diff options
Diffstat (limited to 'arch')
105 files changed, 1332 insertions, 1119 deletions
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index b4e5f8ff2b2..dd876967059 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/mm/numa.c b/arch/alpha/mm/numa.c index 6d5251254f6..bf6b65c81be 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 bf2e72698d0..9731b3f826a 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 @@ -839,6 +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 e851d86c212..35c9a64ac14 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/mach-integrator/time.c b/arch/arm/mach-integrator/time.c index 3c22c16b38b..bc07f52a6fd 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 60d5f8a3339..7520e602d7a 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 bfd5fdd1a87..52e4a9d6964 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 9b48a90aefc..5efa84749f3 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 2abdc419e98..9ea71551fc0 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/mm/init.c b/arch/arm26/mm/init.c index e3ecaa45374..7da8a520567 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/kernel/setup.c b/arch/cris/kernel/setup.c index 1ba57efff60..619a6eefd89 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/i386/Kconfig b/arch/i386/Kconfig index f7db71d0b91..f17bd1d2707 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -231,6 +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/boot/video.S b/arch/i386/boot/video.S index 2ac40c8244c..0000a267453 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/cpu/common.c b/arch/i386/kernel/cpu/common.c index 7e3d6b6a4e9..a06a49075f1 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/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index ce61921369e..9df87b03612 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/setup.c b/arch/i386/kernel/setup.c index 6917daa159a..8c08660b4e5 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> diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 82371d83bfa..a6969903f2d 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 ac687d00a1c..326595f3fa4 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 264edaaac31..144e94a0493 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 4624f8ca245..6b63a5aa1e4 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 && diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index c4af9638dbf..fe6eb901326 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 9db3242103b..2889567e21a 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/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index dabd6c32641..7c1ddc8ac44 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/mm/discontig.c b/arch/ia64/mm/discontig.c index 2f5e44862e9..ec9eeb89975 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 ff4f31fcd33..2ef1151cde9 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/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index d742037a7cc..0d78942b4c7 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 08e72795555..cf610a7c5ff 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 c9e7dad860b..b71348fec1f 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/mips/ddb5xxx/common/rtc_ds1386.c b/arch/mips/ddb5xxx/common/rtc_ds1386.c index 995896ac0e3..5dc34daa715 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 17482234413..f17d3378e9a 100644 --- a/arch/mips/dec/time.c +++ b/arch/mips/dec/time.c @@ -193,8 +193,8 @@ 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 f5d67ee21ac..b79817bb6cc 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 ea4e1935fec..b774db035b3 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 56dca7e0c21..e8ec8be66a8 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 9a8bff153d8..a6bd3f4d304 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/setup.c b/arch/mips/kernel/setup.c index 0cb3b6097e0..dcbfd27071f 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 51273b7297a..5e51a2d8f3f 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 83eb08b7a07..bb70a8240e6 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/mips-boards/atlas/atlas_setup.c b/arch/mips/mips-boards/atlas/atlas_setup.c index 873cf3141a3..c20d401ecf8 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 ee5e70c95cf..32c9210373a 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 2209e8a9de3..b8488aab6df 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 1ec4e75656b..e57f737bab1 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 52f7d59fe61..ad89c442f29 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 3784c898db1..91d9637143d 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 f95677f4f06..969612eab8a 100644 --- a/arch/mips/momentum/ocelot_3/setup.c +++ b/arch/mips/momentum/ocelot_3/setup.c @@ -215,8 +215,8 @@ 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 bd02e60d037..a3e6f557559 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 8bce711575d..3f724d661bd 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 92a3b3c15ed..a9c58e067b5 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 b7300cc5c5a..cca688ad64a 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 e0d095daa5e..6c00dce9f73 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 0c948008b02..ab9d9cef089 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 2f50c79b788..a2dd8ae1ea8 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 b661d2425a3..4b5f74ff3ed 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 1141fcd13a5..01ba6c581e3 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 2ad6401d2af..6dcf077f61a 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 d249edbb6af..f74295f2852 100644 --- a/arch/mips/tx4938/common/rtc_rx5c348.c +++ b/arch/mips/tx4938/common/rtc_rx5c348.c @@ -197,6 +197,6 @@ 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/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c index 2a01fe1bdc9..0cea6958f42 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/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2f3fdad3559..e20c1fae342 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/traps.c b/arch/powerpc/kernel/traps.c index 98660aedeeb..9763faab673 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/mem.c b/arch/powerpc/mm/mem.c index badac10d700..5e435a9c343 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/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 86cfa6ecdcf..5ad90676567 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/platforms/prep_setup.c b/arch/ppc/platforms/prep_setup.c index a0fc628ffb1..d95c05d9824 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/kernel/process.c b/arch/s390/kernel/process.c index 99182a415fe..4a0f5a1551e 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/sh/kernel/setup.c b/arch/sh/kernel/setup.c index c0e79843f58..7ee4ca20361 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/kernel/setup.c b/arch/sh64/kernel/setup.c index c7a7b816a30..d2711c9c9d1 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/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c index df612e4f75f..ff090bb9734 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/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 54388d10bcf..1488816588e 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 fa617e0719a..0336575d244 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 b61deb8b362..69a93c804f0 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 7d223beccbc..4ce3fc650e5 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 00000000000..989bc08de36 --- /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 2a1c64d8d0b..d3d1bc6074e 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 37d76e29a14..fe99ea163c2 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 260065cfeef..8bc6916bbbb 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 86357282d68..853b26f148c 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 a6f1f176cf8..992a7e1e0fc 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 693018ba80f..fe08971b64c 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 c264e1c05ab..1ca84319317 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 bbf94bf2921..c39ea3abeda 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 0e32f5f4a88..00000000000 --- 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 0e65340eee3..0500800df1c 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 229988463c4..1c1300fb1e9 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 72113b0a96e..c8d8d0ac1a7 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 80c9c18aae9..7d51dd7201c 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 08a4e628b24..1659386b42b 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 00000000000..e599be423da --- /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 f7b18e157d3..9ba94294714 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 829d6b0d8b0..32753131f8d 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 919d19f1153..5461a065bbb 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 9ada656f68c..c6ba56c1560 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 ecf107ae5ac..198e5916328 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 e839ce65ad2..8032a105949 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 7cd1a82dc8c..33a40f5ef0d 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 26b68675053..6f4ef2b7fa4 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 74eee5c7c6d..147bbf05cbc 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 fe1d065332b..e75c4e1838b 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 7bd54a921cf..899cebb57c3 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/x86_64/Kconfig b/arch/x86_64/Kconfig index 45efe0ca88f..4310b4a311a 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -250,6 +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 @@ -325,6 +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/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 7549a4389fb..35b2faccdc6 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -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/kernel/process.c b/arch/x86_64/kernel/process.c index 0370720515f..70dd8e5c688 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -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 */ diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index a57eec8311a..d1f3e9272c0 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 66e98659d07..ea48fa63807 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/traps.c b/arch/x86_64/kernel/traps.c index 7b148309c52..edaa9fe654d 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 b0441562544..e5f7f1c3446 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 63c72641b73..4be82d6e2b4 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/platform-iss/setup.c b/arch/xtensa/platform-iss/setup.c index 2e6dcbf0cc0..23790a5610e 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); } |