diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-04-29 17:29:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-04-29 17:29:08 -0700 |
commit | 73154383f02998fdd6a1f26c7ef33bfc3785a101 (patch) | |
tree | 85a4c10cf32172b99aed01e95ded7269afcc9d7d /kernel | |
parent | 362ed48dee509abe24cf84b7e137c7a29a8f4d2d (diff) | |
parent | ca0dde97178e75ed1370b8616326f5496a803d65 (diff) |
Merge branch 'akpm' (incoming from Andrew)
Merge first batch of fixes from Andrew Morton:
- A couple of kthread changes
- A few minor audit patches
- A number of fbdev patches. Florian remains AWOL so I'm picking up
some of these.
- A few kbuild things
- ocfs2 updates
- Almost all of the MM queue
(And in the meantime, I already have the second big batch from Andrew
pending in my mailbox ;^)
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (149 commits)
memcg: take reference before releasing rcu_read_lock
mem hotunplug: fix kfree() of bootmem memory
mmKconfig: add an option to disable bounce
mm, nobootmem: do memset() after memblock_reserve()
mm, nobootmem: clean-up of free_low_memory_core_early()
fs/buffer.c: remove unnecessary init operation after allocating buffer_head.
numa, cpu hotplug: change links of CPU and node when changing node number by onlining CPU
mm: fix memory_hotplug.c printk format warning
mm: swap: mark swap pages writeback before queueing for direct IO
swap: redirty page if page write fails on swap file
mm, memcg: give exiting processes access to memory reserves
thp: fix huge zero page logic for page with pfn == 0
memcg: avoid accessing memcg after releasing reference
fs: fix fsync() error reporting
memblock: fix missing comment of memblock_insert_region()
mm: Remove unused parameter of pages_correctly_reserved()
firmware, memmap: fix firmware_map_entry leak
mm/vmstat: add note on safety of drain_zonestat
mm: thp: add split tail pages to shrink page list in page reclaim
mm: allow for outstanding swap writeback accounting
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit.c | 12 | ||||
-rw-r--r-- | kernel/audit.h | 3 | ||||
-rw-r--r-- | kernel/audit_tree.c | 2 | ||||
-rw-r--r-- | kernel/auditfilter.c | 4 | ||||
-rw-r--r-- | kernel/auditsc.c | 14 | ||||
-rw-r--r-- | kernel/cgroup.c | 49 | ||||
-rw-r--r-- | kernel/cpuset.c | 12 | ||||
-rw-r--r-- | kernel/kexec.c | 13 | ||||
-rw-r--r-- | kernel/kthread.c | 44 | ||||
-rw-r--r-- | kernel/resource.c | 198 | ||||
-rw-r--r-- | kernel/sysctl.c | 15 |
11 files changed, 239 insertions, 127 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index d596e5355f15..9816a1b96cfc 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -660,14 +660,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* As soon as there's any sign of userspace auditd, * start kauditd to talk to it */ - if (!kauditd_task) + if (!kauditd_task) { kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); - if (IS_ERR(kauditd_task)) { - err = PTR_ERR(kauditd_task); - kauditd_task = NULL; - return err; + if (IS_ERR(kauditd_task)) { + err = PTR_ERR(kauditd_task); + kauditd_task = NULL; + return err; + } } - loginuid = audit_get_loginuid(current); sessionid = audit_get_sessionid(current); security_task_getsecid(current, &sid); diff --git a/kernel/audit.h b/kernel/audit.h index d51cba868e1b..11468d99dad0 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -59,10 +59,7 @@ struct audit_entry { struct audit_krule rule; }; -#ifdef CONFIG_AUDIT -extern int audit_enabled; extern int audit_ever_enabled; -#endif extern int audit_pid; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 642a89c4f3d6..a291aa23fb3f 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -617,9 +617,9 @@ void audit_trim_trees(void) } spin_unlock(&hash_lock); trim_marked(tree); - put_tree(tree); drop_collected_mounts(root_mnt); skip_it: + put_tree(tree); mutex_lock(&audit_filter_mutex); } list_del(&cursor); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index f9fc54bbe06f..267436826c3b 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -594,6 +594,10 @@ exit_nofree: return entry; exit_free: + if (entry->rule.watch) + audit_put_watch(entry->rule.watch); /* matches initial get */ + if (entry->rule.tree) + audit_put_tree(entry->rule.tree); /* that's the temporary one */ audit_free_rule(entry); return ERR_PTR(err); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index a371f857a0a9..c68229411a7c 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1034,21 +1034,15 @@ static inline void audit_free_aux(struct audit_context *context) } } -static inline void audit_zero_context(struct audit_context *context, - enum audit_state state) -{ - memset(context, 0, sizeof(*context)); - context->state = state; - context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; -} - static inline struct audit_context *audit_alloc_context(enum audit_state state) { struct audit_context *context; - if (!(context = kmalloc(sizeof(*context), GFP_KERNEL))) + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) return NULL; - audit_zero_context(context, state); + context->state = state; + context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; INIT_LIST_HEAD(&context->killed_trees); INIT_LIST_HEAD(&context->names_list); return context; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a32f9432666c..dfaf50d4705e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5416,55 +5416,6 @@ struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) } EXPORT_SYMBOL_GPL(css_lookup); -/** - * css_get_next - lookup next cgroup under specified hierarchy. - * @ss: pointer to subsystem - * @id: current position of iteration. - * @root: pointer to css. search tree under this. - * @foundid: position of found object. - * - * Search next css under the specified hierarchy of rootid. Calling under - * rcu_read_lock() is necessary. Returns NULL if it reaches the end. - */ -struct cgroup_subsys_state * -css_get_next(struct cgroup_subsys *ss, int id, - struct cgroup_subsys_state *root, int *foundid) -{ - struct cgroup_subsys_state *ret = NULL; - struct css_id *tmp; - int tmpid; - int rootid = css_id(root); - int depth = css_depth(root); - - if (!rootid) - return NULL; - - BUG_ON(!ss->use_id); - WARN_ON_ONCE(!rcu_read_lock_held()); - - /* fill start point for scan */ - tmpid = id; - while (1) { - /* - * scan next entry from bitmap(tree), tmpid is updated after - * idr_get_next(). - */ - tmp = idr_get_next(&ss->idr, &tmpid); - if (!tmp) - break; - if (tmp->depth >= depth && tmp->stack[depth] == rootid) { - ret = rcu_dereference(tmp->css); - if (ret) { - *foundid = tmpid; - break; - } - } - /* continue to scan from next id */ - tmpid = tmpid + 1; - } - return ret; -} - /* * get corresponding css from file open on cgroupfs directory */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4f9dfe43ecbd..334d983a36b2 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2251,7 +2251,6 @@ void cpuset_update_active_cpus(bool cpu_online) schedule_work(&cpuset_hotplug_work); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. @@ -2263,20 +2262,23 @@ static int cpuset_track_online_nodes(struct notifier_block *self, schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } -#endif + +static struct notifier_block cpuset_track_online_nodes_nb = { + .notifier_call = cpuset_track_online_nodes, + .priority = 10, /* ??! */ +}; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized - **/ - + */ void __init cpuset_init_smp(void) { cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); top_cpuset.mems_allowed = node_states[N_MEMORY]; - hotplug_memory_notifier(cpuset_track_online_nodes, 10); + register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_propagate_hotplug_wq = alloc_ordered_workqueue("cpuset_hotplug", 0); diff --git a/kernel/kexec.c b/kernel/kexec.c index ffd4e111fd67..b574920cbd4b 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1118,12 +1118,8 @@ void __weak crash_free_reserved_phys_range(unsigned long begin, { unsigned long addr; - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); - init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); - free_page((unsigned long)__va(addr)); - totalram_pages++; - } + for (addr = begin; addr < end; addr += PAGE_SIZE) + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); } int crash_shrink_memory(unsigned long new_size) @@ -1581,7 +1577,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(swapper_pg_dir); #endif VMCOREINFO_SYMBOL(_stext); - VMCOREINFO_SYMBOL(vmlist); + VMCOREINFO_SYMBOL(vmap_area_list); #ifndef CONFIG_NEED_MULTIPLE_NODES VMCOREINFO_SYMBOL(mem_map); @@ -1619,7 +1615,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(free_area, free_list); VMCOREINFO_OFFSET(list_head, next); VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_OFFSET(vm_struct, addr); + VMCOREINFO_OFFSET(vmap_area, va_start); + VMCOREINFO_OFFSET(vmap_area, list); VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); log_buf_kexec_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); diff --git a/kernel/kthread.c b/kernel/kthread.c index 9eb7fed0bbaa..9b12d65186f7 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -52,8 +52,21 @@ enum KTHREAD_BITS { KTHREAD_IS_PARKED, }; -#define to_kthread(tsk) \ - container_of((tsk)->vfork_done, struct kthread, exited) +#define __to_kthread(vfork) \ + container_of(vfork, struct kthread, exited) + +static inline struct kthread *to_kthread(struct task_struct *k) +{ + return __to_kthread(k->vfork_done); +} + +static struct kthread *to_live_kthread(struct task_struct *k) +{ + struct completion *vfork = ACCESS_ONCE(k->vfork_done); + if (likely(vfork)) + return __to_kthread(vfork); + return NULL; +} /** * kthread_should_stop - should this kthread return now? @@ -311,19 +324,6 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; } -static struct kthread *task_get_live_kthread(struct task_struct *k) -{ - struct kthread *kthread; - - get_task_struct(k); - kthread = to_kthread(k); - /* It might have exited */ - barrier(); - if (k->vfork_done != NULL) - return kthread; - return NULL; -} - static void __kthread_unpark(struct task_struct *k, struct kthread *kthread) { clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); @@ -350,11 +350,10 @@ static void __kthread_unpark(struct task_struct *k, struct kthread *kthread) */ void kthread_unpark(struct task_struct *k) { - struct kthread *kthread = task_get_live_kthread(k); + struct kthread *kthread = to_live_kthread(k); if (kthread) __kthread_unpark(k, kthread); - put_task_struct(k); } /** @@ -371,7 +370,7 @@ void kthread_unpark(struct task_struct *k) */ int kthread_park(struct task_struct *k) { - struct kthread *kthread = task_get_live_kthread(k); + struct kthread *kthread = to_live_kthread(k); int ret = -ENOSYS; if (kthread) { @@ -384,7 +383,6 @@ int kthread_park(struct task_struct *k) } ret = 0; } - put_task_struct(k); return ret; } @@ -405,10 +403,13 @@ int kthread_park(struct task_struct *k) */ int kthread_stop(struct task_struct *k) { - struct kthread *kthread = task_get_live_kthread(k); + struct kthread *kthread; int ret; trace_sched_kthread_stop(k); + + get_task_struct(k); + kthread = to_live_kthread(k); if (kthread) { set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); __kthread_unpark(k, kthread); @@ -416,10 +417,9 @@ int kthread_stop(struct task_struct *k) wait_for_completion(&kthread->exited); } ret = k->exit_code; - put_task_struct(k); - trace_sched_kthread_stop_ret(ret); + trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); diff --git a/kernel/resource.c b/kernel/resource.c index 73f35d4b30b9..d7386986e10e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -21,6 +21,7 @@ #include <linux/seq_file.h> #include <linux/device.h> #include <linux/pfn.h> +#include <linux/mm.h> #include <asm/io.h> @@ -50,6 +51,14 @@ struct resource_constraint { static DEFINE_RWLOCK(resource_lock); +/* + * For memory hotplug, there is no way to free resource entries allocated + * by boot mem after the system is up. So for reusing the resource entry + * we need to remember the resource. + */ +static struct resource *bootmem_resource_free; +static DEFINE_SPINLOCK(bootmem_resource_lock); + static void *r_next(struct seq_file *m, void *v, loff_t *pos) { struct resource *p = v; @@ -151,6 +160,40 @@ __initcall(ioresources_init); #endif /* CONFIG_PROC_FS */ +static void free_resource(struct resource *res) +{ + if (!res) + return; + + if (!PageSlab(virt_to_head_page(res))) { + spin_lock(&bootmem_resource_lock); + res->sibling = bootmem_resource_free; + bootmem_resource_free = res; + spin_unlock(&bootmem_resource_lock); + } else { + kfree(res); + } +} + +static struct resource *alloc_resource(gfp_t flags) +{ + struct resource *res = NULL; + + spin_lock(&bootmem_resource_lock); + if (bootmem_resource_free) { + res = bootmem_resource_free; + bootmem_resource_free = res->sibling; + } + spin_unlock(&bootmem_resource_lock); + + if (res) + memset(res, 0, sizeof(struct resource)); + else + res = kzalloc(sizeof(struct resource), flags); + + return res; +} + /* Return the conflict entry if you can't request it */ static struct resource * __request_resource(struct resource *root, struct resource *new) { @@ -706,24 +749,13 @@ void insert_resource_expand_to_fit(struct resource *root, struct resource *new) write_unlock(&resource_lock); } -/** - * adjust_resource - modify a resource's start and size - * @res: resource to modify - * @start: new start value - * @size: new size - * - * Given an existing resource, change its start and size to match the - * arguments. Returns 0 on success, -EBUSY if it can't fit. - * Existing children of the resource are assumed to be immutable. - */ -int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) +static int __adjust_resource(struct resource *res, resource_size_t start, + resource_size_t size) { struct resource *tmp, *parent = res->parent; resource_size_t end = start + size - 1; int result = -EBUSY; - write_lock(&resource_lock); - if (!parent) goto skip; @@ -751,6 +783,26 @@ skip: result = 0; out: + return result; +} + +/** + * adjust_resource - modify a resource's start and size + * @res: resource to modify + * @start: new start value + * @size: new size + * + * Given an existing resource, change its start and size to match the + * arguments. Returns 0 on success, -EBUSY if it can't fit. + * Existing children of the resource are assumed to be immutable. + */ +int adjust_resource(struct resource *res, resource_size_t start, + resource_size_t size) +{ + int result; + + write_lock(&resource_lock); + result = __adjust_resource(res, start, size); write_unlock(&resource_lock); return result; } @@ -762,7 +814,7 @@ static void __init __reserve_region_with_split(struct resource *root, { struct resource *parent = root; struct resource *conflict; - struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC); + struct resource *res = alloc_resource(GFP_ATOMIC); struct resource *next_res = NULL; if (!res) @@ -787,7 +839,7 @@ static void __init __reserve_region_with_split(struct resource *root, /* conflict covered whole area */ if (conflict->start <= res->start && conflict->end >= res->end) { - kfree(res); + free_resource(res); WARN_ON(next_res); break; } @@ -797,10 +849,9 @@ static void __init __reserve_region_with_split(struct resource *root, end = res->end; res->end = conflict->start - 1; if (conflict->end < end) { - next_res = kzalloc(sizeof(*next_res), - GFP_ATOMIC); + next_res = alloc_resource(GFP_ATOMIC); if (!next_res) { - kfree(res); + free_resource(res); break; } next_res->name = name; @@ -890,7 +941,7 @@ struct resource * __request_region(struct resource *parent, const char *name, int flags) { DECLARE_WAITQUEUE(wait, current); - struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); + struct resource *res = alloc_resource(GFP_KERNEL); if (!res) return NULL; @@ -924,7 +975,7 @@ struct resource * __request_region(struct resource *parent, continue; } /* Uhhuh, that didn't work out.. */ - kfree(res); + free_resource(res); res = NULL; break; } @@ -958,7 +1009,7 @@ int __check_region(struct resource *parent, resource_size_t start, return -EBUSY; release_resource(res); - kfree(res); + free_resource(res); return 0; } EXPORT_SYMBOL(__check_region); @@ -998,7 +1049,7 @@ void __release_region(struct resource *parent, resource_size_t start, write_unlock(&resource_lock); if (res->flags & IORESOURCE_MUXED) wake_up(&muxed_resource_wait); - kfree(res); + free_resource(res); return; } p = &res->sibling; @@ -1012,6 +1063,109 @@ void __release_region(struct resource *parent, resource_size_t start, } EXPORT_SYMBOL(__release_region); +#ifdef CONFIG_MEMORY_HOTREMOVE +/** + * release_mem_region_adjustable - release a previously reserved memory region + * @parent: parent resource descriptor + * @start: resource start address + * @size: resource region size + * + * This interface is intended for memory hot-delete. The requested region + * is released from a currently busy memory resource. The requested region + * must either match exactly or fit into a single busy resource entry. In + * the latter case, the remaining resource is adjusted accordingly. + * Existing children of the busy memory resource must be immutable in the + * request. + * + * Note: + * - Additional release conditions, such as overlapping region, can be + * supported after they are confirmed as valid cases. + * - When a busy memory resource gets split into two entries, the code + * assumes that all children remain in the lower address entry for + * simplicity. Enhance this logic when necessary. + */ +int release_mem_region_adjustable(struct resource *parent, + resource_size_t start, resource_size_t size) +{ + struct resource **p; + struct resource *res; + struct resource *new_res; + resource_size_t end; + int ret = -EINVAL; + + end = start + size - 1; + if ((start < parent->start) || (end > parent->end)) + return ret; + + /* The alloc_resource() result gets checked later */ + new_res = alloc_resource(GFP_KERNEL); + + p = &parent->child; + write_lock(&resource_lock); + + while ((res = *p)) { + if (res->start >= end) + break; + + /* look for the next resource if it does not fit into */ + if (res->start > start || res->end < end) { + p = &res->sibling; + continue; + } + + if (!(res->flags & IORESOURCE_MEM)) + break; + + if (!(res->flags & IORESOURCE_BUSY)) { + p = &res->child; + continue; + } + + /* found the target resource; let's adjust accordingly */ + if (res->start == start && res->end == end) { + /* free the whole entry */ + *p = res->sibling; + free_resource(res); + ret = 0; + } else if (res->start == start && res->end != end) { + /* adjust the start */ + ret = __adjust_resource(res, end + 1, + res->end - end); + } else if (res->start != start && res->end == end) { + /* adjust the end */ + ret = __adjust_resource(res, res->start, + start - res->start); + } else { + /* split into two entries */ + if (!new_res) { + ret = -ENOMEM; + break; + } + new_res->name = res->name; + new_res->start = end + 1; + new_res->end = res->end; + new_res->flags = res->flags; + new_res->parent = res->parent; + new_res->sibling = res->sibling; + new_res->child = NULL; + + ret = __adjust_resource(res, res->start, + start - res->start); + if (ret) + break; + res->sibling = new_res; + new_res = NULL; + } + + break; + } + + write_unlock(&resource_lock); + free_resource(new_res); + return ret; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + /* * Managed region resource */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index afc1dc60f3f8..9edcf456e0fc 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -106,7 +106,6 @@ extern unsigned int core_pipe_limit; #endif extern int pid_max; extern int pid_max_min, pid_max_max; -extern int sysctl_drop_caches; extern int percpu_pagelist_fraction; extern int compat_log; extern int latencytop_enabled; @@ -1430,6 +1429,20 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif + { + .procname = "user_reserve_kbytes", + .data = &sysctl_user_reserve_kbytes, + .maxlen = sizeof(sysctl_user_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "admin_reserve_kbytes", + .data = &sysctl_admin_reserve_kbytes, + .maxlen = sizeof(sysctl_admin_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, { } }; |