diff options
Diffstat (limited to 'kernel')
50 files changed, 4771 insertions, 2011 deletions
diff --git a/kernel/.gitignore b/kernel/.gitignore new file mode 100644 index 00000000000..f2ab70073bd --- /dev/null +++ b/kernel/.gitignore @@ -0,0 +1,5 @@ +# +# Generated files +# +config_data.h +config_data.gz diff --git a/kernel/Makefile b/kernel/Makefile index 4f5a1453093..4ae0fbde815 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -6,15 +6,18 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ exit.o itimer.o time.o softirq.o resource.o \ sysctl.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ - rcupdate.o intermodule.o extable.o params.o posix-timers.o \ - kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o + rcupdate.o extable.o params.o posix-timers.o \ + kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ + hrtimer.o +obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o obj-$(CONFIG_FUTEX) += futex.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += cpu.o spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_OBSOLETE_INTERMODULE) += intermodule.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_PM) += power/ obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o @@ -29,7 +32,6 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ -obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o diff --git a/kernel/acct.c b/kernel/acct.c index 6312d6bd43e..065d8b4e51e 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -47,6 +47,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/acct.h> +#include <linux/capability.h> #include <linux/file.h> #include <linux/tty.h> #include <linux/security.h> @@ -427,6 +428,7 @@ static void do_acct_process(long exitcode, struct file *file) u64 elapsed; u64 run_time; struct timespec uptime; + unsigned long jiffies; /* * First check to see if there is enough free_space to continue @@ -467,12 +469,12 @@ static void do_acct_process(long exitcode, struct file *file) #endif do_div(elapsed, AHZ); ac.ac_btime = xtime.tv_sec - elapsed; - ac.ac_utime = encode_comp_t(jiffies_to_AHZ( - current->signal->utime + - current->group_leader->utime)); - ac.ac_stime = encode_comp_t(jiffies_to_AHZ( - current->signal->stime + - current->group_leader->stime)); + jiffies = cputime_to_jiffies(cputime_add(current->group_leader->utime, + current->signal->utime)); + ac.ac_utime = encode_comp_t(jiffies_to_AHZ(jiffies)); + jiffies = cputime_to_jiffies(cputime_add(current->group_leader->stime, + current->signal->stime)); + ac.ac_stime = encode_comp_t(jiffies_to_AHZ(jiffies)); /* we really need to bite the bullet and change layout */ ac.ac_uid = current->uid; ac.ac_gid = current->gid; @@ -580,7 +582,8 @@ void acct_process(long exitcode) void acct_update_integrals(struct task_struct *tsk) { if (likely(tsk->mm)) { - long delta = tsk->stime - tsk->acct_stimexpd; + long delta = + cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd; if (delta == 0) return; diff --git a/kernel/audit.c b/kernel/audit.c index 0c56320d38d..0a813d2883e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -42,8 +42,8 @@ */ #include <linux/init.h> -#include <asm/atomic.h> #include <asm/types.h> +#include <asm/atomic.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/err.h> @@ -267,7 +267,7 @@ static int audit_set_failure(int state, uid_t loginuid) return old; } -int kauditd_thread(void *dummy) +static int kauditd_thread(void *dummy) { struct sk_buff *skb; @@ -291,8 +291,10 @@ int kauditd_thread(void *dummy) set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&kauditd_wait, &wait); - if (!skb_queue_len(&audit_skb_queue)) + if (!skb_queue_len(&audit_skb_queue)) { + try_to_freeze(); schedule(); + } __set_current_state(TASK_RUNNING); remove_wait_queue(&kauditd_wait, &wait); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d8a68509e72..685c25175d9 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -30,8 +30,8 @@ */ #include <linux/init.h> -#include <asm/atomic.h> #include <asm/types.h> +#include <asm/atomic.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mount.h> diff --git a/kernel/capability.c b/kernel/capability.c index 8986a37a67e..bfa3c92e16f 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -7,6 +7,7 @@ * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ +#include <linux/capability.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/security.h> diff --git a/kernel/compat.c b/kernel/compat.c index 102296e21ea..1867290c37e 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -514,6 +514,24 @@ static int put_compat_itimerspec(struct compat_itimerspec __user *dst, return 0; } +long compat_sys_timer_create(clockid_t which_clock, + struct compat_sigevent __user *timer_event_spec, + timer_t __user *created_timer_id) +{ + struct sigevent __user *event = NULL; + + if (timer_event_spec) { + struct sigevent kevent; + + event = compat_alloc_user_space(sizeof(*event)); + if (get_compat_sigevent(&kevent, timer_event_spec) || + copy_to_user(event, &kevent, sizeof(*event))) + return -EFAULT; + } + + return sys_timer_create(which_clock, event, created_timer_id); +} + long compat_sys_timer_settime(timer_t timer_id, int flags, struct compat_itimerspec __user *new, struct compat_itimerspec __user *old) @@ -649,8 +667,6 @@ int get_compat_sigevent(struct sigevent *event, ? -EFAULT : 0; } -/* timer_create is architecture specific because it needs sigevent conversion */ - long compat_get_bitmap(unsigned long *mask, compat_ulong_t __user *umask, unsigned long bitmap_size) { @@ -855,3 +871,31 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr) } #endif /* __ARCH_WANT_COMPAT_SYS_TIME */ + +#ifdef __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND +asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize) +{ + sigset_t newset; + compat_sigset_t newset32; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset32, unewset, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&newset, &newset32); + sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + spin_lock_irq(¤t->sighand->siglock); + current->saved_sigmask = current->blocked; + current->blocked = newset; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_thread_flag(TIF_RESTORE_SIGMASK); + return -ERESTARTNOHAND; +} +#endif /* __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND */ diff --git a/kernel/configs.c b/kernel/configs.c index 986f7af31e0..009e1ebdcb8 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -3,7 +3,7 @@ * Echo the kernel .config file used to build the kernel * * Copyright (C) 2002 Khalid Aziz <khalid_aziz@hp.com> - * Copyright (C) 2002 Randy Dunlap <rddunlap@osdl.org> + * Copyright (C) 2002 Randy Dunlap <rdunlap@xenotime.net> * Copyright (C) 2002 Al Stone <ahs3@fc.hp.com> * Copyright (C) 2002 Hewlett-Packard Company * diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7430640f981..fe2f71f92ae 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -39,6 +39,7 @@ #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> +#include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -54,7 +55,23 @@ #include <asm/atomic.h> #include <asm/semaphore.h> -#define CPUSET_SUPER_MAGIC 0x27e0eb +#define CPUSET_SUPER_MAGIC 0x27e0eb + +/* + * Tracks how many cpusets are currently defined in system. + * When there is only one cpuset (the root cpuset) we can + * short circuit some hooks. + */ +int number_of_cpusets __read_mostly; + +/* See "Frequency meter" comments, below. */ + +struct fmeter { + int cnt; /* unprocessed events count */ + int val; /* most recent output value */ + time_t time; /* clock (secs) when val computed */ + spinlock_t lock; /* guards read or write of above */ +}; struct cpuset { unsigned long flags; /* "unsigned long" so bitops work */ @@ -80,13 +97,16 @@ struct cpuset { * Copy of global cpuset_mems_generation as of the most * recent time this cpuset changed its mems_allowed. */ - int mems_generation; + int mems_generation; + + struct fmeter fmeter; /* memory_pressure filter */ }; /* bits in struct cpuset flags field */ typedef enum { CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, + CS_MEMORY_MIGRATE, CS_REMOVED, CS_NOTIFY_ON_RELEASE } cpuset_flagbits_t; @@ -112,6 +132,11 @@ static inline int notify_on_release(const struct cpuset *cs) return !!test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags); } +static inline int is_memory_migrate(const struct cpuset *cs) +{ + return !!test_bit(CS_MEMORY_MIGRATE, &cs->flags); +} + /* * Increment this atomic integer everytime any cpuset changes its * mems_allowed value. Users of cpusets can track this generation @@ -137,13 +162,10 @@ static struct cpuset top_cpuset = { .count = ATOMIC_INIT(0), .sibling = LIST_HEAD_INIT(top_cpuset.sibling), .children = LIST_HEAD_INIT(top_cpuset.children), - .parent = NULL, - .dentry = NULL, - .mems_generation = 0, }; static struct vfsmount *cpuset_mount; -static struct super_block *cpuset_sb = NULL; +static struct super_block *cpuset_sb; /* * We have two global cpuset semaphores below. They can nest. @@ -227,6 +249,11 @@ static struct super_block *cpuset_sb = NULL; * a tasks cpuset pointer we use task_lock(), which acts on a spinlock * (task->alloc_lock) already in the task_struct routinely used for * such matters. + * + * P.S. One more locking exception. RCU is used to guard the + * update of a tasks cpuset pointer by attach_task() and the + * access of task->cpuset->mems_generation via that pointer in + * the routine cpuset_update_task_memory_state(). */ static DECLARE_MUTEX(manage_sem); @@ -304,7 +331,7 @@ static void cpuset_d_remove_dir(struct dentry *dentry) spin_lock(&dcache_lock); node = dentry->d_subdirs.next; while (node != &dentry->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_child); + struct dentry *d = list_entry(node, struct dentry, d_u.d_child); list_del_init(node); if (d->d_inode) { d = dget_locked(d); @@ -316,7 +343,7 @@ static void cpuset_d_remove_dir(struct dentry *dentry) } node = dentry->d_subdirs.next; } - list_del_init(&dentry->d_child); + list_del_init(&dentry->d_u.d_child); spin_unlock(&dcache_lock); remove_dir(dentry); } @@ -570,20 +597,43 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) BUG_ON(!nodes_intersects(*pmask, node_online_map)); } -/* - * Refresh current tasks mems_allowed and mems_generation from current - * tasks cpuset. +/** + * cpuset_update_task_memory_state - update task memory placement + * + * If the current tasks cpusets mems_allowed changed behind our + * backs, update current->mems_allowed, mems_generation and task NUMA + * mempolicy to the new value. * - * Call without callback_sem or task_lock() held. May be called with - * or without manage_sem held. Will acquire task_lock() and might - * acquire callback_sem during call. + * Task mempolicy is updated by rebinding it relative to the + * current->cpuset if a task has its memory placement changed. + * Do not call this routine if in_interrupt(). * - * The task_lock() is required to dereference current->cpuset safely. - * Without it, we could pick up the pointer value of current->cpuset - * in one instruction, and then attach_task could give us a different - * cpuset, and then the cpuset we had could be removed and freed, - * and then on our next instruction, we could dereference a no longer - * valid cpuset pointer to get its mems_generation field. + * Call without callback_sem or task_lock() held. May be called + * with or without manage_sem held. Doesn't need task_lock to guard + * against another task changing a non-NULL cpuset pointer to NULL, + * as that is only done by a task on itself, and if the current task + * is here, it is not simultaneously in the exit code NULL'ing its + * cpuset pointer. This routine also might acquire callback_sem and + * current->mm->mmap_sem during call. + * + * Reading current->cpuset->mems_generation doesn't need task_lock + * to guard the current->cpuset derefence, because it is guarded + * from concurrent freeing of current->cpuset by attach_task(), + * using RCU. + * + * The rcu_dereference() is technically probably not needed, + * as I don't actually mind if I see a new cpuset pointer but + * an old value of mems_generation. However this really only + * matters on alpha systems using cpusets heavily. If I dropped + * that rcu_dereference(), it would save them a memory barrier. + * For all other arch's, rcu_dereference is a no-op anyway, and for + * alpha systems not using cpusets, another planned optimization, + * avoiding the rcu critical section for tasks in the root cpuset + * which is statically allocated, so can't vanish, will make this + * irrelevant. Better to use RCU as intended, than to engage in + * some cute trick to save a memory barrier that is impossible to + * test, for alpha systems using cpusets heavily, which might not + * even exist. * * This routine is needed to update the per-task mems_allowed data, * within the tasks context, when it is trying to allocate memory @@ -591,27 +641,31 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) * task has been modifying its cpuset. */ -static void refresh_mems(void) +void cpuset_update_task_memory_state() { int my_cpusets_mem_gen; + struct task_struct *tsk = current; + struct cpuset *cs; - task_lock(current); - my_cpusets_mem_gen = current->cpuset->mems_generation; - task_unlock(current); - - if (current->cpuset_mems_generation != my_cpusets_mem_gen) { - struct cpuset *cs; - nodemask_t oldmem = current->mems_allowed; + if (tsk->cpuset == &top_cpuset) { + /* Don't need rcu for top_cpuset. It's never freed. */ + my_cpusets_mem_gen = top_cpuset.mems_generation; + } else { + rcu_read_lock(); + cs = rcu_dereference(tsk->cpuset); + my_cpusets_mem_gen = cs->mems_generation; + rcu_read_unlock(); + } + if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) { down(&callback_sem); - task_lock(current); - cs = current->cpuset; - guarantee_online_mems(cs, ¤t->mems_allowed); - current->cpuset_mems_generation = cs->mems_generation; - task_unlock(current); + task_lock(tsk); + cs = tsk->cpuset; /* Maybe changed when task not locked */ + guarantee_online_mems(cs, &tsk->mems_allowed); + tsk->cpuset_mems_generation = cs->mems_generation; + task_unlock(tsk); up(&callback_sem); - if (!nodes_equal(oldmem, current->mems_allowed)) - numa_policy_rebind(&oldmem, ¤t->mems_allowed); + mpol_rebind_task(tsk, &tsk->mems_allowed); } } @@ -766,36 +820,150 @@ static int update_cpumask(struct cpuset *cs, char *buf) } /* + * Handle user request to change the 'mems' memory placement + * of a cpuset. Needs to validate the request, update the + * cpusets mems_allowed and mems_generation, and for each + * task in the cpuset, rebind any vma mempolicies and if + * the cpuset is marked 'memory_migrate', migrate the tasks + * pages to the new memory. + * * Call with manage_sem held. May take callback_sem during call. + * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, + * lock each such tasks mm->mmap_sem, scan its vma's and rebind + * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, char *buf) { struct cpuset trialcs; + nodemask_t oldmem; + struct task_struct *g, *p; + struct mm_struct **mmarray; + int i, n, ntasks; + int migrate; + int fudge; int retval; trialcs = *cs; retval = nodelist_parse(buf, trialcs.mems_allowed); if (retval < 0) - return retval; + goto done; nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map); - if (nodes_empty(trialcs.mems_allowed)) - return -ENOSPC; + oldmem = cs->mems_allowed; + if (nodes_equal(oldmem, trialcs.mems_allowed)) { + retval = 0; /* Too easy - nothing to do */ + goto done; + } + if (nodes_empty(trialcs.mems_allowed)) { + retval = -ENOSPC; + goto done; + } retval = validate_change(cs, &trialcs); - if (retval == 0) { - down(&callback_sem); - cs->mems_allowed = trialcs.mems_allowed; - atomic_inc(&cpuset_mems_generation); - cs->mems_generation = atomic_read(&cpuset_mems_generation); - up(&callback_sem); + if (retval < 0) + goto done; + + down(&callback_sem); + cs->mems_allowed = trialcs.mems_allowed; + atomic_inc(&cpuset_mems_generation); + cs->mems_generation = atomic_read(&cpuset_mems_generation); + up(&callback_sem); + + set_cpuset_being_rebound(cs); /* causes mpol_copy() rebind */ + + fudge = 10; /* spare mmarray[] slots */ + fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */ + retval = -ENOMEM; + + /* + * Allocate mmarray[] to hold mm reference for each task + * in cpuset cs. Can't kmalloc GFP_KERNEL while holding + * tasklist_lock. We could use GFP_ATOMIC, but with a + * few more lines of code, we can retry until we get a big + * enough mmarray[] w/o using GFP_ATOMIC. + */ + while (1) { + ntasks = atomic_read(&cs->count); /* guess */ + ntasks += fudge; + mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL); + if (!mmarray) + goto done; + write_lock_irq(&tasklist_lock); /* block fork */ + if (atomic_read(&cs->count) <= ntasks) + break; /* got enough */ + write_unlock_irq(&tasklist_lock); /* try again */ + kfree(mmarray); } + + n = 0; + + /* Load up mmarray[] with mm reference for each task in cpuset. */ + do_each_thread(g, p) { + struct mm_struct *mm; + + if (n >= ntasks) { + printk(KERN_WARNING + "Cpuset mempolicy rebind incomplete.\n"); + continue; + } + if (p->cpuset != cs) + continue; + mm = get_task_mm(p); + if (!mm) + continue; + mmarray[n++] = mm; + } while_each_thread(g, p); + write_unlock_irq(&tasklist_lock); + + /* + * Now that we've dropped the tasklist spinlock, we can + * rebind the vma mempolicies of each mm in mmarray[] to their + * new cpuset, and release that mm. The mpol_rebind_mm() + * call takes mmap_sem, which we couldn't take while holding + * tasklist_lock. Forks can happen again now - the mpol_copy() + * cpuset_being_rebound check will catch such forks, and rebind + * their vma mempolicies too. Because we still hold the global + * cpuset manage_sem, we know that no other rebind effort will + * be contending for the global variable cpuset_being_rebound. + * It's ok if we rebind the same mm twice; mpol_rebind_mm() + * is idempotent. Also migrate pages in each mm to new nodes. + */ + migrate = is_memory_migrate(cs); + for (i = 0; i < n; i++) { + struct mm_struct *mm = mmarray[i]; + + mpol_rebind_mm(mm, &cs->mems_allowed); + if (migrate) { + do_migrate_pages(mm, &oldmem, &cs->mems_allowed, + MPOL_MF_MOVE_ALL); + } + mmput(mm); + } + + /* We're done rebinding vma's to this cpusets new mems_allowed. */ + kfree(mmarray); + set_cpuset_being_rebound(NULL); + retval = 0; +done: return retval; } /* + * Call with manage_sem held. + */ + +static int update_memory_pressure_enabled(struct cpuset *cs, char *buf) +{ + if (simple_strtoul(buf, NULL, 10) != 0) + cpuset_memory_pressure_enabled = 1; + else + cpuset_memory_pressure_enabled = 0; + return 0; +} + +/* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, - * CS_NOTIFY_ON_RELEASE) + * CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE) * cs: the cpuset to update * buf: the buffer where we read the 0 or 1 * @@ -834,6 +1002,104 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) } /* + * Frequency meter - How fast is some event occuring? + * + * These routines manage a digitally filtered, constant time based, + * event frequency meter. There are four routines: + * fmeter_init() - initialize a frequency meter. + * fmeter_markevent() - called each time the event happens. + * fmeter_getrate() - returns the recent rate of such events. + * fmeter_update() - internal routine used to update fmeter. + * + * A common data structure is passed to each of these routines, + * which is used to keep track of the state required to manage the + * frequency meter and its digital filter. + * + * The filter works on the number of events marked per unit time. + * The filter is single-pole low-pass recursive (IIR). The time unit + * is 1 second. Arithmetic is done using 32-bit integers scaled to + * simulate 3 decimal digits of precision (multiplied by 1000). + * + * With an FM_COEF of 933, and a time base of 1 second, the filter + * has a half-life of 10 seconds, meaning that if the events quit + * happening, then the rate returned from the fmeter_getrate() + * will be cut in half each 10 seconds, until it converges to zero. + * + * It is not worth doing a real infinitely recursive filter. If more + * than FM_MAXTICKS ticks have elapsed since the last filter event, + * just compute FM_MAXTICKS ticks worth, by which point the level + * will be stable. + * + * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid + * arithmetic overflow in the fmeter_update() routine. + * + * Given the simple 32 bit integer arithmetic used, this meter works + * best for reporting rates between one per millisecond (msec) and + * one per 32 (approx) seconds. At constant rates faster than one + * per msec it maxes out at values just under 1,000,000. At constant + * rates between one per msec, and one per second it will stabilize + * to a value N*1000, where N is the rate of events per second. + * At constant rates between one per second and one per 32 seconds, + * it will be choppy, moving up on the seconds that have an event, + * and then decaying until the next event. At rates slower than + * about one in 32 seconds, it decays all the way back to zero between + * each event. + */ + +#define FM_COEF 933 /* coefficient for half-life of 10 secs */ +#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */ +#define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ +#define FM_SCALE 1000 /* faux fixed point scale */ + +/* Initialize a frequency meter */ +static void fmeter_init(struct fmeter *fmp) +{ + fmp->cnt = 0; + fmp->val = 0; + fmp->time = 0; + spin_lock_init(&fmp->lock); +} + +/* Internal meter update - process cnt events and update value */ +static void fmeter_update(struct fmeter *fmp) +{ + time_t now = get_seconds(); + time_t ticks = now - fmp->time; + + if (ticks == 0) + return; + + ticks = min(FM_MAXTICKS, ticks); + while (ticks-- > 0) + fmp->val = (FM_COEF * fmp->val) / FM_SCALE; + fmp->time = now; + + fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; + fmp->cnt = 0; +} + +/* Process any previous ticks, then bump cnt by one (times scale). */ +static void fmeter_markevent(struct fmeter *fmp) +{ + spin_lock(&fmp->lock); + fmeter_update(fmp); + fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); + spin_unlock(&fmp->lock); +} + +/* Process any previous ticks, then return current value. */ +static int fmeter_getrate(struct fmeter *fmp) +{ + int val; + + spin_lock(&fmp->lock); + fmeter_update(fmp); + val = fmp->val; + spin_unlock(&fmp->lock); + return val; +} + +/* * Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly * writing the path of the old cpuset in 'ppathbuf' if it needs to be * notified on release. @@ -848,6 +1114,8 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) struct task_struct *tsk; struct cpuset *oldcs; cpumask_t cpus; + nodemask_t from, to; + struct mm_struct *mm; if (sscanf(pidbuf, "%d", &pid) != 1) return -EIO; @@ -887,14 +1155,27 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) return -ESRCH; } atomic_inc(&cs->count); - tsk->cpuset = cs; + rcu_assign_pointer(tsk->cpuset, cs); task_unlock(tsk); guarantee_online_cpus(cs, &cpus); set_cpus_allowed(tsk, cpus); + from = oldcs->mems_allowed; + to = cs->mems_allowed; + up(&callback_sem); + + mm = get_task_mm(tsk); + if (mm) { + mpol_rebind_mm(mm, &to); + mmput(mm); + } + + if (is_memory_migrate(cs)) + do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL); put_task_struct(tsk); + synchronize_rcu(); if (atomic_dec_and_test(&oldcs->count)) check_for_release(oldcs, ppathbuf); return 0; @@ -905,11 +1186,14 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) typedef enum { FILE_ROOT, FILE_DIR, + FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_NOTIFY_ON_RELEASE, + FILE_MEMORY_PRESSURE_ENABLED, + FILE_MEMORY_PRESSURE, FILE_TASKLIST, } cpuset_filetype_t; @@ -960,6 +1244,15 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us case FILE_NOTIFY_ON_RELEASE: retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer); break; + case FILE_MEMORY_MIGRATE: + retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer); + break; + case FILE_MEMORY_PRESSURE_ENABLED: + retval = update_memory_pressure_enabled(cs, buffer); + break; + case FILE_MEMORY_PRESSURE: + retval = -EACCES; + break; case FILE_TASKLIST: retval = attach_task(cs, buffer, &pathbuf); break; @@ -1060,6 +1353,15 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf, case FILE_NOTIFY_ON_RELEASE: *s++ = notify_on_release(cs) ? '1' : '0'; break; + case FILE_MEMORY_MIGRATE: + *s++ = is_memory_migrate(cs) ? '1' : '0'; + break; + case FILE_MEMORY_PRESSURE_ENABLED: + *s++ = cpuset_memory_pressure_enabled ? '1' : '0'; + break; + case FILE_MEMORY_PRESSURE: + s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter)); + break; default: retval = -EINVAL; goto out; @@ -1178,7 +1480,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode) /* * cpuset_create_dir - create a directory for an object. - * cs: the cpuset we create the directory for. + * cs: the cpuset we create the directory for. * It must have a valid ->parent field * And we are going to fill its ->dentry field. * name: The name to give to the cpuset directory. Will be copied. @@ -1211,7 +1513,7 @@ static int cpuset_add_file(struct dentry *dir, const struct cftype *cft) struct dentry *dentry; int error; - down(&dir->d_inode->i_sem); + mutex_lock(&dir->d_inode->i_mutex); dentry = cpuset_get_dentry(dir, cft->name); if (!IS_ERR(dentry)) { error = cpuset_create_file(dentry, 0644 | S_IFREG); @@ -1220,7 +1522,7 @@ static int cpuset_add_file(struct dentry *dir, const struct cftype *cft) dput(dentry); } else error = PTR_ERR(dentry); - up(&dir->d_inode->i_sem); + mutex_unlock(&dir->d_inode->i_mutex); return error; } @@ -1252,7 +1554,7 @@ struct ctr_struct { * when reading out p->cpuset, as we don't really care if it changes * on the next cycle, and we are not going to try to dereference it. */ -static inline int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs) +static int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs) { int n = 0; struct task_struct *g, *p; @@ -1408,6 +1710,21 @@ static struct cftype cft_notify_on_release = { .private = FILE_NOTIFY_ON_RELEASE, }; +static struct cftype cft_memory_migrate = { + .name = "memory_migrate", + .private = FILE_MEMORY_MIGRATE, +}; + +static struct cftype cft_memory_pressure_enabled = { + .name = "memory_pressure_enabled", + .private = FILE_MEMORY_PRESSURE_ENABLED, +}; + +static struct cftype cft_memory_pressure = { + .name = "memory_pressure", + .private = FILE_MEMORY_PRESSURE, +}; + static int cpuset_populate_dir(struct dentry *cs_dentry) { int err; @@ -1422,6 +1739,10 @@ static int cpuset_populate_dir(struct dentry *cs_dentry) return err; if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0) return err; + if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0) + return err; if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0) return err; return 0; @@ -1446,7 +1767,7 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode) return -ENOMEM; down(&manage_sem); - refresh_mems(); + cpuset_update_task_memory_state(); cs->flags = 0; if (notify_on_release(parent)) set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags); @@ -1457,11 +1778,13 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode) INIT_LIST_HEAD(&cs->children); atomic_inc(&cpuset_mems_generation); cs->mems_generation = atomic_read(&cpuset_mems_generation); + fmeter_init(&cs->fmeter); cs->parent = parent; down(&callback_sem); list_add(&cs->sibling, &cs->parent->children); + number_of_cpusets++; up(&callback_sem); err = cpuset_create_dir(cs, name, mode); @@ -1470,7 +1793,7 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode) /* * Release manage_sem before cpuset_populate_dir() because it - * will down() this new directory's i_sem and if we race with + * will down() this new directory's i_mutex and if we race with * another mkdir, we might deadlock. */ up(&manage_sem); @@ -1489,7 +1812,7 @@ static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode) { struct cpuset *c_parent = dentry->d_parent->d_fsdata; - /* the vfs holds inode->i_sem already */ + /* the vfs holds inode->i_mutex already */ return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR); } @@ -1500,10 +1823,10 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cpuset *parent; char *pathbuf = NULL; - /* the vfs holds both inode->i_sem already */ + /* the vfs holds both inode->i_mutex already */ down(&manage_sem); - refresh_mems(); + cpuset_update_task_memory_state(); if (atomic_read(&cs->count) > 0) { up(&manage_sem); return -EBUSY; @@ -1524,6 +1847,7 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) spin_unlock(&d->d_lock); cpuset_d_remove_dir(d); dput(d); + number_of_cpusets--; up(&callback_sem); if (list_empty(&parent->children)) check_for_release(parent, &pathbuf); @@ -1532,6 +1856,21 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) return 0; } +/* + * cpuset_init_early - just enough so that the calls to + * cpuset_update_task_memory_state() in early init code + * are harmless. + */ + +int __init cpuset_init_early(void) +{ + struct task_struct *tsk = current; + + tsk->cpuset = &top_cpuset; + tsk->cpuset->mems_generation = atomic_read(&cpuset_mems_generation); + return 0; +} + /** * cpuset_init - initialize cpusets at system boot * @@ -1546,6 +1885,7 @@ int __init cpuset_init(void) top_cpuset.cpus_allowed = CPU_MASK_ALL; top_cpuset.mems_allowed = NODE_MASK_ALL; + fmeter_init(&top_cpuset.fmeter); atomic_inc(&cpuset_mems_generation); top_cpuset.mems_generation = atomic_read(&cpuset_mems_generation); @@ -1566,7 +1906,11 @@ int __init cpuset_init(void) root->d_inode->i_nlink++; top_cpuset.dentry = root; root->d_inode->i_op = &cpuset_dir_inode_operations; + number_of_cpusets = 1; err = cpuset_populate_dir(root); + /* memory_pressure_enabled is in root cpuset only */ + if (err == 0) + err = cpuset_add_file(root, &cft_memory_pressure_enabled); out: return err; } @@ -1632,15 +1976,13 @@ void cpuset_fork(struct task_struct *child) * * We don't need to task_lock() this reference to tsk->cpuset, * because tsk is already marked PF_EXITING, so attach_task() won't - * mess with it. + * mess with it, or task is a failed fork, never visible to attach_task. **/ void cpuset_exit(struct task_struct *tsk) { struct cpuset *cs; - BUG_ON(!(tsk->flags & PF_EXITING)); - cs = tsk->cpuset; tsk->cpuset = NULL; @@ -1667,14 +2009,14 @@ void cpuset_exit(struct task_struct *tsk) * tasks cpuset. **/ -cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk) +cpumask_t cpuset_cpus_allowed(struct task_struct *tsk) { cpumask_t mask; down(&callback_sem); - task_lock((struct task_struct *)tsk); + task_lock(tsk); guarantee_online_cpus(tsk->cpuset, &mask); - task_unlock((struct task_struct *)tsk); + task_unlock(tsk); up(&callback_sem); return mask; @@ -1686,43 +2028,26 @@ void cpuset_init_current_mems_allowed(void) } /** - * cpuset_update_current_mems_allowed - update mems parameters to new values - * - * If the current tasks cpusets mems_allowed changed behind our backs, - * update current->mems_allowed and mems_generation to the new value. - * Do not call this routine if in_interrupt(). + * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * - * Call without callback_sem or task_lock() held. May be called - * with or without manage_sem held. Unless exiting, it will acquire - * task_lock(). Also might acquire callback_sem during call to - * refresh_mems(). - */ + * Description: Returns the nodemask_t mems_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of node_online_map, even if this means going outside the + * tasks cpuset. + **/ -void cpuset_update_current_mems_allowed(void) +nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { - struct cpuset *cs; - int need_to_refresh = 0; + nodemask_t mask; - task_lock(current); - cs = current->cpuset; - if (!cs) - goto done; - if (current->cpuset_mems_generation != cs->mems_generation) - need_to_refresh = 1; -done: - task_unlock(current); - if (need_to_refresh) - refresh_mems(); -} + down(&callback_sem); + task_lock(tsk); + guarantee_online_mems(tsk->cpuset, &mask); + task_unlock(tsk); + up(&callback_sem); -/** - * cpuset_restrict_to_mems_allowed - limit nodes to current mems_allowed - * @nodes: pointer to a node bitmap that is and-ed with mems_allowed - */ -void cpuset_restrict_to_mems_allowed(unsigned long *nodes) -{ - bitmap_and(nodes, nodes, nodes_addr(current->mems_allowed), - MAX_NUMNODES); + return mask; } /** @@ -1795,7 +2120,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs) * GFP_USER - only nodes in current tasks mems allowed ok. **/ -int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) +int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { int node; /* node that zone z is on */ const struct cpuset *cs; /* current cpuset ancestors */ @@ -1825,6 +2150,33 @@ int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) } /** + * cpuset_lock - lock out any changes to cpuset structures + * + * The out of memory (oom) code needs to lock down cpusets + * from being changed while it scans the tasklist looking for a + * task in an overlapping cpuset. Expose callback_sem via this + * cpuset_lock() routine, so the oom code can lock it, before + * locking the task list. The tasklist_lock is a spinlock, so + * must be taken inside callback_sem. + */ + +void cpuset_lock(void) +{ + down(&callback_sem); +} + +/** + * cpuset_unlock - release lock on cpuset changes + * + * Undo the lock taken in a previous cpuset_lock() call. + */ + +void cpuset_unlock(void) +{ + up(&callback_sem); +} + +/** * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors? * @p: pointer to task_struct of some other task. * @@ -1833,7 +2185,7 @@ int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) * determine if task @p's memory usage might impact the memory * available to the current task. * - * Acquires callback_sem - not suitable for calling from a fast path. + * Call while holding callback_sem. **/ int cpuset_excl_nodes_overlap(const struct task_struct *p) @@ -1841,8 +2193,6 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p) const struct cpuset *cs1, *cs2; /* my and p's cpuset ancestors */ int overlap = 0; /* do cpusets overlap? */ - down(&callback_sem); - task_lock(current); if (current->flags & PF_EXITING) { task_unlock(current); @@ -1861,12 +2211,46 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p) overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed); done: - up(&callback_sem); - return overlap; } /* + * Collection of memory_pressure is suppressed unless + * this flag is enabled by writing "1" to the special + * cpuset file 'memory_pressure_enabled' in the root cpuset. + */ + +int cpuset_memory_pressure_enabled __read_mostly; + +/** + * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. + * + * Keep a running average of the rate of synchronous (direct) + * page reclaim efforts initiated by tasks in each cpuset. + * + * This represents the rate at which some task in the cpuset + * ran low on memory on all nodes it was allowed to use, and + * had to enter the kernels page reclaim code in an effort to + * create more free memory by tossing clean pages or swapping + * or writing dirty pages. + * + * Display to user space in the per-cpuset read-only file + * "memory_pressure". Value displayed is an integer + * representing the recent rate of entry into the synchronous + * (direct) page reclaim by any task attached to the cpuset. + **/ + +void __cpuset_memory_pressure_bump(void) +{ + struct cpuset *cs; + + task_lock(current); + cs = current->cpuset; + fmeter_markevent(&cs->fmeter); + task_unlock(current); +} + +/* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c deleted file mode 100644 index 334c37f5218..00000000000 --- a/kernel/crash_dump.c +++ /dev/null @@ -1,61 +0,0 @@ -/* - * kernel/crash_dump.c - Memory preserving reboot related code. - * - * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) - * Copyright (C) IBM Corporation, 2004. All rights reserved - */ - -#include <linux/smp_lock.h> -#include <linux/errno.h> -#include <linux/proc_fs.h> -#include <linux/bootmem.h> -#include <linux/highmem.h> -#include <linux/crash_dump.h> - -#include <asm/io.h> -#include <asm/uaccess.h> - -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; - -/** - * copy_oldmem_page - copy one page from "oldmem" - * @pfn: page frame number to be copied - * @buf: target memory address for the copy; this can be in kernel address - * space or user address space (see @userbuf) - * @csize: number of bytes to copy - * @offset: offset in bytes into the page (based on pfn) to begin the copy - * @userbuf: if set, @buf is in user address space, use copy_to_user(), - * otherwise @buf is in kernel address space, use memcpy(). - * - * Copy a page from "oldmem". For this page, there is no pte mapped - * in the current kernel. We stitch up a pte, similar to kmap_atomic. - */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) -{ - void *page, *vaddr; - - if (!csize) - return 0; - - page = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!page) - return -ENOMEM; - - vaddr = kmap_atomic_pfn(pfn, KM_PTE0); - copy_page(page, vaddr); - kunmap_atomic(vaddr, KM_PTE0); - - if (userbuf) { - if (copy_to_user(buf, (page + offset), csize)) { - kfree(page); - return -EFAULT; - } - } else { - memcpy(buf, (page + offset), csize); - } - - kfree(page); - return csize; -} diff --git a/kernel/exit.c b/kernel/exit.c index ee515683b92..93cee367133 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -10,6 +10,7 @@ #include <linux/interrupt.h> #include <linux/smp_lock.h> #include <linux/module.h> +#include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> @@ -29,6 +30,7 @@ #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/cn_proc.h> +#include <linux/mutex.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -72,7 +74,6 @@ repeat: __ptrace_unlink(p); BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); __exit_signal(p); - __exit_sighand(p); /* * Note that the fastpath in sys_times depends on __exit_signal having * updated the counters before a task is removed from the tasklist of @@ -192,7 +193,7 @@ int is_orphaned_pgrp(int pgrp) return retval; } -static inline int has_stopped_jobs(int pgrp) +static int has_stopped_jobs(int pgrp) { int retval = 0; struct task_struct *p; @@ -229,7 +230,7 @@ static inline int has_stopped_jobs(int pgrp) * * NOTE that reparent_to_init() gives the caller full capabilities. */ -static inline void reparent_to_init(void) +static void reparent_to_init(void) { write_lock_irq(&tasklist_lock); @@ -243,7 +244,9 @@ static inline void reparent_to_init(void) /* Set the exit signal to SIGCHLD so we signal init on exit */ current->exit_signal = SIGCHLD; - if ((current->policy == SCHED_NORMAL) && (task_nice(current) < 0)) + if ((current->policy == SCHED_NORMAL || + current->policy == SCHED_BATCH) + && (task_nice(current) < 0)) set_user_nice(current, 0); /* cpus_allowed? */ /* rt_priority? */ @@ -258,7 +261,7 @@ static inline void reparent_to_init(void) void __set_special_pids(pid_t session, pid_t pgrp) { - struct task_struct *curr = current; + struct task_struct *curr = current->group_leader; if (curr->signal->session != session) { detach_pid(curr, PIDTYPE_SID); @@ -366,7 +369,7 @@ void daemonize(const char *name, ...) EXPORT_SYMBOL(daemonize); -static inline void close_files(struct files_struct * files) +static void close_files(struct files_struct * files) { int i, j; struct fdtable *fdt; @@ -540,7 +543,7 @@ static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_re p->real_parent = reaper; } -static inline void reparent_thread(task_t *p, task_t *father, int traced) +static void reparent_thread(task_t *p, task_t *father, int traced) { /* We don't want people slaying init. */ if (p->exit_signal != -1) @@ -604,7 +607,7 @@ static inline void reparent_thread(task_t *p, task_t *father, int traced) * group, and if no such member exists, give it to * the global child reaper process (ie "init") */ -static inline void forget_original_parent(struct task_struct * father, +static void forget_original_parent(struct task_struct * father, struct list_head *to_release) { struct task_struct *p, *reaper = father; @@ -842,7 +845,7 @@ fastcall NORET_TYPE void do_exit(long code) } group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { - del_timer_sync(&tsk->signal->real_timer); + hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); acct_process(code); } @@ -870,6 +873,10 @@ fastcall NORET_TYPE void do_exit(long code) mpol_free(tsk->mempolicy); tsk->mempolicy = NULL; #endif + /* + * If DEBUG_MUTEXES is on, make sure we are holding no locks: + */ + mutex_debug_check_no_locks_held(tsk); /* PF_DEAD causes final put_task_struct after we schedule. */ preempt_disable(); @@ -926,7 +933,6 @@ do_group_exit(int exit_code) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { - sig->flags = SIGNAL_GROUP_EXIT; sig->group_exit_code = exit_code; zap_other_threads(current); } @@ -1068,6 +1074,9 @@ static int wait_task_zombie(task_t *p, int noreap, } if (likely(p->real_parent == p->parent) && likely(p->signal)) { + struct signal_struct *psig; + struct signal_struct *sig; + /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group @@ -1084,24 +1093,26 @@ static int wait_task_zombie(task_t *p, int noreap, * here reaping other children at the same time. */ spin_lock_irq(&p->parent->sighand->siglock); - p->parent->signal->cutime = - cputime_add(p->parent->signal->cutime, + psig = p->parent->signal; + sig = p->signal; + psig->cutime = + cputime_add(psig->cutime, cputime_add(p->utime, - cputime_add(p->signal->utime, - p->signal->cutime))); - p->parent->signal->cstime = - cputime_add(p->parent->signal->cstime, + cputime_add(sig->utime, + sig->cutime))); + psig->cstime = + cputime_add(psig->cstime, cputime_add(p->stime, - cputime_add(p->signal->stime, - p->signal->cstime))); - p->parent->signal->cmin_flt += - p->min_flt + p->signal->min_flt + p->signal->cmin_flt; - p->parent->signal->cmaj_flt += - p->maj_flt + p->signal->maj_flt + p->signal->cmaj_flt; - p->parent->signal->cnvcsw += - p->nvcsw + p->signal->nvcsw + p->signal->cnvcsw; - p->parent->signal->cnivcsw += - p->nivcsw + p->signal->nivcsw + p->signal->cnivcsw; + cputime_add(sig->stime, + sig->cstime))); + psig->cmin_flt += + p->min_flt + sig->min_flt + sig->cmin_flt; + psig->cmaj_flt += + p->maj_flt + sig->maj_flt + sig->cmaj_flt; + psig->cnvcsw += + p->nvcsw + sig->nvcsw + sig->cnvcsw; + psig->cnivcsw += + p->nivcsw + sig->nivcsw + sig->cnivcsw; spin_unlock_irq(&p->parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index fb8572a4229..4ae8cfc1c89 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,7 @@ #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/fs.h> +#include <linux/capability.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/security.h> @@ -743,6 +744,14 @@ int unshare_files(void) EXPORT_SYMBOL(unshare_files); +void sighand_free_cb(struct rcu_head *rhp) +{ + struct sighand_struct *sp; + + sp = container_of(rhp, struct sighand_struct, rcu); + kmem_cache_free(sighand_cachep, sp); +} + static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk) { struct sighand_struct *sig; @@ -752,7 +761,7 @@ static inline int copy_sighand(unsigned long clone_flags, struct task_struct * t return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - tsk->sighand = sig; + rcu_assign_pointer(tsk->sighand, sig); if (!sig) return -ENOMEM; spin_lock_init(&sig->siglock); @@ -793,19 +802,16 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); - sig->it_real_value = sig->it_real_incr = 0; + hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC); + sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->real_timer.data = (unsigned long) tsk; - init_timer(&sig->real_timer); + sig->real_timer.data = tsk; sig->it_virt_expires = cputime_zero; sig->it_virt_incr = cputime_zero; sig->it_prof_expires = cputime_zero; sig->it_prof_incr = cputime_zero; - sig->tty = current->signal->tty; - sig->pgrp = process_group(current); - sig->session = current->signal->session; sig->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = 0; @@ -964,15 +970,20 @@ static task_t *copy_process(unsigned long clone_flags, p->io_context = NULL; p->io_wait = NULL; p->audit_context = NULL; + cpuset_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_copy(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; - goto bad_fork_cleanup; + goto bad_fork_cleanup_cpuset; } #endif +#ifdef CONFIG_DEBUG_MUTEXES + p->blocked_on = NULL; /* not blocked yet */ +#endif + p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; @@ -1127,25 +1138,19 @@ static task_t *copy_process(unsigned long clone_flags, attach_pid(p, PIDTYPE_PID, p->pid); attach_pid(p, PIDTYPE_TGID, p->tgid); if (thread_group_leader(p)) { + p->signal->tty = current->signal->tty; + p->signal->pgrp = process_group(current); + p->signal->session = current->signal->session; attach_pid(p, PIDTYPE_PGID, process_group(p)); attach_pid(p, PIDTYPE_SID, p->signal->session); if (p->pid) __get_cpu_var(process_counts)++; } - if (!current->signal->tty && p->signal->tty) - p->signal->tty = NULL; - nr_threads++; total_forks++; write_unlock_irq(&tasklist_lock); proc_fork_connector(p); - cpuset_fork(p); - retval = 0; - -fork_out: - if (retval) - return ERR_PTR(retval); return p; bad_fork_cleanup_namespace: @@ -1172,7 +1177,9 @@ bad_fork_cleanup_security: bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_free(p->mempolicy); +bad_fork_cleanup_cpuset: #endif + cpuset_exit(p); bad_fork_cleanup: if (p->binfmt) module_put(p->binfmt->module); @@ -1184,7 +1191,8 @@ bad_fork_cleanup_count: free_uid(p->user); bad_fork_free: free_task(p); - goto fork_out; +fork_out: + return ERR_PTR(retval); } struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) @@ -1290,6 +1298,10 @@ long do_fork(unsigned long clone_flags, return pid; } +#ifndef ARCH_MIN_MMSTRUCT_ALIGN +#define ARCH_MIN_MMSTRUCT_ALIGN 0 +#endif + void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", @@ -1308,6 +1320,6 @@ void __init proc_caches_init(void) sizeof(struct vm_area_struct), 0, SLAB_PANIC, NULL, NULL); mm_cachep = kmem_cache_create("mm_struct", - sizeof(struct mm_struct), 0, + sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); } diff --git a/kernel/futex.c b/kernel/futex.c index 5872e3507f3..5efa2f97803 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -270,7 +270,13 @@ static void wake_futex(struct futex_q *q) /* * The waiting task can free the futex_q as soon as this is written, * without taking any locks. This must come last. + * + * A memory barrier is required here to prevent the following store + * to lock_ptr from getting ahead of the wakeup. Clearing the lock + * at the end of wake_up_all() does not prevent this store from + * moving. */ + wmb(); q->lock_ptr = NULL; } @@ -350,6 +356,13 @@ retry: if (bh1 != bh2) spin_unlock(&bh2->lock); +#ifndef CONFIG_MMU + /* we don't get EFAULT from MMU faults if we don't have an MMU, + * but we might get them from range checking */ + ret = op_ret; + goto out; +#endif + if (unlikely(op_ret != -EFAULT)) { ret = op_ret; goto out; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c new file mode 100644 index 00000000000..f1c4155b49a --- /dev/null +++ b/kernel/hrtimer.c @@ -0,0 +1,826 @@ +/* + * linux/kernel/hrtimer.c + * + * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> + * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar + * + * High-resolution kernel timers + * + * In contrast to the low-resolution timeout API implemented in + * kernel/timer.c, hrtimers provide finer resolution and accuracy + * depending on system configuration and capabilities. + * + * These timers are currently used for: + * - itimers + * - POSIX timers + * - nanosleep + * - precise in-kernel timing + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * Credits: + * based on kernel/timer.c + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/cpu.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/hrtimer.h> +#include <linux/notifier.h> +#include <linux/syscalls.h> +#include <linux/interrupt.h> + +#include <asm/uaccess.h> + +/** + * ktime_get - get the monotonic time in ktime_t format + * + * returns the time in ktime_t format + */ +static ktime_t ktime_get(void) +{ + struct timespec now; + + ktime_get_ts(&now); + + return timespec_to_ktime(now); +} + +/** + * ktime_get_real - get the real (wall-) time in ktime_t format + * + * returns the time in ktime_t format + */ +static ktime_t ktime_get_real(void) +{ + struct timespec now; + + getnstimeofday(&now); + + return timespec_to_ktime(now); +} + +EXPORT_SYMBOL_GPL(ktime_get_real); + +/* + * The timer bases: + */ + +#define MAX_HRTIMER_BASES 2 + +static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) = +{ + { + .index = CLOCK_REALTIME, + .get_time = &ktime_get_real, + .resolution = KTIME_REALTIME_RES, + }, + { + .index = CLOCK_MONOTONIC, + .get_time = &ktime_get, + .resolution = KTIME_MONOTONIC_RES, + }, +}; + +/** + * ktime_get_ts - get the monotonic clock in timespec format + * + * @ts: pointer to timespec variable + * + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by ts. + */ +void ktime_get_ts(struct timespec *ts) +{ + struct timespec tomono; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + getnstimeofday(ts); + tomono = wall_to_monotonic; + + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, + ts->tv_nsec + tomono.tv_nsec); +} +EXPORT_SYMBOL_GPL(ktime_get_ts); + +/* + * Functions and macros which are different for UP/SMP systems are kept in a + * single place + */ +#ifdef CONFIG_SMP + +#define set_curr_timer(b, t) do { (b)->curr_timer = (t); } while (0) + +/* + * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock + * means that all timers which are tied to this base via timer->base are + * locked, and the base itself is locked too. + * + * So __run_timers/migrate_timers can safely modify all timers which could + * be found on the lists/queues. + * + * When the timer's base is locked, and the timer removed from list, it is + * possible to set timer->base = NULL and drop the lock: the timer remains + * locked. + */ +static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer, + unsigned long *flags) +{ + struct hrtimer_base *base; + + for (;;) { + base = timer->base; + if (likely(base != NULL)) { + spin_lock_irqsave(&base->lock, *flags); + if (likely(base == timer->base)) + return base; + /* The timer has migrated to another CPU: */ + spin_unlock_irqrestore(&base->lock, *flags); + } + cpu_relax(); + } +} + +/* + * Switch the timer base to the current CPU when possible. + */ +static inline struct hrtimer_base * +switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base) +{ + struct hrtimer_base *new_base; + + new_base = &__get_cpu_var(hrtimer_bases[base->index]); + + if (base != new_base) { + /* + * We are trying to schedule the timer on the local CPU. + * However we can't change timer's base while it is running, + * so we keep it on the same CPU. No hassle vs. reprogramming + * the event source in the high resolution case. The softirq + * code will take care of this when the timer function has + * completed. There is no conflict as we hold the lock until + * the timer is enqueued. + */ + if (unlikely(base->curr_timer == timer)) + return base; + + /* See the comment in lock_timer_base() */ + timer->base = NULL; + spin_unlock(&base->lock); + spin_lock(&new_base->lock); + timer->base = new_base; + } + return new_base; +} + +#else /* CONFIG_SMP */ + +#define set_curr_timer(b, t) do { } while (0) + +static inline struct hrtimer_base * +lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + struct hrtimer_base *base = timer->base; + + spin_lock_irqsave(&base->lock, *flags); + + return base; +} + +#define switch_hrtimer_base(t, b) (b) + +#endif /* !CONFIG_SMP */ + +/* + * Functions for the union type storage format of ktime_t which are + * too large for inlining: + */ +#if BITS_PER_LONG < 64 +# ifndef CONFIG_KTIME_SCALAR +/** + * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable + * + * @kt: addend + * @nsec: the scalar nsec value to add + * + * Returns the sum of kt and nsec in ktime_t format + */ +ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) +{ + ktime_t tmp; + + if (likely(nsec < NSEC_PER_SEC)) { + tmp.tv64 = nsec; + } else { + unsigned long rem = do_div(nsec, NSEC_PER_SEC); + + tmp = ktime_set((long)nsec, rem); + } + + return ktime_add(kt, tmp); +} + +#else /* CONFIG_KTIME_SCALAR */ + +# endif /* !CONFIG_KTIME_SCALAR */ + +/* + * Divide a ktime value by a nanosecond value + */ +static unsigned long ktime_divns(const ktime_t kt, nsec_t div) +{ + u64 dclc, inc, dns; + int sft = 0; + + dclc = dns = ktime_to_ns(kt); + inc = div; + /* Make sure the divisor is less than 2^32: */ + while (div >> 32) { + sft++; + div >>= 1; + } + dclc >>= sft; + do_div(dclc, (unsigned long) div); + + return (unsigned long) dclc; +} + +#else /* BITS_PER_LONG < 64 */ +# define ktime_divns(kt, div) (unsigned long)((kt).tv64 / (div)) +#endif /* BITS_PER_LONG >= 64 */ + +/* + * Counterpart to lock_timer_base above: + */ +static inline +void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) +{ + spin_unlock_irqrestore(&timer->base->lock, *flags); +} + +/** + * hrtimer_forward - forward the timer expiry + * + * @timer: hrtimer to forward + * @interval: the interval to forward + * + * Forward the timer expiry so it will expire in the future. + * Returns the number of overruns. + */ +unsigned long +hrtimer_forward(struct hrtimer *timer, ktime_t interval) +{ + unsigned long orun = 1; + ktime_t delta, now; + + now = timer->base->get_time(); + + delta = ktime_sub(now, timer->expires); + + if (delta.tv64 < 0) + return 0; + + if (interval.tv64 < timer->base->resolution.tv64) + interval.tv64 = timer->base->resolution.tv64; + + if (unlikely(delta.tv64 >= interval.tv64)) { + nsec_t incr = ktime_to_ns(interval); + + orun = ktime_divns(delta, incr); + timer->expires = ktime_add_ns(timer->expires, incr * orun); + if (timer->expires.tv64 > now.tv64) + return orun; + /* + * This (and the ktime_add() below) is the + * correction for exact: + */ + orun++; + } + timer->expires = ktime_add(timer->expires, interval); + + return orun; +} + +/* + * enqueue_hrtimer - internal function to (re)start a timer + * + * The timer is inserted in expiry order. Insertion into the + * red black tree is O(log(n)). Must hold the base lock. + */ +static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + struct rb_node **link = &base->active.rb_node; + struct rb_node *parent = NULL; + struct hrtimer *entry; + + /* + * Find the right place in the rbtree: + */ + while (*link) { + parent = *link; + entry = rb_entry(parent, struct hrtimer, node); + /* + * We dont care about collisions. Nodes with + * the same expiry time stay together. + */ + if (timer->expires.tv64 < entry->expires.tv64) + link = &(*link)->rb_left; + else + link = &(*link)->rb_right; + } + + /* + * Insert the timer to the rbtree and check whether it + * replaces the first pending timer + */ + rb_link_node(&timer->node, parent, link); + rb_insert_color(&timer->node, &base->active); + + timer->state = HRTIMER_PENDING; + + if (!base->first || timer->expires.tv64 < + rb_entry(base->first, struct hrtimer, node)->expires.tv64) + base->first = &timer->node; +} + +/* + * __remove_hrtimer - internal function to remove a timer + * + * Caller must hold the base lock. + */ +static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + /* + * Remove the timer from the rbtree and replace the + * first entry pointer if necessary. + */ + if (base->first == &timer->node) + base->first = rb_next(&timer->node); + rb_erase(&timer->node, &base->active); +} + +/* + * remove hrtimer, called with base lock held + */ +static inline int +remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base) +{ + if (hrtimer_active(timer)) { + __remove_hrtimer(timer, base); + timer->state = HRTIMER_INACTIVE; + return 1; + } + return 0; +} + +/** + * hrtimer_start - (re)start an relative timer on the current CPU + * + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + struct hrtimer_base *base, *new_base; + unsigned long flags; + int ret; + + base = lock_hrtimer_base(timer, &flags); + + /* Remove an active timer from the queue: */ + ret = remove_hrtimer(timer, base); + + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base); + + if (mode == HRTIMER_REL) + tim = ktime_add(tim, new_base->get_time()); + timer->expires = tim; + + enqueue_hrtimer(timer, new_base); + + unlock_hrtimer_base(timer, &flags); + + return ret; +} + +/** + * hrtimer_try_to_cancel - try to deactivate a timer + * + * @timer: hrtimer to stop + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + * -1 when the timer is currently excuting the callback function and + * can not be stopped + */ +int hrtimer_try_to_cancel(struct hrtimer *timer) +{ + struct hrtimer_base *base; + unsigned long flags; + int ret = -1; + + base = lock_hrtimer_base(timer, &flags); + + if (base->curr_timer != timer) + ret = remove_hrtimer(timer, base); + + unlock_hrtimer_base(timer, &flags); + + return ret; + +} + +/** + * hrtimer_cancel - cancel a timer and wait for the handler to finish. + * + * @timer: the timer to be cancelled + * + * Returns: + * 0 when the timer was not active + * 1 when the timer was active + */ +int hrtimer_cancel(struct hrtimer *timer) +{ + for (;;) { + int ret = hrtimer_try_to_cancel(timer); + + if (ret >= 0) + return ret; + } +} + +/** + * hrtimer_get_remaining - get remaining time for the timer + * + * @timer: the timer to read + */ +ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + struct hrtimer_base *base; + unsigned long flags; + ktime_t rem; + + base = lock_hrtimer_base(timer, &flags); + rem = ktime_sub(timer->expires, timer->base->get_time()); + unlock_hrtimer_base(timer, &flags); + + return rem; +} + +/** + * hrtimer_rebase - rebase an initialized hrtimer to a different base + * + * @timer: the timer to be rebased + * @clock_id: the clock to be used + */ +void hrtimer_rebase(struct hrtimer *timer, const clockid_t clock_id) +{ + struct hrtimer_base *bases; + + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); + timer->base = &bases[clock_id]; +} + +/** + * hrtimer_init - initialize a timer to the given clock + * + * @timer: the timer to be initialized + * @clock_id: the clock to be used + */ +void hrtimer_init(struct hrtimer *timer, const clockid_t clock_id) +{ + memset(timer, 0, sizeof(struct hrtimer)); + hrtimer_rebase(timer, clock_id); +} + +/** + * hrtimer_get_res - get the timer resolution for a clock + * + * @which_clock: which clock to query + * @tp: pointer to timespec variable to store the resolution + * + * Store the resolution of the clock selected by which_clock in the + * variable pointed to by tp. + */ +int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) +{ + struct hrtimer_base *bases; + + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); + *tp = ktime_to_timespec(bases[which_clock].resolution); + + return 0; +} + +/* + * Expire the per base hrtimer-queue: + */ +static inline void run_hrtimer_queue(struct hrtimer_base *base) +{ + ktime_t now = base->get_time(); + struct rb_node *node; + + spin_lock_irq(&base->lock); + + while ((node = base->first)) { + struct hrtimer *timer; + int (*fn)(void *); + int restart; + void *data; + + timer = rb_entry(node, struct hrtimer, node); + if (now.tv64 <= timer->expires.tv64) + break; + + fn = timer->function; + data = timer->data; + set_curr_timer(base, timer); + __remove_hrtimer(timer, base); + spin_unlock_irq(&base->lock); + + /* + * fn == NULL is special case for the simplest timer + * variant - wake up process and do not restart: + */ + if (!fn) { + wake_up_process(data); + restart = HRTIMER_NORESTART; + } else + restart = fn(data); + + spin_lock_irq(&base->lock); + + if (restart == HRTIMER_RESTART) + enqueue_hrtimer(timer, base); + else + timer->state = HRTIMER_EXPIRED; + } + set_curr_timer(base, NULL); + spin_unlock_irq(&base->lock); +} + +/* + * Called from timer softirq every jiffy, expire hrtimers: + */ +void hrtimer_run_queues(void) +{ + struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++) + run_hrtimer_queue(&base[i]); +} + +/* + * Sleep related functions: + */ + +/** + * schedule_hrtimer - sleep until timeout + * + * @timer: hrtimer variable initialized with the correct clock base + * @mode: timeout value is abs/rel + * + * Make the current task sleep until @timeout is + * elapsed. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout is guaranteed to + * pass before the routine returns. The routine will return 0 + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. In this case the remaining time + * will be returned + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + */ +static ktime_t __sched +schedule_hrtimer(struct hrtimer *timer, const enum hrtimer_mode mode) +{ + /* fn stays NULL, meaning single-shot wakeup: */ + timer->data = current; + + hrtimer_start(timer, timer->expires, mode); + + schedule(); + hrtimer_cancel(timer); + + /* Return the remaining time: */ + if (timer->state != HRTIMER_EXPIRED) + return ktime_sub(timer->expires, timer->base->get_time()); + else + return (ktime_t) {.tv64 = 0 }; +} + +static inline ktime_t __sched +schedule_hrtimer_interruptible(struct hrtimer *timer, + const enum hrtimer_mode mode) +{ + set_current_state(TASK_INTERRUPTIBLE); + + return schedule_hrtimer(timer, mode); +} + +static long __sched +nanosleep_restart(struct restart_block *restart, clockid_t clockid) +{ + struct timespec __user *rmtp; + struct timespec tu; + void *rfn_save = restart->fn; + struct hrtimer timer; + ktime_t rem; + + restart->fn = do_no_restart_syscall; + + hrtimer_init(&timer, clockid); + + timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0; + + rem = schedule_hrtimer_interruptible(&timer, HRTIMER_ABS); + + if (rem.tv64 <= 0) + return 0; + + rmtp = (struct timespec __user *) restart->arg2; + tu = ktime_to_timespec(rem); + if (rmtp && copy_to_user(rmtp, &tu, sizeof(tu))) + return -EFAULT; + + restart->fn = rfn_save; + + /* The other values in restart are already filled in */ + return -ERESTART_RESTARTBLOCK; +} + +static long __sched nanosleep_restart_mono(struct restart_block *restart) +{ + return nanosleep_restart(restart, CLOCK_MONOTONIC); +} + +static long __sched nanosleep_restart_real(struct restart_block *restart) +{ + return nanosleep_restart(restart, CLOCK_REALTIME); +} + +long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, + const enum hrtimer_mode mode, const clockid_t clockid) +{ + struct restart_block *restart; + struct hrtimer timer; + struct timespec tu; + ktime_t rem; + + hrtimer_init(&timer, clockid); + + timer.expires = timespec_to_ktime(*rqtp); + + rem = schedule_hrtimer_interruptible(&timer, mode); + if (rem.tv64 <= 0) + return 0; + + /* Absolute timers do not update the rmtp value: */ + if (mode == HRTIMER_ABS) + return -ERESTARTNOHAND; + + tu = ktime_to_timespec(rem); + + if (rmtp && copy_to_user(rmtp, &tu, sizeof(tu))) + return -EFAULT; + + restart = ¤t_thread_info()->restart_block; + restart->fn = (clockid == CLOCK_MONOTONIC) ? + nanosleep_restart_mono : nanosleep_restart_real; + restart->arg0 = timer.expires.tv64 & 0xFFFFFFFF; + restart->arg1 = timer.expires.tv64 >> 32; + restart->arg2 = (unsigned long) rmtp; + + return -ERESTART_RESTARTBLOCK; +} + +asmlinkage long +sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp) +{ + struct timespec tu; + + if (copy_from_user(&tu, rqtp, sizeof(tu))) + return -EFAULT; + + if (!timespec_valid(&tu)) + return -EINVAL; + + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_REL, CLOCK_MONOTONIC); +} + +/* + * Functions related to boot-time initialization: + */ +static void __devinit init_hrtimers_cpu(int cpu) +{ + struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++) { + spin_lock_init(&base->lock); + base++; + } +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void migrate_hrtimer_list(struct hrtimer_base *old_base, + struct hrtimer_base *new_base) +{ + struct hrtimer *timer; + struct rb_node *node; + + while ((node = rb_first(&old_base->active))) { + timer = rb_entry(node, struct hrtimer, node); + __remove_hrtimer(timer, old_base); + timer->base = new_base; + enqueue_hrtimer(timer, new_base); + } +} + +static void migrate_hrtimers(int cpu) +{ + struct hrtimer_base *old_base, *new_base; + int i; + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu(hrtimer_bases, cpu); + new_base = get_cpu_var(hrtimer_bases); + + local_irq_disable(); + + for (i = 0; i < MAX_HRTIMER_BASES; i++) { + + spin_lock(&new_base->lock); + spin_lock(&old_base->lock); + + BUG_ON(old_base->curr_timer); + + migrate_hrtimer_list(old_base, new_base); + + spin_unlock(&old_base->lock); + spin_unlock(&new_base->lock); + old_base++; + new_base++; + } + + local_irq_enable(); + put_cpu_var(hrtimer_bases); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +static int __devinit hrtimer_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + + case CPU_UP_PREPARE: + init_hrtimers_cpu(cpu); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + migrate_hrtimers(cpu); + break; +#endif + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block __devinitdata hrtimers_nb = { + .notifier_call = hrtimer_cpu_notify, +}; + +void __init hrtimers_init(void) +{ + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); +} + diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 81c49a4d679..97d5559997d 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -366,6 +366,8 @@ int request_irq(unsigned int irq, action->next = NULL; action->dev_id = dev_id; + select_smp_affinity(irq); + retval = setup_irq(irq, action); if (retval) kfree(action); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index f26e534c658..d03b5eef8ce 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -10,6 +10,8 @@ #include <linux/proc_fs.h> #include <linux/interrupt.h> +#include "internals.h" + static struct proc_dir_entry *root_irq_dir, *irq_dir[NR_IRQS]; #ifdef CONFIG_SMP @@ -68,7 +70,9 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer, */ cpus_and(tmp, new_value, cpu_online_map); if (cpus_empty(tmp)) - return -EINVAL; + /* Special case for empty set - allow the architecture + code to set default SMP affinity. */ + return select_smp_affinity(irq) ? -EINVAL : full_count; proc_set_irq_affinity(irq, new_value); diff --git a/kernel/itimer.c b/kernel/itimer.c index 7c1b25e25e4..c2c05c4ff28 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -12,36 +12,46 @@ #include <linux/syscalls.h> #include <linux/time.h> #include <linux/posix-timers.h> +#include <linux/hrtimer.h> #include <asm/uaccess.h> -static unsigned long it_real_value(struct signal_struct *sig) +/** + * itimer_get_remtime - get remaining time for the timer + * + * @timer: the timer to read + * + * Returns the delta between the expiry time and now, which can be + * less than zero or 1usec for an pending expired timer + */ +static struct timeval itimer_get_remtime(struct hrtimer *timer) { - unsigned long val = 0; - if (timer_pending(&sig->real_timer)) { - val = sig->real_timer.expires - jiffies; + ktime_t rem = hrtimer_get_remaining(timer); - /* look out for negative/zero itimer.. */ - if ((long) val <= 0) - val = 1; - } - return val; + /* + * Racy but safe: if the itimer expires after the above + * hrtimer_get_remtime() call but before this condition + * then we return 0 - which is correct. + */ + if (hrtimer_active(timer)) { + if (rem.tv64 <= 0) + rem.tv64 = NSEC_PER_USEC; + } else + rem.tv64 = 0; + + return ktime_to_timeval(rem); } int do_getitimer(int which, struct itimerval *value) { struct task_struct *tsk = current; - unsigned long interval, val; cputime_t cinterval, cval; switch (which) { case ITIMER_REAL: - spin_lock_irq(&tsk->sighand->siglock); - interval = tsk->signal->it_real_incr; - val = it_real_value(tsk->signal); - spin_unlock_irq(&tsk->sighand->siglock); - jiffies_to_timeval(val, &value->it_value); - jiffies_to_timeval(interval, &value->it_interval); + value->it_value = itimer_get_remtime(&tsk->signal->real_timer); + value->it_interval = + ktime_to_timeval(tsk->signal->it_real_incr); break; case ITIMER_VIRTUAL: read_lock(&tasklist_lock); @@ -113,59 +123,45 @@ asmlinkage long sys_getitimer(int which, struct itimerval __user *value) } -void it_real_fn(unsigned long __data) +/* + * The timer is automagically restarted, when interval != 0 + */ +int it_real_fn(void *data) { - struct task_struct * p = (struct task_struct *) __data; - unsigned long inc = p->signal->it_real_incr; + struct task_struct *tsk = (struct task_struct *) data; - send_group_sig_info(SIGALRM, SEND_SIG_PRIV, p); + send_group_sig_info(SIGALRM, SEND_SIG_PRIV, tsk); - /* - * Now restart the timer if necessary. We don't need any locking - * here because do_setitimer makes sure we have finished running - * before it touches anything. - * Note, we KNOW we are (or should be) at a jiffie edge here so - * we don't need the +1 stuff. Also, we want to use the prior - * expire value so as to not "slip" a jiffie if we are late. - * Deal with requesting a time prior to "now" here rather than - * in add_timer. - */ - if (!inc) - return; - while (time_before_eq(p->signal->real_timer.expires, jiffies)) - p->signal->real_timer.expires += inc; - add_timer(&p->signal->real_timer); + if (tsk->signal->it_real_incr.tv64 != 0) { + hrtimer_forward(&tsk->signal->real_timer, + tsk->signal->it_real_incr); + + return HRTIMER_RESTART; + } + return HRTIMER_NORESTART; } int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) { struct task_struct *tsk = current; - unsigned long val, interval, expires; + struct hrtimer *timer; + ktime_t expires; cputime_t cval, cinterval, nval, ninterval; switch (which) { case ITIMER_REAL: -again: - spin_lock_irq(&tsk->sighand->siglock); - interval = tsk->signal->it_real_incr; - val = it_real_value(tsk->signal); - /* We are sharing ->siglock with it_real_fn() */ - if (try_to_del_timer_sync(&tsk->signal->real_timer) < 0) { - spin_unlock_irq(&tsk->sighand->siglock); - goto again; - } - tsk->signal->it_real_incr = - timeval_to_jiffies(&value->it_interval); - expires = timeval_to_jiffies(&value->it_value); - if (expires) - mod_timer(&tsk->signal->real_timer, - jiffies + 1 + expires); - spin_unlock_irq(&tsk->sighand->siglock); + timer = &tsk->signal->real_timer; + hrtimer_cancel(timer); if (ovalue) { - jiffies_to_timeval(val, &ovalue->it_value); - jiffies_to_timeval(interval, - &ovalue->it_interval); + ovalue->it_value = itimer_get_remtime(timer); + ovalue->it_interval + = ktime_to_timeval(tsk->signal->it_real_incr); } + tsk->signal->it_real_incr = + timeval_to_ktime(value->it_interval); + expires = timeval_to_ktime(value->it_value); + if (expires.tv64 != 0) + hrtimer_start(timer, expires, HRTIMER_REL); break; case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); diff --git a/kernel/kexec.c b/kernel/kexec.c index 2c95848fbce..bf39d28e4c0 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -6,6 +6,7 @@ * Version 2. See the file COPYING for more details. */ +#include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/slab.h> @@ -26,6 +27,9 @@ #include <asm/system.h> #include <asm/semaphore.h> +/* Per cpu memory for storing cpu states in case of system crash. */ +note_buf_t* crash_notes; + /* Location of the reserved area for the crash kernel */ struct resource crashk_res = { .name = "Crash kernel", @@ -1054,9 +1058,24 @@ void crash_kexec(struct pt_regs *regs) if (!locked) { image = xchg(&kexec_crash_image, NULL); if (image) { - machine_crash_shutdown(regs); + struct pt_regs fixed_regs; + crash_setup_regs(&fixed_regs, regs); + machine_crash_shutdown(&fixed_regs); machine_kexec(image); } xchg(&kexec_lock, 0); } } + +static int __init crash_notes_memory_init(void) +{ + /* Allocate memory for saving cpu registers. */ + crash_notes = alloc_percpu(note_buf_t); + if (!crash_notes) { + printk("Kexec: Memory allocation for saving cpu register" + " states failed\n"); + return -ENOMEM; + } + return 0; +} +module_init(crash_notes_memory_init) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 5beda378cc7..3ea6325228d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -48,10 +48,11 @@ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; -static DEFINE_SPINLOCK(kprobe_lock); /* Protects kprobe_table */ +DECLARE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ DEFINE_SPINLOCK(kretprobe_lock); /* Protects kretprobe_inst_table */ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; +#ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* * kprobe->ainsn.insn points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and @@ -151,6 +152,7 @@ void __kprobes free_insn_slot(kprobe_opcode_t *slot) } } } +#endif /* We have preemption disabled.. so it is safe to use __ versions */ static inline void set_kprobe_instance(struct kprobe *kp) @@ -165,7 +167,7 @@ static inline void reset_kprobe_instance(void) /* * This routine is called either: - * - under the kprobe_lock spinlock - during kprobe_[un]register() + * - under the kprobe_mutex - during kprobe_[un]register() * OR * - with preemption disabled - from arch/xxx/kernel/kprobes.c */ @@ -246,6 +248,19 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) return ret; } +/* Walks the list and increments nmissed count for multiprobe case */ +void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) +{ + struct kprobe *kp; + if (p->pre_handler != aggr_pre_handler) { + p->nmissed++; + } else { + list_for_each_entry_rcu(kp, &p->list, list) + kp->nmissed++; + } + return; +} + /* Called with kretprobe_lock held */ struct kretprobe_instance __kprobes *get_free_rp_inst(struct kretprobe *rp) { @@ -399,16 +414,12 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) INIT_LIST_HEAD(&ap->list); list_add_rcu(&p->list, &ap->list); - INIT_HLIST_NODE(&ap->hlist); - hlist_del_rcu(&p->hlist); - hlist_add_head_rcu(&ap->hlist, - &kprobe_table[hash_ptr(ap->addr, KPROBE_HASH_BITS)]); + hlist_replace_rcu(&p->hlist, &ap->hlist); } /* * This is the second or subsequent kprobe at the address - handle * the intricacies - * TODO: Move kcalloc outside the spin_lock */ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, struct kprobe *p) @@ -420,7 +431,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, copy_kprobe(old_p, p); ret = add_new_kprobe(old_p, p); } else { - ap = kcalloc(1, sizeof(struct kprobe), GFP_ATOMIC); + ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); if (!ap) return -ENOMEM; add_aggr_kprobe(ap, old_p); @@ -430,25 +441,6 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, return ret; } -/* kprobe removal house-keeping routines */ -static inline void cleanup_kprobe(struct kprobe *p, unsigned long flags) -{ - arch_disarm_kprobe(p); - hlist_del_rcu(&p->hlist); - spin_unlock_irqrestore(&kprobe_lock, flags); - arch_remove_kprobe(p); -} - -static inline void cleanup_aggr_kprobe(struct kprobe *old_p, - struct kprobe *p, unsigned long flags) -{ - list_del_rcu(&p->list); - if (list_empty(&old_p->list)) - cleanup_kprobe(old_p, flags); - else - spin_unlock_irqrestore(&kprobe_lock, flags); -} - static int __kprobes in_kprobes_functions(unsigned long addr) { if (addr >= (unsigned long)__kprobes_text_start @@ -457,26 +449,44 @@ static int __kprobes in_kprobes_functions(unsigned long addr) return 0; } -int __kprobes register_kprobe(struct kprobe *p) +static int __kprobes __register_kprobe(struct kprobe *p, + unsigned long called_from) { int ret = 0; - unsigned long flags = 0; struct kprobe *old_p; + struct module *probed_mod; - if ((ret = in_kprobes_functions((unsigned long) p->addr)) != 0) - return ret; - if ((ret = arch_prepare_kprobe(p)) != 0) - goto rm_kprobe; + if ((!kernel_text_address((unsigned long) p->addr)) || + in_kprobes_functions((unsigned long) p->addr)) + return -EINVAL; + + p->mod_refcounted = 0; + /* Check are we probing a module */ + if ((probed_mod = module_text_address((unsigned long) p->addr))) { + struct module *calling_mod = module_text_address(called_from); + /* We must allow modules to probe themself and + * in this case avoid incrementing the module refcount, + * so as to allow unloading of self probing modules. + */ + if (calling_mod && (calling_mod != probed_mod)) { + if (unlikely(!try_module_get(probed_mod))) + return -EINVAL; + p->mod_refcounted = 1; + } else + probed_mod = NULL; + } p->nmissed = 0; - spin_lock_irqsave(&kprobe_lock, flags); + down(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { ret = register_aggr_kprobe(old_p, p); goto out; } - arch_copy_kprobe(p); + if ((ret = arch_prepare_kprobe(p)) != 0) + goto out; + INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); @@ -484,33 +494,66 @@ int __kprobes register_kprobe(struct kprobe *p) arch_arm_kprobe(p); out: - spin_unlock_irqrestore(&kprobe_lock, flags); -rm_kprobe: - if (ret == -EEXIST) - arch_remove_kprobe(p); + up(&kprobe_mutex); + + if (ret && probed_mod) + module_put(probed_mod); return ret; } +int __kprobes register_kprobe(struct kprobe *p) +{ + return __register_kprobe(p, + (unsigned long)__builtin_return_address(0)); +} + void __kprobes unregister_kprobe(struct kprobe *p) { - unsigned long flags; - struct kprobe *old_p; + struct module *mod; + struct kprobe *old_p, *list_p; + int cleanup_p; - spin_lock_irqsave(&kprobe_lock, flags); + down(&kprobe_mutex); old_p = get_kprobe(p->addr); - if (old_p) { - /* cleanup_*_kprobe() does the spin_unlock_irqrestore */ - if (old_p->pre_handler == aggr_pre_handler) - cleanup_aggr_kprobe(old_p, p, flags); - else - cleanup_kprobe(p, flags); - - synchronize_sched(); - if (old_p->pre_handler == aggr_pre_handler && - list_empty(&old_p->list)) + if (unlikely(!old_p)) { + up(&kprobe_mutex); + return; + } + if (p != old_p) { + list_for_each_entry_rcu(list_p, &old_p->list, list) + if (list_p == p) + /* kprobe p is a valid probe */ + goto valid_p; + up(&kprobe_mutex); + return; + } +valid_p: + if ((old_p == p) || ((old_p->pre_handler == aggr_pre_handler) && + (p->list.next == &old_p->list) && + (p->list.prev == &old_p->list))) { + /* Only probe on the hash list */ + arch_disarm_kprobe(p); + hlist_del_rcu(&old_p->hlist); + cleanup_p = 1; + } else { + list_del_rcu(&p->list); + cleanup_p = 0; + } + + up(&kprobe_mutex); + + synchronize_sched(); + if (p->mod_refcounted && + (mod = module_text_address((unsigned long)p->addr))) + module_put(mod); + + if (cleanup_p) { + if (p != old_p) { + list_del_rcu(&p->list); kfree(old_p); - } else - spin_unlock_irqrestore(&kprobe_lock, flags); + } + arch_remove_kprobe(p); + } } static struct notifier_block kprobe_exceptions_nb = { @@ -524,7 +567,8 @@ int __kprobes register_jprobe(struct jprobe *jp) jp->kp.pre_handler = setjmp_pre_handler; jp->kp.break_handler = longjmp_break_handler; - return register_kprobe(&jp->kp); + return __register_kprobe(&jp->kp, + (unsigned long)__builtin_return_address(0)); } void __kprobes unregister_jprobe(struct jprobe *jp) @@ -564,7 +608,8 @@ int __kprobes register_kretprobe(struct kretprobe *rp) rp->nmissed = 0; /* Establish function entry probe point */ - if ((ret = register_kprobe(&rp->kp)) != 0) + if ((ret = __register_kprobe(&rp->kp, + (unsigned long)__builtin_return_address(0))) != 0) free_rp_inst(rp); return ret; } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 015fb69ad94..d5eeae0fa5b 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -15,6 +15,9 @@ #include <linux/module.h> #include <linux/init.h> +u64 uevent_seqnum; +char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug"; + #define KERNEL_ATTR_RO(_name) \ static struct subsys_attribute _name##_attr = __ATTR_RO(_name) @@ -23,21 +26,29 @@ static struct subsys_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) #ifdef CONFIG_HOTPLUG -static ssize_t hotplug_seqnum_show(struct subsystem *subsys, char *page) +/* current uevent sequence number */ +static ssize_t uevent_seqnum_show(struct subsystem *subsys, char *page) { - return sprintf(page, "%llu\n", (unsigned long long)hotplug_seqnum); + return sprintf(page, "%llu\n", (unsigned long long)uevent_seqnum); } -KERNEL_ATTR_RO(hotplug_seqnum); -#endif - -#ifdef CONFIG_KEXEC -#include <asm/kexec.h> +KERNEL_ATTR_RO(uevent_seqnum); -static ssize_t crash_notes_show(struct subsystem *subsys, char *page) +/* uevent helper program, used during early boo */ +static ssize_t uevent_helper_show(struct subsystem *subsys, char *page) { - return sprintf(page, "%p\n", (void *)crash_notes); + return sprintf(page, "%s\n", uevent_helper); } -KERNEL_ATTR_RO(crash_notes); +static ssize_t uevent_helper_store(struct subsystem *subsys, const char *page, size_t count) +{ + if (count+1 > UEVENT_HELPER_PATH_LEN) + return -ENOENT; + memcpy(uevent_helper, page, count); + uevent_helper[count] = '\0'; + if (count && uevent_helper[count-1] == '\n') + uevent_helper[count-1] = '\0'; + return count; +} +KERNEL_ATTR_RW(uevent_helper); #endif decl_subsys(kernel, NULL, NULL); @@ -45,10 +56,8 @@ EXPORT_SYMBOL_GPL(kernel_subsys); static struct attribute * kernel_attrs[] = { #ifdef CONFIG_HOTPLUG - &hotplug_seqnum_attr.attr, -#endif -#ifdef CONFIG_KEXEC - &crash_notes_attr.attr, + &uevent_seqnum_attr.attr, + &uevent_helper_attr.attr, #endif NULL }; diff --git a/kernel/module.c b/kernel/module.c index 2ea929d51ad..618ed6e23ec 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -28,6 +28,7 @@ #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/rcupdate.h> +#include <linux/capability.h> #include <linux/cpu.h> #include <linux/moduleparam.h> #include <linux/errno.h> @@ -496,15 +497,15 @@ static void module_unload_free(struct module *mod) } #ifdef CONFIG_MODULE_FORCE_UNLOAD -static inline int try_force(unsigned int flags) +static inline int try_force_unload(unsigned int flags) { int ret = (flags & O_TRUNC); if (ret) - add_taint(TAINT_FORCED_MODULE); + add_taint(TAINT_FORCED_RMMOD); return ret; } #else -static inline int try_force(unsigned int flags) +static inline int try_force_unload(unsigned int flags) { return 0; } @@ -524,7 +525,7 @@ static int __try_stop_module(void *_sref) /* If it's not unused, quit unless we are told to block. */ if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) { - if (!(*sref->forced = try_force(sref->flags))) + if (!(*sref->forced = try_force_unload(sref->flags))) return -EWOULDBLOCK; } @@ -609,7 +610,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags) /* If it has an init func, it must have an exit func to unload */ if ((mod->init != NULL && mod->exit == NULL) || mod->unsafe) { - forced = try_force(flags); + forced = try_force_unload(flags); if (!forced) { /* This module can't be removed */ ret = -EBUSY; @@ -958,7 +959,6 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, unsigned long ret; const unsigned long *crc; - spin_lock_irq(&modlist_lock); ret = __find_symbol(name, &owner, &crc, mod->license_gplok); if (ret) { /* use_module can fail due to OOM, or module unloading */ @@ -966,7 +966,6 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, !use_module(mod, owner)) ret = 0; } - spin_unlock_irq(&modlist_lock); return ret; } @@ -1204,6 +1203,39 @@ void *__symbol_get(const char *symbol) } EXPORT_SYMBOL_GPL(__symbol_get); +/* + * Ensure that an exported symbol [global namespace] does not already exist + * in the Kernel or in some other modules exported symbol table. + */ +static int verify_export_symbols(struct module *mod) +{ + const char *name = NULL; + unsigned long i, ret = 0; + struct module *owner; + const unsigned long *crc; + + for (i = 0; i < mod->num_syms; i++) + if (__find_symbol(mod->syms[i].name, &owner, &crc, 1)) { + name = mod->syms[i].name; + ret = -ENOEXEC; + goto dup; + } + + for (i = 0; i < mod->num_gpl_syms; i++) + if (__find_symbol(mod->gpl_syms[i].name, &owner, &crc, 1)) { + name = mod->gpl_syms[i].name; + ret = -ENOEXEC; + goto dup; + } + +dup: + if (ret) + printk(KERN_ERR "%s: exports duplicate symbol %s (owned by %s)\n", + mod->name, name, module_name(owner)); + + return ret; +} + /* Change all symbols so that sh_value encodes the pointer directly. */ static int simplify_symbols(Elf_Shdr *sechdrs, unsigned int symindex, @@ -1715,6 +1747,11 @@ static struct module *load_module(void __user *umod, /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); + if (strcmp(mod->name, "ndiswrapper") == 0) + add_taint(TAINT_PROPRIETARY_MODULE); + if (strcmp(mod->name, "driverloader") == 0) + add_taint(TAINT_PROPRIETARY_MODULE); + #ifdef CONFIG_MODULE_UNLOAD /* Set up MODINFO_ATTR fields */ setup_modinfo(mod, sechdrs, infoindex); @@ -1767,6 +1804,12 @@ static struct module *load_module(void __user *umod, goto cleanup; } + /* Find duplicate symbols */ + err = verify_export_symbols(mod); + + if (err < 0) + goto cleanup; + /* Set up and sort exception table */ mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); mod->extable = extable = (void *)sechdrs[exindex].sh_addr; @@ -1854,8 +1897,7 @@ static struct module *load_module(void __user *umod, kfree(args); free_hdr: vfree(hdr); - if (err < 0) return ERR_PTR(err); - else return ptr; + return ERR_PTR(err); truncated: printk(KERN_ERR "Module len %lu truncated\n", len); diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c new file mode 100644 index 00000000000..f4913c37695 --- /dev/null +++ b/kernel/mutex-debug.c @@ -0,0 +1,462 @@ +/* + * kernel/mutex-debug.c + * + * Debugging code for mutexes + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * lock debugging, locking tree, deadlock detection started by: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + */ +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/kallsyms.h> +#include <linux/interrupt.h> + +#include "mutex-debug.h" + +/* + * We need a global lock when we walk through the multi-process + * lock tree. Only used in the deadlock-debugging case. + */ +DEFINE_SPINLOCK(debug_mutex_lock); + +/* + * All locks held by all tasks, in a single global list: + */ +LIST_HEAD(debug_mutex_held_locks); + +/* + * In the debug case we carry the caller's instruction pointer into + * other functions, but we dont want the function argument overhead + * in the nondebug case - hence these macros: + */ +#define __IP_DECL__ , unsigned long ip +#define __IP__ , ip +#define __RET_IP__ , (unsigned long)__builtin_return_address(0) + +/* + * "mutex debugging enabled" flag. We turn it off when we detect + * the first problem because we dont want to recurse back + * into the tracing code when doing error printk or + * executing a BUG(): + */ +int debug_mutex_on = 1; + +static void printk_task(struct task_struct *p) +{ + if (p) + printk("%16s:%5d [%p, %3d]", p->comm, p->pid, p, p->prio); + else + printk("<none>"); +} + +static void printk_ti(struct thread_info *ti) +{ + if (ti) + printk_task(ti->task); + else + printk("<none>"); +} + +static void printk_task_short(struct task_struct *p) +{ + if (p) + printk("%s/%d [%p, %3d]", p->comm, p->pid, p, p->prio); + else + printk("<none>"); +} + +static void printk_lock(struct mutex *lock, int print_owner) +{ + printk(" [%p] {%s}\n", lock, lock->name); + + if (print_owner && lock->owner) { + printk(".. held by: "); + printk_ti(lock->owner); + printk("\n"); + } + if (lock->owner) { + printk("... acquired at: "); + print_symbol("%s\n", lock->acquire_ip); + } +} + +/* + * printk locks held by a task: + */ +static void show_task_locks(struct task_struct *p) +{ + switch (p->state) { + case TASK_RUNNING: printk("R"); break; + case TASK_INTERRUPTIBLE: printk("S"); break; + case TASK_UNINTERRUPTIBLE: printk("D"); break; + case TASK_STOPPED: printk("T"); break; + case EXIT_ZOMBIE: printk("Z"); break; + case EXIT_DEAD: printk("X"); break; + default: printk("?"); break; + } + printk_task(p); + if (p->blocked_on) { + struct mutex *lock = p->blocked_on->lock; + + printk(" blocked on mutex:"); + printk_lock(lock, 1); + } else + printk(" (not blocked on mutex)\n"); +} + +/* + * printk all locks held in the system (if filter == NULL), + * or all locks belonging to a single task (if filter != NULL): + */ +void show_held_locks(struct task_struct *filter) +{ + struct list_head *curr, *cursor = NULL; + struct mutex *lock; + struct thread_info *t; + unsigned long flags; + int count = 0; + + if (filter) { + printk("------------------------------\n"); + printk("| showing all locks held by: | ("); + printk_task_short(filter); + printk("):\n"); + printk("------------------------------\n"); + } else { + printk("---------------------------\n"); + printk("| showing all locks held: |\n"); + printk("---------------------------\n"); + } + + /* + * Play safe and acquire the global trace lock. We + * cannot printk with that lock held so we iterate + * very carefully: + */ +next: + debug_spin_lock_save(&debug_mutex_lock, flags); + list_for_each(curr, &debug_mutex_held_locks) { + if (cursor && curr != cursor) + continue; + lock = list_entry(curr, struct mutex, held_list); + t = lock->owner; + if (filter && (t != filter->thread_info)) + continue; + count++; + cursor = curr->next; + debug_spin_lock_restore(&debug_mutex_lock, flags); + + printk("\n#%03d: ", count); + printk_lock(lock, filter ? 0 : 1); + goto next; + } + debug_spin_lock_restore(&debug_mutex_lock, flags); + printk("\n"); +} + +void mutex_debug_show_all_locks(void) +{ + struct task_struct *g, *p; + int count = 10; + int unlock = 1; + + printk("\nShowing all blocking locks in the system:\n"); + + /* + * Here we try to get the tasklist_lock as hard as possible, + * if not successful after 2 seconds we ignore it (but keep + * trying). This is to enable a debug printout even if a + * tasklist_lock-holding task deadlocks or crashes. + */ +retry: + if (!read_trylock(&tasklist_lock)) { + if (count == 10) + printk("hm, tasklist_lock locked, retrying... "); + if (count) { + count--; + printk(" #%d", 10-count); + mdelay(200); + goto retry; + } + printk(" ignoring it.\n"); + unlock = 0; + } + if (count != 10) + printk(" locked it.\n"); + + do_each_thread(g, p) { + show_task_locks(p); + if (!unlock) + if (read_trylock(&tasklist_lock)) + unlock = 1; + } while_each_thread(g, p); + + printk("\n"); + show_held_locks(NULL); + printk("=============================================\n\n"); + + if (unlock) + read_unlock(&tasklist_lock); +} + +static void report_deadlock(struct task_struct *task, struct mutex *lock, + struct mutex *lockblk, unsigned long ip) +{ + printk("\n%s/%d is trying to acquire this lock:\n", + current->comm, current->pid); + printk_lock(lock, 1); + printk("... trying at: "); + print_symbol("%s\n", ip); + show_held_locks(current); + + if (lockblk) { + printk("but %s/%d is deadlocking current task %s/%d!\n\n", + task->comm, task->pid, current->comm, current->pid); + printk("\n%s/%d is blocked on this lock:\n", + task->comm, task->pid); + printk_lock(lockblk, 1); + + show_held_locks(task); + + printk("\n%s/%d's [blocked] stackdump:\n\n", + task->comm, task->pid); + show_stack(task, NULL); + } + + printk("\n%s/%d's [current] stackdump:\n\n", + current->comm, current->pid); + dump_stack(); + mutex_debug_show_all_locks(); + printk("[ turning off deadlock detection. Please report this. ]\n\n"); + local_irq_disable(); +} + +/* + * Recursively check for mutex deadlocks: + */ +static int check_deadlock(struct mutex *lock, int depth, + struct thread_info *ti, unsigned long ip) +{ + struct mutex *lockblk; + struct task_struct *task; + + if (!debug_mutex_on) + return 0; + + ti = lock->owner; + if (!ti) + return 0; + + task = ti->task; + lockblk = NULL; + if (task->blocked_on) + lockblk = task->blocked_on->lock; + + /* Self-deadlock: */ + if (current == task) { + DEBUG_OFF(); + if (depth) + return 1; + printk("\n==========================================\n"); + printk( "[ BUG: lock recursion deadlock detected! |\n"); + printk( "------------------------------------------\n"); + report_deadlock(task, lock, NULL, ip); + return 0; + } + + /* Ugh, something corrupted the lock data structure? */ + if (depth > 20) { + DEBUG_OFF(); + printk("\n===========================================\n"); + printk( "[ BUG: infinite lock dependency detected!? |\n"); + printk( "-------------------------------------------\n"); + report_deadlock(task, lock, lockblk, ip); + return 0; + } + + /* Recursively check for dependencies: */ + if (lockblk && check_deadlock(lockblk, depth+1, ti, ip)) { + printk("\n============================================\n"); + printk( "[ BUG: circular locking deadlock detected! ]\n"); + printk( "--------------------------------------------\n"); + report_deadlock(task, lock, lockblk, ip); + return 0; + } + return 0; +} + +/* + * Called when a task exits, this function checks whether the + * task is holding any locks, and reports the first one if so: + */ +void mutex_debug_check_no_locks_held(struct task_struct *task) +{ + struct list_head *curr, *next; + struct thread_info *t; + unsigned long flags; + struct mutex *lock; + + if (!debug_mutex_on) + return; + + debug_spin_lock_save(&debug_mutex_lock, flags); + list_for_each_safe(curr, next, &debug_mutex_held_locks) { + lock = list_entry(curr, struct mutex, held_list); + t = lock->owner; + if (t != task->thread_info) + continue; + list_del_init(curr); + DEBUG_OFF(); + debug_spin_lock_restore(&debug_mutex_lock, flags); + + printk("BUG: %s/%d, lock held at task exit time!\n", + task->comm, task->pid); + printk_lock(lock, 1); + if (lock->owner != task->thread_info) + printk("exiting task is not even the owner??\n"); + return; + } + debug_spin_lock_restore(&debug_mutex_lock, flags); +} + +/* + * Called when kernel memory is freed (or unmapped), or if a mutex + * is destroyed or reinitialized - this code checks whether there is + * any held lock in the memory range of <from> to <to>: + */ +void mutex_debug_check_no_locks_freed(const void *from, unsigned long len) +{ + struct list_head *curr, *next; + const void *to = from + len; + unsigned long flags; + struct mutex *lock; + void *lock_addr; + + if (!debug_mutex_on) + return; + + debug_spin_lock_save(&debug_mutex_lock, flags); + list_for_each_safe(curr, next, &debug_mutex_held_locks) { + lock = list_entry(curr, struct mutex, held_list); + lock_addr = lock; + if (lock_addr < from || lock_addr >= to) + continue; + list_del_init(curr); + DEBUG_OFF(); + debug_spin_lock_restore(&debug_mutex_lock, flags); + + printk("BUG: %s/%d, active lock [%p(%p-%p)] freed!\n", + current->comm, current->pid, lock, from, to); + dump_stack(); + printk_lock(lock, 1); + if (lock->owner != current_thread_info()) + printk("freeing task is not even the owner??\n"); + return; + } + debug_spin_lock_restore(&debug_mutex_lock, flags); +} + +/* + * Must be called with lock->wait_lock held. + */ +void debug_mutex_set_owner(struct mutex *lock, + struct thread_info *new_owner __IP_DECL__) +{ + lock->owner = new_owner; + DEBUG_WARN_ON(!list_empty(&lock->held_list)); + if (debug_mutex_on) { + list_add_tail(&lock->held_list, &debug_mutex_held_locks); + lock->acquire_ip = ip; + } +} + +void debug_mutex_init_waiter(struct mutex_waiter *waiter) +{ + memset(waiter, 0x11, sizeof(*waiter)); + waiter->magic = waiter; + INIT_LIST_HEAD(&waiter->list); +} + +void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter) +{ + SMP_DEBUG_WARN_ON(!spin_is_locked(&lock->wait_lock)); + DEBUG_WARN_ON(list_empty(&lock->wait_list)); + DEBUG_WARN_ON(waiter->magic != waiter); + DEBUG_WARN_ON(list_empty(&waiter->list)); +} + +void debug_mutex_free_waiter(struct mutex_waiter *waiter) +{ + DEBUG_WARN_ON(!list_empty(&waiter->list)); + memset(waiter, 0x22, sizeof(*waiter)); +} + +void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti __IP_DECL__) +{ + SMP_DEBUG_WARN_ON(!spin_is_locked(&lock->wait_lock)); + check_deadlock(lock, 0, ti, ip); + /* Mark the current thread as blocked on the lock: */ + ti->task->blocked_on = waiter; + waiter->lock = lock; +} + +void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti) +{ + DEBUG_WARN_ON(list_empty(&waiter->list)); + DEBUG_WARN_ON(waiter->task != ti->task); + DEBUG_WARN_ON(ti->task->blocked_on != waiter); + ti->task->blocked_on = NULL; + + list_del_init(&waiter->list); + waiter->task = NULL; +} + +void debug_mutex_unlock(struct mutex *lock) +{ + DEBUG_WARN_ON(lock->magic != lock); + DEBUG_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); + DEBUG_WARN_ON(lock->owner != current_thread_info()); + if (debug_mutex_on) { + DEBUG_WARN_ON(list_empty(&lock->held_list)); + list_del_init(&lock->held_list); + } +} + +void debug_mutex_init(struct mutex *lock, const char *name) +{ + /* + * Make sure we are not reinitializing a held lock: + */ + mutex_debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lock->owner = NULL; + INIT_LIST_HEAD(&lock->held_list); + lock->name = name; + lock->magic = lock; +} + +/*** + * mutex_destroy - mark a mutex unusable + * @lock: the mutex to be destroyed + * + * This function marks the mutex uninitialized, and any subsequent + * use of the mutex is forbidden. The mutex must not be locked when + * this function is called. + */ +void fastcall mutex_destroy(struct mutex *lock) +{ + DEBUG_WARN_ON(mutex_is_locked(lock)); + lock->magic = NULL; +} + +EXPORT_SYMBOL_GPL(mutex_destroy); diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h new file mode 100644 index 00000000000..fd384050acb --- /dev/null +++ b/kernel/mutex-debug.h @@ -0,0 +1,134 @@ +/* + * Mutexes: blocking mutual exclusion locks + * + * started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * This file contains mutex debugging related internal declarations, + * prototypes and inline functions, for the CONFIG_DEBUG_MUTEXES case. + * More details are in kernel/mutex-debug.c. + */ + +extern spinlock_t debug_mutex_lock; +extern struct list_head debug_mutex_held_locks; +extern int debug_mutex_on; + +/* + * In the debug case we carry the caller's instruction pointer into + * other functions, but we dont want the function argument overhead + * in the nondebug case - hence these macros: + */ +#define __IP_DECL__ , unsigned long ip +#define __IP__ , ip +#define __RET_IP__ , (unsigned long)__builtin_return_address(0) + +/* + * This must be called with lock->wait_lock held. + */ +extern void debug_mutex_set_owner(struct mutex *lock, + struct thread_info *new_owner __IP_DECL__); + +static inline void debug_mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} + +extern void debug_mutex_init_waiter(struct mutex_waiter *waiter); +extern void debug_mutex_wake_waiter(struct mutex *lock, + struct mutex_waiter *waiter); +extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); +extern void debug_mutex_add_waiter(struct mutex *lock, + struct mutex_waiter *waiter, + struct thread_info *ti __IP_DECL__); +extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct thread_info *ti); +extern void debug_mutex_unlock(struct mutex *lock); +extern void debug_mutex_init(struct mutex *lock, const char *name); + +#define debug_spin_lock(lock) \ + do { \ + local_irq_disable(); \ + if (debug_mutex_on) \ + spin_lock(lock); \ + } while (0) + +#define debug_spin_unlock(lock) \ + do { \ + if (debug_mutex_on) \ + spin_unlock(lock); \ + local_irq_enable(); \ + preempt_check_resched(); \ + } while (0) + +#define debug_spin_lock_save(lock, flags) \ + do { \ + local_irq_save(flags); \ + if (debug_mutex_on) \ + spin_lock(lock); \ + } while (0) + +#define debug_spin_lock_restore(lock, flags) \ + do { \ + if (debug_mutex_on) \ + spin_unlock(lock); \ + local_irq_restore(flags); \ + preempt_check_resched(); \ + } while (0) + +#define spin_lock_mutex(lock) \ + do { \ + struct mutex *l = container_of(lock, struct mutex, wait_lock); \ + \ + DEBUG_WARN_ON(in_interrupt()); \ + debug_spin_lock(&debug_mutex_lock); \ + spin_lock(lock); \ + DEBUG_WARN_ON(l->magic != l); \ + } while (0) + +#define spin_unlock_mutex(lock) \ + do { \ + spin_unlock(lock); \ + debug_spin_unlock(&debug_mutex_lock); \ + } while (0) + +#define DEBUG_OFF() \ +do { \ + if (debug_mutex_on) { \ + debug_mutex_on = 0; \ + console_verbose(); \ + if (spin_is_locked(&debug_mutex_lock)) \ + spin_unlock(&debug_mutex_lock); \ + } \ +} while (0) + +#define DEBUG_BUG() \ +do { \ + if (debug_mutex_on) { \ + DEBUG_OFF(); \ + BUG(); \ + } \ +} while (0) + +#define DEBUG_WARN_ON(c) \ +do { \ + if (unlikely(c && debug_mutex_on)) { \ + DEBUG_OFF(); \ + WARN_ON(1); \ + } \ +} while (0) + +# define DEBUG_BUG_ON(c) \ +do { \ + if (unlikely(c)) \ + DEBUG_BUG(); \ +} while (0) + +#ifdef CONFIG_SMP +# define SMP_DEBUG_WARN_ON(c) DEBUG_WARN_ON(c) +# define SMP_DEBUG_BUG_ON(c) DEBUG_BUG_ON(c) +#else +# define SMP_DEBUG_WARN_ON(c) do { } while (0) +# define SMP_DEBUG_BUG_ON(c) do { } while (0) +#endif + diff --git a/kernel/mutex.c b/kernel/mutex.c new file mode 100644 index 00000000000..5449b210d9e --- /dev/null +++ b/kernel/mutex.c @@ -0,0 +1,315 @@ +/* + * kernel/mutex.c + * + * Mutexes: blocking mutual exclusion locks + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and + * David Howells for suggestions and improvements. + * + * Also see Documentation/mutex-design.txt. + */ +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> + +/* + * In the DEBUG case we are using the "NULL fastpath" for mutexes, + * which forces all calls into the slowpath: + */ +#ifdef CONFIG_DEBUG_MUTEXES +# include "mutex-debug.h" +# include <asm-generic/mutex-null.h> +#else +# include "mutex.h" +# include <asm/mutex.h> +#endif + +/*** + * mutex_init - initialize the mutex + * @lock: the mutex to be initialized + * + * Initialize the mutex to unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ +void fastcall __mutex_init(struct mutex *lock, const char *name) +{ + atomic_set(&lock->count, 1); + spin_lock_init(&lock->wait_lock); + INIT_LIST_HEAD(&lock->wait_list); + + debug_mutex_init(lock, name); +} + +EXPORT_SYMBOL(__mutex_init); + +/* + * We split the mutex lock/unlock logic into separate fastpath and + * slowpath functions, to reduce the register pressure on the fastpath. + * We also put the fastpath first in the kernel image, to make sure the + * branch is predicted by the CPU as default-untaken. + */ +static void fastcall noinline __sched +__mutex_lock_slowpath(atomic_t *lock_count __IP_DECL__); + +/*** + * mutex_lock - acquire the mutex + * @lock: the mutex to be acquired + * + * Lock the mutex exclusively for this task. If the mutex is not + * available right now, it will sleep until it can get it. + * + * The mutex must later on be released by the same task that + * acquired it. Recursive locking is not allowed. The task + * may not exit without first unlocking the mutex. Also, kernel + * memory where the mutex resides mutex must not be freed with + * the mutex still locked. The mutex must first be initialized + * (or statically defined) before it can be locked. memset()-ing + * the mutex to 0 is not allowed. + * + * ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging + * checks that will enforce the restrictions and will also do + * deadlock debugging. ) + * + * This function is similar to (but not equivalent to) down(). + */ +void fastcall __sched mutex_lock(struct mutex *lock) +{ + might_sleep(); + /* + * The locking fastpath is the 1->0 transition from + * 'unlocked' into 'locked' state. + */ + __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); +} + +EXPORT_SYMBOL(mutex_lock); + +static void fastcall noinline __sched +__mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__); + +/*** + * mutex_unlock - release the mutex + * @lock: the mutex to be released + * + * Unlock a mutex that has been locked by this task previously. + * + * This function must not be used in interrupt context. Unlocking + * of a not locked mutex is not allowed. + * + * This function is similar to (but not equivalent to) up(). + */ +void fastcall __sched mutex_unlock(struct mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); +} + +EXPORT_SYMBOL(mutex_unlock); + +/* + * Lock a mutex (possibly interruptible), slowpath: + */ +static inline int __sched +__mutex_lock_common(struct mutex *lock, long state __IP_DECL__) +{ + struct task_struct *task = current; + struct mutex_waiter waiter; + unsigned int old_val; + + debug_mutex_init_waiter(&waiter); + + spin_lock_mutex(&lock->wait_lock); + + debug_mutex_add_waiter(lock, &waiter, task->thread_info, ip); + + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + waiter.task = task; + + for (;;) { + /* + * Lets try to take the lock again - this is needed even if + * we get here for the first time (shortly after failing to + * acquire the lock), to make sure that we get a wakeup once + * it's unlocked. Later on, if we sleep, this is the + * operation that gives us the lock. We xchg it to -1, so + * that when we release the lock, we properly wake up the + * other waiters: + */ + old_val = atomic_xchg(&lock->count, -1); + if (old_val == 1) + break; + + /* + * got a signal? (This code gets eliminated in the + * TASK_UNINTERRUPTIBLE case.) + */ + if (unlikely(state == TASK_INTERRUPTIBLE && + signal_pending(task))) { + mutex_remove_waiter(lock, &waiter, task->thread_info); + spin_unlock_mutex(&lock->wait_lock); + + debug_mutex_free_waiter(&waiter); + return -EINTR; + } + __set_task_state(task, state); + + /* didnt get the lock, go to sleep: */ + spin_unlock_mutex(&lock->wait_lock); + schedule(); + spin_lock_mutex(&lock->wait_lock); + } + + /* got the lock - rejoice! */ + mutex_remove_waiter(lock, &waiter, task->thread_info); + debug_mutex_set_owner(lock, task->thread_info __IP__); + + /* set it to 0 if there are no waiters left: */ + if (likely(list_empty(&lock->wait_list))) + atomic_set(&lock->count, 0); + + spin_unlock_mutex(&lock->wait_lock); + + debug_mutex_free_waiter(&waiter); + + DEBUG_WARN_ON(list_empty(&lock->held_list)); + DEBUG_WARN_ON(lock->owner != task->thread_info); + + return 0; +} + +static void fastcall noinline __sched +__mutex_lock_slowpath(atomic_t *lock_count __IP_DECL__) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE __IP__); +} + +/* + * Release the lock, slowpath: + */ +static fastcall noinline void +__mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + + DEBUG_WARN_ON(lock->owner != current_thread_info()); + + spin_lock_mutex(&lock->wait_lock); + + /* + * some architectures leave the lock unlocked in the fastpath failure + * case, others need to leave it locked. In the later case we have to + * unlock it here + */ + if (__mutex_slowpath_needs_to_unlock()) + atomic_set(&lock->count, 1); + + debug_mutex_unlock(lock); + + if (!list_empty(&lock->wait_list)) { + /* get the first entry from the wait-list: */ + struct mutex_waiter *waiter = + list_entry(lock->wait_list.next, + struct mutex_waiter, list); + + debug_mutex_wake_waiter(lock, waiter); + + wake_up_process(waiter->task); + } + + debug_mutex_clear_owner(lock); + + spin_unlock_mutex(&lock->wait_lock); +} + +/* + * Here come the less common (and hence less performance-critical) APIs: + * mutex_lock_interruptible() and mutex_trylock(). + */ +static int fastcall noinline __sched +__mutex_lock_interruptible_slowpath(atomic_t *lock_count __IP_DECL__); + +/*** + * mutex_lock_interruptible - acquire the mutex, interruptable + * @lock: the mutex to be acquired + * + * Lock the mutex like mutex_lock(), and return 0 if the mutex has + * been acquired or sleep until the mutex becomes available. If a + * signal arrives while waiting for the lock then this function + * returns -EINTR. + * + * This function is similar to (but not equivalent to) down_interruptible(). + */ +int fastcall __sched mutex_lock_interruptible(struct mutex *lock) +{ + might_sleep(); + return __mutex_fastpath_lock_retval + (&lock->count, __mutex_lock_interruptible_slowpath); +} + +EXPORT_SYMBOL(mutex_lock_interruptible); + +static int fastcall noinline __sched +__mutex_lock_interruptible_slowpath(atomic_t *lock_count __IP_DECL__) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE __IP__); +} + +/* + * Spinlock based trylock, we take the spinlock and check whether we + * can get the lock: + */ +static inline int __mutex_trylock_slowpath(atomic_t *lock_count) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + int prev; + + spin_lock_mutex(&lock->wait_lock); + + prev = atomic_xchg(&lock->count, -1); + if (likely(prev == 1)) + debug_mutex_set_owner(lock, current_thread_info() __RET_IP__); + /* Set it back to 0 if there are no waiters: */ + if (likely(list_empty(&lock->wait_list))) + atomic_set(&lock->count, 0); + + spin_unlock_mutex(&lock->wait_lock); + + return prev == 1; +} + +/*** + * mutex_trylock - try acquire the mutex, without waiting + * @lock: the mutex to be acquired + * + * Try to acquire the mutex atomically. Returns 1 if the mutex + * has been acquired successfully, and 0 on contention. + * + * NOTE: this function follows the spin_trylock() convention, so + * it is negated to the down_trylock() return values! Be careful + * about this when converting semaphore users to mutexes. + * + * This function must not be used in interrupt context. The + * mutex must be released by the same task that acquired it. + */ +int fastcall mutex_trylock(struct mutex *lock) +{ + return __mutex_fastpath_trylock(&lock->count, + __mutex_trylock_slowpath); +} + +EXPORT_SYMBOL(mutex_trylock); diff --git a/kernel/mutex.h b/kernel/mutex.h new file mode 100644 index 00000000000..00fe84e7b67 --- /dev/null +++ b/kernel/mutex.h @@ -0,0 +1,35 @@ +/* + * Mutexes: blocking mutual exclusion locks + * + * started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * This file contains mutex debugging related internal prototypes, for the + * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: + */ + +#define spin_lock_mutex(lock) spin_lock(lock) +#define spin_unlock_mutex(lock) spin_unlock(lock) +#define mutex_remove_waiter(lock, waiter, ti) \ + __list_del((waiter)->list.prev, (waiter)->list.next) + +#define DEBUG_WARN_ON(c) do { } while (0) +#define debug_mutex_set_owner(lock, new_owner) do { } while (0) +#define debug_mutex_clear_owner(lock) do { } while (0) +#define debug_mutex_init_waiter(waiter) do { } while (0) +#define debug_mutex_wake_waiter(lock, waiter) do { } while (0) +#define debug_mutex_free_waiter(waiter) do { } while (0) +#define debug_mutex_add_waiter(lock, waiter, ti, ip) do { } while (0) +#define debug_mutex_unlock(lock) do { } while (0) +#define debug_mutex_init(lock, name) do { } while (0) + +/* + * Return-address parameters/declarations. They are very useful for + * debugging, but add overhead in the !DEBUG case - so we go the + * trouble of using this not too elegant but zero-cost solution: + */ +#define __IP_DECL__ +#define __IP__ +#define __RET_IP__ + diff --git a/kernel/panic.c b/kernel/panic.c index aabc5f86fa3..c5c4ab25583 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -60,7 +60,7 @@ NORET_TYPE void panic(const char * fmt, ...) long i; static char buf[1024]; va_list args; -#if defined(CONFIG_ARCH_S390) +#if defined(CONFIG_S390) unsigned long caller = (unsigned long) __builtin_return_address(0); #endif @@ -125,7 +125,7 @@ NORET_TYPE void panic(const char * fmt, ...) printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n"); } #endif -#if defined(CONFIG_ARCH_S390) +#if defined(CONFIG_S390) disabled_wait(caller); #endif local_irq_enable(); diff --git a/kernel/params.c b/kernel/params.c index 47ba6954794..c76ad25e6a2 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -619,7 +619,7 @@ static void __init param_sysfs_builtin(void) /* module-related sysfs stuff */ -#ifdef CONFIG_MODULES +#ifdef CONFIG_SYSFS #define to_module_attr(n) container_of(n, struct module_attribute, attr); #define to_module_kobject(n) container_of(n, struct module_kobject, kobj); diff --git a/kernel/pid.c b/kernel/pid.c index edba31c681a..1acc0724699 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -136,7 +136,7 @@ struct pid * fastcall find_pid(enum pid_type type, int nr) struct hlist_node *elem; struct pid *pid; - hlist_for_each_entry(pid, elem, + hlist_for_each_entry_rcu(pid, elem, &pid_hash[type][pid_hashfn(nr)], pid_chain) { if (pid->nr == nr) return pid; @@ -150,15 +150,15 @@ int fastcall attach_pid(task_t *task, enum pid_type type, int nr) task_pid = &task->pids[type]; pid = find_pid(type, nr); + task_pid->nr = nr; if (pid == NULL) { - hlist_add_head(&task_pid->pid_chain, - &pid_hash[type][pid_hashfn(nr)]); INIT_LIST_HEAD(&task_pid->pid_list); + hlist_add_head_rcu(&task_pid->pid_chain, + &pid_hash[type][pid_hashfn(nr)]); } else { INIT_HLIST_NODE(&task_pid->pid_chain); - list_add_tail(&task_pid->pid_list, &pid->pid_list); + list_add_tail_rcu(&task_pid->pid_list, &pid->pid_list); } - task_pid->nr = nr; return 0; } @@ -170,20 +170,20 @@ static fastcall int __detach_pid(task_t *task, enum pid_type type) pid = &task->pids[type]; if (!hlist_unhashed(&pid->pid_chain)) { - hlist_del(&pid->pid_chain); - if (list_empty(&pid->pid_list)) + if (list_empty(&pid->pid_list)) { nr = pid->nr; - else { + hlist_del_rcu(&pid->pid_chain); + } else { pid_next = list_entry(pid->pid_list.next, struct pid, pid_list); /* insert next pid from pid_list to hash */ - hlist_add_head(&pid_next->pid_chain, - &pid_hash[type][pid_hashfn(pid_next->nr)]); + hlist_replace_rcu(&pid->pid_chain, + &pid_next->pid_chain); } } - list_del(&pid->pid_list); + list_del_rcu(&pid->pid_list); pid->nr = 0; return nr; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index cae4f572899..520f6c59948 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,7 +7,7 @@ #include <asm/uaccess.h> #include <linux/errno.h> -static int check_clock(clockid_t which_clock) +static int check_clock(const clockid_t which_clock) { int error = 0; struct task_struct *p; @@ -31,7 +31,7 @@ static int check_clock(clockid_t which_clock) } static inline union cpu_time_count -timespec_to_sample(clockid_t which_clock, const struct timespec *tp) +timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) { union cpu_time_count ret; ret.sched = 0; /* high half always zero when .cpu used */ @@ -43,7 +43,7 @@ timespec_to_sample(clockid_t which_clock, const struct timespec *tp) return ret; } -static void sample_to_timespec(clockid_t which_clock, +static void sample_to_timespec(const clockid_t which_clock, union cpu_time_count cpu, struct timespec *tp) { @@ -55,7 +55,7 @@ static void sample_to_timespec(clockid_t which_clock, } } -static inline int cpu_time_before(clockid_t which_clock, +static inline int cpu_time_before(const clockid_t which_clock, union cpu_time_count now, union cpu_time_count then) { @@ -65,7 +65,7 @@ static inline int cpu_time_before(clockid_t which_clock, return cputime_lt(now.cpu, then.cpu); } } -static inline void cpu_time_add(clockid_t which_clock, +static inline void cpu_time_add(const clockid_t which_clock, union cpu_time_count *acc, union cpu_time_count val) { @@ -75,7 +75,7 @@ static inline void cpu_time_add(clockid_t which_clock, acc->cpu = cputime_add(acc->cpu, val.cpu); } } -static inline union cpu_time_count cpu_time_sub(clockid_t which_clock, +static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, union cpu_time_count a, union cpu_time_count b) { @@ -151,7 +151,7 @@ static inline unsigned long long sched_ns(struct task_struct *p) return (p == current) ? current_sched_time(p) : p->sched_time; } -int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { int error = check_clock(which_clock); if (!error) { @@ -169,7 +169,7 @@ int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) return error; } -int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp) +int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) { /* * You can never reset a CPU clock, but we check for other errors @@ -186,7 +186,7 @@ int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp) /* * Sample a per-thread clock for the given task. */ -static int cpu_clock_sample(clockid_t which_clock, struct task_struct *p, +static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, union cpu_time_count *cpu) { switch (CPUCLOCK_WHICH(which_clock)) { @@ -238,18 +238,7 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, while ((t = next_thread(t)) != p) { cpu->sched += t->sched_time; } - if (p->tgid == current->tgid) { - /* - * We're sampling ourselves, so include the - * cycles not yet banked. We still omit - * other threads running on other CPUs, - * so the total can always be behind as - * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ). - */ - cpu->sched += current_sched_time(current); - } else { - cpu->sched += p->sched_time; - } + cpu->sched += sched_ns(p); break; } return 0; @@ -259,7 +248,7 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. */ -static int cpu_clock_sample_group(clockid_t which_clock, +static int cpu_clock_sample_group(const clockid_t which_clock, struct task_struct *p, union cpu_time_count *cpu) { @@ -273,7 +262,7 @@ static int cpu_clock_sample_group(clockid_t which_clock, } -int posix_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { const pid_t pid = CPUCLOCK_PID(which_clock); int error = -EINVAL; @@ -1410,8 +1399,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, static long posix_cpu_clock_nanosleep_restart(struct restart_block *); -int posix_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +int posix_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct timespec __user *rmtp) { struct restart_block *restart_block = ¤t_thread_info()->restart_block; @@ -1436,7 +1425,6 @@ int posix_cpu_nsleep(clockid_t which_clock, int flags, error = posix_cpu_timer_create(&timer); timer.it_process = current; if (!error) { - struct timespec __user *rmtp; static struct itimerspec zero_it; struct itimerspec it = { .it_value = *rqtp, .it_interval = {} }; @@ -1483,7 +1471,6 @@ int posix_cpu_nsleep(clockid_t which_clock, int flags, /* * Report back to the user the time still remaining. */ - rmtp = (struct timespec __user *) restart_block->arg1; if (rmtp != NULL && !(flags & TIMER_ABSTIME) && copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) return -EFAULT; @@ -1491,6 +1478,7 @@ int posix_cpu_nsleep(clockid_t which_clock, int flags, restart_block->fn = posix_cpu_clock_nanosleep_restart; /* Caller already set restart_block->arg1 */ restart_block->arg0 = which_clock; + restart_block->arg1 = (unsigned long) rmtp; restart_block->arg2 = rqtp->tv_sec; restart_block->arg3 = rqtp->tv_nsec; @@ -1504,21 +1492,28 @@ static long posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block) { clockid_t which_clock = restart_block->arg0; - struct timespec t = { .tv_sec = restart_block->arg2, - .tv_nsec = restart_block->arg3 }; + struct timespec __user *rmtp; + struct timespec t; + + rmtp = (struct timespec __user *) restart_block->arg1; + t.tv_sec = restart_block->arg2; + t.tv_nsec = restart_block->arg3; + restart_block->fn = do_no_restart_syscall; - return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t); + return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t, rmtp); } #define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED) #define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED) -static int process_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +static int process_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_getres(PROCESS_CLOCK, tp); } -static int process_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +static int process_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_get(PROCESS_CLOCK, tp); } @@ -1527,16 +1522,19 @@ static int process_cpu_timer_create(struct k_itimer *timer) timer->it_clock = PROCESS_CLOCK; return posix_cpu_timer_create(timer); } -static int process_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +static int process_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, + struct timespec __user *rmtp) { - return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); + return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp); } -static int thread_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +static int thread_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_getres(THREAD_CLOCK, tp); } -static int thread_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +static int thread_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_get(THREAD_CLOCK, tp); } @@ -1545,8 +1543,8 @@ static int thread_cpu_timer_create(struct k_itimer *timer) timer->it_clock = THREAD_CLOCK; return posix_cpu_timer_create(timer); } -static int thread_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +static int thread_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct timespec __user *rmtp) { return -EINVAL; } diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 5870efb3e20..197208b3aa2 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -48,21 +48,6 @@ #include <linux/workqueue.h> #include <linux/module.h> -#ifndef div_long_long_rem -#include <asm/div64.h> - -#define div_long_long_rem(dividend,divisor,remainder) ({ \ - u64 result = dividend; \ - *remainder = do_div(result,divisor); \ - result; }) - -#endif -#define CLOCK_REALTIME_RES TICK_NSEC /* In nano seconds. */ - -static inline u64 mpy_l_X_l_ll(unsigned long mpy1,unsigned long mpy2) -{ - return (u64)mpy1 * mpy2; -} /* * Management arrays for POSIX timers. Timers are kept in slab memory * Timer ids are allocated by an external routine that keeps track of the @@ -148,18 +133,18 @@ static DEFINE_SPINLOCK(idr_lock); */ static struct k_clock posix_clocks[MAX_CLOCKS]; + /* - * We only have one real clock that can be set so we need only one abs list, - * even if we should want to have several clocks with differing resolutions. + * These ones are defined below. */ -static struct k_clock_abs abs_list = {.list = LIST_HEAD_INIT(abs_list.list), - .lock = SPIN_LOCK_UNLOCKED}; +static int common_nsleep(const clockid_t, int flags, struct timespec *t, + struct timespec __user *rmtp); +static void common_timer_get(struct k_itimer *, struct itimerspec *); +static int common_timer_set(struct k_itimer *, int, + struct itimerspec *, struct itimerspec *); +static int common_timer_del(struct k_itimer *timer); -static void posix_timer_fn(unsigned long); -static u64 do_posix_clock_monotonic_gettime_parts( - struct timespec *tp, struct timespec *mo); -int do_posix_clock_monotonic_gettime(struct timespec *tp); -static int do_posix_clock_monotonic_get(clockid_t, struct timespec *tp); +static int posix_timer_fn(void *data); static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags); @@ -184,7 +169,7 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) * the function pointer CALL in struct k_clock. */ -static inline int common_clock_getres(clockid_t which_clock, +static inline int common_clock_getres(const clockid_t which_clock, struct timespec *tp) { tp->tv_sec = 0; @@ -192,39 +177,33 @@ static inline int common_clock_getres(clockid_t which_clock, return 0; } -static inline int common_clock_get(clockid_t which_clock, struct timespec *tp) +/* + * Get real time for posix timers + */ +static int common_clock_get(clockid_t which_clock, struct timespec *tp) { - getnstimeofday(tp); + ktime_get_real_ts(tp); return 0; } -static inline int common_clock_set(clockid_t which_clock, struct timespec *tp) +static inline int common_clock_set(const clockid_t which_clock, + struct timespec *tp) { return do_sys_settimeofday(tp, NULL); } -static inline int common_timer_create(struct k_itimer *new_timer) +static int common_timer_create(struct k_itimer *new_timer) { - INIT_LIST_HEAD(&new_timer->it.real.abs_timer_entry); - init_timer(&new_timer->it.real.timer); - new_timer->it.real.timer.data = (unsigned long) new_timer; + hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock); + new_timer->it.real.timer.data = new_timer; new_timer->it.real.timer.function = posix_timer_fn; return 0; } /* - * These ones are defined below. - */ -static int common_nsleep(clockid_t, int flags, struct timespec *t); -static void common_timer_get(struct k_itimer *, struct itimerspec *); -static int common_timer_set(struct k_itimer *, int, - struct itimerspec *, struct itimerspec *); -static int common_timer_del(struct k_itimer *timer); - -/* - * Return nonzero iff we know a priori this clockid_t value is bogus. + * Return nonzero if we know a priori this clockid_t value is bogus. */ -static inline int invalid_clockid(clockid_t which_clock) +static inline int invalid_clockid(const clockid_t which_clock) { if (which_clock < 0) /* CPU clock, posix_cpu_* will check it */ return 0; @@ -232,26 +211,32 @@ static inline int invalid_clockid(clockid_t which_clock) return 1; if (posix_clocks[which_clock].clock_getres != NULL) return 0; -#ifndef CLOCK_DISPATCH_DIRECT if (posix_clocks[which_clock].res != 0) return 0; -#endif return 1; } +/* + * Get monotonic time for posix timers + */ +static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp) +{ + ktime_get_ts(tp); + return 0; +} /* * Initialize everything, well, just everything in Posix clocks/timers ;) */ static __init int init_posix_timers(void) { - struct k_clock clock_realtime = {.res = CLOCK_REALTIME_RES, - .abs_struct = &abs_list + struct k_clock clock_realtime = { + .clock_getres = hrtimer_get_res, }; - struct k_clock clock_monotonic = {.res = CLOCK_REALTIME_RES, - .abs_struct = NULL, - .clock_get = do_posix_clock_monotonic_get, - .clock_set = do_posix_clock_nosettime + struct k_clock clock_monotonic = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_ktime_get_ts, + .clock_set = do_posix_clock_nosettime, }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); @@ -265,117 +250,17 @@ static __init int init_posix_timers(void) __initcall(init_posix_timers); -static void tstojiffie(struct timespec *tp, int res, u64 *jiff) -{ - long sec = tp->tv_sec; - long nsec = tp->tv_nsec + res - 1; - - if (nsec >= NSEC_PER_SEC) { - sec++; - nsec -= NSEC_PER_SEC; - } - - /* - * The scaling constants are defined in <linux/time.h> - * The difference between there and here is that we do the - * res rounding and compute a 64-bit result (well so does that - * but it then throws away the high bits). - */ - *jiff = (mpy_l_X_l_ll(sec, SEC_CONVERSION) + - (mpy_l_X_l_ll(nsec, NSEC_CONVERSION) >> - (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; -} - -/* - * This function adjusts the timer as needed as a result of the clock - * being set. It should only be called for absolute timers, and then - * under the abs_list lock. It computes the time difference and sets - * the new jiffies value in the timer. It also updates the timers - * reference wall_to_monotonic value. It is complicated by the fact - * that tstojiffies() only handles positive times and it needs to work - * with both positive and negative times. Also, for negative offsets, - * we need to defeat the res round up. - * - * Return is true if there is a new time, else false. - */ -static long add_clockset_delta(struct k_itimer *timr, - struct timespec *new_wall_to) -{ - struct timespec delta; - int sign = 0; - u64 exp; - - set_normalized_timespec(&delta, - new_wall_to->tv_sec - - timr->it.real.wall_to_prev.tv_sec, - new_wall_to->tv_nsec - - timr->it.real.wall_to_prev.tv_nsec); - if (likely(!(delta.tv_sec | delta.tv_nsec))) - return 0; - if (delta.tv_sec < 0) { - set_normalized_timespec(&delta, - -delta.tv_sec, - 1 - delta.tv_nsec - - posix_clocks[timr->it_clock].res); - sign++; - } - tstojiffie(&delta, posix_clocks[timr->it_clock].res, &exp); - timr->it.real.wall_to_prev = *new_wall_to; - timr->it.real.timer.expires += (sign ? -exp : exp); - return 1; -} - -static void remove_from_abslist(struct k_itimer *timr) -{ - if (!list_empty(&timr->it.real.abs_timer_entry)) { - spin_lock(&abs_list.lock); - list_del_init(&timr->it.real.abs_timer_entry); - spin_unlock(&abs_list.lock); - } -} - static void schedule_next_timer(struct k_itimer *timr) { - struct timespec new_wall_to; - struct now_struct now; - unsigned long seq; - - /* - * Set up the timer for the next interval (if there is one). - * Note: this code uses the abs_timer_lock to protect - * it.real.wall_to_prev and must hold it until exp is set, not exactly - * obvious... - - * This function is used for CLOCK_REALTIME* and - * CLOCK_MONOTONIC* timers. If we ever want to handle other - * CLOCKs, the calling code (do_schedule_next_timer) would need - * to pull the "clock" info from the timer and dispatch the - * "other" CLOCKs "next timer" code (which, I suppose should - * also be added to the k_clock structure). - */ - if (!timr->it.real.incr) + if (timr->it.real.interval.tv64 == 0) return; - do { - seq = read_seqbegin(&xtime_lock); - new_wall_to = wall_to_monotonic; - posix_get_now(&now); - } while (read_seqretry(&xtime_lock, seq)); - - if (!list_empty(&timr->it.real.abs_timer_entry)) { - spin_lock(&abs_list.lock); - add_clockset_delta(timr, &new_wall_to); - - posix_bump_timer(timr, now); - - spin_unlock(&abs_list.lock); - } else { - posix_bump_timer(timr, now); - } + timr->it_overrun += hrtimer_forward(&timr->it.real.timer, + timr->it.real.interval); timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1; ++timr->it_requeue_pending; - add_timer(&timr->it.real.timer); + hrtimer_restart(&timr->it.real.timer); } /* @@ -396,31 +281,23 @@ void do_schedule_next_timer(struct siginfo *info) timr = lock_timer(info->si_tid, &flags); - if (!timr || timr->it_requeue_pending != info->si_sys_private) - goto exit; + if (timr && timr->it_requeue_pending == info->si_sys_private) { + if (timr->it_clock < 0) + posix_cpu_timer_schedule(timr); + else + schedule_next_timer(timr); - if (timr->it_clock < 0) /* CPU clock */ - posix_cpu_timer_schedule(timr); - else - schedule_next_timer(timr); - info->si_overrun = timr->it_overrun_last; -exit: - if (timr) - unlock_timer(timr, flags); + info->si_overrun = timr->it_overrun_last; + } + + unlock_timer(timr, flags); } int posix_timer_event(struct k_itimer *timr,int si_private) { memset(&timr->sigq->info, 0, sizeof(siginfo_t)); timr->sigq->info.si_sys_private = si_private; - /* - * Send signal to the process that owns this timer. - - * This code assumes that all the possible abs_lists share the - * same lock (there is only one list at this time). If this is - * not the case, the CLOCK info would need to be used to find - * the proper abs list lock. - */ + /* Send signal to the process that owns this timer.*/ timr->sigq->info.si_signo = timr->it_sigev_signo; timr->sigq->info.si_errno = 0; @@ -454,66 +331,37 @@ EXPORT_SYMBOL_GPL(posix_timer_event); * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers. */ -static void posix_timer_fn(unsigned long __data) +static int posix_timer_fn(void *data) { - struct k_itimer *timr = (struct k_itimer *) __data; + struct k_itimer *timr = data; unsigned long flags; - unsigned long seq; - struct timespec delta, new_wall_to; - u64 exp = 0; - int do_notify = 1; + int si_private = 0; + int ret = HRTIMER_NORESTART; spin_lock_irqsave(&timr->it_lock, flags); - if (!list_empty(&timr->it.real.abs_timer_entry)) { - spin_lock(&abs_list.lock); - do { - seq = read_seqbegin(&xtime_lock); - new_wall_to = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); - set_normalized_timespec(&delta, - new_wall_to.tv_sec - - timr->it.real.wall_to_prev.tv_sec, - new_wall_to.tv_nsec - - timr->it.real.wall_to_prev.tv_nsec); - if (likely((delta.tv_sec | delta.tv_nsec ) == 0)) { - /* do nothing, timer is on time */ - } else if (delta.tv_sec < 0) { - /* do nothing, timer is already late */ - } else { - /* timer is early due to a clock set */ - tstojiffie(&delta, - posix_clocks[timr->it_clock].res, - &exp); - timr->it.real.wall_to_prev = new_wall_to; - timr->it.real.timer.expires += exp; - add_timer(&timr->it.real.timer); - do_notify = 0; - } - spin_unlock(&abs_list.lock); - } - if (do_notify) { - int si_private=0; + if (timr->it.real.interval.tv64 != 0) + si_private = ++timr->it_requeue_pending; - if (timr->it.real.incr) - si_private = ++timr->it_requeue_pending; - else { - remove_from_abslist(timr); + if (posix_timer_event(timr, si_private)) { + /* + * signal was not sent because of sig_ignor + * we will not get a call back to restart it AND + * it should be restarted. + */ + if (timr->it.real.interval.tv64 != 0) { + timr->it_overrun += + hrtimer_forward(&timr->it.real.timer, + timr->it.real.interval); + ret = HRTIMER_RESTART; } - - if (posix_timer_event(timr, si_private)) - /* - * signal was not sent because of sig_ignor - * we will not get a call back to restart it AND - * it should be restarted. - */ - schedule_next_timer(timr); } - unlock_timer(timr, flags); /* hold thru abs lock to keep irq off */ -} + unlock_timer(timr, flags); + return ret; +} -static inline struct task_struct * good_sigevent(sigevent_t * event) +static struct task_struct * good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; @@ -530,7 +378,7 @@ static inline struct task_struct * good_sigevent(sigevent_t * event) return rtn; } -void register_posix_clock(clockid_t clock_id, struct k_clock *new_clock) +void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock) { if ((unsigned) clock_id >= MAX_CLOCKS) { printk("POSIX clock register failed for clock_id %d\n", @@ -576,7 +424,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) /* Create a POSIX.1b interval timer. */ asmlinkage long -sys_timer_create(clockid_t which_clock, +sys_timer_create(const clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id) { @@ -602,8 +450,7 @@ sys_timer_create(clockid_t which_clock, goto out; } spin_lock_irq(&idr_lock); - error = idr_get_new(&posix_timers_id, - (void *) new_timer, + error = idr_get_new(&posix_timers_id, (void *) new_timer, &new_timer_id); spin_unlock_irq(&idr_lock); if (error == -EAGAIN) @@ -704,27 +551,6 @@ out: } /* - * good_timespec - * - * This function checks the elements of a timespec structure. - * - * Arguments: - * ts : Pointer to the timespec structure to check - * - * Return value: - * If a NULL pointer was passed in, or the tv_nsec field was less than 0 - * or greater than NSEC_PER_SEC, or the tv_sec field was less than 0, - * this function returns 0. Otherwise it returns 1. - */ -static int good_timespec(const struct timespec *ts) -{ - if ((!ts) || (ts->tv_sec < 0) || - ((unsigned) ts->tv_nsec >= NSEC_PER_SEC)) - return 0; - return 1; -} - -/* * Locking issues: We need to protect the result of the id look up until * we get the timer locked down so it is not deleted under us. The * removal is done under the idr spinlock so we use that here to bridge @@ -776,39 +602,39 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) static void common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { - unsigned long expires; - struct now_struct now; - - do - expires = timr->it.real.timer.expires; - while ((volatile long) (timr->it.real.timer.expires) != expires); - - posix_get_now(&now); - - if (expires && - ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) && - !timr->it.real.incr && - posix_time_before(&timr->it.real.timer, &now)) - timr->it.real.timer.expires = expires = 0; - if (expires) { - if (timr->it_requeue_pending & REQUEUE_PENDING || - (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { - posix_bump_timer(timr, now); - expires = timr->it.real.timer.expires; - } - else - if (!timer_pending(&timr->it.real.timer)) - expires = 0; - if (expires) - expires -= now.jiffies; - } - jiffies_to_timespec(expires, &cur_setting->it_value); - jiffies_to_timespec(timr->it.real.incr, &cur_setting->it_interval); + ktime_t remaining; + struct hrtimer *timer = &timr->it.real.timer; + + memset(cur_setting, 0, sizeof(struct itimerspec)); + remaining = hrtimer_get_remaining(timer); - if (cur_setting->it_value.tv_sec < 0) { + /* Time left ? or timer pending */ + if (remaining.tv64 > 0 || hrtimer_active(timer)) + goto calci; + /* interval timer ? */ + if (timr->it.real.interval.tv64 == 0) + return; + /* + * When a requeue is pending or this is a SIGEV_NONE timer + * move the expiry time forward by intervals, so expiry is > + * now. + */ + if (timr->it_requeue_pending & REQUEUE_PENDING || + (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { + timr->it_overrun += + hrtimer_forward(timer, timr->it.real.interval); + remaining = hrtimer_get_remaining(timer); + } + calci: + /* interval timer ? */ + if (timr->it.real.interval.tv64 != 0) + cur_setting->it_interval = + ktime_to_timespec(timr->it.real.interval); + /* Return 0 only, when the timer is expired and not pending */ + if (remaining.tv64 <= 0) cur_setting->it_value.tv_nsec = 1; - cur_setting->it_value.tv_sec = 0; - } + else + cur_setting->it_value = ktime_to_timespec(remaining); } /* Get the time remaining on a POSIX.1b interval timer. */ @@ -832,6 +658,7 @@ sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting) return 0; } + /* * Get the number of overruns of a POSIX.1b interval timer. This is to * be the overrun of the timer last delivered. At the same time we are @@ -841,7 +668,6 @@ sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting) * the call back to do_schedule_next_timer(). So all we need to do is * to pick up the frozen overrun. */ - asmlinkage long sys_timer_getoverrun(timer_t timer_id) { @@ -858,153 +684,55 @@ sys_timer_getoverrun(timer_t timer_id) return overrun; } -/* - * Adjust for absolute time - * - * If absolute time is given and it is not CLOCK_MONOTONIC, we need to - * adjust for the offset between the timer clock (CLOCK_MONOTONIC) and - * what ever clock he is using. - * - * If it is relative time, we need to add the current (CLOCK_MONOTONIC) - * time to it to get the proper time for the timer. - */ -static int adjust_abs_time(struct k_clock *clock, struct timespec *tp, - int abs, u64 *exp, struct timespec *wall_to) -{ - struct timespec now; - struct timespec oc = *tp; - u64 jiffies_64_f; - int rtn =0; - - if (abs) { - /* - * The mask pick up the 4 basic clocks - */ - if (!((clock - &posix_clocks[0]) & ~CLOCKS_MASK)) { - jiffies_64_f = do_posix_clock_monotonic_gettime_parts( - &now, wall_to); - /* - * If we are doing a MONOTONIC clock - */ - if((clock - &posix_clocks[0]) & CLOCKS_MONO){ - now.tv_sec += wall_to->tv_sec; - now.tv_nsec += wall_to->tv_nsec; - } - } else { - /* - * Not one of the basic clocks - */ - clock->clock_get(clock - posix_clocks, &now); - jiffies_64_f = get_jiffies_64(); - } - /* - * Take away now to get delta and normalize - */ - set_normalized_timespec(&oc, oc.tv_sec - now.tv_sec, - oc.tv_nsec - now.tv_nsec); - }else{ - jiffies_64_f = get_jiffies_64(); - } - /* - * Check if the requested time is prior to now (if so set now) - */ - if (oc.tv_sec < 0) - oc.tv_sec = oc.tv_nsec = 0; - - if (oc.tv_sec | oc.tv_nsec) - set_normalized_timespec(&oc, oc.tv_sec, - oc.tv_nsec + clock->res); - tstojiffie(&oc, clock->res, exp); - - /* - * Check if the requested time is more than the timer code - * can handle (if so we error out but return the value too). - */ - if (*exp > ((u64)MAX_JIFFY_OFFSET)) - /* - * This is a considered response, not exactly in - * line with the standard (in fact it is silent on - * possible overflows). We assume such a large - * value is ALMOST always a programming error and - * try not to compound it by setting a really dumb - * value. - */ - rtn = -EINVAL; - /* - * return the actual jiffies expire time, full 64 bits - */ - *exp += jiffies_64_f; - return rtn; -} /* Set a POSIX.1b interval timer. */ /* timr->it_lock is taken. */ -static inline int +static int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { - struct k_clock *clock = &posix_clocks[timr->it_clock]; - u64 expire_64; + struct hrtimer *timer = &timr->it.real.timer; if (old_setting) common_timer_get(timr, old_setting); /* disable the timer */ - timr->it.real.incr = 0; + timr->it.real.interval.tv64 = 0; /* * careful here. If smp we could be in the "fire" routine which will * be spinning as we hold the lock. But this is ONLY an SMP issue. */ - if (try_to_del_timer_sync(&timr->it.real.timer) < 0) { -#ifdef CONFIG_SMP - /* - * It can only be active if on an other cpu. Since - * we have cleared the interval stuff above, it should - * clear once we release the spin lock. Of course once - * we do that anything could happen, including the - * complete melt down of the timer. So return with - * a "retry" exit status. - */ + if (hrtimer_try_to_cancel(timer) < 0) return TIMER_RETRY; -#endif - } - - remove_from_abslist(timr); timr->it_requeue_pending = (timr->it_requeue_pending + 2) & ~REQUEUE_PENDING; timr->it_overrun_last = 0; - timr->it_overrun = -1; - /* - *switch off the timer when it_value is zero - */ - if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) { - timr->it.real.timer.expires = 0; - return 0; - } - if (adjust_abs_time(clock, - &new_setting->it_value, flags & TIMER_ABSTIME, - &expire_64, &(timr->it.real.wall_to_prev))) { - return -EINVAL; - } - timr->it.real.timer.expires = (unsigned long)expire_64; - tstojiffie(&new_setting->it_interval, clock->res, &expire_64); - timr->it.real.incr = (unsigned long)expire_64; + /* switch off the timer when it_value is zero */ + if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) + return 0; - /* - * We do not even queue SIGEV_NONE timers! But we do put them - * in the abs list so we can do that right. + /* Posix madness. Only absolute CLOCK_REALTIME timers + * are affected by clock sets. So we must reiniatilize + * the timer. */ - if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)) - add_timer(&timr->it.real.timer); - - if (flags & TIMER_ABSTIME && clock->abs_struct) { - spin_lock(&clock->abs_struct->lock); - list_add_tail(&(timr->it.real.abs_timer_entry), - &(clock->abs_struct->list)); - spin_unlock(&clock->abs_struct->lock); - } + if (timr->it_clock == CLOCK_REALTIME && (flags & TIMER_ABSTIME)) + hrtimer_rebase(timer, CLOCK_REALTIME); + else + hrtimer_rebase(timer, CLOCK_MONOTONIC); + + timer->expires = timespec_to_ktime(new_setting->it_value); + + /* Convert interval */ + timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); + + /* SIGEV_NONE timers are not queued ! See common_timer_get */ + if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) + return 0; + + hrtimer_start(timer, timer->expires, (flags & TIMER_ABSTIME) ? + HRTIMER_ABS : HRTIMER_REL); return 0; } @@ -1026,8 +754,8 @@ sys_timer_settime(timer_t timer_id, int flags, if (copy_from_user(&new_spec, new_setting, sizeof (new_spec))) return -EFAULT; - if ((!good_timespec(&new_spec.it_interval)) || - (!good_timespec(&new_spec.it_value))) + if (!timespec_valid(&new_spec.it_interval) || + !timespec_valid(&new_spec.it_value)) return -EINVAL; retry: timr = lock_timer(timer_id, &flag); @@ -1043,8 +771,8 @@ retry: goto retry; } - if (old_setting && !error && copy_to_user(old_setting, - &old_spec, sizeof (old_spec))) + if (old_setting && !error && + copy_to_user(old_setting, &old_spec, sizeof (old_spec))) error = -EFAULT; return error; @@ -1052,24 +780,10 @@ retry: static inline int common_timer_del(struct k_itimer *timer) { - timer->it.real.incr = 0; + timer->it.real.interval.tv64 = 0; - if (try_to_del_timer_sync(&timer->it.real.timer) < 0) { -#ifdef CONFIG_SMP - /* - * It can only be active if on an other cpu. Since - * we have cleared the interval stuff above, it should - * clear once we release the spin lock. Of course once - * we do that anything could happen, including the - * complete melt down of the timer. So return with - * a "retry" exit status. - */ + if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0) return TIMER_RETRY; -#endif - } - - remove_from_abslist(timer); - return 0; } @@ -1085,24 +799,16 @@ sys_timer_delete(timer_t timer_id) struct k_itimer *timer; long flags; -#ifdef CONFIG_SMP - int error; retry_delete: -#endif timer = lock_timer(timer_id, &flags); if (!timer) return -EINVAL; -#ifdef CONFIG_SMP - error = timer_delete_hook(timer); - - if (error == TIMER_RETRY) { + if (timer_delete_hook(timer) == TIMER_RETRY) { unlock_timer(timer, flags); goto retry_delete; } -#else - timer_delete_hook(timer); -#endif + spin_lock(¤t->sighand->siglock); list_del(&timer->list); spin_unlock(¤t->sighand->siglock); @@ -1119,29 +825,21 @@ retry_delete: release_posix_timer(timer, IT_ID_SET); return 0; } + /* * return timer owned by the process, used by exit_itimers */ -static inline void itimer_delete(struct k_itimer *timer) +static void itimer_delete(struct k_itimer *timer) { unsigned long flags; -#ifdef CONFIG_SMP - int error; retry_delete: -#endif spin_lock_irqsave(&timer->it_lock, flags); -#ifdef CONFIG_SMP - error = timer_delete_hook(timer); - - if (error == TIMER_RETRY) { + if (timer_delete_hook(timer) == TIMER_RETRY) { unlock_timer(timer, flags); goto retry_delete; } -#else - timer_delete_hook(timer); -#endif list_del(&timer->list); /* * This keeps any tasks waiting on the spin lock from thinking @@ -1170,57 +868,8 @@ void exit_itimers(struct signal_struct *sig) } } -/* - * And now for the "clock" calls - * - * These functions are called both from timer functions (with the timer - * spin_lock_irq() held and from clock calls with no locking. They must - * use the save flags versions of locks. - */ - -/* - * We do ticks here to avoid the irq lock ( they take sooo long). - * The seqlock is great here. Since we a reader, we don't really care - * if we are interrupted since we don't take lock that will stall us or - * any other cpu. Voila, no irq lock is needed. - * - */ - -static u64 do_posix_clock_monotonic_gettime_parts( - struct timespec *tp, struct timespec *mo) -{ - u64 jiff; - unsigned int seq; - - do { - seq = read_seqbegin(&xtime_lock); - getnstimeofday(tp); - *mo = wall_to_monotonic; - jiff = jiffies_64; - - } while(read_seqretry(&xtime_lock, seq)); - - return jiff; -} - -static int do_posix_clock_monotonic_get(clockid_t clock, struct timespec *tp) -{ - struct timespec wall_to_mono; - - do_posix_clock_monotonic_gettime_parts(tp, &wall_to_mono); - - set_normalized_timespec(tp, tp->tv_sec + wall_to_mono.tv_sec, - tp->tv_nsec + wall_to_mono.tv_nsec); - - return 0; -} - -int do_posix_clock_monotonic_gettime(struct timespec *tp) -{ - return do_posix_clock_monotonic_get(CLOCK_MONOTONIC, tp); -} - -int do_posix_clock_nosettime(clockid_t clockid, struct timespec *tp) +/* Not available / possible... functions */ +int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp) { return -EINVAL; } @@ -1232,7 +881,8 @@ int do_posix_clock_notimer_create(struct k_itimer *timer) } EXPORT_SYMBOL_GPL(do_posix_clock_notimer_create); -int do_posix_clock_nonanosleep(clockid_t clock, int flags, struct timespec *t) +int do_posix_clock_nonanosleep(const clockid_t clock, int flags, + struct timespec *t, struct timespec __user *r) { #ifndef ENOTSUP return -EOPNOTSUPP; /* aka ENOTSUP in userland for POSIX */ @@ -1242,8 +892,8 @@ int do_posix_clock_nonanosleep(clockid_t clock, int flags, struct timespec *t) } EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep); -asmlinkage long -sys_clock_settime(clockid_t which_clock, const struct timespec __user *tp) +asmlinkage long sys_clock_settime(const clockid_t which_clock, + const struct timespec __user *tp) { struct timespec new_tp; @@ -1256,7 +906,7 @@ sys_clock_settime(clockid_t which_clock, const struct timespec __user *tp) } asmlinkage long -sys_clock_gettime(clockid_t which_clock, struct timespec __user *tp) +sys_clock_gettime(const clockid_t which_clock, struct timespec __user *tp) { struct timespec kernel_tp; int error; @@ -1273,7 +923,7 @@ sys_clock_gettime(clockid_t which_clock, struct timespec __user *tp) } asmlinkage long -sys_clock_getres(clockid_t which_clock, struct timespec __user *tp) +sys_clock_getres(const clockid_t which_clock, struct timespec __user *tp) { struct timespec rtn_tp; int error; @@ -1292,117 +942,34 @@ sys_clock_getres(clockid_t which_clock, struct timespec __user *tp) } /* - * The standard says that an absolute nanosleep call MUST wake up at - * the requested time in spite of clock settings. Here is what we do: - * For each nanosleep call that needs it (only absolute and not on - * CLOCK_MONOTONIC* (as it can not be set)) we thread a little structure - * into the "nanosleep_abs_list". All we need is the task_struct pointer. - * When ever the clock is set we just wake up all those tasks. The rest - * is done by the while loop in clock_nanosleep(). - * - * On locking, clock_was_set() is called from update_wall_clock which - * holds (or has held for it) a write_lock_irq( xtime_lock) and is - * called from the timer bh code. Thus we need the irq save locks. - * - * Also, on the call from update_wall_clock, that is done as part of a - * softirq thing. We don't want to delay the system that much (possibly - * long list of timers to fix), so we defer that work to keventd. + * nanosleep for monotonic and realtime clocks */ - -static DECLARE_WAIT_QUEUE_HEAD(nanosleep_abs_wqueue); -static DECLARE_WORK(clock_was_set_work, (void(*)(void*))clock_was_set, NULL); - -static DECLARE_MUTEX(clock_was_set_lock); - -void clock_was_set(void) -{ - struct k_itimer *timr; - struct timespec new_wall_to; - LIST_HEAD(cws_list); - unsigned long seq; - - - if (unlikely(in_interrupt())) { - schedule_work(&clock_was_set_work); - return; +static int common_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsave, struct timespec __user *rmtp) +{ + int mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL; + int clockid = which_clock; + + switch (which_clock) { + case CLOCK_REALTIME: + /* Posix madness. Only absolute timers on clock realtime + are affected by clock set. */ + if (mode != HRTIMER_ABS) + clockid = CLOCK_MONOTONIC; + case CLOCK_MONOTONIC: + break; + default: + return -EINVAL; } - wake_up_all(&nanosleep_abs_wqueue); - - /* - * Check if there exist TIMER_ABSTIME timers to correct. - * - * Notes on locking: This code is run in task context with irq - * on. We CAN be interrupted! All other usage of the abs list - * lock is under the timer lock which holds the irq lock as - * well. We REALLY don't want to scan the whole list with the - * interrupt system off, AND we would like a sequence lock on - * this code as well. Since we assume that the clock will not - * be set often, it seems ok to take and release the irq lock - * for each timer. In fact add_timer will do this, so this is - * not an issue. So we know when we are done, we will move the - * whole list to a new location. Then as we process each entry, - * we will move it to the actual list again. This way, when our - * copy is empty, we are done. We are not all that concerned - * about preemption so we will use a semaphore lock to protect - * aginst reentry. This way we will not stall another - * processor. It is possible that this may delay some timers - * that should have expired, given the new clock, but even this - * will be minimal as we will always update to the current time, - * even if it was set by a task that is waiting for entry to - * this code. Timers that expire too early will be caught by - * the expire code and restarted. - - * Absolute timers that repeat are left in the abs list while - * waiting for the task to pick up the signal. This means we - * may find timers that are not in the "add_timer" list, but are - * in the abs list. We do the same thing for these, save - * putting them back in the "add_timer" list. (Note, these are - * left in the abs list mainly to indicate that they are - * ABSOLUTE timers, a fact that is used by the re-arm code, and - * for which we have no other flag.) - - */ - - down(&clock_was_set_lock); - spin_lock_irq(&abs_list.lock); - list_splice_init(&abs_list.list, &cws_list); - spin_unlock_irq(&abs_list.lock); - do { - do { - seq = read_seqbegin(&xtime_lock); - new_wall_to = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); - - spin_lock_irq(&abs_list.lock); - if (list_empty(&cws_list)) { - spin_unlock_irq(&abs_list.lock); - break; - } - timr = list_entry(cws_list.next, struct k_itimer, - it.real.abs_timer_entry); - - list_del_init(&timr->it.real.abs_timer_entry); - if (add_clockset_delta(timr, &new_wall_to) && - del_timer(&timr->it.real.timer)) /* timer run yet? */ - add_timer(&timr->it.real.timer); - list_add(&timr->it.real.abs_timer_entry, &abs_list.list); - spin_unlock_irq(&abs_list.lock); - } while (1); - - up(&clock_was_set_lock); + return hrtimer_nanosleep(tsave, rmtp, mode, clockid); } -long clock_nanosleep_restart(struct restart_block *restart_block); - asmlinkage long -sys_clock_nanosleep(clockid_t which_clock, int flags, +sys_clock_nanosleep(const clockid_t which_clock, int flags, const struct timespec __user *rqtp, struct timespec __user *rmtp) { struct timespec t; - struct restart_block *restart_block = - &(current_thread_info()->restart_block); - int ret; if (invalid_clockid(which_clock)) return -EINVAL; @@ -1410,125 +977,9 @@ sys_clock_nanosleep(clockid_t which_clock, int flags, if (copy_from_user(&t, rqtp, sizeof (struct timespec))) return -EFAULT; - if ((unsigned) t.tv_nsec >= NSEC_PER_SEC || t.tv_sec < 0) + if (!timespec_valid(&t)) return -EINVAL; - /* - * Do this here as nsleep function does not have the real address. - */ - restart_block->arg1 = (unsigned long)rmtp; - - ret = CLOCK_DISPATCH(which_clock, nsleep, (which_clock, flags, &t)); - - if ((ret == -ERESTART_RESTARTBLOCK) && rmtp && - copy_to_user(rmtp, &t, sizeof (t))) - return -EFAULT; - return ret; -} - - -static int common_nsleep(clockid_t which_clock, - int flags, struct timespec *tsave) -{ - struct timespec t, dum; - DECLARE_WAITQUEUE(abs_wqueue, current); - u64 rq_time = (u64)0; - s64 left; - int abs; - struct restart_block *restart_block = - ¤t_thread_info()->restart_block; - - abs_wqueue.flags = 0; - abs = flags & TIMER_ABSTIME; - - if (restart_block->fn == clock_nanosleep_restart) { - /* - * Interrupted by a non-delivered signal, pick up remaining - * time and continue. Remaining time is in arg2 & 3. - */ - restart_block->fn = do_no_restart_syscall; - - rq_time = restart_block->arg3; - rq_time = (rq_time << 32) + restart_block->arg2; - if (!rq_time) - return -EINTR; - left = rq_time - get_jiffies_64(); - if (left <= (s64)0) - return 0; /* Already passed */ - } - - if (abs && (posix_clocks[which_clock].clock_get != - posix_clocks[CLOCK_MONOTONIC].clock_get)) - add_wait_queue(&nanosleep_abs_wqueue, &abs_wqueue); - - do { - t = *tsave; - if (abs || !rq_time) { - adjust_abs_time(&posix_clocks[which_clock], &t, abs, - &rq_time, &dum); - } - - left = rq_time - get_jiffies_64(); - if (left >= (s64)MAX_JIFFY_OFFSET) - left = (s64)MAX_JIFFY_OFFSET; - if (left < (s64)0) - break; - - schedule_timeout_interruptible(left); - - left = rq_time - get_jiffies_64(); - } while (left > (s64)0 && !test_thread_flag(TIF_SIGPENDING)); - - if (abs_wqueue.task_list.next) - finish_wait(&nanosleep_abs_wqueue, &abs_wqueue); - - if (left > (s64)0) { - - /* - * Always restart abs calls from scratch to pick up any - * clock shifting that happened while we are away. - */ - if (abs) - return -ERESTARTNOHAND; - - left *= TICK_NSEC; - tsave->tv_sec = div_long_long_rem(left, - NSEC_PER_SEC, - &tsave->tv_nsec); - /* - * Restart works by saving the time remaing in - * arg2 & 3 (it is 64-bits of jiffies). The other - * info we need is the clock_id (saved in arg0). - * The sys_call interface needs the users - * timespec return address which _it_ saves in arg1. - * Since we have cast the nanosleep call to a clock_nanosleep - * both can be restarted with the same code. - */ - restart_block->fn = clock_nanosleep_restart; - restart_block->arg0 = which_clock; - /* - * Caller sets arg1 - */ - restart_block->arg2 = rq_time & 0xffffffffLL; - restart_block->arg3 = rq_time >> 32; - - return -ERESTART_RESTARTBLOCK; - } - - return 0; -} -/* - * This will restart clock_nanosleep. - */ -long -clock_nanosleep_restart(struct restart_block *restart_block) -{ - struct timespec t; - int ret = common_nsleep(restart_block->arg0, 0, &t); - - if ((ret == -ERESTART_RESTARTBLOCK) && restart_block->arg1 && - copy_to_user((struct timespec __user *)(restart_block->arg1), &t, - sizeof (t))) - return -EFAULT; - return ret; + return CLOCK_DISPATCH(which_clock, nsleep, + (which_clock, flags, &t, rmtp)); } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 5ec248cb7f4..9fd8d4f0359 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -38,7 +38,7 @@ config PM_DEBUG config SOFTWARE_SUSPEND bool "Software Suspend" - depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FVR || PPC32) && !SMP) + depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FRV || PPC32) && !SMP) ---help--- Enable the possibility of suspending the machine. It doesn't need APM. diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 027322a564f..e03d85e5529 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -24,10 +24,11 @@ extern suspend_disk_method_t pm_disk_mode; +extern int swsusp_shrink_memory(void); extern int swsusp_suspend(void); -extern int swsusp_write(void); +extern int swsusp_write(struct pbe *pblist, unsigned int nr_pages); extern int swsusp_check(void); -extern int swsusp_read(void); +extern int swsusp_read(struct pbe **pblist_ptr); extern void swsusp_close(void); extern int swsusp_resume(void); @@ -52,7 +53,7 @@ static void power_down(suspend_disk_method_t mode) switch(mode) { case PM_DISK_PLATFORM: - kernel_power_off_prepare(); + kernel_shutdown_prepare(SYSTEM_SUSPEND_DISK); error = pm_ops->enter(PM_SUSPEND_DISK); break; case PM_DISK_SHUTDOWN: @@ -73,31 +74,6 @@ static void power_down(suspend_disk_method_t mode) static int in_suspend __nosavedata = 0; -/** - * free_some_memory - Try to free as much memory as possible - * - * ... but do not OOM-kill anyone - * - * Notice: all userland should be stopped at this point, or - * livelock is possible. - */ - -static void free_some_memory(void) -{ - unsigned int i = 0; - unsigned int tmp; - unsigned long pages = 0; - char *p = "-\\|/"; - - printk("Freeing memory... "); - while ((tmp = shrink_all_memory(10000))) { - pages += tmp; - printk("\b%c", p[i++ % 4]); - } - printk("\bdone (%li pages freed)\n", pages); -} - - static inline void platform_finish(void) { if (pm_disk_mode == PM_DISK_PLATFORM) { @@ -119,16 +95,9 @@ static int prepare_processes(void) goto thaw; } - if (pm_disk_mode == PM_DISK_PLATFORM) { - if (pm_ops && pm_ops->prepare) { - if ((error = pm_ops->prepare(PM_SUSPEND_DISK))) - goto thaw; - } - } - /* Free memory before shutting down devices. */ - free_some_memory(); - return 0; + if (!(error = swsusp_shrink_memory())) + return 0; thaw: thaw_processes(); enable_nonboot_cpus(); @@ -176,7 +145,7 @@ int pm_suspend_disk(void) if (in_suspend) { device_resume(); pr_debug("PM: writing image.\n"); - error = swsusp_write(); + error = swsusp_write(pagedir_nosave, nr_copy_pages); if (!error) power_down(pm_disk_mode); else { @@ -247,7 +216,7 @@ static int software_resume(void) pr_debug("PM: Reading swsusp image.\n"); - if ((error = swsusp_read())) { + if ((error = swsusp_read(&pagedir_nosave))) { swsusp_free(); goto Thaw; } @@ -363,37 +332,55 @@ static ssize_t resume_show(struct subsystem * subsys, char *buf) MINOR(swsusp_resume_device)); } -static ssize_t resume_store(struct subsystem * subsys, const char * buf, size_t n) +static ssize_t resume_store(struct subsystem *subsys, const char *buf, size_t n) { - int len; - char *p; unsigned int maj, min; - int error = -EINVAL; dev_t res; + int ret = -EINVAL; - p = memchr(buf, '\n', n); - len = p ? p - buf : n; + if (sscanf(buf, "%u:%u", &maj, &min) != 2) + goto out; - if (sscanf(buf, "%u:%u", &maj, &min) == 2) { - res = MKDEV(maj,min); - if (maj == MAJOR(res) && min == MINOR(res)) { - down(&pm_sem); - swsusp_resume_device = res; - up(&pm_sem); - printk("Attempting manual resume\n"); - noresume = 0; - software_resume(); - } - } + res = MKDEV(maj,min); + if (maj != MAJOR(res) || min != MINOR(res)) + goto out; - return error >= 0 ? n : error; + down(&pm_sem); + swsusp_resume_device = res; + up(&pm_sem); + printk("Attempting manual resume\n"); + noresume = 0; + software_resume(); + ret = n; +out: + return ret; } power_attr(resume); +static ssize_t image_size_show(struct subsystem * subsys, char *buf) +{ + return sprintf(buf, "%u\n", image_size); +} + +static ssize_t image_size_store(struct subsystem * subsys, const char * buf, size_t n) +{ + unsigned int size; + + if (sscanf(buf, "%u", &size) == 1) { + image_size = size; + return n; + } + + return -EINVAL; +} + +power_attr(image_size); + static struct attribute * g[] = { &disk_attr.attr, &resume_attr.attr, + &image_size_attr.attr, NULL, }; diff --git a/kernel/power/power.h b/kernel/power/power.h index 6c042b5ee14..7e8492fd142 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -9,19 +9,13 @@ #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) #endif -#define MAX_PBES ((PAGE_SIZE - sizeof(struct new_utsname) \ - - 4 - 3*sizeof(unsigned long) - sizeof(int) \ - - sizeof(void *)) / sizeof(swp_entry_t)) - struct swsusp_info { struct new_utsname uts; u32 version_code; unsigned long num_physpages; int cpus; unsigned long image_pages; - unsigned long pagedir_pages; - suspend_pagedir_t * suspend_pagedir; - swp_entry_t pagedir[MAX_PBES]; + unsigned long pages; } __attribute__((aligned(PAGE_SIZE))); @@ -48,25 +42,27 @@ static struct subsys_attribute _name##_attr = { \ extern struct subsystem power_subsys; -extern int freeze_processes(void); -extern void thaw_processes(void); - extern int pm_prepare_console(void); extern void pm_restore_console(void); - /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; extern unsigned int nr_copy_pages; -extern suspend_pagedir_t *pagedir_nosave; -extern suspend_pagedir_t *pagedir_save; +extern struct pbe *pagedir_nosave; + +/* Preferred image size in MB (default 500) */ +extern unsigned int image_size; extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); +extern unsigned int count_data_pages(void); extern void free_pagedir(struct pbe *pblist); +extern void release_eaten_pages(void); extern struct pbe *alloc_pagedir(unsigned nr_pages, gfp_t gfp_mask, int safe_needed); -extern void create_pbe_list(struct pbe *pblist, unsigned nr_pages); extern void swsusp_free(void); extern int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed); +extern unsigned int snapshot_nr_pages(void); +extern struct pbe *snapshot_pblist(void); +extern void snapshot_pblist_set(struct pbe *pblist); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 4a6dbcefd37..41f66365f0d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -33,7 +33,35 @@ #include "power.h" +struct pbe *pagedir_nosave; +unsigned int nr_copy_pages; + #ifdef CONFIG_HIGHMEM +unsigned int count_highmem_pages(void) +{ + struct zone *zone; + unsigned long zone_pfn; + unsigned int n = 0; + + for_each_zone (zone) + if (is_highmem(zone)) { + mark_free_pages(zone); + for (zone_pfn = 0; zone_pfn < zone->spanned_pages; zone_pfn++) { + struct page *page; + unsigned long pfn = zone_pfn + zone->zone_start_pfn; + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageReserved(page)) + continue; + if (PageNosaveFree(page)) + continue; + n++; + } + } + return n; +} + struct highmem_page { char *data; struct page *page; @@ -149,17 +177,15 @@ static int saveable(struct zone *zone, unsigned long *zone_pfn) BUG_ON(PageReserved(page) && PageNosave(page)); if (PageNosave(page)) return 0; - if (PageReserved(page) && pfn_is_nosave(pfn)) { - pr_debug("[nosave pfn 0x%lx]", pfn); + if (PageReserved(page) && pfn_is_nosave(pfn)) return 0; - } if (PageNosaveFree(page)) return 0; return 1; } -static unsigned count_data_pages(void) +unsigned int count_data_pages(void) { struct zone *zone; unsigned long zone_pfn; @@ -244,7 +270,7 @@ static inline void fill_pb_page(struct pbe *pbpage) * of memory pages allocated with alloc_pagedir() */ -void create_pbe_list(struct pbe *pblist, unsigned int nr_pages) +static inline void create_pbe_list(struct pbe *pblist, unsigned int nr_pages) { struct pbe *pbpage, *p; unsigned int num = PBES_PER_PAGE; @@ -261,7 +287,35 @@ void create_pbe_list(struct pbe *pblist, unsigned int nr_pages) p->next = p + 1; p->next = NULL; } - pr_debug("create_pbe_list(): initialized %d PBEs\n", num); +} + +/** + * On resume it is necessary to trace and eventually free the unsafe + * pages that have been allocated, because they are needed for I/O + * (on x86-64 we likely will "eat" these pages once again while + * creating the temporary page translation tables) + */ + +struct eaten_page { + struct eaten_page *next; + char padding[PAGE_SIZE - sizeof(void *)]; +}; + +static struct eaten_page *eaten_pages = NULL; + +void release_eaten_pages(void) +{ + struct eaten_page *p, *q; + + p = eaten_pages; + while (p) { + q = p->next; + /* We don't want swsusp_free() to free this page again */ + ClearPageNosave(virt_to_page(p)); + free_page((unsigned long)p); + p = q; + } + eaten_pages = NULL; } /** @@ -282,9 +336,12 @@ static inline void *alloc_image_page(gfp_t gfp_mask, int safe_needed) if (safe_needed) do { res = (void *)get_zeroed_page(gfp_mask); - if (res && PageNosaveFree(virt_to_page(res))) + if (res && PageNosaveFree(virt_to_page(res))) { /* This is for swsusp_free() */ SetPageNosave(virt_to_page(res)); + ((struct eaten_page *)res)->next = eaten_pages; + eaten_pages = res; + } } while (res && PageNosaveFree(virt_to_page(res))); else res = (void *)get_zeroed_page(gfp_mask); @@ -332,7 +389,8 @@ struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed if (!pbe) { /* get_zeroed_page() failed */ free_pagedir(pblist); pblist = NULL; - } + } else + create_pbe_list(pblist, nr_pages); return pblist; } @@ -370,8 +428,14 @@ void swsusp_free(void) static int enough_free_mem(unsigned int nr_pages) { - pr_debug("swsusp: available memory: %u pages\n", nr_free_pages()); - return nr_free_pages() > (nr_pages + PAGES_FOR_IO + + struct zone *zone; + unsigned int n = 0; + + for_each_zone (zone) + if (!is_highmem(zone)) + n += zone->free_pages; + pr_debug("swsusp: available memory: %u pages\n", n); + return n > (nr_pages + PAGES_FOR_IO + (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE); } @@ -395,7 +459,6 @@ static struct pbe *swsusp_alloc(unsigned int nr_pages) printk(KERN_ERR "suspend: Allocating pagedir failed.\n"); return NULL; } - create_pbe_list(pblist, nr_pages); if (alloc_data_pages(pblist, GFP_ATOMIC | __GFP_COLD, 0)) { printk(KERN_ERR "suspend: Allocating image pages failed.\n"); @@ -421,10 +484,6 @@ asmlinkage int swsusp_save(void) (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE, PAGES_FOR_IO, nr_free_pages()); - /* This is needed because of the fixed size of swsusp_info */ - if (MAX_PBES < (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE) - return -ENOSPC; - if (!enough_free_mem(nr_pages)) { printk(KERN_ERR "swsusp: Not enough free memory\n"); return -ENOMEM; diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index c05f46e7348..55a18d26abe 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -30,8 +30,8 @@ * Alex Badea <vampire@go.ro>: * Fixed runaway init * - * Andreas Steinmetz <ast@domdv.de>: - * Added encrypted suspend option + * Rafael J. Wysocki <rjw@sisk.pl> + * Added the swap map data structure and reworked the handling of swap * * More state savers are welcome. Especially for the scsi layer... * @@ -67,44 +67,33 @@ #include <asm/tlbflush.h> #include <asm/io.h> -#include <linux/random.h> -#include <linux/crypto.h> -#include <asm/scatterlist.h> - #include "power.h" +/* + * Preferred image size in MB (tunable via /sys/power/image_size). + * When it is set to N, swsusp will do its best to ensure the image + * size will not exceed N MB, but if that is impossible, it will + * try to create the smallest image possible. + */ +unsigned int image_size = 500; + #ifdef CONFIG_HIGHMEM +unsigned int count_highmem_pages(void); int save_highmem(void); int restore_highmem(void); #else static int save_highmem(void) { return 0; } static int restore_highmem(void) { return 0; } +static unsigned int count_highmem_pages(void) { return 0; } #endif -#define CIPHER "aes" -#define MAXKEY 32 -#define MAXIV 32 - extern char resume_file[]; -/* Local variables that should not be affected by save */ -unsigned int nr_copy_pages __nosavedata = 0; - -/* Suspend pagedir is allocated before final copy, therefore it - must be freed after resume - - Warning: this is even more evil than it seems. Pagedirs this file - talks about are completely different from page directories used by - MMU hardware. - */ -suspend_pagedir_t *pagedir_nosave __nosavedata = NULL; - #define SWSUSP_SIG "S1SUSPEND" static struct swsusp_header { - char reserved[PAGE_SIZE - 20 - MAXKEY - MAXIV - sizeof(swp_entry_t)]; - u8 key_iv[MAXKEY+MAXIV]; - swp_entry_t swsusp_info; + char reserved[PAGE_SIZE - 20 - sizeof(swp_entry_t)]; + swp_entry_t image; char orig_sig[10]; char sig[10]; } __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header; @@ -115,140 +104,9 @@ static struct swsusp_info swsusp_info; * Saving part... */ -/* We memorize in swapfile_used what swap devices are used for suspension */ -#define SWAPFILE_UNUSED 0 -#define SWAPFILE_SUSPEND 1 /* This is the suspending device */ -#define SWAPFILE_IGNORED 2 /* Those are other swap devices ignored for suspension */ - -static unsigned short swapfile_used[MAX_SWAPFILES]; -static unsigned short root_swap; - -static int write_page(unsigned long addr, swp_entry_t *loc); -static int bio_read_page(pgoff_t page_off, void *page); - -static u8 key_iv[MAXKEY+MAXIV]; - -#ifdef CONFIG_SWSUSP_ENCRYPT - -static int crypto_init(int mode, void **mem) -{ - int error = 0; - int len; - char *modemsg; - struct crypto_tfm *tfm; - - modemsg = mode ? "suspend not possible" : "resume not possible"; - - tfm = crypto_alloc_tfm(CIPHER, CRYPTO_TFM_MODE_CBC); - if(!tfm) { - printk(KERN_ERR "swsusp: no tfm, %s\n", modemsg); - error = -EINVAL; - goto out; - } - - if(MAXKEY < crypto_tfm_alg_min_keysize(tfm)) { - printk(KERN_ERR "swsusp: key buffer too small, %s\n", modemsg); - error = -ENOKEY; - goto fail; - } - - if (mode) - get_random_bytes(key_iv, MAXKEY+MAXIV); - - len = crypto_tfm_alg_max_keysize(tfm); - if (len > MAXKEY) - len = MAXKEY; - - if (crypto_cipher_setkey(tfm, key_iv, len)) { - printk(KERN_ERR "swsusp: key setup failure, %s\n", modemsg); - error = -EKEYREJECTED; - goto fail; - } - - len = crypto_tfm_alg_ivsize(tfm); - - if (MAXIV < len) { - printk(KERN_ERR "swsusp: iv buffer too small, %s\n", modemsg); - error = -EOVERFLOW; - goto fail; - } - - crypto_cipher_set_iv(tfm, key_iv+MAXKEY, len); - - *mem=(void *)tfm; - - goto out; - -fail: crypto_free_tfm(tfm); -out: return error; -} - -static __inline__ void crypto_exit(void *mem) -{ - crypto_free_tfm((struct crypto_tfm *)mem); -} - -static __inline__ int crypto_write(struct pbe *p, void *mem) -{ - int error = 0; - struct scatterlist src, dst; - - src.page = virt_to_page(p->address); - src.offset = 0; - src.length = PAGE_SIZE; - dst.page = virt_to_page((void *)&swsusp_header); - dst.offset = 0; - dst.length = PAGE_SIZE; - - error = crypto_cipher_encrypt((struct crypto_tfm *)mem, &dst, &src, - PAGE_SIZE); - - if (!error) - error = write_page((unsigned long)&swsusp_header, - &(p->swap_address)); - return error; -} - -static __inline__ int crypto_read(struct pbe *p, void *mem) -{ - int error = 0; - struct scatterlist src, dst; - - error = bio_read_page(swp_offset(p->swap_address), (void *)p->address); - if (!error) { - src.offset = 0; - src.length = PAGE_SIZE; - dst.offset = 0; - dst.length = PAGE_SIZE; - src.page = dst.page = virt_to_page((void *)p->address); - - error = crypto_cipher_decrypt((struct crypto_tfm *)mem, &dst, - &src, PAGE_SIZE); - } - return error; -} -#else -static __inline__ int crypto_init(int mode, void *mem) -{ - return 0; -} - -static __inline__ void crypto_exit(void *mem) -{ -} - -static __inline__ int crypto_write(struct pbe *p, void *mem) -{ - return write_page(p->address, &(p->swap_address)); -} +static unsigned short root_swap = 0xffff; -static __inline__ int crypto_read(struct pbe *p, void *mem) -{ - return bio_read_page(swp_offset(p->swap_address), (void *)p->address); -} -#endif - -static int mark_swapfiles(swp_entry_t prev) +static int mark_swapfiles(swp_entry_t start) { int error; @@ -259,8 +117,7 @@ static int mark_swapfiles(swp_entry_t prev) !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) { memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10); memcpy(swsusp_header.sig,SWSUSP_SIG, 10); - memcpy(swsusp_header.key_iv, key_iv, MAXKEY+MAXIV); - swsusp_header.swsusp_info = prev; + swsusp_header.image = start; error = rw_swap_page_sync(WRITE, swp_entry(root_swap, 0), virt_to_page((unsigned long) @@ -283,7 +140,7 @@ static int mark_swapfiles(swp_entry_t prev) * devfs, since the resume code can only recognize the form /dev/hda4, * but the suspend code would see the long name.) */ -static int is_resume_device(const struct swap_info_struct *swap_info) +static inline int is_resume_device(const struct swap_info_struct *swap_info) { struct file *file = swap_info->swap_file; struct inode *inode = file->f_dentry->d_inode; @@ -294,54 +151,22 @@ static int is_resume_device(const struct swap_info_struct *swap_info) static int swsusp_swap_check(void) /* This is called before saving image */ { - int i, len; - - len=strlen(resume_file); - root_swap = 0xFFFF; - - spin_lock(&swap_lock); - for (i=0; i<MAX_SWAPFILES; i++) { - if (!(swap_info[i].flags & SWP_WRITEOK)) { - swapfile_used[i]=SWAPFILE_UNUSED; - } else { - if (!len) { - printk(KERN_WARNING "resume= option should be used to set suspend device" ); - if (root_swap == 0xFFFF) { - swapfile_used[i] = SWAPFILE_SUSPEND; - root_swap = i; - } else - swapfile_used[i] = SWAPFILE_IGNORED; - } else { - /* we ignore all swap devices that are not the resume_file */ - if (is_resume_device(&swap_info[i])) { - swapfile_used[i] = SWAPFILE_SUSPEND; - root_swap = i; - } else { - swapfile_used[i] = SWAPFILE_IGNORED; - } - } - } - } - spin_unlock(&swap_lock); - return (root_swap != 0xffff) ? 0 : -ENODEV; -} - -/** - * This is called after saving image so modification - * will be lost after resume... and that's what we want. - * we make the device unusable. A new call to - * lock_swapdevices can unlock the devices. - */ -static void lock_swapdevices(void) -{ int i; + if (!swsusp_resume_device) + return -ENODEV; spin_lock(&swap_lock); - for (i = 0; i< MAX_SWAPFILES; i++) - if (swapfile_used[i] == SWAPFILE_IGNORED) { - swap_info[i].flags ^= SWP_WRITEOK; + for (i = 0; i < MAX_SWAPFILES; i++) { + if (!(swap_info[i].flags & SWP_WRITEOK)) + continue; + if (is_resume_device(swap_info + i)) { + spin_unlock(&swap_lock); + root_swap = i; + return 0; } + } spin_unlock(&swap_lock); + return -ENODEV; } /** @@ -359,72 +184,217 @@ static void lock_swapdevices(void) static int write_page(unsigned long addr, swp_entry_t *loc) { swp_entry_t entry; - int error = 0; + int error = -ENOSPC; - entry = get_swap_page(); - if (swp_offset(entry) && - swapfile_used[swp_type(entry)] == SWAPFILE_SUSPEND) { - error = rw_swap_page_sync(WRITE, entry, - virt_to_page(addr)); - if (error == -EIO) - error = 0; - if (!error) + entry = get_swap_page_of_type(root_swap); + if (swp_offset(entry)) { + error = rw_swap_page_sync(WRITE, entry, virt_to_page(addr)); + if (!error || error == -EIO) *loc = entry; - } else - error = -ENOSPC; + } return error; } /** - * data_free - Free the swap entries used by the saved image. + * Swap map-handling functions + * + * The swap map is a data structure used for keeping track of each page + * written to the swap. It consists of many swap_map_page structures + * that contain each an array of MAP_PAGE_SIZE swap entries. + * These structures are linked together with the help of either the + * .next (in memory) or the .next_swap (in swap) member. * - * Walk the list of used swap entries and free each one. - * This is only used for cleanup when suspend fails. + * The swap map is created during suspend. At that time we need to keep + * it in memory, because we have to free all of the allocated swap + * entries if an error occurs. The memory needed is preallocated + * so that we know in advance if there's enough of it. + * + * The first swap_map_page structure is filled with the swap entries that + * correspond to the first MAP_PAGE_SIZE data pages written to swap and + * so on. After the all of the data pages have been written, the order + * of the swap_map_page structures in the map is reversed so that they + * can be read from swap in the original order. This causes the data + * pages to be loaded in exactly the same order in which they have been + * saved. + * + * During resume we only need to use one swap_map_page structure + * at a time, which means that we only need to use two memory pages for + * reading the image - one for reading the swap_map_page structures + * and the second for reading the data pages from swap. */ -static void data_free(void) + +#define MAP_PAGE_SIZE ((PAGE_SIZE - sizeof(swp_entry_t) - sizeof(void *)) \ + / sizeof(swp_entry_t)) + +struct swap_map_page { + swp_entry_t entries[MAP_PAGE_SIZE]; + swp_entry_t next_swap; + struct swap_map_page *next; +}; + +static inline void free_swap_map(struct swap_map_page *swap_map) { - swp_entry_t entry; - struct pbe *p; + struct swap_map_page *swp; - for_each_pbe (p, pagedir_nosave) { - entry = p->swap_address; - if (entry.val) - swap_free(entry); - else - break; + while (swap_map) { + swp = swap_map->next; + free_page((unsigned long)swap_map); + swap_map = swp; } } +static struct swap_map_page *alloc_swap_map(unsigned int nr_pages) +{ + struct swap_map_page *swap_map, *swp; + unsigned n = 0; + + if (!nr_pages) + return NULL; + + pr_debug("alloc_swap_map(): nr_pages = %d\n", nr_pages); + swap_map = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC); + swp = swap_map; + for (n = MAP_PAGE_SIZE; n < nr_pages; n += MAP_PAGE_SIZE) { + swp->next = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC); + swp = swp->next; + if (!swp) { + free_swap_map(swap_map); + return NULL; + } + } + return swap_map; +} + /** - * data_write - Write saved image to swap. - * - * Walk the list of pages in the image and sync each one to swap. + * reverse_swap_map - reverse the order of pages in the swap map + * @swap_map */ -static int data_write(void) + +static inline struct swap_map_page *reverse_swap_map(struct swap_map_page *swap_map) { - int error = 0, i = 0; - unsigned int mod = nr_copy_pages / 100; - struct pbe *p; - void *tfm; + struct swap_map_page *prev, *next; + + prev = NULL; + while (swap_map) { + next = swap_map->next; + swap_map->next = prev; + prev = swap_map; + swap_map = next; + } + return prev; +} - if ((error = crypto_init(1, &tfm))) - return error; +/** + * free_swap_map_entries - free the swap entries allocated to store + * the swap map @swap_map (this is only called in case of an error) + */ +static inline void free_swap_map_entries(struct swap_map_page *swap_map) +{ + while (swap_map) { + if (swap_map->next_swap.val) + swap_free(swap_map->next_swap); + swap_map = swap_map->next; + } +} - if (!mod) - mod = 1; +/** + * save_swap_map - save the swap map used for tracing the data pages + * stored in the swap + */ - printk( "Writing data to swap (%d pages)... ", nr_copy_pages ); - for_each_pbe (p, pagedir_nosave) { - if (!(i%mod)) - printk( "\b\b\b\b%3d%%", i / mod ); - if ((error = crypto_write(p, tfm))) { - crypto_exit(tfm); +static int save_swap_map(struct swap_map_page *swap_map, swp_entry_t *start) +{ + swp_entry_t entry = (swp_entry_t){0}; + int error; + + while (swap_map) { + swap_map->next_swap = entry; + if ((error = write_page((unsigned long)swap_map, &entry))) return error; - } - i++; + swap_map = swap_map->next; } - printk("\b\b\b\bdone\n"); - crypto_exit(tfm); + *start = entry; + return 0; +} + +/** + * free_image_entries - free the swap entries allocated to store + * the image data pages (this is only called in case of an error) + */ + +static inline void free_image_entries(struct swap_map_page *swp) +{ + unsigned k; + + while (swp) { + for (k = 0; k < MAP_PAGE_SIZE; k++) + if (swp->entries[k].val) + swap_free(swp->entries[k]); + swp = swp->next; + } +} + +/** + * The swap_map_handle structure is used for handling the swap map in + * a file-alike way + */ + +struct swap_map_handle { + struct swap_map_page *cur; + unsigned int k; +}; + +static inline void init_swap_map_handle(struct swap_map_handle *handle, + struct swap_map_page *map) +{ + handle->cur = map; + handle->k = 0; +} + +static inline int swap_map_write_page(struct swap_map_handle *handle, + unsigned long addr) +{ + int error; + + error = write_page(addr, handle->cur->entries + handle->k); + if (error) + return error; + if (++handle->k >= MAP_PAGE_SIZE) { + handle->cur = handle->cur->next; + handle->k = 0; + } + return 0; +} + +/** + * save_image_data - save the data pages pointed to by the PBEs + * from the list @pblist using the swap map handle @handle + * (assume there are @nr_pages data pages to save) + */ + +static int save_image_data(struct pbe *pblist, + struct swap_map_handle *handle, + unsigned int nr_pages) +{ + unsigned int m; + struct pbe *p; + int error = 0; + + printk("Saving image data pages (%u pages) ... ", nr_pages); + m = nr_pages / 100; + if (!m) + m = 1; + nr_pages = 0; + for_each_pbe (p, pblist) { + error = swap_map_write_page(handle, p->address); + if (error) + break; + if (!(nr_pages % m)) + printk("\b\b\b\b%3d%%", nr_pages / m); + nr_pages++; + } + if (!error) + printk("\b\b\b\bdone\n"); return error; } @@ -440,70 +410,70 @@ static void dump_info(void) pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname); pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus); pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages); - pr_debug(" swsusp: Pagedir: %ld Pages\n",swsusp_info.pagedir_pages); + pr_debug(" swsusp: Total: %ld Pages\n", swsusp_info.pages); } -static void init_header(void) +static void init_header(unsigned int nr_pages) { memset(&swsusp_info, 0, sizeof(swsusp_info)); swsusp_info.version_code = LINUX_VERSION_CODE; swsusp_info.num_physpages = num_physpages; memcpy(&swsusp_info.uts, &system_utsname, sizeof(system_utsname)); - swsusp_info.suspend_pagedir = pagedir_nosave; swsusp_info.cpus = num_online_cpus(); - swsusp_info.image_pages = nr_copy_pages; -} - -static int close_swap(void) -{ - swp_entry_t entry; - int error; - - dump_info(); - error = write_page((unsigned long)&swsusp_info, &entry); - if (!error) { - printk( "S" ); - error = mark_swapfiles(entry); - printk( "|\n" ); - } - return error; + swsusp_info.image_pages = nr_pages; + swsusp_info.pages = nr_pages + + ((nr_pages * sizeof(long) + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1; } /** - * free_pagedir_entries - Free pages used by the page directory. - * - * This is used during suspend for error recovery. + * pack_orig_addresses - the .orig_address fields of the PBEs from the + * list starting at @pbe are stored in the array @buf[] (1 page) */ -static void free_pagedir_entries(void) +static inline struct pbe *pack_orig_addresses(unsigned long *buf, + struct pbe *pbe) { - int i; + int j; - for (i = 0; i < swsusp_info.pagedir_pages; i++) - swap_free(swsusp_info.pagedir[i]); + for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) { + buf[j] = pbe->orig_address; + pbe = pbe->next; + } + if (!pbe) + for (; j < PAGE_SIZE / sizeof(long); j++) + buf[j] = 0; + return pbe; } - /** - * write_pagedir - Write the array of pages holding the page directory. - * @last: Last swap entry we write (needed for header). + * save_image_metadata - save the .orig_address fields of the PBEs + * from the list @pblist using the swap map handle @handle */ -static int write_pagedir(void) +static int save_image_metadata(struct pbe *pblist, + struct swap_map_handle *handle) { - int error = 0; + unsigned long *buf; unsigned int n = 0; - struct pbe *pbe; + struct pbe *p; + int error = 0; - printk( "Writing pagedir..."); - for_each_pb_page (pbe, pagedir_nosave) { - if ((error = write_page((unsigned long)pbe, &swsusp_info.pagedir[n++]))) - return error; + printk("Saving image metadata ... "); + buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC); + if (!buf) + return -ENOMEM; + p = pblist; + while (p) { + p = pack_orig_addresses(buf, p); + error = swap_map_write_page(handle, (unsigned long)buf); + if (error) + break; + n++; } - - swsusp_info.pagedir_pages = n; - printk("done (%u pages)\n", n); + free_page((unsigned long)buf); + if (!error) + printk("done (%u pages saved)\n", n); return error; } @@ -511,75 +481,125 @@ static int write_pagedir(void) * enough_swap - Make sure we have enough swap to save the image. * * Returns TRUE or FALSE after checking the total amount of swap - * space avaiable. - * - * FIXME: si_swapinfo(&i) returns all swap devices information. - * We should only consider resume_device. + * space avaiable from the resume partition. */ static int enough_swap(unsigned int nr_pages) { - struct sysinfo i; + unsigned int free_swap = swap_info[root_swap].pages - + swap_info[root_swap].inuse_pages; - si_swapinfo(&i); - pr_debug("swsusp: available swap: %lu pages\n", i.freeswap); - return i.freeswap > (nr_pages + PAGES_FOR_IO + + pr_debug("swsusp: free swap pages: %u\n", free_swap); + return free_swap > (nr_pages + PAGES_FOR_IO + (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE); } /** - * write_suspend_image - Write entire image and metadata. + * swsusp_write - Write entire image and metadata. * + * It is important _NOT_ to umount filesystems at this point. We want + * them synced (in case something goes wrong) but we DO not want to mark + * filesystem clean: it is not. (And it does not matter, if we resume + * correctly, we'll mark system clean, anyway.) */ -static int write_suspend_image(void) + +int swsusp_write(struct pbe *pblist, unsigned int nr_pages) { + struct swap_map_page *swap_map; + struct swap_map_handle handle; + swp_entry_t start; int error; - if (!enough_swap(nr_copy_pages)) { + if ((error = swsusp_swap_check())) { + printk(KERN_ERR "swsusp: Cannot find swap device, try swapon -a.\n"); + return error; + } + if (!enough_swap(nr_pages)) { printk(KERN_ERR "swsusp: Not enough free swap\n"); return -ENOSPC; } - init_header(); - if ((error = data_write())) - goto FreeData; + init_header(nr_pages); + swap_map = alloc_swap_map(swsusp_info.pages); + if (!swap_map) + return -ENOMEM; + init_swap_map_handle(&handle, swap_map); + + error = swap_map_write_page(&handle, (unsigned long)&swsusp_info); + if (!error) + error = save_image_metadata(pblist, &handle); + if (!error) + error = save_image_data(pblist, &handle, nr_pages); + if (error) + goto Free_image_entries; - if ((error = write_pagedir())) - goto FreePagedir; + swap_map = reverse_swap_map(swap_map); + error = save_swap_map(swap_map, &start); + if (error) + goto Free_map_entries; - if ((error = close_swap())) - goto FreePagedir; - Done: - memset(key_iv, 0, MAXKEY+MAXIV); + dump_info(); + printk( "S" ); + error = mark_swapfiles(start); + printk( "|\n" ); + if (error) + goto Free_map_entries; + +Free_swap_map: + free_swap_map(swap_map); return error; - FreePagedir: - free_pagedir_entries(); - FreeData: - data_free(); - goto Done; + +Free_map_entries: + free_swap_map_entries(swap_map); +Free_image_entries: + free_image_entries(swap_map); + goto Free_swap_map; } -/* It is important _NOT_ to umount filesystems at this point. We want - * them synced (in case something goes wrong) but we DO not want to mark - * filesystem clean: it is not. (And it does not matter, if we resume - * correctly, we'll mark system clean, anyway.) +/** + * swsusp_shrink_memory - Try to free as much memory as needed + * + * ... but do not OOM-kill anyone + * + * Notice: all userland should be stopped before it is called, or + * livelock is possible. */ -int swsusp_write(void) -{ - int error; - if ((error = swsusp_swap_check())) { - printk(KERN_ERR "swsusp: cannot find swap device, try swapon -a.\n"); - return error; - } - lock_swapdevices(); - error = write_suspend_image(); - /* This will unlock ignored swap devices since writing is finished */ - lock_swapdevices(); - return error; -} +#define SHRINK_BITE 10000 +int swsusp_shrink_memory(void) +{ + long size, tmp; + struct zone *zone; + unsigned long pages = 0; + unsigned int i = 0; + char *p = "-\\|/"; + + printk("Shrinking memory... "); + do { + size = 2 * count_highmem_pages(); + size += size / 50 + count_data_pages(); + size += (size + PBES_PER_PAGE - 1) / PBES_PER_PAGE + + PAGES_FOR_IO; + tmp = size; + for_each_zone (zone) + if (!is_highmem(zone)) + tmp -= zone->free_pages; + if (tmp > 0) { + tmp = shrink_all_memory(SHRINK_BITE); + if (!tmp) + return -ENOMEM; + pages += tmp; + } else if (size > (image_size * 1024 * 1024) / PAGE_SIZE) { + tmp = shrink_all_memory(SHRINK_BITE); + pages += tmp; + } + printk("\b%c", p[i++%4]); + } while (tmp > 0); + printk("\bdone (%lu pages freed)\n", pages); + return 0; +} int swsusp_suspend(void) { @@ -677,7 +697,6 @@ static void copy_page_backup_list(struct pbe *dst, struct pbe *src) /* We assume both lists contain the same number of elements */ while (src) { dst->orig_address = src->orig_address; - dst->swap_address = src->swap_address; dst = dst->next; src = src->next; } @@ -757,198 +776,224 @@ static int bio_write_page(pgoff_t page_off, void *page) return submit(WRITE, page_off, page); } -/* - * Sanity check if this image makes sense with this kernel/swap context - * I really don't think that it's foolproof but more than nothing.. +/** + * The following functions allow us to read data using a swap map + * in a file-alike way */ -static const char *sanity_check(void) +static inline void release_swap_map_reader(struct swap_map_handle *handle) { - dump_info(); - if (swsusp_info.version_code != LINUX_VERSION_CODE) - return "kernel version"; - if (swsusp_info.num_physpages != num_physpages) - return "memory size"; - if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname)) - return "system type"; - if (strcmp(swsusp_info.uts.release,system_utsname.release)) - return "kernel release"; - if (strcmp(swsusp_info.uts.version,system_utsname.version)) - return "version"; - if (strcmp(swsusp_info.uts.machine,system_utsname.machine)) - return "machine"; -#if 0 - /* We can't use number of online CPUs when we use hotplug to remove them ;-))) */ - if (swsusp_info.cpus != num_possible_cpus()) - return "number of cpus"; -#endif - return NULL; + if (handle->cur) + free_page((unsigned long)handle->cur); + handle->cur = NULL; } - -static int check_header(void) +static inline int get_swap_map_reader(struct swap_map_handle *handle, + swp_entry_t start) { - const char *reason = NULL; int error; - if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info))) + if (!swp_offset(start)) + return -EINVAL; + handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC); + if (!handle->cur) + return -ENOMEM; + error = bio_read_page(swp_offset(start), handle->cur); + if (error) { + release_swap_map_reader(handle); return error; - - /* Is this same machine? */ - if ((reason = sanity_check())) { - printk(KERN_ERR "swsusp: Resume mismatch: %s\n",reason); - return -EPERM; } - nr_copy_pages = swsusp_info.image_pages; - return error; + handle->k = 0; + return 0; } -static int check_sig(void) +static inline int swap_map_read_page(struct swap_map_handle *handle, void *buf) { + unsigned long offset; int error; - memset(&swsusp_header, 0, sizeof(swsusp_header)); - if ((error = bio_read_page(0, &swsusp_header))) - return error; - if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) { - memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10); - memcpy(key_iv, swsusp_header.key_iv, MAXKEY+MAXIV); - memset(swsusp_header.key_iv, 0, MAXKEY+MAXIV); - - /* - * Reset swap signature now. - */ - error = bio_write_page(0, &swsusp_header); - } else { + if (!handle->cur) + return -EINVAL; + offset = swp_offset(handle->cur->entries[handle->k]); + if (!offset) return -EINVAL; + error = bio_read_page(offset, buf); + if (error) + return error; + if (++handle->k >= MAP_PAGE_SIZE) { + handle->k = 0; + offset = swp_offset(handle->cur->next_swap); + if (!offset) + release_swap_map_reader(handle); + else + error = bio_read_page(offset, handle->cur); } - if (!error) - pr_debug("swsusp: Signature found, resuming\n"); return error; } -/** - * data_read - Read image pages from swap. - * - * You do not need to check for overlaps, check_pagedir() - * already did that. - */ - -static int data_read(struct pbe *pblist) +static int check_header(void) { - struct pbe *p; - int error = 0; - int i = 0; - int mod = swsusp_info.image_pages / 100; - void *tfm; - - if ((error = crypto_init(0, &tfm))) - return error; - - if (!mod) - mod = 1; - - printk("swsusp: Reading image data (%lu pages): ", - swsusp_info.image_pages); - - for_each_pbe (p, pblist) { - if (!(i % mod)) - printk("\b\b\b\b%3d%%", i / mod); + char *reason = NULL; - if ((error = crypto_read(p, tfm))) { - crypto_exit(tfm); - return error; - } - - i++; + dump_info(); + if (swsusp_info.version_code != LINUX_VERSION_CODE) + reason = "kernel version"; + if (swsusp_info.num_physpages != num_physpages) + reason = "memory size"; + if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname)) + reason = "system type"; + if (strcmp(swsusp_info.uts.release,system_utsname.release)) + reason = "kernel release"; + if (strcmp(swsusp_info.uts.version,system_utsname.version)) + reason = "version"; + if (strcmp(swsusp_info.uts.machine,system_utsname.machine)) + reason = "machine"; + if (reason) { + printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason); + return -EPERM; } - printk("\b\b\b\bdone\n"); - crypto_exit(tfm); - return error; + return 0; } /** - * read_pagedir - Read page backup list pages from swap + * load_image_data - load the image data using the swap map handle + * @handle and store them using the page backup list @pblist + * (assume there are @nr_pages pages to load) */ -static int read_pagedir(struct pbe *pblist) +static int load_image_data(struct pbe *pblist, + struct swap_map_handle *handle, + unsigned int nr_pages) { - struct pbe *pbpage, *p; - unsigned int i = 0; int error; + unsigned int m; + struct pbe *p; if (!pblist) - return -EFAULT; - - printk("swsusp: Reading pagedir (%lu pages)\n", - swsusp_info.pagedir_pages); - - for_each_pb_page (pbpage, pblist) { - unsigned long offset = swp_offset(swsusp_info.pagedir[i++]); - - error = -EFAULT; - if (offset) { - p = (pbpage + PB_PAGE_SKIP)->next; - error = bio_read_page(offset, (void *)pbpage); - (pbpage + PB_PAGE_SKIP)->next = p; - } + return -EINVAL; + printk("Loading image data pages (%u pages) ... ", nr_pages); + m = nr_pages / 100; + if (!m) + m = 1; + nr_pages = 0; + p = pblist; + while (p) { + error = swap_map_read_page(handle, (void *)p->address); if (error) break; + p = p->next; + if (!(nr_pages % m)) + printk("\b\b\b\b%3d%%", nr_pages / m); + nr_pages++; } - if (!error) - BUG_ON(i != swsusp_info.pagedir_pages); - + printk("\b\b\b\bdone\n"); return error; } +/** + * unpack_orig_addresses - copy the elements of @buf[] (1 page) to + * the PBEs in the list starting at @pbe + */ -static int check_suspend_image(void) +static inline struct pbe *unpack_orig_addresses(unsigned long *buf, + struct pbe *pbe) { - int error = 0; + int j; - if ((error = check_sig())) - return error; - - if ((error = check_header())) - return error; - - return 0; + for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) { + pbe->orig_address = buf[j]; + pbe = pbe->next; + } + return pbe; } -static int read_suspend_image(void) +/** + * load_image_metadata - load the image metadata using the swap map + * handle @handle and put them into the PBEs in the list @pblist + */ + +static int load_image_metadata(struct pbe *pblist, struct swap_map_handle *handle) { - int error = 0; struct pbe *p; + unsigned long *buf; + unsigned int n = 0; + int error = 0; - if (!(p = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 0))) + printk("Loading image metadata ... "); + buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC); + if (!buf) return -ENOMEM; - - if ((error = read_pagedir(p))) - return error; - create_pbe_list(p, nr_copy_pages); - mark_unsafe_pages(p); - pagedir_nosave = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 1); - if (pagedir_nosave) { - create_pbe_list(pagedir_nosave, nr_copy_pages); - copy_page_backup_list(pagedir_nosave, p); + p = pblist; + while (p) { + error = swap_map_read_page(handle, buf); + if (error) + break; + p = unpack_orig_addresses(buf, p); + n++; } - free_pagedir(p); - if (!pagedir_nosave) - return -ENOMEM; + free_page((unsigned long)buf); + if (!error) + printk("done (%u pages loaded)\n", n); + return error; +} - /* Allocate memory for the image and read the data from swap */ +int swsusp_read(struct pbe **pblist_ptr) +{ + int error; + struct pbe *p, *pblist; + struct swap_map_handle handle; + unsigned int nr_pages; - error = alloc_data_pages(pagedir_nosave, GFP_ATOMIC, 1); + if (IS_ERR(resume_bdev)) { + pr_debug("swsusp: block device not initialised\n"); + return PTR_ERR(resume_bdev); + } + error = get_swap_map_reader(&handle, swsusp_header.image); if (!error) - error = data_read(pagedir_nosave); + error = swap_map_read_page(&handle, &swsusp_info); + if (!error) + error = check_header(); + if (error) + return error; + nr_pages = swsusp_info.image_pages; + p = alloc_pagedir(nr_pages, GFP_ATOMIC, 0); + if (!p) + return -ENOMEM; + error = load_image_metadata(p, &handle); + if (!error) { + mark_unsafe_pages(p); + pblist = alloc_pagedir(nr_pages, GFP_ATOMIC, 1); + if (pblist) + copy_page_backup_list(pblist, p); + free_pagedir(p); + if (!pblist) + error = -ENOMEM; + + /* Allocate memory for the image and read the data from swap */ + if (!error) + error = alloc_data_pages(pblist, GFP_ATOMIC, 1); + if (!error) { + release_eaten_pages(); + error = load_image_data(pblist, &handle, nr_pages); + } + if (!error) + *pblist_ptr = pblist; + } + release_swap_map_reader(&handle); + blkdev_put(resume_bdev); + + if (!error) + pr_debug("swsusp: Reading resume file was successful\n"); + else + pr_debug("swsusp: Error %d resuming\n", error); return error; } /** - * swsusp_check - Check for saved image in swap + * swsusp_check - Check for swsusp signature in the resume device */ int swsusp_check(void) @@ -958,40 +1003,27 @@ int swsusp_check(void) resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ); if (!IS_ERR(resume_bdev)) { set_blocksize(resume_bdev, PAGE_SIZE); - error = check_suspend_image(); + memset(&swsusp_header, 0, sizeof(swsusp_header)); + if ((error = bio_read_page(0, &swsusp_header))) + return error; + if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) { + memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10); + /* Reset swap signature now */ + error = bio_write_page(0, &swsusp_header); + } else { + return -EINVAL; + } if (error) - blkdev_put(resume_bdev); - } else + blkdev_put(resume_bdev); + else + pr_debug("swsusp: Signature found, resuming\n"); + } else { error = PTR_ERR(resume_bdev); - - if (!error) - pr_debug("swsusp: resume file found\n"); - else - pr_debug("swsusp: Error %d check for resume file\n", error); - return error; -} - -/** - * swsusp_read - Read saved image from swap. - */ - -int swsusp_read(void) -{ - int error; - - if (IS_ERR(resume_bdev)) { - pr_debug("swsusp: block device not initialised\n"); - return PTR_ERR(resume_bdev); } - error = read_suspend_image(); - blkdev_put(resume_bdev); - memset(key_iv, 0, MAXKEY+MAXIV); + if (error) + pr_debug("swsusp: Error %d check for resume file\n", error); - if (!error) - pr_debug("swsusp: Reading resume file was successful\n"); - else - pr_debug("swsusp: Error %d resuming\n", error); return error; } diff --git a/kernel/printk.c b/kernel/printk.c index 5287be83e3e..13ced0f7828 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -11,7 +11,7 @@ * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul - * manfreds@colorfullife.com + * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton <andrewm@uow.edu.au> */ @@ -569,7 +569,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) p[1] <= '7' && p[2] == '>') { loglev_char = p[1]; p += 3; - printed_len += 3; + printed_len -= 3; } else { loglev_char = default_message_loglevel + '0'; @@ -584,7 +584,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) for (tp = tbuf; tp < tbuf + tlen; tp++) emit_log_char(*tp); - printed_len += tlen - 3; + printed_len += tlen; } else { if (p[0] != '<' || p[1] < '0' || p[1] > '7' || p[2] != '>') { @@ -592,8 +592,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) emit_log_char(default_message_loglevel + '0'); emit_log_char('>'); + printed_len += 3; } - printed_len += 3; } log_level_unknown = 0; if (!*p) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 656476eedb1..5f33cdb6fff 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -7,6 +7,7 @@ * to continually duplicate across every architecture. */ +#include <linux/capability.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/errno.h> @@ -408,54 +409,62 @@ int ptrace_request(struct task_struct *child, long request, return ret; } -#ifndef __ARCH_SYS_PTRACE -static int ptrace_get_task_struct(long request, long pid, - struct task_struct **childp) +/** + * ptrace_traceme -- helper for PTRACE_TRACEME + * + * Performs checks and sets PT_PTRACED. + * Should be used by all ptrace implementations for PTRACE_TRACEME. + */ +int ptrace_traceme(void) { - struct task_struct *child; int ret; /* - * Callers use child == NULL as an indication to exit early even - * when the return value is 0, so make sure it is non-NULL here. + * Are we already being traced? + */ + if (current->ptrace & PT_PTRACED) + return -EPERM; + ret = security_ptrace(current->parent, current); + if (ret) + return -EPERM; + /* + * Set the ptrace bit in the process ptrace flags. */ - *childp = NULL; + current->ptrace |= PT_PTRACED; + return 0; +} - if (request == PTRACE_TRACEME) { - /* - * Are we already being traced? - */ - if (current->ptrace & PT_PTRACED) - return -EPERM; - ret = security_ptrace(current->parent, current); - if (ret) - return -EPERM; - /* - * Set the ptrace bit in the process ptrace flags. - */ - current->ptrace |= PT_PTRACED; - return 0; - } +/** + * ptrace_get_task_struct -- grab a task struct reference for ptrace + * @pid: process id to grab a task_struct reference of + * + * This function is a helper for ptrace implementations. It checks + * permissions and then grabs a task struct for use of the actual + * ptrace implementation. + * + * Returns the task_struct for @pid or an ERR_PTR() on failure. + */ +struct task_struct *ptrace_get_task_struct(pid_t pid) +{ + struct task_struct *child; /* - * You may not mess with init + * Tracing init is not allowed. */ if (pid == 1) - return -EPERM; + return ERR_PTR(-EPERM); - ret = -ESRCH; read_lock(&tasklist_lock); child = find_task_by_pid(pid); if (child) get_task_struct(child); read_unlock(&tasklist_lock); if (!child) - return -ESRCH; - - *childp = child; - return 0; + return ERR_PTR(-ESRCH); + return child; } +#ifndef __ARCH_SYS_PTRACE asmlinkage long sys_ptrace(long request, long pid, long addr, long data) { struct task_struct *child; @@ -465,9 +474,16 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data) * This lock_kernel fixes a subtle race with suid exec */ lock_kernel(); - ret = ptrace_get_task_struct(request, pid, &child); - if (!child) + if (request == PTRACE_TRACEME) { + ret = ptrace_traceme(); goto out; + } + + child = ptrace_get_task_struct(pid); + if (IS_ERR(child)) { + ret = PTR_ERR(child); + goto out; + } if (request == PTRACE_ATTACH) { ret = ptrace_attach(child); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index c4d159a21e0..0cf8146bd58 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -35,6 +35,7 @@ #include <linux/init.h> #include <linux/spinlock.h> #include <linux/smp.h> +#include <linux/rcupdate.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <asm/atomic.h> @@ -45,26 +46,21 @@ #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/rcupdate.h> -#include <linux/rcuref.h> #include <linux/cpu.h> /* Definition for rcupdate control block. */ -struct rcu_ctrlblk rcu_ctrlblk = - { .cur = -300, .completed = -300 }; -struct rcu_ctrlblk rcu_bh_ctrlblk = - { .cur = -300, .completed = -300 }; - -/* Bookkeeping of the progress of the grace period */ -struct rcu_state { - spinlock_t lock; /* Guard this struct and writes to rcu_ctrlblk */ - cpumask_t cpumask; /* CPUs that need to switch in order */ - /* for current batch to proceed. */ +struct rcu_ctrlblk rcu_ctrlblk = { + .cur = -300, + .completed = -300, + .lock = SPIN_LOCK_UNLOCKED, + .cpumask = CPU_MASK_NONE, +}; +struct rcu_ctrlblk rcu_bh_ctrlblk = { + .cur = -300, + .completed = -300, + .lock = SPIN_LOCK_UNLOCKED, + .cpumask = CPU_MASK_NONE, }; - -static struct rcu_state rcu_state ____cacheline_maxaligned_in_smp = - {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE }; -static struct rcu_state rcu_bh_state ____cacheline_maxaligned_in_smp = - {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE }; DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L }; DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L }; @@ -73,19 +69,6 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L }; static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL}; static int maxbatch = 10000; -#ifndef __HAVE_ARCH_CMPXCHG -/* - * We use an array of spinlocks for the rcurefs -- similar to ones in sparc - * 32 bit atomic_t implementations, and a hash function similar to that - * for our refcounting needs. - * Can't help multiprocessors which donot have cmpxchg :( - */ - -spinlock_t __rcuref_hash[RCUREF_HASH_SIZE] = { - [0 ... (RCUREF_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED -}; -#endif - /** * call_rcu - Queue an RCU callback for invocation after a grace period. * @head: structure to be used for queueing the RCU updates. @@ -116,6 +99,10 @@ void fastcall call_rcu(struct rcu_head *head, local_irq_restore(flags); } +static atomic_t rcu_barrier_cpu_count; +static struct semaphore rcu_barrier_sema; +static struct completion rcu_barrier_completion; + /** * call_rcu_bh - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. @@ -162,6 +149,42 @@ long rcu_batches_completed(void) return rcu_ctrlblk.completed; } +static void rcu_barrier_callback(struct rcu_head *notused) +{ + if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + complete(&rcu_barrier_completion); +} + +/* + * Called with preemption disabled, and from cross-cpu IRQ context. + */ +static void rcu_barrier_func(void *notused) +{ + int cpu = smp_processor_id(); + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + struct rcu_head *head; + + head = &rdp->barrier; + atomic_inc(&rcu_barrier_cpu_count); + call_rcu(head, rcu_barrier_callback); +} + +/** + * rcu_barrier - Wait until all the in-flight RCUs are complete. + */ +void rcu_barrier(void) +{ + BUG_ON(in_interrupt()); + /* Take cpucontrol semaphore to protect against CPU hotplug */ + down(&rcu_barrier_sema); + init_completion(&rcu_barrier_completion); + atomic_set(&rcu_barrier_cpu_count, 0); + on_each_cpu(rcu_barrier_func, NULL, 0, 1); + wait_for_completion(&rcu_barrier_completion); + up(&rcu_barrier_sema); +} +EXPORT_SYMBOL_GPL(rcu_barrier); + /* * Invoke the completed RCU callbacks. They are expected to be in * a per-cpu list. @@ -193,13 +216,13 @@ static void rcu_do_batch(struct rcu_data *rdp) * This is done by rcu_start_batch. The start is not broadcasted to * all cpus, they must pick this up by comparing rcp->cur with * rdp->quiescbatch. All cpus are recorded in the - * rcu_state.cpumask bitmap. + * rcu_ctrlblk.cpumask bitmap. * - All cpus must go through a quiescent state. * Since the start of the grace period is not broadcasted, at least two * calls to rcu_check_quiescent_state are required: * The first call just notices that a new grace period is running. The * following calls check if there was a quiescent state since the beginning - * of the grace period. If so, it updates rcu_state.cpumask. If + * of the grace period. If so, it updates rcu_ctrlblk.cpumask. If * the bitmap is empty, then the grace period is completed. * rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace * period (if necessary). @@ -207,25 +230,29 @@ static void rcu_do_batch(struct rcu_data *rdp) /* * Register a new batch of callbacks, and start it up if there is currently no * active batch and the batch to be registered has not already occurred. - * Caller must hold rcu_state.lock. + * Caller must hold rcu_ctrlblk.lock. */ -static void rcu_start_batch(struct rcu_ctrlblk *rcp, struct rcu_state *rsp, - int next_pending) +static void rcu_start_batch(struct rcu_ctrlblk *rcp) { - if (next_pending) - rcp->next_pending = 1; - if (rcp->next_pending && rcp->completed == rcp->cur) { - /* Can't change, since spin lock held. */ - cpus_andnot(rsp->cpumask, cpu_online_map, nohz_cpu_mask); - rcp->next_pending = 0; - /* next_pending == 0 must be visible in __rcu_process_callbacks() - * before it can see new value of cur. + /* + * next_pending == 0 must be visible in + * __rcu_process_callbacks() before it can see new value of cur. */ smp_wmb(); rcp->cur++; + + /* + * Accessing nohz_cpu_mask before incrementing rcp->cur needs a + * Barrier Otherwise it can cause tickless idle CPUs to be + * included in rcp->cpumask, which will extend graceperiods + * unnecessarily. + */ + smp_mb(); + cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask); + } } @@ -234,13 +261,13 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp, struct rcu_state *rsp, * Clear it from the cpu mask and complete the grace period if it was the last * cpu. Start another grace period if someone has further entries pending */ -static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp, struct rcu_state *rsp) +static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp) { - cpu_clear(cpu, rsp->cpumask); - if (cpus_empty(rsp->cpumask)) { + cpu_clear(cpu, rcp->cpumask); + if (cpus_empty(rcp->cpumask)) { /* batch completed ! */ rcp->completed = rcp->cur; - rcu_start_batch(rcp, rsp, 0); + rcu_start_batch(rcp); } } @@ -250,7 +277,7 @@ static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp, struct rcu_state *rsp) * quiescent cycle, then indicate that it has done so. */ static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp, - struct rcu_state *rsp, struct rcu_data *rdp) + struct rcu_data *rdp) { if (rdp->quiescbatch != rcp->cur) { /* start new grace period: */ @@ -275,15 +302,15 @@ static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp, return; rdp->qs_pending = 0; - spin_lock(&rsp->lock); + spin_lock(&rcp->lock); /* * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync * during cpu startup. Ignore the quiescent state. */ if (likely(rdp->quiescbatch == rcp->cur)) - cpu_quiet(rdp->cpu, rcp, rsp); + cpu_quiet(rdp->cpu, rcp); - spin_unlock(&rsp->lock); + spin_unlock(&rcp->lock); } @@ -304,28 +331,29 @@ static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list, } static void __rcu_offline_cpu(struct rcu_data *this_rdp, - struct rcu_ctrlblk *rcp, struct rcu_state *rsp, struct rcu_data *rdp) + struct rcu_ctrlblk *rcp, struct rcu_data *rdp) { /* if the cpu going offline owns the grace period * we can block indefinitely waiting for it, so flush * it here */ - spin_lock_bh(&rsp->lock); + spin_lock_bh(&rcp->lock); if (rcp->cur != rcp->completed) - cpu_quiet(rdp->cpu, rcp, rsp); - spin_unlock_bh(&rsp->lock); + cpu_quiet(rdp->cpu, rcp); + spin_unlock_bh(&rcp->lock); rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail); rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail); - + rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail); } + static void rcu_offline_cpu(int cpu) { struct rcu_data *this_rdp = &get_cpu_var(rcu_data); struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data); - __rcu_offline_cpu(this_rdp, &rcu_ctrlblk, &rcu_state, + __rcu_offline_cpu(this_rdp, &rcu_ctrlblk, &per_cpu(rcu_data, cpu)); - __rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk, &rcu_bh_state, + __rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu)); put_cpu_var(rcu_data); put_cpu_var(rcu_bh_data); @@ -344,7 +372,7 @@ static void rcu_offline_cpu(int cpu) * This does the RCU processing work from tasklet context. */ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp, - struct rcu_state *rsp, struct rcu_data *rdp) + struct rcu_data *rdp) { if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) { *rdp->donetail = rdp->curlist; @@ -374,24 +402,53 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp, if (!rcp->next_pending) { /* and start it/schedule start if it's a new batch */ - spin_lock(&rsp->lock); - rcu_start_batch(rcp, rsp, 1); - spin_unlock(&rsp->lock); + spin_lock(&rcp->lock); + rcp->next_pending = 1; + rcu_start_batch(rcp); + spin_unlock(&rcp->lock); } } else { local_irq_enable(); } - rcu_check_quiescent_state(rcp, rsp, rdp); + rcu_check_quiescent_state(rcp, rdp); if (rdp->donelist) rcu_do_batch(rdp); } static void rcu_process_callbacks(unsigned long unused) { - __rcu_process_callbacks(&rcu_ctrlblk, &rcu_state, - &__get_cpu_var(rcu_data)); - __rcu_process_callbacks(&rcu_bh_ctrlblk, &rcu_bh_state, - &__get_cpu_var(rcu_bh_data)); + __rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data)); + __rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data)); +} + +static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp) +{ + /* This cpu has pending rcu entries and the grace period + * for them has completed. + */ + if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) + return 1; + + /* This cpu has no pending entries, but there are new entries */ + if (!rdp->curlist && rdp->nxtlist) + return 1; + + /* This cpu has finished callbacks to invoke */ + if (rdp->donelist) + return 1; + + /* The rcu core waits for a quiescent state from the cpu */ + if (rdp->quiescbatch != rcp->cur || rdp->qs_pending) + return 1; + + /* nothing to do */ + return 0; +} + +int rcu_pending(int cpu) +{ + return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) || + __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu)); } void rcu_check_callbacks(int cpu, int user) @@ -457,6 +514,7 @@ static struct notifier_block __devinitdata rcu_nb = { */ void __init rcu_init(void) { + sema_init(&rcu_barrier_sema, 1); rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)smp_processor_id()); /* Register notifier for non-boot CPUs */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 88c28d47655..773219907dd 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -39,7 +39,6 @@ #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> -#include <linux/rcuref.h> #include <linux/cpu.h> #include <linux/random.h> #include <linux/delay.h> @@ -49,9 +48,11 @@ MODULE_LICENSE("GPL"); static int nreaders = -1; /* # reader threads, defaults to 4*ncpus */ -static int stat_interval = 0; /* Interval between stats, in seconds. */ +static int stat_interval; /* Interval between stats, in seconds. */ /* Defaults to "only at end of test". */ -static int verbose = 0; /* Print more debug info. */ +static int verbose; /* Print more debug info. */ +static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ +static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/ MODULE_PARM(nreaders, "i"); MODULE_PARM_DESC(nreaders, "Number of RCU reader threads"); @@ -59,6 +60,10 @@ MODULE_PARM(stat_interval, "i"); MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s"); MODULE_PARM(verbose, "i"); MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s"); +MODULE_PARM(test_no_idle_hz, "i"); +MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs"); +MODULE_PARM(shuffle_interval, "i"); +MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles"); #define TORTURE_FLAG "rcutorture: " #define PRINTK_STRING(s) \ do { printk(KERN_ALERT TORTURE_FLAG s "\n"); } while (0) @@ -73,6 +78,7 @@ static int nrealreaders; static struct task_struct *writer_task; static struct task_struct **reader_tasks; static struct task_struct *stats_task; +static struct task_struct *shuffler_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -103,7 +109,7 @@ atomic_t n_rcu_torture_error; /* * Allocate an element from the rcu_tortures pool. */ -struct rcu_torture * +static struct rcu_torture * rcu_torture_alloc(void) { struct list_head *p; @@ -376,12 +382,77 @@ rcu_torture_stats(void *arg) return 0; } +static int rcu_idle_cpu; /* Force all torture tasks off this CPU */ + +/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case + * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs. + */ +void rcu_torture_shuffle_tasks(void) +{ + cpumask_t tmp_mask = CPU_MASK_ALL; + int i; + + lock_cpu_hotplug(); + + /* No point in shuffling if there is only one online CPU (ex: UP) */ + if (num_online_cpus() == 1) { + unlock_cpu_hotplug(); + return; + } + + if (rcu_idle_cpu != -1) + cpu_clear(rcu_idle_cpu, tmp_mask); + + set_cpus_allowed(current, tmp_mask); + + if (reader_tasks != NULL) { + for (i = 0; i < nrealreaders; i++) + if (reader_tasks[i]) + set_cpus_allowed(reader_tasks[i], tmp_mask); + } + + if (writer_task) + set_cpus_allowed(writer_task, tmp_mask); + + if (stats_task) + set_cpus_allowed(stats_task, tmp_mask); + + if (rcu_idle_cpu == -1) + rcu_idle_cpu = num_online_cpus() - 1; + else + rcu_idle_cpu--; + + unlock_cpu_hotplug(); +} + +/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the + * system to become idle at a time and cut off its timer ticks. This is meant + * to test the support for such tickless idle CPU in RCU. + */ +static int +rcu_torture_shuffle(void *arg) +{ + VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started"); + do { + schedule_timeout_interruptible(shuffle_interval * HZ); + rcu_torture_shuffle_tasks(); + } while (!kthread_should_stop()); + VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping"); + return 0; +} + static void rcu_torture_cleanup(void) { int i; fullstop = 1; + if (shuffler_task != NULL) { + VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task"); + kthread_stop(shuffler_task); + } + shuffler_task = NULL; + if (writer_task != NULL) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task"); kthread_stop(writer_task); @@ -409,9 +480,8 @@ rcu_torture_cleanup(void) stats_task = NULL; /* Wait for all RCU callbacks to fire. */ + rcu_barrier(); - for (i = 0; i < RCU_TORTURE_PIPE_LEN; i++) - synchronize_rcu(); rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ printk(KERN_ALERT TORTURE_FLAG "--- End of test: %s\n", @@ -431,9 +501,11 @@ rcu_torture_init(void) nrealreaders = nreaders; else nrealreaders = 2 * num_online_cpus(); - printk(KERN_ALERT TORTURE_FLAG - "--- Start of test: nreaders=%d stat_interval=%d verbose=%d\n", - nrealreaders, stat_interval, verbose); + printk(KERN_ALERT TORTURE_FLAG "--- Start of test: nreaders=%d " + "stat_interval=%d verbose=%d test_no_idle_hz=%d " + "shuffle_interval = %d\n", + nrealreaders, stat_interval, verbose, test_no_idle_hz, + shuffle_interval); fullstop = 0; /* Set up the freelist. */ @@ -503,6 +575,18 @@ rcu_torture_init(void) goto unwind; } } + if (test_no_idle_hz) { + rcu_idle_cpu = num_online_cpus() - 1; + /* Create the shuffler thread */ + shuffler_task = kthread_run(rcu_torture_shuffle, NULL, + "rcu_torture_shuffle"); + if (IS_ERR(shuffler_task)) { + firsterr = PTR_ERR(shuffler_task); + VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler"); + shuffler_task = NULL; + goto unwind; + } + } return 0; unwind: diff --git a/kernel/resource.c b/kernel/resource.c index 92285d822de..e3080fcc66a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -464,7 +464,7 @@ struct resource * __request_region(struct resource *parent, unsigned long start, EXPORT_SYMBOL(__request_region); -int __deprecated __check_region(struct resource *parent, unsigned long start, unsigned long n) +int __check_region(struct resource *parent, unsigned long start, unsigned long n) { struct resource * res; diff --git a/kernel/sched.c b/kernel/sched.c index 6f46c94cc29..3ee2ae45125 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -27,12 +27,14 @@ #include <linux/smp_lock.h> #include <asm/mmu_context.h> #include <linux/interrupt.h> +#include <linux/capability.h> #include <linux/completion.h> #include <linux/kernel_stat.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/profile.h> #include <linux/suspend.h> +#include <linux/vmalloc.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/smp.h> @@ -176,6 +178,13 @@ static unsigned int task_timeslice(task_t *p) #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \ < (long long) (sd)->cache_hot_time) +void __put_task_struct_cb(struct rcu_head *rhp) +{ + __put_task_struct(container_of(rhp, struct task_struct, rcu)); +} + +EXPORT_SYMBOL_GPL(__put_task_struct_cb); + /* * These are the runqueue data structures: */ @@ -512,7 +521,7 @@ static inline void sched_info_dequeued(task_t *t) * long it was waiting to run. We also note when it began so that we * can keep stats on how long its timeslice is. */ -static inline void sched_info_arrive(task_t *t) +static void sched_info_arrive(task_t *t) { unsigned long now = jiffies, diff = 0; struct runqueue *rq = task_rq(t); @@ -739,10 +748,14 @@ static int recalc_task_prio(task_t *p, unsigned long long now) unsigned long long __sleep_time = now - p->timestamp; unsigned long sleep_time; - if (__sleep_time > NS_MAX_SLEEP_AVG) - sleep_time = NS_MAX_SLEEP_AVG; - else - sleep_time = (unsigned long)__sleep_time; + if (unlikely(p->policy == SCHED_BATCH)) + sleep_time = 0; + else { + if (__sleep_time > NS_MAX_SLEEP_AVG) + sleep_time = NS_MAX_SLEEP_AVG; + else + sleep_time = (unsigned long)__sleep_time; + } if (likely(sleep_time > 0)) { /* @@ -994,7 +1007,7 @@ void kick_process(task_t *p) * We want to under-estimate the load of migration sources, to * balance conservatively. */ -static inline unsigned long __source_load(int cpu, int type, enum idle_type idle) +static unsigned long __source_load(int cpu, int type, enum idle_type idle) { runqueue_t *rq = cpu_rq(cpu); unsigned long running = rq->nr_running; @@ -1281,6 +1294,9 @@ static int try_to_wake_up(task_t *p, unsigned int state, int sync) } } + if (p->last_waker_cpu != this_cpu) + goto out_set_cpu; + if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) goto out_set_cpu; @@ -1351,6 +1367,8 @@ out_set_cpu: cpu = task_cpu(p); } + p->last_waker_cpu = this_cpu; + out_activate: #endif /* CONFIG_SMP */ if (old_state == TASK_UNINTERRUPTIBLE) { @@ -1432,9 +1450,12 @@ void fastcall sched_fork(task_t *p, int clone_flags) #ifdef CONFIG_SCHEDSTATS memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP) + p->last_waker_cpu = cpu; +#if defined(__ARCH_WANT_UNLOCKED_CTXSW) p->oncpu = 0; #endif +#endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; @@ -1849,7 +1870,7 @@ void sched_exec(void) * pull_task - move a task from a remote runqueue to the local runqueue. * Both runqueues must be locked. */ -static inline +static void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p, runqueue_t *this_rq, prio_array_t *this_array, int this_cpu) { @@ -1871,7 +1892,7 @@ void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p, /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ -static inline +static int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu, struct sched_domain *sd, enum idle_type idle, int *all_pinned) @@ -2357,7 +2378,7 @@ out_balanced: * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static inline void idle_balance(int this_cpu, runqueue_t *this_rq) +static void idle_balance(int this_cpu, runqueue_t *this_rq) { struct sched_domain *sd; @@ -2741,7 +2762,7 @@ static inline void wakeup_busy_runqueue(runqueue_t *rq) resched_task(rq->idle); } -static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq) +static void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq) { struct sched_domain *tmp, *sd = NULL; cpumask_t sibling_map; @@ -2795,7 +2816,7 @@ static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd) return p->time_slice * (100 - sd->per_cpu_gain) / 100; } -static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq) +static int dependent_sleeper(int this_cpu, runqueue_t *this_rq) { struct sched_domain *tmp, *sd = NULL; cpumask_t sibling_map; @@ -3543,7 +3564,7 @@ void set_user_nice(task_t *p, long nice) * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected * it wont have any effect on scheduling until the task is - * not SCHED_NORMAL: + * not SCHED_NORMAL/SCHED_BATCH: */ if (rt_task(p)) { p->static_prio = NICE_TO_PRIO(nice); @@ -3689,10 +3710,16 @@ static void __setscheduler(struct task_struct *p, int policy, int prio) BUG_ON(p->array); p->policy = policy; p->rt_priority = prio; - if (policy != SCHED_NORMAL) + if (policy != SCHED_NORMAL && policy != SCHED_BATCH) { p->prio = MAX_RT_PRIO-1 - p->rt_priority; - else + } else { p->prio = p->static_prio; + /* + * SCHED_BATCH tasks are treated as perpetual CPU hogs: + */ + if (policy == SCHED_BATCH) + p->sleep_avg = 0; + } } /** @@ -3716,29 +3743,35 @@ recheck: if (policy < 0) policy = oldpolicy = p->policy; else if (policy != SCHED_FIFO && policy != SCHED_RR && - policy != SCHED_NORMAL) - return -EINVAL; + policy != SCHED_NORMAL && policy != SCHED_BATCH) + return -EINVAL; /* * Valid priorities for SCHED_FIFO and SCHED_RR are - * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL is 0. + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and + * SCHED_BATCH is 0. */ if (param->sched_priority < 0 || (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) return -EINVAL; - if ((policy == SCHED_NORMAL) != (param->sched_priority == 0)) + if ((policy == SCHED_NORMAL || policy == SCHED_BATCH) + != (param->sched_priority == 0)) return -EINVAL; /* * Allow unprivileged RT tasks to decrease priority: */ if (!capable(CAP_SYS_NICE)) { - /* can't change policy */ - if (policy != p->policy && - !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur) + /* + * can't change policy, except between SCHED_NORMAL + * and SCHED_BATCH: + */ + if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) && + (policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) && + !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur) return -EPERM; /* can't increase priority */ - if (policy != SCHED_NORMAL && + if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) && param->sched_priority > p->rt_priority && param->sched_priority > p->signal->rlim[RLIMIT_RTPRIO].rlim_cur) @@ -3817,6 +3850,10 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) { + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + return do_sched_setscheduler(pid, policy, param); } @@ -3972,12 +4009,12 @@ asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, * method, such as ACPI for e.g. */ -cpumask_t cpu_present_map; +cpumask_t cpu_present_map __read_mostly; EXPORT_SYMBOL(cpu_present_map); #ifndef CONFIG_SMP -cpumask_t cpu_online_map = CPU_MASK_ALL; -cpumask_t cpu_possible_map = CPU_MASK_ALL; +cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; +cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; #endif long sched_getaffinity(pid_t pid, cpumask_t *mask) @@ -4216,6 +4253,7 @@ asmlinkage long sys_sched_get_priority_max(int policy) ret = MAX_USER_RT_PRIO-1; break; case SCHED_NORMAL: + case SCHED_BATCH: ret = 0; break; } @@ -4239,6 +4277,7 @@ asmlinkage long sys_sched_get_priority_min(int policy) ret = 1; break; case SCHED_NORMAL: + case SCHED_BATCH: ret = 0; } return ret; @@ -4379,6 +4418,7 @@ void show_state(void) } while_each_thread(g, p); read_unlock(&tasklist_lock); + mutex_debug_show_all_locks(); } /** @@ -5073,7 +5113,470 @@ static void init_sched_build_groups(struct sched_group groups[], cpumask_t span, #define SD_NODES_PER_DOMAIN 16 +/* + * Self-tuning task migration cost measurement between source and target CPUs. + * + * This is done by measuring the cost of manipulating buffers of varying + * sizes. For a given buffer-size here are the steps that are taken: + * + * 1) the source CPU reads+dirties a shared buffer + * 2) the target CPU reads+dirties the same shared buffer + * + * We measure how long they take, in the following 4 scenarios: + * + * - source: CPU1, target: CPU2 | cost1 + * - source: CPU2, target: CPU1 | cost2 + * - source: CPU1, target: CPU1 | cost3 + * - source: CPU2, target: CPU2 | cost4 + * + * We then calculate the cost3+cost4-cost1-cost2 difference - this is + * the cost of migration. + * + * We then start off from a small buffer-size and iterate up to larger + * buffer sizes, in 5% steps - measuring each buffer-size separately, and + * doing a maximum search for the cost. (The maximum cost for a migration + * normally occurs when the working set size is around the effective cache + * size.) + */ +#define SEARCH_SCOPE 2 +#define MIN_CACHE_SIZE (64*1024U) +#define DEFAULT_CACHE_SIZE (5*1024*1024U) +#define ITERATIONS 2 +#define SIZE_THRESH 130 +#define COST_THRESH 130 + +/* + * The migration cost is a function of 'domain distance'. Domain + * distance is the number of steps a CPU has to iterate down its + * domain tree to share a domain with the other CPU. The farther + * two CPUs are from each other, the larger the distance gets. + * + * Note that we use the distance only to cache measurement results, + * the distance value is not used numerically otherwise. When two + * CPUs have the same distance it is assumed that the migration + * cost is the same. (this is a simplification but quite practical) + */ +#define MAX_DOMAIN_DISTANCE 32 + +static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] = + { [ 0 ... MAX_DOMAIN_DISTANCE-1 ] = -1LL }; + +/* + * Allow override of migration cost - in units of microseconds. + * E.g. migration_cost=1000,2000,3000 will set up a level-1 cost + * of 1 msec, level-2 cost of 2 msecs and level3 cost of 3 msecs: + */ +static int __init migration_cost_setup(char *str) +{ + int ints[MAX_DOMAIN_DISTANCE+1], i; + + str = get_options(str, ARRAY_SIZE(ints), ints); + + printk("#ints: %d\n", ints[0]); + for (i = 1; i <= ints[0]; i++) { + migration_cost[i-1] = (unsigned long long)ints[i]*1000; + printk("migration_cost[%d]: %Ld\n", i-1, migration_cost[i-1]); + } + return 1; +} + +__setup ("migration_cost=", migration_cost_setup); + +/* + * Global multiplier (divisor) for migration-cutoff values, + * in percentiles. E.g. use a value of 150 to get 1.5 times + * longer cache-hot cutoff times. + * + * (We scale it from 100 to 128 to long long handling easier.) + */ + +#define MIGRATION_FACTOR_SCALE 128 + +static unsigned int migration_factor = MIGRATION_FACTOR_SCALE; + +static int __init setup_migration_factor(char *str) +{ + get_option(&str, &migration_factor); + migration_factor = migration_factor * MIGRATION_FACTOR_SCALE / 100; + return 1; +} + +__setup("migration_factor=", setup_migration_factor); + +/* + * Estimated distance of two CPUs, measured via the number of domains + * we have to pass for the two CPUs to be in the same span: + */ +static unsigned long domain_distance(int cpu1, int cpu2) +{ + unsigned long distance = 0; + struct sched_domain *sd; + + for_each_domain(cpu1, sd) { + WARN_ON(!cpu_isset(cpu1, sd->span)); + if (cpu_isset(cpu2, sd->span)) + return distance; + distance++; + } + if (distance >= MAX_DOMAIN_DISTANCE) { + WARN_ON(1); + distance = MAX_DOMAIN_DISTANCE-1; + } + + return distance; +} + +static unsigned int migration_debug; + +static int __init setup_migration_debug(char *str) +{ + get_option(&str, &migration_debug); + return 1; +} + +__setup("migration_debug=", setup_migration_debug); + +/* + * Maximum cache-size that the scheduler should try to measure. + * Architectures with larger caches should tune this up during + * bootup. Gets used in the domain-setup code (i.e. during SMP + * bootup). + */ +unsigned int max_cache_size; + +static int __init setup_max_cache_size(char *str) +{ + get_option(&str, &max_cache_size); + return 1; +} + +__setup("max_cache_size=", setup_max_cache_size); + +/* + * Dirty a big buffer in a hard-to-predict (for the L2 cache) way. This + * is the operation that is timed, so we try to generate unpredictable + * cachemisses that still end up filling the L2 cache: + */ +static void touch_cache(void *__cache, unsigned long __size) +{ + unsigned long size = __size/sizeof(long), chunk1 = size/3, + chunk2 = 2*size/3; + unsigned long *cache = __cache; + int i; + + for (i = 0; i < size/6; i += 8) { + switch (i % 6) { + case 0: cache[i]++; + case 1: cache[size-1-i]++; + case 2: cache[chunk1-i]++; + case 3: cache[chunk1+i]++; + case 4: cache[chunk2-i]++; + case 5: cache[chunk2+i]++; + } + } +} + +/* + * Measure the cache-cost of one task migration. Returns in units of nsec. + */ +static unsigned long long measure_one(void *cache, unsigned long size, + int source, int target) +{ + cpumask_t mask, saved_mask; + unsigned long long t0, t1, t2, t3, cost; + + saved_mask = current->cpus_allowed; + + /* + * Flush source caches to RAM and invalidate them: + */ + sched_cacheflush(); + + /* + * Migrate to the source CPU: + */ + mask = cpumask_of_cpu(source); + set_cpus_allowed(current, mask); + WARN_ON(smp_processor_id() != source); + + /* + * Dirty the working set: + */ + t0 = sched_clock(); + touch_cache(cache, size); + t1 = sched_clock(); + + /* + * Migrate to the target CPU, dirty the L2 cache and access + * the shared buffer. (which represents the working set + * of a migrated task.) + */ + mask = cpumask_of_cpu(target); + set_cpus_allowed(current, mask); + WARN_ON(smp_processor_id() != target); + + t2 = sched_clock(); + touch_cache(cache, size); + t3 = sched_clock(); + + cost = t1-t0 + t3-t2; + + if (migration_debug >= 2) + printk("[%d->%d]: %8Ld %8Ld %8Ld => %10Ld.\n", + source, target, t1-t0, t1-t0, t3-t2, cost); + /* + * Flush target caches to RAM and invalidate them: + */ + sched_cacheflush(); + + set_cpus_allowed(current, saved_mask); + + return cost; +} + +/* + * Measure a series of task migrations and return the average + * result. Since this code runs early during bootup the system + * is 'undisturbed' and the average latency makes sense. + * + * The algorithm in essence auto-detects the relevant cache-size, + * so it will properly detect different cachesizes for different + * cache-hierarchies, depending on how the CPUs are connected. + * + * Architectures can prime the upper limit of the search range via + * max_cache_size, otherwise the search range defaults to 20MB...64K. + */ +static unsigned long long +measure_cost(int cpu1, int cpu2, void *cache, unsigned int size) +{ + unsigned long long cost1, cost2; + int i; + + /* + * Measure the migration cost of 'size' bytes, over an + * average of 10 runs: + * + * (We perturb the cache size by a small (0..4k) + * value to compensate size/alignment related artifacts. + * We also subtract the cost of the operation done on + * the same CPU.) + */ + cost1 = 0; + + /* + * dry run, to make sure we start off cache-cold on cpu1, + * and to get any vmalloc pagefaults in advance: + */ + measure_one(cache, size, cpu1, cpu2); + for (i = 0; i < ITERATIONS; i++) + cost1 += measure_one(cache, size - i*1024, cpu1, cpu2); + + measure_one(cache, size, cpu2, cpu1); + for (i = 0; i < ITERATIONS; i++) + cost1 += measure_one(cache, size - i*1024, cpu2, cpu1); + + /* + * (We measure the non-migrating [cached] cost on both + * cpu1 and cpu2, to handle CPUs with different speeds) + */ + cost2 = 0; + + measure_one(cache, size, cpu1, cpu1); + for (i = 0; i < ITERATIONS; i++) + cost2 += measure_one(cache, size - i*1024, cpu1, cpu1); + + measure_one(cache, size, cpu2, cpu2); + for (i = 0; i < ITERATIONS; i++) + cost2 += measure_one(cache, size - i*1024, cpu2, cpu2); + + /* + * Get the per-iteration migration cost: + */ + do_div(cost1, 2*ITERATIONS); + do_div(cost2, 2*ITERATIONS); + + return cost1 - cost2; +} + +static unsigned long long measure_migration_cost(int cpu1, int cpu2) +{ + unsigned long long max_cost = 0, fluct = 0, avg_fluct = 0; + unsigned int max_size, size, size_found = 0; + long long cost = 0, prev_cost; + void *cache; + + /* + * Search from max_cache_size*5 down to 64K - the real relevant + * cachesize has to lie somewhere inbetween. + */ + if (max_cache_size) { + max_size = max(max_cache_size * SEARCH_SCOPE, MIN_CACHE_SIZE); + size = max(max_cache_size / SEARCH_SCOPE, MIN_CACHE_SIZE); + } else { + /* + * Since we have no estimation about the relevant + * search range + */ + max_size = DEFAULT_CACHE_SIZE * SEARCH_SCOPE; + size = MIN_CACHE_SIZE; + } + + if (!cpu_online(cpu1) || !cpu_online(cpu2)) { + printk("cpu %d and %d not both online!\n", cpu1, cpu2); + return 0; + } + + /* + * Allocate the working set: + */ + cache = vmalloc(max_size); + if (!cache) { + printk("could not vmalloc %d bytes for cache!\n", 2*max_size); + return 1000000; // return 1 msec on very small boxen + } + + while (size <= max_size) { + prev_cost = cost; + cost = measure_cost(cpu1, cpu2, cache, size); + + /* + * Update the max: + */ + if (cost > 0) { + if (max_cost < cost) { + max_cost = cost; + size_found = size; + } + } + /* + * Calculate average fluctuation, we use this to prevent + * noise from triggering an early break out of the loop: + */ + fluct = abs(cost - prev_cost); + avg_fluct = (avg_fluct + fluct)/2; + + if (migration_debug) + printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n", + cpu1, cpu2, size, + (long)cost / 1000000, + ((long)cost / 100000) % 10, + (long)max_cost / 1000000, + ((long)max_cost / 100000) % 10, + domain_distance(cpu1, cpu2), + cost, avg_fluct); + + /* + * If we iterated at least 20% past the previous maximum, + * and the cost has dropped by more than 20% already, + * (taking fluctuations into account) then we assume to + * have found the maximum and break out of the loop early: + */ + if (size_found && (size*100 > size_found*SIZE_THRESH)) + if (cost+avg_fluct <= 0 || + max_cost*100 > (cost+avg_fluct)*COST_THRESH) { + + if (migration_debug) + printk("-> found max.\n"); + break; + } + /* + * Increase the cachesize in 5% steps: + */ + size = size * 20 / 19; + } + + if (migration_debug) + printk("[%d][%d] working set size found: %d, cost: %Ld\n", + cpu1, cpu2, size_found, max_cost); + + vfree(cache); + + /* + * A task is considered 'cache cold' if at least 2 times + * the worst-case cost of migration has passed. + * + * (this limit is only listened to if the load-balancing + * situation is 'nice' - if there is a large imbalance we + * ignore it for the sake of CPU utilization and + * processing fairness.) + */ + return 2 * max_cost * migration_factor / MIGRATION_FACTOR_SCALE; +} + +static void calibrate_migration_costs(const cpumask_t *cpu_map) +{ + int cpu1 = -1, cpu2 = -1, cpu, orig_cpu = raw_smp_processor_id(); + unsigned long j0, j1, distance, max_distance = 0; + struct sched_domain *sd; + + j0 = jiffies; + + /* + * First pass - calculate the cacheflush times: + */ + for_each_cpu_mask(cpu1, *cpu_map) { + for_each_cpu_mask(cpu2, *cpu_map) { + if (cpu1 == cpu2) + continue; + distance = domain_distance(cpu1, cpu2); + max_distance = max(max_distance, distance); + /* + * No result cached yet? + */ + if (migration_cost[distance] == -1LL) + migration_cost[distance] = + measure_migration_cost(cpu1, cpu2); + } + } + /* + * Second pass - update the sched domain hierarchy with + * the new cache-hot-time estimations: + */ + for_each_cpu_mask(cpu, *cpu_map) { + distance = 0; + for_each_domain(cpu, sd) { + sd->cache_hot_time = migration_cost[distance]; + distance++; + } + } + /* + * Print the matrix: + */ + if (migration_debug) + printk("migration: max_cache_size: %d, cpu: %d MHz:\n", + max_cache_size, +#ifdef CONFIG_X86 + cpu_khz/1000 +#else + -1 +#endif + ); + printk("migration_cost="); + for (distance = 0; distance <= max_distance; distance++) { + if (distance) + printk(","); + printk("%ld", (long)migration_cost[distance] / 1000); + } + printk("\n"); + j1 = jiffies; + if (migration_debug) + printk("migration: %ld seconds\n", (j1-j0)/HZ); + + /* + * Move back to the original CPU. NUMA-Q gets confused + * if we migrate to another quad during bootup. + */ + if (raw_smp_processor_id() != orig_cpu) { + cpumask_t mask = cpumask_of_cpu(orig_cpu), + saved_mask = current->cpus_allowed; + + set_cpus_allowed(current, mask); + set_cpus_allowed(current, saved_mask); + } +} + #ifdef CONFIG_NUMA + /** * find_next_best_node - find the next node to include in a sched_domain * @node: node whose sched_domain we're building @@ -5439,6 +5942,10 @@ next_sg: #endif cpu_attach_domain(sd, i); } + /* + * Tune cache-hot values: + */ + calibrate_migration_costs(cpu_map); } /* * Set up scheduler domains and groups. Callers must hold the hotplug lock. @@ -5505,7 +6012,7 @@ next_sg: * Detach sched domains from a group of cpus specified in cpu_map * These cpus will now be attached to the NULL domain */ -static inline void detach_destroy_domains(const cpumask_t *cpu_map) +static void detach_destroy_domains(const cpumask_t *cpu_map) { int i; diff --git a/kernel/signal.c b/kernel/signal.c index d7611f189ef..d3efafd8109 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -25,6 +25,7 @@ #include <linux/posix-timers.h> #include <linux/signal.h> #include <linux/audit.h> +#include <linux/capability.h> #include <asm/param.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -329,13 +330,20 @@ void __exit_sighand(struct task_struct *tsk) /* Ok, we're done with the signal handlers */ tsk->sighand = NULL; if (atomic_dec_and_test(&sighand->count)) - kmem_cache_free(sighand_cachep, sighand); + sighand_free(sighand); } void exit_sighand(struct task_struct *tsk) { write_lock_irq(&tasklist_lock); - __exit_sighand(tsk); + rcu_read_lock(); + if (tsk->sighand != NULL) { + struct sighand_struct *sighand = rcu_dereference(tsk->sighand); + spin_lock(&sighand->siglock); + __exit_sighand(tsk); + spin_unlock(&sighand->siglock); + } + rcu_read_unlock(); write_unlock_irq(&tasklist_lock); } @@ -345,19 +353,20 @@ void exit_sighand(struct task_struct *tsk) void __exit_signal(struct task_struct *tsk) { struct signal_struct * sig = tsk->signal; - struct sighand_struct * sighand = tsk->sighand; + struct sighand_struct * sighand; if (!sig) BUG(); if (!atomic_read(&sig->count)) BUG(); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); spin_lock(&sighand->siglock); posix_cpu_timers_exit(tsk); if (atomic_dec_and_test(&sig->count)) { posix_cpu_timers_exit_group(tsk); - if (tsk == sig->curr_target) - sig->curr_target = next_thread(tsk); tsk->signal = NULL; + __exit_sighand(tsk); spin_unlock(&sighand->siglock); flush_sigqueue(&sig->shared_pending); } else { @@ -389,9 +398,11 @@ void __exit_signal(struct task_struct *tsk) sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->sched_time += tsk->sched_time; + __exit_sighand(tsk); spin_unlock(&sighand->siglock); sig = NULL; /* Marker for below. */ } + rcu_read_unlock(); clear_tsk_thread_flag(tsk,TIF_SIGPENDING); flush_sigqueue(&tsk->pending); if (sig) { @@ -465,7 +476,7 @@ unblock_all_signals(void) spin_unlock_irqrestore(¤t->sighand->siglock, flags); } -static inline int collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static int collect_signal(int sig, struct sigpending *list, siginfo_t *info) { struct sigqueue *q, *first = NULL; int still_pending = 0; @@ -613,6 +624,33 @@ void signal_wake_up(struct task_struct *t, int resume) * Returns 1 if any signals were found. * * All callers must be holding the siglock. + * + * This version takes a sigset mask and looks at all signals, + * not just those in the first mask word. + */ +static int rm_from_queue_full(sigset_t *mask, struct sigpending *s) +{ + struct sigqueue *q, *n; + sigset_t m; + + sigandsets(&m, mask, &s->signal); + if (sigisemptyset(&m)) + return 0; + + signandsets(&s->signal, &s->signal, mask); + list_for_each_entry_safe(q, n, &s->list, list) { + if (sigismember(mask, q->info.si_signo)) { + list_del_init(&q->list); + __sigqueue_free(q); + } + } + return 1; +} +/* + * Remove signals in mask from the pending set and queue. + * Returns 1 if any signals were found. + * + * All callers must be holding the siglock. */ static int rm_from_queue(unsigned long mask, struct sigpending *s) { @@ -1080,18 +1118,29 @@ void zap_other_threads(struct task_struct *p) } /* - * Must be called with the tasklist_lock held for reading! + * Must be called under rcu_read_lock() or with tasklist_lock read-held. */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { unsigned long flags; + struct sighand_struct *sp; int ret; +retry: ret = check_kill_permission(sig, info, p); - if (!ret && sig && p->sighand) { - spin_lock_irqsave(&p->sighand->siglock, flags); + if (!ret && sig && (sp = rcu_dereference(p->sighand))) { + spin_lock_irqsave(&sp->siglock, flags); + if (p->sighand != sp) { + spin_unlock_irqrestore(&sp->siglock, flags); + goto retry; + } + if ((atomic_read(&sp->count) == 0) || + (atomic_read(&p->usage) == 0)) { + spin_unlock_irqrestore(&sp->siglock, flags); + return -ESRCH; + } ret = __group_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); + spin_unlock_irqrestore(&sp->siglock, flags); } return ret; @@ -1136,14 +1185,21 @@ int kill_proc_info(int sig, struct siginfo *info, pid_t pid) { int error; + int acquired_tasklist_lock = 0; struct task_struct *p; - read_lock(&tasklist_lock); + rcu_read_lock(); + if (unlikely(sig_kernel_stop(sig) || sig == SIGCONT)) { + read_lock(&tasklist_lock); + acquired_tasklist_lock = 1; + } p = find_task_by_pid(pid); error = -ESRCH; if (p) error = group_send_sig_info(sig, info, p); - read_unlock(&tasklist_lock); + if (unlikely(acquired_tasklist_lock)) + read_unlock(&tasklist_lock); + rcu_read_unlock(); return error; } @@ -1163,8 +1219,7 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, ret = -ESRCH; goto out_unlock; } - if ((!info || ((unsigned long)info != 1 && - (unsigned long)info != 2 && SI_FROMUSER(info))) + if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) && (euid != p->suid) && (euid != p->uid) && (uid != p->suid) && (uid != p->uid)) { ret = -EPERM; @@ -1355,16 +1410,54 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) { unsigned long flags; int ret = 0; + struct sighand_struct *sh; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); - read_lock(&tasklist_lock); + + /* + * The rcu based delayed sighand destroy makes it possible to + * run this without tasklist lock held. The task struct itself + * cannot go away as create_timer did get_task_struct(). + * + * We return -1, when the task is marked exiting, so + * posix_timer_event can redirect it to the group leader + */ + rcu_read_lock(); if (unlikely(p->flags & PF_EXITING)) { ret = -1; goto out_err; } - spin_lock_irqsave(&p->sighand->siglock, flags); +retry: + sh = rcu_dereference(p->sighand); + + spin_lock_irqsave(&sh->siglock, flags); + if (p->sighand != sh) { + /* We raced with exec() in a multithreaded process... */ + spin_unlock_irqrestore(&sh->siglock, flags); + goto retry; + } + + /* + * We do the check here again to handle the following scenario: + * + * CPU 0 CPU 1 + * send_sigqueue + * check PF_EXITING + * interrupt exit code running + * __exit_signal + * lock sighand->siglock + * unlock sighand->siglock + * lock sh->siglock + * add(tsk->pending) flush_sigqueue(tsk->pending) + * + */ + + if (unlikely(p->flags & PF_EXITING)) { + ret = -1; + goto out; + } if (unlikely(!list_empty(&q->list))) { /* @@ -1388,9 +1481,9 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) signal_wake_up(p, sig == SIGKILL); out: - spin_unlock_irqrestore(&p->sighand->siglock, flags); + spin_unlock_irqrestore(&sh->siglock, flags); out_err: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } @@ -1402,7 +1495,9 @@ send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) int ret = 0; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); + read_lock(&tasklist_lock); + /* Since it_lock is held, p->sighand cannot be NULL. */ spin_lock_irqsave(&p->sighand->siglock, flags); handle_stop_signal(sig, p); @@ -1436,7 +1531,7 @@ send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) out: spin_unlock_irqrestore(&p->sighand->siglock, flags); read_unlock(&tasklist_lock); - return(ret); + return ret; } /* @@ -1786,7 +1881,7 @@ do_signal_stop(int signr) * We return zero if we still hold the siglock and should look * for another signal without checking group_stop_count again. */ -static inline int handle_group_stop(void) +static int handle_group_stop(void) { int stop_count; @@ -2338,6 +2433,7 @@ int do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) { struct k_sigaction *k; + sigset_t mask; if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig))) return -EINVAL; @@ -2385,9 +2481,11 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) *k = *act; sigdelsetmask(&k->sa.sa_mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); - rm_from_queue(sigmask(sig), &t->signal->shared_pending); + sigemptyset(&mask); + sigaddset(&mask, sig); + rm_from_queue_full(&mask, &t->signal->shared_pending); do { - rm_from_queue(sigmask(sig), &t->pending); + rm_from_queue_full(&mask, &t->pending); recalc_sigpending_tsk(t); t = next_thread(t); } while (t != current); @@ -2623,6 +2721,32 @@ sys_pause(void) #endif +#ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND +asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize) +{ + sigset_t newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset, unewset, sizeof(newset))) + return -EFAULT; + sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + spin_lock_irq(¤t->sighand->siglock); + current->saved_sigmask = current->blocked; + current->blocked = newset; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_thread_flag(TIF_RESTORE_SIGMASK); + return -ERESTARTNOHAND; +} +#endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */ + void __init signals_init(void) { sigqueue_cachep = diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index b3d4dc858e3..dcfb5d73146 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -87,13 +87,9 @@ static int stop_machine(void) { int i, ret = 0; struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - mm_segment_t old_fs = get_fs(); /* One high-prio thread per cpu. We'll do this one. */ - set_fs(KERNEL_DS); - sys_sched_setscheduler(current->pid, SCHED_FIFO, - (struct sched_param __user *)¶m); - set_fs(old_fs); + sched_setscheduler(current, SCHED_FIFO, ¶m); atomic_set(&stopmachine_thread_ack, 0); stopmachine_num_threads = 0; diff --git a/kernel/sys.c b/kernel/sys.c index bce933ebb29..0929c698aff 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/kexec.h> #include <linux/workqueue.h> +#include <linux/capability.h> #include <linux/device.h> #include <linux/key.h> #include <linux/times.h> @@ -32,6 +33,7 @@ #include <linux/compat.h> #include <linux/syscalls.h> +#include <linux/kprobes.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -168,7 +170,7 @@ EXPORT_SYMBOL(notifier_chain_unregister); * of the last notifier function called. */ -int notifier_call_chain(struct notifier_block **n, unsigned long val, void *v) +int __kprobes notifier_call_chain(struct notifier_block **n, unsigned long val, void *v) { int ret=NOTIFY_DONE; struct notifier_block *nb = *n; @@ -222,6 +224,18 @@ int unregister_reboot_notifier(struct notifier_block * nb) EXPORT_SYMBOL(unregister_reboot_notifier); +#ifndef CONFIG_SECURITY +int capable(int cap) +{ + if (cap_raised(current->cap_effective, cap)) { + current->flags |= PF_SUPERPRIV; + return 1; + } + return 0; +} +EXPORT_SYMBOL(capable); +#endif + static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; @@ -426,23 +440,25 @@ void kernel_kexec(void) } EXPORT_SYMBOL_GPL(kernel_kexec); +void kernel_shutdown_prepare(enum system_states state) +{ + notifier_call_chain(&reboot_notifier_list, + (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); + system_state = state; + device_shutdown(); +} /** * kernel_halt - halt the system * * Shutdown everything and perform a clean system halt. */ -void kernel_halt_prepare(void) -{ - notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL); - system_state = SYSTEM_HALT; - device_shutdown(); -} void kernel_halt(void) { - kernel_halt_prepare(); + kernel_shutdown_prepare(SYSTEM_HALT); printk(KERN_EMERG "System halted.\n"); machine_halt(); } + EXPORT_SYMBOL_GPL(kernel_halt); /** @@ -450,20 +466,13 @@ EXPORT_SYMBOL_GPL(kernel_halt); * * Shutdown everything and perform a clean system power_off. */ -void kernel_power_off_prepare(void) -{ - notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL); - system_state = SYSTEM_POWER_OFF; - device_shutdown(); -} void kernel_power_off(void) { - kernel_power_off_prepare(); + kernel_shutdown_prepare(SYSTEM_POWER_OFF); printk(KERN_EMERG "Power down.\n"); machine_power_off(); } EXPORT_SYMBOL_GPL(kernel_power_off); - /* * Reboot system call: for obvious reasons only root may call it, * and even root needs to set up some magic numbers in the registers @@ -488,6 +497,12 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user magic2 != LINUX_REBOOT_MAGIC2C)) return -EINVAL; + /* Instead of trying to make the power_off code look like + * halt when pm_power_off is not set do it the easy way. + */ + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) + cmd = LINUX_REBOOT_CMD_HALT; + lock_kernel(); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: @@ -1083,10 +1098,11 @@ asmlinkage long sys_times(struct tms __user * tbuf) asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) { struct task_struct *p; + struct task_struct *group_leader = current->group_leader; int err = -EINVAL; if (!pid) - pid = current->pid; + pid = group_leader->pid; if (!pgid) pgid = pid; if (pgid < 0) @@ -1106,16 +1122,16 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) if (!thread_group_leader(p)) goto out; - if (p->parent == current || p->real_parent == current) { + if (p->real_parent == group_leader) { err = -EPERM; - if (p->signal->session != current->signal->session) + if (p->signal->session != group_leader->signal->session) goto out; err = -EACCES; if (p->did_exec) goto out; } else { err = -ESRCH; - if (p != current) + if (p != group_leader) goto out; } @@ -1127,7 +1143,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) struct task_struct *p; do_each_task_pid(pgid, PIDTYPE_PGID, p) { - if (p->signal->session == current->signal->session) + if (p->signal->session == group_leader->signal->session) goto ok_pgid; } while_each_task_pid(pgid, PIDTYPE_PGID, p); goto out; @@ -1207,24 +1223,22 @@ asmlinkage long sys_getsid(pid_t pid) asmlinkage long sys_setsid(void) { + struct task_struct *group_leader = current->group_leader; struct pid *pid; int err = -EPERM; - if (!thread_group_leader(current)) - return -EINVAL; - down(&tty_sem); write_lock_irq(&tasklist_lock); - pid = find_pid(PIDTYPE_PGID, current->pid); + pid = find_pid(PIDTYPE_PGID, group_leader->pid); if (pid) goto out; - current->signal->leader = 1; - __set_special_pids(current->pid, current->pid); - current->signal->tty = NULL; - current->signal->tty_old_pgrp = 0; - err = process_group(current); + group_leader->signal->leader = 1; + __set_special_pids(group_leader->pid, group_leader->pid); + group_leader->signal->tty = NULL; + group_leader->signal->tty_old_pgrp = 0; + err = process_group(group_leader); out: write_unlock_irq(&tasklist_lock); up(&tty_sem); @@ -1686,7 +1700,10 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) if (unlikely(!p->signal)) return; + utime = stime = cputime_zero; + switch (who) { + case RUSAGE_BOTH: case RUSAGE_CHILDREN: spin_lock_irqsave(&p->sighand->siglock, flags); utime = p->signal->cutime; @@ -1696,22 +1713,11 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; spin_unlock_irqrestore(&p->sighand->siglock, flags); - cputime_to_timeval(utime, &r->ru_utime); - cputime_to_timeval(stime, &r->ru_stime); - break; + + if (who == RUSAGE_CHILDREN) + break; + case RUSAGE_SELF: - spin_lock_irqsave(&p->sighand->siglock, flags); - utime = stime = cputime_zero; - goto sum_group; - case RUSAGE_BOTH: - spin_lock_irqsave(&p->sighand->siglock, flags); - utime = p->signal->cutime; - stime = p->signal->cstime; - r->ru_nvcsw = p->signal->cnvcsw; - r->ru_nivcsw = p->signal->cnivcsw; - r->ru_minflt = p->signal->cmin_flt; - r->ru_majflt = p->signal->cmaj_flt; - sum_group: utime = cputime_add(utime, p->signal->utime); stime = cputime_add(stime, p->signal->stime); r->ru_nvcsw += p->signal->nvcsw; @@ -1728,13 +1734,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_majflt += t->maj_flt; t = next_thread(t); } while (t != p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - cputime_to_timeval(utime, &r->ru_utime); - cputime_to_timeval(stime, &r->ru_stime); break; + default: BUG(); } + + cputime_to_timeval(utime, &r->ru_utime); + cputime_to_timeval(stime, &r->ru_stime); } int getrusage(struct task_struct *p, int who, struct rusage __user *ru) diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 1ab2370e2ef..17313b99e53 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -82,6 +82,28 @@ cond_syscall(compat_sys_socketcall); cond_syscall(sys_inotify_init); cond_syscall(sys_inotify_add_watch); cond_syscall(sys_inotify_rm_watch); +cond_syscall(sys_migrate_pages); +cond_syscall(sys_chown16); +cond_syscall(sys_fchown16); +cond_syscall(sys_getegid16); +cond_syscall(sys_geteuid16); +cond_syscall(sys_getgid16); +cond_syscall(sys_getgroups16); +cond_syscall(sys_getresgid16); +cond_syscall(sys_getresuid16); +cond_syscall(sys_getuid16); +cond_syscall(sys_lchown16); +cond_syscall(sys_setfsgid16); +cond_syscall(sys_setfsuid16); +cond_syscall(sys_setgid16); +cond_syscall(sys_setgroups16); +cond_syscall(sys_setregid16); +cond_syscall(sys_setresgid16); +cond_syscall(sys_setresuid16); +cond_syscall(sys_setreuid16); +cond_syscall(sys_setuid16); +cond_syscall(sys_vm86old); +cond_syscall(sys_vm86); /* arch-specific weak syscall entries */ cond_syscall(sys_pciconfig_read); @@ -90,3 +112,5 @@ cond_syscall(sys_pciconfig_iobase); cond_syscall(sys32_ipc); cond_syscall(sys32_sysctl); cond_syscall(ppc_rtas); +cond_syscall(sys_spu_run); +cond_syscall(sys_spu_create); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9990e10192e..cb99a42f8b3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -25,12 +25,14 @@ #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> +#include <linux/capability.h> #include <linux/ctype.h> #include <linux/utsname.h> #include <linux/capability.h> #include <linux/smp_lock.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/kobject.h> #include <linux/net.h> #include <linux/sysrq.h> #include <linux/highuid.h> @@ -67,6 +69,8 @@ extern int min_free_kbytes; extern int printk_ratelimit_jiffies; extern int printk_ratelimit_burst; extern int pid_max_min, pid_max_max; +extern int sysctl_drop_caches; +extern int percpu_pagelist_fraction; #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) int unknown_nmi_panic; @@ -77,15 +81,13 @@ extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *, /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ static int maxolduid = 65535; static int minolduid; +static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; #ifdef CONFIG_KMOD extern char modprobe_path[]; #endif -#ifdef CONFIG_HOTPLUG -extern char hotplug_path[]; -#endif #ifdef CONFIG_CHR_DEV_SG extern int sg_big_buff; #endif @@ -110,7 +112,7 @@ extern int pwrsw_enabled; extern int unaligned_enabled; #endif -#ifdef CONFIG_ARCH_S390 +#ifdef CONFIG_S390 #ifdef CONFIG_MATHEMU extern int sysctl_ieee_emulation_warnings; #endif @@ -397,8 +399,8 @@ static ctl_table kern_table[] = { { .ctl_name = KERN_HOTPLUG, .procname = "hotplug", - .data = &hotplug_path, - .maxlen = HOTPLUG_PATH_LEN, + .data = &uevent_helper, + .maxlen = UEVENT_HELPER_PATH_LEN, .mode = 0644, .proc_handler = &proc_dostring, .strategy = &sysctl_string, @@ -544,7 +546,7 @@ static ctl_table kern_table[] = { .extra1 = &minolduid, .extra2 = &maxolduid, }, -#ifdef CONFIG_ARCH_S390 +#ifdef CONFIG_S390 #ifdef CONFIG_MATHEMU { .ctl_name = KERN_IEEE_EMULATION_WARNINGS, @@ -646,7 +648,7 @@ static ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, -#if defined(CONFIG_ARCH_S390) +#if defined(CONFIG_S390) && defined(CONFIG_SMP) { .ctl_name = KERN_SPIN_RETRY, .procname = "spin_retry", @@ -777,6 +779,15 @@ static ctl_table vm_table[] = { .strategy = &sysctl_intvec, }, { + .ctl_name = VM_DROP_PAGECACHE, + .procname = "drop_caches", + .data = &sysctl_drop_caches, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = drop_caches_sysctl_handler, + .strategy = &sysctl_intvec, + }, + { .ctl_name = VM_MIN_FREE_KBYTES, .procname = "min_free_kbytes", .data = &min_free_kbytes, @@ -786,6 +797,16 @@ static ctl_table vm_table[] = { .strategy = &sysctl_intvec, .extra1 = &zero, }, + { + .ctl_name = VM_PERCPU_PAGELIST_FRACTION, + .procname = "percpu_pagelist_fraction", + .data = &percpu_pagelist_fraction, + .maxlen = sizeof(percpu_pagelist_fraction), + .mode = 0644, + .proc_handler = &percpu_pagelist_fraction_sysctl_handler, + .strategy = &sysctl_intvec, + .extra1 = &min_percpu_pagelist_fract, + }, #ifdef CONFIG_MMU { .ctl_name = VM_MAX_MAP_COUNT, @@ -849,6 +870,17 @@ static ctl_table vm_table[] = { .strategy = &sysctl_jiffies, }, #endif +#ifdef CONFIG_NUMA + { + .ctl_name = VM_ZONE_RECLAIM_MODE, + .procname = "zone_reclaim_mode", + .data = &zone_reclaim_mode, + .maxlen = sizeof(zone_reclaim_mode), + .mode = 0644, + .proc_handler = &proc_dointvec, + .strategy = &zero, + }, +#endif { .ctl_name = 0 } }; @@ -2192,29 +2224,32 @@ int sysctl_string(ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen, void **context) { - size_t l, len; - if (!table->data || !table->maxlen) return -ENOTDIR; if (oldval && oldlenp) { - if (get_user(len, oldlenp)) + size_t bufsize; + if (get_user(bufsize, oldlenp)) return -EFAULT; - if (len) { - l = strlen(table->data); - if (len > l) len = l; - if (len >= table->maxlen) + if (bufsize) { + size_t len = strlen(table->data), copied; + + /* This shouldn't trigger for a well-formed sysctl */ + if (len > table->maxlen) len = table->maxlen; - if(copy_to_user(oldval, table->data, len)) - return -EFAULT; - if(put_user(0, ((char __user *) oldval) + len)) + + /* Copy up to a max of bufsize-1 bytes of the string */ + copied = (len >= bufsize) ? bufsize - 1 : len; + + if (copy_to_user(oldval, table->data, copied) || + put_user(0, (char __user *)(oldval + copied))) return -EFAULT; - if(put_user(len, oldlenp)) + if (put_user(len, oldlenp)) return -EFAULT; } } if (newval && newlen) { - len = newlen; + size_t len = newlen; if (len > table->maxlen) len = table->maxlen; if(copy_from_user(table->data, newval, len)) @@ -2223,7 +2258,7 @@ int sysctl_string(ctl_table *table, int __user *name, int nlen, len--; ((char *) table->data)[len] = 0; } - return 0; + return 1; } /* diff --git a/kernel/time.c b/kernel/time.c index 245d595a13c..7477b1d2079 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/timex.h> +#include <linux/capability.h> #include <linux/errno.h> #include <linux/smp_lock.h> #include <linux/syscalls.h> @@ -154,6 +155,9 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz) static int firsttime = 1; int error = 0; + if (!timespec_valid(tv)) + return -EINVAL; + error = security_settime(tv, tz); if (error) return error; @@ -561,6 +565,108 @@ void getnstimeofday(struct timespec *tv) EXPORT_SYMBOL_GPL(getnstimeofday); #endif +/* Converts Gregorian date to seconds since 1970-01-01 00:00:00. + * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 + * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. + * + * [For the Julian calendar (which was used in Russia before 1917, + * Britain & colonies before 1752, anywhere else before 1582, + * and is still in use by some communities) leave out the + * -year/100+year/400 terms, and add 10.] + * + * This algorithm was first published by Gauss (I think). + * + * WARNING: this function will overflow on 2106-02-07 06:28:16 on + * machines were long is 32-bit! (However, as time_t is signed, we + * will already get problems at other places on 2038-01-19 03:14:08) + */ +unsigned long +mktime(const unsigned int year0, const unsigned int mon0, + const unsigned int day, const unsigned int hour, + const unsigned int min, const unsigned int sec) +{ + unsigned int mon = mon0, year = year0; + + /* 1..12 -> 11,12,1..10 */ + if (0 >= (int) (mon -= 2)) { + mon += 12; /* Puts Feb last since it has leap day */ + year -= 1; + } + + return ((((unsigned long) + (year/4 - year/100 + year/400 + 367*mon/12 + day) + + year*365 - 719499 + )*24 + hour /* now have hours */ + )*60 + min /* now have minutes */ + )*60 + sec; /* finally seconds */ +} + +EXPORT_SYMBOL(mktime); + +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec) +{ + while (nsec >= NSEC_PER_SEC) { + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} + +/** + * ns_to_timespec - Convert nanoseconds to timespec + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec representation of the nsec parameter. + */ +inline struct timespec ns_to_timespec(const nsec_t nsec) +{ + struct timespec ts; + + if (nsec) + ts.tv_sec = div_long_long_rem_signed(nsec, NSEC_PER_SEC, + &ts.tv_nsec); + else + ts.tv_sec = ts.tv_nsec = 0; + + return ts; +} + +/** + * ns_to_timeval - Convert nanoseconds to timeval + * @nsec: the nanoseconds value to be converted + * + * Returns the timeval representation of the nsec parameter. + */ +struct timeval ns_to_timeval(const nsec_t nsec) +{ + struct timespec ts = ns_to_timespec(nsec); + struct timeval tv; + + tv.tv_sec = ts.tv_sec; + tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000; + + return tv; +} + #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) { diff --git a/kernel/timer.c b/kernel/timer.c index fd74268d866..4f1cb0ab525 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -33,6 +33,7 @@ #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> +#include <linux/delay.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -857,6 +858,7 @@ static void run_timer_softirq(struct softirq_action *h) { tvec_base_t *base = &__get_cpu_var(tvec_bases); + hrtimer_run_queues(); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } @@ -1118,62 +1120,6 @@ asmlinkage long sys_gettid(void) return current->pid; } -static long __sched nanosleep_restart(struct restart_block *restart) -{ - unsigned long expire = restart->arg0, now = jiffies; - struct timespec __user *rmtp = (struct timespec __user *) restart->arg1; - long ret; - - /* Did it expire while we handled signals? */ - if (!time_after(expire, now)) - return 0; - - expire = schedule_timeout_interruptible(expire - now); - - ret = 0; - if (expire) { - struct timespec t; - jiffies_to_timespec(expire, &t); - - ret = -ERESTART_RESTARTBLOCK; - if (rmtp && copy_to_user(rmtp, &t, sizeof(t))) - ret = -EFAULT; - /* The 'restart' block is already filled in */ - } - return ret; -} - -asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp) -{ - struct timespec t; - unsigned long expire; - long ret; - - if (copy_from_user(&t, rqtp, sizeof(t))) - return -EFAULT; - - if ((t.tv_nsec >= 1000000000L) || (t.tv_nsec < 0) || (t.tv_sec < 0)) - return -EINVAL; - - expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec); - expire = schedule_timeout_interruptible(expire); - - ret = 0; - if (expire) { - struct restart_block *restart; - jiffies_to_timespec(expire, &t); - if (rmtp && copy_to_user(rmtp, &t, sizeof(t))) - return -EFAULT; - - restart = ¤t_thread_info()->restart_block; - restart->fn = nanosleep_restart; - restart->arg0 = jiffies + expire; - restart->arg1 = (unsigned long) rmtp; - ret = -ERESTART_RESTARTBLOCK; - } - return ret; -} - /* * sys_sysinfo - fill in sysinfo struct */ diff --git a/kernel/uid16.c b/kernel/uid16.c index f669941e8b2..aa25605027c 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -10,6 +10,7 @@ #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/prctl.h> +#include <linux/capability.h> #include <linux/init.h> #include <linux/highuid.h> #include <linux/security.h> diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2bd5aee1c73..b052e2c4c71 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -29,7 +29,8 @@ #include <linux/kthread.h> /* - * The per-CPU workqueue (if single thread, we always use cpu 0's). + * The per-CPU workqueue (if single thread, we always use the first + * possible cpu). * * The sequence counters are for flush_scheduled_work(). It wants to wait * until until all currently-scheduled works are completed, but it doesn't @@ -69,6 +70,8 @@ struct workqueue_struct { static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); +static int singlethread_cpu; + /* If it's single threaded, it isn't in the list of workqueues. */ static inline int is_single_threaded(struct workqueue_struct *wq) { @@ -102,7 +105,7 @@ int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work) if (!test_and_set_bit(0, &work->pending)) { if (unlikely(is_single_threaded(wq))) - cpu = any_online_cpu(cpu_online_map); + cpu = singlethread_cpu; BUG_ON(!list_empty(&work->entry)); __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work); ret = 1; @@ -118,7 +121,7 @@ static void delayed_work_timer_fn(unsigned long __data) int cpu = smp_processor_id(); if (unlikely(is_single_threaded(wq))) - cpu = any_online_cpu(cpu_online_map); + cpu = singlethread_cpu; __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work); } @@ -144,7 +147,7 @@ int fastcall queue_delayed_work(struct workqueue_struct *wq, return ret; } -static inline void run_workqueue(struct cpu_workqueue_struct *cwq) +static void run_workqueue(struct cpu_workqueue_struct *cwq) { unsigned long flags; @@ -267,7 +270,7 @@ void fastcall flush_workqueue(struct workqueue_struct *wq) if (is_single_threaded(wq)) { /* Always use first cpu's area. */ - flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, any_online_cpu(cpu_online_map))); + flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, singlethread_cpu)); } else { int cpu; @@ -315,12 +318,17 @@ struct workqueue_struct *__create_workqueue(const char *name, return NULL; wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct); + if (!wq->cpu_wq) { + kfree(wq); + return NULL; + } + wq->name = name; /* We don't need the distraction of CPUs appearing and vanishing. */ lock_cpu_hotplug(); if (singlethread) { INIT_LIST_HEAD(&wq->list); - p = create_workqueue_thread(wq, any_online_cpu(cpu_online_map)); + p = create_workqueue_thread(wq, singlethread_cpu); if (!p) destroy = 1; else @@ -374,7 +382,7 @@ void destroy_workqueue(struct workqueue_struct *wq) /* We don't need the distraction of CPUs appearing and vanishing. */ lock_cpu_hotplug(); if (is_single_threaded(wq)) - cleanup_workqueue_thread(wq, any_online_cpu(cpu_online_map)); + cleanup_workqueue_thread(wq, singlethread_cpu); else { for_each_online_cpu(cpu) cleanup_workqueue_thread(wq, cpu); @@ -419,6 +427,25 @@ int schedule_delayed_work_on(int cpu, return ret; } +int schedule_on_each_cpu(void (*func) (void *info), void *info) +{ + int cpu; + struct work_struct *work; + + work = kmalloc(NR_CPUS * sizeof(struct work_struct), GFP_KERNEL); + + if (!work) + return -ENOMEM; + for_each_online_cpu(cpu) { + INIT_WORK(work + cpu, func, info); + __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), + work + cpu); + } + flush_workqueue(keventd_wq); + kfree(work); + return 0; +} + void flush_scheduled_work(void) { flush_workqueue(keventd_wq); @@ -543,6 +570,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, void init_workqueues(void) { + singlethread_cpu = first_cpu(cpu_possible_map); hotcpu_notifier(workqueue_cpu_callback, 0); keventd_wq = create_workqueue("events"); BUG_ON(!keventd_wq); |