diff options
Diffstat (limited to 'arch')
206 files changed, 2418 insertions, 2510 deletions
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index eedf41b..9bef61b 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -25,6 +25,10 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_FIND_NEXT_BIT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y @@ -447,6 +451,10 @@ config ALPHA_IRONGATE depends on ALPHA_NAUTILUS default y +config GENERIC_HWEIGHT + bool + default y if !ALPHA_EV6 && !ALPHA_EV67 + config ALPHA_AVANTI bool depends on ALPHA_XL || ALPHA_AVANTI_CH diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 7fb14f4..31afe3d 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -821,7 +821,6 @@ osf_setsysinfo(unsigned long op, void __user *buffer, unsigned long nbytes, affects all sorts of things, like timeval and itimerval. */ extern struct timezone sys_tz; -extern int do_adjtimex(struct timex *); struct timeval32 { diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index b4e5f8f..dd87696 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -34,6 +34,7 @@ #include <linux/root_dev.h> #include <linux/initrd.h> #include <linux/eisa.h> +#include <linux/pfn.h> #ifdef CONFIG_MAGIC_SYSRQ #include <linux/sysrq.h> #include <linux/reboot.h> @@ -42,7 +43,7 @@ #include <asm/setup.h> #include <asm/io.h> -extern struct notifier_block *panic_notifier_list; +extern struct atomic_notifier_head panic_notifier_list; static int alpha_panic_event(struct notifier_block *, unsigned long, void *); static struct notifier_block alpha_panic_block = { alpha_panic_event, @@ -241,9 +242,6 @@ reserve_std_resources(void) request_resource(io, standard_io_resources+i); } -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) #define PFN_MAX PFN_DOWN(0x80000000) #define for_each_mem_cluster(memdesc, cluster, i) \ for ((cluster) = (memdesc)->cluster, (i) = 0; \ @@ -472,11 +470,6 @@ page_is_ram(unsigned long pfn) return 0; } -#undef PFN_UP -#undef PFN_DOWN -#undef PFN_PHYS -#undef PFN_MAX - void __init setup_arch(char **cmdline_p) { @@ -507,7 +500,8 @@ setup_arch(char **cmdline_p) } /* Register a call for panic conditions. */ - notifier_chain_register(&panic_notifier_list, &alpha_panic_block); + atomic_notifier_chain_register(&panic_notifier_list, + &alpha_panic_block); #ifdef CONFIG_ALPHA_GENERIC /* Assume that we've booted from SRM if we haven't booted from MILO. diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index 6b2921b..3859749 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -314,10 +314,11 @@ time_init(void) if (!est_cycle_freq) est_cycle_freq = validate_cc_value(calibrate_cc_with_pit()); - cc1 = rpcc_after_update_in_progress(); + cc1 = rpcc(); /* Calibrate CPU clock -- attempt #2. */ if (!est_cycle_freq) { + cc1 = rpcc_after_update_in_progress(); cc2 = rpcc_after_update_in_progress(); est_cycle_freq = validate_cc_value(cc2 - cc1); cc1 = cc2; diff --git a/arch/alpha/lib/ev6-memchr.S b/arch/alpha/lib/ev6-memchr.S index a8e843d..1a5f71b 100644 --- a/arch/alpha/lib/ev6-memchr.S +++ b/arch/alpha/lib/ev6-memchr.S @@ -84,7 +84,7 @@ $last_quad: beq $2, $not_found # U : U L U L $found_it: -#if defined(__alpha_fix__) && defined(__alpha_cix__) +#ifdef CONFIG_ALPHA_EV67 /* * Since we are guaranteed to have set one of the bits, we don't * have to worry about coming back with a 0x40 out of cttz... diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c index 97c4d9d..05017ba 100644 --- a/arch/alpha/lib/fpreg.c +++ b/arch/alpha/lib/fpreg.c @@ -4,7 +4,7 @@ * (C) Copyright 1998 Linus Torvalds */ -#if defined(__alpha_cix__) || defined(__alpha_fix__) +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) #define STT(reg,val) asm volatile ("ftoit $f"#reg",%0" : "=r"(val)); #else #define STT(reg,val) asm volatile ("stt $f"#reg",%0" : "=m"(val)); @@ -53,7 +53,7 @@ alpha_read_fp_reg (unsigned long reg) return val; } -#if defined(__alpha_cix__) || defined(__alpha_fix__) +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) #define LDT(reg,val) asm volatile ("itoft %0,$f"#reg : : "r"(val)); #else #define LDT(reg,val) asm volatile ("ldt $f"#reg",%0" : : "m"(val)); @@ -98,7 +98,7 @@ alpha_write_fp_reg (unsigned long reg, unsigned long val) } } -#if defined(__alpha_cix__) || defined(__alpha_fix__) +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) #define STS(reg,val) asm volatile ("ftois $f"#reg",%0" : "=r"(val)); #else #define STS(reg,val) asm volatile ("sts $f"#reg",%0" : "=m"(val)); @@ -147,7 +147,7 @@ alpha_read_fp_reg_s (unsigned long reg) return val; } -#if defined(__alpha_cix__) || defined(__alpha_fix__) +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) #define LDS(reg,val) asm volatile ("itofs %0,$f"#reg : : "r"(val)); #else #define LDS(reg,val) asm volatile ("lds $f"#reg",%0" : : "m"(val)); diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 6d52512..bf6b65c 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -13,6 +13,7 @@ #include <linux/bootmem.h> #include <linux/swap.h> #include <linux/initrd.h> +#include <linux/pfn.h> #include <asm/hwrpb.h> #include <asm/pgalloc.h> @@ -27,9 +28,6 @@ bootmem_data_t node_bdata[MAX_NUMNODES]; #define DBGDCONT(args...) #endif -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) #define for_each_mem_cluster(memdesc, cluster, i) \ for ((cluster) = (memdesc)->cluster, (i) = 0; \ (i) < (memdesc)->numclusters; (i)++, (cluster)++) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0dd24eb..9731b3f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -8,6 +8,7 @@ mainmenu "Linux Kernel Configuration" config ARM bool default y + select RTC_LIB help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and @@ -53,6 +54,10 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y @@ -835,6 +840,8 @@ source "drivers/usb/Kconfig" source "drivers/mmc/Kconfig" +source "drivers/rtc/Kconfig" + endmenu source "fs/Kconfig" diff --git a/arch/arm/common/rtctime.c b/arch/arm/common/rtctime.c index e851d86..35c9a64 100644 --- a/arch/arm/common/rtctime.c +++ b/arch/arm/common/rtctime.c @@ -20,6 +20,7 @@ #include <linux/capability.h> #include <linux/device.h> #include <linux/mutex.h> +#include <linux/rtc.h> #include <asm/rtc.h> #include <asm/semaphore.h> @@ -42,89 +43,6 @@ static struct rtc_ops *rtc_ops; #define rtc_epoch 1900UL -static const unsigned char days_in_month[] = { - 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 -}; - -#define LEAPS_THRU_END_OF(y) ((y)/4 - (y)/100 + (y)/400) -#define LEAP_YEAR(year) ((!(year % 4) && (year % 100)) || !(year % 400)) - -static int month_days(unsigned int month, unsigned int year) -{ - return days_in_month[month] + (LEAP_YEAR(year) && month == 1); -} - -/* - * Convert seconds since 01-01-1970 00:00:00 to Gregorian date. - */ -void rtc_time_to_tm(unsigned long time, struct rtc_time *tm) -{ - int days, month, year; - - days = time / 86400; - time -= days * 86400; - - tm->tm_wday = (days + 4) % 7; - - year = 1970 + days / 365; - days -= (year - 1970) * 365 - + LEAPS_THRU_END_OF(year - 1) - - LEAPS_THRU_END_OF(1970 - 1); - if (days < 0) { - year -= 1; - days += 365 + LEAP_YEAR(year); - } - tm->tm_year = year - 1900; - tm->tm_yday = days + 1; - - for (month = 0; month < 11; month++) { - int newdays; - - newdays = days - month_days(month, year); - if (newdays < 0) - break; - days = newdays; - } - tm->tm_mon = month; - tm->tm_mday = days + 1; - - tm->tm_hour = time / 3600; - time -= tm->tm_hour * 3600; - tm->tm_min = time / 60; - tm->tm_sec = time - tm->tm_min * 60; -} -EXPORT_SYMBOL(rtc_time_to_tm); - -/* - * Does the rtc_time represent a valid date/time? - */ -int rtc_valid_tm(struct rtc_time *tm) -{ - if (tm->tm_year < 70 || - tm->tm_mon >= 12 || - tm->tm_mday < 1 || - tm->tm_mday > month_days(tm->tm_mon, tm->tm_year + 1900) || - tm->tm_hour >= 24 || - tm->tm_min >= 60 || - tm->tm_sec >= 60) - return -EINVAL; - - return 0; -} -EXPORT_SYMBOL(rtc_valid_tm); - -/* - * Convert Gregorian date to seconds since 01-01-1970 00:00:00. - */ -int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time) -{ - *time = mktime(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday, - tm->tm_hour, tm->tm_min, tm->tm_sec); - - return 0; -} -EXPORT_SYMBOL(rtc_tm_to_time); - /* * Calculate the next alarm time given the requested alarm time mask * and the current time. @@ -151,13 +69,13 @@ void rtc_next_alarm_time(struct rtc_time *next, struct rtc_time *now, struct rtc } } -static inline int rtc_read_time(struct rtc_ops *ops, struct rtc_time *tm) +static inline int rtc_arm_read_time(struct rtc_ops *ops, struct rtc_time *tm) { memset(tm, 0, sizeof(struct rtc_time)); return ops->read_time(tm); } -static inline int rtc_set_time(struct rtc_ops *ops, struct rtc_time *tm) +static inline int rtc_arm_set_time(struct rtc_ops *ops, struct rtc_time *tm) { int ret; @@ -168,7 +86,7 @@ static inline int rtc_set_time(struct rtc_ops *ops, struct rtc_time *tm) return ret; } -static inline int rtc_read_alarm(struct rtc_ops *ops, struct rtc_wkalrm *alrm) +static inline int rtc_arm_read_alarm(struct rtc_ops *ops, struct rtc_wkalrm *alrm) { int ret = -EINVAL; if (ops->read_alarm) { @@ -178,7 +96,7 @@ static inline int rtc_read_alarm(struct rtc_ops *ops, struct rtc_wkalrm *alrm) return ret; } -static inline int rtc_set_alarm(struct rtc_ops *ops, struct rtc_wkalrm *alrm) +static inline int rtc_arm_set_alarm(struct rtc_ops *ops, struct rtc_wkalrm *alrm) { int ret = -EINVAL; if (ops->set_alarm) @@ -266,7 +184,7 @@ static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, switch (cmd) { case RTC_ALM_READ: - ret = rtc_read_alarm(ops, &alrm); + ret = rtc_arm_read_alarm(ops, &alrm); if (ret) break; ret = copy_to_user(uarg, &alrm.time, sizeof(tm)); @@ -288,11 +206,11 @@ static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, alrm.time.tm_wday = -1; alrm.time.tm_yday = -1; alrm.time.tm_isdst = -1; - ret = rtc_set_alarm(ops, &alrm); + ret = rtc_arm_set_alarm(ops, &alrm); break; case RTC_RD_TIME: - ret = rtc_read_time(ops, &tm); + ret = rtc_arm_read_time(ops, &tm); if (ret) break; ret = copy_to_user(uarg, &tm, sizeof(tm)); @@ -310,7 +228,7 @@ static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, ret = -EFAULT; break; } - ret = rtc_set_time(ops, &tm); + ret = rtc_arm_set_time(ops, &tm); break; case RTC_EPOCH_SET: @@ -341,11 +259,11 @@ static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, ret = -EFAULT; break; } - ret = rtc_set_alarm(ops, &alrm); + ret = rtc_arm_set_alarm(ops, &alrm); break; case RTC_WKALM_RD: - ret = rtc_read_alarm(ops, &alrm); + ret = rtc_arm_read_alarm(ops, &alrm); if (ret) break; ret = copy_to_user(uarg, &alrm, sizeof(alrm)); @@ -435,7 +353,7 @@ static int rtc_read_proc(char *page, char **start, off_t off, int count, int *eo struct rtc_time tm; char *p = page; - if (rtc_read_time(ops, &tm) == 0) { + if (rtc_arm_read_time(ops, &tm) == 0) { p += sprintf(p, "rtc_time\t: %02d:%02d:%02d\n" "rtc_date\t: %04d-%02d-%02d\n" @@ -445,7 +363,7 @@ static int rtc_read_proc(char *page, char **start, off_t off, int count, int *eo rtc_epoch); } - if (rtc_read_alarm(ops, &alrm) == 0) { + if (rtc_arm_read_alarm(ops, &alrm) == 0) { p += sprintf(p, "alrm_time\t: "); if ((unsigned int)alrm.time.tm_hour <= 24) p += sprintf(p, "%02d:", alrm.time.tm_hour); diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S index 838e435..cab355c 100644 --- a/arch/arm/lib/copy_template.S +++ b/arch/arm/lib/copy_template.S @@ -236,7 +236,7 @@ /* - * Abort preanble and completion macros. + * Abort preamble and completion macros. * If a fixup handler is required then those macros must surround it. * It is assumed that the fixup code will handle the private part of * the exit macro. diff --git a/arch/arm/mach-footbridge/time.c b/arch/arm/mach-footbridge/time.c index 2c64a0b..5d02e95 100644 --- a/arch/arm/mach-footbridge/time.c +++ b/arch/arm/mach-footbridge/time.c @@ -34,27 +34,12 @@ static int rtc_base; static unsigned long __init get_isa_cmos_time(void) { unsigned int year, mon, day, hour, min, sec; - int i; // check to see if the RTC makes sense..... if ((CMOS_READ(RTC_VALID) & RTC_VRT) == 0) return mktime(1970, 1, 1, 0, 0, 0); - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - /* read RTC exactly on falling edge of update flag */ - for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */ - if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) - break; - - for (i = 0 ; i < 1000000 ; i++) /* must try at least 2.228 ms */ - if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - break; - - do { /* Isn't this overkill ? UIP above should guarantee consistency */ + do { sec = CMOS_READ(RTC_SECONDS); min = CMOS_READ(RTC_MINUTES); hour = CMOS_READ(RTC_HOURS); diff --git a/arch/arm/mach-integrator/time.c b/arch/arm/mach-integrator/time.c index 3c22c16..bc07f52 100644 --- a/arch/arm/mach-integrator/time.c +++ b/arch/arm/mach-integrator/time.c @@ -40,13 +40,13 @@ static int integrator_set_rtc(void) return 1; } -static int rtc_read_alarm(struct rtc_wkalrm *alrm) +static int integrator_rtc_read_alarm(struct rtc_wkalrm *alrm) { rtc_time_to_tm(readl(rtc_base + RTC_MR), &alrm->time); return 0; } -static inline int rtc_set_alarm(struct rtc_wkalrm *alrm) +static inline int integrator_rtc_set_alarm(struct rtc_wkalrm *alrm) { unsigned long time; int ret; @@ -62,7 +62,7 @@ static inline int rtc_set_alarm(struct rtc_wkalrm *alrm) return ret; } -static int rtc_read_time(struct rtc_time *tm) +static int integrator_rtc_read_time(struct rtc_time *tm) { rtc_time_to_tm(readl(rtc_base + RTC_DR), tm); return 0; @@ -76,7 +76,7 @@ static int rtc_read_time(struct rtc_time *tm) * edge of the 1Hz clock, we must write the time one second * in advance. */ -static inline int rtc_set_time(struct rtc_time *tm) +static inline int integrator_rtc_set_time(struct rtc_time *tm) { unsigned long time; int ret; @@ -90,10 +90,10 @@ static inline int rtc_set_time(struct rtc_time *tm) static struct rtc_ops rtc_ops = { .owner = THIS_MODULE, - .read_time = rtc_read_time, - .set_time = rtc_set_time, - .read_alarm = rtc_read_alarm, - .set_alarm = rtc_set_alarm, + .read_time = integrator_rtc_read_time, + .set_time = integrator_rtc_set_time, + .read_alarm = integrator_rtc_read_alarm, + .set_alarm = integrator_rtc_set_alarm, }; static irqreturn_t arm_rtc_interrupt(int irq, void *dev_id, diff --git a/arch/arm/mach-omap1/board-netstar.c b/arch/arm/mach-omap1/board-netstar.c index 60d5f8a..7520e60 100644 --- a/arch/arm/mach-omap1/board-netstar.c +++ b/arch/arm/mach-omap1/board-netstar.c @@ -141,7 +141,7 @@ static int __init netstar_late_init(void) /* TODO: Setup front panel switch here */ /* Setup panic notifier */ - notifier_chain_register(&panic_notifier_list, &panic_block); + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); return 0; } diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c index bfd5fdd..52e4a9d 100644 --- a/arch/arm/mach-omap1/board-voiceblue.c +++ b/arch/arm/mach-omap1/board-voiceblue.c @@ -235,7 +235,7 @@ static struct notifier_block panic_block = { static int __init voiceblue_setup(void) { /* Setup panic notifier */ - notifier_chain_register(&panic_notifier_list, &panic_block); + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); return 0; } diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c index 9b48a90..5efa847 100644 --- a/arch/arm/mach-pxa/generic.c +++ b/arch/arm/mach-pxa/generic.c @@ -319,6 +319,11 @@ void __init pxa_set_ficp_info(struct pxaficp_platform_data *info) pxaficp_device.dev.platform_data = info; } +static struct platform_device pxartc_device = { + .name = "sa1100-rtc", + .id = -1, +}; + static struct platform_device *devices[] __initdata = { &pxamci_device, &udc_device, @@ -329,6 +334,7 @@ static struct platform_device *devices[] __initdata = { &pxaficp_device, &i2c_device, &i2s_device, + &pxartc_device, }; static int __init pxa_init(void) diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c index 2abdc41..9ea7155 100644 --- a/arch/arm/mach-sa1100/generic.c +++ b/arch/arm/mach-sa1100/generic.c @@ -324,6 +324,11 @@ void sa11x0_set_irda_data(struct irda_platform_data *irda) sa11x0ir_device.dev.platform_data = irda; } +static struct platform_device sa11x0rtc_device = { + .name = "sa1100-rtc", + .id = -1, +}; + static struct platform_device *sa11x0_devices[] __initdata = { &sa11x0udc_device, &sa11x0uart1_device, @@ -333,6 +338,7 @@ static struct platform_device *sa11x0_devices[] __initdata = { &sa11x0pcmcia_device, &sa11x0fb_device, &sa11x0mtd_device, + &sa11x0rtc_device, }; static int __init sa1100_init(void) diff --git a/arch/arm26/Kconfig b/arch/arm26/Kconfig index dee23d8..cf4ebf4 100644 --- a/arch/arm26/Kconfig +++ b/arch/arm26/Kconfig @@ -41,6 +41,10 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/arm26/kernel/traps.c b/arch/arm26/kernel/traps.c index 5847ea5..a79de04 100644 --- a/arch/arm26/kernel/traps.c +++ b/arch/arm26/kernel/traps.c @@ -34,7 +34,7 @@ #include <asm/system.h> #include <asm/uaccess.h> #include <asm/unistd.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include "ptrace.h" @@ -207,19 +207,19 @@ void die_if_kernel(const char *str, struct pt_regs *regs, int err) die(str, regs, err); } -static DECLARE_MUTEX(undef_sem); +static DEFINE_MUTEX(undef_mutex); static int (*undef_hook)(struct pt_regs *); int request_undef_hook(int (*fn)(struct pt_regs *)) { int ret = -EBUSY; - down(&undef_sem); + mutex_lock(&undef_mutex); if (undef_hook == NULL) { undef_hook = fn; ret = 0; } - up(&undef_sem); + mutex_unlock(&undef_mutex); return ret; } @@ -228,12 +228,12 @@ int release_undef_hook(int (*fn)(struct pt_regs *)) { int ret = -EINVAL; - down(&undef_sem); + mutex_lock(&undef_mutex); if (undef_hook == fn) { undef_hook = NULL; ret = 0; } - up(&undef_sem); + mutex_unlock(&undef_mutex); return ret; } diff --git a/arch/arm26/mm/init.c b/arch/arm26/mm/init.c index e3ecaa4..7da8a52 100644 --- a/arch/arm26/mm/init.c +++ b/arch/arm26/mm/init.c @@ -23,6 +23,7 @@ #include <linux/initrd.h> #include <linux/bootmem.h> #include <linux/blkdev.h> +#include <linux/pfn.h> #include <asm/segment.h> #include <asm/mach-types.h> @@ -101,12 +102,6 @@ struct node_info { int bootmap_pages; }; -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_UP(x) (PAGE_ALIGN(x) >> PAGE_SHIFT) -#define PFN_SIZE(x) ((x) >> PAGE_SHIFT) -#define PFN_RANGE(s,e) PFN_SIZE(PAGE_ALIGN((unsigned long)(e)) - \ - (((unsigned long)(s)) & PAGE_MASK)) - /* * FIXME: We really want to avoid allocating the bootmap bitmap * over the top of the initrd. Hopefully, this is located towards diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index b832619..856b665 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -16,6 +16,14 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c index 1ba57ef..619a6ee 100644 --- a/arch/cris/kernel/setup.c +++ b/arch/cris/kernel/setup.c @@ -18,6 +18,7 @@ #include <linux/seq_file.h> #include <linux/tty.h> #include <linux/utsname.h> +#include <linux/pfn.h> #include <asm/setup.h> @@ -88,10 +89,6 @@ setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) &_edata; init_mm.brk = (unsigned long) &_end; -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) - /* min_low_pfn points to the start of DRAM, start_pfn points * to the first DRAM pages after the kernel, and max_low_pfn * to the end of DRAM. diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index e083837..95a3892 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -17,6 +17,10 @@ config GENERIC_FIND_NEXT_BIT bool default y +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default n diff --git a/arch/frv/mm/mmu-context.c b/arch/frv/mm/mmu-context.c index f2c6866..1530a411 100644 --- a/arch/frv/mm/mmu-context.c +++ b/arch/frv/mm/mmu-context.c @@ -54,9 +54,9 @@ static unsigned get_cxn(mm_context_t *ctx) /* find the first unallocated context number * - 0 is reserved for the kernel */ - cxn = find_next_zero_bit(&cxn_bitmap, NR_CXN, 1); + cxn = find_next_zero_bit(cxn_bitmap, NR_CXN, 1); if (cxn < NR_CXN) { - set_bit(cxn, &cxn_bitmap); + set_bit(cxn, cxn_bitmap); } else { /* none remaining - need to steal someone else's cxn */ @@ -138,7 +138,7 @@ void destroy_context(struct mm_struct *mm) cxn_pinned = -1; list_del_init(&ctx->id_link); - clear_bit(ctx->id, &cxn_bitmap); + clear_bit(ctx->id, cxn_bitmap); __flush_tlb_mm(ctx->id); ctx->id = 0; } diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 98308b0..cabf0bf 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -29,6 +29,14 @@ config RWSEM_XCHGADD_ALGORITHM bool default n +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index b008fb0..f17bd1d 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -37,6 +37,10 @@ config GENERIC_IOMAP bool default y +config GENERIC_HWEIGHT + bool + default y + config ARCH_MAY_HAVE_PC_FDC bool default y @@ -227,6 +231,15 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + default y + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + source "kernel/Kconfig.preempt" config X86_UP_APIC diff --git a/arch/i386/Makefile b/arch/i386/Makefile index c848a5b..3e4adb1 100644 --- a/arch/i386/Makefile +++ b/arch/i386/Makefile @@ -103,7 +103,7 @@ AFLAGS += $(mflags-y) boot := arch/i386/boot PHONY += zImage bzImage compressed zlilo bzlilo \ - zdisk bzdisk fdimage fdimage144 fdimage288 install + zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install all: bzImage @@ -122,7 +122,7 @@ zlilo bzlilo: vmlinux zdisk bzdisk: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk -fdimage fdimage144 fdimage288: vmlinux +fdimage fdimage144 fdimage288 isoimage: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@ install: @@ -139,6 +139,9 @@ define archhelp echo ' install to $$(INSTALL_PATH) and run lilo' echo ' bzdisk - Create a boot floppy in /dev/fd0' echo ' fdimage - Create a boot floppy image' + echo ' isoimage - Create a boot CD-ROM image' endef -CLEAN_FILES += arch/$(ARCH)/boot/fdimage arch/$(ARCH)/boot/mtools.conf +CLEAN_FILES += arch/$(ARCH)/boot/fdimage \ + arch/$(ARCH)/boot/image.iso \ + arch/$(ARCH)/boot/mtools.conf diff --git a/arch/i386/boot/Makefile b/arch/i386/boot/Makefile index f136752..33e5547 100644 --- a/arch/i386/boot/Makefile +++ b/arch/i386/boot/Makefile @@ -62,8 +62,12 @@ $(obj)/setup $(obj)/bootsect: %: %.o FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed IMAGE_OFFSET=$(IMAGE_OFFSET) $@ -# Set this if you want to pass append arguments to the zdisk/fdimage kernel +# Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel FDARGS = +# Set this if you want an initrd included with the zdisk/fdimage/isoimage kernel +FDINITRD = + +image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,) $(obj)/mtools.conf: $(src)/mtools.conf.in sed -e 's|@OBJ@|$(obj)|g' < $< > $@ @@ -72,8 +76,11 @@ $(obj)/mtools.conf: $(src)/mtools.conf.in zdisk: $(BOOTIMAGE) $(obj)/mtools.conf MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync syslinux /dev/fd0 ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(src)/mtools.conf mcopy - a:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) a:linux ; sync # These require being root or having syslinux 2.02 or higher installed @@ -81,18 +88,39 @@ fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440 MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - v:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) v:linux ; sync fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880 MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - w:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) w:linux ; sync +isoimage: $(BOOTIMAGE) + -rm -rf $(obj)/isoimage + mkdir $(obj)/isoimage + cp `echo /usr/lib*/syslinux/isolinux.bin | awk '{ print $1; }'` \ + $(obj)/isoimage + cp $(BOOTIMAGE) $(obj)/isoimage/linux + echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \ + fi + mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \ + -no-emul-boot -boot-load-size 4 -boot-info-table \ + $(obj)/isoimage + rm -rf $(obj)/isoimage + zlilo: $(BOOTIMAGE) if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S index 2ac40c8..0000a26 100644 --- a/arch/i386/boot/video.S +++ b/arch/i386/boot/video.S @@ -1924,6 +1924,7 @@ skip10: movb %ah, %al ret store_edid: +#ifdef CONFIG_FB_FIRMWARE_EDID pushw %es # just save all registers pushw %ax pushw %bx @@ -1954,6 +1955,7 @@ store_edid: popw %bx popw %ax popw %es +#endif ret # VIDEO_SELECT-only variables diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index f1a2194..0330661 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -668,10 +668,10 @@ unsigned long __init acpi_find_rsdp(void) unsigned long rsdp_phys = 0; if (efi_enabled) { - if (efi.acpi20) - return __pa(efi.acpi20); - else if (efi.acpi) - return __pa(efi.acpi); + if (efi.acpi20 != EFI_INVALID_TABLE_ADDR) + return efi.acpi20; + else if (efi.acpi != EFI_INVALID_TABLE_ADDR) + return efi.acpi; } /* * Scan memory looking for the RSDP signature. First search EBDA (low diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 7e3d6b6..a06a490 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -266,7 +266,7 @@ static void __init early_cpu_detect(void) void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; - int junk; + int ebx; if (have_cpuid_p()) { /* Get vendor name */ @@ -282,7 +282,7 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) /* Intel-defined flags: level 0x00000001 */ if ( c->cpuid_level >= 0x00000001 ) { u32 capability, excap; - cpuid(0x00000001, &tfms, &junk, &excap, &capability); + cpuid(0x00000001, &tfms, &ebx, &excap, &capability); c->x86_capability[0] = capability; c->x86_capability[4] = excap; c->x86 = (tfms >> 8) & 15; @@ -292,6 +292,11 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; c->x86_mask = tfms & 15; +#ifdef CONFIG_SMP + c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); +#else + c->apicid = (ebx >> 24) & 0xFF; +#endif } else { /* Have CPUID level 0 only - unheard of */ c->x86 = 4; @@ -474,7 +479,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) cpuid(1, &eax, &ebx, &ecx, &edx); - c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index e5bc064..712a26b 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -40,6 +40,7 @@ #ifdef CONFIG_X86_POWERNOW_K8_ACPI #include <linux/acpi.h> +#include <linux/mutex.h> #include <acpi/processor.h> #endif @@ -49,7 +50,7 @@ #include "powernow-k8.h" /* serialize freq changes */ -static DECLARE_MUTEX(fidvid_sem); +static DEFINE_MUTEX(fidvid_mutex); static struct powernow_k8_data *powernow_data[NR_CPUS]; @@ -943,17 +944,17 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate)) goto err_out; - down(&fidvid_sem); + mutex_lock(&fidvid_mutex); powernow_k8_acpi_pst_values(data, newstate); if (transition_frequency(data, newstate)) { printk(KERN_ERR PFX "transition frequency failed\n"); ret = 1; - up(&fidvid_sem); + mutex_unlock(&fidvid_mutex); goto err_out; } - up(&fidvid_sem); + mutex_unlock(&fidvid_mutex); pol->cur = find_khz_freq_from_fid(data->currfid); ret = 0; @@ -1094,10 +1095,15 @@ static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) static unsigned int powernowk8_get (unsigned int cpu) { - struct powernow_k8_data *data = powernow_data[cpu]; + struct powernow_k8_data *data; cpumask_t oldmask = current->cpus_allowed; unsigned int khz = 0; + data = powernow_data[first_cpu(cpu_core_map[cpu])]; + + if (!data) + return -EINVAL; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu); diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h index 00ea899c..79a7c5c 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h @@ -182,10 +182,6 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); -#ifndef for_each_cpu_mask -#define for_each_cpu_mask(i,mask) for (i=0;i<1;i++) -#endif - #ifdef CONFIG_SMP static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[]) { diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index ce61921..9df87b0 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -173,6 +173,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */ unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ + unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; +#ifdef CONFIG_SMP + unsigned int cpu = (c == &boot_cpu_data) ? 0 : (c - cpu_data); +#endif if (c->cpuid_level > 3) { static int is_initialized; @@ -205,9 +209,15 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) break; case 2: new_l2 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l2_id = c->apicid >> index_msb; break; case 3: new_l3 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l3_id = c->apicid >> index_msb; break; default: break; @@ -215,11 +225,19 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) } } } - if (c->cpuid_level > 1) { + /* + * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for + * trace cache + */ + if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) { /* supports eax=2 call */ int i, j, n; int regs[4]; unsigned char *dp = (unsigned char *)regs; + int only_trace = 0; + + if (num_cache_leaves != 0 && c->x86 == 15) + only_trace = 1; /* Number of times to iterate */ n = cpuid_eax(2) & 0xFF; @@ -241,6 +259,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) while (cache_table[k].descriptor != 0) { if (cache_table[k].descriptor == des) { + if (only_trace && cache_table[k].cache_type != LVL_TRACE) + break; switch (cache_table[k].cache_type) { case LVL_1_INST: l1i += cache_table[k].size; @@ -266,34 +286,45 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) } } } + } - if (new_l1d) - l1d = new_l1d; + if (new_l1d) + l1d = new_l1d; - if (new_l1i) - l1i = new_l1i; + if (new_l1i) + l1i = new_l1i; - if (new_l2) - l2 = new_l2; + if (new_l2) { + l2 = new_l2; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l2_id; +#endif + } - if (new_l3) - l3 = new_l3; + if (new_l3) { + l3 = new_l3; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l3_id; +#endif + } - if ( trace ) - printk (KERN_INFO "CPU: Trace cache: %dK uops", trace); - else if ( l1i ) - printk (KERN_INFO "CPU: L1 I cache: %dK", l1i); - if ( l1d ) - printk(", L1 D cache: %dK\n", l1d); - else - printk("\n"); - if ( l2 ) - printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); - if ( l3 ) - printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); + if (trace) + printk (KERN_INFO "CPU: Trace cache: %dK uops", trace); + else if ( l1i ) + printk (KERN_INFO "CPU: L1 I cache: %dK", l1i); - c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); - } + if (l1d) + printk(", L1 D cache: %dK\n", l1d); + else + printk("\n"); + + if (l2) + printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); + + if (l3) + printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); + + c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); return l2; } diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 3b4618b..fff90bd 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -36,6 +36,7 @@ #include <linux/pci.h> #include <linux/smp.h> #include <linux/cpu.h> +#include <linux/mutex.h> #include <asm/mtrr.h> @@ -47,7 +48,7 @@ u32 num_var_ranges = 0; unsigned int *usage_table; -static DECLARE_MUTEX(mtrr_sem); +static DEFINE_MUTEX(mtrr_mutex); u32 size_or_mask, size_and_mask; @@ -333,7 +334,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); /* Search for existing MTRR */ - down(&mtrr_sem); + mutex_lock(&mtrr_mutex); for (i = 0; i < num_var_ranges; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (base >= lbase + lsize) @@ -371,7 +372,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, printk(KERN_INFO "mtrr: no more MTRRs available\n"); error = i; out: - up(&mtrr_sem); + mutex_unlock(&mtrr_mutex); unlock_cpu_hotplug(); return error; } @@ -464,7 +465,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); - down(&mtrr_sem); + mutex_lock(&mtrr_mutex); if (reg < 0) { /* Search for existing MTRR */ for (i = 0; i < max; ++i) { @@ -503,7 +504,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) set_mtrr(reg, 0, 0, 0); error = reg; out: - up(&mtrr_sem); + mutex_unlock(&mtrr_mutex); unlock_cpu_hotplug(); return error; } @@ -685,7 +686,7 @@ void mtrr_ap_init(void) if (!mtrr_if || !use_intel()) return; /* - * Ideally we should hold mtrr_sem here to avoid mtrr entries changed, + * Ideally we should hold mtrr_mutex here to avoid mtrr entries changed, * but this routine will be called in cpu boot time, holding the lock * breaks it. This routine is called in two cases: 1.very earily time * of software resume, when there absolutely isn't mtrr entry changes; diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index ebc8dc116..5efceeb 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/dmi.h> +#include <linux/efi.h> #include <linux/bootmem.h> #include <linux/slab.h> #include <asm/dmi.h> @@ -185,47 +186,72 @@ static void __init dmi_decode(struct dmi_header *dm) } } -void __init dmi_scan_machine(void) +static int __init dmi_present(char __iomem *p) { u8 buf[15]; - char __iomem *p, *q; + memcpy_fromio(buf, p, 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]; - /* - * 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"); + /* + * 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 0; + } + return 1; +} - if (dmi_table(base,len, num, dmi_decode) == 0) +void __init dmi_scan_machine(void) +{ + char __iomem *p, *q; + int rc; + + if (efi_enabled) { + if (efi.smbios == EFI_INVALID_TABLE_ADDR) + goto out; + + /* This is called as a core_initcall() because it isn't + * needed during early boot. This also means we can + * iounmap the space when we're done with it. + */ + p = dmi_ioremap(efi.smbios, 32); + if (p == NULL) + goto out; + + rc = dmi_present(p + 0x10); /* offset of _DMI_ string */ + dmi_iounmap(p, 32); + if (!rc) + return; + } + else { + /* + * 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 = dmi_ioremap(0xF0000, 0x10000); + if (p == NULL) + goto out; + + for (q = p; q < p + 0x10000; q += 16) { + rc = dmi_present(q); + if (!rc) return; } } - -out: printk(KERN_INFO "DMI not present or invalid.\n"); + out: printk(KERN_INFO "DMI not present or invalid.\n"); } - /** * dmi_check_system - check system DMI data * @list: array of dmi_system_id structures to match against diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c index 7ec6cfa..9202b67 100644 --- a/arch/i386/kernel/efi.c +++ b/arch/i386/kernel/efi.c @@ -361,7 +361,7 @@ void __init efi_init(void) */ c16 = (efi_char16_t *) boot_ioremap(efi.systab->fw_vendor, 2); if (c16) { - for (i = 0; i < sizeof(vendor) && *c16; ++i) + for (i = 0; i < (sizeof(vendor) - 1) && *c16; ++i) vendor[i] = *c16++; vendor[i] = '\0'; } else @@ -381,29 +381,38 @@ void __init efi_init(void) if (config_tables == NULL) printk(KERN_ERR PFX "Could not map EFI Configuration Table!\n"); + efi.mps = EFI_INVALID_TABLE_ADDR; + efi.acpi = EFI_INVALID_TABLE_ADDR; + efi.acpi20 = EFI_INVALID_TABLE_ADDR; + efi.smbios = EFI_INVALID_TABLE_ADDR; + efi.sal_systab = EFI_INVALID_TABLE_ADDR; + efi.boot_info = EFI_INVALID_TABLE_ADDR; + efi.hcdp = EFI_INVALID_TABLE_ADDR; + efi.uga = EFI_INVALID_TABLE_ADDR; + for (i = 0; i < num_config_tables; i++) { if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) { - efi.mps = (void *)config_tables[i].table; + efi.mps = config_tables[i].table; printk(KERN_INFO " MPS=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) { - efi.acpi20 = __va(config_tables[i].table); + efi.acpi20 = config_tables[i].table; printk(KERN_INFO " ACPI 2.0=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) { - efi.acpi = __va(config_tables[i].table); + efi.acpi = config_tables[i].table; printk(KERN_INFO " ACPI=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) { - efi.smbios = (void *) config_tables[i].table; + efi.smbios = config_tables[i].table; printk(KERN_INFO " SMBIOS=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) { - efi.hcdp = (void *)config_tables[i].table; + efi.hcdp = config_tables[i].table; printk(KERN_INFO " HCDP=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, UGA_IO_PROTOCOL_GUID) == 0) { - efi.uga = (void *)config_tables[i].table; + efi.uga = config_tables[i].table; printk(KERN_INFO " UGA=0x%lx ", config_tables[i].table); } } diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 311b4e7..3b329af 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -381,7 +381,7 @@ static void do_irq_balance(void) unsigned long imbalance = 0; cpumask_t allowed_mask, target_cpu_mask, tmp; - for_each_cpu(i) { + for_each_possible_cpu(i) { int package_index; CPU_IRQ(i) = 0; if (!cpu_online(i)) @@ -632,7 +632,7 @@ static int __init balanced_irq_init(void) else printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq"); failed: - for_each_cpu(i) { + for_each_possible_cpu(i) { kfree(irq_cpu_data[i].irq_delta); irq_cpu_data[i].irq_delta = NULL; kfree(irq_cpu_data[i].last_irq); diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index 7a59050..f197687 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -35,12 +35,56 @@ #include <asm/cacheflush.h> #include <asm/kdebug.h> #include <asm/desc.h> +#include <asm/uaccess.h> void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); +/* insert a jmp code */ +static inline void set_jmp_op(void *from, void *to) +{ + struct __arch_jmp_op { + char op; + long raddr; + } __attribute__((packed)) *jop; + jop = (struct __arch_jmp_op *)from; + jop->raddr = (long)(to) - ((long)(from) + 5); + jop->op = RELATIVEJUMP_INSTRUCTION; +} + +/* + * returns non-zero if opcodes can be boosted. + */ +static inline int can_boost(kprobe_opcode_t opcode) +{ + switch (opcode & 0xf0 ) { + case 0x70: + return 0; /* can't boost conditional jump */ + case 0x90: + /* can't boost call and pushf */ + return opcode != 0x9a && opcode != 0x9c; + case 0xc0: + /* can't boost undefined opcodes and soft-interruptions */ + return (0xc1 < opcode && opcode < 0xc6) || + (0xc7 < opcode && opcode < 0xcc) || opcode == 0xcf; + case 0xd0: + /* can boost AA* and XLAT */ + return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7); + case 0xe0: + /* can boost in/out and (may be) jmps */ + return (0xe3 < opcode && opcode != 0xe8); + case 0xf0: + /* clear and set flags can be boost */ + return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); + default: + /* currently, can't boost 2 bytes opcodes */ + return opcode != 0x0f; + } +} + + /* * returns non-zero if opcode modifies the interrupt flag. */ @@ -65,6 +109,11 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; + if (can_boost(p->opcode)) { + p->ainsn.boostable = 0; + } else { + p->ainsn.boostable = -1; + } return 0; } @@ -155,9 +204,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; int ret = 0; - kprobe_opcode_t *addr = NULL; - unsigned long *lp; + kprobe_opcode_t *addr; struct kprobe_ctlblk *kcb; +#ifdef CONFIG_PREEMPT + unsigned pre_preempt_count = preempt_count(); +#endif /* CONFIG_PREEMPT */ + + addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t)); /* * We don't want to be preempted for the entire @@ -166,17 +219,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_disable(); kcb = get_kprobe_ctlblk(); - /* Check if the application is using LDT entry for its code segment and - * calculate the address by reading the base address from the LDT entry. - */ - if ((regs->xcs & 4) && (current->mm)) { - lp = (unsigned long *) ((unsigned long)((regs->xcs >> 3) * 8) - + (char *) current->mm->context.ldt); - addr = (kprobe_opcode_t *) (get_desc_base(lp) + regs->eip - - sizeof(kprobe_opcode_t)); - } else { - addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t)); - } /* Check we're not actually recursing */ if (kprobe_running()) { p = get_kprobe(addr); @@ -252,6 +294,21 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) /* handler has already set things up, so skip ss setup */ return 1; + if (p->ainsn.boostable == 1 && +#ifdef CONFIG_PREEMPT + !(pre_preempt_count) && /* + * This enables booster when the direct + * execution path aren't preempted. + */ +#endif /* CONFIG_PREEMPT */ + !p->post_handler && !p->break_handler ) { + /* Boost up -- we can execute copied instructions directly */ + reset_current_kprobe(); + regs->eip = (unsigned long)p->ainsn.insn; + preempt_enable_no_resched(); + return 1; + } + ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; @@ -267,17 +324,44 @@ no_kprobe: * here. When a retprobed function returns, this probe is hit and * trampoline_probe_handler() runs, calling the kretprobe's handler. */ - void kretprobe_trampoline_holder(void) + void __kprobes kretprobe_trampoline_holder(void) { - asm volatile ( ".global kretprobe_trampoline\n" + asm volatile ( ".global kretprobe_trampoline\n" "kretprobe_trampoline: \n" - "nop\n"); - } + " pushf\n" + /* skip cs, eip, orig_eax, es, ds */ + " subl $20, %esp\n" + " pushl %eax\n" + " pushl %ebp\n" + " pushl %edi\n" + " pushl %esi\n" + " pushl %edx\n" + " pushl %ecx\n" + " pushl %ebx\n" + " movl %esp, %eax\n" + " call trampoline_handler\n" + /* move eflags to cs */ + " movl 48(%esp), %edx\n" + " movl %edx, 44(%esp)\n" + /* save true return address on eflags */ + " movl %eax, 48(%esp)\n" + " popl %ebx\n" + " popl %ecx\n" + " popl %edx\n" + " popl %esi\n" + " popl %edi\n" + " popl %ebp\n" + " popl %eax\n" + /* skip eip, orig_eax, es, ds */ + " addl $16, %esp\n" + " popf\n" + " ret\n"); +} /* - * Called when we hit the probe point at kretprobe_trampoline + * Called from kretprobe_trampoline */ -int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -306,8 +390,11 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) /* another task is sharing our hash bucket */ continue; - if (ri->rp && ri->rp->handler) + if (ri->rp && ri->rp->handler){ + __get_cpu_var(current_kprobe) = &ri->rp->kp; ri->rp->handler(ri, regs); + __get_cpu_var(current_kprobe) = NULL; + } orig_ret_address = (unsigned long)ri->ret_addr; recycle_rp_inst(ri); @@ -322,18 +409,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) } BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); - regs->eip = orig_ret_address; - reset_current_kprobe(); spin_unlock_irqrestore(&kretprobe_lock, flags); - preempt_enable_no_resched(); - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler - * to run (and have re-enabled preemption) - */ - return 1; + return (void*)orig_ret_address; } /* @@ -357,15 +436,17 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * 2) If the single-stepped instruction was a call, the return address * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. + * + * This function also checks instruction size for preparing direct execution. */ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { unsigned long *tos = (unsigned long *)®s->esp; - unsigned long next_eip = 0; unsigned long copy_eip = (unsigned long)p->ainsn.insn; unsigned long orig_eip = (unsigned long)p->addr; + regs->eflags &= ~TF_MASK; switch (p->ainsn.insn[0]) { case 0x9c: /* pushfl */ *tos &= ~(TF_MASK | IF_MASK); @@ -375,37 +456,51 @@ static void __kprobes resume_execution(struct kprobe *p, case 0xcb: case 0xc2: case 0xca: - regs->eflags &= ~TF_MASK; - /* eip is already adjusted, no more changes required*/ - return; + case 0xea: /* jmp absolute -- eip is correct */ + /* eip is already adjusted, no more changes required */ + p->ainsn.boostable = 1; + goto no_change; case 0xe8: /* call relative - Fix return addr */ *tos = orig_eip + (*tos - copy_eip); break; case 0xff: if ((p->ainsn.insn[1] & 0x30) == 0x10) { /* call absolute, indirect */ - /* Fix return addr; eip is correct. */ - next_eip = regs->eip; + /* + * Fix return addr; eip is correct. + * But this is not boostable + */ *tos = orig_eip + (*tos - copy_eip); + goto no_change; } else if (((p->ainsn.insn[1] & 0x31) == 0x20) || /* jmp near, absolute indirect */ ((p->ainsn.insn[1] & 0x31) == 0x21)) { /* jmp far, absolute indirect */ - /* eip is correct. */ - next_eip = regs->eip; + /* eip is correct. And this is boostable */ + p->ainsn.boostable = 1; + goto no_change; } - break; - case 0xea: /* jmp absolute -- eip is correct */ - next_eip = regs->eip; - break; default: break; } - regs->eflags &= ~TF_MASK; - if (next_eip) { - regs->eip = next_eip; - } else { - regs->eip = orig_eip + (regs->eip - copy_eip); + if (p->ainsn.boostable == 0) { + if ((regs->eip > copy_eip) && + (regs->eip - copy_eip) + 5 < MAX_INSN_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + set_jmp_op((void *)regs->eip, + (void *)orig_eip + (regs->eip - copy_eip)); + p->ainsn.boostable = 1; + } else { + p->ainsn.boostable = -1; + } } + + regs->eip = orig_eip + (regs->eip - copy_eip); + +no_change: + return; } /* @@ -453,15 +548,57 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs, kcb); + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the eip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->eip = (unsigned long)cur->addr; regs->eflags |= kcb->kprobe_old_eflags; - - reset_current_kprobe(); + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; } return 0; } @@ -475,6 +612,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch (val) { case DIE_INT3: if (kprobe_handler(args->regs)) @@ -564,12 +704,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } -static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, - .pre_handler = trampoline_probe_handler -}; - int __init arch_init_kprobes(void) { - return register_kprobe(&trampoline_p); + return 0; } diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index 55bc365..e7c138f 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -81,6 +81,7 @@ #include <linux/miscdevice.h> #include <linux/spinlock.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <asm/msr.h> #include <asm/uaccess.h> @@ -114,7 +115,7 @@ MODULE_LICENSE("GPL"); static DEFINE_SPINLOCK(microcode_update_lock); /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ -static DECLARE_MUTEX(microcode_sem); +static DEFINE_MUTEX(microcode_mutex); static void __user *user_buffer; /* user area microcode data buffer */ static unsigned int user_buffer_size; /* it's size */ @@ -444,7 +445,7 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_ return -EINVAL; } - down(µcode_sem); + mutex_lock(µcode_mutex); user_buffer = (void __user *) buf; user_buffer_size = (int) len; @@ -453,31 +454,14 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_ if (!ret) ret = (ssize_t)len; - up(µcode_sem); + mutex_unlock(µcode_mutex); return ret; } -static int microcode_ioctl (struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - /* - * XXX: will be removed after microcode_ctl - * is updated to ignore failure of this ioctl() - */ - case MICROCODE_IOCFREE: - return 0; - default: - return -EINVAL; - } - return -EINVAL; -} - static struct file_operations microcode_fops = { .owner = THIS_MODULE, .write = microcode_write, - .ioctl = microcode_ioctl, .open = microcode_open, }; diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 9074818..d43b498 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -138,12 +138,12 @@ static int __init check_nmi_watchdog(void) if (nmi_watchdog == NMI_LOCAL_APIC) smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); - for_each_cpu(cpu) + for_each_possible_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); mdelay((10*1000)/nmi_hz); // wait 10 ticks - for_each_cpu(cpu) { + for_each_possible_cpu(cpu) { #ifdef CONFIG_SMP /* Check cpu_callin_map here because that is set after the timer is started. */ @@ -510,7 +510,7 @@ void touch_nmi_watchdog (void) * Just reset the alert counters, (other CPUs might be * spinning on locks we hold): */ - for_each_cpu(i) + for_each_possible_cpu(i) alert_counter[i] = 0; /* @@ -529,7 +529,8 @@ void nmi_watchdog_tick (struct pt_regs * regs) * always switch the stack NMI-atomically, it's safe to use * smp_processor_id(). */ - int sum, cpu = smp_processor_id(); + unsigned int sum; + int cpu = smp_processor_id(); sum = per_cpu(irq_stat, cpu).apic_timer_irqs; diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 299e616..24b3e74 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -38,7 +38,6 @@ #include <linux/kallsyms.h> #include <linux/ptrace.h> #include <linux/random.h> -#include <linux/kprobes.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -364,13 +363,6 @@ void exit_thread(void) struct task_struct *tsk = current; struct thread_struct *t = &tsk->thread; - /* - * Remove function-return probe instances associated with this task - * and put them back on the free list. Do not insert an exit probe for - * this function, it will be disabled by kprobe_flush_task if you do. - */ - kprobe_flush_task(tsk); - /* The process may have allocated an io port bitmap... nuke it. */ if (unlikely(NULL != t->io_bitmap_ptr)) { int cpu = get_cpu(); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index d313a11..8c08660 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -46,6 +46,7 @@ #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/dmi.h> +#include <linux/pfn.h> #include <video/edid.h> @@ -1058,10 +1059,10 @@ static int __init free_available_memory(unsigned long start, unsigned long end, void *arg) { /* check max_low_pfn */ - if (start >= ((max_low_pfn + 1) << PAGE_SHIFT)) + if (start >= (max_low_pfn << PAGE_SHIFT)) return 0; - if (end >= ((max_low_pfn + 1) << PAGE_SHIFT)) - end = (max_low_pfn + 1) << PAGE_SHIFT; + if (end >= (max_low_pfn << PAGE_SHIFT)) + end = max_low_pfn << PAGE_SHIFT; if (start < end) free_bootmem(start, end - start); @@ -1286,8 +1287,6 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat probe_roms(); for (i = 0; i < e820.nr_map; i++) { struct resource *res; - if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) - continue; res = kzalloc(sizeof(struct resource), GFP_ATOMIC); switch (e820.map[i].type) { case E820_RAM: res->name = "System RAM"; break; diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 82371d8..a696990 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -72,6 +72,9 @@ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; /* Core ID of each logical CPU */ int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; +/* Last level cache ID of each logical CPU */ +int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; + /* representing HT siblings of each logical CPU */ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_sibling_map); @@ -440,6 +443,18 @@ static void __devinit smp_callin(void) static int cpucount; +/* maps the cpu to the sched domain representing multi-core */ +cpumask_t cpu_coregroup_map(int cpu) +{ + struct cpuinfo_x86 *c = cpu_data + cpu; + /* + * For perf, we return last level cache shared map. + * TBD: when power saving sched policy is added, we will return + * cpu_core_map when power saving policy is enabled + */ + return c->llc_shared_map; +} + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -459,12 +474,16 @@ set_cpu_sibling_map(int cpu) cpu_set(cpu, cpu_sibling_map[i]); cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } + cpu_set(cpu, c[cpu].llc_shared_map); + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; c[cpu].booted_cores = 1; @@ -472,6 +491,11 @@ set_cpu_sibling_map(int cpu) } for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (cpu_llc_id[cpu] != BAD_APICID && + cpu_llc_id[cpu] == cpu_llc_id[i]) { + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); + } if (phys_proc_id[cpu] == phys_proc_id[i]) { cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index ac687d0..326595f 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -310,3 +310,5 @@ ENTRY(sys_call_table) .long sys_pselect6 .long sys_ppoll .long sys_unshare /* 310 */ + .long sys_set_robust_list + .long sys_get_robust_list diff --git a/arch/i386/kernel/timers/timer_pm.c b/arch/i386/kernel/timers/timer_pm.c index 264edaa..144e94a 100644 --- a/arch/i386/kernel/timers/timer_pm.c +++ b/arch/i386/kernel/timers/timer_pm.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/device.h> #include <linux/init.h> +#include <linux/pci.h> #include <asm/types.h> #include <asm/timer.h> #include <asm/smp.h> @@ -45,24 +46,31 @@ static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED; #define ACPI_PM_MASK 0xFFFFFF /* limit it to 24 bits */ +static int pmtmr_need_workaround __read_mostly = 1; + /*helper function to safely read acpi pm timesource*/ static inline u32 read_pmtmr(void) { - u32 v1=0,v2=0,v3=0; - /* It has been reported that because of various broken - * chipsets (ICH4, PIIX4 and PIIX4E) where the ACPI PM time - * source is not latched, so you must read it multiple - * times to insure a safe value is read. - */ - do { - v1 = inl(pmtmr_ioport); - v2 = inl(pmtmr_ioport); - v3 = inl(pmtmr_ioport); - } while ((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1) - || (v3 > v1 && v3 < v2)); - - /* mask the output to 24 bits */ - return v2 & ACPI_PM_MASK; + if (pmtmr_need_workaround) { + u32 v1, v2, v3; + + /* It has been reported that because of various broken + * chipsets (ICH4, PIIX4 and PIIX4E) where the ACPI PM time + * source is not latched, so you must read it multiple + * times to insure a safe value is read. + */ + do { + v1 = inl(pmtmr_ioport); + v2 = inl(pmtmr_ioport); + v3 = inl(pmtmr_ioport); + } while ((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1) + || (v3 > v1 && v3 < v2)); + + /* mask the output to 24 bits */ + return v2 & ACPI_PM_MASK; + } + + return inl(pmtmr_ioport) & ACPI_PM_MASK; } @@ -263,6 +271,72 @@ struct init_timer_opts __initdata timer_pmtmr_init = { .opts = &timer_pmtmr, }; +#ifdef CONFIG_PCI +/* + * PIIX4 Errata: + * + * The power management timer may return improper results when read. + * Although the timer value settles properly after incrementing, + * while incrementing there is a 3 ns window every 69.8 ns where the + * timer value is indeterminate (a 4.2% chance that the data will be + * incorrect when read). As a result, the ACPI free running count up + * timer specification is violated due to erroneous reads. + */ +static int __init pmtmr_bug_check(void) +{ + static struct pci_device_id gray_list[] __initdata = { + /* these chipsets may have bug. */ + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82801DB_0) }, + { }, + }; + struct pci_dev *dev; + int pmtmr_has_bug = 0; + u8 rev; + + if (cur_timer != &timer_pmtmr || !pmtmr_need_workaround) + return 0; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB_3, NULL); + if (dev) { + pci_read_config_byte(dev, PCI_REVISION_ID, &rev); + /* the bug has been fixed in PIIX4M */ + if (rev < 3) { + printk(KERN_WARNING "* Found PM-Timer Bug on this " + "chipset. Due to workarounds for a bug,\n" + "* this time source is slow. Consider trying " + "other time sources (clock=)\n"); + pmtmr_has_bug = 1; + } + pci_dev_put(dev); + } + + if (pci_dev_present(gray_list)) { + printk(KERN_WARNING "* This chipset may have PM-Timer Bug. Due" + " to workarounds for a bug,\n" + "* this time source is slow. If you are sure your timer" + " does not have\n" + "* this bug, please use \"pmtmr_good\" to disable the " + "workaround\n"); + pmtmr_has_bug = 1; + } + + if (!pmtmr_has_bug) + pmtmr_need_workaround = 0; + + return 0; +} +device_initcall(pmtmr_bug_check); +#endif + +static int __init pmtr_good_setup(char *__str) +{ + pmtmr_need_workaround = 0; + return 1; +} +__setup("pmtmr_good", pmtr_good_setup); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("Power Management Timer (PMTMR) as primary timing source for x86"); diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index de5386b..6b63a5a 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -92,22 +92,21 @@ asmlinkage void spurious_interrupt_bug(void); asmlinkage void machine_check(void); static int kstack_depth_to_print = 24; -struct notifier_block *i386die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); +ATOMIC_NOTIFIER_HEAD(i386die_chain); int register_die_notifier(struct notifier_block *nb) { - int err = 0; - unsigned long flags; - vmalloc_sync_all(); - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&i386die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; + return atomic_notifier_chain_register(&i386die_chain, nb); } EXPORT_SYMBOL(register_die_notifier); +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&i386die_chain, nb); +} +EXPORT_SYMBOL(unregister_die_notifier); + static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) { return p > (void *)tinfo && @@ -386,8 +385,12 @@ void die(const char * str, struct pt_regs * regs, long err) #endif if (nl) printk("\n"); - notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); - show_registers(regs); + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) != + NOTIFY_STOP) + show_registers(regs); + else + regs = NULL; } else printk(KERN_EMERG "Recursive die() failure, output suppressed\n"); @@ -395,6 +398,9 @@ void die(const char * str, struct pt_regs * regs, long err) die.lock_owner = -1; spin_unlock_irqrestore(&die.lock, flags); + if (!regs) + return; + if (kexec_should_crash(current)) crash_kexec(regs); @@ -623,7 +629,7 @@ static DEFINE_SPINLOCK(nmi_print_lock); void die_nmi (struct pt_regs *regs, const char *msg) { - if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 0, SIGINT) == + if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == NOTIFY_STOP) return; @@ -662,7 +668,7 @@ static void default_do_nmi(struct pt_regs * regs) reason = get_nmi_reason(); if (!(reason & 0xc0)) { - if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) + if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; #ifdef CONFIG_X86_LOCAL_APIC @@ -678,7 +684,7 @@ static void default_do_nmi(struct pt_regs * regs) unknown_nmi_error(reason, regs); return; } - if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; if (reason & 0x80) mem_parity_error(reason, regs); diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c index 8165626..70e560a 100644 --- a/arch/i386/mach-voyager/voyager_smp.c +++ b/arch/i386/mach-voyager/voyager_smp.c @@ -1700,7 +1700,7 @@ after_handle_vic_irq(unsigned int irq) printk("VOYAGER SMP: CPU%d lost interrupt %d\n", cpu, irq); - for_each_cpu(real_cpu, mask) { + for_each_possible_cpu(real_cpu, mask) { outb(VIC_CPU_MASQUERADE_ENABLE | real_cpu, VIC_PROCESSOR_ID); diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index c4af963..fe6eb90 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -31,6 +31,7 @@ #include <linux/nodemask.h> #include <linux/module.h> #include <linux/kexec.h> +#include <linux/pfn.h> #include <asm/e820.h> #include <asm/setup.h> @@ -352,17 +353,6 @@ void __init zone_sizes_init(void) { int nid; - /* - * Insert nodes into pgdat_list backward so they appear in order. - * Clobber node 0's links and NULL out pgdat_list before starting. - */ - pgdat_list = NULL; - for (nid = MAX_NUMNODES - 1; nid >= 0; nid--) { - if (!node_online(nid)) - continue; - NODE_DATA(nid)->pgdat_next = pgdat_list; - pgdat_list = NODE_DATA(nid); - } for_each_online_node(nid) { unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c index 9db3242..2889567 100644 --- a/arch/i386/mm/pgtable.c +++ b/arch/i386/mm/pgtable.c @@ -36,7 +36,7 @@ void show_mem(void) printk(KERN_INFO "Mem-info:\n"); show_free_areas(); printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { page = pgdat_page_nr(pgdat, i); diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c index 1accce5..1a2076c 100644 --- a/arch/i386/oprofile/nmi_int.c +++ b/arch/i386/oprofile/nmi_int.c @@ -122,7 +122,7 @@ static void nmi_save_registers(void * dummy) static void free_msrs(void) { int i; - for_each_cpu(i) { + for_each_possible_cpu(i) { kfree(cpu_msrs[i].counters); cpu_msrs[i].counters = NULL; kfree(cpu_msrs[i].controls); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 10b6b9e..edffe25 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -34,6 +34,10 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_FIND_NEXT_BIT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y @@ -42,6 +46,10 @@ config TIME_INTERPOLATION bool default y +config DMI + bool + default y + config EFI bool default y diff --git a/arch/ia64/ia32/ia32priv.h b/arch/ia64/ia32/ia32priv.h index 68ceb4e..ccb98ed 100644 --- a/arch/ia64/ia32/ia32priv.h +++ b/arch/ia64/ia32/ia32priv.h @@ -29,9 +29,9 @@ struct partial_page { struct partial_page *next; /* linked list, sorted by address */ struct rb_node pp_rb; - /* 64K is the largest "normal" page supported by ia64 ABI. So 4K*32 + /* 64K is the largest "normal" page supported by ia64 ABI. So 4K*64 * should suffice.*/ - unsigned int bitmap; + unsigned long bitmap; unsigned int base; }; diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 13e739e..5366b3b 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -25,7 +25,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -2591,78 +2590,4 @@ sys32_setresgid(compat_gid_t rgid, compat_gid_t egid, ssgid = (sgid == (compat_gid_t)-1) ? ((gid_t)-1) : ((gid_t)sgid); return sys_setresgid(srgid, segid, ssgid); } - -/* Handle adjtimex compatibility. */ - -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage long -sys32_adjtimex(struct timex32 *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if(get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if(put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} #endif /* NOTYET */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 09a0dbc..59e871d 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -7,7 +7,7 @@ extra-y := head.o init_task.o vmlinux.lds obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \ salinfo.o semaphore.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \ - unwind.o mca.o mca_asm.o topology.o + unwind.o mca.o mca_asm.o topology.o dmi_scan.o obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o obj-$(CONFIG_IA64_GENERIC) += acpi-ext.o @@ -30,6 +30,7 @@ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o mca_recovery-y += mca_drv.o mca_drv_asm.o +dmi_scan-y += ../../i386/kernel/dmi_scan.o # The gate DSO image is built using a special linker script. targets += gate.so gate-syms.o diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index a4e218c..58c93a3 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -651,9 +651,9 @@ unsigned long __init acpi_find_rsdp(void) { unsigned long rsdp_phys = 0; - if (efi.acpi20) - rsdp_phys = __pa(efi.acpi20); - else if (efi.acpi) + if (efi.acpi20 != EFI_INVALID_TABLE_ADDR) + rsdp_phys = efi.acpi20; + else if (efi.acpi != EFI_INVALID_TABLE_ADDR) printk(KERN_WARNING PREFIX "v1.0/r0.71 tables no longer supported\n"); return rsdp_phys; diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 9990320..12cfedc 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -458,24 +458,33 @@ efi_init (void) printk(KERN_INFO "EFI v%u.%.02u by %s:", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); + efi.mps = EFI_INVALID_TABLE_ADDR; + efi.acpi = EFI_INVALID_TABLE_ADDR; + efi.acpi20 = EFI_INVALID_TABLE_ADDR; + efi.smbios = EFI_INVALID_TABLE_ADDR; + efi.sal_systab = EFI_INVALID_TABLE_ADDR; + efi.boot_info = EFI_INVALID_TABLE_ADDR; + efi.hcdp = EFI_INVALID_TABLE_ADDR; + efi.uga = EFI_INVALID_TABLE_ADDR; + for (i = 0; i < (int) efi.systab->nr_tables; i++) { if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) { - efi.mps = __va(config_tables[i].table); + efi.mps = config_tables[i].table; printk(" MPS=0x%lx", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) { - efi.acpi20 = __va(config_tables[i].table); + efi.acpi20 = config_tables[i].table; printk(" ACPI 2.0=0x%lx", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) { - efi.acpi = __va(config_tables[i].table); + efi.acpi = config_tables[i].table; printk(" ACPI=0x%lx", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) { - efi.smbios = __va(config_tables[i].table); + efi.smbios = config_tables[i].table; printk(" SMBIOS=0x%lx", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) { - efi.sal_systab = __va(config_tables[i].table); + efi.sal_systab = config_tables[i].table; printk(" SALsystab=0x%lx", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) { - efi.hcdp = __va(config_tables[i].table); + efi.hcdp = config_tables[i].table; printk(" HCDP=0x%lx", config_tables[i].table); } } @@ -677,27 +686,34 @@ EXPORT_SYMBOL(efi_mem_attributes); /* * Determines whether the memory at phys_addr supports the desired * attribute (WB, UC, etc). If this returns 1, the caller can safely - * access *size bytes at phys_addr with the specified attribute. + * access size bytes at phys_addr with the specified attribute. */ -static int -efi_mem_attribute_range (unsigned long phys_addr, unsigned long *size, u64 attr) +int +efi_mem_attribute_range (unsigned long phys_addr, unsigned long size, u64 attr) { + unsigned long end = phys_addr + size; efi_memory_desc_t *md = efi_memory_descriptor(phys_addr); - unsigned long md_end; - if (!md || (md->attribute & attr) != attr) + /* + * Some firmware doesn't report MMIO regions in the EFI memory + * map. The Intel BigSur (a.k.a. HP i2000) has this problem. + * On those platforms, we have to assume UC is valid everywhere. + */ + if (!md || (md->attribute & attr) != attr) { + if (attr == EFI_MEMORY_UC && !efi_memmap_has_mmio()) + return 1; return 0; + } do { - md_end = efi_md_end(md); - if (phys_addr + *size <= md_end) + unsigned long md_end = efi_md_end(md); + + if (end <= md_end) return 1; md = efi_memory_descriptor(md_end); - if (!md || (md->attribute & attr) != attr) { - *size = md_end - phys_addr; - return 1; - } + if (!md || (md->attribute & attr) != attr) + return 0; } while (md); return 0; } @@ -708,7 +724,7 @@ efi_mem_attribute_range (unsigned long phys_addr, unsigned long *size, u64 attr) * control access size. */ int -valid_phys_addr_range (unsigned long phys_addr, unsigned long *size) +valid_phys_addr_range (unsigned long phys_addr, unsigned long size) { return efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB); } @@ -723,7 +739,7 @@ valid_phys_addr_range (unsigned long phys_addr, unsigned long *size) * because that doesn't appear in the boot-time EFI memory map. */ int -valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long *size) +valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long size) { if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB)) return 1; @@ -731,14 +747,6 @@ valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long *size) if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_UC)) return 1; - /* - * Some firmware doesn't report MMIO regions in the EFI memory map. - * The Intel BigSur (a.k.a. HP i2000) has this problem. In this - * case, we can't use the EFI memory map to validate mmap requests. - */ - if (!efi_memmap_has_mmio()) - return 1; - return 0; } diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 50ae8c7..789881c 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -34,6 +34,7 @@ #include <asm/pgtable.h> #include <asm/kdebug.h> #include <asm/sections.h> +#include <asm/uaccess.h> extern void jprobe_inst_return(void); @@ -722,13 +723,50 @@ static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr) struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs); - reset_current_kprobe(); + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the instruction pointer points back to + * the probe address and allow the page fault handler + * to continue as a normal page fault. + */ + regs->cr_iip = ((unsigned long)cur->addr) & ~0xFULL; + ia64_psr(regs)->ri = ((unsigned long)cur->addr) & 0xf; + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * Let ia64_do_page_fault() fix it. + */ + break; + default: + break; } return 0; @@ -740,6 +778,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch(val) { case DIE_BREAK: /* err is break number from ia64_bad_break() */ diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 87ff7fe..8963171 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -69,6 +69,7 @@ #include <linux/kernel.h> #include <linux/smp.h> #include <linux/workqueue.h> +#include <linux/cpumask.h> #include <asm/delay.h> #include <asm/kdebug.h> @@ -1505,7 +1506,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset, ti->cpu = cpu; p->thread_info = ti; p->state = TASK_UNINTERRUPTIBLE; - __set_bit(cpu, &p->cpus_allowed); + cpu_set(cpu, p->cpus_allowed); INIT_LIST_HEAD(&p->tasks); p->parent = p->real_parent = p->group_leader = p; INIT_LIST_HEAD(&p->children); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 309d596..355d579 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -30,7 +30,6 @@ #include <linux/efi.h> #include <linux/interrupt.h> #include <linux/delay.h> -#include <linux/kprobes.h> #include <asm/cpu.h> #include <asm/delay.h> @@ -738,13 +737,6 @@ void exit_thread (void) { - /* - * Remove function-return probe instances associated with this task - * and put them back on the free list. Do not insert an exit probe for - * this function, it will be disabled by kprobe_flush_task if you do. - */ - kprobe_flush_task(current); - ia64_drop_fpu(current); #ifdef CONFIG_PERFMON /* if needed, stop monitoring and flush state to perfmon context */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index eb388e2..e4dfda1 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -37,6 +37,7 @@ #include <linux/string.h> #include <linux/threads.h> #include <linux/tty.h> +#include <linux/dmi.h> #include <linux/serial.h> #include <linux/serial_core.h> #include <linux/efi.h> @@ -433,7 +434,7 @@ setup_arch (char **cmdline_p) find_memory(); /* process SAL system table: */ - ia64_sal_init(efi.sal_systab); + ia64_sal_init(__va(efi.sal_systab)); ia64_setup_printk_clock(); @@ -887,3 +888,10 @@ check_bugs (void) ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles, (unsigned long) __end___mckinley_e9_bundles); } + +static int __init run_dmi_scan(void) +{ + dmi_scan_machine(); + return 0; +} +core_initcall(run_dmi_scan); diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index dabd6c3..7c1ddc8 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -30,19 +30,19 @@ extern spinlock_t timerlist_lock; fpswa_interface_t *fpswa_interface; EXPORT_SYMBOL(fpswa_interface); -struct notifier_block *ia64die_chain; +ATOMIC_NOTIFIER_HEAD(ia64die_chain); int register_die_notifier(struct notifier_block *nb) { - return notifier_chain_register(&ia64die_chain, nb); + return atomic_notifier_chain_register(&ia64die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); int unregister_die_notifier(struct notifier_block *nb) { - return notifier_chain_unregister(&ia64die_chain, nb); + return atomic_notifier_chain_unregister(&ia64die_chain, nb); } EXPORT_SYMBOL_GPL(unregister_die_notifier); diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index ac64664..d8536a2 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -6,7 +6,7 @@ obj-y := io.o lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ __divdi3.o __udivdi3.o __moddi3.o __umoddi3.o \ - bitop.o checksum.o clear_page.o csum_partial_copy.o \ + checksum.o clear_page.o csum_partial_copy.o \ clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \ flush.o ip_fast_csum.o do_csum.o \ memset.o strlen.o diff --git a/arch/ia64/lib/bitop.c b/arch/ia64/lib/bitop.c deleted file mode 100644 index 82e299c..0000000 --- a/arch/ia64/lib/bitop.c +++ /dev/null @@ -1,88 +0,0 @@ -#include <linux/compiler.h> -#include <linux/types.h> -#include <asm/intrinsics.h> -#include <linux/module.h> -#include <linux/bitops.h> - -/* - * Find next zero bit in a bitmap reasonably efficiently.. - */ - -int __find_next_zero_bit (const void *addr, unsigned long size, unsigned long offset) -{ - unsigned long *p = ((unsigned long *) addr) + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp |= ~0UL >> (64-offset); - if (size < 64) - goto found_first; - if (~tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if (~(tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; -found_first: - tmp |= ~0UL << size; - if (tmp == ~0UL) /* any bits zero? */ - return result + size; /* nope */ -found_middle: - return result + ffz(tmp); -} -EXPORT_SYMBOL(__find_next_zero_bit); - -/* - * Find next bit in a bitmap reasonably efficiently.. - */ -int __find_next_bit(const void *addr, unsigned long size, unsigned long offset) -{ - unsigned long *p = ((unsigned long *) addr) + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp &= ~0UL << offset; - if (size < 64) - goto found_first; - if (tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if ((tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; - found_first: - tmp &= ~0UL >> (64-size); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ - found_middle: - return result + __ffs(tmp); -} -EXPORT_SYMBOL(__find_next_bit); diff --git a/arch/ia64/mm/Makefile b/arch/ia64/mm/Makefile index d78d20f..bb0a01a 100644 --- a/arch/ia64/mm/Makefile +++ b/arch/ia64/mm/Makefile @@ -2,7 +2,7 @@ # Makefile for the ia64-specific parts of the memory manager. # -obj-y := init.o fault.o tlb.o extable.o +obj-y := init.o fault.o tlb.o extable.o ioremap.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_NUMA) += numa.o diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 2f5e448..ec9eeb8 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -379,31 +379,6 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) } /** - * pgdat_insert - insert the pgdat into global pgdat_list - * @pgdat: the pgdat for a node. - */ -static void __init pgdat_insert(pg_data_t *pgdat) -{ - pg_data_t *prev = NULL, *next; - - for_each_pgdat(next) - if (pgdat->node_id < next->node_id) - break; - else - prev = next; - - if (prev) { - prev->pgdat_next = pgdat; - pgdat->pgdat_next = next; - } else { - pgdat->pgdat_next = pgdat_list; - pgdat_list = pgdat; - } - - return; -} - -/** * memory_less_nodes - allocate and initialize CPU only nodes pernode * information. */ @@ -560,7 +535,7 @@ void show_mem(void) printk("Mem-info:\n"); show_free_areas(); printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { unsigned long present; unsigned long flags; int shared = 0, cached = 0, reserved = 0; @@ -745,11 +720,5 @@ void __init paging_init(void) pfn_offset, zholes_size); } - /* - * Make memory less nodes become a member of the known nodes. - */ - for_each_node_mask(node, memory_less_mask) - pgdat_insert(mem_data[node].pgdat); - zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page)); } diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index ff4f31f..2ef1151 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -600,7 +600,7 @@ mem_init (void) kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); kclist_add(&kcore_kernel, _stext, _end - _stext); - for_each_pgdat(pgdat) + for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) totalram_pages += free_all_bootmem_node(pgdat); diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c new file mode 100644 index 0000000..6232862 --- /dev/null +++ b/arch/ia64/mm/ioremap.c @@ -0,0 +1,43 @@ +/* + * (c) Copyright 2006 Hewlett-Packard Development Company, L.P. + * Bjorn Helgaas <bjorn.helgaas@hp.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/compiler.h> +#include <linux/module.h> +#include <linux/efi.h> +#include <asm/io.h> + +static inline void __iomem * +__ioremap (unsigned long offset, unsigned long size) +{ + return (void __iomem *) (__IA64_UNCACHED_OFFSET | offset); +} + +void __iomem * +ioremap (unsigned long offset, unsigned long size) +{ + if (efi_mem_attribute_range(offset, size, EFI_MEMORY_UC)) + return __ioremap(offset, size); + + if (efi_mem_attribute_range(offset, size, EFI_MEMORY_WB)) + return phys_to_virt(offset); + + /* + * Someday this should check ACPI resources so we + * can do the right thing for hot-plugged regions. + */ + return __ioremap(offset, size); +} +EXPORT_SYMBOL(ioremap); + +void __iomem * +ioremap_nocache (unsigned long offset, unsigned long size) +{ + return __ioremap(offset, size); +} +EXPORT_SYMBOL(ioremap_nocache); diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index 8b6d5c8..30988df 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -327,10 +327,11 @@ sn_scan_pcdp(void) struct pcdp_interface_pci if_pci; extern struct efi efi; - pcdp = efi.hcdp; - if (! pcdp) + if (efi.hcdp == EFI_INVALID_TABLE_ADDR) return; /* no hcdp/pcdp table */ + pcdp = __va(efi.hcdp); + if (pcdp->rev < 3) return; /* only support PCDP (rev >= 3) */ diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c index c686d9c..5100261 100644 --- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c +++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c @@ -93,19 +93,22 @@ static int coherence_id_open(struct inode *inode, struct file *file) static struct proc_dir_entry *sn_procfs_create_entry(const char *name, struct proc_dir_entry *parent, int (*openfunc)(struct inode *, struct file *), - int (*releasefunc)(struct inode *, struct file *)) + int (*releasefunc)(struct inode *, struct file *), + ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *)) { struct proc_dir_entry *e = create_proc_entry(name, 0444, parent); if (e) { - e->proc_fops = (struct file_operations *)kmalloc( - sizeof(struct file_operations), GFP_KERNEL); - if (e->proc_fops) { - memset(e->proc_fops, 0, sizeof(struct file_operations)); - e->proc_fops->open = openfunc; - e->proc_fops->read = seq_read; - e->proc_fops->llseek = seq_lseek; - e->proc_fops->release = releasefunc; + struct file_operations *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (f) { + f->open = openfunc; + f->read = seq_read; + f->llseek = seq_lseek; + f->release = releasefunc; + f->write = write; + e->proc_fops = f; } } @@ -119,31 +122,29 @@ extern int sn_topology_release(struct inode *, struct file *); void register_sn_procfs(void) { static struct proc_dir_entry *sgi_proc_dir = NULL; - struct proc_dir_entry *e; BUG_ON(sgi_proc_dir != NULL); if (!(sgi_proc_dir = proc_mkdir("sgi_sn", NULL))) return; sn_procfs_create_entry("partition_id", sgi_proc_dir, - partition_id_open, single_release); + partition_id_open, single_release, NULL); sn_procfs_create_entry("system_serial_number", sgi_proc_dir, - system_serial_number_open, single_release); + system_serial_number_open, single_release, NULL); sn_procfs_create_entry("licenseID", sgi_proc_dir, - licenseID_open, single_release); + licenseID_open, single_release, NULL); - e = sn_procfs_create_entry("sn_force_interrupt", sgi_proc_dir, - sn_force_interrupt_open, single_release); - if (e) - e->proc_fops->write = sn_force_interrupt_write_proc; + sn_procfs_create_entry("sn_force_interrupt", sgi_proc_dir, + sn_force_interrupt_open, single_release, + sn_force_interrupt_write_proc); sn_procfs_create_entry("coherence_id", sgi_proc_dir, - coherence_id_open, single_release); + coherence_id_open, single_release, NULL); sn_procfs_create_entry("sn_topology", sgi_proc_dir, - sn_topology_open, sn_topology_release); + sn_topology_open, sn_topology_release, NULL); } #endif /* CONFIG_PROC_FS */ diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index a3dcc3f..05c864c 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -214,6 +214,14 @@ config RWSEM_XCHGADD_ALGORITHM bool default n +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index d742037..0d78942 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -24,6 +24,7 @@ #include <linux/tty.h> #include <linux/cpu.h> #include <linux/nodemask.h> +#include <linux/pfn.h> #include <asm/processor.h> #include <asm/pgtable.h> diff --git a/arch/m32r/mm/discontig.c b/arch/m32r/mm/discontig.c index 08e7279..cf610a7 100644 --- a/arch/m32r/mm/discontig.c +++ b/arch/m32r/mm/discontig.c @@ -13,6 +13,7 @@ #include <linux/initrd.h> #include <linux/nodemask.h> #include <linux/module.h> +#include <linux/pfn.h> #include <asm/setup.h> @@ -137,12 +138,6 @@ unsigned long __init zone_sizes_init(void) int nid, i; mem_prof_t *mp; - pgdat_list = NULL; - for (nid = num_online_nodes() - 1 ; nid >= 0 ; nid--) { - NODE_DATA(nid)->pgdat_next = pgdat_list; - pgdat_list = NODE_DATA(nid); - } - for_each_online_node(nid) { mp = &mem_prof[nid]; for (i = 0 ; i < MAX_NR_ZONES ; i++) { diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index c9e7dad..b71348f 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -18,6 +18,7 @@ #include <linux/highmem.h> #include <linux/bitops.h> #include <linux/nodemask.h> +#include <linux/pfn.h> #include <asm/types.h> #include <asm/processor.h> #include <asm/page.h> @@ -47,7 +48,7 @@ void show_mem(void) printk("Mem-info:\n"); show_free_areas(); printk("Free swap: %6ldkB\n",nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { unsigned long flags; pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 8849439e..805b81f 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -17,6 +17,10 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c index 3ffc84f..c90cb5f 100644 --- a/arch/m68k/bvme6000/config.c +++ b/arch/m68k/bvme6000/config.c @@ -142,7 +142,7 @@ void __init config_bvme6000(void) /* Now do the PIT configuration */ pit->pgcr = 0x00; /* Unidirectional 8 bit, no handshake for now */ - pit->psrr = 0x18; /* PIACK and PIRQ fucntions enabled */ + pit->psrr = 0x18; /* PIACK and PIRQ functions enabled */ pit->pacr = 0x00; /* Sub Mode 00, H2 i/p, no DMA */ pit->padr = 0x00; /* Just to be tidy! */ pit->paddr = 0x00; /* All inputs for now (safest) */ diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c index a69fe30..b0e4c08 100644 --- a/arch/m68k/mvme16x/rtc.c +++ b/arch/m68k/mvme16x/rtc.c @@ -17,6 +17,7 @@ #include <linux/poll.h> #include <linux/mc146818rtc.h> /* For struct rtc_time and ioctls, etc */ #include <linux/smp_lock.h> +#include <linux/bcd.h> #include <asm/mvme16xhw.h> #include <asm/io.h> @@ -31,9 +32,6 @@ * ioctls. */ -#define BCD2BIN(val) (((val)&15) + ((val)>>4)*10) -#define BIN2BCD(val) ((((val)/10)<<4) + (val)%10) - static const unsigned char days_in_mo[] = {0, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31}; diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig index e50858d..3cde682 100644 --- a/arch/m68knommu/Kconfig +++ b/arch/m68knommu/Kconfig @@ -25,6 +25,14 @@ config RWSEM_XCHGADD_ALGORITHM bool default n +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index ac2012f..5080ea1 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -801,6 +801,14 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/mips/ddb5xxx/common/rtc_ds1386.c b/arch/mips/ddb5xxx/common/rtc_ds1386.c index 995896a..5dc34da 100644 --- a/arch/mips/ddb5xxx/common/rtc_ds1386.c +++ b/arch/mips/ddb5xxx/common/rtc_ds1386.c @@ -165,6 +165,6 @@ rtc_ds1386_init(unsigned long base) WRITE_RTC(0xB, byte); /* set the function pointers */ - rtc_get_time = rtc_ds1386_get_time; - rtc_set_time = rtc_ds1386_set_time; + rtc_mips_get_time = rtc_ds1386_get_time; + rtc_mips_set_time = rtc_ds1386_set_time; } diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c index 1748223..74cb055 100644 --- a/arch/mips/dec/time.c +++ b/arch/mips/dec/time.c @@ -36,41 +36,13 @@ #include <asm/dec/ioasic_addrs.h> #include <asm/dec/machtype.h> - -/* - * Returns true if a clock update is in progress - */ -static inline unsigned char dec_rtc_is_updating(void) -{ - unsigned char uip; - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); - spin_unlock_irqrestore(&rtc_lock, flags); - return uip; -} - static unsigned long dec_rtc_get_time(void) { unsigned int year, mon, day, hour, min, sec, real_year; - int i; unsigned long flags; - /* The Linux interpretation of the DS1287 clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - /* read RTC exactly on falling edge of update flag */ - for (i = 0; i < 1000000; i++) /* may take up to 1 second... */ - if (dec_rtc_is_updating()) - break; - for (i = 0; i < 1000000; i++) /* must try at least 2.228 ms */ - if (!dec_rtc_is_updating()) - break; spin_lock_irqsave(&rtc_lock, flags); - /* Isn't this overkill? UIP above should guarantee consistency */ + do { sec = CMOS_READ(RTC_SECONDS); min = CMOS_READ(RTC_MINUTES); @@ -78,7 +50,16 @@ static unsigned long dec_rtc_get_time(void) day = CMOS_READ(RTC_DAY_OF_MONTH); mon = CMOS_READ(RTC_MONTH); year = CMOS_READ(RTC_YEAR); + /* + * The PROM will reset the year to either '72 or '73. + * Therefore we store the real year separately, in one + * of unused BBU RAM locations. + */ + real_year = CMOS_READ(RTC_DEC_YEAR); } while (sec != CMOS_READ(RTC_SECONDS)); + + spin_unlock_irqrestore(&rtc_lock, flags); + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { sec = BCD2BIN(sec); min = BCD2BIN(min); @@ -87,13 +68,7 @@ static unsigned long dec_rtc_get_time(void) mon = BCD2BIN(mon); year = BCD2BIN(year); } - /* - * The PROM will reset the year to either '72 or '73. - * Therefore we store the real year separately, in one - * of unused BBU RAM locations. - */ - real_year = CMOS_READ(RTC_DEC_YEAR); - spin_unlock_irqrestore(&rtc_lock, flags); + year += real_year - 72 + 2000; return mktime(year, mon, day, hour, min, sec); @@ -193,8 +168,8 @@ static void dec_ioasic_hpt_init(unsigned int count) void __init dec_time_init(void) { - rtc_get_time = dec_rtc_get_time; - rtc_set_mmss = dec_rtc_set_mmss; + rtc_mips_get_time = dec_rtc_get_time; + rtc_mips_set_mmss = dec_rtc_set_mmss; mips_timer_state = dec_timer_state; mips_timer_ack = dec_timer_ack; diff --git a/arch/mips/ite-boards/generic/time.c b/arch/mips/ite-boards/generic/time.c index f5d67ee..b79817b 100644 --- a/arch/mips/ite-boards/generic/time.c +++ b/arch/mips/ite-boards/generic/time.c @@ -227,8 +227,8 @@ void __init it8172_time_init(void) local_irq_restore(flags); - rtc_get_time = it8172_rtc_get_time; - rtc_set_time = it8172_rtc_set_time; + rtc_mips_get_time = it8172_rtc_get_time; + rtc_mips_set_time = it8172_rtc_set_time; } #define ALLINTS (IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5) diff --git a/arch/mips/ite-boards/ivr/init.c b/arch/mips/ite-boards/ivr/init.c index ea4e193..b774db0 100644 --- a/arch/mips/ite-boards/ivr/init.c +++ b/arch/mips/ite-boards/ivr/init.c @@ -45,9 +45,6 @@ extern void __init prom_init_cmdline(void); extern unsigned long __init prom_get_memsize(void); extern void __init it8172_init_ram_resource(unsigned long memsize); -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) - const char *get_system_type(void) { return "Globespan IVR"; diff --git a/arch/mips/ite-boards/qed-4n-s01b/init.c b/arch/mips/ite-boards/qed-4n-s01b/init.c index 56dca7e..e8ec8be 100644 --- a/arch/mips/ite-boards/qed-4n-s01b/init.c +++ b/arch/mips/ite-boards/qed-4n-s01b/init.c @@ -45,9 +45,6 @@ extern void __init prom_init_cmdline(void); extern unsigned long __init prom_get_memsize(void); extern void __init it8172_init_ram_resource(unsigned long memsize); -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) - const char *get_system_type(void) { return "ITE QED-4N-S01B"; diff --git a/arch/mips/jmr3927/common/rtc_ds1742.c b/arch/mips/jmr3927/common/rtc_ds1742.c index 9a8bff1..a6bd3f4 100644 --- a/arch/mips/jmr3927/common/rtc_ds1742.c +++ b/arch/mips/jmr3927/common/rtc_ds1742.c @@ -159,8 +159,8 @@ rtc_ds1742_init(unsigned long base) db_assert((rtc_base & 0xe0000000) == KSEG1); /* set the function pointers */ - rtc_get_time = rtc_ds1742_get_time; - rtc_set_time = rtc_ds1742_set_time; + rtc_mips_get_time = rtc_ds1742_get_time; + rtc_mips_set_time = rtc_ds1742_set_time; /* clear oscillator stop bit */ CMOS_WRITE(RTC_READ, RTC_CONTROL); diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 013bc93..3f40c37 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -30,7 +30,6 @@ #include <linux/utime.h> #include <linux/utsname.h> #include <linux/personality.h> -#include <linux/timex.h> #include <linux/dnotify.h> #include <linux/module.h> #include <linux/binfmts.h> @@ -1157,79 +1156,6 @@ out: return err; } -/* Handle adjtimex compatibility. */ - -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage int sys32_adjtimex(struct timex32 __user *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if (get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if (put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} - asmlinkage int sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, s32 count) { diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 02c8267..05a2c05 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -273,7 +273,7 @@ EXPORT(sysn32_call_table) PTR sys_pivot_root PTR sys32_sysctl PTR sys_prctl - PTR sys32_adjtimex + PTR compat_sys_adjtimex PTR compat_sys_setrlimit /* 6155 */ PTR sys_chroot PTR sys_sync diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 797e0d8..19c4ca4 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -328,7 +328,7 @@ sys_call_table: PTR sys_setdomainname PTR sys32_newuname PTR sys_ni_syscall /* sys_modify_ldt */ - PTR sys32_adjtimex + PTR compat_sys_adjtimex PTR sys_mprotect /* 4125 */ PTR compat_sys_sigprocmask PTR sys_ni_syscall /* was creat_module */ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0cb3b60..dcbfd27 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -34,6 +34,7 @@ #include <linux/highmem.h> #include <linux/console.h> #include <linux/mmzone.h> +#include <linux/pfn.h> #include <asm/addrspace.h> #include <asm/bootinfo.h> @@ -257,10 +258,6 @@ static inline int parse_rd_cmdline(unsigned long* rd_start, unsigned long* rd_en return 0; } -#define PFN_UP(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) - #define MAXMEM HIGHMEM_START #define MAXMEM_PFN PFN_DOWN(MAXMEM) @@ -493,10 +490,6 @@ static inline void resource_init(void) } } -#undef PFN_UP -#undef PFN_DOWN -#undef PFN_PHYS - #undef MAXMEM #undef MAXMEM_PFN diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index 51273b7..5e51a2d 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -65,9 +65,9 @@ static int null_rtc_set_time(unsigned long sec) return 0; } -unsigned long (*rtc_get_time)(void) = null_rtc_get_time; -int (*rtc_set_time)(unsigned long) = null_rtc_set_time; -int (*rtc_set_mmss)(unsigned long); +unsigned long (*rtc_mips_get_time)(void) = null_rtc_get_time; +int (*rtc_mips_set_time)(unsigned long) = null_rtc_set_time; +int (*rtc_mips_set_mmss)(unsigned long); /* usecs per counter cycle, shifted to left by 32 bits */ @@ -440,14 +440,14 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) /* * If we have an externally synchronized Linux clock, then update - * CMOS clock accordingly every ~11 minutes. rtc_set_time() has to be + * CMOS clock accordingly every ~11 minutes. rtc_mips_set_time() has to be * called as close as possible to 500 ms before the new second starts. */ 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) { - if (rtc_set_mmss(xtime.tv_sec) == 0) { + if (rtc_mips_set_mmss(xtime.tv_sec) == 0) { last_rtc_update = xtime.tv_sec; } else { /* do it again in 60 s */ @@ -565,7 +565,7 @@ asmlinkage void ll_local_timer_interrupt(int irq, struct pt_regs *regs) * b) (optional) calibrate and set the mips_hpt_frequency * (only needed if you intended to use fixed_rate_gettimeoffset * or use cpu counter as timer interrupt source) - * 2) setup xtime based on rtc_get_time(). + * 2) setup xtime based on rtc_mips_get_time(). * 3) choose a appropriate gettimeoffset routine. * 4) calculate a couple of cached variables for later usage * 5) board_timer_setup() - @@ -633,10 +633,10 @@ void __init time_init(void) if (board_time_init) board_time_init(); - if (!rtc_set_mmss) - rtc_set_mmss = rtc_set_time; + if (!rtc_mips_set_mmss) + rtc_mips_set_mmss = rtc_mips_set_time; - xtime.tv_sec = rtc_get_time(); + xtime.tv_sec = rtc_mips_get_time(); xtime.tv_nsec = 0; set_normalized_timespec(&wall_to_monotonic, @@ -772,8 +772,8 @@ void to_tm(unsigned long tim, struct rtc_time *tm) EXPORT_SYMBOL(rtc_lock); EXPORT_SYMBOL(to_tm); -EXPORT_SYMBOL(rtc_set_time); -EXPORT_SYMBOL(rtc_get_time); +EXPORT_SYMBOL(rtc_mips_set_time); +EXPORT_SYMBOL(rtc_mips_get_time); unsigned long long sched_clock(void) { diff --git a/arch/mips/lasat/setup.c b/arch/mips/lasat/setup.c index 83eb08b..bb70a82 100644 --- a/arch/mips/lasat/setup.c +++ b/arch/mips/lasat/setup.c @@ -165,7 +165,8 @@ void __init plat_setup(void) /* Set up panic notifier */ for (i = 0; i < sizeof(lasat_panic_block) / sizeof(struct notifier_block); i++) - notifier_chain_register(&panic_notifier_list, &lasat_panic_block[i]); + atomic_notifier_chain_register(&panic_notifier_list, + &lasat_panic_block[i]); lasat_reboot_setup(); @@ -174,8 +175,8 @@ void __init plat_setup(void) #ifdef CONFIG_DS1603 ds1603 = &ds_defs[mips_machtype]; - rtc_get_time = ds1603_read; - rtc_set_time = ds1603_set; + rtc_mips_get_time = ds1603_read; + rtc_mips_set_time = ds1603_set; #endif #ifdef DYNAMIC_SERIAL_INIT diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 8ff43a1..e3d5aaa 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -30,12 +30,13 @@ #include <linux/string.h> #include <linux/net.h> #include <linux/inet.h> +#include <linux/mutex.h> #include <asm/uaccess.h> #include "sysctl.h" #include "ds1603.h" -static DECLARE_MUTEX(lasat_info_sem); +static DEFINE_MUTEX(lasat_info_mutex); /* Strategy function to write EEPROM after changing string entry */ int sysctl_lasatstring(ctl_table *table, int *name, int nlen, @@ -43,17 +44,17 @@ int sysctl_lasatstring(ctl_table *table, int *name, int nlen, void *newval, size_t newlen, void **context) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = sysctl_string(table, name, nlen, oldval, oldlenp, newval, newlen, context); if (r < 0) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } if (newval && newlen) { lasat_write_eeprom_info(); } - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 1; } @@ -63,14 +64,14 @@ int proc_dolasatstring(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = proc_dostring(table, write, filp, buffer, lenp, ppos); if ( (!write) || r) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } lasat_write_eeprom_info(); - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } @@ -79,14 +80,14 @@ int proc_dolasatint(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = proc_dointvec(table, write, filp, buffer, lenp, ppos); if ( (!write) || r) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } lasat_write_eeprom_info(); - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } @@ -98,7 +99,7 @@ int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); if (!write) { rtctmp = ds1603_read(); /* check for time < 0 and set to 0 */ @@ -107,11 +108,11 @@ int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, } r = proc_dointvec(table, write, filp, buffer, lenp, ppos); if ( (!write) || r) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } ds1603_set(rtctmp); - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } #endif @@ -122,16 +123,16 @@ int sysctl_lasat_intvec(ctl_table *table, int *name, int nlen, void *newval, size_t newlen, void **context) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = sysctl_intvec(table, name, nlen, oldval, oldlenp, newval, newlen, context); if (r < 0) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } if (newval && newlen) { lasat_write_eeprom_info(); } - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 1; } @@ -142,19 +143,19 @@ int sysctl_lasat_rtc(ctl_table *table, int *name, int nlen, void *newval, size_t newlen, void **context) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); rtctmp = ds1603_read(); if (rtctmp < 0) rtctmp = 0; r = sysctl_intvec(table, name, nlen, oldval, oldlenp, newval, newlen, context); if (r < 0) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } if (newval && newlen) { ds1603_set(rtctmp); } - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 1; } #endif @@ -192,13 +193,13 @@ int proc_lasat_ip(ctl_table *table, int write, struct file *filp, return 0; } - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); if (write) { len = 0; p = buffer; while (len < *lenp) { if(get_user(c, p++)) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return -EFAULT; } if (c == 0 || c == '\n') @@ -209,7 +210,7 @@ int proc_lasat_ip(ctl_table *table, int write, struct file *filp, len = sizeof(proc_lasat_ipbuf) - 1; if (copy_from_user(proc_lasat_ipbuf, buffer, len)) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return -EFAULT; } proc_lasat_ipbuf[len] = 0; @@ -230,12 +231,12 @@ int proc_lasat_ip(ctl_table *table, int write, struct file *filp, len = *lenp; if (len) if(copy_to_user(buffer, proc_lasat_ipbuf, len)) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return -EFAULT; } if (len < *lenp) { if(put_user('\n', ((char *) buffer) + len)) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return -EFAULT; } len++; @@ -244,7 +245,7 @@ int proc_lasat_ip(ctl_table *table, int write, struct file *filp, *ppos += len; } update_bcastaddr(); - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } #endif /* defined(CONFIG_INET) */ @@ -256,10 +257,10 @@ static int sysctl_lasat_eeprom_value(ctl_table *table, int *name, int nlen, { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = sysctl_intvec(table, name, nlen, oldval, oldlenp, newval, newlen, context); if (r < 0) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } @@ -271,7 +272,7 @@ static int sysctl_lasat_eeprom_value(ctl_table *table, int *name, int nlen, lasat_write_eeprom_info(); lasat_init_board_info(); } - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } @@ -280,10 +281,10 @@ int proc_lasat_eeprom_value(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { int r; - down(&lasat_info_sem); + mutex_lock(&lasat_info_mutex); r = proc_dointvec(table, write, filp, buffer, lenp, ppos); if ( (!write) || r) { - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return r; } if (filp && filp->f_dentry) @@ -294,7 +295,7 @@ int proc_lasat_eeprom_value(ctl_table *table, int write, struct file *filp, lasat_board_info.li_eeprom_info.debugaccess = lasat_board_info.li_debugaccess; } lasat_write_eeprom_info(); - up(&lasat_info_sem); + mutex_unlock(&lasat_info_mutex); return 0; } diff --git a/arch/mips/mips-boards/atlas/atlas_setup.c b/arch/mips/mips-boards/atlas/atlas_setup.c index 873cf31..c20d401 100644 --- a/arch/mips/mips-boards/atlas/atlas_setup.c +++ b/arch/mips/mips-boards/atlas/atlas_setup.c @@ -65,7 +65,7 @@ void __init plat_setup(void) board_time_init = mips_time_init; board_timer_setup = mips_timer_setup; - rtc_get_time = mips_rtc_get_time; + rtc_mips_get_time = mips_rtc_get_time; } static void __init serial_init(void) diff --git a/arch/mips/mips-boards/generic/memory.c b/arch/mips/mips-boards/generic/memory.c index ee5e70c..32c9210 100644 --- a/arch/mips/mips-boards/generic/memory.c +++ b/arch/mips/mips-boards/generic/memory.c @@ -49,9 +49,6 @@ static char *mtypes[3] = { /* References to section boundaries */ extern char _end; -#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) - - struct prom_pmemblock * __init prom_getmdesc(void) { char *memsize_str; @@ -109,10 +106,10 @@ struct prom_pmemblock * __init prom_getmdesc(void) mdesc[3].type = yamon_dontuse; mdesc[3].base = 0x00100000; - mdesc[3].size = CPHYSADDR(PFN_ALIGN(&_end)) - mdesc[3].base; + mdesc[3].size = CPHYSADDR(PAGE_ALIGN(&_end)) - mdesc[3].base; mdesc[4].type = yamon_free; - mdesc[4].base = CPHYSADDR(PFN_ALIGN(&_end)); + mdesc[4].base = CPHYSADDR(PAGE_ALIGN(&_end)); mdesc[4].size = memsize - mdesc[4].base; return &mdesc[0]; diff --git a/arch/mips/mips-boards/malta/malta_setup.c b/arch/mips/mips-boards/malta/malta_setup.c index 2209e8a..b8488aa 100644 --- a/arch/mips/mips-boards/malta/malta_setup.c +++ b/arch/mips/mips-boards/malta/malta_setup.c @@ -225,5 +225,5 @@ void __init plat_setup(void) board_time_init = mips_time_init; board_timer_setup = mips_timer_setup; - rtc_get_time = mips_rtc_get_time; + rtc_mips_get_time = mips_rtc_get_time; } diff --git a/arch/mips/mips-boards/sim/sim_mem.c b/arch/mips/mips-boards/sim/sim_mem.c index 1ec4e75..e57f737 100644 --- a/arch/mips/mips-boards/sim/sim_mem.c +++ b/arch/mips/mips-boards/sim/sim_mem.c @@ -42,9 +42,6 @@ static char *mtypes[3] = { /* References to section boundaries */ extern char _end; -#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) - - struct prom_pmemblock * __init prom_getmdesc(void) { unsigned int memsize; @@ -64,10 +61,10 @@ struct prom_pmemblock * __init prom_getmdesc(void) mdesc[2].type = simmem_reserved; mdesc[2].base = 0x00100000; - mdesc[2].size = CPHYSADDR(PFN_ALIGN(&_end)) - mdesc[2].base; + mdesc[2].size = CPHYSADDR(PAGE_ALIGN(&_end)) - mdesc[2].base; mdesc[3].type = simmem_free; - mdesc[3].base = CPHYSADDR(PFN_ALIGN(&_end)); + mdesc[3].base = CPHYSADDR(PAGE_ALIGN(&_end)); mdesc[3].size = memsize - mdesc[3].base; return &mdesc[0]; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 52f7d59..ad89c44 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -25,6 +25,7 @@ #include <linux/highmem.h> #include <linux/swap.h> #include <linux/proc_fs.h> +#include <linux/pfn.h> #include <asm/bootinfo.h> #include <asm/cachectl.h> @@ -177,9 +178,6 @@ void __init paging_init(void) free_area_init(zones_size); } -#define PFN_UP(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) - static inline int page_is_ram(unsigned long pagenr) { int i; diff --git a/arch/mips/momentum/jaguar_atx/setup.c b/arch/mips/momentum/jaguar_atx/setup.c index 3784c89..91d9637 100644 --- a/arch/mips/momentum/jaguar_atx/setup.c +++ b/arch/mips/momentum/jaguar_atx/setup.c @@ -229,8 +229,8 @@ void momenco_time_init(void) mips_hpt_frequency = cpu_clock / 2; board_timer_setup = momenco_timer_setup; - rtc_get_time = m48t37y_get_time; - rtc_set_time = m48t37y_set_time; + rtc_mips_get_time = m48t37y_get_time; + rtc_mips_set_time = m48t37y_set_time; } static struct resource mv_pci_io_mem0_resource = { diff --git a/arch/mips/momentum/ocelot_3/setup.c b/arch/mips/momentum/ocelot_3/setup.c index f95677f..370e75d 100644 --- a/arch/mips/momentum/ocelot_3/setup.c +++ b/arch/mips/momentum/ocelot_3/setup.c @@ -58,6 +58,7 @@ #include <linux/bootmem.h> #include <linux/mv643xx.h> #include <linux/pm.h> +#include <linux/bcd.h> #include <asm/time.h> #include <asm/page.h> @@ -131,9 +132,6 @@ void setup_wired_tlb_entries(void) add_wired_entry(ENTRYLO(0xfc000000), ENTRYLO(0xfd000000), (signed)0xfc000000, PM_16M); } -#define CONV_BCD_TO_BIN(val) (((val) & 0xf) + (((val) >> 4) * 10)) -#define CONV_BIN_TO_BCD(val) (((val) % 10) + (((val) / 10) << 4)) - unsigned long m48t37y_get_time(void) { unsigned int year, month, day, hour, min, sec; @@ -143,16 +141,16 @@ unsigned long m48t37y_get_time(void) /* stop the update */ rtc_base[0x7ff8] = 0x40; - year = CONV_BCD_TO_BIN(rtc_base[0x7fff]); - year += CONV_BCD_TO_BIN(rtc_base[0x7ff1]) * 100; + year = BCD2BIN(rtc_base[0x7fff]); + year += BCD2BIN(rtc_base[0x7ff1]) * 100; - month = CONV_BCD_TO_BIN(rtc_base[0x7ffe]); + month = BCD2BIN(rtc_base[0x7ffe]); - day = CONV_BCD_TO_BIN(rtc_base[0x7ffd]); + day = BCD2BIN(rtc_base[0x7ffd]); - hour = CONV_BCD_TO_BIN(rtc_base[0x7ffb]); - min = CONV_BCD_TO_BIN(rtc_base[0x7ffa]); - sec = CONV_BCD_TO_BIN(rtc_base[0x7ff9]); + hour = BCD2BIN(rtc_base[0x7ffb]); + min = BCD2BIN(rtc_base[0x7ffa]); + sec = BCD2BIN(rtc_base[0x7ff9]); /* start the update */ rtc_base[0x7ff8] = 0x00; @@ -175,22 +173,22 @@ int m48t37y_set_time(unsigned long sec) rtc_base[0x7ff8] = 0x80; /* year */ - rtc_base[0x7fff] = CONV_BIN_TO_BCD(tm.tm_year % 100); - rtc_base[0x7ff1] = CONV_BIN_TO_BCD(tm.tm_year / 100); + rtc_base[0x7fff] = BIN2BCD(tm.tm_year % 100); + rtc_base[0x7ff1] = BIN2BCD(tm.tm_year / 100); /* month */ - rtc_base[0x7ffe] = CONV_BIN_TO_BCD(tm.tm_mon); + rtc_base[0x7ffe] = BIN2BCD(tm.tm_mon); /* day */ - rtc_base[0x7ffd] = CONV_BIN_TO_BCD(tm.tm_mday); + rtc_base[0x7ffd] = BIN2BCD(tm.tm_mday); /* hour/min/sec */ - rtc_base[0x7ffb] = CONV_BIN_TO_BCD(tm.tm_hour); - rtc_base[0x7ffa] = CONV_BIN_TO_BCD(tm.tm_min); - rtc_base[0x7ff9] = CONV_BIN_TO_BCD(tm.tm_sec); + rtc_base[0x7ffb] = BIN2BCD(tm.tm_hour); + rtc_base[0x7ffa] = BIN2BCD(tm.tm_min); + rtc_base[0x7ff9] = BIN2BCD(tm.tm_sec); /* day of week -- not really used, but let's keep it up-to-date */ - rtc_base[0x7ffc] = CONV_BIN_TO_BCD(tm.tm_wday + 1); + rtc_base[0x7ffc] = BIN2BCD(tm.tm_wday + 1); /* disable writing */ rtc_base[0x7ff8] = 0x00; @@ -215,8 +213,8 @@ void momenco_time_init(void) mips_hpt_frequency = cpu_clock / 2; board_timer_setup = momenco_timer_setup; - rtc_get_time = m48t37y_get_time; - rtc_set_time = m48t37y_set_time; + rtc_mips_get_time = m48t37y_get_time; + rtc_mips_set_time = m48t37y_set_time; } /* diff --git a/arch/mips/momentum/ocelot_c/setup.c b/arch/mips/momentum/ocelot_c/setup.c index bd02e60..a3e6f55 100644 --- a/arch/mips/momentum/ocelot_c/setup.c +++ b/arch/mips/momentum/ocelot_c/setup.c @@ -227,8 +227,8 @@ void momenco_time_init(void) printk("momenco_time_init cpu_clock=%d\n", cpu_clock); board_timer_setup = momenco_timer_setup; - rtc_get_time = m48t37y_get_time; - rtc_set_time = m48t37y_set_time; + rtc_mips_get_time = m48t37y_get_time; + rtc_mips_set_time = m48t37y_set_time; } void __init plat_setup(void) diff --git a/arch/mips/pmc-sierra/yosemite/setup.c b/arch/mips/pmc-sierra/yosemite/setup.c index 8bce711..3f724d6 100644 --- a/arch/mips/pmc-sierra/yosemite/setup.c +++ b/arch/mips/pmc-sierra/yosemite/setup.c @@ -198,8 +198,8 @@ static void __init py_rtc_setup(void) if (!m48t37_base) printk(KERN_ERR "Mapping the RTC failed\n"); - rtc_get_time = m48t37y_get_time; - rtc_set_time = m48t37y_set_time; + rtc_mips_get_time = m48t37y_get_time; + rtc_mips_set_time = m48t37y_set_time; write_seqlock(&xtime_lock); xtime.tv_sec = m48t37y_get_time(); diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c index 92a3b3c..a9c58e0 100644 --- a/arch/mips/sgi-ip22/ip22-reset.c +++ b/arch/mips/sgi-ip22/ip22-reset.c @@ -238,7 +238,7 @@ static int __init reboot_setup(void) request_irq(SGI_PANEL_IRQ, panel_int, 0, "Front Panel", NULL); init_timer(&blink_timer); blink_timer.function = blink_timeout; - notifier_chain_register(&panic_notifier_list, &panic_block); + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); return 0; } diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c index b7300cc..cca688a 100644 --- a/arch/mips/sgi-ip22/ip22-time.c +++ b/arch/mips/sgi-ip22/ip22-time.c @@ -212,8 +212,8 @@ static void indy_timer_setup(struct irqaction *irq) void __init ip22_time_init(void) { /* setup hookup functions */ - rtc_get_time = indy_rtc_get_time; - rtc_set_time = indy_rtc_set_time; + rtc_mips_get_time = indy_rtc_get_time; + rtc_mips_set_time = indy_rtc_set_time; board_time_init = indy_time_init; board_timer_setup = indy_timer_setup; diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index e0d095d..6c00dce 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -19,6 +19,7 @@ #include <linux/nodemask.h> #include <linux/swap.h> #include <linux/bootmem.h> +#include <linux/pfn.h> #include <asm/page.h> #include <asm/sections.h> @@ -28,8 +29,6 @@ #include <asm/sn/sn_private.h> -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) - #define SLOT_PFNSHIFT (SLOT_SHIFT - PAGE_SHIFT) #define PFN_NASIDSHFT (NASID_SHFT - PAGE_SHIFT) diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c index 0c94800..ab9d9ce 100644 --- a/arch/mips/sgi-ip32/ip32-reset.c +++ b/arch/mips/sgi-ip32/ip32-reset.c @@ -193,7 +193,7 @@ static __init int ip32_reboot_setup(void) init_timer(&blink_timer); blink_timer.function = blink_timeout; - notifier_chain_register(&panic_notifier_list, &panic_block); + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); request_irq(MACEISA_RTC_IRQ, ip32_rtc_int, 0, "rtc", NULL); diff --git a/arch/mips/sgi-ip32/ip32-setup.c b/arch/mips/sgi-ip32/ip32-setup.c index 2f50c79..a2dd8ae 100644 --- a/arch/mips/sgi-ip32/ip32-setup.c +++ b/arch/mips/sgi-ip32/ip32-setup.c @@ -91,8 +91,8 @@ void __init plat_setup(void) { board_be_init = ip32_be_init; - rtc_get_time = mc146818_get_cmos_time; - rtc_set_mmss = mc146818_set_rtc_mmss; + rtc_mips_get_time = mc146818_get_cmos_time; + rtc_mips_set_mmss = mc146818_set_rtc_mmss; board_time_init = ip32_time_init; board_timer_setup = ip32_timer_setup; diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index b661d24..4b5f74f 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -121,14 +121,14 @@ void __init plat_setup(void) if (xicor_probe()) { printk("swarm setup: Xicor 1241 RTC detected.\n"); - rtc_get_time = xicor_get_time; - rtc_set_time = xicor_set_time; + rtc_mips_get_time = xicor_get_time; + rtc_mips_set_time = xicor_set_time; } if (m41t81_probe()) { printk("swarm setup: M41T81 RTC detected.\n"); - rtc_get_time = m41t81_get_time; - rtc_set_time = m41t81_set_time; + rtc_mips_get_time = m41t81_get_time; + rtc_mips_set_time = m41t81_set_time; } printk("This kernel optimized for " diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c index 1141fcd..01ba6c5 100644 --- a/arch/mips/sni/setup.c +++ b/arch/mips/sni/setup.c @@ -164,8 +164,8 @@ static struct pci_controller sni_controller = { static inline void sni_pcimt_time_init(void) { - rtc_get_time = mc146818_get_cmos_time; - rtc_set_time = mc146818_set_rtc_mmss; + rtc_mips_get_time = mc146818_get_cmos_time; + rtc_mips_set_time = mc146818_set_rtc_mmss; } void __init plat_setup(void) diff --git a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c index 2ad6401..6dcf077 100644 --- a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c +++ b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c @@ -1036,8 +1036,8 @@ toshiba_rbtx4927_time_init(void) #ifdef CONFIG_RTC_DS1742 - rtc_get_time = rtc_ds1742_get_time; - rtc_set_time = rtc_ds1742_set_time; + rtc_mips_get_time = rtc_ds1742_get_time; + rtc_mips_set_time = rtc_ds1742_set_time; TOSHIBA_RBTX4927_SETUP_DPRINTK(TOSHIBA_RBTX4927_SETUP_TIME_INIT, ":rtc_ds1742_init()-\n"); diff --git a/arch/mips/tx4938/common/rtc_rx5c348.c b/arch/mips/tx4938/common/rtc_rx5c348.c index d249edb..07f782f 100644 --- a/arch/mips/tx4938/common/rtc_rx5c348.c +++ b/arch/mips/tx4938/common/rtc_rx5c348.c @@ -14,6 +14,7 @@ #include <linux/string.h> #include <linux/rtc.h> #include <linux/time.h> +#include <linux/bcd.h> #include <asm/time.h> #include <asm/tx4938/spi.h> @@ -77,17 +78,6 @@ spi_rtc_io(unsigned char *inbuf, unsigned char *outbuf, unsigned int count) inbufs, incounts, outbufs, outcounts, 0); } -/* - * Conversion between binary and BCD. - */ -#ifndef BCD_TO_BIN -#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10) -#endif - -#ifndef BIN_TO_BCD -#define BIN_TO_BCD(val) ((val)=(((val)/10)<<4) + (val)%10) -#endif - /* RTC-dependent code for time.c */ static int @@ -197,6 +187,6 @@ rtc_rx5c348_init(int chipid) srtc_24h = 1; /* set the function pointers */ - rtc_get_time = rtc_rx5c348_get_time; - rtc_set_time = rtc_rx5c348_set_time; + rtc_mips_get_time = rtc_rx5c348_get_time; + rtc_mips_set_time = rtc_rx5c348_set_time; } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index eca33cf..6b3c509 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -25,6 +25,14 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/parisc/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c index 2a01fe1..0cea695 100644 --- a/arch/parisc/kernel/pdc_chassis.c +++ b/arch/parisc/kernel/pdc_chassis.c @@ -150,7 +150,8 @@ void __init parisc_pdc_chassis_init(void) if (handle) { /* initialize panic notifier chain */ - notifier_chain_register(&panic_notifier_list, &pdc_chassis_panic_block); + atomic_notifier_chain_register(&panic_notifier_list, + &pdc_chassis_panic_block); /* initialize reboot notifier chain */ register_reboot_notifier(&pdc_chassis_reboot_block); diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 6135690..d286f68 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -21,7 +21,6 @@ #include <linux/times.h> #include <linux/utsname.h> #include <linux/time.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -567,63 +566,6 @@ asmlinkage int sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *off } -struct timex32 { - unsigned int modes; /* mode selector */ - int offset; /* time offset (usec) */ - int freq; /* frequency offset (scaled ppm) */ - int maxerror; /* maximum error (usec) */ - int esterror; /* estimated error (usec) */ - int status; /* clock command/status */ - int constant; /* pll time constant */ - int precision; /* clock precision (usec) (read only) */ - int tolerance; /* clock frequency tolerance (ppm) - * (read only) - */ - struct compat_timeval time; /* (read only) */ - int tick; /* (modified) usecs between clock ticks */ - - int ppsfreq; /* pps frequency (scaled ppm) (ro) */ - int jitter; /* pps jitter (us) (ro) */ - int shift; /* interval duration (s) (shift) (ro) */ - int stabil; /* pps stability (scaled ppm) (ro) */ - int jitcnt; /* jitter limit exceeded (ro) */ - int calcnt; /* calibration intervals (ro) */ - int errcnt; /* calibration errors (ro) */ - int stbcnt; /* stability limit exceeded (ro) */ - - int :32; int :32; int :32; int :32; - int :32; int :32; int :32; int :32; - int :32; int :32; int :32; int :32; -}; - -asmlinkage long sys32_adjtimex(struct timex32 __user *txc_p32) -{ - struct timex txc; - struct timex32 t32; - int ret; - extern int do_adjtimex(struct timex *txc); - - if(copy_from_user(&t32, txc_p32, sizeof(struct timex32))) - return -EFAULT; -#undef CP -#define CP(x) txc.x = t32.x - CP(modes); CP(offset); CP(freq); CP(maxerror); CP(esterror); - CP(status); CP(constant); CP(precision); CP(tolerance); - CP(time.tv_sec); CP(time.tv_usec); CP(tick); CP(ppsfreq); CP(jitter); - CP(shift); CP(stabil); CP(jitcnt); CP(calcnt); CP(errcnt); - CP(stbcnt); - ret = do_adjtimex(&txc); -#undef CP -#define CP(x) t32.x = txc.x - CP(modes); CP(offset); CP(freq); CP(maxerror); CP(esterror); - CP(status); CP(constant); CP(precision); CP(tolerance); - CP(time.tv_sec); CP(time.tv_usec); CP(tick); CP(ppsfreq); CP(jitter); - CP(shift); CP(stabil); CP(jitcnt); CP(calcnt); CP(errcnt); - CP(stbcnt); - return copy_to_user(txc_p32, &t32, sizeof(struct timex32)) ? -EFAULT : ret; -} - - struct sysinfo32 { s32 uptime; u32 loads[3]; diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 71011ea..89b6c56 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -207,7 +207,7 @@ /* struct sockaddr... */ ENTRY_SAME(recvfrom) /* struct timex contains longs */ - ENTRY_DIFF(adjtimex) + ENTRY_COMP(adjtimex) ENTRY_SAME(mprotect) /* 125 */ /* old_sigset_t forced to 32 bits. Beware glibc sigset_t */ ENTRY_COMP(sigprocmask) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fae42da..a433b71 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -37,6 +37,10 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index cb1fe58..ad7a902 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -30,9 +30,11 @@ #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/preempt.h> +#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/kdebug.h> #include <asm/sstep.h> +#include <asm/uaccess.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -372,17 +374,62 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs); + const struct exception_table_entry *entry; + + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the nip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->nip = (unsigned long)cur->addr; regs->msr &= ~MSR_SE; regs->msr |= kcb->kprobe_saved_msr; - - reset_current_kprobe(); + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if ((entry = search_exception_tables(regs->nip)) != NULL) { + regs->nip = entry->fixup; + return 1; + } + + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; } return 0; } @@ -396,6 +443,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch (val) { case DIE_BPT: if (kprobe_handler(args->regs)) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1770a06..f698aa7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -35,7 +35,6 @@ #include <linux/mqueue.h> #include <linux/hardirq.h> #include <linux/utsname.h> -#include <linux/kprobes.h> #include <asm/pgtable.h> #include <asm/uaccess.h> @@ -460,7 +459,6 @@ void show_regs(struct pt_regs * regs) void exit_thread(void) { - kprobe_flush_task(current); discard_lazy_cpu_state(); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2f3fdad..e20c1fa 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -579,7 +579,8 @@ void __init setup_arch(char **cmdline_p) panic_timeout = 180; if (ppc_md.panic) - notifier_chain_register(&panic_notifier_list, &ppc64_panic_block); + atomic_notifier_chain_register(&panic_notifier_list, + &ppc64_panic_block); init_mm.start_code = PAGE_OFFSET; init_mm.end_code = (unsigned long) _etext; diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index cd75ab2..ec274e6 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -24,7 +24,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -161,78 +160,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2) return sys_sysfs((int)option, arg1, arg2); } -/* Handle adjtimex compatibility. */ -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage long compat_sys_adjtimex(struct timex32 __user *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if(get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if(put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} - asmlinkage long compat_sys_pause(void) { current->state = TASK_INTERRUPTIBLE; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 98660ae..9763faa 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -74,19 +74,19 @@ EXPORT_SYMBOL(__debugger_dabr_match); EXPORT_SYMBOL(__debugger_fault_handler); #endif -struct notifier_block *powerpc_die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); +ATOMIC_NOTIFIER_HEAD(powerpc_die_chain); int register_die_notifier(struct notifier_block *nb) { - int err = 0; - unsigned long flags; + return atomic_notifier_chain_register(&powerpc_die_chain, nb); +} +EXPORT_SYMBOL(register_die_notifier); - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&powerpc_die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&powerpc_die_chain, nb); } +EXPORT_SYMBOL(unregister_die_notifier); /* * Trap & Exception support diff --git a/arch/powerpc/mm/imalloc.c b/arch/powerpc/mm/imalloc.c index 8b0c132..add8c1a 100644 --- a/arch/powerpc/mm/imalloc.c +++ b/arch/powerpc/mm/imalloc.c @@ -13,12 +13,12 @@ #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <asm/cacheflush.h> #include "mmu_decl.h" -static DECLARE_MUTEX(imlist_sem); +static DEFINE_MUTEX(imlist_mutex); struct vm_struct * imlist = NULL; static int get_free_im_addr(unsigned long size, unsigned long *im_addr) @@ -257,7 +257,7 @@ struct vm_struct * im_get_free_area(unsigned long size) struct vm_struct *area; unsigned long addr; - down(&imlist_sem); + mutex_lock(&imlist_mutex); if (get_free_im_addr(size, &addr)) { printk(KERN_ERR "%s() cannot obtain addr for size 0x%lx\n", __FUNCTION__, size); @@ -272,7 +272,7 @@ struct vm_struct * im_get_free_area(unsigned long size) __FUNCTION__, addr, size); } next_im_done: - up(&imlist_sem); + mutex_unlock(&imlist_mutex); return area; } @@ -281,9 +281,9 @@ struct vm_struct * im_get_area(unsigned long v_addr, unsigned long size, { struct vm_struct *area; - down(&imlist_sem); + mutex_lock(&imlist_mutex); area = __im_get_area(v_addr, size, criteria); - up(&imlist_sem); + mutex_unlock(&imlist_mutex); return area; } @@ -297,17 +297,17 @@ void im_free(void * addr) printk(KERN_ERR "Trying to %s bad address (%p)\n", __FUNCTION__, addr); return; } - down(&imlist_sem); + mutex_lock(&imlist_mutex); for (p = &imlist ; (tmp = *p) ; p = &tmp->next) { if (tmp->addr == addr) { *p = tmp->next; unmap_vm_area(tmp); kfree(tmp); - up(&imlist_sem); + mutex_unlock(&imlist_mutex); return; } } - up(&imlist_sem); + mutex_unlock(&imlist_mutex); printk(KERN_ERR "Trying to %s nonexistent area (%p)\n", __FUNCTION__, addr); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index badac10..5e435a9 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -195,7 +195,7 @@ void show_mem(void) printk("Mem-info:\n"); show_free_areas(); printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { unsigned long flags; pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; i++) { @@ -351,7 +351,7 @@ void __init mem_init(void) max_mapnr = max_pfn; totalram_pages += free_all_bootmem(); #endif - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { for (i = 0; i < pgdat->node_spanned_pages; i++) { if (!pfn_valid(pgdat->node_start_pfn + i)) continue; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index d75ae03..a8fa1ee 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -32,7 +32,7 @@ #include <asm/io.h> #include <asm/prom.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <asm/spu.h> #include <asm/mmu_context.h> @@ -342,7 +342,7 @@ spu_free_irqs(struct spu *spu) } static LIST_HEAD(spu_list); -static DECLARE_MUTEX(spu_mutex); +static DEFINE_MUTEX(spu_mutex); static void spu_init_channels(struct spu *spu) { @@ -382,7 +382,7 @@ struct spu *spu_alloc(void) { struct spu *spu; - down(&spu_mutex); + mutex_lock(&spu_mutex); if (!list_empty(&spu_list)) { spu = list_entry(spu_list.next, struct spu, list); list_del_init(&spu->list); @@ -391,7 +391,7 @@ struct spu *spu_alloc(void) pr_debug("No SPU left\n"); spu = NULL; } - up(&spu_mutex); + mutex_unlock(&spu_mutex); if (spu) spu_init_channels(spu); @@ -402,9 +402,9 @@ EXPORT_SYMBOL_GPL(spu_alloc); void spu_free(struct spu *spu) { - down(&spu_mutex); + mutex_lock(&spu_mutex); list_add_tail(&spu->list, &spu_list); - up(&spu_mutex); + mutex_unlock(&spu_mutex); } EXPORT_SYMBOL_GPL(spu_free); @@ -633,14 +633,14 @@ static int __init create_spu(struct device_node *spe) spu->wbox_callback = NULL; spu->stop_callback = NULL; - down(&spu_mutex); + mutex_lock(&spu_mutex); spu->number = number++; ret = spu_request_irqs(spu); if (ret) goto out_unmap; list_add(&spu->list, &spu_list); - up(&spu_mutex); + mutex_unlock(&spu_mutex); pr_debug(KERN_DEBUG "Using SPE %s %02x %p %p %p %p %d\n", spu->name, spu->isrc, spu->local_store, @@ -648,7 +648,7 @@ static int __init create_spu(struct device_node *spe) goto out; out_unmap: - up(&spu_mutex); + mutex_unlock(&spu_mutex); spu_unmap(spu); out_free: kfree(spu); @@ -668,10 +668,10 @@ static void destroy_spu(struct spu *spu) static void cleanup_spu_base(void) { struct spu *spu, *tmp; - down(&spu_mutex); + mutex_lock(&spu_mutex); list_for_each_entry_safe(spu, tmp, &spu_list, list) destroy_spu(spu); - up(&spu_mutex); + mutex_unlock(&spu_mutex); } module_exit(cleanup_spu_base); diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index b3962c3a..5be40aa 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -103,7 +103,7 @@ spufs_setattr(struct dentry *dentry, struct iattr *attr) static int spufs_new_file(struct super_block *sb, struct dentry *dentry, - struct file_operations *fops, int mode, + const struct file_operations *fops, int mode, struct spu_context *ctx) { static struct inode_operations spufs_file_iops = { diff --git a/arch/powerpc/platforms/chrp/time.c b/arch/powerpc/platforms/chrp/time.c index 12c6f68..7d78890 100644 --- a/arch/powerpc/platforms/chrp/time.c +++ b/arch/powerpc/platforms/chrp/time.c @@ -120,33 +120,15 @@ int chrp_set_rtc_time(struct rtc_time *tmarg) void chrp_get_rtc_time(struct rtc_time *tm) { unsigned int year, mon, day, hour, min, sec; - int uip, i; - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - - /* Since the UIP flag is set for about 2.2 ms and the clock - * is typically written with a precision of 1 jiffy, trying - * to obtain a precision better than a few milliseconds is - * an illusion. Only consistency is interesting, this also - * allows to use the routine for /dev/rtc without a potential - * 1 second kernel busy loop triggered by any reader of /dev/rtc. - */ - - for ( i = 0; i<1000000; i++) { - uip = chrp_cmos_clock_read(RTC_FREQ_SELECT); + do { sec = chrp_cmos_clock_read(RTC_SECONDS); min = chrp_cmos_clock_read(RTC_MINUTES); hour = chrp_cmos_clock_read(RTC_HOURS); day = chrp_cmos_clock_read(RTC_DAY_OF_MONTH); mon = chrp_cmos_clock_read(RTC_MONTH); year = chrp_cmos_clock_read(RTC_YEAR); - uip |= chrp_cmos_clock_read(RTC_FREQ_SELECT); - if ((uip & RTC_UIP)==0) break; - } + } while (sec != chrp_cmos_clock_read(RTC_SECONDS)); if (!(chrp_cmos_clock_read(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { BCD_TO_BIN(sec); diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c index 5e6981d..b9a2b3d 100644 --- a/arch/powerpc/platforms/maple/time.c +++ b/arch/powerpc/platforms/maple/time.c @@ -60,34 +60,14 @@ static void maple_clock_write(unsigned long val, int addr) void maple_get_rtc_time(struct rtc_time *tm) { - int uip, i; - - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - - /* Since the UIP flag is set for about 2.2 ms and the clock - * is typically written with a precision of 1 jiffy, trying - * to obtain a precision better than a few milliseconds is - * an illusion. Only consistency is interesting, this also - * allows to use the routine for /dev/rtc without a potential - * 1 second kernel busy loop triggered by any reader of /dev/rtc. - */ - - for (i = 0; i<1000000; i++) { - uip = maple_clock_read(RTC_FREQ_SELECT); + do { tm->tm_sec = maple_clock_read(RTC_SECONDS); tm->tm_min = maple_clock_read(RTC_MINUTES); tm->tm_hour = maple_clock_read(RTC_HOURS); tm->tm_mday = maple_clock_read(RTC_DAY_OF_MONTH); tm->tm_mon = maple_clock_read(RTC_MONTH); tm->tm_year = maple_clock_read(RTC_YEAR); - uip |= maple_clock_read(RTC_FREQ_SELECT); - if ((uip & RTC_UIP)==0) - break; - } + } while (tm->tm_sec != maple_clock_read(RTC_SECONDS)); if (!(maple_clock_read(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c index a415e8d..b57e465 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ b/arch/powerpc/platforms/powermac/cpufreq_64.c @@ -21,6 +21,7 @@ #include <linux/cpufreq.h> #include <linux/init.h> #include <linux/completion.h> +#include <linux/mutex.h> #include <asm/prom.h> #include <asm/machdep.h> #include <asm/irq.h> @@ -90,7 +91,7 @@ static void (*g5_switch_volt)(int speed_mode); static int (*g5_switch_freq)(int speed_mode); static int (*g5_query_freq)(void); -static DECLARE_MUTEX(g5_switch_mutex); +static DEFINE_MUTEX(g5_switch_mutex); static struct smu_sdbp_fvt *g5_fvt_table; /* table of op. points */ @@ -327,7 +328,7 @@ static int g5_cpufreq_target(struct cpufreq_policy *policy, if (g5_pmode_cur == newstate) return 0; - down(&g5_switch_mutex); + mutex_lock(&g5_switch_mutex); freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency; freqs.new = g5_cpu_freqs[newstate].frequency; @@ -337,7 +338,7 @@ static int g5_cpufreq_target(struct cpufreq_policy *policy, rc = g5_switch_freq(newstate); cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - up(&g5_switch_mutex); + mutex_unlock(&g5_switch_mutex); return rc; } diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 86cfa6e..5ad9067 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -94,16 +94,16 @@ static struct device_node *derive_parent(const char *path) return parent; } -static struct notifier_block *pSeries_reconfig_chain; +static BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain); int pSeries_reconfig_notifier_register(struct notifier_block *nb) { - return notifier_chain_register(&pSeries_reconfig_chain, nb); + return blocking_notifier_chain_register(&pSeries_reconfig_chain, nb); } void pSeries_reconfig_notifier_unregister(struct notifier_block *nb) { - notifier_chain_unregister(&pSeries_reconfig_chain, nb); + blocking_notifier_chain_unregister(&pSeries_reconfig_chain, nb); } static int pSeries_reconfig_add_node(const char *path, struct property *proplist) @@ -131,7 +131,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist goto out_err; } - err = notifier_call_chain(&pSeries_reconfig_chain, + err = blocking_notifier_call_chain(&pSeries_reconfig_chain, PSERIES_RECONFIG_ADD, np); if (err == NOTIFY_BAD) { printk(KERN_ERR "Failed to add device node %s\n", path); @@ -171,7 +171,7 @@ static int pSeries_reconfig_remove_node(struct device_node *np) remove_node_proc_entries(np); - notifier_call_chain(&pSeries_reconfig_chain, + blocking_notifier_call_chain(&pSeries_reconfig_chain, PSERIES_RECONFIG_REMOVE, np); of_detach_node(np); diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig index 54a0a9b..3a3e302 100644 --- a/arch/ppc/Kconfig +++ b/arch/ppc/Kconfig @@ -19,6 +19,10 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/ppc/kernel/ppc_htab.c b/arch/ppc/kernel/ppc_htab.c index 2f5c765..9b84bff 100644 --- a/arch/ppc/kernel/ppc_htab.c +++ b/arch/ppc/kernel/ppc_htab.c @@ -52,7 +52,7 @@ static int ppc_htab_open(struct inode *inode, struct file *file) return single_open(file, ppc_htab_show, NULL); } -struct file_operations ppc_htab_operations = { +const struct file_operations ppc_htab_operations = { .open = ppc_htab_open, .read = seq_read, .llseek = seq_lseek, diff --git a/arch/ppc/platforms/chrp_time.c b/arch/ppc/platforms/chrp_time.c index c862777..51e06ad 100644 --- a/arch/ppc/platforms/chrp_time.c +++ b/arch/ppc/platforms/chrp_time.c @@ -119,44 +119,28 @@ int chrp_set_rtc_time(unsigned long nowtime) unsigned long chrp_get_rtc_time(void) { unsigned int year, mon, day, hour, min, sec; - int uip, i; - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - - /* Since the UIP flag is set for about 2.2 ms and the clock - * is typically written with a precision of 1 jiffy, trying - * to obtain a precision better than a few milliseconds is - * an illusion. Only consistency is interesting, this also - * allows to use the routine for /dev/rtc without a potential - * 1 second kernel busy loop triggered by any reader of /dev/rtc. - */ - - for ( i = 0; i<1000000; i++) { - uip = chrp_cmos_clock_read(RTC_FREQ_SELECT); + do { sec = chrp_cmos_clock_read(RTC_SECONDS); min = chrp_cmos_clock_read(RTC_MINUTES); hour = chrp_cmos_clock_read(RTC_HOURS); day = chrp_cmos_clock_read(RTC_DAY_OF_MONTH); mon = chrp_cmos_clock_read(RTC_MONTH); year = chrp_cmos_clock_read(RTC_YEAR); - uip |= chrp_cmos_clock_read(RTC_FREQ_SELECT); - if ((uip & RTC_UIP)==0) break; + } while (sec != chrp_cmos_clock_read(RTC_SECONDS)); + + if (!(chrp_cmos_clock_read(RTC_CONTROL) & RTC_DM_BINARY) + || RTC_ALWAYS_BCD) { + BCD_TO_BIN(sec); + BCD_TO_BIN(min); + BCD_TO_BIN(hour); + BCD_TO_BIN(day); + BCD_TO_BIN(mon); + BCD_TO_BIN(year); } - if (!(chrp_cmos_clock_read(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - BCD_TO_BIN(sec); - BCD_TO_BIN(min); - BCD_TO_BIN(hour); - BCD_TO_BIN(day); - BCD_TO_BIN(mon); - BCD_TO_BIN(year); - } - if ((year += 1900) < 1970) + year += 1900; + if (year < 1970) year += 100; return mktime(year, mon, day, hour, min, sec); } diff --git a/arch/ppc/platforms/prep_setup.c b/arch/ppc/platforms/prep_setup.c index a0fc628..d95c05d 100644 --- a/arch/ppc/platforms/prep_setup.c +++ b/arch/ppc/platforms/prep_setup.c @@ -736,7 +736,7 @@ ibm_statusled_progress(char *s, unsigned short hex) hex = 0xfff; if (!notifier_installed) { ++notifier_installed; - notifier_chain_register(&panic_notifier_list, + atomic_notifier_chain_register(&panic_notifier_list, &ibm_statusled_block); } } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2b7364e..01c5c08 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -14,6 +14,10 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/s390/crypto/crypt_s390_query.c b/arch/s390/crypto/crypt_s390_query.c index def02bd..54fb11d 100644 --- a/arch/s390/crypto/crypt_s390_query.c +++ b/arch/s390/crypto/crypt_s390_query.c @@ -55,7 +55,7 @@ static void query_available_functions(void) printk(KERN_INFO "KMC_AES_256: %d\n", crypt_s390_func_available(KMC_AES_256_ENCRYPT)); - /* query available KIMD fucntions */ + /* query available KIMD functions */ printk(KERN_INFO "KIMD_QUERY: %d\n", crypt_s390_func_available(KIMD_QUERY)); printk(KERN_INFO "KIMD_SHA_1: %d\n", diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index cc058dc..5e14de3 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -26,7 +26,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -705,79 +704,6 @@ asmlinkage long sys32_sendfile64(int out_fd, int in_fd, return ret; } -/* Handle adjtimex compatibility. */ - -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage long sys32_adjtimex(struct timex32 __user *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if(get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if(put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} - #ifdef CONFIG_SYSCTL struct __sysctl_args32 { u32 name; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 50e8013..199da68 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -551,10 +551,10 @@ sys32_newuname_wrapper: llgtr %r2,%r2 # struct new_utsname * jg s390x_newuname # branch to system call - .globl sys32_adjtimex_wrapper -sys32_adjtimex_wrapper: - llgtr %r2,%r2 # struct timex_emu31 * - jg sys32_adjtimex # branch to system call + .globl compat_sys_adjtimex_wrapper +compat_sys_adjtimex_wrapper: + llgtr %r2,%r2 # struct compat_timex * + jg compat_sys_adjtimex # branch to system call .globl sys32_mprotect_wrapper sys32_mprotect_wrapper: diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 99182a41..4a0f5a1 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -76,17 +76,17 @@ unsigned long thread_saved_pc(struct task_struct *tsk) /* * Need to know about CPUs going idle? */ -static struct notifier_block *idle_chain; +static ATOMIC_NOTIFIER_HEAD(idle_chain); int register_idle_notifier(struct notifier_block *nb) { - return notifier_chain_register(&idle_chain, nb); + return atomic_notifier_chain_register(&idle_chain, nb); } EXPORT_SYMBOL(register_idle_notifier); int unregister_idle_notifier(struct notifier_block *nb) { - return notifier_chain_unregister(&idle_chain, nb); + return atomic_notifier_chain_unregister(&idle_chain, nb); } EXPORT_SYMBOL(unregister_idle_notifier); @@ -95,7 +95,7 @@ void do_monitor_call(struct pt_regs *regs, long interruption_code) /* disable monitor call class 0 */ __ctl_clear_bit(8, 15); - notifier_call_chain(&idle_chain, CPU_NOT_IDLE, + atomic_notifier_call_chain(&idle_chain, CPU_NOT_IDLE, (void *)(long) smp_processor_id()); } @@ -116,7 +116,8 @@ static void default_idle(void) return; } - rc = notifier_call_chain(&idle_chain, CPU_IDLE, (void *)(long) cpu); + rc = atomic_notifier_call_chain(&idle_chain, + CPU_IDLE, (void *)(long) cpu); if (rc != NOTIFY_OK && rc != NOTIFY_DONE) BUG(); if (rc != NOTIFY_OK) { diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 7c88d85..2f56654 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -132,7 +132,7 @@ SYSCALL(sys_clone_glue,sys_clone_glue,sys32_clone_glue) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) SYSCALL(sys_newuname,s390x_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ -SYSCALL(sys_adjtimex,sys_adjtimex,sys32_adjtimex_wrapper) +SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) NI_SYSCALL /* old "create module" */ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index e9b275d..58583f4 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -21,6 +21,14 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_HARDIRQS bool default y diff --git a/arch/sh/boards/mpc1211/rtc.c b/arch/sh/boards/mpc1211/rtc.c index 4d100f0..a76c655 100644 --- a/arch/sh/boards/mpc1211/rtc.c +++ b/arch/sh/boards/mpc1211/rtc.c @@ -9,36 +9,16 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/time.h> +#include <linux/bcd.h> #include <linux/mc146818rtc.h> -#ifndef BCD_TO_BIN -#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10) -#endif - -#ifndef BIN_TO_BCD -#define BIN_TO_BCD(val) ((val)=(((val)/10)<<4) + (val)%10) -#endif - -/* arc/i386/kernel/time.c */ unsigned long get_cmos_time(void) { unsigned int year, mon, day, hour, min, sec; - int i; spin_lock(&rtc_lock); - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - /* read RTC exactly on falling edge of update flag */ - for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */ - if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) - break; - for (i = 0 ; i < 1000000 ; i++) /* must try at least 2.228 ms */ - if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - break; - do { /* Isn't this overkill ? UIP above should guarantee consistency */ + + do { sec = CMOS_READ(RTC_SECONDS); min = CMOS_READ(RTC_MINUTES); hour = CMOS_READ(RTC_HOURS); @@ -46,18 +26,22 @@ unsigned long get_cmos_time(void) mon = CMOS_READ(RTC_MONTH); year = CMOS_READ(RTC_YEAR); } while (sec != CMOS_READ(RTC_SECONDS)); - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - BCD_TO_BIN(sec); - BCD_TO_BIN(min); - BCD_TO_BIN(hour); - BCD_TO_BIN(day); - BCD_TO_BIN(mon); - BCD_TO_BIN(year); - } + + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { + BCD_TO_BIN(sec); + BCD_TO_BIN(min); + BCD_TO_BIN(hour); + BCD_TO_BIN(day); + BCD_TO_BIN(mon); + BCD_TO_BIN(year); + } + spin_unlock(&rtc_lock); - if ((year += 1900) < 1970) + + year += 1900; + if (year < 1970) year += 100; + return mktime(year, mon, day, hour, min, sec); } diff --git a/arch/sh/boards/sh03/rtc.c b/arch/sh/boards/sh03/rtc.c index cbeca70..d609863 100644 --- a/arch/sh/boards/sh03/rtc.c +++ b/arch/sh/boards/sh03/rtc.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/time.h> +#include <linux/bcd.h> #include <asm/io.h> #include <linux/rtc.h> #include <linux/spinlock.h> @@ -33,14 +34,6 @@ #define RTC_BUSY 1 #define RTC_STOP 2 -#ifndef BCD_TO_BIN -#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10) -#endif - -#ifndef BIN_TO_BCD -#define BIN_TO_BCD(val) ((val)=(((val)/10)<<4) + (val)%10) -#endif - extern void (*rtc_get_time)(struct timespec *); extern int (*rtc_set_time)(const time_t); extern spinlock_t rtc_lock; @@ -48,13 +41,9 @@ extern spinlock_t rtc_lock; unsigned long get_cmos_time(void) { unsigned int year, mon, day, hour, min, sec; - int i; spin_lock(&rtc_lock); again: - for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */ - if (!(ctrl_inb(RTC_CTL) & RTC_BUSY)) - break; do { sec = (ctrl_inb(RTC_SEC1) & 0xf) + (ctrl_inb(RTC_SEC10) & 0x7) * 10; min = (ctrl_inb(RTC_MIN1) & 0xf) + (ctrl_inb(RTC_MIN10) & 0xf) * 10; diff --git a/arch/sh/kernel/cpu/rtc.c b/arch/sh/kernel/cpu/rtc.c index f8361f5..4304cf7 100644 --- a/arch/sh/kernel/cpu/rtc.c +++ b/arch/sh/kernel/cpu/rtc.c @@ -9,18 +9,10 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/time.h> - +#include <linux/bcd.h> #include <asm/io.h> #include <asm/rtc.h> -#ifndef BCD_TO_BIN -#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10) -#endif - -#ifndef BIN_TO_BCD -#define BIN_TO_BCD(val) ((val)=(((val)/10)<<4) + (val)%10) -#endif - void sh_rtc_gettimeofday(struct timespec *ts) { unsigned int sec128, sec, sec2, min, hr, wk, day, mon, yr, yr100, cf_bit; diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index c0e79843..7ee4ca2 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -20,6 +20,7 @@ #include <linux/root_dev.h> #include <linux/utsname.h> #include <linux/cpu.h> +#include <linux/pfn.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/sections.h> @@ -275,10 +276,6 @@ void __init setup_arch(char **cmdline_p) sh_mv_setup(cmdline_p); -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) - /* * Find the highest page frame number we have available */ diff --git a/arch/sh64/Kconfig b/arch/sh64/Kconfig index 07b172d..58c678e 100644 --- a/arch/sh64/Kconfig +++ b/arch/sh64/Kconfig @@ -21,6 +21,14 @@ config RWSEM_GENERIC_SPINLOCK bool default y +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/sh64/kernel/setup.c b/arch/sh64/kernel/setup.c index c7a7b816..d2711c9 100644 --- a/arch/sh64/kernel/setup.c +++ b/arch/sh64/kernel/setup.c @@ -48,6 +48,7 @@ #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/initrd.h> +#include <linux/pfn.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/pgtable.h> diff --git a/arch/sh64/kernel/time.c b/arch/sh64/kernel/time.c index 0773c9f..6b8f4d2 100644 --- a/arch/sh64/kernel/time.c +++ b/arch/sh64/kernel/time.c @@ -30,6 +30,7 @@ #include <linux/profile.h> #include <linux/smp.h> #include <linux/module.h> +#include <linux/bcd.h> #include <asm/registers.h> /* required by inline __asm__ stmt. */ @@ -105,14 +106,6 @@ #define RCR1 rtc_base+0x38 #define RCR2 rtc_base+0x3c -#ifndef BCD_TO_BIN -#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10) -#endif - -#ifndef BIN_TO_BCD -#define BIN_TO_BCD(val) ((val)=(((val)/10)<<4) + (val)%10) -#endif - #define TICK_SIZE (tick_nsec / 1000) extern unsigned long wall_jiffies; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 7c58fc1..9431e96 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -150,6 +150,14 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index 267afdd..d1e2fc5 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -162,6 +162,14 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y if !ULTRA_HAS_POPULATION_COUNT + config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig index f819a96..900fb0b 100644 --- a/arch/sparc64/defconfig +++ b/arch/sparc64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit # Linux kernel version: 2.6.16 -# Mon Mar 20 01:23:21 2006 +# Sun Mar 26 14:58:11 2006 # CONFIG_SPARC=y CONFIG_SPARC64=y @@ -38,6 +38,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_SYSCTL=y # CONFIG_AUDIT is not set # CONFIG_IKCONFIG is not set +CONFIG_RELAY=y CONFIG_INITRAMFS_SOURCE="" CONFIG_UID16=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -53,10 +54,6 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -68,7 +65,6 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_KMOD=y @@ -76,6 +72,7 @@ CONFIG_KMOD=y # # Block layer # +CONFIG_BLK_DEV_IO_TRACE=y # # IO Schedulers @@ -111,6 +108,8 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m CONFIG_US3_FREQ=m CONFIG_US2E_FREQ=m CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_FIND_NEXT_BIT=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_HUGETLB_PAGE_SIZE_4MB=y # CONFIG_HUGETLB_PAGE_SIZE_512K is not set @@ -128,7 +127,6 @@ CONFIG_HAVE_MEMORY_PRESENT=y CONFIG_SPARSEMEM_EXTREME=y CONFIG_MEMORY_HOTPLUG=y CONFIG_SPLIT_PTLOCK_CPUS=4 -CONFIG_MIGRATION=y CONFIG_GENERIC_ISA_DMA=y CONFIG_SBUS=y CONFIG_SBUSCHAR=y @@ -136,7 +134,6 @@ CONFIG_SUN_AUXIO=y CONFIG_SUN_IO=y CONFIG_PCI=y CONFIG_PCI_DOMAINS=y -# CONFIG_PCI_LEGACY_PROC is not set # CONFIG_PCI_DEBUG is not set CONFIG_SUN_OPENPROMFS=m CONFIG_SPARC32_COMPAT=y @@ -201,6 +198,8 @@ CONFIG_TCP_CONG_VEGAS=m CONFIG_TCP_CONG_SCALABLE=m CONFIG_IPV6=m CONFIG_IPV6_PRIVACY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -213,10 +212,12 @@ CONFIG_IPV6_TUNNEL=m # CONFIG_IP_DCCP=m CONFIG_INET_DCCP_DIAG=m +CONFIG_IP_DCCP_ACKVEC=y # # DCCP CCIDs Configuration (EXPERIMENTAL) # +CONFIG_IP_DCCP_CCID2=m CONFIG_IP_DCCP_CCID3=m CONFIG_IP_DCCP_TFRC_LIB=m @@ -224,7 +225,6 @@ CONFIG_IP_DCCP_TFRC_LIB=m # DCCP Kernel Hacking # # CONFIG_IP_DCCP_DEBUG is not set -# CONFIG_IP_DCCP_UNLOAD_HACK is not set # # SCTP Configuration (EXPERIMENTAL) @@ -309,6 +309,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_UB=m # CONFIG_BLK_DEV_RAM is not set CONFIG_BLK_DEV_RAM_COUNT=16 +# CONFIG_BLK_DEV_INITRD is not set CONFIG_CDROM_PKTCDVD=m CONFIG_CDROM_PKTCDVD_BUFFERS=8 CONFIG_CDROM_PKTCDVD_WCACHE=y @@ -722,7 +723,6 @@ CONFIG_I2C_ALGOBIT=y # CONFIG_I2C_PARPORT_LIGHT is not set # CONFIG_I2C_PROSAVAGE is not set # CONFIG_I2C_SAVAGE4 is not set -# CONFIG_SCx200_ACB is not set # CONFIG_I2C_SIS5595 is not set # CONFIG_I2C_SIS630 is not set # CONFIG_I2C_SIS96X is not set @@ -808,10 +808,6 @@ CONFIG_HWMON=y # # -# Multimedia Capabilities Port drivers -# - -# # Multimedia devices # # CONFIG_VIDEO_DEV is not set @@ -820,6 +816,7 @@ CONFIG_HWMON=y # Digital Video Broadcasting Devices # # CONFIG_DVB is not set +# CONFIG_USB_DABUSB is not set # # Graphics support @@ -901,10 +898,12 @@ CONFIG_SND_SEQ_DUMMY=m CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m +CONFIG_SND_PCM_OSS_PLUGINS=y CONFIG_SND_SEQUENCER_OSS=y # CONFIG_SND_RTCTIMER is not set # CONFIG_SND_DYNAMIC_MINORS is not set CONFIG_SND_SUPPORT_OLD_API=y +CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_VERBOSE_PRINTK is not set # CONFIG_SND_DEBUG is not set @@ -987,6 +986,7 @@ CONFIG_SND_SUN_CS4231=m # CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB_ARCH_HAS_EHCI=y CONFIG_USB=y # CONFIG_USB_DEBUG is not set @@ -1014,7 +1014,6 @@ CONFIG_USB_UHCI_HCD=m # # USB Device Class drivers # -# CONFIG_OBSOLETE_OSS_USB_DRIVER is not set # CONFIG_USB_ACM is not set # CONFIG_USB_PRINTER is not set @@ -1058,15 +1057,6 @@ CONFIG_USB_HIDDEV=y # CONFIG_USB_MICROTEK is not set # -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# # USB Network Adapters # # CONFIG_USB_CATC is not set @@ -1194,7 +1184,6 @@ CONFIG_TMPFS=y CONFIG_HUGETLBFS=y CONFIG_HUGETLB_PAGE=y CONFIG_RAMFS=y -CONFIG_RELAYFS_FS=m # CONFIG_CONFIGFS_FS is not set # diff --git a/arch/sparc64/kernel/kprobes.c b/arch/sparc64/kernel/kprobes.c index b9a9ce7..ffc7309 100644 --- a/arch/sparc64/kernel/kprobes.c +++ b/arch/sparc64/kernel/kprobes.c @@ -6,9 +6,11 @@ #include <linux/config.h> #include <linux/kernel.h> #include <linux/kprobes.h> +#include <linux/module.h> #include <asm/kdebug.h> #include <asm/signal.h> #include <asm/cacheflush.h> +#include <asm/uaccess.h> /* We do not have hardware single-stepping on sparc64. * So we implement software single-stepping with breakpoint @@ -302,16 +304,68 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + const struct exception_table_entry *entry; + + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the tpc points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->tpc = (unsigned long)cur->addr; + regs->tnpc = kcb->kprobe_orig_tnpc; + regs->tstate = ((regs->tstate & ~TSTATE_PIL) | + kcb->kprobe_orig_tstate_pil); + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs, kcb); + entry = search_exception_tables(regs->tpc); + if (entry) { + regs->tpc = entry->fixup; + regs->tnpc = regs->tpc + 4; + return 1; + } - reset_current_kprobe(); - preempt_enable_no_resched(); + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; } + return 0; } @@ -324,6 +378,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch (val) { case DIE_DEBUG: if (kprobe_handler(args->regs)) diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c index 9914a17..f5e8db1 100644 --- a/arch/sparc64/kernel/sparc64_ksyms.c +++ b/arch/sparc64/kernel/sparc64_ksyms.c @@ -175,11 +175,6 @@ EXPORT_SYMBOL(set_bit); EXPORT_SYMBOL(clear_bit); EXPORT_SYMBOL(change_bit); -/* Bit searching */ -EXPORT_SYMBOL(find_next_bit); -EXPORT_SYMBOL(find_next_zero_bit); -EXPORT_SYMBOL(find_next_zero_le_bit); - EXPORT_SYMBOL(ivector_table); EXPORT_SYMBOL(enable_irq); EXPORT_SYMBOL(disable_irq); @@ -279,18 +274,9 @@ EXPORT_SYMBOL(__prom_getsibling); /* sparc library symbols */ EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(__strlen_user); EXPORT_SYMBOL(__strnlen_user); -EXPORT_SYMBOL(strcpy); -EXPORT_SYMBOL(strncpy); -EXPORT_SYMBOL(strcat); -EXPORT_SYMBOL(strncat); -EXPORT_SYMBOL(strcmp); -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strpbrk); -EXPORT_SYMBOL(strstr); #ifdef CONFIG_SOLARIS_EMUL_MODULE EXPORT_SYMBOL(linux_sparc_syscall); @@ -324,7 +310,6 @@ EXPORT_SYMBOL(__memscan_zero); EXPORT_SYMBOL(__memscan_generic); EXPORT_SYMBOL(__memcmp); EXPORT_SYMBOL(__memset); -EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_nocheck); diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 0e41df0..2e906ba 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -19,7 +19,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -945,79 +944,6 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, return ret; } -/* Handle adjtimex compatibility. */ - -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage long sys32_adjtimex(struct timex32 __user *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if (get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if (put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} - /* This is just a version for 32-bit applications which does * not force O_LARGEFILE on. */ diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S index c3adb7a..3b250f2 100644 --- a/arch/sparc64/kernel/systbls.S +++ b/arch/sparc64/kernel/systbls.S @@ -63,7 +63,7 @@ sys_call_table32: /*200*/ .word sys32_ssetmask, sys_sigsuspend, compat_sys_newlstat, sys_uselib, compat_sys_old_readdir .word sys32_readahead, sys32_socketcall, sys32_syslog, sys32_lookup_dcookie, sys32_fadvise64 /*210*/ .word sys32_fadvise64_64, sys32_tgkill, sys32_waitpid, sys_swapoff, sys32_sysinfo - .word sys32_ipc, sys32_sigreturn, sys_clone, sys32_ioprio_get, sys32_adjtimex + .word sys32_ipc, sys32_sigreturn, sys_clone, sys32_ioprio_get, compat_sys_adjtimex /*220*/ .word sys32_sigprocmask, sys_ni_syscall, sys32_delete_module, sys_ni_syscall, sys32_getpgid .word sys32_bdflush, sys32_sysfs, sys_nis_syscall, sys32_setfsuid16, sys32_setfsgid16 /*230*/ .word sys32_select, compat_sys_time, sys_nis_syscall, compat_sys_stime, compat_sys_statfs64 diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c index 7d61f1b..e55b5c6 100644 --- a/arch/sparc64/kernel/time.c +++ b/arch/sparc64/kernel/time.c @@ -641,23 +641,8 @@ static void __init set_system_time(void) mon = MSTK_REG_MONTH(mregs); year = MSTK_CVT_YEAR( MSTK_REG_YEAR(mregs) ); } else { - int i; - /* Dallas 12887 RTC chip. */ - /* Stolen from arch/i386/kernel/time.c, see there for - * credits and descriptive comments. - */ - for (i = 0; i < 1000000; i++) { - if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) - break; - udelay(10); - } - for (i = 0; i < 1000000; i++) { - if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - break; - udelay(10); - } do { sec = CMOS_READ(RTC_SECONDS); min = CMOS_READ(RTC_MINUTES); @@ -666,6 +651,7 @@ static void __init set_system_time(void) mon = CMOS_READ(RTC_MONTH); year = CMOS_READ(RTC_YEAR); } while (sec != CMOS_READ(RTC_SECONDS)); + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { BCD_TO_BIN(sec); BCD_TO_BIN(min); diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c index df612e4..ff090bb 100644 --- a/arch/sparc64/kernel/traps.c +++ b/arch/sparc64/kernel/traps.c @@ -43,18 +43,19 @@ #include <linux/kmod.h> #endif -struct notifier_block *sparc64die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); +ATOMIC_NOTIFIER_HEAD(sparc64die_chain); int register_die_notifier(struct notifier_block *nb) { - int err = 0; - unsigned long flags; - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&sparc64die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; + return atomic_notifier_chain_register(&sparc64die_chain, nb); } +EXPORT_SYMBOL(register_die_notifier); + +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&sparc64die_chain, nb); +} +EXPORT_SYMBOL(unregister_die_notifier); /* When an irrecoverable trap occurs at tl > 0, the trap entry * code logs the trap state registers at every level in the trap diff --git a/arch/sparc64/lib/Makefile b/arch/sparc64/lib/Makefile index 8812ded..4a725d8 100644 --- a/arch/sparc64/lib/Makefile +++ b/arch/sparc64/lib/Makefile @@ -14,6 +14,6 @@ lib-y := PeeCeeI.o copy_page.o clear_page.o strlen.o strncmp.o \ NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o NGpatch.o \ NGpage.o NGbzero.o \ copy_in_user.o user_fixup.o memmove.o \ - mcount.o ipcsum.o rwsem.o xor.o find_bit.o delay.o + mcount.o ipcsum.o rwsem.o xor.o delay.o obj-y += iomap.o diff --git a/arch/sparc64/lib/find_bit.c b/arch/sparc64/lib/find_bit.c deleted file mode 100644 index 6059557..0000000 --- a/arch/sparc64/lib/find_bit.c +++ /dev/null @@ -1,127 +0,0 @@ -#include <linux/bitops.h> - -/** - * find_next_bit - find the next set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - const unsigned long *p = addr + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < 64) - goto found_first; - if (tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if ((tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (64 - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); -} - -/* find_next_zero_bit() finds the first zero bit in a bit string of length - * 'size' bits, starting the search at bit 'offset'. This is largely based - * on Linus's ALPHA routines, which are pretty portable BTW. - */ - -unsigned long find_next_zero_bit(const unsigned long *addr, - unsigned long size, unsigned long offset) -{ - const unsigned long *p = addr + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp |= ~0UL >> (64-offset); - if (size < 64) - goto found_first; - if (~tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if (~(tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp |= ~0UL << size; - if (tmp == ~0UL) /* Are any bits zero? */ - return result + size; /* Nope. */ -found_middle: - return result + ffz(tmp); -} - -unsigned long find_next_zero_le_bit(unsigned long *addr, unsigned long size, unsigned long offset) -{ - unsigned long *p = addr + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if(offset) { - tmp = __swab64p(p++); - tmp |= (~0UL >> (64-offset)); - if(size < 64) - goto found_first; - if(~tmp) - goto found_middle; - size -= 64; - result += 64; - } - while(size & ~63) { - if(~(tmp = __swab64p(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if(!size) - return result; - tmp = __swab64p(p); -found_first: - tmp |= (~0UL << size); - if (tmp == ~0UL) /* Are any bits zero? */ - return result + size; /* Nope. */ -found_middle: - return result + ffz(tmp); -} diff --git a/arch/sparc64/mm/fault.c b/arch/sparc64/mm/fault.c index d21ff32..0db2f7d 100644 --- a/arch/sparc64/mm/fault.c +++ b/arch/sparc64/mm/fault.c @@ -413,12 +413,12 @@ good_area: #ifdef CONFIG_HUGETLB_PAGE mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE)); #endif - if (unlikely(mm_rss >= + if (unlikely(mm_rss > mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit)) tsb_grow(mm, MM_TSB_BASE, mm_rss); #ifdef CONFIG_HUGETLB_PAGE mm_rss = mm->context.huge_pte_count; - if (unlikely(mm_rss >= + if (unlikely(mm_rss > mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) tsb_grow(mm, MM_TSB_HUGE, mm_rss); #endif diff --git a/arch/um/Kconfig.i386 b/arch/um/Kconfig.i386 index ef79ed2..85e6a55 100644 --- a/arch/um/Kconfig.i386 +++ b/arch/um/Kconfig.i386 @@ -52,3 +52,8 @@ config ARCH_HAS_SC_SIGNALS config ARCH_REUSE_HOST_VSYSCALL_AREA bool default y + +config GENERIC_HWEIGHT + bool + default y + diff --git a/arch/um/Kconfig.x86_64 b/arch/um/Kconfig.x86_64 index aae19bc..f60e9e5 100644 --- a/arch/um/Kconfig.x86_64 +++ b/arch/um/Kconfig.x86_64 @@ -46,3 +46,8 @@ config ARCH_REUSE_HOST_VSYSCALL_AREA config SMP_BROKEN bool default y + +config GENERIC_HWEIGHT + bool + default y + diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 54388d1..1488816 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -762,7 +762,8 @@ static struct notifier_block panic_exit_notifier = { static int add_notifier(void) { - notifier_chain_register(&panic_notifier_list, &panic_exit_notifier); + atomic_notifier_chain_register(&panic_notifier_list, + &panic_exit_notifier); return(0); } diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index fa617e0..0336575 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -71,7 +71,7 @@ struct io_thread_req { int error; }; -extern int open_ubd_file(char *file, struct openflags *openflags, +extern int open_ubd_file(char *file, struct openflags *openflags, int shared, char **backing_file_out, int *bitmap_offset_out, unsigned long *bitmap_len_out, int *data_offset_out, int *create_cow_out); @@ -137,7 +137,7 @@ static int fake_major = MAJOR_NR; static struct gendisk *ubd_gendisk[MAX_DEV]; static struct gendisk *fake_gendisk[MAX_DEV]; - + #ifdef CONFIG_BLK_DEV_UBD_SYNC #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \ .cl = 1 }) @@ -168,6 +168,7 @@ struct ubd { __u64 size; struct openflags boot_openflags; struct openflags openflags; + int shared; int no_cow; struct cow cow; struct platform_device pdev; @@ -189,6 +190,7 @@ struct ubd { .boot_openflags = OPEN_FLAGS, \ .openflags = OPEN_FLAGS, \ .no_cow = 0, \ + .shared = 0, \ .cow = DEFAULT_COW, \ } @@ -305,7 +307,7 @@ static int ubd_setup_common(char *str, int *index_out) } major = simple_strtoul(str, &end, 0); if((*end != '\0') || (end == str)){ - printk(KERN_ERR + printk(KERN_ERR "ubd_setup : didn't parse major number\n"); return(1); } @@ -316,7 +318,7 @@ static int ubd_setup_common(char *str, int *index_out) printk(KERN_ERR "Can't assign a fake major twice\n"); goto out1; } - + fake_major = major; printk(KERN_INFO "Setting extra ubd major number to %d\n", @@ -351,7 +353,7 @@ static int ubd_setup_common(char *str, int *index_out) if (index_out) *index_out = n; - for (i = 0; i < 4; i++) { + for (i = 0; i < sizeof("rscd="); i++) { switch (*str) { case 'r': flags.w = 0; @@ -362,11 +364,14 @@ static int ubd_setup_common(char *str, int *index_out) case 'd': dev->no_cow = 1; break; + case 'c': + dev->shared = 1; + break; case '=': str++; goto break_loop; default: - printk(KERN_ERR "ubd_setup : Expected '=' or flag letter (r,s or d)\n"); + printk(KERN_ERR "ubd_setup : Expected '=' or flag letter (r, s, c, or d)\n"); goto out; } str++; @@ -515,7 +520,7 @@ static void ubd_handler(void) spin_unlock(&ubd_io_lock); return; } - + ubd_finish(rq, req.error); reactivate_fd(thread_fd, UBD_IRQ); do_ubd_request(ubd_queue); @@ -532,7 +537,7 @@ static int io_pid = -1; void kill_io_thread(void) { - if(io_pid != -1) + if(io_pid != -1) os_kill_process(io_pid, 1); } @@ -567,14 +572,15 @@ static int ubd_open_dev(struct ubd *dev) create_cow = 0; create_ptr = (dev->cow.file != NULL) ? &create_cow : NULL; back_ptr = dev->no_cow ? NULL : &dev->cow.file; - dev->fd = open_ubd_file(dev->file, &dev->openflags, back_ptr, - &dev->cow.bitmap_offset, &dev->cow.bitmap_len, - &dev->cow.data_offset, create_ptr); + dev->fd = open_ubd_file(dev->file, &dev->openflags, dev->shared, + back_ptr, &dev->cow.bitmap_offset, + &dev->cow.bitmap_len, &dev->cow.data_offset, + create_ptr); if((dev->fd == -ENOENT) && create_cow){ - dev->fd = create_cow_file(dev->file, dev->cow.file, + dev->fd = create_cow_file(dev->file, dev->cow.file, dev->openflags, 1 << 9, PAGE_SIZE, - &dev->cow.bitmap_offset, + &dev->cow.bitmap_offset, &dev->cow.bitmap_len, &dev->cow.data_offset); if(dev->fd >= 0){ @@ -598,16 +604,16 @@ static int ubd_open_dev(struct ubd *dev) } flush_tlb_kernel_vm(); - err = read_cow_bitmap(dev->fd, dev->cow.bitmap, - dev->cow.bitmap_offset, + err = read_cow_bitmap(dev->fd, dev->cow.bitmap, + dev->cow.bitmap_offset, dev->cow.bitmap_len); if(err < 0) goto error; flags = dev->openflags; flags.w = 0; - err = open_ubd_file(dev->cow.file, &flags, NULL, NULL, NULL, - NULL, NULL); + err = open_ubd_file(dev->cow.file, &flags, dev->shared, NULL, + NULL, NULL, NULL, NULL); if(err < 0) goto error; dev->cow.fd = err; } @@ -685,11 +691,11 @@ static int ubd_add(int n) dev->size = ROUND_BLOCK(dev->size); err = ubd_new_disk(MAJOR_NR, dev->size, n, &ubd_gendisk[n]); - if(err) + if(err) goto out_close; - + if(fake_major != MAJOR_NR) - ubd_new_disk(fake_major, dev->size, n, + ubd_new_disk(fake_major, dev->size, n, &fake_gendisk[n]); /* perhaps this should also be under the "if (fake_major)" above */ @@ -854,7 +860,7 @@ int ubd_init(void) return -1; } platform_driver_register(&ubd_driver); - for (i = 0; i < MAX_DEV; i++) + for (i = 0; i < MAX_DEV; i++) ubd_add(i); return 0; } @@ -872,16 +878,16 @@ int ubd_driver_init(void){ * enough. So use anyway the io thread. */ } stack = alloc_stack(0, 0); - io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), + io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), &thread_fd); if(io_pid < 0){ - printk(KERN_ERR + printk(KERN_ERR "ubd : Failed to start I/O thread (errno = %d) - " "falling back to synchronous I/O\n", -io_pid); io_pid = -1; return(0); } - err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr, + err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr, SA_INTERRUPT, "ubd", ubd_dev); if(err != 0) printk(KERN_ERR "um_request_irq failed - errno = %d\n", -err); @@ -978,7 +984,7 @@ static void cowify_req(struct io_thread_req *req, unsigned long *bitmap, if(req->op == UBD_READ) { for(i = 0; i < req->length >> 9; i++){ if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) - ubd_set_bit(i, (unsigned char *) + ubd_set_bit(i, (unsigned char *) &req->sector_mask); } } @@ -999,7 +1005,7 @@ static int prepare_request(struct request *req, struct io_thread_req *io_req) /* This should be impossible now */ if((rq_data_dir(req) == WRITE) && !dev->openflags.w){ - printk("Write attempted on readonly ubd device %s\n", + printk("Write attempted on readonly ubd device %s\n", disk->disk_name); end_request(req, 0); return(1); @@ -1182,7 +1188,7 @@ int read_cow_bitmap(int fd, void *buf, int offset, int len) return(0); } -int open_ubd_file(char *file, struct openflags *openflags, +int open_ubd_file(char *file, struct openflags *openflags, int shared, char **backing_file_out, int *bitmap_offset_out, unsigned long *bitmap_len_out, int *data_offset_out, int *create_cow_out) @@ -1206,10 +1212,14 @@ int open_ubd_file(char *file, struct openflags *openflags, return fd; } - err = os_lock_file(fd, openflags->w); - if(err < 0){ - printk("Failed to lock '%s', err = %d\n", file, -err); - goto out_close; + if(shared) + printk("Not locking \"%s\" on the host\n", file); + else { + err = os_lock_file(fd, openflags->w); + if(err < 0){ + printk("Failed to lock '%s', err = %d\n", file, -err); + goto out_close; + } } /* Succesful return case! */ @@ -1260,7 +1270,7 @@ int create_cow_file(char *cow_file, char *backing_file, struct openflags flags, int err, fd; flags.c = 1; - fd = open_ubd_file(cow_file, &flags, NULL, NULL, NULL, NULL, NULL); + fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL); if(fd < 0){ err = fd; printk("Open of COW file '%s' failed, errno = %d\n", cow_file, diff --git a/arch/um/include/irq_user.h b/arch/um/include/irq_user.h index b61deb8..69a93c8 100644 --- a/arch/um/include/irq_user.h +++ b/arch/um/include/irq_user.h @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2001, 2002 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -6,6 +6,17 @@ #ifndef __IRQ_USER_H__ #define __IRQ_USER_H__ +struct irq_fd { + struct irq_fd *next; + void *id; + int fd; + int type; + int irq; + int pid; + int events; + int current_events; +}; + enum { IRQ_READ, IRQ_WRITE }; extern void sigio_handler(int sig, union uml_pt_regs *regs); @@ -16,8 +27,6 @@ extern void reactivate_fd(int fd, int irqnum); extern void deactivate_fd(int fd, int irqnum); extern int deactivate_all_fds(void); extern void forward_interrupts(int pid); -extern void init_irq_signals(int on_sigstack); -extern void forward_ipi(int fd, int pid); extern int activate_ipi(int fd, int pid); extern unsigned long irq_lock(void); extern void irq_unlock(unsigned long flags); diff --git a/arch/um/include/kern.h b/arch/um/include/kern.h index 7d223be..4ce3fc6 100644 --- a/arch/um/include/kern.h +++ b/arch/um/include/kern.h @@ -29,7 +29,7 @@ extern int getuid(void); extern int getgid(void); extern int pause(void); extern int write(int, const void *, int); -extern int exit(int); +extern void exit(int); extern int close(int); extern int read(unsigned int, char *, int); extern int pipe(int *); diff --git a/arch/um/include/misc_constants.h b/arch/um/include/misc_constants.h new file mode 100644 index 0000000..989bc08 --- /dev/null +++ b/arch/um/include/misc_constants.h @@ -0,0 +1,6 @@ +#ifndef __MISC_CONSTANT_H_ +#define __MISC_CONSTANT_H_ + +#include <user_constants.h> + +#endif diff --git a/arch/um/include/os.h b/arch/um/include/os.h index 2a1c64d..d3d1bc6 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -12,6 +12,7 @@ #include "sysdep/ptrace.h" #include "kern_util.h" #include "skas/mm_id.h" +#include "irq_user.h" #define OS_TYPE_FILE 1 #define OS_TYPE_DIR 2 @@ -121,6 +122,7 @@ static inline struct openflags of_cloexec(struct openflags flags) return(flags); } +/* file.c */ extern int os_stat_file(const char *file_name, struct uml_stat *buf); extern int os_stat_fd(const int fd, struct uml_stat *buf); extern int os_access(const char *file, int mode); @@ -156,10 +158,20 @@ extern int os_connect_socket(char *name); extern int os_file_type(char *file); extern int os_file_mode(char *file, struct openflags *mode_out); extern int os_lock_file(int fd, int excl); +extern void os_flush_stdout(void); +extern int os_stat_filesystem(char *path, long *bsize_out, + long long *blocks_out, long long *bfree_out, + long long *bavail_out, long long *files_out, + long long *ffree_out, void *fsid_out, + int fsid_size, long *namelen_out, + long *spare_out); +extern int os_change_dir(char *dir); +extern int os_fchange_dir(int fd); /* start_up.c */ extern void os_early_checks(void); extern int can_do_skas(void); +extern void os_check_bugs(void); /* Make sure they are clear when running in TT mode. Required by * SEGV_MAYBE_FIXABLE */ @@ -198,6 +210,8 @@ extern void os_flush_stdout(void); /* tt.c * for tt mode only (will be deleted in future...) */ +extern void forward_ipi(int fd, int pid); +extern void kill_child_dead(int pid); extern void stop(void); extern int wait_for_stop(int pid, int sig, int cont_type, void *relay); extern int protect_memory(unsigned long addr, unsigned long len, @@ -294,4 +308,26 @@ extern void initial_thread_cb_skas(void (*proc)(void *), extern void halt_skas(void); extern void reboot_skas(void); +/* irq.c */ +extern int os_waiting_for_events(struct irq_fd *active_fds); +extern int os_isatty(int fd); +extern int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds); +extern void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, + struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2); +extern void os_free_irq_later(struct irq_fd *active_fds, + int irq, void *dev_id); +extern int os_get_pollfd(int i); +extern void os_set_pollfd(int i, int fd); +extern void os_set_ioignore(void); +extern void init_irq_signals(int on_sigstack); + +/* sigio.c */ +extern void write_sigio_workaround(void); +extern int add_sigio_fd(int fd, int read); +extern int ignore_sigio_fd(int fd); + +/* skas/trap */ +extern void sig_handler_common_skas(int sig, void *sc_ptr); +extern void user_signal(int sig, union uml_pt_regs *regs, int pid); + #endif diff --git a/arch/um/include/sigio.h b/arch/um/include/sigio.h index 37d76e2..fe99ea1 100644 --- a/arch/um/include/sigio.h +++ b/arch/um/include/sigio.h @@ -8,9 +8,6 @@ extern int write_sigio_irq(int fd); extern int register_sigio_fd(int fd); -extern int read_sigio_fd(int fd); -extern int add_sigio_fd(int fd, int read); -extern int ignore_sigio_fd(int fd); extern void sigio_lock(void); extern void sigio_unlock(void); diff --git a/arch/um/include/skas/mode-skas.h b/arch/um/include/skas/mode-skas.h index 260065c..8bc6916 100644 --- a/arch/um/include/skas/mode-skas.h +++ b/arch/um/include/skas/mode-skas.h @@ -13,7 +13,6 @@ extern unsigned long exec_fp_regs[]; extern unsigned long exec_fpx_regs[]; extern int have_fpx_regs; -extern void sig_handler_common_skas(int sig, void *sc_ptr); extern void kill_off_processes_skas(void); #endif diff --git a/arch/um/include/skas/skas.h b/arch/um/include/skas/skas.h index 8635728..853b26f 100644 --- a/arch/um/include/skas/skas.h +++ b/arch/um/include/skas/skas.h @@ -17,7 +17,6 @@ extern int user_thread(unsigned long stack, int flags); extern void new_thread_proc(void *stack, void (*handler)(int sig)); extern void new_thread_handler(int sig); extern void handle_syscall(union uml_pt_regs *regs); -extern void user_signal(int sig, union uml_pt_regs *regs, int pid); extern int new_mm(unsigned long stack); extern void get_skas_faultinfo(int pid, struct faultinfo * fi); extern long execute_syscall_skas(void *r); diff --git a/arch/um/include/user_util.h b/arch/um/include/user_util.h index a6f1f17..992a7e1 100644 --- a/arch/um/include/user_util.h +++ b/arch/um/include/user_util.h @@ -58,7 +58,6 @@ extern int attach(int pid); extern void kill_child_dead(int pid); extern int cont(int pid); extern void check_sigio(void); -extern void write_sigio_workaround(void); extern void arch_check_bugs(void); extern int cpu_feature(char *what, char *buf, int len); extern int arch_handle_signal(int sig, union uml_pt_regs *regs); diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index 693018b..fe08971 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -7,23 +7,20 @@ extra-y := vmlinux.lds clean-files := obj-y = config.o exec_kern.o exitcode.o \ - init_task.o irq.o irq_user.o ksyms.o mem.o physmem.o \ - process_kern.o ptrace.o reboot.o resource.o sigio_user.o sigio_kern.o \ + init_task.o irq.o ksyms.o mem.o physmem.o \ + process_kern.o ptrace.o reboot.o resource.o sigio_kern.o \ signal_kern.o smp.o syscall_kern.o sysrq.o \ time_kern.o tlb.o trap_kern.o uaccess.o um_arch.o umid.o obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o obj-$(CONFIG_GPROF) += gprof_syms.o obj-$(CONFIG_GCOV) += gmon_syms.o -obj-$(CONFIG_TTY_LOG) += tty_log.o obj-$(CONFIG_SYSCALL_DEBUG) += syscall.o obj-$(CONFIG_MODE_TT) += tt/ obj-$(CONFIG_MODE_SKAS) += skas/ -user-objs-$(CONFIG_TTY_LOG) += tty_log.o - -USER_OBJS := $(user-objs-y) config.o tty_log.o +USER_OBJS := config.o include arch/um/scripts/Makefile.rules diff --git a/arch/um/kernel/exec_kern.c b/arch/um/kernel/exec_kern.c index c264e1c..1ca8431 100644 --- a/arch/um/kernel/exec_kern.c +++ b/arch/um/kernel/exec_kern.c @@ -30,8 +30,6 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) CHOOSE_MODE_PROC(start_thread_tt, start_thread_skas, regs, eip, esp); } -extern void log_exec(char **argv, void *tty); - static long execve1(char *file, char __user * __user *argv, char __user *__user *env) { diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index bbf94bf..c39ea3a 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -31,6 +31,8 @@ #include "irq_user.h" #include "irq_kern.h" #include "os.h" +#include "sigio.h" +#include "misc_constants.h" /* * Generic, controller-independent functions: @@ -77,6 +79,298 @@ skip: return 0; } +struct irq_fd *active_fds = NULL; +static struct irq_fd **last_irq_ptr = &active_fds; + +extern void free_irqs(void); + +void sigio_handler(int sig, union uml_pt_regs *regs) +{ + struct irq_fd *irq_fd; + int n; + + if(smp_sigio_handler()) return; + while(1){ + n = os_waiting_for_events(active_fds); + if (n <= 0) { + if(n == -EINTR) continue; + else break; + } + + for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ + if(irq_fd->current_events != 0){ + irq_fd->current_events = 0; + do_IRQ(irq_fd->irq, regs); + } + } + } + + free_irqs(); +} + +static void maybe_sigio_broken(int fd, int type) +{ + if(os_isatty(fd)){ + if((type == IRQ_WRITE) && !pty_output_sigio){ + write_sigio_workaround(); + add_sigio_fd(fd, 0); + } + else if((type == IRQ_READ) && !pty_close_sigio){ + write_sigio_workaround(); + add_sigio_fd(fd, 1); + } + } +} + + +int activate_fd(int irq, int fd, int type, void *dev_id) +{ + struct pollfd *tmp_pfd; + struct irq_fd *new_fd, *irq_fd; + unsigned long flags; + int pid, events, err, n; + + pid = os_getpid(); + err = os_set_fd_async(fd, pid); + if(err < 0) + goto out; + + new_fd = um_kmalloc(sizeof(*new_fd)); + err = -ENOMEM; + if(new_fd == NULL) + goto out; + + if(type == IRQ_READ) events = UM_POLLIN | UM_POLLPRI; + else events = UM_POLLOUT; + *new_fd = ((struct irq_fd) { .next = NULL, + .id = dev_id, + .fd = fd, + .type = type, + .irq = irq, + .pid = pid, + .events = events, + .current_events = 0 } ); + + /* Critical section - locked by a spinlock because this stuff can + * be changed from interrupt handlers. The stuff above is done + * outside the lock because it allocates memory. + */ + + /* Actually, it only looks like it can be called from interrupt + * context. The culprit is reactivate_fd, which calls + * maybe_sigio_broken, which calls write_sigio_workaround, + * which calls activate_fd. However, write_sigio_workaround should + * only be called once, at boot time. That would make it clear that + * this is called only from process context, and can be locked with + * a semaphore. + */ + flags = irq_lock(); + for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ + if((irq_fd->fd == fd) && (irq_fd->type == type)){ + printk("Registering fd %d twice\n", fd); + printk("Irqs : %d, %d\n", irq_fd->irq, irq); + printk("Ids : 0x%p, 0x%p\n", irq_fd->id, dev_id); + goto out_unlock; + } + } + + /*-------------*/ + if(type == IRQ_WRITE) + fd = -1; + + tmp_pfd = NULL; + n = 0; + + while(1){ + n = os_create_pollfd(fd, events, tmp_pfd, n); + if (n == 0) + break; + + /* n > 0 + * It means we couldn't put new pollfd to current pollfds + * and tmp_fds is NULL or too small for new pollfds array. + * Needed size is equal to n as minimum. + * + * Here we have to drop the lock in order to call + * kmalloc, which might sleep. + * If something else came in and changed the pollfds array + * so we will not be able to put new pollfd struct to pollfds + * then we free the buffer tmp_fds and try again. + */ + irq_unlock(flags); + if (tmp_pfd != NULL) { + kfree(tmp_pfd); + tmp_pfd = NULL; + } + + tmp_pfd = um_kmalloc(n); + if (tmp_pfd == NULL) + goto out_kfree; + + flags = irq_lock(); + } + /*-------------*/ + + *last_irq_ptr = new_fd; + last_irq_ptr = &new_fd->next; + + irq_unlock(flags); + + /* This calls activate_fd, so it has to be outside the critical + * section. + */ + maybe_sigio_broken(fd, type); + + return(0); + + out_unlock: + irq_unlock(flags); + out_kfree: + kfree(new_fd); + out: + return(err); +} + +static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) +{ + unsigned long flags; + + flags = irq_lock(); + os_free_irq_by_cb(test, arg, active_fds, &last_irq_ptr); + irq_unlock(flags); +} + +struct irq_and_dev { + int irq; + void *dev; +}; + +static int same_irq_and_dev(struct irq_fd *irq, void *d) +{ + struct irq_and_dev *data = d; + + return((irq->irq == data->irq) && (irq->id == data->dev)); +} + +void free_irq_by_irq_and_dev(unsigned int irq, void *dev) +{ + struct irq_and_dev data = ((struct irq_and_dev) { .irq = irq, + .dev = dev }); + + free_irq_by_cb(same_irq_and_dev, &data); +} + +static int same_fd(struct irq_fd *irq, void *fd) +{ + return(irq->fd == *((int *) fd)); +} + +void free_irq_by_fd(int fd) +{ + free_irq_by_cb(same_fd, &fd); +} + +static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) +{ + struct irq_fd *irq; + int i = 0; + int fdi; + + for(irq=active_fds; irq != NULL; irq = irq->next){ + if((irq->fd == fd) && (irq->irq == irqnum)) break; + i++; + } + if(irq == NULL){ + printk("find_irq_by_fd doesn't have descriptor %d\n", fd); + goto out; + } + fdi = os_get_pollfd(i); + if((fdi != -1) && (fdi != fd)){ + printk("find_irq_by_fd - mismatch between active_fds and " + "pollfds, fd %d vs %d, need %d\n", irq->fd, + fdi, fd); + irq = NULL; + goto out; + } + *index_out = i; + out: + return(irq); +} + +void reactivate_fd(int fd, int irqnum) +{ + struct irq_fd *irq; + unsigned long flags; + int i; + + flags = irq_lock(); + irq = find_irq_by_fd(fd, irqnum, &i); + if(irq == NULL){ + irq_unlock(flags); + return; + } + os_set_pollfd(i, irq->fd); + irq_unlock(flags); + + /* This calls activate_fd, so it has to be outside the critical + * section. + */ + maybe_sigio_broken(fd, irq->type); +} + +void deactivate_fd(int fd, int irqnum) +{ + struct irq_fd *irq; + unsigned long flags; + int i; + + flags = irq_lock(); + irq = find_irq_by_fd(fd, irqnum, &i); + if(irq == NULL) + goto out; + os_set_pollfd(i, -1); + out: + irq_unlock(flags); +} + +int deactivate_all_fds(void) +{ + struct irq_fd *irq; + int err; + + for(irq=active_fds;irq != NULL;irq = irq->next){ + err = os_clear_fd_async(irq->fd); + if(err) + return(err); + } + /* If there is a signal already queued, after unblocking ignore it */ + os_set_ioignore(); + + return(0); +} + +void forward_interrupts(int pid) +{ + struct irq_fd *irq; + unsigned long flags; + int err; + + flags = irq_lock(); + for(irq=active_fds;irq != NULL;irq = irq->next){ + err = os_set_owner(irq->fd, pid); + if(err < 0){ + /* XXX Just remove the irq rather than + * print out an infinite stream of these + */ + printk("Failed to forward %d to pid %d, err = %d\n", + irq->fd, pid, -err); + } + + irq->pid = pid; + } + irq_unlock(flags); +} + /* * do_IRQ handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific diff --git a/arch/um/kernel/irq_user.c b/arch/um/kernel/irq_user.c deleted file mode 100644 index 0e32f5f..0000000 --- a/arch/um/kernel/irq_user.c +++ /dev/null @@ -1,412 +0,0 @@ -/* - * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) - * Licensed under the GPL - */ - -#include <stdlib.h> -#include <unistd.h> -#include <errno.h> -#include <signal.h> -#include <string.h> -#include <sys/poll.h> -#include <sys/types.h> -#include <sys/time.h> -#include "user_util.h" -#include "kern_util.h" -#include "user.h" -#include "process.h" -#include "sigio.h" -#include "irq_user.h" -#include "os.h" - -struct irq_fd { - struct irq_fd *next; - void *id; - int fd; - int type; - int irq; - int pid; - int events; - int current_events; -}; - -static struct irq_fd *active_fds = NULL; -static struct irq_fd **last_irq_ptr = &active_fds; - -static struct pollfd *pollfds = NULL; -static int pollfds_num = 0; -static int pollfds_size = 0; - -extern int io_count, intr_count; - -extern void free_irqs(void); - -void sigio_handler(int sig, union uml_pt_regs *regs) -{ - struct irq_fd *irq_fd; - int i, n; - - if(smp_sigio_handler()) return; - while(1){ - n = poll(pollfds, pollfds_num, 0); - if(n < 0){ - if(errno == EINTR) continue; - printk("sigio_handler : poll returned %d, " - "errno = %d\n", n, errno); - break; - } - if(n == 0) break; - - irq_fd = active_fds; - for(i = 0; i < pollfds_num; i++){ - if(pollfds[i].revents != 0){ - irq_fd->current_events = pollfds[i].revents; - pollfds[i].fd = -1; - } - irq_fd = irq_fd->next; - } - - for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ - if(irq_fd->current_events != 0){ - irq_fd->current_events = 0; - do_IRQ(irq_fd->irq, regs); - } - } - } - - free_irqs(); -} - -int activate_ipi(int fd, int pid) -{ - return(os_set_fd_async(fd, pid)); -} - -static void maybe_sigio_broken(int fd, int type) -{ - if(isatty(fd)){ - if((type == IRQ_WRITE) && !pty_output_sigio){ - write_sigio_workaround(); - add_sigio_fd(fd, 0); - } - else if((type == IRQ_READ) && !pty_close_sigio){ - write_sigio_workaround(); - add_sigio_fd(fd, 1); - } - } -} - -int activate_fd(int irq, int fd, int type, void *dev_id) -{ - struct pollfd *tmp_pfd; - struct irq_fd *new_fd, *irq_fd; - unsigned long flags; - int pid, events, err, n, size; - - pid = os_getpid(); - err = os_set_fd_async(fd, pid); - if(err < 0) - goto out; - - new_fd = um_kmalloc(sizeof(*new_fd)); - err = -ENOMEM; - if(new_fd == NULL) - goto out; - - if(type == IRQ_READ) events = POLLIN | POLLPRI; - else events = POLLOUT; - *new_fd = ((struct irq_fd) { .next = NULL, - .id = dev_id, - .fd = fd, - .type = type, - .irq = irq, - .pid = pid, - .events = events, - .current_events = 0 } ); - - /* Critical section - locked by a spinlock because this stuff can - * be changed from interrupt handlers. The stuff above is done - * outside the lock because it allocates memory. - */ - - /* Actually, it only looks like it can be called from interrupt - * context. The culprit is reactivate_fd, which calls - * maybe_sigio_broken, which calls write_sigio_workaround, - * which calls activate_fd. However, write_sigio_workaround should - * only be called once, at boot time. That would make it clear that - * this is called only from process context, and can be locked with - * a semaphore. - */ - flags = irq_lock(); - for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ - if((irq_fd->fd == fd) && (irq_fd->type == type)){ - printk("Registering fd %d twice\n", fd); - printk("Irqs : %d, %d\n", irq_fd->irq, irq); - printk("Ids : 0x%x, 0x%x\n", irq_fd->id, dev_id); - goto out_unlock; - } - } - - n = pollfds_num; - if(n == pollfds_size){ - while(1){ - /* Here we have to drop the lock in order to call - * kmalloc, which might sleep. If something else - * came in and changed the pollfds array, we free - * the buffer and try again. - */ - irq_unlock(flags); - size = (pollfds_num + 1) * sizeof(pollfds[0]); - tmp_pfd = um_kmalloc(size); - flags = irq_lock(); - if(tmp_pfd == NULL) - goto out_unlock; - if(n == pollfds_size) - break; - kfree(tmp_pfd); - } - if(pollfds != NULL){ - memcpy(tmp_pfd, pollfds, - sizeof(pollfds[0]) * pollfds_size); - kfree(pollfds); - } - pollfds = tmp_pfd; - pollfds_size++; - } - - if(type == IRQ_WRITE) - fd = -1; - - pollfds[pollfds_num] = ((struct pollfd) { .fd = fd, - .events = events, - .revents = 0 }); - pollfds_num++; - - *last_irq_ptr = new_fd; - last_irq_ptr = &new_fd->next; - - irq_unlock(flags); - - /* This calls activate_fd, so it has to be outside the critical - * section. - */ - maybe_sigio_broken(fd, type); - - return(0); - - out_unlock: - irq_unlock(flags); - kfree(new_fd); - out: - return(err); -} - -static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) -{ - struct irq_fd **prev; - unsigned long flags; - int i = 0; - - flags = irq_lock(); - prev = &active_fds; - while(*prev != NULL){ - if((*test)(*prev, arg)){ - struct irq_fd *old_fd = *prev; - if((pollfds[i].fd != -1) && - (pollfds[i].fd != (*prev)->fd)){ - printk("free_irq_by_cb - mismatch between " - "active_fds and pollfds, fd %d vs %d\n", - (*prev)->fd, pollfds[i].fd); - goto out; - } - - pollfds_num--; - - /* This moves the *whole* array after pollfds[i] (though - * it doesn't spot as such)! */ - - memmove(&pollfds[i], &pollfds[i + 1], - (pollfds_num - i) * sizeof(pollfds[0])); - - if(last_irq_ptr == &old_fd->next) - last_irq_ptr = prev; - *prev = (*prev)->next; - if(old_fd->type == IRQ_WRITE) - ignore_sigio_fd(old_fd->fd); - kfree(old_fd); - continue; - } - prev = &(*prev)->next; - i++; - } - out: - irq_unlock(flags); -} - -struct irq_and_dev { - int irq; - void *dev; -}; - -static int same_irq_and_dev(struct irq_fd *irq, void *d) -{ - struct irq_and_dev *data = d; - - return((irq->irq == data->irq) && (irq->id == data->dev)); -} - -void free_irq_by_irq_and_dev(unsigned int irq, void *dev) -{ - struct irq_and_dev data = ((struct irq_and_dev) { .irq = irq, - .dev = dev }); - - free_irq_by_cb(same_irq_and_dev, &data); -} - -static int same_fd(struct irq_fd *irq, void *fd) -{ - return(irq->fd == *((int *) fd)); -} - -void free_irq_by_fd(int fd) -{ - free_irq_by_cb(same_fd, &fd); -} - -static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) -{ - struct irq_fd *irq; - int i = 0; - - for(irq=active_fds; irq != NULL; irq = irq->next){ - if((irq->fd == fd) && (irq->irq == irqnum)) break; - i++; - } - if(irq == NULL){ - printk("find_irq_by_fd doesn't have descriptor %d\n", fd); - goto out; - } - if((pollfds[i].fd != -1) && (pollfds[i].fd != fd)){ - printk("find_irq_by_fd - mismatch between active_fds and " - "pollfds, fd %d vs %d, need %d\n", irq->fd, - pollfds[i].fd, fd); - irq = NULL; - goto out; - } - *index_out = i; - out: - return(irq); -} - -void reactivate_fd(int fd, int irqnum) -{ - struct irq_fd *irq; - unsigned long flags; - int i; - - flags = irq_lock(); - irq = find_irq_by_fd(fd, irqnum, &i); - if(irq == NULL){ - irq_unlock(flags); - return; - } - - pollfds[i].fd = irq->fd; - - irq_unlock(flags); - - /* This calls activate_fd, so it has to be outside the critical - * section. - */ - maybe_sigio_broken(fd, irq->type); -} - -void deactivate_fd(int fd, int irqnum) -{ - struct irq_fd *irq; - unsigned long flags; - int i; - - flags = irq_lock(); - irq = find_irq_by_fd(fd, irqnum, &i); - if(irq == NULL) - goto out; - pollfds[i].fd = -1; - out: - irq_unlock(flags); -} - -int deactivate_all_fds(void) -{ - struct irq_fd *irq; - int err; - - for(irq=active_fds;irq != NULL;irq = irq->next){ - err = os_clear_fd_async(irq->fd); - if(err) - return(err); - } - /* If there is a signal already queued, after unblocking ignore it */ - set_handler(SIGIO, SIG_IGN, 0, -1); - - return(0); -} - -void forward_ipi(int fd, int pid) -{ - int err; - - err = os_set_owner(fd, pid); - if(err < 0) - printk("forward_ipi: set_owner failed, fd = %d, me = %d, " - "target = %d, err = %d\n", fd, os_getpid(), pid, -err); -} - -void forward_interrupts(int pid) -{ - struct irq_fd *irq; - unsigned long flags; - int err; - - flags = irq_lock(); - for(irq=active_fds;irq != NULL;irq = irq->next){ - err = os_set_owner(irq->fd, pid); - if(err < 0){ - /* XXX Just remove the irq rather than - * print out an infinite stream of these - */ - printk("Failed to forward %d to pid %d, err = %d\n", - irq->fd, pid, -err); - } - - irq->pid = pid; - } - irq_unlock(flags); -} - -void init_irq_signals(int on_sigstack) -{ - __sighandler_t h; - int flags; - - flags = on_sigstack ? SA_ONSTACK : 0; - if(timer_irq_inited) h = (__sighandler_t) alarm_handler; - else h = boot_timer_handler; - - set_handler(SIGVTALRM, h, flags | SA_RESTART, - SIGUSR1, SIGIO, SIGWINCH, SIGALRM, -1); - set_handler(SIGIO, (__sighandler_t) sig_handler, flags | SA_RESTART, - SIGUSR1, SIGIO, SIGWINCH, SIGALRM, SIGVTALRM, -1); - signal(SIGWINCH, SIG_IGN); -} - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 0e65340..0500800 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -9,6 +9,7 @@ #include "linux/vmalloc.h" #include "linux/bootmem.h" #include "linux/module.h" +#include "linux/pfn.h" #include "asm/types.h" #include "asm/pgtable.h" #include "kern_util.h" @@ -316,8 +317,6 @@ void map_memory(unsigned long virt, unsigned long phys, unsigned long len, } } -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) - extern int __syscall_stub_start, __binary_start; void setup_physmem(unsigned long start, unsigned long reserve_end, diff --git a/arch/um/kernel/sigio_kern.c b/arch/um/kernel/sigio_kern.c index 2299884..1c1300f 100644 --- a/arch/um/kernel/sigio_kern.c +++ b/arch/um/kernel/sigio_kern.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2002 - 2003 Jeff Dike (jdike@addtoit.com) * Licensed under the GPL */ @@ -12,13 +12,16 @@ #include "sigio.h" #include "irq_user.h" #include "irq_kern.h" +#include "os.h" /* Protected by sigio_lock() called from write_sigio_workaround */ static int sigio_irq_fd = -1; static irqreturn_t sigio_interrupt(int irq, void *data, struct pt_regs *unused) { - read_sigio_fd(sigio_irq_fd); + char c; + + os_read_file(sigio_irq_fd, &c, sizeof(c)); reactivate_fd(sigio_irq_fd, SIGIO_WRITE_IRQ); return(IRQ_HANDLED); } @@ -51,6 +54,9 @@ void sigio_unlock(void) spin_unlock(&sigio_spinlock); } +extern void sigio_cleanup(void); +__uml_exitcall(sigio_cleanup); + /* * Overrides for Emacs so that we follow Linus's tabbing style. * Emacs will notice this stuff at the end of the file and automatically diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 72113b0..c8d8d0a 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) * Licensed under the GPL */ @@ -77,9 +77,9 @@ static int idle_proc(void *cpup) if(err < 0) panic("CPU#%d failed to create IPI pipe, err = %d", cpu, -err); - activate_ipi(cpu_data[cpu].ipi_pipe[0], + os_set_fd_async(cpu_data[cpu].ipi_pipe[0], current->thread.mode.tt.extern_pid); - + wmb(); if (cpu_test_and_set(cpu, cpu_callin_map)) { printk("huh, CPU#%d already present??\n", cpu); @@ -106,7 +106,7 @@ static struct task_struct *idle_thread(int cpu) panic("copy_process failed in idle_thread, error = %ld", PTR_ERR(new_task)); - cpu_tasks[cpu] = ((struct cpu_task) + cpu_tasks[cpu] = ((struct cpu_task) { .pid = new_task->thread.mode.tt.extern_pid, .task = new_task } ); idle_threads[cpu] = new_task; @@ -134,12 +134,12 @@ void smp_prepare_cpus(unsigned int maxcpus) if(err < 0) panic("CPU#0 failed to create IPI pipe, errno = %d", -err); - activate_ipi(cpu_data[me].ipi_pipe[0], + os_set_fd_async(cpu_data[me].ipi_pipe[0], current->thread.mode.tt.extern_pid); for(cpu = 1; cpu < ncpus; cpu++){ printk("Booting processor %d...\n", cpu); - + idle = idle_thread(cpu); init_idle(idle, cpu); @@ -223,7 +223,7 @@ void smp_call_function_slave(int cpu) atomic_inc(&scf_finished); } -int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic, +int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic, int wait) { int cpus = num_online_cpus() - 1; diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 80c9c18..7d51dd7 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -421,7 +421,7 @@ int linux_main(int argc, char **argv) #ifndef CONFIG_HIGHMEM highmem = 0; printf("CONFIG_HIGHMEM not enabled - physical memory shrunk " - "to %lu bytes\n", physmem_size); + "to %Lu bytes\n", physmem_size); #endif } @@ -433,8 +433,8 @@ int linux_main(int argc, char **argv) setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem); if(init_maps(physmem_size, iomem_size, highmem)){ - printf("Failed to allocate mem_map for %lu bytes of physical " - "memory and %lu bytes of highmem\n", physmem_size, + printf("Failed to allocate mem_map for %Lu bytes of physical " + "memory and %Lu bytes of highmem\n", physmem_size, highmem); exit(1); } @@ -477,7 +477,8 @@ static struct notifier_block panic_exit_notifier = { void __init setup_arch(char **cmdline_p) { - notifier_chain_register(&panic_notifier_list, &panic_exit_notifier); + atomic_notifier_chain_register(&panic_notifier_list, + &panic_exit_notifier); paging_init(); strlcpy(saved_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; @@ -487,8 +488,7 @@ void __init setup_arch(char **cmdline_p) void __init check_bugs(void) { arch_check_bugs(); - check_sigio(); - check_devanon(); + os_check_bugs(); } void apply_alternatives(struct alt_instr *start, struct alt_instr *end) diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 08a4e62..1659386 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,14 +3,17 @@ # Licensed under the GPL # -obj-y = aio.o elf_aux.o file.o helper.o main.o mem.o process.o signal.o \ - start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o user_syms.o \ - util.o drivers/ sys-$(SUBARCH)/ +obj-y = aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o sigio.o \ + signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o \ + user_syms.o util.o drivers/ sys-$(SUBARCH)/ obj-$(CONFIG_MODE_SKAS) += skas/ +obj-$(CONFIG_TTY_LOG) += tty_log.o +user-objs-$(CONFIG_TTY_LOG) += tty_log.o -USER_OBJS := aio.o elf_aux.o file.o helper.o main.o mem.o process.o signal.o \ - start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o util.o +USER_OBJS := $(user-objs-y) aio.o elf_aux.o file.o helper.o irq.o main.o mem.o \ + process.o sigio.o signal.o start_up.o time.o trap.o tt.o tty.o \ + uaccess.o umid.o util.o elf_aux.o: $(ARCH_DIR)/kernel-offsets.h CFLAGS_elf_aux.o += -I$(objtree)/arch/um diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c new file mode 100644 index 0000000..e599be4 --- /dev/null +++ b/arch/um/os-Linux/irq.c @@ -0,0 +1,162 @@ +/* + * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com) + * Licensed under the GPL + */ + +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <signal.h> +#include <string.h> +#include <sys/poll.h> +#include <sys/types.h> +#include <sys/time.h> +#include "user_util.h" +#include "kern_util.h" +#include "user.h" +#include "process.h" +#include "sigio.h" +#include "irq_user.h" +#include "os.h" + +static struct pollfd *pollfds = NULL; +static int pollfds_num = 0; +static int pollfds_size = 0; + +int os_waiting_for_events(struct irq_fd *active_fds) +{ + struct irq_fd *irq_fd; + int i, n, err; + + n = poll(pollfds, pollfds_num, 0); + if(n < 0){ + err = -errno; + if(errno != EINTR) + printk("sigio_handler: os_waiting_for_events:" + " poll returned %d, errno = %d\n", n, errno); + return err; + } + + if(n == 0) + return 0; + + irq_fd = active_fds; + + for(i = 0; i < pollfds_num; i++){ + if(pollfds[i].revents != 0){ + irq_fd->current_events = pollfds[i].revents; + pollfds[i].fd = -1; + } + irq_fd = irq_fd->next; + } + return n; +} + +int os_isatty(int fd) +{ + return(isatty(fd)); +} + +int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds) +{ + if (pollfds_num == pollfds_size) { + if (size_tmpfds <= pollfds_size * sizeof(pollfds[0])) { + /* return min size needed for new pollfds area */ + return((pollfds_size + 1) * sizeof(pollfds[0])); + } + + if(pollfds != NULL){ + memcpy(tmp_pfd, pollfds, + sizeof(pollfds[0]) * pollfds_size); + /* remove old pollfds */ + kfree(pollfds); + } + pollfds = tmp_pfd; + pollfds_size++; + } else { + /* remove not used tmp_pfd */ + if (tmp_pfd != NULL) + kfree(tmp_pfd); + } + + pollfds[pollfds_num] = ((struct pollfd) { .fd = fd, + .events = events, + .revents = 0 }); + pollfds_num++; + + return(0); +} + +void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, + struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2) +{ + struct irq_fd **prev; + int i = 0; + + prev = &active_fds; + while(*prev != NULL){ + if((*test)(*prev, arg)){ + struct irq_fd *old_fd = *prev; + if((pollfds[i].fd != -1) && + (pollfds[i].fd != (*prev)->fd)){ + printk("os_free_irq_by_cb - mismatch between " + "active_fds and pollfds, fd %d vs %d\n", + (*prev)->fd, pollfds[i].fd); + goto out; + } + + pollfds_num--; + + /* This moves the *whole* array after pollfds[i] + * (though it doesn't spot as such)! + */ + + memmove(&pollfds[i], &pollfds[i + 1], + (pollfds_num - i) * sizeof(pollfds[0])); + if(*last_irq_ptr2 == &old_fd->next) + *last_irq_ptr2 = prev; + + *prev = (*prev)->next; + if(old_fd->type == IRQ_WRITE) + ignore_sigio_fd(old_fd->fd); + kfree(old_fd); + continue; + } + prev = &(*prev)->next; + i++; + } + out: + return; +} + + +int os_get_pollfd(int i) +{ + return(pollfds[i].fd); +} + +void os_set_pollfd(int i, int fd) +{ + pollfds[i].fd = fd; +} + +void os_set_ioignore(void) +{ + set_handler(SIGIO, SIG_IGN, 0, -1); +} + +void init_irq_signals(int on_sigstack) +{ + __sighandler_t h; + int flags; + + flags = on_sigstack ? SA_ONSTACK : 0; + if(timer_irq_inited) h = (__sighandler_t) alarm_handler; + else h = boot_timer_handler; + + set_handler(SIGVTALRM, h, flags | SA_RESTART, + SIGUSR1, SIGIO, SIGWINCH, SIGALRM, -1); + set_handler(SIGIO, (__sighandler_t) sig_handler, flags | SA_RESTART, + SIGUSR1, SIGIO, SIGWINCH, SIGALRM, SIGVTALRM, -1); + signal(SIGWINCH, SIG_IGN); +} diff --git a/arch/um/kernel/sigio_user.c b/arch/um/os-Linux/sigio.c index f7b18e1..9ba9429 100644 --- a/arch/um/kernel/sigio_user.c +++ b/arch/um/os-Linux/sigio.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -20,128 +20,7 @@ #include "sigio.h" #include "os.h" -/* Changed during early boot */ -int pty_output_sigio = 0; -int pty_close_sigio = 0; - -/* Used as a flag during SIGIO testing early in boot */ -static volatile int got_sigio = 0; - -void __init handler(int sig) -{ - got_sigio = 1; -} - -struct openpty_arg { - int master; - int slave; - int err; -}; - -static void openpty_cb(void *arg) -{ - struct openpty_arg *info = arg; - - info->err = 0; - if(openpty(&info->master, &info->slave, NULL, NULL, NULL)) - info->err = -errno; -} - -void __init check_one_sigio(void (*proc)(int, int)) -{ - struct sigaction old, new; - struct openpty_arg pty = { .master = -1, .slave = -1 }; - int master, slave, err; - - initial_thread_cb(openpty_cb, &pty); - if(pty.err){ - printk("openpty failed, errno = %d\n", -pty.err); - return; - } - - master = pty.master; - slave = pty.slave; - - if((master == -1) || (slave == -1)){ - printk("openpty failed to allocate a pty\n"); - return; - } - - /* Not now, but complain so we now where we failed. */ - err = raw(master); - if (err < 0) - panic("check_sigio : __raw failed, errno = %d\n", -err); - - err = os_sigio_async(master, slave); - if(err < 0) - panic("tty_fds : sigio_async failed, err = %d\n", -err); - - if(sigaction(SIGIO, NULL, &old) < 0) - panic("check_sigio : sigaction 1 failed, errno = %d\n", errno); - new = old; - new.sa_handler = handler; - if(sigaction(SIGIO, &new, NULL) < 0) - panic("check_sigio : sigaction 2 failed, errno = %d\n", errno); - - got_sigio = 0; - (*proc)(master, slave); - - os_close_file(master); - os_close_file(slave); - - if(sigaction(SIGIO, &old, NULL) < 0) - panic("check_sigio : sigaction 3 failed, errno = %d\n", errno); -} - -static void tty_output(int master, int slave) -{ - int n; - char buf[512]; - - printk("Checking that host ptys support output SIGIO..."); - - memset(buf, 0, sizeof(buf)); - - while(os_write_file(master, buf, sizeof(buf)) > 0) ; - if(errno != EAGAIN) - panic("check_sigio : write failed, errno = %d\n", errno); - while(((n = os_read_file(slave, buf, sizeof(buf))) > 0) && !got_sigio) ; - - if (got_sigio) { - printk("Yes\n"); - pty_output_sigio = 1; - } else if (n == -EAGAIN) { - printk("No, enabling workaround\n"); - } else { - panic("check_sigio : read failed, err = %d\n", n); - } -} - -static void tty_close(int master, int slave) -{ - printk("Checking that host ptys support SIGIO on close..."); - - os_close_file(slave); - if(got_sigio){ - printk("Yes\n"); - pty_close_sigio = 1; - } - else printk("No, enabling workaround\n"); -} - -void __init check_sigio(void) -{ - if((os_access("/dev/ptmx", OS_ACC_R_OK) < 0) && - (os_access("/dev/ptyp0", OS_ACC_R_OK) < 0)){ - printk("No pseudo-terminals available - skipping pty SIGIO " - "check\n"); - return; - } - check_one_sigio(tty_output); - check_one_sigio(tty_close); -} - -/* Protected by sigio_lock(), also used by sigio_cleanup, which is an +/* Protected by sigio_lock(), also used by sigio_cleanup, which is an * exitcall. */ static int write_sigio_pid = -1; @@ -150,8 +29,10 @@ static int write_sigio_pid = -1; * the descriptors closed after it is killed. So, it can't see them change. * On the UML side, they are changed under the sigio_lock. */ -static int write_sigio_fds[2] = { -1, -1 }; -static int sigio_private[2] = { -1, -1 }; +#define SIGIO_FDS_INIT {-1, -1} + +static int write_sigio_fds[2] = SIGIO_FDS_INIT; +static int sigio_private[2] = SIGIO_FDS_INIT; struct pollfds { struct pollfd *poll; @@ -264,13 +145,13 @@ static void update_thread(void) return; fail: /* Critical section start */ - if(write_sigio_pid != -1) + if(write_sigio_pid != -1) os_kill_process(write_sigio_pid, 1); write_sigio_pid = -1; - os_close_file(sigio_private[0]); - os_close_file(sigio_private[1]); - os_close_file(write_sigio_fds[0]); - os_close_file(write_sigio_fds[1]); + close(sigio_private[0]); + close(sigio_private[1]); + close(write_sigio_fds[0]); + close(write_sigio_fds[1]); /* Critical section end */ set_signals(flags); } @@ -281,13 +162,13 @@ int add_sigio_fd(int fd, int read) sigio_lock(); for(i = 0; i < current_poll.used; i++){ - if(current_poll.poll[i].fd == fd) + if(current_poll.poll[i].fd == fd) goto out; } n = current_poll.used + 1; err = need_poll(n); - if(err) + if(err) goto out; for(i = 0; i < current_poll.used; i++) @@ -316,7 +197,7 @@ int ignore_sigio_fd(int fd) } if(i == current_poll.used) goto out; - + err = need_poll(current_poll.used - 1); if(err) goto out; @@ -337,7 +218,7 @@ int ignore_sigio_fd(int fd) return(err); } -static struct pollfd* setup_initial_poll(int fd) +static struct pollfd *setup_initial_poll(int fd) { struct pollfd *p; @@ -377,7 +258,7 @@ void write_sigio_workaround(void) } err = os_pipe(l_sigio_private, 1, 1); if(err < 0){ - printk("write_sigio_workaround - os_pipe 1 failed, " + printk("write_sigio_workaround - os_pipe 2 failed, " "err = %d\n", -err); goto out_close1; } @@ -391,76 +272,52 @@ void write_sigio_workaround(void) /* Did we race? Don't try to optimize this, please, it's not so likely * to happen, and no more than once at the boot. */ if(write_sigio_pid != -1) - goto out_unlock; + goto out_free; - write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, - CLONE_FILES | CLONE_VM, &stack, 0); - - if (write_sigio_pid < 0) - goto out_clear; + current_poll = ((struct pollfds) { .poll = p, + .used = 1, + .size = 1 }); if (write_sigio_irq(l_write_sigio_fds[0])) - goto out_kill; + goto out_clear_poll; - /* Success, finally. */ memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds)); memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private)); - current_poll = ((struct pollfds) { .poll = p, - .used = 1, - .size = 1 }); + write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, + CLONE_FILES | CLONE_VM, &stack, 0); - sigio_unlock(); - return; + if (write_sigio_pid < 0) + goto out_clear; - out_kill: - l_write_sigio_pid = write_sigio_pid; - write_sigio_pid = -1; sigio_unlock(); - /* Going to call waitpid, avoid holding the lock. */ - os_kill_process(l_write_sigio_pid, 1); - goto out_free; + return; - out_clear: +out_clear: write_sigio_pid = -1; - out_unlock: - sigio_unlock(); - out_free: + write_sigio_fds[0] = -1; + write_sigio_fds[1] = -1; + sigio_private[0] = -1; + sigio_private[1] = -1; +out_clear_poll: + current_poll = ((struct pollfds) { .poll = NULL, + .size = 0, + .used = 0 }); +out_free: kfree(p); - out_close2: - os_close_file(l_sigio_private[0]); - os_close_file(l_sigio_private[1]); - out_close1: - os_close_file(l_write_sigio_fds[0]); - os_close_file(l_write_sigio_fds[1]); - return; -} - -int read_sigio_fd(int fd) -{ - int n; - char c; - - n = os_read_file(fd, &c, sizeof(c)); - if(n != sizeof(c)){ - if(n < 0) { - printk("read_sigio_fd - read failed, err = %d\n", -n); - return(n); - } - else { - printk("read_sigio_fd - short read, bytes = %d\n", n); - return(-EIO); - } - } - return(n); + sigio_unlock(); +out_close2: + close(l_sigio_private[0]); + close(l_sigio_private[1]); +out_close1: + close(l_write_sigio_fds[0]); + close(l_write_sigio_fds[1]); } -static void sigio_cleanup(void) +void sigio_cleanup(void) { - if (write_sigio_pid != -1) { + if(write_sigio_pid != -1){ os_kill_process(write_sigio_pid, 1); write_sigio_pid = -1; } } - -__uml_exitcall(sigio_cleanup); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 829d6b0..3275313 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <pty.h> #include <stdio.h> #include <stddef.h> #include <stdarg.h> @@ -539,3 +540,130 @@ int __init parse_iomem(char *str, int *add) return(1); } + +/* Changed during early boot */ +int pty_output_sigio = 0; +int pty_close_sigio = 0; + +/* Used as a flag during SIGIO testing early in boot */ +static volatile int got_sigio = 0; + +static void __init handler(int sig) +{ + got_sigio = 1; +} + +struct openpty_arg { + int master; + int slave; + int err; +}; + +static void openpty_cb(void *arg) +{ + struct openpty_arg *info = arg; + + info->err = 0; + if(openpty(&info->master, &info->slave, NULL, NULL, NULL)) + info->err = -errno; +} + +static void __init check_one_sigio(void (*proc)(int, int)) +{ + struct sigaction old, new; + struct openpty_arg pty = { .master = -1, .slave = -1 }; + int master, slave, err; + + initial_thread_cb(openpty_cb, &pty); + if(pty.err){ + printk("openpty failed, errno = %d\n", -pty.err); + return; + } + + master = pty.master; + slave = pty.slave; + + if((master == -1) || (slave == -1)){ + printk("openpty failed to allocate a pty\n"); + return; + } + + /* Not now, but complain so we now where we failed. */ + err = raw(master); + if (err < 0) + panic("check_sigio : __raw failed, errno = %d\n", -err); + + err = os_sigio_async(master, slave); + if(err < 0) + panic("tty_fds : sigio_async failed, err = %d\n", -err); + + if(sigaction(SIGIO, NULL, &old) < 0) + panic("check_sigio : sigaction 1 failed, errno = %d\n", errno); + new = old; + new.sa_handler = handler; + if(sigaction(SIGIO, &new, NULL) < 0) + panic("check_sigio : sigaction 2 failed, errno = %d\n", errno); + + got_sigio = 0; + (*proc)(master, slave); + + close(master); + close(slave); + + if(sigaction(SIGIO, &old, NULL) < 0) + panic("check_sigio : sigaction 3 failed, errno = %d\n", errno); +} + +static void tty_output(int master, int slave) +{ + int n; + char buf[512]; + + printk("Checking that host ptys support output SIGIO..."); + + memset(buf, 0, sizeof(buf)); + + while(os_write_file(master, buf, sizeof(buf)) > 0) ; + if(errno != EAGAIN) + panic("check_sigio : write failed, errno = %d\n", errno); + while(((n = os_read_file(slave, buf, sizeof(buf))) > 0) && !got_sigio) ; + + if(got_sigio){ + printk("Yes\n"); + pty_output_sigio = 1; + } + else if(n == -EAGAIN) printk("No, enabling workaround\n"); + else panic("check_sigio : read failed, err = %d\n", n); +} + +static void tty_close(int master, int slave) +{ + printk("Checking that host ptys support SIGIO on close..."); + + close(slave); + if(got_sigio){ + printk("Yes\n"); + pty_close_sigio = 1; + } + else printk("No, enabling workaround\n"); +} + +void __init check_sigio(void) +{ + if((os_access("/dev/ptmx", OS_ACC_R_OK) < 0) && + (os_access("/dev/ptyp0", OS_ACC_R_OK) < 0)){ + printk("No pseudo-terminals available - skipping pty SIGIO " + "check\n"); + return; + } + check_one_sigio(tty_output); + check_one_sigio(tty_close); +} + +void os_check_bugs(void) +{ + check_ptrace(); + check_sigio(); + check_devanon(); +} + diff --git a/arch/um/os-Linux/tt.c b/arch/um/os-Linux/tt.c index 919d19f..5461a06 100644 --- a/arch/um/os-Linux/tt.c +++ b/arch/um/os-Linux/tt.c @@ -110,6 +110,16 @@ int wait_for_stop(int pid, int sig, int cont_type, void *relay) } } +void forward_ipi(int fd, int pid) +{ + int err; + + err = os_set_owner(fd, pid); + if(err < 0) + printk("forward_ipi: set_owner failed, fd = %d, me = %d, " + "target = %d, err = %d\n", fd, os_getpid(), pid, -err); +} + /* *------------------------- * only for tt mode (will be deleted in future...) diff --git a/arch/um/kernel/tty_log.c b/arch/um/os-Linux/tty_log.c index 9ada656..c6ba56c 100644 --- a/arch/um/kernel/tty_log.c +++ b/arch/um/os-Linux/tty_log.c @@ -1,5 +1,5 @@ -/* - * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) and +/* + * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) and * geoffrey hing <ghing@net.ohio-state.edu> * Licensed under the GPL */ @@ -58,7 +58,7 @@ int open_tty_log(void *tty, void *current_tty) return(tty_log_fd); } - sprintf(buf, "%s/%0u-%0u", tty_log_dir, (unsigned int) tv.tv_sec, + sprintf(buf, "%s/%0u-%0u", tty_log_dir, (unsigned int) tv.tv_sec, (unsigned int) tv.tv_usec); fd = os_open_file(buf, of_append(of_create(of_rdwr(OPENFLAGS()))), @@ -216,15 +216,3 @@ __uml_setup("tty_log_fd=", set_tty_log_fd, " tty data will be written. Preconfigure the descriptor with something\n" " like '10>tty_log tty_log_fd=10'.\n\n" ); - - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index ecf107a..198e591 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -143,8 +143,10 @@ static int not_dead_yet(char *dir) goto out_close; } - if((kill(p, 0) == 0) || (errno != ESRCH)) + if((kill(p, 0) == 0) || (errno != ESRCH)){ + printk("umid \"%s\" is already in use by pid %d\n", umid, p); return 1; + } err = actually_do_remove(dir); if(err) @@ -234,33 +236,44 @@ int __init make_umid(void) err = mkdir(tmp, 0777); if(err < 0){ err = -errno; - if(errno != EEXIST) + if(err != -EEXIST) goto err; - if(not_dead_yet(tmp) < 0) + /* 1 -> this umid is already in use + * < 0 -> we couldn't remove the umid directory + * In either case, we can't use this umid, so return -EEXIST. + */ + if(not_dead_yet(tmp) != 0) goto err; err = mkdir(tmp, 0777); } - if(err < 0){ - printk("Failed to create '%s' - err = %d\n", umid, err); - goto err_rmdir; + if(err){ + err = -errno; + printk("Failed to create '%s' - err = %d\n", umid, -errno); + goto err; } umid_setup = 1; create_pid_file(); - return 0; - - err_rmdir: - rmdir(tmp); + err = 0; err: return err; } static int __init make_umid_init(void) { + if(!make_umid()) + return 0; + + /* If initializing with the given umid failed, then try again with + * a random one. + */ + printk("Failed to initialize umid \"%s\", trying with a random umid\n", + umid); + *umid = '\0'; make_umid(); return 0; diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c index e839ce6..8032a10 100644 --- a/arch/um/sys-i386/ptrace.c +++ b/arch/um/sys-i386/ptrace.c @@ -6,6 +6,7 @@ #include <linux/config.h> #include <linux/compiler.h> #include "linux/sched.h" +#include "linux/mm.h" #include "asm/elf.h" #include "asm/ptrace.h" #include "asm/uaccess.h" @@ -26,9 +27,17 @@ int is_syscall(unsigned long addr) n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); if(n){ - printk("is_syscall : failed to read instruction from 0x%lx\n", - addr); - return(0); + /* access_process_vm() grants access to vsyscall and stub, + * while copy_from_user doesn't. Maybe access_process_vm is + * slow, but that doesn't matter, since it will be called only + * in case of singlestepping, if copy_from_user failed. + */ + n = access_process_vm(current, addr, &instr, sizeof(instr), 0); + if(n != sizeof(instr)) { + printk("is_syscall : failed to read instruction from " + "0x%lx\n", addr); + return(1); + } } /* int 0x80 or sysenter */ return((instr == 0x80cd) || (instr == 0x340f)); diff --git a/arch/um/sys-i386/signal.c b/arch/um/sys-i386/signal.c index 7cd1a82..33a40f5 100644 --- a/arch/um/sys-i386/signal.c +++ b/arch/um/sys-i386/signal.c @@ -58,7 +58,7 @@ static int copy_sc_from_user_skas(struct pt_regs *regs, } int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, - struct pt_regs *regs) + struct pt_regs *regs, unsigned long sp) { struct sigcontext sc; unsigned long fpregs[HOST_FP_SIZE]; @@ -72,7 +72,7 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, sc.edi = REGS_EDI(regs->regs.skas.regs); sc.esi = REGS_ESI(regs->regs.skas.regs); sc.ebp = REGS_EBP(regs->regs.skas.regs); - sc.esp = REGS_SP(regs->regs.skas.regs); + sc.esp = sp; sc.ebx = REGS_EBX(regs->regs.skas.regs); sc.edx = REGS_EDX(regs->regs.skas.regs); sc.ecx = REGS_ECX(regs->regs.skas.regs); @@ -132,7 +132,7 @@ int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, } int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, - struct sigcontext *from, int fpsize) + struct sigcontext *from, int fpsize, unsigned long sp) { struct _fpstate *to_fp, *from_fp; int err; @@ -140,11 +140,18 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, to_fp = (fp ? fp : (struct _fpstate *) (to + 1)); from_fp = from->fpstate; err = copy_to_user(to, from, sizeof(*to)); + + /* The SP in the sigcontext is the updated one for the signal + * delivery. The sp passed in is the original, and this needs + * to be restored, so we stick it in separately. + */ + err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); err |= copy_to_user(to_fp, from_fp, fpsize); } - return(err); + return err; } #endif @@ -159,11 +166,11 @@ static int copy_sc_from_user(struct pt_regs *to, void __user *from) } static int copy_sc_to_user(struct sigcontext *to, struct _fpstate *fp, - struct pt_regs *from) + struct pt_regs *from, unsigned long sp) { return(CHOOSE_MODE(copy_sc_to_user_tt(to, fp, UPT_SC(&from->regs), - sizeof(*fp)), - copy_sc_to_user_skas(to, fp, from))); + sizeof(*fp), sp), + copy_sc_to_user_skas(to, fp, from, sp))); } static int copy_ucontext_to_user(struct ucontext *uc, struct _fpstate *fp, @@ -174,7 +181,7 @@ static int copy_ucontext_to_user(struct ucontext *uc, struct _fpstate *fp, err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp); err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags); err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size); - err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs); + err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs, sp); err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set)); return(err); } @@ -207,6 +214,7 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, { struct sigframe __user *frame; void *restorer; + unsigned long save_sp = PT_REGS_SP(regs); int err = 0; stack_top &= -8UL; @@ -218,9 +226,19 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, if(ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; + /* Update SP now because the page fault handler refuses to extend + * the stack if the faulting address is too far below the current + * SP, which frame now certainly is. If there's an error, the original + * value is restored on the way out. + * When writing the sigcontext to the stack, we have to write the + * original value, so that's passed to copy_sc_to_user, which does + * the right thing with it. + */ + PT_REGS_SP(regs) = (unsigned long) frame; + err |= __put_user(restorer, &frame->pretcode); err |= __put_user(sig, &frame->sig); - err |= copy_sc_to_user(&frame->sc, NULL, regs); + err |= copy_sc_to_user(&frame->sc, NULL, regs, save_sp); err |= __put_user(mask->sig[0], &frame->sc.oldmask); if (_NSIG_WORDS > 1) err |= __copy_to_user(&frame->extramask, &mask->sig[1], @@ -238,7 +256,7 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, err |= __put_user(0x80cd, (short __user *)(frame->retcode+6)); if(err) - return(err); + goto err; PT_REGS_SP(regs) = (unsigned long) frame; PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler; @@ -248,7 +266,11 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) ptrace_notify(SIGTRAP); - return(0); + return 0; + +err: + PT_REGS_SP(regs) = save_sp; + return err; } int setup_signal_stack_si(unsigned long stack_top, int sig, @@ -257,6 +279,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, { struct rt_sigframe __user *frame; void *restorer; + unsigned long save_sp = PT_REGS_SP(regs); int err = 0; stack_top &= -8UL; @@ -268,13 +291,16 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, if(ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; + /* See comment above about why this is here */ + PT_REGS_SP(regs) = (unsigned long) frame; + err |= __put_user(restorer, &frame->pretcode); err |= __put_user(sig, &frame->sig); err |= __put_user(&frame->info, &frame->pinfo); err |= __put_user(&frame->uc, &frame->puc); err |= copy_siginfo_to_user(&frame->info, info); err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask, - PT_REGS_SP(regs)); + save_sp); /* * This is movl $,%eax ; int $0x80 @@ -288,9 +314,8 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, err |= __put_user(0x80cd, (short __user *)(frame->retcode+5)); if(err) - return(err); + goto err; - PT_REGS_SP(regs) = (unsigned long) frame; PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler; PT_REGS_EAX(regs) = (unsigned long) sig; PT_REGS_EDX(regs) = (unsigned long) &frame->info; @@ -298,7 +323,11 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) ptrace_notify(SIGTRAP); - return(0); + return 0; + +err: + PT_REGS_SP(regs) = save_sp; + return err; } long sys_sigreturn(struct pt_regs regs) diff --git a/arch/um/sys-i386/user-offsets.c b/arch/um/sys-i386/user-offsets.c index 26b6867..6f4ef2b 100644 --- a/arch/um/sys-i386/user-offsets.c +++ b/arch/um/sys-i386/user-offsets.c @@ -3,12 +3,13 @@ #include <asm/ptrace.h> #include <asm/user.h> #include <linux/stddef.h> +#include <sys/poll.h> #define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) + asm volatile("\n->" #sym " %0 " #val : : "i" (val)) #define DEFINE_LONGS(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long))) + asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long))) #define OFFSET(sym, str, mem) \ DEFINE(sym, offsetof(struct str, mem)); @@ -67,4 +68,9 @@ void foo(void) DEFINE(HOST_ES, ES); DEFINE(HOST_GS, GS); DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct)); + + /* XXX Duplicated between i386 and x86_64 */ + DEFINE(UM_POLLIN, POLLIN); + DEFINE(UM_POLLPRI, POLLPRI); + DEFINE(UM_POLLOUT, POLLOUT); } diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c index 74eee5c..147bbf0 100644 --- a/arch/um/sys-x86_64/ptrace.c +++ b/arch/um/sys-x86_64/ptrace.c @@ -8,6 +8,7 @@ #include <asm/ptrace.h> #include <linux/sched.h> #include <linux/errno.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include <asm/elf.h> @@ -136,9 +137,28 @@ void arch_switch(void) */ } +/* XXX Mostly copied from sys-i386 */ int is_syscall(unsigned long addr) { - panic("is_syscall"); + unsigned short instr; + int n; + + n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); + if(n){ + /* access_process_vm() grants access to vsyscall and stub, + * while copy_from_user doesn't. Maybe access_process_vm is + * slow, but that doesn't matter, since it will be called only + * in case of singlestepping, if copy_from_user failed. + */ + n = access_process_vm(current, addr, &instr, sizeof(instr), 0); + if(n != sizeof(instr)) { + printk("is_syscall : failed to read instruction from " + "0x%lx\n", addr); + return(1); + } + } + /* sysenter */ + return(instr == 0x050f); } int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu ) diff --git a/arch/um/sys-x86_64/signal.c b/arch/um/sys-x86_64/signal.c index fe1d065..e75c4e1 100644 --- a/arch/um/sys-x86_64/signal.c +++ b/arch/um/sys-x86_64/signal.c @@ -55,7 +55,8 @@ static int copy_sc_from_user_skas(struct pt_regs *regs, } int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, - struct pt_regs *regs, unsigned long mask) + struct pt_regs *regs, unsigned long mask, + unsigned long sp) { struct faultinfo * fi = ¤t->thread.arch.faultinfo; int err = 0; @@ -70,7 +71,11 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, err |= PUTREG(regs, RDI, to, rdi); err |= PUTREG(regs, RSI, to, rsi); err |= PUTREG(regs, RBP, to, rbp); - err |= PUTREG(regs, RSP, to, rsp); + /* Must use orignal RSP, which is passed in, rather than what's in + * the pt_regs, because that's already been updated to point at the + * signal frame. + */ + err |= __put_user(sp, &to->rsp); err |= PUTREG(regs, RBX, to, rbx); err |= PUTREG(regs, RDX, to, rdx); err |= PUTREG(regs, RCX, to, rcx); @@ -102,7 +107,7 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, #ifdef CONFIG_MODE_TT int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, - int fpsize) + int fpsize) { struct _fpstate *to_fp, *from_fp; unsigned long sigs; @@ -120,7 +125,7 @@ int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, } int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, - struct sigcontext *from, int fpsize) + struct sigcontext *from, int fpsize, unsigned long sp) { struct _fpstate *to_fp, *from_fp; int err; @@ -128,11 +133,17 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, to_fp = (fp ? fp : (struct _fpstate *) (to + 1)); from_fp = from->fpstate; err = copy_to_user(to, from, sizeof(*to)); + /* The SP in the sigcontext is the updated one for the signal + * delivery. The sp passed in is the original, and this needs + * to be restored, so we stick it in separately. + */ + err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); err |= copy_to_user(to_fp, from_fp, fpsize); } - return(err); + return err; } #endif @@ -148,11 +159,12 @@ static int copy_sc_from_user(struct pt_regs *to, void __user *from) } static int copy_sc_to_user(struct sigcontext *to, struct _fpstate *fp, - struct pt_regs *from, unsigned long mask) + struct pt_regs *from, unsigned long mask, + unsigned long sp) { return(CHOOSE_MODE(copy_sc_to_user_tt(to, fp, UPT_SC(&from->regs), - sizeof(*fp)), - copy_sc_to_user_skas(to, fp, from, mask))); + sizeof(*fp), sp), + copy_sc_to_user_skas(to, fp, from, mask, sp))); } struct rt_sigframe @@ -170,6 +182,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, { struct rt_sigframe __user *frame; struct _fpstate __user *fp = NULL; + unsigned long save_sp = PT_REGS_RSP(regs); int err = 0; struct task_struct *me = current; @@ -193,14 +206,25 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, goto out; } + /* Update SP now because the page fault handler refuses to extend + * the stack if the faulting address is too far below the current + * SP, which frame now certainly is. If there's an error, the original + * value is restored on the way out. + * When writing the sigcontext to the stack, we have to write the + * original value, so that's passed to copy_sc_to_user, which does + * the right thing with it. + */ + PT_REGS_RSP(regs) = (unsigned long) frame; + /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)), + err |= __put_user(sas_ss_flags(save_sp), &frame->uc.uc_stack.ss_flags); err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= copy_sc_to_user(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); + err |= copy_sc_to_user(&frame->uc.uc_mcontext, fp, regs, set->sig[0], + save_sp); err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); @@ -217,10 +241,10 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); else /* could use a vstub here */ - goto out; + goto restore_sp; if (err) - goto out; + goto restore_sp; /* Set up registers for signal handler */ { @@ -238,10 +262,12 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, PT_REGS_RSI(regs) = (unsigned long) &frame->info; PT_REGS_RDX(regs) = (unsigned long) &frame->uc; PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler; - - PT_REGS_RSP(regs) = (unsigned long) frame; out: - return(err); + return err; + +restore_sp: + PT_REGS_RSP(regs) = save_sp; + return err; } long sys_rt_sigreturn(struct pt_regs *regs) diff --git a/arch/um/sys-x86_64/user-offsets.c b/arch/um/sys-x86_64/user-offsets.c index 7bd54a9..899cebb 100644 --- a/arch/um/sys-x86_64/user-offsets.c +++ b/arch/um/sys-x86_64/user-offsets.c @@ -1,6 +1,7 @@ #include <stdio.h> #include <stddef.h> #include <signal.h> +#include <sys/poll.h> #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <asm/types.h> @@ -88,4 +89,9 @@ void foo(void) DEFINE_LONGS(HOST_IP, RIP); DEFINE_LONGS(HOST_SP, RSP); DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct)); + + /* XXX Duplicated between i386 and x86_64 */ + DEFINE(UM_POLLIN, POLLIN); + DEFINE(UM_POLLPRI, POLLPRI); + DEFINE(UM_POLLOUT, POLLOUT); } diff --git a/arch/v850/Kconfig b/arch/v850/Kconfig index e7fc3e5..37ec644 100644 --- a/arch/v850/Kconfig +++ b/arch/v850/Kconfig @@ -16,6 +16,12 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool default n +config GENERIC_FIND_NEXT_BIT + bool + default y +config GENERIC_HWEIGHT + bool + default y config GENERIC_CALIBRATE_DELAY bool default y diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 6420bae..4310b4a 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -45,6 +45,10 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config GENERIC_HWEIGHT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y @@ -246,6 +250,15 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + default y + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + source "kernel/Kconfig.preempt" config NUMA @@ -321,6 +334,10 @@ config HAVE_ARCH_EARLY_PFN_TO_NID def_bool y depends on NUMA +config OUT_OF_LINE_PFN_TO_PAGE + def_bool y + depends on DISCONTIGMEM + config NR_CPUS int "Maximum number of CPUs (2-256)" range 2 255 diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile index 0fbc028..585fd4a 100644 --- a/arch/x86_64/Makefile +++ b/arch/x86_64/Makefile @@ -70,7 +70,7 @@ drivers-$(CONFIG_OPROFILE) += arch/x86_64/oprofile/ boot := arch/x86_64/boot PHONY += bzImage bzlilo install archmrproper \ - fdimage fdimage144 fdimage288 archclean + fdimage fdimage144 fdimage288 isoimage archclean #Default target when executing "make" all: bzImage @@ -87,7 +87,7 @@ bzlilo: vmlinux bzdisk: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zdisk -fdimage fdimage144 fdimage288: vmlinux +fdimage fdimage144 fdimage288 isoimage: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@ install: @@ -99,11 +99,16 @@ archclean: define archhelp echo '* bzImage - Compressed kernel image (arch/$(ARCH)/boot/bzImage)' echo ' install - Install kernel using' - echo ' (your) ~/bin/installkernel or' - echo ' (distribution) /sbin/installkernel or' - echo ' install to $$(INSTALL_PATH) and run lilo' + echo ' (your) ~/bin/installkernel or' + echo ' (distribution) /sbin/installkernel or' + echo ' install to $$(INSTALL_PATH) and run lilo' + echo ' bzdisk - Create a boot floppy in /dev/fd0' + echo ' fdimage - Create a boot floppy image' + echo ' isoimage - Create a boot CD-ROM image' endef -CLEAN_FILES += arch/$(ARCH)/boot/fdimage arch/$(ARCH)/boot/mtools.conf +CLEAN_FILES += arch/$(ARCH)/boot/fdimage \ + arch/$(ARCH)/boot/image.iso \ + arch/$(ARCH)/boot/mtools.conf diff --git a/arch/x86_64/boot/Makefile b/arch/x86_64/boot/Makefile index 29f8396..43ee6c5 100644 --- a/arch/x86_64/boot/Makefile +++ b/arch/x86_64/boot/Makefile @@ -60,8 +60,12 @@ $(obj)/setup $(obj)/bootsect: %: %.o FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed IMAGE_OFFSET=$(IMAGE_OFFSET) $@ -# Set this if you want to pass append arguments to the zdisk/fdimage kernel +# Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel FDARGS = +# Set this if you want an initrd included with the zdisk/fdimage/isoimage kernel +FDINITRD = + +image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,) $(obj)/mtools.conf: $(src)/mtools.conf.in sed -e 's|@OBJ@|$(obj)|g' < $< > $@ @@ -70,8 +74,11 @@ $(obj)/mtools.conf: $(src)/mtools.conf.in zdisk: $(BOOTIMAGE) $(obj)/mtools.conf MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync syslinux /dev/fd0 ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - a:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) a:linux ; sync # These require being root or having syslinux 2.02 or higher installed @@ -79,18 +86,39 @@ fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440 MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - v:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) v:linux ; sync fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880 MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - w:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) w:linux ; sync +isoimage: $(BOOTIMAGE) + -rm -rf $(obj)/isoimage + mkdir $(obj)/isoimage + cp `echo /usr/lib*/syslinux/isolinux.bin | awk '{ print $1; }'` \ + $(obj)/isoimage + cp $(BOOTIMAGE) $(obj)/isoimage/linux + echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \ + fi + mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \ + -no-emul-boot -boot-load-size 4 -boot-info-table \ + $(obj)/isoimage + rm -rf $(obj)/isoimage + zlilo: $(BOOTIMAGE) if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 00dee17..35b2fac 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -501,7 +501,7 @@ ia32_sys_call_table: .quad sys_setdomainname .quad sys_uname .quad sys_modify_ldt - .quad sys32_adjtimex + .quad compat_sys_adjtimex .quad sys32_mprotect /* 125 */ .quad compat_sys_sigprocmask .quad quiet_ni_syscall /* create_module */ @@ -688,6 +688,8 @@ ia32_sys_call_table: .quad sys_ni_syscall /* pselect6 for now */ .quad sys_ni_syscall /* ppoll for now */ .quad sys_unshare /* 310 */ + .quad compat_sys_set_robust_list + .quad compat_sys_get_robust_list ia32_syscall_end: .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8 .quad ni_syscall diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c index 2b2d029..f182b20 100644 --- a/arch/x86_64/ia32/sys_ia32.c +++ b/arch/x86_64/ia32/sys_ia32.c @@ -30,7 +30,6 @@ #include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/timex.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -767,82 +766,6 @@ sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, s32 count) return ret; } -/* Handle adjtimex compatibility. */ - -struct timex32 { - u32 modes; - s32 offset, freq, maxerror, esterror; - s32 status, constant, precision, tolerance; - struct compat_timeval time; - s32 tick; - s32 ppsfreq, jitter, shift, stabil; - s32 jitcnt, calcnt, errcnt, stbcnt; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; - s32 :32; s32 :32; s32 :32; s32 :32; -}; - -extern int do_adjtimex(struct timex *); - -asmlinkage long -sys32_adjtimex(struct timex32 __user *utp) -{ - struct timex txc; - int ret; - - memset(&txc, 0, sizeof(struct timex)); - - if (!access_ok(VERIFY_READ, utp, sizeof(struct timex32)) || - __get_user(txc.modes, &utp->modes) || - __get_user(txc.offset, &utp->offset) || - __get_user(txc.freq, &utp->freq) || - __get_user(txc.maxerror, &utp->maxerror) || - __get_user(txc.esterror, &utp->esterror) || - __get_user(txc.status, &utp->status) || - __get_user(txc.constant, &utp->constant) || - __get_user(txc.precision, &utp->precision) || - __get_user(txc.tolerance, &utp->tolerance) || - __get_user(txc.time.tv_sec, &utp->time.tv_sec) || - __get_user(txc.time.tv_usec, &utp->time.tv_usec) || - __get_user(txc.tick, &utp->tick) || - __get_user(txc.ppsfreq, &utp->ppsfreq) || - __get_user(txc.jitter, &utp->jitter) || - __get_user(txc.shift, &utp->shift) || - __get_user(txc.stabil, &utp->stabil) || - __get_user(txc.jitcnt, &utp->jitcnt) || - __get_user(txc.calcnt, &utp->calcnt) || - __get_user(txc.errcnt, &utp->errcnt) || - __get_user(txc.stbcnt, &utp->stbcnt)) - return -EFAULT; - - ret = do_adjtimex(&txc); - - if (!access_ok(VERIFY_WRITE, utp, sizeof(struct timex32)) || - __put_user(txc.modes, &utp->modes) || - __put_user(txc.offset, &utp->offset) || - __put_user(txc.freq, &utp->freq) || - __put_user(txc.maxerror, &utp->maxerror) || - __put_user(txc.esterror, &utp->esterror) || - __put_user(txc.status, &utp->status) || - __put_user(txc.constant, &utp->constant) || - __put_user(txc.precision, &utp->precision) || - __put_user(txc.tolerance, &utp->tolerance) || - __put_user(txc.time.tv_sec, &utp->time.tv_sec) || - __put_user(txc.time.tv_usec, &utp->time.tv_usec) || - __put_user(txc.tick, &utp->tick) || - __put_user(txc.ppsfreq, &utp->ppsfreq) || - __put_user(txc.jitter, &utp->jitter) || - __put_user(txc.shift, &utp->shift) || - __put_user(txc.stabil, &utp->stabil) || - __put_user(txc.jitcnt, &utp->jitcnt) || - __put_user(txc.calcnt, &utp->calcnt) || - __put_user(txc.errcnt, &utp->errcnt) || - __put_user(txc.stbcnt, &utp->stbcnt)) - ret = -EFAULT; - - return ret; -} - asmlinkage long sys32_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c index 14f0ced..accbff3 100644 --- a/arch/x86_64/kernel/kprobes.c +++ b/arch/x86_64/kernel/kprobes.c @@ -37,10 +37,12 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/preempt.h> +#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> #include <asm/kdebug.h> +#include <asm/uaccess.h> void jprobe_return_end(void); static void __kprobes arch_copy_kprobe(struct kprobe *p); @@ -578,16 +580,62 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + const struct exception_table_entry *fixup; - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs, kcb); + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the rip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->rip = (unsigned long)cur->addr; regs->eflags |= kcb->kprobe_old_rflags; - - reset_current_kprobe(); + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + fixup = search_exception_tables(regs->rip); + if (fixup) { + regs->rip = fixup->fixup; + return 1; + } + + /* + * fixup() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; } return 0; } @@ -601,6 +649,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch (val) { case DIE_INT3: if (kprobe_handler(args->regs)) diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 8111183..70dd8e5 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -35,8 +35,8 @@ #include <linux/ptrace.h> #include <linux/utsname.h> #include <linux/random.h> -#include <linux/kprobes.h> #include <linux/notifier.h> +#include <linux/kprobes.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -66,24 +66,17 @@ EXPORT_SYMBOL(boot_option_idle_override); void (*pm_idle)(void); static DEFINE_PER_CPU(unsigned int, cpu_idle_state); -static struct notifier_block *idle_notifier; -static DEFINE_SPINLOCK(idle_notifier_lock); +static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) { - unsigned long flags; - spin_lock_irqsave(&idle_notifier_lock, flags); - notifier_chain_register(&idle_notifier, n); - spin_unlock_irqrestore(&idle_notifier_lock, flags); + atomic_notifier_chain_register(&idle_notifier, n); } EXPORT_SYMBOL_GPL(idle_notifier_register); void idle_notifier_unregister(struct notifier_block *n) { - unsigned long flags; - spin_lock_irqsave(&idle_notifier_lock, flags); - notifier_chain_unregister(&idle_notifier, n); - spin_unlock_irqrestore(&idle_notifier_lock, flags); + atomic_notifier_chain_unregister(&idle_notifier, n); } EXPORT_SYMBOL(idle_notifier_unregister); @@ -93,13 +86,13 @@ static DEFINE_PER_CPU(enum idle_state, idle_state) = CPU_NOT_IDLE; void enter_idle(void) { __get_cpu_var(idle_state) = CPU_IDLE; - notifier_call_chain(&idle_notifier, IDLE_START, NULL); + atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); } static void __exit_idle(void) { __get_cpu_var(idle_state) = CPU_NOT_IDLE; - notifier_call_chain(&idle_notifier, IDLE_END, NULL); + atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); } /* Called from interrupts to signify idle end */ @@ -353,13 +346,6 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; - /* - * Remove function-return probe instances associated with this task - * and put them back on the free list. Do not insert an exit probe for - * this function, it will be disabled by kprobe_flush_task if you do. - */ - kprobe_flush_task(me); - if (me->thread.io_bitmap_ptr) { struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index a57eec8..d1f3e92 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -962,7 +962,6 @@ static void __cpuinit detect_ht(struct cpuinfo_x86 *c) cpuid(1, &eax, &ebx, &ecx, &edx); - c->apicid = phys_pkg_id(0); if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; @@ -1171,6 +1170,8 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_capability[2] = cpuid_edx(0x80860001); } + c->apicid = phys_pkg_id(0); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index 66e9865..ea48fa6 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -68,6 +68,9 @@ u8 phys_proc_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; /* core ID of each logical CPU */ u8 cpu_core_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; +/* Last level cache ID of each logical CPU */ +u8 cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; + /* Bitmask of currently online CPUs */ cpumask_t cpu_online_map __read_mostly; @@ -445,6 +448,18 @@ void __cpuinit smp_callin(void) cpu_set(cpuid, cpu_callin_map); } +/* maps the cpu to the sched domain representing multi-core */ +cpumask_t cpu_coregroup_map(int cpu) +{ + struct cpuinfo_x86 *c = cpu_data + cpu; + /* + * For perf, we return last level cache shared map. + * TBD: when power saving sched policy is added, we will return + * cpu_core_map when power saving policy is enabled + */ + return c->llc_shared_map; +} + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -463,12 +478,16 @@ static inline void set_cpu_sibling_map(int cpu) cpu_set(cpu, cpu_sibling_map[i]); cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } + cpu_set(cpu, c[cpu].llc_shared_map); + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; c[cpu].booted_cores = 1; @@ -476,6 +495,11 @@ static inline void set_cpu_sibling_map(int cpu) } for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (cpu_llc_id[cpu] != BAD_APICID && + cpu_llc_id[cpu] == cpu_llc_id[i]) { + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); + } if (phys_proc_id[cpu] == phys_proc_id[i]) { cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index 7f58fa6..473b514 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -504,42 +504,25 @@ unsigned long long sched_clock(void) static unsigned long get_cmos_time(void) { - unsigned int timeout = 1000000, year, mon, day, hour, min, sec; - unsigned char uip = 0, this = 0; + unsigned int year, mon, day, hour, min, sec; unsigned long flags; unsigned extyear = 0; -/* - * The Linux interpretation of the CMOS clock register contents: When the - * Update-In-Progress (UIP) flag goes from 1 to 0, the RTC registers show the - * second which has precisely just started. Waiting for this can take up to 1 - * second, we timeout approximately after 2.4 seconds on a machine with - * standard 8.3 MHz ISA bus. - */ - spin_lock_irqsave(&rtc_lock, flags); - while (timeout && (!uip || this)) { - uip |= this; - this = CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP; - timeout--; - } - - /* - * Here we are safe to assume the registers won't change for a whole - * second, so we just go ahead and read them. - */ - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - + do { + sec = CMOS_READ(RTC_SECONDS); + min = CMOS_READ(RTC_MINUTES); + hour = CMOS_READ(RTC_HOURS); + day = CMOS_READ(RTC_DAY_OF_MONTH); + mon = CMOS_READ(RTC_MONTH); + year = CMOS_READ(RTC_YEAR); #ifdef CONFIG_ACPI - if (acpi_fadt.revision >= FADT2_REVISION_ID && acpi_fadt.century) - extyear = CMOS_READ(acpi_fadt.century); + if (acpi_fadt.revision >= FADT2_REVISION_ID && + acpi_fadt.century) + extyear = CMOS_READ(acpi_fadt.century); #endif + } while (sec != CMOS_READ(RTC_SECONDS)); spin_unlock_irqrestore(&rtc_lock, flags); diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c index 7b14830..edaa9fe 100644 --- a/arch/x86_64/kernel/traps.c +++ b/arch/x86_64/kernel/traps.c @@ -69,20 +69,20 @@ asmlinkage void alignment_check(void); asmlinkage void machine_check(void); asmlinkage void spurious_interrupt_bug(void); -struct notifier_block *die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); +ATOMIC_NOTIFIER_HEAD(die_chain); int register_die_notifier(struct notifier_block *nb) { - int err = 0; - unsigned long flags; - vmalloc_sync_all(); - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; + return atomic_notifier_chain_register(&die_chain, nb); +} +EXPORT_SYMBOL(register_die_notifier); + +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&die_chain, nb); } +EXPORT_SYMBOL(unregister_die_notifier); static inline void conditional_sti(struct pt_regs *regs) { diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index b044156..e5f7f1c 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -72,7 +72,7 @@ void show_mem(void) show_free_areas(); printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { for (i = 0; i < pgdat->node_spanned_pages; ++i) { page = pfn_to_page(pgdat->node_start_pfn + i); total++; diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 63c7264..4be82d6 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -377,21 +377,6 @@ EXPORT_SYMBOL(node_data); * Should do that. */ -/* Requires pfn_valid(pfn) to be true */ -struct page *pfn_to_page(unsigned long pfn) -{ - int nid = phys_to_nid(((unsigned long)(pfn)) << PAGE_SHIFT); - return (pfn - node_start_pfn(nid)) + NODE_DATA(nid)->node_mem_map; -} -EXPORT_SYMBOL(pfn_to_page); - -unsigned long page_to_pfn(struct page *page) -{ - return (long)(((page) - page_zone(page)->zone_mem_map) + - page_zone(page)->zone_start_pfn); -} -EXPORT_SYMBOL(page_to_pfn); - int pfn_valid(unsigned long pfn) { unsigned nid; diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index e90ef5d..dbeb350 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -22,6 +22,14 @@ config RWSEM_XCHGADD_ALGORITHM bool default y +config GENERIC_FIND_NEXT_BIT + bool + default y + +config GENERIC_HWEIGHT + bool + default y + config GENERIC_HARDIRQS bool default y diff --git a/arch/xtensa/platform-iss/setup.c b/arch/xtensa/platform-iss/setup.c index 2e6dcbf..23790a5 100644 --- a/arch/xtensa/platform-iss/setup.c +++ b/arch/xtensa/platform-iss/setup.c @@ -108,5 +108,5 @@ static struct notifier_block iss_panic_block = { void __init platform_setup(char **p_cmdline) { - notifier_chain_register(&panic_notifier_list, &iss_panic_block); + atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block); } |
