diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 2 | ||||
-rw-r--r-- | kernel/audit.c | 2 | ||||
-rw-r--r-- | kernel/cgroup.c | 30 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_main.c | 2 | ||||
-rw-r--r-- | kernel/hrtimer.c | 2 | ||||
-rw-r--r-- | kernel/kexec.c | 2 | ||||
-rw-r--r-- | kernel/latencytop.c | 23 | ||||
-rw-r--r-- | kernel/perf_event.c | 2 | ||||
-rw-r--r-- | kernel/power/hibernate.c | 4 | ||||
-rw-r--r-- | kernel/power/suspend.c | 4 | ||||
-rw-r--r-- | kernel/power/swap.c | 2 | ||||
-rw-r--r-- | kernel/printk.c | 30 | ||||
-rw-r--r-- | kernel/sched.c | 2 | ||||
-rw-r--r-- | kernel/smp.c | 19 | ||||
-rw-r--r-- | kernel/softirq.c | 19 | ||||
-rw-r--r-- | kernel/sys.c | 6 | ||||
-rw-r--r-- | kernel/sysctl.c | 31 | ||||
-rw-r--r-- | kernel/sysctl_binary.c | 2 | ||||
-rw-r--r-- | kernel/taskstats.c | 2 | ||||
-rw-r--r-- | kernel/time.c | 4 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 2 | ||||
-rw-r--r-- | kernel/time/ntp.c | 425 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 43 | ||||
-rw-r--r-- | kernel/trace/trace_entries.h | 2 | ||||
-rw-r--r-- | kernel/user_namespace.c | 15 |
25 files changed, 543 insertions, 134 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 5669f71dfdd..353d3fe8ba3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o -obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o +obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) obj-y += up.o endif diff --git a/kernel/audit.c b/kernel/audit.c index 77770a034d5..e4956244ae5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -400,7 +400,7 @@ static void kauditd_send_skb(struct sk_buff *skb) if (err < 0) { BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid); - audit_log_lost("auditd dissapeared\n"); + audit_log_lost("auditd disappeared\n"); audit_pid = 0; /* we might get lucky and get this in the next auditd */ audit_hold_skb(skb); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 51cddc11cd8..5c5f4cc2e99 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -763,8 +763,6 @@ EXPORT_SYMBOL_GPL(cgroup_unlock); * -> cgroup_mkdir. */ -static struct dentry *cgroup_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd); static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); @@ -1451,6 +1449,10 @@ static int cgroup_set_super(struct super_block *sb, void *data) static int cgroup_get_rootdir(struct super_block *sb) { + static const struct dentry_operations cgroup_dops = { + .d_iput = cgroup_diput, + }; + struct inode *inode = cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb); struct dentry *dentry; @@ -1468,6 +1470,8 @@ static int cgroup_get_rootdir(struct super_block *sb) return -ENOMEM; } sb->s_root = dentry; + /* for everything else we want ->d_op set */ + sb->s_d_op = &cgroup_dops; return 0; } @@ -2191,7 +2195,7 @@ static const struct file_operations cgroup_file_operations = { }; static const struct inode_operations cgroup_dir_inode_operations = { - .lookup = cgroup_lookup, + .lookup = simple_lookup, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .rename = cgroup_rename, @@ -2207,26 +2211,6 @@ static inline struct cftype *__file_cft(struct file *file) return __d_cft(file->f_dentry); } -static int cgroup_delete_dentry(const struct dentry *dentry) -{ - return 1; -} - -static struct dentry *cgroup_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) -{ - static const struct dentry_operations cgroup_dentry_operations = { - .d_delete = cgroup_delete_dentry, - .d_iput = cgroup_diput, - }; - - if (dentry->d_name.len > NAME_MAX) - return ERR_PTR(-ENAMETOOLONG); - d_set_d_op(dentry, &cgroup_dentry_operations); - d_add(dentry, NULL); - return NULL; -} - static int cgroup_create_file(struct dentry *dentry, mode_t mode, struct super_block *sb) { diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index a6e72976682..bd3e8e29caa 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2914,7 +2914,7 @@ static void __init kdb_cmd_init(void) } } -/* Intialize kdb_printf, breakpoint tables and kdb state */ +/* Initialize kdb_printf, breakpoint tables and kdb state */ void __init kdb_init(int lvl) { static int kdb_init_lvl = KDB_NOT_INITIALIZED; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 45da2b6920a..0c8d7c04861 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1745,7 +1745,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, } /* - * A NULL parameter means "inifinte" + * A NULL parameter means "infinite" */ if (!expires) { schedule(); diff --git a/kernel/kexec.c b/kernel/kexec.c index b55045bc756..ec19b92c7eb 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -163,7 +163,7 @@ static int do_kimage_alloc(struct kimage **rimage, unsigned long entry, * just verifies it is an address we can use. * * Since the kernel does everything in page size chunks ensure - * the destination addreses are page aligned. Too many + * the destination addresses are page aligned. Too many * special cases crop of when we don't do this. The most * insidious is getting overlapping destination addresses * simply because addresses are changed to page size diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 17110a4a4fc..ee74b35e528 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -241,24 +241,19 @@ static int lstats_show(struct seq_file *m, void *v) seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < MAXLR; i++) { - if (latency_record[i].backtrace[0]) { + struct latency_record *lr = &latency_record[i]; + + if (lr->backtrace[0]) { int q; - seq_printf(m, "%i %lu %lu ", - latency_record[i].count, - latency_record[i].time, - latency_record[i].max); + seq_printf(m, "%i %lu %lu", + lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { - char sym[KSYM_SYMBOL_LEN]; - char *c; - if (!latency_record[i].backtrace[q]) + unsigned long bt = lr->backtrace[q]; + if (!bt) break; - if (latency_record[i].backtrace[q] == ULONG_MAX) + if (bt == ULONG_MAX) break; - sprint_symbol(sym, latency_record[i].backtrace[q]); - c = strchr(sym, '+'); - if (c) - *c = 0; - seq_printf(m, "%s ", sym); + seq_printf(m, " %ps", (void *)bt); } seq_printf(m, "\n"); } diff --git a/kernel/perf_event.c b/kernel/perf_event.c index b782b7a79f0..05ebe841270 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4664,7 +4664,7 @@ int perf_swevent_get_recursion_context(void) } EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context); -void inline perf_swevent_put_recursion_context(int rctx) +inline void perf_swevent_put_recursion_context(int rctx) { struct swevent_htable *swhash = &__get_cpu_var(swevent_htable); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 870f72bc72a..1832bd26421 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -51,14 +51,14 @@ enum { static int hibernation_mode = HIBERNATION_SHUTDOWN; -static struct platform_hibernation_ops *hibernation_ops; +static const struct platform_hibernation_ops *hibernation_ops; /** * hibernation_set_ops - set the global hibernate operations * @ops: the hibernation operations to use in subsequent hibernation transitions */ -void hibernation_set_ops(struct platform_hibernation_ops *ops) +void hibernation_set_ops(const struct platform_hibernation_ops *ops) { if (ops && !(ops->begin && ops->end && ops->pre_snapshot && ops->prepare && ops->finish && ops->enter && ops->pre_restore diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 8850df68794..de6f86bfa30 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -31,13 +31,13 @@ const char *const pm_states[PM_SUSPEND_MAX] = { [PM_SUSPEND_MEM] = "mem", }; -static struct platform_suspend_ops *suspend_ops; +static const struct platform_suspend_ops *suspend_ops; /** * suspend_set_ops - Set the global suspend method table. * @ops: Pointer to ops structure. */ -void suspend_set_ops(struct platform_suspend_ops *ops) +void suspend_set_ops(const struct platform_suspend_ops *ops) { mutex_lock(&pm_mutex); suspend_ops = ops; diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 8c7e4832b9b..69425889bd4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -888,7 +888,7 @@ out_finish: /** * swsusp_read - read the hibernation image. * @flags_p: flags passed by the "frozen" kernel in the image header should - * be written into this memeory location + * be written into this memory location */ int swsusp_read(unsigned int *flags_p) diff --git a/kernel/printk.c b/kernel/printk.c index f64b8997fc7..53d9a9ec88e 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -39,6 +39,7 @@ #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/notifier.h> +#include <linux/rculist.h> #include <asm/uaccess.h> @@ -1502,7 +1503,7 @@ int kmsg_dump_register(struct kmsg_dumper *dumper) /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; - list_add_tail(&dumper->list, &dump_list); + list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); @@ -1526,29 +1527,16 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper) spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; - list_del(&dumper->list); + list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); + synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); -static const char * const kmsg_reasons[] = { - [KMSG_DUMP_OOPS] = "oops", - [KMSG_DUMP_PANIC] = "panic", - [KMSG_DUMP_KEXEC] = "kexec", -}; - -static const char *kmsg_to_str(enum kmsg_dump_reason reason) -{ - if (reason >= ARRAY_SIZE(kmsg_reasons) || reason < 0) - return "unknown"; - - return kmsg_reasons[reason]; -} - /** * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping @@ -1587,13 +1575,9 @@ void kmsg_dump(enum kmsg_dump_reason reason) l2 = chars; } - if (!spin_trylock_irqsave(&dump_list_lock, flags)) { - printk(KERN_ERR "dump_kmsg: dump list lock is held during %s, skipping dump\n", - kmsg_to_str(reason)); - return; - } - list_for_each_entry(dumper, &dump_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) dumper->dump(dumper, reason, s1, l1, s2, l2); - spin_unlock_irqrestore(&dump_list_lock, flags); + rcu_read_unlock(); } #endif diff --git a/kernel/sched.c b/kernel/sched.c index a0eb0941fa8..ea3e5eff387 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2505,7 +2505,7 @@ out: * try_to_wake_up_local - try to wake up a local task with rq lock held * @p: the thread to be awakened * - * Put @p on the run-queue if it's not alredy there. The caller must + * Put @p on the run-queue if it's not already there. The caller must * ensure that this_rq() is locked, @p is bound to this_rq() and not * the current task. this_rq() stays locked over invocation. */ diff --git a/kernel/smp.c b/kernel/smp.c index 12ed8b013e2..4ec30e06998 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <linux/cpu.h> +#ifdef CONFIG_USE_GENERIC_SMP_HELPERS static struct { struct list_head queue; raw_spinlock_t lock; @@ -529,3 +530,21 @@ void ipi_call_unlock_irq(void) { raw_spin_unlock_irq(&call_function.lock); } +#endif /* USE_GENERIC_SMP_HELPERS */ + +/* + * Call a function on all processors + */ +int on_each_cpu(void (*func) (void *info), void *info, int wait) +{ + int ret = 0; + + preempt_disable(); + ret = smp_call_function(func, info, wait); + local_irq_disable(); + func(info); + local_irq_enable(); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL(on_each_cpu); diff --git a/kernel/softirq.c b/kernel/softirq.c index 0823778f87f..68eb5efec38 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -885,25 +885,6 @@ static __init int spawn_ksoftirqd(void) } early_initcall(spawn_ksoftirqd); -#ifdef CONFIG_SMP -/* - * Call a function on all processors - */ -int on_each_cpu(void (*func) (void *info), void *info, int wait) -{ - int ret = 0; - - preempt_disable(); - ret = smp_call_function(func, info, wait); - local_irq_disable(); - func(info); - local_irq_enable(); - preempt_enable(); - return ret; -} -EXPORT_SYMBOL(on_each_cpu); -#endif - /* * [ These __weak aliases are kept in a separate compilation unit, so that * GCC does not inline them incorrectly. ] diff --git a/kernel/sys.c b/kernel/sys.c index 2745dcdb6c6..31b71a276b4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -43,6 +43,8 @@ #include <linux/kprobes.h> #include <linux/user_namespace.h> +#include <linux/kmsg_dump.h> + #include <asm/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> @@ -285,6 +287,7 @@ out_unlock: */ void emergency_restart(void) { + kmsg_dump(KMSG_DUMP_EMERG); machine_emergency_restart(); } EXPORT_SYMBOL_GPL(emergency_restart); @@ -312,6 +315,7 @@ void kernel_restart(char *cmd) printk(KERN_EMERG "Restarting system.\n"); else printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); + kmsg_dump(KMSG_DUMP_RESTART); machine_restart(cmd); } EXPORT_SYMBOL_GPL(kernel_restart); @@ -333,6 +337,7 @@ void kernel_halt(void) kernel_shutdown_prepare(SYSTEM_HALT); sysdev_shutdown(); printk(KERN_EMERG "System halted.\n"); + kmsg_dump(KMSG_DUMP_HALT); machine_halt(); } @@ -351,6 +356,7 @@ void kernel_power_off(void) disable_nonboot_cpus(); sysdev_shutdown(); printk(KERN_EMERG "Power down.\n"); + kmsg_dump(KMSG_DUMP_POWEROFF); machine_power_off(); } EXPORT_SYMBOL_GPL(kernel_power_off); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ae5cbb1e3ce..bc86bb32e12 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/signal.h> +#include <linux/printk.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/ctype.h> @@ -245,10 +246,6 @@ static struct ctl_table root_table[] = { .mode = 0555, .child = dev_table, }, -/* - * NOTE: do not add new entries to this table unless you have read - * Documentation/sysctl/ctl_unnumbered.txt - */ { } }; @@ -710,6 +707,15 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "kptr_restrict", + .data = &kptr_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, #endif { .procname = "ngroups_max", @@ -962,10 +968,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -/* - * NOTE: do not add new entries to this table unless you have read - * Documentation/sysctl/ctl_unnumbered.txt - */ { } }; @@ -1326,11 +1328,6 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif - -/* - * NOTE: do not add new entries to this table unless you have read - * Documentation/sysctl/ctl_unnumbered.txt - */ { } }; @@ -1486,10 +1483,6 @@ static struct ctl_table fs_table[] = { .proc_handler = &pipe_proc_fn, .extra1 = &pipe_min_size, }, -/* - * NOTE: do not add new entries to this table unless you have read - * Documentation/sysctl/ctl_unnumbered.txt - */ { } }; @@ -2899,7 +2892,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, } } -#else /* CONFIG_PROC_FS */ +#else /* CONFIG_PROC_SYSCTL */ int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -2951,7 +2944,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, } -#endif /* CONFIG_PROC_FS */ +#endif /* CONFIG_PROC_SYSCTL */ /* * No sense putting this after each symbol definition, twice, diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 4b2545a136f..b875bedf7c9 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1192,7 +1192,7 @@ static ssize_t bin_dn_node_address(struct file *file, buf[result] = '\0'; - /* Convert the decnet addresss to binary */ + /* Convert the decnet address to binary */ result = -EIO; nodep = strchr(buf, '.') + 1; if (!nodep) diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 69691eb4b71..3971c6b9d58 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -348,7 +348,7 @@ static int parse(struct nlattr *na, struct cpumask *mask) return ret; } -#ifdef CONFIG_IA64 +#if defined(CONFIG_64BIT) && !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) #define TASKSTATS_NEEDS_PADDING 1 #endif diff --git a/kernel/time.c b/kernel/time.c index ba9b338d183..32174359576 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -238,7 +238,7 @@ EXPORT_SYMBOL(current_fs_time); * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ -unsigned int inline jiffies_to_msecs(const unsigned long j) +inline unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; @@ -254,7 +254,7 @@ unsigned int inline jiffies_to_msecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_msecs); -unsigned int inline jiffies_to_usecs(const unsigned long j) +inline unsigned int jiffies_to_usecs(const unsigned long j) { #if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index df140cd3ea4..c50a034de30 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -679,7 +679,7 @@ EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { - /* Intialize mult/shift and max_idle_ns */ + /* Initialize mult/shift and max_idle_ns */ __clocksource_updatefreq_scale(cs, scale, freq); /* Add clocksource to the clcoksource list */ diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index d2321891538..5c00242fa92 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -14,6 +14,7 @@ #include <linux/timex.h> #include <linux/time.h> #include <linux/mm.h> +#include <linux/module.h> /* * NTP timekeeping variables: @@ -74,6 +75,162 @@ static long time_adjust; /* constant (boot-param configurable) NTP tick adjustment (upscaled) */ static s64 ntp_tick_adj; +#ifdef CONFIG_NTP_PPS + +/* + * The following variables are used when a pulse-per-second (PPS) signal + * is available. They establish the engineering parameters of the clock + * discipline loop when controlled by the PPS signal. + */ +#define PPS_VALID 10 /* PPS signal watchdog max (s) */ +#define PPS_POPCORN 4 /* popcorn spike threshold (shift) */ +#define PPS_INTMIN 2 /* min freq interval (s) (shift) */ +#define PPS_INTMAX 8 /* max freq interval (s) (shift) */ +#define PPS_INTCOUNT 4 /* number of consecutive good intervals to + increase pps_shift or consecutive bad + intervals to decrease it */ +#define PPS_MAXWANDER 100000 /* max PPS freq wander (ns/s) */ + +static int pps_valid; /* signal watchdog counter */ +static long pps_tf[3]; /* phase median filter */ +static long pps_jitter; /* current jitter (ns) */ +static struct timespec pps_fbase; /* beginning of the last freq interval */ +static int pps_shift; /* current interval duration (s) (shift) */ +static int pps_intcnt; /* interval counter */ +static s64 pps_freq; /* frequency offset (scaled ns/s) */ +static long pps_stabil; /* current stability (scaled ns/s) */ + +/* + * PPS signal quality monitors + */ +static long pps_calcnt; /* calibration intervals */ +static long pps_jitcnt; /* jitter limit exceeded */ +static long pps_stbcnt; /* stability limit exceeded */ +static long pps_errcnt; /* calibration errors */ + + +/* PPS kernel consumer compensates the whole phase error immediately. + * Otherwise, reduce the offset by a fixed factor times the time constant. + */ +static inline s64 ntp_offset_chunk(s64 offset) +{ + if (time_status & STA_PPSTIME && time_status & STA_PPSSIGNAL) + return offset; + else + return shift_right(offset, SHIFT_PLL + time_constant); +} + +static inline void pps_reset_freq_interval(void) +{ + /* the PPS calibration interval may end + surprisingly early */ + pps_shift = PPS_INTMIN; + pps_intcnt = 0; +} + +/** + * pps_clear - Clears the PPS state variables + * + * Must be called while holding a write on the xtime_lock + */ +static inline void pps_clear(void) +{ + pps_reset_freq_interval(); + pps_tf[0] = 0; + pps_tf[1] = 0; + pps_tf[2] = 0; + pps_fbase.tv_sec = pps_fbase.tv_nsec = 0; + pps_freq = 0; +} + +/* Decrease pps_valid to indicate that another second has passed since + * the last PPS signal. When it reaches 0, indicate that PPS signal is + * missing. + * + * Must be called while holding a write on the xtime_lock + */ +static inline void pps_dec_valid(void) +{ + if (pps_valid > 0) + pps_valid--; + else { + time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER | + STA_PPSWANDER | STA_PPSERROR); + pps_clear(); + } +} + +static inline void pps_set_freq(s64 freq) +{ + pps_freq = freq; +} + +static inline int is_error_status(int status) +{ + return (time_status & (STA_UNSYNC|STA_CLOCKERR)) + /* PPS signal lost when either PPS time or + * PPS frequency synchronization requested + */ + || ((time_status & (STA_PPSFREQ|STA_PPSTIME)) + && !(time_status & STA_PPSSIGNAL)) + /* PPS jitter exceeded when + * PPS time synchronization requested */ + || ((time_status & (STA_PPSTIME|STA_PPSJITTER)) + == (STA_PPSTIME|STA_PPSJITTER)) + /* PPS wander exceeded or calibration error when + * PPS frequency synchronization requested + */ + || ((time_status & STA_PPSFREQ) + && (time_status & (STA_PPSWANDER|STA_PPSERROR))); +} + +static inline void pps_fill_timex(struct timex *txc) +{ + txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) * + PPM_SCALE_INV, NTP_SCALE_SHIFT); + txc->jitter = pps_jitter; + if (!(time_status & STA_NANO)) + txc->jitter /= NSEC_PER_USEC; + txc->shift = pps_shift; + txc->stabil = pps_stabil; + txc->jitcnt = pps_jitcnt; + txc->calcnt = pps_calcnt; + txc->errcnt = pps_errcnt; + txc->stbcnt = pps_stbcnt; +} + +#else /* !CONFIG_NTP_PPS */ + +static inline s64 ntp_offset_chunk(s64 offset) +{ + return shift_right(offset, SHIFT_PLL + time_constant); +} + +static inline void pps_reset_freq_interval(void) {} +static inline void pps_clear(void) {} +static inline void pps_dec_valid(void) {} +static inline void pps_set_freq(s64 freq) {} + +static inline int is_error_status(int status) +{ + return status & (STA_UNSYNC|STA_CLOCKERR); +} + +static inline void pps_fill_timex(struct timex *txc) +{ + /* PPS is not implemented, so these are zero */ + txc->ppsfreq = 0; + txc->jitter = 0; + txc->shift = 0; + txc->stabil = 0; + txc->jitcnt = 0; + txc->calcnt = 0; + txc->errcnt = 0; + txc->stbcnt = 0; +} + +#endif /* CONFIG_NTP_PPS */ + /* * NTP methods: */ @@ -185,6 +342,9 @@ void ntp_clear(void) tick_length = tick_length_base; time_offset = 0; + + /* Clear PPS state variables */ + pps_clear(); } /* @@ -250,16 +410,16 @@ void second_overflow(void) time_status |= STA_UNSYNC; } - /* - * Compute the phase adjustment for the next second. The offset is - * reduced by a fixed factor times the time constant. - */ + /* Compute the phase adjustment for the next second */ tick_length = tick_length_base; - delta = shift_right(time_offset, SHIFT_PLL + time_constant); + delta = ntp_offset_chunk(time_offset); time_offset -= delta; tick_length += delta; + /* Check PPS signal */ + pps_dec_valid(); + if (!time_adjust) return; @@ -369,6 +529,8 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; time_status = STA_UNSYNC; + /* restart PPS frequency calibration */ + pps_reset_freq_interval(); } /* @@ -418,6 +580,8 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts time_freq = txc->freq * PPM_SCALE; time_freq = min(time_freq, MAXFREQ_SCALED); time_freq = max(time_freq, -MAXFREQ_SCALED); + /* update pps_freq */ + pps_set_freq(time_freq); } if (txc->modes & ADJ_MAXERROR) @@ -508,7 +672,8 @@ int do_adjtimex(struct timex *txc) } result = time_state; /* mostly `TIME_OK' */ - if (time_status & (STA_UNSYNC|STA_CLOCKERR)) + /* check for errors */ + if (is_error_status(time_status)) result = TIME_ERROR; txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * @@ -522,15 +687,8 @@ int do_adjtimex(struct timex *txc) txc->tick = tick_usec; txc->tai = time_tai; - /* PPS is not implemented, so these are zero */ - txc->ppsfreq = 0; - txc->jitter = 0; - txc->shift = 0; - txc->stabil = 0; - txc->jitcnt = 0; - txc->calcnt = 0; - txc->errcnt = 0; - txc->stbcnt = 0; + /* fill PPS status fields */ + pps_fill_timex(txc); write_sequnlock_irq(&xtime_lock); @@ -544,6 +702,243 @@ int do_adjtimex(struct timex *txc) return result; } +#ifdef CONFIG_NTP_PPS + +/* actually struct pps_normtime is good old struct timespec, but it is + * semantically different (and it is the reason why it was invented): + * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] + * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */ +struct pps_normtime { + __kernel_time_t sec; /* seconds */ + long nsec; /* nanoseconds */ +}; + +/* normalize the timestamp so that nsec is in the + ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */ +static inline struct pps_normtime pps_normalize_ts(struct timespec ts) +{ + struct pps_normtime norm = { + .sec = ts.tv_sec, + .nsec = ts.tv_nsec + }; + + if (norm.nsec > (NSEC_PER_SEC >> 1)) { + norm.nsec -= NSEC_PER_SEC; + norm.sec++; + } + + return norm; +} + +/* get current phase correction and jitter */ +static inline long pps_phase_filter_get(long *jitter) +{ + *jitter = pps_tf[0] - pps_tf[1]; + if (*jitter < 0) + *jitter = -*jitter; + + /* TODO: test various filters */ + return pps_tf[0]; +} + +/* add the sample to the phase filter */ +static inline void pps_phase_filter_add(long err) +{ + pps_tf[2] = pps_tf[1]; + pps_tf[1] = pps_tf[0]; + pps_tf[0] = err; +} + +/* decrease frequency calibration interval length. + * It is halved after four consecutive unstable intervals. + */ +static inline void pps_dec_freq_interval(void) +{ + if (--pps_intcnt <= -PPS_INTCOUNT) { + pps_intcnt = -PPS_INTCOUNT; + if (pps_shift > PPS_INTMIN) { + pps_shift--; + pps_intcnt = 0; + } + } +} + +/* increase frequency calibration interval length. + * It is doubled after four consecutive stable intervals. + */ +static inline void pps_inc_freq_interval(void) +{ + if (++pps_intcnt >= PPS_INTCOUNT) { + pps_intcnt = PPS_INTCOUNT; + if (pps_shift < PPS_INTMAX) { + pps_shift++; + pps_intcnt = 0; + } + } +} + +/* update clock frequency based on MONOTONIC_RAW clock PPS signal + * timestamps + * + * At the end of the calibration interval the difference between the + * first and last MONOTONIC_RAW clock timestamps divided by the length + * of the interval becomes the frequency update. If the interval was + * too long, the data are discarded. + * Returns the difference between old and new frequency values. + */ +static long hardpps_update_freq(struct pps_normtime freq_norm) +{ + long delta, delta_mod; + s64 ftemp; + + /* check if the frequency interval was too long */ + if (freq_norm.sec > (2 << pps_shift)) { + time_status |= STA_PPSERROR; + pps_errcnt++; + pps_dec_freq_interval(); + pr_err("hardpps: PPSERROR: interval too long - %ld s\n", + freq_norm.sec); + return 0; + } + + /* here the raw frequency offset and wander (stability) is + * calculated. If the wander is less than the wander threshold + * the interval is increased; otherwise it is decreased. + */ + ftemp = div_s64(((s64)(-freq_norm.nsec)) << NTP_SCALE_SHIFT, + freq_norm.sec); + delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT); + pps_freq = ftemp; + if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) { + pr_warning("hardpps: PPSWANDER: change=%ld\n", delta); + time_status |= STA_PPSWANDER; + pps_stbcnt++; + pps_dec_freq_interval(); + } else { /* good sample */ + pps_inc_freq_interval(); + } + + /* the stability metric is calculated as the average of recent + * frequency changes, but is used only for performance + * monitoring + */ + delta_mod = delta; + if (delta_mod < 0) + delta_mod = -delta_mod; + pps_stabil += (div_s64(((s64)delta_mod) << + (NTP_SCALE_SHIFT - SHIFT_USEC), + NSEC_PER_USEC) - pps_stabil) >> PPS_INTMIN; + + /* if enabled, the system clock frequency is updated */ + if ((time_status & STA_PPSFREQ) != 0 && + (time_status & STA_FREQHOLD) == 0) { + time_freq = pps_freq; + ntp_update_frequency(); + } + + return delta; +} + +/* correct REALTIME clock phase error against PPS signal */ +static void hardpps_update_phase(long error) +{ + long correction = -error; + long jitter; + + /* add the sample to the median filter */ + pps_phase_filter_add(correction); + correction = pps_phase_filter_get(&jitter); + + /* Nominal jitter is due to PPS signal noise. If it exceeds the + * threshold, the sample is discarded; otherwise, if so enabled, + * the time offset is updated. + */ + if (jitter > (pps_jitter << PPS_POPCORN)) { + pr_warning("hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", + jitter, (pps_jitter << PPS_POPCORN)); + time_status |= STA_PPSJITTER; + pps_jitcnt++; + } else if (time_status & STA_PPSTIME) { + /* correct the time using the phase offset */ + time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT, + NTP_INTERVAL_FREQ); + /* cancel running adjtime() */ + time_adjust = 0; + } + /* update jitter */ + pps_jitter += (jitter - pps_jitter) >> PPS_INTMIN; +} + +/* + * hardpps() - discipline CPU clock oscillator to external PPS signal + * + * This routine is called at each PPS signal arrival in order to + * discipline the CPU clock oscillator to the PPS signal. It takes two + * parameters: REALTIME and MONOTONIC_RAW clock timestamps. The former + * is used to correct clock phase error and the latter is used to + * correct the frequency. + * + * This code is based on David Mills's reference nanokernel + * implementation. It was mostly rewritten but keeps the same idea. + */ +void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) +{ + struct pps_normtime pts_norm, freq_norm; + unsigned long flags; + + pts_norm = pps_normalize_ts(*phase_ts); + + write_seqlock_irqsave(&xtime_lock, flags); + + /* clear the error bits, they will be set again if needed */ + time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); + + /* indicate signal presence */ + time_status |= STA_PPSSIGNAL; + pps_valid = PPS_VALID; + + /* when called for the first time, + * just start the frequency interval */ + if (unlikely(pps_fbase.tv_sec == 0)) { + pps_fbase = *raw_ts; + write_sequnlock_irqrestore(&xtime_lock, flags); + return; + } + + /* ok, now we have a base for frequency calculation */ + freq_norm = pps_normalize_ts(timespec_sub(*raw_ts, pps_fbase)); + + /* check that the signal is in the range + * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */ + if ((freq_norm.sec == 0) || + (freq_norm.nsec > MAXFREQ * freq_norm.sec) || + (freq_norm.nsec < -MAXFREQ * freq_norm.sec)) { + time_status |= STA_PPSJITTER; + /* restart the frequency calibration interval */ + pps_fbase = *raw_ts; + write_sequnlock_irqrestore(&xtime_lock, flags); + pr_err("hardpps: PPSJITTER: bad pulse\n"); + return; + } + + /* signal is ok */ + + /* check if the current frequency interval is finished */ + if (freq_norm.sec >= (1 << pps_shift)) { + pps_calcnt++; + /* restart the frequency calibration interval */ + pps_fbase = *raw_ts; + hardpps_update_freq(freq_norm); + } + + hardpps_update_phase(pts_norm.nsec); + + write_sequnlock_irqrestore(&xtime_lock, flags); +} +EXPORT_SYMBOL(hardpps); + +#endif /* CONFIG_NTP_PPS */ + static int __init ntp_tick_adj_setup(char *str) { ntp_tick_adj = simple_strtol(str, NULL, 0); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5bb86da8200..5536aaf3ba3 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -288,6 +288,49 @@ void ktime_get_ts(struct timespec *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts); +#ifdef CONFIG_NTP_PPS + +/** + * getnstime_raw_and_real - get day and raw monotonic time in timespec format + * @ts_raw: pointer to the timespec to be set to raw monotonic time + * @ts_real: pointer to the timespec to be set to the time of day + * + * This function reads both the time of day and raw monotonic time at the + * same time atomically and stores the resulting timestamps in timespec + * format. + */ +void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) +{ + unsigned long seq; + s64 nsecs_raw, nsecs_real; + + WARN_ON_ONCE(timekeeping_suspended); + + do { + u32 arch_offset; + + seq = read_seqbegin(&xtime_lock); + + *ts_raw = raw_time; + *ts_real = xtime; + + nsecs_raw = timekeeping_get_ns_raw(); + nsecs_real = timekeeping_get_ns(); + + /* If arch requires, add in gettimeoffset() */ + arch_offset = arch_gettimeoffset(); + nsecs_raw += arch_offset; + nsecs_real += arch_offset; + + } while (read_seqretry(&xtime_lock, seq)); + + timespec_add_ns(ts_raw, nsecs_raw); + timespec_add_ns(ts_real, nsecs_real); +} +EXPORT_SYMBOL(getnstime_raw_and_real); + +#endif /* CONFIG_NTP_PPS */ + /** * do_gettimeofday - Returns the time of day in a timeval * @tv: pointer to the timeval to be set diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e3dfecaf13e..6cf223764be 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -53,7 +53,7 @@ */ /* - * Function trace entry - function address and parent function addres: + * Function trace entry - function address and parent function address: */ FTRACE_ENTRY(function, ftrace_entry, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 25915832291..9da289c34f2 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -12,6 +12,8 @@ #include <linux/highuid.h> #include <linux/cred.h> +static struct kmem_cache *user_ns_cachep __read_mostly; + /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the @@ -26,7 +28,7 @@ int create_user_ns(struct cred *new) struct user_struct *root_user; int n; - ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL); + ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL); if (!ns) return -ENOMEM; @@ -38,7 +40,7 @@ int create_user_ns(struct cred *new) /* Alloc new root user. */ root_user = alloc_uid(ns, 0); if (!root_user) { - kfree(ns); + kmem_cache_free(user_ns_cachep, ns); return -ENOMEM; } @@ -71,7 +73,7 @@ static void free_user_ns_work(struct work_struct *work) struct user_namespace *ns = container_of(work, struct user_namespace, destroyer); free_uid(ns->creator); - kfree(ns); + kmem_cache_free(user_ns_cachep, ns); } void free_user_ns(struct kref *kref) @@ -126,3 +128,10 @@ gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t /* No useful relationship so no mapping */ return overflowgid; } + +static __init int user_namespaces_init(void) +{ + user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); + return 0; +} +module_init(user_namespaces_init); |