diff options
Diffstat (limited to 'arch')
102 files changed, 1067 insertions, 1057 deletions
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index 8226c5cd788c..67be50b7d80a 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -149,7 +149,7 @@ irqreturn_t timer_interrupt(int irq, void *dev, struct pt_regs * regs) * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 + if (ntp_synced() && xtime.tv_sec > state.last_rtc_update + 660 && xtime.tv_nsec >= 500000 - ((unsigned) TICK_SIZE) / 2 && xtime.tv_nsec <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -502,10 +502,7 @@ do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 8880482dcbff..69449a818dcc 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -102,7 +102,7 @@ static unsigned long next_rtc_update; */ static inline void do_set_rtc(void) { - if (time_status & STA_UNSYNC || set_rtc == NULL) + if (!ntp_synced() || set_rtc == NULL) return; if (next_rtc_update && @@ -292,10 +292,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile index efc2f657184e..33dae99ec2d8 100644 --- a/arch/arm/mach-pxa/Makefile +++ b/arch/arm/mach-pxa/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_PXA27x) += pxa27x.o obj-$(CONFIG_ARCH_LUBBOCK) += lubbock.o obj-$(CONFIG_MACH_MAINSTONE) += mainstone.o obj-$(CONFIG_ARCH_PXA_IDP) += idp.o -obj-$(CONFIG_PXA_SHARP_C7xx) += corgi.o corgi_ssp.o ssp.o +obj-$(CONFIG_PXA_SHARP_C7xx) += corgi.o corgi_ssp.o corgi_lcd.o ssp.o obj-$(CONFIG_MACH_POODLE) += poodle.o # Support for blinky lights diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index 06ea730e8675..29185acdd9e1 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -39,7 +39,6 @@ #include <asm/mach/sharpsl_param.h> #include <asm/hardware/scoop.h> -#include <video/w100fb.h> #include "generic.h" @@ -87,7 +86,7 @@ struct platform_device corgiscoop_device = { * also use scoop functions and this makes the power up/down order * work correctly. */ -static struct platform_device corgissp_device = { +struct platform_device corgissp_device = { .name = "corgi-ssp", .dev = { .parent = &corgiscoop_device.dev, @@ -97,41 +96,33 @@ static struct platform_device corgissp_device = { /* - * Corgi w100 Frame Buffer Device + * Corgi Backlight Device */ -static struct w100fb_mach_info corgi_fb_info = { - .w100fb_ssp_send = corgi_ssp_lcdtg_send, - .comadj = -1, - .phadadj = -1, -}; - -static struct resource corgi_fb_resources[] = { - [0] = { - .start = 0x08000000, - .end = 0x08ffffff, - .flags = IORESOURCE_MEM, +static struct platform_device corgibl_device = { + .name = "corgi-bl", + .dev = { + .parent = &corgifb_device.dev, }, + .id = -1, }; -static struct platform_device corgifb_device = { - .name = "w100fb", + +/* + * Corgi Keyboard Device + */ +static struct platform_device corgikbd_device = { + .name = "corgi-keyboard", .id = -1, - .dev = { - .platform_data = &corgi_fb_info, - .parent = &corgissp_device.dev, - }, - .num_resources = ARRAY_SIZE(corgi_fb_resources), - .resource = corgi_fb_resources, }; /* - * Corgi Backlight Device + * Corgi Touch Screen Device */ -static struct platform_device corgibl_device = { - .name = "corgi-bl", +static struct platform_device corgits_device = { + .name = "corgi-ts", .dev = { - .parent = &corgifb_device.dev, + .parent = &corgissp_device.dev, }, .id = -1, }; @@ -199,6 +190,11 @@ static void corgi_mci_setpower(struct device *dev, unsigned int vdd) } } +static int corgi_mci_get_ro(struct device *dev) +{ + return GPLR(CORGI_GPIO_nSD_WP) & GPIO_bit(CORGI_GPIO_nSD_WP); +} + static void corgi_mci_exit(struct device *dev, void *data) { free_irq(CORGI_IRQ_GPIO_nSD_DETECT, data); @@ -208,11 +204,13 @@ static void corgi_mci_exit(struct device *dev, void *data) static struct pxamci_platform_data corgi_mci_platform_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .init = corgi_mci_init, + .get_ro = corgi_mci_get_ro, .setpower = corgi_mci_setpower, .exit = corgi_mci_exit, }; + /* * USB Device Controller */ @@ -238,14 +236,13 @@ static struct platform_device *devices[] __initdata = { &corgiscoop_device, &corgissp_device, &corgifb_device, + &corgikbd_device, &corgibl_device, + &corgits_device, }; static void __init corgi_init(void) { - corgi_fb_info.comadj=sharpsl_param.comadj; - corgi_fb_info.phadadj=sharpsl_param.phadadj; - pxa_gpio_mode(CORGI_GPIO_USB_PULLUP | GPIO_OUT); pxa_set_udc_info(&udc_info); pxa_set_mci_info(&corgi_mci_platform_data); diff --git a/arch/arm/mach-pxa/corgi_lcd.c b/arch/arm/mach-pxa/corgi_lcd.c new file mode 100644 index 000000000000..deac29c00290 --- /dev/null +++ b/arch/arm/mach-pxa/corgi_lcd.c @@ -0,0 +1,396 @@ +/* + * linux/drivers/video/w100fb.c + * + * Corgi LCD Specific Code for ATI Imageon w100 (Wallaby) + * + * Copyright (C) 2005 Richard Purdie + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/device.h> +#include <asm/arch/corgi.h> +#include <asm/mach/sharpsl_param.h> +#include <video/w100fb.h> + +/* Register Addresses */ +#define RESCTL_ADRS 0x00 +#define PHACTRL_ADRS 0x01 +#define DUTYCTRL_ADRS 0x02 +#define POWERREG0_ADRS 0x03 +#define POWERREG1_ADRS 0x04 +#define GPOR3_ADRS 0x05 +#define PICTRL_ADRS 0x06 +#define POLCTRL_ADRS 0x07 + +/* Resgister Bit Definitions */ +#define RESCTL_QVGA 0x01 +#define RESCTL_VGA 0x00 + +#define POWER1_VW_ON 0x01 /* VW Supply FET ON */ +#define POWER1_GVSS_ON 0x02 /* GVSS(-8V) Power Supply ON */ +#define POWER1_VDD_ON 0x04 /* VDD(8V),SVSS(-4V) Power Supply ON */ + +#define POWER1_VW_OFF 0x00 /* VW Supply FET OFF */ +#define POWER1_GVSS_OFF 0x00 /* GVSS(-8V) Power Supply OFF */ +#define POWER1_VDD_OFF 0x00 /* VDD(8V),SVSS(-4V) Power Supply OFF */ + +#define POWER0_COM_DCLK 0x01 /* COM Voltage DC Bias DAC Serial Data Clock */ +#define POWER0_COM_DOUT 0x02 /* COM Voltage DC Bias DAC Serial Data Out */ +#define POWER0_DAC_ON 0x04 /* DAC Power Supply ON */ +#define POWER0_COM_ON 0x08 /* COM Powewr Supply ON */ +#define POWER0_VCC5_ON 0x10 /* VCC5 Power Supply ON */ + +#define POWER0_DAC_OFF 0x00 /* DAC Power Supply OFF */ +#define POWER0_COM_OFF 0x00 /* COM Powewr Supply OFF */ +#define POWER0_VCC5_OFF 0x00 /* VCC5 Power Supply OFF */ + +#define PICTRL_INIT_STATE 0x01 +#define PICTRL_INIOFF 0x02 +#define PICTRL_POWER_DOWN 0x04 +#define PICTRL_COM_SIGNAL_OFF 0x08 +#define PICTRL_DAC_SIGNAL_OFF 0x10 + +#define POLCTRL_SYNC_POL_FALL 0x01 +#define POLCTRL_EN_POL_FALL 0x02 +#define POLCTRL_DATA_POL_FALL 0x04 +#define POLCTRL_SYNC_ACT_H 0x08 +#define POLCTRL_EN_ACT_L 0x10 + +#define POLCTRL_SYNC_POL_RISE 0x00 +#define POLCTRL_EN_POL_RISE 0x00 +#define POLCTRL_DATA_POL_RISE 0x00 +#define POLCTRL_SYNC_ACT_L 0x00 +#define POLCTRL_EN_ACT_H 0x00 + +#define PHACTRL_PHASE_MANUAL 0x01 +#define DEFAULT_PHAD_QVGA (9) +#define DEFAULT_COMADJ (125) + +/* + * This is only a psuedo I2C interface. We can't use the standard kernel + * routines as the interface is write only. We just assume the data is acked... + */ +static void lcdtg_ssp_i2c_send(u8 data) +{ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, data); + udelay(10); +} + +static void lcdtg_i2c_send_bit(u8 data) +{ + lcdtg_ssp_i2c_send(data); + lcdtg_ssp_i2c_send(data | POWER0_COM_DCLK); + lcdtg_ssp_i2c_send(data); +} + +static void lcdtg_i2c_send_start(u8 base) +{ + lcdtg_ssp_i2c_send(base | POWER0_COM_DCLK | POWER0_COM_DOUT); + lcdtg_ssp_i2c_send(base | POWER0_COM_DCLK); + lcdtg_ssp_i2c_send(base); +} + +static void lcdtg_i2c_send_stop(u8 base) +{ + lcdtg_ssp_i2c_send(base); + lcdtg_ssp_i2c_send(base | POWER0_COM_DCLK); + lcdtg_ssp_i2c_send(base | POWER0_COM_DCLK | POWER0_COM_DOUT); +} + +static void lcdtg_i2c_send_byte(u8 base, u8 data) +{ + int i; + for (i = 0; i < 8; i++) { + if (data & 0x80) + lcdtg_i2c_send_bit(base | POWER0_COM_DOUT); + else + lcdtg_i2c_send_bit(base); + data <<= 1; + } +} + +static void lcdtg_i2c_wait_ack(u8 base) +{ + lcdtg_i2c_send_bit(base); +} + +static void lcdtg_set_common_voltage(u8 base_data, u8 data) +{ + /* Set Common Voltage to M62332FP via I2C */ + lcdtg_i2c_send_start(base_data); + lcdtg_i2c_send_byte(base_data, 0x9c); + lcdtg_i2c_wait_ack(base_data); + lcdtg_i2c_send_byte(base_data, 0x00); + lcdtg_i2c_wait_ack(base_data); + lcdtg_i2c_send_byte(base_data, data); + lcdtg_i2c_wait_ack(base_data); + lcdtg_i2c_send_stop(base_data); +} + +/* Set Phase Adjuct */ +static void lcdtg_set_phadadj(struct w100fb_par *par) +{ + int adj; + switch(par->xres) { + case 480: + case 640: + /* Setting for VGA */ + adj = sharpsl_param.phadadj; + if (adj < 0) { + adj = PHACTRL_PHASE_MANUAL; + } else { + adj = ((adj & 0x0f) << 1) | PHACTRL_PHASE_MANUAL; + } + break; + case 240: + case 320: + default: + /* Setting for QVGA */ + adj = (DEFAULT_PHAD_QVGA << 1) | PHACTRL_PHASE_MANUAL; + break; + } + + corgi_ssp_lcdtg_send(PHACTRL_ADRS, adj); +} + +static int lcd_inited; + +static void lcdtg_hw_init(struct w100fb_par *par) +{ + if (!lcd_inited) { + int comadj; + + /* Initialize Internal Logic & Port */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, PICTRL_POWER_DOWN | PICTRL_INIOFF | PICTRL_INIT_STATE + | PICTRL_COM_SIGNAL_OFF | PICTRL_DAC_SIGNAL_OFF); + + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_COM_DCLK | POWER0_COM_DOUT | POWER0_DAC_OFF + | POWER0_COM_OFF | POWER0_VCC5_OFF); + + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_OFF | POWER1_VDD_OFF); + + /* VDD(+8V), SVSS(-4V) ON */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_OFF | POWER1_VDD_ON); + mdelay(3); + + /* DAC ON */ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_COM_DCLK | POWER0_COM_DOUT | POWER0_DAC_ON + | POWER0_COM_OFF | POWER0_VCC5_OFF); + + /* INIB = H, INI = L */ + /* PICTL[0] = H , PICTL[1] = PICTL[2] = PICTL[4] = L */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, PICTRL_INIT_STATE | PICTRL_COM_SIGNAL_OFF); + + /* Set Common Voltage */ + comadj = sharpsl_param.comadj; + if (comadj < 0) + comadj = DEFAULT_COMADJ; + lcdtg_set_common_voltage((POWER0_DAC_ON | POWER0_COM_OFF | POWER0_VCC5_OFF), comadj); + + /* VCC5 ON, DAC ON */ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_COM_DCLK | POWER0_COM_DOUT | POWER0_DAC_ON | + POWER0_COM_OFF | POWER0_VCC5_ON); + + /* GVSS(-8V) ON, VDD ON */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_ON | POWER1_VDD_ON); + mdelay(2); + + /* COM SIGNAL ON (PICTL[3] = L) */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, PICTRL_INIT_STATE); + + /* COM ON, DAC ON, VCC5_ON */ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_COM_DCLK | POWER0_COM_DOUT | POWER0_DAC_ON + | POWER0_COM_ON | POWER0_VCC5_ON); + + /* VW ON, GVSS ON, VDD ON */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_ON | POWER1_GVSS_ON | POWER1_VDD_ON); + + /* Signals output enable */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, 0); + + /* Set Phase Adjuct */ + lcdtg_set_phadadj(par); + + /* Initialize for Input Signals from ATI */ + corgi_ssp_lcdtg_send(POLCTRL_ADRS, POLCTRL_SYNC_POL_RISE | POLCTRL_EN_POL_RISE + | POLCTRL_DATA_POL_RISE | POLCTRL_SYNC_ACT_L | POLCTRL_EN_ACT_H); + udelay(1000); + + lcd_inited=1; + } else { + lcdtg_set_phadadj(par); + } + + switch(par->xres) { + case 480: + case 640: + /* Set Lcd Resolution (VGA) */ + corgi_ssp_lcdtg_send(RESCTL_ADRS, RESCTL_VGA); + break; + case 240: + case 320: + default: + /* Set Lcd Resolution (QVGA) */ + corgi_ssp_lcdtg_send(RESCTL_ADRS, RESCTL_QVGA); + break; + } +} + +static void lcdtg_suspend(struct w100fb_par *par) +{ + /* 60Hz x 2 frame = 16.7msec x 2 = 33.4 msec */ + mdelay(34); + + /* (1)VW OFF */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_ON | POWER1_VDD_ON); + + /* (2)COM OFF */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, PICTRL_COM_SIGNAL_OFF); + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_DAC_ON | POWER0_COM_OFF | POWER0_VCC5_ON); + + /* (3)Set Common Voltage Bias 0V */ + lcdtg_set_common_voltage(POWER0_DAC_ON | POWER0_COM_OFF | POWER0_VCC5_ON, 0); + + /* (4)GVSS OFF */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_OFF | POWER1_VDD_ON); + + /* (5)VCC5 OFF */ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_DAC_ON | POWER0_COM_OFF | POWER0_VCC5_OFF); + + /* (6)Set PDWN, INIOFF, DACOFF */ + corgi_ssp_lcdtg_send(PICTRL_ADRS, PICTRL_INIOFF | PICTRL_DAC_SIGNAL_OFF | + PICTRL_POWER_DOWN | PICTRL_COM_SIGNAL_OFF); + + /* (7)DAC OFF */ + corgi_ssp_lcdtg_send(POWERREG0_ADRS, POWER0_DAC_OFF | POWER0_COM_OFF | POWER0_VCC5_OFF); + + /* (8)VDD OFF */ + corgi_ssp_lcdtg_send(POWERREG1_ADRS, POWER1_VW_OFF | POWER1_GVSS_OFF | POWER1_VDD_OFF); + + lcd_inited = 0; +} + +static struct w100_tg_info corgi_lcdtg_info = { + .change=lcdtg_hw_init, + .suspend=lcdtg_suspend, + .resume=lcdtg_hw_init, +}; + +/* + * Corgi w100 Frame Buffer Device + */ + +static struct w100_mem_info corgi_fb_mem = { + .ext_cntl = 0x00040003, + .sdram_mode_reg = 0x00650021, + .ext_timing_cntl = 0x10002a4a, + .io_cntl = 0x7ff87012, + .size = 0x1fffff, +}; + +static struct w100_gen_regs corgi_fb_regs = { + .lcd_format = 0x00000003, + .lcdd_cntl1 = 0x01CC0000, + .lcdd_cntl2 = 0x0003FFFF, + .genlcd_cntl1 = 0x00FFFF0D, + .genlcd_cntl2 = 0x003F3003, + .genlcd_cntl3 = 0x000102aa, +}; + +static struct w100_gpio_regs corgi_fb_gpio = { + .init_data1 = 0x000000bf, + .init_data2 = 0x00000000, + .gpio_dir1 = 0x00000000, + .gpio_oe1 = 0x03c0feff, + .gpio_dir2 = 0x00000000, + .gpio_oe2 = 0x00000000, +}; + +static struct w100_mode corgi_fb_modes[] = { +{ + .xres = 480, + .yres = 640, + .left_margin = 0x56, + .right_margin = 0x55, + .upper_margin = 0x03, + .lower_margin = 0x00, + .crtc_ss = 0x82360056, + .crtc_ls = 0xA0280000, + .crtc_gs = 0x80280028, + .crtc_vpos_gs = 0x02830002, + .crtc_rev = 0x00400008, + .crtc_dclk = 0xA0000000, + .crtc_gclk = 0x8015010F, + .crtc_goe = 0x80100110, + .crtc_ps1_active = 0x41060010, + .pll_freq = 75, + .fast_pll_freq = 100, + .sysclk_src = CLK_SRC_PLL, + .sysclk_divider = 0, + .pixclk_src = CLK_SRC_PLL, + .pixclk_divider = 2, + .pixclk_divider_rotated = 6, +},{ + .xres = 240, + .yres = 320, + .left_margin = 0x27, + .right_margin = 0x2e, + .upper_margin = 0x01, + .lower_margin = 0x00, + .crtc_ss = 0x81170027, + .crtc_ls = 0xA0140000, + .crtc_gs = 0xC0140014, + .crtc_vpos_gs = 0x00010141, + .crtc_rev = 0x00400008, + .crtc_dclk = 0xA0000000, + .crtc_gclk = 0x8015010F, + .crtc_goe = 0x80100110, + .crtc_ps1_active = 0x41060010, + .pll_freq = 0, + .fast_pll_freq = 0, + .sysclk_src = CLK_SRC_XTAL, + .sysclk_divider = 0, + .pixclk_src = CLK_SRC_XTAL, + .pixclk_divider = 1, + .pixclk_divider_rotated = 1, +}, + +}; + +static struct w100fb_mach_info corgi_fb_info = { + .tg = &corgi_lcdtg_info, + .init_mode = INIT_MODE_ROTATED, + .mem = &corgi_fb_mem, + .regs = &corgi_fb_regs, + .modelist = &corgi_fb_modes[0], + .num_modes = 2, + .gpio = &corgi_fb_gpio, + .xtal_freq = 12500000, + .xtal_dbl = 0, +}; + +static struct resource corgi_fb_resources[] = { + [0] = { + .start = 0x08000000, + .end = 0x08ffffff, + .flags = IORESOURCE_MEM, + }, +}; + +struct platform_device corgifb_device = { + .name = "w100fb", + .id = -1, + .num_resources = ARRAY_SIZE(corgi_fb_resources), + .resource = corgi_fb_resources, + .dev = { + .platform_data = &corgi_fb_info, + .parent = &corgissp_device.dev, + }, + +}; diff --git a/arch/arm26/Makefile b/arch/arm26/Makefile index ada8985530a5..e9cb8ef4f3fb 100644 --- a/arch/arm26/Makefile +++ b/arch/arm26/Makefile @@ -17,10 +17,6 @@ ifeq ($(CONFIG_FRAME_POINTER),y) CFLAGS +=-fno-omit-frame-pointer -mno-sched-prolog endif -ifeq ($(CONFIG_DEBUG_INFO),y) -CFLAGS +=-g -endif - CFLAGS_BOOT :=-mapcs-26 -mcpu=arm3 -msoft-float -Uarm CFLAGS +=-mapcs-26 -mcpu=arm3 -msoft-float -Uarm AFLAGS +=-mapcs-26 -mcpu=arm3 -msoft-float diff --git a/arch/arm26/kernel/time.c b/arch/arm26/kernel/time.c index 549a6b2e177e..e66aedd02fad 100644 --- a/arch/arm26/kernel/time.c +++ b/arch/arm26/kernel/time.c @@ -114,7 +114,7 @@ static unsigned long next_rtc_update; */ static inline void do_set_rtc(void) { - if (time_status & STA_UNSYNC || set_rtc == NULL) + if (!ntp_synced() || set_rtc == NULL) return; //FIXME - timespec.tv_sec is a time_t not unsigned long @@ -189,10 +189,7 @@ int do_settimeofday(struct timespec *tv) xtime.tv_sec = tv->tv_sec; xtime.tv_nsec = tv->tv_nsec; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/cris/arch-v10/kernel/time.c b/arch/cris/arch-v10/kernel/time.c index 6b7b4e0802e3..dc3dfe9b4a1a 100644 --- a/arch/cris/arch-v10/kernel/time.c +++ b/arch/cris/arch-v10/kernel/time.c @@ -240,7 +240,7 @@ timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * The division here is not time critical since it will run once in * 11 minutes */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - (tick_nsec / 1000) / 2 && (xtime.tv_nsec / 1000) <= 500000 + (tick_nsec / 1000) / 2) { diff --git a/arch/cris/kernel/time.c b/arch/cris/kernel/time.c index fa2d4323da25..a2d99b4aedcd 100644 --- a/arch/cris/kernel/time.c +++ b/arch/cris/kernel/time.c @@ -114,10 +114,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/frv/kernel/time.c b/arch/frv/kernel/time.c index 075db6644694..8d6558b00e44 100644 --- a/arch/frv/kernel/time.c +++ b/arch/frv/kernel/time.c @@ -85,7 +85,7 @@ static irqreturn_t timer_interrupt(int irq, void *dummy, struct pt_regs * regs) * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2 @@ -216,10 +216,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/h8300/kernel/time.c b/arch/h8300/kernel/time.c index 8a600218334d..af8c5d2057dd 100644 --- a/arch/h8300/kernel/time.c +++ b/arch/h8300/kernel/time.c @@ -116,10 +116,7 @@ int do_settimeofday(struct timespec *tv) xtime.tv_sec = tv->tv_sec; xtime.tv_nsec = tv->tv_nsec; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 3b3b017e1c15..4b7de3e1e57b 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -1318,6 +1318,11 @@ config GENERIC_IRQ_PROBE bool default y +config GENERIC_PENDING_IRQ + bool + depends on GENERIC_HARDIRQS && SMP + default y + config X86_SMP bool depends on SMP && !X86_VOYAGER diff --git a/arch/i386/boot/setup.S b/arch/i386/boot/setup.S index 8cb420f40c58..ca668d9df164 100644 --- a/arch/i386/boot/setup.S +++ b/arch/i386/boot/setup.S @@ -82,7 +82,7 @@ start: # This is the setup header, and it must start at %cs:2 (old 0x9020:2) .ascii "HdrS" # header signature - .word 0x0203 # header version number (>= 0x0105) + .word 0x0204 # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) realmode_swtch: .word 0, 0 # default_switch, SETUPSEG start_sys_seg: .word SYSSEG diff --git a/arch/i386/boot/tools/build.c b/arch/i386/boot/tools/build.c index 6835f6d47c31..05798419a6a9 100644 --- a/arch/i386/boot/tools/build.c +++ b/arch/i386/boot/tools/build.c @@ -177,7 +177,9 @@ int main(int argc, char ** argv) die("Output: seek failed"); buf[0] = (sys_size & 0xff); buf[1] = ((sys_size >> 8) & 0xff); - if (write(1, buf, 2) != 2) + buf[2] = ((sys_size >> 16) & 0xff); + buf[3] = ((sys_size >> 24) & 0xff); + if (write(1, buf, 4) != 4) die("Write of image length failed"); return 0; /* Everything is OK */ diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index a3cdf894302b..58516e2ac172 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -6,32 +6,28 @@ #include <linux/bootmem.h> -struct dmi_header { - u8 type; - u8 length; - u16 handle; -}; - -#undef DMI_DEBUG - -#ifdef DMI_DEBUG -#define dmi_printk(x) printk x -#else -#define dmi_printk(x) -#endif - static char * __init dmi_string(struct dmi_header *dm, u8 s) { u8 *bp = ((u8 *) dm) + dm->length; + char *str = ""; - if (!s) - return ""; - s--; - while (s > 0 && *bp) { - bp += strlen(bp) + 1; + if (s) { s--; - } - return bp; + while (s > 0 && *bp) { + bp += strlen(bp) + 1; + s--; + } + + if (*bp != 0) { + str = alloc_bootmem(strlen(bp) + 1); + if (str != NULL) + strcpy(str, bp); + else + printk(KERN_ERR "dmi_string: out of memory.\n"); + } + } + + return str; } /* @@ -84,69 +80,76 @@ static int __init dmi_checksum(u8 *buf) return sum == 0; } -static int __init dmi_iterate(void (*decode)(struct dmi_header *)) +static char *dmi_ident[DMI_STRING_MAX]; +static LIST_HEAD(dmi_devices); + +/* + * Save a DMI string + */ +static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) { - u8 buf[15]; - char __iomem *p, *q; + char *p, *d = (char*) dm; - /* - * no iounmap() for that ioremap(); it would be a no-op, but it's - * so early in setup that sucker gets confused into doing what - * it shouldn't if we actually call it. - */ - p = ioremap(0xF0000, 0x10000); + if (dmi_ident[slot]) + return; + + p = dmi_string(dm, d[string]); if (p == NULL) - return -1; + return; - for (q = p; q < p + 0x10000; q += 16) { - memcpy_fromio(buf, q, 15); - if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { - u16 num = (buf[13] << 8) | buf[12]; - u16 len = (buf[7] << 8) | buf[6]; - u32 base = (buf[11] << 24) | (buf[10] << 16) | - (buf[9] << 8) | buf[8]; + dmi_ident[slot] = p; +} - /* - * DMI version 0.0 means that the real version is taken from - * the SMBIOS version, which we don't know at this point. - */ - if (buf[14] != 0) - printk(KERN_INFO "DMI %d.%d present.\n", - buf[14] >> 4, buf[14] & 0xF); - else - printk(KERN_INFO "DMI present.\n"); +static void __init dmi_save_devices(struct dmi_header *dm) +{ + int i, count = (dm->length - sizeof(struct dmi_header)) / 2; + struct dmi_device *dev; + + for (i = 0; i < count; i++) { + char *d = ((char *) dm) + (i * 2); - dmi_printk((KERN_INFO "%d structures occupying %d bytes.\n", - num, len)); - dmi_printk((KERN_INFO "DMI table at 0x%08X.\n", base)); + /* Skip disabled device */ + if ((*d & 0x80) == 0) + continue; - if (dmi_table(base,len, num, decode) == 0) - return 0; + dev = alloc_bootmem(sizeof(*dev)); + if (!dev) { + printk(KERN_ERR "dmi_save_devices: out of memory.\n"); + break; } + + dev->type = *d++ & 0x7f; + dev->name = dmi_string(dm, *d); + dev->device_data = NULL; + + list_add(&dev->list, &dmi_devices); } - return -1; } -static char *dmi_ident[DMI_STRING_MAX]; - -/* - * Save a DMI string - */ -static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) +static void __init dmi_save_ipmi_device(struct dmi_header *dm) { - char *d = (char*)dm; - char *p = dmi_string(dm, d[string]); + struct dmi_device *dev; + void * data; - if (p == NULL || *p == 0) + data = alloc_bootmem(dm->length); + if (data == NULL) { + printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); return; - if (dmi_ident[slot]) + } + + memcpy(data, dm, dm->length); + + dev = alloc_bootmem(sizeof(*dev)); + if (!dev) { + printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); return; + } - dmi_ident[slot] = alloc_bootmem(strlen(p) + 1); - if(dmi_ident[slot]) - strcpy(dmi_ident[slot], p); - else - printk(KERN_ERR "dmi_save_ident: out of memory.\n"); + dev->type = DMI_DEV_TYPE_IPMI; + dev->name = "IPMI controller"; + dev->device_data = data; + + list_add(&dev->list, &dmi_devices); } /* @@ -156,42 +159,69 @@ static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) */ static void __init dmi_decode(struct dmi_header *dm) { - u8 *data __attribute__((__unused__)) = (u8 *)dm; - switch(dm->type) { - case 0: - dmi_printk(("BIOS Vendor: %s\n", dmi_string(dm, data[4]))); + case 0: /* BIOS Information */ dmi_save_ident(dm, DMI_BIOS_VENDOR, 4); - dmi_printk(("BIOS Version: %s\n", dmi_string(dm, data[5]))); dmi_save_ident(dm, DMI_BIOS_VERSION, 5); - dmi_printk(("BIOS Release: %s\n", dmi_string(dm, data[8]))); dmi_save_ident(dm, DMI_BIOS_DATE, 8); break; - case 1: - dmi_printk(("System Vendor: %s\n", dmi_string(dm, data[4]))); + case 1: /* System Information */ dmi_save_ident(dm, DMI_SYS_VENDOR, 4); - dmi_printk(("Product Name: %s\n", dmi_string(dm, data[5]))); dmi_save_ident(dm, DMI_PRODUCT_NAME, 5); - dmi_printk(("Version: %s\n", dmi_string(dm, data[6]))); dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); - dmi_printk(("Serial Number: %s\n", dmi_string(dm, data[7]))); dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); break; - case 2: - dmi_printk(("Board Vendor: %s\n", dmi_string(dm, data[4]))); + case 2: /* Base Board Information */ dmi_save_ident(dm, DMI_BOARD_VENDOR, 4); - dmi_printk(("Board Name: %s\n", dmi_string(dm, data[5]))); dmi_save_ident(dm, DMI_BOARD_NAME, 5); - dmi_printk(("Board Version: %s\n", dmi_string(dm, data[6]))); dmi_save_ident(dm, DMI_BOARD_VERSION, 6); break; + case 10: /* Onboard Devices Information */ + dmi_save_devices(dm); + break; + case 38: /* IPMI Device Information */ + dmi_save_ipmi_device(dm); } } void __init dmi_scan_machine(void) { - if (dmi_iterate(dmi_decode)) - printk(KERN_INFO "DMI not present.\n"); + u8 buf[15]; + char __iomem *p, *q; + + /* + * no iounmap() for that ioremap(); it would be a no-op, but it's + * so early in setup that sucker gets confused into doing what + * it shouldn't if we actually call it. + */ + p = ioremap(0xF0000, 0x10000); + if (p == NULL) + goto out; + + for (q = p; q < p + 0x10000; q += 16) { + memcpy_fromio(buf, q, 15); + if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { + u16 num = (buf[13] << 8) | buf[12]; + u16 len = (buf[7] << 8) | buf[6]; + u32 base = (buf[11] << 24) | (buf[10] << 16) | + (buf[9] << 8) | buf[8]; + + /* + * DMI version 0.0 means that the real version is taken from + * the SMBIOS version, which we don't know at this point. + */ + if (buf[14] != 0) + printk(KERN_INFO "DMI %d.%d present.\n", + buf[14] >> 4, buf[14] & 0xF); + else + printk(KERN_INFO "DMI present.\n"); + + if (dmi_table(base,len, num, dmi_decode) == 0) + return; + } + } + +out: printk(KERN_INFO "DMI not present.\n"); } @@ -218,9 +248,9 @@ int dmi_check_system(struct dmi_system_id *list) /* No match */ goto fail; } + count++; if (d->callback && d->callback(d)) break; - count++; fail: d++; } @@ -240,3 +270,32 @@ char *dmi_get_system_info(int field) return dmi_ident[field]; } EXPORT_SYMBOL(dmi_get_system_info); + +/** + * dmi_find_device - find onboard device by type/name + * @type: device type or %DMI_DEV_TYPE_ANY to match all device types + * @desc: device name string or %NULL to match all + * @from: previous device found in search, or %NULL for new search. + * + * Iterates through the list of known onboard devices. If a device is + * found with a matching @vendor and @device, a pointer to its device + * structure is returned. Otherwise, %NULL is returned. + * A new search is initiated by passing %NULL to the @from argument. + * If @from is not %NULL, searches continue from next device. + */ +struct dmi_device * dmi_find_device(int type, const char *name, + struct dmi_device *from) +{ + struct list_head *d, *head = from ? &from->list : &dmi_devices; + + for(d = head->next; d != &dmi_devices; d = d->next) { + struct dmi_device *dev = list_entry(d, struct dmi_device, list); + + if (((type == DMI_DEV_TYPE_ANY) || (dev->type == type)) && + ((name == NULL) || (strcmp(dev->name, name) == 0))) + return dev; + } + + return NULL; +} +EXPORT_SYMBOL(dmi_find_device); diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index abb909793efc..3aad03839660 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -507,7 +507,7 @@ label: \ pushl $__KERNEL_CS; \ pushl $sysenter_past_esp -ENTRY(debug) +KPROBE_ENTRY(debug) cmpl $sysenter_entry,(%esp) jne debug_stack_correct FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn) @@ -518,7 +518,7 @@ debug_stack_correct: movl %esp,%eax # pt_regs pointer call do_debug jmp ret_from_exception - + .previous .text /* * NMI is doubly nasty. It can happen _while_ we're handling * a debug fault, and the debug fault hasn't yet been able to @@ -591,13 +591,14 @@ nmi_16bit_stack: .long 1b,iret_exc .previous -ENTRY(int3) +KPROBE_ENTRY(int3) pushl $-1 # mark this as an int SAVE_ALL xorl %edx,%edx # zero error code movl %esp,%eax # pt_regs pointer call do_int3 jmp ret_from_exception + .previous .text ENTRY(overflow) pushl $0 @@ -631,17 +632,19 @@ ENTRY(stack_segment) pushl $do_stack_segment jmp error_code -ENTRY(general_protection) +KPROBE_ENTRY(general_protection) pushl $do_general_protection jmp error_code + .previous .text ENTRY(alignment_check) pushl $do_alignment_check jmp error_code -ENTRY(page_fault) +KPROBE_ENTRY(page_fault) pushl $do_page_fault jmp error_code + .previous .text #ifdef CONFIG_X86_MCE ENTRY(machine_check) diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 6578f40bd501..0e727e6da5c9 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -33,6 +33,7 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/sysdev.h> + #include <asm/io.h> #include <asm/smp.h> #include <asm/desc.h> @@ -77,7 +78,7 @@ static struct irq_pin_list { int apic, pin, next; } irq_2_pin[PIN_MAP_SIZE]; -int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; +int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1}; #ifdef CONFIG_PCI_MSI #define vector_to_irq(vector) \ (platform_legacy_irq(vector) ? vector : vector_irq[vector]) @@ -222,13 +223,21 @@ static void clear_IO_APIC (void) clear_IO_APIC_pin(apic, pin); } +#ifdef CONFIG_SMP static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) { unsigned long flags; int pin; struct irq_pin_list *entry = irq_2_pin + irq; unsigned int apicid_value; + cpumask_t tmp; + cpus_and(tmp, cpumask, cpu_online_map); + if (cpus_empty(tmp)) + tmp = TARGET_CPUS; + + cpus_and(cpumask, tmp, CPU_MASK_ALL); + apicid_value = cpu_mask_to_apicid(cpumask); /* Prepare to do the io_apic_write */ apicid_value = apicid_value << 24; @@ -242,6 +251,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) break; entry = irq_2_pin + entry->next; } + set_irq_info(irq, cpumask); spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -259,7 +269,6 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) # define Dprintk(x...) # endif -cpumask_t __cacheline_aligned pending_irq_balance_cpumask[NR_IRQS]; #define IRQBALANCE_CHECK_ARCH -999 static int irqbalance_disabled = IRQBALANCE_CHECK_ARCH; @@ -328,12 +337,7 @@ static inline void balance_irq(int cpu, int irq) cpus_and(allowed_mask, cpu_online_map, irq_affinity[irq]); new_cpu = move(cpu, allowed_mask, now, 1); if (cpu != new_cpu) { - irq_desc_t *desc = irq_desc + irq; - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - pending_irq_balance_cpumask[irq] = cpumask_of_cpu(new_cpu); - spin_unlock_irqrestore(&desc->lock, flags); + set_pending_irq(irq, cpumask_of_cpu(new_cpu)); } } @@ -528,16 +532,12 @@ tryanotherirq: cpus_and(tmp, target_cpu_mask, allowed_mask); if (!cpus_empty(tmp)) { - irq_desc_t *desc = irq_desc + selected_irq; - unsigned long flags; Dprintk("irq = %d moved to cpu = %d\n", selected_irq, min_loaded); /* mark for change destination */ - spin_lock_irqsave(&desc->lock, flags); - pending_irq_balance_cpumask[selected_irq] = - cpumask_of_cpu(min_loaded); - spin_unlock_irqrestore(&desc->lock, flags); + set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded)); + /* Since we made a change, come back sooner to * check for more variation. */ @@ -568,7 +568,8 @@ static int balanced_irq(void *unused) /* push everything to CPU 0 to give us a starting point. */ for (i = 0 ; i < NR_IRQS ; i++) { - pending_irq_balance_cpumask[i] = cpumask_of_cpu(0); + pending_irq_cpumask[i] = cpumask_of_cpu(0); + set_pending_irq(i, cpumask_of_cpu(0)); } for ( ; ; ) { @@ -647,20 +648,9 @@ int __init irqbalance_disable(char *str) __setup("noirqbalance", irqbalance_disable); -static inline void move_irq(int irq) -{ - /* note - we hold the desc->lock */ - if (unlikely(!cpus_empty(pending_irq_balance_cpumask[irq]))) { - set_ioapic_affinity_irq(irq, pending_irq_balance_cpumask[irq]); - cpus_clear(pending_irq_balance_cpumask[irq]); - } -} - late_initcall(balanced_irq_init); - -#else /* !CONFIG_IRQBALANCE */ -static inline void move_irq(int irq) { } #endif /* CONFIG_IRQBALANCE */ +#endif /* CONFIG_SMP */ #ifndef CONFIG_SMP void fastcall send_IPI_self(int vector) @@ -820,6 +810,7 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); * we need to reprogram the ioredtbls to cater for the cpus which have come online * so mask in all cases should simply be TARGET_CPUS */ +#ifdef CONFIG_SMP void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; @@ -838,6 +829,7 @@ void __init setup_ioapic_dest(void) } } +#endif /* * EISA Edge/Level control register, ELCR @@ -1127,7 +1119,7 @@ static inline int IO_APIC_irq_trigger(int irq) } /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ -u8 irq_vector[NR_IRQ_VECTORS] = { FIRST_DEVICE_VECTOR , 0 }; +u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 }; int assign_irq_vector(int irq) { @@ -1249,6 +1241,7 @@ static void __init setup_IO_APIC_irqs(void) spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); + set_native_irq_info(irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); } } @@ -1944,6 +1937,7 @@ static void ack_edge_ioapic_vector(unsigned int vector) { int irq = vector_to_irq(vector); + move_irq(vector); ack_edge_ioapic_irq(irq); } @@ -1958,6 +1952,7 @@ static void end_level_ioapic_vector (unsigned int vector) { int irq = vector_to_irq(vector); + move_irq(vector); end_level_ioapic_irq(irq); } @@ -1975,14 +1970,17 @@ static void unmask_IO_APIC_vector (unsigned int vector) unmask_IO_APIC_irq(irq); } +#ifdef CONFIG_SMP static void set_ioapic_affinity_vector (unsigned int vector, cpumask_t cpu_mask) { int irq = vector_to_irq(vector); + set_native_irq_info(vector, cpu_mask); set_ioapic_affinity_irq(irq, cpu_mask); } #endif +#endif /* * Level and edge triggered IO-APIC interrupts need different handling, @@ -1992,7 +1990,7 @@ static void set_ioapic_affinity_vector (unsigned int vector, * edge-triggered handler, without risking IRQ storms and other ugly * races. */ -static struct hw_interrupt_type ioapic_edge_type = { +static struct hw_interrupt_type ioapic_edge_type __read_mostly = { .typename = "IO-APIC-edge", .startup = startup_edge_ioapic, .shutdown = shutdown_edge_ioapic, @@ -2000,10 +1998,12 @@ static struct hw_interrupt_type ioapic_edge_type = { .disable = disable_edge_ioapic, .ack = ack_edge_ioapic, .end = end_edge_ioapic, +#ifdef CONFIG_SMP .set_affinity = set_ioapic_affinity, +#endif }; -static struct hw_interrupt_type ioapic_level_type = { +static struct hw_interrupt_type ioapic_level_type __read_mostly = { .typename = "IO-APIC-level", .startup = startup_level_ioapic, .shutdown = shutdown_level_ioapic, @@ -2011,7 +2011,9 @@ static struct hw_interrupt_type ioapic_level_type = { .disable = disable_level_ioapic, .ack = mask_and_ack_level_ioapic, .end = end_level_ioapic, +#ifdef CONFIG_SMP .set_affinity = set_ioapic_affinity, +#endif }; static inline void init_IO_APIC_traps(void) @@ -2074,7 +2076,7 @@ static void ack_lapic_irq (unsigned int irq) static void end_lapic_irq (unsigned int i) { /* nothing */ } -static struct hw_interrupt_type lapic_irq_type = { +static struct hw_interrupt_type lapic_irq_type __read_mostly = { .typename = "local-APIC-edge", .startup = NULL, /* startup_irq() not used for IRQ0 */ .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ @@ -2569,6 +2571,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); + set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); return 0; diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index a6d8c45961d3..6345b430b105 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -62,32 +62,32 @@ static inline int is_IF_modifier(kprobe_opcode_t opcode) return 0; } -int arch_prepare_kprobe(struct kprobe *p) +int __kprobes arch_prepare_kprobe(struct kprobe *p) { return 0; } -void arch_copy_kprobe(struct kprobe *p) +void __kprobes arch_copy_kprobe(struct kprobe *p) { memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; } -void arch_arm_kprobe(struct kprobe *p) +void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_disarm_kprobe(struct kprobe *p) +void __kprobes arch_disarm_kprobe(struct kprobe *p) { *p->addr = p->opcode; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_remove_kprobe(struct kprobe *p) +void __kprobes arch_remove_kprobe(struct kprobe *p) { } @@ -127,7 +127,8 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->eip = (unsigned long)&p->ainsn.insn; } -void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) +void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) { unsigned long *sara = (unsigned long *)®s->esp; struct kretprobe_instance *ri; @@ -150,7 +151,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled thorough out this function. */ -static int kprobe_handler(struct pt_regs *regs) +static int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; int ret = 0; @@ -176,7 +177,8 @@ static int kprobe_handler(struct pt_regs *regs) Disarm the probe we just hit, and ignore it. */ p = get_kprobe(addr); if (p) { - if (kprobe_status == KPROBE_HIT_SS) { + if (kprobe_status == KPROBE_HIT_SS && + *p->ainsn.insn == BREAKPOINT_INSTRUCTION) { regs->eflags &= ~TF_MASK; regs->eflags |= kprobe_saved_eflags; unlock_kprobes(); @@ -220,7 +222,10 @@ static int kprobe_handler(struct pt_regs *regs) * either a probepoint or a debugger breakpoint * at this address. In either case, no further * handling of this interrupt is appropriate. + * Back up over the (now missing) int3 and run + * the original instruction. */ + regs->eip -= sizeof(kprobe_opcode_t); ret = 1; } /* Not one of ours: let kernel handle it */ @@ -259,7 +264,7 @@ no_kprobe: /* * Called when we hit the probe point at kretprobe_trampoline */ -int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -338,7 +343,7 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. */ -static void resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { unsigned long *tos = (unsigned long *)®s->esp; unsigned long next_eip = 0; @@ -444,8 +449,8 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine to for handling exceptions. */ -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; switch (val) { @@ -473,7 +478,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, return NOTIFY_DONE; } -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr; @@ -495,7 +500,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -void jprobe_return(void) +void __kprobes jprobe_return(void) { preempt_enable_no_resched(); asm volatile (" xchgl %%ebx,%%esp \n" @@ -506,7 +511,7 @@ void jprobe_return(void) (jprobe_saved_esp):"memory"); } -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { u8 *addr = (u8 *) (regs->eip - 1); unsigned long stack_addr = (unsigned long)jprobe_saved_esp; diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 8bbdbda07a2d..0178457db721 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -478,6 +478,11 @@ void touch_nmi_watchdog (void) */ for (i = 0; i < NR_CPUS; i++) alert_counter[i] = 0; + + /* + * Tickle the softlockup detector too: + */ + touch_softlockup_watchdog(); } extern void die_nmi(struct pt_regs *, const char *msg); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 294bcca985ab..e29fd5aeaf8e 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -82,7 +82,7 @@ EXPORT_SYMBOL(efi_enabled); /* cpu data as detected by the assembly code in head.S */ struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; /* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; +struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; EXPORT_SYMBOL(boot_cpu_data); unsigned long mmu_cr4_features; diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index 6f794a78ee1e..eefea7c55008 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -194,10 +194,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; @@ -252,8 +249,7 @@ EXPORT_SYMBOL(profile_pc); * timer_interrupt() needs to keep up the real-time clock, * as well as call the "do_timer()" routine every clocktick */ -static inline void do_timer_interrupt(int irq, void *dev_id, - struct pt_regs *regs) +static inline void do_timer_interrupt(int irq, struct pt_regs *regs) { #ifdef CONFIG_X86_IO_APIC if (timer_ack) { @@ -307,7 +303,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) cur_timer->mark_offset(); - do_timer_interrupt(irq, NULL, regs); + do_timer_interrupt(irq, regs); write_sequnlock(&xtime_lock); return IRQ_HANDLED; @@ -348,7 +344,7 @@ static void sync_cmos_clock(unsigned long dummy) * This code is run on a timer. If the clock is set, that timer * may not expire at the correct time. Thus, we adjust... */ - if ((time_status & STA_UNSYNC) != 0) + if (!ntp_synced()) /* * Not synced, exit, do not restart a timer (if one is * running, let it run out). @@ -422,6 +418,7 @@ static int timer_resume(struct sys_device *dev) last_timer->resume(); cur_timer = last_timer; last_timer = NULL; + touch_softlockup_watchdog(); return 0; } diff --git a/arch/i386/kernel/timers/timer_hpet.c b/arch/i386/kernel/timers/timer_hpet.c index 001de97c9e4a..d973a8b681fd 100644 --- a/arch/i386/kernel/timers/timer_hpet.c +++ b/arch/i386/kernel/timers/timer_hpet.c @@ -18,8 +18,8 @@ #include "mach_timer.h" #include <asm/hpet.h> -static unsigned long __read_mostly hpet_usec_quotient; /* convert hpet clks to usec */ -static unsigned long tsc_hpet_quotient; /* convert tsc to hpet clks */ +static unsigned long hpet_usec_quotient __read_mostly; /* convert hpet clks to usec */ +static unsigned long tsc_hpet_quotient __read_mostly; /* convert tsc to hpet clks */ static unsigned long hpet_last; /* hpet counter value at last tick*/ static unsigned long last_tsc_low; /* lsb 32 bits of Time Stamp Counter */ static unsigned long last_tsc_high; /* msb 32 bits of Time Stamp Counter */ diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 54629bb5893a..09a58cb6daa7 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -363,8 +363,9 @@ static inline void die_if_kernel(const char * str, struct pt_regs * regs, long e die(str, regs, err); } -static void do_trap(int trapnr, int signr, char *str, int vm86, - struct pt_regs * regs, long error_code, siginfo_t *info) +static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86, + struct pt_regs * regs, long error_code, + siginfo_t *info) { struct task_struct *tsk = current; tsk->thread.error_code = error_code; @@ -460,7 +461,8 @@ DO_ERROR(12, SIGBUS, "stack segment", stack_segment) DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0) -fastcall void do_general_protection(struct pt_regs * regs, long error_code) +fastcall void __kprobes do_general_protection(struct pt_regs * regs, + long error_code) { int cpu = get_cpu(); struct tss_struct *tss = &per_cpu(init_tss, cpu); @@ -657,7 +659,7 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code) ++nmi_count(cpu); - if (!nmi_callback(regs, cpu)) + if (!rcu_dereference(nmi_callback)(regs, cpu)) default_do_nmi(regs); nmi_exit(); @@ -665,7 +667,7 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code) void set_nmi_callback(nmi_callback_t callback) { - nmi_callback = callback; + rcu_assign_pointer(nmi_callback, callback); } EXPORT_SYMBOL_GPL(set_nmi_callback); @@ -676,7 +678,7 @@ void unset_nmi_callback(void) EXPORT_SYMBOL_GPL(unset_nmi_callback); #ifdef CONFIG_KPROBES -fastcall void do_int3(struct pt_regs *regs, long error_code) +fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code) { if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) @@ -710,7 +712,7 @@ fastcall void do_int3(struct pt_regs *regs, long error_code) * find every occurrence of the TF bit that could be saved away even * by user code) */ -fastcall void do_debug(struct pt_regs * regs, long error_code) +fastcall void __kprobes do_debug(struct pt_regs * regs, long error_code) { unsigned int condition; struct task_struct *tsk = current; diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S index 761972f8cb6c..13b9c62cbbb4 100644 --- a/arch/i386/kernel/vmlinux.lds.S +++ b/arch/i386/kernel/vmlinux.lds.S @@ -22,6 +22,7 @@ SECTIONS *(.text) SCHED_TEXT LOCK_TEXT + KPROBES_TEXT *(.fixup) *(.gnu.warning) } = 0x9090 diff --git a/arch/i386/mach-default/topology.c b/arch/i386/mach-default/topology.c index 23395fff35d1..b64314069e78 100644 --- a/arch/i386/mach-default/topology.c +++ b/arch/i386/mach-default/topology.c @@ -76,7 +76,7 @@ static int __init topology_init(void) for_each_online_node(i) arch_register_node(i); - for_each_cpu(i) + for_each_present_cpu(i) arch_register_cpu(i); return 0; } @@ -87,7 +87,7 @@ static int __init topology_init(void) { int i; - for_each_cpu(i) + for_each_present_cpu(i) arch_register_cpu(i); return 0; } diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 6711ce3f6916..244d8ec66be2 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -37,7 +37,7 @@ #include <asm/mmzone.h> #include <bios_ebda.h> -struct pglist_data *node_data[MAX_NUMNODES]; +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); bootmem_data_t node0_bdata; @@ -49,8 +49,8 @@ bootmem_data_t node0_bdata; * 2) node_start_pfn - the starting page frame number for a node * 3) node_end_pfn - the ending page fram number for a node */ -unsigned long node_start_pfn[MAX_NUMNODES]; -unsigned long node_end_pfn[MAX_NUMNODES]; +unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly; +unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly; #ifdef CONFIG_DISCONTIGMEM @@ -66,7 +66,7 @@ unsigned long node_end_pfn[MAX_NUMNODES]; * physnode_map[4-7] = 1; * physnode_map[8- ] = -1; */ -s8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1}; +s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1}; EXPORT_SYMBOL(physnode_map); void memory_present(int nid, unsigned long start, unsigned long end) diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c index 411b8500ad1b..9edd4485b91e 100644 --- a/arch/i386/mm/fault.c +++ b/arch/i386/mm/fault.c @@ -21,6 +21,7 @@ #include <linux/vt_kern.h> /* For unblank_screen() */ #include <linux/highmem.h> #include <linux/module.h> +#include <linux/kprobes.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -223,7 +224,8 @@ fastcall void do_invalid_op(struct pt_regs *, unsigned long); * bit 1 == 0 means read, 1 means write * bit 2 == 0 means kernel, 1 means user-mode */ -fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) +fastcall void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long error_code) { struct task_struct *tsk; struct mm_struct *mm; diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 9edfc058b894..2ebaf75f732e 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -393,7 +393,7 @@ void zap_low_mappings (void) } static int disable_nx __initdata = 0; -u64 __supported_pte_mask = ~_PAGE_NX; +u64 __supported_pte_mask __read_mostly = ~_PAGE_NX; /* * noexec = on|off diff --git a/arch/i386/oprofile/init.c b/arch/i386/oprofile/init.c index c90332de582b..5341d481d92f 100644 --- a/arch/i386/oprofile/init.c +++ b/arch/i386/oprofile/init.c @@ -15,9 +15,9 @@ * with the NMI mode driver. */ -extern int nmi_init(struct oprofile_operations * ops); -extern int nmi_timer_init(struct oprofile_operations * ops); -extern void nmi_exit(void); +extern int op_nmi_init(struct oprofile_operations * ops); +extern int op_nmi_timer_init(struct oprofile_operations * ops); +extern void op_nmi_exit(void); extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth); @@ -28,11 +28,11 @@ int __init oprofile_arch_init(struct oprofile_operations * ops) ret = -ENODEV; #ifdef CONFIG_X86_LOCAL_APIC - ret = nmi_init(ops); + ret = op_nmi_init(ops); #endif #ifdef CONFIG_X86_IO_APIC if (ret < 0) - ret = nmi_timer_init(ops); + ret = op_nmi_timer_init(ops); #endif ops->backtrace = x86_backtrace; @@ -43,6 +43,6 @@ int __init oprofile_arch_init(struct oprofile_operations * ops) void oprofile_arch_exit(void) { #ifdef CONFIG_X86_LOCAL_APIC - nmi_exit(); + op_nmi_exit(); #endif } diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c index 255e4702d185..0493e8b8ec49 100644 --- a/arch/i386/oprofile/nmi_int.c +++ b/arch/i386/oprofile/nmi_int.c @@ -355,7 +355,7 @@ static int __init ppro_init(char ** cpu_type) /* in order to get driverfs right */ static int using_nmi; -int __init nmi_init(struct oprofile_operations *ops) +int __init op_nmi_init(struct oprofile_operations *ops) { __u8 vendor = boot_cpu_data.x86_vendor; __u8 family = boot_cpu_data.x86; @@ -420,7 +420,7 @@ int __init nmi_init(struct oprofile_operations *ops) } -void nmi_exit(void) +void op_nmi_exit(void) { if (using_nmi) exit_driverfs(); diff --git a/arch/i386/oprofile/nmi_timer_int.c b/arch/i386/oprofile/nmi_timer_int.c index c58d0c14f274..ad93cdd55d63 100644 --- a/arch/i386/oprofile/nmi_timer_int.c +++ b/arch/i386/oprofile/nmi_timer_int.c @@ -40,7 +40,7 @@ static void timer_stop(void) } -int __init nmi_timer_init(struct oprofile_operations * ops) +int __init op_nmi_timer_init(struct oprofile_operations * ops) { extern int nmi_active; diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 3deced637f07..17b5dbf8c311 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -434,6 +434,11 @@ config GENERIC_IRQ_PROBE bool default y +config GENERIC_PENDING_IRQ + bool + depends on GENERIC_HARDIRQS && SMP + default y + source "arch/ia64/hp/sim/Kconfig" source "arch/ia64/oprofile/Kconfig" diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index 829a6d80711c..0708edb06cc4 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -215,7 +215,7 @@ ia32_syscall_table: data8 sys32_fork data8 sys_read data8 sys_write - data8 sys32_open /* 5 */ + data8 compat_sys_open /* 5 */ data8 sys_close data8 sys32_waitpid data8 sys_creat diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index c1e20d65dd6c..e29a8a55486a 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -2359,37 +2359,6 @@ sys32_brk (unsigned int brk) return ret; } -/* - * Exactly like fs/open.c:sys_open(), except that it doesn't set the O_LARGEFILE flag. - */ -asmlinkage long -sys32_open (const char __user * filename, int flags, int mode) -{ - char * tmp; - int fd, error; - - tmp = getname(filename); - fd = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - fd = get_unused_fd(); - if (fd >= 0) { - struct file *f = filp_open(tmp, flags, mode); - error = PTR_ERR(f); - if (IS_ERR(f)) - goto out_error; - fd_install(fd, f); - } -out: - putname(tmp); - } - return fd; - -out_error: - put_unused_fd(fd); - fd = error; - goto out; -} - /* Structure for ia32 emulation on ia64 */ struct epoll_event32 { diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index b242594be55b..307514f7a282 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -16,7 +16,7 @@ obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o obj-$(CONFIG_IA64_PALINFO) += palinfo.o obj-$(CONFIG_IOSAPIC) += iosapic.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_SMP) += smp.o smpboot.o domain.o +obj-$(CONFIG_SMP) += smp.o smpboot.o obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o obj-$(CONFIG_IA64_CYCLONE) += cyclone.o diff --git a/arch/ia64/kernel/domain.c b/arch/ia64/kernel/domain.c deleted file mode 100644 index bbb8efe126b7..000000000000 --- a/arch/ia64/kernel/domain.c +++ /dev/null @@ -1,396 +0,0 @@ -/* - * arch/ia64/kernel/domain.c - * Architecture specific sched-domains builder. - * - * Copyright (C) 2004 Jesse Barnes - * Copyright (C) 2004 Silicon Graphics, Inc. - */ - -#include <linux/sched.h> -#include <linux/percpu.h> -#include <linux/slab.h> -#include <linux/cpumask.h> -#include <linux/init.h> -#include <linux/topology.h> -#include <linux/nodemask.h> - -#define SD_NODES_PER_DOMAIN 16 - -#ifdef CONFIG_NUMA -/** - * find_next_best_node - find the next node to include in a sched_domain - * @node: node whose sched_domain we're building - * @used_nodes: nodes already in the sched_domain - * - * Find the next node to include in a given scheduling domain. Simply - * finds the closest node not already in the @used_nodes map. - * - * Should use nodemask_t. - */ -static int find_next_best_node(int node, unsigned long *used_nodes) -{ - int i, n, val, min_val, best_node = 0; - - min_val = INT_MAX; - - for (i = 0; i < MAX_NUMNODES; i++) { - /* Start at @node */ - n = (node + i) % MAX_NUMNODES; - - if (!nr_cpus_node(n)) - continue; - - /* Skip already used nodes */ - if (test_bit(n, used_nodes)) - continue; - - /* Simple min distance search */ - val = node_distance(node, n); - - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - set_bit(best_node, used_nodes); - return best_node; -} - -/** - * sched_domain_node_span - get a cpumask for a node's sched_domain - * @node: node whose cpumask we're constructing - * @size: number of nodes to include in this span - * - * Given a node, construct a good cpumask for its sched_domain to span. It - * should be one that prevents unnecessary balancing, but also spreads tasks - * out optimally. - */ -static cpumask_t sched_domain_node_span(int node) -{ - int i; - cpumask_t span, nodemask; - DECLARE_BITMAP(used_nodes, MAX_NUMNODES); - - cpus_clear(span); - bitmap_zero(used_nodes, MAX_NUMNODES); - - nodemask = node_to_cpumask(node); - cpus_or(span, span, nodemask); - set_bit(node, used_nodes); - - for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, used_nodes); - nodemask = node_to_cpumask(next_node); - cpus_or(span, span, nodemask); - } - - return span; -} -#endif - -/* - * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we - * can switch it on easily if needed. - */ -#ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct sched_domain, cpu_domains); -static struct sched_group sched_group_cpus[NR_CPUS]; -static int cpu_to_cpu_group(int cpu) -{ - return cpu; -} -#endif - -static DEFINE_PER_CPU(struct sched_domain, phys_domains); -static struct sched_group sched_group_phys[NR_CPUS]; -static int cpu_to_phys_group(int cpu) -{ -#ifdef CONFIG_SCHED_SMT - return first_cpu(cpu_sibling_map[cpu]); -#else - return cpu; -#endif -} - -#ifdef CONFIG_NUMA -/* - * The init_sched_build_groups can't handle what we want to do with node - * groups, so roll our own. Now each node has its own list of groups which - * gets dynamically allocated. - */ -static DEFINE_PER_CPU(struct sched_domain, node_domains); -static struct sched_group *sched_group_nodes[MAX_NUMNODES]; - -static DEFINE_PER_CPU(struct sched_domain, allnodes_domains); -static struct sched_group sched_group_allnodes[MAX_NUMNODES]; - -static int cpu_to_allnodes_group(int cpu) -{ - return cpu_to_node(cpu); -} -#endif - -/* - * Build sched domains for a given set of cpus and attach the sched domains - * to the individual cpus - */ -void build_sched_domains(const cpumask_t *cpu_map) -{ - int i; - - /* - * Set up domains for cpus specified by the cpu_map. - */ - for_each_cpu_mask(i, *cpu_map) { - int group; - struct sched_domain *sd = NULL, *p; - cpumask_t nodemask = node_to_cpumask(cpu_to_node(i)); - - cpus_and(nodemask, nodemask, *cpu_map); - -#ifdef CONFIG_NUMA - if (num_online_cpus() - > SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) { - sd = &per_cpu(allnodes_domains, i); - *sd = SD_ALLNODES_INIT; - sd->span = *cpu_map; - group = cpu_to_allnodes_group(i); - sd->groups = &sched_group_allnodes[group]; - p = sd; - } else - p = NULL; - - sd = &per_cpu(node_domains, i); - *sd = SD_NODE_INIT; - sd->span = sched_domain_node_span(cpu_to_node(i)); - sd->parent = p; - cpus_and(sd->span, sd->span, *cpu_map); -#endif - - p = sd; - sd = &per_cpu(phys_domains, i); - group = cpu_to_phys_group(i); - *sd = SD_CPU_INIT; - sd->span = nodemask; - sd->parent = p; - sd->groups = &sched_group_phys[group]; - -#ifdef CONFIG_SCHED_SMT - p = sd; - sd = &per_cpu(cpu_domains, i); - group = cpu_to_cpu_group(i); - *sd = SD_SIBLING_INIT; - sd->span = cpu_sibling_map[i]; - cpus_and(sd->span, sd->span, *cpu_map); - sd->parent = p; - sd->groups = &sched_group_cpus[group]; -#endif - } - -#ifdef CONFIG_SCHED_SMT - /* Set up CPU (sibling) groups */ - for_each_cpu_mask(i, *cpu_map) { - cpumask_t this_sibling_map = cpu_sibling_map[i]; - cpus_and(this_sibling_map, this_sibling_map, *cpu_map); - if (i != first_cpu(this_sibling_map)) - continue; - - init_sched_build_groups(sched_group_cpus, this_sibling_map, - &cpu_to_cpu_group); - } -#endif - - /* Set up physical groups */ - for (i = 0; i < MAX_NUMNODES; i++) { - cpumask_t nodemask = node_to_cpumask(i); - - cpus_and(nodemask, nodemask, *cpu_map); - if (cpus_empty(nodemask)) - continue; - - init_sched_build_groups(sched_group_phys, nodemask, - &cpu_to_phys_group); - } - -#ifdef CONFIG_NUMA - init_sched_build_groups(sched_group_allnodes, *cpu_map, - &cpu_to_allnodes_group); - - for (i = 0; i < MAX_NUMNODES; i++) { - /* Set up node groups */ - struct sched_group *sg, *prev; - cpumask_t nodemask = node_to_cpumask(i); - cpumask_t domainspan; - cpumask_t covered = CPU_MASK_NONE; - int j; - - cpus_and(nodemask, nodemask, *cpu_map); - if (cpus_empty(nodemask)) - continue; - - domainspan = sched_domain_node_span(i); - cpus_and(domainspan, domainspan, *cpu_map); - - sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL); - sched_group_nodes[i] = sg; - for_each_cpu_mask(j, nodemask) { - struct sched_domain *sd; - sd = &per_cpu(node_domains, j); - sd->groups = sg; - if (sd->groups == NULL) { - /* Turn off balancing if we have no groups */ - sd->flags = 0; - } - } - if (!sg) { - printk(KERN_WARNING - "Can not alloc domain group for node %d\n", i); - continue; - } - sg->cpu_power = 0; - sg->cpumask = nodemask; - cpus_or(covered, covered, nodemask); - prev = sg; - - for (j = 0; j < MAX_NUMNODES; j++) { - cpumask_t tmp, notcovered; - int n = (i + j) % MAX_NUMNODES; - - cpus_complement(notcovered, covered); - cpus_and(tmp, notcovered, *cpu_map); - cpus_and(tmp, tmp, domainspan); - if (cpus_empty(tmp)) - break; - - nodemask = node_to_cpumask(n); - cpus_and(tmp, tmp, nodemask); - if (cpus_empty(tmp)) - continue; - - sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL); - if (!sg) { - printk(KERN_WARNING - "Can not alloc domain group for node %d\n", j); - break; - } - sg->cpu_power = 0; - sg->cpumask = tmp; - cpus_or(covered, covered, tmp); - prev->next = sg; - prev = sg; - } - prev->next = sched_group_nodes[i]; - } -#endif - - /* Calculate CPU power for physical packages and nodes */ - for_each_cpu_mask(i, *cpu_map) { - int power; - struct sched_domain *sd; -#ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i); - power = SCHED_LOAD_SCALE; - sd->groups->cpu_power = power; -#endif - - sd = &per_cpu(phys_domains, i); - power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE * - (cpus_weight(sd->groups->cpumask)-1) / 10; - sd->groups->cpu_power = power; - -#ifdef CONFIG_NUMA - sd = &per_cpu(allnodes_domains, i); - if (sd->groups) { - power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE * - (cpus_weight(sd->groups->cpumask)-1) / 10; - sd->groups->cpu_power = power; - } -#endif - } - -#ifdef CONFIG_NUMA - for (i = 0; i < MAX_NUMNODES; i++) { - struct sched_group *sg = sched_group_nodes[i]; - int j; - - if (sg == NULL) - continue; -next_sg: - for_each_cpu_mask(j, sg->cpumask) { - struct sched_domain *sd; - int power; - - sd = &per_cpu(phys_domains, j); - if (j != first_cpu(sd->groups->cpumask)) { - /* - * Only add "power" once for each - * physical package. - */ - continue; - } - power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE * - (cpus_weight(sd->groups->cpumask)-1) / 10; - - sg->cpu_power += power; - } - sg = sg->next; - if (sg != sched_group_nodes[i]) - goto next_sg; - } -#endif - - /* Attach the domains */ - for_each_cpu_mask(i, *cpu_map) { - struct sched_domain *sd; -#ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i); -#else - sd = &per_cpu(phys_domains, i); -#endif - cpu_attach_domain(sd, i); - } -} -/* - * Set up scheduler domains and groups. Callers must hold the hotplug lock. - */ -void arch_init_sched_domains(const cpumask_t *cpu_map) -{ - cpumask_t cpu_default_map; - - /* - * Setup mask for cpus without special case scheduling requirements. - * For now this just excludes isolated cpus, but could be used to - * exclude other special cases in the future. - */ - cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map); - - build_sched_domains(&cpu_default_map); -} - -void arch_destroy_sched_domains(const cpumask_t *cpu_map) -{ -#ifdef CONFIG_NUMA - int i; - for (i = 0; i < MAX_NUMNODES; i++) { - cpumask_t nodemask = node_to_cpumask(i); - struct sched_group *oldsg, *sg = sched_group_nodes[i]; - - cpus_and(nodemask, nodemask, *cpu_map); - if (cpus_empty(nodemask)) - continue; - - if (sg == NULL) - continue; - sg = sg->next; -next_sg: - oldsg = sg; - sg = sg->next; - kfree(oldsg); - if (oldsg != sched_group_nodes[i]) - goto next_sg; - sched_group_nodes[i] = NULL; - } -#endif -} - diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index 28f2aadc38d0..205d98028261 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -91,23 +91,8 @@ skip: } #ifdef CONFIG_SMP -/* - * This is updated when the user sets irq affinity via /proc - */ -static cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS]; -static unsigned long pending_irq_redir[BITS_TO_LONGS(NR_IRQS)]; - static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 }; -/* - * Arch specific routine for deferred write to iosapic rte to reprogram - * intr destination. - */ -void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) -{ - pending_irq_cpumask[irq] = mask_val; -} - void set_irq_affinity_info (unsigned int irq, int hwid, int redir) { cpumask_t mask = CPU_MASK_NONE; @@ -116,32 +101,10 @@ void set_irq_affinity_info (unsigned int irq, int hwid, int redir) if (irq < NR_IRQS) { irq_affinity[irq] = mask; + set_irq_info(irq, mask); irq_redir[irq] = (char) (redir & 0xff); } } - - -void move_irq(int irq) -{ - /* note - we hold desc->lock */ - cpumask_t tmp; - irq_desc_t *desc = irq_descp(irq); - int redir = test_bit(irq, pending_irq_redir); - - if (unlikely(!desc->handler->set_affinity)) - return; - - if (!cpus_empty(pending_irq_cpumask[irq])) { - cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map); - if (unlikely(!cpus_empty(tmp))) { - desc->handler->set_affinity(irq | (redir ? IA64_IRQ_REDIRECTED : 0), - pending_irq_cpumask[irq]); - } - cpus_clear(pending_irq_cpumask[irq]); - } -} - - #endif /* CONFIG_SMP */ #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S index b7fa3ccd2b0f..2323377e3695 100644 --- a/arch/ia64/kernel/jprobes.S +++ b/arch/ia64/kernel/jprobes.S @@ -49,6 +49,7 @@ /* * void jprobe_break(void) */ + .section .kprobes.text, "ax" ENTRY(jprobe_break) break.m 0x80300 END(jprobe_break) diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 884f5cd27d8a..471086b808a4 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -87,12 +87,25 @@ static enum instruction_type bundle_encoding[32][3] = { * is IP relative instruction and update the kprobe * inst flag accordingly */ -static void update_kprobe_inst_flag(uint template, uint slot, uint major_opcode, - unsigned long kprobe_inst, struct kprobe *p) +static void __kprobes update_kprobe_inst_flag(uint template, uint slot, + uint major_opcode, + unsigned long kprobe_inst, + struct kprobe *p) { p->ainsn.inst_flag = 0; p->ainsn.target_br_reg = 0; + /* Check for Break instruction + * Bits 37:40 Major opcode to be zero + * Bits 27:32 X6 to be zero + * Bits 32:35 X3 to be zero + */ + if ((!major_opcode) && (!((kprobe_inst >> 27) & 0x1FF)) ) { + /* is a break instruction */ + p->ainsn.inst_flag |= INST_FLAG_BREAK_INST; + return; + } + if (bundle_encoding[template][slot] == B) { switch (major_opcode) { case INDIRECT_CALL_OPCODE: @@ -126,8 +139,10 @@ static void update_kprobe_inst_flag(uint template, uint slot, uint major_opcode * Returns 0 if supported * Returns -EINVAL if unsupported */ -static int unsupported_inst(uint template, uint slot, uint major_opcode, - unsigned long kprobe_inst, struct kprobe *p) +static int __kprobes unsupported_inst(uint template, uint slot, + uint major_opcode, + unsigned long kprobe_inst, + struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; @@ -168,8 +183,9 @@ static int unsupported_inst(uint template, uint slot, uint major_opcode, * on which we are inserting kprobe is cmp instruction * with ctype as unc. */ -static uint is_cmp_ctype_unc_inst(uint template, uint slot, uint major_opcode, -unsigned long kprobe_inst) +static uint __kprobes is_cmp_ctype_unc_inst(uint template, uint slot, + uint major_opcode, + unsigned long kprobe_inst) { cmp_inst_t cmp_inst; uint ctype_unc = 0; @@ -201,8 +217,10 @@ out: * In this function we override the bundle with * the break instruction at the given slot. */ -static void prepare_break_inst(uint template, uint slot, uint major_opcode, - unsigned long kprobe_inst, struct kprobe *p) +static void __kprobes prepare_break_inst(uint template, uint slot, + uint major_opcode, + unsigned long kprobe_inst, + struct kprobe *p) { unsigned long break_inst = BREAK_INST; bundle_t *bundle = &p->ainsn.insn.bundle; @@ -271,7 +289,8 @@ static inline int in_ivt_functions(unsigned long addr) && addr < (unsigned long)__end_ivt_text); } -static int valid_kprobe_addr(int template, int slot, unsigned long addr) +static int __kprobes valid_kprobe_addr(int template, int slot, + unsigned long addr) { if ((slot > 2) || ((bundle_encoding[template][1] == L) && slot > 1)) { printk(KERN_WARNING "Attempting to insert unaligned kprobe " @@ -323,7 +342,7 @@ static void kretprobe_trampoline(void) * - cleanup by marking the instance as unused * - long jump back to the original return address */ -int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -381,7 +400,8 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) +void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) { struct kretprobe_instance *ri; @@ -399,7 +419,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) } } -int arch_prepare_kprobe(struct kprobe *p) +int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long addr = (unsigned long) p->addr; unsigned long *kprobe_addr = (unsigned long *)(addr & ~0xFULL); @@ -430,7 +450,7 @@ int arch_prepare_kprobe(struct kprobe *p) return 0; } -void arch_arm_kprobe(struct kprobe *p) +void __kprobes arch_arm_kprobe(struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; unsigned long arm_addr = addr & ~0xFULL; @@ -439,7 +459,7 @@ void arch_arm_kprobe(struct kprobe *p) flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t)); } -void arch_disarm_kprobe(struct kprobe *p) +void __kprobes arch_disarm_kprobe(struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; unsigned long arm_addr = addr & ~0xFULL; @@ -449,7 +469,7 @@ void arch_disarm_kprobe(struct kprobe *p) flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t)); } -void arch_remove_kprobe(struct kprobe *p) +void __kprobes arch_remove_kprobe(struct kprobe *p) { } @@ -461,7 +481,7 @@ void arch_remove_kprobe(struct kprobe *p) * to original stack address, handle the case where we need to fixup the * relative IP address and/or fixup branch register. */ -static void resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { unsigned long bundle_addr = ((unsigned long) (&p->opcode.bundle)) & ~0xFULL; unsigned long resume_addr = (unsigned long)p->addr & ~0xFULL; @@ -528,13 +548,16 @@ turn_ss_off: ia64_psr(regs)->ss = 0; } -static void prepare_ss(struct kprobe *p, struct pt_regs *regs) +static void __kprobes prepare_ss(struct kprobe *p, struct pt_regs *regs) { unsigned long bundle_addr = (unsigned long) &p->opcode.bundle; unsigned long slot = (unsigned long)p->addr & 0xf; - /* Update instruction pointer (IIP) and slot number (IPSR.ri) */ - regs->cr_iip = bundle_addr & ~0xFULL; + /* single step inline if break instruction */ + if (p->ainsn.inst_flag == INST_FLAG_BREAK_INST) + regs->cr_iip = (unsigned long)p->addr & ~0xFULL; + else + regs->cr_iip = bundle_addr & ~0xFULL; if (slot > 2) slot = 0; @@ -545,7 +568,39 @@ static void prepare_ss(struct kprobe *p, struct pt_regs *regs) ia64_psr(regs)->ss = 1; } -static int pre_kprobes_handler(struct die_args *args) +static int __kprobes is_ia64_break_inst(struct pt_regs *regs) +{ + unsigned int slot = ia64_psr(regs)->ri; + unsigned int template, major_opcode; + unsigned long kprobe_inst; + unsigned long *kprobe_addr = (unsigned long *)regs->cr_iip; + bundle_t bundle; + + memcpy(&bundle, kprobe_addr, sizeof(bundle_t)); + template = bundle.quad0.template; + + /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */ + if (slot == 1 && bundle_encoding[template][1] == L) + slot++; + + /* Get Kprobe probe instruction at given slot*/ + get_kprobe_inst(&bundle, slot, &kprobe_inst, &major_opcode); + + /* For break instruction, + * Bits 37:40 Major opcode to be zero + * Bits 27:32 X6 to be zero + * Bits 32:35 X3 to be zero + */ + if (major_opcode || ((kprobe_inst >> 27) & 0x1FF) ) { + /* Not a break instruction */ + return 0; + } + + /* Is a break instruction */ + return 1; +} + +static int __kprobes pre_kprobes_handler(struct die_args *args) { struct kprobe *p; int ret = 0; @@ -558,7 +613,9 @@ static int pre_kprobes_handler(struct die_args *args) if (kprobe_running()) { p = get_kprobe(addr); if (p) { - if (kprobe_status == KPROBE_HIT_SS) { + if ( (kprobe_status == KPROBE_HIT_SS) && + (p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) { + ia64_psr(regs)->ss = 0; unlock_kprobes(); goto no_kprobe; } @@ -592,6 +649,19 @@ static int pre_kprobes_handler(struct die_args *args) p = get_kprobe(addr); if (!p) { unlock_kprobes(); + if (!is_ia64_break_inst(regs)) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + */ + ret = 1; + + } + + /* Not one of our break, let kernel handle it */ goto no_kprobe; } @@ -616,7 +686,7 @@ no_kprobe: return ret; } -static int post_kprobes_handler(struct pt_regs *regs) +static int __kprobes post_kprobes_handler(struct pt_regs *regs) { if (!kprobe_running()) return 0; @@ -641,7 +711,7 @@ out: return 1; } -static int kprobes_fault_handler(struct pt_regs *regs, int trapnr) +static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr) { if (!kprobe_running()) return 0; @@ -659,8 +729,8 @@ static int kprobes_fault_handler(struct pt_regs *regs, int trapnr) return 0; } -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; switch(val) { @@ -681,7 +751,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, return NOTIFY_DONE; } -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr = ((struct fnptr *)(jp->entry))->ip; @@ -703,7 +773,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { *regs = jprobe_saved_regs; return 1; diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index 4440c8343fa4..f970359e7edf 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -15,6 +15,7 @@ #include <linux/vt_kern.h> /* For unblank_screen() */ #include <linux/module.h> /* for EXPORT_SYMBOL */ #include <linux/hardirq.h> +#include <linux/kprobes.h> #include <asm/fpswa.h> #include <asm/ia32.h> @@ -122,7 +123,7 @@ die_if_kernel (char *str, struct pt_regs *regs, long err) } void -ia64_bad_break (unsigned long break_num, struct pt_regs *regs) +__kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs) { siginfo_t siginfo; int sig, code; @@ -444,7 +445,7 @@ ia64_illegal_op_fault (unsigned long ec, long arg1, long arg2, long arg3, return rv; } -void +void __kprobes ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, unsigned long iim, unsigned long itir, long arg5, long arg6, long arg7, struct pt_regs regs) diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index a676e79e0681..30d8564e9603 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -48,6 +48,7 @@ SECTIONS *(.text) SCHED_TEXT LOCK_TEXT + KPROBES_TEXT *(.gnu.linkonce.t*) } .text2 : AT(ADDR(.text2) - LOAD_OFFSET) diff --git a/arch/ia64/lib/flush.S b/arch/ia64/lib/flush.S index 3e2cfa2c6d39..2a0d27f2f21b 100644 --- a/arch/ia64/lib/flush.S +++ b/arch/ia64/lib/flush.S @@ -20,6 +20,7 @@ * * Note: "in0" and "in1" are preserved for debugging purposes. */ + .section .kprobes.text,"ax" GLOBAL_ENTRY(flush_icache_range) .prologue diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index ff62551eb3a1..24614869e866 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/smp_lock.h> #include <linux/interrupt.h> +#include <linux/kprobes.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -76,7 +77,7 @@ mapped_kernel_page_is_present (unsigned long address) return pte_present(pte); } -void +void __kprobes ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs) { int signal = SIGSEGV, code = SEGV_MAPERR; diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 4564ed0b5ff3..906622d9f933 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -431,7 +431,7 @@ void sn_bus_store_sysdata(struct pci_dev *dev) { struct sysdata_el *element; - element = kcalloc(1, sizeof(struct sysdata_el), GFP_KERNEL); + element = kzalloc(sizeof(struct sysdata_el), GFP_KERNEL); if (!element) { dev_dbg(dev, "%s: out of memory!\n", __FUNCTION__); return; diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c index 254fe15c064b..b45db5133f55 100644 --- a/arch/ia64/sn/kernel/tiocx.c +++ b/arch/ia64/sn/kernel/tiocx.c @@ -191,7 +191,7 @@ cx_device_register(nasid_t nasid, int part_num, int mfg_num, { struct cx_dev *cx_dev; - cx_dev = kcalloc(1, sizeof(struct cx_dev), GFP_KERNEL); + cx_dev = kzalloc(sizeof(struct cx_dev), GFP_KERNEL); DBG("cx_dev= 0x%p\n", cx_dev); if (cx_dev == NULL) return -ENOMEM; diff --git a/arch/ia64/sn/pci/tioca_provider.c b/arch/ia64/sn/pci/tioca_provider.c index ea09c12f0258..19bced34d5f1 100644 --- a/arch/ia64/sn/pci/tioca_provider.c +++ b/arch/ia64/sn/pci/tioca_provider.c @@ -148,7 +148,7 @@ tioca_gart_init(struct tioca_kernel *tioca_kern) tioca_kern->ca_pcigart_entries = tioca_kern->ca_pciap_size / tioca_kern->ca_ap_pagesize; tioca_kern->ca_pcigart_pagemap = - kcalloc(1, tioca_kern->ca_pcigart_entries / 8, GFP_KERNEL); + kzalloc(tioca_kern->ca_pcigart_entries / 8, GFP_KERNEL); if (!tioca_kern->ca_pcigart_pagemap) { free_pages((unsigned long)tioca_kern->ca_gart, get_order(tioca_kern->ca_gart_size)); @@ -392,7 +392,7 @@ tioca_dma_mapped(struct pci_dev *pdev, uint64_t paddr, size_t req_size) * allocate a map struct */ - ca_dmamap = kcalloc(1, sizeof(struct tioca_dmamap), GFP_ATOMIC); + ca_dmamap = kzalloc(sizeof(struct tioca_dmamap), GFP_ATOMIC); if (!ca_dmamap) goto map_return; @@ -600,7 +600,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont * Allocate kernel bus soft and copy from prom. */ - tioca_common = kcalloc(1, sizeof(struct tioca_common), GFP_KERNEL); + tioca_common = kzalloc(sizeof(struct tioca_common), GFP_KERNEL); if (!tioca_common) return NULL; @@ -609,7 +609,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont /* init kernel-private area */ - tioca_kern = kcalloc(1, sizeof(struct tioca_kernel), GFP_KERNEL); + tioca_kern = kzalloc(sizeof(struct tioca_kernel), GFP_KERNEL); if (!tioca_kern) { kfree(tioca_common); return NULL; diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c index 8a2b77bc5749..539c562cd54d 100644 --- a/arch/m32r/kernel/time.c +++ b/arch/m32r/kernel/time.c @@ -171,10 +171,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); @@ -221,7 +218,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * called as close as possible to 500 ms before the new second starts. */ write_seqlock(&xtime_lock); - if ((time_status & STA_UNSYNC) == 0 + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned)TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned)TICK_SIZE) / 2) diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c index c6b2a410bf9a..eb63ca6ed94c 100644 --- a/arch/m68k/bvme6000/rtc.c +++ b/arch/m68k/bvme6000/rtc.c @@ -14,6 +14,7 @@ #include <linux/fcntl.h> #include <linux/init.h> #include <linux/poll.h> +#include <linux/module.h> #include <linux/mc146818rtc.h> /* For struct rtc_time and ioctls, etc */ #include <linux/smp_lock.h> #include <asm/bvme6000hw.h> @@ -171,7 +172,7 @@ static struct miscdevice rtc_dev = { .fops = &rtc_fops }; -int __init rtc_DP8570A_init(void) +static int __init rtc_DP8570A_init(void) { if (!MACH_IS_BVME6000) return -ENODEV; @@ -179,4 +180,4 @@ int __init rtc_DP8570A_init(void) printk(KERN_INFO "DP8570A Real Time Clock Driver v%s\n", RTC_VERSION); return misc_register(&rtc_dev); } - +module_init(rtc_DP8570A_init); diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c index e47e19588525..4ec95e3cb874 100644 --- a/arch/m68k/kernel/time.c +++ b/arch/m68k/kernel/time.c @@ -166,10 +166,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c index 8a2425069088..7977eae50af2 100644 --- a/arch/m68k/mvme16x/rtc.c +++ b/arch/m68k/mvme16x/rtc.c @@ -161,7 +161,7 @@ static struct miscdevice rtc_dev= .fops = &rtc_fops }; -int __init rtc_MK48T08_init(void) +static int __init rtc_MK48T08_init(void) { if (!MACH_IS_MVME16x) return -ENODEV; @@ -169,4 +169,4 @@ int __init rtc_MK48T08_init(void) printk(KERN_INFO "MK48T08 Real Time Clock Driver v%s\n", RTC_VERSION); return misc_register(&rtc_dev); } - +module_init(rtc_MK48T08_init); diff --git a/arch/m68knommu/kernel/time.c b/arch/m68knommu/kernel/time.c index 5c3ca671627c..b17c1ecba966 100644 --- a/arch/m68knommu/kernel/time.c +++ b/arch/m68knommu/kernel/time.c @@ -68,7 +68,7 @@ static irqreturn_t timer_interrupt(int irq, void *dummy, struct pt_regs * regs) * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -178,10 +178,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 4613219dd73e..ece4564919d8 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -546,20 +546,20 @@ struct msgbuf32 { s32 mtype; char mtext[1]; }; struct ipc_perm32 { key_t key; - compat_uid_t uid; - compat_gid_t gid; - compat_uid_t cuid; - compat_gid_t cgid; + __compat_uid_t uid; + __compat_gid_t gid; + __compat_uid_t cuid; + __compat_gid_t cgid; compat_mode_t mode; unsigned short seq; }; struct ipc64_perm32 { key_t key; - compat_uid_t uid; - compat_gid_t gid; - compat_uid_t cuid; - compat_gid_t cgid; + __compat_uid_t uid; + __compat_gid_t gid; + __compat_uid_t cuid; + __compat_gid_t cgid; compat_mode_t mode; unsigned short seq; unsigned short __pad1; diff --git a/arch/mips/kernel/sysirix.c b/arch/mips/kernel/sysirix.c index f3bf0e43b8bb..b46595462717 100644 --- a/arch/mips/kernel/sysirix.c +++ b/arch/mips/kernel/sysirix.c @@ -632,10 +632,7 @@ asmlinkage int irix_stime(int value) write_seqlock_irq(&xtime_lock); xtime.tv_sec = value; xtime.tv_nsec = 0; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); return 0; diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index 648c82292ed6..0dd0df7a3b04 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -223,10 +223,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); @@ -442,7 +439,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * called as close as possible to 500 ms before the new second starts. */ write_seqlock(&xtime_lock); - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index 8c1b96fffa76..cddf1cedf007 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -118,7 +118,7 @@ again: * RTC clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to when a second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 6cf7407344ba..7ff67f8e9f8c 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -188,10 +188,7 @@ do_settimeofday (struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); } write_sequnlock_irq(&xtime_lock); clock_was_set(); diff --git a/arch/ppc/kernel/time.c b/arch/ppc/kernel/time.c index bf4ddca5e853..a3c5281a5d2d 100644 --- a/arch/ppc/kernel/time.c +++ b/arch/ppc/kernel/time.c @@ -169,7 +169,7 @@ void timer_interrupt(struct pt_regs * regs) * We should have an rtc call that only sets the minutes and * seconds like on Intel to avoid problems with non UTC clocks. */ - if ( ppc_md.set_rtc_time && (time_status & STA_UNSYNC) == 0 && + if ( ppc_md.set_rtc_time && ntp_synced() && xtime.tv_sec - last_rtc_update >= 659 && abs((xtime.tv_nsec / 1000) - (1000000-1000000/HZ)) < 500000/HZ && jiffies - wall_jiffies == 1) { @@ -271,10 +271,7 @@ int do_settimeofday(struct timespec *tv) */ last_rtc_update = new_sec - 658; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irqrestore(&xtime_lock, flags); clock_was_set(); return 0; diff --git a/arch/ppc/syslib/ocp.c b/arch/ppc/syslib/ocp.c index e5fd2ae503ea..9ccce438bd7a 100644 --- a/arch/ppc/syslib/ocp.c +++ b/arch/ppc/syslib/ocp.c @@ -165,7 +165,7 @@ ocp_device_remove(struct device *dev) } static int -ocp_device_suspend(struct device *dev, u32 state) +ocp_device_suspend(struct device *dev, pm_message_t state) { struct ocp_device *ocp_dev = to_ocp_dev(dev); struct ocp_driver *ocp_drv = to_ocp_drv(dev->driver); diff --git a/arch/ppc64/kernel/kprobes.c b/arch/ppc64/kernel/kprobes.c index a3d519518fb8..7e80d49c589a 100644 --- a/arch/ppc64/kernel/kprobes.c +++ b/arch/ppc64/kernel/kprobes.c @@ -44,7 +44,7 @@ static struct kprobe *kprobe_prev; static unsigned long kprobe_status_prev, kprobe_saved_msr_prev; static struct pt_regs jprobe_saved_regs; -int arch_prepare_kprobe(struct kprobe *p) +int __kprobes arch_prepare_kprobe(struct kprobe *p) { int ret = 0; kprobe_opcode_t insn = *p->addr; @@ -68,27 +68,27 @@ int arch_prepare_kprobe(struct kprobe *p) return ret; } -void arch_copy_kprobe(struct kprobe *p) +void __kprobes arch_copy_kprobe(struct kprobe *p) { memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; } -void arch_arm_kprobe(struct kprobe *p) +void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_disarm_kprobe(struct kprobe *p) +void __kprobes arch_disarm_kprobe(struct kprobe *p) { *p->addr = p->opcode; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_remove_kprobe(struct kprobe *p) +void __kprobes arch_remove_kprobe(struct kprobe *p) { up(&kprobe_mutex); free_insn_slot(p->ainsn.insn); @@ -102,7 +102,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->msr |= MSR_SE; /* single step inline if it is a trap variant */ - if (IS_TW(insn) || IS_TD(insn) || IS_TWI(insn) || IS_TDI(insn)) + if (is_trap(insn)) regs->nip = (unsigned long)p->addr; else regs->nip = (unsigned long)p->ainsn.insn; @@ -122,7 +122,8 @@ static inline void restore_previous_kprobe(void) kprobe_saved_msr = kprobe_saved_msr_prev; } -void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) +void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) { struct kretprobe_instance *ri; @@ -151,7 +152,9 @@ static inline int kprobe_handler(struct pt_regs *regs) Disarm the probe we just hit, and ignore it. */ p = get_kprobe(addr); if (p) { - if (kprobe_status == KPROBE_HIT_SS) { + kprobe_opcode_t insn = *p->ainsn.insn; + if (kprobe_status == KPROBE_HIT_SS && + is_trap(insn)) { regs->msr &= ~MSR_SE; regs->msr |= kprobe_saved_msr; unlock_kprobes(); @@ -191,8 +194,7 @@ static inline int kprobe_handler(struct pt_regs *regs) * trap variant, it could belong to someone else */ kprobe_opcode_t cur_insn = *addr; - if (IS_TW(cur_insn) || IS_TD(cur_insn) || - IS_TWI(cur_insn) || IS_TDI(cur_insn)) + if (is_trap(cur_insn)) goto no_kprobe; /* * The breakpoint instruction was removed right @@ -244,7 +246,7 @@ void kretprobe_trampoline_holder(void) /* * Called when the probe at kretprobe trampoline is hit */ -int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -308,7 +310,7 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * single-stepped a copy of the instruction. The address of this * copy is p->ainsn.insn. */ -static void resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { int ret; unsigned int insn = *p->ainsn.insn; @@ -373,8 +375,8 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine to for handling exceptions. */ -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; @@ -402,11 +404,11 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, default: break; } - preempt_enable(); + preempt_enable_no_resched(); return ret; } -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); @@ -419,16 +421,16 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -void jprobe_return(void) +void __kprobes jprobe_return(void) { asm volatile("trap" ::: "memory"); } -void jprobe_return_end(void) +void __kprobes jprobe_return_end(void) { }; -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { /* * FIXME - we should ideally be validating that we got here 'cos diff --git a/arch/ppc64/kernel/misc.S b/arch/ppc64/kernel/misc.S index 474df0a862bf..6d860c1d9fa0 100644 --- a/arch/ppc64/kernel/misc.S +++ b/arch/ppc64/kernel/misc.S @@ -183,7 +183,7 @@ PPC64_CACHES: * flush all bytes from start through stop-1 inclusive */ -_GLOBAL(__flush_icache_range) +_KPROBE(__flush_icache_range) /* * Flush the data cache to memory @@ -223,7 +223,7 @@ _GLOBAL(__flush_icache_range) bdnz 2b isync blr - + .previous .text /* * Like above, but only do the D-cache. * @@ -957,7 +957,7 @@ _GLOBAL(sys_call_table32) .llong .ppc_fork .llong .sys_read .llong .sys_write - .llong .sys32_open /* 5 */ + .llong .compat_sys_open /* 5 */ .llong .sys_close .llong .sys32_waitpid .llong .sys32_creat diff --git a/arch/ppc64/kernel/pSeries_reconfig.c b/arch/ppc64/kernel/pSeries_reconfig.c index dc2a69d412a2..58c61219d08e 100644 --- a/arch/ppc64/kernel/pSeries_reconfig.c +++ b/arch/ppc64/kernel/pSeries_reconfig.c @@ -111,7 +111,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist struct device_node *np; int err = -ENOMEM; - np = kcalloc(1, sizeof(*np), GFP_KERNEL); + np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) goto out_err; diff --git a/arch/ppc64/kernel/sys_ppc32.c b/arch/ppc64/kernel/sys_ppc32.c index 206619080e66..214914a95a50 100644 --- a/arch/ppc64/kernel/sys_ppc32.c +++ b/arch/ppc64/kernel/sys_ppc32.c @@ -867,37 +867,6 @@ off_t ppc32_lseek(unsigned int fd, u32 offset, unsigned int origin) return sys_lseek(fd, (int)offset, origin); } -/* - * This is just a version for 32-bit applications which does - * not force O_LARGEFILE on. - */ -asmlinkage long sys32_open(const char __user * filename, int flags, int mode) -{ - char * tmp; - int fd, error; - - tmp = getname(filename); - fd = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - fd = get_unused_fd(); - if (fd >= 0) { - struct file * f = filp_open(tmp, flags, mode); - error = PTR_ERR(f); - if (IS_ERR(f)) - goto out_error; - fd_install(fd, f); - } -out: - putname(tmp); - } - return fd; - -out_error: - put_unused_fd(fd); - fd = error; - goto out; -} - /* Note: it is necessary to treat bufsiz as an unsigned int, * with the corresponding cast to a signed int to insure that the * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) diff --git a/arch/ppc64/kernel/time.c b/arch/ppc64/kernel/time.c index 91ef95ccda4f..9939c206afa4 100644 --- a/arch/ppc64/kernel/time.c +++ b/arch/ppc64/kernel/time.c @@ -128,7 +128,7 @@ static __inline__ void timer_check_rtc(void) * We should have an rtc call that only sets the minutes and * seconds like on Intel to avoid problems with non UTC clocks. */ - if ( (time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec - last_rtc_update >= 659 && abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ && jiffies - wall_jiffies == 1) { @@ -435,10 +435,7 @@ int do_settimeofday(struct timespec *tv) */ last_rtc_update = new_sec - 658; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); delta_xsec = mulhdu( (tb_last_stamp-do_gtod.varp->tb_orig_stamp), do_gtod.varp->tb_to_xs ); diff --git a/arch/ppc64/kernel/traps.c b/arch/ppc64/kernel/traps.c index a8d5e83ee89f..7467ae508e6e 100644 --- a/arch/ppc64/kernel/traps.c +++ b/arch/ppc64/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/kprobes.h> #include <asm/kdebug.h> #include <asm/pgtable.h> @@ -220,7 +221,7 @@ void instruction_breakpoint_exception(struct pt_regs *regs) _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); } -void single_step_exception(struct pt_regs *regs) +void __kprobes single_step_exception(struct pt_regs *regs) { regs->msr &= ~MSR_SE; /* Turn off 'trace' bit */ @@ -398,7 +399,7 @@ check_bug_trap(struct pt_regs *regs) return 0; } -void program_check_exception(struct pt_regs *regs) +void __kprobes program_check_exception(struct pt_regs *regs) { if (debugger_fault_handler(regs)) return; diff --git a/arch/ppc64/kernel/vmlinux.lds.S b/arch/ppc64/kernel/vmlinux.lds.S index 4103cc13f8d6..0306510bc4ff 100644 --- a/arch/ppc64/kernel/vmlinux.lds.S +++ b/arch/ppc64/kernel/vmlinux.lds.S @@ -15,6 +15,7 @@ SECTIONS *(.text .text.*) SCHED_TEXT LOCK_TEXT + KPROBES_TEXT *(.fixup) . = ALIGN(4096); _etext = .; diff --git a/arch/ppc64/mm/fault.c b/arch/ppc64/mm/fault.c index 20b0f37e8bf8..772f0714a5b7 100644 --- a/arch/ppc64/mm/fault.c +++ b/arch/ppc64/mm/fault.c @@ -29,6 +29,7 @@ #include <linux/interrupt.h> #include <linux/smp_lock.h> #include <linux/module.h> +#include <linux/kprobes.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -84,8 +85,8 @@ static int store_updates_sp(struct pt_regs *regs) * The return value is 0 if the fault was handled, or the signal * number if this is a kernel fault that can't be handled here. */ -int do_page_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code) +int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, + unsigned long error_code) { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 8ca485676780..2fd75da15495 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -139,10 +139,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); return 0; diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index df7a9b9d4cbf..02ca69918d7c 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -215,10 +215,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); @@ -234,7 +231,7 @@ static long last_rtc_update; * timer_interrupt() needs to keep up the real-time clock, * as well as call the "do_timer()" routine every clocktick */ -static inline void do_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +static inline void do_timer_interrupt(int irq, struct pt_regs *regs) { do_timer(regs); #ifndef CONFIG_SMP @@ -252,7 +249,7 @@ static inline void do_timer_interrupt(int irq, void *dev_id, struct pt_regs *reg * RTC clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -285,7 +282,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * locally disabled. -arca */ write_seqlock(&xtime_lock); - do_timer_interrupt(irq, NULL, regs); + do_timer_interrupt(irq, regs); write_sequnlock(&xtime_lock); return IRQ_HANDLED; diff --git a/arch/sh64/kernel/time.c b/arch/sh64/kernel/time.c index 6c84da3efc73..f4a62a10053c 100644 --- a/arch/sh64/kernel/time.c +++ b/arch/sh64/kernel/time.c @@ -247,10 +247,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); @@ -303,7 +300,7 @@ static long last_rtc_update = 0; * timer_interrupt() needs to keep up the real-time clock, * as well as call the "do_timer()" routine every clocktick */ -static inline void do_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +static inline void do_timer_interrupt(int irq, struct pt_regs *regs) { unsigned long long current_ctc; asm ("getcon cr62, %0" : "=r" (current_ctc)); @@ -328,7 +325,7 @@ static inline void do_timer_interrupt(int irq, void *dev_id, struct pt_regs *reg * RTC clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -361,7 +358,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * locally disabled. -arca */ write_lock(&xtime_lock); - do_timer_interrupt(irq, NULL, regs); + do_timer_interrupt(irq, regs); write_unlock(&xtime_lock); return IRQ_HANDLED; diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index 597d3ff6ad68..36a40697b8d6 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -840,10 +840,7 @@ static int pci_do_settimeofday(struct timespec *tv) xtime.tv_sec = tv->tv_sec; xtime.tv_nsec = tv->tv_nsec; - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); return 0; } diff --git a/arch/sparc/kernel/time.c b/arch/sparc/kernel/time.c index 3b759aefc170..bc015e980341 100644 --- a/arch/sparc/kernel/time.c +++ b/arch/sparc/kernel/time.c @@ -139,7 +139,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs * regs) /* Determine when to update the Mostek clock. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -554,10 +554,7 @@ static int sbus_do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); return 0; } diff --git a/arch/sparc64/kernel/kprobes.c b/arch/sparc64/kernel/kprobes.c index bbf11f85dab1..0d66d07c8c6e 100644 --- a/arch/sparc64/kernel/kprobes.c +++ b/arch/sparc64/kernel/kprobes.c @@ -8,6 +8,7 @@ #include <linux/kprobes.h> #include <asm/kdebug.h> #include <asm/signal.h> +#include <asm/cacheflush.h> /* We do not have hardware single-stepping on sparc64. * So we implement software single-stepping with breakpoint @@ -37,31 +38,31 @@ * - Mark that we are no longer actively in a kprobe. */ -int arch_prepare_kprobe(struct kprobe *p) +int __kprobes arch_prepare_kprobe(struct kprobe *p) { return 0; } -void arch_copy_kprobe(struct kprobe *p) +void __kprobes arch_copy_kprobe(struct kprobe *p) { p->ainsn.insn[0] = *p->addr; p->ainsn.insn[1] = BREAKPOINT_INSTRUCTION_2; p->opcode = *p->addr; } -void arch_arm_kprobe(struct kprobe *p) +void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; flushi(p->addr); } -void arch_disarm_kprobe(struct kprobe *p) +void __kprobes arch_disarm_kprobe(struct kprobe *p) { *p->addr = p->opcode; flushi(p->addr); } -void arch_remove_kprobe(struct kprobe *p) +void __kprobes arch_remove_kprobe(struct kprobe *p) { } @@ -111,7 +112,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) } } -static int kprobe_handler(struct pt_regs *regs) +static int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; void *addr = (void *) regs->tpc; @@ -191,8 +192,9 @@ no_kprobe: * The original INSN location was REAL_PC, it actually * executed at PC and produced destination address NPC. */ -static unsigned long relbranch_fixup(u32 insn, unsigned long real_pc, - unsigned long pc, unsigned long npc) +static unsigned long __kprobes relbranch_fixup(u32 insn, unsigned long real_pc, + unsigned long pc, + unsigned long npc) { /* Branch not taken, no mods necessary. */ if (npc == pc + 0x4UL) @@ -217,7 +219,8 @@ static unsigned long relbranch_fixup(u32 insn, unsigned long real_pc, /* If INSN is an instruction which writes it's PC location * into a destination register, fix that up. */ -static void retpc_fixup(struct pt_regs *regs, u32 insn, unsigned long real_pc) +static void __kprobes retpc_fixup(struct pt_regs *regs, u32 insn, + unsigned long real_pc) { unsigned long *slot = NULL; @@ -257,7 +260,7 @@ static void retpc_fixup(struct pt_regs *regs, u32 insn, unsigned long real_pc) * This function prepares to return from the post-single-step * breakpoint trap. */ -static void resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { u32 insn = p->ainsn.insn[0]; @@ -315,8 +318,8 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine to for handling exceptions. */ -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; switch (val) { @@ -344,7 +347,8 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, return NOTIFY_DONE; } -asmlinkage void kprobe_trap(unsigned long trap_level, struct pt_regs *regs) +asmlinkage void __kprobes kprobe_trap(unsigned long trap_level, + struct pt_regs *regs) { BUG_ON(trap_level != 0x170 && trap_level != 0x171); @@ -368,7 +372,7 @@ static struct pt_regs jprobe_saved_regs; static struct pt_regs *jprobe_saved_regs_location; static struct sparc_stackf jprobe_saved_stack; -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); @@ -390,7 +394,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -void jprobe_return(void) +void __kprobes jprobe_return(void) { preempt_enable_no_resched(); __asm__ __volatile__( @@ -403,7 +407,7 @@ extern void jprobe_return_trap_instruction(void); extern void __show_regs(struct pt_regs * regs); -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { u32 *addr = (u32 *) regs->tpc; diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 1d3aa588df8a..7f6239ed2521 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -1002,29 +1002,7 @@ asmlinkage long sys32_adjtimex(struct timex32 __user *utp) asmlinkage long sparc32_open(const char __user *filename, int flags, int mode) { - char * tmp; - int fd, error; - - tmp = getname(filename); - fd = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - fd = get_unused_fd(); - if (fd >= 0) { - struct file * f = filp_open(tmp, flags, mode); - error = PTR_ERR(f); - if (IS_ERR(f)) - goto out_error; - fd_install(fd, f); - } -out: - putname(tmp); - } - return fd; - -out_error: - put_unused_fd(fd); - fd = error; - goto out; + return do_sys_open(filename, flags, mode); } extern unsigned long do_mremap(unsigned long addr, diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c index 362b9c26871b..3f08a32f51a1 100644 --- a/arch/sparc64/kernel/time.c +++ b/arch/sparc64/kernel/time.c @@ -449,7 +449,7 @@ static inline void timer_check_rtc(void) static long last_rtc_update; /* Determine when to update the Mostek clock. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { diff --git a/arch/sparc64/kernel/vmlinux.lds.S b/arch/sparc64/kernel/vmlinux.lds.S index 950423da8a6a..f47d0be39378 100644 --- a/arch/sparc64/kernel/vmlinux.lds.S +++ b/arch/sparc64/kernel/vmlinux.lds.S @@ -17,6 +17,7 @@ SECTIONS *(.text) SCHED_TEXT LOCK_TEXT + KPROBES_TEXT *(.gnu.warning) } =0 _etext = .; diff --git a/arch/sparc64/mm/fault.c b/arch/sparc64/mm/fault.c index 52e9375288a9..db1e3310e907 100644 --- a/arch/sparc64/mm/fault.c +++ b/arch/sparc64/mm/fault.c @@ -18,6 +18,7 @@ #include <linux/smp_lock.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/kprobes.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -117,8 +118,9 @@ unsigned long __init prom_probe_memory (void) return tally; } -static void unhandled_fault(unsigned long address, struct task_struct *tsk, - struct pt_regs *regs) +static void __kprobes unhandled_fault(unsigned long address, + struct task_struct *tsk, + struct pt_regs *regs) { if ((unsigned long) address < PAGE_SIZE) { printk(KERN_ALERT "Unable to handle kernel NULL " @@ -304,7 +306,7 @@ cannot_handle: unhandled_fault (address, current, regs); } -asmlinkage void do_sparc64_fault(struct pt_regs *regs) +asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c index 3fbaf342a452..fdb1ebb308c9 100644 --- a/arch/sparc64/mm/init.c +++ b/arch/sparc64/mm/init.c @@ -19,6 +19,7 @@ #include <linux/pagemap.h> #include <linux/fs.h> #include <linux/seq_file.h> +#include <linux/kprobes.h> #include <asm/head.h> #include <asm/system.h> @@ -250,7 +251,7 @@ out: put_cpu(); } -void flush_icache_range(unsigned long start, unsigned long end) +void __kprobes flush_icache_range(unsigned long start, unsigned long end) { /* Cheetah has coherent I-cache. */ if (tlb_type == spitfire) { diff --git a/arch/sparc64/mm/ultra.S b/arch/sparc64/mm/ultra.S index 8dfa825eca51..b2ee9b53227f 100644 --- a/arch/sparc64/mm/ultra.S +++ b/arch/sparc64/mm/ultra.S @@ -119,6 +119,7 @@ __spitfire_flush_tlb_mm_slow: #else #error unsupported PAGE_SIZE #endif + .section .kprobes.text, "ax" .align 32 .globl __flush_icache_page __flush_icache_page: /* %o0 = phys_page */ @@ -201,6 +202,7 @@ dflush4:stxa %g0, [%o4] ASI_DCACHE_TAG nop #endif /* DCACHE_ALIASING_POSSIBLE */ + .previous .text .align 32 __prefill_dtlb: rdpr %pstate, %g7 diff --git a/arch/um/include/um_uaccess.h b/arch/um/include/um_uaccess.h index 6e348cb6de24..84c0868cd561 100644 --- a/arch/um/include/um_uaccess.h +++ b/arch/um/include/um_uaccess.h @@ -20,13 +20,6 @@ #define access_ok(type, addr, size) \ CHOOSE_MODE_PROC(access_ok_tt, access_ok_skas, type, addr, size) -/* this function will go away soon - use access_ok() instead */ -static inline int __deprecated verify_area(int type, const void __user *addr, unsigned long size) -{ - return (CHOOSE_MODE_PROC(verify_area_tt, verify_area_skas, type, addr, - size)); -} - static inline int copy_from_user(void *to, const void __user *from, int n) { return(CHOOSE_MODE_PROC(copy_from_user_tt, copy_from_user_skas, to, diff --git a/arch/v850/kernel/time.c b/arch/v850/kernel/time.c index f722a268238a..ea3fd8844ff0 100644 --- a/arch/v850/kernel/time.c +++ b/arch/v850/kernel/time.c @@ -66,7 +66,7 @@ static irqreturn_t timer_interrupt (int irq, void *dummy, struct pt_regs *regs) * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be * called as close as possible to 500 ms before the new second starts. */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec > last_rtc_update + 660 && (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { @@ -169,10 +169,7 @@ int do_settimeofday(struct timespec *tv) xtime.tv_sec = tv->tv_sec; xtime.tv_nsec = tv->tv_nsec; - time_adjust = 0; /* stop active adjtime () */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq (&xtime_lock); clock_was_set(); diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 75e52c57f19c..251ce7cf1a38 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -441,6 +441,11 @@ config ISA_DMA_API bool default y +config GENERIC_PENDING_IRQ + bool + depends on GENERIC_HARDIRQS && SMP + default y + menu "Power management options" source kernel/power/Kconfig diff --git a/arch/x86_64/boot/setup.S b/arch/x86_64/boot/setup.S index ff58b2832b75..12ea0b6c52e2 100644 --- a/arch/x86_64/boot/setup.S +++ b/arch/x86_64/boot/setup.S @@ -81,7 +81,7 @@ start: # This is the setup header, and it must start at %cs:2 (old 0x9020:2) .ascii "HdrS" # header signature - .word 0x0203 # header version number (>= 0x0105) + .word 0x0204 # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) realmode_swtch: .word 0, 0 # default_switch, SETUPSEG start_sys_seg: .word SYSSEG diff --git a/arch/x86_64/boot/tools/build.c b/arch/x86_64/boot/tools/build.c index 18b5bac1c428..c44f5e2ec100 100644 --- a/arch/x86_64/boot/tools/build.c +++ b/arch/x86_64/boot/tools/build.c @@ -178,7 +178,9 @@ int main(int argc, char ** argv) die("Output: seek failed"); buf[0] = (sys_size & 0xff); buf[1] = ((sys_size >> 8) & 0xff); - if (write(1, buf, 2) != 2) + buf[2] = ((sys_size >> 16) & 0xff); + buf[3] = ((sys_size >> 24) & 0xff); + if (write(1, buf, 4) != 4) die("Write of image length failed"); return 0; /* Everything is OK */ diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index c45d6a05b984..f174083d5567 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -307,7 +307,7 @@ ia32_sys_call_table: .quad stub32_fork .quad sys_read .quad sys_write - .quad sys32_open /* 5 */ + .quad compat_sys_open /* 5 */ .quad sys_close .quad sys32_waitpid .quad sys_creat diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c index be996d1b691e..04d80406ce4f 100644 --- a/arch/x86_64/ia32/sys_ia32.c +++ b/arch/x86_64/ia32/sys_ia32.c @@ -969,32 +969,6 @@ long sys32_kill(int pid, int sig) return sys_kill(pid, sig); } -asmlinkage long sys32_open(const char __user * filename, int flags, int mode) -{ - char * tmp; - int fd, error; - - /* don't force O_LARGEFILE */ - tmp = getname(filename); - fd = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - fd = get_unused_fd(); - if (fd >= 0) { - struct file *f = filp_open(tmp, flags, mode); - error = PTR_ERR(f); - if (IS_ERR(f)) { - put_unused_fd(fd); - fd = error; - } else { - fsnotify_open(f->f_dentry); - fd_install(fd, f); - } - } - putname(tmp); - } - return fd; -} - extern asmlinkage long sys_timer_create(clockid_t which_clock, struct sigevent __user *timer_event_spec, diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c index b548dea4e5b9..116ac5f53dce 100644 --- a/arch/x86_64/kernel/e820.c +++ b/arch/x86_64/kernel/e820.c @@ -85,7 +85,7 @@ int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) struct e820entry *ei = &e820.map[i]; if (type && ei->type != type) continue; - if (ei->addr >= end || ei->addr + ei->size < start) + if (ei->addr >= end || ei->addr + ei->size <= start) continue; return 1; } diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S index 096d470e280f..be51dbe1f75e 100644 --- a/arch/x86_64/kernel/entry.S +++ b/arch/x86_64/kernel/entry.S @@ -784,8 +784,9 @@ ENTRY(execve) ret CFI_ENDPROC -ENTRY(page_fault) +KPROBE_ENTRY(page_fault) errorentry do_page_fault + .previous .text ENTRY(coprocessor_error) zeroentry do_coprocessor_error @@ -797,13 +798,14 @@ ENTRY(device_not_available) zeroentry math_state_restore /* runs on exception stack */ -ENTRY(debug) +KPROBE_ENTRY(debug) CFI_STARTPROC pushq $0 CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_debug jmp paranoid_exit CFI_ENDPROC + .previous .text /* runs on exception stack */ ENTRY(nmi) @@ -854,8 +856,9 @@ paranoid_schedule: jmp paranoid_userspace CFI_ENDPROC -ENTRY(int3) +KPROBE_ENTRY(int3) zeroentry do_int3 + .previous .text ENTRY(overflow) zeroentry do_overflow @@ -892,8 +895,9 @@ ENTRY(stack_segment) jmp paranoid_exit CFI_ENDPROC -ENTRY(general_protection) +KPROBE_ENTRY(general_protection) errorentry do_general_protection + .previous .text ENTRY(alignment_check) errorentry do_alignment_check diff --git a/arch/x86_64/kernel/genapic.c b/arch/x86_64/kernel/genapic.c index 30c843a5efdd..f062aa03bab7 100644 --- a/arch/x86_64/kernel/genapic.c +++ b/arch/x86_64/kernel/genapic.c @@ -25,7 +25,7 @@ #endif /* which logical CPU number maps to which CPU (physical APIC ID) */ -u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; +u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; EXPORT_SYMBOL(x86_cpu_to_apicid); u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; diff --git a/arch/x86_64/kernel/genapic_cluster.c b/arch/x86_64/kernel/genapic_cluster.c index 9703da7202e3..f6523dd1bc09 100644 --- a/arch/x86_64/kernel/genapic_cluster.c +++ b/arch/x86_64/kernel/genapic_cluster.c @@ -72,10 +72,14 @@ static void cluster_send_IPI_mask(cpumask_t mask, int vector) static void cluster_send_IPI_allbutself(int vector) { cpumask_t mask = cpu_online_map; - cpu_clear(smp_processor_id(), mask); + int me = get_cpu(); /* Ensure we are not preempted when we clear */ + + cpu_clear(me, mask); if (!cpus_empty(mask)) cluster_send_IPI_mask(mask, vector); + + put_cpu(); } static void cluster_send_IPI_all(int vector) diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c index d206d7e49cf5..ba1a744e9bf0 100644 --- a/arch/x86_64/kernel/io_apic.c +++ b/arch/x86_64/kernel/io_apic.c @@ -70,7 +70,7 @@ static struct irq_pin_list { short apic, pin, next; } irq_2_pin[PIN_MAP_SIZE]; -int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; +int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1}; #ifdef CONFIG_PCI_MSI #define vector_to_irq(vector) \ (platform_legacy_irq(vector) ? vector : vector_irq[vector]) @@ -78,6 +78,54 @@ int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; #define vector_to_irq(vector) (vector) #endif +#define __DO_ACTION(R, ACTION, FINAL) \ + \ +{ \ + int pin; \ + struct irq_pin_list *entry = irq_2_pin + irq; \ + \ + for (;;) { \ + unsigned int reg; \ + pin = entry->pin; \ + if (pin == -1) \ + break; \ + reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \ + reg ACTION; \ + io_apic_modify(entry->apic, reg); \ + if (!entry->next) \ + break; \ + entry = irq_2_pin + entry->next; \ + } \ + FINAL; \ +} + +#ifdef CONFIG_SMP +static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask) +{ + unsigned long flags; + unsigned int dest; + cpumask_t tmp; + + cpus_and(tmp, mask, cpu_online_map); + if (cpus_empty(tmp)) + tmp = TARGET_CPUS; + + cpus_and(mask, tmp, CPU_MASK_ALL); + + dest = cpu_mask_to_apicid(mask); + + /* + * Only the high 8 bits are valid. + */ + dest = SET_APIC_LOGICAL_ID(dest); + + spin_lock_irqsave(&ioapic_lock, flags); + __DO_ACTION(1, = dest, ) + set_irq_info(irq, mask); + spin_unlock_irqrestore(&ioapic_lock, flags); +} +#endif + /* * The common case is 1:1 IRQ<->pin mappings. Sometimes there are * shared ISA-space IRQs, so we have to support them. We are super @@ -101,26 +149,6 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin) entry->pin = pin; } -#define __DO_ACTION(R, ACTION, FINAL) \ - \ -{ \ - int pin; \ - struct irq_pin_list *entry = irq_2_pin + irq; \ - \ - for (;;) { \ - unsigned int reg; \ - pin = entry->pin; \ - if (pin == -1) \ - break; \ - reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \ - reg ACTION; \ - io_apic_modify(entry->apic, reg); \ - if (!entry->next) \ - break; \ - entry = irq_2_pin + entry->next; \ - } \ - FINAL; \ -} #define DO_ACTION(name,R,ACTION, FINAL) \ \ @@ -655,7 +683,7 @@ static inline int IO_APIC_irq_trigger(int irq) } /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ -u8 irq_vector[NR_IRQ_VECTORS] = { FIRST_DEVICE_VECTOR , 0 }; +u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 }; int assign_irq_vector(int irq) { @@ -767,6 +795,7 @@ static void __init setup_IO_APIC_irqs(void) spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); + set_native_irq_info(irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); } } @@ -1314,6 +1343,7 @@ static unsigned int startup_edge_ioapic_irq(unsigned int irq) */ static void ack_edge_ioapic_irq(unsigned int irq) { + move_irq(irq); if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) == (IRQ_PENDING | IRQ_DISABLED)) mask_IO_APIC_irq(irq); @@ -1343,26 +1373,10 @@ static unsigned int startup_level_ioapic_irq (unsigned int irq) static void end_level_ioapic_irq (unsigned int irq) { + move_irq(irq); ack_APIC_irq(); } -static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask) -{ - unsigned long flags; - unsigned int dest; - - dest = cpu_mask_to_apicid(mask); - - /* - * Only the high 8 bits are valid. - */ - dest = SET_APIC_LOGICAL_ID(dest); - - spin_lock_irqsave(&ioapic_lock, flags); - __DO_ACTION(1, = dest, ) - spin_unlock_irqrestore(&ioapic_lock, flags); -} - #ifdef CONFIG_PCI_MSI static unsigned int startup_edge_ioapic_vector(unsigned int vector) { @@ -1375,6 +1389,7 @@ static void ack_edge_ioapic_vector(unsigned int vector) { int irq = vector_to_irq(vector); + move_native_irq(vector); ack_edge_ioapic_irq(irq); } @@ -1389,6 +1404,7 @@ static void end_level_ioapic_vector (unsigned int vector) { int irq = vector_to_irq(vector); + move_native_irq(vector); end_level_ioapic_irq(irq); } @@ -1406,14 +1422,17 @@ static void unmask_IO_APIC_vector (unsigned int vector) unmask_IO_APIC_irq(irq); } +#ifdef CONFIG_SMP static void set_ioapic_affinity_vector (unsigned int vector, cpumask_t cpu_mask) { int irq = vector_to_irq(vector); + set_native_irq_info(vector, cpu_mask); set_ioapic_affinity_irq(irq, cpu_mask); } -#endif +#endif // CONFIG_SMP +#endif // CONFIG_PCI_MSI /* * Level and edge triggered IO-APIC interrupts need different handling, @@ -1424,7 +1443,7 @@ static void set_ioapic_affinity_vector (unsigned int vector, * races. */ -static struct hw_interrupt_type ioapic_edge_type = { +static struct hw_interrupt_type ioapic_edge_type __read_mostly = { .typename = "IO-APIC-edge", .startup = startup_edge_ioapic, .shutdown = shutdown_edge_ioapic, @@ -1432,10 +1451,12 @@ static struct hw_interrupt_type ioapic_edge_type = { .disable = disable_edge_ioapic, .ack = ack_edge_ioapic, .end = end_edge_ioapic, +#ifdef CONFIG_SMP .set_affinity = set_ioapic_affinity, +#endif }; -static struct hw_interrupt_type ioapic_level_type = { +static struct hw_interrupt_type ioapic_level_type __read_mostly = { .typename = "IO-APIC-level", .startup = startup_level_ioapic, .shutdown = shutdown_level_ioapic, @@ -1443,7 +1464,9 @@ static struct hw_interrupt_type ioapic_level_type = { .disable = disable_level_ioapic, .ack = mask_and_ack_level_ioapic, .end = end_level_ioapic, +#ifdef CONFIG_SMP .set_affinity = set_ioapic_affinity, +#endif }; static inline void init_IO_APIC_traps(void) @@ -1506,7 +1529,7 @@ static void ack_lapic_irq (unsigned int irq) static void end_lapic_irq (unsigned int i) { /* nothing */ } -static struct hw_interrupt_type lapic_irq_type = { +static struct hw_interrupt_type lapic_irq_type __read_mostly = { .typename = "local-APIC-edge", .startup = NULL, /* startup_irq() not used for IRQ0 */ .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ @@ -1918,6 +1941,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); + set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); return 0; @@ -1931,6 +1955,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a * we need to reprogram the ioredtbls to cater for the cpus which have come online * so mask in all cases should simply be TARGET_CPUS */ +#ifdef CONFIG_SMP void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; @@ -1949,3 +1974,4 @@ void __init setup_ioapic_dest(void) } } +#endif diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c index 5c6dc7051482..df08c43276a0 100644 --- a/arch/x86_64/kernel/kprobes.c +++ b/arch/x86_64/kernel/kprobes.c @@ -74,7 +74,7 @@ static inline int is_IF_modifier(kprobe_opcode_t *insn) return 0; } -int arch_prepare_kprobe(struct kprobe *p) +int __kprobes arch_prepare_kprobe(struct kprobe *p) { /* insn: must be on special executable page on x86_64. */ up(&kprobe_mutex); @@ -189,7 +189,7 @@ static inline s32 *is_riprel(u8 *insn) return NULL; } -void arch_copy_kprobe(struct kprobe *p) +void __kprobes arch_copy_kprobe(struct kprobe *p) { s32 *ripdisp; memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE); @@ -215,21 +215,21 @@ void arch_copy_kprobe(struct kprobe *p) p->opcode = *p->addr; } -void arch_arm_kprobe(struct kprobe *p) +void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_disarm_kprobe(struct kprobe *p) +void __kprobes arch_disarm_kprobe(struct kprobe *p) { *p->addr = p->opcode; flush_icache_range((unsigned long) p->addr, (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } -void arch_remove_kprobe(struct kprobe *p) +void __kprobes arch_remove_kprobe(struct kprobe *p) { up(&kprobe_mutex); free_insn_slot(p->ainsn.insn); @@ -261,7 +261,7 @@ static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs) kprobe_saved_rflags &= ~IF_MASK; } -static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) +static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) { regs->eflags |= TF_MASK; regs->eflags &= ~IF_MASK; @@ -272,7 +272,8 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->rip = (unsigned long)p->ainsn.insn; } -void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) +void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) { unsigned long *sara = (unsigned long *)regs->rsp; struct kretprobe_instance *ri; @@ -295,7 +296,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled thorough out this function. */ -int kprobe_handler(struct pt_regs *regs) +int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; int ret = 0; @@ -310,7 +311,8 @@ int kprobe_handler(struct pt_regs *regs) Disarm the probe we just hit, and ignore it. */ p = get_kprobe(addr); if (p) { - if (kprobe_status == KPROBE_HIT_SS) { + if (kprobe_status == KPROBE_HIT_SS && + *p->ainsn.insn == BREAKPOINT_INSTRUCTION) { regs->eflags &= ~TF_MASK; regs->eflags |= kprobe_saved_rflags; unlock_kprobes(); @@ -360,7 +362,10 @@ int kprobe_handler(struct pt_regs *regs) * either a probepoint or a debugger breakpoint * at this address. In either case, no further * handling of this interrupt is appropriate. + * Back up over the (now missing) int3 and run + * the original instruction. */ + regs->rip = (unsigned long)addr; ret = 1; } /* Not one of ours: let kernel handle it */ @@ -399,7 +404,7 @@ no_kprobe: /* * Called when we hit the probe point at kretprobe_trampoline */ -int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -478,7 +483,7 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. */ -static void resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) { unsigned long *tos = (unsigned long *)regs->rsp; unsigned long next_rip = 0; @@ -536,7 +541,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs) * Interrupts are disabled on entry as trap1 is an interrupt gate and they * remain disabled thoroughout this function. And we hold kprobe lock. */ -int post_kprobe_handler(struct pt_regs *regs) +int __kprobes post_kprobe_handler(struct pt_regs *regs) { if (!kprobe_running()) return 0; @@ -571,7 +576,7 @@ out: } /* Interrupts disabled, kprobe_lock held. */ -int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) { if (current_kprobe->fault_handler && current_kprobe->fault_handler(current_kprobe, regs, trapnr)) @@ -590,8 +595,8 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine for handling exceptions. */ -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; switch (val) { @@ -619,7 +624,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, return NOTIFY_DONE; } -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr; @@ -640,7 +645,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) return 1; } -void jprobe_return(void) +void __kprobes jprobe_return(void) { preempt_enable_no_resched(); asm volatile (" xchg %%rbx,%%rsp \n" @@ -651,7 +656,7 @@ void jprobe_return(void) (jprobe_saved_rsp):"memory"); } -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { u8 *addr = (u8 *) (regs->rip - 1); unsigned long stack_addr = (unsigned long)jprobe_saved_rsp; diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c index 64a8e05d5811..caf164959e19 100644 --- a/arch/x86_64/kernel/nmi.c +++ b/arch/x86_64/kernel/nmi.c @@ -463,6 +463,8 @@ void touch_nmi_watchdog (void) */ for (i = 0; i < NR_CPUS; i++) per_cpu(nmi_touch, i) = 1; + + touch_softlockup_watchdog(); } void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason) @@ -522,14 +524,14 @@ asmlinkage void do_nmi(struct pt_regs * regs, long error_code) nmi_enter(); add_pda(__nmi_count,1); - if (!nmi_callback(regs, cpu)) + if (!rcu_dereference(nmi_callback)(regs, cpu)) default_do_nmi(regs); nmi_exit(); } void set_nmi_callback(nmi_callback_t callback) { - nmi_callback = callback; + rcu_assign_pointer(nmi_callback, callback); } void unset_nmi_callback(void) diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 7577f9d7a75d..8661f82ac70b 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -310,6 +310,7 @@ void __show_regs(struct pt_regs * regs) void show_regs(struct pt_regs *regs) { + printk("CPU %d:", smp_processor_id()); __show_regs(regs); show_trace(®s->rsp); } diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index 116a491e2961..b356f8e6adfe 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -65,7 +65,7 @@ * Machine setup.. */ -struct cpuinfo_x86 boot_cpu_data; +struct cpuinfo_x86 boot_cpu_data __read_mostly; unsigned long mmu_cr4_features; diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c index 34082c1cc41e..e3ffcacc8c90 100644 --- a/arch/x86_64/kernel/setup64.c +++ b/arch/x86_64/kernel/setup64.c @@ -36,7 +36,7 @@ struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table }; char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned"))); -unsigned long __supported_pte_mask = ~0UL; +unsigned long __supported_pte_mask __read_mostly = ~0UL; static int do_not_nx __initdata = 0; /* noexec=on|off diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index fa25e39fe54d..90aeccd15190 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -62,13 +62,13 @@ /* Number of siblings per CPU package */ int smp_num_siblings = 1; /* Package ID of each logical CPU */ -u8 phys_proc_id[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; -u8 cpu_core_id[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; +u8 phys_proc_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; +u8 cpu_core_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; EXPORT_SYMBOL(phys_proc_id); EXPORT_SYMBOL(cpu_core_id); /* Bitmask of currently online CPUs */ -cpumask_t cpu_online_map; +cpumask_t cpu_online_map __read_mostly; EXPORT_SYMBOL(cpu_online_map); @@ -88,8 +88,8 @@ struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; /* Set when the idlers are all forked */ int smp_threads_ready; -cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned; -cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned; +cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; +cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); /* diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index 66bf6ddeb0c3..7b6abe058253 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -176,10 +176,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); clock_was_set(); @@ -471,7 +468,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * off) isn't likely to go away much sooner anyway. */ - if ((~time_status & STA_UNSYNC) && xtime.tv_sec > rtc_update && + if (ntp_synced() && xtime.tv_sec > rtc_update && abs(xtime.tv_nsec - 500000000) <= tick_nsec / 2) { set_rtc_mmss(xtime.tv_sec); rtc_update = xtime.tv_sec + 660; @@ -1041,6 +1038,7 @@ static int timer_resume(struct sys_device *dev) write_sequnlock_irqrestore(&xtime_lock,flags); jiffies += sleep_length; wall_jiffies += sleep_length; + touch_softlockup_watchdog(); return 0; } diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c index 6ead433a3885..f238d6078a5a 100644 --- a/arch/x86_64/kernel/traps.c +++ b/arch/x86_64/kernel/traps.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/nmi.h> +#include <linux/kprobes.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -419,8 +420,9 @@ void die_nmi(char *str, struct pt_regs *regs) do_exit(SIGSEGV); } -static void do_trap(int trapnr, int signr, char *str, - struct pt_regs * regs, long error_code, siginfo_t *info) +static void __kprobes do_trap(int trapnr, int signr, char *str, + struct pt_regs * regs, long error_code, + siginfo_t *info) { conditional_sti(regs); @@ -504,7 +506,8 @@ DO_ERROR(18, SIGSEGV, "reserved", reserved) DO_ERROR(12, SIGBUS, "stack segment", stack_segment) DO_ERROR( 8, SIGSEGV, "double fault", double_fault) -asmlinkage void do_general_protection(struct pt_regs * regs, long error_code) +asmlinkage void __kprobes do_general_protection(struct pt_regs * regs, + long error_code) { conditional_sti(regs); @@ -622,7 +625,7 @@ asmlinkage void default_do_nmi(struct pt_regs *regs) io_check_error(reason, regs); } -asmlinkage void do_int3(struct pt_regs * regs, long error_code) +asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code) { if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) { return; @@ -653,7 +656,8 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs) } /* runs on IST stack. */ -asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code) +asmlinkage void __kprobes do_debug(struct pt_regs * regs, + unsigned long error_code) { unsigned long condition; struct task_struct *tsk = current; diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index 2a94f9b60b2d..d4abb07af52d 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS *(.text) SCHED_TEXT LOCK_TEXT + KPROBES_TEXT *(.fixup) *(.gnu.warning) } = 0x9090 diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c index ca914c3bd49c..816732d8858c 100644 --- a/arch/x86_64/mm/fault.c +++ b/arch/x86_64/mm/fault.c @@ -23,6 +23,7 @@ #include <linux/vt_kern.h> /* For unblank_screen() */ #include <linux/compiler.h> #include <linux/module.h> +#include <linux/kprobes.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -294,7 +295,8 @@ int exception_trace = 1; * bit 2 == 0 means kernel, 1 means user-mode * bit 3 == 1 means fault was an instruction fetch */ -asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) +asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long error_code) { struct task_struct *tsk; struct mm_struct *mm; diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 6a156f5692ae..04f7a33e144c 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -22,14 +22,14 @@ #define Dprintk(x...) #endif -struct pglist_data *node_data[MAX_NUMNODES]; +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; bootmem_data_t plat_node_bdata[MAX_NUMNODES]; int memnode_shift; u8 memnodemap[NODEMAPSIZE]; -unsigned char cpu_to_node[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; -cpumask_t node_to_cpumask[MAX_NUMNODES]; +unsigned char cpu_to_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; +cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly; int numa_off __initdata; diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index e07287db5a40..1ac7d5ce7456 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -122,10 +122,7 @@ int do_settimeofday(struct timespec *tv) set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + ntp_clear(); write_sequnlock_irq(&xtime_lock); return 0; } @@ -184,7 +181,7 @@ again: next += CCOUNT_PER_JIFFY; do_timer (regs); /* Linux handler in kernel/timer.c */ - if ((time_status & STA_UNSYNC) == 0 && + if (ntp_synced() && xtime.tv_sec - last_rtc_update >= 659 && abs((xtime.tv_nsec/1000)-(1000000-1000000/HZ))<5000000/HZ && jiffies - wall_jiffies == 1) { |