diff options
Diffstat (limited to 'kernel')
36 files changed, 1391 insertions, 826 deletions
diff --git a/kernel/Kconfig.instrumentation b/kernel/Kconfig.instrumentation deleted file mode 100644 index 468f47ad750..00000000000 --- a/kernel/Kconfig.instrumentation +++ /dev/null @@ -1,49 +0,0 @@ -menuconfig INSTRUMENTATION - bool "Instrumentation Support" - default y - ---help--- - Say Y here to get to see options related to performance measurement, - system-wide debugging, and testing. This option alone does not add any - kernel code. - - If you say N, all options in this submenu will be skipped and - disabled. If you're trying to debug the kernel itself, go see the - Kernel Hacking menu. - -if INSTRUMENTATION - -config PROFILING - bool "Profiling support (EXPERIMENTAL)" - help - Say Y here to enable the extended profiling support mechanisms used - by profilers such as OProfile. - -config OPROFILE - tristate "OProfile system profiling (EXPERIMENTAL)" - depends on PROFILING && !UML - depends on ARCH_SUPPORTS_OPROFILE || ALPHA || ARM || BLACKFIN || IA64 || M32R || PARISC || PPC || S390 || SUPERH || SPARC - help - OProfile is a profiling system capable of profiling the - whole system, include the kernel, kernel modules, libraries, - and applications. - - If unsure, say N. - -config KPROBES - bool "Kprobes" - depends on KALLSYMS && MODULES && !UML - depends on X86_32 || IA64 || PPC || S390 || SPARC64 || X86_64 || AVR32 - help - Kprobes allows you to trap at almost any kernel address and - execute a callback function. register_kprobe() establishes - a probepoint and specifies the callback. Kprobes is useful - for kernel debugging, non-intrusive instrumentation and testing. - If in doubt, say "N". - -config MARKERS - bool "Activate markers" - help - Place an empty function call at each marker site. Can be - dynamically changed for a probe function. - -endif # INSTRUMENTATION diff --git a/kernel/Makefile b/kernel/Makefile index 8885627ea02..685697c0a18 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -8,8 +8,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ signal.o sys.o kmod.o workqueue.o pid.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 rwsem.o latency.o nsproxy.o srcu.o \ - utsname.o notifier.o + hrtimer.o rwsem.o nsproxy.o srcu.o \ + utsname.o notifier.o ksysfs.o pm_qos_params.o obj-$(CONFIG_SYSCTL) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o @@ -43,13 +43,13 @@ obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o obj-$(CONFIG_IKCONFIG) += configs.o +obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o obj-$(CONFIG_STOP_MACHINE) += stop_machine.o obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o obj-$(CONFIG_AUDIT) += audit.o auditfilter.o obj-$(CONFIG_AUDITSYSCALL) += auditsc.o obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_SYSFS) += ksysfs.o obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o diff --git a/kernel/capability.c b/kernel/capability.c index efbd9cdce13..39e8193b41e 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -22,6 +22,37 @@ static DEFINE_SPINLOCK(task_capability_lock); /* + * Leveraged for setting/resetting capabilities + */ + +const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; +const kernel_cap_t __cap_full_set = CAP_FULL_SET; +const kernel_cap_t __cap_init_eff_set = CAP_INIT_EFF_SET; + +EXPORT_SYMBOL(__cap_empty_set); +EXPORT_SYMBOL(__cap_full_set); +EXPORT_SYMBOL(__cap_init_eff_set); + +/* + * More recent versions of libcap are available from: + * + * http://www.kernel.org/pub/linux/libs/security/linux-privs/ + */ + +static void warn_legacy_capability_use(void) +{ + static int warned; + if (!warned) { + char name[sizeof(current->comm)]; + + printk(KERN_INFO "warning: `%s' uses 32-bit capabilities" + " (legacy support in use)\n", + get_task_comm(name, current)); + warned = 1; + } +} + +/* * For sys_getproccap() and sys_setproccap(), any of the three * capability set pointers may be NULL -- indicating that that set is * uninteresting and/or not to be changed. @@ -42,12 +73,21 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) pid_t pid; __u32 version; struct task_struct *target; - struct __user_cap_data_struct data; + unsigned tocopy; + kernel_cap_t pE, pI, pP; if (get_user(version, &header->version)) return -EFAULT; - if (version != _LINUX_CAPABILITY_VERSION) { + switch (version) { + case _LINUX_CAPABILITY_VERSION_1: + warn_legacy_capability_use(); + tocopy = _LINUX_CAPABILITY_U32S_1; + break; + case _LINUX_CAPABILITY_VERSION_2: + tocopy = _LINUX_CAPABILITY_U32S_2; + break; + default: if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; @@ -71,14 +111,47 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) } else target = current; - ret = security_capget(target, &data.effective, &data.inheritable, &data.permitted); + ret = security_capget(target, &pE, &pI, &pP); out: read_unlock(&tasklist_lock); spin_unlock(&task_capability_lock); - if (!ret && copy_to_user(dataptr, &data, sizeof data)) - return -EFAULT; + if (!ret) { + struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + unsigned i; + + for (i = 0; i < tocopy; i++) { + kdata[i].effective = pE.cap[i]; + kdata[i].permitted = pP.cap[i]; + kdata[i].inheritable = pI.cap[i]; + } + + /* + * Note, in the case, tocopy < _LINUX_CAPABILITY_U32S, + * we silently drop the upper capabilities here. This + * has the effect of making older libcap + * implementations implicitly drop upper capability + * bits when they perform a: capget/modify/capset + * sequence. + * + * This behavior is considered fail-safe + * behavior. Upgrading the application to a newer + * version of libcap will enable access to the newer + * capabilities. + * + * An alternative would be to return an error here + * (-ERANGE), but that causes legacy applications to + * unexpectidly fail; the capget/modify/capset aborts + * before modification is attempted and the application + * fails. + */ + + if (copy_to_user(dataptr, kdata, tocopy + * sizeof(struct __user_cap_data_struct))) { + return -EFAULT; + } + } return ret; } @@ -167,6 +240,8 @@ static inline int cap_set_all(kernel_cap_t *effective, */ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) { + struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + unsigned i, tocopy; kernel_cap_t inheritable, permitted, effective; __u32 version; struct task_struct *target; @@ -176,7 +251,15 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) if (get_user(version, &header->version)) return -EFAULT; - if (version != _LINUX_CAPABILITY_VERSION) { + switch (version) { + case _LINUX_CAPABILITY_VERSION_1: + warn_legacy_capability_use(); + tocopy = _LINUX_CAPABILITY_U32S_1; + break; + case _LINUX_CAPABILITY_VERSION_2: + tocopy = _LINUX_CAPABILITY_U32S_2; + break; + default: if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; @@ -188,10 +271,22 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) if (pid && pid != task_pid_vnr(current) && !capable(CAP_SETPCAP)) return -EPERM; - if (copy_from_user(&effective, &data->effective, sizeof(effective)) || - copy_from_user(&inheritable, &data->inheritable, sizeof(inheritable)) || - copy_from_user(&permitted, &data->permitted, sizeof(permitted))) + if (copy_from_user(&kdata, data, tocopy + * sizeof(struct __user_cap_data_struct))) { return -EFAULT; + } + + for (i = 0; i < tocopy; i++) { + effective.cap[i] = kdata[i].effective; + permitted.cap[i] = kdata[i].permitted; + inheritable.cap[i] = kdata[i].inheritable; + } + while (i < _LINUX_CAPABILITY_U32S) { + effective.cap[i] = 0; + permitted.cap[i] = 0; + inheritable.cap[i] = 0; + i++; + } spin_lock(&task_capability_lock); read_lock(&tasklist_lock); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1a3c23936d4..4766bb65e4d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -141,7 +141,7 @@ enum { ROOT_NOPREFIX, /* mounted subsystems have no named prefix */ }; -inline int cgroup_is_releasable(const struct cgroup *cgrp) +static int cgroup_is_releasable(const struct cgroup *cgrp) { const int bits = (1 << CGRP_RELEASABLE) | @@ -149,7 +149,7 @@ inline int cgroup_is_releasable(const struct cgroup *cgrp) return (cgrp->flags & bits) == bits; } -inline int notify_on_release(const struct cgroup *cgrp) +static int notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } @@ -489,7 +489,7 @@ static struct css_set *find_css_set( * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only - * attach_task() can increment it again. Because a count of zero + * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely @@ -520,17 +520,17 @@ static struct css_set *find_css_set( * The task_lock() exception * * The need for this exception arises from the action of - * attach_task(), which overwrites one tasks cgroup pointer with + * cgroup_attach_task(), which overwrites one tasks cgroup pointer with * another. It does so using cgroup_mutexe, however there are * several performance critical places that need to reference * task->cgroup without the expense of grabbing a system global * mutex. Therefore except as noted below, when dereferencing or, as - * in attach_task(), modifying a task'ss cgroup pointer we use + * in cgroup_attach_task(), modifying a task'ss cgroup 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 cgroup pointer by attach_task() + * update of a tasks cgroup pointer by cgroup_attach_task() */ /** @@ -586,11 +586,27 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) return inode; } +/* + * Call subsys's pre_destroy handler. + * This is called before css refcnt check. + */ + +static void cgroup_call_pre_destroy(struct cgroup *cgrp) +{ + struct cgroup_subsys *ss; + for_each_subsys(cgrp->root, ss) + if (ss->pre_destroy && cgrp->subsys[ss->subsys_id]) + ss->pre_destroy(ss, cgrp); + return; +} + + static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ if (S_ISDIR(inode->i_mode)) { struct cgroup *cgrp = dentry->d_fsdata; + struct cgroup_subsys *ss; BUG_ON(!(cgroup_is_removed(cgrp))); /* It's possible for external users to be holding css * reference counts on a cgroup; css_put() needs to @@ -599,6 +615,23 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) * queue the cgroup to be handled by the release * agent */ synchronize_rcu(); + + mutex_lock(&cgroup_mutex); + /* + * Release the subsystem state objects. + */ + for_each_subsys(cgrp->root, ss) { + if (cgrp->subsys[ss->subsys_id]) + ss->destroy(ss, cgrp); + } + + cgrp->root->number_of_cgroups--; + mutex_unlock(&cgroup_mutex); + + /* Drop the active superblock reference that we took when we + * created the cgroup */ + deactivate_super(cgrp->root->sb); + kfree(cgrp); } iput(inode); @@ -1161,7 +1194,7 @@ static void get_first_subsys(const struct cgroup *cgrp, * Call holding cgroup_mutex. May take task_lock of * the task 'pid' during call. */ -static int attach_task(struct cgroup *cgrp, struct task_struct *tsk) +int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { int retval = 0; struct cgroup_subsys *ss; @@ -1181,9 +1214,8 @@ static int attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { retval = ss->can_attach(ss, cgrp, tsk); - if (retval) { + if (retval) return retval; - } } } @@ -1192,9 +1224,8 @@ static int attach_task(struct cgroup *cgrp, struct task_struct *tsk) * based on its final set of cgroups */ newcg = find_css_set(cg, cgrp); - if (!newcg) { + if (!newcg) return -ENOMEM; - } task_lock(tsk); if (tsk->flags & PF_EXITING) { @@ -1214,9 +1245,8 @@ static int attach_task(struct cgroup *cgrp, struct task_struct *tsk) write_unlock(&css_set_lock); for_each_subsys(root, ss) { - if (ss->attach) { + if (ss->attach) ss->attach(ss, cgrp, oldcgrp, tsk); - } } set_bit(CGRP_RELEASABLE, &oldcgrp->flags); synchronize_rcu(); @@ -1239,7 +1269,7 @@ static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf) if (pid) { rcu_read_lock(); - tsk = find_task_by_pid(pid); + tsk = find_task_by_vpid(pid); if (!tsk || tsk->flags & PF_EXITING) { rcu_read_unlock(); return -ESRCH; @@ -1257,7 +1287,7 @@ static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf) get_task_struct(tsk); } - ret = attach_task(cgrp, tsk); + ret = cgroup_attach_task(cgrp, tsk); put_task_struct(tsk); return ret; } @@ -1329,9 +1359,14 @@ static ssize_t cgroup_common_file_write(struct cgroup *cgrp, goto out1; } buffer[nbytes] = 0; /* nul-terminate */ + strstrip(buffer); /* strip -just- trailing whitespace */ mutex_lock(&cgroup_mutex); + /* + * This was already checked for in cgroup_file_write(), but + * check again now we're holding cgroup_mutex. + */ if (cgroup_is_removed(cgrp)) { retval = -ENODEV; goto out2; @@ -1349,24 +1384,9 @@ static ssize_t cgroup_common_file_write(struct cgroup *cgrp, clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); break; case FILE_RELEASE_AGENT: - { - struct cgroupfs_root *root = cgrp->root; - /* Strip trailing newline */ - if (nbytes && (buffer[nbytes-1] == '\n')) { - buffer[nbytes-1] = 0; - } - if (nbytes < sizeof(root->release_agent_path)) { - /* We never write anything other than '\0' - * into the last char of release_agent_path, - * so it always remains a NUL-terminated - * string */ - strncpy(root->release_agent_path, buffer, nbytes); - root->release_agent_path[nbytes] = 0; - } else { - retval = -ENOSPC; - } + BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + strcpy(cgrp->root->release_agent_path, buffer); break; - } default: retval = -EINVAL; goto out2; @@ -1387,7 +1407,7 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft) + if (!cft || cgroup_is_removed(cgrp)) return -ENODEV; if (cft->write) return cft->write(cgrp, cft, file, buf, nbytes, ppos); @@ -1457,7 +1477,7 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft) + if (!cft || cgroup_is_removed(cgrp)) return -ENODEV; if (cft->read) @@ -1675,6 +1695,29 @@ static void cgroup_advance_iter(struct cgroup *cgrp, it->task = cg->tasks.next; } +/* + * To reduce the fork() overhead for systems that are not actually + * using their cgroups capability, we don't maintain the lists running + * through each css_set to its tasks until we see the list actually + * used - in other words after the first call to cgroup_iter_start(). + * + * The tasklist_lock is not held here, as do_each_thread() and + * while_each_thread() are protected by RCU. + */ +void cgroup_enable_task_cg_lists(void) +{ + struct task_struct *p, *g; + write_lock(&css_set_lock); + use_task_css_set_links = 1; + do_each_thread(g, p) { + task_lock(p); + if (list_empty(&p->cg_list)) + list_add(&p->cg_list, &p->cgroups->tasks); + task_unlock(p); + } while_each_thread(g, p); + write_unlock(&css_set_lock); +} + void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) { /* @@ -1682,18 +1725,9 @@ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) * we need to enable the list linking each css_set to its * tasks, and fix up all existing tasks. */ - if (!use_task_css_set_links) { - struct task_struct *p, *g; - write_lock(&css_set_lock); - use_task_css_set_links = 1; - do_each_thread(g, p) { - task_lock(p); - if (list_empty(&p->cg_list)) - list_add(&p->cg_list, &p->cgroups->tasks); - task_unlock(p); - } while_each_thread(g, p); - write_unlock(&css_set_lock); - } + if (!use_task_css_set_links) + cgroup_enable_task_cg_lists(); + read_lock(&css_set_lock); it->cg_link = &cgrp->css_sets; cgroup_advance_iter(cgrp, it); @@ -1726,6 +1760,166 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it) read_unlock(&css_set_lock); } +static inline int started_after_time(struct task_struct *t1, + struct timespec *time, + struct task_struct *t2) +{ + int start_diff = timespec_compare(&t1->start_time, time); + if (start_diff > 0) { + return 1; + } else if (start_diff < 0) { + return 0; + } else { + /* + * Arbitrarily, if two processes started at the same + * time, we'll say that the lower pointer value + * started first. Note that t2 may have exited by now + * so this may not be a valid pointer any longer, but + * that's fine - it still serves to distinguish + * between two tasks started (effectively) simultaneously. + */ + return t1 > t2; + } +} + +/* + * This function is a callback from heap_insert() and is used to order + * the heap. + * In this case we order the heap in descending task start time. + */ +static inline int started_after(void *p1, void *p2) +{ + struct task_struct *t1 = p1; + struct task_struct *t2 = p2; + return started_after_time(t1, &t2->start_time, t2); +} + +/** + * cgroup_scan_tasks - iterate though all the tasks in a cgroup + * @scan: struct cgroup_scanner containing arguments for the scan + * + * Arguments include pointers to callback functions test_task() and + * process_task(). + * Iterate through all the tasks in a cgroup, calling test_task() for each, + * and if it returns true, call process_task() for it also. + * The test_task pointer may be NULL, meaning always true (select all tasks). + * Effectively duplicates cgroup_iter_{start,next,end}() + * but does not lock css_set_lock for the call to process_task(). + * The struct cgroup_scanner may be embedded in any structure of the caller's + * creation. + * It is guaranteed that process_task() will act on every task that + * is a member of the cgroup for the duration of this call. This + * function may or may not call process_task() for tasks that exit + * or move to a different cgroup during the call, or are forked or + * move into the cgroup during the call. + * + * Note that test_task() may be called with locks held, and may in some + * situations be called multiple times for the same task, so it should + * be cheap. + * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been + * pre-allocated and will be used for heap operations (and its "gt" member will + * be overwritten), else a temporary heap will be used (allocation of which + * may cause this function to fail). + */ +int cgroup_scan_tasks(struct cgroup_scanner *scan) +{ + int retval, i; + struct cgroup_iter it; + struct task_struct *p, *dropped; + /* Never dereference latest_task, since it's not refcounted */ + struct task_struct *latest_task = NULL; + struct ptr_heap tmp_heap; + struct ptr_heap *heap; + struct timespec latest_time = { 0, 0 }; + + if (scan->heap) { + /* The caller supplied our heap and pre-allocated its memory */ + heap = scan->heap; + heap->gt = &started_after; + } else { + /* We need to allocate our own heap memory */ + heap = &tmp_heap; + retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after); + if (retval) + /* cannot allocate the heap */ + return retval; + } + + again: + /* + * Scan tasks in the cgroup, using the scanner's "test_task" callback + * to determine which are of interest, and using the scanner's + * "process_task" callback to process any of them that need an update. + * Since we don't want to hold any locks during the task updates, + * gather tasks to be processed in a heap structure. + * The heap is sorted by descending task start time. + * If the statically-sized heap fills up, we overflow tasks that + * started later, and in future iterations only consider tasks that + * started after the latest task in the previous pass. This + * guarantees forward progress and that we don't miss any tasks. + */ + heap->size = 0; + cgroup_iter_start(scan->cg, &it); + while ((p = cgroup_iter_next(scan->cg, &it))) { + /* + * Only affect tasks that qualify per the caller's callback, + * if he provided one + */ + if (scan->test_task && !scan->test_task(p, scan)) + continue; + /* + * Only process tasks that started after the last task + * we processed + */ + if (!started_after_time(p, &latest_time, latest_task)) + continue; + dropped = heap_insert(heap, p); + if (dropped == NULL) { + /* + * The new task was inserted; the heap wasn't + * previously full + */ + get_task_struct(p); + } else if (dropped != p) { + /* + * The new task was inserted, and pushed out a + * different task + */ + get_task_struct(p); + put_task_struct(dropped); + } + /* + * Else the new task was newer than anything already in + * the heap and wasn't inserted + */ + } + cgroup_iter_end(scan->cg, &it); + + if (heap->size) { + for (i = 0; i < heap->size; i++) { + struct task_struct *p = heap->ptrs[i]; + if (i == 0) { + latest_time = p->start_time; + latest_task = p; + } + /* Process the task per the caller's callback */ + scan->process_task(p, scan); + put_task_struct(p); + } + /* + * If we had to process any tasks at all, scan again + * in case some of them were in the middle of forking + * children that didn't get processed. + * Not the most efficient way to do it, but it avoids + * having to take callback_mutex in the fork path + */ + goto again; + } + if (heap == &tmp_heap) + heap_free(&tmp_heap); + return 0; +} + /* * Stuff for reading the 'tasks' file. * @@ -1761,7 +1955,7 @@ static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp) while ((tsk = cgroup_iter_next(cgrp, &it))) { if (unlikely(n == npids)) break; - pidarray[n++] = task_pid_nr(tsk); + pidarray[n++] = task_pid_vnr(tsk); } cgroup_iter_end(cgrp, &it); return n; @@ -2126,9 +2320,8 @@ static inline int cgroup_has_css_refs(struct cgroup *cgrp) * matter, since it can only happen if the cgroup * has been deleted and hence no longer needs the * release agent to be called anyway. */ - if (css && atomic_read(&css->refcnt)) { + if (css && atomic_read(&css->refcnt)) return 1; - } } return 0; } @@ -2138,7 +2331,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup *cgrp = dentry->d_fsdata; struct dentry *d; struct cgroup *parent; - struct cgroup_subsys *ss; struct super_block *sb; struct cgroupfs_root *root; @@ -2157,17 +2349,19 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) parent = cgrp->parent; root = cgrp->root; sb = root->sb; + /* + * Call pre_destroy handlers of subsys + */ + cgroup_call_pre_destroy(cgrp); + /* + * Notify subsyses that rmdir() request comes. + */ if (cgroup_has_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } - for_each_subsys(root, ss) { - if (cgrp->subsys[ss->subsys_id]) - ss->destroy(ss, cgrp); - } - spin_lock(&release_list_lock); set_bit(CGRP_REMOVED, &cgrp->flags); if (!list_empty(&cgrp->release_list)) @@ -2182,15 +2376,11 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) cgroup_d_remove_dir(d); dput(d); - root->number_of_cgroups--; set_bit(CGRP_RELEASABLE, &parent->flags); check_for_release(parent); mutex_unlock(&cgroup_mutex); - /* Drop the active superblock reference that we took when we - * created the cgroup */ - deactivate_super(sb); return 0; } @@ -2324,7 +2514,7 @@ out: * - Used for /proc/<pid>/cgroup. * - No need to task_lock(tsk) on this tsk->cgroup reference, as it * doesn't really matter if tsk->cgroup changes after we read it, - * and we take cgroup_mutex, keeping attach_task() from changing it + * and we take cgroup_mutex, keeping cgroup_attach_task() from changing it * anyway. No need to check that tsk->cgroup != NULL, thanks to * the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks * cgroup to top_cgroup. @@ -2435,7 +2625,7 @@ static struct file_operations proc_cgroupstats_operations = { * A pointer to the shared css_set was automatically copied in * fork.c by dup_task_struct(). However, we ignore that copy, since * it was not made under the protection of RCU or cgroup_mutex, so - * might no longer be a valid cgroup pointer. attach_task() might + * might no longer be a valid cgroup pointer. cgroup_attach_task() might * have already changed current->cgroups, allowing the previously * referenced cgroup group to be removed and freed. * @@ -2514,8 +2704,8 @@ void cgroup_post_fork(struct task_struct *child) * attach us to a different cgroup, decrementing the count on * the first cgroup that we never incremented. But in this case, * top_cgroup isn't going away, and either task has PF_EXITING set, - * which wards off any attach_task() attempts, or task is a failed - * fork, never visible to attach_task. + * which wards off any cgroup_attach_task() attempts, or task is a failed + * fork, never visible to cgroup_attach_task. * */ void cgroup_exit(struct task_struct *tsk, int run_callbacks) @@ -2655,7 +2845,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys) } /* All seems fine. Finish by moving the task into the new cgroup */ - ret = attach_task(child, tsk); + ret = cgroup_attach_task(child, tsk); mutex_unlock(&cgroup_mutex); out_release: diff --git a/kernel/cpuset.c b/kernel/cpuset.c index cfaf6419d81..67b2bfe2781 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -38,7 +38,6 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/pagemap.h> -#include <linux/prio_heap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> @@ -56,6 +55,8 @@ #include <asm/atomic.h> #include <linux/mutex.h> #include <linux/kfifo.h> +#include <linux/workqueue.h> +#include <linux/cgroup.h> /* * Tracks how many cpusets are currently defined in system. @@ -64,7 +65,7 @@ */ int number_of_cpusets __read_mostly; -/* Retrieve the cpuset from a cgroup */ +/* Forward declare cgroup structures */ struct cgroup_subsys cpuset_subsys; struct cpuset; @@ -96,6 +97,9 @@ struct cpuset { /* partition number for rebuild_sched_domains() */ int pn; + + /* used for walking a cpuset heirarchy */ + struct list_head stack_list; }; /* Retrieve the cpuset for a cgroup */ @@ -111,7 +115,10 @@ static inline struct cpuset *task_cs(struct task_struct *task) return container_of(task_subsys_state(task, cpuset_subsys_id), struct cpuset, css); } - +struct cpuset_hotplug_scanner { + struct cgroup_scanner scan; + struct cgroup *to; +}; /* bits in struct cpuset flags field */ typedef enum { @@ -160,17 +167,17 @@ static inline int is_spread_slab(const struct cpuset *cs) * number, and avoid having to lock and reload mems_allowed unless * the cpuset they're using changes generation. * - * A single, global generation is needed because attach_task() could + * A single, global generation is needed because cpuset_attach_task() could * reattach a task to a different cpuset, which must not have its * generation numbers aliased with those of that tasks previous cpuset. * * Generations are needed for mems_allowed because one task cannot - * modify anothers memory placement. So we must enable every task, + * modify another's memory placement. So we must enable every task, * on every visit to __alloc_pages(), to efficiently check whether * its current->cpuset->mems_allowed has changed, requiring an update * of its current->mems_allowed. * - * Since cpuset_mems_generation is guarded by manage_mutex, + * Since writes to cpuset_mems_generation are guarded by the cgroup lock * there is no need to mark it atomic. */ static int cpuset_mems_generation; @@ -182,17 +189,20 @@ static struct cpuset top_cpuset = { }; /* - * We have two global cpuset mutexes below. They can nest. - * It is ok to first take manage_mutex, then nest callback_mutex. We also - * require taking task_lock() when dereferencing a tasks cpuset pointer. - * See "The task_lock() exception", at the end of this comment. + * There are two global mutexes guarding cpuset structures. The first + * is the main control groups cgroup_mutex, accessed via + * cgroup_lock()/cgroup_unlock(). The second is the cpuset-specific + * callback_mutex, below. They can nest. It is ok to first take + * cgroup_mutex, then nest callback_mutex. We also require taking + * task_lock() when dereferencing a task's cpuset pointer. See "The + * task_lock() exception", at the end of this comment. * * A task must hold both mutexes to modify cpusets. If a task - * holds manage_mutex, then it blocks others wanting that mutex, + * holds cgroup_mutex, then it blocks others wanting that mutex, * ensuring that it is the only task able to also acquire callback_mutex * and be able to modify cpusets. It can perform various checks on * the cpuset structure first, knowing nothing will change. It can - * also allocate memory while just holding manage_mutex. While it is + * also allocate memory while just holding cgroup_mutex. While it is * performing these checks, various callback routines can briefly * acquire callback_mutex to query cpusets. Once it is ready to make * the changes, it takes callback_mutex, blocking everyone else. @@ -208,60 +218,16 @@ static struct cpuset top_cpuset = { * The task_struct fields mems_allowed and mems_generation may only * be accessed in the context of that task, so require no locks. * - * Any task can increment and decrement the count field without lock. - * So in general, code holding manage_mutex or callback_mutex can't rely - * on the count field not changing. However, if the count goes to - * zero, then only attach_task(), which holds both mutexes, can - * increment it again. Because a count of zero means that no tasks - * are currently attached, therefore there is no way a task attached - * to that cpuset can fork (the other way to increment the count). - * So code holding manage_mutex or callback_mutex can safely assume that - * if the count is zero, it will stay zero. Similarly, if a task - * holds manage_mutex or callback_mutex on a cpuset with zero count, it - * knows that the cpuset won't be removed, as cpuset_rmdir() needs - * both of those mutexes. - * * The cpuset_common_file_write handler for operations that modify - * the cpuset hierarchy holds manage_mutex across the entire operation, + * the cpuset hierarchy holds cgroup_mutex across the entire operation, * single threading all such cpuset modifications across the system. * * The cpuset_common_file_read() handlers only hold callback_mutex across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * - * The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't - * (usually) take either mutex. These are the two most performance - * critical pieces of code here. The exception occurs on cpuset_exit(), - * when a task in a notify_on_release cpuset exits. Then manage_mutex - * is taken, and if the cpuset count is zero, a usermode call made - * to /sbin/cpuset_release_agent with the name of the cpuset (path - * relative to the root of cpuset file system) as the argument. - * - * A cpuset can only be deleted if both its 'count' of using tasks - * is zero, and its list of 'children' cpusets is empty. Since all - * tasks in the system use _some_ cpuset, and since there is always at - * least one task in the system (init), therefore, top_cpuset - * always has either children cpusets and/or using tasks. So we don't - * need a special hack to ensure that top_cpuset cannot be deleted. - * - * The above "Tale of Two Semaphores" would be complete, but for: - * - * The task_lock() exception - * - * The need for this exception arises from the action of attach_task(), - * which overwrites one tasks cpuset pointer with another. It does - * so using both mutexes, however there are several performance - * critical places that need to reference task->cpuset without the - * expense of grabbing a system global mutex. Therefore except as - * noted below, when dereferencing or, as in attach_task(), modifying - * 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(). + * Accessing a task's cpuset should be done in accordance with the + * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(callback_mutex); @@ -354,15 +320,14 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) * Do not call this routine if in_interrupt(). * * Call without callback_mutex or task_lock() held. May be - * called with or without manage_mutex held. Thanks in part to - * 'the_top_cpuset_hack', the tasks cpuset pointer will never + * called with or without cgroup_mutex held. Thanks in part to + * 'the_top_cpuset_hack', the task's cpuset pointer will never * be NULL. This routine also might acquire callback_mutex 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. + * from concurrent freeing of current->cpuset using RCU. * * The rcu_dereference() is technically probably not needed, * as I don't actually mind if I see a new cpuset pointer but @@ -424,7 +389,7 @@ void cpuset_update_task_memory_state(void) * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding manage_mutex. + * are only set if the other's are set. Call holding cgroup_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -442,7 +407,7 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * manage_mutex held. + * cgroup_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -476,7 +441,10 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) if (!is_cpuset_subset(trial, par)) return -EACCES; - /* If either I or some sibling (!= me) is exclusive, we can't overlap */ + /* + * If either I or some sibling (!= me) is exclusive, we can't + * overlap + */ list_for_each_entry(cont, &par->css.cgroup->children, sibling) { c = cgroup_cs(cont); if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && @@ -732,22 +700,50 @@ static inline int started_after(void *p1, void *p2) return started_after_time(t1, &t2->start_time, t2); } -/* - * Call with manage_mutex held. May take callback_mutex during call. +/** + * cpuset_test_cpumask - test a task's cpus_allowed versus its cpuset's + * @tsk: task to test + * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner + * + * Call with cgroup_mutex held. May take callback_mutex during call. + * Called for each task in a cgroup by cgroup_scan_tasks(). + * Return nonzero if this tasks's cpus_allowed mask should be changed (in other + * words, if its mask is not equal to its cpuset's mask). + */ +int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) +{ + return !cpus_equal(tsk->cpus_allowed, + (cgroup_cs(scan->cg))->cpus_allowed); +} + +/** + * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's + * @tsk: task to test + * @scan: struct cgroup_scanner containing the cgroup of the task + * + * Called by cgroup_scan_tasks() for each task in a cgroup whose + * cpus_allowed mask needs to be changed. + * + * We don't need to re-check for the cgroup/cpuset membership, since we're + * holding cgroup_lock() at this point. */ +void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) +{ + set_cpus_allowed(tsk, (cgroup_cs(scan->cg))->cpus_allowed); +} +/** + * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it + * @cs: the cpuset to consider + * @buf: buffer of cpu numbers written to this cpuset + */ static int update_cpumask(struct cpuset *cs, char *buf) { struct cpuset trialcs; - int retval, i; - int is_load_balanced; - struct cgroup_iter it; - struct cgroup *cgrp = cs->css.cgroup; - struct task_struct *p, *dropped; - /* Never dereference latest_task, since it's not refcounted */ - struct task_struct *latest_task = NULL; + struct cgroup_scanner scan; struct ptr_heap heap; - struct timespec latest_time = { 0, 0 }; + int retval; + int is_load_balanced; /* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */ if (cs == &top_cpuset) @@ -756,7 +752,7 @@ static int update_cpumask(struct cpuset *cs, char *buf) trialcs = *cs; /* - * An empty cpus_allowed is ok iff there are no tasks in the cpuset. + * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. @@ -777,6 +773,7 @@ static int update_cpumask(struct cpuset *cs, char *buf) /* Nothing to do if the cpus didn't change */ if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed)) return 0; + retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after); if (retval) return retval; @@ -787,62 +784,19 @@ static int update_cpumask(struct cpuset *cs, char *buf) cs->cpus_allowed = trialcs.cpus_allowed; mutex_unlock(&callback_mutex); - again: /* * Scan tasks in the cpuset, and update the cpumasks of any - * that need an update. Since we can't call set_cpus_allowed() - * while holding tasklist_lock, gather tasks to be processed - * in a heap structure. If the statically-sized heap fills up, - * overflow tasks that started later, and in future iterations - * only consider tasks that started after the latest task in - * the previous pass. This guarantees forward progress and - * that we don't miss any tasks + * that need an update. */ - heap.size = 0; - cgroup_iter_start(cgrp, &it); - while ((p = cgroup_iter_next(cgrp, &it))) { - /* Only affect tasks that don't have the right cpus_allowed */ - if (cpus_equal(p->cpus_allowed, cs->cpus_allowed)) - continue; - /* - * Only process tasks that started after the last task - * we processed - */ - if (!started_after_time(p, &latest_time, latest_task)) - continue; - dropped = heap_insert(&heap, p); - if (dropped == NULL) { - get_task_struct(p); - } else if (dropped != p) { - get_task_struct(p); - put_task_struct(dropped); - } - } - cgroup_iter_end(cgrp, &it); - if (heap.size) { - for (i = 0; i < heap.size; i++) { - struct task_struct *p = heap.ptrs[i]; - if (i == 0) { - latest_time = p->start_time; - latest_task = p; - } - set_cpus_allowed(p, cs->cpus_allowed); - put_task_struct(p); - } - /* - * If we had to process any tasks at all, scan again - * in case some of them were in the middle of forking - * children that didn't notice the new cpumask - * restriction. Not the most efficient way to do it, - * but it avoids having to take callback_mutex in the - * fork path - */ - goto again; - } + scan.cg = cs->css.cgroup; + scan.test_task = cpuset_test_cpumask; + scan.process_task = cpuset_change_cpumask; + scan.heap = &heap; + cgroup_scan_tasks(&scan); heap_free(&heap); + if (is_load_balanced) rebuild_sched_domains(); - return 0; } @@ -854,11 +808,11 @@ static int update_cpumask(struct cpuset *cs, char *buf) * Temporarilly set tasks mems_allowed to target nodes of migration, * so that the migration code can allocate pages on these nodes. * - * Call holding manage_mutex, so our current->cpuset won't change - * during this call, as manage_mutex holds off any attach_task() + * Call holding cgroup_mutex, so current's cpuset won't change + * during this call, as manage_mutex holds off any cpuset_attach() * calls. Therefore we don't need to take task_lock around the * call to guarantee_online_mems(), as we know no one is changing - * our tasks cpuset. + * our task's cpuset. * * Hold callback_mutex around the two modifications of our tasks * mems_allowed to synchronize with cpuset_mems_allowed(). @@ -903,7 +857,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, * the cpuset is marked 'memory_migrate', migrate the tasks * pages to the new memory. * - * Call with manage_mutex held. May take callback_mutex during call. + * Call with cgroup_mutex held. May take callback_mutex 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. @@ -1016,7 +970,7 @@ static int update_nodemask(struct cpuset *cs, char *buf) * 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_mutex, we know that no other rebind effort will + * cgroup_mutex, 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. @@ -1031,7 +985,7 @@ static int update_nodemask(struct cpuset *cs, char *buf) mmput(mm); } - /* We're done rebinding vma's to this cpusets new mems_allowed. */ + /* We're done rebinding vmas to this cpuset's new mems_allowed. */ kfree(mmarray); cpuset_being_rebound = NULL; retval = 0; @@ -1045,7 +999,7 @@ int current_cpuset_is_being_rebound(void) } /* - * Call with manage_mutex held. + * Call with cgroup_mutex held. */ static int update_memory_pressure_enabled(struct cpuset *cs, char *buf) @@ -1066,7 +1020,7 @@ static int update_memory_pressure_enabled(struct cpuset *cs, char *buf) * cs: the cpuset to update * buf: the buffer where we read the 0 or 1 * - * Call with manage_mutex held. + * Call with cgroup_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) @@ -1200,6 +1154,7 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } +/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct task_struct *tsk) { @@ -1547,7 +1502,8 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) * If this becomes a problem for some users who wish to * allow that scenario, then cpuset_post_clone() could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive - * (and likewise for mems) to the new cgroup. + * (and likewise for mems) to the new cgroup. Called with cgroup_mutex + * held. */ static void cpuset_post_clone(struct cgroup_subsys *ss, struct cgroup *cgroup) @@ -1571,11 +1527,8 @@ static void cpuset_post_clone(struct cgroup_subsys *ss, /* * cpuset_create - create a cpuset - * parent: cpuset that will be parent of the new cpuset. - * name: name of the new cpuset. Will be strcpy'ed. - * mode: mode to set on new inode - * - * Must be called with the mutex on the parent inode held + * ss: cpuset cgroup subsystem + * cont: control group that the new cpuset will be part of */ static struct cgroup_subsys_state *cpuset_create( @@ -1687,53 +1640,140 @@ int __init cpuset_init(void) return 0; } +/** + * cpuset_do_move_task - move a given task to another cpuset + * @tsk: pointer to task_struct the task to move + * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner + * + * Called by cgroup_scan_tasks() for each task in a cgroup. + * Return nonzero to stop the walk through the tasks. + */ +void cpuset_do_move_task(struct task_struct *tsk, struct cgroup_scanner *scan) +{ + struct cpuset_hotplug_scanner *chsp; + + chsp = container_of(scan, struct cpuset_hotplug_scanner, scan); + cgroup_attach_task(chsp->to, tsk); +} + +/** + * move_member_tasks_to_cpuset - move tasks from one cpuset to another + * @from: cpuset in which the tasks currently reside + * @to: cpuset to which the tasks will be moved + * + * Called with cgroup_mutex held + * callback_mutex must not be held, as cpuset_attach() will take it. + * + * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * calling callback functions for each. + */ +static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to) +{ + struct cpuset_hotplug_scanner scan; + + scan.scan.cg = from->css.cgroup; + scan.scan.test_task = NULL; /* select all tasks in cgroup */ + scan.scan.process_task = cpuset_do_move_task; + scan.scan.heap = NULL; + scan.to = to->css.cgroup; + + if (cgroup_scan_tasks((struct cgroup_scanner *)&scan)) + printk(KERN_ERR "move_member_tasks_to_cpuset: " + "cgroup_scan_tasks failed\n"); +} + /* * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the - * last CPU or node from a cpuset, then the guarantee_online_cpus() - * or guarantee_online_mems() code will use that emptied cpusets - * parent online CPUs or nodes. Cpusets that were already empty of - * CPUs or nodes are left empty. + * last CPU or node from a cpuset, then move the tasks in the empty + * cpuset to its next-highest non-empty parent. * - * This routine is intentionally inefficient in a couple of regards. - * It will check all cpusets in a subtree even if the top cpuset of - * the subtree has no offline CPUs or nodes. It checks both CPUs and - * nodes, even though the caller could have been coded to know that - * only one of CPUs or nodes needed to be checked on a given call. - * This was done to minimize text size rather than cpu cycles. + * Called with cgroup_mutex held + * callback_mutex must not be held, as cpuset_attach() will take it. + */ +static void remove_tasks_in_empty_cpuset(struct cpuset *cs) +{ + struct cpuset *parent; + + /* + * The cgroup's css_sets list is in use if there are tasks + * in the cpuset; the list is empty if there are none; + * the cs->css.refcnt seems always 0. + */ + if (list_empty(&cs->css.cgroup->css_sets)) + return; + + /* + * Find its next-highest non-empty parent, (top cpuset + * has online cpus, so can't be empty). + */ + parent = cs->parent; + while (cpus_empty(parent->cpus_allowed) || + nodes_empty(parent->mems_allowed)) + parent = parent->parent; + + move_member_tasks_to_cpuset(cs, parent); +} + +/* + * Walk the specified cpuset subtree and look for empty cpusets. + * The tasks of such cpuset must be moved to a parent cpuset. + * + * Called with cgroup_mutex held. We take callback_mutex to modify + * cpus_allowed and mems_allowed. * - * Call with both manage_mutex and callback_mutex held. + * This walk processes the tree from top to bottom, completing one layer + * before dropping down to the next. It always processes a node before + * any of its children. * - * Recursive, on depth of cpuset subtree. + * For now, since we lack memory hot unplug, we'll never see a cpuset + * that has tasks along with an empty 'mems'. But if we did see such + * a cpuset, we'd handle it just like we do if its 'cpus' was empty. */ - -static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur) +static void scan_for_empty_cpusets(const struct cpuset *root) { + struct cpuset *cp; /* scans cpusets being updated */ + struct cpuset *child; /* scans child cpusets of cp */ + struct list_head queue; struct cgroup *cont; - struct cpuset *c; - /* Each of our child cpusets mems must be online */ - list_for_each_entry(cont, &cur->css.cgroup->children, sibling) { - c = cgroup_cs(cont); - guarantee_online_cpus_mems_in_subtree(c); - if (!cpus_empty(c->cpus_allowed)) - guarantee_online_cpus(c, &c->cpus_allowed); - if (!nodes_empty(c->mems_allowed)) - guarantee_online_mems(c, &c->mems_allowed); + INIT_LIST_HEAD(&queue); + + list_add_tail((struct list_head *)&root->stack_list, &queue); + + while (!list_empty(&queue)) { + cp = container_of(queue.next, struct cpuset, stack_list); + list_del(queue.next); + list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { + child = cgroup_cs(cont); + list_add_tail(&child->stack_list, &queue); + } + cont = cp->css.cgroup; + + /* Continue past cpusets with all cpus, mems online */ + if (cpus_subset(cp->cpus_allowed, cpu_online_map) && + nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) + continue; + + /* Remove offline cpus and mems from this cpuset. */ + mutex_lock(&callback_mutex); + cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map); + nodes_and(cp->mems_allowed, cp->mems_allowed, + node_states[N_HIGH_MEMORY]); + mutex_unlock(&callback_mutex); + + /* Move tasks from the empty cpuset to a parent */ + if (cpus_empty(cp->cpus_allowed) || + nodes_empty(cp->mems_allowed)) + remove_tasks_in_empty_cpuset(cp); } } /* * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track * cpu_online_map and node_states[N_HIGH_MEMORY]. Force the top cpuset to - * track what's online after any CPU or memory node hotplug or unplug - * event. - * - * To ensure that we don't remove a CPU or node from the top cpuset - * that is currently in use by a child cpuset (which would violate - * the rule that cpusets must be subsets of their parent), we first - * call the recursive routine guarantee_online_cpus_mems_in_subtree(). + * track what's online after any CPU or memory node hotplug or unplug event. * * Since there are two callers of this routine, one for CPU hotplug * events and one for memory node hotplug events, we could have coded @@ -1744,13 +1784,11 @@ static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur) static void common_cpu_mem_hotplug_unplug(void) { cgroup_lock(); - mutex_lock(&callback_mutex); - guarantee_online_cpus_mems_in_subtree(&top_cpuset); top_cpuset.cpus_allowed = cpu_online_map; top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; + scan_for_empty_cpusets(&top_cpuset); - mutex_unlock(&callback_mutex); cgroup_unlock(); } @@ -1826,7 +1864,7 @@ cpumask_t cpuset_cpus_allowed(struct task_struct *tsk) /** * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset. - * Must be called with callback_mutex held. + * Must be called with callback_mutex held. **/ cpumask_t cpuset_cpus_allowed_locked(struct task_struct *tsk) { @@ -2163,10 +2201,8 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take manage_mutex, keeping attach_task() from changing it - * anyway. No need to check that tsk->cpuset != NULL, thanks to - * the_top_cpuset_hack in cpuset_exit(), which sets an exiting tasks - * cpuset to top_cpuset. + * and we take cgroup_mutex, keeping cpuset_attach() from changing it + * anyway. */ static int proc_cpuset_show(struct seq_file *m, void *unused_v) { diff --git a/kernel/exit.c b/kernel/exit.c index bfb1c0e940e..eb9934a82fc 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -50,8 +50,6 @@ #include <asm/pgtable.h> #include <asm/mmu_context.h> -extern void sem_exit (void); - static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p) @@ -1085,11 +1083,12 @@ do_group_exit(int exit_code) struct signal_struct *const sig = current->signal; struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); - if (sig->flags & SIGNAL_GROUP_EXIT) + if (signal_group_exit(sig)) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { sig->group_exit_code = exit_code; + sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); @@ -1591,8 +1590,6 @@ repeat: goto repeat; if (retval != 0) /* He released the lock. */ goto end; - } else if (p->exit_state == EXIT_DEAD) { - continue; } else if (p->exit_state == EXIT_ZOMBIE) { /* * Eligible but we cannot release it yet: @@ -1607,7 +1604,7 @@ repeat: /* He released the lock. */ if (retval != 0) goto end; - } else { + } else if (p->exit_state != EXIT_DEAD) { check_continued: /* * It's running now, so it might later diff --git a/kernel/fork.c b/kernel/fork.c index 05e0b6f4365..b2ef8e4fad7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,6 +40,7 @@ #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> +#include <linux/memcontrol.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/acct.h> @@ -325,7 +326,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm) static inline void mm_free_pgd(struct mm_struct * mm) { - pgd_free(mm->pgd); + pgd_free(mm, mm->pgd); } #else #define dup_mmap(mm, oldmm) (0) @@ -340,7 +341,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); #include <linux/init_task.h> -static struct mm_struct * mm_init(struct mm_struct * mm) +static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -357,11 +358,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm) mm->ioctx_list = NULL; mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; + mm_init_cgroup(mm, p); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; return mm; } + + mm_free_cgroup(mm); free_mm(mm); return NULL; } @@ -376,7 +380,7 @@ struct mm_struct * mm_alloc(void) mm = allocate_mm(); if (mm) { memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm); + mm = mm_init(mm, current); } return mm; } @@ -390,6 +394,7 @@ void fastcall __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); mm_free_pgd(mm); + mm_free_cgroup(mm); destroy_context(mm); free_mm(mm); } @@ -511,7 +516,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk) mm->token_priority = 0; mm->last_interval = 0; - if (!mm_init(mm)) + if (!mm_init(mm, tsk)) goto fail_nomem; if (init_new_context(tsk, mm)) @@ -1118,6 +1123,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_SECURITY p->security = NULL; #endif + p->cap_bset = current->cap_bset; p->io_context = NULL; p->audit_context = NULL; cgroup_fork(p); @@ -1398,7 +1404,7 @@ fork_out: return ERR_PTR(retval); } -noinline struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) +noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); return regs; @@ -1450,6 +1456,23 @@ long do_fork(unsigned long clone_flags, int trace = 0; long nr; + /* + * We hope to recycle these flags after 2.6.26 + */ + if (unlikely(clone_flags & CLONE_STOPPED)) { + static int __read_mostly count = 100; + + if (count > 0 && printk_ratelimit()) { + char comm[TASK_COMM_LEN]; + + count--; + printk(KERN_INFO "fork(): process `%s' used deprecated " + "clone flags 0x%lx\n", + get_task_comm(comm, current), + clone_flags & CLONE_STOPPED); + } + } + if (unlikely(current->ptrace)) { trace = fork_traceflag (clone_flags); if (trace) @@ -1492,7 +1515,7 @@ long do_fork(unsigned long clone_flags, if (!(clone_flags & CLONE_STOPPED)) wake_up_new_task(p, clone_flags); else - p->state = TASK_STOPPED; + __set_task_state(p, TASK_STOPPED); if (unlikely (trace)) { current->ptrace_message = nr; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 1069998fe25..668f3967eb3 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -306,7 +306,7 @@ EXPORT_SYMBOL_GPL(ktime_sub_ns); /* * Divide a ktime value by a nanosecond value */ -unsigned long ktime_divns(const ktime_t kt, s64 div) +u64 ktime_divns(const ktime_t kt, s64 div) { u64 dclc, inc, dns; int sft = 0; @@ -321,7 +321,7 @@ unsigned long ktime_divns(const ktime_t kt, s64 div) dclc >>= sft; do_div(dclc, (unsigned long) div); - return (unsigned long) dclc; + return dclc; } #endif /* BITS_PER_LONG >= 64 */ @@ -656,10 +656,9 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * 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 now, ktime_t interval) +u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { - unsigned long orun = 1; + u64 orun = 1; ktime_t delta; delta = ktime_sub(now, timer->expires); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 7dadc71ce51..f091d13def0 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -53,14 +53,6 @@ static inline int is_kernel_inittext(unsigned long addr) return 0; } -static inline int is_kernel_extratext(unsigned long addr) -{ - if (addr >= (unsigned long)_sextratext - && addr <= (unsigned long)_eextratext) - return 1; - return 0; -} - static inline int is_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) @@ -80,8 +72,7 @@ static int is_ksym_addr(unsigned long addr) if (all_var) return is_kernel(addr); - return is_kernel_text(addr) || is_kernel_inittext(addr) || - is_kernel_extratext(addr); + return is_kernel_text(addr) || is_kernel_inittext(addr); } /* expand a compressed symbol data into the resulting uncompressed string, diff --git a/kernel/kexec.c b/kernel/kexec.c index 9a26eec9eb0..06a0e277565 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1361,8 +1361,8 @@ unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void) static int __init crash_save_vmcoreinfo_init(void) { - vmcoreinfo_append_str("OSRELEASE=%s\n", init_uts_ns.name.release); - vmcoreinfo_append_str("PAGESIZE=%ld\n", PAGE_SIZE); + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_PAGESIZE(PAGE_SIZE); VMCOREINFO_SYMBOL(init_uts_ns); VMCOREINFO_SYMBOL(node_online_map); @@ -1376,15 +1376,15 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_SPARSEMEM VMCOREINFO_SYMBOL(mem_section); VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); - VMCOREINFO_SIZE(mem_section); + VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); #endif - VMCOREINFO_SIZE(page); - VMCOREINFO_SIZE(pglist_data); - VMCOREINFO_SIZE(zone); - VMCOREINFO_SIZE(free_area); - VMCOREINFO_SIZE(list_head); - VMCOREINFO_TYPEDEF_SIZE(nodemask_t); + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); VMCOREINFO_OFFSET(page, flags); VMCOREINFO_OFFSET(page, _count); VMCOREINFO_OFFSET(page, mapping); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d0493eafea3..7a86e643233 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -699,6 +699,12 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, struct kretprobe_instance, uflist); ri->rp = rp; ri->task = current; + + if (rp->entry_handler && rp->entry_handler(ri, regs)) { + spin_unlock_irqrestore(&kretprobe_lock, flags); + return 0; + } + arch_prepare_kretprobe(ri, regs); /* XXX(hch): why is there no hlist_move_head? */ @@ -745,7 +751,8 @@ int __kprobes register_kretprobe(struct kretprobe *rp) INIT_HLIST_HEAD(&rp->used_instances); INIT_HLIST_HEAD(&rp->free_instances); for (i = 0; i < rp->maxactive; i++) { - inst = kmalloc(sizeof(struct kretprobe_instance), GFP_KERNEL); + inst = kmalloc(sizeof(struct kretprobe_instance) + + rp->data_size, GFP_KERNEL); if (inst == NULL) { free_rp_inst(rp); return -ENOMEM; diff --git a/kernel/latency.c b/kernel/latency.c deleted file mode 100644 index e63fcacb61a..00000000000 --- a/kernel/latency.c +++ /dev/null @@ -1,280 +0,0 @@ -/* - * latency.c: Explicit system-wide latency-expectation infrastructure - * - * The purpose of this infrastructure is to allow device drivers to set - * latency constraint they have and to collect and summarize these - * expectations globally. The cummulated result can then be used by - * power management and similar users to make decisions that have - * tradoffs with a latency component. - * - * An example user of this are the x86 C-states; each higher C state saves - * more power, but has a higher exit latency. For the idle loop power - * code to make a good decision which C-state to use, information about - * acceptable latencies is required. - * - * An example announcer of latency is an audio driver that knowns it - * will get an interrupt when the hardware has 200 usec of samples - * left in the DMA buffer; in that case the driver can set a latency - * constraint of, say, 150 usec. - * - * Multiple drivers can each announce their maximum accepted latency, - * to keep these appart, a string based identifier is used. - * - * - * (C) Copyright 2006 Intel Corporation - * Author: Arjan van de Ven <arjan@linux.intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <linux/latency.h> -#include <linux/list.h> -#include <linux/spinlock.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/notifier.h> -#include <linux/jiffies.h> -#include <asm/atomic.h> - -struct latency_info { - struct list_head list; - int usecs; - char *identifier; -}; - -/* - * locking rule: all modifications to current_max_latency and - * latency_list need to be done while holding the latency_lock. - * latency_lock needs to be taken _irqsave. - */ -static atomic_t current_max_latency; -static DEFINE_SPINLOCK(latency_lock); - -static LIST_HEAD(latency_list); -static BLOCKING_NOTIFIER_HEAD(latency_notifier); - -/* - * This function returns the maximum latency allowed, which - * happens to be the minimum of all maximum latencies on the - * list. - */ -static int __find_max_latency(void) -{ - int min = INFINITE_LATENCY; - struct latency_info *info; - - list_for_each_entry(info, &latency_list, list) { - if (info->usecs < min) - min = info->usecs; - } - return min; -} - -/** - * set_acceptable_latency - sets the maximum latency acceptable - * @identifier: string that identifies this driver - * @usecs: maximum acceptable latency for this driver - * - * This function informs the kernel that this device(driver) - * can accept at most usecs latency. This setting is used for - * power management and similar tradeoffs. - * - * This function sleeps and can only be called from process - * context. - * Calling this function with an existing identifier is valid - * and will cause the existing latency setting to be changed. - */ -void set_acceptable_latency(char *identifier, int usecs) -{ - struct latency_info *info, *iter; - unsigned long flags; - int found_old = 0; - - info = kzalloc(sizeof(struct latency_info), GFP_KERNEL); - if (!info) - return; - info->usecs = usecs; - info->identifier = kstrdup(identifier, GFP_KERNEL); - if (!info->identifier) - goto free_info; - - spin_lock_irqsave(&latency_lock, flags); - list_for_each_entry(iter, &latency_list, list) { - if (strcmp(iter->identifier, identifier)==0) { - found_old = 1; - iter->usecs = usecs; - break; - } - } - if (!found_old) - list_add(&info->list, &latency_list); - - if (usecs < atomic_read(¤t_max_latency)) - atomic_set(¤t_max_latency, usecs); - - spin_unlock_irqrestore(&latency_lock, flags); - - blocking_notifier_call_chain(&latency_notifier, - atomic_read(¤t_max_latency), NULL); - - /* - * if we inserted the new one, we're done; otherwise there was - * an existing one so we need to free the redundant data - */ - if (!found_old) - return; - - kfree(info->identifier); -free_info: - kfree(info); -} -EXPORT_SYMBOL_GPL(set_acceptable_latency); - -/** - * modify_acceptable_latency - changes the maximum latency acceptable - * @identifier: string that identifies this driver - * @usecs: maximum acceptable latency for this driver - * - * This function informs the kernel that this device(driver) - * can accept at most usecs latency. This setting is used for - * power management and similar tradeoffs. - * - * This function does not sleep and can be called in any context. - * Trying to use a non-existing identifier silently gets ignored. - * - * Due to the atomic nature of this function, the modified latency - * value will only be used for future decisions; past decisions - * can still lead to longer latencies in the near future. - */ -void modify_acceptable_latency(char *identifier, int usecs) -{ - struct latency_info *iter; - unsigned long flags; - - spin_lock_irqsave(&latency_lock, flags); - list_for_each_entry(iter, &latency_list, list) { - if (strcmp(iter->identifier, identifier) == 0) { - iter->usecs = usecs; - break; - } - } - if (usecs < atomic_read(¤t_max_latency)) - atomic_set(¤t_max_latency, usecs); - spin_unlock_irqrestore(&latency_lock, flags); -} -EXPORT_SYMBOL_GPL(modify_acceptable_latency); - -/** - * remove_acceptable_latency - removes the maximum latency acceptable - * @identifier: string that identifies this driver - * - * This function removes a previously set maximum latency setting - * for the driver and frees up any resources associated with the - * bookkeeping needed for this. - * - * This function does not sleep and can be called in any context. - * Trying to use a non-existing identifier silently gets ignored. - */ -void remove_acceptable_latency(char *identifier) -{ - unsigned long flags; - int newmax = 0; - struct latency_info *iter, *temp; - - spin_lock_irqsave(&latency_lock, flags); - - list_for_each_entry_safe(iter, temp, &latency_list, list) { - if (strcmp(iter->identifier, identifier) == 0) { - list_del(&iter->list); - newmax = iter->usecs; - kfree(iter->identifier); - kfree(iter); - break; - } - } - - /* If we just deleted the system wide value, we need to - * recalculate with a full search - */ - if (newmax == atomic_read(¤t_max_latency)) { - newmax = __find_max_latency(); - atomic_set(¤t_max_latency, newmax); - } - spin_unlock_irqrestore(&latency_lock, flags); -} -EXPORT_SYMBOL_GPL(remove_acceptable_latency); - -/** - * system_latency_constraint - queries the system wide latency maximum - * - * This function returns the system wide maximum latency in - * microseconds. - * - * This function does not sleep and can be called in any context. - */ -int system_latency_constraint(void) -{ - return atomic_read(¤t_max_latency); -} -EXPORT_SYMBOL_GPL(system_latency_constraint); - -/** - * synchronize_acceptable_latency - recalculates all latency decisions - * - * This function will cause a callback to various kernel pieces that - * will make those pieces rethink their latency decisions. This implies - * that if there are overlong latencies in hardware state already, those - * latencies get taken right now. When this call completes no overlong - * latency decisions should be active anymore. - * - * Typical usecase of this is after a modify_acceptable_latency() call, - * which in itself is non-blocking and non-synchronizing. - * - * This function blocks and should not be called with locks held. - */ - -void synchronize_acceptable_latency(void) -{ - blocking_notifier_call_chain(&latency_notifier, - atomic_read(¤t_max_latency), NULL); -} -EXPORT_SYMBOL_GPL(synchronize_acceptable_latency); - -/* - * Latency notifier: this notifier gets called when a non-atomic new - * latency value gets set. The expectation nof the caller of the - * non-atomic set is that when the call returns, future latencies - * are within bounds, so the functions on the notifier list are - * expected to take the overlong latencies immediately, inside the - * callback, and not make a overlong latency decision anymore. - * - * The callback gets called when the new latency value is made - * active so system_latency_constraint() returns the new latency. - */ -int register_latency_notifier(struct notifier_block * nb) -{ - return blocking_notifier_chain_register(&latency_notifier, nb); -} -EXPORT_SYMBOL_GPL(register_latency_notifier); - -int unregister_latency_notifier(struct notifier_block * nb) -{ - return blocking_notifier_chain_unregister(&latency_notifier, nb); -} -EXPORT_SYMBOL_GPL(unregister_latency_notifier); - -static __init int latency_init(void) -{ - atomic_set(¤t_max_latency, INFINITE_LATENCY); - /* - * we don't want by default to have longer latencies than 2 ticks, - * since that would cause lost ticks - */ - set_acceptable_latency("kernel", 2*1000000/HZ); - return 0; -} - -module_init(latency_init); diff --git a/kernel/notifier.c b/kernel/notifier.c index 4253f472f06..643360d1bb1 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -4,6 +4,7 @@ #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/vmalloc.h> +#include <linux/reboot.h> /* * Notifier list for kernel code which wants to be called diff --git a/kernel/panic.c b/kernel/panic.c index d9e90cfe329..24af9f8bac9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -161,7 +161,7 @@ const char *print_tainted(void) { static char buf[20]; if (tainted) { - snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c", + snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c", tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G', tainted & TAINT_FORCED_MODULE ? 'F' : ' ', tainted & TAINT_UNSAFE_SMP ? 'S' : ' ', @@ -169,7 +169,8 @@ const char *print_tainted(void) tainted & TAINT_MACHINE_CHECK ? 'M' : ' ', tainted & TAINT_BAD_PAGE ? 'B' : ' ', tainted & TAINT_USER ? 'U' : ' ', - tainted & TAINT_DIE ? 'D' : ' '); + tainted & TAINT_DIE ? 'D' : ' ', + tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' '); } else snprintf(buf, sizeof(buf), "Not tainted"); diff --git a/kernel/params.c b/kernel/params.c index 42fe5e6126c..e28c70628bb 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -272,7 +272,7 @@ static int param_array(const char *name, unsigned int min, unsigned int max, void *elem, int elemsize, int (*set)(const char *, struct kernel_param *kp), - int *num) + unsigned int *num) { int ret; struct kernel_param kp; diff --git a/kernel/pid.c b/kernel/pid.c index f815455431b..3b30bccdfcd 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -368,6 +368,7 @@ struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) } return result; } +EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock() or with tasklist_lock read-held. diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c new file mode 100644 index 00000000000..0afe32be4c8 --- /dev/null +++ b/kernel/pm_qos_params.c @@ -0,0 +1,425 @@ +/* + * This module exposes the interface to kernel space for specifying + * QoS dependencies. It provides infrastructure for registration of: + * + * Dependents on a QoS value : register requirements + * Watchers of QoS value : get notified when target QoS value changes + * + * This QoS design is best effort based. Dependents register their QoS needs. + * Watchers register to keep track of the current QoS needs of the system. + * + * There are 3 basic classes of QoS parameter: latency, timeout, throughput + * each have defined units: + * latency: usec + * timeout: usec <-- currently not used. + * throughput: kbs (kilo byte / sec) + * + * There are lists of pm_qos_objects each one wrapping requirements, notifiers + * + * User mode requirements on a QOS parameter register themselves to the + * subsystem by opening the device node /dev/... and writing there request to + * the node. As long as the process holds a file handle open to the node the + * client continues to be accounted for. Upon file release the usermode + * requirement is removed and a new qos target is computed. This way when the + * requirement that the application has is cleaned up when closes the file + * pointer or exits the pm_qos_object will get an opportunity to clean up. + * + * mark gross mgross@linux.intel.com + */ + +#include <linux/pm_qos_params.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/device.h> +#include <linux/miscdevice.h> +#include <linux/string.h> +#include <linux/platform_device.h> +#include <linux/init.h> + +#include <linux/uaccess.h> + +/* + * locking rule: all changes to target_value or requirements or notifiers lists + * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock + * held, taken with _irqsave. One lock to rule them all + */ +struct requirement_list { + struct list_head list; + union { + s32 value; + s32 usec; + s32 kbps; + }; + char *name; +}; + +static s32 max_compare(s32 v1, s32 v2); +static s32 min_compare(s32 v1, s32 v2); + +struct pm_qos_object { + struct requirement_list requirements; + struct blocking_notifier_head *notifiers; + struct miscdevice pm_qos_power_miscdev; + char *name; + s32 default_value; + s32 target_value; + s32 (*comparitor)(s32, s32); +}; + +static struct pm_qos_object null_pm_qos; +static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); +static struct pm_qos_object cpu_dma_pm_qos = { + .requirements = {LIST_HEAD_INIT(cpu_dma_pm_qos.requirements.list)}, + .notifiers = &cpu_dma_lat_notifier, + .name = "cpu_dma_latency", + .default_value = 2000 * USEC_PER_SEC, + .target_value = 2000 * USEC_PER_SEC, + .comparitor = min_compare +}; + +static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); +static struct pm_qos_object network_lat_pm_qos = { + .requirements = {LIST_HEAD_INIT(network_lat_pm_qos.requirements.list)}, + .notifiers = &network_lat_notifier, + .name = "network_latency", + .default_value = 2000 * USEC_PER_SEC, + .target_value = 2000 * USEC_PER_SEC, + .comparitor = min_compare +}; + + +static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); +static struct pm_qos_object network_throughput_pm_qos = { + .requirements = + {LIST_HEAD_INIT(network_throughput_pm_qos.requirements.list)}, + .notifiers = &network_throughput_notifier, + .name = "network_throughput", + .default_value = 0, + .target_value = 0, + .comparitor = max_compare +}; + + +static struct pm_qos_object *pm_qos_array[] = { + &null_pm_qos, + &cpu_dma_pm_qos, + &network_lat_pm_qos, + &network_throughput_pm_qos +}; + +static DEFINE_SPINLOCK(pm_qos_lock); + +static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos); +static int pm_qos_power_open(struct inode *inode, struct file *filp); +static int pm_qos_power_release(struct inode *inode, struct file *filp); + +static const struct file_operations pm_qos_power_fops = { + .write = pm_qos_power_write, + .open = pm_qos_power_open, + .release = pm_qos_power_release, +}; + +/* static helper functions */ +static s32 max_compare(s32 v1, s32 v2) +{ + return max(v1, v2); +} + +static s32 min_compare(s32 v1, s32 v2) +{ + return min(v1, v2); +} + + +static void update_target(int target) +{ + s32 extreme_value; + struct requirement_list *node; + unsigned long flags; + int call_notifier = 0; + + spin_lock_irqsave(&pm_qos_lock, flags); + extreme_value = pm_qos_array[target]->default_value; + list_for_each_entry(node, + &pm_qos_array[target]->requirements.list, list) { + extreme_value = pm_qos_array[target]->comparitor( + extreme_value, node->value); + } + if (pm_qos_array[target]->target_value != extreme_value) { + call_notifier = 1; + pm_qos_array[target]->target_value = extreme_value; + pr_debug(KERN_ERR "new target for qos %d is %d\n", target, + pm_qos_array[target]->target_value); + } + spin_unlock_irqrestore(&pm_qos_lock, flags); + + if (call_notifier) + blocking_notifier_call_chain(pm_qos_array[target]->notifiers, + (unsigned long) extreme_value, NULL); +} + +static int register_pm_qos_misc(struct pm_qos_object *qos) +{ + qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR; + qos->pm_qos_power_miscdev.name = qos->name; + qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; + + return misc_register(&qos->pm_qos_power_miscdev); +} + +static int find_pm_qos_object_by_minor(int minor) +{ + int pm_qos_class; + + for (pm_qos_class = 0; + pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) { + if (minor == + pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor) + return pm_qos_class; + } + return -1; +} + +/** + * pm_qos_requirement - returns current system wide qos expectation + * @pm_qos_class: identification of which qos value is requested + * + * This function returns the current target value in an atomic manner. + */ +int pm_qos_requirement(int pm_qos_class) +{ + int ret_val; + unsigned long flags; + + spin_lock_irqsave(&pm_qos_lock, flags); + ret_val = pm_qos_array[pm_qos_class]->target_value; + spin_unlock_irqrestore(&pm_qos_lock, flags); + + return ret_val; +} +EXPORT_SYMBOL_GPL(pm_qos_requirement); + +/** + * pm_qos_add_requirement - inserts new qos request into the list + * @pm_qos_class: identifies which list of qos request to us + * @name: identifies the request + * @value: defines the qos request + * + * This function inserts a new entry in the pm_qos_class list of requested qos + * performance charactoistics. It recomputes the agregate QoS expectations for + * the pm_qos_class of parrameters. + */ +int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value) +{ + struct requirement_list *dep; + unsigned long flags; + + dep = kzalloc(sizeof(struct requirement_list), GFP_KERNEL); + if (dep) { + if (value == PM_QOS_DEFAULT_VALUE) + dep->value = pm_qos_array[pm_qos_class]->default_value; + else + dep->value = value; + dep->name = kstrdup(name, GFP_KERNEL); + if (!dep->name) + goto cleanup; + + spin_lock_irqsave(&pm_qos_lock, flags); + list_add(&dep->list, + &pm_qos_array[pm_qos_class]->requirements.list); + spin_unlock_irqrestore(&pm_qos_lock, flags); + update_target(pm_qos_class); + + return 0; + } + +cleanup: + kfree(dep); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(pm_qos_add_requirement); + +/** + * pm_qos_update_requirement - modifies an existing qos request + * @pm_qos_class: identifies which list of qos request to us + * @name: identifies the request + * @value: defines the qos request + * + * Updates an existing qos requierement for the pm_qos_class of parameters along + * with updating the target pm_qos_class value. + * + * If the named request isn't in the lest then no change is made. + */ +int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value) +{ + unsigned long flags; + struct requirement_list *node; + int pending_update = 0; + + spin_lock_irqsave(&pm_qos_lock, flags); + list_for_each_entry(node, + &pm_qos_array[pm_qos_class]->requirements.list, list) { + if (strcmp(node->name, name) == 0) { + if (new_value == PM_QOS_DEFAULT_VALUE) + node->value = + pm_qos_array[pm_qos_class]->default_value; + else + node->value = new_value; + pending_update = 1; + break; + } + } + spin_unlock_irqrestore(&pm_qos_lock, flags); + if (pending_update) + update_target(pm_qos_class); + + return 0; +} +EXPORT_SYMBOL_GPL(pm_qos_update_requirement); + +/** + * pm_qos_remove_requirement - modifies an existing qos request + * @pm_qos_class: identifies which list of qos request to us + * @name: identifies the request + * + * Will remove named qos request from pm_qos_class list of parrameters and + * recompute the current target value for the pm_qos_class. + */ +void pm_qos_remove_requirement(int pm_qos_class, char *name) +{ + unsigned long flags; + struct requirement_list *node; + int pending_update = 0; + + spin_lock_irqsave(&pm_qos_lock, flags); + list_for_each_entry(node, + &pm_qos_array[pm_qos_class]->requirements.list, list) { + if (strcmp(node->name, name) == 0) { + kfree(node->name); + list_del(&node->list); + kfree(node); + pending_update = 1; + break; + } + } + spin_unlock_irqrestore(&pm_qos_lock, flags); + if (pending_update) + update_target(pm_qos_class); +} +EXPORT_SYMBOL_GPL(pm_qos_remove_requirement); + +/** + * pm_qos_add_notifier - sets notification entry for changes to target value + * @pm_qos_class: identifies which qos target changes should be notified. + * @notifier: notifier block managed by caller. + * + * will register the notifier into a notification chain that gets called + * uppon changes to the pm_qos_class target value. + */ + int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier) +{ + int retval; + + retval = blocking_notifier_chain_register( + pm_qos_array[pm_qos_class]->notifiers, notifier); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_qos_add_notifier); + +/** + * pm_qos_remove_notifier - deletes notification entry from chain. + * @pm_qos_class: identifies which qos target changes are notified. + * @notifier: notifier block to be removed. + * + * will remove the notifier from the notification chain that gets called + * uppon changes to the pm_qos_class target value. + */ +int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) +{ + int retval; + + retval = blocking_notifier_chain_unregister( + pm_qos_array[pm_qos_class]->notifiers, notifier); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_qos_remove_notifier); + +#define PID_NAME_LEN sizeof("process_1234567890") +static char name[PID_NAME_LEN]; + +static int pm_qos_power_open(struct inode *inode, struct file *filp) +{ + int ret; + long pm_qos_class; + + pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); + if (pm_qos_class >= 0) { + filp->private_data = (void *)pm_qos_class; + sprintf(name, "process_%d", current->pid); + ret = pm_qos_add_requirement(pm_qos_class, name, + PM_QOS_DEFAULT_VALUE); + if (ret >= 0) + return 0; + } + + return -EPERM; +} + +static int pm_qos_power_release(struct inode *inode, struct file *filp) +{ + int pm_qos_class; + + pm_qos_class = (long)filp->private_data; + sprintf(name, "process_%d", current->pid); + pm_qos_remove_requirement(pm_qos_class, name); + + return 0; +} + +static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos) +{ + s32 value; + int pm_qos_class; + + pm_qos_class = (long)filp->private_data; + if (count != sizeof(s32)) + return -EINVAL; + if (copy_from_user(&value, buf, sizeof(s32))) + return -EFAULT; + sprintf(name, "process_%d", current->pid); + pm_qos_update_requirement(pm_qos_class, name, value); + + return sizeof(s32); +} + + +static int __init pm_qos_power_init(void) +{ + int ret = 0; + + ret = register_pm_qos_misc(&cpu_dma_pm_qos); + if (ret < 0) { + printk(KERN_ERR "pm_qos_param: cpu_dma_latency setup failed\n"); + return ret; + } + ret = register_pm_qos_misc(&network_lat_pm_qos); + if (ret < 0) { + printk(KERN_ERR "pm_qos_param: network_latency setup failed\n"); + return ret; + } + ret = register_pm_qos_misc(&network_throughput_pm_qos); + if (ret < 0) + printk(KERN_ERR + "pm_qos_param: network_throughput setup failed\n"); + + return ret; +} + +late_initcall(pm_qos_power_init); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 35b4bbfc78f..122d5c787fe 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -256,8 +256,9 @@ static void schedule_next_timer(struct k_itimer *timr) if (timr->it.real.interval.tv64 == 0) return; - timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), - timr->it.real.interval); + timr->it_overrun += (unsigned int) hrtimer_forward(timer, + timer->base->get_time(), + timr->it.real.interval); timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1; @@ -386,7 +387,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) now = ktime_add(now, kj); } #endif - timr->it_overrun += + timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, timr->it.real.interval); ret = HRTIMER_RESTART; @@ -493,7 +494,7 @@ sys_timer_create(const clockid_t which_clock, goto retry; else if (error) { /* - * Wierd looking, but we return EAGAIN if the IDR is + * Weird looking, but we return EAGAIN if the IDR is * full (proper POSIX return value for this) */ error = -EAGAIN; @@ -662,7 +663,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) */ if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING || (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) - timr->it_overrun += hrtimer_forward(timer, now, iv); + timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); remaining = ktime_sub(timer->expires, now); /* Return 0 only, when the timer is expired and not pending */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index ef9b802738a..79833170bb9 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -74,8 +74,8 @@ config PM_TRACE_RTC RTC across reboots, so that you can debug a machine that just hangs during suspend (or more commonly, during resume). - To use this debugging feature you should attempt to suspend the machine, - then reboot it, then run + To use this debugging feature you should attempt to suspend the + machine, reboot it and then run dmesg -s 1000000 | grep 'hash matches' @@ -123,7 +123,10 @@ config HIBERNATION called "hibernation" in user interfaces. STD checkpoints the system and powers it off; and restores that checkpoint on reboot. - You can suspend your machine with 'echo disk > /sys/power/state'. + You can suspend your machine with 'echo disk > /sys/power/state' + after placing resume=/dev/swappartition on the kernel command line + in your bootloader's configuration file. + Alternatively, you can use the additional userland tools available from <http://suspend.sf.net>. diff --git a/kernel/power/disk.c b/kernel/power/disk.c index d09da089517..859a8e59773 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -26,7 +26,7 @@ static int noresume = 0; -char resume_file[256] = CONFIG_PM_STD_PARTITION; +static char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; sector_t swsusp_resume_block; @@ -185,7 +185,7 @@ static void platform_restore_cleanup(int platform_mode) * reappears in this routine after a restore. */ -int create_image(int platform_mode) +static int create_image(int platform_mode) { int error; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f6a5df934f8..95250d7c8d9 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1203,7 +1203,7 @@ asmlinkage int swsusp_save(void) printk(KERN_INFO "PM: Creating hibernation image: \n"); - drain_local_pages(); + drain_local_pages(NULL); nr_pages = count_data_pages(); nr_highmem = count_highmem_pages(); printk(KERN_INFO "PM: Need to copy %u pages\n", nr_pages + nr_highmem); @@ -1221,7 +1221,7 @@ asmlinkage int swsusp_save(void) /* During allocating of suspend pagedir, new cold pages may appear. * Kill them. */ - drain_local_pages(); + drain_local_pages(NULL); copy_data_pages(©_bm, &orig_bm); /* diff --git a/kernel/printk.c b/kernel/printk.c index 29ae1e99cde..4a090621f37 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -93,16 +93,16 @@ static int console_locked, console_suspended; */ static DEFINE_SPINLOCK(logbuf_lock); -#define LOG_BUF_MASK (log_buf_len-1) +#define LOG_BUF_MASK (log_buf_len-1) #define LOG_BUF(idx) (log_buf[(idx) & LOG_BUF_MASK]) /* * The indices into log_buf are not constrained to log_buf_len - they * must be masked before subscripting */ -static unsigned long log_start; /* Index into log_buf: next char to be read by syslog() */ -static unsigned long con_start; /* Index into log_buf: next char to be sent to consoles */ -static unsigned long log_end; /* Index into log_buf: most-recently-written-char + 1 */ +static unsigned log_start; /* Index into log_buf: next char to be read by syslog() */ +static unsigned con_start; /* Index into log_buf: next char to be sent to consoles */ +static unsigned log_end; /* Index into log_buf: most-recently-written-char + 1 */ /* * Array of consoles built from command line options (console=) @@ -128,17 +128,17 @@ static int console_may_schedule; static char __log_buf[__LOG_BUF_LEN]; static char *log_buf = __log_buf; static int log_buf_len = __LOG_BUF_LEN; -static unsigned long logged_chars; /* Number of chars produced since last read+clear operation */ +static unsigned logged_chars; /* Number of chars produced since last read+clear operation */ static int __init log_buf_len_setup(char *str) { - unsigned long size = memparse(str, &str); + unsigned size = memparse(str, &str); unsigned long flags; if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) { - unsigned long start, dest_idx, offset; + unsigned start, dest_idx, offset; char *new_log_buf; new_log_buf = alloc_bootmem(size); @@ -295,7 +295,7 @@ int log_buf_read(int idx) */ int do_syslog(int type, char __user *buf, int len) { - unsigned long i, j, limit, count; + unsigned i, j, limit, count; int do_clear = 0; char c; int error = 0; @@ -436,7 +436,7 @@ asmlinkage long sys_syslog(int type, char __user *buf, int len) /* * Call the console drivers on a range of log_buf */ -static void __call_console_drivers(unsigned long start, unsigned long end) +static void __call_console_drivers(unsigned start, unsigned end) { struct console *con; @@ -463,8 +463,8 @@ early_param("ignore_loglevel", ignore_loglevel_setup); /* * Write out chars from start to end - 1 inclusive */ -static void _call_console_drivers(unsigned long start, - unsigned long end, int msg_log_level) +static void _call_console_drivers(unsigned start, + unsigned end, int msg_log_level) { if ((msg_log_level < console_loglevel || ignore_loglevel) && console_drivers && start != end) { @@ -484,12 +484,12 @@ static void _call_console_drivers(unsigned long start, * log_buf[start] to log_buf[end - 1]. * The console_sem must be held. */ -static void call_console_drivers(unsigned long start, unsigned long end) +static void call_console_drivers(unsigned start, unsigned end) { - unsigned long cur_index, start_print; + unsigned cur_index, start_print; static int msg_level = -1; - BUG_ON(((long)(start - end)) > 0); + BUG_ON(((int)(start - end)) > 0); cur_index = start; start_print = start; @@ -790,7 +790,7 @@ asmlinkage long sys_syslog(int type, char __user *buf, int len) return -ENOSYS; } -static void call_console_drivers(unsigned long start, unsigned long end) +static void call_console_drivers(unsigned start, unsigned end) { } @@ -983,8 +983,8 @@ void wake_up_klogd(void) void release_console_sem(void) { unsigned long flags; - unsigned long _con_start, _log_end; - unsigned long wake_klogd = 0; + unsigned _con_start, _log_end; + unsigned wake_klogd = 0; if (console_suspended) { up(&secondary_console_sem); @@ -1275,7 +1275,7 @@ void tty_write_message(struct tty_struct *tty, char *msg) int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst) { static DEFINE_SPINLOCK(ratelimit_lock); - static unsigned long toks = 10 * 5 * HZ; + static unsigned toks = 10 * 5 * HZ; static unsigned long last_msg; static int missed; unsigned long flags; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index b0d4ab4dfd3..628b03ab88a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -20,6 +20,7 @@ #include <linux/signal.h> #include <linux/audit.h> #include <linux/pid_namespace.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/uaccess.h> @@ -53,7 +54,7 @@ void ptrace_untrace(struct task_struct *child) spin_lock(&child->sighand->siglock); if (task_is_traced(child)) { if (child->signal->flags & SIGNAL_STOP_STOPPED) { - child->state = TASK_STOPPED; + __set_task_state(child, TASK_STOPPED); } else { signal_wake_up(child, 1); } @@ -103,18 +104,16 @@ int ptrace_check_attach(struct task_struct *child, int kill) && child->signal != NULL) { ret = 0; spin_lock_irq(&child->sighand->siglock); - if (task_is_stopped(child)) { + if (task_is_stopped(child)) child->state = TASK_TRACED; - } else if (!task_is_traced(child) && !kill) { + else if (!task_is_traced(child) && !kill) ret = -ESRCH; - } spin_unlock_irq(&child->sighand->siglock); } read_unlock(&tasklist_lock); - if (!ret && !kill) { + if (!ret && !kill) wait_task_inactive(child); - } /* All systems go.. */ return ret; diff --git a/kernel/relay.c b/kernel/relay.c index 61134eb7a0c..d080b9d161a 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -37,37 +37,31 @@ static void relay_file_mmap_close(struct vm_area_struct *vma) } /* - * nopage() vm_op implementation for relay file mapping. + * fault() vm_op implementation for relay file mapping. */ -static struct page *relay_buf_nopage(struct vm_area_struct *vma, - unsigned long address, - int *type) +static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page; struct rchan_buf *buf = vma->vm_private_data; - unsigned long offset = address - vma->vm_start; + pgoff_t pgoff = vmf->pgoff; - if (address > vma->vm_end) - return NOPAGE_SIGBUS; /* Disallow mremap */ if (!buf) - return NOPAGE_OOM; + return VM_FAULT_OOM; - page = vmalloc_to_page(buf->start + offset); + page = vmalloc_to_page(buf->start + (pgoff << PAGE_SHIFT)); if (!page) - return NOPAGE_OOM; + return VM_FAULT_SIGBUS; get_page(page); + vmf->page = page; - if (type) - *type = VM_FAULT_MINOR; - - return page; + return 0; } /* * vm_ops for relay file mappings. */ static struct vm_operations_struct relay_file_mmap_ops = { - .nopage = relay_buf_nopage, + .fault = relay_buf_fault, .close = relay_file_mmap_close, }; @@ -92,6 +86,7 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) return -EINVAL; vma->vm_ops = &relay_file_mmap_ops; + vma->vm_flags |= VM_DONTEXPAND; vma->vm_private_data = buf; buf->chan->cb->buf_mapped(buf, filp); diff --git a/kernel/res_counter.c b/kernel/res_counter.c new file mode 100644 index 00000000000..16cbec2d5d6 --- /dev/null +++ b/kernel/res_counter.c @@ -0,0 +1,134 @@ +/* + * resource cgroups + * + * Copyright 2007 OpenVZ SWsoft Inc + * + * Author: Pavel Emelianov <xemul@openvz.org> + * + */ + +#include <linux/types.h> +#include <linux/parser.h> +#include <linux/fs.h> +#include <linux/res_counter.h> +#include <linux/uaccess.h> + +void res_counter_init(struct res_counter *counter) +{ + spin_lock_init(&counter->lock); + counter->limit = (unsigned long long)LLONG_MAX; +} + +int res_counter_charge_locked(struct res_counter *counter, unsigned long val) +{ + if (counter->usage + val > counter->limit) { + counter->failcnt++; + return -ENOMEM; + } + + counter->usage += val; + return 0; +} + +int res_counter_charge(struct res_counter *counter, unsigned long val) +{ + int ret; + unsigned long flags; + + spin_lock_irqsave(&counter->lock, flags); + ret = res_counter_charge_locked(counter, val); + spin_unlock_irqrestore(&counter->lock, flags); + return ret; +} + +void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) +{ + if (WARN_ON(counter->usage < val)) + val = counter->usage; + + counter->usage -= val; +} + +void res_counter_uncharge(struct res_counter *counter, unsigned long val) +{ + unsigned long flags; + + spin_lock_irqsave(&counter->lock, flags); + res_counter_uncharge_locked(counter, val); + spin_unlock_irqrestore(&counter->lock, flags); +} + + +static inline unsigned long long * +res_counter_member(struct res_counter *counter, int member) +{ + switch (member) { + case RES_USAGE: + return &counter->usage; + case RES_LIMIT: + return &counter->limit; + case RES_FAILCNT: + return &counter->failcnt; + }; + + BUG(); + return NULL; +} + +ssize_t res_counter_read(struct res_counter *counter, int member, + const char __user *userbuf, size_t nbytes, loff_t *pos, + int (*read_strategy)(unsigned long long val, char *st_buf)) +{ + unsigned long long *val; + char buf[64], *s; + + s = buf; + val = res_counter_member(counter, member); + if (read_strategy) + s += read_strategy(*val, s); + else + s += sprintf(s, "%llu\n", *val); + return simple_read_from_buffer((void __user *)userbuf, nbytes, + pos, buf, s - buf); +} + +ssize_t res_counter_write(struct res_counter *counter, int member, + const char __user *userbuf, size_t nbytes, loff_t *pos, + int (*write_strategy)(char *st_buf, unsigned long long *val)) +{ + int ret; + char *buf, *end; + unsigned long flags; + unsigned long long tmp, *val; + + buf = kmalloc(nbytes + 1, GFP_KERNEL); + ret = -ENOMEM; + if (buf == NULL) + goto out; + + buf[nbytes] = '\0'; + ret = -EFAULT; + if (copy_from_user(buf, userbuf, nbytes)) + goto out_free; + + ret = -EINVAL; + + if (write_strategy) { + if (write_strategy(buf, &tmp)) { + goto out_free; + } + } else { + tmp = simple_strtoull(buf, &end, 10); + if (*end != '\0') + goto out_free; + } + spin_lock_irqsave(&counter->lock, flags); + val = res_counter_member(counter, member); + *val = tmp; + spin_unlock_irqrestore(&counter->lock, flags); + ret = nbytes; +out_free: + kfree(buf); +out: + return ret; +} diff --git a/kernel/signal.c b/kernel/signal.c index 4333b6dbb42..5d30ff56184 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -911,27 +911,6 @@ __group_complete_signal(int sig, struct task_struct *p) } while_each_thread(p, t); return; } - - /* - * There will be a core dump. We make all threads other - * than the chosen one go into a group stop so that nothing - * happens until it gets scheduled, takes the signal off - * the shared queue, and does the core dump. This is a - * little more complicated than strictly necessary, but it - * keeps the signal state that winds up in the core dump - * unchanged from the death state, e.g. which thread had - * the core-dump signal unblocked. - */ - rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending); - rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending); - p->signal->group_stop_count = 0; - p->signal->group_exit_task = t; - p = t; - do { - p->signal->group_stop_count++; - signal_wake_up(t, t == p); - } while_each_thread(p, t); - return; } /* @@ -978,7 +957,6 @@ void zap_other_threads(struct task_struct *p) { struct task_struct *t; - p->signal->flags = SIGNAL_GROUP_EXIT; p->signal->group_stop_count = 0; for (t = next_thread(p); t != p; t = next_thread(t)) { @@ -1600,6 +1578,17 @@ static inline int may_ptrace_stop(void) } /* + * Return nonzero if there is a SIGKILL that should be waking us up. + * Called with the siglock held. + */ +static int sigkill_pending(struct task_struct *tsk) +{ + return ((sigismember(&tsk->pending.signal, SIGKILL) || + sigismember(&tsk->signal->shared_pending.signal, SIGKILL)) && + !unlikely(sigismember(&tsk->blocked, SIGKILL))); +} + +/* * This must be called with current->sighand->siglock held. * * This should be the path for all ptrace stops. @@ -1612,6 +1601,26 @@ static inline int may_ptrace_stop(void) */ static void ptrace_stop(int exit_code, int nostop_code, siginfo_t *info) { + int killed = 0; + + if (arch_ptrace_stop_needed(exit_code, info)) { + /* + * The arch code has something special to do before a + * ptrace stop. This is allowed to block, e.g. for faults + * on user stack pages. We can't keep the siglock while + * calling arch_ptrace_stop, so we must release it now. + * To preserve proper semantics, we must do this before + * any signal bookkeeping like checking group_stop_count. + * Meanwhile, a SIGKILL could come in before we retake the + * siglock. That must prevent us from sleeping in TASK_TRACED. + * So after regaining the lock, we must check for SIGKILL. + */ + spin_unlock_irq(¤t->sighand->siglock); + arch_ptrace_stop(exit_code, info); + spin_lock_irq(¤t->sighand->siglock); + killed = sigkill_pending(current); + } + /* * If there is a group stop in progress, * we must participate in the bookkeeping. @@ -1623,11 +1632,11 @@ static void ptrace_stop(int exit_code, int nostop_code, siginfo_t *info) current->exit_code = exit_code; /* Let the debugger run. */ - set_current_state(TASK_TRACED); + __set_current_state(TASK_TRACED); spin_unlock_irq(¤t->sighand->siglock); try_to_freeze(); read_lock(&tasklist_lock); - if (may_ptrace_stop()) { + if (!unlikely(killed) && may_ptrace_stop()) { do_notify_parent_cldstop(current, CLD_TRAPPED); read_unlock(&tasklist_lock); schedule(); @@ -1709,9 +1718,6 @@ static int do_signal_stop(int signr) struct signal_struct *sig = current->signal; int stop_count; - if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED)) - return 0; - if (sig->group_stop_count > 0) { /* * There is a group stop in progress. We don't need to @@ -1719,12 +1725,15 @@ static int do_signal_stop(int signr) */ stop_count = --sig->group_stop_count; } else { + struct task_struct *t; + + if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || + unlikely(sig->group_exit_task)) + return 0; /* * There is no group stop already in progress. * We must initiate one now. */ - struct task_struct *t; - sig->group_exit_code = signr; stop_count = 0; @@ -1752,47 +1761,6 @@ static int do_signal_stop(int signr) return 1; } -/* - * Do appropriate magic when group_stop_count > 0. - * We return nonzero if we stopped, after releasing the siglock. - * We return zero if we still hold the siglock and should look - * for another signal without checking group_stop_count again. - */ -static int handle_group_stop(void) -{ - int stop_count; - - if (current->signal->group_exit_task == current) { - /* - * Group stop is so we can do a core dump, - * We are the initiating thread, so get on with it. - */ - current->signal->group_exit_task = NULL; - return 0; - } - - if (current->signal->flags & SIGNAL_GROUP_EXIT) - /* - * Group stop is so another thread can do a core dump, - * or else we are racing against a death signal. - * Just punt the stop so we can get the next signal. - */ - return 0; - - /* - * There is a group stop in progress. We stop - * without any associated signal being in our queue. - */ - stop_count = --current->signal->group_stop_count; - if (stop_count == 0) - current->signal->flags = SIGNAL_STOP_STOPPED; - current->exit_code = current->signal->group_exit_code; - set_current_state(TASK_STOPPED); - spin_unlock_irq(¤t->sighand->siglock); - finish_stop(stop_count); - return 1; -} - int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie) { @@ -1807,7 +1775,7 @@ relock: struct k_sigaction *ka; if (unlikely(current->signal->group_stop_count > 0) && - handle_group_stop()) + do_signal_stop(0)) goto relock; signr = dequeue_signal(current, mask, info); diff --git a/kernel/srcu.c b/kernel/srcu.c index 3507cabe963..b0aeeaf22ce 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -74,7 +74,7 @@ static int srcu_readers_active_idx(struct srcu_struct *sp, int idx) * severe errors when invoked on an active srcu_struct. That said, it * can be useful as an error check at cleanup time. */ -int srcu_readers_active(struct srcu_struct *sp) +static int srcu_readers_active(struct srcu_struct *sp) { return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1); } @@ -255,4 +255,3 @@ EXPORT_SYMBOL_GPL(srcu_read_lock); EXPORT_SYMBOL_GPL(srcu_read_unlock); EXPORT_SYMBOL_GPL(synchronize_srcu); EXPORT_SYMBOL_GPL(srcu_batches_completed); -EXPORT_SYMBOL_GPL(srcu_readers_active); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 51b5ee53571..6f4e0e13f70 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -29,7 +29,6 @@ enum stopmachine_state { static enum stopmachine_state stopmachine_state; static unsigned int stopmachine_num_threads; static atomic_t stopmachine_thread_ack; -static DECLARE_MUTEX(stopmachine_mutex); static int stopmachine(void *cpu) { @@ -170,6 +169,7 @@ static int do_stop(void *_smdata) struct task_struct *__stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu) { + static DEFINE_MUTEX(stopmachine_mutex); struct stop_machine_data smdata; struct task_struct *p; @@ -177,7 +177,7 @@ struct task_struct *__stop_machine_run(int (*fn)(void *), void *data, smdata.data = data; init_completion(&smdata.done); - down(&stopmachine_mutex); + mutex_lock(&stopmachine_mutex); /* If they don't care which CPU fn runs on, bind to any online one. */ if (cpu == NR_CPUS) @@ -193,7 +193,7 @@ struct task_struct *__stop_machine_run(int (*fn)(void *), void *data, wake_up_process(p); wait_for_completion(&smdata.done); } - up(&stopmachine_mutex); + mutex_unlock(&stopmachine_mutex); return p; } diff --git a/kernel/sys.c b/kernel/sys.c index d1fe71eb454..e3c08d4324d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -315,7 +315,7 @@ static void kernel_kexec(void) #endif } -void kernel_shutdown_prepare(enum system_states state) +static void kernel_shutdown_prepare(enum system_states state) { blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); @@ -1145,16 +1145,16 @@ static int groups_to_user(gid_t __user *grouplist, struct group_info *group_info) { int i; - int count = group_info->ngroups; + unsigned int count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min(NGROUPS_PER_BLOCK, count); - int off = i * NGROUPS_PER_BLOCK; - int len = cp_count * sizeof(*grouplist); + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); - if (copy_to_user(grouplist+off, group_info->blocks[i], len)) + if (copy_to_user(grouplist, group_info->blocks[i], len)) return -EFAULT; + grouplist += NGROUPS_PER_BLOCK; count -= cp_count; } return 0; @@ -1165,16 +1165,16 @@ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { int i; - int count = group_info->ngroups; + unsigned int count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min(NGROUPS_PER_BLOCK, count); - int off = i * NGROUPS_PER_BLOCK; - int len = cp_count * sizeof(*grouplist); + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); - if (copy_from_user(group_info->blocks[i], grouplist+off, len)) + if (copy_from_user(group_info->blocks[i], grouplist, len)) return -EFAULT; + grouplist += NGROUPS_PER_BLOCK; count -= cp_count; } return 0; @@ -1472,7 +1472,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if ((new_rlim.rlim_max > old_rlim->rlim_max) && !capable(CAP_SYS_RESOURCE)) return -EPERM; - if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN) + if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open) return -EPERM; retval = security_task_setrlimit(resource, &new_rlim); @@ -1637,7 +1637,7 @@ asmlinkage long sys_umask(int mask) mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } - + asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { @@ -1742,6 +1742,17 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, error = prctl_set_seccomp(arg2); break; + case PR_CAPBSET_READ: + if (!cap_valid(arg2)) + return -EINVAL; + return !!cap_raised(current->cap_bset, arg2); + case PR_CAPBSET_DROP: +#ifdef CONFIG_SECURITY_FILE_CAPABILITIES + return cap_prctl_drop(arg2); +#else + return -EINVAL; +#endif + default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index beee5b3b68a..5b9b467de07 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -154,7 +154,10 @@ cond_syscall(sys_ioprio_get); /* New file descriptors */ cond_syscall(sys_signalfd); -cond_syscall(sys_timerfd); cond_syscall(compat_sys_signalfd); -cond_syscall(compat_sys_timerfd); +cond_syscall(sys_timerfd_create); +cond_syscall(sys_timerfd_settime); +cond_syscall(sys_timerfd_gettime); +cond_syscall(compat_sys_timerfd_settime); +cond_syscall(compat_sys_timerfd_gettime); cond_syscall(sys_eventfd); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7cb1ac3e6ff..8c98d8147d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -67,6 +67,7 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern int sysctl_panic_on_oom; extern int sysctl_oom_kill_allocating_task; +extern int sysctl_oom_dump_tasks; extern int max_threads; extern int core_uses_pid; extern int suid_dumpable; @@ -84,8 +85,11 @@ extern int sysctl_stat_interval; extern int latencytop_enabled; /* Constants used for minimum and maximum */ -#ifdef CONFIG_DETECT_SOFTLOCKUP +#if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM) static int one = 1; +#endif + +#ifdef CONFIG_DETECT_SOFTLOCKUP static int sixty = 60; #endif @@ -416,15 +420,6 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_SECURITY_CAPABILITIES - { - .procname = "cap-bound", - .data = &cap_bset, - .maxlen = sizeof(kernel_cap_t), - .mode = 0600, - .proc_handler = &proc_dointvec_bset, - }, -#endif /* def CONFIG_SECURITY_CAPABILITIES */ #ifdef CONFIG_BLK_DEV_INITRD { .ctl_name = KERN_REALROOTDEV, @@ -877,6 +872,14 @@ static struct ctl_table vm_table[] = { .proc_handler = &proc_dointvec, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "oom_dump_tasks", + .data = &sysctl_oom_dump_tasks, + .maxlen = sizeof(sysctl_oom_dump_tasks), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = VM_OVERCOMMIT_RATIO, .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, @@ -1150,6 +1153,19 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, }, #endif +#ifdef CONFIG_HIGHMEM + { + .ctl_name = CTL_UNNUMBERED, + .procname = "highmem_is_dirtyable", + .data = &vm_highmem_is_dirtyable, + .maxlen = sizeof(vm_highmem_is_dirtyable), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt @@ -1196,6 +1212,14 @@ static struct ctl_table fs_table[] = { .proc_handler = &proc_dointvec, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "nr_open", + .data = &sysctl_nr_open, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = FS_DENTRY, .procname = "dentry-state", .data = &dentry_stat, @@ -2080,26 +2104,6 @@ static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp, return 0; } -#ifdef CONFIG_SECURITY_CAPABILITIES -/* - * init may raise the set. - */ - -int proc_dointvec_bset(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int op; - - if (write && !capable(CAP_SYS_MODULE)) { - return -EPERM; - } - - op = is_global_init(current) ? OP_SET : OP_AND; - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, - do_proc_dointvec_bset_conv,&op); -} -#endif /* def CONFIG_SECURITY_CAPABILITIES */ - /* * Taint values can only be increased */ @@ -2513,12 +2517,6 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp, return -ENOSYS; } -int proc_dointvec_bset(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index c3206fa5004..006365b69ea 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -37,10 +37,6 @@ static struct trans_ctl_table trans_kern_table[] = { { KERN_NODENAME, "hostname" }, { KERN_DOMAINNAME, "domainname" }, -#ifdef CONFIG_SECURITY_CAPABILITIES - { KERN_CAP_BSET, "cap-bound" }, -#endif /* def CONFIG_SECURITY_CAPABILITIES */ - { KERN_PANIC, "panic" }, { KERN_REALROOTDEV, "real-root-dev" }, @@ -1498,9 +1494,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) (table->strategy == sysctl_ms_jiffies) || (table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || -#ifdef CONFIG_SECURITY_CAPABILITIES - (table->proc_handler == proc_dointvec_bset) || -#endif /* def CONFIG_SECURITY_CAPABILITIES */ (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index 88cdb109e13..06b6395b45b 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -135,6 +135,12 @@ static int test_jprobe(void) #ifdef CONFIG_KRETPROBES static u32 krph_val; +static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + krph_val = (rand1 / div_factor); + return 0; +} + static int return_handler(struct kretprobe_instance *ri, struct pt_regs *regs) { unsigned long ret = regs_return_value(regs); @@ -144,13 +150,19 @@ static int return_handler(struct kretprobe_instance *ri, struct pt_regs *regs) printk(KERN_ERR "Kprobe smoke test failed: " "incorrect value in kretprobe handler\n"); } + if (krph_val == 0) { + handler_errors++; + printk(KERN_ERR "Kprobe smoke test failed: " + "call to kretprobe entry handler failed\n"); + } - krph_val = (rand1 / div_factor); + krph_val = rand1; return 0; } static struct kretprobe rp = { .handler = return_handler, + .entry_handler = entry_handler, .kp.symbol_name = "kprobe_target" }; @@ -167,7 +179,7 @@ static int test_kretprobe(void) ret = kprobe_target(rand1); unregister_kretprobe(&rp); - if (krph_val == 0) { + if (krph_val != rand1) { printk(KERN_ERR "Kprobe smoke test failed: " "kretprobe handler not called\n"); handler_errors++; diff --git a/kernel/time.c b/kernel/time.c index 4064c0566e7..33af3e55570 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -566,7 +566,11 @@ EXPORT_SYMBOL(jiffies_to_timeval); clock_t jiffies_to_clock_t(long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 +# if HZ < USER_HZ + return x * (USER_HZ / HZ); +# else return x / (HZ / USER_HZ); +# endif #else u64 tmp = (u64)x * TICK_NSEC; do_div(tmp, (NSEC_PER_SEC / USER_HZ)); @@ -599,7 +603,14 @@ EXPORT_SYMBOL(clock_t_to_jiffies); u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 +# if HZ < USER_HZ + x *= USER_HZ; + do_div(x, HZ); +# elif HZ > USER_HZ do_div(x, HZ / USER_HZ); +# else + /* Nothing to do */ +# endif #else /* * There are better ways that don't overflow early, @@ -611,7 +622,6 @@ u64 jiffies_64_to_clock_t(u64 x) #endif return x; } - EXPORT_SYMBOL(jiffies_64_to_clock_t); u64 nsec_to_clock_t(u64 x) @@ -646,7 +656,6 @@ u64 get_jiffies_64(void) } while (read_seqretry(&xtime_lock, seq)); return ret; } - EXPORT_SYMBOL(get_jiffies_64); #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 6e9259a5d50..81afb3927ec 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -363,15 +363,13 @@ void clocksource_unregister(struct clocksource *cs) static ssize_t sysfs_show_current_clocksources(struct sys_device *dev, char *buf) { - char *curr = buf; + ssize_t count = 0; spin_lock_irq(&clocksource_lock); - curr += sprintf(curr, "%s ", curr_clocksource->name); + count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); spin_unlock_irq(&clocksource_lock); - curr += sprintf(curr, "\n"); - - return curr - buf; + return count; } /** @@ -439,17 +437,20 @@ static ssize_t sysfs_show_available_clocksources(struct sys_device *dev, char *buf) { struct clocksource *src; - char *curr = buf; + ssize_t count = 0; spin_lock_irq(&clocksource_lock); list_for_each_entry(src, &clocksource_list, list) { - curr += sprintf(curr, "%s ", src->name); + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), + "%s ", src->name); } spin_unlock_irq(&clocksource_lock); - curr += sprintf(curr, "\n"); + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n"); - return curr - buf; + return count; } /* diff --git a/kernel/timer.c b/kernel/timer.c index 9fbb472b8cf..70b29b59343 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -818,12 +818,14 @@ unsigned long next_timer_interrupt(void) #ifndef CONFIG_VIRT_CPU_ACCOUNTING void account_process_tick(struct task_struct *p, int user_tick) { + cputime_t one_jiffy = jiffies_to_cputime(1); + if (user_tick) { - account_user_time(p, jiffies_to_cputime(1)); - account_user_time_scaled(p, jiffies_to_cputime(1)); + account_user_time(p, one_jiffy); + account_user_time_scaled(p, cputime_to_scaled(one_jiffy)); } else { - account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1)); - account_system_time_scaled(p, jiffies_to_cputime(1)); + account_system_time(p, HARDIRQ_OFFSET, one_jiffy); + account_system_time_scaled(p, cputime_to_scaled(one_jiffy)); } } #endif |