diff options
Diffstat (limited to 'kernel')
39 files changed, 3298 insertions, 1041 deletions
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz new file mode 100644 index 00000000000..248e1c396f8 --- /dev/null +++ b/kernel/Kconfig.hz @@ -0,0 +1,46 @@ +# +# Timer Interrupt Frequency Configuration +# + +choice + prompt "Timer frequency" + default HZ_250 + help + Allows the configuration of the timer frequency. It is customary + to have the timer interrupt run at 1000 HZ but 100 HZ may be more + beneficial for servers and NUMA systems that do not need to have + a fast response for user interaction and that may experience bus + contention and cacheline bounces as a result of timer interrupts. + Note that the timer interrupt occurs on each processor in an SMP + environment leading to NR_CPUS * HZ number of timer interrupts + per second. + + + config HZ_100 + bool "100 HZ" + help + 100 HZ is a typical choice for servers, SMP and NUMA systems + with lots of processors that may show reduced performance if + too many timer interrupts are occurring. + + config HZ_250 + bool "250 HZ" + help + 250 HZ is a good compromise choice allowing server performance + while also showing good interactive responsiveness even + on SMP and NUMA systems. + + config HZ_1000 + bool "1000 HZ" + help + 1000 HZ is the preferred choice for desktop systems and other + systems requiring fast interactive responses to events. + +endchoice + +config HZ + int + default 100 if HZ_100 + default 250 if HZ_250 + default 1000 if HZ_1000 + diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt new file mode 100644 index 00000000000..0b46a5dff4c --- /dev/null +++ b/kernel/Kconfig.preempt @@ -0,0 +1,65 @@ + +choice + prompt "Preemption Model" + default PREEMPT_NONE + +config PREEMPT_NONE + bool "No Forced Preemption (Server)" + help + This is the traditional Linux preemption model, geared towards + throughput. It will still provide good latencies most of the + time, but there are no guarantees and occasional longer delays + are possible. + + Select this option if you are building a kernel for a server or + scientific/computation system, or if you want to maximize the + raw processing power of the kernel, irrespective of scheduling + latencies. + +config PREEMPT_VOLUNTARY + bool "Voluntary Kernel Preemption (Desktop)" + help + This option reduces the latency of the kernel by adding more + "explicit preemption points" to the kernel code. These new + preemption points have been selected to reduce the maximum + latency of rescheduling, providing faster application reactions, + at the cost of slighly lower throughput. + + This allows reaction to interactive events by allowing a + low priority process to voluntarily preempt itself even if it + is in kernel mode executing a system call. This allows + applications to run more 'smoothly' even when the system is + under load. + + Select this if you are building a kernel for a desktop system. + +config PREEMPT + bool "Preemptible Kernel (Low-Latency Desktop)" + help + This option reduces the latency of the kernel by making + all kernel code (that is not executing in a critical section) + preemptible. This allows reaction to interactive events by + permitting a low priority process to be preempted involuntarily + even if it is in kernel mode executing a system call and would + otherwise not be about to reach a natural preemption point. + This allows applications to run more 'smoothly' even when the + system is under load, at the cost of slighly lower throughput + and a slight runtime overhead to kernel code. + + Select this if you are building a kernel for a desktop or + embedded system with latency requirements in the milliseconds + range. + +endchoice + +config PREEMPT_BKL + bool "Preempt The Big Kernel Lock" + depends on SMP || PREEMPT + default y + help + This option reduces the latency of the kernel by making the + big kernel lock preemptible. + + Say Y here if you are building a kernel for a desktop system. + Say N if you are unsure. + diff --git a/kernel/Makefile b/kernel/Makefile index b01d26fe8db..cb05cd05d23 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_PM) += power/ obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o +obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_IKCONFIG) += configs.o @@ -27,6 +28,7 @@ obj-$(CONFIG_AUDITSYSCALL) += auditsc.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_SECCOMP) += seccomp.o ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) diff --git a/kernel/capability.c b/kernel/capability.c index 64db1ee820c..8986a37a67e 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -31,8 +31,14 @@ static DEFINE_SPINLOCK(task_capability_lock); * uninteresting and/or not to be changed. */ -/* +/** * sys_capget - get the capabilities of a given process. + * @header: pointer to struct that contains capability version and + * target pid data + * @dataptr: pointer to struct that contains the effective, permitted, + * and inheritable capabilities that are returned + * + * Returns 0 on success and < 0 on error. */ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) { @@ -141,8 +147,14 @@ static inline int cap_set_all(kernel_cap_t *effective, return ret; } -/* - * sys_capset - set capabilities for a given process, all processes, or all +/** + * sys_capset - set capabilities for a process or a group of processes + * @header: pointer to struct that contains capability version and + * target pid data + * @data: pointer to struct that contains the effective, permitted, + * and inheritable capabilities + * + * Set capabilities for a given process, all processes, or all * processes in a given process group. * * The restrictions on setting capabilities are specified as: @@ -152,6 +164,8 @@ static inline int cap_set_all(kernel_cap_t *effective, * I: any raised capabilities must be a subset of the (old current) permitted * P: any raised capabilities must be a subset of the (old current) permitted * E: must be set to a subset of (new target) permitted + * + * Returns 0 on success and < 0 on error. */ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 628f4ccda12..53d8263ae12 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -63,19 +63,15 @@ static int take_cpu_down(void *unused) { int err; - /* Take offline: makes arch_cpu_down somewhat easier. */ - cpu_clear(smp_processor_id(), cpu_online_map); - /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) - cpu_set(smp_processor_id(), cpu_online_map); - else - /* Force idle task to run as soon as we yield: it should - immediately notice cpu is offline and die quickly. */ - sched_idle_next(); + return err; - return err; + /* Force idle task to run as soon as we yield: it should + immediately notice cpu is offline and die quickly. */ + sched_idle_next(); + return 0; } int cpu_down(unsigned int cpu) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 00e8f257551..21a4e3b2cbd 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -228,13 +228,7 @@ static struct dentry_operations cpuset_dops = { static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name) { - struct qstr qstr; - struct dentry *d; - - qstr.name = name; - qstr.len = strlen(name); - qstr.hash = full_name_hash(name, qstr.len); - d = lookup_hash(&qstr, parent); + struct dentry *d = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(d)) d->d_op = &cpuset_dops; return d; @@ -404,21 +398,31 @@ static int cpuset_path(const struct cpuset *cs, char *buf, int buflen) * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * - * Note final arg to call_usermodehelper() is 0 - that means - * don't wait. Since we are holding the global cpuset_sem here, - * and we are asking another thread (started from keventd) to rmdir a - * cpuset, we can't wait - or we'd deadlock with the removing thread - * on cpuset_sem. + * The final arg to call_usermodehelper() is 0, which means don't + * wait. The separate /sbin/cpuset_release_agent task is forked by + * call_usermodehelper(), then control in this thread returns here, + * without waiting for the release agent task. We don't bother to + * wait because the caller of this routine has no use for the exit + * status of the /sbin/cpuset_release_agent task, so no sense holding + * our caller up for that. + * + * The simple act of forking that task might require more memory, + * which might need cpuset_sem. So this routine must be called while + * cpuset_sem is not held, to avoid a possible deadlock. See also + * comments for check_for_release(), below. */ -static int cpuset_release_agent(char *cpuset_str) +static void cpuset_release_agent(const char *pathbuf) { char *argv[3], *envp[3]; int i; + if (!pathbuf) + return; + i = 0; argv[i++] = "/sbin/cpuset_release_agent"; - argv[i++] = cpuset_str; + argv[i++] = (char *)pathbuf; argv[i] = NULL; i = 0; @@ -427,17 +431,29 @@ static int cpuset_release_agent(char *cpuset_str) envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[i] = NULL; - return call_usermodehelper(argv[0], argv, envp, 0); + call_usermodehelper(argv[0], argv, envp, 0); + kfree(pathbuf); } /* * Either cs->count of using tasks transitioned to zero, or the * cs->children list of child cpusets just became empty. If this * cs is notify_on_release() and now both the user count is zero and - * the list of children is empty, send notice to user land. + * the list of children is empty, prepare cpuset path in a kmalloc'd + * buffer, to be returned via ppathbuf, so that the caller can invoke + * cpuset_release_agent() with it later on, once cpuset_sem is dropped. + * Call here with cpuset_sem held. + * + * This check_for_release() routine is responsible for kmalloc'ing + * pathbuf. The above cpuset_release_agent() is responsible for + * kfree'ing pathbuf. The caller of these routines is responsible + * for providing a pathbuf pointer, initialized to NULL, then + * calling check_for_release() with cpuset_sem held and the address + * of the pathbuf pointer, then dropping cpuset_sem, then calling + * cpuset_release_agent() with pathbuf, as set by check_for_release(). */ -static void check_for_release(struct cpuset *cs) +static void check_for_release(struct cpuset *cs, char **ppathbuf) { if (notify_on_release(cs) && atomic_read(&cs->count) == 0 && list_empty(&cs->children)) { @@ -447,10 +463,9 @@ static void check_for_release(struct cpuset *cs) if (!buf) return; if (cpuset_path(cs, buf, PAGE_SIZE) < 0) - goto out; - cpuset_release_agent(buf); -out: - kfree(buf); + kfree(buf); + else + *ppathbuf = buf; } } @@ -601,10 +616,62 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) return 0; } +/* + * For a given cpuset cur, partition the system as follows + * a. All cpus in the parent cpuset's cpus_allowed that are not part of any + * exclusive child cpusets + * b. All cpus in the current cpuset's cpus_allowed that are not part of any + * exclusive child cpusets + * Build these two partitions by calling partition_sched_domains + * + * Call with cpuset_sem held. May nest a call to the + * lock_cpu_hotplug()/unlock_cpu_hotplug() pair. + */ +static void update_cpu_domains(struct cpuset *cur) +{ + struct cpuset *c, *par = cur->parent; + cpumask_t pspan, cspan; + + if (par == NULL || cpus_empty(cur->cpus_allowed)) + return; + + /* + * Get all cpus from parent's cpus_allowed not part of exclusive + * children + */ + pspan = par->cpus_allowed; + list_for_each_entry(c, &par->children, sibling) { + if (is_cpu_exclusive(c)) + cpus_andnot(pspan, pspan, c->cpus_allowed); + } + if (is_removed(cur) || !is_cpu_exclusive(cur)) { + cpus_or(pspan, pspan, cur->cpus_allowed); + if (cpus_equal(pspan, cur->cpus_allowed)) + return; + cspan = CPU_MASK_NONE; + } else { + if (cpus_empty(pspan)) + return; + cspan = cur->cpus_allowed; + /* + * Get all cpus from current cpuset's cpus_allowed not part + * of exclusive children + */ + list_for_each_entry(c, &cur->children, sibling) { + if (is_cpu_exclusive(c)) + cpus_andnot(cspan, cspan, c->cpus_allowed); + } + } + + lock_cpu_hotplug(); + partition_sched_domains(&pspan, &cspan); + unlock_cpu_hotplug(); +} + static int update_cpumask(struct cpuset *cs, char *buf) { struct cpuset trialcs; - int retval; + int retval, cpus_unchanged; trialcs = *cs; retval = cpulist_parse(buf, trialcs.cpus_allowed); @@ -614,9 +681,13 @@ static int update_cpumask(struct cpuset *cs, char *buf) if (cpus_empty(trialcs.cpus_allowed)) return -ENOSPC; retval = validate_change(cs, &trialcs); - if (retval == 0) - cs->cpus_allowed = trialcs.cpus_allowed; - return retval; + if (retval < 0) + return retval; + cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed); + cs->cpus_allowed = trialcs.cpus_allowed; + if (is_cpu_exclusive(cs) && !cpus_unchanged) + update_cpu_domains(cs); + return 0; } static int update_nodemask(struct cpuset *cs, char *buf) @@ -652,7 +723,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) { int turning_on; struct cpuset trialcs; - int err; + int err, cpu_exclusive_changed; turning_on = (simple_strtoul(buf, NULL, 10) != 0); @@ -663,23 +734,28 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) clear_bit(bit, &trialcs.flags); err = validate_change(cs, &trialcs); - if (err == 0) { - if (turning_on) - set_bit(bit, &cs->flags); - else - clear_bit(bit, &cs->flags); - } - return err; + if (err < 0) + return err; + cpu_exclusive_changed = + (is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs)); + if (turning_on) + set_bit(bit, &cs->flags); + else + clear_bit(bit, &cs->flags); + + if (cpu_exclusive_changed) + update_cpu_domains(cs); + return 0; } -static int attach_task(struct cpuset *cs, char *buf) +static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) { pid_t pid; struct task_struct *tsk; struct cpuset *oldcs; cpumask_t cpus; - if (sscanf(buf, "%d", &pid) != 1) + if (sscanf(pidbuf, "%d", &pid) != 1) return -EIO; if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; @@ -722,7 +798,7 @@ static int attach_task(struct cpuset *cs, char *buf) put_task_struct(tsk); if (atomic_dec_and_test(&oldcs->count)) - check_for_release(oldcs); + check_for_release(oldcs, ppathbuf); return 0; } @@ -746,6 +822,7 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us struct cftype *cft = __d_cft(file->f_dentry); cpuset_filetype_t type = cft->private; char *buffer; + char *pathbuf = NULL; int retval = 0; /* Crude upper limit on largest legitimate cpulist user might write. */ @@ -786,7 +863,7 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer); break; case FILE_TASKLIST: - retval = attach_task(cs, buffer); + retval = attach_task(cs, buffer, &pathbuf); break; default: retval = -EINVAL; @@ -797,6 +874,7 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us retval = nbytes; out2: up(&cpuset_sem); + cpuset_release_agent(pathbuf); out1: kfree(buffer); return retval; @@ -1302,6 +1380,7 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cpuset *cs = dentry->d_fsdata; struct dentry *d; struct cpuset *parent; + char *pathbuf = NULL; /* the vfs holds both inode->i_sem already */ @@ -1315,18 +1394,21 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) up(&cpuset_sem); return -EBUSY; } - spin_lock(&cs->dentry->d_lock); parent = cs->parent; set_bit(CS_REMOVED, &cs->flags); + if (is_cpu_exclusive(cs)) + update_cpu_domains(cs); list_del(&cs->sibling); /* delete my sibling from parent->children */ if (list_empty(&parent->children)) - check_for_release(parent); + check_for_release(parent, &pathbuf); + spin_lock(&cs->dentry->d_lock); d = dget(cs->dentry); cs->dentry = NULL; spin_unlock(&d->d_lock); cpuset_d_remove_dir(d); dput(d); up(&cpuset_sem); + cpuset_release_agent(pathbuf); return 0; } @@ -1383,10 +1465,10 @@ void __init cpuset_init_smp(void) /** * cpuset_fork - attach newly forked task to its parents cpuset. - * @p: pointer to task_struct of forking parent process. + * @tsk: pointer to task_struct of forking parent process. * * Description: By default, on fork, a task inherits its - * parents cpuset. The pointer to the shared cpuset is + * parent's cpuset. The pointer to the shared cpuset is * automatically copied in fork.c by dup_task_struct(). * This cpuset_fork() routine need only increment the usage * counter in that cpuset. @@ -1414,7 +1496,6 @@ void cpuset_fork(struct task_struct *tsk) * by the cpuset_sem semaphore. If you don't hold cpuset_sem, * then a zero cpuset use count is a license to any other task to * nuke the cpuset immediately. - * **/ void cpuset_exit(struct task_struct *tsk) @@ -1427,10 +1508,13 @@ void cpuset_exit(struct task_struct *tsk) task_unlock(tsk); if (notify_on_release(cs)) { + char *pathbuf = NULL; + down(&cpuset_sem); if (atomic_dec_and_test(&cs->count)) - check_for_release(cs); + check_for_release(cs, &pathbuf); up(&cpuset_sem); + cpuset_release_agent(pathbuf); } else { atomic_dec(&cs->count); } @@ -1464,7 +1548,9 @@ void cpuset_init_current_mems_allowed(void) current->mems_allowed = NODE_MASK_ALL; } -/* +/** + * cpuset_update_current_mems_allowed - update mems parameters to new values + * * If the current tasks cpusets mems_allowed changed behind our backs, * update current->mems_allowed and mems_generation to the new value. * Do not call this routine if in_interrupt(). @@ -1483,13 +1569,20 @@ void cpuset_update_current_mems_allowed(void) } } +/** + * cpuset_restrict_to_mems_allowed - limit nodes to current mems_allowed + * @nodes: pointer to a node bitmap that is and-ed with mems_allowed + */ void cpuset_restrict_to_mems_allowed(unsigned long *nodes) { bitmap_and(nodes, nodes, nodes_addr(current->mems_allowed), MAX_NUMNODES); } -/* +/** + * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed + * @zl: the zonelist to be checked + * * Are any of the nodes on zonelist zl allowed in current->mems_allowed? */ int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) @@ -1505,8 +1598,12 @@ int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) return 0; } -/* - * Is 'current' valid, and is zone z allowed in current->mems_allowed? +/** + * cpuset_zone_allowed - is zone z allowed in current->mems_allowed + * @z: zone in question + * + * Is zone z allowed in current->mems_allowed, or is + * the CPU in interrupt context? (zone is always allowed in this case) */ int cpuset_zone_allowed(struct zone *z) { diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c new file mode 100644 index 00000000000..334c37f5218 --- /dev/null +++ b/kernel/crash_dump.c @@ -0,0 +1,61 @@ +/* + * kernel/crash_dump.c - Memory preserving reboot related code. + * + * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) + * Copyright (C) IBM Corporation, 2004. All rights reserved + */ + +#include <linux/smp_lock.h> +#include <linux/errno.h> +#include <linux/proc_fs.h> +#include <linux/bootmem.h> +#include <linux/highmem.h> +#include <linux/crash_dump.h> + +#include <asm/io.h> +#include <asm/uaccess.h> + +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + +/** + * copy_oldmem_page - copy one page from "oldmem" + * @pfn: page frame number to be copied + * @buf: target memory address for the copy; this can be in kernel address + * space or user address space (see @userbuf) + * @csize: number of bytes to copy + * @offset: offset in bytes into the page (based on pfn) to begin the copy + * @userbuf: if set, @buf is in user address space, use copy_to_user(), + * otherwise @buf is in kernel address space, use memcpy(). + * + * Copy a page from "oldmem". For this page, there is no pte mapped + * in the current kernel. We stitch up a pte, similar to kmap_atomic. + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, int userbuf) +{ + void *page, *vaddr; + + if (!csize) + return 0; + + page = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!page) + return -ENOMEM; + + vaddr = kmap_atomic_pfn(pfn, KM_PTE0); + copy_page(page, vaddr); + kunmap_atomic(vaddr, KM_PTE0); + + if (userbuf) { + if (copy_to_user(buf, (page + offset), csize)) { + kfree(page); + return -EFAULT; + } + } else { + memcpy(buf, (page + offset), csize); + } + + kfree(page); + return csize; +} diff --git a/kernel/exit.c b/kernel/exit.c index 2ef2ad54020..5b0fb9f09f2 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -72,6 +72,11 @@ repeat: BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); __exit_signal(p); __exit_sighand(p); + /* + * Note that the fastpath in sys_times depends on __exit_signal having + * updated the counters before a task is removed from the tasklist of + * the process by __unhash_process. + */ __unhash_process(p); /* @@ -779,6 +784,8 @@ fastcall NORET_TYPE void do_exit(long code) profile_task_exit(tsk); + WARN_ON(atomic_read(&tsk->fs_excl)); + if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) @@ -793,6 +800,17 @@ fastcall NORET_TYPE void do_exit(long code) ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); } + /* + * We're taking recursive faults here in do_exit. Safest is to just + * leave this task alone and wait for reboot. + */ + if (unlikely(tsk->flags & PF_EXITING)) { + printk(KERN_ALERT + "Fixing recursive fault but reboot is needed!\n"); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + } + tsk->flags |= PF_EXITING; /* @@ -811,8 +829,10 @@ fastcall NORET_TYPE void do_exit(long code) acct_update_integrals(tsk); update_mem_hiwater(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); - if (group_dead) + if (group_dead) { + del_timer_sync(&tsk->signal->real_timer); acct_process(code); + } exit_mm(tsk); exit_sem(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index a28d11e1087..b65187f0c74 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -208,8 +208,10 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { + long pages = vma_pages(mpnt); + mm->total_vm -= pages; __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, - -vma_pages(mpnt)); + -pages); continue; } charge = 0; @@ -1003,9 +1005,6 @@ static task_t *copy_process(unsigned long clone_flags, p->pdeath_signal = 0; p->exit_state = 0; - /* Perform scheduler related setup */ - sched_fork(p); - /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. @@ -1014,18 +1013,24 @@ static task_t *copy_process(unsigned long clone_flags, INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); + /* Perform scheduler related setup. Assign this task to a CPU. */ + sched_fork(p, clone_flags); + /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* - * The task hasn't been attached yet, so cpus_allowed mask cannot - * have changed. The cpus_allowed mask of the parent may have - * changed after it was copied first time, and it may then move to - * another CPU - so we re-copy it here and set the child's CPU to - * the parent's CPU. This avoids alot of nasty races. + * The task hasn't been attached yet, so its cpus_allowed mask will + * not be changed, nor will its assigned CPU. + * + * The cpus_allowed mask of the parent may have changed after it was + * copied first time - so re-copy it here, then check the child's CPU + * to ensure it is on a valid CPU (and if not, just force it back to + * parent's CPU). This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; - set_task_cpu(p, smp_processor_id()); + if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed))) + set_task_cpu(p, smp_processor_id()); /* * Check for pending SIGKILL! The new thread should not be allowed @@ -1087,6 +1092,11 @@ static task_t *copy_process(unsigned long clone_flags, spin_unlock(¤t->sighand->siglock); } + /* + * inherit ioprio + */ + p->ioprio = current->ioprio; + SET_LINKS(p); if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 98d62d8efea..3467097ca61 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/delay.h> /* * Autodetection depends on the fact that any interrupt that @@ -26,7 +27,7 @@ static DECLARE_MUTEX(probe_sem); */ unsigned long probe_irq_on(void) { - unsigned long val, delay; + unsigned long val; |