diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 4 | ||||
| -rw-r--r-- | kernel/capability.c | 113 | ||||
| -rw-r--r-- | kernel/exit.c | 3 | ||||
| -rw-r--r-- | kernel/fork.c | 20 | ||||
| -rw-r--r-- | kernel/hrtimer.c | 9 | ||||
| -rw-r--r-- | kernel/latency.c | 280 | ||||
| -rw-r--r-- | kernel/pm_qos_params.c | 425 | ||||
| -rw-r--r-- | kernel/posix-timers.c | 9 | ||||
| -rw-r--r-- | kernel/power/disk.c | 4 | ||||
| -rw-r--r-- | kernel/power/snapshot.c | 4 | ||||
| -rw-r--r-- | kernel/signal.c | 75 | ||||
| -rw-r--r-- | kernel/sys.c | 15 | ||||
| -rw-r--r-- | kernel/sys_ni.c | 7 | ||||
| -rw-r--r-- | kernel/sysctl.c | 53 | ||||
| -rw-r--r-- | kernel/sysctl_check.c | 7 |
15 files changed, 606 insertions, 422 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index db9af707ff5..135a1b94344 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 ksysfs.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 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/exit.c b/kernel/exit.c index 9e459fefda7..9d3d0f0b27d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1083,11 +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); diff --git a/kernel/fork.c b/kernel/fork.c index 05e0b6f4365..2b55b74cd99 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -325,7 +325,7 @@ 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) @@ -1118,6 +1118,7 @@ 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); @@ -1450,6 +1451,23 @@ 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) 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/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/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 36d563fd9e3..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; @@ -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/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/signal.c b/kernel/signal.c index 4333b6dbb42..6a5f97cd337 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)) { @@ -1709,9 +1687,6 @@ 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 +1694,15 @@ 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 +1730,6 @@ 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 +1744,7 @@ 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/sys.c b/kernel/sys.c index d1fe71eb454..53de35fc824 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); @@ -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..5e2ad5bf88e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -84,8 +84,11 @@ 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 +419,6 @@ 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, @@ -1150,6 +1144,19 @@ 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 @@ -2080,26 +2087,6 @@ 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 +2500,6 @@ 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) || |