diff options
Diffstat (limited to 'kernel')
36 files changed, 1277 insertions, 821 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..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 + 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 @@ -49,7 +49,6 @@ 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/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..3995297567a 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); @@ -1398,7 +1399,7 @@ 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 +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) @@ -1492,7 +1510,7 @@ 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/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/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/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 8e186c67814..ef9b802738a 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -44,9 +44,30 @@ config PM_VERBOSE ---help--- This option enables verbose messages from the Power Management code. +config CAN_PM_TRACE + def_bool y + depends on PM_DEBUG && PM_SLEEP && EXPERIMENTAL + config PM_TRACE + bool + help + This enables code to save the last PM event point across + reboot. The architecture needs to support this, x86 for + example does by saving things in the RTC, see below. + + The architecture specific code must provide the extern + functions from <linux/resume-trace.h> as well as the + <asm/resume-trace.h> header with a TRACE_RESUME() macro. + + The way the information is presented is architecture- + dependent, x86 will print the information during a + late_initcall. + +config PM_TRACE_RTC bool "Suspend/resume event tracing" - depends on PM_DEBUG && X86 && PM_SLEEP && EXPERIMENTAL + depends on CAN_PM_TRACE + depends on X86 + select PM_TRACE default n ---help--- This enables some cheesy code to save the last PM event point in the @@ -63,7 +84,8 @@ config PM_TRACE config PM_SLEEP_SMP bool - depends on SUSPEND_SMP_POSSIBLE || HIBERNATION_SMP_POSSIBLE + depends on SMP + depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE depends on PM_SLEEP select HOTPLUG_CPU default y @@ -73,46 +95,29 @@ config PM_SLEEP depends on SUSPEND || HIBERNATION default y -config SUSPEND_UP_POSSIBLE - bool - depends on (X86 && !X86_VOYAGER) || PPC || ARM || BLACKFIN || MIPS \ - || SUPERH || FRV - depends on !SMP - default y - -config SUSPEND_SMP_POSSIBLE - bool - depends on (X86 && !X86_VOYAGER) \ - || (PPC && (PPC_PSERIES || PPC_PMAC)) || ARM - depends on SMP - default y - config SUSPEND bool "Suspend to RAM and standby" - depends on PM - depends on SUSPEND_UP_POSSIBLE || SUSPEND_SMP_POSSIBLE + depends on PM && ARCH_SUSPEND_POSSIBLE default y ---help--- Allow the system to enter sleep states in which main memory is powered and thus its contents are preserved, such as the - suspend-to-RAM state (i.e. the ACPI S3 state). + suspend-to-RAM state (e.g. the ACPI S3 state). -config HIBERNATION_UP_POSSIBLE - bool - depends on X86 || PPC64_SWSUSP || PPC32 - depends on !SMP +config SUSPEND_FREEZER + bool "Enable freezer for suspend to RAM/standby" \ + if ARCH_WANTS_FREEZER_CONTROL || BROKEN + depends on SUSPEND default y + help + This allows you to turn off the freezer for suspend. If this is + done, no tasks are frozen for suspend to RAM/standby. -config HIBERNATION_SMP_POSSIBLE - bool - depends on (X86 && !X86_VOYAGER) || PPC64_SWSUSP - depends on SMP - default y + Turning OFF this setting is NOT recommended! If in doubt, say Y. config HIBERNATION bool "Hibernation (aka 'suspend to disk')" - depends on PM && SWAP - depends on HIBERNATION_UP_POSSIBLE || HIBERNATION_SMP_POSSIBLE + depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE ---help--- Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the diff --git a/kernel/power/disk.c b/kernel/power/disk.c index b138b431e27..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; @@ -54,8 +54,8 @@ static struct platform_hibernation_ops *hibernation_ops; void hibernation_set_ops(struct platform_hibernation_ops *ops) { - if (ops && !(ops->start && ops->pre_snapshot && ops->finish - && ops->prepare && ops->enter && ops->pre_restore + if (ops && !(ops->begin && ops->end && ops->pre_snapshot + && ops->prepare && ops->finish && ops->enter && ops->pre_restore && ops->restore_cleanup)) { WARN_ON(1); return; @@ -70,15 +70,55 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops) mutex_unlock(&pm_mutex); } +#ifdef CONFIG_PM_DEBUG +static void hibernation_debug_sleep(void) +{ + printk(KERN_INFO "hibernation debug: Waiting for 5 seconds.\n"); + mdelay(5000); +} + +static int hibernation_testmode(int mode) +{ + if (hibernation_mode == mode) { + hibernation_debug_sleep(); + return 1; + } + return 0; +} + +static int hibernation_test(int level) +{ + if (pm_test_level == level) { + hibernation_debug_sleep(); + return 1; + } + return 0; +} +#else /* !CONFIG_PM_DEBUG */ +static int hibernation_testmode(int mode) { return 0; } +static int hibernation_test(int level) { return 0; } +#endif /* !CONFIG_PM_DEBUG */ + /** - * platform_start - tell the platform driver that we're starting + * platform_begin - tell the platform driver that we're starting * hibernation */ -static int platform_start(int platform_mode) +static int platform_begin(int platform_mode) { return (platform_mode && hibernation_ops) ? - hibernation_ops->start() : 0; + hibernation_ops->begin() : 0; +} + +/** + * platform_end - tell the platform driver that we've entered the + * working state + */ + +static void platform_end(int platform_mode) +{ + if (platform_mode && hibernation_ops) + hibernation_ops->end(); } /** @@ -145,7 +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; @@ -162,19 +202,25 @@ int create_image(int platform_mode) */ error = device_power_down(PMSG_FREEZE); if (error) { - printk(KERN_ERR "Some devices failed to power down, " - KERN_ERR "aborting suspend\n"); + printk(KERN_ERR "PM: Some devices failed to power down, " + "aborting hibernation\n"); goto Enable_irqs; } + if (hibernation_test(TEST_CORE)) + goto Power_up; + + in_suspend = 1; save_processor_state(); error = swsusp_arch_suspend(); if (error) - printk(KERN_ERR "Error %d while creating the image\n", error); + printk(KERN_ERR "PM: Error %d creating hibernation image\n", + error); /* Restore control flow magically appears here */ restore_processor_state(); if (!in_suspend) platform_leave(platform_mode); + Power_up: /* NOTE: device_power_up() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ @@ -202,36 +248,90 @@ int hibernation_snapshot(int platform_mode) if (error) return error; - error = platform_start(platform_mode); + error = platform_begin(platform_mode); if (error) - return error; + goto Close; suspend_console(); error = device_suspend(PMSG_FREEZE); if (error) goto Resume_console; - error = platform_pre_snapshot(platform_mode); - if (error) + if (hibernation_test(TEST_DEVICES)) goto Resume_devices; + error = platform_pre_snapshot(platform_mode); + if (error || hibernation_test(TEST_PLATFORM)) + goto Finish; + error = disable_nonboot_cpus(); if (!error) { - if (hibernation_mode != HIBERNATION_TEST) { - in_suspend = 1; - error = create_image(platform_mode); - /* Control returns here after successful restore */ - } else { - printk("swsusp debug: Waiting for 5 seconds.\n"); - mdelay(5000); - } + if (hibernation_test(TEST_CPUS)) + goto Enable_cpus; + + if (hibernation_testmode(HIBERNATION_TEST)) + goto Enable_cpus; + + error = create_image(platform_mode); + /* Control returns here after successful restore */ } + Enable_cpus: enable_nonboot_cpus(); - Resume_devices: + Finish: platform_finish(platform_mode); + Resume_devices: device_resume(); Resume_console: resume_console(); + Close: + platform_end(platform_mode); + return error; +} + +/** + * resume_target_kernel - prepare devices that need to be suspended with + * interrupts off, restore the contents of highmem that have not been + * restored yet from the image and run the low level code that will restore + * the remaining contents of memory and switch to the just restored target + * kernel. + */ + +static int resume_target_kernel(void) +{ + int error; + + local_irq_disable(); + error = device_power_down(PMSG_PRETHAW); + if (error) { + printk(KERN_ERR "PM: Some devices failed to power down, " + "aborting resume\n"); + goto Enable_irqs; + } + /* We'll ignore saved state, but this gets preempt count (etc) right */ + save_processor_state(); + error = restore_highmem(); + if (!error) { + error = swsusp_arch_resume(); + /* + * The code below is only ever reached in case of a failure. + * Otherwise execution continues at place where + * swsusp_arch_suspend() was called + */ + BUG_ON(!error); + /* This call to restore_highmem() undos the previous one */ + restore_highmem(); + } + /* + * The only reason why swsusp_arch_resume() can fail is memory being + * very tight, so we have to free it as soon as we can to avoid + * subsequent failures + */ + swsusp_free(); + restore_processor_state(); + touch_softlockup_watchdog(); + device_power_up(); + Enable_irqs: + local_irq_enable(); return error; } @@ -258,7 +358,7 @@ int hibernation_restore(int platform_mode) if (!error) { error = disable_nonboot_cpus(); if (!error) - error = swsusp_resume(); + error = resume_target_kernel(); enable_nonboot_cpus(); } platform_restore_cleanup(platform_mode); @@ -286,9 +386,9 @@ int hibernation_platform_enter(void) * hibernation_ops->finish() before saving the image, so we should let * the firmware know that we're going to enter the sleep state after all */ - error = hibernation_ops->start(); + error = hibernation_ops->begin(); if (error) - return error; + goto Close; suspend_console(); error = device_suspend(PMSG_SUSPEND); @@ -322,6 +422,8 @@ int hibernation_platform_enter(void) device_resume(); Resume_console: resume_console(); + Close: + hibernation_ops->end(); return error; } @@ -352,24 +454,17 @@ static void power_down(void) * Valid image is on the disk, if we continue we risk serious data * corruption after resume. */ - printk(KERN_CRIT "Please power me down manually\n"); + printk(KERN_CRIT "PM: Please power down manually\n"); while(1); } -static void unprepare_processes(void) -{ - thaw_processes(); - pm_restore_console(); -} - static int prepare_processes(void) { int error = 0; - pm_prepare_console(); if (freeze_processes()) { error = -EBUSY; - unprepare_processes(); + thaw_processes(); } return error; } @@ -389,6 +484,7 @@ int hibernate(void) goto Unlock; } + pm_prepare_console(); error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); if (error) goto Exit; @@ -398,7 +494,7 @@ int hibernate(void) if (error) goto Exit; - printk("Syncing filesystems ... "); + printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); printk("done.\n"); @@ -406,11 +502,12 @@ int hibernate(void) if (error) goto Finish; - if (hibernation_mode == HIBERNATION_TESTPROC) { - printk("swsusp debug: Waiting for 5 seconds.\n"); - mdelay(5000); + if (hibernation_test(TEST_FREEZER)) goto Thaw; - } + + if (hibernation_testmode(HIBERNATION_TESTPROC)) + goto Thaw; + error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM); if (in_suspend && !error) { unsigned int flags = 0; @@ -427,11 +524,12 @@ int hibernate(void) swsusp_free(); } Thaw: - unprepare_processes(); + thaw_processes(); Finish: free_basic_memory_bitmaps(); Exit: pm_notifier_call_chain(PM_POST_HIBERNATION); + pm_restore_console(); atomic_inc(&snapshot_device_available); Unlock: mutex_unlock(&pm_mutex); @@ -473,22 +571,23 @@ static int software_resume(void) return -ENOENT; } swsusp_resume_device = name_to_dev_t(resume_file); - pr_debug("swsusp: Resume From Partition %s\n", resume_file); + pr_debug("PM: Resume from partition %s\n", resume_file); } else { - pr_debug("swsusp: Resume From Partition %d:%d\n", - MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); + pr_debug("PM: Resume from partition %d:%d\n", + MAJOR(swsusp_resume_device), + MINOR(swsusp_resume_device)); } if (noresume) { /** - * FIXME: If noresume is specified, we need to find the partition - * and reset it back to normal swap space. + * FIXME: If noresume is specified, we need to find the + * partition and reset it back to normal swap space. */ mutex_unlock(&pm_mutex); return 0; } - pr_debug("PM: Checking swsusp image.\n"); + pr_debug("PM: Checking hibernation image.\n"); error = swsusp_check(); if (error) goto Unlock; @@ -499,6 +598,11 @@ static int software_resume(void) goto Unlock; } + pm_prepare_console(); + error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + if (error) + goto Finish; + error = create_basic_memory_bitmaps(); if (error) goto Finish; @@ -510,7 +614,7 @@ static int software_resume(void) goto Done; } - pr_debug("PM: Reading swsusp image.\n"); + pr_debug("PM: Reading hibernation image.\n"); error = swsusp_read(&flags); if (!error) @@ -518,10 +622,12 @@ static int software_resume(void) printk(KERN_ERR "PM: Restore failed, recovering.\n"); swsusp_free(); - unprepare_processes(); + thaw_processes(); Done: free_basic_memory_bitmaps(); Finish: + pm_notifier_call_chain(PM_POST_RESTORE); + pm_restore_console(); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ Unlock: @@ -636,7 +742,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, error = -EINVAL; if (!error) - pr_debug("PM: suspend-to-disk mode set to '%s'\n", + pr_debug("PM: Hibernation mode set to '%s'\n", hibernation_modes[mode]); mutex_unlock(&pm_mutex); return error ? error : n; @@ -668,7 +774,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, mutex_lock(&pm_mutex); swsusp_resume_device = res; mutex_unlock(&pm_mutex); - printk("Attempting manual resume\n"); + printk(KERN_INFO "PM: Starting manual resume from disk\n"); noresume = 0; software_resume(); ret = n; diff --git a/kernel/power/main.c b/kernel/power/main.c index efc08360e62..6a6d5eb3524 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -24,13 +24,112 @@ #include "power.h" -BLOCKING_NOTIFIER_HEAD(pm_chain_head); - DEFINE_MUTEX(pm_mutex); unsigned int pm_flags; EXPORT_SYMBOL(pm_flags); +#ifdef CONFIG_PM_SLEEP + +/* Routines for PM-transition notifications */ + +static BLOCKING_NOTIFIER_HEAD(pm_chain_head); + +int register_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&pm_chain_head, nb); +} +EXPORT_SYMBOL_GPL(register_pm_notifier); + +int unregister_pm_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&pm_chain_head, nb); +} +EXPORT_SYMBOL_GPL(unregister_pm_notifier); + +int pm_notifier_call_chain(unsigned long val) +{ + return (blocking_notifier_call_chain(&pm_chain_head, val, NULL) + == NOTIFY_BAD) ? -EINVAL : 0; +} + +#ifdef CONFIG_PM_DEBUG +int pm_test_level = TEST_NONE; + +static int suspend_test(int level) +{ + if (pm_test_level == level) { + printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); + mdelay(5000); + return 1; + } + return 0; +} + +static const char * const pm_tests[__TEST_AFTER_LAST] = { + [TEST_NONE] = "none", + [TEST_CORE] = "core", + [TEST_CPUS] = "processors", + [TEST_PLATFORM] = "platform", + [TEST_DEVICES] = "devices", + [TEST_FREEZER] = "freezer", +}; + +static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + char *s = buf; + int level; + + for (level = TEST_FIRST; level <= TEST_MAX; level++) + if (pm_tests[level]) { + if (level == pm_test_level) + s += sprintf(s, "[%s] ", pm_tests[level]); + else + s += sprintf(s, "%s ", pm_tests[level]); + } + + if (s != buf) + /* convert the last space to a newline */ + *(s-1) = '\n'; + + return (s - buf); +} + +static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + const char * const *s; + int level; + char *p; + int len; + int error = -EINVAL; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + mutex_lock(&pm_mutex); + + level = TEST_FIRST; + for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++) + if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) { + pm_test_level = level; + error = 0; + break; + } + + mutex_unlock(&pm_mutex); + + return error ? error : n; +} + +power_attr(pm_test); +#else /* !CONFIG_PM_DEBUG */ +static inline int suspend_test(int level) { return 0; } +#endif /* !CONFIG_PM_DEBUG */ + +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_SUSPEND /* This is just an arbitrary number */ @@ -76,13 +175,13 @@ static int suspend_prepare(void) if (!suspend_ops || !suspend_ops->enter) return -EPERM; + pm_prepare_console(); + error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); if (error) goto Finish; - pm_prepare_console(); - - if (freeze_processes()) { + if (suspend_freeze_processes()) { error = -EAGAIN; goto Thaw; } @@ -100,10 +199,10 @@ static int suspend_prepare(void) return 0; Thaw: - thaw_processes(); - pm_restore_console(); + suspend_thaw_processes(); Finish: pm_notifier_call_chain(PM_POST_SUSPEND); + pm_restore_console(); return error; } @@ -133,10 +232,13 @@ static int suspend_enter(suspend_state_t state) BUG_ON(!irqs_disabled()); if ((error = device_power_down(PMSG_SUSPEND))) { - printk(KERN_ERR "Some devices failed to power down\n"); + printk(KERN_ERR "PM: Some devices failed to power down\n"); goto Done; } - error = suspend_ops->enter(state); + + if (!suspend_test(TEST_CORE)) + error = suspend_ops->enter(state); + device_power_up(); Done: arch_suspend_enable_irqs(); @@ -145,8 +247,8 @@ static int suspend_enter(suspend_state_t state) } /** - * suspend_devices_and_enter - suspend devices and enter the desired system sleep - * state. + * suspend_devices_and_enter - suspend devices and enter the desired system + * sleep state. * @state: state to enter */ int suspend_devices_and_enter(suspend_state_t state) @@ -156,33 +258,45 @@ int suspend_devices_and_enter(suspend_state_t state) if (!suspend_ops) return -ENOSYS; - if (suspend_ops->set_target) { - error = suspend_ops->set_target(state); + if (suspend_ops->begin) { + error = suspend_ops->begin(state); if (error) - return error; + goto Close; } suspend_console(); error = device_suspend(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "Some devices failed to suspend\n"); + printk(KERN_ERR "PM: Some devices failed to suspend\n"); goto Resume_console; } + + if (suspend_test(TEST_DEVICES)) + goto Resume_devices; + if (suspend_ops->prepare) { error = suspend_ops->prepare(); if (error) goto Resume_devices; } + + if (suspend_test(TEST_PLATFORM)) + goto Finish; + error = disable_nonboot_cpus(); - if (!error) + if (!error && !suspend_test(TEST_CPUS)) suspend_enter(state); enable_nonboot_cpus(); + Finish: if (suspend_ops->finish) suspend_ops->finish(); Resume_devices: device_resume(); Resume_console: resume_console(); + Close: + if (suspend_ops->end) + suspend_ops->end(); return error; } @@ -194,9 +308,9 @@ int suspend_devices_and_enter(suspend_state_t state) */ static void suspend_finish(void) { - thaw_processes(); - pm_restore_console(); + suspend_thaw_processes(); pm_notifier_call_chain(PM_POST_SUSPEND); + pm_restore_console(); } @@ -238,17 +352,22 @@ static int enter_state(suspend_state_t state) if (!mutex_trylock(&pm_mutex)) return -EBUSY; - printk("Syncing filesystems ... "); + printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); printk("done.\n"); pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]); - if ((error = suspend_prepare())) + error = suspend_prepare(); + if (error) goto Unlock; + if (suspend_test(TEST_FREEZER)) + goto Finish; + pr_debug("PM: Entering %s sleep\n", pm_states[state]); error = suspend_devices_and_enter(state); + Finish: pr_debug("PM: Finishing wakeup.\n"); suspend_finish(); Unlock: @@ -369,18 +488,18 @@ pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr, } power_attr(pm_trace); +#endif /* CONFIG_PM_TRACE */ static struct attribute * g[] = { &state_attr.attr, +#ifdef CONFIG_PM_TRACE &pm_trace_attr.attr, +#endif +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_PM_DEBUG) + &pm_test_attr.attr, +#endif NULL, }; -#else -static struct attribute * g[] = { - &state_attr.attr, - NULL, -}; -#endif /* CONFIG_PM_TRACE */ static struct attribute_group attr_group = { .attrs = g, diff --git a/kernel/power/power.h b/kernel/power/power.h index 2093c3a9a99..700f44ec840 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -1,5 +1,7 @@ #include <linux/suspend.h> +#include <linux/suspend_ioctls.h> #include <linux/utsname.h> +#include <linux/freezer.h> struct swsusp_info { struct new_utsname uts; @@ -128,42 +130,12 @@ struct snapshot_handle { #define data_of(handle) ((handle).buffer + (handle).buf_offset) extern unsigned int snapshot_additional_pages(struct zone *zone); +extern unsigned long snapshot_get_image_size(void); extern int snapshot_read_next(struct snapshot_handle *handle, size_t count); extern int snapshot_write_next(struct snapshot_handle *handle, size_t count); extern void snapshot_write_finalize(struct snapshot_handle *handle); extern int snapshot_image_loaded(struct snapshot_handle *handle); -/* - * This structure is used to pass the values needed for the identification - * of the resume swap area from a user space to the kernel via the - * SNAPSHOT_SET_SWAP_AREA ioctl - */ -struct resume_swap_area { - loff_t offset; - u_int32_t dev; -} __attribute__((packed)); - -#define SNAPSHOT_IOC_MAGIC '3' -#define SNAPSHOT_FREEZE _IO(SNAPSHOT_IOC_MAGIC, 1) -#define SNAPSHOT_UNFREEZE _IO(SNAPSHOT_IOC_MAGIC, 2) -#define SNAPSHOT_ATOMIC_SNAPSHOT _IOW(SNAPSHOT_IOC_MAGIC, 3, void *) -#define SNAPSHOT_ATOMIC_RESTORE _IO(SNAPSHOT_IOC_MAGIC, 4) -#define SNAPSHOT_FREE _IO(SNAPSHOT_IOC_MAGIC, 5) -#define SNAPSHOT_SET_IMAGE_SIZE _IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long) -#define SNAPSHOT_AVAIL_SWAP _IOR(SNAPSHOT_IOC_MAGIC, 7, void *) -#define SNAPSHOT_GET_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 8, void *) -#define SNAPSHOT_FREE_SWAP_PAGES _IO(SNAPSHOT_IOC_MAGIC, 9) -#define SNAPSHOT_SET_SWAP_FILE _IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int) -#define SNAPSHOT_S2RAM _IO(SNAPSHOT_IOC_MAGIC, 11) -#define SNAPSHOT_PMOPS _IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int) -#define SNAPSHOT_SET_SWAP_AREA _IOW(SNAPSHOT_IOC_MAGIC, 13, \ - struct resume_swap_area) -#define SNAPSHOT_IOC_MAXNR 13 - -#define PMOPS_PREPARE 1 -#define PMOPS_ENTER 2 -#define PMOPS_FINISH 3 - /* If unset, the snapshot device cannot be open. */ extern atomic_t snapshot_device_available; @@ -181,7 +153,6 @@ extern int swsusp_swap_in_use(void); extern int swsusp_check(void); extern int swsusp_shrink_memory(void); extern void swsusp_free(void); -extern int swsusp_resume(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); extern void swsusp_close(void); @@ -201,11 +172,56 @@ static inline int suspend_devices_and_enter(suspend_state_t state) } #endif /* !CONFIG_SUSPEND */ -/* kernel/power/common.c */ -extern struct blocking_notifier_head pm_chain_head; +#ifdef CONFIG_PM_SLEEP +/* kernel/power/main.c */ +extern int pm_notifier_call_chain(unsigned long val); +#endif + +#ifdef CONFIG_HIGHMEM +unsigned int count_highmem_pages(void); +int restore_highmem(void); +#else +static inline unsigned int count_highmem_pages(void) { return 0; } +static inline int restore_highmem(void) { return 0; } +#endif + +/* + * Suspend test levels + */ +enum { + /* keep first */ + TEST_NONE, + TEST_CORE, + TEST_CPUS, + TEST_PLATFORM, + TEST_DEVICES, + TEST_FREEZER, + /* keep last */ + __TEST_AFTER_LAST +}; + +#define TEST_FIRST TEST_NONE +#define TEST_MAX (__TEST_AFTER_LAST - 1) + +extern int pm_test_level; + +#ifdef CONFIG_SUSPEND_FREEZER +static inline int suspend_freeze_processes(void) +{ + return freeze_processes(); +} -static inline int pm_notifier_call_chain(unsigned long val) +static inline void suspend_thaw_processes(void) { - return (blocking_notifier_call_chain(&pm_chain_head, val, NULL) - == NOTIFY_BAD) ? -EINVAL : 0; + thaw_processes(); } +#else +static inline int suspend_freeze_processes(void) +{ + return 0; +} + +static inline void suspend_thaw_processes(void) +{ +} +#endif diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 78039b477d2..95250d7c8d9 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -635,7 +635,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); Report: - printk("swsusp: Registered nosave memory region: %016lx - %016lx\n", + printk(KERN_INFO "PM: Registered nosave memory: %016lx - %016lx\n", start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT); } @@ -704,7 +704,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm) list_for_each_entry(region, &nosave_regions, list) { unsigned long pfn; - printk("swsusp: Marking nosave pages: %016lx - %016lx\n", + pr_debug("PM: Marking nosave pages: %016lx - %016lx\n", region->start_pfn << PAGE_SHIFT, region->end_pfn << PAGE_SHIFT); @@ -749,7 +749,7 @@ int create_basic_memory_bitmaps(void) free_pages_map = bm2; mark_nosave_pages(forbidden_pages_map); - printk("swsusp: Basic memory bitmaps created\n"); + pr_debug("PM: Basic memory bitmaps created\n"); return 0; @@ -784,7 +784,7 @@ void free_basic_memory_bitmaps(void) memory_bm_free(bm2, PG_UNSAFE_CLEAR); kfree(bm2); - printk("swsusp: Basic memory bitmaps freed\n"); + pr_debug("PM: Basic memory bitmaps freed\n"); } /** @@ -872,7 +872,6 @@ unsigned int count_highmem_pages(void) } #else static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } -static inline unsigned int count_highmem_pages(void) { return 0; } #endif /* CONFIG_HIGHMEM */ /** @@ -1089,7 +1088,7 @@ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) } nr_pages += count_pages_for_highmem(nr_highmem); - pr_debug("swsusp: Normal pages needed: %u + %u + %u, available pages: %u\n", + pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n", nr_pages, PAGES_FOR_IO, meta, free); return free > nr_pages + PAGES_FOR_IO + meta; @@ -1202,27 +1201,27 @@ asmlinkage int swsusp_save(void) { unsigned int nr_pages, nr_highmem; - printk("swsusp: critical section: \n"); + 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("swsusp: Need to copy %u pages\n", nr_pages + nr_highmem); + printk(KERN_INFO "PM: Need to copy %u pages\n", nr_pages + nr_highmem); if (!enough_free_mem(nr_pages, nr_highmem)) { - printk(KERN_ERR "swsusp: Not enough free memory\n"); + printk(KERN_ERR "PM: Not enough free memory\n"); return -ENOMEM; } if (swsusp_alloc(&orig_bm, ©_bm, nr_pages, nr_highmem)) { - printk(KERN_ERR "swsusp: Memory allocation failed\n"); + printk(KERN_ERR "PM: Memory allocation failed\n"); return -ENOMEM; } /* 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); /* @@ -1235,7 +1234,8 @@ asmlinkage int swsusp_save(void) nr_copy_pages = nr_pages; nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); - printk("swsusp: critical section: done (%d pages copied)\n", nr_pages); + printk(KERN_INFO "PM: Hibernation image created (%d pages copied)\n", + nr_pages); return 0; } @@ -1264,12 +1264,17 @@ static char *check_image_kernel(struct swsusp_info *info) } #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ +unsigned long snapshot_get_image_size(void) +{ + return nr_copy_pages + nr_meta_pages + 1; +} + static int init_header(struct swsusp_info *info) { memset(info, 0, sizeof(struct swsusp_info)); info->num_physpages = num_physpages; info->image_pages = nr_copy_pages; - info->pages = nr_copy_pages + nr_meta_pages + 1; + info->pages = snapshot_get_image_size(); info->size = info->pages; info->size <<= PAGE_SHIFT; return init_header_complete(info); @@ -1429,7 +1434,7 @@ static int check_header(struct swsusp_info *info) if (!reason && info->num_physpages != num_physpages) reason = "memory size"; if (reason) { - printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason); + printk(KERN_ERR "PM: Image mismatch: %s\n", reason); return -EPERM; } return 0; diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 917aba10057..a0abf9a463f 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -28,8 +28,6 @@ #include "power.h" -extern char resume_file[]; - #define SWSUSP_SIG "S1SUSPEND" struct swsusp_header { @@ -73,7 +71,8 @@ static int submit(int rw, pgoff_t page_off, struct page *page, bio->bi_end_io = end_swap_bio_read; if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { - printk("swsusp: ERROR: adding page to bio at %ld\n", page_off); + printk(KERN_ERR "PM: Adding page to bio failed at %ld\n", + page_off); bio_put(bio); return -EFAULT; } @@ -153,7 +152,7 @@ static int mark_swapfiles(sector_t start, unsigned int flags) error = bio_write_page(swsusp_resume_block, swsusp_header, NULL); } else { - printk(KERN_ERR "swsusp: Swap header not found!\n"); + printk(KERN_ERR "PM: Swap header not found!\n"); error = -ENODEV; } return error; @@ -325,7 +324,8 @@ static int save_image(struct swap_map_handle *handle, struct timeval start; struct timeval stop; - printk("Saving image data pages (%u pages) ... ", nr_to_write); + printk(KERN_INFO "PM: Saving image data pages (%u pages) ... ", + nr_to_write); m = nr_to_write / 100; if (!m) m = 1; @@ -365,7 +365,7 @@ static int enough_swap(unsigned int nr_pages) { unsigned int free_swap = count_swap_pages(root_swap, 1); - pr_debug("swsusp: free swap pages: %u\n", free_swap); + pr_debug("PM: Free swap pages: %u\n", free_swap); return free_swap > nr_pages + PAGES_FOR_IO; } @@ -388,7 +388,7 @@ int swsusp_write(unsigned int flags) error = swsusp_swap_check(); if (error) { - printk(KERN_ERR "swsusp: Cannot find swap device, try " + printk(KERN_ERR "PM: Cannot find swap device, try " "swapon -a.\n"); return error; } @@ -402,7 +402,7 @@ int swsusp_write(unsigned int flags) } header = (struct swsusp_info *)data_of(snapshot); if (!enough_swap(header->pages)) { - printk(KERN_ERR "swsusp: Not enough free swap\n"); + printk(KERN_ERR "PM: Not enough free swap\n"); error = -ENOSPC; goto out; } @@ -417,7 +417,7 @@ int swsusp_write(unsigned int flags) if (!error) { flush_swap_writer(&handle); - printk("S"); + printk(KERN_INFO "PM: S"); error = mark_swapfiles(start, flags); printk("|\n"); } @@ -507,7 +507,8 @@ static int load_image(struct swap_map_handle *handle, int err2; unsigned nr_pages; - printk("Loading image data pages (%u pages) ... ", nr_to_read); + printk(KERN_INFO "PM: Loading image data pages (%u pages) ... ", + nr_to_read); m = nr_to_read / 100; if (!m) m = 1; @@ -558,7 +559,7 @@ int swsusp_read(unsigned int *flags_p) *flags_p = swsusp_header->flags; if (IS_ERR(resume_bdev)) { - pr_debug("swsusp: block device not initialised\n"); + pr_debug("PM: Image device not initialised\n"); return PTR_ERR(resume_bdev); } @@ -577,9 +578,9 @@ int swsusp_read(unsigned int *flags_p) blkdev_put(resume_bdev); if (!error) - pr_debug("swsusp: Reading resume file was successful\n"); + pr_debug("PM: Image successfully loaded\n"); else - pr_debug("swsusp: Error %d resuming\n", error); + pr_debug("PM: Error %d resuming\n", error); return error; } @@ -611,13 +612,13 @@ int swsusp_check(void) if (error) blkdev_put(resume_bdev); else - pr_debug("swsusp: Signature found, resuming\n"); + pr_debug("PM: Signature found, resuming\n"); } else { error = PTR_ERR(resume_bdev); } if (error) - pr_debug("swsusp: Error %d check for resume file\n", error); + pr_debug("PM: Error %d checking image file\n", error); return error; } @@ -629,7 +630,7 @@ int swsusp_check(void) void swsusp_close(void) { if (IS_ERR(resume_bdev)) { - pr_debug("swsusp: block device not initialised\n"); + pr_debug("PM: Image device not initialised\n"); return; } diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index e1722d3155f..023ff2a31d8 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -64,14 +64,6 @@ unsigned long image_size = 500 * 1024 * 1024; int in_suspend __nosavedata = 0; -#ifdef CONFIG_HIGHMEM -unsigned int count_highmem_pages(void); -int restore_highmem(void); -#else -static inline int restore_highmem(void) { return 0; } -static inline unsigned int count_highmem_pages(void) { return 0; } -#endif - /** * The following functions are used for tracing the allocated * swap pages, so that they can be freed in case of an error. @@ -196,7 +188,8 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop, centisecs = 1; /* avoid div-by-zero */ k = nr_pages * (PAGE_SIZE / 1024); kps = (k * 100) / centisecs; - printk("%s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", msg, k, + printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", + msg, k, centisecs / 100, centisecs % 100, kps / 1000, (kps % 1000) / 10); } @@ -227,7 +220,7 @@ int swsusp_shrink_memory(void) char *p = "-\\|/"; struct timeval start, stop; - printk("Shrinking memory... "); + printk(KERN_INFO "PM: Shrinking memory... "); do_gettimeofday(&start); do { long size, highmem_size; @@ -269,38 +262,3 @@ int swsusp_shrink_memory(void) return 0; } - -int swsusp_resume(void) -{ - int error; - - local_irq_disable(); - /* NOTE: device_power_down() is just a suspend() with irqs off; - * it has no special "power things down" semantics - */ - if (device_power_down(PMSG_PRETHAW)) - printk(KERN_ERR "Some devices failed to power down, very bad\n"); - /* We'll ignore saved state, but this gets preempt count (etc) right */ - save_processor_state(); - error = restore_highmem(); - if (!error) { - error = swsusp_arch_resume(); - /* The code below is only ever reached in case of a failure. - * Otherwise execution continues at place where - * swsusp_arch_suspend() was called - */ - BUG_ON(!error); - /* This call to restore_highmem() undos the previous one */ - restore_highmem(); - } - /* The only reason why swsusp_arch_resume() can fail is memory being - * very tight, so we have to free it as soon as we can to avoid - * subsequent failures - */ - swsusp_free(); - restore_processor_state(); - touch_softlockup_watchdog(); - device_power_up(); - local_irq_enable(); - return error; -} diff --git a/kernel/power/user.c b/kernel/power/user.c index 5bd321bcbb7..f5512cb3aa8 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -28,6 +28,29 @@ #include "power.h" +/* + * NOTE: The SNAPSHOT_SET_SWAP_FILE and SNAPSHOT_PMOPS ioctls are obsolete and + * will be removed in the future. They are only preserved here for + * compatibility with existing userland utilities. + */ +#define SNAPSHOT_SET_SWAP_FILE _IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int) +#define SNAPSHOT_PMOPS _IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int) + +#define PMOPS_PREPARE 1 +#define PMOPS_ENTER 2 +#define PMOPS_FINISH 3 + +/* + * NOTE: The following ioctl definitions are wrong and have been replaced with + * correct ones. They are only preserved here for compatibility with existing + * userland utilities and will be removed in the future. + */ +#define SNAPSHOT_ATOMIC_SNAPSHOT _IOW(SNAPSHOT_IOC_MAGIC, 3, void *) +#define SNAPSHOT_SET_IMAGE_SIZE _IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long) +#define SNAPSHOT_AVAIL_SWAP _IOR(SNAPSHOT_IOC_MAGIC, 7, void *) +#define SNAPSHOT_GET_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 8, void *) + + #define SNAPSHOT_MINOR 231 static struct snapshot_data { @@ -36,7 +59,7 @@ static struct snapshot_data { int mode; char frozen; char ready; - char platform_suspend; + char platform_support; } snapshot_state; atomic_t snapshot_device_available = ATOMIC_INIT(1); @@ -44,6 +67,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1); static int snapshot_open(struct inode *inode, struct file *filp) { struct snapshot_data *data; + int error; if (!atomic_add_unless(&snapshot_device_available, -1, 0)) return -EBUSY; @@ -64,13 +88,23 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = swsusp_resume_device ? swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; + error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + if (error) + pm_notifier_call_chain(PM_POST_RESTORE); } else { data->swap = -1; data->mode = O_WRONLY; + error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + if (error) + pm_notifier_call_chain(PM_POST_HIBERNATION); + } + if (error) { + atomic_inc(&snapshot_device_available); + return error; } data->frozen = 0; data->ready = 0; - data->platform_suspend = 0; + data->platform_support = 0; return 0; } @@ -88,6 +122,8 @@ static int snapshot_release(struct inode *inode, struct file *filp) thaw_processes(); mutex_unlock(&pm_mutex); } + pm_notifier_call_chain(data->mode == O_WRONLY ? + PM_POST_HIBERNATION : PM_POST_RESTORE); atomic_inc(&snapshot_device_available); return 0; } @@ -133,7 +169,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, { int error = 0; struct snapshot_data *data; - loff_t avail; + loff_t size; sector_t offset; if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) @@ -151,18 +187,13 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, if (data->frozen) break; mutex_lock(&pm_mutex); - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); - if (!error) { - printk("Syncing filesystems ... "); - sys_sync(); - printk("done.\n"); - - error = freeze_processes(); - if (error) - thaw_processes(); - } + printk("Syncing filesystems ... "); + sys_sync(); + printk("done.\n"); + + error = freeze_processes(); if (error) - pm_notifier_call_chain(PM_POST_HIBERNATION); + thaw_processes(); mutex_unlock(&pm_mutex); if (!error) data->frozen = 1; @@ -173,19 +204,19 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, break; mutex_lock(&pm_mutex); thaw_processes(); - pm_notifier_call_chain(PM_POST_HIBERNATION); mutex_unlock(&pm_mutex); data->frozen = 0; break; + case SNAPSHOT_CREATE_IMAGE: case SNAPSHOT_ATOMIC_SNAPSHOT: if (data->mode != O_RDONLY || !data->frozen || data->ready) { error = -EPERM; break; } - error = hibernation_snapshot(data->platform_suspend); + error = hibernation_snapshot(data->platform_support); if (!error) - error = put_user(in_suspend, (unsigned int __user *)arg); + error = put_user(in_suspend, (int __user *)arg); if (!error) data->ready = 1; break; @@ -197,7 +228,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, error = -EPERM; break; } - error = hibernation_restore(data->platform_suspend); + error = hibernation_restore(data->platform_support); break; case SNAPSHOT_FREE: @@ -206,16 +237,29 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, data->ready = 0; break; + case SNAPSHOT_PREF_IMAGE_SIZE: case SNAPSHOT_SET_IMAGE_SIZE: image_size = arg; break; + case SNAPSHOT_GET_IMAGE_SIZE: + if (!data->ready) { + error = -ENODATA; + break; + } + size = snapshot_get_image_size(); + size <<= PAGE_SHIFT; + error = put_user(size, (loff_t __user *)arg); + break; + + case SNAPSHOT_AVAIL_SWAP_SIZE: case SNAPSHOT_AVAIL_SWAP: - avail = count_swap_pages(data->swap, 1); - avail <<= PAGE_SHIFT; - error = put_user(avail, (loff_t __user *)arg); + size = count_swap_pages(data->swap, 1); + size <<= PAGE_SHIFT; + error = put_user(size, (loff_t __user *)arg); break; + case SNAPSHOT_ALLOC_SWAP_PAGE: case SNAPSHOT_GET_SWAP_PAGE: if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { error = -ENODEV; @@ -224,7 +268,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, offset = alloc_swapdev_block(data->swap); if (offset) { offset <<= PAGE_SHIFT; - error = put_user(offset, (sector_t __user *)arg); + error = put_user(offset, (loff_t __user *)arg); } else { error = -ENOSPC; } @@ -238,7 +282,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, free_all_swap_pages(data->swap); break; - case SNAPSHOT_SET_SWAP_FILE: + case SNAPSHOT_SET_SWAP_FILE: /* This ioctl is deprecated */ if (!swsusp_swap_in_use()) { /* * User space encodes device types as two-byte values, @@ -275,26 +319,33 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, mutex_unlock(&pm_mutex); break; - case SNAPSHOT_PMOPS: + case SNAPSHOT_PLATFORM_SUPPORT: + data->platform_support = !!arg; + break; + + case SNAPSHOT_POWER_OFF: + if (data->platform_support) + error = hibernation_platform_enter(); + break; + + case SNAPSHOT_PMOPS: /* This ioctl is deprecated */ error = -EINVAL; switch (arg) { case PMOPS_PREPARE: - data->platform_suspend = 1; + data->platform_support = 1; error = 0; break; case PMOPS_ENTER: - if (data->platform_suspend) + if (data->platform_support) error = hibernation_platform_enter(); - break; case PMOPS_FINISH: - if (data->platform_suspend) + if (data->platform_support) error = 0; - break; default: 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/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/softlockup.c b/kernel/softlockup.c index c1d76552446..7c2da88db4e 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -101,6 +101,10 @@ void softlockup_tick(void) now = get_timestamp(this_cpu); + /* Wake up the high-prio watchdog task every second: */ + if (now > (touch_timestamp + 1)) + wake_up_process(per_cpu(watchdog_task, this_cpu)); + /* Warn about unreasonable delays: */ if (now <= (touch_timestamp + softlockup_thresh)) return; @@ -191,11 +195,11 @@ static void check_hung_uninterruptible_tasks(int this_cpu) read_lock(&tasklist_lock); do_each_thread(g, t) { if (!--max_count) - break; + goto unlock; if (t->state & TASK_UNINTERRUPTIBLE) check_hung_task(t, now); } while_each_thread(g, t); - + unlock: read_unlock(&tasklist_lock); } @@ -218,14 +222,19 @@ static int watchdog(void *__bind_cpu) * debug-printout triggers in softlockup_tick(). */ while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); touch_softlockup_watchdog(); - msleep_interruptible(10000); + schedule(); + + if (kthread_should_stop()) + break; if (this_cpu != check_cpu) continue; if (sysctl_hung_task_timeout_secs) check_hung_uninterruptible_tasks(this_cpu); + } return 0; @@ -259,13 +268,6 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!per_cpu(watchdog_task, hotcpu)) - break; - /* Unbind so it can run. Fall thru. */ - kthread_bind(per_cpu(watchdog_task, hotcpu), - any_online_cpu(cpu_online_map)); case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: if (hotcpu == check_cpu) { @@ -275,6 +277,14 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) check_cpu = any_online_cpu(temp_cpu_online_map); } break; + + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + if (!per_cpu(watchdog_task, hotcpu)) + break; + /* Unbind so it can run. Fall thru. */ + kthread_bind(per_cpu(watchdog_task, hotcpu), + any_online_cpu(cpu_online_map)); case CPU_DEAD: case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); 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..86daaa26d12 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 @@ -1196,6 +1203,14 @@ 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 +2095,6 @@ 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 +2508,6 @@ 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 |