), but if the link does not come up, + ::NETIO_LINK_DOWN will be returned. This flag is the default if + ::NETIO_NOREQUIRE_LINK_UP is not specified. Note that this flag by + itself does not request that the link be brought up; that can be done + with the ::NETIO_AUTO_LINK_UPDN or ::NETIO_AUTO_LINK_UP flags (the + latter is the default if no NETIO_AUTO_LINK_xxx flags are specified), + or by explicitly setting the link's desired state via netio_set(). + If the link is not brought up by one of those methods, and this flag + is specified, the registration operation will return ::NETIO_LINK_DOWN. + This flag is ignored if it is specified along with ::NETIO_NO_XMIT and + ::NETIO_NO_RECV. See @ref link for more information on link + management. + */ +#define NETIO_REQUIRE_LINK_UP 0x00000800 + +/** This registration call will complete even if the network link is not up. + Whenever the link is not up, packets will not be sent or received: + netio_get_packet() will return ::NETIO_NOPKT once all queued packets + have been drained, and netio_send_packet() and similar routines will + return NETIO_QUEUE_FULL once the outgoing packet queue in the EPP + or the I/O shim is full. See @ref link for more information on link + management. + */ +#define NETIO_NOREQUIRE_LINK_UP 0x00001000 + +#ifndef __DOXYGEN__ +/* + * These are part of the implementation of the NETIO_AUTO_LINK_xxx flags, + * but should not be used directly by applications, and are thus not + * documented. + */ +#define _NETIO_AUTO_UP 0x00002000 +#define _NETIO_AUTO_DN 0x00004000 +#define _NETIO_AUTO_PRESENT 0x00008000 +#endif + +/** Set the desired state of the link to up, allowing any speeds which are + supported by the link hardware, as part of this registration operation. + Do not take down the link automatically. This is the default if + no other NETIO_AUTO_LINK_xxx flags are specified. This flag is ignored + if it is specified along with ::NETIO_NO_XMIT and ::NETIO_NO_RECV. + See @ref link for more information on link management. + */ +#define NETIO_AUTO_LINK_UP (_NETIO_AUTO_PRESENT | _NETIO_AUTO_UP) + +/** Set the desired state of the link to up, allowing any speeds which are + supported by the link hardware, as part of this registration operation. + Set the desired state of the link to down the next time no tiles are + registered for packet reception or transmission. This flag is ignored + if it is specified along with ::NETIO_NO_XMIT and ::NETIO_NO_RECV. + See @ref link for more information on link management. + */ +#define NETIO_AUTO_LINK_UPDN (_NETIO_AUTO_PRESENT | _NETIO_AUTO_UP | \ + _NETIO_AUTO_DN) + +/** Set the desired state of the link to down the next time no tiles are + registered for packet reception or transmission. This flag is ignored + if it is specified along with ::NETIO_NO_XMIT and ::NETIO_NO_RECV. + See @ref link for more information on link management. + */ +#define NETIO_AUTO_LINK_DN (_NETIO_AUTO_PRESENT | _NETIO_AUTO_DN) + +/** Do not bring up the link automatically as part of this registration + operation. Do not take down the link automatically. This flag + is ignored if it is specified along with ::NETIO_NO_XMIT and + ::NETIO_NO_RECV. See @ref link for more information on link management. + */ +#define NETIO_AUTO_LINK_NONE _NETIO_AUTO_PRESENT + + +/** Minimum number of receive packets. */ +#define NETIO_MIN_RECEIVE_PKTS 16 + +/** Lower bound on the maximum number of receive packets; may be higher + than this on some interfaces. */ +#define NETIO_MAX_RECEIVE_PKTS 128 + +/** Maximum number of send buffers, per packet size. */ +#define NETIO_MAX_SEND_BUFFERS 16 + +/** Number of EPP queue slots, and thus outstanding sends, per EPP. */ +#define NETIO_TOTAL_SENDS_OUTSTANDING 2015 + +/** Minimum number of EPP queue slots, and thus outstanding sends, per + * transmitting tile. */ +#define NETIO_MIN_SENDS_OUTSTANDING 16 + + +/**@}*/ + +#ifndef __DOXYGEN__ + +/** + * An object for providing Ethernet packets to a process. + */ +struct __netio_queue_impl_t; + +/** + * An object for managing the user end of a NetIO queue. + */ +struct __netio_queue_user_impl_t; + +#endif /* !__DOXYGEN__ */ + + +/** A netio_queue_t describes a NetIO communications endpoint. + * @ingroup setup + */ +typedef struct +{ +#ifdef __DOXYGEN__ + uint8_t opaque[8]; /**< This is an opaque structure. */ +#else + struct __netio_queue_impl_t* __system_part; /**< The system part. */ + struct __netio_queue_user_impl_t* __user_part; /**< The user part. */ +#ifdef _NETIO_PTHREAD + _netio_percpu_mutex_t lock; /**< Queue lock. */ +#endif +#endif +} +netio_queue_t; + + +/** + * @brief Packet send context. + * + * @ingroup egress + * + * Packet send context for use with netio_send_packet_prepare and _commit. + */ +typedef struct +{ +#ifdef __DOXYGEN__ + uint8_t opaque[44]; /**< This is an opaque structure. */ +#else + uint8_t flags; /**< Defined below */ + uint8_t datalen; /**< Number of valid words pointed to by data. */ + uint32_t request[9]; /**< Request to be sent to the EPP or shim. Note + that this is smaller than the 11-word maximum + request size, since some constant values are + not saved in the context. */ + uint32_t *data; /**< Data to be sent to the EPP or shim via IDN. */ +#endif +} +netio_send_pkt_context_t; + + +#ifndef __DOXYGEN__ +#define SEND_PKT_CTX_USE_EPP 1 /**< We're sending to an EPP. */ +#define SEND_PKT_CTX_SEND_CSUM 2 /**< Request includes a checksum. */ +#endif + +/** + * @brief Packet vector entry. + * + * @ingroup egress + * + * This data structure is used with netio_send_packet_vector() to send multiple + * packets with one NetIO call. The structure should be initialized by + * calling netio_pkt_vector_set(), rather than by setting the fields + * directly. + * + * This structure is guaranteed to be a power of two in size, no + * bigger than one L2 cache line, and to be aligned modulo its size. + */ +typedef struct +#ifndef __DOXYGEN__ +__attribute__((aligned(8))) +#endif +{ + /** Reserved for use by the user application. When initialized with + * the netio_set_pkt_vector_entry() function, this field is guaranteed + * to be visible to readers only after all other fields are already + * visible. This way it can be used as a valid flag or generation + * counter. */ + uint8_t user_data; + + /* Structure members below this point should not be accessed directly by + * applications, as they may change in the future. */ + + /** Low 8 bits of the packet address to send. The high bits are + * acquired from the 'handle' field. */ + uint8_t buffer_address_low; + + /** Number of bytes to transmit. */ + uint16_t size; + + /** The raw handle from a netio_pkt_t. If this is NETIO_PKT_HANDLE_NONE, + * this vector entry will be skipped and no packet will be transmitted. */ + netio_pkt_handle_t handle; +} +netio_pkt_vector_entry_t; + + +/** + * @brief Initialize fields in a packet vector entry. + * + * @ingroup egress + * + * @param[out] v Pointer to the vector entry to be initialized. + * @param[in] pkt Packet to be transmitted when the vector entry is passed to + * netio_send_packet_vector(). Note that the packet's attributes + * (e.g., its L2 offset and length) are captured at the time this + * routine is called; subsequent changes in those attributes will not + * be reflected in the packet which is actually transmitted. + * Changes in the packet's contents, however, will be so reflected. + * If this is NULL, no packet will be transmitted. + * @param[in] user_data User data to be set in the vector entry. + * This function guarantees that the "user_data" field will become + * visible to a reader only after all other fields have become visible. + * This allows a structure in a ring buffer to be written and read + * by a polling reader without any locks or other synchronization. + */ +static __inline void +netio_pkt_vector_set(volatile netio_pkt_vector_entry_t* v, netio_pkt_t* pkt, + uint8_t user_data) +{ + if (pkt) + { + if (NETIO_PKT_IS_MINIMAL(pkt)) + { + netio_pkt_minimal_metadata_t* mmd = + (netio_pkt_minimal_metadata_t*) &pkt->__metadata; + v->buffer_address_low = (uintptr_t) NETIO_PKT_L2_DATA_MM(mmd, pkt) & 0xFF; + v->size = NETIO_PKT_L2_LENGTH_MM(mmd, pkt); + } + else + { + netio_pkt_metadata_t* mda = &pkt->__metadata; + v->buffer_address_low = (uintptr_t) NETIO_PKT_L2_DATA_M(mda, pkt) & 0xFF; + v->size = NETIO_PKT_L2_LENGTH_M(mda, pkt); + } + v->handle.word = pkt->__packet.word; + } + else + { + v->handle.word = 0; /* Set handle to NETIO_PKT_HANDLE_NONE. */ + } + + __asm__("" : : : "memory"); + + v->user_data = user_data; +} + + +/** + * Flags and structures for @ref netio_get() and @ref netio_set(). + * @ingroup config + */ + +/** @{ */ +/** Parameter class; addr is a NETIO_PARAM_xxx value. */ +#define NETIO_PARAM 0 +/** Interface MAC address. This address is only valid with @ref netio_get(). + * The value is a 6-byte MAC address. Depending upon the overall system + * design, a MAC address may or may not be available for each interface. */ +#define NETIO_PARAM_MAC 0 + +/** Determine whether to suspend output on the receipt of pause frames. + * If the value is nonzero, the I/O shim will suspend output when a pause + * frame is received. If the value is zero, pause frames will be ignored. */ +#define NETIO_PARAM_PAUSE_IN 1 + +/** Determine whether to send pause frames if the I/O shim packet FIFOs are + * nearly full. If the value is zero, pause frames are not sent. If + * the value is nonzero, it is the delay value which will be sent in any + * pause frames which are output, in units of 512 bit times. */ +#define NETIO_PARAM_PAUSE_OUT 2 + +/** Jumbo frame support. The value is a 4-byte integer. If the value is + * nonzero, the MAC will accept frames of up to 10240 bytes. If the value + * is zero, the MAC will only accept frames of up to 1544 bytes. */ +#define NETIO_PARAM_JUMBO 3 + +/** I/O shim's overflow statistics register. The value is two 16-bit integers. + * The first 16-bit value (or the low 16 bits, if the value is treated as a + * 32-bit number) is the count of packets which were completely dropped and + * not delivered by the shim. The second 16-bit value (or the high 16 bits, + * if the value is treated as a 32-bit number) is the count of packets + * which were truncated and thus only partially delivered by the shim. This + * register is automatically reset to zero after it has been read. + */ +#define NETIO_PARAM_OVERFLOW 4 + +/** IPP statistics. This address is only valid with @ref netio_get(). The + * value is a netio_stat_t structure. Unlike the I/O shim statistics, the + * IPP statistics are not all reset to zero on read; see the description + * of the netio_stat_t for details. */ +#define NETIO_PARAM_STAT 5 + +/** Possible link state. The value is a combination of "NETIO_LINK_xxx" + * flags. With @ref netio_get(), this will indicate which flags are + * actually supported by the hardware. + * + * For historical reasons, specifying this value to netio_set() will have + * the same behavior as using ::NETIO_PARAM_LINK_CONFIG, but this usage is + * discouraged. + */ +#define NETIO_PARAM_LINK_POSSIBLE_STATE 6 + +/** Link configuration. The value is a combination of "NETIO_LINK_xxx" flags. + * With @ref netio_set(), this will attempt to immediately bring up the + * link using whichever of the requested flags are supported by the + * hardware, or take down the link if the flags are zero; if this is + * not possible, an error will be returned. Many programs will want + * to use ::NETIO_PARAM_LINK_DESIRED_STATE instead. + * + * For historical reasons, specifying this value to netio_get() will + * have the same behavior as using ::NETIO_PARAM_LINK_POSSIBLE_STATE, + * but this usage is discouraged. + */ +#define NETIO_PARAM_LINK_CONFIG NETIO_PARAM_LINK_POSSIBLE_STATE + +/** Current link state. This address is only valid with @ref netio_get(). + * The value is zero or more of the "NETIO_LINK_xxx" flags, ORed together. + * If the link is down, the value ANDed with NETIO_LINK_SPEED will be + * zero; if the link is up, the value ANDed with NETIO_LINK_SPEED will + * result in exactly one of the NETIO_LINK_xxx values, indicating the + * current speed. */ +#define NETIO_PARAM_LINK_CURRENT_STATE 7 + +/** Variant symbol for current state, retained for compatibility with + * pre-MDE-2.1 programs. */ +#define NETIO_PARAM_LINK_STATUS NETIO_PARAM_LINK_CURRENT_STATE + +/** Packet Coherence protocol. This address is only valid with @ref netio_get(). + * The value is nonzero if the interface is configured for cache-coherent DMA. + */ +#define NETIO_PARAM_COHERENT 8 + +/** Desired link state. The value is a conbination of "NETIO_LINK_xxx" + * flags, which specify the desired state for the link. With @ref + * netio_set(), this will, in the background, attempt to bring up the link + * using whichever of the requested flags are reasonable, or take down the + * link if the flags are zero. The actual link up or down operation may + * happen after this call completes. If the link state changes in the + * future, the system will continue to try to get back to the desired link + * state; for instance, if the link is brought up successfully, and then + * the network cable is disconnected, the link will go down. However, the + * desired state of the link is still up, so if the cable is reconnected, + * the link will be brought up again. + * + * With @ref netio_get(), this will indicate the desired state for the + * link, as set with a previous netio_set() call, or implicitly by a + * netio_input_register() or netio_input_unregister() operation. This may + * not reflect the current state of the link; to get that, use + * ::NETIO_PARAM_LINK_CURRENT_STATE. */ +#define NETIO_PARAM_LINK_DESIRED_STATE 9 + +/** NetIO statistics structure. Retrieved using the ::NETIO_PARAM_STAT + * address passed to @ref netio_get(). */ +typedef struct +{ + /** Number of packets which have been received by the IPP and forwarded + * to a tile's receive queue for processing. This value wraps at its + * maximum, and is not cleared upon read. */ + uint32_t packets_received; + + /** Number of packets which have been dropped by the IPP, because they could + * not be received, or could not be forwarded to a tile. The former happens + * when the IPP does not have a free packet buffer of suitable size for an + * incoming frame. The latter happens when all potential destination tiles + * for a packet, as defined by the group, bucket, and queue configuration, + * have full receive queues. This value wraps at its maximum, and is not + * cleared upon read. */ + uint32_t packets_dropped; + + /* + * Note: the #defines after each of the following four one-byte values + * denote their location within the third word of the netio_stat_t. They + * are intended for use only by the IPP implementation and are thus omitted + * from the Doxygen output. + */ + + /** Number of packets dropped because no worker was able to accept a new + * packet. This value saturates at its maximum, and is cleared upon + * read. */ + uint8_t drops_no_worker; +#ifndef __DOXYGEN__ +#define NETIO_STAT_DROPS_NO_WORKER 0 +#endif + + /** Number of packets dropped because no small buffers were available. + * This value saturates at its maximum, and is cleared upon read. */ + uint8_t drops_no_smallbuf; +#ifndef __DOXYGEN__ +#define NETIO_STAT_DROPS_NO_SMALLBUF 1 +#endif + + /** Number of packets dropped because no large buffers were available. + * This value saturates at its maximum, and is cleared upon read. */ + uint8_t drops_no_largebuf; +#ifndef __DOXYGEN__ +#define NETIO_STAT_DROPS_NO_LARGEBUF 2 +#endif + + /** Number of packets dropped because no jumbo buffers were available. + * This value saturates at its maximum, and is cleared upon read. */ + uint8_t drops_no_jumbobuf; +#ifndef __DOXYGEN__ +#define NETIO_STAT_DROPS_NO_JUMBOBUF 3 +#endif +} +netio_stat_t; + + +/** Link can run, should run, or is running at 10 Mbps. */ +#define NETIO_LINK_10M 0x01 + +/** Link can run, should run, or is running at 100 Mbps. */ +#define NETIO_LINK_100M 0x02 + +/** Link can run, should run, or is running at 1 Gbps. */ +#define NETIO_LINK_1G 0x04 + +/** Link can run, should run, or is running at 10 Gbps. */ +#define NETIO_LINK_10G 0x08 + +/** Link should run at the highest speed supported by the link and by + * the device connected to the link. Only usable as a value for + * the link's desired state; never returned as a value for the current + * or possible states. */ +#define NETIO_LINK_ANYSPEED 0x10 + +/** All legal link speeds. */ +#define NETIO_LINK_SPEED (NETIO_LINK_10M | \ + NETIO_LINK_100M | \ + NETIO_LINK_1G | \ + NETIO_LINK_10G | \ + NETIO_LINK_ANYSPEED) + + +/** MAC register class. Addr is a register offset within the MAC. + * Registers within the XGbE and GbE MACs are documented in the Tile + * Processor I/O Device Guide (UG104). MAC registers start at address + * 0x4000, and do not include the MAC_INTERFACE registers. */ +#define NETIO_MAC 1 + +/** MDIO register class (IEEE 802.3 clause 22 format). Addr is the "addr" + * member of a netio_mdio_addr_t structure. */ +#define NETIO_MDIO 2 + +/** MDIO register class (IEEE 802.3 clause 45 format). Addr is the "addr" + * member of a netio_mdio_addr_t structure. */ +#define NETIO_MDIO_CLAUSE45 3 + +/** NetIO MDIO address type. Retrieved or provided using the ::NETIO_MDIO + * address passed to @ref netio_get() or @ref netio_set(). */ +typedef union +{ + struct + { + unsigned int reg:16; /**< MDIO register offset. For clause 22 access, + must be less than 32. */ + unsigned int phy:5; /**< Which MDIO PHY to access. */ + unsigned int dev:5; /**< Which MDIO device to access within that PHY. + Applicable for clause 45 access only; ignored + for clause 22 access. */ + } + bits; /**< Container for bitfields. */ + uint64_t addr; /**< Value to pass to @ref netio_get() or + * @ref netio_set(). */ +} +netio_mdio_addr_t; + +/** @} */ + +#endif /* __NETIO_INTF_H__ */ diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile index 112b1e248f05..b4c8e8ec45dc 100644 --- a/arch/tile/kernel/Makefile +++ b/arch/tile/kernel/Makefile @@ -15,3 +15,4 @@ obj-$(CONFIG_SMP) += smpboot.o smp.o tlb.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_PCI) += pci.o diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c index 67617a05e602..dbc213adf5e1 100644 --- a/arch/tile/kernel/compat.c +++ b/arch/tile/kernel/compat.c @@ -21,7 +21,6 @@ #include <linux/kdev_t.h> #include <linux/fs.h> #include <linux/fcntl.h> -#include <linux/smp_lock.h> #include <linux/uaccess.h> #include <linux/signal.h> #include <asm/syscalls.h> diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index fb64b99959d4..dbb0dfc7bece 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -15,7 +15,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/errno.h> @@ -291,12 +290,12 @@ long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr, return ret; } +/* The assembly shim for this function arranges to ignore the return value. */ long compat_sys_rt_sigreturn(struct pt_regs *regs) { struct compat_rt_sigframe __user *frame = (struct compat_rt_sigframe __user *) compat_ptr(regs->sp); sigset_t set; - long r0; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -309,13 +308,13 @@ long compat_sys_rt_sigreturn(struct pt_regs *regs) recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (compat_sys_sigaltstack(&frame->uc.uc_stack, NULL, regs) != 0) goto badframe; - return r0; + return 0; badframe: force_sig(SIGSEGV, current); diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S index f5821626247f..5eed4a02bf62 100644 --- a/arch/tile/kernel/intvec_32.S +++ b/arch/tile/kernel/intvec_32.S @@ -1342,8 +1342,8 @@ handle_syscall: lw r20, r20 /* Jump to syscall handler. */ - jalr r20; .Lhandle_syscall_link: - FEEDBACK_REENTER(handle_syscall) + jalr r20 +.Lhandle_syscall_link: /* value of "lr" after "jalr r20" above */ /* * Write our r0 onto the stack so it gets restored instead @@ -1352,6 +1352,9 @@ handle_syscall: PTREGS_PTR(r29, PTREGS_OFFSET_REG(0)) sw r29, r0 +.Lsyscall_sigreturn_skip: + FEEDBACK_REENTER(handle_syscall) + /* Do syscall trace again, if requested. */ lw r30, r31 andi r30, r30, _TIF_SYSCALL_TRACE @@ -1536,9 +1539,24 @@ STD_ENTRY_LOCAL(bad_intr) }; \ STD_ENDPROC(_##x) +/* + * Special-case sigreturn to not write r0 to the stack on return. + * This is technically more efficient, but it also avoids difficulties + * in the 64-bit OS when handling 32-bit compat code, since we must not + * sign-extend r0 for the sigreturn return-value case. + */ +#define PTREGS_SYSCALL_SIGRETURN(x, reg) \ + STD_ENTRY(_##x); \ + addli lr, lr, .Lsyscall_sigreturn_skip - .Lhandle_syscall_link; \ + { \ + PTREGS_PTR(reg, PTREGS_OFFSET_BASE); \ + j x \ + }; \ + STD_ENDPROC(_##x) + PTREGS_SYSCALL(sys_execve, r3) PTREGS_SYSCALL(sys_sigaltstack, r2) -PTREGS_SYSCALL(sys_rt_sigreturn, r0) +PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0) PTREGS_SYSCALL(sys_cmpxchg_badaddr, r1) /* Save additional callee-saves to pt_regs, put address in r4 and jump. */ diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c new file mode 100644 index 000000000000..a1ee25be9ad9 --- /dev/null +++ b/arch/tile/kernel/pci.c @@ -0,0 +1,621 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/capability.h> +#include <linux/sched.h> +#include <linux/errno.h> +#include <linux/bootmem.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/uaccess.h> + +#include <asm/processor.h> +#include <asm/sections.h> +#include <asm/byteorder.h> +#include <asm/hv_driver.h> +#include <hv/drv_pcie_rc_intf.h> + + +/* + * Initialization flow and process + * ------------------------------- + * + * This files containes the routines to search for PCI buses, + * enumerate the buses, and configure any attached devices. + * + * There are two entry points here: + * 1) tile_pci_init + * This sets up the pci_controller structs, and opens the + * FDs to the hypervisor. This is called from setup_arch() early + * in the boot process. + * 2) pcibios_init + * This probes the PCI bus(es) for any attached hardware. It's + * called by subsys_initcall. All of the real work is done by the + * generic Linux PCI layer. + * + */ + +/* + * This flag tells if the platform is TILEmpower that needs + * special configuration for the PLX switch chip. + */ +int __write_once tile_plx_gen1; + +static struct pci_controller controllers[TILE_NUM_PCIE]; +static int num_controllers; + +static struct pci_ops tile_cfg_ops; + + +/* + * We don't need to worry about the alignment of resources. + */ +resource_size_t pcibios_align_resource(void *data, const struct resource *res, + resource_size_t size, resource_size_t align) +{ + return res->start; +} +EXPORT_SYMBOL(pcibios_align_resource); + +/* + * Open a FD to the hypervisor PCI device. + * + * controller_id is the controller number, config type is 0 or 1 for + * config0 or config1 operations. + */ +static int __init tile_pcie_open(int controller_id, int config_type) +{ + char filename[32]; + int fd; + + sprintf(filename, "pcie/%d/config%d", controller_id, config_type); + + fd = hv_dev_open((HV_VirtAddr)filename, 0); + + return fd; +} + + +/* + * Get the IRQ numbers from the HV and set up the handlers for them. + */ +static int __init tile_init_irqs(int controller_id, + struct pci_controller *controller) +{ + char filename[32]; + int fd; + int ret; + int x; + struct pcie_rc_config rc_config; + + sprintf(filename, "pcie/%d/ctl", controller_id); + fd = hv_dev_open((HV_VirtAddr)filename, 0); + if (fd < 0) { + pr_err("PCI: hv_dev_open(%s) failed\n", filename); + return -1; + } + ret = hv_dev_pread(fd, 0, (HV_VirtAddr)(&rc_config), + sizeof(rc_config), PCIE_RC_CONFIG_MASK_OFF); + hv_dev_close(fd); + if (ret != sizeof(rc_config)) { + pr_err("PCI: wanted %zd bytes, got %d\n", + sizeof(rc_config), ret); + return -1; + } + /* Record irq_base so that we can map INTx to IRQ # later. */ + controller->irq_base = rc_config.intr; + + for (x = 0; x < 4; x++) + tile_irq_activate(rc_config.intr + x, + TILE_IRQ_HW_CLEAR); + + if (rc_config.plx_gen1) + controller->plx_gen1 = 1; + + return 0; +} + +/* + * First initialization entry point, called from setup_arch(). + * + * Find valid controllers and fill in pci_controller structs for each + * of them. + * + * Returns the number of controllers discovered. + */ +int __init tile_pci_init(void) +{ + int i; + + pr_info("PCI: Searching for controllers...\n"); + + /* Do any configuration we need before using the PCIe */ + + for (i = 0; i < TILE_NUM_PCIE; i++) { + int hv_cfg_fd0 = -1; + int hv_cfg_fd1 = -1; + int hv_mem_fd = -1; + char name[32]; + struct pci_controller *controller; + + /* + * Open the fd to the HV. If it fails then this + * device doesn't exist. + */ + hv_cfg_fd0 = tile_pcie_open(i, 0); + if (hv_cfg_fd0 < 0) + continue; + hv_cfg_fd1 = tile_pcie_open(i, 1); + if (hv_cfg_fd1 < 0) { + pr_err("PCI: Couldn't open config fd to HV " + "for controller %d\n", i); + goto err_cont; + } + + sprintf(name, "pcie/%d/mem", i); + hv_mem_fd = hv_dev_open((HV_VirtAddr)name, 0); + if (hv_mem_fd < 0) { + pr_err("PCI: Could not open mem fd to HV!\n"); + goto err_cont; + } + + pr_info("PCI: Found PCI controller #%d\n", i); + + controller = &controllers[num_controllers]; + + if (tile_init_irqs(i, controller)) { + pr_err("PCI: Could not initialize " + "IRQs, aborting.\n"); + goto err_cont; + } + + controller->index = num_controllers; + controller->hv_cfg_fd[0] = hv_cfg_fd0; + controller->hv_cfg_fd[1] = hv_cfg_fd1; + controller->hv_mem_fd = hv_mem_fd; + controller->first_busno = 0; + controller->last_busno = 0xff; + controller->ops = &tile_cfg_ops; + + num_controllers++; + continue; + +err_cont: + if (hv_cfg_fd0 >= 0) + hv_dev_close(hv_cfg_fd0); + if (hv_cfg_fd1 >= 0) + hv_dev_close(hv_cfg_fd1); + if (hv_mem_fd >= 0) + hv_dev_close(hv_mem_fd); + continue; + } + + /* + * Before using the PCIe, see if we need to do any platform-specific + * configuration, such as the PLX switch Gen 1 issue on TILEmpower. + */ + for (i = 0; i < num_controllers; i++) { + struct pci_controller *controller = &controllers[i]; + + if (controller->plx_gen1) + tile_plx_gen1 = 1; + } + + return num_controllers; +} + +/* + * (pin - 1) converts from the PCI standard's [1:4] convention to + * a normal [0:3] range. + */ +static int tile_map_irq(struct pci_dev *dev, u8 slot, u8 pin) +{ + struct pci_controller *controller = + (struct pci_controller *)dev->sysdata; + return (pin - 1) + controller->irq_base; +} + + +static void __init fixup_read_and_payload_sizes(void) +{ + struct pci_dev *dev = NULL; + int smallest_max_payload = 0x1; /* Tile maxes out at 256 bytes. */ + int max_read_size = 0x2; /* Limit to 512 byte reads. */ + u16 new_values; + + /* Scan for the smallest maximum payload size. */ + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + int pcie_caps_offset; + u32 devcap; + int max_payload; + + pcie_caps_offset = pci_find_capability(dev, PCI_CAP_ID_EXP); + if (pcie_caps_offset == 0) + continue; + + pci_read_config_dword(dev, pcie_caps_offset + PCI_EXP_DEVCAP, + &devcap); + max_payload = devcap & PCI_EXP_DEVCAP_PAYLOAD; + if (max_payload < smallest_max_payload) + smallest_max_payload = max_payload; + } + + /* Now, set the max_payload_size for all devices to that value. */ + new_values = (max_read_size << 12) | (smallest_max_payload << 5); + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + int pcie_caps_offset; + u16 devctl; + + pcie_caps_offset = pci_find_capability(dev, PCI_CAP_ID_EXP); + if (pcie_caps_offset == 0) + continue; + + pci_read_config_word(dev, pcie_caps_offset + PCI_EXP_DEVCTL, + &devctl); + devctl &= ~(PCI_EXP_DEVCTL_PAYLOAD | PCI_EXP_DEVCTL_READRQ); + devctl |= new_values; + pci_write_config_word(dev, pcie_caps_offset + PCI_EXP_DEVCTL, + devctl); + } +} + + +/* + * Second PCI initialization entry point, called by subsys_initcall. + * + * The controllers have been set up by the time we get here, by a call to + * tile_pci_init. + */ +static int __init pcibios_init(void) +{ + int i; + + pr_info("PCI: Probing PCI hardware\n"); + + /* + * Delay a bit in case devices aren't ready. Some devices are + * known to require at least 20ms here, but we use a more + * conservative value. + */ + mdelay(250); + + /* Scan all of the recorded PCI controllers. */ + for (i = 0; i < num_controllers; i++) { + struct pci_controller *controller = &controllers[i]; + struct pci_bus *bus; + + pr_info("PCI: initializing controller #%d\n", i); + + /* + * This comes from the generic Linux PCI driver. + * + * It reads the PCI tree for this bus into the Linux + * data structures. + * + * This is inlined in linux/pci.h and calls into + * pci_scan_bus_parented() in probe.c. + */ + bus = pci_scan_bus(0, controller->ops, controller); + controller->root_bus = bus; + controller->last_busno = bus->subordinate; + + } + + /* Do machine dependent PCI interrupt routing */ + pci_fixup_irqs(pci_common_swizzle, tile_map_irq); + + /* + * This comes from the generic Linux PCI driver. + * + * It allocates all of the resources (I/O memory, etc) + * associated with the devices read in above. + */ + + pci_assign_unassigned_resources(); + + /* Configure the max_read_size and max_payload_size values. */ + fixup_read_and_payload_sizes(); + + /* Record the I/O resources in the PCI controller structure. */ + for (i = 0; i < num_controllers; i++) { + struct pci_bus *root_bus = controllers[i].root_bus; + struct pci_bus *next_bus; + struct pci_dev *dev; + + list_for_each_entry(dev, &root_bus->devices, bus_list) { + /* Find the PCI host controller, ie. the 1st bridge. */ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && + (PCI_SLOT(dev->devfn) == 0)) { + next_bus = dev->subordinate; + controllers[i].mem_resources[0] = + *next_bus->resource[0]; + controllers[i].mem_resources[1] = + *next_bus->resource[1]; + controllers[i].mem_resources[2] = + *next_bus->resource[2]; + + break; + } + } + + } + + return 0; +} +subsys_initcall(pcibios_init); + +/* + * No bus fixups needed. + */ +void __devinit pcibios_fixup_bus(struct pci_bus *bus) +{ + /* Nothing needs to be done. */ +} + +/* + * This can be called from the generic PCI layer, but doesn't need to + * do anything. + */ +char __devinit *pcibios_setup(char *str) +{ + /* Nothing needs to be done. */ + return str; +} + +/* + * This is called from the generic Linux layer. + */ +void __init pcibios_update_irq(struct pci_dev *dev, int irq) +{ + pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); +} + +/* + * Enable memory and/or address decoding, as appropriate, for the + * device described by the 'dev' struct. + * + * This is called from the generic PCI layer, and can be called + * for bridges or endpoints. + */ +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + u16 cmd, old_cmd; + u8 header_type; + int i; + struct resource *r; + + pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type); + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + old_cmd = cmd; + if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) { + /* + * For bridges, we enable both memory and I/O decoding + * in call cases. + */ + cmd |= PCI_COMMAND_IO; + cmd |= PCI_COMMAND_MEMORY; + } else { + /* + * For endpoints, we enable memory and/or I/O decoding + * only if they have a memory resource of that type. + */ + for (i = 0; i < 6; i++) { + r = &dev->resource[i]; + if (r->flags & IORESOURCE_UNSET) { + pr_err("PCI: Device %s not available " + "because of resource collisions\n", + pci_name(dev)); + return -EINVAL; + } + if (r->flags & IORESOURCE_IO) + cmd |= PCI_COMMAND_IO; + if (r->flags & IORESOURCE_MEM) + cmd |= PCI_COMMAND_MEMORY; + } + } + + /* + * We only write the command if it changed. + */ + if (cmd != old_cmd) + pci_write_config_word(dev, PCI_COMMAND, cmd); + return 0; +} + +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) +{ + unsigned long start = pci_resource_start(dev, bar); + unsigned long len = pci_resource_len(dev, bar); + unsigned long flags = pci_resource_flags(dev, bar); + + if (!len) + return NULL; + if (max && len > max) + len = max; + + if (!(flags & IORESOURCE_MEM)) { + pr_info("PCI: Trying to map invalid resource %#lx\n", flags); + start = 0; + } + + return (void __iomem *)start; +} +EXPORT_SYMBOL(pci_iomap); + + +/**************************************************************** + * + * Tile PCI config space read/write routines + * + ****************************************************************/ + +/* + * These are the normal read and write ops + * These are expanded with macros from pci_bus_read_config_byte() etc. + * + * devfn is the combined PCI slot & function. + * + * offset is in bytes, from the start of config space for the + * specified bus & slot. + */ + +static int __devinit tile_cfg_read(struct pci_bus *bus, + unsigned int devfn, + int offset, + int size, + u32 *val) +{ + struct pci_controller *controller = bus->sysdata; + int busnum = bus->number & 0xff; + int slot = (devfn >> 3) & 0x1f; + int function = devfn & 0x7; + u32 addr; + int config_mode = 1; + + /* + * There is no bridge between the Tile and bus 0, so we + * use config0 to talk to bus 0. + * + * If we're talking to a bus other than zero then we + * must have found a bridge. + */ + if (busnum == 0) { + /* + * We fake an empty slot for (busnum == 0) && (slot > 0), + * since there is only one slot on bus 0. + */ + if (slot) { + *val = 0xFFFFFFFF; + return 0; + } + config_mode = 0; + } + + addr = busnum << 20; /* Bus in 27:20 */ + addr |= slot << 15; /* Slot (device) in 19:15 */ + addr |= function << 12; /* Function is in 14:12 */ + addr |= (offset & 0xFFF); /* byte address in 0:11 */ + + return hv_dev_pread(controller->hv_cfg_fd[config_mode], 0, + (HV_VirtAddr)(val), size, addr); +} + + +/* + * See tile_cfg_read() for relevent comments. + * Note that "val" is the value to write, not a pointer to that value. + */ +static int __devinit tile_cfg_write(struct pci_bus *bus, + unsigned int devfn, + int offset, + int size, + u32 val) +{ + struct pci_controller *controller = bus->sysdata; + int busnum = bus->number & 0xff; + int slot = (devfn >> 3) & 0x1f; + int function = devfn & 0x7; + u32 addr; + int config_mode = 1; + HV_VirtAddr valp = (HV_VirtAddr)&val; + + /* + * For bus 0 slot 0 we use config 0 accesses. + */ + if (busnum == 0) { + /* + * We fake an empty slot for (busnum == 0) && (slot > 0), + * since there is only one slot on bus 0. + */ + if (slot) + return 0; + config_mode = 0; + } + + addr = busnum << 20; /* Bus in 27:20 */ + addr |= slot << 15; /* Slot (device) in 19:15 */ + addr |= function << 12; /* Function is in 14:12 */ + addr |= (offset & 0xFFF); /* byte address in 0:11 */ + +#ifdef __BIG_ENDIAN + /* Point to the correct part of the 32-bit "val". */ + valp += 4 - size; +#endif + + return hv_dev_pwrite(controller->hv_cfg_fd[config_mode], 0, + valp, size, addr); +} + + +static struct pci_ops tile_cfg_ops = { + .read = tile_cfg_read, + .write = tile_cfg_write, +}; + + +/* + * In the following, each PCI controller's mem_resources[1] + * represents its (non-prefetchable) PCI memory resource. + * mem_resources[0] and mem_resources[2] refer to its PCI I/O and + * prefetchable PCI memory resources, respectively. + * For more details, see pci_setup_bridge() in setup-bus.c. + * By comparing the target PCI memory address against the + * end address of controller 0, we can determine the controller + * that should accept the PCI memory access. + */ +#define TILE_READ(size, type) \ +type _tile_read##size(unsigned long addr) \ +{ \ + type val; \ + int idx = 0; \ + if (addr > controllers[0].mem_resources[1].end && \ + addr > controllers[0].mem_resources[2].end) \ + idx = 1; \ + if (hv_dev_pread(controllers[idx].hv_mem_fd, 0, \ + (HV_VirtAddr)(&val), sizeof(type), addr)) \ + pr_err("PCI: read %zd bytes at 0x%lX failed\n", \ + sizeof(type), addr); \ + return val; \ +} \ +EXPORT_SYMBOL(_tile_read##size) + +TILE_READ(b, u8); +TILE_READ(w, u16); +TILE_READ(l, u32); +TILE_READ(q, u64); + +#define TILE_WRITE(size, type) \ +void _tile_write##size(type val, unsigned long addr) \ +{ \ + int idx = 0; \ + if (addr > controllers[0].mem_resources[1].end && \ + addr > controllers[0].mem_resources[2].end) \ + idx = 1; \ + if (hv_dev_pwrite(controllers[idx].hv_mem_fd, 0, \ + (HV_VirtAddr)(&val), sizeof(type), addr)) \ + pr_err("PCI: write %zd bytes at 0x%lX failed\n", \ + sizeof(type), addr); \ +} \ +EXPORT_SYMBOL(_tile_write##size) + +TILE_WRITE(b, u8); +TILE_WRITE(w, u16); +TILE_WRITE(l, u32); +TILE_WRITE(q, u64); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 8430f45daea6..e90eb53173b0 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -212,6 +212,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->sp = sp; /* override with new user stack pointer */ /* + * If CLONE_SETTLS is set, set "tp" in the new task to "r4", + * which is passed in as arg #5 to sys_clone(). + */ + if (clone_flags & CLONE_SETTLS) + childregs->tp = regs->regs[4]; + + /* * Copy the callee-saved registers from the passed pt_regs struct * into the context-switch callee-saved registers area. * This way when we start the interrupt-return sequence, the @@ -539,6 +546,7 @@ struct task_struct *__sched _switch_to(struct task_struct *prev, return __switch_to(prev, next, next_current_ksp0(next)); } +/* Note there is an implicit fifth argument if (clone_flags & CLONE_SETTLS). */ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, void __user *, parent_tidptr, void __user *, child_tidptr, struct pt_regs *, regs) diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index fb0b3cbeae14..f18573643ed1 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -840,7 +840,7 @@ static int __init topology_init(void) for_each_online_node(i) register_one_node(i); - for_each_present_cpu(i) + for (i = 0; i < smp_height * smp_width; ++i) register_cpu(&cpu_devices[i], i); return 0; diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c index 687719d4abd1..1260321155f1 100644 --- a/arch/tile/kernel/signal.c +++ b/arch/tile/kernel/signal.c @@ -16,7 +16,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/errno.h> @@ -53,7 +52,7 @@ SYSCALL_DEFINE3(sigaltstack, const stack_t __user *, uss, */ int restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *sc, long *pr0) + struct sigcontext __user *sc) { int err = 0; int i; @@ -76,17 +75,15 @@ int restore_sigcontext(struct pt_regs *regs, regs->faultnum = INT_SWINT_1_SIGRETURN; - err |= __get_user(*pr0, &sc->gregs[0]); return err; } -/* sigreturn() returns long since it restores r0 in the interrupted code. */ +/* The assembly shim for this function arranges to ignore the return value. */ SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs) { struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(regs->sp); sigset_t set; - long r0; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -99,13 +96,13 @@ SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs) recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT) goto badframe; - return r0; + return 0; badframe: force_sig(SIGSEGV, current); diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index 74d62d098edf..b949edcec200 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -18,7 +18,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> -#include <linux/smp_lock.h> #include <linux/bootmem.h> #include <linux/notifier.h> #include <linux/cpu.h> diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c index 7e764669a022..e2187d24a9b4 100644 --- a/arch/tile/kernel/sys.c +++ b/arch/tile/kernel/sys.c @@ -20,7 +20,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/file.h> diff --git a/arch/tile/lib/memchr_32.c b/arch/tile/lib/memchr_32.c index 6235283b4859..cc3d9badf030 100644 --- a/arch/tile/lib/memchr_32.c +++ b/arch/tile/lib/memchr_32.c @@ -18,12 +18,24 @@ void *memchr(const void *s, int c, size_t n) { + const uint32_t *last_word_ptr; + const uint32_t *p; + const char *last_byte_ptr; + uintptr_t s_int; + uint32_t goal, before_mask, v, bits; + char *ret; + + if (__builtin_expect(n == 0, 0)) { + /* Don't dereference any memory if the array is empty. */ + return NULL; + } + /* Get an aligned pointer. */ - const uintptr_t s_int = (uintptr_t) s; - const uint32_t *p = (const uint32_t *)(s_int & -4); + s_int = (uintptr_t) s; + p = (const uint32_t *)(s_int & -4); /* Create four copies of the byte for which we are looking. */ - const uint32_t goal = 0x01010101 * (uint8_t) c; + goal = 0x01010101 * (uint8_t) c; /* Read the first word, but munge it so that bytes before the array * will not match goal. @@ -31,23 +43,14 @@ void *memchr(const void *s, int c, size_t n) * Note that this shift count expression works because we know * shift counts are taken mod 32. */ - const uint32_t before_mask = (1 << (s_int << 3)) - 1; - uint32_t v = (*p | before_mask) ^ (goal & before_mask); + before_mask = (1 << (s_int << 3)) - 1; + v = (*p | before_mask) ^ (goal & before_mask); /* Compute the address of the last byte. */ - const char *const last_byte_ptr = (const char *)s + n - 1; + last_byte_ptr = (const char *)s + n - 1; /* Compute the address of the word containing the last byte. */ - const uint32_t *const last_word_ptr = - (const uint32_t *)((uintptr_t) last_byte_ptr & -4); - - uint32_t bits; - char *ret; - - if (__builtin_expect(n == 0, 0)) { - /* Don't dereference any memory if the array is empty. */ - return NULL; - } + last_word_ptr = (const uint32_t *)((uintptr_t) last_byte_ptr & -4); while ((bits = __insn_seqb(v, goal)) == 0) { if (__builtin_expect(p == last_word_ptr, 0)) { diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c index 485e24d62c6b..5cd1c4004eca 100644 --- a/arch/tile/lib/spinlock_32.c +++ b/arch/tile/lib/spinlock_32.c @@ -167,23 +167,30 @@ void arch_write_lock_slow(arch_rwlock_t *rwlock, u32 val) * when we compare them. */ u32 my_ticket_; + u32 iterations = 0; - /* Take out the next ticket; this will also stop would-be readers. */ - if (val & 1) - val = get_rwlock(rwlock); - rwlock->lock = __insn_addb(val, 1 << WR_NEXT_SHIFT); + /* + * Wait until there are no readers, then bump up the next + * field and capture the ticket value. + */ + for (;;) { + if (!(val & 1)) { + if ((val >> RD_COUNT_SHIFT) == 0) + break; + rwlock->lock = val; + } + delay_backoff(iterations++); + val = __insn_tns((int *)&rwlock->lock); + } - /* Extract my ticket value from the original word. */ + /* Take out the next ticket and extract my ticket value. */ + rwlock->lock = __insn_addb(val, 1 << WR_NEXT_SHIFT); my_ticket_ = val >> WR_NEXT_SHIFT; - /* - * Wait until the "current" field matches our ticket, and - * there are no remaining readers. - */ + /* Wait until the "current" field matches our ticket. */ for (;;) { u32 curr_ = val >> WR_CURR_SHIFT; - u32 readers = val >> RD_COUNT_SHIFT; - u32 delta = ((my_ticket_ - curr_) & WR_MASK) + !!readers; + u32 delta = ((my_ticket_ - curr_) & WR_MASK); if (likely(delta == 0)) break; diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index f295b4ac941d..dcebfc831cd6 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -24,7 +24,6 @@ #include <linux/mman.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/tty.h> diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index 24688b697a8d..201a582c4137 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -21,7 +21,6 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> -#include <linux/smp_lock.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/sysctl.h> diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 7f7338c90784..1664cce7b0ac 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -727,6 +727,9 @@ struct winch { static void free_winch(struct winch *winch, int free_irq_ok) { + if (free_irq_ok) + free_irq(WINCH_IRQ, winch); + list_del(&winch->list); if (winch->pid != -1) @@ -735,8 +738,6 @@ static void free_winch(struct winch *winch, int free_irq_ok) os_close_file(winch->fd); if (winch->stack != 0) free_stack(winch->stack, 0); - if (free_irq_ok) - free_irq(WINCH_IRQ, winch); kfree(winch); } diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 340268be00b5..09bd7b585726 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -5,7 +5,6 @@ #include "linux/stddef.h" #include "linux/fs.h" -#include "linux/smp_lock.h" #include "linux/ptrace.h" #include "linux/sched.h" #include "linux/slab.h" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58ecad57aad1..b6fccb07123e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,7 +21,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE - select HAVE_PERF_EVENTS if (!M386 && !M486) + select HAVE_PERF_EVENTS select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index b59ee765414e..45143bbcfe5e 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -117,6 +117,17 @@ config DEBUG_RODATA_TEST feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" +config DEBUG_SET_MODULE_RONX + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + ---help--- + This option helps catch unintended modifications to loadable + kernel module's text and read-only data. It also prevents execution + of module data. Such protection may interfere with run-time code + patching and dynamic kernel tracing - and they might also protect + against certain classes of kernel exploits. + If in doubt, say "N". + config DEBUG_NX_TEST tristate "Testcase for the NX non-executable stack feature" depends on DEBUG_KERNEL && m diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 52f85a196fa0..35af09d13dc1 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -182,7 +182,7 @@ no_longmode: hlt jmp 1b -#include "../../kernel/verify_cpu_64.S" +#include "../../kernel/verify_cpu.S" /* * Be careful here startup_64 needs to be at a predictable diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 23f315c9f215..325c05294fc4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, if (heap > 0x3fffffffffffUL) error("Destination address too large"); #else - if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff)) + if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); #endif #ifndef CONFIG_RELOCATABLE diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index cbcc8d8ea93a..7a6e68e4f748 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -10,6 +10,7 @@ * by the Free Software Foundation. */ +#include <linux/err.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 849813f398e7..5852519b2d0f 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -28,7 +28,6 @@ #include <linux/syscalls.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/smp_lock.h> #include <linux/mm.h> #include <linux/uio.h> #include <linux/poll.h> diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 76561d20ea2f..13009d1af99a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -66,6 +66,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name, extern void alternatives_smp_module_del(struct module *mod); extern void alternatives_smp_switch(int smp); extern int alternatives_text_reserved(void *start, void *end); +extern bool skip_smp_alternatives; #else static inline void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, @@ -180,8 +181,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ +struct text_poke_param { + void *addr; + const void *opcode; + size_t len; +}; + extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); +extern void text_poke_smp_batch(struct text_poke_param *params, int n); #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) #define IDEAL_NOP_SIZE_5 5 diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index a859ca461fb0..47a30ff8e517 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -145,6 +145,7 @@ #ifdef CONFIG_X86_32 # define MAX_IO_APICS 64 +# define MAX_LOCAL_APIC 256 #else # define MAX_IO_APICS 128 # define MAX_LOCAL_APIC 32768 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 5be1542fbfaf..e99d55d74df5 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -72,6 +72,9 @@ struct e820map { #define BIOS_BEGIN 0x000a0000 #define BIOS_END 0x00100000 +#define BIOS_ROM_BASE 0xffe00000 +#define BIOS_ROM_END 0xffffffff + #ifdef __KERNEL__ /* see comment in arch/x86/kernel/e820.c */ extern struct e820map e820; diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 139591a933f6..0141b234406f 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -220,8 +220,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) } /* Return an pointer with offset calculated */ -static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx, - phys_addr_t phys, pgprot_t flags) +static __always_inline unsigned long +__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { __set_fixmap(idx, phys, flags); return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1)); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 4aa2bb3b242a..ef328901c802 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -93,6 +93,17 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) int err; /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxrstorq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "m" (*fx), "0" (0)); +#else asm volatile("1: rex64/fxrstor (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -102,6 +113,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) _ASM_EXTABLE(1b, 3b) : [err] "=r" (err) : [fx] "R" (fx), "m" (*fx), "0" (0)); +#endif return err; } @@ -119,6 +131,17 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) return -EFAULT; /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxsaveq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), [fx] "=m" (*fx) + : "0" (0)); +#else asm volatile("1: rex64/fxsave (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -128,6 +151,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) _ASM_EXTABLE(1b, 3b) : [err] "=r" (err), "=m" (*fx) : [fx] "R" (fx), "0" (0)); +#endif if (unlikely(err) && __clear_user(fx, sizeof(struct i387_fxsave_struct))) err = -EFAULT; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 13b0ebaa512f..ba870bb6dd8e 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq) return ((irq == 2) ? 9 : irq); } -#ifdef CONFIG_X86_LOCAL_APIC -# define ARCH_HAS_NMI_WATCHDOG -#endif - #ifdef CONFIG_X86_32 extern void irq_ctx_init(int cpu); #else diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 5bdfca86581b..f23eb2528464 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -28,7 +28,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_registers(struct pt_regs *regs); extern void show_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp, unsigned long bp); + unsigned long *sp); extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9e6fe391094e..f702f82aa1eb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,7 +79,7 @@ #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 -#define KVM_MAX_CPUID_ENTRIES 40 +#define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 #define KVM_NR_VAR_MTRR 8 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c62c13cb9788..eb16e94ae04f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c); void mce_log_therm_throt_event(__u64 status); +/* Interrupt Handler for core thermal thresholds */ +extern int (*platform_thermal_notify)(__u64 msr_val); + #ifdef CONFIG_X86_THERMAL_VECTOR extern void mcheck_intel_therm_init(void); #else diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index ef51b501e22a..24215072d0e1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -48,6 +48,12 @@ static inline struct microcode_ops * __init init_intel_microcode(void) #ifdef CONFIG_MICROCODE_AMD extern struct microcode_ops * __init init_amd_microcode(void); + +static inline void get_ucode_data(void *to, const u8 *from, size_t n) +{ + memcpy(to, from, n); +} + #else static inline struct microcode_ops * __init init_amd_microcode(void) { diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index c82868e9f905..0c90dd9f0505 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -5,8 +5,9 @@ #include <asm/mpspec_def.h> #include <asm/x86_init.h> +#include <asm/apicdef.h> -extern int apic_version[MAX_APICS]; +extern int apic_version[]; extern int pic_mode; #ifdef CONFIG_X86_32 @@ -107,7 +108,7 @@ extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level, int active_high_low); #endif /* CONFIG_ACPI */ -#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS) +#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) struct physid_mask { unsigned long mask[PHYSID_ARRAY_SIZE]; @@ -122,31 +123,31 @@ typedef struct physid_mask physid_mask_t; test_and_set_bit(physid, (map).mask) #define physids_and(dst, src1, src2) \ - bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS) + bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) #define physids_or(dst, src1, src2) \ - bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS) + bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) #define physids_clear(map) \ - bitmap_zero((map).mask, MAX_APICS) + bitmap_zero((map).mask, MAX_LOCAL_APIC) #define physids_complement(dst, src) \ - bitmap_complement((dst).mask, (src).mask, MAX_APICS) + bitmap_complement((dst).mask, (src).mask, MAX_LOCAL_APIC) #define physids_empty(map) \ - bitmap_empty((map).mask, MAX_APICS) + bitmap_empty((map).mask, MAX_LOCAL_APIC) #define physids_equal(map1, map2) \ - bitmap_equal((map1).mask, (map2).mask, MAX_APICS) + bitmap_equal((map1).mask, (map2).mask, MAX_LOCAL_APIC) #define physids_weight(map) \ - bitmap_weight((map).mask, MAX_APICS) + bitmap_weight((map).mask, MAX_LOCAL_APIC) #define physids_shift_right(d, s, n) \ - bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS) + bitmap_shift_right((d).mask, (s).mask, n, MAX_LOCAL_APIC) #define physids_shift_left(d, s, n) \ - bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS) + bitmap_shift_left((d).mask, (s).mask, n, MAX_LOCAL_APIC) static inline unsigned long physids_coerce(physid_mask_t *map) { @@ -159,14 +160,6 @@ static inline void physids_promote(unsigned long physids, physid_mask_t *map) map->mask[0] = physids; } -/* Note: will create very large stack frames if physid_mask_t is big */ -#define physid_mask_of_physid(physid) \ - ({ \ - physid_mask_t __physid_mask = PHYSID_MASK_NONE; \ - physid_set(physid, __physid_mask); \ - __physid_mask; \ - }) - static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) { physids_clear(*map); diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h index 4a7f96d7c188..c0a955a9a087 100644 --- a/arch/x86/include/asm/mpspec_def.h +++ b/arch/x86/include/asm/mpspec_def.h @@ -15,13 +15,6 @@ #ifdef CONFIG_X86_32 # define MAX_MPC_ENTRY 1024 -# define MAX_APICS 256 -#else -# if NR_CPUS <= 255 -# define MAX_APICS 255 -# else -# define MAX_APICS 32768 -# endif #endif /* Intel MP Floating Pointer Structure */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3ea3dc487047..4d0dfa0d998e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -123,12 +123,16 @@ #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +/* Fam 15h MSRs */ +#define MSR_F15H_PERF_CTL 0xc0010200 +#define MSR_F15H_PERF_CTR 0xc0010201 + /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 #define FAM10H_MMIO_CONF_ENABLE (1<<0) #define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2 -#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffff +#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c @@ -253,6 +257,18 @@ #define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) #define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) +/* Thermal Thresholds Support */ +#define THERM_INT_THRESHOLD0_ENABLE (1 << 15) +#define THERM_SHIFT_THRESHOLD0 8 +#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0) +#define THERM_INT_THRESHOLD1_ENABLE (1 << 23) +#define THERM_SHIFT_THRESHOLD1 16 +#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1) +#define THERM_STATUS_THRESHOLD0 (1 << 6) +#define THERM_LOG_THRESHOLD0 (1 << 7) +#define THERM_STATUS_THRESHOLD1 (1 << 8) +#define THERM_LOG_THRESHOLD1 (1 << 9) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 932f0f86b4b7..c4021b953510 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -5,41 +5,15 @@ #include <asm/irq.h> #include <asm/io.h> -#ifdef ARCH_HAS_NMI_WATCHDOG - -/** - * do_nmi_callback - * - * Check to see if a callback exists and execute it. Return 1 - * if the handler exists and was handled successfully. - */ -int do_nmi_callback(struct pt_regs *regs, int cpu); +#ifdef CONFIG_X86_LOCAL_APIC extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); -extern int check_nmi_watchdog(void); -#if !defined(CONFIG_LOCKUP_DETECTOR) -extern int nmi_watchdog_enabled; -#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); extern void release_evntsel_nmi(unsigned int); -extern void setup_apic_nmi_watchdog(void *); -extern void stop_apic_nmi_watchdog(void *); -extern void disable_timer_nmi_watchdog(void); -extern void enable_timer_nmi_watchdog(void); -extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason); -extern void cpu_nmi_set_wd_enabled(void); - -extern atomic_t nmi_active; -extern unsigned int nmi_watchdog; -#define NMI_NONE 0 -#define NMI_IO_APIC 1 -#define NMI_LOCAL_APIC 2 -#define NMI_INVALID 3 - struct ctl_table; extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -47,33 +21,8 @@ extern int unknown_nmi_panic; void arch_trigger_all_cpu_backtrace(void); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace - -static inline void localise_nmi_watchdog(void) -{ - if (nmi_watchdog == NMI_IO_APIC) - nmi_watchdog = NMI_LOCAL_APIC; -} - -/* check if nmi_watchdog is active (ie was specified at boot) */ -static inline int nmi_watchdog_active(void) -{ - /* - * actually it should be: - * return (nmi_watchdog == NMI_LOCAL_APIC || - * nmi_watchdog == NMI_IO_APIC) - * but since they are power of two we could use a - * cheaper way --cvg - */ - return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC); -} #endif -void lapic_watchdog_stop(void); -int lapic_watchdog_init(unsigned nmi_hz); -int lapic_wd_event(unsigned nmi_hz); -unsigned lapic_adjust_nmi_hz(unsigned hz); -void disable_lapic_nmi_watchdog(void); -void enable_lapic_nmi_watchdog(void); void stop_nmi(void); void restart_nmi(void); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 18e3b8a8709f..7709c12431b8 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -112,7 +112,7 @@ static inline void arch_safe_halt(void) static inline void halt(void) { - PVOP_VCALL0(pv_irq_ops.safe_halt); + PVOP_VCALL0(pv_irq_ops.halt); } static inline void wbinvd(void) @@ -824,27 +824,27 @@ static __always_inline void arch_spin_unlock(struct arch_spinlock *lock) #define __PV_IS_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { func }) -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl); } -static inline void arch_local_irq_restore(unsigned long f) +static inline notrace void arch_local_irq_restore(unsigned long f) { PVOP_VCALLEE1(pv_irq_ops.restore_fl, f); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { PVOP_VCALLEE0(pv_irq_ops.irq_disable); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { PVOP_VCALLEE0(pv_irq_ops.irq_enable); } -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long f; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index ca0437c714b2..676129229630 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -65,6 +65,7 @@ extern unsigned long pci_mem_start; #define PCIBIOS_MIN_CARDBUS_IO 0x4000 +extern int pcibios_enabled; void pcibios_config_init(void); struct pci_bus *pcibios_scan_root(int bus); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 550e26b1dbb3..d9d4dae305f6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -125,7 +125,6 @@ union cpuid10_edx { #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ #ifdef CONFIG_PERF_EVENTS -extern void init_hw_perf_events(void); extern void perf_events_lapic_init(void); #define PERF_EVENT_INDEX_OFFSET 0 @@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); } #else -static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } #endif diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index a70cd216be5d..295e2ff18a6a 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -744,14 +744,6 @@ enum P4_ESCR_EMASKS { }; /* - * P4 PEBS specifics (Replay Event only) - * - * Format (bits): - * 0-6: metric from P4_PEBS_METRIC enum - * 7 : reserved - * 8 : reserved - * 9-11 : reserved - * * Note we have UOP and PEBS bits reserved for now * just in case if we will need them once */ @@ -788,5 +780,60 @@ enum P4_PEBS_METRIC { P4_PEBS_METRIC__max }; +/* + * Notes on internal configuration of ESCR+CCCR tuples + * + * Since P4 has quite the different architecture of + * performance registers in compare with "architectural" + * once and we have on 64 bits to keep configuration + * of performance event, the following trick is used. + * + * 1) Since both ESCR and CCCR registers have only low + * 32 bits valuable, we pack them into a single 64 bit + * configuration. Low 32 bits of such config correspond + * to low 32 bits of CCCR register and high 32 bits + * correspond to low 32 bits of ESCR register. + * + * 2) The meaning of every bit of such config field can + * be found in Intel SDM but it should be noted that + * we "borrow" some reserved bits for own usage and + * clean them or set to a proper value when we do + * a real write to hardware registers. + * + * 3) The format of bits of config is the following + * and should be either 0 or set to some predefined + * values: + * + * Low 32 bits + * ----------- + * 0-6: P4_PEBS_METRIC enum + * 7-11: reserved + * 12: reserved (Enable) + * 13-15: reserved (ESCR select) + * 16-17: Active Thread + * 18: Compare + * 19: Complement + * 20-23: Threshold + * 24: Edge + * 25: reserved (FORCE_OVF) + * 26: reserved (OVF_PMI_T0) + * 27: reserved (OVF_PMI_T1) + * 28-29: reserved + * 30: reserved (Cascade) + * 31: reserved (OVF) + * + * High 32 bits + * ------------ + * 0: reserved (T1_USR) + * 1: reserved (T1_OS) + * 2: reserved (T0_USR) + * 3: reserved (T0_OS) + * 4: Tag Enable + * 5-8: Tag Value + * 9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper) + * 25-30: enum P4_EVENTS + * 31: reserved (HT thread) + */ + #endif /* PERF_EVENT_P4_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7f7e577a0e39..31d84acc1512 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -11,6 +11,7 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct pvclock_vcpu_time_info *vcpu, struct timespec *ts); +void pvclock_resume(void); /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 1def60114906..6c22bf353f26 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } #endif } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 2b16a2ad23dc..52b5c7ed3608 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -7,6 +7,7 @@ #define _ASM_X86_STACKTRACE_H #include <linux/uaccess.h> +#include <linux/ptrace.h> extern int kstack_depth_to_print; @@ -46,7 +47,7 @@ struct stacktrace_ops { }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, + unsigned long *stack, const struct stacktrace_ops *ops, void *data); #ifdef CONFIG_X86_32 @@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif +#ifdef CONFIG_FRAME_POINTER +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + unsigned long bp; + + if (regs) + return regs->bp; + + if (task == current) { + /* Grab bp right from our regs */ + get_bp(bp); + return bp; + } + + /* bp is the last reg pushed by switch_to */ + return *(unsigned long *)task->thread.sp; +} +#else +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + return 0; +} +#endif + extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); + unsigned long *stack, char *log_lvl); extern void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); + unsigned long *sp, char *log_lvl); extern unsigned int code_bytes; diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 5469630b27f5..fa7b9176b76c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -10,12 +10,6 @@ unsigned long long native_sched_clock(void); extern int recalibrate_cpu_khz(void); -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -extern int timer_ack; -#else -# define timer_ack (0) -#endif - extern int no_timer_check; /* Accelerators for sched_clock() diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 42d412fd8b02..ce1d54c8a433 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -26,20 +26,22 @@ * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512, * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on. * - * We will use 31 sets, one for sending BAU messages from each of the 32 + * We will use one set for sending BAU messages from each of the * cpu's on the uvhub. * * TLB shootdown will use the first of the 8 descriptors of each set. * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set). */ +#define MAX_CPUS_PER_UVHUB 64 +#define MAX_CPUS_PER_SOCKET 32 +#define UV_ADP_SIZE 64 /* hardware-provided max. */ +#define UV_CPUS_PER_ACT_STATUS 32 /* hardware-provided max. */ #define UV_ITEMS_PER_DESCRIPTOR 8 /* the 'throttle' to prevent the hardware stay-busy bug */ #define MAX_BAU_CONCURRENT 3 -#define UV_CPUS_PER_ACT_STATUS 32 #define UV_ACT_STATUS_MASK 0x3 #define UV_ACT_STATUS_SIZE 2 -#define UV_ADP_SIZE 32 #define UV_DISTRIBUTION_SIZE 256 #define UV_SW_ACK_NPENDING 8 #define UV_NET_ENDPOINT_INTD 0x38 @@ -100,7 +102,6 @@ * number of destination side software ack resources */ #define DEST_NUM_RESOURCES 8 -#define MAX_CPUS_PER_NODE 32 /* * completion statuses for sending a TLB flush message */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index e969f691cbfd..a501741c2335 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -199,6 +199,8 @@ union uvh_apicid { #define UVH_APICID 0x002D0E00L #define UV_APIC_PNODE_SHIFT 6 +#define UV_APICID_HIBIT_MASK 0xffff0000 + /* Local Bus from cpu's perspective */ #define LOCAL_BUS_BASE 0x1c00000 #define LOCAL_BUS_SIZE (4 * 1024 * 1024) @@ -491,8 +493,10 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +extern unsigned int uv_apicid_hibits; static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode) { + apicid |= uv_apicid_hibits; return (1UL << UVH_IPI_INT_SEND_SHFT) | ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) | (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) | diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index 6d90adf4428a..20cafeac7455 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,7 +5,7 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H @@ -754,6 +754,23 @@ union uvh_lb_bau_sb_descriptor_base_u { }; /* ========================================================================= */ +/* UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK */ +/* ========================================================================= */ +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0 + +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0 +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL + +union uvh_lb_target_physical_apic_id_mask_u { + unsigned long v; + struct uvh_lb_target_physical_apic_id_mask_s { + unsigned long bit_enables : 32; /* RW */ + unsigned long rsvd_32_63 : 32; /* */ + } s; +}; + +/* ========================================================================= */ /* UVH_NODE_ID */ /* ========================================================================= */ #define UVH_NODE_ID 0x0UL diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index e8506c1f0c55..1c10c88ee4e1 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void); #define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) #endif -#ifndef machine_to_phys_mapping -#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) -#endif +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT) /* Maximum number of virtual CPUs in multi-processor guests. */ #define MAX_VIRT_CPUS 32 diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h index 42a7e004ae5c..8413688b2571 100644 --- a/arch/x86/include/asm/xen/interface_32.h +++ b/arch/x86/include/asm/xen/interface_32.h @@ -32,6 +32,11 @@ /* And the trap vector is... */ #define TRAP_INSTR "int $0x82" +#define __MACH2PHYS_VIRT_START 0xF5800000 +#define __MACH2PHYS_VIRT_END 0xF6800000 + +#define __MACH2PHYS_SHIFT 2 + /* * Virtual addresses beyond this are not modifiable by guest OSes. The * machine->physical mapping table starts at this address, read-only. diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h index 100d2662b97c..839a4811cf98 100644 --- a/arch/x86/include/asm/xen/interface_64.h +++ b/arch/x86/include/asm/xen/interface_64.h @@ -39,18 +39,7 @@ #define __HYPERVISOR_VIRT_END 0xFFFF880000000000 #define __MACH2PHYS_VIRT_START 0xFFFF800000000000 #define __MACH2PHYS_VIRT_END 0xFFFF804000000000 - -#ifndef HYPERVISOR_VIRT_START -#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) -#define HYPERVISOR_VIRT_END mk_unsigned_long(__HYPERVISOR_VIRT_END) -#endif - -#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) -#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) -#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3) -#ifndef machine_to_phys_mapping -#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) -#endif +#define __MACH2PHYS_SHIFT 3 /* * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index dd8c1414b3d5..8760cc60a21c 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/pfn.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -35,6 +36,8 @@ typedef struct xpaddr { #define MAX_DOMAIN_PAGES \ ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) +extern unsigned long *machine_to_phys_mapping; +extern unsigned int machine_to_phys_order; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); @@ -69,10 +72,8 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; -#if 0 if (unlikely((mfn >> machine_to_phys_order) != 0)) - return max_mapnr; -#endif + return ~0; pfn = 0; /* diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f60153d5de57..34244b2cd880 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -45,6 +45,7 @@ obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o obj-y += pci-iommu_table.o +obj-y += resource.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1a5b9a8e6c4f..ec881c6bfee0 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; + if (id >= (MAX_LOCAL_APIC-1)) { + printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); + return; + } + if (!enabled) { ++disabled_cpus; return; @@ -898,13 +903,13 @@ static int __init acpi_parse_madt_lapic_entries(void) register_lapic_address(acpi_lapic_addr); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, - acpi_parse_sapic, MAX_APICS); + acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_APICS); + acpi_parse_x2apic, MAX_LOCAL_APIC); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_APICS); + acpi_parse_lapic, MAX_LOCAL_APIC); } if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5079f24c955a..123608531c8f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) mutex_unlock(&smp_alt); } +bool skip_smp_alternatives; void alternatives_smp_switch(int smp) { struct smp_alt_module *mod; @@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp) printk("lockdep: fixing up alternatives.\n"); #endif - if (noreplace_smp || smp_alt_once) + if (noreplace_smp || smp_alt_once || skip_smp_alternatives) return; BUG_ON(!smp && (num_online_cpus() > 1)); @@ -591,17 +592,21 @@ static atomic_t stop_machine_first; static int wrote_text; struct text_poke_params { - void *addr; - const void *opcode; - size_t len; + struct text_poke_param *params; + int nparams; }; static int __kprobes stop_machine_text_poke(void *data) { struct text_poke_params *tpp = data; + struct text_poke_param *p; + int i; if (atomic_dec_and_test(&stop_machine_first)) { - text_poke(tpp->addr, tpp->opcode, tpp->len); + for (i = 0; i < tpp->nparams; i++) { + p = &tpp->params[i]; + text_poke(p->addr, p->opcode, p->len); + } smp_wmb(); /* Make sure other cpus see that this has run */ wrote_text = 1; } else { @@ -610,8 +615,12 @@ static int __kprobes stop_machine_text_poke(void *data) smp_mb(); /* Load wrote_text before following execution */ } - flush_icache_range((unsigned long)tpp->addr, - (unsigned long)tpp->addr + tpp->len); + for (i = 0; i < tpp->nparams; i++) { + p = &tpp->params[i]; + flush_icache_range((unsigned long)p->addr, + (unsigned long)p->addr + p->len); + } + return 0; } @@ -631,10 +640,13 @@ static int __kprobes stop_machine_text_poke(void *data) void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) { struct text_poke_params tpp; + struct text_poke_param p; - tpp.addr = addr; - tpp.opcode = opcode; - tpp.len = len; + p.addr = addr; + p.opcode = opcode; + p.len = len; + tpp.params = &p; + tpp.nparams = 1; atomic_set(&stop_machine_first, 1); wrote_text = 0; /* Use __stop_machine() because the caller already got online_cpus. */ @@ -642,6 +654,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) return addr; } +/** + * text_poke_smp_batch - Update instructions on a live kernel on SMP + * @params: an array of text_poke parameters + * @n: the number of elements in params. + * + * Modify multi-byte instruction by using stop_machine() on SMP. Since the + * stop_machine() is heavy task, it is better to aggregate text_poke requests + * and do it once if possible. + * + * Note: Must be called under get_online_cpus() and text_mutex. + */ +void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +{ + struct text_poke_params tpp = {.params = params, .nparams = n}; + + atomic_set(&stop_machine_first, 1); + wrote_text = 0; + stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); +} + #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 910f20b457c4..3966b564ea47 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -3,10 +3,7 @@ # obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o -ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) -obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o -endif -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o +obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c0f6426cd337..ce65d449b750 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -31,7 +31,6 @@ #include <linux/init.h> #include <linux/cpu.h> #include <linux/dmi.h> -#include <linux/nmi.h> #include <linux/smp.h> #include <linux/mm.h> @@ -432,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask) reserved = reserve_eilvt_offset(offset, new); if (reserved != new) { - pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but " - "vector 0x%x was already reserved by another core, " - "APIC%lX=0x%x\n", - smp_processor_id(), new, reserved, reg, old); + pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for " + "vector 0x%x, but the register is already in use for " + "vector 0x%x on another cpu\n", + smp_processor_id(), reg, offset, new, reserved); return -EINVAL; } if (!eilvt_entry_is_changeable(old, new)) { - pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but " - "register already in use, APIC%lX=0x%x\n", - smp_processor_id(), new, reg, old); + pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for " + "vector 0x%x, but the register is already in use for " + "vector 0x%x on this cpu\n", + smp_processor_id(), reg, offset, new, old); return -EBUSY; } @@ -799,11 +799,7 @@ void __init setup_boot_APIC_clock(void) * PIT/HPET going. Otherwise register lapic as a dummy * device. */ - if (nmi_watchdog != NMI_IO_APIC) - lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; - else - pr_warning("APIC timer registered as dummy," - " due to nmi_watchdog=%d!\n", nmi_watchdog); + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; /* Setup the lapic or request the broadcast */ setup_APIC_timer(); @@ -1384,8 +1380,15 @@ void __cpuinit end_local_APIC_setup(void) } #endif - setup_apic_nmi_watchdog(NULL); apic_pm_activate(); + + /* + * Now that local APIC setup is completed for BP, configure the fault + * handling for interrupt remapping. + */ + if (!smp_processor_id() && intr_remapping_enabled) + enable_drhd_fault_handling(); + } #ifdef CONFIG_X86_X2APIC @@ -1694,7 +1697,7 @@ void __init register_lapic_address(unsigned long address) * This initializes the IO-APIC and APIC hardware if this is * a UP kernel. */ -int apic_version[MAX_APICS]; +int apic_version[MAX_LOCAL_APIC]; int __init APIC_init_uniprocessor(void) { @@ -1759,17 +1762,10 @@ int __init APIC_init_uniprocessor(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } -#else - localise_nmi_watchdog(); #endif x86_init.timers.setup_percpu_clockev(); -#ifdef CONFIG_X86_64 - check_nmi_watchdog(); -#endif - return 0; } diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index cefd6942f0e9..72ec29e1ae06 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -17,19 +17,31 @@ #include <linux/nmi.h> #include <linux/module.h> -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; - +#ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(void) { return (u64)(cpu_khz) * 1000 * 60; } +#endif + +#ifdef arch_trigger_all_cpu_backtrace +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +static unsigned long backtrace_flag; -#ifdef ARCH_HAS_NMI_WATCHDOG void arch_trigger_all_cpu_backtrace(void) { int i; + if (test_and_set_bit(0, &backtrace_flag)) + /* + * If there is already a trigger_all_cpu_backtrace() in progress + * (backtrace_flag == 1), don't output double cpu dump infos. + */ + return; + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); printk(KERN_INFO "sending NMI to all CPUs:\n"); @@ -41,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void) break; mdelay(1); } + + clear_bit(0, &backtrace_flag); + smp_mb__after_clear_bit(); } static int __kprobes @@ -49,7 +64,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, { struct die_args *args = __args; struct pt_regs *regs; - int cpu = smp_processor_id(); + int cpu; switch (cmd) { case DIE_NMI: @@ -61,6 +76,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, } regs = args->regs; + cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -90,18 +106,3 @@ static int __init register_trigger_all_cpu_backtrace(void) } early_initcall(register_trigger_all_cpu_backtrace); #endif - -/* STUB calls to mimic old nmi_watchdog behaviour */ -#if defined(CONFIG_X86_LOCAL_APIC) -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); -void acpi_nmi_enable(void) { return; } -void acpi_nmi_disable(void) { return; } -#endif -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); -int unknown_nmi_panic; -void cpu_nmi_set_wd_enabled(void) { return; } -void stop_apic_nmi_watchdog(void *unused) { return; } -void setup_apic_nmi_watchdog(void *unused) { return; } -int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index bb61a552d8c6..52735a710c30 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -54,7 +54,6 @@ #include <asm/dma.h> #include <asm/timer.h> #include <asm/i8259.h> -#include <asm/nmi.h> #include <asm/msidef.h> #include <asm/hypertransport.h> #include <asm/setup.h> @@ -2458,13 +2457,12 @@ static void ack_apic_level(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; int i, do_unmask_irq = 0, irq = data->irq; - struct irq_desc *desc = irq_to_desc(irq); unsigned long v; irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ /* If we are moving the irq we need to mask it */ - if (unlikely(desc->status & IRQ_MOVE_PENDING)) { + if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) { do_unmask_irq = 1; mask_ioapic(cfg); } @@ -2671,24 +2669,6 @@ static void lapic_register_intr(int irq) "edge"); } -static void __init setup_nmi(void) -{ - /* - * Dirty trick to enable the NMI watchdog ... - * We put the 8259A master into AEOI mode and - * unmask on all local APICs LVT0 as NMI. - * - * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') - * is from Maciej W. Rozycki - so we do not have to EOI from - * the NMI handler or the timer interrupt. - */ - apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); - - enable_NMI_through_LVT0(); - - apic_printk(APIC_VERBOSE, " done.\n"); -} - /* * This looks a bit hackish but it's about the only one way of sending * a few INTA cycles to 8259As and any associated glue logic. ICR does @@ -2794,15 +2774,6 @@ static inline void __init check_timer(void) */ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); legacy_pic->init(1); -#ifdef CONFIG_X86_32 - { - unsigned int ver; - - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); - } -#endif pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2850,10 +2821,6 @@ static inline void __init check_timer(void) unmask_ioapic(cfg); } if (timer_irq_works()) { - if (nmi_watchdog == NMI_IO_APIC) { - setup_nmi(); - legacy_pic->unmask(0); - } if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); goto out; @@ -2879,11 +2846,6 @@ static inline void __init check_timer(void) if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); timer_through_8259 = 1; - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - setup_nmi(); - legacy_pic->unmask(0); - } goto out; } /* @@ -2895,15 +2857,6 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); } - if (nmi_watchdog == NMI_IO_APIC) { - apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work " - "through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = NMI_NONE; - } -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...\n"); @@ -3441,6 +3394,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, msg.data |= MSI_DATA_VECTOR(cfg->vector); msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; msg.address_lo |= MSI_ADDR_DEST_ID(dest); + msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); dmar_msi_write(irq, &msg); @@ -4133,7 +4087,8 @@ void __init pre_init_apic_IRQ0(void) printk(KERN_INFO "Early APIC setup for system timer0\n"); #ifndef CONFIG_SMP - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); + physid_set_mask_of_physid(boot_cpu_physical_apicid, + &phys_cpu_present_map); #endif /* Make sure the irq descriptor is set up */ cfg = alloc_irq_and_cfg_at(0, 0); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c deleted file mode 100644 index c90041ccb742..000000000000 --- a/arch/x86/kernel/apic/nmi.c +++ /dev/null @@ -1,567 +0,0 @@ -/* - * NMI watchdog support on APIC systems - * - * Started by Ingo Molnar <mingo@redhat.com> - * - * Fixes: - * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog. - * Mikael Pettersson : Power Management for local APIC NMI watchdog. - * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. Disable/enable API. - */ - -#include <asm/apic.h> - -#include <linux/nmi.h> -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/sysdev.h> -#include <linux/sysctl.h> -#include <linux/percpu.h> -#include <linux/kprobes.h> -#include <linux/cpumask.h> -#include <linux/kernel_stat.h> -#include <linux/kdebug.h> -#include <linux/smp.h> - -#include <asm/i8259.h> -#include <asm/io_apic.h> -#include <asm/proto.h> -#include <asm/timer.h> - -#include <asm/mce.h> - -#include <asm/mach_traps.h> - -int unknown_nmi_panic; -int nmi_watchdog_enabled; - -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; - -/* nmi_active: - * >0: the lapic NMI watchdog is active, but can be disabled - * <0: the lapic NMI watchdog has not been set up, and cannot - * be enabled - * 0: the lapic NMI watchdog is disabled, but can be enabled - */ -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); - -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); - -static int panic_on_timeout; - -static unsigned int nmi_hz = HZ; -static DEFINE_PER_CPU(short, wd_enabled); -static int endflag __initdata; - -static inline unsigned int get_nmi_count(int cpu) -{ - return per_cpu(irq_stat, cpu).__nmi_count; -} - -static inline int mce_in_progress(void) -{ -#if defined(CONFIG_X86_MCE) - return atomic_read(&mce_entry) > 0; -#endif - return 0; -} - -/* - * Take the local apic timer and PIT/HPET into account. We don't - * know which one is active, when we have highres/dyntick on - */ -static inline unsigned int get_timer_irqs(int cpu) -{ - return per_cpu(irq_stat, cpu).apic_timer_irqs + - per_cpu(irq_stat, cpu).irq0_irqs; -} - -#ifdef CONFIG_SMP -/* - * The performance counters used by NMI_LOCAL_APIC don't trigger when - * the CPU is idle. To make sure the NMI watchdog really ticks on all - * CPUs during the test make them busy. - */ -static __init void nmi_cpu_busy(void *data) -{ - local_irq_enable_in_hardirq(); - /* - * Intentionally don't use cpu_relax here. This is - * to make sure that the performance counter really ticks, - * even if there is a simulator or similar that catches the - * pause instruction. On a real HT machine this is fine because - * all other CPUs are busy with "useless" delay loops and don't - * care if they get somewhat less cycles. - */ - while (endflag == 0) - mb(); -} -#endif - -static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count) -{ - printk(KERN_CONT "\n"); - - printk(KERN_WARNING - "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n", - cpu, prev_nmi_count[cpu], get_nmi_count(cpu)); - - printk(KERN_WARNING - "Please report this to bugzilla.kernel.org,\n"); - printk(KERN_WARNING - "and attach the output of the 'dmesg' command.\n"); - - per_cpu(wd_enabled, cpu) = 0; - atomic_dec(&nmi_active); -} - -static void __acpi_nmi_disable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); -} - -int __init check_nmi_watchdog(void) -{ - unsigned int *prev_nmi_count; - int cpu; - - if (!nmi_watchdog_active() || !atomic_read(&nmi_active)) - return 0; - - prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL); - if (!prev_nmi_count) - goto error; - - printk(KERN_INFO "Testing NMI watchdog ... "); - -#ifdef CONFIG_SMP - if (nmi_watchdog == NMI_LOCAL_APIC) - smp_call_function(nmi_cpu_busy, (void *)&endflag, 0); -#endif - - for_each_possible_cpu(cpu) - prev_nmi_count[cpu] = get_nmi_count(cpu); - local_irq_enable(); - mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */ - - for_each_online_cpu(cpu) { - if (!per_cpu(wd_enabled, cpu)) - continue; - if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) - report_broken_nmi(cpu, prev_nmi_count); - } - endflag = 1; - if (!atomic_read(&nmi_active)) { - kfree(prev_nmi_count); - atomic_set(&nmi_active, -1); - goto error; - } - printk("OK.\n"); - - /* - * now that we know it works we can reduce NMI frequency to - * something more reasonable; makes a difference in some configs - */ - if (nmi_watchdog == NMI_LOCAL_APIC) - nmi_hz = lapic_adjust_nmi_hz(1); - - kfree(prev_nmi_count); - return 0; -error: - if (nmi_watchdog == NMI_IO_APIC) { - if (!timer_through_8259) - legacy_pic->mask(0); - on_each_cpu(__acpi_nmi_disable, NULL, 1); - } - -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - return -1; -} - -static int __init setup_nmi_watchdog(char *str) -{ - unsigned int nmi; - - if (!strncmp(str, "panic", 5)) { - panic_on_timeout = 1; - str = strchr(str, ','); - if (!str) - return 1; - ++str; - } - - if (!strncmp(str, "lapic", 5)) - nmi_watchdog = NMI_LOCAL_APIC; - else if (!strncmp(str, "ioapic", 6)) - nmi_watchdog = NMI_IO_APIC; - else { - get_option(&str, &nmi); - if (nmi >= NMI_INVALID) - return 0; - nmi_watchdog = nmi; - } - - return 1; -} -__setup("nmi_watchdog=", setup_nmi_watchdog); - -/* - * Suspend/resume support - */ -#ifdef CONFIG_PM - -static int nmi_pm_active; /* nmi_active before suspend */ - -static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) -{ - /* only CPU0 goes here, other CPUs should be offline */ - nmi_pm_active = atomic_read(&nmi_active); - stop_apic_nmi_watchdog(NULL); - BUG_ON(atomic_read(&nmi_active) != 0); - return 0; -} - -static int lapic_nmi_resume(struct sys_device *dev) -{ - /* only CPU0 goes here, other CPUs should be offline */ - if (nmi_pm_active > 0) { - setup_apic_nmi_watchdog(NULL); - touch_nmi_watchdog(); - } - return 0; -} - -static struct sysdev_class nmi_sysclass = { - .name = "lapic_nmi", - .resume = lapic_nmi_resume, - .suspend = lapic_nmi_suspend, -}; - -static struct sys_device device_lapic_nmi = { - .id = 0, - .cls = &nmi_sysclass, -}; - -static int __init init_lapic_nmi_sysfs(void) -{ - int error; - - /* - * should really be a BUG_ON but b/c this is an - * init call, it just doesn't work. -dcz - */ - if (nmi_watchdog != NMI_LOCAL_APIC) - return 0; - - if (atomic_read(&nmi_active) < 0) - return 0; - - error = sysdev_class_register(&nmi_sysclass); - if (!error) - error = sysdev_register(&device_lapic_nmi); - return error; -} - -/* must come after the local APIC's device_initcall() */ -late_initcall(init_lapic_nmi_sysfs); - -#endif /* CONFIG_PM */ - -static void __acpi_nmi_enable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI); -} - -/* - * Enable timer based NMIs on all CPUs: - */ -void acpi_nmi_enable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_enable, NULL, 1); -} - -/* - * Disable timer based NMIs on all CPUs: - */ -void acpi_nmi_disable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_disable, NULL, 1); -} - -/* - * This function is called as soon the LAPIC NMI watchdog driver has everything - * in place and it's ready to check if the NMIs belong to the NMI watchdog - */ -void cpu_nmi_set_wd_enabled(void) -{ - __get_cpu_var(wd_enabled) = 1; -} - -void setup_apic_nmi_watchdog(void *unused) -{ - if (__get_cpu_var(wd_enabled)) - return; - - /* cheap hack to support suspend/resume */ - /* if cpu0 is not active neither should the other cpus */ - if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0) - return; - - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - if (lapic_watchdog_init(nmi_hz) < 0) { - __get_cpu_var(wd_enabled) = 0; - return; - } - /* FALL THROUGH */ - case NMI_IO_APIC: - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - } -} - -void stop_apic_nmi_watchdog(void *unused) -{ - /* only support LOCAL and IO APICs for now */ - if (!nmi_watchdog_active()) - return; - if (__get_cpu_var(wd_enabled) == 0) - return; - if (nmi_watchdog == NMI_LOCAL_APIC) - lapic_watchdog_stop(); - else - __acpi_nmi_disable(NULL); - __get_cpu_var(wd_enabled) = 0; - atomic_dec(&nmi_active); -} - -/* - * the best way to detect whether a CPU has a 'hard lockup' problem - * is to check it's local APIC timer IRQ counts. If they are not - * changing then that CPU has some problem. - * - * as these watchdog NMI IRQs are generated on every CPU, we only - * have to check the current processor. - * - * since NMIs don't listen to _any_ locks, we have to be extremely - * careful not to rely on unsafe variables. The printk might lock - * up though, so we have to break up any console locks first ... - * [when there will be more tty-related locks, break them up here too!] - */ - -static DEFINE_PER_CPU(unsigned, last_irq_sum); -static DEFINE_PER_CPU(long, alert_counter); -static DEFINE_PER_CPU(int, nmi_touch); - -void touch_nmi_watchdog(void) -{ - if (nmi_watchdog_active()) { - unsigned cpu; - - /* - * Tell other CPUs to reset their alert counters. We cannot - * do it ourselves because the alert count increase is not - * atomic. - */ - for_each_present_cpu(cpu) { - if (per_cpu(nmi_touch, cpu) != 1) - per_cpu(nmi_touch, cpu) = 1; - } - } - - /* - * Tickle the softlockup detector too: - */ - touch_softlockup_watchdog(); -} -EXPORT_SYMBOL(touch_nmi_watchdog); - -notrace __kprobes int -nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) -{ - /* - * Since current_thread_info()-> is always on the stack, and we - * always switch the stack NMI-atomically, it's safe to use - * smp_processor_id(). - */ - unsigned int sum; - int touched = 0; - int cpu = smp_processor_id(); - int rc = 0; - - sum = get_timer_irqs(cpu); - - if (__get_cpu_var(nmi_touch)) { - __get_cpu_var(nmi_touch) = 0; - touched = 1; - } - - /* We can be called before check_nmi_watchdog, hence NULL check. */ - if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */ - - raw_spin_lock(&lock); - printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); - show_regs(regs); - dump_stack(); - raw_spin_unlock(&lock); - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - - rc = 1; - } - - /* Could check oops_in_progress here too, but it's safer not to */ - if (mce_in_progress()) - touched = 1; - - /* if the none of the timers isn't firing, this cpu isn't doing much */ - if (!touched && __get_cpu_var(last_irq_sum) == sum) { - /* - * Ayiee, looks like this CPU is stuck ... - * wait a few IRQs (5 seconds) before doing the oops ... - */ - __this_cpu_inc(alert_counter); - if (__this_cpu_read(alert_counter) == 5 * nmi_hz) - /* - * die_nmi will return ONLY if NOTIFY_STOP happens.. - */ - die_nmi("BUG: NMI Watchdog detected LOCKUP", - regs, panic_on_timeout); - } else { - __get_cpu_var(last_irq_sum) = sum; - __this_cpu_write(alert_counter, 0); - } - - /* see if the nmi watchdog went off */ - if (!__get_cpu_var(wd_enabled)) - return rc; - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - rc |= lapic_wd_event(nmi_hz); - break; - case NMI_IO_APIC: - /* - * don't know how to accurately check for this. - * just assume it was a watchdog timer interrupt - * This matches the old behaviour. - */ - rc = 1; - break; - } - return rc; -} - -#ifdef CONFIG_SYSCTL - -static void enable_ioapic_nmi_watchdog_single(void *unused) -{ - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - __acpi_nmi_enable(NULL); -} - -static void enable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1); - touch_nmi_watchdog(); -} - -static void disable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); -} - -static int __init setup_unknown_nmi_panic(char *str) -{ - unknown_nmi_panic = 1; - return 1; -} -__setup("unknown_nmi_panic", setup_unknown_nmi_panic); - -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) -{ - unsigned char reason = get_nmi_reason(); - char buf[64]; - - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(buf, regs, 1); /* Always panic here */ - return 0; -} - -/* - * proc handler for /proc/sys/kernel/nmi - */ -int proc_nmi_enabled(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - int old_state; - - nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; - old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, buffer, length, ppos); - if (!!old_state == !!nmi_watchdog_enabled) - return 0; - - if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) { - printk(KERN_WARNING - "NMI watchdog is permanently disabled\n"); - return -EIO; - } - - if (nmi_watchdog == NMI_LOCAL_APIC) { - if (nmi_watchdog_enabled) - enable_lapic_nmi_watchdog(); - else - disable_lapic_nmi_watchdog(); - } else if (nmi_watchdog == NMI_IO_APIC) { - if (nmi_watchdog_enabled) - enable_ioapic_nmi_watchdog(); - else - disable_ioapic_nmi_watchdog(); - } else { - printk(KERN_WARNING - "NMI watchdog doesn't know what hardware to touch\n"); - return -EIO; - } - return 0; -} - -#endif /* CONFIG_SYSCTL */ - -int do_nmi_callback(struct pt_regs *regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - -void arch_trigger_all_cpu_backtrace(void) -{ - int i; - - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); - - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(to_cpumask(backtrace_mask))) - break; - mdelay(1); - } -} diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index f9e4e6a54073..d8c4a6feb286 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void) /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; } - - /* - * Now that apic routing model is selected, configure the - * fault handling for intr remapping. - */ - if (intr_remapping_enabled) - enable_drhd_fault_handling(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 194539aea175..2a3f2a7db243 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -44,8 +44,20 @@ static u64 gru_start_paddr, gru_end_paddr; static union uvh_apicid uvh_apicid; int uv_min_hub_revision_id; EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); +unsigned int uv_apicid_hibits; +EXPORT_SYMBOL_GPL(uv_apicid_hibits); static DEFINE_SPINLOCK(uv_nmi_lock); +static unsigned long __init uv_early_read_mmr(unsigned long addr) +{ + unsigned long val, *mmr; + + mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr)); + val = *mmr; + early_iounmap(mmr, sizeof(*mmr)); + return val; +} + static inline bool is_GRU_range(u64 start, u64 end) { return start >= gru_start_paddr && end <= gru_end_paddr; @@ -56,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end) return is_ISA_range(start, end) || is_GRU_range(start, end); } -static int early_get_nodeid(void) +static int __init early_get_pnodeid(void) { union uvh_node_id_u node_id; - unsigned long *mmr; - - mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr)); - node_id.v = *mmr; - early_iounmap(mmr, sizeof(*mmr)); + union uvh_rh_gam_config_mmr_u m_n_config; + int pnode; /* Currently, all blades have same revision number */ + node_id.v = uv_early_read_mmr(UVH_NODE_ID); + m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR); uv_min_hub_revision_id = node_id.s.revision; - return node_id.s.node_id; + pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); + return pnode; } static void __init early_get_apic_pnode_shift(void) { - unsigned long *mmr; - - mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr)); - uvh_apicid.v = *mmr; - early_iounmap(mmr, sizeof(*mmr)); + uvh_apicid.v = uv_early_read_mmr(UVH_APICID); if (!uvh_apicid.v) /* * Old bios, use default value @@ -85,12 +93,25 @@ static void __init early_get_apic_pnode_shift(void) uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT; } +/* + * Add an extra bit as dictated by bios to the destination apicid of + * interrupts potentially passing through the UV HUB. This prevents + * a deadlock between interrupts and IO port operations. + */ +static void __init uv_set_apicid_hibit(void) +{ + union uvh_lb_target_physical_apic_id_mask_u apicid_mask; + + apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK); + uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK; +} + static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int nodeid; + int pnodeid; if (!strcmp(oem_id, "SGI")) { - nodeid = early_get_nodeid(); + pnodeid = early_get_pnodeid(); early_get_apic_pnode_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; x86_platform.nmi_init = uv_nmi_init; @@ -100,8 +121,9 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) uv_system_type = UV_X2APIC; else if (!strcmp(oem_table_id, "UVH")) { __get_cpu_var(x2apic_extra_bits) = - nodeid << (uvh_apicid.s.pnode_shift - 1); + pnodeid << uvh_apicid.s.pnode_shift; uv_system_type = UV_NON_UNIQUE_APIC; + uv_set_apicid_hibit(); return 1; } } @@ -155,6 +177,7 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri int pnode; pnode = uv_apicid_to_pnode(phys_apicid); + phys_apicid |= uv_apicid_hibits; val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | @@ -236,7 +259,7 @@ static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) int cpu = cpumask_first(cpumask); if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); + return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; else return BAD_APICID; } @@ -255,7 +278,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu); + return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -661,27 +684,32 @@ void uv_nmi_init(void) void __init uv_system_init(void) { union uvh_rh_gam_config_mmr_u m_n_config; + union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; union uvh_node_id_u node_id; unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; - int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; + int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io; int gnode_extra, max_pnode = 0; unsigned long mmr_base, present, paddr; - unsigned short pnode_mask; + unsigned short pnode_mask, pnode_io_mask; map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; + mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); + n_io = mmioh.s.n_io; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; pnode_mask = (1 << n_val) - 1; + pnode_io_mask = (1 << n_io) - 1; + node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n", - n_val, m_val, gnode_upper, gnode_extra); + printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n", + n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask); printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base); @@ -714,7 +742,7 @@ void __init uv_system_init(void) for (j = 0; j < 64; j++) { if (!test_bit(j, &present)) continue; - pnode = (i * 64 + j); + pnode = (i * 64 + j) & pnode_mask; uv_blade_info[blade].pnode = pnode; uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; @@ -735,6 +763,7 @@ void __init uv_system_init(void) /* * apic_pnode_shift must be set before calling uv_apicid_to_pnode(); */ + uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift; pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); @@ -751,7 +780,6 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; uv_cpu_hub_info(cpu)->pnode = pnode; - uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1; uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra; @@ -775,7 +803,7 @@ void __init uv_system_init(void) map_gru_high(max_pnode); map_mmr_high(max_pnode); - map_mmioh_high(max_pnode); + map_mmioh_high(max_pnode & pnode_io_mask); uv_cpu_init(); uv_scir_register_cpu_notifier(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4b68bda30938..1d59834396bd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -894,7 +894,6 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - init_hw_perf_events(); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 80c482382d5c..5bf2fac52aca 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -31,8 +31,6 @@ #include <asm/mce.h> #include <asm/msr.h> -#define PFX "mce_threshold: " -#define VERSION "version 1.1.1" #define NR_BANKS 6 #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF @@ -59,12 +57,6 @@ struct threshold_block { struct list_head miscj; }; -/* defaults used early on boot */ -static struct threshold_block threshold_defaults = { - .interrupt_enable = 0, - .threshold_limit = THRESHOLD_MAX, -}; - struct threshold_bank { struct kobject *kobj; struct threshold_block *blocks; @@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void); struct thresh_restart { struct threshold_block *b; int reset; + int set_lvt_off; + int lvt_off; u16 old_limit; }; +static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +{ + int msr = (hi & MASK_LVTOFF_HI) >> 20; + + if (apic < 0) { + pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, + b->bank, b->block, b->address, hi, lo); + return 0; + } + + if (apic != msr) { + pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", + b->cpu, apic, b->bank, b->block, b->address, hi, lo); + return 0; + } + + return 1; +}; + /* must be called with correct cpu affinity */ /* Called via smp_call_function_single() */ static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; - u32 mci_misc_hi, mci_misc_lo; + u32 hi, lo; - rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi); + rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX)) + if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) tr->reset = 1; /* limit cannot be lower than err count */ if (tr->reset) { /* reset err count and overflow bit */ - mci_misc_hi = - (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | + hi = + (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | (THRESHOLD_MAX - tr->b->threshold_limit); } else if (tr->old_limit) { /* change limit w/o reset */ - int new_count = (mci_misc_hi & THRESHOLD_MAX) + + int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit); - mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) | + hi = (hi & ~MASK_ERR_COUNT_HI) | (new_count & THRESHOLD_MAX); } + if (tr->set_lvt_off) { + if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) { + /* set new lvt offset */ + hi &= ~MASK_LVTOFF_HI; + hi |= tr->lvt_off << 20; + } + } + tr->b->interrupt_enable ? - (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) : - (mci_misc_hi &= ~MASK_INT_TYPE_HI); + (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) : + (hi &= ~MASK_INT_TYPE_HI); - mci_misc_hi |= MASK_COUNT_EN_HI; - wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi); + hi |= MASK_COUNT_EN_HI; + wrmsr(tr->b->address, lo, hi); +} + +static void mce_threshold_block_init(struct threshold_block *b, int offset) +{ + struct thresh_restart tr = { + .b = b, + .set_lvt_off = 1, + .lvt_off = offset, + }; + + b->threshold_limit = THRESHOLD_MAX; + threshold_restart_bank(&tr); +}; + +static int setup_APIC_mce(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; } /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { + struct threshold_block b; unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - struct thresh_restart tr; - int lvt_off = -1; - u8 offset; + int offset = -1; for (bank = 0; bank < NR_BANKS; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { @@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (shared_bank[bank] && c->cpu_core_id) break; #endif - offset = (high & MASK_LVTOFF_HI) >> 20; - if (lvt_off < 0) { - if (setup_APIC_eilvt(offset, - THRESHOLD_APIC_VECTOR, - APIC_EILVT_MSG_FIX, 0)) { - pr_err(FW_BUG "cpu %d, failed to " - "setup threshold interrupt " - "for bank %d, block %d " - "(MSR%08X=0x%x%08x)", - smp_processor_id(), bank, block, - address, high, low); - continue; - } - lvt_off = offset; - } else if (lvt_off != offset) { - pr_err(FW_BUG "cpu %d, invalid threshold " - "interrupt offset %d for bank %d," - "block %d (MSR%08X=0x%x%08x)", - smp_processor_id(), lvt_off, bank, - block, address, high, low); - continue; - } - - high &= ~MASK_LVTOFF_HI; - high |= lvt_off << 20; - wrmsr(address, low, high); + offset = setup_APIC_mce(offset, + (high & MASK_LVTOFF_HI) >> 20); - threshold_defaults.address = address; - tr.b = &threshold_defaults; - tr.reset = 0; - tr.old_limit = 0; - threshold_restart_bank(&tr); + memset(&b, 0, sizeof(b)); + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = address; + mce_threshold_block_init(&b, offset); mce_threshold_vector = amd_threshold_interrupt; } } @@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) b->interrupt_enable = !!new; + memset(&tr, 0, sizeof(tr)); tr.b = b; - tr.reset = 0; - tr.old_limit = 0; smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); @@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) if (new < 1) new = 1; + memset(&tr, 0, sizeof(tr)); tr.old_limit = b->threshold_limit; b->threshold_limit = new; tr.b = b; - tr.reset = 0; smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); @@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu) continue; err = threshold_create_bank(cpu, bank); if (err) - goto out; + return err; } -out: + return err; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 4b683267eca5..e12246ff5aa6 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -53,8 +53,13 @@ struct thermal_state { struct _thermal_state core_power_limit; struct _thermal_state package_throttle; struct _thermal_state package_power_limit; + struct _thermal_state core_thresh0; + struct _thermal_state core_thresh1; }; +/* Callback to handle core threshold interrupts */ +int (*platform_thermal_notify)(__u64 msr_val); + static DEFINE_PER_CPU(struct thermal_state, thermal_state); static atomic_t therm_throt_en = ATOMIC_INIT(0); @@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level) return 0; } +static int thresh_event_valid(int event) +{ + struct _thermal_state *state; + unsigned int this_cpu = smp_processor_id(); + struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); + u64 now = get_jiffies_64(); + + state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1; + + if (time_before64(now, state->next_check)) + return 0; + + state->next_check = now + CHECK_INTERVAL; + return 1; +} + #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev, @@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device); #define PACKAGE_THROTTLED ((__u64)2 << 62) #define PACKAGE_POWER_LIMIT ((__u64)3 << 62) +static void notify_thresholds(__u64 msr_val) +{ + /* check whether the interrupt handler is defined; + * otherwise simply return + */ + if (!platform_thermal_notify) + return; + + /* lower threshold reached */ + if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0)) + platform_thermal_notify(msr_val); + /* higher threshold reached */ + if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1)) + platform_thermal_notify(msr_val); +} + /* Thermal transition interrupt handler */ static void intel_thermal_interrupt(void) { @@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void) rdmsrl(MSR_IA32_THERM_STATUS, msr_val); + /* Check for violation of core thermal thresholds*/ + notify_thresholds(msr_val); + if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, CORE_LEVEL) != 0) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ed6310183efb..0a360d146596 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void) { int i; - if (nmi_watchdog == NMI_LOCAL_APIC) - disable_lapic_nmi_watchdog(); - for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) goto perfctr_fail; @@ -355,9 +352,6 @@ perfctr_fail: for (i--; i >= 0; i--) release_perfctr_nmi(x86_pmu.perfctr + i); - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); - return false; } @@ -369,9 +363,6 @@ static void release_pmc_hardware(void) release_perfctr_nmi(x86_pmu.perfctr + i); release_evntsel_nmi(x86_pmu.eventsel + i); } - - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); } #else @@ -381,6 +372,58 @@ static void release_pmc_hardware(void) {} #endif +static bool check_hw_exists(void) +{ + u64 val, val_new = 0; + int i, reg, ret = 0; + + /* + * Check to see if the BIOS enabled any of the counters, if so + * complain and bail. + */ + for (i = 0; i < x86_pmu.num_counters; i++) { + reg = x86_pmu.eventsel + i; + ret = rdmsrl_safe(reg, &val); + if (ret) + goto msr_fail; + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) + goto bios_fail; + } + + if (x86_pmu.num_counters_fixed) { + reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; + ret = rdmsrl_safe(reg, &val); + if (ret) + goto msr_fail; + for (i = 0; i < x86_pmu.num_counters_fixed; i++) { + if (val & (0x03 << i*4)) + goto bios_fail; + } + } + + /* + * Now write a value and read it back to see if it matches, + * this is needed to detect certain hardware emulators (qemu/kvm) + * that don't trap on the MSR access and always return 0s. + */ + val = 0xabcdUL; + ret = checking_wrmsrl(x86_pmu.perfctr, val); + ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new); + if (ret || val != val_new) + goto msr_fail; + + return true; + +bios_fail: + printk(KERN_CONT "Broken BIOS detected, using software events only.\n"); + printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val); + return false; + +msr_fail: + printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); + return false; +} + static void reserve_ds_buffers(void); static void release_ds_buffers(void); @@ -437,7 +480,7 @@ static int x86_setup_perfctr(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; u64 config; - if (!hwc->sample_period) { + if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); @@ -1348,7 +1391,7 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { struct event_constraint *c; int err; @@ -1363,15 +1406,19 @@ void __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return; + return 0; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); - return; + return 0; } pmu_check_apic(); + /* sanity check that the hardware exists or is emulated */ + if (!check_hw_exists()) + return 0; + pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.quirks) @@ -1418,9 +1465,12 @@ void __init init_hw_perf_events(void) pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(x86_pmu_notifier); + + return 0; } +early_initcall(init_hw_perf_events); static inline void x86_pmu_read(struct perf_event *event) { @@ -1666,7 +1716,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, &backtrace_ops, entry); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index e421b8cd6944..67e2202a6039 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,7 +1,5 @@ #ifdef CONFIG_CPU_SUP_AMD -static DEFINE_RAW_SPINLOCK(amd_nb_lock); - static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -275,7 +273,7 @@ done: return &emptyconstraint; } -static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) +static struct amd_nb *amd_alloc_nb(int cpu) { struct amd_nb *nb; int i; @@ -285,7 +283,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) if (!nb) return NULL; - nb->nb_id = nb_id; + nb->nb_id = -1; /* * initialize all possible NB constraints @@ -306,7 +304,7 @@ static int amd_pmu_cpu_prepare(int cpu) if (boot_cpu_data.x86_max_cores < 2) return NOTIFY_OK; - cpuc->amd_nb = amd_alloc_nb(cpu, -1); + cpuc->amd_nb = amd_alloc_nb(cpu); if (!cpuc->amd_nb) return NOTIFY_BAD; @@ -325,8 +323,6 @@ static void amd_pmu_cpu_starting(int cpu) nb_id = amd_get_nb_id(cpu); WARN_ON_ONCE(nb_id == BAD_APICID); - raw_spin_lock(&amd_nb_lock); - for_each_online_cpu(i) { nb = per_cpu(cpu_hw_events, i).amd_nb; if (WARN_ON_ONCE(!nb)) @@ -341,8 +337,6 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - - raw_spin_unlock(&amd_nb_lock); } static void amd_pmu_cpu_dead(int cpu) @@ -354,8 +348,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw = &per_cpu(cpu_hw_events, cpu); - raw_spin_lock(&amd_nb_lock); - if (cpuhw->amd_nb) { struct amd_nb *nb = cpuhw->amd_nb; @@ -364,8 +356,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } - - raw_spin_unlock(&amd_nb_lock); } static __initconst const struct x86_pmu amd_pmu = { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index c8f5c088cad1..24e390e40f2e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (event->attr.precise_ip && + (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.ANY_P + * (0x00c0), which is a PEBS capable event, to get the same + * count. + * + * INST_RETIRED.ANY_P counts the number of cycles that retires + * CNTMASK instructions. By setting CNTMASK to a value (16) + * larger than the maximum number of instructions that can be + * retired per cycle (4) and then inverting the condition, we + * count all cycles that retire 16 or less instructions, which + * is every cycle. + * + * Thereby we gain a PEBS capable cycle counter. + */ + u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */ + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d9f4ff8fcd69..d5a236615501 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -16,32 +16,12 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/smp.h> -#include <linux/nmi.h> +#include <asm/nmi.h> #include <linux/kprobes.h> #include <asm/apic.h> #include <asm/perf_event.h> -struct nmi_watchdog_ctlblk { - unsigned int cccr_msr; - unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ - unsigned int evntsel_msr; /* the MSR to select the events to handle */ -}; - -/* Interface defining a CPU specific perfctr watchdog */ -struct wd_ops { - int (*reserve)(void); - void (*unreserve)(void); - int (*setup)(unsigned nmi_hz); - void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz); - void (*stop)(void); - unsigned perfctr; - unsigned evntsel; - u64 checkbit; -}; - -static const struct wd_ops *wd_ops; - /* * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's * offset from MSR_P4_BSU_ESCR0. @@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops; static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS); static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS); -static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); - /* converts an msr to an appropriate reservation bit */ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) { @@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr) clear_bit(counter, evntsel_nmi_owner); } EXPORT_SYMBOL(release_evntsel_nmi); - -void disable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - if (atomic_read(&nmi_active) <= 0) - return; - - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); - - if (wd_ops) - wd_ops->unreserve(); - - BUG_ON(atomic_read(&nmi_active) != 0); -} - -void enable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - /* are we already enabled */ - if (atomic_read(&nmi_active) != 0) - return; - - /* are we lapic aware */ - if (!wd_ops) - return; - if (!wd_ops->reserve()) { - printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n"); - return; - } - - on_each_cpu(setup_apic_nmi_watchdog, NULL, 1); - touch_nmi_watchdog(); -} - -/* - * Activate the NMI watchdog via the local APIC. - */ - -static unsigned int adjust_for_32bit_ctr(unsigned int hz) -{ - u64 counter_val; - unsigned int retval = hz; - - /* - * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter - * are writable, with higher bits sign extending from bit 31. - * So, we can only program the counter with 31 bit values and - * 32nd bit should be 1, for 33.. to be 1. - * Find the appropriate nmi_hz - */ - counter_val = (u64)cpu_khz * 1000; - do_div(counter_val, retval); - if (counter_val > 0x7fffffffULL) { - u64 count = (u64)cpu_khz * 1000; - do_div(count, 0x7fffffffUL); - retval = count + 1; - } - return retval; -} - -static void write_watchdog_counter(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsrl(perfctr_msr, 0 - count); -} - -static void write_watchdog_counter32(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsr(perfctr_msr, (u32)(-count), 0); -} - -/* - * AMD K7/K8/Family10h/Family11h support. - * AMD keeps this interface nicely stable so there is not much variety - */ -#define K7_EVNTSEL_ENABLE (1 << 22) -#define K7_EVNTSEL_INT (1 << 20) -#define K7_EVNTSEL_OS (1 << 17) -#define K7_EVNTSEL_USR (1 << 16) -#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 -#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING - -static int setup_k7_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = K7_EVNTSEL_INT - | K7_EVNTSEL_OS - | K7_EVNTSEL_USR - | K7_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= K7_EVNTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void single_msr_stop_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int single_msr_reserve(void) -{ - if (!reserve_perfctr_nmi(wd_ops->perfctr)) - return 0; - - if (!reserve_evntsel_nmi(wd_ops->evntsel)) { - release_perfctr_nmi(wd_ops->perfctr); - return 0; - } - return 1; -} - -static void single_msr_unreserve(void) -{ - release_evntsel_nmi(wd_ops->evntsel); - release_perfctr_nmi(wd_ops->perfctr); -} - -static void __kprobes -single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops k7_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_k7_watchdog, - .rearm = single_msr_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_K7_PERFCTR0, - .evntsel = MSR_K7_EVNTSEL0, - .checkbit = 1ULL << 47, -}; - -/* - * Intel Model 6 (PPro+,P2,P3,P-M,Core1) - */ -#define P6_EVNTSEL0_ENABLE (1 << 22) -#define P6_EVNTSEL_INT (1 << 20) -#define P6_EVNTSEL_OS (1 << 17) -#define P6_EVNTSEL_USR (1 << 16) -#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 -#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED - -static int setup_p6_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - /* KVM doesn't implement this MSR */ - if (wrmsr_safe(perfctr_msr, 0, 0) < 0) - return 0; - - evntsel = P6_EVNTSEL_INT - | P6_EVNTSEL_OS - | P6_EVNTSEL_USR - | P6_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= P6_EVNTSEL0_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* - * P6 based Pentium M need to re-unmask - * the apic vector but it doesn't hurt - * other P6 variant. - * ArchPerfom/Core Duo also needs this - */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - - /* P6/ARCH_PERFMON has 32 bit counter write */ - write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p6_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_p6_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_P6_PERFCTR0, - .evntsel = MSR_P6_EVNTSEL0, - .checkbit = 1ULL << 39, -}; - -/* - * Intel P4 performance counters. - * By far the most complicated of all. - */ -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7) -#define P4_ESCR_EVENT_SELECT(N) ((N) << 25) -#define P4_ESCR_OS (1 << 3) -#define P4_ESCR_USR (1 << 2) -#define P4_CCCR_OVF_PMI0 (1 << 26) -#define P4_CCCR_OVF_PMI1 (1 << 27) -#define P4_CCCR_THRESHOLD(N) ((N) << 20) -#define P4_CCCR_COMPLEMENT (1 << 19) -#define P4_CCCR_COMPARE (1 << 18) -#define P4_CCCR_REQUIRED (3 << 16) -#define P4_CCCR_ESCR_SELECT(N) ((N) << 13) -#define P4_CCCR_ENABLE (1 << 12) -#define P4_CCCR_OVF (1 << 31) - -#define P4_CONTROLS 18 -static unsigned int p4_controls[18] = { - MSR_P4_BPU_CCCR0, - MSR_P4_BPU_CCCR1, - MSR_P4_BPU_CCCR2, - MSR_P4_BPU_CCCR3, - MSR_P4_MS_CCCR0, - MSR_P4_MS_CCCR1, - MSR_P4_MS_CCCR2, - MSR_P4_MS_CCCR3, - MSR_P4_FLAME_CCCR0, - MSR_P4_FLAME_CCCR1, - MSR_P4_FLAME_CCCR2, - MSR_P4_FLAME_CCCR3, - MSR_P4_IQ_CCCR0, - MSR_P4_IQ_CCCR1, - MSR_P4_IQ_CCCR2, - MSR_P4_IQ_CCCR3, - MSR_P4_IQ_CCCR4, - MSR_P4_IQ_CCCR5, -}; -/* - * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - * CRU_ESCR0 (with any non-null event selector) through a complemented - * max threshold. [IA32-Vol3, Section 14.9.9] - */ -static int setup_p4_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr, cccr_msr; - unsigned int evntsel, cccr_val; - unsigned int misc_enable, dummy; - unsigned int ht_num; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); - if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) - return 0; - -#ifdef CONFIG_SMP - /* detect which hyperthread we are on */ - if (smp_num_siblings == 2) { - unsigned int ebx, apicid; - - ebx = cpuid_ebx(1); - apicid = (ebx >> 24) & 0xff; - ht_num = apicid & 1; - } else -#endif - ht_num = 0; - - /* - * performance counters are shared resources - * assign each hyperthread its own set - * (re-use the ESCR0 register, seems safe - * and keeps the cccr_val the same) - */ - if (!ht_num) { - /* logical cpu 0 */ - perfctr_msr = MSR_P4_IQ_PERFCTR0; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR0; - cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); - - /* - * If we're on the kdump kernel or other situation, we may - * still have other performance counter registers set to - * interrupt and they'll keep interrupting forever because - * of the P4_CCCR_OVF quirk. So we need to ACK all the - * pending interrupts and disable all the registers here, - * before reenabling the NMI delivery. Refer to p4_rearm() - * about the P4_CCCR_OVF quirk. - */ - if (reset_devices) { - unsigned int low, high; - int i; - - for (i = 0; i < P4_CONTROLS; i++) { - rdmsr(p4_controls[i], low, high); - low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF); - wrmsr(p4_controls[i], low, high); - } - } - } else { - /* logical cpu 1 */ - perfctr_msr = MSR_P4_IQ_PERFCTR1; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR1; - - /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */ - if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4) - cccr_val = P4_CCCR_OVF_PMI0; - else - cccr_val = P4_CCCR_OVF_PMI1; - cccr_val |= P4_CCCR_ESCR_SELECT(4); - } - - evntsel = P4_ESCR_EVENT_SELECT(0x3F) - | P4_ESCR_OS - | P4_ESCR_USR; - - cccr_val |= P4_CCCR_THRESHOLD(15) - | P4_CCCR_COMPLEMENT - | P4_CCCR_COMPARE - | P4_CCCR_REQUIRED; - - wrmsr(evntsel_msr, evntsel, 0); - wrmsr(cccr_msr, cccr_val, 0); - write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = cccr_msr; - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - cccr_val |= P4_CCCR_ENABLE; - wrmsr(cccr_msr, cccr_val, 0); - return 1; -} - -static void stop_p4_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - wrmsr(wd->cccr_msr, 0, 0); - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int p4_reserve(void) -{ - if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0)) - return 0; -#ifdef CONFIG_SMP - if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1)) - goto fail1; -#endif - if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0)) - goto fail2; - /* RED-PEN why is ESCR1 not reserved here? */ - return 1; - fail2: -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); - fail1: -#endif - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); - return 0; -} - -static void p4_unreserve(void) -{ -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); -#endif - release_evntsel_nmi(MSR_P4_CRU_ESCR0); - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); -} - -static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - unsigned dummy; - /* - * P4 quirks: - * - An overflown perfctr will assert its interrupt - * until the OVF flag in its CCCR is cleared. - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. - */ - rdmsrl(wd->cccr_msr, dummy); - dummy &= ~P4_CCCR_OVF; - wrmsrl(wd->cccr_msr, dummy); - apic_write(APIC_LVTPC, APIC_DM_NMI); - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p4_wd_ops = { - .reserve = p4_reserve, - .unreserve = p4_unreserve, - .setup = setup_p4_watchdog, - .rearm = p4_rearm, - .stop = stop_p4_watchdog, - /* RED-PEN this is wrong for the other sibling */ - .perfctr = MSR_P4_BPU_PERFCTR0, - .evntsel = MSR_P4_BSU_ESCR0, - .checkbit = 1ULL << 39, -}; - -/* - * Watchdog using the Intel architected PerfMon. - * Used for Core2 and hopefully all future Intel CPUs. - */ -#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL -#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK - -static struct wd_ops intel_arch_wd_ops; - -static int setup_intel_arch_watchdog(unsigned nmi_hz) -{ - unsigned int ebx; - union cpuid10_eax eax; - unsigned int unused; - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - /* - * Check whether the Architectural PerfMon supports - * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebx indicates event present. - */ - cpuid(10, &(eax.full), &ebx, &unused, &unused); - if ((eax.split.mask_length < - (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || - (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - return 0; - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = ARCH_PERFMON_EVENTSEL_INT - | ARCH_PERFMON_EVENTSEL_OS - | ARCH_PERFMON_EVENTSEL_USR - | ARCH_PERFMON_NMI_EVENT_SEL - | ARCH_PERFMON_NMI_EVENT_UMASK; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); - return 1; -} - -static struct wd_ops intel_arch_wd_ops __read_mostly = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_intel_arch_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_ARCH_PERFMON_PERFCTR1, - .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, -}; - -static void probe_nmi_watchdog(void) -{ - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (boot_cpu_data.x86 == 6 || - (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15)) - wd_ops = &k7_wd_ops; - return; - case X86_VENDOR_INTEL: - /* Work around where perfctr1 doesn't have a working enable - * bit as described in the following errata: - * AE49 Core Duo and Intel Core Solo 65 nm - * AN49 Intel Pentium Dual-Core - * AF49 Dual-Core Intel Xeon Processor LV - */ - if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) || - ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 && - boot_cpu_data.x86_mask == 4))) { - intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0; - intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0; - } - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - wd_ops = &intel_arch_wd_ops; - break; - } - switch (boot_cpu_data.x86) { - case 6: - if (boot_cpu_data.x86_model > 13) - return; - - wd_ops = &p6_wd_ops; - break; - case 15: - wd_ops = &p4_wd_ops; - break; - default: - return; - } - break; - } -} - -/* Interface to nmi.c */ - -int lapic_watchdog_init(unsigned nmi_hz) -{ - if (!wd_ops) { - probe_nmi_watchdog(); - if (!wd_ops) { - printk(KERN_INFO "NMI watchdog: CPU not supported\n"); - return -1; - } - - if (!wd_ops->reserve()) { - printk(KERN_ERR - "NMI watchdog: cannot reserve perfctrs\n"); - return -1; - } - } - - if (!(wd_ops->setup(nmi_hz))) { - printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n", - raw_smp_processor_id()); - return -1; - } - - return 0; -} - -void lapic_watchdog_stop(void) -{ - if (wd_ops) - wd_ops->stop(); -} - -unsigned lapic_adjust_nmi_hz(unsigned hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - if (wd->perfctr_msr == MSR_P6_PERFCTR0 || - wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) - hz = adjust_for_32bit_ctr(hz); - return hz; -} - -int __kprobes lapic_wd_event(unsigned nmi_hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - u64 ctr; - - rdmsrl(wd->perfctr_msr, ctr); - if (ctr & wd_ops->checkbit) /* perfctr still running? */ - return 0; - - wd_ops->rearm(wd, nmi_hz); - return 1; -} diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 1b7b31ab7d86..212a6a42527c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -33,7 +33,6 @@ #include <linux/init.h> #include <linux/poll.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/device.h> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6e8752c1bd52..8474c998cbd4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = { void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) + unsigned long *stack, char *log_lvl) { printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); + dump_trace(task, regs, stack, &print_trace_ops, log_lvl); } void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) + unsigned long *stack) { - show_trace_log_lvl(task, regs, stack, bp, ""); + show_trace_log_lvl(task, regs, stack, ""); } void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, 0, ""); + show_stack_log_lvl(task, NULL, sp, ""); } /* @@ -210,7 +210,7 @@ void dump_stack(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); + show_trace(NULL, NULL, &stack); } EXPORT_SYMBOL(dump_stack); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 1bc7f75a5bda..74cc1eda384b 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -17,11 +17,12 @@ #include <asm/stacktrace.h> -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { int graph = 0; + unsigned long bp; if (!task) task = current; @@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, stack = (unsigned long *)task->thread.sp; } -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - + bp = stack_frame(task, regs); for (;;) { struct thread_info *context; @@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *stack; int i; @@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } @@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs) u8 *ip; printk(KERN_EMERG "Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, - 0, KERN_EMERG); + show_stack_log_lvl(NULL, regs, ®s->sp, KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6a340485249a..64101335de19 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); @@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned used = 0; struct thread_info *tinfo; int graph = 0; + unsigned long bp; if (!task) task = current; @@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, stack = (unsigned long *)task->thread.sp; } -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - + bp = stack_frame(task, regs); /* * Print function call entries in all stacks, starting at the * current stack address. If the stacks consist of nested @@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *irq_stack_end; unsigned long *irq_stack; @@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, preempt_enable(); printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } void show_registers(struct pt_regs *regs) @@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs) printk(KERN_EMERG "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - regs->bp, KERN_EMERG); + KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 59e175e89599..591e60104278 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -395,7 +395,7 @@ sysenter_past_esp: * A tiny bit of offset fixup is necessary - 4*4 means the 4 words * pushed above; +8 corresponds to copy_thread's esp0 setting. */ - pushl_cfi (TI_sysenter_return-THREAD_SIZE_asm+8+4*4)(%esp) + pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp) CFI_REL_OFFSET eip, 0 pushl_cfi %eax diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index fe2690d71c0c..e3ba417e8697 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64) .endm /* save partial stack frame */ + .pushsection .kprobes.text, "ax" ENTRY(save_args) XCPT_FRAME cld @@ -334,6 +335,7 @@ ENTRY(save_args) ret CFI_ENDPROC END(save_args) + .popsection ENTRY(save_rest) PARTIAL_FRAME 1 REST_SKIP+8 diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3afb33f14d2d..298448656b60 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/init.h> #include <linux/list.h> +#include <linux/module.h> #include <trace/syscall.h> @@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code); int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); + set_all_modules_text_rw(); modifying_code = 1; return 0; } @@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void) int ftrace_arch_code_modify_post_process(void) { modifying_code = 0; + set_all_modules_text_ro(); set_kernel_text_ro(); return 0; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index bcece91dd311..9f54b209c378 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -60,16 +60,18 @@ #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif +/* Number of possible pages in the lowmem region */ +LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) + /* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = \ - PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT +MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT /* * Worst-case size of the kernel mapping we need to make: - * the worst-case size of the kernel itself, plus the extra we need - * to map for the linear map. + * a relocatable kernel can live anywhere in lowmem, so we need to be able + * to map all of lowmem. */ -KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT +KERNEL_PAGES = LOWMEM_PAGES INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm RESERVE_BRK(pagetables, INIT_MAP_SIZE) @@ -137,39 +139,6 @@ ENTRY(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_PARAVIRT - /* This is can only trip for a broken bootloader... */ - cmpw $0x207, pa(boot_params + BP_version) - jb default_entry - - /* Paravirt-compatible boot parameters. Look to see what architecture - we're booting under. */ - movl pa(boot_params + BP_hardware_subarch), %eax - cmpl $num_subarch_entries, %eax - jae bad_subarch - - movl pa(subarch_entries)(,%eax,4), %eax - subl $__PAGE_OFFSET, %eax - jmp *%eax - -bad_subarch: -WEAK(lguest_entry) -WEAK(xen_entry) - /* Unknown implementation; there's really - nothing we can do at this point. */ - ud2a - - __INITDATA - -subarch_entries: - .long default_entry /* normal x86/PC */ - .long lguest_entry /* lguest hypervisor */ - .long xen_entry /* Xen hypervisor */ - .long default_entry /* Moorestown MID */ -num_subarch_entries = (. - subarch_entries) / 4 -.previous -#endif /* CONFIG_PARAVIRT */ - /* * Initialize page tables. This creates a PDE and a set of page * tables, which are located immediately beyond __brk_base. The variable @@ -179,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4 * * Note that the stack is not yet set up! */ -default_entry: #ifdef CONFIG_X86_PAE /* @@ -259,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20); movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax movl %eax,pa(initial_page_table+0xffc) #endif - jmp 3f + +#ifdef CONFIG_PARAVIRT + /* This is can only trip for a broken bootloader... */ + cmpw $0x207, pa(boot_params + BP_version) + jb default_entry + + /* Paravirt-compatible boot parameters. Look to see what architecture + we're booting under. */ + movl pa(boot_params + BP_hardware_subarch), %eax + cmpl $num_subarch_entries, %eax + jae bad_subarch + + movl pa(subarch_entries)(,%eax,4), %eax + subl $__PAGE_OFFSET, %eax + jmp *%eax + +bad_subarch: +WEAK(lguest_entry) +WEAK(xen_entry) + /* Unknown implementation; there's really + nothing we can do at this point. */ + ud2a + + __INITDATA + +subarch_entries: + .long default_entry /* normal x86/PC */ + .long lguest_entry /* lguest hypervisor */ + .long xen_entry /* Xen hypervisor */ + .long default_entry /* Moorestown MID */ +num_subarch_entries = (. - subarch_entries) / 4 +.previous +#else + jmp default_entry +#endif /* CONFIG_PARAVIRT */ + /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but @@ -280,7 +283,7 @@ ENTRY(startup_32_smp) movl %eax,%fs movl %eax,%gs #endif /* CONFIG_SMP */ -3: +default_entry: /* * New page tables may be in 4Mbyte page mode and may @@ -314,6 +317,10 @@ ENTRY(startup_32_smp) subl $0x80000001, %eax cmpl $(0x8000ffff-0x80000001), %eax ja 6f + + /* Clear bogus XD_DISABLE bits */ + call verify_cpu + mov $0x80000001, %eax cpuid /* Execute Disable bit supported? */ @@ -609,6 +616,8 @@ ignore_int: #endif iret +#include "verify_cpu.S" + __REFDATA .align 4 ENTRY(initial_code) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ae03cab4352e..4ff5968f12d2 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -27,6 +27,9 @@ #define HPET_DEV_FSB_CAP 0x1000 #define HPET_DEV_PERI_CAP 0x2000 +#define HPET_MIN_CYCLES 128 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt) /* @@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void) /* Calculate the min / max delta */ hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &hpet_clockevent); - /* 5 usec minimum reprogramming delta. */ - hpet_clockevent.min_delta_ns = 5000; + /* Setup minimum reprogramming delta. */ + hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, + &hpet_clockevent); /* * Start hpet with the boot cpu mask and make it @@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta, * the wraparound into account) nor a simple count down event * mode. Further the write to the comparator register is * delayed internally up to two HPET clock cycles in certain - * chipsets (ATI, ICH9,10). We worked around that by reading - * back the compare register, but that required another - * workaround for ICH9,10 chips where the first readout after - * write can return the old stale value. We already have a - * minimum delta of 5us enforced, but a NMI or SMI hitting + * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even + * longer delays. We worked around that by reading back the + * compare register, but that required another workaround for + * ICH9,10 chips where the first readout after write can + * return the old stale value. We already had a minimum + * programming delta of 5us enforced, but a NMI or SMI hitting * between the counter readout and the comparator write can * move us behind that point easily. Now instead of reading * the compare register back several times, we make the ETIME * decision based on the following: Return ETIME if the - * counter value after the write is less than 8 HPET cycles + * counter value after the write is less than HPET_MIN_CYCLES * away from the event or if the counter is already ahead of - * the event. + * the event. The minimum programming delta for the generic + * clockevents code is set to 1.5 * HPET_MIN_CYCLES. */ res = (s32)(cnt - hpet_readl(HPET_COUNTER)); - return res < 8 ? -ETIME : 0; + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index ff15c9dcc25d..42c594254507 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) dr6_p = (unsigned long *)ERR_PTR(args->err); dr6 = *dr6_p; + /* If it's a single step, TRAP bits are random */ + if (dr6 & DR_STEP) + return NOTIFY_DONE; + /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index ec592caac4b4..cd21b654dec6 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void) if (!breakinfo[i].enabled) continue; bp = *per_cpu_ptr(breakinfo[i].pev, cpu); - if (bp->attr.disabled == 1) + if (!bp->attr.disabled) { + arch_uninstall_hw_breakpoint(bp); + bp->attr.disabled = 1; continue; + } if (dbg_is_early) early_dr7 &= ~encode_dr7(i, breakinfo[i].len, breakinfo[i].type); - else - arch_uninstall_hw_breakpoint(bp); - bp->attr.disabled = 1; + else if (hw_break_release_slot(i)) + printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n", + breakinfo[i].addr); + breakinfo[i].enabled = 0; } } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 1cbd54c0df99..5940282bd2f9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1184,6 +1184,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); @@ -1401,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -/* Replace a breakpoint (int3) with a relative jump. */ -int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) { - unsigned char jmp_code[RELATIVEJUMP_SIZE]; s32 rel = (s32)((long)op->optinsn.insn - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); @@ -1412,16 +1422,79 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, RELATIVE_ADDR_SIZE); - jmp_code[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&jmp_code[1]) = rel; + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } /* * text_poke_smp doesn't support NMI/MCE code modifying. * However, since kprobes itself also doesn't support NMI/MCE * code probing, it's not a problem. */ - text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE); - return 0; + text_poke_smp_batch(jump_poke_params, c); +} + +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); } /* Replace a relative jump with a breakpoint (int3). */ @@ -1453,11 +1526,35 @@ static int __kprobes setup_detour_execution(struct kprobe *p, } return 0; } + +static int __kprobes init_poke_params(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} +#else /* !CONFIG_OPTPROBES */ +static int __kprobes init_poke_params(void) +{ + return 0; +} #endif int __init arch_init_kprobes(void) { - return 0; + return init_poke_params(); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index ce0cb4721c9a..0fe6d1a66c38 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu) return 0; } -static int get_ucode_data(void *to, const u8 *from, size_t n) -{ - memcpy(to, from, n); - return 0; -} - static void * get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) { @@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; void *mc; - if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR)) - return NULL; + get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR); if (section_hdr[0] != UCODE_UCODE_TYPE) { pr_err("error: invalid type field in container file section header\n"); @@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) return NULL; } - mc = vmalloc(UCODE_MAX_SIZE); - if (mc) { - memset(mc, 0, UCODE_MAX_SIZE); - if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, - total_size)) { - vfree(mc); - mc = NULL; - } else - *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR; - } + mc = vzalloc(UCODE_MAX_SIZE); + if (!mc) + return NULL; + + get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size); + *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR; + return mc; } @@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf) unsigned int *buf_pos = (unsigned int *)container_hdr; unsigned long size; - if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE)) - return 0; + get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE); size = buf_pos[2]; @@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf) } buf += UCODE_CONTAINER_HEADER_SIZE; - if (get_ucode_data(equiv_cpu_table, buf, size)) { - vfree(equiv_cpu_table); - return 0; - } + get_ucode_data(equiv_cpu_table, buf, size); return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */ } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index dcb65cc0a053..1a1b606d3e92 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -364,8 +364,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, /* For performance reasons, reuse mc area when possible */ if (!mc || mc_size > curr_mc_size) { - if (mc) - vfree(mc); + vfree(mc); mc = vmalloc(mc_size); if (!mc) break; @@ -374,13 +373,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, if (get_ucode_data(mc, ucode_ptr, mc_size) || microcode_sanity_check(mc) < 0) { - vfree(mc); break; } if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) { - if (new_mc) - vfree(new_mc); + vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; mc = NULL; /* trigger new vmalloc */ @@ -390,12 +387,10 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, leftover -= mc_size; } - if (mc) - vfree(mc); + vfree(mc); if (leftover) { - if (new_mc) - vfree(new_mc); + vfree(new_mc); state = UCODE_ERROR; goto out; } @@ -405,8 +400,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, goto out; } - if (uci->mc) - vfree(uci->mc); + vfree(uci->mc); uci->mc = (struct microcode_intel *)new_mc; pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index 6da143c2a6b8..ac861b8348e2 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -25,7 +25,6 @@ struct pci_hostbridge_probe { }; static u64 __cpuinitdata fam10h_pci_mmconf_base; -static int __cpuinitdata fam10h_pci_mmconf_base_status; static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, @@ -44,10 +43,12 @@ static int __cpuinit cmp_range(const void *x1, const void *x2) return start1 - start2; } -/*[47:0] */ -/* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */ +#define MMCONF_UNIT (1ULL << FAM10H_MMIO_CONF_BASE_SHIFT) +#define MMCONF_MASK (~(MMCONF_UNIT - 1)) +#define MMCONF_SIZE (MMCONF_UNIT << 8) +/* need to avoid (0xfd<<32), (0xfe<<32), and (0xff<<32), ht used space */ #define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32) -#define BASE_VALID(b) ((b != (0xfdULL << 32)) && (b != (0xfeULL << 32))) +#define BASE_VALID(b) ((b) + MMCONF_SIZE <= (0xfdULL<<32) || (b) >= (1ULL<<40)) static void __cpuinit get_fam10h_pci_mmconf_base(void) { int i; @@ -64,12 +65,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) struct range range[8]; /* only try to get setting from BSP */ - /* -1 or 1 */ - if (fam10h_pci_mmconf_base_status) + if (fam10h_pci_mmconf_base) return; if (!early_pci_allowed()) - goto fail; + return; found = 0; for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { @@ -91,7 +91,7 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) } if (!found) - goto fail; + return; /* SYS_CFG */ address = MSR_K8_SYSCFG; @@ -99,16 +99,16 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) /* TOP_MEM2 is not enabled? */ if (!(val & (1<<21))) { - tom2 = 0; + tom2 = 1ULL << 32; } else { /* TOP_MEM2 */ address = MSR_K8_TOP_MEM2; rdmsrl(address, val); - tom2 = val & (0xffffULL<<32); + tom2 = max(val & 0xffffff800000ULL, 1ULL << 32); } if (base <= tom2) - base = tom2 + (1ULL<<32); + base = (tom2 + 2 * MMCONF_UNIT - 1) & MMCONF_MASK; /* * need to check if the range is in the high mmio range that is @@ -123,11 +123,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) if (!(reg & 3)) continue; - start = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + start = (u64)(reg & 0xffffff00) << 8; /* 39:16 on 31:8*/ reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3)); - end = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + end = ((u64)(reg & 0xffffff00) << 8) | 0xffff; /* 39:16 on 31:8*/ - if (!end) + if (end < tom2) continue; range[hi_mmio_num].start = start; @@ -143,32 +143,27 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) if (range[hi_mmio_num - 1].end < base) goto out; - if (range[0].start > base) + if (range[0].start > base + MMCONF_SIZE) goto out; /* need to find one window */ - base = range[0].start - (1ULL << 32); + base = (range[0].start & MMCONF_MASK) - MMCONF_UNIT; if ((base > tom2) && BASE_VALID(base)) goto out; - base = range[hi_mmio_num - 1].end + (1ULL << 32); - if ((base > tom2) && BASE_VALID(base)) + base = (range[hi_mmio_num - 1].end + MMCONF_UNIT) & MMCONF_MASK; + if (BASE_VALID(base)) goto out; /* need to find window between ranges */ - if (hi_mmio_num > 1) - for (i = 0; i < hi_mmio_num - 1; i++) { - if (range[i + 1].start > (range[i].end + (1ULL << 32))) { - base = range[i].end + (1ULL << 32); - if ((base > tom2) && BASE_VALID(base)) - goto out; - } + for (i = 1; i < hi_mmio_num; i++) { + base = (range[i - 1].end + MMCONF_UNIT) & MMCONF_MASK; + val = range[i].start & MMCONF_MASK; + if (val >= base + MMCONF_SIZE && BASE_VALID(base)) + goto out; } - -fail: - fam10h_pci_mmconf_base_status = -1; return; + out: fam10h_pci_mmconf_base = base; - fam10h_pci_mmconf_base_status = 1; } void __cpuinit fam10h_check_enable_mmcfg(void) @@ -190,11 +185,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void) /* only trust the one handle 256 buses, if acpi=off */ if (!acpi_pci_disabled || busnbits >= 8) { - u64 base; - base = val & (0xffffULL << 32); - if (fam10h_pci_mmconf_base_status <= 0) { + u64 base = val & MMCONF_MASK; + + if (!fam10h_pci_mmconf_base) { fam10h_pci_mmconf_base = base; - fam10h_pci_mmconf_base_status = 1; return; } else if (fam10h_pci_mmconf_base == base) return; @@ -206,8 +200,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void) * with 256 buses */ get_fam10h_pci_mmconf_base(); - if (fam10h_pci_mmconf_base_status <= 0) + if (!fam10h_pci_mmconf_base) { + pci_probe &= ~PCI_CHECK_ENABLE_AMD_MMCONF; return; + } printk(KERN_INFO "Enable MMCONFIG on AMD Family 10h\n"); val &= ~((FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT) | diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 7bf2dc4c8f70..12fcbe2c143e 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -30,7 +30,6 @@ #include <linux/init.h> #include <linux/poll.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/device.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 57d1868a86aa..c852041bfc3d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -91,8 +91,7 @@ void exit_thread(void) void show_regs(struct pt_regs *regs) { show_registers(regs); - show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), - regs->bp); + show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs)); } void show_regs_common(void) @@ -374,6 +373,7 @@ void default_idle(void) { if (hlt_use_halt()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -444,6 +444,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); + trace_cpu_idle((ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -460,6 +461,7 @@ static void mwait_idle(void) { if (!need_resched()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -481,10 +483,12 @@ static void mwait_idle(void) static void poll_idle(void) { trace_power_start(POWER_CSTATE, 0, smp_processor_id()); + trace_cpu_idle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end(0); + trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 96586c3cbbbf..4b9befa0e347 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -113,8 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); - trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b3d7a3a04f38..4c818a738396 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -142,6 +142,8 @@ void cpu_idle(void) start_critical_timings(); trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, + smp_processor_id()); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 008b91eefa18..42eb3300dfc6 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -83,6 +83,11 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) static atomic64_t last_value = ATOMIC64_INIT(0); +void pvclock_resume(void) +{ + atomic64_set(&last_value, 0); +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { struct pvclock_shadow_time shadow; diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c new file mode 100644 index 000000000000..2a26819bb6a8 --- /dev/null +++ b/arch/x86/kernel/resource.c @@ -0,0 +1,48 @@ +#include <linux/ioport.h> +#include <asm/e820.h> + +static void resource_clip(struct resource *res, resource_size_t start, + resource_size_t end) +{ + resource_size_t low = 0, high = 0; + + if (res->end < start || res->start > end) + return; /* no conflict */ + + if (res->start < start) + low = start - res->start; + + if (res->end > end) + high = res->end - end; + + /* Keep the area above or below the conflict, whichever is larger */ + if (low > high) + res->end = start - 1; + else + res->start = end + 1; +} + +static void remove_e820_regions(struct resource *avail) +{ + int i; + struct e820entry *entry; + + for (i = 0; i < e820.nr_map; i++) { + entry = &e820.map[i]; + + resource_clip(avail, entry->addr, + entry->addr + entry->size - 1); + } +} + +void arch_remove_reservations(struct resource *avail) +{ + /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + if (avail->flags & IORESOURCE_MEM) { + if (avail->start < BIOS_END) + avail->start = BIOS_END; + resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); + + remove_e820_regions(avail); + } +} diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0afb8c7e3803..d3cfe26c0252 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -501,7 +501,18 @@ static inline unsigned long long get_total_mem(void) return total << PAGE_SHIFT; } -#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF +/* + * Keep the crash kernel below this limit. On 32 bits earlier kernels + * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this + * limit once kexec-tools are fixed. + */ +#ifdef CONFIG_X86_32 +# define CRASH_KERNEL_ADDR_MAX (512 << 20) +#else +# define CRASH_KERNEL_ADDR_MAX (896 << 20) +#endif + static void __init reserve_crashkernel(void) { unsigned long long total_mem; @@ -520,10 +531,10 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ /* - * kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX + * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment); + CRASH_KERNEL_ADDR_MAX, crash_size, alignment); if (crash_base == MEMBLOCK_ERROR) { pr_info("crashkernel reservation failed - No suitable area found.\n"); @@ -769,7 +780,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - resource_alloc_from_bottom = 0; iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 083e99d1b7df..ee886fe10ef4 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -281,6 +281,13 @@ static void __cpuinit smp_callin(void) */ smp_store_cpu_info(cpuid); + /* + * This must be done before setting cpu_online_mask + * or calling notify_cpu_starting. + */ + set_cpu_sibling_map(raw_smp_processor_id()); + wmb(); + notify_cpu_starting(cpuid); /* @@ -316,16 +323,6 @@ notrace static void __cpuinit start_secondary(void *unused) */ check_tsc_sync_target(); - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - enable_NMI_through_LVT0(); - legacy_pic->unmask(0); - } - - /* This must be done before setting cpu_online_mask */ - set_cpu_sibling_map(raw_smp_processor_id()); - wmb(); - /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of @@ -1061,8 +1058,6 @@ static int __init smp_sanity_check(unsigned max_cpus) printk(KERN_INFO "SMP mode deactivated.\n"); smpboot_clear_io_apic(); - localise_nmi_watchdog(); - connect_bsp_APIC(); setup_local_APIC(); end_local_APIC_setup(); @@ -1166,6 +1161,20 @@ out: preempt_enable(); } +void arch_disable_nonboot_cpus_begin(void) +{ + /* + * Avoid the smp alternatives switch during the disable_nonboot_cpus(). + * In the suspend path, we will be back in the SMP mode shortly anyways. + */ + skip_smp_alternatives = true; +} + +void arch_disable_nonboot_cpus_end(void) +{ + skip_smp_alternatives = false; +} + void arch_enable_nonboot_cpus_begin(void) { set_mtrr_aps_delayed_init(); @@ -1196,7 +1205,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif - check_nmi_watchdog(); mtrr_aps_init(); } @@ -1341,8 +1349,6 @@ int native_cpu_disable(void) if (cpu == 0) return -EBUSY; - if (nmi_watchdog == NMI_LOCAL_APIC) - stop_apic_nmi_watchdog(NULL); clear_local_APIC(); cpu_disable_common(); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index b53c525368a7..938c8e10a19a 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = { */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); + dump_trace(current, NULL, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp) +void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs) { - dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace); + dump_trace(current, regs, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); + dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fb5cc5e14cfa..25a28a245937 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -22,10 +22,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -int timer_ack; -#endif - #ifdef CONFIG_X86_64 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; #endif @@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); - /* Optimized out for !IO_APIC and x86_64 */ - if (timer_ack) { - /* - * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to deassert NMI lines for the watchdog if run - * on an 82489DX-based system. - */ - raw_spin_lock(&i8259A_lock); - outb(0x0c, PIC_MASTER_OCW3); - /* Ack the IRQ; AEOI will end it automatically. */ - inb(PIC_MASTER_POLL); - raw_spin_unlock(&i8259A_lock); - } - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index 3af2dff58b21..075d130efcf9 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -127,7 +127,7 @@ startup_64: no_longmode: hlt jmp no_longmode -#include "verify_cpu_64.S" +#include "verify_cpu.S" # Careful these need to be in the same 64K segment as the above; tidt: diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index cb838ca42c96..c76aaca5694d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -83,6 +83,8 @@ EXPORT_SYMBOL_GPL(used_vectors); static int ignore_nmis; +int unknown_nmi_panic; + static inline void conditional_sti(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) @@ -300,6 +302,13 @@ gp_in_kernel: die("general protection fault", regs, error_code); } +static int __init setup_unknown_nmi_panic(char *str) +{ + unknown_nmi_panic = 1; + return 1; +} +__setup("unknown_nmi_panic", setup_unknown_nmi_panic); + static notrace __kprobes void mem_parity_error(unsigned char reason, struct pt_regs *regs) { @@ -342,9 +351,11 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason = (reason & 0xf) | 8; outb(reason, 0x61); - i = 2000; - while (--i) - udelay(1000); + i = 20000; + while (--i) { + touch_nmi_watchdog(); + udelay(100); + } reason &= ~8; outb(reason, 0x61); @@ -371,7 +382,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n"); - if (panic_on_unrecovered_nmi) + if (unknown_nmi_panic || panic_on_unrecovered_nmi) panic("NMI: Not continuing"); printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); @@ -397,20 +408,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; - -#ifndef CONFIG_LOCKUP_DETECTOR - /* - * Ok, so this is none of the documented NMI sources, - * so it must be the NMI watchdog. - */ - if (nmi_watchdog_tick(regs, reason)) - return; - if (!do_nmi_callback(regs, cpu)) -#endif /* !CONFIG_LOCKUP_DETECTOR */ - unknown_nmi_error(reason, regs); -#else - unknown_nmi_error(reason, regs); #endif + unknown_nmi_error(reason, regs); return; } @@ -446,14 +445,12 @@ do_nmi(struct pt_regs *regs, long error_code) void stop_nmi(void) { - acpi_nmi_disable(); ignore_nmis++; } void restart_nmi(void) { ignore_nmis--; - acpi_nmi_enable(); } /* May run on IST stack. */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 0c40d8b72416..356a0d455cf9 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void) if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; + + if (tsc_clocksource_reliable) + return 0; /* * Intel systems are normally all synchronized. * Exceptions must mark TSC as unstable: @@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ if (num_possible_cpus() > 1) - tsc_unstable = 1; + return 1; } - return tsc_unstable; + return 0; +} + + +static void tsc_refine_calibration_work(struct work_struct *work); +static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); +/** + * tsc_refine_calibration_work - Further refine tsc freq calibration + * @work - ignored. + * + * This functions uses delayed work over a period of a + * second to further refine the TSC freq value. Since this is + * timer based, instead of loop based, we don't block the boot + * process while this longer calibration is done. + * + * If there are any calibration anomolies (too many SMIs, etc), + * or the refined calibration is off by 1% of the fast early + * calibration, we throw out the new calibration and use the + * early calibration. + */ +static void tsc_refine_calibration_work(struct work_struct *work) +{ + static u64 tsc_start = -1, ref_start; + static int hpet; + u64 tsc_stop, ref_stop, delta; + unsigned long freq; + + /* Don't bother refining TSC on unstable systems */ + if (check_tsc_unstable()) + goto out; + + /* + * Since the work is started early in boot, we may be + * delayed the first time we expire. So set the workqueue + * again once we know timers are working. + */ + if (tsc_start == -1) { + /* + * Only set hpet once, to avoid mixing hardware + * if the hpet becomes enabled later. + */ + hpet = is_hpet_enabled(); + schedule_delayed_work(&tsc_irqwork, HZ); + tsc_start = tsc_read_refs(&ref_start, hpet); + return; + } + + tsc_stop = tsc_read_refs(&ref_stop, hpet); + + /* hpet or pmtimer available ? */ + if (!hpet && !ref_start && !ref_stop) + goto out; + + /* Check, whether the sampling was disturbed by an SMI */ + if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX) + goto out; + + delta = tsc_stop - tsc_start; + delta *= 1000000LL; + if (hpet) + freq = calc_hpet_ref(delta, ref_start, ref_stop); + else + freq = calc_pmtimer_ref(delta, ref_start, ref_stop); + + /* Make sure we're within 1% */ + if (abs(tsc_khz - freq) > tsc_khz/100) + goto out; + + tsc_khz = freq; + printk(KERN_INFO "Refined TSC clocksource calibration: " + "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + +out: + clocksource_register_khz(&clocksource_tsc, tsc_khz); } -static void __init init_tsc_clocksource(void) + +static int __init init_tsc_clocksource(void) { + if (!cpu_has_tsc || tsc_disabled > 0) + return 0; + if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; /* lower the rating if we already know its unstable: */ @@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } - clocksource_register_khz(&clocksource_tsc, tsc_khz); + schedule_delayed_work(&tsc_irqwork, 0); + return 0; } +/* + * We use device_initcall here, to ensure we run after the hpet + * is fully initialized, which may occur at fs_initcall time. + */ +device_initcall(init_tsc_clocksource); void __init tsc_init(void) { @@ -949,6 +1036,5 @@ void __init tsc_init(void) mark_tsc_unstable("TSCs unsynchronized"); check_system_tsc_reliable(); - init_tsc_clocksource(); } diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu.S index 56a8c2a867d9..0edefc19a113 100644 --- a/arch/x86/kernel/verify_cpu_64.S +++ b/arch/x86/kernel/verify_cpu.S @@ -7,6 +7,7 @@ * Copyright (c) 2007 Andi Kleen (ak@suse.de) * Copyright (c) 2007 Eric Biederman (ebiederm@xmission.com) * Copyright (c) 2007 Vivek Goyal (vgoyal@in.ibm.com) + * Copyright (c) 2010 Kees Cook (kees.cook@canonical.com) * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. @@ -14,18 +15,17 @@ * This is a common code for verification whether CPU supports * long mode and SSE or not. It is not called directly instead this * file is included at various places and compiled in that context. - * Following are the current usage. + * This file is expected to run in 32bit code. Currently: * - * This file is included by both 16bit and 32bit code. + * arch/x86/boot/compressed/head_64.S: Boot cpu verification + * arch/x86/kernel/trampoline_64.S: secondary processor verfication + * arch/x86/kernel/head_32.S: processor startup * - * arch/x86_64/boot/setup.S : Boot cpu verification (16bit) - * arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit) - * arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit) - * arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit) - * - * verify_cpu, returns the status of cpu check in register %eax. + * verify_cpu, returns the status of longmode and SSE in register %eax. * 0: Success 1: Failure * + * On Intel, the XD_DISABLE flag will be cleared as a side-effect. + * * The caller needs to check for the error code and take the action * appropriately. Either display a message or halt. */ @@ -62,8 +62,41 @@ verify_cpu: cmpl $0x444d4163,%ecx jnz verify_cpu_noamd mov $1,%di # cpu is from AMD + jmp verify_cpu_check verify_cpu_noamd: + cmpl $0x756e6547,%ebx # GenuineIntel? + jnz verify_cpu_check + cmpl $0x49656e69,%edx + jnz verify_cpu_check + cmpl $0x6c65746e,%ecx + jnz verify_cpu_check + + # only call IA32_MISC_ENABLE when: + # family > 6 || (family == 6 && model >= 0xd) + movl $0x1, %eax # check CPU family and model + cpuid + movl %eax, %ecx + + andl $0x0ff00f00, %eax # mask family and extended family + shrl $8, %eax + cmpl $6, %eax + ja verify_cpu_clear_xd # family > 6, ok + jb verify_cpu_check # family < 6, skip + + andl $0x000f00f0, %ecx # mask model and extended model + shrl $4, %ecx + cmpl $0xd, %ecx + jb verify_cpu_check # family == 6, model < 0xd, skip + +verify_cpu_clear_xd: + movl $MSR_IA32_MISC_ENABLE, %ecx + rdmsr + btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE + jnc verify_cpu_check # only write MSR if bit was changed + wrmsr + +verify_cpu_check: movl $0x1,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK0,%edx diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e03530aebfd0..bf4700755184 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -69,7 +69,7 @@ jiffies_64 = jiffies; PHDRS { text PT_LOAD FLAGS(5); /* R_E */ - data PT_LOAD FLAGS(7); /* RWE */ + data PT_LOAD FLAGS(6); /* RW_ */ #ifdef CONFIG_X86_64 user PT_LOAD FLAGS(5); /* R_E */ #ifdef CONFIG_SMP @@ -116,6 +116,10 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 +#if defined(CONFIG_DEBUG_RODATA) + /* .text should occupy whole number of pages */ + . = ALIGN(PAGE_SIZE); +#endif X64_ALIGN_DEBUG_RODATA_BEGIN RO_DATA(PAGE_SIZE) X64_ALIGN_DEBUG_RODATA_END @@ -335,7 +339,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) - . = ALIGN(4); + . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 9c253bd65e24..547128546cc3 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -394,7 +394,8 @@ static void __init setup_xstate_init(void) * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ - init_xstate_buf = alloc_bootmem(xstate_size); + init_xstate_buf = alloc_bootmem_align(xstate_size, + __alignof__(struct xsave_struct)); init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; clts(); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index f628234fbeca..3cece05e4ac4 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -575,6 +575,8 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) s->pics[1].elcr_mask = 0xde; s->pics[0].pics_state = s; s->pics[1].pics_state = s; + s->pics[0].isr_ack = 0xff; + s->pics[1].isr_ack = 0xff; /* * Initialize PIO device diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index fb8b376bf28c..fbb04aee8301 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2394,7 +2394,8 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); - sp = kvm_mmu_get_page(vcpu, i << 30, i << 30, + sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL, NULL); root = __pa(sp->spt); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 82e144a4e514..b81a9b7c2ca4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3395,6 +3395,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; load_host_msrs(vcpu); + kvm_load_ldt(ldt_selector); loadsegment(fs, fs_selector); #ifdef CONFIG_X86_64 load_gs_index(gs_selector); @@ -3402,7 +3403,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #else loadsegment(gs, gs_selector); #endif - kvm_load_ldt(ldt_selector); reload_tss(vcpu); @@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { + case 0x00000001: + /* Mask out xsave bit as long as it is not supported by SVM */ + entry->ecx &= ~(bit(X86_FEATURE_XSAVE)); + break; case 0x80000001: if (nested) entry->ecx |= (1 << 2); /* Set SVM bit */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8da0e45ff7c9..81fcbe9515c5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -821,10 +821,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - } #endif for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, @@ -839,23 +838,23 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) ++vmx->vcpu.stat.host_state_reload; vmx->host_state.loaded = 0; - if (vmx->host_state.fs_reload_needed) - loadsegment(fs, vmx->host_state.fs_sel); +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); +#endif if (vmx->host_state.gs_ldt_reload_needed) { kvm_load_ldt(vmx->host_state.ldt_sel); #ifdef CONFIG_X86_64 load_gs_index(vmx->host_state.gs_sel); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); #else loadsegment(gs, vmx->host_state.gs_sel); #endif } + if (vmx->host_state.fs_reload_needed) + loadsegment(fs, vmx->host_state.fs_sel); reload_tss(); #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); - } + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif if (current_thread_info()->status & TS_USEDFPU) clts(); @@ -4228,11 +4227,6 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cdac9e592aa5..b989e1f1e5d3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { u64 __read_mostly host_xcr0; -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; @@ -4569,9 +4564,11 @@ static void kvm_timer_init(void) #ifdef CONFIG_CPU_FREQ struct cpufreq_policy policy; memset(&policy, 0, sizeof(policy)); - cpufreq_get_policy(&policy, get_cpu()); + cpu = get_cpu(); + cpufreq_get_policy(&policy, cpu); if (policy.cpuinfo.max_freq) max_tsc_khz = policy.cpuinfo.max_freq; + put_cpu(); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -5522,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + if (sregs->cr4 & X86_CR4_OSXSAVE) + update_cpuid(vcpu); if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3); mmu_reset_needed = 1; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2cea414489f3..c600da830ce0 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_PG); } +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 73b1e1a1f489..4996cf5f73a0 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -531,7 +531,10 @@ static void lguest_write_cr3(unsigned long cr3) { lguest_data.pgdir = cr3; lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); - cr3_changed = true; + + /* These two page tables are simple, linear, and used during boot */ + if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table)) + cr3_changed = true; } static unsigned long lguest_read_cr3(void) @@ -703,9 +706,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) * to forget all of them. Fortunately, this is very rare. * * ... except in early boot when the kernel sets up the initial pagetables, - * which makes booting astonishingly slow: 1.83 seconds! So we don't even tell - * the Host anything changed until we've done the first page table switch, - * which brings boot back to 0.25 seconds. + * which makes booting astonishingly slow: 48 seconds! So we don't even tell + * the Host anything changed until we've done the first real page table switch, + * which brings boot back to 4.3 seconds. */ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { @@ -1002,7 +1005,7 @@ static void lguest_time_init(void) clockevents_register_device(&lguest_clockevent); /* Finally, we unblock the timer interrupt. */ - enable_lguest_irq(0); + clear_bit(0, lguest_data.blocked_interrupts); } /* @@ -1349,9 +1352,6 @@ __init void lguest_init(void) */ switch_to_new_gdt(0); - /* We actually boot with all memory mapped, but let's say 128MB. */ - max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; - /* * The Host<->Guest Switcher lives at the top of our address space, and * the Host told us how big it is when we made LGUEST_INIT hypercall: diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c0e28a13de7d..947f42abe820 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) /* * We just marked the kernel text read only above, now that * we are going to free part of that, we need to make that - * writeable first. + * writeable and non-executable first. */ + set_memory_nx(begin, (end - begin) >> PAGE_SHIFT); set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 0e969f9f401b..f89b5bb4e93f 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -226,7 +226,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) static inline int is_kernel_text(unsigned long addr) { - if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end) + if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; return 0; } @@ -912,6 +912,23 @@ void set_kernel_text_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); } +static void mark_nxdata_nx(void) +{ + /* + * When this called, init has already been executed and released, + * so everything past _etext sould be NX. + */ + unsigned long start = PFN_ALIGN(_etext); + /* + * This comes from is_kernel_text upper limit. Also HPAGE where used: + */ + unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start; + + if (__supported_pte_mask & _PAGE_NX) + printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10); + set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); @@ -946,6 +963,7 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif + mark_nxdata_nx(); } #endif diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index af3b6c8a436f..704a37cedddb 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state, e->trace.entries = e->trace_entries; e->trace.max_entries = ARRAY_SIZE(e->trace_entries); e->trace.skip = 0; - save_stack_trace_bp(&e->trace, regs->bp); + save_stack_trace_regs(&e->trace, regs); /* Round address down to nearest 16 bytes */ shadow_copy = kmemcheck_shadow_lookup(address diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 532e7933d606..8b830ca14ac4 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -13,6 +13,7 @@ #include <linux/pfn.h> #include <linux/percpu.h> #include <linux/gfp.h> +#include <linux/pci.h> #include <asm/e820.h> #include <asm/processor.h> @@ -255,13 +256,16 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, unsigned long pfn) { pgprot_t forbidden = __pgprot(0); + pgprot_t required = __pgprot(0); /* * The BIOS area between 640k and 1Mb needs to be executable for * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support. */ - if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) +#ifdef CONFIG_PCI_BIOS + if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_NX; +#endif /* * The kernel text needs to be executable for obvious reasons @@ -278,6 +282,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; + /* + * .data and .bss should always be writable. + */ + if (within(address, (unsigned long)_sdata, (unsigned long)_edata) || + within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop)) + pgprot_val(required) |= _PAGE_RW; #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) /* @@ -317,6 +327,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, #endif prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); + prot = __pgprot(pgprot_val(prot) | pgprot_val(required)); return prot; } @@ -393,7 +404,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, { unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn; pte_t new_pte, old_pte, *tmp; - pgprot_t old_prot, new_prot; + pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; unsigned int level; @@ -438,10 +449,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = pte_pgprot(old_pte); + old_prot = new_prot = req_prot = pte_pgprot(old_pte); - pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); - pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); + pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); + pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* * old_pte points to the large page base address. So we need @@ -450,17 +461,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; - new_prot = static_protections(new_prot, address, pfn); + new_prot = static_protections(req_prot, address, pfn); /* * We need to check the full range, whether * static_protection() requires a different pgprot for one of * the pages in the range we try to preserve: */ - addr = address + PAGE_SIZE; - pfn++; - for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) { - pgprot_t chk_prot = static_protections(new_prot, addr, pfn); + addr = address & pmask; + pfn = pte_pfn(old_pte); + for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { + pgprot_t chk_prot = static_protections(req_prot, addr, pfn); if (pgprot_val(chk_prot) != pgprot_val(new_prot)) goto out_unlock; @@ -483,7 +494,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * that we limited the number of possible pages already to * the number of pages in the large page. */ - if (address == (nextpage_addr - psize) && cpa->numpages == numpages) { + if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) { /* * The address is aligned and the number of pages * covers the full page. diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index a3250aa34086..410531d3c292 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -41,7 +41,7 @@ void __init x86_report_nx(void) { if (!cpu_has_nx) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "missing in CPU or disabled in BIOS!\n"); + "missing in CPU!\n"); } else { #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) if (disable_nx) { diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index a17dffd136c1..f16434568a51 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -92,6 +92,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity) /* mark this node as "seen" in node bitmap */ BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo); + /* don't need to check apic_id here, because it is always 8 bits */ apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo; printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n", diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index a35cb9d8b060..171a0aacb99a 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -134,6 +134,10 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } apic_id = pa->apic_id; + if (apic_id >= MAX_LOCAL_APIC) { + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); + return; + } apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; @@ -168,6 +172,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) apic_id = (pa->apic_id << 8) | pa->local_sapic_eid; else apic_id = pa->apic_id; + + if (apic_id >= MAX_LOCAL_APIC) { + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); + return; + } + apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 12cdbb17ad18..6acc724d5d8f 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -223,7 +223,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, static void __cpuinit calculate_tlb_offset(void) { - int cpu, node, nr_node_vecs; + int cpu, node, nr_node_vecs, idx = 0; /* * we are changing tlb_vector_offset for each CPU in runtime, but this * will not cause inconsistency, as the write is atomic under X86. we @@ -239,7 +239,7 @@ static void __cpuinit calculate_tlb_offset(void) nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes; for_each_online_node(node) { - int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) * + int node_offset = (idx % NUM_INVALIDATE_TLB_VECTORS) * nr_node_vecs; int cpu_offset = 0; for_each_cpu(cpu, cpumask_of_node(node)) { @@ -248,6 +248,7 @@ static void __cpuinit calculate_tlb_offset(void) cpu_offset++; cpu_offset = cpu_offset % nr_node_vecs; } + idx++; } } diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 2d49d4e19a36..72cbec14d783 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) if (!user_mode_vm(regs)) { unsigned long stack = kernel_stack_pointer(regs); if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, 0, + dump_trace(NULL, regs, (unsigned long *)stack, &backtrace_ops, &depth); return; } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 4e8baad36d37..358c8b9c96a7 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -732,6 +732,9 @@ int __init op_nmi_init(struct oprofile_operations *ops) case 0x14: cpu_type = "x86-64/family14h"; break; + case 0x15: + cpu_type = "x86-64/family15h"; + break; default: return -ENODEV; } diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c index e3ecb71b5790..0636dd93cef8 100644 --- a/arch/x86/oprofile/nmi_timer_int.c +++ b/arch/x86/oprofile/nmi_timer_int.c @@ -58,9 +58,6 @@ static void timer_stop(void) int __init op_nmi_timer_init(struct oprofile_operations *ops) { - if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0)) - return -ENODEV; - ops->start = timer_start; ops->stop = timer_stop; ops->cpu_type = "timer"; diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index a011bcc0f943..c3b8e24f2b16 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -29,11 +29,12 @@ #include "op_x86_model.h" #include "op_counter.h" -#define NUM_COUNTERS 4 +#define NUM_COUNTERS 4 +#define NUM_COUNTERS_F15H 6 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX -#define NUM_VIRT_COUNTERS 32 +#define NUM_VIRT_COUNTERS 32 #else -#define NUM_VIRT_COUNTERS NUM_COUNTERS +#define NUM_VIRT_COUNTERS 0 #endif #define OP_EVENT_MASK 0x0FFF @@ -41,7 +42,8 @@ #define MSR_AMD_EVENTSEL_RESERVED ((0xFFFFFCF0ULL<<32)|(1ULL<<21)) -static unsigned long reset_value[NUM_VIRT_COUNTERS]; +static int num_counters; +static unsigned long reset_value[OP_MAX_COUNTER]; #define IBS_FETCH_SIZE 6 #define IBS_OP_SIZE 12 @@ -387,7 +389,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, int i; /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -406,7 +408,7 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) { int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!msrs->counters[i].addr) continue; release_perfctr_nmi(MSR_K7_PERFCTR0 + i); @@ -418,7 +420,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) { int i; - for (i = 0; i < NUM_COUNTERS; i++) { + for (i = 0; i < num_counters; i++) { if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) goto fail; if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) { @@ -426,8 +428,13 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) goto fail; } /* both registers must be reserved */ - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + if (num_counters == NUM_COUNTERS_F15H) { + msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); + msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); + } else { + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; + } continue; fail: if (!counter_config[i].enabled) @@ -447,7 +454,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, int i; /* setup reset_value */ - for (i = 0; i < NUM_VIRT_COUNTERS; ++i) { + for (i = 0; i < OP_MAX_COUNTER; ++i) { if (counter_config[i].enabled && msrs->counters[op_x86_virt_to_phys(i)].addr) reset_value[i] = counter_config[i].count; @@ -456,7 +463,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, } /* clear all counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!msrs->controls[i].addr) continue; rdmsrl(msrs->controls[i].addr, val); @@ -472,7 +479,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, } /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -503,7 +510,7 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, u64 val; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -526,7 +533,7 @@ static void op_amd_start(struct op_msrs const * const msrs) u64 val; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); @@ -546,7 +553,7 @@ static void op_amd_stop(struct op_msrs const * const msrs) * Subtle: stop on all counters to avoid race with setting our * pm callback */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); @@ -603,6 +610,7 @@ static int force_ibs_eilvt_setup(void) ret = setup_ibs_ctl(i); if (ret) return ret; + pr_err(FW_BUG "using offset %d for IBS interrupts\n", i); return 0; } @@ -630,21 +638,29 @@ static int __init_ibs_nmi(void) return 0; } -/* initialize the APIC for the IBS interrupts if available */ +/* + * check and reserve APIC extended interrupt LVT offset for IBS if + * available + * + * init_ibs() preforms implicitly cpu-local operations, so pin this + * thread to its current CPU + */ + static void init_ibs(void) { - ibs_caps = get_ibs_caps(); + preempt_disable(); + ibs_caps = get_ibs_caps(); if (!ibs_caps) - return; + goto out; - if (__init_ibs_nmi()) { + if (__init_ibs_nmi() < 0) ibs_caps = 0; - return; - } + else + printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); - printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", - (unsigned)ibs_caps); +out: + preempt_enable(); } static int (*create_arch_files)(struct super_block *sb, struct dentry *root); @@ -698,18 +714,29 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) return 0; } +struct op_x86_model_spec op_amd_spec; + static int op_amd_init(struct oprofile_operations *ops) { init_ibs(); create_arch_files = ops->create_files; ops->create_files = setup_ibs_files; + + if (boot_cpu_data.x86 == 0x15) { + num_counters = NUM_COUNTERS_F15H; + } else { + num_counters = NUM_COUNTERS; + } + + op_amd_spec.num_counters = num_counters; + op_amd_spec.num_controls = num_counters; + op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS); + return 0; } struct op_x86_model_spec op_amd_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_COUNTERS, - .num_virt_counters = NUM_VIRT_COUNTERS, + /* num_counters/num_controls filled in at runtime */ .reserved = MSR_AMD_EVENTSEL_RESERVED, .event_mask = OP_EVENT_MASK, .init = op_amd_init, diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 182558dd5515..9fadec074142 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -11,7 +11,7 @@ #include <linux/oprofile.h> #include <linux/smp.h> #include <linux/ptrace.h> -#include <linux/nmi.h> +#include <asm/nmi.h> #include <asm/msr.h> #include <asm/fixmap.h> #include <asm/apic.h> diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index c4bb261c106e..b1805b78842f 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -65,21 +65,13 @@ pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { struct pci_dev *dev = data; - resource_size_t start = round_down(res->end - size + 1, align); + resource_size_t start = res->start; if (res->flags & IORESOURCE_IO) { - - /* - * If we're avoiding ISA aliases, the largest contiguous I/O - * port space is 256 bytes. Clearing bits 9 and 10 preserves - * all 256-byte and smaller alignments, so the result will - * still be correctly aligned. - */ - if (!skip_isa_ioresource_align(dev)) - start &= ~0x300; - } else if (res->flags & IORESOURCE_MEM) { - if (start < BIOS_END) - start = res->end; /* fail; no space */ + if (skip_isa_ioresource_align(dev)) + return start; + if (start & 0x300) + start = (start + 0x3ff) & ~0x3ff; } return start; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 2492d165096a..a5f7d0d63de0 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -9,6 +9,7 @@ #include <linux/uaccess.h> #include <asm/pci_x86.h> #include <asm/pci-functions.h> +#include <asm/cacheflush.h> /* BIOS32 signature: "_32_" */ #define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24)) @@ -25,6 +26,27 @@ #define PCIBIOS_HW_TYPE1_SPEC 0x10 #define PCIBIOS_HW_TYPE2_SPEC 0x20 +int pcibios_enabled; + +/* According to the BIOS specification at: + * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could + * restrict the x zone to some pages and make it ro. But this may be + * broken on some bios, complex to handle with static_protections. + * We could make the 0xe0000-0x100000 range rox, but this can break + * some ISA mapping. + * + * So we let's an rw and x hole when pcibios is used. This shouldn't + * happen for modern system with mmconfig, and if you don't want it + * you could disable pcibios... + */ +static inline void set_bios_x(void) +{ + pcibios_enabled = 1; + set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT); + if (__supported_pte_mask & _PAGE_NX) + printk(KERN_INFO "PCI : PCI BIOS aera is rw and x. Use pci=nobios if you want it NX.\n"); +} + /* * This is the standard structure used to identify the entry point * to the BIOS32 Service Directory, as documented in @@ -332,6 +354,7 @@ static struct pci_raw_ops * __devinit pci_find_bios(void) DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n", bios32_entry); bios32_indirect.address = bios32_entry + PAGE_OFFSET; + set_bios_x(); if (check_pcibios()) return &pci_bios_access; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index d7b5109f7a9c..25cd4a07d09f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -70,6 +70,9 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); +#define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \ + MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0)) + static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, struct msi_msg *msg) { @@ -83,12 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, MSI_ADDR_REDIRECTION_CPU | MSI_ADDR_DEST_ID(pirq); - msg->data = - MSI_DATA_TRIGGER_EDGE | - MSI_DATA_LEVEL_ASSERT | - /* delivery mode reserved */ - (3 << 8) | - MSI_DATA_VECTOR(0); + msg->data = XEN_PIRQ_MSI_DATA; } static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) @@ -98,8 +96,23 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct msi_msg msg; list_for_each_entry(msidesc, &dev->msi_list, list) { + __read_msi_msg(msidesc, &msg); + pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | + ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); + if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) { + xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ); + if (irq < 0) + goto error; + ret = set_irq_msi(irq, msidesc); + if (ret < 0) + goto error_while; + printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d" + " pirq=%d\n", irq, pirq); + return 0; + } xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq); + "msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ)); if (irq < 0 || pirq < 0) goto error; printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq); diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index cc822a29b227..7785b72ecc3a 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -37,9 +37,9 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; /* All CPUs enumerated by SFI must be present and enabled */ static void __cpuinit mp_sfi_register_lapic(u8 id) { - if (MAX_APICS - id <= 0) { + if (MAX_LOCAL_APIC - id <= 0) { pr_warning("Processor #%d invalid (max %d)\n", - id, MAX_APICS); + id, MAX_LOCAL_APIC); return; } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index a318194002b5..df58e9cad96a 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1341,7 +1341,7 @@ uv_activation_descriptor_init(int node, int pnode) /* * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR) - * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub + * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE) */ bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE * UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node); @@ -1455,7 +1455,7 @@ static void __init uv_init_uvhub(int uvhub, int vector) * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = uvhub_to_first_apicid(uvhub); + apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits; uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, ((apicid << 32) | vector)); } @@ -1490,7 +1490,7 @@ calculate_destination_timeout(void) /* * initialize the bau_control structure for each cpu */ -static void __init uv_init_per_cpu(int nuvhubs) +static int __init uv_init_per_cpu(int nuvhubs) { int i; int cpu; @@ -1507,7 +1507,7 @@ static void __init uv_init_per_cpu(int nuvhubs) struct bau_control *smaster = NULL; struct socket_desc { short num_cpus; - short cpu_number[16]; + short cpu_number[MAX_CPUS_PER_SOCKET]; }; struct uvhub_desc { unsigned short socket_mask; @@ -1540,6 +1540,10 @@ static void __init uv_init_per_cpu(int nuvhubs) sdp = &bdp->socket[socket]; sdp->cpu_number[sdp->num_cpus] = cpu; sdp->num_cpus++; + if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) { + printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus); + return 1; + } } for (uvhub = 0; uvhub < nuvhubs; uvhub++) { if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8)))) @@ -1570,6 +1574,12 @@ static void __init uv_init_per_cpu(int nuvhubs) bcp->uvhub_master = hmaster; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)-> blade_processor_id; + if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { + printk(KERN_EMERG + "%d cpus per uvhub invalid\n", + bcp->uvhub_cpu); + return 1; + } } nextsocket: socket++; @@ -1595,6 +1605,7 @@ nextsocket: bcp->congested_reps = congested_reps; bcp->congested_period = congested_period; } + return 0; } /* @@ -1625,7 +1636,10 @@ static int __init uv_bau_init(void) spin_lock_init(&disable_lock); congested_cycles = microsec_2_cycles(congested_response_us); - uv_init_per_cpu(nuvhubs); + if (uv_init_per_cpu(nuvhubs)) { + nobau = 1; + return 0; + } uv_partition_base_pnode = 0x7fffffff; for (uvhub = 0; uvhub < nuvhubs; uvhub++) diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 56e421bc379b..9daf5d1af9f1 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -89,6 +89,7 @@ static void uv_rtc_send_IPI(int cpu) apicid = cpu_physical_id(cpu); pnode = uv_apicid_to_pnode(apicid); + apicid |= uv_apicid_hibits; val = (1UL << UVH_IPI_INT_SEND_SHFT) | (apicid << UVH_IPI_INT_APIC_ID_SHFT) | (X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT); @@ -107,6 +108,7 @@ static int uv_intr_pending(int pnode) static int uv_setup_intr(int cpu, u64 expires) { u64 val; + unsigned long apicid = cpu_physical_id(cpu) | uv_apicid_hibits; int pnode = uv_cpu_to_pnode(cpu); uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, @@ -117,7 +119,7 @@ static int uv_setup_intr(int cpu, u64 expires) UVH_EVENT_OCCURRED0_RTC1_MASK); val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | - ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); + ((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); /* Set configuration */ uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, val); diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c index 3371bd053b89..632037671746 100644 --- a/arch/x86/platform/visws/visws_quirks.c +++ b/arch/x86/platform/visws/visws_quirks.c @@ -171,7 +171,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) ver = m->apicver; if ((ver >= 0x14 && m->apicid >= 0xff) || m->apicid >= 0xf) { printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->apicid, MAX_APICS); + m->apicid, MAX_LOCAL_APIC); return; } diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 4a2afa1bac51..b6552b189bcd 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -25,7 +25,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) export CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -Wl,-soname=linux-vdso.so.1 \ +VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so @@ -69,7 +69,7 @@ vdso32.so-$(VDSO32-y) += sysenter vdso32-images = $(vdso32.so-y:%=vdso32-%.so) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1 # This makes sure the $(obj) subdirectory exists even though vdso32/ # is not a kbuild sub-make subdirectory. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 235c0f4d3861..44dcad43989d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,6 +75,11 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); enum xen_domain_type xen_domain_type = XEN_NATIVE; EXPORT_SYMBOL_GPL(xen_domain_type); +unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; +EXPORT_SYMBOL(machine_to_phys_mapping); +unsigned int machine_to_phys_order; +EXPORT_SYMBOL(machine_to_phys_order); + struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); @@ -1016,10 +1021,6 @@ static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; -#ifdef CONFIG_SMP - stop_other_cpus(); -#endif - if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); } @@ -1090,6 +1091,8 @@ static void __init xen_setup_stackprotector(void) /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { + struct physdev_set_iopl set_iopl; + int rc; pgd_t *pgd; if (!xen_start_info) @@ -1097,6 +1100,8 @@ asmlinkage void __init xen_start_kernel(void) xen_domain_type = XEN_PV_DOMAIN; + xen_setup_machphys_mapping(); + /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; @@ -1191,8 +1196,6 @@ asmlinkage void __init xen_start_kernel(void) /* Allocate and initialize top and mid mfn levels for p2m structure */ xen_build_mfn_list_list(); - init_mm.pgd = pgd; - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 @@ -1202,10 +1205,18 @@ asmlinkage void __init xen_start_kernel(void) #else pv_info.kernel_rpl = 0; #endif - /* set the limit of our address space */ xen_reserve_top(); + /* We used to do this in xen_arch_setup, but that is too late on AMD + * were early_cpu_init (run before ->arch_setup()) calls early_amd_init + * which pokes 0xcf8 port. + */ + set_iopl.iopl = 1; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); + if (rc != 0) + xen_raw_printk("physdev_op failed %d\n", rc); + #ifdef CONFIG_X86_32 /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 21ed8d7f75a5..44924e551fde 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2034,6 +2034,20 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) set_page_prot(pmd, PAGE_KERNEL_RO); } +void __init xen_setup_machphys_mapping(void) +{ + struct xen_machphys_mapping mapping; + unsigned long machine_to_phys_nr_ents; + + if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) { + machine_to_phys_mapping = (unsigned long *)mapping.v_start; + machine_to_phys_nr_ents = mapping.max_mfn + 1; + } else { + machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES; + } + machine_to_phys_order = fls(machine_to_phys_nr_ents - 1); +} + #ifdef CONFIG_X86_64 static void convert_pfn_mfn(void *v) { @@ -2119,44 +2133,83 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, return pgd; } #else /* !CONFIG_X86_64 */ -static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD); +static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); +static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); + +static __init void xen_write_cr3_init(unsigned long cr3) +{ + unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); + + BUG_ON(read_cr3() != __pa(initial_page_table)); + BUG_ON(cr3 != __pa(swapper_pg_dir)); + + /* + * We are switching to swapper_pg_dir for the first time (from + * initial_page_table) and therefore need to mark that page + * read-only and then pin it. + * + * Xen disallows sharing of kernel PMDs for PAE + * guests. Therefore we must copy the kernel PMD from + * initial_page_table into a new kernel PMD to be used in + * swapper_pg_dir. + */ + swapper_kernel_pmd = + extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); + memcpy(swapper_kernel_pmd, initial_kernel_pmd, + sizeof(pmd_t) * PTRS_PER_PMD); + swapper_pg_dir[KERNEL_PGD_BOUNDARY] = + __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT); + set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO); + + set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); + xen_write_cr3(cr3); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn); + + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, + PFN_DOWN(__pa(initial_page_table))); + set_page_prot(initial_page_table, PAGE_KERNEL); + set_page_prot(initial_kernel_pmd, PAGE_KERNEL); + + pv_mmu_ops.write_cr3 = &xen_write_cr3; +} __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pmd_t *kernel_pmd; - level2_kernel_pgt = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); + initial_kernel_pmd = + extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + xen_start_info->nr_pt_frames * PAGE_SIZE + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); + memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); - xen_map_identity_early(level2_kernel_pgt, max_pfn); + xen_map_identity_early(initial_kernel_pmd, max_pfn); - memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD); - set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY], - __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT)); + memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD); + initial_page_table[KERNEL_PGD_BOUNDARY] = + __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); + set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO); + set_page_prot(initial_page_table, PAGE_KERNEL_RO); set_page_prot(empty_zero_page, PAGE_KERNEL_RO); pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - xen_write_cr3(__pa(swapper_pg_dir)); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, + PFN_DOWN(__pa(initial_page_table))); + xen_write_cr3(__pa(initial_page_table)); memblock_x86_reserve_range(__pa(xen_start_info->pt_base), __pa(xen_start_info->pt_base + xen_start_info->nr_pt_frames * PAGE_SIZE), "XEN PAGETABLES"); - return swapper_pg_dir; + return initial_page_table; } #endif /* CONFIG_X86_64 */ @@ -2290,7 +2343,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .write_cr2 = xen_write_cr2, .read_cr3 = xen_read_cr3, +#ifdef CONFIG_X86_32 + .write_cr3 = xen_write_cr3_init, +#else .write_cr3 = xen_write_cr3, +#endif .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, @@ -2358,8 +2415,6 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; pv_mmu_ops = xen_mmu_ops; - vmap_lazy_unmap = false; - memset(dummy_mapping, 0xff, PAGE_SIZE); } @@ -2627,7 +2682,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP); - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) == + (VM_PFNMAP | VM_RESERVED | VM_IO))); rmd.mfn = mfn; rmd.prot = prot; diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 0f456386cce5..25c52f94a27c 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -68,7 +68,7 @@ static int __init check_platform_magic(void) return 0; } -void __init xen_unplug_emulated_devices(void) +void xen_unplug_emulated_devices(void) { int r; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 769c4b01fa32..b5a7f928234b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -23,7 +23,6 @@ #include <xen/interface/callback.h> #include <xen/interface/memory.h> #include <xen/interface/physdev.h> -#include <xen/interface/memory.h> #include <xen/features.h> #include "xen-ops.h" @@ -182,24 +181,21 @@ char * __init xen_memory_setup(void) for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end = map[i].addr + map[i].size; - if (map[i].type == E820_RAM) { - if (map[i].addr < mem_end && end > mem_end) { - /* Truncate region to max_mem. */ - u64 delta = end - mem_end; + if (map[i].type == E820_RAM && end > mem_end) { + /* RAM off the end - may be partially included */ + u64 delta = min(map[i].size, end - mem_end); - map[i].size -= delta; - extra_pages += PFN_DOWN(delta); + map[i].size -= delta; + end -= delta; - end = mem_end; - } + extra_pages += PFN_DOWN(delta); } - if (end > xen_extra_mem_start) + if (map[i].size > 0 && end > xen_extra_mem_start) xen_extra_mem_start = end; - /* If region is non-RAM or below mem_end, add what remains */ - if ((map[i].type != E820_RAM || map[i].addr < mem_end) && - map[i].size > 0) + /* Add region if any remains */ + if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } @@ -248,26 +244,11 @@ char * __init xen_memory_setup(void) else extra_pages = 0; - if (!xen_initial_domain()) - xen_add_extra_mem(extra_pages); + xen_add_extra_mem(extra_pages); return "Xen"; } -static void xen_idle(void) -{ - local_irq_disable(); - - if (need_resched()) - local_irq_enable(); - else { - current_thread_info()->status &= ~TS_POLLING; - smp_mb__after_clear_bit(); - safe_halt(); - current_thread_info()->status |= TS_POLLING; - } -} - /* * Set the bit indicating "nosegneg" library variants should be used. * We only need to bother in pure 32-bit mode; compat 32-bit processes @@ -337,9 +318,6 @@ void __cpuinit xen_enable_syscall(void) void __init xen_arch_setup(void) { - struct physdev_set_iopl set_iopl; - int rc; - xen_panic_handler_init(); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); @@ -356,11 +334,6 @@ void __init xen_arch_setup(void) xen_enable_sysenter(); xen_enable_syscall(); - set_iopl.iopl = 1; - rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); - if (rc != 0) - printk(KERN_INFO "physdev_op failed %d\n", rc); - #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { printk(KERN_INFO "ACPI in unprivileged domain disabled\n"); @@ -372,7 +345,11 @@ void __init xen_arch_setup(void) MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ? COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE); - pm_idle = xen_idle; + /* Set up idle, making sure it calls safe_halt() pvop */ +#ifdef CONFIG_X86_32 + boot_cpu_data.hlt_works_ok = 1; +#endif + pm_idle = default_idle; fiddle_vdso(); } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 1d789d56877c..9bbd63a129b5 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -31,6 +31,7 @@ void xen_hvm_post_suspend(int suspend_cancelled) int cpu; xen_hvm_init_shared_info(); xen_callback_vector(); + xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { for_each_online_cpu(cpu) { xen_setup_runstate_info(cpu); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index b2bb5aa3b054..5da5e53fb94c 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -426,6 +426,8 @@ void xen_timer_resume(void) { int cpu; + pvclock_resume(); + if (xen_clockevent != &xen_vcpuop_clockevent) return; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 64044747348e..9d41bf985757 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -43,7 +43,7 @@ void xen_vcpu_restore(void); void xen_callback_vector(void); void xen_hvm_init_shared_info(void); -void __init xen_unplug_emulated_devices(void); +void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); |
