diff options
Diffstat (limited to 'arch')
304 files changed, 4088 insertions, 2199 deletions
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index 2ce1ef07c13..ab99c3c3b75 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -62,7 +62,6 @@ config MACH_DAVINCI_EVM bool "TI DM644x EVM" default ARCH_DAVINCI_DM644x depends on ARCH_DAVINCI_DM644x - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -72,7 +71,6 @@ config MACH_DAVINCI_EVM config MACH_SFFSDR bool "Lyrtech SFFSDR" depends on ARCH_DAVINCI_DM644x - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -106,7 +104,6 @@ config MACH_DAVINCI_DM6467_EVM default ARCH_DAVINCI_DM646x depends on ARCH_DAVINCI_DM646x select MACH_DAVINCI_DM6467TEVM - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -120,7 +117,6 @@ config MACH_DAVINCI_DM365_EVM bool "TI DM365 EVM" default ARCH_DAVINCI_DM365 depends on ARCH_DAVINCI_DM365 - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -132,7 +128,6 @@ config MACH_DAVINCI_DA830_EVM default ARCH_DAVINCI_DA830 depends on ARCH_DAVINCI_DA830 select GPIO_PCF857X - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -219,7 +214,6 @@ config MACH_TNETV107X config MACH_MITYOMAPL138 bool "Critical Link MityDSP-L138/MityARM-1808 SoM" depends on ARCH_DAVINCI_DA850 - select MISC_DEVICES select EEPROM_AT24 select I2C help diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c index 519bcd3079e..e5fa46bfde2 100644 --- a/arch/arm/mach-omap2/board-apollon.c +++ b/arch/arm/mach-omap2/board-apollon.c @@ -311,7 +311,7 @@ static void __init omap_apollon_init(void) /* LCD PWR_EN */ omap_mux_init_signal("mcbsp2_dr.gpio_11", OMAP_PULL_ENA | OMAP_PULL_UP); - /* Use Interal loop-back in MMC/SDIO Module Input Clock selection */ + /* Use Internal loop-back in MMC/SDIO Module Input Clock selection */ v = omap_ctrl_readl(OMAP2_CONTROL_DEVCONF0); v |= (1 << 24); omap_ctrl_writel(v, OMAP2_CONTROL_DEVCONF0); diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index b627cdc12b8..70f6d1d2546 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -106,7 +106,7 @@ static struct platform_device leds_gpio = { static struct omap_abe_twl6040_data panda_abe_audio_data = { /* Audio out */ .has_hs = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, - /* HandsFree through expasion connector */ + /* HandsFree through expansion connector */ .has_hf = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, /* PandaBoard: FM TX, PandaBoardES: can be connected to audio out */ .has_aux = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index e35a86bf4e1..637a1bdf2ac 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -313,7 +313,7 @@ int __cpuinit omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state) scu_pwrst_prepare(cpu, power_state); /* - * CPU never retuns back if targetted power state is OFF mode. + * CPU never retuns back if targeted power state is OFF mode. * CPU ONLINE follows normal CPU ONLINE ptah via * omap_secondary_startup(). */ diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c index e107e3915a8..d033a65f4e4 100644 --- a/arch/arm/mach-omap2/sr_device.c +++ b/arch/arm/mach-omap2/sr_device.c @@ -131,7 +131,7 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user) omap_voltage_get_volttable(sr_data->voltdm, &volt_data); if (!volt_data) { - pr_warning("%s: No Voltage table registerd fo VDD%d." + pr_warning("%s: No Voltage table registered fo VDD%d." "Something really wrong\n\n", __func__, i + 1); goto exit; } diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index 3882f3c7608..de47f170ba5 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -96,7 +96,7 @@ void __init omap4_pmic_init(const char *pmic_type, void __init omap_pmic_late_init(void) { - /* Init the OMAP TWL parameters (if PMIC has been registerd) */ + /* Init the OMAP TWL parameters (if PMIC has been registered) */ if (pmic_i2c_board_info.irq) omap3_twl_init(); if (omap4_i2c1_board_info[0].irq) diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 84461fa2a3b..a310222951d 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -25,6 +25,7 @@ #include <linux/mfd/tc3589x.h> #include <linux/mfd/tps6105x.h> #include <linux/mfd/abx500/ab8500-gpio.h> +#include <linux/mfd/abx500/ab8500-codec.h> #include <linux/leds-lp5521.h> #include <linux/input.h> #include <linux/smsc911x.h> @@ -97,6 +98,18 @@ static struct ab8500_gpio_platform_data ab8500_gpio_pdata = { 0x7A, 0x00, 0x00}, }; +/* ab8500-codec */ +static struct ab8500_codec_platform_data ab8500_codec_pdata = { + .amics = { + .mic1_type = AMIC_TYPE_DIFFERENTIAL, + .mic2_type = AMIC_TYPE_DIFFERENTIAL, + .mic1a_micbias = AMIC_MICBIAS_VAMIC1, + .mic1b_micbias = AMIC_MICBIAS_VAMIC1, + .mic2_micbias = AMIC_MICBIAS_VAMIC2 + }, + .ear_cmv = EAR_CMV_0_95V +}; + static struct gpio_keys_button snowball_key_array[] = { { .gpio = 32, @@ -195,6 +208,7 @@ static struct ab8500_platform_data ab8500_platdata = { .regulator = ab8500_regulators, .num_regulator = ARRAY_SIZE(ab8500_regulators), .gpio = &ab8500_gpio_pdata, + .codec = &ab8500_codec_pdata, }; static struct resource ab8500_resources[] = { diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h index df8155b9d4d..08740eed050 100644 --- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h +++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h @@ -24,7 +24,7 @@ #ifndef __PLAT_GPIO_CFG_H #define __PLAT_GPIO_CFG_H __FILE__ -#include<linux/types.h> +#include <linux/types.h> typedef unsigned int __bitwise__ samsung_gpio_pull_t; typedef unsigned int __bitwise__ s5p_gpio_drvstr_t; diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index fef96f47876..9b765107e15 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -352,6 +352,11 @@ config MEM_MT48H32M16LFCJ_75 depends on (BFIN526_EZBRD) default y +config MEM_MT47H64M16 + bool + depends on (BFIN609_EZKIT) + default y + source "arch/blackfin/mach-bf518/Kconfig" source "arch/blackfin/mach-bf527/Kconfig" source "arch/blackfin/mach-bf533/Kconfig" @@ -399,8 +404,9 @@ config ROM_BASE hex "Kernel ROM Base" depends on ROMKERNEL default "0x20040040" - range 0x20000000 0x20400000 if !(BF54x || BF561) + range 0x20000000 0x20400000 if !(BF54x || BF561 || BF60x) range 0x20000000 0x30000000 if (BF54x || BF561) + range 0xB0000000 0xC0000000 if (BF60x) help Make sure your ROM base does not include any file-header information that is prepended to the kernel. @@ -1009,6 +1015,12 @@ config HAVE_PWM choice prompt "Uncached DMA region" default DMA_UNCACHED_1M +config DMA_UNCACHED_32M + bool "Enable 32M DMA region" +config DMA_UNCACHED_16M + bool "Enable 16M DMA region" +config DMA_UNCACHED_8M + bool "Enable 8M DMA region" config DMA_UNCACHED_4M bool "Enable 4M DMA region" config DMA_UNCACHED_2M @@ -1038,7 +1050,7 @@ config BFIN_EXTMEM_ICACHEABLE config BFIN_L2_ICACHEABLE bool "Enable ICACHE for L2 SRAM" depends on BFIN_ICACHE - depends on BF54x || BF561 + depends on (BF54x || BF561 || BF60x) && !SMP default n config BFIN_DCACHE diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig index be9526bee4f..f4b02350e41 100644 --- a/arch/blackfin/configs/BF609-EZKIT_defconfig +++ b/arch/blackfin/configs/BF609-EZKIT_defconfig @@ -90,6 +90,7 @@ CONFIG_INPUT_BFIN_ROTARY=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set CONFIG_BFIN_SIMPLE_TIMER=m +# CONFIG_BFIN_CRC is not set CONFIG_BFIN_LINKPORT=y # CONFIG_DEVKMEM is not set CONFIG_SERIAL_BFIN=y @@ -153,3 +154,4 @@ CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_ARC4=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_BFIN_CRC=y diff --git a/arch/blackfin/include/asm/bfin-global.h b/arch/blackfin/include/asm/bfin-global.h index 608be5e6d25..dc47d79287f 100644 --- a/arch/blackfin/include/asm/bfin-global.h +++ b/arch/blackfin/include/asm/bfin-global.h @@ -14,7 +14,13 @@ #include <linux/linkage.h> #include <linux/types.h> -#if defined(CONFIG_DMA_UNCACHED_4M) +#if defined(CONFIG_DMA_UNCACHED_32M) +# define DMA_UNCACHED_REGION (32 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_16M) +# define DMA_UNCACHED_REGION (16 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_8M) +# define DMA_UNCACHED_REGION (8 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_4M) # define DMA_UNCACHED_REGION (4 * 1024 * 1024) #elif defined(CONFIG_DMA_UNCACHED_2M) # define DMA_UNCACHED_REGION (2 * 1024 * 1024) diff --git a/arch/blackfin/include/asm/bfin_crc.h b/arch/blackfin/include/asm/bfin_crc.h index 3deb4452cee..75cef4dc85a 100644 --- a/arch/blackfin/include/asm/bfin_crc.h +++ b/arch/blackfin/include/asm/bfin_crc.h @@ -79,20 +79,6 @@ struct crc_register { u32 revid; }; -struct bfin_crc { - struct miscdevice mdev; - struct list_head list; - int irq; - int dma_ch_src; - int dma_ch_dest; - volatile struct crc_register *regs; - struct crc_info *info; - struct mutex mutex; - struct completion c; - unsigned short opmode; - char name[20]; -}; - /* CRC_STATUS Masks */ #define CMPERR 0x00000002 /* Compare error */ #define DCNTEXP 0x00000010 /* datacnt register expired */ diff --git a/arch/blackfin/include/asm/bfin_serial.h b/arch/blackfin/include/asm/bfin_serial.h index 8597158010b..2d90d62edc9 100644 --- a/arch/blackfin/include/asm/bfin_serial.h +++ b/arch/blackfin/include/asm/bfin_serial.h @@ -282,7 +282,7 @@ struct bfin_uart_regs { #define UART_GET_GCTL(p) UART_GET_CTL(p) #define UART_GET_LCR(p) UART_GET_CTL(p) #define UART_GET_MCR(p) UART_GET_CTL(p) -#if ANOMALY_05001001 +#if ANOMALY_16000030 #define UART_GET_STAT(p) \ ({ \ u32 __ret; \ diff --git a/arch/blackfin/include/asm/bfin_simple_timer.h b/arch/blackfin/include/asm/bfin_simple_timer.h index aadfb1ad1fa..b2d5e733079 100644 --- a/arch/blackfin/include/asm/bfin_simple_timer.h +++ b/arch/blackfin/include/asm/bfin_simple_timer.h @@ -17,5 +17,11 @@ #define BFIN_SIMPLE_TIMER_START _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 6) #define BFIN_SIMPLE_TIMER_STOP _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 8) #define BFIN_SIMPLE_TIMER_READ _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 10) +#define BFIN_SIMPLE_TIMER_READ_COUNTER _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 11) + +#define BFIN_SIMPLE_TIMER_MODE_PWM_ONESHOT 0 +#define BFIN_SIMPLE_TIMER_MODE_PWMOUT_CONT 1 +#define BFIN_SIMPLE_TIMER_MODE_WDTH_CAP 2 +#define BFIN_SIMPLE_TIMER_MODE_PWMOUT_CONT_NOIRQ 3 #endif diff --git a/arch/blackfin/include/asm/bfin_twi.h b/arch/blackfin/include/asm/bfin_twi.h index 2f3339a4762..f4a07278743 100644 --- a/arch/blackfin/include/asm/bfin_twi.h +++ b/arch/blackfin/include/asm/bfin_twi.h @@ -66,9 +66,9 @@ struct bfin_twi_iface { #define DEFINE_TWI_REG(reg_name, reg) \ static inline u16 read_##reg_name(struct bfin_twi_iface *iface) \ - { return iface->regs_base->reg; } \ + { return bfin_read16(&iface->regs_base->reg); } \ static inline void write_##reg_name(struct bfin_twi_iface *iface, u16 v) \ - { iface->regs_base->reg = v; } + { bfin_write16(&iface->regs_base->reg, v); } DEFINE_TWI_REG(CLKDIV, clkdiv) DEFINE_TWI_REG(CONTROL, control) @@ -84,7 +84,7 @@ DEFINE_TWI_REG(FIFO_CTL, fifo_ctl) DEFINE_TWI_REG(FIFO_STAT, fifo_stat) DEFINE_TWI_REG(XMT_DATA8, xmt_data8) DEFINE_TWI_REG(XMT_DATA16, xmt_data16) -#if !ANOMALY_05001001 +#if !ANOMALY_16000030 DEFINE_TWI_REG(RCV_DATA8, rcv_data8) DEFINE_TWI_REG(RCV_DATA16, rcv_data16) #else @@ -94,7 +94,7 @@ static inline u16 read_RCV_DATA8(struct bfin_twi_iface *iface) unsigned long flags; flags = hard_local_irq_save(); - ret = iface->regs_base->rcv_data8; + ret = bfin_read16(&iface->regs_base->rcv_data8); hard_local_irq_restore(flags); return ret; @@ -106,7 +106,7 @@ static inline u16 read_RCV_DATA16(struct bfin_twi_iface *iface) unsigned long flags; flags = hard_local_irq_save(); - ret = iface->regs_base->rcv_data16; + ret = bfin_read16(&iface->regs_base->rcv_data16); hard_local_irq_restore(flags); return ret; diff --git a/arch/blackfin/include/asm/context.S b/arch/blackfin/include/asm/context.S index 1f9060395a0..507e7aa6a56 100644 --- a/arch/blackfin/include/asm/context.S +++ b/arch/blackfin/include/asm/context.S @@ -396,3 +396,12 @@ call \func; #endif .endm + +#if defined(CONFIG_BFIN_SCRATCH_REG_RETN) +# define EX_SCRATCH_REG RETN +#elif defined(CONFIG_BFIN_SCRATCH_REG_RETE) +# define EX_SCRATCH_REG RETE +#else +# define EX_SCRATCH_REG CYCLES +#endif + diff --git a/arch/blackfin/include/asm/dpmc.h b/arch/blackfin/include/asm/dpmc.h index e91eae8330a..2673b11376f 100644 --- a/arch/blackfin/include/asm/dpmc.h +++ b/arch/blackfin/include/asm/dpmc.h @@ -280,7 +280,7 @@ PM_POP_SYNC(9) #endif -#ifdef EBIU_AMBCTL +#ifdef EBIU_AMGCTL PM_SYS_POP(9, EBIU_AMBCTL1) PM_SYS_POP(8, EBIU_AMBCTL0) PM_SYS_POP16(7, EBIU_AMGCTL) diff --git a/arch/blackfin/include/asm/gpio.h b/arch/blackfin/include/asm/gpio.h index 3d84d96f7c2..98d0133346b 100644 --- a/arch/blackfin/include/asm/gpio.h +++ b/arch/blackfin/include/asm/gpio.h @@ -141,6 +141,8 @@ static inline void bfin_pm_standby_restore(void) void bfin_gpio_pm_hibernate_restore(void); void bfin_gpio_pm_hibernate_suspend(void); +void bfin_pint_suspend(void); +void bfin_pint_resume(void); # if !BFIN_GPIO_PINT int gpio_pm_wakeup_ctrl(unsigned gpio, unsigned ctrl); diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h index 89de539ed01..4ae1144a457 100644 --- a/arch/blackfin/include/asm/irq.h +++ b/arch/blackfin/include/asm/irq.h @@ -20,6 +20,16 @@ /* SYS_IRQS and NR_IRQS are defined in <mach-bf5xx/irq.h> */ #include <mach/irq.h> +/* + * pm save bfin pint registers + */ +struct bfin_pm_pint_save { + u32 mask_set; + u32 assign; + u32 edge_set; + u32 invert_set; +}; + #if ANOMALY_05000244 && defined(CONFIG_BFIN_ICACHE) # define NOP_PAD_ANOMALY_05000244 "nop; nop;" #else diff --git a/arch/blackfin/include/asm/mem_init.h b/arch/blackfin/include/asm/mem_init.h index 237579935e2..f019e9bcefe 100644 --- a/arch/blackfin/include/asm/mem_init.h +++ b/arch/blackfin/include/asm/mem_init.h @@ -6,6 +6,9 @@ * Licensed under the GPL-2 or later. */ +#ifndef __MEM_INIT_H__ +#define __MEM_INIT_H__ + #if defined(EBIU_SDGCTL) #if defined(CONFIG_MEM_MT48LC16M16A2TG_75) || \ defined(CONFIG_MEM_MT48LC64M4A2FB_7E) || \ @@ -277,3 +280,212 @@ #else #define PLL_BYPASS 0 #endif + +#ifdef CONFIG_BF60x + +/* DMC status bits */ +#define IDLE 0x1 +#define MEMINITDONE 0x4 +#define SRACK 0x8 +#define PDACK 0x10 +#define DPDACK 0x20 +#define DLLCALDONE 0x2000 +#define PENDREF 0xF0000 +#define PHYRDPHASE 0xF00000 +#define PHYRDPHASE_OFFSET 20 + +/* DMC control bits */ +#define LPDDR 0x2 +#define INIT 0x4 +#define SRREQ 0x8 +#define PDREQ 0x10 +#define DPDREQ 0x20 +#define PREC 0x40 +#define ADDRMODE 0x100 +#define RDTOWR 0xE00 +#define PPREF 0x1000 +#define DLLCAL 0x2000 + +/* DMC DLL control bits */ +#define DLLCALRDCNT 0xFF +#define DATACYC 0xF00 +#define DATACYC_OFFSET 8 + +/* CGU Divisor bits */ +#define CSEL_OFFSET 0 +#define S0SEL_OFFSET 5 +#define SYSSEL_OFFSET 8 +#define S1SEL_OFFSET 13 +#define DSEL_OFFSET 16 +#define OSEL_OFFSET 22 +#define ALGN 0x20000000 +#define UPDT 0x40000000 +#define LOCK 0x80000000 + +/* CGU Status bits */ +#define PLLEN 0x1 +#define PLLBP 0x2 +#define PLOCK 0x4 +#define CLKSALGN 0x8 + +/* CGU Control bits */ +#define MSEL_MASK 0x7F00 +#define DF_MASK 0x1 + +struct ddr_config { + u32 ddr_clk; + u32 dmc_ddrctl; + u32 dmc_ddrcfg; + u32 dmc_ddrtr0; + u32 dmc_ddrtr1; + u32 dmc_ddrtr2; + u32 dmc_ddrmr; + u32 dmc_ddrmr1; +}; + +#if defined(CONFIG_MEM_MT47H64M16) +static struct ddr_config ddr_config_table[] __attribute__((section(".data_l1"))) = { + [0] = { + .ddr_clk = 125, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20705212, + .dmc_ddrtr1 = 0x201003CF, + .dmc_ddrtr2 = 0x00320107, + .dmc_ddrmr = 0x00000422, + .dmc_ddrmr1 = 0x4, + }, + [1] = { + .ddr_clk = 133, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20806313, + .dmc_ddrtr1 = 0x2013040D, + .dmc_ddrtr2 = 0x00320108, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [2] = { + .ddr_clk = 150, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20A07323, + .dmc_ddrtr1 = 0x20160492, + .dmc_ddrtr2 = 0x00320209, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [3] = { + .ddr_clk = 166, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20A07323, + .dmc_ddrtr1 = 0x2016050E, + .dmc_ddrtr2 = 0x00320209, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [4] = { + .ddr_clk = 200, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20a07323, + .dmc_ddrtr1 = 0x2016050f, + .dmc_ddrtr2 = 0x00320509, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [5] = { + .ddr_clk = 225, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20E0A424, + .dmc_ddrtr1 = 0x302006DB, + .dmc_ddrtr2 = 0x0032020D, + .dmc_ddrmr = 0x00000842, + .dmc_ddrmr1 = 0x4, + }, + [6] = { + .ddr_clk = 250, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20E0A424, + .dmc_ddrtr1 = 0x3020079E, + .dmc_ddrtr2 = 0x0032020D, + .dmc_ddrmr = 0x00000842, + .dmc_ddrmr1 = 0x4, + }, +}; +#endif + +static inline void dmc_enter_self_refresh(void) +{ + if (bfin_read_DMC0_STAT() & MEMINITDONE) { + bfin_write_DMC0_CTL(bfin_read_DMC0_CTL() | SRREQ); + while (!(bfin_read_DMC0_STAT() & SRACK)) + continue; + } +} + +static inline void dmc_exit_self_refresh(void) +{ + if (bfin_read_DMC0_STAT() & MEMINITDONE) { + bfin_write_DMC0_CTL(bfin_read_DMC0_CTL() & ~SRREQ); + while (bfin_read_DMC0_STAT() & SRACK) + continue; + } +} + +static inline void init_cgu(u32 cgu_div, u32 cgu_ctl) +{ + dmc_enter_self_refresh(); + + /* Don't set the same value of MSEL and DF to CGU_CTL */ + if ((bfin_read32(CGU0_CTL) & (MSEL_MASK | DF_MASK)) + != cgu_ctl) { + bfin_write32(CGU0_DIV, cgu_div); + bfin_write32(CGU0_CTL, cgu_ctl); + while ((bfin_read32(CGU0_STAT) & (CLKSALGN | PLLBP)) || + !(bfin_read32(CGU0_STAT) & PLOCK)) + continue; + } + + bfin_write32(CGU0_DIV, cgu_div | UPDT); + while (bfin_read32(CGU0_STAT) & CLKSALGN) + continue; + + dmc_exit_self_refresh(); +} + +static inline void init_dmc(u32 dmc_clk) +{ + int i, dlldatacycle, dll_ctl; + + for (i = 0; i < 7; i++) { + if (ddr_config_table[i].ddr_clk == dmc_clk) { + bfin_write_DMC0_CFG(ddr_config_table[i].dmc_ddrcfg); + bfin_write_DMC0_TR0(ddr_config_table[i].dmc_ddrtr0); + bfin_write_DMC0_TR1(ddr_config_table[i].dmc_ddrtr1); + bfin_write_DMC0_TR2(ddr_config_table[i].dmc_ddrtr2); + bfin_write_DMC0_MR(ddr_config_table[i].dmc_ddrmr); + bfin_write_DMC0_EMR1(ddr_config_table[i].dmc_ddrmr1); + bfin_write_DMC0_CTL(ddr_config_table[i].dmc_ddrctl); + break; + } + } + + while (!(bfin_read_DMC0_STAT() & MEMINITDONE)) + continue; + + dlldatacycle = (bfin_read_DMC0_STAT() & PHYRDPHASE) >> PHYRDPHASE_OFFSET; + dll_ctl = bfin_read_DMC0_DLLCTL(); + dll_ctl &= ~DATACYC; + bfin_write_DMC0_DLLCTL(dll_ctl | (dlldatacycle << DATACYC_OFFSET)); + + while (!(bfin_read_DMC0_STAT() & DLLCALDONE)) + continue; +} +#endif + +#endif /*__MEM_INIT_H__*/ + diff --git a/arch/blackfin/include/asm/traps.h b/arch/blackfin/include/asm/traps.h index 70c4e511cae..cec771b8100 100644 --- a/arch/blackfin/include/asm/traps.h +++ b/arch/blackfin/include/asm/traps.h @@ -125,5 +125,7 @@ level " for Supervisor use: Supervisor only registers, all MMRs, and Supervisor\n" \ level " only instructions.\n" +extern void double_fault_c(struct pt_regs *fp); + #endif /* __ASSEMBLY__ */ #endif /* _BFIN_TRAPS_H */ diff --git a/arch/blackfin/kernel/bfin_dma.c b/arch/blackfin/kernel/bfin_dma.c index c166939ffb2..4a32f2dd5dd 100644 --- a/arch/blackfin/kernel/bfin_dma.c +++ b/arch/blackfin/kernel/bfin_dma.c @@ -45,7 +45,7 @@ static int __init blackfin_dma_init(void) atomic_set(&dma_ch[i].chan_status, 0); dma_ch[i].regs = dma_io_base_addr[i]; } -#ifdef CH_MEM_STREAM3_SRC +#if defined(CH_MEM_STREAM3_SRC) && defined(CONFIG_BF60x) /* Mark MEMDMA Channel 3 as requested since we're using it internally */ request_dma(CH_MEM_STREAM3_DEST, "Blackfin dma_memcpy"); request_dma(CH_MEM_STREAM3_SRC, "Blackfin dma_memcpy"); @@ -361,7 +361,7 @@ void __init early_dma_memcpy_done(void) __builtin_bfin_ssync(); } -#ifdef CH_MEM_STREAM3_SRC +#if defined(CH_MEM_STREAM3_SRC) && defined(CONFIG_BF60x) #define bfin_read_MDMA_S_CONFIG bfin_read_MDMA_S3_CONFIG #define bfin_write_MDMA_S_CONFIG bfin_write_MDMA_S3_CONFIG #define bfin_write_MDMA_S_START_ADDR bfin_write_MDMA_S3_START_ADDR diff --git a/arch/blackfin/kernel/cplb-nompu/cplbinit.c b/arch/blackfin/kernel/cplb-nompu/cplbinit.c index 3e366dc2d6e..34e96ce02aa 100644 --- a/arch/blackfin/kernel/cplb-nompu/cplbinit.c +++ b/arch/blackfin/kernel/cplb-nompu/cplbinit.c @@ -58,12 +58,20 @@ void __init generate_cplb_tables_cpu(unsigned int cpu) #ifdef CONFIG_ROMKERNEL /* Cover kernel XIP flash area */ +#ifdef CONFIG_BF60x + addr = CONFIG_ROM_BASE & ~(16 * 1024 * 1024 - 1); + d_tbl[i_d].addr = addr; + d_tbl[i_d++].data = SDRAM_DGENERIC | PAGE_SIZE_16MB; + i_tbl[i_i].addr = addr; + i_tbl[i_i++].data = SDRAM_IGENERIC | PAGE_SIZE_16MB; +#else addr = CONFIG_ROM_BASE & ~(4 * 1024 * 1024 - 1); d_tbl[i_d].addr = addr; d_tbl[i_d++].data = SDRAM_DGENERIC | PAGE_SIZE_4MB; i_tbl[i_i].addr = addr; i_tbl[i_i++].data = SDRAM_IGENERIC | PAGE_SIZE_4MB; #endif +#endif /* Cover L1 memory. One 4M area for code and data each is enough. */ if (cpu == 0) { diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c index f0d1118f182..e7be6532d6a 100644 --- a/arch/blackfin/kernel/dma-mapping.c +++ b/arch/blackfin/kernel/dma-mapping.c @@ -122,12 +122,13 @@ void __dma_sync(dma_addr_t addr, size_t size, EXPORT_SYMBOL(__dma_sync); int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sg_list, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nents; i++, sg++) { + for_each_sg(sg_list, sg, nents, i) { sg->dma_address = (dma_addr_t) sg_virt(sg); __dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction); } @@ -136,12 +137,13 @@ dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, } EXPORT_SYMBOL(dma_map_sg); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg_list, int nelems, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nelems; i++, sg++) { + for_each_sg(sg_list, sg, nelems, i) { sg->dma_address = (dma_addr_t) sg_virt(sg); __dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction); } diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c index af732eb3a68..fc179ca0779 100644 --- a/arch/blackfin/mach-bf527/boards/ezkit.c +++ b/arch/blackfin/mach-bf527/boards/ezkit.c @@ -114,9 +114,9 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#if defined(CONFIG_USB_MUSB_OTG) +#if defined(CONFIG_USB_MUSB_HDRC) && defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_OTG, -#elif defined(CONFIG_USB_MUSB_HDRC_HCD) +#elif defined(CONFIG_USB_MUSB_HDRC) .mode = MUSB_HOST, #elif defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_PERIPHERAL, diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c index c9d9473a5ab..5ed654ae66e 100644 --- a/arch/blackfin/mach-bf537/boards/stamp.c +++ b/arch/blackfin/mach-bf537/boards/stamp.c @@ -873,7 +873,7 @@ static struct adf702x_platform_data adf7021_platform_data = { }; static inline void adf702x_mac_init(void) { - random_ether_addr(adf7021_platform_data.mac_addr); + eth_random_addr(adf7021_platform_data.mac_addr); } #else static inline void adf702x_mac_init(void) {} diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c index 3bd75bae750..c4d07f04094 100644 --- a/arch/blackfin/mach-bf548/boards/ezkit.c +++ b/arch/blackfin/mach-bf548/boards/ezkit.c @@ -635,9 +635,9 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#if defined(CONFIG_USB_MUSB_OTG) +#if defined(CONFIG_USB_MUSB_HDRC) && defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_OTG, -#elif defined(CONFIG_USB_MUSB_HDRC_HCD) +#elif defined(CONFIG_USB_MUSB_HDRC) .mode = MUSB_HOST, #elif defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_PERIPHERAL, diff --git a/arch/blackfin/mach-bf548/include/mach/gpio.h b/arch/blackfin/mach-bf548/include/mach/gpio.h index 35c8ced4615..be9edb28f96 100644 --- a/arch/blackfin/mach-bf548/include/mach/gpio.h +++ b/arch/blackfin/mach-bf548/include/mach/gpio.h @@ -171,6 +171,8 @@ #define MAX_BLACKFIN_GPIOS 160 #define BFIN_GPIO_PINT 1 +#define NR_PINT_SYS_IRQS 4 +#define NR_PINTS 160 #ifndef __ASSEMBLY__ diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index 838978808a1..7c36777c645 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -452,18 +452,21 @@ static struct v4l2_input adv7183_inputs[] = { .name = "Composite", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, { .index = 1, .name = "S-Video", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, { .index = 2, .name = "Component", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, }; diff --git a/arch/blackfin/mach-bf609/Kconfig b/arch/blackfin/mach-bf609/Kconfig index 2cb72724377..101b33ee9bb 100644 --- a/arch/blackfin/mach-bf609/Kconfig +++ b/arch/blackfin/mach-bf609/Kconfig @@ -51,6 +51,14 @@ config PINT5_ASSIGN endmenu +config SEC_IRQ_PRIORITY_LEVELS + int "SEC interrupt priority levels" + default 7 + range 0 7 + help + Devide the total number of interrupt priority levels into sub-levels. + There is 2 ^ (SEC_IRQ_PRIORITY_LEVELS + 1) different levels. + endmenu endif diff --git a/arch/blackfin/mach-bf609/Makefile b/arch/blackfin/mach-bf609/Makefile index 2a27f817454..234fe1b4bb0 100644 --- a/arch/blackfin/mach-bf609/Makefile +++ b/arch/blackfin/mach-bf609/Makefile @@ -2,5 +2,5 @@ # arch/blackfin/mach-bf609/Makefile # -obj-y := dma.o clock.o -obj-$(CONFIG_PM) += pm.o hibernate.o +obj-y := dma.o clock.o ints-priority.o +obj-$(CONFIG_PM) += pm.o dpm.o diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c index ac64f47217c..c2cf1ae3118 100644 --- a/arch/blackfin/mach-bf609/boards/ezkit.c +++ b/arch/blackfin/mach-bf609/boards/ezkit.c @@ -677,11 +677,28 @@ int bf609_nor_flash_init(struct platform_device *dev) return 0; } +void bf609_nor_flash_exit(struct platform_device *dev) +{ + const unsigned short pins[] = { + P_A3, P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12, + P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21, + P_A22, P_A23, P_A24, P_A25, P_NORCK, 0, + }; + + peripheral_free_list(pins); + + bfin_write32(SMC_GCTL, 0); +} + static struct physmap_flash_data ezkit_flash_data = { .width = 2, .parts = ezkit_partitions, - .init = bf609_nor_flash_init, + .init = bf609_nor_flash_init, + .exit = bf609_nor_flash_exit, .nr_parts = ARRAY_SIZE(ezkit_partitions), +#ifdef CONFIG_ROMKERNEL + .probe_type = "map_rom", +#endif }; static struct resource ezkit_flash_resource = { @@ -739,7 +756,7 @@ static struct bfin6xx_spi_chip spidev_chip_info = { }; #endif -#if defined(CONFIG_SND_BF6XX_I2S) || defined(CONFIG_SND_BF6XX_I2S_MODULE) +#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) static struct platform_device bfin_i2s_pcm = { .name = "bfin-i2s-pcm-audio", .id = -1, @@ -825,6 +842,12 @@ static struct adau1761_platform_data adau1761_info = { static const unsigned short ppi_req[] = { P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3, P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7, + P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11, + P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15, +#if !defined(CONFIG_VIDEO_VS6624) && !defined(CONFIG_VIDEO_VS6624_MODULE) + P_PPI0_D16, P_PPI0_D17, P_PPI0_D18, P_PPI0_D19, + P_PPI0_D20, P_PPI0_D21, P_PPI0_D22, P_PPI0_D23, +#endif P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, 0, }; @@ -855,7 +878,7 @@ static struct bcap_route vs6624_routes[] = { }, }; -static const unsigned vs6624_ce_pin = GPIO_PD1; +static const unsigned vs6624_ce_pin = GPIO_PE4; static struct bfin_capture_config bfin_capture_data = { .card_name = "BF609", @@ -871,7 +894,128 @@ static struct bfin_capture_config bfin_capture_data = { .ppi_info = &ppi_info, .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FS1HI_FS2HI | EPPI_CTL_POLC3 | EPPI_CTL_SYNC2 | EPPI_CTL_NON656), - .blank_clocks = 8, + .blank_pixels = 4, +}; +#endif + +#if defined(CONFIG_VIDEO_ADV7842) \ + || defined(CONFIG_VIDEO_ADV7842_MODULE) +#include <media/adv7842.h> + +static struct v4l2_input adv7842_inputs[] = { + { + .index = 0, + .name = "Composite", + .type = V4L2_INPUT_TYPE_CAMERA, + .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, + }, + { + .index = 1, + .name = "S-Video", + .type = V4L2_INPUT_TYPE_CAMERA, + .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, + }, + { + .index = 2, + .name = "Component", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, + { + .index = 3, + .name = "VGA", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, + { + .index = 4, + .name = "HDMI", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, +}; + +static struct bcap_route adv7842_routes[] = { + { + .input = 3, + .output = 0, + .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FLDSEL + | EPPI_CTL_ACTIVE656), + }, + { + .input = 4, + .output = 0, + }, + { + .input = 2, + .output = 0, + }, + { + .input = 1, + .output = 0, + }, + { + .input = 0, + .output = 1, + .ppi_control = (EPPI_CTL_SPLTWRD | PACK_EN | DLEN_16 + | EPPI_CTL_FS1LO_FS2LO | EPPI_CTL_POLC2 + | EPPI_CTL_SYNC2 | EPPI_CTL_NON656), + }, +}; + +static struct adv7842_output_format adv7842_opf[] = { + { + .op_ch_sel = ADV7842_OP_CH_SEL_BRG, + .op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_8, + .op_656_range = 1, + .blank_data = 1, + .insert_av_codes = 1, + }, + { + .op_ch_sel = ADV7842_OP_CH_SEL_RGB, + .op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_16, + .op_656_range = 1, + .blank_data = 1, + }, +}; + +static struct adv7842_platform_data adv7842_data = { + .opf = adv7842_opf, + .num_opf = ARRAY_SIZE(adv7842_opf), + .ain_sel = ADV7842_AIN10_11_12_NC_SYNC_4_1, + .prim_mode = ADV7842_PRIM_MODE_SDP, + .vid_std_select = ADV7842_SDP_VID_STD_CVBS_SD_4x1, + .inp_color_space = ADV7842_INP_COLOR_SPACE_AUTO, + .i2c_sdp_io = 0x40, + .i2c_sdp = 0x41, + .i2c_cp = 0x42, + .i2c_vdp = 0x43, + .i2c_afe = 0x44, + .i2c_hdmi = 0x45, + .i2c_repeater = 0x46, + .i2c_edid = 0x47, + .i2c_infoframe = 0x48, + .i2c_cec = 0x49, + .i2c_avlink = 0x4a, + .i2c_ex = 0x26, +}; + +static struct bfin_capture_config bfin_capture_data = { + .card_name = "BF609", + .inputs = adv7842_inputs, + .num_inputs = ARRAY_SIZE(adv7842_inputs), + .routes = adv7842_routes, + .i2c_adapter_id = 0, + .board_info = { + .type = "adv7842", + .addr = 0x20, + .platform_data = (void *)&adv7842_data, + }, + .ppi_info = &ppi_info, + .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FLDSEL + | EPPI_CTL_ACTIVE656), }; #endif @@ -883,6 +1027,80 @@ static struct platform_device bfin_capture_device = { }; #endif +#if defined(CONFIG_VIDEO_BLACKFIN_DISPLAY) \ + || defined(CONFIG_VIDEO_BLACKFIN_DISPLAY_MODULE) +#include <linux/videodev2.h> +#include <media/blackfin/bfin_display.h> +#include <media/blackfin/ppi.h> + +static const unsigned short ppi_req_disp[] = { + P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3, + P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7, + P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11, + P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15, + P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, + 0, +}; + +static const struct ppi_info ppi_info = { + .type = PPI_TYPE_EPPI3, + .dma_ch = CH_EPPI0_CH0, + .irq_err = IRQ_EPPI0_STAT, + .base = (void __iomem *)EPPI0_STAT, + .pin_req = ppi_req_disp, +}; + +#if defined(CONFIG_VIDEO_ADV7511) \ + || defined(CONFIG_VIDEO_ADV7511_MODULE) +#include <media/adv7511.h> + +static struct v4l2_output adv7511_outputs[] = { + { + .index = 0, + .name = "HDMI", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_OUT_CAP_CUSTOM_TIMINGS, + }, +}; + +static struct disp_route adv7511_routes[] = { + { + .output = 0, + }, +}; + +static struct adv7511_platform_data adv7511_data = { + .edid_addr = 0x7e, + .i2c_ex = 0x25, +}; + +static struct bfin_display_config bfin_display_data = { + .card_name = "BF609", + .outputs = adv7511_outputs, + .num_outputs = ARRAY_SIZE(adv7511_outputs), + .routes = adv7511_routes, + .i2c_adapter_id = 0, + .board_info = { + .type = "adv7511", + .addr = 0x39, + .platform_data = (void *)&adv7511_data, + }, + .ppi_info = &ppi_info, + .ppi_control = (EPPI_CTL_SPLTWRD | PACK_EN | DLEN_16 + | EPPI_CTL_FS1LO_FS2LO | EPPI_CTL_POLC3 + | EPPI_CTL_IFSGEN | EPPI_CTL_SYNC2 + | EPPI_CTL_NON656 | EPPI_CTL_DIR), +}; +#endif + +static struct platform_device bfin_display_device = { + .name = "bfin_display", + .dev = { + .platform_data = &bfin_display_data, + }, +}; +#endif + #if defined(CONFIG_BFIN_CRC) #define BFIN_CRC_NAME "bfin-crc" @@ -947,6 +1165,39 @@ static struct platform_device bfin_crc1_device = { }; #endif +#if defined(CONFIG_CRYPTO_DEV_BFIN_CRC) +#define BFIN_CRYPTO_CRC_NAME "bfin-hmac-crc" +#define BFIN_CRYPTO_CRC_POLY_DATA 0x5c5c5c5c + +static struct resource bfin_crypto_crc_resources[] = { + { + .start = REG_CRC0_CTL, + .end = REG_CRC0_REVID+4, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_CRC0_DCNTEXP, + .end = IRQ_CRC0_DCNTEXP, + .flags = IORESOURCE_IRQ, + }, + { + .start = CH_MEM_STREAM0_SRC_CRC0, + .end = CH_MEM_STREAM0_SRC_CRC0, + .flags = IORESOURCE_DMA, + }, +}; + +static struct platform_device bfin_crypto_crc_device = { + .name = BFIN_CRYPTO_CRC_NAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_crypto_crc_resources), + .resource = bfin_crypto_crc_resources, + .dev = { + .platform_data = (void *)BFIN_CRYPTO_CRC_POLY_DATA, + }, +}; +#endif + #if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) static const struct ad7877_platform_data bfin_ad7877_ts_info = { .model = 7877, @@ -963,6 +1214,28 @@ static const struct ad7877_platform_data bfin_ad7877_ts_info = { }; #endif +#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) +#include <linux/input.h> +#include <linux/gpio_keys.h> + +static struct gpio_keys_button bfin_gpio_keys_table[] = { + {BTN_0, GPIO_PB10, 1, "gpio-keys: BTN0"}, + {BTN_1, GPIO_PE1, 1, "gpio-keys: BTN1"}, +}; + +static struct gpio_keys_platform_data bfin_gpio_keys_data = { + .buttons = bfin_gpio_keys_table, + .nbuttons = ARRAY_SIZE(bfin_gpio_keys_table), +}; + +static struct platform_device bfin_device_gpiokeys = { + .name = "gpio-keys", + .dev = { + .platform_data = &bfin_gpio_keys_data, + }, +}; +#endif + static struct spi_board_info bfin_spi_board_info[] __initdata = { #if defined(CONFIG_MTD_M25P80) \ || defined(CONFIG_MTD_M25P80_MODULE) @@ -981,10 +1254,10 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { { .modalias = "ad7877", .platform_data = &bfin_ad7877_ts_info, - .irq = IRQ_PB4, /* old boards (<=Rev 1.3) use IRQ_PJ11 */ + .irq = IRQ_PD9, .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 2, + .chip_select = 4, }, #endif #if defined(CONFIG_SPI_SPIDEV) || defined(CONFIG_SPI_SPIDEV_MODULE) @@ -1050,7 +1323,7 @@ static struct resource bfin_spi1_resource[] = { /* SPI controller data */ static struct bfin6xx_spi_master bf60x_spi_master_info0 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .pin_req = {P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0}, }; @@ -1065,7 +1338,7 @@ static struct platform_device bf60x_spi_master0 = { }; static struct bfin6xx_spi_master bf60x_spi_master_info1 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .pin_req = {P_SPI1_SCK, P_SPI1_MISO, P_SPI1_MOSI, 0}, }; @@ -1146,6 +1419,11 @@ static struct i2c_board_info __initdata bfin_i2c_board_info0[] = { .platform_data = (void *)&adau1761_info }, #endif +#if defined(CONFIG_SND_SOC_SSM2602) || defined(CONFIG_SND_SOC_SSM2602_MODULE) + { + I2C_BOARD_INFO("ssm2602", 0x1b), + }, +#endif }; static struct i2c_board_info __initdata bfin_i2c_board_info1[] = { @@ -1261,6 +1539,9 @@ static struct platform_device *ezkit_devices[] __initdata = { &bfin_crc0_device, &bfin_crc1_device, #endif +#if defined(CONFIG_CRYPTO_DEV_BFIN_CRC) + &bfin_crypto_crc_device, +#endif #if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) &bfin_device_gpiokeys, @@ -1269,7 +1550,7 @@ static struct platform_device *ezkit_devices[] __initdata = { #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) &ezkit_flash_device, #endif -#if defined(CONFIG_SND_BF6XX_I2S) || defined(CONFIG_SND_BF6XX_I2S_MODULE) +#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) &bfin_i2s_pcm, #endif #if defined(CONFIG_SND_BF6XX_SOC_I2S) || \ @@ -1284,6 +1565,11 @@ static struct platform_device *ezkit_devices[] __initdata = { || defined(CONFIG_VIDEO_BLACKFIN_CAPTURE_MODULE) &bfin_capture_device, #endif +#if defined(CONFIG_VIDEO_BLACKFIN_DISPLAY) \ + || defined(CONFIG_VIDEO_BLACKFIN_DISPLAY_MODULE) + &bfin_display_device, +#endif + }; static int __init ezkit_init(void) diff --git a/arch/blackfin/mach-bf609/clock.c b/arch/blackfin/mach-bf609/clock.c index 7f8f529693a..437d56c8228 100644 --- a/arch/blackfin/mach-bf609/clock.c +++ b/arch/blackfin/mach-bf609/clock.c @@ -97,9 +97,10 @@ int wait_for_pll_align(void) while (i-- && (bfin_read32(CGU0_STAT) & CGU0_STAT_CLKSALGN)); if (bfin_read32(CGU0_STAT) & CGU0_STAT_CLKSALGN) { - printk(KERN_DEBUG "fail to align clk\n"); + printk(KERN_CRIT "fail to align clk\n"); return -1; } + return 0; } diff --git a/arch/blackfin/mach-bf609/dpm.S b/arch/blackfin/mach-bf609/dpm.S new file mode 100644 index 00000000000..54d50c689db --- /dev/null +++ b/arch/blackfin/mach-bf609/dpm.S @@ -0,0 +1,157 @@ +#include <linux/linkage.h> +#include <asm/blackfin.h> +#include <asm/dpmc.h> + +#include <asm/context.S> + +#define PM_STACK (COREA_L1_SCRATCH_START + L1_SCRATCH_LENGTH - 12) + +.section .l1.text +ENTRY(_enter_hibernate) + /* switch stack to L1 scratch, prepare for ddr srfr */ + P0.H = HI(PM_STACK); + P0.L = LO(PM_STACK); + SP = P0; + + call _bf609_ddr_sr; + call _bfin_hibernate_syscontrol; + + P0.H = HI(DPM0_RESTORE4); + P0.L = LO(DPM0_RESTORE4); + P1.H = _bf609_pm_data; + P1.L = _bf609_pm_data; + [P0] = P1; + + P0.H = HI(DPM0_CTL); + P0.L = LO(DPM0_CTL); + R3.H = HI(0x00000010); + R3.L = LO(0x00000010); + + bfin_init_pm_bench_cycles; + + [P0] = R3; + + SSYNC; +ENDPROC(_enter_hibernate) + +/* DPM wake up interrupt won't wake up core on bf60x if its core IMASK + * is disabled. This behavior differ from bf5xx serial processor. + */ +ENTRY(_dummy_deepsleep) + [--sp] = SYSCFG; + [--sp] = (R7:0,P5:0); + cli r0; + + /* get wake up interrupt ID */ + P0.l = LO(SEC_SCI_BASE + SEC_CSID); + P0.h = HI(SEC_SCI_BASE + SEC_CSID); + R0 = [P0]; + + /* ACK wake up interrupt in SEC */ + P1.l = LO(SEC_END); + P1.h = HI(SEC_END); + + [P1] = R0; + SSYNC; + + /* restore EVT 11 entry */ + p0.h = hi(EVT11); + p0.l = lo(EVT11); + p1.h = _evt_evt11; + p1.l = _evt_evt11; + + [p0] = p1; + SSYNC; + + (R7:0,P5:0) = [sp++]; + SYSCFG = [sp++]; + RTI; +ENDPROC(_dummy_deepsleep) + +ENTRY(_enter_deepsleep) + LINK 0xC; + [--sp] = (R7:0,P5:0); + + /* Change EVT 11 entry to dummy handler for wake up event */ + p0.h = hi(EVT11); + p0.l = lo(EVT11); + p1.h = _dummy_deepsleep; + p1.l = _dummy_deepsleep; + + [p0] = p1; + + P0.H = HI(PM_STACK); + P0.L = LO(PM_STACK); + + EX_SCRATCH_REG = SP; + SP = P0; + + SSYNC; + + /* should put ddr to self refresh mode before sleep */ + call _bf609_ddr_sr; + + /* Set DPM controller to deep sleep mode */ + P0.H = HI(DPM0_CTL); + P0.L = LO(DPM0_CTL); + R3.H = HI(0x00000008); + R3.L = LO(0x00000008); + [P0] = R3; + CSYNC; + + /* Enable evt 11 in IMASK before idle, otherwise core doesn't wake up. */ + r0.l = 0x800; + r0.h = 0; + sti r0; + SSYNC; + + bfin_init_pm_bench_cycles; + + /* Fall into deep sleep in idle*/ + idle; + SSYNC; + + /* Restore PLL after wake up from deep sleep */ + call _bf609_resume_ccbuf; + + /* turn ddr out of self refresh mode */ + call _bf609_ddr_sr_exit; + + SP = EX_SCRATCH_REG; + + (R7:0,P5:0) = [SP++]; + UNLINK; + RTS; +ENDPROC(_enter_deepsleep) + +.section .text +ENTRY(_bf609_hibernate) + bfin_cpu_reg_save; + bfin_core_mmr_save; + + P0.H = _bf609_pm_data; + P0.L = _bf609_pm_data; + R1.H = 0xDEAD; + R1.L = 0xBEEF; + R2.H = .Lpm_resume_here; + R2.L = .Lpm_resume_here; + [P0++] = R1; + [P0++] = R2; + [P0++] = SP; + + P1.H = _enter_hibernate; + P1.L = _enter_hibernate; + + call (P1); +.Lpm_resume_here: + + bfin_core_mmr_restore; + bfin_cpu_reg_restore; + + [--sp] = RETI; /* Clear Global Interrupt Disable */ + SP += 4; + + RTS; + +ENDPROC(_bf609_hibernate) + diff --git a/arch/blackfin/mach-bf609/hibernate.S b/arch/blackfin/mach-bf609/hibernate.S deleted file mode 100644 index d37a532519c..00000000000 --- a/arch/blackfin/mach-bf609/hibernate.S +++ /dev/null @@ -1,65 +0,0 @@ -#include <linux/linkage.h> -#include <asm/blackfin.h> -#include <asm/dpmc.h> - -#define PM_STACK (COREA_L1_SCRATCH_START + L1_SCRATCH_LENGTH - 12) - -.section .l1.text -ENTRY(_enter_hibernate) - /* switch stack to L1 scratch, prepare for ddr srfr */ - P0.H = HI(PM_STACK); - P0.L = LO(PM_STACK); - SP = P0; - - call _bf609_ddr_sr; - call _bfin_hibernate_syscontrol; - - P0.H = HI(DPM0_RESTORE4); - P0.L = LO(DPM0_RESTORE4); - P1.H = _bf609_pm_data; - P1.L = _bf609_pm_data; - [P0] = P1; - - P0.H = HI(DPM0_CTL); - P0.L = LO(DPM0_CTL); - R3.H = HI(0x00000010); - R3.L = LO(0x00000010); - - bfin_init_pm_bench_cycles; - - [P0] = R3; - - SSYNC; -ENDPROC(_enter_hibernate_mode) - -.section .text -ENTRY(_bf609_hibernate) - bfin_cpu_reg_save; - bfin_core_mmr_save; - - P0.H = _bf609_pm_data; - P0.L = _bf609_pm_data; - R1.H = 0xDEAD; - R1.L = 0xBEEF; - R2.H = .Lpm_resume_here; - R2.L = .Lpm_resume_here; - [P0++] = R1; - [P0++] = R2; - [P0++] = SP; - - P1.H = _enter_hibernate; - P1.L = _enter_hibernate; - - call (P1); -.Lpm_resume_here: - - bfin_core_mmr_restore; - bfin_cpu_reg_restore; - - [--sp] = RETI; /* Clear Global Interrupt Disable */ - SP += 4; - - RTS; - -ENDPROC(_bf609_hibernate) - diff --git a/arch/blackfin/mach-bf609/include/mach/anomaly.h b/arch/blackfin/mach-bf609/include/mach/anomaly.h index bdd39aefb56..7a07374308a 100644 --- a/arch/blackfin/mach-bf609/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf609/include/mach/anomaly.h @@ -5,126 +5,99 @@ * and can be replaced with that version at any time * DO NOT EDIT THIS FILE * - * Copyright 2004-2011 Analog Devices Inc. + * Copyright 2004-2012 Analog Devices Inc. * Licensed under the Clear BSD license. */ /* This file should be up to date with: + * - Revision A, 15/06/2012; ADSP-BF609 Blackfin Processor Anomaly List */ #if __SILICON_REVISION__ < 0 -# error will not work on BF506 silicon version +# error will not work on BF609 silicon version #endif #ifndef _MACH_ANOMALY_H_ #define _MACH_ANOMALY_H_ -/* Multi-Issue Instruction with dsp32shiftimm in slot1 and P-reg Store in slot2 Not Supported */ -#define ANOMALY_05000074 (1) -/* DMA_RUN Bit Is Not Valid after a Peripheral Receive Channel DMA Stops */ -#define ANOMALY_05000119 (1) -/* Rx.H Cannot Be Used to Access 16-bit System MMR Registers */ -#define ANOMALY_05000122 (1) -/* False Hardware Error from an Access in the Shadow of a Conditional Branch */ -#define ANOMALY_05000245 (1) -/* Incorrect Timer Pulse Width in Single-Shot PWM_OUT Mode with External Clock */ -#define ANOMALY_05000254 (1) -/* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ -#define ANOMALY_05000265 (1) -/* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ -#define ANOMALY_05000310 (1) -/* PPI Underflow Error Goes Undetected in ITU-R 656 Mode */ -#define ANOMALY_05000366 (1) -/* Speculative Fetches Can Cause Undesired External FIFO Operations */ -#define ANOMALY_05000416 (1) -/* Speculative Fetches of Indirect-Pointer Instructions Can Cause False Hardware Errors */ -#define ANOMALY_05000426 (1) +/* TRU_STAT.ADDRERR and TRU_ERRADDR.ADDR May Not Reflect the Correct Status */ +#define ANOMALY_16000003 (1) +/* The EPPI Data Enable (DEN) Signal is Not Functional */ +#define ANOMALY_16000004 (1) +/* Using L1 Instruction Cache with Parity Enabled is Unreliable */ +#define ANOMALY_16000005 (1) +/* SEQSTAT.SYSNMI Clears Upon Entering the NMI ISR */ +#define ANOMALY_16000006 (1) +/* DDR2 Memory Reads May Fail Intermittently */ +#define ANOMALY_16000007 (1) +/* Instruction Memory Stalls Can Cause IFLUSH to Fail */ +#define ANOMALY_16000008 (1) +/* TestSET Instruction Cannot Be Interrupted */ +#define ANOMALY_16000009 (1) /* IFLUSH Instruction at End of Hardware Loop Causes Infinite Stall */ -#define ANOMALY_05000443 (1) -/* UART IrDA Receiver Fails on Extended Bit Pulses */ -#define ANOMALY_05000447 (1) +#define ANOMALY_16000010 (1) /* False Hardware Error when RETI Points to Invalid Memory */ -#define ANOMALY_05000461 (1) -/* PLL Latches Incorrect Settings During Reset */ -#define ANOMALY_05000469 (1) -/* Incorrect Default MSEL Value in PLL_CTL */ -#define ANOMALY_05000472 (1) -/* Interrupted SPORT Receive Data Register Read Results In Underflow when SLEN > 15 */ -#define ANOMALY_05000473 (1) -/* TESTSET Instruction Cannot Be Interrupted */ -#define ANOMALY_05000477 (1) -/* Reads of ITEST_COMMAND and ITEST_DATA Registers Cause Cache Corruption */ -#define ANOMALY_05000481 (1) -/* IFLUSH sucks at life */ -#define ANOMALY_05000491 (1) -/* Tempopary anomaly ID for data loss in MMR read operation if interrupted */ -#define ANOMALY_05001001 (__SILICON_REVISION__ < 1) +#define ANOMALY_16000011 (1) +/* Speculative Fetches of Indirect-Pointer Instructions Can Cause False Hardware Errors */ +#define ANOMALY_16000012 (1) +/* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ +#define ANOMALY_16000013 (1) +/* False Hardware Error from an Access in the Shadow of a Conditional Branch */ +#define ANOMALY_16000014 (1) +/* Multi-Issue Instruction with dsp32shiftimm in slot1 and P-reg Store in slot2 Not Supported */ +#define ANOMALY_16000015 (1) +/* Speculative Fetches Can Cause Undesired External FIFO Operations */ +#define ANOMALY_16000017 (1) +/* RSI Boot Cleanup Routine Does Not Clear Registers */ +#define ANOMALY_16000018 (1) +/* SPI Master Boot Device Auto-detection Frequency is Set Incorrectly */ +#define ANOMALY_16000019 (1) +/* rom_SysControl() Fails to Set DDR0_CTL.INIT for Wakeup From Hibernate */ +#define ANOMALY_16000020 (1) +/* rom_SysControl() Fails to Save and Restore DDR0_PHYCTL3 for Hibernate/Wakeup Sequence */ +#define ANOMALY_16000021 (1) +/* Boot Code Fails to Enable Parity Fault Detection */ +#define ANOMALY_16000022 (1) +/* USB DMA interrupt status do not show the DMA channel interrupt in the DMA ISR */ +#define ANOMALY_16000027 (1) +/* Interrupted Core Reads of MMRs May Cause Data Loss */ +#define ANOMALY_16000030 (1) /* Anomalies that don't exist on this proc */ -#define ANOMALY_05000099 (0) -#define ANOMALY_05000120 (0) -#define ANOMALY_05000125 (0) -#define ANOMALY_05000149 (0) #define ANOMALY_05000158 (0) -#define ANOMALY_05000171 (0) -#define ANOMALY_05000179 (0) -#define ANOMALY_05000182 (0) -#define ANOMALY_05000183 (0) #define ANOMALY_05000189 (0) #define ANOMALY_05000198 (0) -#define ANOMALY_05000202 (0) -#define ANOMALY_05000215 (0) -#define ANOMALY_05000219 (0) #define ANOMALY_05000220 (0) -#define ANOMALY_05000227 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000231 (0) -#define ANOMALY_05000233 (0) -#define ANOMALY_05000234 (0) -#define ANOMALY_05000242 (0) #define ANOMALY_05000244 (0) -#define ANOMALY_05000248 (0) -#define ANOMALY_05000250 (0) -#define ANOMALY_05000257 (0) -#define ANOMALY_05000261 (0) #define ANOMALY_05000263 (0) -#define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) #define ANOMALY_05000274 (0) #define ANOMALY_05000278 (0) #define ANOMALY_05000281 (0) -#define ANOMALY_05000283 (0) -#define ANOMALY_05000285 (0) #define ANOMALY_05000287 (0) -#define ANOMALY_05000301 (0) -#define ANOMALY_05000305 (0) -#define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) -#define ANOMALY_05000315 (0) #define ANOMALY_05000323 (0) -#define ANOMALY_05000353 (1) -#define ANOMALY_05000357 (0) -#define ANOMALY_05000362 (1) #define ANOMALY_05000363 (0) -#define ANOMALY_05000364 (0) -#define ANOMALY_05000371 (0) #define ANOMALY_05000380 (0) -#define ANOMALY_05000386 (0) -#define ANOMALY_05000389 (0) -#define ANOMALY_05000400 (0) -#define ANOMALY_05000402 (0) -#define ANOMALY_05000412 (0) -#define ANOMALY_05000432 (0) -#define ANOMALY_05000440 (0) #define ANOMALY_05000448 (0) -#define ANOMALY_05000456 (0) #define ANOMALY_05000450 (0) -#define ANOMALY_05000465 (0) -#define ANOMALY_05000467 (0) -#define ANOMALY_05000474 (0) -#define ANOMALY_05000475 (0) +#define ANOMALY_05000456 (0) #define ANOMALY_05000480 (0) -#define ANOMALY_05000485 (0) +#define ANOMALY_05000481 (1) + +/* Reuse BF5xx anomalies IDs for the same anomaly in BF60x */ +#define ANOMALY_05000491 ANOMALY_16000008 +#define ANOMALY_05000477 ANOMALY_16000009 +#define ANOMALY_05000443 ANOMALY_16000010 +#define ANOMALY_05000461 ANOMALY_16000011 +#define ANOMALY_05000426 ANOMALY_16000012 +#define ANOMALY_05000310 ANOMALY_16000013 +#define ANOMALY_05000245 ANOMALY_16000014 +#define ANOMALY_05000074 ANOMALY_16000015 +#define ANOMALY_05000416 ANOMALY_16000017 + #endif diff --git a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h index 6aac38544cc..f1a6afae1a7 100644 --- a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h +++ b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h @@ -2665,7 +2665,6 @@ #define DEVSZ_1G 0x400 /* DMC External Bank Size = 1Gbit */ #define DEVSZ_2G 0x500 /* DMC External Bank Size = 2Gbit */ - /* ========================= L2CTL Registers ========================= */ diff --git a/arch/blackfin/mach-bf609/include/mach/gpio.h b/arch/blackfin/mach-bf609/include/mach/gpio.h index 127586b1e04..c32c8cc8db2 100644 --- a/arch/blackfin/mach-bf609/include/mach/gpio.h +++ b/arch/blackfin/mach-bf609/include/mach/gpio.h @@ -123,6 +123,8 @@ #define BFIN_GPIO_PINT 1 +#define NR_PINT_SYS_IRQS 6 +#define NR_PINTS 112 #ifndef __ASSEMBLY__ diff --git a/arch/blackfin/mach-bf609/include/mach/irq.h b/arch/blackfin/mach-bf609/include/mach/irq.h index 0004552433b..23e74cdeeee 100644 --- a/arch/blackfin/mach-bf609/include/mach/irq.h +++ b/arch/blackfin/mach-bf609/include/mach/irq.h @@ -293,9 +293,13 @@ #define NR_MACH_IRQS (IRQ_PG15 + 1) +#define SEC_SCTL_PRIO_OFFSET 8 + #ifndef __ASSEMBLY__ #include <linux/types.h> +extern u8 sec_int_priority[]; + /* * bfin pint registers layout */ diff --git a/arch/blackfin/mach-bf609/include/mach/pm.h b/arch/blackfin/mach-bf609/include/mach/pm.h index 036d9bdc889..3ca0fb96563 100644 --- a/arch/blackfin/mach-bf609/include/mach/pm.h +++ b/arch/blackfin/mach-bf609/include/mach/pm.h @@ -11,11 +11,14 @@ #include <linux/suspend.h> -int bfin609_pm_enter(suspend_state_t state); -int bf609_pm_prepare(void); -void bf609_pm_finish(void); +extern int bfin609_pm_enter(suspend_state_t state); +extern int bf609_pm_prepare(void); +extern void bf609_pm_finish(void); void bf609_hibernate(void); void bfin_sec_raise_irq(unsigned int sid); void coreb_enable(void); + +int bf609_nor_flash_init(void); +void bf609_nor_flash_exit(void); #endif diff --git a/arch/blackfin/mach-bf609/ints-priority.c b/arch/blackfin/mach-bf609/ints-priority.c new file mode 100644 index 00000000000..f68abb9aa79 --- /dev/null +++ b/arch/blackfin/mach-bf609/ints-priority.c @@ -0,0 +1,156 @@ +/* + * Copyright 2007-2008 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + * + * Set up the interrupt priorities + */ + +#include <linux/module.h> +#include <linux/irq.h> +#include <asm/blackfin.h> + +u8 sec_int_priority[] = { + 255, /* IRQ_SEC_ERR */ + 255, /* IRQ_CGU_EVT */ + 254, /* IRQ_WATCH0 */ + 254, /* IRQ_WATCH1 */ + 253, /* IRQ_L2CTL0_ECC_ERR */ + 253, /* IRQ_L2CTL0_ECC_WARN */ + 253, /* IRQ_C0_DBL_FAULT */ + 253, /* IRQ_C1_DBL_FAULT */ + 252, /* IRQ_C0_HW_ERR */ + 252, /* IRQ_C1_HW_ERR */ + 255, /* IRQ_C0_NMI_L1_PARITY_ERR */ + 255, /* IRQ_C1_NMI_L1_PARITY_ERR */ + + 50, /* IRQ_TIMER0 */ + 50, /* IRQ_TIMER1 */ + 50, /* IRQ_TIMER2 */ + 50, /* IRQ_TIMER3 */ + 50, /* IRQ_TIMER4 */ + 50, /* IRQ_TIMER5 */ + 50, /* IRQ_TIMER6 */ + 50, /* IRQ_TIMER7 */ + 50, /* IRQ_TIMER_STAT */ + 0, /* IRQ_PINT0 */ + 0, /* IRQ_PINT1 */ + 0, /* IRQ_PINT2 */ + 0, /* IRQ_PINT3 */ + 0, /* IRQ_PINT4 */ + 0, /* IRQ_PINT5 */ + 0, /* IRQ_CNT */ + 50, /* RQ_PWM0_TRIP */ + 50, /* IRQ_PWM0_SYNC */ + 50, /* IRQ_PWM1_TRIP */ + 50, /* IRQ_PWM1_SYNC */ + 0, /* IRQ_TWI0 */ + 0, /* IRQ_TWI1 */ + 10, /* IRQ_SOFT0 */ + 10, /* IRQ_SOFT1 */ + 10, /* IRQ_SOFT2 */ + 10, /* IRQ_SOFT3 */ + 0, /* IRQ_ACM_EVT_MISS */ + 0, /* IRQ_ACM_EVT_COMPLETE */ + 0, /* IRQ_CAN0_RX */ + 0, /* IRQ_CAN0_TX */ + 0, /* IRQ_CAN0_STAT */ + 100, /* IRQ_SPORT0_TX */ + 100, /* IRQ_SPORT0_TX_STAT */ + 100, /* IRQ_SPORT0_RX */ + 100, /* IRQ_SPORT0_RX_STAT */ + 100, /* IRQ_SPORT1_TX */ + 100, /* IRQ_SPORT1_TX_STAT */ + 100, /* IRQ_SPORT1_RX */ + 100, /* IRQ_SPORT1_RX_STAT */ + 100, /* IRQ_SPORT2_TX */ + 100, /* IRQ_SPORT2_TX_STAT */ + 100, /* IRQ_SPORT2_RX */ + 100, /* IRQ_SPORT2_RX_STAT */ + 0, /* IRQ_SPI0_TX */ + 0, /* IRQ_SPI0_RX */ + 0, /* IRQ_SPI0_STAT */ + 0, /* IRQ_SPI1_TX */ + 0, /* IRQ_SPI1_RX */ + 0, /* IRQ_SPI1_STAT */ + 0, /* IRQ_RSI */ + 0, /* IRQ_RSI_INT0 */ + 0, /* IRQ_RSI_INT1 */ + 0, /* DMA11 Data (SDU) */ + 0, /* DMA12 Data (Reserved) */ + 0, /* Reserved */ + 0, /* Reserved */ + 30, /* IRQ_EMAC0_STAT */ + 0, /* EMAC0 Power (Reserved) */ + 30, /* IRQ_EMAC1_STAT */ + 0, /* EMAC1 Power (Reserved) */ + 0, /* IRQ_LP0 */ + 0, /* IRQ_LP0_STAT */ + 0, /* IRQ_LP1 */ + 0, /* IRQ_LP1_STAT */ + 0, /* IRQ_LP2 */ + 0, /* IRQ_LP2_STAT */ + 0, /* IRQ_LP3 */ + 0, /* IRQ_LP3_STAT */ + 0, /* IRQ_UART0_TX */ + 0, /* IRQ_UART0_RX */ + 0, /* IRQ_UART0_STAT */ + 0, /* IRQ_UART1_TX */ + 0, /* IRQ_UART1_RX */ + 0, /* IRQ_UART1_STAT */ + 0, /* IRQ_MDMA0_SRC_CRC0 */ + 0, /* IRQ_MDMA0_DEST_CRC0 */ + 0, /* IRQ_CRC0_DCNTEXP */ + 0, /* IRQ_CRC0_ERR */ + 0, /* IRQ_MDMA1_SRC_CRC1 */ + 0, /* IRQ_MDMA1_DEST_CRC1 */ + 0, /* IRQ_CRC1_DCNTEXP */ + 0, /* IRQ_CRC1_ERR */ + 0, /* IRQ_MDMA2_SRC */ + 0, /* IRQ_MDMA2_DEST */ + 0, /* IRQ_MDMA3_SRC */ + 0, /* IRQ_MDMA3_DEST */ + 120, /* IRQ_EPPI0_CH0 */ + 120, /* IRQ_EPPI0_CH1 */ + 120, /* IRQ_EPPI0_STAT */ + 120, /* IRQ_EPPI2_CH0 */ + 120, /* IRQ_EPPI2_CH1 */ + 120, /* IRQ_EPPI2_STAT */ + 120, /* IRQ_EPPI1_CH0 */ + 120, /* IRQ_EPPI1_CH1 */ + 120, /* IRQ_EPPI1_STAT */ + 120, /* IRQ_PIXC_CH0 */ + 120, /* IRQ_PIXC_CH1 */ + 120, /* IRQ_PIXC_CH2 */ + 120, /* IRQ_PIXC_STAT */ + 120, /* IRQ_PVP_CPDOB */ + 120, /* IRQ_PVP_CPDOC */ + 120, /* IRQ_PVP_CPSTAT */ + 120, /* IRQ_PVP_CPCI */ + 120, /* IRQ_PVP_STAT0 */ + 120, /* IRQ_PVP_MPDO */ + 120, /* IRQ_PVP_MPDI */ + 120, /* IRQ_PVP_MPSTAT */ + 120, /* IRQ_PVP_MPCI */ + 120, /* IRQ_PVP_CPDOA */ + 120, /* IRQ_PVP_STAT1 */ + 0, /* IRQ_USB_STAT */ + 0, /* IRQ_USB_DMA */ + 0, /* IRQ_TRU_INT0 */ + 0, /* IRQ_TRU_INT1 */ + 0, /* IRQ_TRU_INT2 */ + 0, /* IRQ_TRU_INT3 */ + 0, /* IRQ_DMAC0_ERROR */ + 0, /* IRQ_CGU0_ERROR */ + 0, /* Reserved */ + 0, /* IRQ_DPM */ + 0, /* Reserved */ + 0, /* IRQ_SWU0 */ + 0, /* IRQ_SWU1 */ + 0, /* IRQ_SWU2 */ + 0, /* IRQ_SWU3 */ + 0, /* IRQ_SWU4 */ + 0, /* IRQ_SWU4 */ + 0, /* IRQ_SWU6 */ +}; + diff --git a/arch/blackfin/mach-bf609/pm.c b/arch/blackfin/mach-bf609/pm.c index b76966eb16a..dacafc163f7 100644 --- a/arch/blackfin/mach-bf609/pm.c +++ b/arch/blackfin/mach-bf609/pm.c @@ -11,13 +11,14 @@ #include <linux/interrupt.h> #include <linux/gpio.h> #include <linux/irq.h> - #include <linux/delay.h> +#include <linux/syscore_ops.h> #include <asm/dpmc.h> #include <asm/pm.h> #include <mach/pm.h> #include <asm/blackfin.h> +#include <asm/mem_init.h> /***********************************************************/ /* */ @@ -132,60 +133,30 @@ void bfin_cpu_suspend(void) } __attribute__((l1_text)) -void bfin_deepsleep(unsigned long mask) +void bf609_ddr_sr(void) { - uint32_t dpm0_ctl; - - bfin_write32(DPM0_WAKE_EN, 0x10); - bfin_write32(DPM0_WAKE_POL, 0x10); - dpm0_ctl = 0x00000008; - bfin_write32(DPM0_CTL, dpm0_ctl); - SSYNC(); - __asm__ __volatile__( \ - ".align 8;" \ - "idle;" \ - : : \ - ); -#ifdef CONFIG_BFIN_PM_WAKEUP_TIME_BENCH - __asm__ __volatile__( - "R0 = 0;" - "CYCLES = R0;" - "CYCLES2 = R0;" - "R0 = SYSCFG;" - "BITSET(R0, 1);" - "SYSCFG = R0;" - : : : "R0" - ); -#endif - + dmc_enter_self_refresh(); } __attribute__((l1_text)) -void bf609_ddr_sr(void) +void bf609_ddr_sr_exit(void) { - uint32_t reg; - - reg = bfin_read_DMC0_CTL(); - reg |= 0x8; - bfin_write_DMC0_CTL(reg); + dmc_exit_self_refresh(); - while (!(bfin_read_DMC0_STAT() & 0x8)) + /* After wake up from deep sleep and exit DDR from self refress mode, + * should wait till CGU PLL is locked. + */ + while (bfin_read32(CGU0_STAT) & CLKSALGN) continue; } __attribute__((l1_text)) -void bf609_ddr_sr_exit(void) +void bf609_resume_ccbuf(void) { - uint32_t reg; - while (!(bfin_read_DMC0_STAT() & 0x1)) - continue; + bfin_write32(DPM0_CCBF_EN, 3); + bfin_write32(DPM0_CTL, 2); - reg = bfin_read_DMC0_CTL(); - reg &= ~0x8; - bfin_write_DMC0_CTL(reg); - - while ((bfin_read_DMC0_STAT() & 0x8)) - continue; + while ((bfin_read32(DPM0_STAT) & 0xf) != 1); } __attribute__((l1_text)) @@ -203,20 +174,25 @@ void bfin_hibernate_syscontrol(void) bfin_write32(DPM0_RESTORE5, bfin_read32(DPM0_RESTORE5) | 4); } -#ifndef CONFIG_BF60x -# define SIC_SYSIRQ(irq) (irq - (IRQ_CORETMR + 1)) -#else -# define SIC_SYSIRQ(irq) ((irq) - IVG15) -#endif -void bfin_hibernate(unsigned long mask) +#define IRQ_SID(irq) ((irq) - IVG15) +asmlinkage void enter_deepsleep(void); + +__attribute__((l1_text)) +void bfin_deepsleep(unsigned long mask, unsigned long pol_mask) { - bfin_write32(DPM0_WAKE_EN, 0x10); - bfin_write32(DPM0_WAKE_POL, 0x10); + bfin_write32(DPM0_WAKE_EN, mask); + bfin_write32(DPM0_WAKE_POL, pol_mask); + SSYNC(); + enter_deepsleep(); +} + +void bfin_hibernate(unsigned long mask, unsigned long pol_mask) +{ + bfin_write32(DPM0_WAKE_EN, mask); + bfin_write32(DPM0_WAKE_POL, pol_mask); bfin_write32(DPM0_PGCNTR, 0x0000FFFF); bfin_write32(DPM0_HIB_DIS, 0xFFFF); - printk(KERN_DEBUG "hibernate: restore %x pgcnt %x\n", bfin_read32(DPM0_RESTORE0), bfin_read32(DPM0_PGCNTR)); - bf609_hibernate(); } @@ -290,10 +266,11 @@ void bf609_cpu_pm_enter(suspend_state_t state) printk(KERN_DEBUG "Unable to get irq wake\n"); if (state == PM_SUSPEND_STANDBY) - bfin_deepsleep(wakeup); + bfin_deepsleep(wakeup, wakeup_pol); else { - bfin_hibernate(wakeup); + bfin_hibernate(wakeup, wakeup_pol); } + } int bf609_cpu_pm_prepare(void) @@ -312,20 +289,36 @@ static struct bfin_cpu_pm_fns bf609_cpu_pm = { .finish = bf609_cpu_pm_finish, }; +#if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) +static int smc_pm_syscore_suspend(void) +{ + bf609_nor_flash_exit(); + return 0; +} + +static void smc_pm_syscore_resume(void) +{ + bf609_nor_flash_init(); +} + +static struct syscore_ops smc_pm_syscore_ops = { + .suspend = smc_pm_syscore_suspend, + .resume = smc_pm_syscore_resume, +}; +#endif + static irqreturn_t test_isr(int irq, void *dev_id) { printk(KERN_DEBUG "gpio irq %d\n", irq); + if (irq == 231) + bfin_sec_raise_irq(IRQ_SID(IRQ_SOFT1)); return IRQ_HANDLED; } static irqreturn_t dpm0_isr(int irq, void *dev_id) { - uint32_t wake_stat; - - wake_stat = bfin_read32(DPM0_WAKE_STAT); - printk(KERN_DEBUG "enter %s wake stat %08x\n", __func__, wake_stat); - - bfin_write32(DPM0_WAKE_STAT, wake_stat); + bfin_write32(DPM0_WAKE_STAT, bfin_read32(DPM0_WAKE_STAT)); + bfin_write32(CGU0_STAT, bfin_read32(CGU0_STAT)); return IRQ_HANDLED; } @@ -334,7 +327,11 @@ static int __init bf609_init_pm(void) int irq; int error; -#if CONFIG_PM_BFIN_WAKE_PE12 +#if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) + register_syscore_ops(&smc_pm_syscore_ops); +#endif + +#ifdef CONFIG_PM_BFIN_WAKE_PE12 irq = gpio_to_irq(GPIO_PE12); if (irq < 0) { error = irq; @@ -342,16 +339,19 @@ static int __init bf609_init_pm(void) GPIO_PE12, error); } - error = request_irq(irq, test_isr, IRQF_TRIGGER_RISING | IRQF_NO_SUSPEND, "gpiope12", NULL); + error = request_irq(irq, test_isr, IRQF_TRIGGER_RISING | IRQF_NO_SUSPEND + | IRQF_FORCE_RESUME, "gpiope12", NULL); if(error < 0) printk(KERN_DEBUG "Unable to get irq\n"); #endif - error = request_irq(IRQ_CGU_EVT, dpm0_isr, IRQF_NO_SUSPEND, "cgu0 event", NULL); + error = request_irq(IRQ_CGU_EVT, dpm0_isr, IRQF_NO_SUSPEND | + IRQF_FORCE_RESUME, "cgu0 event", NULL); if(error < 0) printk(KERN_DEBUG "Unable to get irq\n"); - error = request_irq(IRQ_DPM, dpm0_isr, IRQF_NO_SUSPEND, "dpm0 event", NULL); + error = request_irq(IRQ_DPM, dpm0_isr, IRQF_NO_SUSPEND | + IRQF_FORCE_RESUME, "dpm0 event", NULL); if (error < 0) printk(KERN_DEBUG "Unable to get irq\n"); diff --git a/arch/blackfin/mach-common/clocks-init.c b/arch/blackfin/mach-common/clocks-init.c index 7ad2407d157..2308ce52f84 100644 --- a/arch/blackfin/mach-common/clocks-init.c +++ b/arch/blackfin/mach-common/clocks-init.c @@ -16,23 +16,14 @@ #include <asm/dpmc.h> #ifdef CONFIG_BF60x -#define CSEL_P 0 -#define S0SEL_P 5 -#define SYSSEL_P 8 -#define S1SEL_P 13 -#define DSEL_P 16 -#define OSEL_P 22 -#define ALGN_P 29 -#define UPDT_P 30 -#define LOCK_P 31 #define CGU_CTL_VAL ((CONFIG_VCO_MULT << 8) | CLKIN_HALF) #define CGU_DIV_VAL \ - ((CONFIG_CCLK_DIV << CSEL_P) | \ - (CONFIG_SCLK_DIV << SYSSEL_P) | \ - (CONFIG_SCLK0_DIV << S0SEL_P) | \ - (CONFIG_SCLK1_DIV << S1SEL_P) | \ - (CONFIG_DCLK_DIV << DSEL_P)) + ((CONFIG_CCLK_DIV << CSEL_OFFSET) | \ + (CONFIG_SCLK_DIV << SYSSEL_OFFSET) | \ + (CONFIG_SCLK0_DIV << S0SEL_OFFSET) | \ + (CONFIG_SCLK1_DIV << S1SEL_OFFSET) | \ + (CONFIG_DCLK_DIV << DSEL_OFFSET)) #define CONFIG_BFIN_DCLK (((CONFIG_CLKIN_HZ * CONFIG_VCO_MULT) / CONFIG_DCLK_DIV) / 1000000) #if ((CONFIG_BFIN_DCLK != 125) && \ @@ -41,89 +32,7 @@ (CONFIG_BFIN_DCLK != 225) && (CONFIG_BFIN_DCLK != 250)) #error "DCLK must be in (125, 133, 150, 166, 200, 225, 250)MHz" #endif -struct ddr_config { - u32 ddr_clk; - u32 dmc_ddrctl; - u32 dmc_ddrcfg; - u32 dmc_ddrtr0; - u32 dmc_ddrtr1; - u32 dmc_ddrtr2; - u32 dmc_ddrmr; - u32 dmc_ddrmr1; -}; -struct ddr_config ddr_config_table[] __attribute__((section(".data_l1"))) = { - [0] = { - .ddr_clk = 125, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20705212, - .dmc_ddrtr1 = 0x201003CF, - .dmc_ddrtr2 = 0x00320107, - .dmc_ddrmr = 0x00000422, - .dmc_ddrmr1 = 0x4, - }, - [1] = { - .ddr_clk = 133, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20806313, - .dmc_ddrtr1 = 0x2013040D, - .dmc_ddrtr2 = 0x00320108, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [2] = { - .ddr_clk = 150, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20A07323, - .dmc_ddrtr1 = 0x20160492, - .dmc_ddrtr2 = 0x00320209, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [3] = { - .ddr_clk = 166, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20A07323, - .dmc_ddrtr1 = 0x2016050E, - .dmc_ddrtr2 = 0x00320209, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [4] = { - .ddr_clk = 200, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20a07323, - .dmc_ddrtr1 = 0x2016050f, - .dmc_ddrtr2 = 0x00320509, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [5] = { - .ddr_clk = 225, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20E0A424, - .dmc_ddrtr1 = 0x302006DB, - .dmc_ddrtr2 = 0x0032020D, - .dmc_ddrmr = 0x00000842, - .dmc_ddrmr1 = 0x4, - }, - [6] = { - .ddr_clk = 250, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20E0A424, - .dmc_ddrtr1 = 0x3020079E, - .dmc_ddrtr2 = 0x0032020D, - .dmc_ddrmr = 0x00000842, - .dmc_ddrmr1 = 0x4, - }, -}; #else #define SDGCTL_WIDTH (1 << 31) /* SDRAM external data path width */ #define PLL_CTL_VAL \ @@ -144,43 +53,9 @@ void init_clocks(void) * in the middle of reprogramming things, and that'll screw us up. * For example, any automatic DMAs left by U-Boot for splash screens. */ - #ifdef CONFIG_BF60x - int i, dlldatacycle, dll_ctl; - bfin_write32(CGU0_DIV, CGU_DIV_VAL); - bfin_write32(CGU0_CTL, CGU_CTL_VAL); - while ((bfin_read32(CGU0_STAT) & 0x8) || !(bfin_read32(CGU0_STAT) & 0x4)) - continue; - - bfin_write32(CGU0_DIV, CGU_DIV_VAL | (1 << UPDT_P)); - while (bfin_read32(CGU0_STAT) & (1 << 3)) - continue; - - for (i = 0; i < 7; i++) { - if (ddr_config_table[i].ddr_clk == CONFIG_BFIN_DCLK) { - bfin_write_DDR0_CFG(ddr_config_table[i].dmc_ddrcfg); - bfin_write_DDR0_TR0(ddr_config_table[i].dmc_ddrtr0); - bfin_write_DDR0_TR1(ddr_config_table[i].dmc_ddrtr1); - bfin_write_DDR0_TR2(ddr_config_table[i].dmc_ddrtr2); - bfin_write_DDR0_MR(ddr_config_table[i].dmc_ddrmr); - bfin_write_DDR0_EMR1(ddr_config_table[i].dmc_ddrmr1); - bfin_write_DDR0_CTL(ddr_config_table[i].dmc_ddrctl); - break; - } - } - - do_sync(); - while (!(bfin_read_DDR0_STAT() & 0x4)) - continue; - - dlldatacycle = (bfin_read_DDR0_STAT() & 0x00f00000) >> 20; - dll_ctl = bfin_read_DDR0_DLLCTL(); - dll_ctl &= 0x0ff; - bfin_write_DDR0_DLLCTL(dll_ctl | (dlldatacycle << 8)); - - do_sync(); - while (!(bfin_read_DDR0_STAT() & 0x2000)) - continue; + init_cgu(CGU_DIV_VAL, CGU_CTL_VAL); + init_dmc(CONFIG_BFIN_DCLK); #else size_t i; for (i = 0; i < MAX_DMA_CHANNELS; ++i) { diff --git a/arch/blackfin/mach-common/cpufreq.c b/arch/blackfin/mach-common/cpufreq.c index 6e87dc13f6b..c854a27cbea 100644 --- a/arch/blackfin/mach-common/cpufreq.c +++ b/arch/blackfin/mach-common/cpufreq.c @@ -64,7 +64,8 @@ static void __init bfin_init_tables(unsigned long cclk, unsigned long sclk) /* Anomaly 273 seems to still exist on non-BF54x w/dcache turned on */ #if ANOMALY_05000273 || ANOMALY_05000274 || \ - (!defined(CONFIG_BF54x) && defined(CONFIG_BFIN_EXTMEM_DCACHEABLE)) + (!(defined(CONFIG_BF54x) || defined(CONFIG_BF60x)) \ + && defined(CONFIG_BFIN_EXTMEM_DCACHEABLE)) min_cclk = sclk * 2; #else min_cclk = sclk; @@ -173,7 +174,7 @@ static int bfin_target(struct cpufreq_policy *poli, #else ret = cpu_set_cclk(cpu, freqs.new * 1000); if (ret != 0) { - pr_debug("cpufreq set freq failed %d\n", ret); + WARN_ONCE(ret, "cpufreq set freq failed %d\n", ret); break; } #endif diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 04c2fbe41a7..1c3d2c5bb0b 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -25,13 +25,6 @@ #include <asm/context.S> -#if defined(CONFIG_BFIN_SCRATCH_REG_RETN) -# define EX_SCRATCH_REG RETN -#elif defined(CONFIG_BFIN_SCRATCH_REG_RETE) -# define EX_SCRATCH_REG RETE -#else -# define EX_SCRATCH_REG CYCLES -#endif #ifdef CONFIG_EXCPT_IRQ_SYSC_L1 .section .l1.text diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index 2729cba715b..7ca09ec2ca5 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -26,8 +26,9 @@ #include <asm/gpio.h> #include <asm/irq_handler.h> #include <asm/dpmc.h> +#include <asm/traps.h> -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL # define SIC_SYSIRQ(irq) (irq - (IRQ_CORETMR + 1)) #else # define SIC_SYSIRQ(irq) ((irq) - IVG15) @@ -56,7 +57,7 @@ unsigned long bfin_sic_iwr[3]; /* Up to 3 SIC_IWRx registers */ unsigned vr_wakeup; #endif -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL static struct ivgx { /* irq number for request_irq, available in mach-bf5xx/irq.h */ unsigned int irqno; @@ -143,7 +144,7 @@ static void bfin_core_unmask_irq(struct irq_data *d) void bfin_internal_mask_irq(unsigned int irq) { unsigned long flags = hard_local_irq_save(); -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL #ifdef SIC_IMASK0 unsigned mask_bank = SIC_SYSIRQ(irq) / 32; unsigned mask_bit = SIC_SYSIRQ(irq) % 32; @@ -175,7 +176,7 @@ void bfin_internal_unmask_irq(unsigned int irq) { unsigned long flags = hard_local_irq_save(); -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL #ifdef SIC_IMASK0 unsigned mask_bank = SIC_SYSIRQ(irq) / 32; unsigned mask_bit = SIC_SYSIRQ(irq) % 32; @@ -199,7 +200,7 @@ void bfin_internal_unmask_irq(unsigned int irq) hard_local_irq_restore(flags); } -#ifdef CONFIG_BF60x +#ifdef SEC_GCTL static void bfin_sec_preflow_handler(struct irq_data *d) { unsigned long flags = hard_local_irq_save(); @@ -310,7 +311,24 @@ static void bfin_sec_disable(struct irq_data *d) hard_local_irq_restore(flags); } -static void bfin_sec_raise_irq(unsigned int sid) +static void bfin_sec_set_priority(unsigned int sec_int_levels, u8 *sec_int_priority) +{ + unsigned long flags = hard_local_irq_save(); + uint32_t reg_sctl; + int i; + + bfin_write_SEC_SCI(0, SEC_CPLVL, sec_int_levels); + + for (i = 0; i < SYS_IRQS - BFIN_IRQ(0); i++) { + reg_sctl = bfin_read_SEC_SCTL(i) & ~SEC_SCTL_PRIO; + reg_sctl |= sec_int_priority[i] << SEC_SCTL_PRIO_OFFSET; + bfin_write_SEC_SCTL(i, reg_sctl); + } + + hard_local_irq_restore(flags); +} + +void bfin_sec_raise_irq(unsigned int sid) { unsigned long flags = hard_local_irq_save(); @@ -396,24 +414,34 @@ void handle_sec_fault(unsigned int irq, struct irq_desc *desc) raw_spin_unlock(&desc->lock); } -static int sec_suspend(void) +void handle_core_fault(unsigned int irq, struct irq_desc *desc) { - return 0; -} + struct pt_regs *fp = get_irq_regs(); -static void sec_resume(void) -{ - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); - udelay(100); - bfin_write_SEC_GCTL(SEC_GCTL_EN); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); -} + raw_spin_lock(&desc->lock); -static struct syscore_ops sec_pm_syscore_ops = { - .suspend = sec_suspend, - .resume = sec_resume, -}; + switch (irq) { + case IRQ_C0_DBL_FAULT: + double_fault_c(fp); + break; + case IRQ_C0_HW_ERR: + dump_bfin_process(fp); + dump_bfin_mem(fp); + show_regs(fp); + printk(KERN_NOTICE "Kernel Stack\n"); + show_stack(current, NULL); + print_modules(); + panic("Kernel core hardware error"); + break; + case IRQ_C0_NMI_L1_PARITY_ERR: + panic("NMI occurs unexpectedly"); + break; + default: + panic("Core 1 fault occurs unexpectedly"); + } + raw_spin_unlock(&desc->lock); +} #endif #ifdef CONFIG_SMP @@ -437,7 +465,7 @@ static void bfin_internal_unmask_irq_chip(struct irq_data *d) } #endif -#if defined(CONFIG_PM) && !defined(CONFIG_BF60x) +#if defined(CONFIG_PM) && !defined(SEC_GCTL) int bfin_internal_set_wake(unsigned int irq, unsigned int state) { u32 bank, bit, wakeup = 0; @@ -496,7 +524,10 @@ static int bfin_internal_set_wake_chip(struct irq_data *d, unsigned int state) return bfin_internal_set_wake(d->irq, state); } #else -# define bfin_internal_set_wake(irq, state) +inline int bfin_internal_set_wake(unsigned int irq, unsigned int state) +{ + return 0; +} # define bfin_internal_set_wake_chip NULL #endif @@ -518,7 +549,7 @@ static struct irq_chip bfin_internal_irqchip = { .irq_set_wake = bfin_internal_set_wake_chip, }; -#ifdef CONFIG_BF60x +#ifdef SEC_GCTL static struct irq_chip bfin_sec_irqchip = { .name = "SEC", .irq_mask_ack = bfin_sec_mask_ack_irq, @@ -868,14 +899,6 @@ void bfin_demux_gpio_irq(unsigned int inta_irq, #else -# ifndef CONFIG_BF60x -#define NR_PINT_SYS_IRQS 4 -#define NR_PINTS 160 -# else -#define NR_PINT_SYS_IRQS 6 -#define NR_PINTS 112 -#endif - #define NR_PINT_BITS 32 #define IRQ_NOT_AVAIL 0xFF @@ -897,29 +920,21 @@ static struct bfin_pint_regs * const pint[NR_PINT_SYS_IRQS] = { #endif }; -#ifndef CONFIG_BF60x inline unsigned int get_irq_base(u32 bank, u8 bmap) { unsigned int irq_base; +#ifndef CONFIG_BF60x if (bank < 2) { /*PA-PB */ irq_base = IRQ_PA0 + bmap * 16; } else { /*PC-PJ */ irq_base = IRQ_PC0 + bmap * 16; } - - return irq_base; -} #else -inline unsigned int get_irq_base(u32 bank, u8 bmap) -{ - unsigned int irq_base; - irq_base = IRQ_PA0 + bank * 16 + bmap * 16; - +#endif return irq_base; } -#endif /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ void init_pint_lut(void) @@ -1089,6 +1104,9 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type) } #ifdef CONFIG_PM +static struct bfin_pm_pint_save save_pint_reg[NR_PINT_SYS_IRQS]; +static u32 save_pint_sec_ctl[NR_PINT_SYS_IRQS]; + static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) { u32 pint_irq; @@ -1124,6 +1142,59 @@ static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) return 0; } + +void bfin_pint_suspend(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { + save_pint_reg[bank].mask_set = pint[bank]->mask_set; + save_pint_reg[bank].assign = pint[bank]->assign; + save_pint_reg[bank].edge_set = pint[bank]->edge_set; + save_pint_reg[bank].invert_set = pint[bank]->invert_set; + } +} + +void bfin_pint_resume(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { + pint[bank]->mask_set = save_pint_reg[bank].mask_set; + pint[bank]->assign = save_pint_reg[bank].assign; + pint[bank]->edge_set = save_pint_reg[bank].edge_set; + pint[bank]->invert_set = save_pint_reg[bank].invert_set; + } +} + +#ifdef SEC_GCTL +static int sec_suspend(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) + save_pint_sec_ctl[bank] = bfin_read_SEC_SCTL(bank + SIC_SYSIRQ(IRQ_PINT0)); + return 0; +} + +static void sec_resume(void) +{ + u32 bank; + + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); + udelay(100); + bfin_write_SEC_GCTL(SEC_GCTL_EN); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) + bfin_write_SEC_SCTL(bank + SIC_SYSIRQ(IRQ_PINT0), save_pint_sec_ctl[bank]); +} + +static struct syscore_ops sec_pm_syscore_ops = { + .suspend = sec_suspend, + .resume = sec_resume, +}; +#endif #else # define bfin_gpio_set_wake NULL #endif @@ -1230,6 +1301,7 @@ void __cpuinit init_exception_vectors(void) CSYNC(); } +#ifndef SEC_GCTL /* * This function should be called during kernel startup to initialize * the BFin IRQ handling routines. @@ -1240,7 +1312,6 @@ int __init init_arch_irq(void) int irq; unsigned long ilat = 0; -#ifndef CONFIG_BF60x /* Disable all the peripheral intrs - page 4-29 HW Ref manual */ #ifdef SIC_IMASK0 bfin_write_SIC_IMASK0(SIC_UNMASK_ALL); @@ -1255,9 +1326,6 @@ int __init init_arch_irq(void) #else bfin_write_SIC_IMASK(SIC_UNMASK_ALL); #endif -#else /* CONFIG_BF60x */ - bfin_write_SEC_GCTL(SEC_GCTL_RESET); -#endif local_irq_disable(); @@ -1267,10 +1335,6 @@ int __init init_arch_irq(void) pint[1]->assign = CONFIG_PINT1_ASSIGN; pint[2]->assign = CONFIG_PINT2_ASSIGN; pint[3]->assign = CONFIG_PINT3_ASSIGN; -# ifdef CONFIG_BF60x - pint[4]->assign = CONFIG_PINT4_ASSIGN; - pint[5]->assign = CONFIG_PINT5_ASSIGN; -# endif # endif /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ init_pint_lut(); @@ -1283,7 +1347,6 @@ int __init init_arch_irq(void) irq_set_chip(irq, &bfin_internal_irqchip); switch (irq) { -#ifndef CONFIG_BF60x #if BFIN_GPIO_PINT case IRQ_PINT0: case IRQ_PINT1: @@ -1319,7 +1382,6 @@ int __init init_arch_irq(void) irq_set_handler(irq, handle_percpu_irq); break; #endif -#endif #ifdef CONFIG_TICKSOURCE_CORETMR case IRQ_CORETMR: @@ -1349,8 +1411,7 @@ int __init init_arch_irq(void) init_mach_irq(); -#ifndef CONFIG_BF60x -#if (defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)) && !defined(CONFIG_BF60x) +#if (defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)) for (irq = IRQ_MAC_PHYINT; irq <= IRQ_MAC_STMDONE; irq++) irq_set_chip_and_handler(irq, &bfin_mac_status_irqchip, handle_level_irq); @@ -1360,28 +1421,6 @@ int __init init_arch_irq(void) irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, handle_level_irq); -#else - for (irq = BFIN_IRQ(0); irq <= SYS_IRQS; irq++) { - if (irq < CORE_IRQS) { - irq_set_chip(irq, &bfin_sec_irqchip); - __irq_set_handler(irq, handle_sec_fault, 0, NULL); - } else if (irq >= BFIN_IRQ(21) && irq <= BFIN_IRQ(26)) { - irq_set_chip(irq, &bfin_sec_irqchip); - irq_set_chained_handler(irq, bfin_demux_gpio_irq); - } else if (irq >= BFIN_IRQ(34) && irq <= BFIN_IRQ(37)) { - irq_set_chip(irq, &bfin_sec_irqchip); - irq_set_handler(irq, handle_percpu_irq); - } else { - irq_set_chip_and_handler(irq, &bfin_sec_irqchip, - handle_fasteoi_irq); - __irq_set_preflow_handler(irq, bfin_sec_preflow_handler); - } - } - for (irq = GPIO_IRQ_BASE; - irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) - irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, - handle_level_irq); -#endif bfin_write_IMASK(0); CSYNC(); ilat = bfin_read_ILAT(); @@ -1393,7 +1432,6 @@ int __init init_arch_irq(void) /* IMASK=xxx is equivalent to STI xx or bfin_irq_flags=xx, * local_irq_enable() */ -#ifndef CONFIG_BF60x program_IAR(); /* Therefore it's better to setup IARs before interrupts enabled */ search_IAR(); @@ -1427,23 +1465,6 @@ int __init init_arch_irq(void) #else bfin_write_SIC_IWR(IWR_DISABLE_ALL); #endif -#else /* CONFIG_BF60x */ - /* Enable interrupts IVG7-15 */ - bfin_irq_flags |= IMASK_IVG15 | - IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 | - IMASK_IVG10 | IMASK_IVG9 | IMASK_IVG8 | IMASK_IVG7 | IMASK_IVGHW; - - - bfin_write_SEC_FCTL(SEC_FCTL_EN | SEC_FCTL_SYSRST_EN | SEC_FCTL_FLTIN_EN); - bfin_sec_enable_sci(SIC_SYSIRQ(IRQ_WATCH0)); - bfin_sec_enable_ssi(SIC_SYSIRQ(IRQ_WATCH0)); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); - udelay(100); - bfin_write_SEC_GCTL(SEC_GCTL_EN); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); - init_software_driven_irq(); - register_syscore_ops(&sec_pm_syscore_ops); -#endif return 0; } @@ -1452,14 +1473,11 @@ __attribute__((l1_text)) #endif static int vec_to_irq(int vec) { -#ifndef CONFIG_BF60x struct ivgx *ivg = ivg7_13[vec - IVG7].ifirst; struct ivgx *ivg_stop = ivg7_13[vec - IVG7].istop; unsigned long sic_status[3]; -#endif if (likely(vec == EVT_IVTMR_P)) return IRQ_CORETMR; -#ifndef CONFIG_BF60x #ifdef SIC_ISR sic_status[0] = bfin_read_SIC_IMASK() & bfin_read_SIC_ISR(); #else @@ -1488,11 +1506,119 @@ static int vec_to_irq(int vec) #endif return ivg->irqno; } -#else - /* for bf60x read */ +} + +#else /* SEC_GCTL */ + +/* + * This function should be called during kernel startup to initialize + * the BFin IRQ handling routines. + */ + +int __init init_arch_irq(void) +{ + int irq; + unsigned long ilat = 0; + + bfin_write_SEC_GCTL(SEC_GCTL_RESET); + + local_irq_disable(); + +#if BFIN_GPIO_PINT +# ifdef CONFIG_PINTx_REASSIGN + pint[0]->assign = CONFIG_PINT0_ASSIGN; + pint[1]->assign = CONFIG_PINT1_ASSIGN; + pint[2]->assign = CONFIG_PINT2_ASSIGN; + pint[3]->assign = CONFIG_PINT3_ASSIGN; + pint[4]->assign = CONFIG_PINT4_ASSIGN; + pint[5]->assign = CONFIG_PINT5_ASSIGN; +# endif + /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ + init_pint_lut(); +#endif + + for (irq = 0; irq <= SYS_IRQS; irq++) { + if (irq <= IRQ_CORETMR) { + irq_set_chip(irq, &bfin_core_irqchip); +#ifdef CONFIG_TICKSOURCE_CORETMR + if (irq == IRQ_CORETMR) +# ifdef CONFIG_SMP + irq_set_handler(irq, handle_percpu_irq); +# else + irq_set_handler(irq, handle_simple_irq); +# endif +#endif + } else if (irq < BFIN_IRQ(0)) { + irq_set_chip_and_handler(irq, &bfin_internal_irqchip, + handle_simple_irq); + } else if (irq == IRQ_SEC_ERR) { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_sec_fault); + } else if (irq < CORE_IRQS && irq >= IRQ_C0_DBL_FAULT) { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_core_fault); + } else if (irq >= BFIN_IRQ(21) && irq <= BFIN_IRQ(26)) { + irq_set_chip(irq, &bfin_sec_irqchip); + irq_set_chained_handler(irq, bfin_demux_gpio_irq); + } else if (irq >= BFIN_IRQ(34) && irq <= BFIN_IRQ(37)) { + irq_set_chip(irq, &bfin_sec_irqchip); + irq_set_handler(irq, handle_percpu_irq); + } else { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_fasteoi_irq); + __irq_set_preflow_handler(irq, bfin_sec_preflow_handler); + } + } + for (irq = GPIO_IRQ_BASE; + irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) + irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, + handle_level_irq); + + bfin_write_IMASK(0); + CSYNC(); + ilat = bfin_read_ILAT(); + CSYNC(); + bfin_write_ILAT(ilat); + CSYNC(); + + printk(KERN_INFO "Configuring Blackfin Priority Driven Interrupts\n"); + + bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority); + + bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority); + + /* Enable interrupts IVG7-15 */ + bfin_irq_flags |= IMASK_IVG15 | + IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 | + IMASK_IVG10 | IMASK_IVG9 | IMASK_IVG8 | IMASK_IVG7 | IMASK_IVGHW; + + + bfin_write_SEC_FCTL(SEC_FCTL_EN | SEC_FCTL_SYSRST_EN | SEC_FCTL_FLTIN_EN); + bfin_sec_enable_sci(SIC_SYSIRQ(IRQ_WATCH0)); + bfin_sec_enable_ssi(SIC_SYSIRQ(IRQ_WATCH0)); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); + udelay(100); + bfin_write_SEC_GCTL(SEC_GCTL_EN); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + bfin_write_SEC_SCI(1, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + + init_software_driven_irq(); + register_syscore_ops(&sec_pm_syscore_ops); + + return 0; +} + +#ifdef CONFIG_DO_IRQ_L1 +__attribute__((l1_text)) +#endif +static int vec_to_irq(int vec) +{ + if (likely(vec == EVT_IVTMR_P)) + return IRQ_CORETMR; + return BFIN_IRQ(bfin_read_SEC_SCI(0, SEC_CSID)); -#endif /* end of CONFIG_BF60x */ } +#endif /* SEC_GCTL */ #ifdef CONFIG_DO_IRQ_L1 __attribute__((l1_text)) @@ -1514,6 +1640,10 @@ int __ipipe_get_irq_priority(unsigned irq) if (irq <= IRQ_CORETMR) return irq; +#ifdef SEC_GCTL + if (irq >= BFIN_IRQ(0)) + return IVG11; +#else for (ient = 0; ient < NR_PERI_INTS; ient++) { struct ivgx *ivg = ivg_table + ient; if (ivg->irqno == irq) { @@ -1524,6 +1654,7 @@ int __ipipe_get_irq_priority(unsigned irq) } } } +#endif return IVG15; } @@ -1536,8 +1667,6 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) { struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); struct ipipe_domain *this_domain = __ipipe_current_domain; - struct ivgx *ivg_stop = ivg7_13[vec-IVG7].istop; - struct ivgx *ivg = ivg7_13[vec-IVG7].ifirst; int irq, s = 0; irq = vec_to_irq(vec); diff --git a/arch/blackfin/mach-common/pm.c b/arch/blackfin/mach-common/pm.c index ca6655e0d65..87bfe549ad3 100644 --- a/arch/blackfin/mach-common/pm.c +++ b/arch/blackfin/mach-common/pm.c @@ -172,6 +172,10 @@ int bfin_pm_suspend_mem_enter(void) bfin_gpio_pm_hibernate_suspend(); +#if BFIN_GPIO_PINT + bfin_pint_suspend(); +#endif + #if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK) flushinv_all_dcache(); #endif @@ -190,6 +194,10 @@ int bfin_pm_suspend_mem_enter(void) _enable_icplb(); _enable_dcplb(); +#if BFIN_GPIO_PINT + bfin_pint_resume(); +#endif + bfin_gpio_pm_hibernate_restore(); blackfin_dma_resume(); diff --git a/arch/c6x/boot/dts/evmc6678.dts b/arch/c6x/boot/dts/evmc6678.dts new file mode 100644 index 00000000000..ab686301d32 --- /dev/null +++ b/arch/c6x/boot/dts/evmc6678.dts @@ -0,0 +1,83 @@ +/* + * arch/c6x/boot/dts/evmc6678.dts + * + * EVMC6678 Evaluation Platform For TMS320C6678 + * + * Copyright (C) 2012 Texas Instruments Incorporated + * + * Author: Ken Cox <jkc@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + */ + +/dts-v1/; + +/include/ "tms320c6678.dtsi" + +/ { + model = "Advantech EVMC6678"; + compatible = "advantech,evmc6678"; + + chosen { + bootargs = "root=/dev/nfs ip=dhcp rw"; + }; + + memory { + device_type = "memory"; + reg = <0x80000000 0x20000000>; + }; + + soc { + megamod_pic: interrupt-controller@1800000 { + interrupts = < 12 13 14 15 >; + }; + + timer8: timer@2280000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 66 >; + }; + + timer9: timer@2290000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 68 >; + }; + + timer10: timer@22A0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 70 >; + }; + + timer11: timer@22B0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 72 >; + }; + + timer12: timer@22C0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 74 >; + }; + + timer13: timer@22D0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 76 >; + }; + + timer14: timer@22E0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 78 >; + }; + + timer15: timer@22F0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 80 >; + }; + + clock-controller@2310000 { + clock-frequency = <100000000>; + }; + }; +}; diff --git a/arch/c6x/boot/dts/tms320c6678.dtsi b/arch/c6x/boot/dts/tms320c6678.dtsi new file mode 100644 index 00000000000..386196e5eae --- /dev/null +++ b/arch/c6x/boot/dts/tms320c6678.dtsi @@ -0,0 +1,146 @@ + +/ { + #address-cells = <1>; + #size-cells = <1>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + reg = <0>; + model = "ti,c66x"; + }; + cpu@1 { + device_type = "cpu"; + reg = <1>; + model = "ti,c66x"; + }; + cpu@2 { + device_type = "cpu"; + reg = <2>; + model = "ti,c66x"; + }; + cpu@3 { + device_type = "cpu"; + reg = <3>; + model = "ti,c66x"; + }; + cpu@4 { + device_type = "cpu"; + reg = <4>; + model = "ti,c66x"; + }; + cpu@5 { + device_type = "cpu"; + reg = <5>; + model = "ti,c66x"; + }; + cpu@6 { + device_type = "cpu"; + reg = <6>; + model = "ti,c66x"; + }; + cpu@7 { + device_type = "cpu"; + reg = <7>; + model = "ti,c66x"; + }; + }; + + soc { + compatible = "simple-bus"; + model = "tms320c6678"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + core_pic: interrupt-controller { + compatible = "ti,c64x+core-pic"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + megamod_pic: interrupt-controller@1800000 { + compatible = "ti,c64x+megamod-pic"; + interrupt-controller; + #interrupt-cells = <1>; + reg = <0x1800000 0x1000>; + interrupt-parent = <&core_pic>; + }; + + cache-controller@1840000 { + compatible = "ti,c64x+cache"; + reg = <0x01840000 0x8400>; + }; + + timer8: timer@2280000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x01 >; + reg = <0x2280000 0x40>; + }; + + timer9: timer@2290000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x02 >; + reg = <0x2290000 0x40>; + }; + + timer10: timer@22A0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x04 >; + reg = <0x22A0000 0x40>; + }; + + timer11: timer@22B0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x08 >; + reg = <0x22B0000 0x40>; + }; + + timer12: timer@22C0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x10 >; + reg = <0x22C0000 0x40>; + }; + + timer13: timer@22D0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x20 >; + reg = <0x22D0000 0x40>; + }; + + timer14: timer@22E0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x40 >; + reg = <0x22E0000 0x40>; + }; + + timer15: timer@22F0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x80 >; + reg = <0x22F0000 0x40>; + }; + + clock-controller@2310000 { + compatible = "ti,c6678-pll", "ti,c64x+pll"; + reg = <0x02310000 0x200>; + ti,c64x+pll-bypass-delay = <200>; + ti,c64x+pll-reset-delay = <12000>; + ti,c64x+pll-lock-delay = <80000>; + }; + + device-state-controller@2620000 { + compatible = "ti,c64x+dscr"; + reg = <0x02620000 0x1000>; + + ti,dscr-devstat = <0x20>; + ti,dscr-silicon-rev = <0x18 28 0xf>; + + ti,dscr-mac-fuse-regs = <0x110 1 2 3 4 + 0x114 5 6 0 0>; + + }; + }; +}; diff --git a/arch/c6x/configs/evmc6678_defconfig b/arch/c6x/configs/evmc6678_defconfig new file mode 100644 index 00000000000..5f126d4905b --- /dev/null +++ b/arch/c6x/configs/evmc6678_defconfig @@ -0,0 +1,42 @@ +CONFIG_SOC_TMS320C6678=y +CONFIG_EXPERIMENTAL=y +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +CONFIG_SPARSE_IRQ=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_USER_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_EXPERT=y +# CONFIG_FUTEX is not set +# CONFIG_SLUB_DEBUG is not set +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="" +# CONFIG_CMDLINE_FORCE is not set +CONFIG_BOARD_EVM6678=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=2 +CONFIG_BLK_DEV_RAM_SIZE=17000 +CONFIG_MISC_DEVICES=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_CRC16=y +# CONFIG_ENABLE_MUST_CHECK is not set +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/c6x/include/asm/irq.h b/arch/c6x/include/asm/irq.h index ab4577f93d9..1324e62bd4e 100644 --- a/arch/c6x/include/asm/irq.h +++ b/arch/c6x/include/asm/irq.h @@ -34,8 +34,6 @@ */ #define NR_PRIORITY_IRQS 16 -#define NR_IRQS_LEGACY NR_PRIORITY_IRQS - /* Total number of virq in the platform */ #define NR_IRQS 256 diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c index c90fb5e82ad..247e0eb5e46 100644 --- a/arch/c6x/kernel/irq.c +++ b/arch/c6x/kernel/irq.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2011 Texas Instruments Incorporated + * Copyright (C) 2011-2012 Texas Instruments Incorporated * * This borrows heavily from powerpc version, which is: * @@ -35,9 +35,7 @@ static DEFINE_RAW_SPINLOCK(core_irq_lock); static void mask_core_irq(struct irq_data *data) { - unsigned int prio = data->irq; - - BUG_ON(prio < 4 || prio >= NR_PRIORITY_IRQS); + unsigned int prio = data->hwirq; raw_spin_lock(&core_irq_lock); and_creg(IER, ~(1 << prio)); @@ -46,7 +44,7 @@ static void mask_core_irq(struct irq_data *data) static void unmask_core_irq(struct irq_data *data) { - unsigned int prio = data->irq; + unsigned int prio = data->hwirq; raw_spin_lock(&core_irq_lock); or_creg(IER, 1 << prio); @@ -59,15 +57,15 @@ static struct irq_chip core_chip = { .irq_unmask = unmask_core_irq, }; +static int prio_to_virq[NR_PRIORITY_IRQS]; + asmlinkage void c6x_do_IRQ(unsigned int prio, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); irq_enter(); - BUG_ON(prio < 4 || prio >= NR_PRIORITY_IRQS); - - generic_handle_irq(prio); + generic_handle_irq(prio_to_virq[prio]); irq_exit(); @@ -82,6 +80,8 @@ static int core_domain_map(struct irq_domain *h, unsigned int virq, if (hw < 4 || hw >= NR_PRIORITY_IRQS) return -EINVAL; + prio_to_virq[hw] = virq; + irq_set_status_flags(virq, IRQ_LEVEL); irq_set_chip_and_handler(virq, &core_chip, handle_level_irq); return 0; @@ -102,9 +102,8 @@ void __init init_IRQ(void) np = of_find_compatible_node(NULL, NULL, "ti,c64x+core-pic"); if (np != NULL) { /* create the core host */ - core_domain = irq_domain_add_legacy(np, NR_PRIORITY_IRQS, - 0, 0, &core_domain_ops, - NULL); + core_domain = irq_domain_add_linear(np, NR_PRIORITY_IRQS, + &core_domain_ops, NULL); if (core_domain) irq_set_default_host(core_domain); of_node_put(np); diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index ce46186600c..f4e72bd8c10 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -143,6 +143,10 @@ static void __init get_cpuinfo(void) p->cpu_name = "C64x+"; p->cpu_voltage = "1.2"; break; + case 21: + p->cpu_name = "C66X"; + p->cpu_voltage = "1.2"; + break; default: p->cpu_name = "unknown"; break; diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c index 3d8f3c22a94..3998b24e26f 100644 --- a/arch/c6x/kernel/signal.c +++ b/arch/c6x/kernel/signal.c @@ -249,8 +249,6 @@ static void handle_signal(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int syscall) { - int ret; - /* Are we from a system call? */ if (syscall) { /* If so, check system call restarting.. */ diff --git a/arch/c6x/kernel/soc.c b/arch/c6x/kernel/soc.c index 0748c94ebef..3ac74080fde 100644 --- a/arch/c6x/kernel/soc.c +++ b/arch/c6x/kernel/soc.c @@ -80,7 +80,7 @@ int soc_mac_addr(unsigned int index, u8 *addr) if (have_fuse_mac) memcpy(addr, c6x_fuse_mac, 6); else - random_ether_addr(addr); + eth_random_addr(addr); } /* adjust for specific EMAC device */ diff --git a/arch/c6x/platforms/Kconfig b/arch/c6x/platforms/Kconfig index 401ee678fd0..c4a0fad89aa 100644 --- a/arch/c6x/platforms/Kconfig +++ b/arch/c6x/platforms/Kconfig @@ -14,3 +14,7 @@ config SOC_TMS320C6472 config SOC_TMS320C6474 bool "TMS320C6474" default n + +config SOC_TMS320C6678 + bool "TMS320C6678" + default n diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c index c1c4e2ae3f8..74e3371eb82 100644 --- a/arch/c6x/platforms/megamod-pic.c +++ b/arch/c6x/platforms/megamod-pic.c @@ -243,27 +243,37 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) * as their interrupt parent. */ for (i = 0; i < NR_COMBINERS; i++) { + struct irq_data *irq_data; + irq_hw_number_t hwirq; irq = irq_of_parse_and_map(np, i); if (irq == NO_IRQ) continue; + irq_data = irq_get_irq_data(irq); + if (!irq_data) { + pr_err("%s: combiner-%d no irq_data for virq %d!\n", + np->full_name, i, irq); + continue; + } + + hwirq = irq_data->hwirq; + /* - * We count on the core priority interrupts (4 - 15) being - * direct mapped. Check that device tree provided something - * in that range. + * Check that device tree provided something in the range + * of the core priority interrupts (4 - 15). */ - if (irq < 4 || irq >= NR_PRIORITY_IRQS) { - pr_err("%s: combiner-%d virq %d out of range!\n", - np->full_name, i, irq); + if (hwirq < 4 || hwirq >= NR_PRIORITY_IRQS) { + pr_err("%s: combiner-%d core irq %ld out of range!\n", + np->full_name, i, hwirq); continue; } /* record the mapping */ - mapping[irq - 4] = i; + mapping[hwirq - 4] = i; - pr_debug("%s: combiner-%d cascading to virq %d\n", - np->full_name, i, irq); + pr_debug("%s: combiner-%d cascading to hwirq %ld\n", + np->full_name, i, hwirq); cascade_data[i].pic = pic; cascade_data[i].index = i; diff --git a/arch/c6x/platforms/plldata.c b/arch/c6x/platforms/plldata.c index 2cfd6f42968..755359eb628 100644 --- a/arch/c6x/platforms/plldata.c +++ b/arch/c6x/platforms/plldata.c @@ -335,6 +335,68 @@ static void __init c6474_setup_clocks(struct device_node *node) } #endif /* CONFIG_SOC_TMS320C6474 */ +#ifdef CONFIG_SOC_TMS320C6678 +static struct clk_lookup c6678_clks[] = { + CLK(NULL, "pll1", &c6x_soc_pll1.sysclks[0]), + CLK(NULL, "pll1_refclk", &c6x_soc_pll1.sysclks[1]), + CLK(NULL, "pll1_sysclk2", &c6x_soc_pll1.sysclks[2]), + CLK(NULL, "pll1_sysclk3", &c6x_soc_pll1.sysclks[3]), + CLK(NULL, "pll1_sysclk4", &c6x_soc_pll1.sysclks[4]), + CLK(NULL, "pll1_sysclk5", &c6x_soc_pll1.sysclks[5]), + CLK(NULL, "pll1_sysclk6", &c6x_soc_pll1.sysclks[6]), + CLK(NULL, "pll1_sysclk7", &c6x_soc_pll1.sysclks[7]), + CLK(NULL, "pll1_sysclk8", &c6x_soc_pll1.sysclks[8]), + CLK(NULL, "pll1_sysclk9", &c6x_soc_pll1.sysclks[9]), + CLK(NULL, "pll1_sysclk10", &c6x_soc_pll1.sysclks[10]), + CLK(NULL, "pll1_sysclk11", &c6x_soc_pll1.sysclks[11]), + CLK(NULL, "core", &c6x_core_clk), + CLK("", NULL, NULL) +}; + +static void __init c6678_setup_clocks(struct device_node *node) +{ + struct pll_data *pll = &c6x_soc_pll1; + struct clk *sysclks = pll->sysclks; + + pll->flags = PLL_HAS_MUL; + + sysclks[1].flags |= FIXED_DIV_PLL; + sysclks[1].div = 1; + + sysclks[2].div = PLLDIV2; + + sysclks[3].flags |= FIXED_DIV_PLL; + sysclks[3].div = 2; + + sysclks[4].flags |= FIXED_DIV_PLL; + sysclks[4].div = 3; + + sysclks[5].div = PLLDIV5; + + sysclks[6].flags |= FIXED_DIV_PLL; + sysclks[6].div = 64; + + sysclks[7].flags |= FIXED_DIV_PLL; + sysclks[7].div = 6; + + sysclks[8].div = PLLDIV8; + + sysclks[9].flags |= FIXED_DIV_PLL; + sysclks[9].div = 12; + + sysclks[10].flags |= FIXED_DIV_PLL; + sysclks[10].div = 3; + + sysclks[11].flags |= FIXED_DIV_PLL; + sysclks[11].div = 6; + + c6x_core_clk.parent = &sysclks[0]; + c6x_i2c_clk.parent = &sysclks[7]; + + c6x_clks_init(c6678_clks); +} +#endif /* CONFIG_SOC_TMS320C6678 */ + static struct of_device_id c6x_clkc_match[] __initdata = { #ifdef CONFIG_SOC_TMS320C6455 { .compatible = "ti,c6455-pll", .data = c6455_setup_clocks }, @@ -348,6 +410,9 @@ static struct of_device_id c6x_clkc_match[] __initdata = { #ifdef CONFIG_SOC_TMS320C6474 { .compatible = "ti,c6474-pll", .data = c6474_setup_clocks }, #endif +#ifdef CONFIG_SOC_TMS320C6678 + { .compatible = "ti,c6678-pll", .data = c6678_setup_clocks }, +#endif { .compatible = "ti,c64x+pll" }, {} }; diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index b9f82c84f09..ec6c6b30123 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -26,6 +26,7 @@ /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_IOAPIC +#define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_DEVICE_ASSIGNMENT /* Architectural interrupt line count. */ diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 7f4a0ed2415..5b7791dd396 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -12,7 +12,7 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(strlen); -#include<asm/pgtable.h> +#include <asm/pgtable.h> EXPORT_SYMBOL_GPL(empty_zero_page); #include <asm/checksum.h> diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig index 9806e55f91b..df5351e3eed 100644 --- a/arch/ia64/kvm/Kconfig +++ b/arch/ia64/kvm/Kconfig @@ -19,6 +19,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" + depends on BROKEN depends on HAVE_KVM && MODULES && EXPERIMENTAL # for device assignment: depends on PCI diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c index f0b9cac8241..176a12cd56d 100644 --- a/arch/ia64/kvm/vmm.c +++ b/arch/ia64/kvm/vmm.c @@ -20,9 +20,9 @@ */ -#include<linux/kernel.h> -#include<linux/module.h> -#include<asm/fpswa.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpswa.h> #include "vcpu.h" diff --git a/arch/m68k/include/asm/mcfne.h b/arch/m68k/include/asm/mcf8390.h index bf638be0958..a72a20819a5 100644 --- a/arch/m68k/include/asm/mcfne.h +++ b/arch/m68k/include/asm/mcf8390.h @@ -1,7 +1,7 @@ /****************************************************************************/ /* - * mcfne.h -- NE2000 in ColdFire eval boards. + * mcf8390.h -- NS8390 support for ColdFire eval boards. * * (C) Copyright 1999-2000, Greg Ungerer (gerg@snapgear.com) * (C) Copyright 2000, Lineo (www.lineo.com) @@ -14,8 +14,8 @@ */ /****************************************************************************/ -#ifndef mcfne_h -#define mcfne_h +#ifndef mcf8390_h +#define mcf8390_h /****************************************************************************/ @@ -37,6 +37,7 @@ #if defined(CONFIG_ARN5206) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0xf0 #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 4 @@ -46,6 +47,7 @@ #if defined(CONFIG_M5206eC3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1c #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 4 @@ -54,6 +56,7 @@ #if defined(CONFIG_M5206e) && defined(CONFIG_NETtel) #define NE2000_ADDR 0x30000300 +#define NE2000_ADDRSIZE 0x00001000 #define NE2000_IRQ_VECTOR 25 #define NE2000_IRQ_PRIORITY 1 #define NE2000_IRQ_LEVEL 3 @@ -63,6 +66,7 @@ #if defined(CONFIG_M5307C3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_BYTE volatile unsigned short #endif @@ -70,6 +74,7 @@ #if defined(CONFIG_M5272) && defined(CONFIG_NETtel) #define NE2000_ADDR 0x30600300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR 67 #undef BSWAP #define BSWAP(w) (w) @@ -82,6 +87,7 @@ #define NE2000_ADDR0 0x30600300 #define NE2000_ADDR1 0x30800300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR0 27 #define NE2000_IRQ_VECTOR1 29 #undef BSWAP @@ -94,6 +100,7 @@ #if defined(CONFIG_M5307) && defined(CONFIG_SECUREEDGEMP3) #define NE2000_ADDR 0x30600300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR 27 #undef BSWAP #define BSWAP(w) (w) @@ -105,6 +112,7 @@ #if defined(CONFIG_ARN5307) #define NE2000_ADDR 0xfe600300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 3 @@ -114,129 +122,10 @@ #if defined(CONFIG_M5407C3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_BYTE volatile unsigned short #endif /****************************************************************************/ - -/* - * Side-band address space for odd address requires re-mapping - * many of the standard ISA access functions. - */ -#ifdef NE2000_ODDOFFSET - -#undef outb -#undef outb_p -#undef inb -#undef inb_p -#undef outsb -#undef outsw -#undef insb -#undef insw - -#define outb ne2000_outb -#define inb ne2000_inb -#define outb_p ne2000_outb -#define inb_p ne2000_inb -#define outsb ne2000_outsb -#define outsw ne2000_outsw -#define insb ne2000_insb -#define insw ne2000_insw - - -#ifndef COLDFIRE_NE2000_FUNCS - -void ne2000_outb(unsigned int val, unsigned int addr); -int ne2000_inb(unsigned int addr); -void ne2000_insb(unsigned int addr, void *vbuf, int unsigned long len); -void ne2000_insw(unsigned int addr, void *vbuf, unsigned long len); -void ne2000_outsb(unsigned int addr, void *vbuf, unsigned long len); -void ne2000_outsw(unsigned int addr, void *vbuf, unsigned long len); - -#else - -/* - * This macro converts a conventional register address into the - * real memory pointer of the mapped NE2000 device. - * On most NE2000 implementations on ColdFire boards the chip is - * mapped in kinda funny, due to its ISA heritage. - */ -#define NE2000_PTR(addr) ((addr&0x1)?(NE2000_ODDOFFSET+addr-1):(addr)) -#define NE2000_DATA_PTR(addr) (addr) - - -void ne2000_outb(unsigned int val, unsigned int addr) -{ - NE2000_BYTE *rp; - - rp = (NE2000_BYTE *) NE2000_PTR(addr); - *rp = RSWAP(val); -} - -int ne2000_inb(unsigned int addr) -{ - NE2000_BYTE *rp, val; - - rp = (NE2000_BYTE *) NE2000_PTR(addr); - val = *rp; - return((int) ((NE2000_BYTE) RSWAP(val))); -} - -void ne2000_insb(unsigned int addr, void *vbuf, int unsigned long len) -{ - NE2000_BYTE *rp, val; - unsigned char *buf; - - buf = (unsigned char *) vbuf; - rp = (NE2000_BYTE *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - val = *rp; - *buf++ = RSWAP(val); - } -} - -void ne2000_insw(unsigned int addr, void *vbuf, unsigned long len) -{ - volatile unsigned short *rp; - unsigned short w, *buf; - - buf = (unsigned short *) vbuf; - rp = (volatile unsigned short *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - w = *rp; - *buf++ = BSWAP(w); - } -} - -void ne2000_outsb(unsigned int addr, const void *vbuf, unsigned long len) -{ - NE2000_BYTE *rp, val; - unsigned char *buf; - - buf = (unsigned char *) vbuf; - rp = (NE2000_BYTE *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - val = *buf++; - *rp = RSWAP(val); - } -} - -void ne2000_outsw(unsigned int addr, const void *vbuf, unsigned long len) -{ - volatile unsigned short *rp; - unsigned short w, *buf; - - buf = (unsigned short *) vbuf; - rp = (volatile unsigned short *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - w = *buf++; - *rp = BSWAP(w); - } -} - -#endif /* COLDFIRE_NE2000_FUNCS */ -#endif /* NE2000_OFFOFFSET */ - -/****************************************************************************/ -#endif /* mcfne_h */ +#endif /* mcf8390_h */ diff --git a/arch/m68k/kernel/module.c b/arch/m68k/kernel/module.c index 34849c4c6e3..eb46fd6038c 100644 --- a/arch/m68k/kernel/module.c +++ b/arch/m68k/kernel/module.c @@ -47,7 +47,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_68K_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; default: @@ -87,7 +87,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, *location = rel[i].r_addend + sym->st_value; break; case R_68K_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location = rel[i].r_addend + sym->st_value - (uint32_t)location; break; default: diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 1a24d317e7a..1bbc24b0868 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -310,10 +310,10 @@ static void __init cpmac_get_mac(int instance, unsigned char *dev_addr) &dev_addr[4], &dev_addr[5]) != 6) { pr_warning("cannot parse mac address, " "using random address\n"); - random_ether_addr(dev_addr); + eth_random_addr(dev_addr); } } else - random_ether_addr(dev_addr); + eth_random_addr(dev_addr); } /***************************************************************************** diff --git a/arch/mips/powertv/powertv_setup.c b/arch/mips/powertv/powertv_setup.c index 3933c373a43..820b8480f22 100644 --- a/arch/mips/powertv/powertv_setup.c +++ b/arch/mips/powertv/powertv_setup.c @@ -254,7 +254,7 @@ early_param("rfmac", rfmac_param); * Generates an Ethernet MAC address that is highly likely to be unique for * this particular system on a network with other systems of the same type. * - * The problem we are solving is that, when random_ether_addr() is used to + * The problem we are solving is that, when eth_random_addr() is used to * generate MAC addresses at startup, there isn't much entropy for the random * number generator to use and the addresses it produces are fairly likely to * be the same as those of other identical systems on the same local network. @@ -269,7 +269,7 @@ early_param("rfmac", rfmac_param); * Still, this does give us something to work with. * * The approach we take is: - * 1. If we can't get the RF MAC Address, just call random_ether_addr. + * 1. If we can't get the RF MAC Address, just call eth_random_addr. * 2. Use the 24-bit NIC-specific bits of the RF MAC address as the last 24 * bits of the new address. This is very likely to be unique, except for * the current box. @@ -299,7 +299,7 @@ void platform_random_ether_addr(u8 addr[ETH_ALEN]) if (!have_rfmac) { pr_warning("rfmac not available on command line; " "generating random MAC address\n"); - random_ether_addr(addr); + eth_random_addr(addr); } else { diff --git a/arch/parisc/include/asm/compat_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h index 81bec28bdc4..b3f95a7f18b 100644 --- a/arch/parisc/include/asm/compat_rt_sigframe.h +++ b/arch/parisc/include/asm/compat_rt_sigframe.h @@ -1,6 +1,6 @@ -#include<linux/compat.h> -#include<linux/compat_siginfo.h> -#include<asm/compat_ucontext.h> +#include <linux/compat.h> +#include <linux/compat_siginfo.h> +#include <asm/compat_ucontext.h> #ifndef _ASM_PARISC_COMPAT_RT_SIGFRAME_H #define _ASM_PARISC_COMPAT_RT_SIGFRAME_H diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index 976835d8f22..bf2c06c3387 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -153,6 +153,8 @@ #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5" #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4" +extern bool epapr_paravirt_enabled; +extern u32 epapr_hypercall_start[]; /* * We use "uintptr_t" to define a register because it's guaranteed to be a diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 0554ab062bd..e45c4947a77 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -34,6 +34,8 @@ extern void __replay_interrupt(unsigned int vector); extern void timer_interrupt(struct pt_regs *); extern void performance_monitor_exception(struct pt_regs *regs); +extern void WatchdogException(struct pt_regs *regs); +extern void unknown_exception(struct pt_regs *regs); #ifdef CONFIG_PPC64 #include <asm/paca.h> diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index b0c08b14277..0dd1d86d3e3 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -36,11 +36,8 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #define SPAPR_TCE_SHIFT 12 #ifdef CONFIG_KVM_BOOK3S_64_HV -/* For now use fixed-size 16MB page table */ -#define HPT_ORDER 24 -#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */ -#define HPT_NPTE (HPT_NPTEG << 3) /* 8 PTEs per PTEG */ -#define HPT_HASH_MASK (HPT_NPTEG - 1) +#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ +extern int kvm_hpt_order; /* order of preallocated HPTs */ #endif #define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d848cdc4971..50ea12fd7bf 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -237,6 +237,10 @@ struct kvm_arch { unsigned long vrma_slb_v; int rma_setup_done; int using_mmu_notifiers; + u32 hpt_order; + atomic_t vcpus_running; + unsigned long hpt_npte; + unsigned long hpt_mask; spinlock_t slot_phys_lock; unsigned long *slot_phys[KVM_MEM_SLOTS_NUM]; int slot_npages[KVM_MEM_SLOTS_NUM]; @@ -414,7 +418,9 @@ struct kvm_vcpu_arch { ulong mcsrr1; ulong mcsr; u32 dec; +#ifdef CONFIG_BOOKE u32 decar; +#endif u32 tbl; u32 tbu; u32 tcr; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index f68c22fa2fc..0124937a23b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -119,7 +119,8 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); -extern long kvmppc_alloc_hpt(struct kvm *kvm); +extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp); +extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp); extern void kvmppc_free_hpt(struct kvm *kvm); extern long kvmppc_prepare_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 83afacd3ba7..bb282dd8161 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -128,6 +128,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) obj-y += ppc_save_regs.o endif +obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o # Disable GCOV in odd or sensitive code diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S new file mode 100644 index 00000000000..697b390ebfd --- /dev/null +++ b/arch/powerpc/kernel/epapr_hcalls.S @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2012 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/threads.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* Hypercall entry point. Will be patched with device tree instructions. */ +.global epapr_hypercall_start +epapr_hypercall_start: + li r3, -1 + nop + nop + nop + blr diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c new file mode 100644 index 00000000000..028aeae370b --- /dev/null +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -0,0 +1,52 @@ +/* + * ePAPR para-virtualization support. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright (C) 2012 Freescale Semiconductor, Inc. + */ + +#include <linux/of.h> +#include <asm/epapr_hcalls.h> +#include <asm/cacheflush.h> +#include <asm/code-patching.h> + +bool epapr_paravirt_enabled; + +static int __init epapr_paravirt_init(void) +{ + struct device_node *hyper_node; + const u32 *insts; + int len, i; + + hyper_node = of_find_node_by_path("/hypervisor"); + if (!hyper_node) + return -ENODEV; + + insts = of_get_property(hyper_node, "hcall-instructions", &len); + if (!insts) + return -ENODEV; + + if (len % 4 || len > (4 * 4)) + return -ENODEV; + + for (i = 0; i < (len / 4); i++) + patch_instruction(epapr_hypercall_start + i, insts[i]); + + epapr_paravirt_enabled = true; + + return 0; +} + +early_initcall(epapr_paravirt_init); diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 02c167db6ba..867db1de894 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -31,6 +31,7 @@ #include <asm/cacheflush.h> #include <asm/disassemble.h> #include <asm/ppc-opcode.h> +#include <asm/epapr_hcalls.h> #define KVM_MAGIC_PAGE (-4096L) #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x) @@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in, unsigned long register r11 asm("r11") = nr; unsigned long register r12 asm("r12"); - asm volatile("bl kvm_hypercall_start" + asm volatile("bl epapr_hypercall_start" : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6), "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11), "=r"(r12) @@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in, } EXPORT_SYMBOL_GPL(kvm_hypercall); -static int kvm_para_setup(void) -{ - extern u32 kvm_hypercall_start; - struct device_node *hyper_node; - u32 *insts; - int len, i; - - hyper_node = of_find_node_by_path("/hypervisor"); - if (!hyper_node) - return -1; - - insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len); - if (len % 4) - return -1; - if (len > (4 * 4)) - return -1; - - for (i = 0; i < (len / 4); i++) - kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]); - - return 0; -} - static __init void kvm_free_tmp(void) { unsigned long start, end; @@ -791,7 +769,7 @@ static int __init kvm_guest_init(void) if (!kvm_para_available()) goto free_tmp; - if (kvm_para_setup()) + if (!epapr_paravirt_enabled) goto free_tmp; if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE)) diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S index e291cf3cf95..e100ff324a8 100644 --- a/arch/powerpc/kernel/kvm_emul.S +++ b/arch/powerpc/kernel/kvm_emul.S @@ -24,16 +24,6 @@ #include <asm/page.h> #include <asm/asm-offsets.h> -/* Hypercall entry point. Will be patched with device tree instructions. */ - -.global kvm_hypercall_start -kvm_hypercall_start: - li r3, -1 - nop - nop - nop - blr - #define KVM_MAGIC_PAGE (-4096) #ifdef CONFIG_64BIT @@ -132,7 +122,7 @@ kvm_emulate_mtmsrd_len: .long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4 -#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI) +#define MSR_SAFE_BITS (MSR_EE | MSR_RI) #define MSR_CRITICAL_BITS ~MSR_SAFE_BITS .global kvm_emulate_mtmsr diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 80a57751758..d03eb6f7b05 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -37,56 +37,121 @@ /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */ #define MAX_LPID_970 63 -long kvmppc_alloc_hpt(struct kvm *kvm) +/* Power architecture requires HPT is at least 256kB */ +#define PPC_MIN_HPT_ORDER 18 + +long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) { unsigned long hpt; - long lpid; struct revmap_entry *rev; struct kvmppc_linear_info *li; + long order = kvm_hpt_order; - /* Allocate guest's hashed page table */ - li = kvm_alloc_hpt(); - if (li) { - /* using preallocated memory */ - hpt = (ulong)li->base_virt; - kvm->arch.hpt_li = li; - } else { - /* using dynamic memory */ + if (htab_orderp) { + order = *htab_orderp; + if (order < PPC_MIN_HPT_ORDER) + order = PPC_MIN_HPT_ORDER; + } + + /* + * If the user wants a different size from default, + * try first to allocate it from the kernel page allocator. + */ + hpt = 0; + if (order != kvm_hpt_order) { hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| - __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT); + __GFP_NOWARN, order - PAGE_SHIFT); + if (!hpt) + --order; } + /* Next try to allocate from the preallocated pool */ if (!hpt) { - pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n"); - return -ENOMEM; + li = kvm_alloc_hpt(); + if (li) { + hpt = (ulong)li->base_virt; + kvm->arch.hpt_li = li; + order = kvm_hpt_order; + } } + + /* Lastly try successively smaller sizes from the page allocator */ + while (!hpt && order > PPC_MIN_HPT_ORDER) { + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| + __GFP_NOWARN, order - PAGE_SHIFT); + if (!hpt) + --order; + } + + if (!hpt) + return -ENOMEM; + kvm->arch.hpt_virt = hpt; + kvm->arch.hpt_order = order; + /* HPTEs are 2**4 bytes long */ + kvm->arch.hpt_npte = 1ul << (order - 4); + /* 128 (2**7) bytes in each HPTEG */ + kvm->arch.hpt_mask = (1ul << (order - 7)) - 1; /* Allocate reverse map array */ - rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE); + rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte); if (!rev) { pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n"); goto out_freehpt; } kvm->arch.revmap = rev; + kvm->arch.sdr1 = __pa(hpt) | (order - 18); - lpid = kvmppc_alloc_lpid(); - if (lpid < 0) - goto out_freeboth; + pr_info("KVM guest htab at %lx (order %ld), LPID %x\n", + hpt, order, kvm->arch.lpid); - kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18); - kvm->arch.lpid = lpid; - - pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid); + if (htab_orderp) + *htab_orderp = order; return 0; - out_freeboth: - vfree(rev); out_freehpt: - free_pages(hpt, HPT_ORDER - PAGE_SHIFT); + if (kvm->arch.hpt_li) + kvm_release_hpt(kvm->arch.hpt_li); + else + free_pages(hpt, order - PAGE_SHIFT); return -ENOMEM; } +long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) +{ + long err = -EBUSY; + long order; + + mutex_lock(&kvm->lock); + if (kvm->arch.rma_setup_done) { + kvm->arch.rma_setup_done = 0; + /* order rma_setup_done vs. vcpus_running */ + smp_mb(); + if (atomic_read(&kvm->arch.vcpus_running)) { + kvm->arch.rma_setup_done = 1; + goto out; + } + } + if (kvm->arch.hpt_virt) { + order = kvm->arch.hpt_order; + /* Set the entire HPT to 0, i.e. invalid HPTEs */ + memset((void *)kvm->arch.hpt_virt, 0, 1ul << order); + /* + * Set the whole last_vcpu array to an invalid vcpu number. + * This ensures that each vcpu will flush its TLB on next entry. + */ + memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu)); + *htab_orderp = order; + err = 0; + } else { + err = kvmppc_alloc_hpt(kvm, htab_orderp); + order = *htab_orderp; + } + out: + mutex_unlock(&kvm->lock); + return err; +} + void kvmppc_free_hpt(struct kvm *kvm) { kvmppc_free_lpid(kvm->arch.lpid); @@ -94,7 +159,8 @@ void kvmppc_free_hpt(struct kvm *kvm) if (kvm->arch.hpt_li) kvm_release_hpt(kvm->arch.hpt_li); else - free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT); + free_pages(kvm->arch.hpt_virt, + kvm->arch.hpt_order - PAGE_SHIFT); } /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */ @@ -119,6 +185,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long psize; unsigned long hp0, hp1; long ret; + struct kvm *kvm = vcpu->kvm; psize = 1ul << porder; npages = memslot->npages >> (porder - PAGE_SHIFT); @@ -127,8 +194,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, if (npages > 1ul << (40 - porder)) npages = 1ul << (40 - porder); /* Can't use more than 1 HPTE per HPTEG */ - if (npages > HPT_NPTEG) - npages = HPT_NPTEG; + if (npages > kvm->arch.hpt_mask + 1) + npages = kvm->arch.hpt_mask + 1; hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) | HPTE_V_BOLTED | hpte0_pgsize_encoding(psize); @@ -138,7 +205,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, for (i = 0; i < npages; ++i) { addr = i << porder; /* can't use hpt_hash since va > 64 bits */ - hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK; + hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask; /* * We assume that the hash table is empty and no * vcpus are using it at this stage. Since we create diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 3abe1b86e58..83e929e66f9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -56,7 +56,7 @@ /* #define EXIT_DEBUG_INT */ static void kvmppc_end_cede(struct kvm_vcpu *vcpu); -static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu); +static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { @@ -1104,11 +1104,15 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) return -EINTR; } - /* On the first time here, set up VRMA or RMA */ + atomic_inc(&vcpu->kvm->arch.vcpus_running); + /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */ + smp_mb(); + + /* On the first time here, set up HTAB and VRMA or RMA */ if (!vcpu->kvm->arch.rma_setup_done) { - r = kvmppc_hv_setup_rma(vcpu); + r = kvmppc_hv_setup_htab_rma(vcpu); if (r) - return r; + goto out; } flush_fp_to_thread(current); @@ -1126,6 +1130,9 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); } } while (r == RESUME_GUEST); + + out: + atomic_dec(&vcpu->kvm->arch.vcpus_running); return r; } @@ -1341,7 +1348,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, { } -static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) +static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; struct kvm *kvm = vcpu->kvm; @@ -1360,6 +1367,15 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) if (kvm->arch.rma_setup_done) goto out; /* another vcpu beat us to it */ + /* Allocate hashed page table (if not done already) and reset it */ + if (!kvm->arch.hpt_virt) { + err = kvmppc_alloc_hpt(kvm, NULL); + if (err) { + pr_err("KVM: Couldn't alloc HPT\n"); + goto out; + } + } + /* Look up the memslot for guest physical address 0 */ memslot = gfn_to_memslot(kvm, 0); @@ -1471,13 +1487,14 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) int kvmppc_core_init_vm(struct kvm *kvm) { - long r; - unsigned long lpcr; + unsigned long lpcr, lpid; - /* Allocate hashed page table */ - r = kvmppc_alloc_hpt(kvm); - if (r) - return r; + /* Allocate the guest's logical partition ID */ + + lpid = kvmppc_alloc_lpid(); + if (lpid < 0) + return -ENOMEM; + kvm->arch.lpid = lpid; INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); @@ -1487,7 +1504,6 @@ int kvmppc_core_init_vm(struct kvm *kvm) if (cpu_has_feature(CPU_FTR_ARCH_201)) { /* PPC970; HID4 is effectively the LPCR */ - unsigned long lpid = kvm->arch.lpid; kvm->arch.host_lpid = 0; kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4); lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH)); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index e1b60f56f2a..fb4eac290fe 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -25,6 +25,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type); static struct kvmppc_linear_info *kvm_alloc_linear(int type); static void kvm_release_linear(struct kvmppc_linear_info *ri); +int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER; +EXPORT_SYMBOL_GPL(kvm_hpt_order); + /*************** RMA *************/ /* @@ -209,7 +212,7 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri) void __init kvm_linear_init(void) { /* HPT */ - kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT); + kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT); /* RMA */ /* Only do this on PPC970 in HV mode */ diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index cec4daddbf3..5c70d19494f 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -237,7 +237,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, /* Find and lock the HPTEG slot to use */ do_insert: - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; if (likely((flags & H_EXACT) == 0)) { pte_index &= ~7UL; @@ -352,7 +352,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long v, r, rb; struct revmap_entry *rev; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) @@ -419,7 +419,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) i = 4; break; } - if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) { + if (req != 1 || flags == 3 || + pte_index >= kvm->arch.hpt_npte) { /* parameter error */ args[j] = ((0xa0 | flags) << 56) + pte_index; ret = H_PARAMETER; @@ -521,7 +522,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, struct revmap_entry *rev; unsigned long v, r, rb, mask, bits; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); @@ -583,7 +584,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, int i, n = 1; struct revmap_entry *rev = NULL; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; if (flags & H_READ_4) { pte_index &= ~3; @@ -678,7 +679,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, somask = (1UL << 28) - 1; vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT; } - hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK; + hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask; avpn = slb_v & ~(somask >> 16); /* also includes B */ avpn |= (eaddr & somask) >> 16; @@ -723,7 +724,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, if (val & HPTE_V_SECONDARY) break; val |= HPTE_V_SECONDARY; - hash = hash ^ HPT_HASH_MASK; + hash = hash ^ kvm->arch.hpt_mask; } return -1; } diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 72f13f4a06e..d25a097c852 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -612,6 +612,12 @@ static void kvmppc_fill_pt_regs(struct pt_regs *regs) regs->link = lr; } +/* + * For interrupts needed to be handled by host interrupt handlers, + * corresponding host handler are called from here in similar way + * (but not exact) as they are called from low level handler + * (such as from arch/powerpc/kernel/head_fsl_booke.S). + */ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -639,6 +645,17 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, kvmppc_fill_pt_regs(®s); performance_monitor_exception(®s); break; + case BOOKE_INTERRUPT_WATCHDOG: + kvmppc_fill_pt_regs(®s); +#ifdef CONFIG_BOOKE_WDT + WatchdogException(®s); +#else + unknown_exception(®s); +#endif + break; + case BOOKE_INTERRUPT_CRITICAL: + unknown_exception(®s); + break; } } @@ -683,6 +700,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_GUEST; break; + case BOOKE_INTERRUPT_WATCHDOG: + r = RESUME_GUEST; + break; + case BOOKE_INTERRUPT_DOORBELL: kvmppc_account_exit(vcpu, DBELL_EXITS); r = RESUME_GUEST; @@ -1267,6 +1288,11 @@ void kvmppc_decrementer_func(unsigned long data) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; + if (vcpu->arch.tcr & TCR_ARE) { + vcpu->arch.dec = vcpu->arch.decar; + kvmppc_emulate_dec(vcpu); + } + kvmppc_set_tsr_bits(vcpu, TSR_DIS); } diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c index 6c76397f2af..12834bb608a 100644 --- a/arch/powerpc/kvm/booke_emulate.c +++ b/arch/powerpc/kvm/booke_emulate.c @@ -24,6 +24,7 @@ #include "booke.h" #define OP_19_XOP_RFI 50 +#define OP_19_XOP_RFCI 51 #define OP_31_XOP_MFMSR 83 #define OP_31_XOP_WRTEE 131 @@ -36,6 +37,12 @@ static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu) kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1); } +static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pc = vcpu->arch.csrr0; + kvmppc_set_msr(vcpu, vcpu->arch.csrr1); +} + int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { @@ -52,6 +59,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, *advance = 0; break; + case OP_19_XOP_RFCI: + kvmppc_emul_rfci(vcpu); + kvmppc_set_exit_type(vcpu, EMULATED_RFCI_EXITS); + *advance = 0; + break; + default: emulated = EMULATE_FAIL; break; @@ -113,6 +126,12 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_ESR: vcpu->arch.shared->esr = spr_val; break; + case SPRN_CSRR0: + vcpu->arch.csrr0 = spr_val; + break; + case SPRN_CSRR1: + vcpu->arch.csrr1 = spr_val; + break; case SPRN_DBCR0: vcpu->arch.dbcr0 = spr_val; break; @@ -129,6 +148,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) kvmppc_set_tcr(vcpu, spr_val); break; + case SPRN_DECAR: + vcpu->arch.decar = spr_val; + break; /* * Note: SPRG4-7 are user-readable. * These values are loaded into the real SPRGs when resuming the @@ -229,6 +251,12 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) case SPRN_ESR: *spr_val = vcpu->arch.shared->esr; break; + case SPRN_CSRR0: + *spr_val = vcpu->arch.csrr0; + break; + case SPRN_CSRR1: + *spr_val = vcpu->arch.csrr1; + break; case SPRN_DBCR0: *spr_val = vcpu->arch.dbcr0; break; diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 8fd4b2a0911..bb46b32f981 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -52,16 +52,21 @@ (1<<BOOKE_INTERRUPT_PROGRAM) | \ (1<<BOOKE_INTERRUPT_DTLB_MISS)) -.macro KVM_HANDLER ivor_nr +.macro KVM_HANDLER ivor_nr scratch srr0 _GLOBAL(kvmppc_handler_\ivor_nr) /* Get pointer to vcpu and record exit number. */ - mtspr SPRN_SPRG_WSCRATCH0, r4 + mtspr \scratch , r4 mfspr r4, SPRN_SPRG_RVCPU + stw r3, VCPU_GPR(R3)(r4) stw r5, VCPU_GPR(R5)(r4) stw r6, VCPU_GPR(R6)(r4) + mfspr r3, \scratch mfctr r5 - lis r6, kvmppc_resume_host@h + stw r3, VCPU_GPR(R4)(r4) stw r5, VCPU_CTR(r4) + mfspr r3, \srr0 + lis r6, kvmppc_resume_host@h + stw r3, VCPU_PC(r4) li r5, \ivor_nr ori r6, r6, kvmppc_resume_host@l mtctr r6 @@ -69,37 +74,35 @@ _GLOBAL(kvmppc_handler_\ivor_nr) .endm _GLOBAL(kvmppc_handlers_start) -KVM_HANDLER BOOKE_INTERRUPT_CRITICAL -KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK -KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE -KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE -KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL -KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT -KVM_HANDLER BOOKE_INTERRUPT_PROGRAM -KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_SYSCALL -KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER -KVM_HANDLER BOOKE_INTERRUPT_FIT -KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG -KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS -KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS -KVM_HANDLER BOOKE_INTERRUPT_DEBUG -KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA -KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND +KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0 +KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0 _GLOBAL(kvmppc_handler_len) .long kvmppc_handler_1 - kvmppc_handler_0 - /* Registers: * SPRG_SCRATCH0: guest r4 * r4: vcpu pointer * r5: KVM exit number */ _GLOBAL(kvmppc_resume_host) - stw r3, VCPU_GPR(R3)(r4) mfcr r3 stw r3, VCPU_CR(r4) stw r7, VCPU_GPR(R7)(r4) @@ -180,10 +183,6 @@ _GLOBAL(kvmppc_resume_host) stw r3, VCPU_LR(r4) mfxer r3 stw r3, VCPU_XER(r4) - mfspr r3, SPRN_SPRG_RSCRATCH0 - stw r3, VCPU_GPR(R4)(r4) - mfspr r3, SPRN_SRR0 - stw r3, VCPU_PC(r4) /* Restore host stack pointer and PID before IVPR, since the host * exception handlers use them. */ diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index 1685dc43bcf..d28c2d43ac1 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -262,7 +262,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \ kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \ SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0 kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \ - SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR) + SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR) kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \ diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 8b99e076dc8..e04b0ef55ce 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -269,6 +269,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) *spr_val = vcpu->arch.shared->mas7_3 >> 32; break; #endif + case SPRN_DECAR: + *spr_val = vcpu->arch.decar; + break; case SPRN_TLB0CFG: *spr_val = vcpu->arch.tlbcfg[0]; break; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index fe6c1de6b70..1f89d26e65f 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved. * * Author: Varun Sethi, <varun.sethi@freescale.com> * @@ -57,7 +57,8 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500, struct kvm_book3e_206_tlb_entry *gtlbe) { unsigned int tid, ts; - u32 val, eaddr, lpid; + gva_t eaddr; + u32 val, lpid; unsigned long flags; ts = get_tlb_ts(gtlbe); @@ -183,6 +184,9 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \ SPRN_EPCR_DUVD; +#ifdef CONFIG_64BIT + vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM; +#endif vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP; vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT); vcpu->arch.epsc = vcpu->arch.eplc; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index f90e86dea7a..ee04abaefe2 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -59,11 +59,13 @@ #define OP_31_XOP_STHBRX 918 #define OP_LWZ 32 +#define OP_LD 58 #define OP_LWZU 33 #define OP_LBZ 34 #define OP_LBZU 35 #define OP_STW 36 #define OP_STWU 37 +#define OP_STD 62 #define OP_STB 38 #define OP_STBU 39 #define OP_LHZ 40 @@ -392,6 +394,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); break; + /* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */ + case OP_LD: + rt = get_rt(inst); + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + break; + case OP_LWZU: emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); @@ -412,6 +420,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) 4, 1); break; + /* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */ + case OP_STD: + rs = get_rs(inst); + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), + 8, 1); + break; + case OP_STWU: emulated = kvmppc_handle_store(run, vcpu, kvmppc_get_gpr(vcpu, rs), diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1493c8de947..87f4dc88607 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -246,6 +246,7 @@ int kvm_dev_ioctl_check_extension(long ext) #endif #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: + case KVM_CAP_PPC_ALLOC_HTAB: r = 1; break; #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -802,6 +803,23 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + + case KVM_PPC_ALLOCATE_HTAB: { + struct kvm *kvm = filp->private_data; + u32 htab_order; + + r = -EFAULT; + if (get_user(htab_order, (u32 __user *)argp)) + break; + r = kvmppc_alloc_reset_hpt(kvm, &htab_order); + if (r) + break; + r = -EFAULT; + if (put_user(htab_order, (u32 __user *)argp)) + break; + r = 0; + break; + } #endif /* CONFIG_KVM_BOOK3S_64_HV */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index a35ca44ade6..e7a896acd98 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -25,6 +25,7 @@ source "arch/powerpc/platforms/wsp/Kconfig" config KVM_GUEST bool "KVM Guest support" default n + select EPAPR_PARAVIRT ---help--- This option enables various optimizations for running under the KVM hypervisor. Overhead for the kernel when not running inside KVM should @@ -32,6 +33,14 @@ config KVM_GUEST In case of doubt, say Y +config EPAPR_PARAVIRT + bool "ePAPR para-virtualization support" + default n + help + Enables ePAPR para-virtualization support for guests. + + In case of doubt, say Y + config PPC_NATIVE bool depends on 6xx || PPC64 diff --git a/arch/s390/appldata/appldata.h b/arch/s390/appldata/appldata.h index f0b23fc759b..4a67f2b5f6a 100644 --- a/arch/s390/appldata/appldata.h +++ b/arch/s390/appldata/appldata.h @@ -1,6 +1,4 @@ /* - * arch/s390/appldata/appldata.h - * * Definitions and interface for Linux - z/VM Monitor Stream. * * Copyright IBM Corp. 2003, 2008 diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 24bff4f1cc5..bae0f402bf2 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -1,6 +1,4 @@ /* - * arch/s390/appldata/appldata_base.c - * * Base infrastructure for Linux-z/VM Monitor Stream, Stage 1. * Exports appldata_register_ops() and appldata_unregister_ops() for the * data gathering modules. @@ -29,7 +27,7 @@ #include <linux/suspend.h> #include <linux/platform_device.h> #include <asm/appldata.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/smp.h> @@ -84,8 +82,7 @@ static struct ctl_table appldata_dir_table[] = { /* * Timer */ -static DEFINE_PER_CPU(struct vtimer_list, appldata_timer); -static atomic_t appldata_expire_count = ATOMIC_INIT(0); +static struct vtimer_list appldata_timer; static DEFINE_SPINLOCK(appldata_timer_lock); static int appldata_interval = APPLDATA_CPU_INTERVAL; @@ -115,10 +112,7 @@ static LIST_HEAD(appldata_ops_list); */ static void appldata_timer_function(unsigned long data) { - if (atomic_dec_and_test(&appldata_expire_count)) { - atomic_set(&appldata_expire_count, num_online_cpus()); - queue_work(appldata_wq, (struct work_struct *) data); - } + queue_work(appldata_wq, (struct work_struct *) data); } /* @@ -131,7 +125,6 @@ static void appldata_work_fn(struct work_struct *work) struct list_head *lh; struct appldata_ops *ops; - get_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { ops = list_entry(lh, struct appldata_ops, list); @@ -140,7 +133,6 @@ static void appldata_work_fn(struct work_struct *work) } } mutex_unlock(&appldata_ops_mutex); - put_online_cpus(); } /* @@ -168,20 +160,6 @@ int appldata_diag(char record_nr, u16 function, unsigned long buffer, /****************************** /proc stuff **********************************/ -/* - * appldata_mod_vtimer_wrap() - * - * wrapper function for mod_virt_timer(), because smp_call_function_single() - * accepts only one parameter. - */ -static void __appldata_mod_vtimer_wrap(void *p) { - struct { - struct vtimer_list *timer; - u64 expires; - } *args = p; - mod_virt_timer_periodic(args->timer, args->expires); -} - #define APPLDATA_ADD_TIMER 0 #define APPLDATA_DEL_TIMER 1 #define APPLDATA_MOD_TIMER 2 @@ -192,49 +170,28 @@ static void __appldata_mod_vtimer_wrap(void *p) { * Add, delete or modify virtual timers on all online cpus. * The caller needs to get the appldata_timer_lock spinlock. */ -static void -__appldata_vtimer_setup(int cmd) +static void __appldata_vtimer_setup(int cmd) { - u64 per_cpu_interval; - int i; + u64 timer_interval = (u64) appldata_interval * 1000 * TOD_MICRO; switch (cmd) { case APPLDATA_ADD_TIMER: if (appldata_timer_active) break; - per_cpu_interval = (u64) (appldata_interval*1000 / - num_online_cpus()) * TOD_MICRO; - for_each_online_cpu(i) { - per_cpu(appldata_timer, i).expires = per_cpu_interval; - smp_call_function_single(i, add_virt_timer_periodic, - &per_cpu(appldata_timer, i), - 1); - } + appldata_timer.expires = timer_interval; + add_virt_timer_periodic(&appldata_timer); appldata_timer_active = 1; break; case APPLDATA_DEL_TIMER: - for_each_online_cpu(i) - del_virt_timer(&per_cpu(appldata_timer, i)); + del_virt_timer(&appldata_timer); if (!appldata_timer_active) break; appldata_timer_active = 0; - atomic_set(&appldata_expire_count, num_online_cpus()); break; case APPLDATA_MOD_TIMER: - per_cpu_interval = (u64) (appldata_interval*1000 / - num_online_cpus()) * TOD_MICRO; if (!appldata_timer_active) break; - for_each_online_cpu(i) { - struct { - struct vtimer_list *timer; - u64 expires; - } args; - args.timer = &per_cpu(appldata_timer, i); - args.expires = per_cpu_interval; - smp_call_function_single(i, __appldata_mod_vtimer_wrap, - &args, 1); - } + mod_virt_timer_periodic(&appldata_timer, timer_interval); } } @@ -265,14 +222,12 @@ appldata_timer_handler(ctl_table *ctl, int write, len = *lenp; if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) return -EFAULT; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (buf[0] == '1') __appldata_vtimer_setup(APPLDATA_ADD_TIMER); else if (buf[0] == '0') __appldata_vtimer_setup(APPLDATA_DEL_TIMER); spin_unlock(&appldata_timer_lock); - put_online_cpus(); out: *lenp = len; *ppos += len; @@ -305,20 +260,17 @@ appldata_interval_handler(ctl_table *ctl, int write, goto out; } len = *lenp; - if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) { + if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) return -EFAULT; - } interval = 0; sscanf(buf, "%i", &interval); if (interval <= 0) return -EINVAL; - get_online_cpus(); spin_lock(&appldata_timer_lock); appldata_interval = interval; __appldata_vtimer_setup(APPLDATA_MOD_TIMER); spin_unlock(&appldata_timer_lock); - put_online_cpus(); out: *lenp = len; *ppos += len; @@ -485,14 +437,12 @@ static int appldata_freeze(struct device *dev) int rc; struct list_head *lh; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (appldata_timer_active) { __appldata_vtimer_setup(APPLDATA_DEL_TIMER); appldata_timer_suspended = 1; } spin_unlock(&appldata_timer_lock); - put_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { @@ -516,14 +466,12 @@ static int appldata_restore(struct device *dev) int rc; struct list_head *lh; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (appldata_timer_suspended) { __appldata_vtimer_setup(APPLDATA_ADD_TIMER); appldata_timer_suspended = 0; } spin_unlock(&appldata_timer_lock); - put_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { @@ -567,53 +515,6 @@ static struct platform_driver appldata_pdrv = { /******************************* init / exit *********************************/ -static void __cpuinit appldata_online_cpu(int cpu) -{ - init_virt_timer(&per_cpu(appldata_timer, cpu)); - per_cpu(appldata_timer, cpu).function = appldata_timer_function; - per_cpu(appldata_timer, cpu).data = (unsigned long) - &appldata_work; - atomic_inc(&appldata_expire_count); - spin_lock(&appldata_timer_lock); - __appldata_vtimer_setup(APPLDATA_MOD_TIMER); - spin_unlock(&appldata_timer_lock); -} - -static void __cpuinit appldata_offline_cpu(int cpu) -{ - del_virt_timer(&per_cpu(appldata_timer, cpu)); - if (atomic_dec_and_test(&appldata_expire_count)) { - atomic_set(&appldata_expire_count, num_online_cpus()); - queue_work(appldata_wq, &appldata_work); - } - spin_lock(&appldata_timer_lock); - __appldata_vtimer_setup(APPLDATA_MOD_TIMER); - spin_unlock(&appldata_timer_lock); -} - -static int __cpuinit appldata_cpu_notify(struct notifier_block *self, - unsigned long action, - void *hcpu) -{ - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - appldata_online_cpu((long) hcpu); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - appldata_offline_cpu((long) hcpu); - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block __cpuinitdata appldata_nb = { - .notifier_call = appldata_cpu_notify, -}; - /* * appldata_init() * @@ -621,7 +522,10 @@ static struct notifier_block __cpuinitdata appldata_nb = { */ static int __init appldata_init(void) { - int i, rc; + int rc; + + appldata_timer.function = appldata_timer_function; + appldata_timer.data = (unsigned long) &appldata_work; rc = platform_driver_register(&appldata_pdrv); if (rc) @@ -639,14 +543,6 @@ static int __init appldata_init(void) goto out_device; } - get_online_cpus(); - for_each_online_cpu(i) - appldata_online_cpu(i); - put_online_cpus(); - - /* Register cpu hotplug notifier */ - register_hotcpu_notifier(&appldata_nb); - appldata_sysctl_header = register_sysctl_table(appldata_dir_table); return 0; diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c index f7d3dc555bd..02d9a1cf505 100644 --- a/arch/s390/appldata/appldata_mem.c +++ b/arch/s390/appldata/appldata_mem.c @@ -1,10 +1,8 @@ /* - * arch/s390/appldata/appldata_mem.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects data related to memory management. * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index 5da7c562a90..1370e358d49 100644 --- a/arch/s390/appldata/appldata_net_sum.c +++ b/arch/s390/appldata/appldata_net_sum.c @@ -1,11 +1,9 @@ /* - * arch/s390/appldata/appldata_net_sum.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects accumulated network statistics (Packets received/transmitted, * dropped, errors, ...). * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 4de031d6b76..87521ba682e 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -1,10 +1,8 @@ /* - * arch/s390/appldata/appldata_os.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects misc. OS related data (CPU utilization, running processes). * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index a9ce135893f..e402a9dd4ed 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -4,7 +4,7 @@ * s390 implementation of the AES Cipher Algorithm. * * s390 Version: - * Copyright IBM Corp. 2005,2007 + * Copyright IBM Corp. 2005, 2007 * Author(s): Jan Glauber (jang@de.ibm.com) * Sebastian Siewior (sebastian@breakpoint.cc> SW-Fallback * diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index 9178db6db0a..6c5cc6da711 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -3,7 +3,7 @@ * * Support for s390 cryptographic instructions. * - * Copyright IBM Corp. 2003,2007 + * Copyright IBM Corp. 2003, 2007 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index a52bfd124d8..1eaa371ca3e 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -3,7 +3,7 @@ * * s390 implementation of the DES Cipher Algorithm. * - * Copyright IBM Corp. 2003,2011 + * Copyright IBM Corp. 2003, 2011 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 0808fbf0f7d..94a35a4c1b4 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2006,2007 + * Copyright IBM Corp. 2006, 2007 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> * Driver for the s390 pseudo random number generator */ diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index e9868c6e0a0..a1b3a9dc9d8 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -8,7 +8,7 @@ * implementation written by Steve Reid. * * s390 Version: - * Copyright IBM Corp. 2003,2007 + * Copyright IBM Corp. 2003, 2007 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 0317a3547cb..9b853809a49 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -4,7 +4,7 @@ * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm. * * s390 Version: - * Copyright IBM Corp. 2005,2011 + * Copyright IBM Corp. 2005, 2011 * Author(s): Jan Glauber (jang@de.ibm.com) * * This program is free software; you can redistribute it and/or modify it diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h index d9df5a060a8..f41e0ef7fdf 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -1,8 +1,7 @@ /* - * arch/s390/hypfs/hypfs.h * Hypervisor filesystem for Linux on s390. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> */ diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index b478013b7fe..13e76dabbe8 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -1,7 +1,7 @@ /* * Hypervisor filesystem for Linux on s390 - debugfs interface * - * Copyright (C) IBM Corp. 2010 + * Copyright IBM Corp. 2010 * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 74c8f5e76ce..7fd3690b676 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -1,5 +1,4 @@ /* - * arch/s390/hypfs/hypfs_diag.c * Hypervisor filesystem for Linux on s390. Diag 204 and 224 * implementation. * diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index e54796002f6..4f6afaa8bd8 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -1,7 +1,7 @@ /* * Hypervisor filesystem for Linux on s390. z/VM implementation. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> */ diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 73dae8b9b77..6767b437a10 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -1,5 +1,4 @@ /* - * arch/s390/hypfs/inode.c * Hypervisor filesystem for Linux on s390. * * Copyright IBM Corp. 2006, 2008 @@ -103,6 +102,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode) if (ret) { struct hypfs_sb_info *hypfs_info = sb->s_fs_info; + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 1ac80d6b058..9819891ed7a 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/airq.h - * - * Copyright IBM Corp. 2002,2007 + * Copyright IBM Corp. 2002, 2007 * Author(s): Ingo Adlung <adlung@de.ibm.com> * Cornelia Huck <cornelia.huck@de.ibm.com> * Arnd Bergmann <arndb@de.ibm.com> diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h index 79283dac828..f328294faea 100644 --- a/arch/s390/include/asm/appldata.h +++ b/arch/s390/include/asm/appldata.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/appldata.h - * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * * Author(s): Melissa Howland <melissah@us.ibm.com> */ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 748347baecb..c797832daa5 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -1,8 +1,5 @@ -#ifndef __ARCH_S390_ATOMIC__ -#define __ARCH_S390_ATOMIC__ - /* - * Copyright 1999,2009 IBM Corp. + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Denis Joseph Barrow, * Arnd Bergmann <arndb@de.ibm.com>, @@ -13,6 +10,9 @@ * */ +#ifndef __ARCH_S390_ATOMIC__ +#define __ARCH_S390_ATOMIC__ + #include <linux/compiler.h> #include <linux/types.h> #include <asm/cmpxchg.h> diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index a6ff5a83e22..6f573890fb2 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -1,11 +1,6 @@ -#ifndef _S390_BITOPS_H -#define _S390_BITOPS_H - /* - * include/asm-s390/bitops.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/bitops.h" @@ -13,6 +8,9 @@ * */ +#ifndef _S390_BITOPS_H +#define _S390_BITOPS_H + #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h index 011f1e6a2a6..0f5bd894f4d 100644 --- a/arch/s390/include/asm/bugs.h +++ b/arch/s390/include/asm/bugs.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/bugs.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/bugs.h" diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h index 2a30d5ac066..4d7ccac5fd1 100644 --- a/arch/s390/include/asm/cache.h +++ b/arch/s390/include/asm/cache.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/cache.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * * Derived from "include/asm-i386/cache.h" * Copyright (C) 1992, Linus Torvalds diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index 9381c92cc77..1cb4bb3f32d 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2002, 2009 + * Copyright IBM Corp. 2002, 2009 * * Author(s): Arnd Bergmann <arndb@de.ibm.com> * diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index f2ef34f6d6e..01a905eb11e 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -6,14 +6,12 @@ struct ccw_driver; /** * struct ccwgroup_device - ccw group device - * @creator_id: unique number of the driver * @state: online/offline state * @count: number of attached slave devices * @dev: embedded device structure * @cdev: variable number of slave devices, allocated as needed */ struct ccwgroup_device { - unsigned long creator_id; enum { CCWGROUP_OFFLINE, CCWGROUP_ONLINE, diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 6c00f6800a3..4f57a4f3909 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -1,18 +1,16 @@ -#ifndef _S390_CHECKSUM_H -#define _S390_CHECKSUM_H - /* - * include/asm-s390/checksum.h * S390 fast network checksum routines - * see also arch/S390/lib/checksum.c * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Ulrich Hild (first version) * Martin Schwidefsky (heavily optimized CKSM version) * D.J. Barrow (third attempt) */ +#ifndef _S390_CHECKSUM_H +#define _S390_CHECKSUM_H + #include <asm/uaccess.h> /* diff --git a/arch/s390/include/asm/chpid.h b/arch/s390/include/asm/chpid.h index 8e88e222177..e5bde9f9291 100644 --- a/arch/s390/include/asm/chpid.h +++ b/arch/s390/include/asm/chpid.h @@ -1,6 +1,4 @@ /* - * drivers/s390/cio/chpid.h - * * Copyright IBM Corp. 2007 * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> */ diff --git a/arch/s390/include/asm/chsc.h b/arch/s390/include/asm/chsc.h index 4943654ed7f..bf115b49f44 100644 --- a/arch/s390/include/asm/chsc.h +++ b/arch/s390/include/asm/chsc.h @@ -1,7 +1,7 @@ /* * ioctl interface for /dev/chsc * - * Copyright 2008 IBM Corp. + * Copyright IBM Corp. 2008 * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> */ diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 4c8d4d5b8bd..77043aa44d6 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -1,7 +1,4 @@ /* - * include/asm-s390/cio.h - * include/asm-s390x/cio.h - * * Common interface for I/O on S/390 */ #ifndef _ASM_S390_CIO_H_ diff --git a/arch/s390/include/asm/cpcmd.h b/arch/s390/include/asm/cpcmd.h index 48a9eab1642..3dfadb5d648 100644 --- a/arch/s390/include/asm/cpcmd.h +++ b/arch/s390/include/asm/cpcmd.h @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/cpcmd.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Christian Borntraeger (cborntra@de.ibm.com), */ diff --git a/arch/s390/include/asm/cpu.h b/arch/s390/include/asm/cpu.h index e0b69540216..f5a8e2fcde0 100644 --- a/arch/s390/include/asm/cpu.h +++ b/arch/s390/include/asm/cpu.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Hartmut Penner <hp@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Christian Ehrhardt <ehrhardt@de.ibm.com>, diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 718374de9c7..8709bdef233 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/cputime.h - * - * (C) Copyright IBM Corp. 2004 + * Copyright IBM Corp. 2004 * * Author: Martin Schwidefsky <schwidefsky@de.ibm.com> */ @@ -167,12 +165,14 @@ static inline clock_t cputime64_to_clock_t(cputime64_t cputime) } struct s390_idle_data { + int nohz_delay; unsigned int sequence; unsigned long long idle_count; - unsigned long long idle_enter; - unsigned long long idle_exit; unsigned long long idle_time; - int nohz_delay; + unsigned long long clock_idle_enter; + unsigned long long clock_idle_exit; + unsigned long long timer_idle_enter; + unsigned long long timer_idle_exit; }; DECLARE_PER_CPU(struct s390_idle_data, s390_idle); diff --git a/arch/s390/include/asm/crw.h b/arch/s390/include/asm/crw.h index 749a97e61be..7c31d3e25cd 100644 --- a/arch/s390/include/asm/crw.h +++ b/arch/s390/include/asm/crw.h @@ -1,6 +1,6 @@ /* * Data definitions for channel report processing - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/include/asm/current.h b/arch/s390/include/asm/current.h index 7a68084ec2f..b80941f30df 100644 --- a/arch/s390/include/asm/current.h +++ b/arch/s390/include/asm/current.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/current.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/current.h" diff --git a/arch/s390/include/asm/dasd.h b/arch/s390/include/asm/dasd.h index 0be28efe5b6..38eca3ba40e 100644 --- a/arch/s390/include/asm/dasd.h +++ b/arch/s390/include/asm/dasd.h @@ -1,8 +1,7 @@ /* - * File...........: linux/drivers/s390/block/dasd.c * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 1999,2000 + * Copyright IBM Corp. 1999, 2000 * EMC Symmetrix ioctl Copyright EMC Corporation, 2008 * Author.........: Nigel Hislop <hislop_nigel@emc.com> * diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 8a8245ed14d..f39677e6ccd 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/debug.h * S/390 debug facility * - * Copyright (C) 1999, 2000 IBM Deutschland Entwicklung GmbH, - * IBM Corporation + * Copyright IBM Corp. 1999, 2000 */ #ifndef DEBUG_H diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index 0e3b35f96be..3f6e4095f47 100644 --- a/arch/s390/include/asm/delay.h +++ b/arch/s390/include/asm/delay.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/delay.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/delay.h" diff --git a/arch/s390/include/asm/dma.h b/arch/s390/include/asm/dma.h index 7425c6af6cd..6fb6de4f15b 100644 --- a/arch/s390/include/asm/dma.h +++ b/arch/s390/include/asm/dma.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/dma.h - * * S390 version */ diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h index 7f6f641d32f..c5befc5a3bf 100644 --- a/arch/s390/include/asm/ebcdic.h +++ b/arch/s390/include/asm/ebcdic.h @@ -1,9 +1,8 @@ /* - * include/asm-s390/ebcdic.h * EBCDIC -> ASCII, ASCII -> EBCDIC conversion routines. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 06151e6a309..32e8449640f 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/elf.h - * * S390 version * * Derived from "include/asm-i386/elf.h" diff --git a/arch/s390/include/asm/errno.h b/arch/s390/include/asm/errno.h index e41d5b37c4d..395e97d8005 100644 --- a/arch/s390/include/asm/errno.h +++ b/arch/s390/include/asm/errno.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/errno.h - * * S390 version * */ diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h index 538e1b36a72..a24b03b9fb6 100644 --- a/arch/s390/include/asm/etr.h +++ b/arch/s390/include/asm/etr.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/etr.h - * * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/extmem.h b/arch/s390/include/asm/extmem.h index 33837d75618..6276002d76b 100644 --- a/arch/s390/include/asm/extmem.h +++ b/arch/s390/include/asm/extmem.h @@ -1,8 +1,6 @@ /* - * include/asm-s390x/extmem.h - * * definitions for external memory segment support - * Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2003 */ #ifndef _ASM_S390X_DCSS_H diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index 510ba9ef424..0c82ba86e99 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/hardirq.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * diff --git a/arch/s390/include/asm/idals.h b/arch/s390/include/asm/idals.h index aef0dde340d..ea5a6e45fd9 100644 --- a/arch/s390/include/asm/idals.h +++ b/arch/s390/include/asm/idals.h @@ -1,10 +1,9 @@ /* - * File...........: linux/include/asm-s390x/idals.h * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 2000a - + * Copyright IBM Corp. 2000 + * * History of changes * 07/24/00 new file * 05/04/02 code restructuring. diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index f81a0975cbe..559e921a6bb 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/io.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/io.h" diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 38fdf451feb..37b9091ab8c 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2006,2010 + * Copyright IBM Corp. 2006, 2010 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index f4f38826eeb..694bcd6bd92 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/kexec.h - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger <adelsberger@de.ibm.com> * diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index a231a9439c4..dcf6948a875 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -17,7 +17,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * - * Copyright (C) IBM Corporation, 2002, 2006 + * Copyright IBM Corp. 2002, 2006 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation ( includes suggestions from diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index bdcbe0f8dd7..d25da598ec6 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -1,7 +1,7 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H /* - * asm-s390/kvm.h - KVM s390 specific structures and definitions + * KVM s390 specific structures and definitions * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index dd17537b9a9..b7841546991 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1,7 +1,7 @@ /* - * asm-s390/kvm_host.h - definition for kernel virtual machines on s390 + * definition for kernel virtual machines on s390 * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h index a9883296103..da44867de60 100644 --- a/arch/s390/include/asm/kvm_para.h +++ b/arch/s390/include/asm/kvm_para.h @@ -1,5 +1,5 @@ /* - * asm-s390/kvm_para.h - definition for paravirtual devices on s390 + * definition for paravirtual devices on s390 * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/kvm_virtio.h b/arch/s390/include/asm/kvm_virtio.h index 72f614181ef..44a438ca9e7 100644 --- a/arch/s390/include/asm/kvm_virtio.h +++ b/arch/s390/include/asm/kvm_virtio.h @@ -1,5 +1,5 @@ /* - * kvm_virtio.h - definition for virtio for kvm on s390 + * definition for virtio for kvm on s390 * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 47853debb3b..aab5555bbbd 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Hartmut Penner <hp@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Denis Joseph Barrow, @@ -302,12 +302,7 @@ struct _lowcore { */ __u64 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e08 */ - /* - * Because the vmcore_info pointer is not 8 byte aligned it never - * should not be accessed directly. For accessing the pointer, first - * copy it to a local pointer variable. - */ - __u8 vmcore_info[8]; /* 0x0e0c */ + __u64 vmcore_info; /* 0x0e0c */ __u8 pad_0x0e14[0x0e18-0x0e14]; /* 0x0e14 */ __u64 os_info; /* 0x0e18 */ __u8 pad_0x0e20[0x0f00-0x0e20]; /* 0x0e20 */ diff --git a/arch/s390/include/asm/mathemu.h b/arch/s390/include/asm/mathemu.h index e8dd1ba8edb..614dfaf47f7 100644 --- a/arch/s390/include/asm/mathemu.h +++ b/arch/s390/include/asm/mathemu.h @@ -1,9 +1,8 @@ /* - * arch/s390/kernel/mathemu.h * IEEE floating point emulation. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h index d49760e6350..abc1932ac4e 100644 --- a/arch/s390/include/asm/mman.h +++ b/arch/s390/include/asm/mman.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/mman.h - * * S390 version * * Derived from "include/asm-i386/mman.h" diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 69bdf72e95e..5c63615f134 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/mmu_context.h - * * S390 version * * Derived from "include/asm-i386/mmu_context.h" diff --git a/arch/s390/include/asm/monwriter.h b/arch/s390/include/asm/monwriter.h index f0cbf96c52e..f845c8e2f86 100644 --- a/arch/s390/include/asm/monwriter.h +++ b/arch/s390/include/asm/monwriter.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/monwriter.h - * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Character device driver for writing z/VM APPLDATA monitor records * Version 1.0 * Author(s): Melissa Howland <melissah@us.ibm.com> diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index f4b60441adc..35f8ec18561 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -1,7 +1,7 @@ /* * Machine check handler definitions * - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index f7ec548c2b9..27ab3c7c1e8 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/page.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 43078c19439..590c3219c63 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/pgalloc.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) * diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b3227415abd..6bd7d748301 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/pgtable.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) * Ulrich Weigand (weigand@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h index 7be104c0f19..7bcc14e395f 100644 --- a/arch/s390/include/asm/posix_types.h +++ b/arch/s390/include/asm/posix_types.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/posix_types.h - * * S390 version * */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 20d0585cf90..c40fa91e38a 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/processor.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -348,4 +346,14 @@ extern void (*s390_base_ext_handler_fn)(void); ".previous\n" #endif +extern int memcpy_real(void *, void *, size_t); +extern void memcpy_absolute(void *, void *, size_t); + +#define mem_assign_absolute(dest, val) { \ + __typeof__(dest) __tmp = (val); \ + \ + BUILD_BUG_ON(sizeof(__tmp) != sizeof(val)); \ + memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ +} + #endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index aeb77f01798..d5f08ea566e 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/ptrace.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) */ diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index f039d86adf6..57d0d7e794b 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -1,7 +1,5 @@ /* - * linux/include/asm-s390/qdio.h - * - * Copyright 2000,2008 IBM Corp. + * Copyright IBM Corp. 2000, 2008 * Author(s): Utz Bacher <utz.bacher@de.ibm.com> * Jan Glauber <jang@linux.vnet.ibm.com> * diff --git a/arch/s390/include/asm/qeth.h b/arch/s390/include/asm/qeth.h index 2c7c898c03e..3a896cf5258 100644 --- a/arch/s390/include/asm/qeth.h +++ b/arch/s390/include/asm/qeth.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/qeth.h - * * ioctl definitions for qeth driver * - * Copyright (C) 2004 IBM Corporation + * Copyright IBM Corp. 2004 * * Author(s): Thomas Spatzier <tspat@de.ibm.com> * diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h index 3d6ad4ad2a3..804578587a7 100644 --- a/arch/s390/include/asm/reset.h +++ b/arch/s390/include/asm/reset.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/reset.h - * * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/include/asm/resource.h b/arch/s390/include/asm/resource.h index 366c01de04f..ec23d1c73c9 100644 --- a/arch/s390/include/asm/resource.h +++ b/arch/s390/include/asm/resource.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/resource.h - * * S390 version * * Derived from "include/asm-i386/resources.h" diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h index 1ceee10264c..487f9b64efb 100644 --- a/arch/s390/include/asm/rwsem.h +++ b/arch/s390/include/asm/rwsem.h @@ -2,10 +2,8 @@ #define _S390_RWSEM_H /* - * include/asm-s390/rwsem.h - * * S390 version - * Copyright (C) 2002 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2002 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index bf238c55740..e62a555557e 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/sclp.h - * * Copyright IBM Corp. 2007 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ @@ -55,5 +53,7 @@ int sclp_chp_configure(struct chp_id chpid); int sclp_chp_deconfigure(struct chp_id chpid); int sclp_chp_read_info(struct sclp_chp_info *info); void sclp_get_ipl_info(struct sclp_ipl_info *info); +bool sclp_has_linemode(void); +bool sclp_has_vt220(void); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h index de389cb54d2..4071d00978c 100644 --- a/arch/s390/include/asm/scsw.h +++ b/arch/s390/include/asm/scsw.h @@ -1,7 +1,7 @@ /* * Helper functions for scsw access. * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 40eb2ff88e9..57e80534375 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/setup.h - * * S390 version - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 */ #ifndef _ASM_S390_SETUP_H diff --git a/arch/s390/include/asm/shmparam.h b/arch/s390/include/asm/shmparam.h index c2e0c0508e7..e985182738f 100644 --- a/arch/s390/include/asm/shmparam.h +++ b/arch/s390/include/asm/shmparam.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/shmparam.h - * * S390 version * * Derived from "include/asm-i386/shmparam.h" diff --git a/arch/s390/include/asm/sigcontext.h b/arch/s390/include/asm/sigcontext.h index aeb6e0b1332..584787f6ce4 100644 --- a/arch/s390/include/asm/sigcontext.h +++ b/arch/s390/include/asm/sigcontext.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/sigcontext.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 */ #ifndef _ASM_S390_SIGCONTEXT_H diff --git a/arch/s390/include/asm/siginfo.h b/arch/s390/include/asm/siginfo.h index e0ff1ab054b..91fd3e4b70c 100644 --- a/arch/s390/include/asm/siginfo.h +++ b/arch/s390/include/asm/siginfo.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/siginfo.h - * * S390 version * * Derived from "include/asm-i386/siginfo.h" diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h index cdf5cb2fe03..6d4d9d1faee 100644 --- a/arch/s390/include/asm/signal.h +++ b/arch/s390/include/asm/signal.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/signal.h - * * S390 version * * Derived from "include/asm-i386/signal.h" diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h new file mode 100644 index 00000000000..5a87d16d3e7 --- /dev/null +++ b/arch/s390/include/asm/sigp.h @@ -0,0 +1,32 @@ +#ifndef __S390_ASM_SIGP_H +#define __S390_ASM_SIGP_H + +/* SIGP order codes */ +#define SIGP_SENSE 1 +#define SIGP_EXTERNAL_CALL 2 +#define SIGP_EMERGENCY_SIGNAL 3 +#define SIGP_STOP 5 +#define SIGP_RESTART 6 +#define SIGP_STOP_AND_STORE_STATUS 9 +#define SIGP_INITIAL_CPU_RESET 11 +#define SIGP_SET_PREFIX 13 +#define SIGP_STORE_STATUS_AT_ADDRESS 14 +#define SIGP_SET_ARCHITECTURE 18 +#define SIGP_SENSE_RUNNING 21 + +/* SIGP condition codes */ +#define SIGP_CC_ORDER_CODE_ACCEPTED 0 +#define SIGP_CC_STATUS_STORED 1 +#define SIGP_CC_BUSY 2 +#define SIGP_CC_NOT_OPERATIONAL 3 + +/* SIGP cpu status bits */ + +#define SIGP_STATUS_CHECK_STOP 0x00000010UL +#define SIGP_STATUS_STOPPED 0x00000040UL +#define SIGP_STATUS_EXT_CALL_PENDING 0x00000080UL +#define SIGP_STATUS_INVALID_PARAMETER 0x00000100UL +#define SIGP_STATUS_INCORRECT_STATE 0x00000200UL +#define SIGP_STATUS_NOT_RUNNING 0x00000400UL + +#endif /* __S390_ASM_SIGP_H */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 0b6f586c138..a0a8340daaf 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Denis Joseph Barrow, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index c91b720965c..69718cd6d63 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/socket.h - * * S390 version * * Derived from "include/asm-i386/socket.h" diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index fd94dfec8d0..701fe8c59e1 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/spinlock.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/spinlock.h" diff --git a/arch/s390/include/asm/stat.h b/arch/s390/include/asm/stat.h index d92959eebb6..b4ca97d9146 100644 --- a/arch/s390/include/asm/stat.h +++ b/arch/s390/include/asm/stat.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/stat.h - * * S390 version * * Derived from "include/asm-i386/stat.h" diff --git a/arch/s390/include/asm/statfs.h b/arch/s390/include/asm/statfs.h index 3be7fbd406c..5acca0a34c2 100644 --- a/arch/s390/include/asm/statfs.h +++ b/arch/s390/include/asm/statfs.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/statfs.h - * * S390 version * * Derived from "include/asm-i386/statfs.h" diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 8cc160c9e1c..1bd1352fa3b 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/string.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), */ diff --git a/arch/s390/include/asm/swab.h b/arch/s390/include/asm/swab.h index a3e4ebb3209..da3bfe5cc16 100644 --- a/arch/s390/include/asm/swab.h +++ b/arch/s390/include/asm/swab.h @@ -2,10 +2,8 @@ #define _S390_SWAB_H /* - * include/asm-s390/swab.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 79d3d6e2e9c..282ee36f616 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -1,7 +1,7 @@ /* * definition for store system information stsi * - * Copyright IBM Corp. 2001,2008 + * Copyright IBM Corp. 2001, 2008 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/include/asm/tape390.h b/arch/s390/include/asm/tape390.h index 884fba48f1f..b2bc4bab792 100644 --- a/arch/s390/include/asm/tape390.h +++ b/arch/s390/include/asm/tape390.h @@ -1,10 +1,9 @@ /************************************************************************* * - * tape390.h * enables user programs to display messages and control encryption * on s390 tape devices * - * Copyright IBM Corp. 2001,2006 + * Copyright IBM Corp. 2001, 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> * *************************************************************************/ diff --git a/arch/s390/include/asm/termios.h b/arch/s390/include/asm/termios.h index bc3a35cefc9..cb9fe2786b8 100644 --- a/arch/s390/include/asm/termios.h +++ b/arch/s390/include/asm/termios.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/termios.h - * * S390 version * * Derived from "include/asm-i386/termios.h" diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 4e40b25cd06..bb08e2afc5d 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/thread_info.h - * * S390 version - * Copyright (C) IBM Corp. 2002,2006 + * Copyright IBM Corp. 2002, 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/timer.h b/arch/s390/include/asm/timer.h deleted file mode 100644 index 15d647901e5..00000000000 --- a/arch/s390/include/asm/timer.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * include/asm-s390/timer.h - * - * (C) Copyright IBM Corp. 2003,2006 - * Virtual CPU timer - * - * Author: Jan Glauber (jang@de.ibm.com) - */ - -#ifndef _ASM_S390_TIMER_H -#define _ASM_S390_TIMER_H - -#include <linux/timer.h> - -#define VTIMER_MAX_SLICE (0x7ffffffffffff000LL) - -struct vtimer_list { - struct list_head entry; - - int cpu; - __u64 expires; - __u64 interval; - - void (*function)(unsigned long); - unsigned long data; -}; - -/* the vtimer value will wrap after ca. 71 years */ -struct vtimer_queue { - struct list_head list; - spinlock_t lock; - __u64 timer; /* last programmed timer */ - __u64 elapsed; /* elapsed time of timer expire values */ - __u64 idle_enter; /* cpu timer on idle enter */ - __u64 idle_exit; /* cpu timer on idle exit */ -}; - -extern void init_virt_timer(struct vtimer_list *timer); -extern void add_virt_timer(void *new); -extern void add_virt_timer_periodic(void *new); -extern int mod_virt_timer(struct vtimer_list *timer, __u64 expires); -extern int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires); -extern int del_virt_timer(struct vtimer_list *timer); - -extern void init_cpu_vtimer(void); -extern void vtime_init(void); - -extern void vtime_stop_cpu(void); -extern void vtime_start_leave(void); - -#endif /* _ASM_S390_TIMER_H */ diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 239ece9e53c..fba4d66788a 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/timex.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * * Derived from "include/asm-i386/timex.h" * Copyright (C) 1992, Linus Torvalds diff --git a/arch/s390/include/asm/types.h b/arch/s390/include/asm/types.h index 6c8c35f8df1..6ba7c2c7217 100644 --- a/arch/s390/include/asm/types.h +++ b/arch/s390/include/asm/types.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/types.h - * * S390 version * * Derived from "include/asm-i386/types.h" diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 1f3a79bcd26..a8ab18b18b5 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/uaccess.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -381,8 +379,6 @@ clear_user(void __user *to, unsigned long n) return n; } -extern int memcpy_real(void *, void *, size_t); -extern void memcpy_absolute(void *, void *, size_t); extern int copy_to_user_real(void __user *dest, void *src, size_t count); extern int copy_from_user_real(void *dest, void __user *src, size_t count); diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index cfb874e66c9..200e06325c6 100644 --- a/arch/s390/include/asm/ucontext.h +++ b/arch/s390/include/asm/ucontext.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/ucontext.h - * * S390 version * * Derived from "include/asm-i386/ucontext.h" diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 8a8008fe7b8..2e37157ba6a 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/unistd.h - * * S390 version * * Derived from "include/asm-i386/unistd.h" diff --git a/arch/s390/include/asm/user.h b/arch/s390/include/asm/user.h index 1b050e35fdc..6ed1d188633 100644 --- a/arch/s390/include/asm/user.h +++ b/arch/s390/include/asm/user.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/user.h - * * S390 version * * Derived from "include/asm-i386/usr.h" diff --git a/arch/s390/include/asm/vtimer.h b/arch/s390/include/asm/vtimer.h new file mode 100644 index 00000000000..bfe25d513ad --- /dev/null +++ b/arch/s390/include/asm/vtimer.h @@ -0,0 +1,33 @@ +/* + * Copyright IBM Corp. 2003, 2012 + * Virtual CPU timer + * + * Author(s): Jan Glauber <jan.glauber@de.ibm.com> + */ + +#ifndef _ASM_S390_TIMER_H +#define _ASM_S390_TIMER_H + +#define VTIMER_MAX_SLICE (0x7fffffffffffffffULL) + +struct vtimer_list { + struct list_head entry; + u64 expires; + u64 interval; + void (*function)(unsigned long); + unsigned long data; +}; + +extern void init_virt_timer(struct vtimer_list *timer); +extern void add_virt_timer(struct vtimer_list *timer); +extern void add_virt_timer_periodic(struct vtimer_list *timer); +extern int mod_virt_timer(struct vtimer_list *timer, u64 expires); +extern int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires); +extern int del_virt_timer(struct vtimer_list *timer); + +extern void init_cpu_vtimer(void); +extern void vtime_init(void); + +extern void vtime_stop_cpu(void); + +#endif /* _ASM_S390_TIMER_H */ diff --git a/arch/s390/include/asm/vtoc.h b/arch/s390/include/asm/vtoc.h index 8406a2b3157..221419de275 100644 --- a/arch/s390/include/asm/vtoc.h +++ b/arch/s390/include/asm/vtoc.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/vtoc.h - * * This file contains volume label definitions for DASD devices. * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Volker Sameske <sameske@de.ibm.com> * diff --git a/arch/s390/include/asm/zcrypt.h b/arch/s390/include/asm/zcrypt.h index 00d3bbd4411..e83fc116f5b 100644 --- a/arch/s390/include/asm/zcrypt.h +++ b/arch/s390/include/asm/zcrypt.h @@ -3,7 +3,7 @@ * * zcrypt 2.1.0 (user-visible header) * - * Copyright (C) 2001, 2006 IBM Corporation + * Copyright IBM Corp. 2001, 2006 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 83e6edf5cf1..45ef1a7b08f 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -9,7 +9,6 @@ #include <linux/kbuild.h> #include <linux/sched.h> #include <asm/cputime.h> -#include <asm/timer.h> #include <asm/vdso.h> #include <asm/pgtable.h> @@ -72,11 +71,10 @@ int main(void) DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); BLANK(); /* idle data offsets */ - DEFINE(__IDLE_ENTER, offsetof(struct s390_idle_data, idle_enter)); - DEFINE(__IDLE_EXIT, offsetof(struct s390_idle_data, idle_exit)); - /* vtimer queue offsets */ - DEFINE(__VQ_IDLE_ENTER, offsetof(struct vtimer_queue, idle_enter)); - DEFINE(__VQ_IDLE_EXIT, offsetof(struct vtimer_queue, idle_exit)); + DEFINE(__CLOCK_IDLE_ENTER, offsetof(struct s390_idle_data, clock_idle_enter)); + DEFINE(__CLOCK_IDLE_EXIT, offsetof(struct s390_idle_data, clock_idle_exit)); + DEFINE(__TIMER_IDLE_ENTER, offsetof(struct s390_idle_data, timer_idle_enter)); + DEFINE(__TIMER_IDLE_EXIT, offsetof(struct s390_idle_data, timer_idle_exit)); /* lowcore offsets */ DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params)); DEFINE(__LC_EXT_CPU_ADDR, offsetof(struct _lowcore, ext_cpu_addr)); @@ -131,6 +129,8 @@ int main(void) DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); DEFINE(__LC_RESTART_STACK, offsetof(struct _lowcore, restart_stack)); DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn)); + DEFINE(__LC_RESTART_DATA, offsetof(struct _lowcore, restart_data)); + DEFINE(__LC_RESTART_SOURCE, offsetof(struct _lowcore, restart_source)); DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index c880ff72db4..797a823a227 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -1,7 +1,7 @@ /* * arch/s390/kernel/base.S * - * Copyright IBM Corp. 2006,2007 + * Copyright IBM Corp. 2006, 2007 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> * Michael Holzheu <holzheu@de.ibm.com> */ @@ -9,6 +9,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/sigp.h> #ifdef CONFIG_64BIT @@ -100,7 +101,7 @@ ENTRY(diag308_reset) .Lrestart_part2: lhi %r0,0 # Load r0 with zero lhi %r1,2 # Use mode 2 = ESAME (dump) - sigp %r1,%r0,0x12 # Switch to ESAME mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode sam64 # Switch to 64 bit addressing mode larl %r4,.Lctlregs # Restore control registers lctlg %c0,%c15,0(%r4) diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c index 3ae4757b006..102da5e2303 100644 --- a/arch/s390/kernel/bitmap.c +++ b/arch/s390/kernel/bitmap.c @@ -2,7 +2,7 @@ * Bitmaps for set_bit, clear_bit, test_and_set_bit, ... * See include/asm/{bitops.h|posix_types.h} for details * - * Copyright IBM Corp. 1999,2009 + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, */ diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c index 914d49444f9..765fabdada9 100644 --- a/arch/s390/kernel/compat_exec_domain.c +++ b/arch/s390/kernel/compat_exec_domain.c @@ -1,7 +1,7 @@ /* * Support for 32-bit Linux for S390 personality. * - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Gerhard Tonn (ton@de.ibm.com) * * diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 65426525d9f..d1225089a4b 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -1,8 +1,6 @@ /* - * arch/s390x/kernel/linux32.c - * * S390 version - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerhard Tonn (ton@de.ibm.com) * Thomas Spatzier (tspat@de.ibm.com) diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 3c0c19830c3..a1e8a8694bb 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/compat_signal.c - * - * Copyright (C) IBM Corp. 2000,2006 + * Copyright IBM Corp. 2000, 2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * Gerhard Tonn (ton@de.ibm.com) * diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index ff605a39cf4..e835d6d5b7f 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1,8 +1,7 @@ /* -* arch/s390/kernel/compat_wrapper.S * wrapper for 31 bit compatible system calls. * -* Copyright (C) IBM Corp. 2000,2006 +* Copyright IBM Corp. 2000, 2006 * Author(s): Gerhard Tonn (ton@de.ibm.com), * Thomas Spatzier (tspat@de.ibm.com) */ diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index e3dd886e1b3..d7b0c4d2788 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/cpcmd.c - * * S390 version - * Copyright IBM Corp. 1999,2007 + * Copyright IBM Corp. 1999, 2007 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Christian Borntraeger (cborntra@de.ibm.com), */ diff --git a/arch/s390/kernel/crash.c b/arch/s390/kernel/crash.c index 8cc7c9fa64f..3819153de8b 100644 --- a/arch/s390/kernel/crash.c +++ b/arch/s390/kernel/crash.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/crash.c - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> * diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 19e5e9eba54..21be961e8a4 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1,5 +1,4 @@ /* - * arch/s390/kernel/debug.c * S/390 debug facility * * Copyright IBM Corp. 1999, 2012 diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 3221c6fca8b..1f6b428e276 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/dis.c - * * Disassemble s390 instructions. * * Copyright IBM Corp. 2007 @@ -613,6 +611,7 @@ static struct insn opcode_b2[] = { { "sie", 0x14, INSTR_S_RD }, { "pc", 0x18, INSTR_S_RD }, { "sac", 0x19, INSTR_S_RD }, + { "servc", 0x20, INSTR_RRE_RR }, { "cfc", 0x1a, INSTR_S_RD }, { "ipte", 0x21, INSTR_RRE_RR }, { "ipm", 0x22, INSTR_RRE_R0 }, diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 6684fff1755..bc95a8ebd9c 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/early.c - * * Copyright IBM Corp. 2007, 2009 * Author(s): Hongjie Yang <hongjie@us.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com> diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c index cc0dc609d73..b971c6be629 100644 --- a/arch/s390/kernel/ebcdic.c +++ b/arch/s390/kernel/ebcdic.c @@ -1,10 +1,9 @@ /* - * arch/s390/kernel/ebcdic.c * ECBDIC -> ASCII, ASCII -> ECBDIC, * upper to lower case (EBCDIC) conversion tables. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> * Martin Peschke <peschke@fh-brandenburg.de> */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 1ae93b573d7..870bad6d56f 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/entry.S * S390 low-level entry points. * - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -18,6 +17,7 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/page.h> +#include <asm/sigp.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 4 @@ -616,17 +616,13 @@ ext_skip: * Load idle PSW. The second "half" of this function is in cleanup_idle. */ ENTRY(psw_idle) - st %r4,__SF_EMPTY(%r15) + st %r3,__SF_EMPTY(%r15) basr %r1,0 la %r1,psw_idle_lpsw+4-.(%r1) st %r1,__SF_EMPTY+4(%r15) oi __SF_EMPTY+4(%r15),0x80 - la %r1,.Lvtimer_max-psw_idle_lpsw-4(%r1) - stck __IDLE_ENTER(%r2) - ltr %r5,%r5 - stpt __VQ_IDLE_ENTER(%r3) - jz psw_idle_lpsw - spt 0(%r1) + stck __CLOCK_IDLE_ENTER(%r2) + stpt __TIMER_IDLE_ENTER(%r2) psw_idle_lpsw: lpsw __SF_EMPTY(%r15) br %r14 @@ -723,15 +719,17 @@ ENTRY(restart_int_handler) mvc __PT_PSW(8,%r15),__LC_RST_OLD_PSW # store restart old psw ahi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) - lm %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + l %r1,__LC_RESTART_FN # load fn, parm & source cpu + l %r2,__LC_RESTART_DATA + l %r3,__LC_RESTART_SOURCE ltr %r3,%r3 # test source cpu address jm 1f # negative -> skip source stop -0: sigp %r4,%r3,1 # sigp sense to source cpu +0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu brc 10,0b # wait for status stored 1: basr %r14,%r1 # call function stap __SF_EMPTY(%r15) # store cpu address lh %r3,__SF_EMPTY(%r15) -2: sigp %r4,%r3,5 # sigp stop to current cpu +2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu brc 2,2b 3: j 3b @@ -883,33 +881,28 @@ cleanup_io_restore_insn: cleanup_idle: # copy interrupt clock & cpu timer - mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER chi %r11,__LC_SAVE_AREA_ASYNC je 0f - mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck has been executed cl %r9,BASED(cleanup_idle_insn) jhe 1f - mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) - mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) - j 2f -1: # check if the cpu timer has been reprogrammed - ltr %r5,%r5 - jz 2f - spt __VQ_IDLE_ENTER(%r3) -2: # account system time going idle + mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) + mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r3) +1: # account system time going idle lm %r9,%r10,__LC_STEAL_TIMER - ADD64 %r9,%r10,__IDLE_ENTER(%r2) + ADD64 %r9,%r10,__CLOCK_IDLE_ENTER(%r2) SUB64 %r9,%r10,__LC_LAST_UPDATE_CLOCK stm %r9,%r10,__LC_STEAL_TIMER - mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) lm %r9,%r10,__LC_SYSTEM_TIMER ADD64 %r9,%r10,__LC_LAST_UPDATE_TIMER - SUB64 %r9,%r10,__VQ_IDLE_ENTER(%r3) + SUB64 %r9,%r10,__TIMER_IDLE_ENTER(%r2) stm %r9,%r10,__LC_SYSTEM_TIMER - mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw n %r8,BASED(cleanup_idle_wait) # clear wait state bit l %r9,24(%r11) # return from psw_idle diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index f66a229ab0b..a5f4dc42a5d 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -5,7 +5,6 @@ #include <linux/signal.h> #include <asm/ptrace.h> #include <asm/cputime.h> -#include <asm/timer.h> extern void (*pgm_check_table[128])(struct pt_regs *); extern void *restart_stack; @@ -17,8 +16,7 @@ void io_int_handler(void); void mcck_int_handler(void); void restart_int_handler(void); void restart_call_handler(void); -void psw_idle(struct s390_idle_data *, struct vtimer_queue *, - unsigned long, int); +void psw_idle(struct s390_idle_data *, unsigned long); asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 229fe1d0774..349b7eeb348 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/entry64.S * S390 low-level entry points. * - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -18,6 +17,7 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/page.h> +#include <asm/sigp.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -642,15 +642,11 @@ ext_skip: * Load idle PSW. The second "half" of this function is in cleanup_idle. */ ENTRY(psw_idle) - stg %r4,__SF_EMPTY(%r15) + stg %r3,__SF_EMPTY(%r15) larl %r1,psw_idle_lpsw+4 stg %r1,__SF_EMPTY+8(%r15) - larl %r1,.Lvtimer_max - STCK __IDLE_ENTER(%r2) - ltr %r5,%r5 - stpt __VQ_IDLE_ENTER(%r3) - jz psw_idle_lpsw - spt 0(%r1) + STCK __CLOCK_IDLE_ENTER(%r2) + stpt __TIMER_IDLE_ENTER(%r2) psw_idle_lpsw: lpswe __SF_EMPTY(%r15) br %r14 @@ -750,15 +746,17 @@ ENTRY(restart_int_handler) mvc __PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw aghi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) - lmg %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + lg %r1,__LC_RESTART_FN # load fn, parm & source cpu + lg %r2,__LC_RESTART_DATA + lg %r3,__LC_RESTART_SOURCE ltgr %r3,%r3 # test source cpu address jm 1f # negative -> skip source stop -0: sigp %r4,%r3,1 # sigp sense to source cpu +0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu brc 10,0b # wait for status stored 1: basr %r14,%r1 # call function stap __SF_EMPTY(%r15) # store cpu address llgh %r3,__SF_EMPTY(%r15) -2: sigp %r4,%r3,5 # sigp stop to current cpu +2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu brc 2,2b 3: j 3b @@ -916,33 +914,28 @@ cleanup_io_restore_insn: cleanup_idle: # copy interrupt clock & cpu timer - mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER cghi %r11,__LC_SAVE_AREA_ASYNC je 0f - mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck & stpt have been executed clg %r9,BASED(cleanup_idle_insn) jhe 1f - mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) - mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) - j 2f -1: # check if the cpu timer has been reprogrammed - ltr %r5,%r5 - jz 2f - spt __VQ_IDLE_ENTER(%r3) -2: # account system time going idle + mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) + mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2) +1: # account system time going idle lg %r9,__LC_STEAL_TIMER - alg %r9,__IDLE_ENTER(%r2) + alg %r9,__CLOCK_IDLE_ENTER(%r2) slg %r9,__LC_LAST_UPDATE_CLOCK stg %r9,__LC_STEAL_TIMER - mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) lg %r9,__LC_SYSTEM_TIMER alg %r9,__LC_LAST_UPDATE_TIMER - slg %r9,__VQ_IDLE_ENTER(%r3) + slg %r9,__TIMER_IDLE_ENTER(%r2) stg %r9,__LC_SYSTEM_TIMER - mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw nihh %r8,0xfffd # clear wait state bit lg %r9,48(%r11) # return from psw_idle @@ -958,8 +951,6 @@ cleanup_idle_insn: .quad __critical_start .Lcritical_length: .quad __critical_end - __critical_start -.Lvtimer_max: - .quad 0x7fffffffffffffff #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) @@ -974,7 +965,6 @@ ENTRY(sie64a) stg %r3,__SF_EMPTY+8(%r15) # save guest register save area xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0 lmg %r0,%r13,0(%r3) # load guest gprs 0-13 - lg %r14,__LC_THREAD_INFO # pointer thread_info struct sie_loop: lg %r14,__LC_THREAD_INFO # pointer thread_info struct tm __TI_flags+7(%r14),_TIF_EXIT_SIE diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 4939d15375a..805b6686b64 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index d3f1ab7d90a..a1372ae24ae 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/head31.S - * - * Copyright (C) IBM Corp. 2005,2010 + * Copyright IBM Corp. 2005, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 99348c0eaa4..c108af28bbe 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/head64.S - * - * Copyright (C) IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S index 796c976b5fd..acaaaf4b705 100644 --- a/arch/s390/kernel/head_kdump.S +++ b/arch/s390/kernel/head_kdump.S @@ -5,6 +5,8 @@ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ +#include <asm/sigp.h> + #define DATAMOVER_ADDR 0x4000 #define COPY_PAGE_ADDR 0x6000 @@ -19,7 +21,7 @@ .align 2 .Lep_startup_kdump: lhi %r1,2 # mode 2 = esame (dump) - sigp %r1,%r0,0x12 # Switch to esame mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to esame mode sam64 # Switch to 64 bit addressing basr %r13,0 .Lbase: @@ -88,7 +90,7 @@ startup_kdump_relocated: sam31 # Switch to 31 bit addr mode sr %r1,%r1 # Erase register r1 sr %r2,%r2 # Erase register r2 - sigp %r1,%r2,0x12 # Switch to 31 bit arch mode + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # Switch to 31 bit arch mode lpsw 0 # Start new kernel... .align 8 .Lrestart_psw: diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 2f6cfd460cb..e64d141555c 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/ipl.c * ipl/reipl/dump support for Linux on s390. * - * Copyright IBM Corp. 2005,2012 + * Copyright IBM Corp. 2005, 2012 * Author(s): Michael Holzheu <holzheu@de.ibm.com> * Heiko Carstens <heiko.carstens@de.ibm.com> * Volker Sameske <sameske@de.ibm.com> @@ -1528,15 +1527,12 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - struct { - void *addr; - __u32 csum; - } __packed ipib; + unsigned long ipib = (unsigned long) reipl_block_actual; + unsigned int csum; - ipib.csum = csum_partial(reipl_block_actual, - reipl_block_actual->hdr.len, 0); - ipib.addr = reipl_block_actual; - memcpy_absolute(&S390_lowcore.ipib, &ipib, sizeof(ipib)); + csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); + mem_assign_absolute(S390_lowcore.ipib, ipib); + mem_assign_absolute(S390_lowcore.ipib_checksum, csum); dump_run(trigger); } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index b4f4a7133fa..dd7630d8aab 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2004,2011 + * Copyright IBM Corp. 2004, 2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Holger Smolinski <Holger.Smolinski@de.ibm.com>, * Thomas Spatzier <tspat@de.ibm.com>, diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 64b761aef00..8aa634f5944 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -15,7 +15,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * - * Copyright (C) IBM Corporation, 2002, 2006 + * Copyright IBM Corp. 2002, 2006 * * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com> */ diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c index 87f080b17af..eca94e74d19 100644 --- a/arch/s390/kernel/lgr.c +++ b/arch/s390/kernel/lgr.c @@ -45,7 +45,7 @@ struct lgr_info { /* * LGR globals */ -static void *lgr_page; +static char lgr_page[PAGE_SIZE] __aligned(PAGE_SIZE); static struct lgr_info lgr_info_last; static struct lgr_info lgr_info_cur; static struct debug_info *lgr_dbf; @@ -74,7 +74,7 @@ static void cpascii(char *dst, char *src, int size) */ static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) { - struct sysinfo_1_1_1 *si = lgr_page; + struct sysinfo_1_1_1 *si = (void *) lgr_page; if (stsi(si, 1, 1, 1) == -ENOSYS) return; @@ -91,7 +91,7 @@ static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) */ static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) { - struct sysinfo_2_2_2 *si = lgr_page; + struct sysinfo_2_2_2 *si = (void *) lgr_page; if (stsi(si, 2, 2, 2) == -ENOSYS) return; @@ -105,7 +105,7 @@ static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) */ static void lgr_stsi_3_2_2(struct lgr_info *lgr_info) { - struct sysinfo_3_2_2 *si = lgr_page; + struct sysinfo_3_2_2 *si = (void *) lgr_page; int i; if (stsi(si, 3, 2, 2) == -ENOSYS) @@ -183,14 +183,9 @@ static void lgr_timer_set(void) */ static int __init lgr_init(void) { - lgr_page = (void *) __get_free_pages(GFP_KERNEL, 0); - if (!lgr_page) - return -ENOMEM; lgr_dbf = debug_register("lgr", 1, 1, sizeof(struct lgr_info)); - if (!lgr_dbf) { - free_page((unsigned long) lgr_page); + if (!lgr_dbf) return -ENOMEM; - } debug_register_view(lgr_dbf, &debug_hex_ascii_view); lgr_info_get(&lgr_info_last); debug_event(lgr_dbf, 1, &lgr_info_last, sizeof(lgr_info_last)); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index cdacf8f91b2..493304bdf1c 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/machine_kexec.c - * - * Copyright IBM Corp. 2005,2011 + * Copyright IBM Corp. 2005, 2011 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 7e2c38ba137..4567ce20d90 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, * diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index f70cadec68f..11332193db3 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, * diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index dfcb3436bad..46412b1d7e1 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -1,9 +1,8 @@ /* - * arch/s390/kernel/module.c - Kernel module help for s390. + * Kernel module help for s390. * * S390 version - * Copyright (C) 2002, 2003 IBM Deutschland Entwicklung GmbH, - * IBM Corporation + * Copyright IBM Corp. 2002, 2003 * Author(s): Arnd Bergmann (arndb@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) * diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 8c372ca6135..a6daa5c5cdb 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -1,7 +1,7 @@ /* * Machine check handler * - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 95fa5ac6c4c..46480d81df0 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -60,7 +60,7 @@ void __init os_info_init(void) os_info.version_minor = OS_INFO_VERSION_MINOR; os_info.magic = OS_INFO_MAGIC; os_info.csum = os_info_csum(&os_info); - memcpy_absolute(&S390_lowcore.os_info, &ptr, sizeof(ptr)); + mem_assign_absolute(S390_lowcore.os_info, (unsigned long) ptr); } #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 60055cefdd0..733175373a4 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -1,7 +1,7 @@ /* * This file handles the architecture dependent parts of process handling. * - * Copyright IBM Corp. 1999,2009 + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Hartmut Penner <hp@de.ibm.com>, * Denis Joseph Barrow, @@ -25,8 +25,8 @@ #include <linux/module.h> #include <asm/io.h> #include <asm/processor.h> +#include <asm/vtimer.h> #include <asm/irq.h> -#include <asm/timer.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/switch_to.h> diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 6e0073e43f5..572d4c9cb33 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/processor.c - * * Copyright IBM Corp. 2008 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ @@ -25,13 +23,15 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id); */ void __cpuinit cpu_init(void) { - struct cpuid *id = &per_cpu(cpu_id, smp_processor_id()); + struct s390_idle_data *idle = &__get_cpu_var(s390_idle); + struct cpuid *id = &__get_cpu_var(cpu_id); get_cpu_id(id); atomic_inc(&init_mm.mm_count); current->active_mm = &init_mm; BUG_ON(current->mm); enter_lazy_tlb(&init_mm, current); + memset(idle, 0, sizeof(*idle)); } /* diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 4993e689b2c..f4eb37680b9 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1,7 +1,7 @@ /* * Ptrace user space interface. * - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * Author(s): Denis Joseph Barrow * Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index ad67c214be0..dd8016b0477 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -1,13 +1,12 @@ /* - * arch/s390/kernel/reipl.S - * * S390 version - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com) */ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> # # store_status: Empty implementation until kdump is supported on 31 bit @@ -60,7 +59,7 @@ ENTRY(do_reipl_asm) bas %r14,.Ldisab-.Lpg0(%r13) .L003: st %r1,__LC_SUBCHANNEL_ID lpsw 0 - sigp 0,0,0(6) + sigp 0,0,SIGP_RESTART .Ldisab: st %r14,.Ldispsw+4-.Lpg0(%r13) lpsw .Ldispsw-.Lpg0(%r13) .align 8 diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S index 36b32658fb2..dc3b1273c4d 100644 --- a/arch/s390/kernel/reipl64.S +++ b/arch/s390/kernel/reipl64.S @@ -1,11 +1,12 @@ /* - * Copyright IBM Corp 2000,2011 + * Copyright IBM Corp 2000, 2011 * Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>, * Denis Joseph Barrow, */ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> # # store_status @@ -106,7 +107,7 @@ ENTRY(do_reipl_asm) .L003: st %r1,__LC_SUBCHANNEL_ID lhi %r1,0 # mode 0 = esa slr %r0,%r0 # set cpuid to zero - sigp %r1,%r0,0x12 # switch to esa mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # switch to esa mode lpsw 0 .Ldisab: sll %r14,1 srl %r14,1 # need to kill hi bit to avoid specification exceptions. diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index c91d70aede9..f4e6f20e117 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/relocate_kernel.S - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> @@ -9,6 +7,7 @@ */ #include <linux/linkage.h> +#include <asm/sigp.h> /* * moves the new kernel to its destination... @@ -93,7 +92,7 @@ ENTRY(relocate_kernel) .no_diag308: sr %r1,%r1 # clear %r1 sr %r2,%r2 # clear %r2 - sigp %r1,%r2,0x12 # set cpuid to zero + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # set cpuid to zero lpsw 0 # hopefully start new kernel... .align 8 diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S index 7c3ce589a7f..cfac28330b0 100644 --- a/arch/s390/kernel/relocate_kernel64.S +++ b/arch/s390/kernel/relocate_kernel64.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/relocate_kernel64.S - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> @@ -9,6 +7,7 @@ */ #include <linux/linkage.h> +#include <asm/sigp.h> /* * moves the new kernel to its destination... @@ -45,7 +44,7 @@ ENTRY(relocate_kernel) diag %r0,%r0,0x308 .back: lhi %r1,1 # mode 1 = esame - sigp %r1,%r0,0x12 # switch to esame mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # switch to esame mode sam64 # switch to 64 bit addressing mode basr %r13,0 .back_base: @@ -96,7 +95,7 @@ ENTRY(relocate_kernel) sam31 # 31 bit mode sr %r1,%r1 # erase register r1 sr %r2,%r2 # erase register r2 - sigp %r1,%r2,0x12 # set cpuid to zero + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # set cpuid to zero lpsw 0 # hopefully start new kernel... .align 8 diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 95792d846bb..bf053898630 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -1,7 +1,7 @@ /* * Mini SCLP driver. * - * Copyright IBM Corp. 2004,2009 + * Copyright IBM Corp. 2004, 2009 * * Author(s): Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 489d1d8d96b..743c0f32fe3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/setup.c - * * S390 version - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -63,6 +61,7 @@ #include <asm/kvm_virtio.h> #include <asm/diag.h> #include <asm/os_info.h> +#include <asm/sclp.h> #include "entry.h" long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | @@ -138,9 +137,14 @@ __setup("condev=", condev_setup); static void __init set_preferred_console(void) { - if (MACHINE_IS_KVM) - add_preferred_console("hvc", 0, NULL); - else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) + if (MACHINE_IS_KVM) { + if (sclp_has_vt220()) + add_preferred_console("ttyS", 1, NULL); + else if (sclp_has_linemode()) + add_preferred_console("ttyS", 0, NULL); + else + add_preferred_console("hvc", 0, NULL); + } else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) add_preferred_console("ttyS", 0, NULL); else if (CONSOLE_IS_3270) add_preferred_console("tty3270", 0, NULL); @@ -430,10 +434,11 @@ static void __init setup_lowcore(void) lc->restart_source = -1UL; /* Setup absolute zero lowcore */ - memcpy_absolute(&S390_lowcore.restart_stack, &lc->restart_stack, - 4 * sizeof(unsigned long)); - memcpy_absolute(&S390_lowcore.restart_psw, &lc->restart_psw, - sizeof(lc->restart_psw)); + mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack); + mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn); + mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data); + mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); + mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; @@ -598,9 +603,7 @@ static void __init setup_memory_end(void) static void __init setup_vmcoreinfo(void) { #ifdef CONFIG_KEXEC - unsigned long ptr = paddr_vmcoreinfo_note(); - - memcpy_absolute(&S390_lowcore.vmcore_info, &ptr, sizeof(ptr)); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); #endif } diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index ac565b44aab..c13a2a37ef0 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/signal.c - * - * Copyright (C) IBM Corp. 1999,2006 + * Copyright IBM Corp. 1999, 2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * * Based on Intel version diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 8dca9c248ac..720fda1620f 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1,7 +1,7 @@ /* * SMP related functions * - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Denis Joseph Barrow, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, @@ -38,40 +38,16 @@ #include <asm/setup.h> #include <asm/irq.h> #include <asm/tlbflush.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/lowcore.h> #include <asm/sclp.h> #include <asm/vdso.h> #include <asm/debug.h> #include <asm/os_info.h> +#include <asm/sigp.h> #include "entry.h" enum { - sigp_sense = 1, - sigp_external_call = 2, - sigp_emergency_signal = 3, - sigp_start = 4, - sigp_stop = 5, - sigp_restart = 6, - sigp_stop_and_store_status = 9, - sigp_initial_cpu_reset = 11, - sigp_cpu_reset = 12, - sigp_set_prefix = 13, - sigp_store_status_at_address = 14, - sigp_store_extended_status_at_address = 15, - sigp_set_architecture = 18, - sigp_conditional_emergency_signal = 19, - sigp_sense_running = 21, -}; - -enum { - sigp_order_code_accepted = 0, - sigp_status_stored = 1, - sigp_busy = 2, - sigp_not_operational = 3, -}; - -enum { ec_schedule = 0, ec_call_function, ec_call_function_single, @@ -124,7 +100,7 @@ static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status) while (1) { cc = __pcpu_sigp(addr, order, parm, status); - if (cc != sigp_busy) + if (cc != SIGP_CC_BUSY) return cc; cpu_relax(); } @@ -136,7 +112,7 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) for (retry = 0; ; retry++) { cc = __pcpu_sigp(pcpu->address, order, parm, &pcpu->status); - if (cc != sigp_busy) + if (cc != SIGP_CC_BUSY) break; if (retry >= 3) udelay(10); @@ -146,20 +122,19 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) static inline int pcpu_stopped(struct pcpu *pcpu) { - if (__pcpu_sigp(pcpu->address, sigp_sense, - 0, &pcpu->status) != sigp_status_stored) + if (__pcpu_sigp(pcpu->address, SIGP_SENSE, + 0, &pcpu->status) != SIGP_CC_STATUS_STORED) return 0; - /* Check for stopped and check stop state */ - return !!(pcpu->status & 0x50); + return !!(pcpu->status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED)); } static inline int pcpu_running(struct pcpu *pcpu) { - if (__pcpu_sigp(pcpu->address, sigp_sense_running, - 0, &pcpu->status) != sigp_status_stored) + if (__pcpu_sigp(pcpu->address, SIGP_SENSE_RUNNING, + 0, &pcpu->status) != SIGP_CC_STATUS_STORED) return 1; - /* Check for running status */ - return !(pcpu->status & 0x400); + /* Status stored condition code is equivalent to cpu not running. */ + return 0; } /* @@ -181,7 +156,7 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit) set_bit(ec_bit, &pcpu->ec_mask); order = pcpu_running(pcpu) ? - sigp_external_call : sigp_emergency_signal; + SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL; pcpu_sigp_retry(pcpu, order, 0); } @@ -214,7 +189,7 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) goto out; #endif lowcore_ptr[cpu] = lc; - pcpu_sigp_retry(pcpu, sigp_set_prefix, (u32)(unsigned long) lc); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc); return 0; out: if (pcpu != &pcpu_devices[0]) { @@ -229,7 +204,7 @@ out: static void pcpu_free_lowcore(struct pcpu *pcpu) { - pcpu_sigp_retry(pcpu, sigp_set_prefix, 0); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0); lowcore_ptr[pcpu - pcpu_devices] = NULL; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { @@ -288,7 +263,7 @@ static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data) lc->restart_fn = (unsigned long) func; lc->restart_data = (unsigned long) data; lc->restart_source = -1UL; - pcpu_sigp_retry(pcpu, sigp_restart, 0); + pcpu_sigp_retry(pcpu, SIGP_RESTART, 0); } /* @@ -298,26 +273,26 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), void *data, unsigned long stack) { struct _lowcore *lc = lowcore_ptr[pcpu - pcpu_devices]; - struct { - unsigned long stack; - void *func; - void *data; - unsigned long source; - } restart = { stack, func, data, stap() }; + unsigned long source_cpu = stap(); __load_psw_mask(psw_kernel_bits); - if (pcpu->address == restart.source) + if (pcpu->address == source_cpu) func(data); /* should not return */ /* Stop target cpu (if func returns this stops the current cpu). */ - pcpu_sigp_retry(pcpu, sigp_stop, 0); + pcpu_sigp_retry(pcpu, SIGP_STOP, 0); /* Restart func on the target cpu and stop the current cpu. */ - memcpy_absolute(&lc->restart_stack, &restart, sizeof(restart)); + mem_assign_absolute(lc->restart_stack, stack); + mem_assign_absolute(lc->restart_fn, (unsigned long) func); + mem_assign_absolute(lc->restart_data, (unsigned long) data); + mem_assign_absolute(lc->restart_source, source_cpu); asm volatile( - "0: sigp 0,%0,6 # sigp restart to target cpu\n" + "0: sigp 0,%0,%2 # sigp restart to target cpu\n" " brc 2,0b # busy, try again\n" - "1: sigp 0,%1,5 # sigp stop to current cpu\n" + "1: sigp 0,%1,%3 # sigp stop to current cpu\n" " brc 2,1b # busy, try again\n" - : : "d" (pcpu->address), "d" (restart.source) : "0", "1", "cc"); + : : "d" (pcpu->address), "d" (source_cpu), + "K" (SIGP_RESTART), "K" (SIGP_STOP) + : "0", "1", "cc"); for (;;) ; } @@ -388,8 +363,8 @@ void smp_emergency_stop(cpumask_t *cpumask) for_each_cpu(cpu, cpumask) { struct pcpu *pcpu = pcpu_devices + cpu; set_bit(ec_stop_cpu, &pcpu->ec_mask); - while (__pcpu_sigp(pcpu->address, sigp_emergency_signal, - 0, NULL) == sigp_busy && + while (__pcpu_sigp(pcpu->address, SIGP_EMERGENCY_SIGNAL, + 0, NULL) == SIGP_CC_BUSY && get_clock() < end) cpu_relax(); } @@ -425,7 +400,7 @@ void smp_send_stop(void) /* stop all processors */ for_each_cpu(cpu, &cpumask) { struct pcpu *pcpu = pcpu_devices + cpu; - pcpu_sigp_retry(pcpu, sigp_stop, 0); + pcpu_sigp_retry(pcpu, SIGP_STOP, 0); while (!pcpu_stopped(pcpu)) cpu_relax(); } @@ -436,7 +411,7 @@ void smp_send_stop(void) */ void smp_stop_cpu(void) { - pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } @@ -590,7 +565,7 @@ static void __init smp_get_save_area(int cpu, u16 address) } #endif /* Get the registers of a non-boot cpu. */ - __pcpu_sigp_relax(address, sigp_stop_and_store_status, 0, NULL); + __pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL); memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area)); } @@ -599,8 +574,8 @@ int smp_store_status(int cpu) struct pcpu *pcpu; pcpu = pcpu_devices + cpu; - if (__pcpu_sigp_relax(pcpu->address, sigp_stop_and_store_status, - 0, NULL) != sigp_order_code_accepted) + if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS, + 0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; return 0; } @@ -621,8 +596,8 @@ static struct sclp_cpu_info *smp_get_cpu_info(void) if (info && (use_sigp_detection || sclp_get_cpu_info(info))) { use_sigp_detection = 1; for (address = 0; address <= MAX_CPU_ADDRESS; address++) { - if (__pcpu_sigp_relax(address, sigp_sense, 0, NULL) == - sigp_not_operational) + if (__pcpu_sigp_relax(address, SIGP_SENSE, 0, NULL) == + SIGP_CC_NOT_OPERATIONAL) continue; info->cpu[info->configured].address = address; info->configured++; @@ -732,8 +707,8 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) pcpu = pcpu_devices + cpu; if (pcpu->state != CPU_STATE_CONFIGURED) return -EIO; - if (pcpu_sigp_retry(pcpu, sigp_initial_cpu_reset, 0) != - sigp_order_code_accepted) + if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) != + SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; rc = pcpu_alloc_lowcore(pcpu, cpu); @@ -793,7 +768,7 @@ void __cpu_die(unsigned int cpu) void __noreturn cpu_die(void) { idle_task_exit(); - pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } @@ -940,7 +915,7 @@ static ssize_t show_idle_count(struct device *dev, do { sequence = ACCESS_ONCE(idle->sequence); idle_count = ACCESS_ONCE(idle->idle_count); - if (ACCESS_ONCE(idle->idle_enter)) + if (ACCESS_ONCE(idle->clock_idle_enter)) idle_count++; } while ((sequence & 1) || (idle->sequence != sequence)); return sprintf(buf, "%llu\n", idle_count); @@ -958,8 +933,8 @@ static ssize_t show_idle_time(struct device *dev, now = get_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_time = ACCESS_ONCE(idle->idle_time); - idle_enter = ACCESS_ONCE(idle->idle_enter); - idle_exit = ACCESS_ONCE(idle->idle_exit); + idle_enter = ACCESS_ONCE(idle->clock_idle_enter); + idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while ((sequence & 1) || (idle->sequence != sequence)); idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; return sprintf(buf, "%llu\n", idle_time >> 12); @@ -982,14 +957,11 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, unsigned int cpu = (unsigned int)(long)hcpu; struct cpu *c = &pcpu_devices[cpu].cpu; struct device *s = &c->dev; - struct s390_idle_data *idle; int err = 0; switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - idle = &per_cpu(s390_idle, cpu); - memset(idle, 0, sizeof(struct s390_idle_data)); err = sysfs_create_group(&s->kobj, &cpu_online_attr_group); break; case CPU_DEAD: diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 8841919ef7e..1785cd82253 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -1,9 +1,7 @@ /* - * arch/s390/kernel/stacktrace.c - * * Stack trace management functions * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index dd70ef04605..d4ca4e0617b 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -12,6 +12,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> /* * Save register context in absolute 0 lowcore and call swsusp_save() to @@ -163,7 +164,7 @@ ENTRY(swsusp_arch_resume) diag %r0,%r0,0x308 restart_entry: lhi %r1,1 - sigp %r1,%r0,0x12 + sigp %r1,%r0,SIGP_SET_ARCHITECTURE sam64 larl %r1,.Lnew_pgm_check_psw lpswe 0(%r1) @@ -179,7 +180,7 @@ pgm_check_entry: larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ mvc __LC_RST_NEW_PSW(16,%r0),0(%r4) 3: - sigp %r9,%r1,11 /* sigp initial cpu reset */ + sigp %r9,%r1,SIGP_INITIAL_CPU_RESET /* sigp initial cpu reset */ brc 8,4f /* accepted */ brc 2,3b /* busy, try again */ @@ -190,16 +191,16 @@ pgm_check_entry: larl %r3,_sclp_print_early lghi %r1,0 sam31 - sigp %r1,%r0,0x12 + sigp %r1,%r0,SIGP_SET_ARCHITECTURE basr %r14,%r3 larl %r3,.Ldisabled_wait_31 lpsw 0(%r3) 4: /* Switch to suspend CPU */ - sigp %r9,%r1,6 /* sigp restart to suspend CPU */ + sigp %r9,%r1,SIGP_RESTART /* sigp restart to suspend CPU */ brc 2,4b /* busy, try again */ 5: - sigp %r9,%r2,5 /* sigp stop to current resume CPU */ + sigp %r9,%r2,SIGP_STOP /* sigp stop to current resume CPU */ brc 2,5b /* busy, try again */ 6: j 6b @@ -207,7 +208,7 @@ restart_suspend: larl %r1,.Lresume_cpu llgh %r2,0(%r1) 7: - sigp %r9,%r2,1 /* sigp sense, wait for resume CPU */ + sigp %r9,%r2,SIGP_SENSE /* sigp sense, wait for resume CPU */ brc 8,7b /* accepted, status 0, still running */ brc 2,7b /* busy, try again */ tmll %r9,0x40 /* Test if resume CPU is stopped */ diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index 78ea1948ff5..b4a29eee41b 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/sys_s390.c - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Thomas Spatzier (tspat@de.ibm.com) * diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index d4e1cb1dbcd..dcec960fc72 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -1,5 +1,4 @@ /* - * arch/s390/kernel/time.c * Time of day based timer functions. * * S390 version @@ -45,7 +44,7 @@ #include <asm/vdso.h> #include <asm/irq.h> #include <asm/irq_regs.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/etr.h> #include <asm/cio.h> #include "entry.h" diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4f8dc942257..05151e06c38 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2011 + * Copyright IBM Corp. 2007, 2011 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 77cdf4234eb..af2421a0f31 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/traps.c - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), * diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 39ebff50694..4fc97b40a6e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -1,71 +1,82 @@ /* - * arch/s390/kernel/vtime.c * Virtual cpu timer based timer functions. * - * S390 version - * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2004, 2012 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> */ -#include <linux/module.h> +#include <linux/kernel_stat.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/export.h> #include <linux/kernel.h> -#include <linux/time.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/smp.h> -#include <linux/types.h> #include <linux/timex.h> -#include <linux/notifier.h> -#include <linux/kernel_stat.h> -#include <linux/rcupdate.h> -#include <linux/posix-timers.h> +#include <linux/types.h> +#include <linux/time.h> #include <linux/cpu.h> -#include <linux/kprobes.h> +#include <linux/smp.h> -#include <asm/timer.h> #include <asm/irq_regs.h> #include <asm/cputime.h> +#include <asm/vtimer.h> #include <asm/irq.h> #include "entry.h" -static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer); +static void virt_timer_expire(void); DEFINE_PER_CPU(struct s390_idle_data, s390_idle); -static inline __u64 get_vtimer(void) +static LIST_HEAD(virt_timer_list); +static DEFINE_SPINLOCK(virt_timer_lock); +static atomic64_t virt_timer_current; +static atomic64_t virt_timer_elapsed; + +static inline u64 get_vtimer(void) { - __u64 timer; + u64 timer; - asm volatile("STPT %0" : "=m" (timer)); + asm volatile("stpt %0" : "=m" (timer)); return timer; } -static inline void set_vtimer(__u64 expires) +static inline void set_vtimer(u64 expires) { - __u64 timer; + u64 timer; - asm volatile (" STPT %0\n" /* Store current cpu timer value */ - " SPT %1" /* Set new value immediately afterwards */ - : "=m" (timer) : "m" (expires) ); + asm volatile( + " stpt %0\n" /* Store current cpu timer value */ + " spt %1" /* Set new value imm. afterwards */ + : "=m" (timer) : "m" (expires)); S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer; S390_lowcore.last_update_timer = expires; } +static inline int virt_timer_forward(u64 elapsed) +{ + BUG_ON(!irqs_disabled()); + + if (list_empty(&virt_timer_list)) + return 0; + elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed); + return elapsed >= atomic64_read(&virt_timer_current); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -static void do_account_vtime(struct task_struct *tsk, int hardirq_offset) +static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) { struct thread_info *ti = task_thread_info(tsk); - __u64 timer, clock, user, system, steal; + u64 timer, clock, user, system, steal; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; - asm volatile (" STPT %0\n" /* Store current cpu timer value */ - " STCK %1" /* Store current tod clock value */ - : "=m" (S390_lowcore.last_update_timer), - "=m" (S390_lowcore.last_update_clock) ); + asm volatile( + " stpt %0\n" /* Store current cpu timer value */ + " stck %1" /* Store current tod clock value */ + : "=m" (S390_lowcore.last_update_timer), + "=m" (S390_lowcore.last_update_clock)); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; @@ -84,6 +95,8 @@ static void do_account_vtime(struct task_struct *tsk, int hardirq_offset) S390_lowcore.steal_timer = 0; account_steal_time(steal); } + + return virt_timer_forward(user + system); } void account_vtime(struct task_struct *prev, struct task_struct *next) @@ -101,7 +114,8 @@ void account_vtime(struct task_struct *prev, struct task_struct *next) void account_process_tick(struct task_struct *tsk, int user_tick) { - do_account_vtime(tsk, HARDIRQ_OFFSET); + if (do_account_vtime(tsk, HARDIRQ_OFFSET)) + virt_timer_expire(); } /* @@ -111,7 +125,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick) void account_system_vtime(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - __u64 timer, system; + u64 timer, system; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); @@ -121,13 +135,14 @@ void account_system_vtime(struct task_struct *tsk) S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; account_system_time(tsk, 0, system, system); + + virt_timer_forward(system); } EXPORT_SYMBOL_GPL(account_system_vtime); void __kprobes vtime_stop_cpu(void) { struct s390_idle_data *idle = &__get_cpu_var(s390_idle); - struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer); unsigned long long idle_time; unsigned long psw_mask; @@ -141,7 +156,7 @@ void __kprobes vtime_stop_cpu(void) idle->nohz_delay = 0; /* Call the assembler magic in entry.S */ - psw_idle(idle, vq, psw_mask, !list_empty(&vq->list)); + psw_idle(idle, psw_mask); /* Reenable preemption tracer. */ start_critical_timings(); @@ -149,9 +164,9 @@ void __kprobes vtime_stop_cpu(void) /* Account time spent with enabled wait psw loaded as idle time. */ idle->sequence++; smp_wmb(); - idle_time = idle->idle_exit - idle->idle_enter; + idle_time = idle->clock_idle_exit - idle->clock_idle_enter; + idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; - idle->idle_enter = idle->idle_exit = 0ULL; idle->idle_count++; account_idle_time(idle_time); smp_wmb(); @@ -167,10 +182,10 @@ cputime64_t s390_get_idle_time(int cpu) do { now = get_clock(); sequence = ACCESS_ONCE(idle->sequence); - idle_enter = ACCESS_ONCE(idle->idle_enter); - idle_exit = ACCESS_ONCE(idle->idle_exit); + idle_enter = ACCESS_ONCE(idle->clock_idle_enter); + idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while ((sequence & 1) || (idle->sequence != sequence)); - return idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; } /* @@ -179,11 +194,11 @@ cputime64_t s390_get_idle_time(int cpu) */ static void list_add_sorted(struct vtimer_list *timer, struct list_head *head) { - struct vtimer_list *event; + struct vtimer_list *tmp; - list_for_each_entry(event, head, entry) { - if (event->expires > timer->expires) { - list_add_tail(&timer->entry, &event->entry); + list_for_each_entry(tmp, head, entry) { + if (tmp->expires > timer->expires) { + list_add_tail(&timer->entry, &tmp->entry); return; } } @@ -191,82 +206,45 @@ static void list_add_sorted(struct vtimer_list *timer, struct list_head *head) } /* - * Do the callback functions of expired vtimer events. - * Called from within the interrupt handler. - */ -static void do_callbacks(struct list_head *cb_list) -{ - struct vtimer_queue *vq; - struct vtimer_list *event, *tmp; - - if (list_empty(cb_list)) - return; - - vq = &__get_cpu_var(virt_cpu_timer); - - list_for_each_entry_safe(event, tmp, cb_list, entry) { - list_del_init(&event->entry); - (event->function)(event->data); - if (event->interval) { - /* Recharge interval timer */ - event->expires = event->interval + vq->elapsed; - spin_lock(&vq->lock); - list_add_sorted(event, &vq->list); - spin_unlock(&vq->lock); - } - } -} - -/* - * Handler for the virtual CPU timer. + * Handler for expired virtual CPU timer. */ -static void do_cpu_timer_interrupt(struct ext_code ext_code, - unsigned int param32, unsigned long param64) +static void virt_timer_expire(void) { - struct vtimer_queue *vq; - struct vtimer_list *event, *tmp; - struct list_head cb_list; /* the callback queue */ - __u64 elapsed, next; - - kstat_cpu(smp_processor_id()).irqs[EXTINT_TMR]++; - INIT_LIST_HEAD(&cb_list); - vq = &__get_cpu_var(virt_cpu_timer); - - /* walk timer list, fire all expired events */ - spin_lock(&vq->lock); - - elapsed = vq->elapsed + (vq->timer - S390_lowcore.async_enter_timer); - BUG_ON((s64) elapsed < 0); - vq->elapsed = 0; - list_for_each_entry_safe(event, tmp, &vq->list, entry) { - if (event->expires < elapsed) + struct vtimer_list *timer, *tmp; + unsigned long elapsed; + LIST_HEAD(cb_list); + + /* walk timer list, fire all expired timers */ + spin_lock(&virt_timer_lock); + elapsed = atomic64_read(&virt_timer_elapsed); + list_for_each_entry_safe(timer, tmp, &virt_timer_list, entry) { + if (timer->expires < elapsed) /* move expired timer to the callback queue */ - list_move_tail(&event->entry, &cb_list); + list_move_tail(&timer->entry, &cb_list); else - event->expires -= elapsed; + timer->expires -= elapsed; } - spin_unlock(&vq->lock); - - do_callbacks(&cb_list); - - /* next event is first in list */ - next = VTIMER_MAX_SLICE; - spin_lock(&vq->lock); - if (!list_empty(&vq->list)) { - event = list_first_entry(&vq->list, struct vtimer_list, entry); - next = event->expires; + if (!list_empty(&virt_timer_list)) { + timer = list_first_entry(&virt_timer_list, + struct vtimer_list, entry); + atomic64_set(&virt_timer_current, timer->expires); + } + atomic64_sub(elapsed, &virt_timer_elapsed); + spin_unlock(&virt_timer_lock); + + /* Do callbacks and recharge periodic timers */ + list_for_each_entry_safe(timer, tmp, &cb_list, entry) { + list_del_init(&timer->entry); + timer->function(timer->data); + if (timer->interval) { + /* Recharge interval timer */ + timer->expires = timer->interval + + atomic64_read(&virt_timer_elapsed); + spin_lock(&virt_timer_lock); + list_add_sorted(timer, &virt_timer_list); + spin_unlock(&virt_timer_lock); + } } - spin_unlock(&vq->lock); - /* - * To improve precision add the time spent by the - * interrupt handler to the elapsed time. - * Note: CPU timer counts down and we got an interrupt, - * the current content is negative - */ - elapsed = S390_lowcore.async_enter_timer - get_vtimer(); - set_vtimer(next - elapsed); - vq->timer = next - elapsed; - vq->elapsed = elapsed; } void init_virt_timer(struct vtimer_list *timer) @@ -278,179 +256,108 @@ EXPORT_SYMBOL(init_virt_timer); static inline int vtimer_pending(struct vtimer_list *timer) { - return (!list_empty(&timer->entry)); + return !list_empty(&timer->entry); } -/* - * this function should only run on the specified CPU - */ static void internal_add_vtimer(struct vtimer_list *timer) { - struct vtimer_queue *vq; - unsigned long flags; - __u64 left, expires; - - vq = &per_cpu(virt_cpu_timer, timer->cpu); - spin_lock_irqsave(&vq->lock, flags); - - BUG_ON(timer->cpu != smp_processor_id()); - - if (list_empty(&vq->list)) { - /* First timer on this cpu, just program it. */ - list_add(&timer->entry, &vq->list); - set_vtimer(timer->expires); - vq->timer = timer->expires; - vq->elapsed = 0; + if (list_empty(&virt_timer_list)) { + /* First timer, just program it. */ + atomic64_set(&virt_timer_current, timer->expires); + atomic64_set(&virt_timer_elapsed, 0); + list_add(&timer->entry, &virt_timer_list); } else { - /* Check progress of old timers. */ - expires = timer->expires; - left = get_vtimer(); - if (likely((s64) expires < (s64) left)) { + /* Update timer against current base. */ + timer->expires += atomic64_read(&virt_timer_elapsed); + if (likely((s64) timer->expires < + (s64) atomic64_read(&virt_timer_current))) /* The new timer expires before the current timer. */ - set_vtimer(expires); - vq->elapsed += vq->timer - left; - vq->timer = expires; - } else { - vq->elapsed += vq->timer - left; - vq->timer = left; - } - /* Insert new timer into per cpu list. */ - timer->expires += vq->elapsed; - list_add_sorted(timer, &vq->list); + atomic64_set(&virt_timer_current, timer->expires); + /* Insert new timer into the list. */ + list_add_sorted(timer, &virt_timer_list); } - - spin_unlock_irqrestore(&vq->lock, flags); - /* release CPU acquired in prepare_vtimer or mod_virt_timer() */ - put_cpu(); } -static inline void prepare_vtimer(struct vtimer_list *timer) +static void __add_vtimer(struct vtimer_list *timer, int periodic) { - BUG_ON(!timer->function); - BUG_ON(!timer->expires || timer->expires > VTIMER_MAX_SLICE); - BUG_ON(vtimer_pending(timer)); - timer->cpu = get_cpu(); + unsigned long flags; + + timer->interval = periodic ? timer->expires : 0; + spin_lock_irqsave(&virt_timer_lock, flags); + internal_add_vtimer(timer); + spin_unlock_irqrestore(&virt_timer_lock, flags); } /* * add_virt_timer - add an oneshot virtual CPU timer */ -void add_virt_timer(void *new) +void add_virt_timer(struct vtimer_list *timer) { - struct vtimer_list *timer; - - timer = (struct vtimer_list *)new; - prepare_vtimer(timer); - timer->interval = 0; - internal_add_vtimer(timer); + __add_vtimer(timer, 0); } EXPORT_SYMBOL(add_virt_timer); /* * add_virt_timer_int - add an interval virtual CPU timer */ -void add_virt_timer_periodic(void *new) +void add_virt_timer_periodic(struct vtimer_list *timer) { - struct vtimer_list *timer; - - timer = (struct vtimer_list *)new; - prepare_vtimer(timer); - timer->interval = timer->expires; - internal_add_vtimer(timer); + __add_vtimer(timer, 1); } EXPORT_SYMBOL(add_virt_timer_periodic); -static int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) +static int __mod_vtimer(struct vtimer_list *timer, u64 expires, int periodic) { - struct vtimer_queue *vq; unsigned long flags; - int cpu; + int rc; BUG_ON(!timer->function); - BUG_ON(!expires || expires > VTIMER_MAX_SLICE); if (timer->expires == expires && vtimer_pending(timer)) return 1; - - cpu = get_cpu(); - vq = &per_cpu(virt_cpu_timer, cpu); - - /* disable interrupts before test if timer is pending */ - spin_lock_irqsave(&vq->lock, flags); - - /* if timer isn't pending add it on the current CPU */ - if (!vtimer_pending(timer)) { - spin_unlock_irqrestore(&vq->lock, flags); - - if (periodic) - timer->interval = expires; - else - timer->interval = 0; - timer->expires = expires; - timer->cpu = cpu; - internal_add_vtimer(timer); - return 0; - } - - /* check if we run on the right CPU */ - BUG_ON(timer->cpu != cpu); - - list_del_init(&timer->entry); + spin_lock_irqsave(&virt_timer_lock, flags); + rc = vtimer_pending(timer); + if (rc) + list_del_init(&timer->entry); + timer->interval = periodic ? expires : 0; timer->expires = expires; - if (periodic) - timer->interval = expires; - - /* the timer can't expire anymore so we can release the lock */ - spin_unlock_irqrestore(&vq->lock, flags); internal_add_vtimer(timer); - return 1; + spin_unlock_irqrestore(&virt_timer_lock, flags); + return rc; } /* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on. - * * returns whether it has modified a pending timer (1) or not (0) */ -int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +int mod_virt_timer(struct vtimer_list *timer, u64 expires) { return __mod_vtimer(timer, expires, 0); } EXPORT_SYMBOL(mod_virt_timer); /* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on. - * * returns whether it has modified a pending timer (1) or not (0) */ -int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires) +int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires) { return __mod_vtimer(timer, expires, 1); } EXPORT_SYMBOL(mod_virt_timer_periodic); /* - * delete a virtual timer + * Delete a virtual timer. * * returns whether the deleted timer was pending (1) or not (0) */ int del_virt_timer(struct vtimer_list *timer) { unsigned long flags; - struct vtimer_queue *vq; - /* check if timer is pending */ if (!vtimer_pending(timer)) return 0; - - vq = &per_cpu(virt_cpu_timer, timer->cpu); - spin_lock_irqsave(&vq->lock, flags); - - /* we don't interrupt a running timer, just let it expire! */ + spin_lock_irqsave(&virt_timer_lock, flags); list_del_init(&timer->entry); - - spin_unlock_irqrestore(&vq->lock, flags); + spin_unlock_irqrestore(&virt_timer_lock, flags); return 1; } EXPORT_SYMBOL(del_virt_timer); @@ -458,20 +365,10 @@ EXPORT_SYMBOL(del_virt_timer); /* * Start the virtual CPU timer on the current CPU. */ -void init_cpu_vtimer(void) +void __cpuinit init_cpu_vtimer(void) { - struct vtimer_queue *vq; - - /* initialize per cpu vtimer structure */ - vq = &__get_cpu_var(virt_cpu_timer); - INIT_LIST_HEAD(&vq->list); - spin_lock_init(&vq->lock); - - /* enable cpu timer interrupts */ - __ctl_set_bit(0,10); - /* set initial cpu timer */ - set_vtimer(0x7fffffffffffffffULL); + set_vtimer(VTIMER_MAX_SLICE); } static int __cpuinit s390_nohz_notify(struct notifier_block *self, @@ -493,12 +390,7 @@ static int __cpuinit s390_nohz_notify(struct notifier_block *self, void __init vtime_init(void) { - /* request the cpu timer external interrupt */ - if (register_external_interrupt(0x1005, do_cpu_timer_interrupt)) - panic("Couldn't request external interrupt 0x1005"); - /* Enable cpu timer interrupts on the boot cpu. */ init_cpu_vtimer(); cpu_notifier(s390_nohz_notify, 0); } - diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index b23d9ac77df..c88bb779339 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -1,7 +1,7 @@ /* - * diag.c - handling diagnose instructions + * handling diagnose instructions * - * Copyright IBM Corp. 2008,2011 + * Copyright IBM Corp. 2008, 2011 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index c86f6ae43f7..4703f129e95 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,7 +1,7 @@ /* - * access.h - access guest memory + * access guest memory * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 979cbe55bf5..adae539f12e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,7 +1,7 @@ /* - * intercept.c - in-kernel handling for sie intercepts + * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2d9f9a72bb8..b7bc1aac8ed 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,5 +1,5 @@ /* - * interrupt.c - handling kvm guest interrupts + * handling kvm guest interrupts * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 664766d0c83..d470ccbfaba 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1,7 +1,7 @@ /* - * s390host.c -- hosting zSeries kernel virtual machines + * hosting zSeries kernel virtual machines * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -347,6 +347,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.guest_fpregs.fpc = 0; asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); vcpu->arch.sie_block->gbea = 1; + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); } int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 2294377975e..d75bc5e92c5 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -1,7 +1,7 @@ /* - * kvm_s390.h - definition for kvm on s390 + * definition for kvm on s390 * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 68a6b2ed16b..60da903d6f3 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1,5 +1,5 @@ /* - * priv.c - handling privileged instructions + * handling privileged instructions * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 0ad4cf23839..56f80e1f98f 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -1,7 +1,7 @@ /* - * sigp.c - handlinge interprocessor communication + * handling interprocessor communication * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -15,38 +15,10 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/slab.h> +#include <asm/sigp.h> #include "gaccess.h" #include "kvm-s390.h" -/* sigp order codes */ -#define SIGP_SENSE 0x01 -#define SIGP_EXTERNAL_CALL 0x02 -#define SIGP_EMERGENCY 0x03 -#define SIGP_START 0x04 -#define SIGP_STOP 0x05 -#define SIGP_RESTART 0x06 -#define SIGP_STOP_STORE_STATUS 0x09 -#define SIGP_INITIAL_CPU_RESET 0x0b -#define SIGP_CPU_RESET 0x0c -#define SIGP_SET_PREFIX 0x0d -#define SIGP_STORE_STATUS_ADDR 0x0e -#define SIGP_SET_ARCH 0x12 -#define SIGP_SENSE_RUNNING 0x15 - -/* cpu status bits */ -#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL -#define SIGP_STAT_NOT_RUNNING 0x00000400UL -#define SIGP_STAT_INCORRECT_STATE 0x00000200UL -#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL -#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL -#define SIGP_STAT_STOPPED 0x00000040UL -#define SIGP_STAT_OPERATOR_INTERV 0x00000020UL -#define SIGP_STAT_CHECK_STOP 0x00000010UL -#define SIGP_STAT_INOPERATIVE 0x00000004UL -#define SIGP_STAT_INVALID_ORDER 0x00000002UL -#define SIGP_STAT_RECEIVER_CHECK 0x00000001UL - - static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg) { @@ -54,19 +26,23 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags) - & CPUSTAT_STOPPED)) { - *reg &= 0xffffffff00000000UL; - rc = 1; /* status stored */ - } else { + & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED))) + rc = SIGP_CC_ORDER_CODE_ACCEPTED; + else { *reg &= 0xffffffff00000000UL; - *reg |= SIGP_STAT_STOPPED; - rc = 1; /* status stored */ + if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_ECALL_PEND) + *reg |= SIGP_STATUS_EXT_CALL_PENDING; + if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_STOPPED) + *reg |= SIGP_STATUS_STOPPED; + rc = SIGP_CC_STATUS_STORED; } spin_unlock(&fi->lock); @@ -82,7 +58,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) @@ -94,7 +70,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; kfree(inti); goto unlock; } @@ -105,7 +81,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); @@ -120,7 +96,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) @@ -132,7 +108,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; kfree(inti); goto unlock; } @@ -143,7 +119,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); @@ -171,7 +147,7 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) out: spin_unlock_bh(&li->lock); - return 0; /* order accepted */ + return SIGP_CC_ORDER_CODE_ACCEPTED; } static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) @@ -181,12 +157,12 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; goto unlock; } @@ -210,11 +186,11 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) switch (parameter & 0xff) { case 0: - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; break; case 1: case 2: - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; break; default: rc = -EOPNOTSUPP; @@ -235,21 +211,23 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, address = address & 0x7fffe000u; if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) { - *reg |= SIGP_STAT_INVALID_PARAMETER; - return 1; /* invalid parameter */ + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INVALID_PARAMETER; + return SIGP_CC_STATUS_STORED; } inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) - return 2; /* busy */ + return SIGP_CC_BUSY; spin_lock(&fi->lock); if (cpu_addr < KVM_MAX_VCPUS) li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 1; /* incorrect state */ - *reg &= SIGP_STAT_INCORRECT_STATE; + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + rc = SIGP_CC_STATUS_STORED; kfree(inti); goto out_fi; } @@ -257,8 +235,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, spin_lock_bh(&li->lock); /* cpu must be in stopped state */ if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { - rc = 1; /* incorrect state */ - *reg &= SIGP_STAT_INCORRECT_STATE; + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + rc = SIGP_CC_STATUS_STORED; kfree(inti); goto out_li; } @@ -270,7 +249,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, atomic_set(&li->active, 1); if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address); out_li: @@ -287,21 +266,21 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; else { if (atomic_read(fi->local_int[cpu_addr]->cpuflags) & CPUSTAT_RUNNING) { /* running */ - rc = 1; + rc = SIGP_CC_ORDER_CODE_ACCEPTED; } else { /* not running */ *reg &= 0xffffffff00000000UL; - *reg |= SIGP_STAT_NOT_RUNNING; - rc = 0; + *reg |= SIGP_STATUS_NOT_RUNNING; + rc = SIGP_CC_STATUS_STORED; } } spin_unlock(&fi->lock); @@ -314,23 +293,23 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr) { - int rc = 0; struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li; + int rc = SIGP_CC_ORDER_CODE_ACCEPTED; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; goto out; } spin_lock_bh(&li->lock); if (li->action_bits & ACTION_STOP_ON_STOP) - rc = 2; /* busy */ + rc = SIGP_CC_BUSY; else VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace", cpu_addr); @@ -375,7 +354,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) vcpu->stat.instruction_sigp_external_call++; rc = __sigp_external_call(vcpu, cpu_addr); break; - case SIGP_EMERGENCY: + case SIGP_EMERGENCY_SIGNAL: vcpu->stat.instruction_sigp_emergency++; rc = __sigp_emergency(vcpu, cpu_addr); break; @@ -383,12 +362,12 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) vcpu->stat.instruction_sigp_stop++; rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP); break; - case SIGP_STOP_STORE_STATUS: + case SIGP_STOP_AND_STORE_STATUS: vcpu->stat.instruction_sigp_stop++; rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP | ACTION_STOP_ON_STOP); break; - case SIGP_SET_ARCH: + case SIGP_SET_ARCHITECTURE: vcpu->stat.instruction_sigp_arch++; rc = __sigp_set_arch(vcpu, parameter); break; @@ -405,7 +384,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) case SIGP_RESTART: vcpu->stat.instruction_sigp_restart++; rc = __sigp_restart(vcpu, cpu_addr); - if (rc == 2) /* busy */ + if (rc == SIGP_CC_BUSY) break; /* user space must know about restart */ default: diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 9f1f71e8577..42d0cf89121 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -1,7 +1,7 @@ /* * Precise Delay Loops for S390 * - * Copyright IBM Corp. 1999,2008 + * Copyright IBM Corp. 1999, 2008 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, */ @@ -12,8 +12,8 @@ #include <linux/module.h> #include <linux/irqflags.h> #include <linux/interrupt.h> +#include <asm/vtimer.h> #include <asm/div64.h> -#include <asm/timer.h> void __delay(unsigned long loops) { diff --git a/arch/s390/lib/div64.c b/arch/s390/lib/div64.c index d9e62c0b576..261152f8324 100644 --- a/arch/s390/lib/div64.c +++ b/arch/s390/lib/div64.c @@ -1,9 +1,7 @@ /* - * arch/s390/lib/div64.c - * * __div64_32 implementation for 31 bit. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), */ diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 093eb694d9c..f709983f41f 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -1,8 +1,7 @@ /* - * arch/s390/lib/spinlock.c * Out of line spinlock code. * - * Copyright (C) IBM Corp. 2004, 2006 + * Copyright IBM Corp. 2004, 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index 4143b7c1909..846ec64ab2c 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -1,9 +1,8 @@ /* - * arch/s390/lib/string.c * Optimized string functions * * S390 version - * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2004 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h index 1d2536cb630..315dbe09983 100644 --- a/arch/s390/lib/uaccess.h +++ b/arch/s390/lib/uaccess.h @@ -1,6 +1,4 @@ /* - * arch/s390/uaccess.h - * * Copyright IBM Corp. 2007 * */ diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 58a75a8ae90..2443ae476e3 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -1,9 +1,7 @@ /* - * arch/s390/lib/uaccess_mvcos.c - * * Optimized user space space access functions based on mvcos. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerald Schaefer (gerald.schaefer@de.ibm.com) */ diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 342ae35a5ba..60ee2b88379 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -1,6 +1,4 @@ /* - * arch/s390/lib/uaccess_pt.c - * * User access functions based on page table walks for enhanced * system layout without hardware support. * diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index 57e94298539..6fbd0633827 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -1,10 +1,8 @@ /* - * arch/s390/lib/uaccess_std.c - * * Standard user space access functions based on mvcp/mvcs and doing * interesting things in the secondary space mode. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerald Schaefer (gerald.schaefer@de.ibm.com) */ diff --git a/arch/s390/math-emu/math.c b/arch/s390/math-emu/math.c index cd4e9c168dd..58bff541fde 100644 --- a/arch/s390/math-emu/math.c +++ b/arch/s390/math-emu/math.c @@ -1,8 +1,6 @@ /* - * arch/s390/math-emu/math.c - * * S390 version - * Copyright (C) 1999-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2001 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * * 'math.c' emulates IEEE instructions on a S390 processor diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 1f1dba9dcf5..479e9428291 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -1,7 +1,7 @@ /* * Collaborative memory management interface. * - * Copyright IBM Corp 2003,2010 + * Copyright IBM Corp 2003, 2010 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * */ diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 075ddada491..519bba716cc 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -1,10 +1,9 @@ /* - * File...........: arch/s390/mm/extmem.c * Author(s)......: Carsten Otte <cotte@de.ibm.com> * Rob M van der Heij <rvdheij@nl.ibm.com> * Steven Shultz <shultzss@us.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation 2002-2004 + * Copyright IBM Corp. 2002, 2004 */ #define KMSG_COMPONENT "extmem" diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 72cec9ecd96..6a12d1bb6e0 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -1,8 +1,6 @@ /* - * arch/s390/mm/fault.c - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com) * Ulrich Weigand (uweigand@de.ibm.com) * diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 900de2b3cf2..532525ec88c 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -1,7 +1,7 @@ /* * IBM System z Huge TLB Page Support for Kernel. * - * Copyright 2007 IBM Corp. + * Copyright IBM Corp. 2007 * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 2bea0605856..6adbc082618 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -1,8 +1,6 @@ /* - * arch/s390/mm/init.c - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com) * * Derived from "arch/i386/mm/init.c" diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 2857c48486e..573384256c5 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -1,6 +1,4 @@ /* - * linux/arch/s390/mm/mmap.c - * * flexible mmap layout support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a3db5a3ea08..1cab221077c 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2011 + * Copyright IBM Corp. 2007, 2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 71ae20df674..6f896e75ab4 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -1,6 +1,4 @@ /* - * arch/s390/mm/vmem.c - * * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index bc4b84a35ca..c82f62fb9c2 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -1,8 +1,6 @@ -/** - * arch/s390/oprofile/backtrace.c - * +/* * S390 Version - * Copyright (C) 2005 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2005 * Author(s): Andreas Krebbel <Andreas.Krebbel@de.ibm.com> */ diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c index a4a89fa980d..0cb385da202 100644 --- a/arch/s390/oprofile/hwsampler.c +++ b/arch/s390/oprofile/hwsampler.c @@ -1,6 +1,4 @@ -/** - * arch/s390/oprofile/hwsampler.c - * +/* * Copyright IBM Corp. 2010 * Author: Heinz Graalfs <graalfs@de.ibm.com> */ diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 2297be406c6..a1e9d69a9c9 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -1,8 +1,6 @@ -/** - * arch/s390/oprofile/init.c - * +/* * S390 Version - * Copyright (C) 2002-2011 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2002, 2011 * Author(s): Thomas Spatzier (tspat@de.ibm.com) * Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com) * Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com) diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h index 1a8d3ca0901..61b2531eef1 100644 --- a/arch/s390/oprofile/op_counter.h +++ b/arch/s390/oprofile/op_counter.h @@ -1,7 +1,5 @@ -/** - * arch/s390/oprofile/op_counter.h - * - * Copyright (C) 2011 IBM Deutschland Entwicklung GmbH, IBM Corporation +/* + * Copyright IBM Corp. 2011 * Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com) * * @remark Copyright 2011 OProfile authors diff --git a/arch/sh/boards/board-polaris.c b/arch/sh/boards/board-polaris.c index 37d03c097ae..0978ae2e484 100644 --- a/arch/sh/boards/board-polaris.c +++ b/arch/sh/boards/board-polaris.c @@ -1,5 +1,5 @@ /* - * June 2006 steve.glendinning@smsc.com + * June 2006 Steve Glendinning <steve.glendinning@shawell.net> * * Polaris-specific resource declaration * diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 1a69244e785..e9073e9501b 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -96,6 +96,7 @@ static void bpf_flush_icache(void *start_, void *end_) #define AND F3(2, 0x01) #define ANDCC F3(2, 0x11) #define OR F3(2, 0x02) +#define XOR F3(2, 0x03) #define SUB F3(2, 0x04) #define SUBCC F3(2, 0x14) #define MUL F3(2, 0x0a) /* umul */ @@ -462,6 +463,9 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ALU_OR_K: /* A |= K */ emit_alu_K(OR, K); break; + case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ + emit_alu_X(XOR); + break; case BPF_S_ALU_LSH_X: /* A <<= X */ emit_alu_X(SLL); break; diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 0d60c5685c2..458d324f062 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -339,7 +339,7 @@ static int setup_etheraddr(char *str, unsigned char *addr, char *name) random: printk(KERN_INFO "Choosing a random ethernet address for device %s\n", name); - random_ether_addr(addr); + eth_random_addr(addr); return 1; } diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 03c9ff808b5..b0a47433341 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -238,7 +238,6 @@ config I2C_BATTERY_BQ27200 config I2C_EEPROM_AT24 tristate "I2C EEPROMs AT24 support" select I2C_PUV3 - select MISC_DEVICES select EEPROM_AT24 config LCD_BACKLIGHT diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 88093c1d44f..3ea51a84a0e 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -465,6 +465,8 @@ static inline u32 safe_apic_wait_icr_idle(void) return apic->safe_wait_icr_idle(); } +extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)); + #else /* CONFIG_X86_LOCAL_APIC */ static inline u32 apic_read(u32 reg) { return 0; } @@ -474,6 +476,7 @@ static inline u64 apic_icr_read(void) { return 0; } static inline void apic_icr_write(u32 low, u32 high) { } static inline void apic_wait_icr_idle(void) { } static inline u32 safe_apic_wait_icr_idle(void) { return 0; } +static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {} #endif /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index a6983b27722..72f5009deb5 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -264,6 +264,13 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. + * + * Note: the operation is performed atomically with respect to + * the local CPU, but not other CPUs. Portable code should not + * rely on this behaviour. + * KVM relies on this behaviour on x86 for modifying memory that is also + * accessed from a hypervisor on the same CPU if running in a VM: don't change + * this without also updating arch/x86/kernel/kvm.c */ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) { diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 7a15153c675..b518c750993 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -49,6 +49,7 @@ extern const struct hypervisor_x86 *x86_hyper; extern const struct hypervisor_x86 x86_hyper_vmware; extern const struct hypervisor_x86 x86_hyper_ms_hyperv; extern const struct hypervisor_x86 x86_hyper_xen_hvm; +extern const struct hypervisor_x86 x86_hyper_kvm; static inline bool hypervisor_x2apic_available(void) { diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index e7d1c194d27..246617efd67 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -12,6 +12,7 @@ /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT #define __KVM_HAVE_IOAPIC +#define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_DEVICE_ASSIGNMENT #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 1ac46c22dd5..c764f43b71c 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -192,8 +192,8 @@ struct x86_emulate_ops { struct x86_instruction_info *info, enum x86_intercept_stage stage); - bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); + void (*get_cpuid)(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -280,9 +280,9 @@ struct x86_emulate_ctxt { u8 modrm_seg; bool rip_relative; unsigned long _eip; + struct operand memop; /* Fields above regs are cleared together. */ unsigned long regs[NR_VCPU_REGS]; - struct operand memop; struct operand *memopp; struct fetch_cache fetch; struct read_cache io_read; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2da88c0cda1..09155d64cf7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -48,12 +48,13 @@ #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) +#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ 0xFFFFFF0000000000ULL) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ + | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_RDWRGSFS \ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) @@ -175,6 +176,13 @@ enum { /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 +/* + * The following bit is set with PV-EOI, unset on EOI. + * We detect PV-EOI changes by guest by comparing + * this bit with PV-EOI in guest memory. + * See the implementation in apic_update_pv_eoi. + */ +#define KVM_APIC_PV_EOI_PENDING 1 /* * We don't want allocation failures within the mmu code, so we preallocate @@ -484,6 +492,11 @@ struct kvm_vcpu_arch { u64 length; u64 status; } osvw; + + struct { + u64 msr_val; + struct gfn_to_hva_cache data; + } pv_eoi; }; struct kvm_lpage_info { @@ -661,6 +674,7 @@ struct kvm_x86_ops { u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); + bool (*invpcid_supported)(void); void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -802,7 +816,20 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); -int kvm_pic_set_irq(void *opaque, int irq, int level); +static inline int __kvm_irq_line_state(unsigned long *irq_state, + int irq_source_id, int level) +{ + /* Logical OR for level trig interrupt */ + if (level) + __set_bit(irq_source_id, irq_state); + else + __clear_bit(irq_source_id, irq_state); + + return !!(*irq_state); +} + +int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); +void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 63ab1661d00..2f7712e08b1 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -22,6 +22,7 @@ #define KVM_FEATURE_CLOCKSOURCE2 3 #define KVM_FEATURE_ASYNC_PF 4 #define KVM_FEATURE_STEAL_TIME 5 +#define KVM_FEATURE_PV_EOI 6 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. @@ -37,6 +38,7 @@ #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02 #define MSR_KVM_STEAL_TIME 0x4b564d03 +#define MSR_KVM_PV_EOI_EN 0x4b564d04 struct kvm_steal_time { __u64 steal; @@ -89,6 +91,11 @@ struct kvm_vcpu_pv_apf_data { __u32 enabled; }; +#define KVM_PV_EOI_BIT 0 +#define KVM_PV_EOI_MASK (0x1 << KVM_PV_EOI_BIT) +#define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK +#define KVM_PV_EOI_DISABLED 0x0 + #ifdef __KERNEL__ #include <asm/processor.h> diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index f8ab3eaad12..aea1d1d848c 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -44,6 +44,7 @@ */ #define X86_CR3_PWT 0x00000008 /* Page Write Through */ #define X86_CR3_PCD 0x00000010 /* Page Cache Disable */ +#define X86_CR3_PCID_MASK 0x00000fff /* PCID Mask */ /* * Intel CPU features in CR4 @@ -61,6 +62,7 @@ #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */ #define X86_CR4_VMXE 0x00002000 /* enable VMX virtualization */ #define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */ +#define X86_CR4_PCIDE 0x00020000 /* enable PCID support */ #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */ #define X86_CR4_SMEP 0x00100000 /* enable SMEP support */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 31f180c21ce..74fcb963595 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -60,6 +60,7 @@ #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 +#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -281,6 +282,7 @@ enum vmcs_field { #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 +#define EXIT_REASON_INVPCID 58 /* * Interruption-information format @@ -404,6 +406,7 @@ enum vmcs_field { #define VMX_EPTP_WB_BIT (1ull << 14) #define VMX_EPT_2MB_PAGE_BIT (1ull << 16) #define VMX_EPT_1GB_PAGE_BIT (1ull << 17) +#define VMX_EPT_AD_BIT (1ull << 21) #define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24) #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) @@ -415,11 +418,14 @@ enum vmcs_field { #define VMX_EPT_MAX_GAW 0x4 #define VMX_EPT_MT_EPTE_SHIFT 3 #define VMX_EPT_GAW_EPTP_SHIFT 3 +#define VMX_EPT_AD_ENABLE_BIT (1ull << 6) #define VMX_EPT_DEFAULT_MT 0x6ull #define VMX_EPT_READABLE_MASK 0x1ull #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull #define VMX_EPT_IPAT_BIT (1ull << 6) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 5728852fb90..59c226d120c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -48,6 +48,7 @@ #include <xen/interface/sched.h> #include <xen/interface/physdev.h> #include <xen/interface/platform.h> +#include <xen/interface/xen-mca.h> /* * The hypercall asms have to meet several constraints: @@ -302,6 +303,13 @@ HYPERVISOR_set_timer_op(u64 timeout) } static inline int +HYPERVISOR_mca(struct xen_mc *mc_op) +{ + mc_op->interface_version = XEN_MCA_INTERFACE_VERSION; + return _hypercall1(int, mca, mc_op); +} + +static inline int HYPERVISOR_dom0_op(struct xen_platform_op *platform_op) { platform_op->interface_version = XENPF_INTERFACE_VERSION; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c421512ca5e..98e24131ff3 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2143,6 +2143,23 @@ int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, } /* + * Override the generic EOI implementation with an optimized version. + * Only called during early boot when only one CPU is active and with + * interrupts disabled, so we know this does not race with actual APIC driver + * use. + */ +void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) +{ + struct apic **drv; + + for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) { + /* Should happen once for each apic */ + WARN_ON((*drv)->eoi_write == eoi_write); + (*drv)->eoi_write = eoi_write; + } +} + +/* * Power management */ #ifdef CONFIG_PM diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 755f64fb074..a8f8fa9769d 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -37,6 +37,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = #endif &x86_hyper_vmware, &x86_hyper_ms_hyperv, +#ifdef CONFIG_KVM_GUEST + &x86_hyper_kvm, +#endif }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9473e8772fd..5e095f873e3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); int mce_disabled __read_mostly; -#define MISC_MCELOG_MINOR 227 - #define SPINUNIT 100 /* 100ns */ atomic_t mce_entry; @@ -2346,7 +2344,7 @@ static __init int mcheck_init_device(void) return err; } -device_initcall(mcheck_init_device); +device_initcall_sync(mcheck_init_device); /* * Old style boot options parsing. Only for compatibility. diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 671b95a2ffb..c4e916d7737 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -759,4 +759,24 @@ static __init int threshold_init_device(void) return 0; } -device_initcall(threshold_init_device); +/* + * there are 3 funcs which need to be _initcalled in a logic sequence: + * 1. xen_late_init_mcelog + * 2. mcheck_init_device + * 3. threshold_init_device + * + * xen_late_init_mcelog must register xen_mce_chrdev_device before + * native mce_chrdev_device registration if running under xen platform; + * + * mcheck_init_device should be inited before threshold_init_device to + * initialize mce_device, otherwise a NULL ptr dereference will cause panic. + * + * so we use following _initcalls + * 1. device_initcall(xen_late_init_mcelog); + * 2. device_initcall_sync(mcheck_init_device); + * 3. late_initcall(threshold_init_device); + * + * when running under xen, the initcall order is 1,2,3; + * on baremetal, we skip 1 and we do only 2 and 3. + */ +late_initcall(threshold_init_device); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e554e5ad2fe..c1d61ee4b4f 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -39,6 +39,9 @@ #include <asm/desc.h> #include <asm/tlbflush.h> #include <asm/idle.h> +#include <asm/apic.h> +#include <asm/apicdef.h> +#include <asm/hypervisor.h> static int kvmapf = 1; @@ -283,6 +286,22 @@ static void kvm_register_steal_time(void) cpu, __pa(st)); } +static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; + +static void kvm_guest_apic_eoi_write(u32 reg, u32 val) +{ + /** + * This relies on __test_and_clear_bit to modify the memory + * in a way that is atomic with respect to the local CPU. + * The hypervisor only accesses this memory from the local CPU so + * there's no need for lock or memory barriers. + * An optimization barrier is implied in apic write. + */ + if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi))) + return; + apic_write(APIC_EOI, APIC_EOI_ACK); +} + void __cpuinit kvm_guest_cpu_init(void) { if (!kvm_para_available()) @@ -300,11 +319,20 @@ void __cpuinit kvm_guest_cpu_init(void) smp_processor_id()); } + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { + unsigned long pa; + /* Size alignment is implied but just to make it explicit. */ + BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); + __get_cpu_var(kvm_apic_eoi) = 0; + pa = __pa(&__get_cpu_var(kvm_apic_eoi)) | KVM_MSR_ENABLED; + wrmsrl(MSR_KVM_PV_EOI_EN, pa); + } + if (has_steal_clock) kvm_register_steal_time(); } -static void kvm_pv_disable_apf(void *unused) +static void kvm_pv_disable_apf(void) { if (!__get_cpu_var(apf_reason).enabled) return; @@ -316,11 +344,23 @@ static void kvm_pv_disable_apf(void *unused) smp_processor_id()); } +static void kvm_pv_guest_cpu_reboot(void *unused) +{ + /* + * We disable PV EOI before we load a new kernel by kexec, + * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory. + * New kernel can re-enable when it boots. + */ + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); +} + static int kvm_pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) { if (code == SYS_RESTART) - on_each_cpu(kvm_pv_disable_apf, NULL, 1); + on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); return NOTIFY_DONE; } @@ -371,7 +411,9 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy) static void kvm_guest_cpu_offline(void *dummy) { kvm_disable_steal_time(); - kvm_pv_disable_apf(NULL); + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); apf_task_wake_all(); } @@ -424,6 +466,9 @@ void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + apic_set_eoi_write(kvm_guest_apic_eoi_write); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); @@ -432,6 +477,19 @@ void __init kvm_guest_init(void) #endif } +static bool __init kvm_detect(void) +{ + if (!kvm_para_available()) + return false; + return true; +} + +const struct hypervisor_x86 x86_hyper_kvm __refconst = { + .name = "KVM", + .detect = kvm_detect, +}; +EXPORT_SYMBOL_GPL(x86_hyper_kvm); + static __init int activate_jump_labels(void) { if (has_steal_clock) { diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 202494d2ec6..216a4d754b0 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -81,7 +81,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_386_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; default: diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7df1c6d839f..0595f1397b7 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -201,6 +201,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_lm = 0; #endif unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; + unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; /* cpuid 1.edx */ const u32 kvm_supported_word0_x86_features = @@ -228,7 +229,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | - 0 /* Reserved, DCA */ | F(XMM4_1) | + F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | F(F16C) | F(RDRAND); @@ -248,7 +249,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ebx */ const u32 kvm_supported_word9_x86_features = F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | F(RTM); + F(BMI2) | F(ERMS) | f_invpcid | F(RTM); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -409,6 +410,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_NOP_IO_DELAY) | (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | + (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); if (sched_info_on()) @@ -639,33 +641,37 @@ static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); } -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) { - u32 function, index; + u32 function = *eax, index = *ecx; struct kvm_cpuid_entry2 *best; - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); best = kvm_find_cpuid_entry(vcpu, function, index); if (!best) best = check_cpuid_limit(vcpu, function, index); if (best) { - kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); - kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); - kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); - } + *eax = best->eax; + *ebx = best->ebx; + *ecx = best->ecx; + *edx = best->edx; + } else + *eax = *ebx = *ecx = *edx = 0; +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, eax, ebx, ecx, edx; + + function = eax = kvm_register_read(vcpu, VCPU_REGS_RAX); + ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx); + kvm_register_write(vcpu, VCPU_REGS_RAX, eax); + kvm_register_write(vcpu, VCPU_REGS_RBX, ebx); + kvm_register_write(vcpu, VCPU_REGS_RCX, ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, edx); kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, - kvm_register_read(vcpu, VCPU_REGS_RAX), - kvm_register_read(vcpu, VCPU_REGS_RBX), - kvm_register_read(vcpu, VCPU_REGS_RCX), - kvm_register_read(vcpu, VCPU_REGS_RDX)); + trace_kvm_cpuid(function, eax, ebx, ecx, edx); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 26d1fb437eb..a10e4601685 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -17,6 +17,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) @@ -51,4 +52,12 @@ static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_OSVW)); } +static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_PCID)); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f95d242ee9f..97d9a9914ba 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -433,11 +433,32 @@ static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, return ctxt->ops->intercept(ctxt, &info, stage); } +static void assign_masked(ulong *dest, ulong src, ulong mask) +{ + *dest = (*dest & ~mask) | (src & mask); +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; } +static ulong stack_mask(struct x86_emulate_ctxt *ctxt) +{ + u16 sel; + struct desc_struct ss; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + return ~0UL; + ctxt->ops->get_segment(ctxt, &sel, &ss, NULL, VCPU_SREG_SS); + return ~0U >> ((ss.d ^ 1) * 16); /* d=0: 0xffff; d=1: 0xffffffff */ +} + +static int stack_size(struct x86_emulate_ctxt *ctxt) +{ + return (__fls(stack_mask(ctxt)) + 1) >> 3; +} + /* Access/update address held in a register, based on addressing mode. */ static inline unsigned long address_mask(struct x86_emulate_ctxt *ctxt, unsigned long reg) @@ -958,6 +979,12 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->orig_val = op->val; } +static void adjust_modrm_seg(struct x86_emulate_ctxt *ctxt, int base_reg) +{ + if (base_reg == VCPU_REGS_RSP || base_reg == VCPU_REGS_RBP) + ctxt->modrm_seg = VCPU_SREG_SS; +} + static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct operand *op) { @@ -1061,15 +1088,20 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) modrm_ea += insn_fetch(s32, ctxt); - else + else { modrm_ea += ctxt->regs[base_reg]; + adjust_modrm_seg(ctxt, base_reg); + } if (index_reg != 4) modrm_ea += ctxt->regs[index_reg] << scale; } else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) { if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->rip_relative = 1; - } else - modrm_ea += ctxt->regs[ctxt->modrm_rm]; + } else { + base_reg = ctxt->modrm_rm; + modrm_ea += ctxt->regs[base_reg]; + adjust_modrm_seg(ctxt, base_reg); + } switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 5) @@ -1264,7 +1296,8 @@ static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, /* allowed just for 8 bytes segments */ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, - u16 selector, struct desc_struct *desc) + u16 selector, struct desc_struct *desc, + ulong *desc_addr_p) { struct desc_ptr dt; u16 index = selector >> 3; @@ -1275,7 +1308,7 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (dt.size < index * 8 + 7) return emulate_gp(ctxt, selector & 0xfffc); - addr = dt.address + index * 8; + *desc_addr_p = addr = dt.address + index * 8; return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc, &ctxt->exception); } @@ -1302,11 +1335,12 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { - struct desc_struct seg_desc; + struct desc_struct seg_desc, old_desc; u8 dpl, rpl, cpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + ulong desc_addr; int ret; memset(&seg_desc, 0, sizeof seg_desc); @@ -1324,8 +1358,14 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto load; } - /* NULL selector is not valid for TR, CS and SS */ - if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + rpl = selector & 3; + cpl = ctxt->ops->cpl(ctxt); + + /* NULL selector is not valid for TR, CS and SS (except for long mode) */ + if ((seg == VCPU_SREG_CS + || (seg == VCPU_SREG_SS + && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)) + || seg == VCPU_SREG_TR) && null_selector) goto exception; @@ -1336,7 +1376,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (null_selector) /* for NULL selector skip all following checks */ goto load; - ret = read_segment_descriptor(ctxt, selector, &seg_desc); + ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; @@ -1352,9 +1392,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; } - rpl = selector & 3; dpl = seg_desc.dpl; - cpl = ctxt->ops->cpl(ctxt); switch (seg) { case VCPU_SREG_SS: @@ -1384,6 +1422,12 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; + old_desc = seg_desc; + seg_desc.type |= 2; /* busy */ + ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, + sizeof(seg_desc), &ctxt->exception); + if (ret != X86EMUL_CONTINUE) + return ret; break; case VCPU_SREG_LDTR: if (seg_desc.s || seg_desc.type != 2) @@ -1474,17 +1518,22 @@ static int writeback(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_push(struct x86_emulate_ctxt *ctxt) +static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -ctxt->op_bytes); + register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); addr.seg = VCPU_SREG_SS; + return segmented_write(ctxt, addr, data, bytes); +} + +static int em_push(struct x86_emulate_ctxt *ctxt) +{ /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return segmented_write(ctxt, addr, &ctxt->src.val, ctxt->op_bytes); + return push(ctxt, &ctxt->src.val, ctxt->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, @@ -1556,6 +1605,33 @@ static int em_popf(struct x86_emulate_ctxt *ctxt) return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } +static int em_enter(struct x86_emulate_ctxt *ctxt) +{ + int rc; + unsigned frame_size = ctxt->src.val; + unsigned nesting_level = ctxt->src2.val & 31; + + if (nesting_level) + return X86EMUL_UNHANDLEABLE; + + rc = push(ctxt, &ctxt->regs[VCPU_REGS_RBP], stack_size(ctxt)); + if (rc != X86EMUL_CONTINUE) + return rc; + assign_masked(&ctxt->regs[VCPU_REGS_RBP], ctxt->regs[VCPU_REGS_RSP], + stack_mask(ctxt)); + assign_masked(&ctxt->regs[VCPU_REGS_RSP], + ctxt->regs[VCPU_REGS_RSP] - frame_size, + stack_mask(ctxt)); + return X86EMUL_CONTINUE; +} + +static int em_leave(struct x86_emulate_ctxt *ctxt) +{ + assign_masked(&ctxt->regs[VCPU_REGS_RSP], ctxt->regs[VCPU_REGS_RBP], + stack_mask(ctxt)); + return emulate_pop(ctxt, &ctxt->regs[VCPU_REGS_RBP], ctxt->op_bytes); +} + static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; @@ -1993,8 +2069,8 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt) u32 eax, ebx, ecx, edx; eax = ecx = 0; - return ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx) - && ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; } @@ -2013,32 +2089,31 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) eax = 0x00000000; ecx = 0x00000000; - if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) { - /* - * Intel ("GenuineIntel") - * remark: Intel CPUs only support "syscall" in 64bit - * longmode. Also an 64bit guest with a - * 32bit compat-app running will #UD !! While this - * behaviour can be fixed (by emulating) into AMD - * response - CPUs of AMD can't behave like Intel. - */ - if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && - ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && - edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) - return false; + ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + /* + * Intel ("GenuineIntel") + * remark: Intel CPUs only support "syscall" in 64bit + * longmode. Also an 64bit guest with a + * 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD + * response - CPUs of AMD can't behave like Intel. + */ + if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + return false; - /* AMD ("AuthenticAMD") */ - if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && - ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && - edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) - return true; - - /* AMD ("AMDisbetter!") */ - if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && - ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && - edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) - return true; - } + /* AMD ("AuthenticAMD") */ + if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return true; + + /* AMD ("AMDisbetter!") */ + if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) + return true; /* default: (not Intel, not AMD), apply Intel's stricter rules... */ return false; @@ -2547,13 +2622,14 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; + ulong desc_addr; /* FIXME: old_tss_base == ~0 ? */ - ret = read_segment_descriptor(ctxt, tss_selector, &next_tss_desc); + ret = read_segment_descriptor(ctxt, tss_selector, &next_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; - ret = read_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc); + ret = read_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; @@ -2948,6 +3024,24 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } +static int em_lldt(struct x86_emulate_ctxt *ctxt) +{ + u16 sel = ctxt->src.val; + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR); +} + +static int em_ltr(struct x86_emulate_ctxt *ctxt) +{ + u16 sel = ctxt->src.val; + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return load_segment_descriptor(ctxt, sel, VCPU_SREG_TR); +} + static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; @@ -2989,11 +3083,42 @@ static int em_vmcall(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, + void (*get)(struct x86_emulate_ctxt *ctxt, + struct desc_ptr *ptr)) +{ + struct desc_ptr desc_ptr; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; + get(ctxt, &desc_ptr); + if (ctxt->op_bytes == 2) { + ctxt->op_bytes = 4; + desc_ptr.address &= 0x00ffffff; + } + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return segmented_write(ctxt, ctxt->dst.addr.mem, + &desc_ptr, 2 + ctxt->op_bytes); +} + +static int em_sgdt(struct x86_emulate_ctxt *ctxt) +{ + return emulate_store_desc_ptr(ctxt, ctxt->ops->get_gdt); +} + +static int em_sidt(struct x86_emulate_ctxt *ctxt) +{ + return emulate_store_desc_ptr(ctxt, ctxt->ops->get_idt); +} + static int em_lgdt(struct x86_emulate_ctxt *ctxt) { struct desc_ptr desc_ptr; int rc; + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; rc = read_descriptor(ctxt, ctxt->src.addr.mem, &desc_ptr.size, &desc_ptr.address, ctxt->op_bytes); @@ -3021,6 +3146,8 @@ static int em_lidt(struct x86_emulate_ctxt *ctxt) struct desc_ptr desc_ptr; int rc; + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; rc = read_descriptor(ctxt, ctxt->src.addr.mem, &desc_ptr.size, &desc_ptr.address, ctxt->op_bytes); @@ -3143,6 +3270,42 @@ static int em_bsr(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_cpuid(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = ctxt->regs[VCPU_REGS_RAX]; + ecx = ctxt->regs[VCPU_REGS_RCX]; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + ctxt->regs[VCPU_REGS_RAX] = eax; + ctxt->regs[VCPU_REGS_RBX] = ebx; + ctxt->regs[VCPU_REGS_RCX] = ecx; + ctxt->regs[VCPU_REGS_RDX] = edx; + return X86EMUL_CONTINUE; +} + +static int em_lahf(struct x86_emulate_ctxt *ctxt) +{ + ctxt->regs[VCPU_REGS_RAX] &= ~0xff00UL; + ctxt->regs[VCPU_REGS_RAX] |= (ctxt->eflags & 0xff) << 8; + return X86EMUL_CONTINUE; +} + +static int em_bswap(struct x86_emulate_ctxt *ctxt) +{ + switch (ctxt->op_bytes) { +#ifdef CONFIG_X86_64 + case 8: + asm("bswap %0" : "+r"(ctxt->dst.val)); + break; +#endif + default: + asm("bswap %0" : "+r"(*(u32 *)&ctxt->dst.val)); + break; + } + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -3424,14 +3587,14 @@ static struct opcode group5[] = { static struct opcode group6[] = { DI(Prot, sldt), DI(Prot, str), - DI(Prot | Priv, lldt), - DI(Prot | Priv, ltr), + II(Prot | Priv | SrcMem16, em_lldt, lldt), + II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, }; static struct group_dual group7 = { { - DI(Mov | DstMem | Priv, sgdt), - DI(Mov | DstMem | Priv, sidt), + II(Mov | DstMem | Priv, em_sgdt, sgdt), + II(Mov | DstMem | Priv, em_sidt, sidt), II(SrcMem | Priv, em_lgdt, lgdt), II(SrcMem | Priv, em_lidt, lidt), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, @@ -3538,7 +3701,7 @@ static struct opcode opcode_table[256] = { D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), - II(ImplicitOps | Stack, em_popf, popf), N, N, + II(ImplicitOps | Stack, em_popf, popf), N, I(ImplicitOps, em_lahf), /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), @@ -3561,7 +3724,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ - N, N, N, I(ImplicitOps | Stack, em_ret_far), + I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave), + N, I(ImplicitOps | Stack, em_ret_far), D(ImplicitOps), DI(SrcImmByte, intn), D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret), /* 0xD0 - 0xD7 */ @@ -3635,7 +3799,7 @@ static struct opcode twobyte_table[256] = { X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), - DI(ImplicitOps, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), + II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ @@ -3658,11 +3822,12 @@ static struct opcode twobyte_table[256] = { I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), - /* 0xC0 - 0xCF */ + /* 0xC0 - 0xC7 */ D2bv(DstMem | SrcReg | ModRM | Lock), N, D(DstMem | SrcReg | ModRM | Mov), N, N, N, GD(0, &group9), - N, N, N, N, N, N, N, N, + /* 0xC8 - 0xCF */ + X8(I(DstReg, em_bswap)), /* 0xD0 - 0xDF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0xE0 - 0xEF */ @@ -4426,12 +4591,12 @@ twobyte_insn: break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val + ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val : + ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val : (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 81cf4fa4a2b..1df8fb9e1d5 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -188,14 +188,15 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -int kvm_pic_set_irq(void *opaque, int irq, int level) +int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level) { - struct kvm_pic *s = opaque; int ret = -1; pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { - ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + int irq_level = __kvm_irq_line_state(&s->irq_states[irq], + irq_source_id, level); + ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level); pic_update_irq(s); trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, s->pics[irq >> 3].imr, ret == 0); @@ -205,6 +206,16 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) return ret; } +void kvm_pic_clear_all(struct kvm_pic *s, int irq_source_id) +{ + int i; + + pic_lock(s); + for (i = 0; i < PIC_NUM_PINS; i++) + __clear_bit(irq_source_id, &s->irq_states[i]); + pic_unlock(s); +} + /* * acknowledge interrupt 'irq' */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 93c15743f1e..ce878788a39 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -107,6 +107,16 @@ static inline void apic_clear_vector(int vec, void *bitmap) clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +static inline int __apic_test_and_set_vector(int vec, void *bitmap) +{ + return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline int __apic_test_and_clear_vector(int vec, void *bitmap) +{ + return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + static inline int apic_hw_enabled(struct kvm_lapic *apic) { return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; @@ -210,6 +220,16 @@ static int find_highest_vector(void *bitmap) return fls(word[word_offset << 2]) - 1 + (word_offset << 5); } +static u8 count_vectors(void *bitmap) +{ + u32 *word = bitmap; + int word_offset; + u8 count = 0; + for (word_offset = 0; word_offset < MAX_APIC_VECTOR >> 5; ++word_offset) + count += hweight32(word[word_offset << 2]); + return count; +} + static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) { apic->irr_pending = true; @@ -242,6 +262,27 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) apic->irr_pending = true; } +static inline void apic_set_isr(int vec, struct kvm_lapic *apic) +{ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + ++apic->isr_count; + BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + /* + * ISR (in service register) bit is set when injecting an interrupt. + * The highest vector is injected. Thus the latest bit set matches + * the highest bit in ISR. + */ + apic->highest_isr_cache = vec; +} + +static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) +{ + if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + --apic->isr_count; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; +} + int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -270,9 +311,61 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) irq->level, irq->trig_mode); } +static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) +{ + + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val, + sizeof(val)); +} + +static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val) +{ + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val, + sizeof(*val)); +} + +static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; +} + +static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) +{ + u8 val; + if (pv_eoi_get_user(vcpu, &val) < 0) + apic_debug("Can't read EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return val & 0x1; +} + +static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) +{ + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { + apic_debug("Can't set EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return; + } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); +} + +static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +{ + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { + apic_debug("Can't clear EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return; + } + __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); +} + static inline int apic_find_highest_isr(struct kvm_lapic *apic) { int result; + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; result = find_highest_vector(apic->regs + APIC_ISR); ASSERT(result == -1 || result >= 16); @@ -482,17 +575,20 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } -static void apic_set_eoi(struct kvm_lapic *apic) +static int apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); + + trace_kvm_eoi(apic, vector); + /* * Not every write EOI will has corresponding ISR, * one example is when Kernel check timer on setup_IO_APIC */ if (vector == -1) - return; + return vector; - apic_clear_vector(vector, apic->regs + APIC_ISR); + apic_clear_isr(vector, apic); apic_update_ppr(apic); if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && @@ -505,6 +601,7 @@ static void apic_set_eoi(struct kvm_lapic *apic) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); } kvm_make_request(KVM_REQ_EVENT, apic->vcpu); + return vector; } static void apic_send_ipi(struct kvm_lapic *apic) @@ -1081,10 +1178,13 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } apic->irr_pending = false; + apic->isr_count = 0; + apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); if (kvm_vcpu_is_bsp(vcpu)) vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); vcpu->arch.apic_arb_prio = 0; @@ -1248,7 +1348,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) if (vector == -1) return -1; - apic_set_vector(vector, apic->regs + APIC_ISR); + apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); return vector; @@ -1267,6 +1367,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; + apic->isr_count = count_vectors(apic->regs + APIC_ISR); + apic->highest_isr_cache = -1; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -1283,11 +1385,51 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } +/* + * apic_sync_pv_eoi_from_guest - called on vmexit or cancel interrupt + * + * Detect whether guest triggered PV EOI since the + * last entry. If yes, set EOI on guests's behalf. + * Clear PV EOI in guest memory in any case. + */ +static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, + struct kvm_lapic *apic) +{ + bool pending; + int vector; + /* + * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host + * and KVM_PV_EOI_ENABLED in guest memory as follows: + * + * KVM_APIC_PV_EOI_PENDING is unset: + * -> host disabled PV EOI. + * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is set: + * -> host enabled PV EOI, guest did not execute EOI yet. + * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset: + * -> host enabled PV EOI, guest executed EOI. + */ + BUG_ON(!pv_eoi_enabled(vcpu)); + pending = pv_eoi_get_pending(vcpu); + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ + pv_eoi_clr_pending(vcpu); + if (pending) + return; + vector = apic_set_eoi(apic); + trace_kvm_pv_eoi(apic, vector); +} + void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) { u32 data; void *vapic; + if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention)) + apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic); + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; @@ -1298,17 +1440,44 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) apic_set_tpr(vcpu->arch.apic, data & 0xff); } +/* + * apic_sync_pv_eoi_to_guest - called before vmentry + * + * Detect whether it's safe to enable PV EOI and + * if yes do so. + */ +static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu, + struct kvm_lapic *apic) +{ + if (!pv_eoi_enabled(vcpu) || + /* IRR set or many bits in ISR: could be nested. */ + apic->irr_pending || + /* Cache not set: could be safe but we don't bother. */ + apic->highest_isr_cache == -1 || + /* Need EOI to update ioapic. */ + kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) { + /* + * PV EOI was disabled by apic_sync_pv_eoi_from_guest + * so we need not do anything here. + */ + return; + } + + pv_eoi_set_pending(apic->vcpu); +} + void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) { u32 data, tpr; int max_irr, max_isr; - struct kvm_lapic *apic; + struct kvm_lapic *apic = vcpu->arch.apic; void *vapic; + apic_sync_pv_eoi_to_guest(vcpu, apic); + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - apic = vcpu->arch.apic; tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff; max_irr = apic_find_highest_irr(apic); if (max_irr < 0) @@ -1394,3 +1563,16 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) return 0; } + +int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) +{ + u64 addr = data & ~KVM_MSR_ENABLED; + if (!IS_ALIGNED(addr, 4)) + return 1; + + vcpu->arch.pv_eoi.msr_val = data; + if (!pv_eoi_enabled(vcpu)) + return 0; + return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, + addr); +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 6f4ce2575d0..4af5405ae1e 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -13,6 +13,15 @@ struct kvm_lapic { u32 divide_count; struct kvm_vcpu *vcpu; bool irr_pending; + /* Number of bits set in ISR. */ + s16 isr_count; + /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ + int highest_isr_cache; + /** + * APIC register page. The layout matches the register layout seen by + * the guest 1:1, because it is accessed by the vmx microcode. + * Note: Only one register, the TPR, is used by the microcode. + */ void *regs; gpa_t vapic_addr; struct page *vapic_page; @@ -60,4 +69,6 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; } + +int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 57e168e27b5..01ca0042393 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -90,7 +90,7 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 -#define PT_FIRST_AVAIL_BITS_SHIFT 9 +#define PT_FIRST_AVAIL_BITS_SHIFT 10 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 #define PT64_LEVEL_BITS 9 @@ -145,7 +145,8 @@ module_param(dbg, bool, 0644); #define CREATE_TRACE_POINTS #include "mmutrace.h" -#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -188,6 +189,7 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static void mmu_spte_set(u64 *sptep, u64 spte); +static void mmu_free_roots(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { @@ -444,8 +446,22 @@ static bool __check_direct_spte_mmio_pf(u64 spte) } #endif +static bool spte_is_locklessly_modifiable(u64 spte) +{ + return !(~spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)); +} + static bool spte_has_volatile_bits(u64 spte) { + /* + * Always atomicly update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (spte_is_locklessly_modifiable(spte)) + return true; + if (!shadow_accessed_mask) return false; @@ -478,34 +494,47 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) /* Rules for using mmu_spte_update: * Update the state bits, it means the mapped pfn is not changged. + * + * Whenever we overwrite a writable spte with a read-only one we + * should flush remote TLBs. Otherwise rmap_write_protect + * will find a read-only spte, even though the writable spte + * might be cached on a CPU's TLB, the return value indicates this + * case. */ -static void mmu_spte_update(u64 *sptep, u64 new_spte) +static bool mmu_spte_update(u64 *sptep, u64 new_spte) { - u64 mask, old_spte = *sptep; + u64 old_spte = *sptep; + bool ret = false; WARN_ON(!is_rmap_spte(new_spte)); - if (!is_shadow_present_pte(old_spte)) - return mmu_spte_set(sptep, new_spte); - - new_spte |= old_spte & shadow_dirty_mask; - - mask = shadow_accessed_mask; - if (is_writable_pte(old_spte)) - mask |= shadow_dirty_mask; + if (!is_shadow_present_pte(old_spte)) { + mmu_spte_set(sptep, new_spte); + return ret; + } - if (!spte_has_volatile_bits(old_spte) || (new_spte & mask) == mask) + if (!spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, new_spte); else old_spte = __update_clear_spte_slow(sptep, new_spte); + /* + * For the spte updated out of mmu-lock is safe, since + * we always atomicly update it, see the comments in + * spte_has_volatile_bits(). + */ + if (is_writable_pte(old_spte) && !is_writable_pte(new_spte)) + ret = true; + if (!shadow_accessed_mask) - return; + return ret; if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask)) kvm_set_pfn_accessed(spte_to_pfn(old_spte)); if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask)) kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + + return ret; } /* @@ -652,8 +681,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) mmu_page_header_cache); } -static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, - size_t size) +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; @@ -664,8 +692,7 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu) { - return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache, - sizeof(struct pte_list_desc)); + return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache); } static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc) @@ -1051,35 +1078,82 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static int __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level) + +static bool __drop_large_spte(struct kvm *kvm, u64 *sptep) +{ + if (is_large_pte(*sptep)) { + WARN_ON(page_header(__pa(sptep))->role.level == + PT_PAGE_TABLE_LEVEL); + drop_spte(kvm, sptep); + --kvm->stat.lpages; + return true; + } + + return false; +} + +static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) +{ + if (__drop_large_spte(vcpu->kvm, sptep)) + kvm_flush_remote_tlbs(vcpu->kvm); +} + +/* + * Write-protect on the specified @sptep, @pt_protect indicates whether + * spte writ-protection is caused by protecting shadow page table. + * @flush indicates whether tlb need be flushed. + * + * Note: write protection is difference between drity logging and spte + * protection: + * - for dirty logging, the spte can be set to writable at anytime if + * its dirty bitmap is properly set. + * - for spte protection, the spte can be writable only after unsync-ing + * shadow page. + * + * Return true if the spte is dropped. + */ +static bool +spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) +{ + u64 spte = *sptep; + + if (!is_writable_pte(spte) && + !(pt_protect && spte_is_locklessly_modifiable(spte))) + return false; + + rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + + if (__drop_large_spte(kvm, sptep)) { + *flush |= true; + return true; + } + + if (pt_protect) + spte &= ~SPTE_MMU_WRITEABLE; + spte = spte & ~PT_WRITABLE_MASK; + + *flush |= mmu_spte_update(sptep, spte); + return false; +} + +static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, + int level, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; - int write_protected = 0; + bool flush = false; for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); - - if (!is_writable_pte(*sptep)) { - sptep = rmap_get_next(&iter); - continue; - } - - if (level == PT_PAGE_TABLE_LEVEL) { - mmu_spte_update(sptep, *sptep & ~PT_WRITABLE_MASK); - sptep = rmap_get_next(&iter); - } else { - BUG_ON(!is_large_pte(*sptep)); - drop_spte(kvm, sptep); - --kvm->stat.lpages; + if (spte_write_protect(kvm, sptep, &flush, pt_protect)) { sptep = rmap_get_first(*rmapp, &iter); + continue; } - write_protected = 1; + sptep = rmap_get_next(&iter); } - return write_protected; + return flush; } /** @@ -1100,26 +1174,26 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, while (mask) { rmapp = &slot->rmap[gfn_offset + __ffs(mask)]; - __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL); + __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false); /* clear the first set bit */ mask &= mask - 1; } } -static int rmap_write_protect(struct kvm *kvm, u64 gfn) +static bool rmap_write_protect(struct kvm *kvm, u64 gfn) { struct kvm_memory_slot *slot; unsigned long *rmapp; int i; - int write_protected = 0; + bool write_protected = false; slot = gfn_to_memslot(kvm, gfn); for (i = PT_PAGE_TABLE_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, i); + write_protected |= __rmap_write_protect(kvm, rmapp, i, true); } return write_protected; @@ -1238,11 +1312,12 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long data) { u64 *sptep; - struct rmap_iterator iter; + struct rmap_iterator uninitialized_var(iter); int young = 0; /* - * Emulate the accessed bit for EPT, by checking if this page has + * In case of absence of EPT Access and Dirty Bits supports, + * emulate the accessed bit for EPT, by checking if this page has * an EPT mapping, and clearing it if it does. On the next access, * a new EPT mapping will be established. * This has some overhead, but not as much as the cost of swapping @@ -1253,11 +1328,12 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep; sptep = rmap_get_next(&iter)) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + BUG_ON(!is_shadow_present_pte(*sptep)); - if (*sptep & PT_ACCESSED_MASK) { + if (*sptep & shadow_accessed_mask) { young = 1; - clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)sptep); + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); } } @@ -1281,9 +1357,9 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep; sptep = rmap_get_next(&iter)) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + BUG_ON(!is_shadow_present_pte(*sptep)); - if (*sptep & PT_ACCESSED_MASK) { + if (*sptep & shadow_accessed_mask) { young = 1; break; } @@ -1401,12 +1477,10 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, u64 *parent_pte, int direct) { struct kvm_mmu_page *sp; - sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, - sizeof *sp); - sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache); + sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); if (!direct) - sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, - PAGE_SIZE); + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM); @@ -1701,7 +1775,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { - int protected = 0; + bool protected = false; for_each_sp(pages, sp, parents, i) protected |= rmap_write_protect(vcpu->kvm, sp->gfn); @@ -1866,15 +1940,6 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) mmu_spte_set(sptep, spte); } -static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) -{ - if (is_large_pte(*sptep)) { - drop_spte(vcpu->kvm, sptep); - --vcpu->kvm->stat.lpages; - kvm_flush_remote_tlbs(vcpu->kvm); - } -} - static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned direct_access) { @@ -2243,7 +2308,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { - u64 spte, entry = *sptep; + u64 spte; int ret = 0; if (set_mmio_spte(sptep, gfn, pfn, pte_access)) @@ -2257,8 +2322,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= shadow_x_mask; else spte |= shadow_nx_mask; + if (pte_access & ACC_USER_MASK) spte |= shadow_user_mask; + if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) @@ -2283,7 +2350,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, goto done; } - spte |= PT_WRITABLE_MASK; + spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; if (!vcpu->arch.mmu.direct_map && !(pte_access & ACC_WRITE_MASK)) { @@ -2312,8 +2379,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, __func__, gfn); ret = 1; pte_access &= ~ACC_WRITE_MASK; - if (is_writable_pte(spte)) - spte &= ~PT_WRITABLE_MASK; + spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE); } } @@ -2321,14 +2387,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, mark_page_dirty(vcpu->kvm, gfn); set_pte: - mmu_spte_update(sptep, spte); - /* - * If we overwrite a writable spte with a read-only one we - * should flush remote TLBs. Otherwise rmap_write_protect - * will find a read-only spte, even though the writable spte - * might be cached on a CPU's TLB. - */ - if (is_writable_pte(entry) && !is_writable_pte(*sptep)) + if (mmu_spte_update(sptep, spte)) kvm_flush_remote_tlbs(vcpu->kvm); done: return ret; @@ -2403,6 +2462,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { + mmu_free_roots(vcpu); } static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2625,18 +2685,116 @@ exit: return ret; } +static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code) +{ + /* + * #PF can be fast only if the shadow page table is present and it + * is caused by write-protect, that means we just need change the + * W bit of the spte which can be done out of mmu-lock. + */ + if (!(error_code & PFERR_PRESENT_MASK) || + !(error_code & PFERR_WRITE_MASK)) + return false; + + return true; +} + +static bool +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + gfn_t gfn; + + WARN_ON(!sp->role.direct); + + /* + * The gfn of direct spte is stable since it is calculated + * by sp->gfn. + */ + gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); + + if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) + mark_page_dirty(vcpu->kvm, gfn); + + return true; +} + +/* + * Return value: + * - true: let the vcpu to access on the same address again. + * - false: let the real page fault path to fix it. + */ +static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, + u32 error_code) +{ + struct kvm_shadow_walk_iterator iterator; + bool ret = false; + u64 spte = 0ull; + + if (!page_fault_can_be_fast(vcpu, error_code)) + return false; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + if (!is_shadow_present_pte(spte) || iterator.level < level) + break; + + /* + * If the mapping has been changed, let the vcpu fault on the + * same address again. + */ + if (!is_rmap_spte(spte)) { + ret = true; + goto exit; + } + + if (!is_last_spte(spte, level)) + goto exit; + + /* + * Check if it is a spurious fault caused by TLB lazily flushed. + * + * Need not check the access of upper level table entries since + * they are always ACC_ALL. + */ + if (is_writable_pte(spte)) { + ret = true; + goto exit; + } + + /* + * Currently, to simplify the code, only the spte write-protected + * by dirty-log can be fast fixed. + */ + if (!spte_is_locklessly_modifiable(spte)) + goto exit; + + /* + * Currently, fast page fault only works for direct mapping since + * the gfn is not stable for indirect shadow page. + * See Documentation/virtual/kvm/locking.txt to get more detail. + */ + ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte); +exit: + trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + spte, ret); + walk_shadow_page_lockless_end(vcpu); + + return ret; +} + static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable); -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, - bool prefault) +static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, + gfn_t gfn, bool prefault) { int r; int level; int force_pt_level; pfn_t pfn; unsigned long mmu_seq; - bool map_writable; + bool map_writable, write = error_code & PFERR_WRITE_MASK; force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); if (likely(!force_pt_level)) { @@ -2653,6 +2811,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, } else level = PT_PAGE_TABLE_LEVEL; + if (fast_page_fault(vcpu, v, level, error_code)) + return 0; + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -3041,7 +3202,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, gfn = gva >> PAGE_SHIFT; return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code & PFERR_WRITE_MASK, gfn, prefault); + error_code, gfn, prefault); } static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) @@ -3121,6 +3282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, } else level = PT_PAGE_TABLE_LEVEL; + if (fast_page_fault(vcpu, gpa, level, error_code)) + return 0; + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -3885,6 +4049,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu) void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) { struct kvm_mmu_page *sp; + bool flush = false; list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) { int i; @@ -3899,16 +4064,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) !is_last_spte(pt[i], sp->role.level)) continue; - if (is_large_pte(pt[i])) { - drop_spte(kvm, &pt[i]); - --kvm->stat.lpages; - continue; - } - - /* avoid RMW */ - if (is_writable_pte(pt[i])) - mmu_spte_update(&pt[i], - pt[i] & ~PT_WRITABLE_MASK); + spte_write_protect(kvm, &pt[i], &flush, false); } } kvm_flush_remote_tlbs(kvm); @@ -3945,7 +4101,6 @@ static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; - struct kvm *kvm_freed = NULL; int nr_to_scan = sc->nr_to_scan; if (nr_to_scan == 0) @@ -3957,22 +4112,30 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) int idx; LIST_HEAD(invalid_list); + /* + * n_used_mmu_pages is accessed without holding kvm->mmu_lock + * here. We may skip a VM instance errorneosly, but we do not + * want to shrink a VM that only started to populate its MMU + * anyway. + */ + if (kvm->arch.n_used_mmu_pages > 0) { + if (!nr_to_scan--) + break; + continue; + } + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - if (!kvm_freed && nr_to_scan > 0 && - kvm->arch.n_used_mmu_pages > 0) { - kvm_mmu_remove_some_alloc_mmu_pages(kvm, - &invalid_list); - kvm_freed = kvm; - } - nr_to_scan--; + kvm_mmu_remove_some_alloc_mmu_pages(kvm, &invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); + spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); + + list_move_tail(&kvm->vm_list, &vm_list); + break; } - if (kvm_freed) - list_move_tail(&kvm_freed->vm_list, &vm_list); raw_spin_unlock(&kvm_lock); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 89fb0e81322..cd6e98333ba 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -54,8 +54,8 @@ */ TRACE_EVENT( kvm_mmu_pagetable_walk, - TP_PROTO(u64 addr, int write_fault, int user_fault, int fetch_fault), - TP_ARGS(addr, write_fault, user_fault, fetch_fault), + TP_PROTO(u64 addr, u32 pferr), + TP_ARGS(addr, pferr), TP_STRUCT__entry( __field(__u64, addr) @@ -64,8 +64,7 @@ TRACE_EVENT( TP_fast_assign( __entry->addr = addr; - __entry->pferr = (!!write_fault << 1) | (!!user_fault << 2) - | (!!fetch_fault << 4); + __entry->pferr = pferr; ), TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr, @@ -243,6 +242,44 @@ TRACE_EVENT( TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn, __entry->access) ); + +#define __spte_satisfied(__spte) \ + (__entry->retry && is_writable_pte(__entry->__spte)) + +TRACE_EVENT( + fast_page_fault, + TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + u64 *sptep, u64 old_spte, bool retry), + TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(gva_t, gva) + __field(u32, error_code) + __field(u64 *, sptep) + __field(u64, old_spte) + __field(u64, new_spte) + __field(bool, retry) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->gva = gva; + __entry->error_code = error_code; + __entry->sptep = sptep; + __entry->old_spte = old_spte; + __entry->new_spte = *sptep; + __entry->retry = retry; + ), + + TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + " new %llx spurious %d fixed %d", __entry->vcpu_id, + __entry->gva, __print_flags(__entry->error_code, "|", + kvm_mmu_trace_pferr_flags), __entry->sptep, + __entry->old_spte, __entry->new_spte, + __spte_satisfied(old_spte), __spte_satisfied(new_spte) + ) +); #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 34f970937ef..bb7cf01cae7 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -154,8 +154,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, const int fetch_fault = access & PFERR_FETCH_MASK; u16 errcode = 0; - trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault, - fetch_fault); + trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: eperm = false; walker->level = mmu->root_level; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f75af406b26..baead950d6c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3185,8 +3185,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) break; case MSR_IA32_DEBUGCTLMSR: if (!boot_cpu_has(X86_FEATURE_LBRV)) { - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", + __func__, data); break; } if (data & DEBUGCTL_RESERVED_BITS) @@ -3205,7 +3205,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; default: return kvm_set_msr_common(vcpu, ecx, data); @@ -4044,6 +4044,11 @@ static bool svm_rdtscp_supported(void) return false; } +static bool svm_invpcid_supported(void) +{ + return false; +} + static bool svm_has_wbinvd_exit(void) { return true; @@ -4312,6 +4317,7 @@ static struct kvm_x86_ops svm_x86_ops = { .cpuid_update = svm_cpuid_update, .rdtscp_supported = svm_rdtscp_supported, + .invpcid_supported = svm_invpcid_supported, .set_supported_cpuid = svm_set_supported_cpuid, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 62d02e3c3ed..a71faf727ff 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -517,6 +517,40 @@ TRACE_EVENT(kvm_apic_accept_irq, __entry->coalesced ? " (coalesced)" : "") ); +TRACE_EVENT(kvm_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + __entry->apicid = apic->vcpu->vcpu_id; + __entry->vector = vector; + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +); + +TRACE_EVENT(kvm_pv_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + __entry->apicid = apic->vcpu->vcpu_id; + __entry->vector = vector; + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +); + /* * Tracepoint for nested VMRUN */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32eb5886629..c39b60707e0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,7 +71,10 @@ static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static bool __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly enable_ept_ad_bits = 1; +module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); + +static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly vmm_exclusive = 1; @@ -615,6 +618,10 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +static void vmx_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); +static void vmx_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -789,6 +796,11 @@ static inline bool cpu_has_vmx_ept_4levels(void) return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT; } +static inline bool cpu_has_vmx_ept_ad_bits(void) +{ + return vmx_capability.ept & VMX_EPT_AD_BIT; +} + static inline bool cpu_has_vmx_invept_individual_addr(void) { return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; @@ -849,6 +861,12 @@ static inline bool cpu_has_vmx_rdtscp(void) SECONDARY_EXEC_RDTSCP; } +static inline bool cpu_has_vmx_invpcid(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_INVPCID; +} + static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; @@ -1739,6 +1757,11 @@ static bool vmx_rdtscp_supported(void) return cpu_has_vmx_rdtscp(); } +static bool vmx_invpcid_supported(void) +{ + return cpu_has_vmx_invpcid() && enable_ept; +} + /* * Swap MSR entry in host/guest MSR entry array. */ @@ -2458,7 +2481,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_RDTSCP; + SECONDARY_EXEC_RDTSCP | + SECONDARY_EXEC_ENABLE_INVPCID; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2645,8 +2669,12 @@ static __init int hardware_setup(void) !cpu_has_vmx_ept_4levels()) { enable_ept = 0; enable_unrestricted_guest = 0; + enable_ept_ad_bits = 0; } + if (!cpu_has_vmx_ept_ad_bits()) + enable_ept_ad_bits = 0; + if (!cpu_has_vmx_unrestricted_guest()) enable_unrestricted_guest = 0; @@ -2770,6 +2798,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_segment var; if (enable_unrestricted_guest) return; @@ -2813,20 +2842,23 @@ static void enter_rmode(struct kvm_vcpu *vcpu) if (emulate_invalid_guest_state) goto continue_rmode; - vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); - vmcs_write32(GUEST_SS_LIMIT, 0xffff); - vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + vmx_get_segment(vcpu, &var, VCPU_SREG_SS); + vmx_set_segment(vcpu, &var, VCPU_SREG_SS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_CS); + vmx_set_segment(vcpu, &var, VCPU_SREG_CS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_ES); + vmx_set_segment(vcpu, &var, VCPU_SREG_ES); + + vmx_get_segment(vcpu, &var, VCPU_SREG_DS); + vmx_set_segment(vcpu, &var, VCPU_SREG_DS); - vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) - vmcs_writel(GUEST_CS_BASE, 0xf0000); - vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); + vmx_get_segment(vcpu, &var, VCPU_SREG_GS); + vmx_set_segment(vcpu, &var, VCPU_SREG_GS); - fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); - fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); - fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); - fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + vmx_get_segment(vcpu, &var, VCPU_SREG_FS); + vmx_set_segment(vcpu, &var, VCPU_SREG_FS); continue_rmode: kvm_mmu_reset_context(vcpu); @@ -3027,6 +3059,8 @@ static u64 construct_eptp(unsigned long root_hpa) /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; + if (enable_ept_ad_bits) + eptp |= VMX_EPT_AD_ENABLE_BIT; eptp |= (root_hpa & PAGE_MASK); return eptp; @@ -3153,11 +3187,22 @@ static int __vmx_get_cpl(struct kvm_vcpu *vcpu) static int vmx_get_cpl(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If we enter real mode with cs.sel & 3 != 0, the normal CPL calculations + * fail; use the cache instead. + */ + if (unlikely(vmx->emulation_required && emulate_invalid_guest_state)) { + return vmx->cpl; + } + if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->cpl = __vmx_get_cpl(vcpu); + vmx->cpl = __vmx_get_cpl(vcpu); } - return to_vmx(vcpu)->cpl; + + return vmx->cpl; } @@ -3165,7 +3210,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable) + if (var->unusable || !var->present) ar = 1 << 16; else { ar = var->type & 15; @@ -3177,8 +3222,6 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; } - if (ar == 0) /* a 0 value means unusable */ - ar = AR_UNUSABLE_MASK; return ar; } @@ -3229,6 +3272,44 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, vmcs_write32(sf->ar_bytes, ar); __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + + /* + * Fix segments for real mode guest in hosts that don't have + * "unrestricted_mode" or it was disabled. + * This is done to allow migration of the guests from hosts with + * unrestricted guest like Westmere to older host that don't have + * unrestricted guest like Nehelem. + */ + if (!enable_unrestricted_guest && vmx->rmode.vm86_active) { + switch (seg) { + case VCPU_SREG_CS: + vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); + vmcs_write32(GUEST_CS_LIMIT, 0xffff); + if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) + vmcs_writel(GUEST_CS_BASE, 0xf0000); + vmcs_write16(GUEST_CS_SELECTOR, + vmcs_readl(GUEST_CS_BASE) >> 4); + break; + case VCPU_SREG_ES: + fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); + break; + case VCPU_SREG_DS: + fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); + break; + case VCPU_SREG_GS: + fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); + break; + case VCPU_SREG_FS: + fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + break; + case VCPU_SREG_SS: + vmcs_write16(GUEST_SS_SELECTOR, + vmcs_readl(GUEST_SS_BASE) >> 4); + vmcs_write32(GUEST_SS_LIMIT, 0xffff); + vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + break; + } + } } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3731,6 +3812,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; enable_unrestricted_guest = 0; + /* Enable INVPCID for non-ept guests may cause performance regression. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -4489,7 +4572,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; } vcpu->run->exit_reason = 0; - pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", + vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } @@ -4769,6 +4852,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; + u32 error_code; int gla_validity; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4793,7 +4877,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3, NULL, 0); + + /* It is a write fault? */ + error_code = exit_qualification & (1U << 1); + /* ept page table is present? */ + error_code |= (exit_qualification >> 3) & 0x1; + + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } static u64 ept_rsvd_mask(u64 spte, int level) @@ -4908,15 +4998,18 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) int ret = 1; u32 cpu_exec_ctrl; bool intr_window_requested; + unsigned count = 130; cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING; - while (!guest_state_valid(vcpu)) { - if (intr_window_requested - && (kvm_get_rflags(&vmx->vcpu) & X86_EFLAGS_IF)) + while (!guest_state_valid(vcpu) && count-- != 0) { + if (intr_window_requested && vmx_interrupt_allowed(vcpu)) return handle_interrupt_window(&vmx->vcpu); + if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) + return 1; + err = emulate_instruction(vcpu, 0); if (err == EMULATE_DO_MMIO) { @@ -4924,8 +5017,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) goto out; } - if (err != EMULATE_DONE) + if (err != EMULATE_DONE) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; + } if (signal_pending(current)) goto out; @@ -4933,7 +5030,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) schedule(); } - vmx->emulation_required = 0; + vmx->emulation_required = !guest_state_valid(vcpu); out: return ret; } @@ -6467,6 +6564,23 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } } + + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + /* Exposing INVPCID only when PCID is exposed */ + best = kvm_find_cpuid_entry(vcpu, 0x7, 0); + if (vmx_invpcid_supported() && + best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + guest_cpuid_has_pcid(vcpu)) { + exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + } else { + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + if (best) + best->ecx &= ~bit(X86_FEATURE_INVPCID); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -7201,6 +7315,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .cpuid_update = vmx_cpuid_update, .rdtscp_supported = vmx_rdtscp_supported, + .invpcid_supported = vmx_invpcid_supported, .set_supported_cpuid = vmx_set_supported_cpuid, @@ -7230,23 +7345,21 @@ static int __init vmx_init(void) if (!vmx_io_bitmap_a) return -ENOMEM; + r = -ENOMEM; + vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_io_bitmap_b) { - r = -ENOMEM; + if (!vmx_io_bitmap_b) goto out; - } vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) { - r = -ENOMEM; + if (!vmx_msr_bitmap_legacy) goto out1; - } + vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) { - r = -ENOMEM; + if (!vmx_msr_bitmap_longmode) goto out2; - } + /* * Allow direct access to the PC debug port (it is often used for I/O @@ -7275,8 +7388,10 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull, - VMX_EPT_EXECUTABLE_MASK); + kvm_mmu_set_mask_ptes(0ull, + (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, + (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); } else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be6d54929fa..59b59508ff0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -528,6 +528,9 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) return 1; } + if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + return 1; + kvm_x86_ops->set_cr0(vcpu, cr0); if ((cr0 ^ old_cr0) & X86_CR0_PG) { @@ -604,10 +607,20 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_read_cr3(vcpu))) return 1; + if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { + if (!guest_cpuid_has_pcid(vcpu)) + return 1; + + /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + return 1; + } + if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - if ((cr4 ^ old_cr4) & pdptr_bits) + if (((cr4 ^ old_cr4) & pdptr_bits) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) @@ -626,8 +639,12 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) - return 1; + if (kvm_read_cr4(vcpu) & X86_CR4_PCIDE) { + if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS) + return 1; + } else + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; } else { if (is_pae(vcpu)) { if (cr3 & CR3_PAE_RESERVED_BITS) @@ -795,6 +812,7 @@ static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1437,8 +1455,8 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; } default: - pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); return 1; } return 0; @@ -1470,8 +1488,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); default: - pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); return 1; } @@ -1551,15 +1569,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ if (data != 0) { - pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", + data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " + "0x%llx\n", data); return 1; } break; @@ -1574,8 +1592,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) thus reserved and should throw a #GP */ return 1; } - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: @@ -1653,6 +1671,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; + case MSR_KVM_PV_EOI_EN: + if (kvm_lapic_enable_pv_eoi(vcpu, data)) + return 1; + break; case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: @@ -1671,8 +1693,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_K7_EVNTSEL2: case MSR_K7_EVNTSEL3: if (data != 0) - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; /* at least RHEL 4 unconditionally writes to the perfctr registers, * so we ignore writes to make it happy. @@ -1681,8 +1703,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_K7_PERFCTR1: case MSR_K7_PERFCTR2: case MSR_K7_PERFCTR3: - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -1693,8 +1715,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) return kvm_pmu_set_msr(vcpu, msr, data); if (pr || data != 0) - pr_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; case MSR_K7_CLK_CTL: /* @@ -1720,7 +1742,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) @@ -1738,12 +1760,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr, data); if (!ignore_msrs) { - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", - msr, data); + vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + msr, data); return 1; } else { - pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", - msr, data); + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + msr, data); break; } } @@ -1846,7 +1868,7 @@ static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = kvm->arch.hv_hypercall; break; default: - pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; } @@ -1877,7 +1899,7 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = vcpu->arch.hv_vapic; break; default: - pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; } *pdata = data; @@ -2030,10 +2052,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_get_msr(vcpu, msr, pdata); if (!ignore_msrs) { - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); return 1; } else { - pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); data = 0; } break; @@ -4116,7 +4138,7 @@ static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) value = kvm_get_cr8(vcpu); break; default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + kvm_err("%s: unexpected cr %u\n", __func__, cr); return 0; } @@ -4145,7 +4167,7 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) res = kvm_set_cr8(vcpu, val); break; default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + kvm_err("%s: unexpected cr %u\n", __func__, cr); res = -1; } @@ -4297,26 +4319,10 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); } -static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, +static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) { - struct kvm_cpuid_entry2 *cpuid = NULL; - - if (eax && ecx) - cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt), - *eax, *ecx); - - if (cpuid) { - *eax = cpuid->eax; - *ecx = cpuid->ecx; - if (ebx) - *ebx = cpuid->ebx; - if (edx) - *edx = cpuid->edx; - return true; - } - - return false; + kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx); } static struct x86_emulate_ops emulate_ops = { @@ -5296,8 +5302,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = kvm_mmu_reload(vcpu); if (unlikely(r)) { - kvm_x86_ops->cancel_injection(vcpu); - goto out; + goto cancel_injection; } preempt_disable(); @@ -5322,9 +5327,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - kvm_x86_ops->cancel_injection(vcpu); r = 1; - goto out; + goto cancel_injection; } srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -5388,9 +5392,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(vcpu->arch.tsc_always_catchup)) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - kvm_lapic_sync_from_vapic(vcpu); + if (vcpu->arch.apic_attention) + kvm_lapic_sync_from_vapic(vcpu); r = kvm_x86_ops->handle_exit(vcpu); + return r; + +cancel_injection: + kvm_x86_ops->cancel_injection(vcpu); + if (unlikely(vcpu->arch.apic_attention)) + kvm_lapic_sync_from_vapic(vcpu); out: return r; } @@ -6304,7 +6315,7 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) { - vfree(free->arch.lpage_info[i]); + kvm_kvfree(free->arch.lpage_info[i]); free->arch.lpage_info[i] = NULL; } } @@ -6323,7 +6334,7 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) slot->base_gfn, level) + 1; slot->arch.lpage_info[i] = - vzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); + kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); if (!slot->arch.lpage_info[i]) goto out_free; @@ -6350,7 +6361,7 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) out_free: for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { - vfree(slot->arch.lpage_info[i]); + kvm_kvfree(slot->arch.lpage_info[i]); slot->arch.lpage_info[i] = NULL; } return -ENOMEM; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0597f95b6da..33643a8bcbb 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -309,6 +309,10 @@ void bpf_jit_compile(struct sk_filter *fp) else EMIT1_off32(0x0d, K); /* or imm32,%eax */ break; + case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ + seen |= SEEN_XREG; + EMIT2(0x31, 0xd8); /* xor %ebx,%eax */ + break; case BPF_S_ALU_LSH_X: /* A <<= X; */ seen |= SEEN_XREG; EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ed7d54985d0..bf4bda6d3e9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,6 +31,7 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/syscore_ops.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -38,6 +39,7 @@ #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> #include <xen/interface/memory.h> +#include <xen/interface/xen-mca.h> #include <xen/features.h> #include <xen/page.h> #include <xen/hvm.h> @@ -107,7 +109,7 @@ EXPORT_SYMBOL_GPL(xen_have_vector_callback); * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ -struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; /* * Flag to determine whether vcpu info placement is available on all @@ -124,6 +126,19 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; */ static int have_vcpu_info_placement = 1; +struct tls_descs { + struct desc_struct desc[3]; +}; + +/* + * Updating the 3 TLS descriptors in the GDT on every task switch is + * surprisingly expensive so we avoid updating them if they haven't + * changed. Since Xen writes different descriptors than the one + * passed in the update_descriptor hypercall we keep shadow copies to + * compare against. + */ +static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); + static void clamp_max_cpus(void) { #ifdef CONFIG_SMP @@ -341,9 +356,7 @@ static void __init xen_init_cpuid_mask(void) unsigned int xsave_mask; cpuid_leaf1_edx_mask = - ~((1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_MTRR) | /* disable MTRR */ + ~((1 << X86_FEATURE_MTRR) | /* disable MTRR */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ if (!xen_initial_domain()) @@ -540,12 +553,28 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) BUG(); } +static inline bool desc_equal(const struct desc_struct *d1, + const struct desc_struct *d2) +{ + return d1->a == d2->a && d1->b == d2->b; +} + static void load_TLS_descriptor(struct thread_struct *t, unsigned int cpu, unsigned int i) { - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); - struct multicall_space mc = __xen_mc_entry(0); + struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i]; + struct desc_struct *gdt; + xmaddr_t maddr; + struct multicall_space mc; + + if (desc_equal(shadow, &t->tls_array[i])) + return; + + *shadow = t->tls_array[i]; + + gdt = get_cpu_gdt_table(cpu); + maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); + mc = __xen_mc_entry(0); MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); } @@ -627,8 +656,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, /* * Look for known traps using IST, and substitute them * appropriately. The debugger ones are the only ones we care - * about. Xen will handle faults like double_fault and - * machine_check, so we should never see them. Warn if + * about. Xen will handle faults like double_fault, + * so we should never see them. Warn if * there's an unexpected IST-using fault handler. */ if (addr == (unsigned long)debug) @@ -643,7 +672,11 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, return 0; #ifdef CONFIG_X86_MCE } else if (addr == (unsigned long)machine_check) { - return 0; + /* + * when xen hypervisor inject vMCE to guest, + * use native mce handler to handle it + */ + ; #endif } else { /* Some other trap using IST? */ @@ -1437,64 +1470,155 @@ asmlinkage void __init xen_start_kernel(void) #endif } -static int init_hvm_pv_info(int *major, int *minor) -{ - uint32_t eax, ebx, ecx, edx, pages, msr, base; - u64 pfn; - - base = xen_cpuid_base(); - cpuid(base + 1, &eax, &ebx, &ecx, &edx); - - *major = eax >> 16; - *minor = eax & 0xffff; - printk(KERN_INFO "Xen version %d.%d.\n", *major, *minor); - - cpuid(base + 2, &pages, &msr, &ecx, &edx); - - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - - xen_setup_features(); - - pv_info.name = "Xen HVM"; - - xen_domain_type = XEN_HVM_DOMAIN; +#ifdef CONFIG_XEN_PVHVM +/* + * The pfn containing the shared_info is located somewhere in RAM. This + * will cause trouble if the current kernel is doing a kexec boot into a + * new kernel. The new kernel (and its startup code) can not know where + * the pfn is, so it can not reserve the page. The hypervisor will + * continue to update the pfn, and as a result memory corruption occours + * in the new kernel. + * + * One way to work around this issue is to allocate a page in the + * xen-platform pci device's BAR memory range. But pci init is done very + * late and the shared_info page is already in use very early to read + * the pvclock. So moving the pfn from RAM to MMIO is racy because some + * code paths on other vcpus could access the pfn during the small + * window when the old pfn is moved to the new pfn. There is even a + * small window were the old pfn is not backed by a mfn, and during that + * time all reads return -1. + * + * Because it is not known upfront where the MMIO region is located it + * can not be used right from the start in xen_hvm_init_shared_info. + * + * To minimise trouble the move of the pfn is done shortly before kexec. + * This does not eliminate the race because all vcpus are still online + * when the syscore_ops will be called. But hopefully there is no work + * pending at this point in time. Also the syscore_op is run last which + * reduces the risk further. + */ - return 0; -} +static struct shared_info *xen_hvm_shared_info; -void __ref xen_hvm_init_shared_info(void) +static void xen_hvm_connect_shared_info(unsigned long pfn) { - int cpu; struct xen_add_to_physmap xatp; - static struct shared_info *shared_info_page = 0; - if (!shared_info_page) - shared_info_page = (struct shared_info *) - extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + xatp.gpfn = pfn; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); - HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; +} +static void xen_hvm_set_shared_info(struct shared_info *sip) +{ + int cpu; + + HYPERVISOR_shared_info = sip; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on * HVM. - * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_init_shared_info is run at resume time too and + * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_set_shared_info is run at resume time too and * in that case multiple vcpus might be online. */ for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; } } -#ifdef CONFIG_XEN_PVHVM +/* Reconnect the shared_info pfn to a mfn */ +void xen_hvm_resume_shared_info(void) +{ + xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); +} + +#ifdef CONFIG_KEXEC +static struct shared_info *xen_hvm_shared_info_kexec; +static unsigned long xen_hvm_shared_info_pfn_kexec; + +/* Remember a pfn in MMIO space for kexec reboot */ +void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) +{ + xen_hvm_shared_info_kexec = sip; + xen_hvm_shared_info_pfn_kexec = pfn; +} + +static void xen_hvm_syscore_shutdown(void) +{ + struct xen_memory_reservation reservation = { + .domid = DOMID_SELF, + .nr_extents = 1, + }; + unsigned long prev_pfn; + int rc; + + if (!xen_hvm_shared_info_kexec) + return; + + prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; + set_xen_guest_handle(reservation.extent_start, &prev_pfn); + + /* Move pfn to MMIO, disconnects previous pfn from mfn */ + xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); + + /* Update pointers, following hypercall is also a memory barrier */ + xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); + + /* Allocate new mfn for previous pfn */ + do { + rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); + if (rc == 0) + msleep(123); + } while (rc == 0); + + /* Make sure the previous pfn is really connected to a (new) mfn */ + BUG_ON(rc != 1); +} + +static struct syscore_ops xen_hvm_syscore_ops = { + .shutdown = xen_hvm_syscore_shutdown, +}; +#endif + +/* Use a pfn in RAM, may move to MMIO before kexec. */ +static void __init xen_hvm_init_shared_info(void) +{ + /* Remember pointer for resume */ + xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); + xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); + xen_hvm_set_shared_info(xen_hvm_shared_info); +} + +static void __init init_hvm_pv_info(void) +{ + int major, minor; + uint32_t eax, ebx, ecx, edx, pages, msr, base; + u64 pfn; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + major = eax >> 16; + minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", major, minor); + + cpuid(base + 2, &pages, &msr, &ecx, &edx); + + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info.name = "Xen HVM"; + + xen_domain_type = XEN_HVM_DOMAIN; +} + static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1517,14 +1641,12 @@ static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = { static void __init xen_hvm_guest_init(void) { - int r; - int major, minor; - - r = init_hvm_pv_info(&major, &minor); - if (r < 0) - return; + init_hvm_pv_info(); xen_hvm_init_shared_info(); +#ifdef CONFIG_KEXEC + register_syscore_ops(&xen_hvm_syscore_ops); +#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3a73785631c..27336dfcda8 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -308,8 +308,20 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) static inline void __xen_set_pte(pte_t *ptep, pte_t pteval) { - if (!xen_batched_set_pte(ptep, pteval)) - native_set_pte(ptep, pteval); + if (!xen_batched_set_pte(ptep, pteval)) { + /* + * Could call native_set_pte() here and trap and + * emulate the PTE write but with 32-bit guests this + * needs two traps (one for each of the two 32-bit + * words in the PTE) so do one hypercall directly + * instead. + */ + struct mmu_update u; + + u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE; + u.val = pte_val_ma(pteval); + HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF); + } } static void xen_set_pte(pte_t *ptep, pte_t pteval) @@ -1416,13 +1428,28 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) } #endif /* CONFIG_X86_64 */ -/* Init-time set_pte while constructing initial pagetables, which - doesn't allow RO pagetable pages to be remapped RW */ +/* + * Init-time set_pte while constructing initial pagetables, which + * doesn't allow RO page table pages to be remapped RW. + * + * If there is no MFN for this PFN then this page is initially + * ballooned out so clear the PTE (as in decrease_reservation() in + * drivers/xen/balloon.c). + * + * Many of these PTE updates are done on unpinned and writable pages + * and doing a hypercall for these is unnecessary and expensive. At + * this point it is not possible to tell if a page is pinned or not, + * so always write the PTE directly and rely on Xen trapping and + * emulating any updates as necessary. + */ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) { - pte = mask_rw_pte(ptep, pte); + if (pte_mfn(pte) != INVALID_P2M_ENTRY) + pte = mask_rw_pte(ptep, pte); + else + pte = __pte_ma(0); - xen_set_pte(ptep, pte); + native_set_pte(ptep, pte); } static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a4790bf22c5..ead85576d54 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -157,25 +157,24 @@ static unsigned long __init xen_populate_chunk( unsigned long dest_pfn; for (i = 0, entry = list; i < map_size; i++, entry++) { - unsigned long credits = credits_left; unsigned long s_pfn; unsigned long e_pfn; unsigned long pfns; long capacity; - if (credits <= 0) + if (credits_left <= 0) break; if (entry->type != E820_RAM) continue; - e_pfn = PFN_UP(entry->addr + entry->size); + e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after the xen_start_info->nr_pages */ if (e_pfn <= max_pfn) continue; - s_pfn = PFN_DOWN(entry->addr); + s_pfn = PFN_UP(entry->addr); /* If the E820 falls within the nr_pages, we want to start * at the nr_pages PFN. * If that would mean going past the E820 entry, skip it @@ -184,23 +183,19 @@ static unsigned long __init xen_populate_chunk( capacity = e_pfn - max_pfn; dest_pfn = max_pfn; } else { - /* last_pfn MUST be within E820_RAM regions */ - if (*last_pfn && e_pfn >= *last_pfn) - s_pfn = *last_pfn; capacity = e_pfn - s_pfn; dest_pfn = s_pfn; } - /* If we had filled this E820_RAM entry, go to the next one. */ - if (capacity <= 0) - continue; - if (credits > capacity) - credits = capacity; + if (credits_left < capacity) + capacity = credits_left; - pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false); + pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false); done += pfns; - credits_left -= pfns; *last_pfn = (dest_pfn + pfns); + if (pfns < capacity) + break; + credits_left -= pfns; } return done; } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 45329c8c226..ae8a00c39de 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + xen_hvm_resume_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 202d4c15015..1e4329e04e0 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_init_shared_info(void); +void xen_hvm_resume_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); |