diff options
Diffstat (limited to 'kernel')
44 files changed, 1195 insertions, 599 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 54f69837d35..4e1d7df7c3e 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FTRACE) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o diff --git a/kernel/audit.c b/kernel/audit.c index e092f1c0ce3..4414e93d875 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -707,12 +707,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (status_get->mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(status_get->enabled, loginuid, sessionid, sid); - if (err < 0) return err; + if (err < 0) + return err; } if (status_get->mask & AUDIT_STATUS_FAILURE) { err = audit_set_failure(status_get->failure, loginuid, sessionid, sid); - if (err < 0) return err; + if (err < 0) + return err; } if (status_get->mask & AUDIT_STATUS_PID) { int new_pid = status_get->pid; @@ -725,9 +727,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_pid = new_pid; audit_nlk_pid = NETLINK_CB(skb).pid; } - if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) + if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(status_get->rate_limit, loginuid, sessionid, sid); + if (err < 0) + return err; + } if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT) err = audit_set_backlog_limit(status_get->backlog_limit, loginuid, sessionid, sid); @@ -1366,7 +1371,7 @@ int audit_string_contains_control(const char *string, size_t len) { const unsigned char *p; for (p = string; p < (const unsigned char *)string + len && *p; p++) { - if (*p == '"' || *p < 0x21 || *p > 0x7f) + if (*p == '"' || *p < 0x21 || *p > 0x7e) return 1; } return 0; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 98c50cc671b..b7d354e2b0e 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1022,8 +1022,11 @@ static void audit_update_watch(struct audit_parent *parent, struct audit_buffer *ab; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + audit_log_format(ab, "auid=%u ses=%u", + audit_get_loginuid(current), + audit_get_sessionid(current)); audit_log_format(ab, - "op=updated rules specifying path="); + " op=updated rules specifying path="); audit_log_untrustedstring(ab, owatch->path); audit_log_format(ab, " with dev=%u ino=%lu\n", dev, ino); @@ -1058,7 +1061,10 @@ static void audit_remove_parent_watches(struct audit_parent *parent) struct audit_buffer *ab; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "op=remove rule path="); + audit_log_format(ab, "auid=%u ses=%u", + audit_get_loginuid(current), + audit_get_sessionid(current)); + audit_log_format(ab, " op=remove rule path="); audit_log_untrustedstring(ab, w->path); if (r->filterkey) { audit_log_format(ab, " key="); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4699950e65b..972f8e61d36 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -243,6 +243,9 @@ static inline int open_arg(int flags, int mask) static int audit_match_perm(struct audit_context *ctx, int mask) { + if (unlikely(!ctx)) + return 0; + unsigned n = ctx->major; switch (audit_classify_syscall(ctx->arch, n)) { case 0: /* native */ @@ -284,6 +287,10 @@ static int audit_match_filetype(struct audit_context *ctx, int which) { unsigned index = which & ~S_IFMT; mode_t mode = which & S_IFMT; + + if (unlikely(!ctx)) + return 0; + if (index >= ctx->name_count) return 0; if (ctx->names[index].ino == -1) @@ -610,7 +617,7 @@ static int audit_filter_rules(struct task_struct *tsk, if (!result) return 0; } - if (rule->filterkey) + if (rule->filterkey && ctx) ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); switch (rule->action) { case AUDIT_NEVER: *state = AUDIT_DISABLED; break; @@ -2375,7 +2382,7 @@ int __audit_signal_info(int sig, struct task_struct *t) struct audit_context *ctx = tsk->audit_context; if (audit_pid && t->tgid == audit_pid) { - if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) { + if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { audit_sig_pid = tsk->pid; if (tsk->loginuid != -1) audit_sig_uid = tsk->loginuid; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 66ec9fd21e0..13932abde15 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -45,6 +45,7 @@ #include <linux/delayacct.h> #include <linux/cgroupstats.h> #include <linux/hash.h> +#include <linux/namei.h> #include <asm/atomic.h> @@ -354,6 +355,17 @@ static struct css_set *find_existing_css_set( return NULL; } +static void free_cg_links(struct list_head *tmp) +{ + struct cg_cgroup_link *link; + struct cg_cgroup_link *saved_link; + + list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) { + list_del(&link->cgrp_link_list); + kfree(link); + } +} + /* * allocate_cg_links() allocates "count" cg_cgroup_link structures * and chains them on tmp through their cgrp_link_list fields. Returns 0 on @@ -362,17 +374,12 @@ static struct css_set *find_existing_css_set( static int allocate_cg_links(int count, struct list_head *tmp) { struct cg_cgroup_link *link; - struct cg_cgroup_link *saved_link; int i; INIT_LIST_HEAD(tmp); for (i = 0; i < count; i++) { link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { - list_for_each_entry_safe(link, saved_link, tmp, - cgrp_link_list) { - list_del(&link->cgrp_link_list); - kfree(link); - } + free_cg_links(tmp); return -ENOMEM; } list_add(&link->cgrp_link_list, tmp); @@ -380,17 +387,6 @@ static int allocate_cg_links(int count, struct list_head *tmp) return 0; } -static void free_cg_links(struct list_head *tmp) -{ - struct cg_cgroup_link *link; - struct cg_cgroup_link *saved_link; - - list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) { - list_del(&link->cgrp_link_list); - kfree(link); - } -} - /* * find_css_set() takes an existing cgroup group and a * cgroup object, and returns a css_set object that's @@ -955,7 +951,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct super_block *sb; struct cgroupfs_root *root; struct list_head tmp_cg_links; - INIT_LIST_HEAD(&tmp_cg_links); /* First find the desired set of subsystems */ ret = parse_cgroupfs_options(data, &opts); @@ -1423,14 +1418,17 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft, if (buffer == NULL) return -ENOMEM; } - if (nbytes && copy_from_user(buffer, userbuf, nbytes)) - return -EFAULT; + if (nbytes && copy_from_user(buffer, userbuf, nbytes)) { + retval = -EFAULT; + goto out; + } buffer[nbytes] = 0; /* nul-terminate */ strstrip(buffer); retval = cft->write_string(cgrp, cft, buffer); if (!retval) retval = nbytes; +out: if (buffer != local_buffer) kfree(buffer); return retval; @@ -1529,7 +1527,7 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg) return cft->read_seq_string(state->cgroup, cft, m); } -int cgroup_seqfile_release(struct inode *inode, struct file *file) +static int cgroup_seqfile_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; kfree(seq->private); @@ -2370,7 +2368,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode) return cgroup_create(c_parent, dentry, mode | S_IFDIR); } -static inline int cgroup_has_css_refs(struct cgroup *cgrp) +static int cgroup_has_css_refs(struct cgroup *cgrp) { /* Check the reference count on each subsystem. Since we * already established that there are no tasks in the diff --git a/kernel/cpu.c b/kernel/cpu.c index 10ba5f1004a..e202a68d1cc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -216,7 +216,6 @@ static int __ref take_cpu_down(void *_param) static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { int err, nr_calls = 0; - struct task_struct *p; cpumask_t old_allowed, tmp; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; @@ -249,21 +248,18 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) cpus_setall(tmp); cpu_clear(cpu, tmp); set_cpus_allowed_ptr(current, &tmp); + tmp = cpumask_of_cpu(cpu); - p = __stop_machine_run(take_cpu_down, &tcd_param, cpu); - - if (IS_ERR(p) || cpu_online(cpu)) { + err = __stop_machine(take_cpu_down, &tcd_param, &tmp); + if (err) { /* CPU didn't die: tell everyone. Can't complain. */ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod, hcpu) == NOTIFY_BAD) BUG(); - if (IS_ERR(p)) { - err = PTR_ERR(p); - goto out_allowed; - } - goto out_thread; + goto out_allowed; } + BUG_ON(cpu_online(cpu)); /* Wait for it to sleep (leaving idle task). */ while (!idle_cpu(cpu)) @@ -279,8 +275,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); -out_thread: - err = kthread_stop(p); out_allowed: set_cpus_allowed_ptr(current, &old_allowed); out_release: @@ -461,3 +455,28 @@ out: #endif /* CONFIG_PM_SLEEP_SMP */ #endif /* CONFIG_SMP */ + +/* + * cpu_bit_bitmap[] is a special, "compressed" data structure that + * represents all NR_CPUS bits binary values of 1<<nr. + * + * It is used by cpumask_of_cpu() to get a constant address to a CPU + * mask value that has a single bit set only. + */ + +/* cpu_bit_bitmap[0] is empty - so we can back into it */ +#define MASK_DECLARE_1(x) [x+1][0] = 1UL << (x) +#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) +#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) +#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) + +const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { + + MASK_DECLARE_8(0), MASK_DECLARE_8(8), + MASK_DECLARE_8(16), MASK_DECLARE_8(24), +#if BITS_PER_LONG > 32 + MASK_DECLARE_8(32), MASK_DECLARE_8(40), + MASK_DECLARE_8(48), MASK_DECLARE_8(56), +#endif +}; +EXPORT_SYMBOL_GPL(cpu_bit_bitmap); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 91cf85b36dd..d5ab79cf516 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -54,7 +54,6 @@ #include <asm/uaccess.h> #include <asm/atomic.h> #include <linux/mutex.h> -#include <linux/kfifo.h> #include <linux/workqueue.h> #include <linux/cgroup.h> @@ -486,13 +485,38 @@ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { - if (!dattr) - return; if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } +static void +update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) +{ + LIST_HEAD(q); + + list_add(&c->stack_list, &q); + while (!list_empty(&q)) { + struct cpuset *cp; + struct cgroup *cont; + struct cpuset *child; + + cp = list_first_entry(&q, struct cpuset, stack_list); + list_del(q.next); + + if (cpus_empty(cp->cpus_allowed)) + continue; + + if (is_sched_load_balance(cp)) + update_domain_attr(dattr, cp); + + list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { + child = cgroup_cs(cont); + list_add_tail(&child->stack_list, &q); + } + } +} + /* * rebuild_sched_domains() * @@ -532,7 +556,7 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) * So the reverse nesting would risk an ABBA deadlock. * * The three key local variables below are: - * q - a kfifo queue of cpuset pointers, used to implement a + * q - a linked-list queue of cpuset pointers, used to implement a * top-down scan of all cpusets. This scan loads a pointer * to each cpuset marked is_sched_load_balance into the * array 'csa'. For our purposes, rebuilding the schedulers @@ -567,7 +591,7 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) void rebuild_sched_domains(void) { - struct kfifo *q; /* queue of cpusets to be scanned */ + LIST_HEAD(q); /* queue of cpusets to be scanned*/ struct cpuset *cp; /* scans q */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ @@ -577,7 +601,6 @@ void rebuild_sched_domains(void) int ndoms; /* number of sched domains in result */ int nslot; /* next empty doms[] cpumask_t slot */ - q = NULL; csa = NULL; doms = NULL; dattr = NULL; @@ -591,35 +614,42 @@ void rebuild_sched_domains(void) dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; - update_domain_attr(dattr, &top_cpuset); + update_domain_attr_tree(dattr, &top_cpuset); } *doms = top_cpuset.cpus_allowed; goto rebuild; } - q = kfifo_alloc(number_of_cpusets * sizeof(cp), GFP_KERNEL, NULL); - if (IS_ERR(q)) - goto done; csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; - cp = &top_cpuset; - __kfifo_put(q, (void *)&cp, sizeof(cp)); - while (__kfifo_get(q, (void *)&cp, sizeof(cp))) { + list_add(&top_cpuset.stack_list, &q); + while (!list_empty(&q)) { struct cgroup *cont; struct cpuset *child; /* scans child cpusets of cp */ + cp = list_first_entry(&q, struct cpuset, stack_list); + list_del(q.next); + if (cpus_empty(cp->cpus_allowed)) continue; - if (is_sched_load_balance(cp)) + /* + * All child cpusets contain a subset of the parent's cpus, so + * just skip them, and then we call update_domain_attr_tree() + * to calc relax_domain_level of the corresponding sched + * domain. + */ + if (is_sched_load_balance(cp)) { csa[csn++] = cp; + continue; + } list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { child = cgroup_cs(cont); - __kfifo_put(q, (void *)&child, sizeof(cp)); + list_add_tail(&child->stack_list, &q); } } @@ -686,7 +716,7 @@ restart: cpus_or(*dp, *dp, b->cpus_allowed); b->pn = -1; if (dattr) - update_domain_attr(dattr + update_domain_attr_tree(dattr + nslot, b); } } @@ -702,8 +732,6 @@ rebuild: put_online_cpus(); done: - if (q && !IS_ERR(q)) - kfifo_free(q); kfree(csa); /* Don't kfree(doms) -- partition_sched_domains() does that. */ /* Don't kfree(dattr) -- partition_sched_domains() does that. */ @@ -1833,24 +1861,21 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) */ static void scan_for_empty_cpusets(const struct cpuset *root) { + LIST_HEAD(queue); struct cpuset *cp; /* scans cpusets being updated */ struct cpuset *child; /* scans child cpusets of cp */ - struct list_head queue; struct cgroup *cont; nodemask_t oldmems; - INIT_LIST_HEAD(&queue); - list_add_tail((struct list_head *)&root->stack_list, &queue); while (!list_empty(&queue)) { - cp = container_of(queue.next, struct cpuset, stack_list); + cp = list_first_entry(&queue, struct cpuset, stack_list); list_del(queue.next); list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { child = cgroup_cs(cont); list_add_tail(&child->stack_list, &queue); } - cont = cp->css.cgroup; /* Continue past cpusets with all cpus, mems online */ if (cpus_subset(cp->cpus_allowed, cpu_online_map) && diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c new file mode 100644 index 00000000000..91e96950cd5 --- /dev/null +++ b/kernel/dma-coherent.c @@ -0,0 +1,153 @@ +/* + * Coherent per-device memory handling. + * Borrowed from i386 + */ +#include <linux/kernel.h> +#include <linux/dma-mapping.h> + +struct dma_coherent_mem { + void *virt_base; + u32 device_base; + int size; + int flags; + unsigned long *bitmap; +}; + +int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, + dma_addr_t device_addr, size_t size, int flags) +{ + void __iomem *mem_base = NULL; + int pages = size >> PAGE_SHIFT; + int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); + + if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) + goto out; + if (!size) + goto out; + if (dev->dma_mem) + goto out; + + /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ + + mem_base = ioremap(bus_addr, size); + if (!mem_base) + goto out; + + dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); + if (!dev->dma_mem) + goto out; + dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!dev->dma_mem->bitmap) + goto free1_out; + + dev->dma_mem->virt_base = mem_base; + dev->dma_mem->device_base = device_addr; + dev->dma_mem->size = pages; + dev->dma_mem->flags = flags; + + if (flags & DMA_MEMORY_MAP) + return DMA_MEMORY_MAP; + + return DMA_MEMORY_IO; + + free1_out: + kfree(dev->dma_mem); + out: + if (mem_base) + iounmap(mem_base); + return 0; +} +EXPORT_SYMBOL(dma_declare_coherent_memory); + +void dma_release_declared_memory(struct device *dev) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + + if (!mem) + return; + dev->dma_mem = NULL; + iounmap(mem->virt_base); + kfree(mem->bitmap); + kfree(mem); +} +EXPORT_SYMBOL(dma_release_declared_memory); + +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + int pos, err; + + size += device_addr & ~PAGE_MASK; + + if (!mem) + return ERR_PTR(-EINVAL); + + pos = (device_addr - mem->device_base) >> PAGE_SHIFT; + err = bitmap_allocate_region(mem->bitmap, pos, get_order(size)); + if (err != 0) + return ERR_PTR(err); + return mem->virt_base + (pos << PAGE_SHIFT); +} +EXPORT_SYMBOL(dma_mark_declared_memory_occupied); + +/** + * Try to allocate memory from the per-device coherent area. + * + * @dev: device from which we allocate memory + * @size: size of requested memory area + * @dma_handle: This will be filled with the correct dma handle + * @ret: This pointer will be filled with the virtual address + * to allocated area. + * + * This function should be only called from per-arch %dma_alloc_coherent() + * to support allocation from per-device coherent memory pools. + * + * Returns 0 if dma_alloc_coherent should continue with allocating from + * generic memory areas, or !0 if dma_alloc_coherent should return %ret. + */ +int dma_alloc_from_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle, void **ret) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + int order = get_order(size); + + if (mem) { + int page = bitmap_find_free_region(mem->bitmap, mem->size, + order); + if (page >= 0) { + *dma_handle = mem->device_base + (page << PAGE_SHIFT); + *ret = mem->virt_base + (page << PAGE_SHIFT); + memset(*ret, 0, size); + } else if (mem->flags & DMA_MEMORY_EXCLUSIVE) + *ret = NULL; + } + return (mem != NULL); +} + +/** + * Try to free the memory allocated from per-device coherent memory pool. + * @dev: device from which the memory was allocated + * @order: the order of pages allocated + * @vaddr: virtual address of allocated pages + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, releases that memory. + * + * Returns 1 if we correctly released the memory, or 0 if + * %dma_release_coherent() should proceed with releasing memory from + * generic pools. + */ +int dma_release_from_coherent(struct device *dev, int order, void *vaddr) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + + if (mem && vaddr >= mem->virt_base && vaddr < + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; + + bitmap_release_region(mem->bitmap, page, order); + return 1; + } + return 0; +} diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index c1ef192aa65..0d407e88673 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -168,7 +168,6 @@ __set_personality(u_long personality) current->personality = personality; oep = current_thread_info()->exec_domain; current_thread_info()->exec_domain = ep; - set_fs_altroot(); module_put(oep->module); return 0; diff --git a/kernel/exit.c b/kernel/exit.c index ad933bb29ec..38ec4063014 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -46,6 +46,7 @@ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> +#include <linux/tracehook.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -120,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk) sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); -#ifdef CONFIG_TASK_XACCT - sig->rchar += tsk->rchar; - sig->wchar += tsk->wchar; - sig->syscr += tsk->syscr; - sig->syscw += tsk->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - sig->ioac.read_bytes += tsk->ioac.read_bytes; - sig->ioac.write_bytes += tsk->ioac.write_bytes; - sig->ioac.cancelled_write_bytes += - tsk->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -162,27 +152,17 @@ static void delayed_put_task_struct(struct rcu_head *rhp) put_task_struct(container_of(rhp, struct task_struct, rcu)); } -/* - * Do final ptrace-related cleanup of a zombie being reaped. - * - * Called with write_lock(&tasklist_lock) held. - */ -static void ptrace_release_task(struct task_struct *p) -{ - BUG_ON(!list_empty(&p->ptraced)); - ptrace_unlink(p); - BUG_ON(!list_empty(&p->ptrace_entry)); -} void release_task(struct task_struct * p) { struct task_struct *leader; int zap_leader; repeat: + tracehook_prepare_release_task(p); atomic_dec(&p->user->processes); proc_flush_task(p); write_lock_irq(&tasklist_lock); - ptrace_release_task(p); + tracehook_finish_release_task(p); __exit_signal(p); /* @@ -204,6 +184,13 @@ repeat: * that case. */ zap_leader = task_detached(leader); + + /* + * This maintains the invariant that release_task() + * only runs on a task in EXIT_DEAD, just for sanity. + */ + if (zap_leader) + leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); @@ -567,8 +554,6 @@ void put_fs_struct(struct fs_struct *fs) if (atomic_dec_and_test(&fs->count)) { path_put(&fs->root); path_put(&fs->pwd); - if (fs->altroot.dentry) - path_put(&fs->altroot); kmem_cache_free(fs_cachep, fs); } } @@ -887,7 +872,8 @@ static void forget_original_parent(struct task_struct *father) */ static void exit_notify(struct task_struct *tsk, int group_dead) { - int state; + int signal; + void *cookie; /* * This does two things: @@ -924,22 +910,11 @@ static void exit_notify(struct task_struct *tsk, int group_dead) !capable(CAP_KILL)) tsk->exit_signal = SIGCHLD; - /* If something other than our normal parent is ptracing us, then - * send it a SIGCHLD instead of honoring exit_signal. exit_signal - * only has special meaning to our real parent. - */ - if (!task_detached(tsk) && thread_group_empty(tsk)) { - int signal = ptrace_reparented(tsk) ? - SIGCHLD : tsk->exit_signal; - do_notify_parent(tsk, signal); - } else if (tsk->ptrace) { - do_notify_parent(tsk, SIGCHLD); - } + signal = tracehook_notify_death(tsk, &cookie, group_dead); + if (signal >= 0) + signal = do_notify_parent(tsk, signal); - state = EXIT_ZOMBIE; - if (task_detached(tsk) && likely(!tsk->ptrace)) - state = EXIT_DEAD; - tsk->exit_state = state; + tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE; /* mt-exec, de_thread() is waiting for us */ if (thread_group_leader(tsk) && @@ -949,8 +924,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead) write_unlock_irq(&tasklist_lock); + tracehook_report_death(tsk, signal, cookie, group_dead); + /* If the process is dead, release it - nobody will wait for it */ - if (state == EXIT_DEAD) + if (signal == DEATH_REAP) release_task(tsk); } @@ -1029,10 +1006,7 @@ NORET_TYPE void do_exit(long code) if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); - if (unlikely(current->ptrace & PT_TRACE_EXIT)) { - current->ptrace_message = code; - ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); - } + tracehook_report_exit(&code); /* * We're taking recursive faults here in do_exit. Safest is to just @@ -1378,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options, psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; -#ifdef CONFIG_TASK_XACCT - psig->rchar += p->rchar + sig->rchar; - psig->wchar += p->wchar + sig->wchar; - psig->syscr += p->syscr + sig->syscr; - psig->syscw += p->syscw + sig->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - psig->ioac.read_bytes += - p->ioac.read_bytes + sig->ioac.read_bytes; - psig->ioac.write_bytes += - p->ioac.write_bytes + sig->ioac.write_bytes; - psig->ioac.cancelled_write_bytes += - p->ioac.cancelled_write_bytes + - sig->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); spin_unlock_irq(&p->parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index b99d73e971a..7ce2ebe8479 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include <linux/key.h> #include <linux/binfmts.h> #include <linux/mman.h> +#include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/nsproxy.h> #include <linux/capability.h> @@ -37,6 +38,7 @@ #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> +#include <linux/tracehook.h> #include <linux/futex.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> @@ -413,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; + mmu_notifier_mm_init(mm); return mm; } @@ -445,6 +448,7 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); + mmu_notifier_mm_destroy(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); @@ -656,13 +660,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old) path_get(&old->root); fs->pwd = old->pwd; path_get(&old->pwd); - if (old->altroot.dentry) { - fs->altroot = old->altroot; - path_get(&old->altroot); - } else { - fs->altroot.mnt = NULL; - fs->altroot.dentry = NULL; - } read_unlock(&old->lock); } return fs; @@ -812,12 +809,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; -#ifdef CONFIG_TASK_XACCT - sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0; -#endif -#ifdef CONFIG_TASK_IO_ACCOUNTING - memset(&sig->ioac, 0, sizeof(sig->ioac)); -#endif + task_io_accounting_init(&sig->ioac); sig->sum_sched_runtime = 0; INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); @@ -865,8 +857,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags &= ~PF_SUPERPRIV; new_flags |= PF_FORKNOEXEC; - if (!(clone_flags & CLONE_PTRACE)) - p->ptrace = 0; + new_flags |= PF_STARTING; p->flags = new_flags; clear_freeze_flag(p); } @@ -907,7 +898,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, struct pt_regs *regs, unsigned long stack_size, int __user *child_tidptr, - struct pid *pid) + struct pid *pid, + int trace) { int retval; struct task_struct *p; @@ -1000,13 +992,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->last_switch_timestamp = 0; #endif -#ifdef CONFIG_TASK_XACCT - p->rchar = 0; /* I/O counter: bytes read */ - p->wchar = 0; /* I/O counter: bytes written */ - p->syscr = 0; /* I/O counter: read syscalls */ - p->syscw = 0; /* I/O counter: write syscalls */ -#endif - task_io_accounting_init(p); + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); p->it_virt_expires = cputime_zero; @@ -1163,8 +1149,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_LIST_HEAD(&p->ptrace_entry); - INIT_LIST_HEAD(&p->ptraced); /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible @@ -1195,7 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_parent = current->real_parent; else p->real_parent = current; - p->parent = p->real_parent; spin_lock(¤t->sighand->siglock); @@ -1237,8 +1220,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (likely(p->pid)) { list_add_tail(&p->sibling, &p->real_parent->children); - if (unlikely(p->ptrace & PT_PTRACED)) - __ptrace_link(p, current->parent); + tracehook_finish_clone(p, clone_flags, trace); if (thread_group_leader(p)) { if (clone_flags & CLONE_NEWPID) @@ -1323,29 +1305,13 @@ struct task_struct * __cpuinit fork_idle(int cpu) struct pt_regs regs; task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, - &init_struct_pid); + &init_struct_pid, 0); if (!IS_ERR(task)) init_idle(task, cpu); return task; } -static int fork_traceflag(unsigned clone_flags) -{ - if (clone_flags & CLONE_UNTRACED) - return 0; - else if (clone_flags & CLONE_VFORK) { - if (current->ptrace & PT_TRACE_VFORK) - return PTRACE_EVENT_VFORK; - } else if ((clone_flags & CSIGNAL) != SIGCHLD) { - if (current->ptrace & PT_TRACE_CLONE) - return PTRACE_EVENT_CLONE; - } else if (current->ptrace & PT_TRACE_FORK) - return PTRACE_EVENT_FORK; - - return 0; -} - /* * Ok, this is the main fork-routine. * @@ -1380,14 +1346,14 @@ long do_fork(unsigned long clone_flags, } } - if (unlikely(current->ptrace)) { - trace = fork_traceflag (clone_flags); - if (trace) - clone_flags |= CLONE_PTRACE; - } + /* + * When called from kernel_thread, don't do user tracing stuff. + */ + if (likely(user_mode(regs))) + trace = tracehook_prepare_clone(clone_flags); p = copy_process(clone_flags, stack_start, regs, stack_size, - child_tidptr, NULL); + child_tidptr, NULL, trace); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1405,32 +1371,35 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { + tracehook_report_clone(trace, regs, clone_flags, nr, p); + + /* + * We set PF_STARTING at creation in case tracing wants to + * use this to distinguish a fully live task from one that + * hasn't gotten to tracehook_report_clone() yet. Now we + * clear it and set the child going. + */ + p->flags &= ~PF_STARTING; + + if (unlikely(clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); - } - - if (!(clone_flags & CLONE_STOPPED)) - wake_up_new_task(p, clone_flags); - else __set_task_state(p, TASK_STOPPED); - - if (unlikely (trace)) { - current->ptrace_message = nr; - ptrace_notify ((trace << 8) | SIGTRAP); + } else { + wake_up_new_task(p, clone_flags); } + tracehook_report_clone_complete(trace, regs, + clone_flags, nr, p); + if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) { - current->ptrace_message = nr; - ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); - } + tracehook_report_vfork_done(p, nr); } } else { nr = PTR_ERR(p); @@ -1442,7 +1411,7 @@ long do_fork(unsigned long clone_flags, #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif -static void sighand_ctor(struct kmem_cache *cachep, void *data) +static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 964964baefa..3cd441ebf5d 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -28,8 +28,7 @@ void dynamic_irq_init(unsigned int irq) unsigned long flags; if (irq >= NR_IRQS) { - printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq); - WARN_ON(1); + WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq); return; } @@ -62,8 +61,7 @@ void dynamic_irq_cleanup(unsigned int irq) unsigned long flags; if (irq >= NR_IRQS) { - printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq); - WARN_ON(1); + WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq); return; } @@ -71,9 +69,8 @@ void dynamic_irq_cleanup(unsigned int irq) spin_lock_irqsave(&desc->lock, flags); if (desc->action) { spin_unlock_irqrestore(&desc->lock, flags); - printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n", + WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n", irq); - WARN_ON(1); return; } desc->msi_desc = NULL; @@ -96,8 +93,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip) unsigned long flags; if (irq >= NR_IRQS) { - printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq); - WARN_ON(1); + WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq); return -EINVAL; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f8914b92b66..0314074fa23 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -177,8 +177,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq) { switch (desc->depth) { case 0: - printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); - WARN_ON(1); + WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); break; case 1: { unsigned int status = desc->status & ~IRQ_DISABLED; @@ -324,7 +323,8 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq, ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK); if (ret) - pr_err("setting flow type for irq %u failed (%pF)\n", + pr_err("setting trigger mode %d for irq %u failed (%pF)\n", + (int)(flags & IRQF_TRIGGER_MASK), irq, chip->set_type); return ret; diff --git a/kernel/kexec.c b/kernel/kexec.c index 1c5fcacbcf3..c8a4370e2a3 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -24,6 +24,12 @@ #include <linux/utsrelease.h> #include <linux/utsname.h> #include <linux/numa.h> +#include <linux/suspend.h> +#include <linux/device.h> +#include <linux/freezer.h> +#include <linux/pm.h> +#include <linux/cpu.h> +#include <linux/console.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -242,6 +248,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry, goto out; } + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + printk(KERN_ERR "Could not allocate swap buffer\n"); + goto out; + } + result = 0; out: if (result == 0) @@ -589,14 +601,12 @@ static void kimage_free_extra_pages(struct kimage *image) kimage_free_page_list(&image->unuseable_pages); } -static int kimage_terminate(struct kimage *image) +static void kimage_terminate(struct kimage *image) { if (*image->entry != 0) image->entry++; *image->entry = IND_DONE; - - return 0; } #define for_each_kimage_entry(image, ptr, entry) \ @@ -988,6 +998,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, if (result) goto out; + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; result = machine_kexec_prepare(image); if (result) goto out; @@ -997,9 +1009,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, if (result) goto out; } - result = kimage_terminate(image); - if (result) - goto out; + kimage_terminate(image); } /* Install the new kernel, and Uninstall the old */ image = xchg(dest_image, image); @@ -1415,3 +1425,85 @@ static int __init crash_save_vmcoreinfo_init(void) } module_init(crash_save_vmcoreinfo_init) + +/** + * kernel_kexec - reboot the system + * + * Move into place and start executing a preloaded standalone + * executable. If nothing was preloaded return an error. + */ +int kernel_kexec(void) +{ + int error = 0; + + if (xchg(&kexec_lock, 1)) + return -EBUSY; + if (!kexec_image) { + error = -EINVAL; + goto Unlock; + } + + if (kexec_image->preserve_context) { +#ifdef CONFIG_KEXEC_JUMP + mutex_lock(&pm_mutex); + pm_prepare_console(); + error = freeze_processes(); + if (error) { + error = -EBUSY; + goto Restore_console; + } + suspend_console(); + error = device_suspend(PMSG_FREEZE); + if (error) + goto Resume_console; + error = disable_nonboot_cpus(); + if (error) + goto Resume_devices; + local_irq_disable(); + /* At this point, device_suspend() has been called, + * but *not* device_power_down(). We *must* + * device_power_down() now. Otherwise, drivers for + * some devices (e.g. interrupt controllers) become + * desynchronized with the actual state of the + * hardware at resume time, and evil weirdness ensues. + */ + error = device_power_down(PMSG_FREEZE); + if (error) + goto Enable_irqs; + save_processor_state(); +#endif + } else { + blocking_notifier_call_chain(&reboot_notifier_list, + SYS_RESTART, NULL); + system_state = SYSTEM_RESTART; + device_shutdown(); + sysdev_shutdown(); + printk(KERN_EMERG "Starting new kernel\n"); + machine_shutdown(); + } + + machine_kexec(kexec_image); + + if (kexec_image->preserve_context) { +#ifdef CONFIG_KEXEC_JUMP + restore_processor_state(); + device_power_up(PMSG_RESTORE); + Enable_irqs: + local_irq_enable(); + enable_nonboot_cpus(); + Resume_devices: + device_resume(PMSG_RESTORE); + Resume_console: + resume_console(); + thaw_processes(); + Restore_console: + pm_restore_console(); + mutex_unlock(&pm_mutex); +#endif + } + + Unlock: + xchg(&kexec_lock, 0); + + return error; +} diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 3ec23c3ec97..eaa21fc9ad1 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -56,12 +56,14 @@ static int kgdb_break_asap; +#define KGDB_MAX_THREAD_QUERY 17 struct kgdb_state { int ex_vector; int signo; int err_code; int cpu; int pass_exception; + unsigned long thr_query; unsigned long threadid; long kgdb_usethreadid; struct pt_regs *linux_regs; @@ -166,13 +168,6 @@ early_param("nokgdbroundup", opt_nokgdbroundup); * Weak aliases for breakpoint management, * can be overriden by architectures when needed: */ -int __weak kgdb_validate_break_address(unsigned long addr) -{ - char tmp_variable[BREAK_INSTR_SIZE]; - - return probe_kernel_read(tmp_variable, (char *)addr, BREAK_INSTR_SIZE); -} - int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr) { int err; @@ -191,6 +186,25 @@ int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle) (char *)bundle, BREAK_INSTR_SIZE); } +int __weak kgdb_validate_break_address(unsigned long addr) +{ + char tmp_variable[BREAK_INSTR_SIZE]; + int err; + /* Validate setting the breakpoint and then removing it. In the + * remove fails, the kernel needs to emit a bad message because we + * are deep trouble not being able to put things back the way we + * found them. + */ + err = kgdb_arch_set_breakpoint(addr, tmp_variable); + if (err) + return err; + err = kgdb_arch_remove_breakpoint(addr, tmp_variable); + if (err) + printk(KERN_ERR "KGDB: Critical breakpoint error, kernel " + "memory destroyed at: %lx", addr); + return err; +} + unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs) { return instruction_pointer(regs); @@ -433,9 +447,14 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val) { int hex_val; int num = 0; + int negate = 0; *long_val = 0; + if (**ptr == '-') { + negate = 1; + (*ptr)++; + } while (**ptr) { hex_val = hex(**ptr); if (hex_val < 0) @@ -446,6 +465,9 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val) (*ptr)++; } + if (negate) + *long_val = -*long_val; + return num; } @@ -515,10 +537,16 @@ static void int_to_threadref(unsigned char *id, int value) static struct task_struct *getthread(struct pt_regs *regs, int tid) { /* - * Non-positive TIDs are remapped idle tasks: + * Non-positive TIDs are remapped to the cpu shadow information */ - if (tid <= 0) - return idle_task(-tid); + if (tid == 0 || tid == -1) + tid = -atomic_read(&kgdb_active) - 2; + if (tid < 0) { + if (kgdb_info[-tid - 2].task) + return kgdb_info[-tid - 2].task; + else + return idle_task(-tid - 2); + } /* * find_task_by_pid_ns() does not take the tasklist lock anymore @@ -725,14 +753,15 @@ setundefined: } /* - * Remap normal tasks to their real PID, idle tasks to -1 ... -NR_CPUs: + * Remap normal tasks to their real PID, + * CPU shadow threads are mapped to -CPU - 2 */ static inline int shadow_pid(int realpid) { if (realpid) return realpid; - return -1-raw_smp_processor_id(); + return -raw_smp_processor_id() - 2; } static char gdbmsgbuf[BUFMAX + 1]; @@ -826,7 +855,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks) local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo; } else { local_debuggerinfo = NULL; - for (i = 0; i < NR_CPUS; i++) { + for_each_online_cpu(i) { /* * Try to find the task on some other * or possibly this node if we do not @@ -960,10 +989,13 @@ static int gdb_cmd_reboot(struct kgdb_state *ks) /* Handle the 'q' query packets */ static void gdb_cmd_query(struct kgdb_state *ks) { - struct task_struct *thread; + struct task_struct *g; + struct task_struct *p; unsigned char thref[8]; char *ptr; int i; + int cpu; + int finished = 0; switch (remcom_in_buffer[1]) { case 's': @@ -973,22 +1005,34 @@ static void gdb_cmd_query(struct kgdb_state *ks) break; } - if (remcom_in_buffer[1] == 'f') - ks->threadid = 1; - + i = 0; remcom_out_buffer[0] = 'm'; ptr = remcom_out_buffer + 1; - - for (i = 0; i < 17; ks->threadid++) { - thread = getthread(ks->linux_regs, ks->threadid); - if (thread) { - int_to_threadref(thref, ks->threadid); + if (remcom_in_buffer[1] == 'f') { + /* Each cpu is a shadow thread */ + for_each_online_cpu(cpu) { + ks->thr_query = 0; + int_to_threadref(thref, -cpu - 2); pack_threadid(ptr, thref); ptr += BUF_THREAD_ID_SIZE; *(ptr++) = ','; i++; } } + + do_each_thread(g, p) { + if (i >= ks->thr_query && !finished) { + int_to_threadref(thref, p->pid); + pack_threadid(ptr, thref); + ptr += BUF_THREAD_ID_SIZE; + *(ptr++) = ','; + ks->thr_query++; + if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0) + finished = 1; + } + i++; + } while_each_thread(g, p); + *(--ptr) = '\0'; break; @@ -1011,15 +1055,15 @@ static void gdb_cmd_query(struct kgdb_state *ks) error_packet(remcom_out_buffer, -EINVAL); break; } - if (ks->threadid > 0) { + if ((int)ks->threadid > 0) { kgdb_mem2hex(getthread(ks->linux_regs, ks->threadid)->comm, remcom_out_buffer, 16); } else { static char tmpstr[23 + BUF_THREAD_ID_SIZE]; - sprintf(tmpstr, "Shadow task %d for pid 0", - (int)(-ks->threadid-1)); + sprintf(tmpstr, "shadowCPU%d", + (int)(-ks->threadid - 2)); kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr)); } break; diff --git a/kernel/kthread.c b/kernel/kthread.c index 6111c27491b..96cff2f8710 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -176,7 +176,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu) return; } /* Must have done schedule() in kthread() before we set_task_cpu */ - wait_task_inactive(k); + wait_task_inactive(k, 0); set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->rt.nr_cpus_allowed = 1; diff --git a/kernel/marker.c b/kernel/marker.c index 971da531790..7d1faecd7a5 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -126,6 +126,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) struct marker_probe_closure *multi; int i; /* + * Read mdata->ptype before mdata->multi. + */ + smp_rmb(); + multi = mdata->multi; + /* * multi points to an array, therefore accessing the array * depends on reading multi. However, even in this case, * we must insure that the pointer is read _before_ the array @@ -133,7 +138,6 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) * in the fast path, so put the explicit barrier here. */ smp_read_barrier_depends(); - multi = mdata->multi; for (i = 0; multi[i].func; i++) { va_start(args, call_private); multi[i].func(multi[i].probe_private, call_private, @@ -175,6 +179,11 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) struct marker_probe_closure *multi; int i; /* + * Read mdata->ptype before mdata->multi. + */ + smp_rmb(); + multi = mdata->multi; + /* * multi points to an array, therefore accessing the array * depends on reading multi. However, even in this case, * we must insure that the pointer is read _before_ the array @@ -182,7 +191,6 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) * in the fast path, so put the explicit barrier here. */ smp_read_barrier_depends(); - multi = mdata->multi; for (i = 0; multi[i].func; i++) multi[i].func(multi[i].probe_private, call_private, mdata->format, &args); diff --git a/kernel/module.c b/kernel/module.c index d8b5605132a..61d212120df 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -325,18 +325,6 @@ static unsigned long find_symbol(const char *name, return -ENOENT; } -/* lookup symbol in given range of kernel_symbols */ -static const struct kernel_symbol *lookup_symbol(const char *name, - const struct kernel_symbol *start, - const struct kernel_symbol *stop) -{ - const struct kernel_symbol *ks = start; - for (; ks < stop; ks++) - if (strcmp(ks->name, name) == 0) - return ks; - return NULL; -} - /* Search for module by name: must hold module_mutex. */ static struct module *find_module(const char *name) { @@ -690,7 +678,7 @@ static int try_stop_module(struct module *mod, int flags, int *forced) if (flags & O_NONBLOCK) { struct stopref sref = { mod, flags, forced }; - return stop_machine_run(__try_stop_module, &sref, NR_CPUS); + return stop_machine(__try_stop_module, &sref, NULL); } else { /* We don't need to stop the machine for this. */ mod->state = MODULE_STATE_GOING; @@ -1428,7 +1416,7 @@ static int __unlink_module(void *_mod) static void free_module(struct module *mod) { /* Delete from various lists */ - stop_machine_run(__unlink_module, mod, NR_CPUS); + stop_machine(__unlink_module, mod, NULL); remove_notes_attrs(mod); remove_sect_attrs(mod); mod_kobject_remove(mod); @@ -1703,6 +1691,19 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, } #ifdef CONFIG_KALLSYMS + +/* lookup symbol in given range of kernel_symbols */ +static const struct kernel_symbol *lookup_symbol(const char *name, + const struct kernel_symbol *start, + const struct kernel_symbol *stop) +{ + const struct kernel_symbol *ks = start; + for (; ks < stop; ks++) + if (strcmp(ks->name, name) == 0) + return ks; + return NULL; +} + static int is_exported(const char *name, const struct module *mod) { if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab)) @@ -2196,7 +2197,7 @@ static struct module *load_module(void __user *umod, /* Now sew it into the lists so we can get lockdep and oops * info during argument parsing. Noone should access us, since * strong_try_module_get() will fail. */ - stop_machine_run(__link_module, mod, NR_CPUS); + stop_machine(__link_module, mod, NULL); /* Size of section 0 is 0, so this works well if no params */ err = parse_args(mod->name, mod->args, @@ -2230,7 +2231,7 @@ static struct module *load_module(void __user *umod, return mod; unlink: - stop_machine_run(__unlink_module, mod, NR_CPUS); + stop_machine(__unlink_module, mod, NULL); module_arch_cleanup(mod); cleanup: kobject_del(&mod->mkobj.kobj); diff --git a/kernel/mutex.c b/kernel/mutex.c index bcdc9ac8ef6..12c779dc65d 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -34,6 +34,7 @@ /*** * mutex_init - initialize the mutex * @lock: the mutex to be initialized + * @key: the lock_class_key for the class; used by mutex lock debugging * * Initialize the mutex to unlocked state. * diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 8cb75702638..da9c2dda6a4 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -24,7 +24,7 @@ * 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 + * Mark Gross <mgross@linux.intel.com> */ #include <linux/pm_qos_params.h> @@ -211,8 +211,8 @@ EXPORT_SYMBOL_GPL(pm_qos_requirement); * @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. + * performance characteristics. It recomputes the aggregate QoS expectations + * for the pm_qos_class of parameters. */ int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value) { @@ -250,10 +250,10 @@ EXPORT_SYMBOL_GPL(pm_qos_add_requirement); * @name: identifies the request * @value: defines the qos request * - * Updates an existing qos requierement for the pm_qos_class of parameters along + * Updates an existing qos requirement 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. + * If the named request isn't in the list then no change is made. */ int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value) { @@ -287,7 +287,7 @@ EXPORT_SYMBOL_GPL(pm_qos_update_requirement); * @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 + * Will remove named qos request from pm_qos_class list of parameters and * recompute the current target value for the pm_qos_class. */ void pm_qos_remove_requirement(int pm_qos_class, char *name) @@ -319,7 +319,7 @@ EXPORT_SYMBOL_GPL(pm_qos_remove_requirement); * @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. + * upon changes to the pm_qos_class target value. */ int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier) { @@ -338,7 +338,7 @@ EXPORT_SYMBOL_GPL(pm_qos_add_notifier); * @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. + * upon changes to the pm_qos_class target value. */ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) { diff --git a/kernel/power/main.c b/kernel/power/main.c index 95bff23ecda..0b7476f5d2a 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -635,6 +635,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) } if (status < 0) printk(err_suspend, status); + + /* Some platforms can't detect that the alarm triggered the + * wakeup, or (accordingly) disable it after it afterwards. + * It's supposed to give oneshot behavior; cope. + */ + alm.enabled = false; + rtc_set_alarm(rtc, &alm); } static int __init has_wakealarm(struct device *dev, void *name_ptr) diff --git a/kernel/power/power.h b/kernel/power/power.h index 700f44ec840..acc0c101dbd 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void); extern int pfn_is_nosave(unsigned long); -extern struct mutex pm_mutex; - #define power_attr(_name) \ static struct kobj_attribute _name##_attr = { \ .attr = { \ diff --git a/kernel/printk.c b/kernel/printk.c index a7f7559c5f6..b51b1567bb5 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1309,14 +1309,14 @@ void tty_write_message(struct tty_struct *tty, char *msg) #if defined CONFIG_PRINTK -DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); /* * printk rate limiting, lifted from the networking subsystem. * - * This enforces a rate limit: not more than one kernel message - * every printk_ratelimit_jiffies to make a denial-of-service - * attack impossible. + * This enforces a rate limit: not more than 10 kernel messages + * every 5s to make a denial-of-service attack impossible. */ +DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); + int printk_ratelimit(void) { return __ratelimit(&printk_ratelimit_state); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 8392a9da645..082b3fcb32a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -107,7 +107,7 @@ int ptrace_check_attach(struct task_struct *child, int kill) read_unlock(&tasklist_lock); if (!ret && !kill) - wait_task_inactive(child); + ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH; /* All systems go.. */ return ret; diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index 6f8696c502f..aad93cdc9f6 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -91,8 +91,8 @@ static void force_quiescent_state(struct rcu_data *rdp, * rdp->cpu is the current cpu. * * cpu_online_map is updated by the _cpu_down() - * using stop_machine_run(). Since we're in irqs disabled - * section, stop_machine_run() is not exectuting, hence + * using __stop_machine(). Since we're in irqs disabled + * section, __stop_machine() is not exectuting, hence * the cpu_online_map is stable. * * However, a cpu might have been offlined _just_ before diff --git a/kernel/relay.c b/kernel/relay.c index 7de644cdec4..8d13a7855c0 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -407,6 +407,35 @@ void relay_reset(struct rchan *chan) } EXPORT_SYMBOL_GPL(relay_reset); +static inline void relay_set_buf_dentry(struct rchan_buf *buf, + struct dentry *dentry) +{ + buf->dentry = dentry; + buf->dentry->d_inode->i_size = buf->early_bytes; +} + +static struct dentry *relay_create_buf_file(struct rchan *chan, + struct rchan_buf *buf, + unsigned int cpu) +{ + struct dentry *dentry; + char *tmpname; + + tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); + if (!tmpname) + return NULL; + snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); + + /* Create file in fs */ + dentry = chan->cb->create_buf_file(tmpname, chan->parent, + S_IRUSR, buf, + &chan->is_global); + + kfree(tmpname); + + return dentry; +} + /* * relay_open_buf - create a new relay channel buffer * @@ -416,45 +445,34 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) { struct rchan_buf *buf = NULL; struct dentry *dentry; - char *tmpname; if (chan->is_global) return chan->buf[0]; - tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); - if (!tmpname) - goto end; - snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); - buf = relay_create_buf(chan); if (!buf) - goto free_name; + return NULL; + + if (chan->has_base_filename) { + dentry = relay_create_buf_file(chan, buf, cpu); + if (!dentry) + goto free_buf; + relay_set_buf_dentry(buf, dentry); + } buf->cpu = cpu; __relay_reset(buf, 1); - /* Create file in fs */ - dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, - buf, &chan->is_global); - if (!dentry) - goto free_buf; - - buf->dentry = dentry; - if(chan->is_global) { chan->buf[0] = buf; buf->cpu = 0; } - goto free_name; + return buf; free_buf: relay_destroy_buf(buf); - buf = NULL; -free_name: - kfree(tmpname); -end: - return buf; + return NULL; } /** @@ -537,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb, /** * relay_open - create a new relay channel - * @base_filename: base name of files to create - * @parent: dentry of parent directory, %NULL for root directory + * @base_filename: base name of files to create, %NULL for buffering only + * @parent: dentry of parent directory, %NULL for root directory or buffer * @subbuf_size: size of sub-buffers * @n_subbufs: number of sub-buffers * @cb: client callback functions @@ -560,8 +578,6 @@ struct rchan *relay_open(const char *base_filename, { unsigned int i; struct rchan *chan; - if (!base_filename) - return NULL; if (!(subbuf_size && n_subbufs)) return NULL; @@ -576,7 +592,10 @@ struct rchan *relay_open(const char *base_filename, chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs); chan->parent = parent; chan->private_data = private_data; - strlcpy(chan->base_filename, base_filename, NAME_MAX); + if (base_filename) { + chan->has_base_filename = 1; + strlcpy(chan->base_filename, base_filename, NAME_MAX); + } setup_callbacks(chan, cb); kref_init(&chan->kref); @@ -604,6 +623,94 @@ free_bufs: } EXPORT_SYMBOL_GPL(relay_open); +struct rchan_percpu_buf_dispatcher { + struct rchan_buf *buf; + struct dentry *dentry; +}; + +/* Called in atomic context. */ +static void __relay_set_buf_dentry(void *info) +{ + struct rchan_percpu_buf_dispatcher *p = info; + + relay_set_buf_dentry(p->buf, p->dentry); +} + +/** + * relay_late_setup_files - triggers file creation + * @chan: channel to operate on + * @base_filename: base name of files to create + * @parent: dentry of parent directory, %NULL for root directory + * + * Returns 0 if successful, non-zero otherwise. + * + * Use to setup files for a previously buffer-only channel. + * Useful to do early tracing in kernel, before VFS is up, for example. + */ +int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent) +{ + int err = 0; + unsigned int i, curr_cpu; + unsigned long flags; + struct dentry *dentry; + struct rchan_percpu_buf_dispatcher disp; + + if (!chan || !base_filename) + return -EINVAL; + + strlcpy(chan->base_filename, base_filename, NAME_MAX); + + mutex_lock(&relay_channels_mutex); + /* Is chan already set up? */ + if (unlikely(chan->has_base_filename)) + return -EEXIST; + chan->has_base_filename = 1; + chan->parent = parent; + curr_cpu = get_cpu(); + /* + * The CPU hotplug notifier ran before us and created buffers with + * no files associated. So it's safe to call relay_setup_buf_file() + * on all currently online CPUs. + */ + for_each_online_cpu(i) { + if (unlikely(!chan->buf[i])) { + printk(KERN_ERR "relay_late_setup_files: CPU %u " + "has no buffer, it must have!\n", i); + BUG(); + err = -EINVAL; + break; + } + + dentry = relay_create_buf_file(chan, chan->buf[i], i); + if (unlikely(!dentry)) { + err = -EINVAL; + break; + } + + if (curr_cpu == i) { + local_irq_save(flags); + relay_set_buf_dentry(chan->buf[i], dentry); + local_irq_restore(flags); + } else { + disp.buf = chan->buf[i]; + disp.dentry = dentry; + smp_mb(); + /* relay_channels_mutex must be held, so wait. */ + err = smp_call_function_single(i, + __relay_set_buf_dentry, + &disp, 1); + } + if (unlikely(err)) + break; + } + put_cpu(); + mutex_unlock(&relay_channels_mutex); + + return err; +} + /** * relay_switch_subbuf - switch to a new sub-buffer * @buf: channel buffer @@ -627,8 +734,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; buf->padding[old_subbuf] = buf->prev_padding; buf->subbufs_produced++; - buf->dentry->d_inode->i_size += buf->chan->subbuf_size - - buf->padding[old_subbuf]; + if (buf->dentry) + buf->dentry->d_inode->i_size += + buf->chan->subbuf_size - + buf->padding[old_subbuf]; + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; smp_mb(); if (waitqueue_active(&buf->read_wait)) /* @@ -832,6 +944,10 @@ static void relay_file_read_consume(struct rchan_buf *buf, size_t n_subbufs = buf->chan->n_subbufs; size_t read_subbuf; + if (buf->subbufs_produced == buf->subbufs_consumed && + buf->offset == buf->bytes_consumed) + return; + if (buf->bytes_consumed + bytes_consumed > subbuf_size) { relay_subbufs_consumed(buf->chan, buf->cpu, 1); buf->bytes_consumed = 0; @@ -863,6 +979,8 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos) relay_file_read_consume(buf, read_pos, 0); + consumed = buf->subbufs_consumed; + if (unlikely(buf->offset > subbuf_size)) { if (produced == consumed) return 0; @@ -881,8 +999,12 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos) if (consumed > produced) produced += n_subbufs * subbuf_size; - if (consumed == produced) + if (consumed == produced) { + if (buf->offset == subbuf_size && + buf->subbufs_produced > buf->subbufs_consumed) + return 1; return 0; + } return 1; } @@ -1237,4 +1359,4 @@ static __init int relay_init(void) return 0; } -module_init(relay_init); +early_initcall(relay_init); diff --git a/kernel/resource.c b/kernel/resource.c index 74af2d7cb5a..f5b518eabef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -490,7 +490,7 @@ resource_size_t resource_alignment(struct resource *res) { switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) { case IORESOURCE_SIZEALIGN: - return res->end - res->start + 1; + return resource_size(res); case IORESOURCE_STARTALIGN: return res->start; default: diff --git a/kernel/sched.c b/kernel/sched.c index 0047bd9b96a..04160d277e7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1867,16 +1867,24 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) /* * wait_task_inactive - wait for a thread to unschedule. * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * * The caller must ensure that the task *will* unschedule sometime soon, * else this function might spin for a *long* time. This function can't * be called with interrupts off, or it may introduce deadlock with * smp_call_function() if an IPI is sent by the same process we are * waiting to become inactive. */ -void wait_task_inactive(struct task_struct *p) +unsigned long wait_task_inactive(struct task_struct *p, long match_state) { unsigned long flags; int running, on_rq; + unsigned long ncsw; struct rq *rq; for (;;) { @@ -1899,8 +1907,11 @@ void wait_task_inactive(struct task_struct *p) * return false if the runqueue has changed and p * is actually now running somewhere else! */ - while (task_running(rq, p)) + while (task_running(rq, p)) { + if (match_state && unlikely(p->state != match_state)) + return 0; cpu_relax(); + } /* * Ok, time to look more closely! We need the rq @@ -1910,9 +1921,21 @@ void wait_task_inactive(struct task_struct *p) rq = task_rq_lock(p, &flags); running = task_running(rq, p); on_rq = p->se.on_rq; + ncsw = 0; + if (!match_state || p->state == match_state) { + ncsw = p->nivcsw + p->nvcsw; + if (unlikely(!ncsw)) + ncsw = 1; + } task_rq_unlock(rq, &flags); /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* * Was it really running after all now that we * checked with the proper locks actually held? * @@ -1944,6 +1967,8 @@ void wait_task_inactive(struct task_struct *p) */ break; } + + return ncsw; } /*** @@ -4979,19 +5004,21 @@ recheck: return -EPERM; } + if (user) { #ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (user - && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) - return -EPERM; + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) + return -EPERM; #endif - retval = security_task_setscheduler(p, policy, param); - if (retval) - return retval; + retval = security_task_setscheduler(p, policy, param); + if (retval) + return retval; + } + /* * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: @@ -6389,7 +6416,7 @@ static struct notifier_block __cpuinitdata migration_notifier = { .priority = 10 }; -void __init migration_init(void) +static int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; @@ -6399,7 +6426,10 @@ void __init migration_init(void) BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); + + return err; } +early_initcall(migration_init); #endif #ifdef CONFIG_SMP @@ -7643,34 +7673,34 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) } #ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct sys_device *dev, - struct sysdev_attribute *attr, char *page) +static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + char *page) { return sprintf(page, "%u\n", sched_mc_power_savings); } -static ssize_t sched_mc_power_savings_store(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); } -static SYSDEV_ATTR(sched_mc_power_savings, 0644, sched_mc_power_savings_show, - sched_mc_power_savings_store); +static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, + sched_mc_power_savings_show, + sched_mc_power_savings_store); #endif #ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct sys_device *dev, - struct sysdev_attribute *attr, char *page) +static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, + char *page) { return sprintf(page, "%u\n", sched_smt_power_savings); } -static ssize_t sched_smt_power_savings_store(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); } -static SYSDEV_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_show, +static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, + sched_smt_power_savings_show, sched_smt_power_savings_store); #endif diff --git a/kernel/semaphore.c b/kernel/semaphore.c index aaaeae8244e..94a62c0d4ad 100644 --- a/kernel/semaphore.c +++ b/kernel/semaphore.c @@ -212,9 +212,7 @@ static inline int __sched __down_common(struct semaphore *sem, long state, waiter.up = 0; for (;;) { - if (state == TASK_INTERRUPTIBLE && signal_pending(task)) - goto interrupted; - if (state == TASK_KILLABLE && fatal_signal_pending(task)) + if (signal_pending_state(state, task)) goto interrupted; if (timeout <= 0) goto timed_out; diff --git a/kernel/signal.c b/kernel/signal.c index 82c3545596c..954f77d7e3b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -22,6 +22,7 @@ #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/signalfd.h> +#include <linux/tracehook.h> #include <linux/capability.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> @@ -39,24 +40,21 @@ static struct kmem_cache *sigqueue_cachep; -static int __sig_ignored(struct task_struct *t, int sig) +static void __user *sig_handler(struct task_struct *t, int sig) { - void __user *handler; + return t->sighand->action[sig - 1].sa.sa_handler; +} +static int sig_handler_ignored(void __user *handler, int sig) +{ /* Is it explicitly or implicitly ignored? */ - - handler = t->sighand->action[sig - 1].sa.sa_handler; return handler == SIG_IGN || (handler == SIG_DFL && sig_kernel_ignore(sig)); } static int sig_ignored(struct task_struct *t, int sig) { - /* - * Tracers always want to know about signals.. - */ - if (t->ptrace & PT_PTRACED) - return 0; + void __user *handler; /* * Blocked signals are never ignored, since the @@ -66,7 +64,14 @@ static int sig_ignored(struct task_struct *t, int sig) if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return 0; - return __sig_ignored(t, sig); + handler = sig_handler(t, sig); + if (!sig_handler_ignored(handler, sig)) + return 0; + + /* + * Tracers may want to know about even ignored signals. + */ + return !tracehook_consider_ignored_signal(t, sig, handler); } /* @@ -129,7 +134,9 @@ void recalc_sigpending_and_wake(struct task_struct *t) void recalc_sigpending(void) { - if (!recalc_sigpending_tsk(current) && !freezing(current)) + if (unlikely(tracehook_force_sigpending())) + set_thread_flag(TIF_SIGPENDING); + else if (!recalc_sigpending_tsk(current) && !freezing(current)) clear_thread_flag(TIF_SIGPENDING); } @@ -295,12 +302,12 @@ flush_signal_handlers(struct task_struct *t, int force_default) int unhandled_signal(struct task_struct *tsk, int sig) { + void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler; if (is_global_init(tsk)) return 1; - if (tsk->ptrace & PT_PTRACED) + if (handler != SIG_IGN && handler != SIG_DFL) return 0; - return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) || - (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL); + return !tracehook_consider_fatal_signal(tsk, sig, handler); } @@ -591,9 +598,6 @@ static int check_kill_permission(int sig, struct siginfo *info, return security_task_kill(t, info, sig, 0); } -/* forward decl */ -static void do_notify_parent_cldstop(struct task_struct *tsk, int why); - /* * Handle magic process-wide effects of stop/continue signals. Unlike * the signal actions, these happen immediately at signal-generation @@ -756,7 +760,8 @@ static void complete_signal(int sig, struct task_struct *p, int group) if (sig_fatal(p, sig) && !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && - (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) { + (sig == SIGKILL || + !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) { /* * This signal will be fatal to the whole group. */ @@ -1323,9 +1328,11 @@ static inline void __wake_up_parent(struct task_struct *p, /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. + * + * Returns -1 if our parent ignored us and so we've switched to + * self-reaping, or else @sig. */ - -void do_notify_parent(struct task_struct *tsk, int sig) +int do_notify_parent(struct task_struct *tsk, int sig) { struct siginfo info; unsigned long flags; @@ -1396,12 +1403,14 @@ void do_notify_parent(struct task_struct *tsk, int sig) */ tsk->exit_signal = -1; if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) - sig = 0; + sig = -1; } if (valid_signal(sig) && sig > 0) __group_send_sig_info(sig, &info, tsk->parent); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); + + return sig; } static void do_notify_parent_cldstop(struct task_struct *tsk, int why) @@ -1599,7 +1608,7 @@ finish_stop(int stop_count) * a group stop in progress and we are the last to stop, * report to the parent. When ptraced, every thread reports itself. */ - if (stop_count == 0 || (current->ptrace & PT_PTRACED)) { + if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) { read_lock(&tasklist_lock); do_notify_parent_cldstop(current, CLD_STOPPED); read_unlock(&tasklist_lock); @@ -1735,6 +1744,9 @@ relock: signal->flags &= ~SIGNAL_CLD_MASK; spin_unlock_irq(&sighand->siglock); + if (unlikely(!tracehook_notify_jctl(1, why))) + goto relock; + read_lock(&tasklist_lock); do_notify_parent_cldstop(current->group_leader, why); read_unlock(&tasklist_lock); @@ -1748,17 +1760,33 @@ relock: do_signal_stop(0)) goto relock; - signr = dequeue_signal(current, ¤t->blocked, info); - if (!signr) - break; /* will return 0 */ + /* + * Tracing can induce an artifical signal and choose sigaction. + * The return value in @signr determines the default action, + * but @info->si_signo is the signal number we will report. + */ + signr = tracehook_get_signal(current, regs, info, return_ka); + if (unlikely(signr < 0)) + goto relock; + if (unlikely(signr != 0)) + ka = return_ka; + else { + signr = dequeue_signal(current, ¤t->blocked, + info); - if (signr != SIGKILL) { - signr = ptrace_signal(signr, info, regs, cookie); if (!signr) - continue; + break; /* will return 0 */ + + if (signr != SIGKILL) { + signr = ptrace_signal(signr, info, + regs, cookie); + if (!signr) + continue; + } + + ka = &sighand->action[signr-1]; } - ka = &sighand->action[signr-1]; if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ continue; if (ka->sa.sa_handler != SIG_DFL) { @@ -1806,7 +1834,7 @@ relock: spin_lock_irq(&sighand->siglock); } - if (likely(do_signal_stop(signr))) { + if (likely(do_signal_stop(info->si_signo))) { /* It released the siglock. */ goto relock; } @@ -1827,7 +1855,7 @@ relock: if (sig_kernel_coredump(signr)) { if (print_fatal_signals) - print_fatal_signal(regs, signr); + print_fatal_signal(regs, info->si_signo); /* * If it was able to dump core, this kills all * other threads in the group and synchronizes with @@ -1836,13 +1864,13 @@ relock: * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ - do_coredump((long)signr, signr, regs); + do_coredump(info->si_signo, info->si_signo, regs); } /* * Death signals, no core dump. */ - do_group_exit(signr); + do_group_exit(info->si_signo); /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); @@ -1884,7 +1912,7 @@ void exit_signals(struct task_struct *tsk) out: spin_unlock_irq(&tsk->sighand->siglock); - if (unlikely(group_stop)) { + if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) { read_lock(&tasklist_lock); do_notify_parent_cldstop(tsk, CLD_STOPPED); read_unlock(&tasklist_lock); @@ -1895,7 +1923,6 @@ EXPORT_SYMBOL(recalc_sigpending); EXPORT_SYMBOL_GPL(dequeue_signal); EXPORT_SYMBOL(flush_signals); EXPORT_SYMBOL(force_sig); -EXPORT_SYMBOL(ptrace_notify); EXPORT_SYMBOL(send_sig); EXPORT_SYMBOL(send_sig_info); EXPORT_SYMBOL(sigprocmask); @@ -2299,7 +2326,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) * (for example, SIGCHLD), shall cause the pending signal to * be discarded, whether or not it is blocked" */ - if (__sig_ignored(t, sig)) { + if (sig_handler_ignored(sig_handler(t, sig), sig)) { sigemptyset(&mask); sigaddset(&mask, sig); rm_from_queue_full(&mask, &t->signal->shared_pending); diff --git a/kernel/smp.c b/kernel/smp.c index 462c785ca1e..96fc7c0edc5 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -33,7 +33,7 @@ struct call_single_queue { spinlock_t lock; }; -void __cpuinit init_call_single_data(void) +static int __cpuinit init_call_single_data(void) { int i; @@ -43,7 +43,9 @@ void __cpuinit init_call_single_data(void) spin_lock_init(&q->lock); INIT_LIST_HEAD(&q->list); } + return 0; } +early_initcall(init_call_single_data); static void csd_flag_wait(struct call_single_data *data) { diff --git a/kernel/softirq.c b/kernel/softirq.c index f6b03d56c2b..c506f266a6b 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -630,7 +630,7 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; -__init int spawn_ksoftirqd(void) +static __init int spawn_ksoftirqd(void) { void *cpu = (void *)(long)smp_processor_id(); int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); @@ -640,6 +640,7 @@ __init int spawn_ksoftirqd(void) register_cpu_notifier(&cpu_nfb); return 0; } +early_initcall(spawn_ksoftirqd); #ifdef CONFIG_SMP /* diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 7bd8d1aadd5..b75b492fbfc 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -338,14 +338,33 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; -__init void spawn_softlockup_task(void) +static int __initdata nosoftlockup; + +static int __init nosoftlockup_setup(char *str) +{ + nosoftlockup = 1; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); + +static int __init spawn_softlockup_task(void) { void *cpu = (void *)(long)smp_processor_id(); - int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + int err; - BUG_ON(err == NOTIFY_BAD); + if (nosoftlockup) + return 0; + + err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + if (err == NOTIFY_BAD) { + BUG(); + return 1; + } cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + return 0; } +early_initcall(spawn_softlockup_task); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 738b411ff2d..e446c7c7d6a 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -1,4 +1,4 @@ -/* Copyright 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation. +/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation. * GPL v2 and any later version. */ #include <linux/cpu.h> @@ -13,204 +13,178 @@ #include <asm/atomic.h> #include <asm/uaccess.h> -/* Since we effect priority and affinity (both of which are visible - * to, and settable by outside processes) we do indirection via a - * kthread. */ - -/* Thread to stop each CPU in user context. */ +/* This controls the threads on each CPU. */ enum stopmachine_state { - STOPMACHINE_WAIT, + /* Dummy starting state for thread. */ + STOPMACHINE_NONE, + /* Awaiting everyone to be scheduled. */ STOPMACHINE_PREPARE, + /* Disable interrupts. */ STOPMACHINE_DISABLE_IRQ, + /* Run the function */ + STOPMACHINE_RUN, + /* Exit */ STOPMACHINE_EXIT, }; +static enum stopmachine_state state; -static enum stopmachine_state stopmachine_state; -static unsigned int stopmachine_num_threads; -static atomic_t stopmachine_thread_ack; - -static int stopmachine(void *cpu) -{ - int irqs_disabled = 0; - int prepared = 0; - cpumask_of_cpu_ptr(cpumask, (int)(long)cpu); - - set_cpus_allowed_ptr(current, cpumask); - - /* Ack: we are alive */ - smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */ - atomic_inc(&stopmachine_thread_ack); - - /* Simple state machine */ - while (stopmachine_state != STOPMACHINE_EXIT) { - if (stopmachine_state == STOPMACHINE_DISABLE_IRQ - && !irqs_disabled) { - local_irq_disable(); - hard_irq_disable(); - irqs_disabled = 1; - /* Ack: irqs disabled. */ - smp_mb(); /* Must read state first. */ - atomic_inc(&stopmachine_thread_ack); - } else if (stopmachine_state == STOPMACHINE_PREPARE - && !prepared) { - /* Everyone is in place, hold CPU. */ - preempt_disable(); - prepared = 1; - smp_mb(); /* Must read state first. */ - atomic_inc(&stopmachine_thread_ack); - } - /* Yield in first stage: migration threads need to - * help our sisters onto their CPUs. */ - if (!prepared && !irqs_disabled) - yield(); - cpu_relax(); - } - - /* Ack: we are exiting. */ - smp_mb(); /* Must read state first. */ - atomic_inc(&stopmachine_thread_ack); - - if (irqs_disabled) - local_irq_enable(); - if (prepared) - preempt_enable(); +struct stop_machine_data { + int (*fn)(void *); + void *data; + int fnret; +}; - return 0; -} +/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ +static unsigned int num_threads; +static atomic_t thread_ack; +static struct completion finished; +static DEFINE_MUTEX(lock); -/* Change the thread state */ -static void stopmachine_set_state(enum stopmachine_state state) +static void set_state(enum stopmachine_state newstate) { - atomic_set(&stopmachine_thread_ack, 0); + /* Reset ack counter. */ + atomic_set(&thread_ack, num_threads); smp_wmb(); - stopmachine_state = state; - while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) - cpu_relax(); + state = newstate; } -static int stop_machine(void) +/* Last one to ack a state moves to the next state. */ +static void ack_state(void) { - int i, ret = 0; - - atomic_set(&stopmachine_thread_ack, 0); - stopmachine_num_threads = 0; - stopmachine_state = STOPMACHINE_WAIT; - - for_each_online_cpu(i) { - if (i == raw_smp_processor_id()) - continue; - ret = kernel_thread(stopmachine, (void *)(long)i,CLONE_KERNEL); - if (ret < 0) - break; - stopmachine_num_threads++; - } - - /* Wait for them all to come to life. */ - while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) { - yield(); - cpu_relax(); + if (atomic_dec_and_test(&thread_ack)) { + /* If we're the last one to ack the EXIT, we're finished. */ + if (state == STOPMACHINE_EXIT) + complete(&finished); + else + set_state(state + 1); } +} - /* If some failed, kill them all. */ - if (ret < 0) { - stopmachine_set_state(STOPMACHINE_EXIT); - return ret; - } +/* This is the actual thread which stops the CPU. It exits by itself rather + * than waiting for kthread_stop(), because it's easier for hotplug CPU. */ +static int stop_cpu(struct stop_machine_data *smdata) +{ + enum stopmachine_state curstate = STOPMACHINE_NONE; + int uninitialized_var(ret); - /* Now they are all started, make them hold the CPUs, ready. */ - preempt_disable(); - stopmachine_set_state(STOPMACHINE_PREPARE); + /* Simple state machine */ + do { + /* Chill out and ensure we re-read stopmachine_state. */ + cpu_relax(); + if (state != curstate) { + curstate = state; + switch (curstate) { + case STOPMACHINE_DISABLE_IRQ: + local_irq_disable(); + hard_irq_disable(); + break; + case STOPMACHINE_RUN: + /* |= allows error detection if functions on + * multiple CPUs. */ + smdata->fnret |= smdata->fn(smdata->data); + break; + default: + break; + } + ack_state(); + } + } while (curstate != STOPMACHINE_EXIT); - /* Make them disable irqs. */ - local_irq_disable(); - hard_irq_disable(); - stopmachine_set_state(STOPMACHINE_DISABLE_IRQ); + local_irq_enable(); + do_exit(0); +} +/* Callback for CPUs which aren't supposed to do anything. */ +static int chill(void *unused) +{ return 0; } -static void restart_machine(void) +int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { - stopmachine_set_state(STOPMACHINE_EXIT); - local_irq_enable(); - preempt_enable_no_resched(); -} + int i, err; + struct stop_machine_data active, idle; + struct task_struct **threads; + + active.fn = fn; + active.data = data; + active.fnret = 0; + idle.fn = chill; + idle.data = NULL; + + /* This could be too big for stack on large machines. */ + threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL); + if (!threads) + return -ENOMEM; + + /* Set up initial state. */ + mutex_lock(&lock); + init_completion(&finished); + num_threads = num_online_cpus(); + set_state(STOPMACHINE_PREPARE); -struct stop_machine_data { - int (*fn)(void *); - void *data; - struct completion done; -}; + for_each_online_cpu(i) { + struct stop_machine_data *smdata = &idle; + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; -static int do_stop(void *_smdata) -{ - struct stop_machine_data *smdata = _smdata; - int ret; + if (!cpus) { + if (i == first_cpu(cpu_online_map)) + smdata = &active; + } else { + if (cpu_isset(i, *cpus)) + smdata = &active; + } - ret = stop_machine(); - if (ret == 0) { - ret = smdata->fn(smdata->data); - restart_machine(); - } + threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u", + i); + if (IS_ERR(threads[i])) { + err = PTR_ERR(threads[i]); + threads[i] = NULL; + goto kill_threads; + } - /* We're done: you can kthread_stop us now */ - complete(&smdata->done); + /* Place it onto correct cpu. */ + kthread_bind(threads[i], i); - /* Wait for kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_INTERRUPTIBLE); + /* Make it highest prio. */ + if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, ¶m)) + BUG(); } - __set_current_state(TASK_RUNNING); - return ret; -} -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; + /* We've created all the threads. Wake them all: hold this CPU so one + * doesn't hit this CPU until we're ready. */ + get_cpu(); + for_each_online_cpu(i) + wake_up_process(threads[i]); - smdata.fn = fn; - smdata.data = data; - init_completion(&smdata.done); + /* This will release the thread on our CPU. */ + put_cpu(); + wait_for_completion(&finished); + mutex_unlock(&lock); - mutex_lock(&stopmachine_mutex); + kfree(threads); - /* If they don't care which CPU fn runs on, bind to any online one. */ - if (cpu == NR_CPUS) - cpu = raw_smp_processor_id(); + return active.fnret; - p = kthread_create(do_stop, &smdata, "kstopmachine"); - if (!IS_ERR(p)) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; +kill_threads: + for_each_online_cpu(i) + if (threads[i]) + kthread_stop(threads[i]); + mutex_unlock(&lock); - /* One high-prio thread per cpu. We'll do this one. */ - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); - kthread_bind(p, cpu); - wake_up_process(p); - wait_for_completion(&smdata.done); - } - mutex_unlock(&stopmachine_mutex); - return p; + kfree(threads); + return err; } -int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu) +int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { - struct task_struct *p; int ret; /* No CPUs can come up or down during this. */ get_online_cpus(); - p = __stop_machine_run(fn, data, cpu); - if (!IS_ERR(p)) - ret = kthread_stop(p); - else - ret = PTR_ERR(p); + ret = __stop_machine(fn, data, cpus); put_online_cpus(); return ret; } -EXPORT_SYMBOL_GPL(stop_machine_run); +EXPORT_SYMBOL_GPL(stop_machine); diff --git a/kernel/sys.c b/kernel/sys.c index 0c9d3fa1f5f..c01858090a9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -301,26 +301,6 @@ void kernel_restart(char *cmd) } EXPORT_SYMBOL_GPL(kernel_restart); -/** - * kernel_kexec - reboot the system - * - * Move into place and start executing a preloaded standalone - * executable. If nothing was preloaded return an error. - */ -static void kernel_kexec(void) -{ -#ifdef CONFIG_KEXEC - struct kimage *image; - image = xchg(&kexec_image, NULL); - if (!image) - return; - kernel_restart_prepare(NULL); - printk(KERN_EMERG "Starting new kernel\n"); - machine_shutdown(); - machine_kexec(image); -#endif -} - static void kernel_shutdown_prepare(enum system_states state) { blocking_notifier_call_chain(&reboot_notifier_list, @@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user kernel_restart(buffer); break; +#ifdef CONFIG_KEXEC case LINUX_REBOOT_CMD_KEXEC: - kernel_kexec(); - unlock_kernel(); - return -EINVAL; + { + int ret; + ret = kernel_kexec(); + unlock_kernel(); + return ret; + } +#endif #ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 35a50db9b6c..fe471334727 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -160,12 +160,13 @@ static struct ctl_table root_table[]; static struct ctl_table_root sysctl_table_root; static struct ctl_table_header root_table_header = { .ctl_table = root_table, - .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list), + .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list), .root = &sysctl_table_root, + .set = &sysctl_table_root.default_set, }; static struct ctl_table_root sysctl_table_root = { .root_list = LIST_HEAD_INIT(sysctl_table_root.root_list), - .header_list = LIST_HEAD_INIT(root_table_header.ctl_entry), + .default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry), }; static struct ctl_table kern_table[]; @@ -1386,6 +1387,9 @@ static void start_unregistering(struct ctl_table_header *p) spin_unlock(&sysctl_lock); wait_for_completion(&wait); spin_lock(&sysctl_lock); + } else { + /* anything non-NULL; we'll never dereference it */ + p->unregistering = ERR_PTR(-EINVAL); } /* * do not remove from the list until nobody holds it; walking the @@ -1394,6 +1398,32 @@ static void start_unregistering(struct ctl_table_header *p) list_del_init(&p->ctl_entry); } +void sysctl_head_get(struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + head->count++; + spin_unlock(&sysctl_lock); +} + +void sysctl_head_put(struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + if (!--head->count) + kfree(head); + spin_unlock(&sysctl_lock); +} + +struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) +{ + if (!head) + BUG(); + spin_lock(&sysctl_lock); + if (!use_table(head)) + head = ERR_PTR(-ENOENT); + spin_unlock(&sysctl_lock); + return head; +} + void sysctl_head_finish(struct ctl_table_header *head) { if (!head) @@ -1403,14 +1433,20 @@ void sysctl_head_finish(struct ctl_table_header *head) spin_unlock(&sysctl_lock); } +static struct ctl_table_set * +lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces) +{ + struct ctl_table_set *set = &root->default_set; + if (root->lookup) + set = root->lookup(root, namespaces); + return set; +} + static struct list_head * lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces) { - struct list_head *header_list; - header_list = &root->header_list; - if (root->lookup) - header_list = root->lookup(root, namespaces); - return header_list; + struct ctl_table_set *set = lookup_header_set(root, namespaces); + return &set->list; } struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, @@ -1480,9 +1516,9 @@ static int do_sysctl_strategy(struct ctl_table_root *root, int op = 0, rc; if (oldval) - op |= 004; + op |= MAY_READ; if (newval) - op |= 002; + op |= MAY_WRITE; if (sysctl_perm(root, table, op)) return -EPERM; @@ -1524,7 +1560,7 @@ repeat: if (n == table->ctl_name) { int error; if (table->child) { - if (sysctl_perm(root, table, 001)) + if (sysctl_perm(root, table, MAY_EXEC)) return -EPERM; name++; nlen--; @@ -1599,7 +1635,7 @@ static int test_perm(int mode, int op) mode >>= 6; else if (in_egroup_p(0)) mode >>= 3; - if ((mode & op & 0007) == op) + if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) return 0; return -EACCES; } @@ -1609,7 +1645,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) int error; int mode; - error = security_sysctl(table, op); + error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC)); if (error) return error; @@ -1644,6 +1680,54 @@ static __init int sysctl_init(void) core_initcall(sysctl_init); +static struct ctl_table *is_branch_in(struct ctl_table *branch, + struct ctl_table *table) +{ + struct ctl_table *p; + const char *s = branch->procname; + + /* branch should have named subdirectory as its first element */ + if (!s || !branch->child) + return NULL; + + /* ... and nothing else */ + if (branch[1].procname || branch[1].ctl_name) + return NULL; + + /* table should contain subdirectory with the same name */ + for (p = table; p->procname || p->ctl_name; p++) { + if (!p->child) + continue; + if (p->procname && strcmp(p->procname, s) == 0) + return p; + } + return NULL; +} + +/* see if attaching q to p would be an improvement */ +static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) +{ + struct ctl_table *to = p->ctl_table, *by = q->ctl_table; + struct ctl_table *next; + int is_better = 0; + int not_in_parent = !p->attached_by; + + while ((next = is_branch_in(by, to)) != NULL) { + if (by == q->attached_by) + is_better = 1; + if (to == p->attached_by) + not_in_parent = 1; + by = by->child; + to = next->child; + } + + if (is_better && not_in_parent) { + q->attached_by = by; + q->attached_to = to; + q->parent = p; + } +} + /** * __register_sysctl_paths - register a sysctl hierarchy * @root: List of sysctl headers to register on @@ -1720,10 +1804,10 @@ struct ctl_table_header *__register_sysctl_paths( struct nsproxy *namespaces, const struct ctl_path *path, struct ctl_table *table) { - struct list_head *header_list; struct ctl_table_header *header; struct ctl_table *new, **prevp; unsigned int n, npath; + struct ctl_table_set *set; /* Count the path components */ for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath) @@ -1765,6 +1849,7 @@ struct ctl_table_header *__register_sysctl_paths( header->unregistering = NULL; header->root = root; sysctl_set_parent(NULL, header->ctl_table); + header->count = 1; #ifdef CONFIG_SYSCTL_SYSCALL_CHECK if (sysctl_check_table(namespaces, header->ctl_table)) { kfree(header); @@ -1772,8 +1857,20 @@ struct ctl_table_header *__register_sysctl_paths( } #endif spin_lock(&sysctl_lock); - header_list = lookup_header_list(root, namespaces); - list_add_tail(&header->ctl_entry, header_list); + header->set = lookup_header_set(root, namespaces); + header->attached_by = header->ctl_table; + header->attached_to = root_table; + header->parent = &root_table_header; + for (set = header->set; set; set = set->parent) { + struct ctl_table_header *p; + list_for_each_entry(p, &set->list, ctl_entry) { + if (p->unregistering) + continue; + try_attach(p, header); + } + } + header->parent->count++; + list_add_tail(&header->ctl_entry, &header->set->list); spin_unlock(&sysctl_lock); return header; @@ -1828,8 +1925,37 @@ void unregister_sysctl_table(struct ctl_table_header * header) spin_lock(&sysctl_lock); start_unregistering(header); + if (!--header->parent->count) { + WARN_ON(1); + kfree(header->parent); + } + if (!--header->count) + kfree(header); spin_unlock(&sysctl_lock); - kfree(header); +} + +int sysctl_is_seen(struct ctl_table_header *p) +{ + struct ctl_table_set *set = p->set; + int res; + spin_lock(&sysctl_lock); + if (p->unregistering) + res = 0; + else if (!set->is_seen) + res = 1; + else + res = set->is_seen(set); + spin_unlock(&sysctl_lock); + return res; +} + +void setup_sysctl_set(struct ctl_table_set *p, + struct ctl_table_set *parent, + int (*is_seen)(struct ctl_table_set *)) +{ + INIT_LIST_HEAD(&p->list); + p->parent = parent ? parent : &sysctl_table_root.default_set; + p->is_seen = is_seen; } #else /* !CONFIG_SYSCTL */ @@ -1848,6 +1974,16 @@ void unregister_sysctl_table(struct ctl_table_header * table) { } +void setup_sysctl_set(struct ctl_table_set *p, + struct ctl_table_set *parent, + int (*is_seen)(struct ctl_table_set *)) +{ +} + +void sysctl_head_put(struct ctl_table_header *head) +{ +} + #endif /* CONFIG_SYSCTL */ /* diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index bf43284d685..80c4336f418 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -196,12 +196,10 @@ static int tick_check_new_device(struct clock_event_device *newdev) struct tick_device *td; int cpu, ret = NOTIFY_OK; unsigned long flags; - cpumask_of_cpu_ptr_declare(cpumask); spin_lock_irqsave(&tick_device_lock, flags); cpu = smp_processor_id(); - cpumask_of_cpu_ptr_next(cpumask, cpu); if (!cpu_isset(cpu, newdev->cpumask)) goto out_bc; @@ -209,7 +207,7 @@ static int tick_check_new_device(struct clock_event_device *newdev) curdev = td->evtdev; /* cpu local device ? */ - if (!cpus_equal(newdev->cpumask, *cpumask)) { + if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) { /* * If the cpu affinity of the device interrupt can not @@ -222,7 +220,7 @@ static int tick_check_new_device(struct clock_event_device *newdev) * If we have a cpu local device already, do not replace it * by a non cpu local device */ - if (curdev && cpus_equal(curdev->cpumask, *cpumask)) + if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu))) goto out_bc; } @@ -254,7 +252,7 @@ static int tick_check_new_device(struct clock_event_device *newdev) curdev = NULL; } clockevents_exchange_device(curdev, newdev); - tick_setup_device(td, newdev, cpu, cpumask); + tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4231a3dc224..f6e3af31b40 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -587,7 +587,7 @@ static int __ftrace_modify_code(void *data) static void ftrace_run_update_code(int command) { - stop_machine_run(__ftrace_modify_code, &command, NR_CPUS); + stop_machine(__ftrace_modify_code, &command, NULL); } void ftrace_disable_daemon(void) @@ -787,7 +787,7 @@ static int ftrace_update_code(void) !ftrace_enabled || !ftraced_trigger) return 0; - stop_machine_run(__ftrace_update_code, NULL, NR_CPUS); + stop_machine(__ftrace_update_code, NULL, NULL); return 1; } @@ -1564,7 +1564,7 @@ static int __init ftrace_dynamic_init(void) addr = (unsigned long)ftrace_record_ip; - stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS); + stop_machine(ftrace_dyn_arch_init, &addr, NULL); /* ftrace_dyn_arch_init places the return code in addr */ if (addr) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 868e121c8e3..8f3fb3db61c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1183,7 +1183,6 @@ static void *find_next_entry_inc(struct trace_iterator *iter) static void *s_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_iterator *iter = m->private; - void *last_ent = iter->ent; int i = (int)*pos; void *ent; @@ -1203,9 +1202,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) iter->pos = *pos; - if (last_ent && !ent) - seq_puts(m, "\n\nvim:ft=help\n"); - return ent; } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 421d6fe3650..ece6cfb649f 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -253,12 +253,14 @@ void start_critical_timings(void) if (preempt_trace() || irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } +EXPORT_SYMBOL_GPL(start_critical_timings); void stop_critical_timings(void) { if (preempt_trace() || irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } +EXPORT_SYMBOL_GPL(stop_critical_timings); #ifdef CONFIG_IRQSOFF_TRACER #ifdef CONFIG_PROVE_LOCKING @@ -337,12 +339,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { - stop_critical_timing(a0, a1); + if (preempt_trace()) + stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { - start_critical_timing(a0, a1); + if (preempt_trace()) + start_critical_timing(a0, a1); } #endif /* CONFIG_PREEMPT_TRACER */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 3c8d61df447..e303ccb62cd 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -26,7 +26,8 @@ static struct task_struct *wakeup_task; static int wakeup_cpu; static unsigned wakeup_prio = -1; -static DEFINE_SPINLOCK(wakeup_lock); +static raw_spinlock_t wakeup_lock = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; static void __wakeup_reset(struct trace_array *tr); @@ -56,7 +57,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) if (unlikely(disabled != 1)) goto out; - spin_lock_irqsave(&wakeup_lock, flags); + local_irq_save(flags); + __raw_spin_lock(&wakeup_lock); if (unlikely(!wakeup_task)) goto unlock; @@ -71,7 +73,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) trace_function(tr, data, ip, parent_ip, flags); unlock: - spin_unlock_irqrestore(&wakeup_lock, flags); + __raw_spin_unlock(&wakeup_lock); + local_irq_restore(flags); out: atomic_dec(&data->disabled); @@ -145,7 +148,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev, if (likely(disabled != 1)) goto out; - spin_lock_irqsave(&wakeup_lock, flags); + local_irq_save(flags); + __raw_spin_lock(&wakeup_lock); /* We could race with grabbing wakeup_lock */ if (unlikely(!tracer_enabled || next != wakeup_task)) @@ -174,7 +178,8 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev, out_unlock: __wakeup_reset(tr); - spin_unlock_irqrestore(&wakeup_lock, flags); + __raw_spin_unlock(&wakeup_lock); + local_irq_restore(flags); out: atomic_dec(&tr->data[cpu]->disabled); } @@ -209,8 +214,6 @@ static void __wakeup_reset(struct trace_array *tr) struct trace_array_cpu *data; int cpu; - assert_spin_locked(&wakeup_lock); - for_each_possible_cpu(cpu) { data = tr->data[cpu]; tracing_reset(data); @@ -229,9 +232,11 @@ static void wakeup_reset(struct trace_array *tr) { unsigned long flags; - spin_lock_irqsave(&wakeup_lock, flags); + local_irq_save(flags); + __raw_spin_lock(&wakeup_lock); __wakeup_reset(tr); - spin_unlock_irqrestore(&wakeup_lock, flags); + __raw_spin_unlock(&wakeup_lock); + local_irq_restore(flags); } static void @@ -252,7 +257,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p, goto out; /* interrupts should be off from try_to_wake_up */ - spin_lock(&wakeup_lock); + __raw_spin_lock(&wakeup_lock); /* check for races. */ if (!tracer_enabled || p->prio >= wakeup_prio) @@ -274,7 +279,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p, CALLER_ADDR1, CALLER_ADDR2, flags); out_locked: - spin_unlock(&wakeup_lock); + __raw_spin_unlock(&wakeup_lock); out: atomic_dec(&tr->data[cpu]->disabled); } diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index ce2d723c10e..bb948e52ce2 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -213,9 +213,7 @@ static void start_stack_timers(void) int cpu; for_each_online_cpu(cpu) { - cpumask_of_cpu_ptr(new_mask, cpu); - - set_cpus_allowed_ptr(current, new_mask); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); start_stack_timer(cpu); } set_cpus_allowed_ptr(current, &saved_mask); diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 3da47ccdc5e..8ebcd8532df 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -94,10 +94,10 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) stats->hiwater_vm = mm->hiwater_vm * PAGE_SIZE / KB; mmput(mm); } - stats->read_char = p->rchar; - stats->write_char = p->wchar; - stats->read_syscalls = p->syscr; - stats->write_syscalls = p->syscw; + stats->read_char = p->ioac.rchar; + stats->write_char = p->ioac.wchar; + stats->read_syscalls = p->ioac.syscr; + stats->write_syscalls = p->ioac.syscw; #ifdef CONFIG_TASK_IO_ACCOUNTING stats->read_bytes = p->ioac.read_bytes; stats->write_bytes = p->ioac.write_bytes; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ec7e4f62aaf..4a26a1382df 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -830,10 +830,21 @@ struct workqueue_struct *__create_workqueue_key(const char *name, start_workqueue_thread(cwq, -1); } else { cpu_maps_update_begin(); + /* + * We must place this wq on list even if the code below fails. + * cpu_down(cpu) can remove cpu from cpu_populated_map before + * destroy_workqueue() takes the lock, in that case we leak + * cwq[cpu]->thread. + */ spin_lock(&workqueue_lock); list_add(&wq->list, &workqueues); spin_unlock(&workqueue_lock); - + /* + * We must initialize cwqs for each possible cpu even if we + * are going to call destroy_workqueue() finally. Otherwise + * cpu_up() can hit the uninitialized cwq once we drop the + * lock. + */ for_each_possible_cpu(cpu) { cwq = init_cpu_workqueue(wq, cpu); if (err || !cpu_online(cpu)) |