aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/cpuset.c260
-rw-r--r--kernel/groups.c288
-rw-r--r--kernel/kfifo.c4
-rw-r--r--kernel/kthread.c2
-rw-r--r--kernel/power/process.c5
-rw-r--r--kernel/profile.c8
-rw-r--r--kernel/slow-work.c23
-rw-r--r--kernel/sys.c283
-rw-r--r--kernel/sysctl.c2
10 files changed, 431 insertions, 445 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 90b53f6dc22..9df4501cb92 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
async.o
+obj-y += groups.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d5a7e17474e..7e75a41bd50 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -97,12 +97,6 @@ struct cpuset {
struct cpuset *parent; /* my parent */
- /*
- * Copy of global cpuset_mems_generation as of the most
- * recent time this cpuset changed its mems_allowed.
- */
- int mems_generation;
-
struct fmeter fmeter; /* memory_pressure filter */
/* partition number for rebuild_sched_domains() */
@@ -176,27 +170,6 @@ static inline int is_spread_slab(const struct cpuset *cs)
return test_bit(CS_SPREAD_SLAB, &cs->flags);
}
-/*
- * Increment this integer everytime any cpuset changes its
- * mems_allowed value. Users of cpusets can track this generation
- * number, and avoid having to lock and reload mems_allowed unless
- * the cpuset they're using changes generation.
- *
- * A single, global generation is needed because cpuset_attach_task() could
- * reattach a task to a different cpuset, which must not have its
- * generation numbers aliased with those of that tasks previous cpuset.
- *
- * Generations are needed for mems_allowed because one task cannot
- * modify another's memory placement. So we must enable every task,
- * on every visit to __alloc_pages(), to efficiently check whether
- * its current->cpuset->mems_allowed has changed, requiring an update
- * of its current->mems_allowed.
- *
- * Since writes to cpuset_mems_generation are guarded by the cgroup lock
- * there is no need to mark it atomic.
- */
-static int cpuset_mems_generation;
-
static struct cpuset top_cpuset = {
.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
};
@@ -228,8 +201,9 @@ static struct cpuset top_cpuset = {
* If a task is only holding callback_mutex, then it has read-only
* access to cpusets.
*
- * The task_struct fields mems_allowed and mems_generation may only
- * be accessed in the context of that task, so require no locks.
+ * Now, the task_struct fields mems_allowed and mempolicy may be changed
+ * by other task, we use alloc_lock in the task_struct fields to protect
+ * them.
*
* The cpuset_common_file_read() handlers only hold callback_mutex across
* small pieces of code, such as when reading out possibly multi-word
@@ -331,75 +305,22 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
}
-/**
- * cpuset_update_task_memory_state - update task memory placement
- *
- * If the current tasks cpusets mems_allowed changed behind our
- * backs, update current->mems_allowed, mems_generation and task NUMA
- * mempolicy to the new value.
- *
- * Task mempolicy is updated by rebinding it relative to the
- * current->cpuset if a task has its memory placement changed.
- * Do not call this routine if in_interrupt().
- *
- * Call without callback_mutex or task_lock() held. May be
- * called with or without cgroup_mutex held. Thanks in part to
- * 'the_top_cpuset_hack', the task's cpuset pointer will never
- * be NULL. This routine also might acquire callback_mutex during
- * call.
- *
- * Reading current->cpuset->mems_generation doesn't need task_lock
- * to guard the current->cpuset derefence, because it is guarded
- * from concurrent freeing of current->cpuset using RCU.
- *
- * The rcu_dereference() is technically probably not needed,
- * as I don't actually mind if I see a new cpuset pointer but
- * an old value of mems_generation. However this really only
- * matters on alpha systems using cpusets heavily. If I dropped
- * that rcu_dereference(), it would save them a memory barrier.
- * For all other arch's, rcu_dereference is a no-op anyway, and for
- * alpha systems not using cpusets, another planned optimization,
- * avoiding the rcu critical section for tasks in the root cpuset
- * which is statically allocated, so can't vanish, will make this
- * irrelevant. Better to use RCU as intended, than to engage in
- * some cute trick to save a memory barrier that is impossible to
- * test, for alpha systems using cpusets heavily, which might not
- * even exist.
- *
- * This routine is needed to update the per-task mems_allowed data,
- * within the tasks context, when it is trying to allocate memory
- * (in various mm/mempolicy.c routines) and notices that some other
- * task has been modifying its cpuset.
+/*
+ * update task's spread flag if cpuset's page/slab spread flag is set
+ *
+ * Called with callback_mutex/cgroup_mutex held
*/
-
-void cpuset_update_task_memory_state(void)
+static void cpuset_update_task_spread_flag(struct cpuset *cs,
+ struct task_struct *tsk)
{
- int my_cpusets_mem_gen;
- struct task_struct *tsk = current;
- struct cpuset *cs;
-
- rcu_read_lock();
- my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
- rcu_read_unlock();
-
- if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
- mutex_lock(&callback_mutex);
- task_lock(tsk);
- cs = task_cs(tsk); /* Maybe changed when task not locked */
- guarantee_online_mems(cs, &tsk->mems_allowed);
- tsk->cpuset_mems_generation = cs->mems_generation;
- if (is_spread_page(cs))
- tsk->flags |= PF_SPREAD_PAGE;
- else
- tsk->flags &= ~PF_SPREAD_PAGE;
- if (is_spread_slab(cs))
- tsk->flags |= PF_SPREAD_SLAB;
- else
- tsk->flags &= ~PF_SPREAD_SLAB;
- task_unlock(tsk);
- mutex_unlock(&callback_mutex);
- mpol_rebind_task(tsk, &tsk->mems_allowed);
- }
+ if (is_spread_page(cs))
+ tsk->flags |= PF_SPREAD_PAGE;
+ else
+ tsk->flags &= ~PF_SPREAD_PAGE;
+ if (is_spread_slab(cs))
+ tsk->flags |= PF_SPREAD_SLAB;
+ else
+ tsk->flags &= ~PF_SPREAD_SLAB;
}
/*
@@ -1007,14 +928,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
* migrating memory region.
- *
- * We call cpuset_update_task_memory_state() before hacking
- * our tasks mems_allowed, so that we are assured of being in
- * sync with our tasks cpuset, and in particular, callbacks to
- * cpuset_update_task_memory_state() from nested page allocations
- * won't see any mismatch of our cpuset and task mems_generation
- * values, so won't overwrite our hacked tasks mems_allowed
- * nodemask.
*/
static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
@@ -1022,22 +935,37 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
{
struct task_struct *tsk = current;
- cpuset_update_task_memory_state();
-
- mutex_lock(&callback_mutex);
tsk->mems_allowed = *to;
- mutex_unlock(&callback_mutex);
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
- mutex_lock(&callback_mutex);
guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
- mutex_unlock(&callback_mutex);
}
/*
- * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new
- * nodes if memory_migrate flag is set. Called with cgroup_mutex held.
+ * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy
+ * @tsk: the task to change
+ * @newmems: new nodes that the task will be set
+ *
+ * In order to avoid seeing no nodes if the old and new nodes are disjoint,
+ * we structure updates as setting all new allowed nodes, then clearing newly
+ * disallowed ones.
+ *
+ * Called with task's alloc_lock held
+ */
+static void cpuset_change_task_nodemask(struct task_struct *tsk,
+ nodemask_t *newmems)
+{
+ nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+ mpol_rebind_task(tsk, &tsk->mems_allowed);
+ mpol_rebind_task(tsk, newmems);
+ tsk->mems_allowed = *newmems;
+}
+
+/*
+ * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy
+ * of it to cpuset's new mems_allowed, and migrate pages to new nodes if
+ * memory_migrate flag is set. Called with cgroup_mutex held.
*/
static void cpuset_change_nodemask(struct task_struct *p,
struct cgroup_scanner *scan)
@@ -1046,12 +974,19 @@ static void cpuset_change_nodemask(struct task_struct *p,
struct cpuset *cs;
int migrate;
const nodemask_t *oldmem = scan->data;
+ nodemask_t newmems;
+
+ cs = cgroup_cs(scan->cg);
+ guarantee_online_mems(cs, &newmems);
+
+ task_lock(p);
+ cpuset_change_task_nodemask(p, &newmems);
+ task_unlock(p);
mm = get_task_mm(p);
if (!mm)
return;
- cs = cgroup_cs(scan->cg);
migrate = is_memory_migrate(cs);
mpol_rebind_mm(mm, &cs->mems_allowed);
@@ -1104,10 +1039,10 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
/*
* Handle user request to change the 'mems' memory placement
* of a cpuset. Needs to validate the request, update the
- * cpusets mems_allowed and mems_generation, and for each
- * task in the cpuset, rebind any vma mempolicies and if
- * the cpuset is marked 'memory_migrate', migrate the tasks
- * pages to the new memory.
+ * cpusets mems_allowed, and for each task in the cpuset,
+ * update mems_allowed and rebind task's mempolicy and any vma
+ * mempolicies and if the cpuset is marked 'memory_migrate',
+ * migrate the tasks pages to the new memory.
*
* Call with cgroup_mutex held. May take callback_mutex during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
@@ -1160,7 +1095,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
mutex_lock(&callback_mutex);
cs->mems_allowed = trialcs->mems_allowed;
- cs->mems_generation = cpuset_mems_generation++;
mutex_unlock(&callback_mutex);
update_tasks_nodemask(cs, &oldmem, &heap);
@@ -1193,6 +1127,46 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
}
/*
+ * cpuset_change_flag - make a task's spread flags the same as its cpuset's
+ * @tsk: task to be updated
+ * @scan: struct cgroup_scanner containing the cgroup of the task
+ *
+ * Called by cgroup_scan_tasks() for each task in a cgroup.
+ *
+ * We don't need to re-check for the cgroup/cpuset membership, since we're
+ * holding cgroup_lock() at this point.
+ */
+static void cpuset_change_flag(struct task_struct *tsk,
+ struct cgroup_scanner *scan)
+{
+ cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk);
+}
+
+/*
+ * update_tasks_flags - update the spread flags of tasks in the cpuset.
+ * @cs: the cpuset in which each task's spread flags needs to be changed
+ * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ *
+ * Called with cgroup_mutex held
+ *
+ * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
+ * calling callback functions for each.
+ *
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
+ */
+static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
+{
+ struct cgroup_scanner scan;
+
+ scan.cg = cs->css.cgroup;
+ scan.test_task = NULL;
+ scan.process_task = cpuset_change_flag;
+ scan.heap = heap;
+ cgroup_scan_tasks(&scan);
+}
+
+/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (see cpuset_flagbits_t)
* cs: the cpuset to update
@@ -1205,8 +1179,10 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on)
{
struct cpuset *trialcs;
- int err;
int balance_flag_changed;
+ int spread_flag_changed;
+ struct ptr_heap heap;
+ int err;
trialcs = alloc_trial_cpuset(cs);
if (!trialcs)
@@ -1221,9 +1197,16 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
if (err < 0)
goto out;
+ err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
+ if (err < 0)
+ goto out;
+
balance_flag_changed = (is_sched_load_balance(cs) !=
is_sched_load_balance(trialcs));
+ spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
+ || (is_spread_page(cs) != is_spread_page(trialcs)));
+
mutex_lock(&callback_mutex);
cs->flags = trialcs->flags;
mutex_unlock(&callback_mutex);
@@ -1231,6 +1214,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
async_rebuild_sched_domains();
+ if (spread_flag_changed)
+ update_tasks_flags(cs, &heap);
+ heap_free(&heap);
out:
free_trial_cpuset(trialcs);
return err;
@@ -1372,15 +1358,20 @@ static void cpuset_attach(struct cgroup_subsys *ss,
if (cs == &top_cpuset) {
cpumask_copy(cpus_attach, cpu_possible_mask);
+ to = node_possible_map;
} else {
- mutex_lock(&callback_mutex);
guarantee_online_cpus(cs, cpus_attach);
- mutex_unlock(&callback_mutex);
+ guarantee_online_mems(cs, &to);
}
err = set_cpus_allowed_ptr(tsk, cpus_attach);
if (err)
return;
+ task_lock(tsk);
+ cpuset_change_task_nodemask(tsk, &to);
+ task_unlock(tsk);
+ cpuset_update_task_spread_flag(cs, tsk);
+
from = oldcs->mems_allowed;
to = cs->mems_allowed;
mm = get_task_mm(tsk);
@@ -1442,11 +1433,9 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
break;
case FILE_SPREAD_PAGE:
retval = update_flag(CS_SPREAD_PAGE, cs, val);
- cs->mems_generation = cpuset_mems_generation++;
break;
case FILE_SPREAD_SLAB:
retval = update_flag(CS_SPREAD_SLAB, cs, val);
- cs->mems_generation = cpuset_mems_generation++;
break;
default:
retval = -EINVAL;
@@ -1786,8 +1775,6 @@ static struct cgroup_subsys_state *cpuset_create(
struct cpuset *parent;
if (!cont->parent) {
- /* This is early initialization for the top cgroup */
- top_cpuset.mems_generation = cpuset_mems_generation++;
return &top_cpuset.css;
}
parent = cgroup_cs(cont->parent);
@@ -1799,7 +1786,6 @@ static struct cgroup_subsys_state *cpuset_create(
return ERR_PTR(-ENOMEM);
}
- cpuset_update_task_memory_state();
cs->flags = 0;
if (is_spread_page(parent))
set_bit(CS_SPREAD_PAGE, &cs->flags);
@@ -1808,7 +1794,6 @@ static struct cgroup_subsys_state *cpuset_create(
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cpumask_clear(cs->cpus_allowed);
nodes_clear(cs->mems_allowed);
- cs->mems_generation = cpuset_mems_generation++;
fmeter_init(&cs->fmeter);
cs->relax_domain_level = -1;
@@ -1827,8 +1812,6 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
struct cpuset *cs = cgroup_cs(cont);
- cpuset_update_task_memory_state();
-
if (is_sched_load_balance(cs))
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
@@ -1849,21 +1832,6 @@ struct cgroup_subsys cpuset_subsys = {
.early_init = 1,
};
-/*
- * cpuset_init_early - just enough so that the calls to
- * cpuset_update_task_memory_state() in early init code
- * are harmless.
- */
-
-int __init cpuset_init_early(void)
-{
- alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT);
-
- top_cpuset.mems_generation = cpuset_mems_generation++;
- return 0;
-}
-
-
/**
* cpuset_init - initialize cpusets at system boot
*
@@ -1874,11 +1842,13 @@ int __init cpuset_init(void)
{
int err = 0;
+ if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
+ BUG();
+
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
fmeter_init(&top_cpuset.fmeter);
- top_cpuset.mems_generation = cpuset_mems_generation++;
set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
top_cpuset.relax_domain_level = -1;
diff --git a/kernel/groups.c b/kernel/groups.c
new file mode 100644
index 00000000000..2b45b2ee396
--- /dev/null
+++ b/kernel/groups.c
@@ -0,0 +1,288 @@
+/*
+ * Supplementary group IDs
+ */
+#include <linux/cred.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <asm/uaccess.h>
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+
+struct group_info *groups_alloc(int gidsetsize)
+{
+ struct group_info *group_info;
+ int nblocks;
+ int i;
+
+ nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
+ /* Make sure we always allocate at least one indirect block pointer */
+ nblocks = nblocks ? : 1;
+ group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
+ if (!group_info)
+ return NULL;
+ group_info->ngroups = gidsetsize;
+ group_info->nblocks = nblocks;
+ atomic_set(&group_info->usage, 1);
+
+ if (gidsetsize <= NGROUPS_SMALL)
+ group_info->blocks[0] = group_info->small_block;
+ else {
+ for (i = 0; i < nblocks; i++) {
+ gid_t *b;
+ b = (void *)__get_free_page(GFP_USER);
+ if (!b)
+ goto out_undo_partial_alloc;
+ group_info->blocks[i] = b;
+ }
+ }
+ return group_info;
+
+out_undo_partial_alloc:
+ while (--i >= 0) {
+ free_page((unsigned long)group_info->blocks[i]);
+ }
+ kfree(group_info);
+ return NULL;
+}
+
+EXPORT_SYMBOL(groups_alloc);
+
+void groups_free(struct group_info *group_info)
+{
+ if (group_info->blocks[0] != group_info->small_block) {
+ int i;
+ for (i = 0; i < group_info->nblocks; i++)
+ free_page((unsigned long)group_info->blocks[i]);
+ }
+ kfree(group_info);
+}
+
+EXPORT_SYMBOL(groups_free);
+
+/* export the group_info to a user-space array */
+static int groups_to_user(gid_t __user *grouplist,
+ const struct group_info *group_info)
+{
+ int i;
+ unsigned int count = group_info->ngroups;
+
+ for (i = 0; i < group_info->nblocks; i++) {
+ unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+ unsigned int len = cp_count * sizeof(*grouplist);
+
+ if (copy_to_user(grouplist, group_info->blocks[i], len))
+ return -EFAULT;
+
+ grouplist += NGROUPS_PER_BLOCK;
+ count -= cp_count;
+ }
+ return 0;
+}
+
+/* fill a group_info from a user-space array - it must be allocated already */
+static int groups_from_user(struct group_info *group_info,
+ gid_t __user *grouplist)
+{
+ int i;
+ unsigned int count = group_info->ngroups;
+
+ for (i = 0; i < group_info->nblocks; i++) {
+ unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+ unsigned int len = cp_count * sizeof(*grouplist);
+
+ if (copy_from_user(group_info->blocks[i], grouplist, len))
+ return -EFAULT;
+
+ grouplist += NGROUPS_PER_BLOCK;
+ count -= cp_count;
+ }
+ return 0;
+}
+
+/* a simple Shell sort */
+static void groups_sort(struct group_info *group_info)
+{
+ int base, max, stride;
+ int gidsetsize = group_info->ngroups;
+
+ for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
+ ; /* nothing */
+ stride /= 3;
+
+ while (stride) {
+ max = gidsetsize - stride;
+ for (base = 0; base < max; base++) {
+ int left = base;
+ int right = left + stride;
+ gid_t tmp = GROUP_AT(group_info, right);
+
+ while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
+ GROUP_AT(group_info, right) =
+ GROUP_AT(group_info, left);
+ right = left;
+ left -= stride;
+ }
+ GROUP_AT(group_info, right) = tmp;
+ }
+ stride /= 3;
+ }
+}
+
+/* a simple bsearch */
+int groups_search(const struct group_info *group_info, gid_t grp)
+{
+ unsigned int left, right;
+
+ if (!group_info)
+ return 0;
+
+ left = 0;
+ right = group_info->ngroups;
+ while (left < right) {
+ unsigned int mid = (left+right)/2;
+ int cmp = grp - GROUP_AT(group_info, mid);
+ if (cmp > 0)
+ left = mid + 1;
+ else if (cmp < 0)
+ right = mid;
+ else
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * set_groups - Change a group subscription in a set of credentials
+ * @new: The newly prepared set of credentials to alter
+ * @group_info: The group list to install
+ *
+ * Validate a group subscription and, if valid, insert it into a set
+ * of credentials.
+ */
+int set_groups(struct cred *new, struct group_info *group_info)
+{
+ int retval;
+
+ retval = security_task_setgroups(group_info);
+ if (retval)
+ return retval;
+
+ put_group_info(new->group_info);
+ groups_sort(group_info);
+ get_group_info(group_info);
+ new->group_info = group_info;
+ return 0;
+}
+
+EXPORT_SYMBOL(set_groups);
+
+/**
+ * set_current_groups - Change current's group subscription
+ * @group_info: The group list to impose
+ *
+ * Validate a group subscription and, if valid, impose it upon current's task
+ * security record.
+ */
+int set_current_groups(struct group_info *group_info)
+{
+ struct cred *new;
+ int ret;
+
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+
+ ret = set_groups(new, group_info);
+ if (ret < 0) {
+ abort_creds(new);
+ return ret;
+ }
+
+ return commit_creds(new);
+}
+
+EXPORT_SYMBOL(set_current_groups);
+
+SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+ const struct cred *cred = current_cred();
+ int i;
+
+ if (gidsetsize < 0)
+ return -EINVAL;
+
+ /* no need to grab task_lock here; it cannot change */
+ i = cred->group_info->ngroups;
+ if (gidsetsize) {
+ if (i > gidsetsize) {
+ i = -EINVAL;
+ goto out;
+ }
+ if (groups_to_user(grouplist, cred->group_info)) {
+ i = -EFAULT;
+ goto out;
+ }
+ }
+out:
+ return i;
+}
+
+/*
+ * SMP: Our groups are copy-on-write. We can set them safely
+ * without another task interfering.
+ */
+
+SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+ struct group_info *group_info;
+ int retval;
+
+ if (!capable(CAP_SETGID))
+ return -EPERM;
+ if ((unsigned)gidsetsize > NGROUPS_MAX)
+ return -EINVAL;
+
+ group_info = groups_alloc(gidsetsize);
+ if (!group_info)
+ return -ENOMEM;
+ retval = groups_from_user(group_info, grouplist);
+ if (retval) {
+ put_group_info(group_info);
+ return retval;
+ }
+
+ retval = set_current_groups(group_info);
+ put_group_info(group_info);
+
+ return retval;
+}
+
+/*
+ * Check whether we're fsgid/egid or in the supplemental group..
+ */
+int in_group_p(gid_t grp)
+{
+ const struct cred *cred = current_cred();
+ int retval = 1;
+
+ if (grp != cred->fsgid)
+ retval = groups_search(cred->group_info, grp);
+ return retval;
+}
+
+EXPORT_SYMBOL(in_group_p);
+
+int in_egroup_p(gid_t grp)
+{
+ const struct cred *cred = current_cred();
+ int retval = 1;
+
+ if (grp != cred->egid)
+ retval = groups_search(cred->group_info, grp);
+ return retval;
+}
+
+EXPORT_SYMBOL(in_egroup_p);
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index bc41ad0f24f..26539e3228e 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -72,9 +72,9 @@ struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
/*
* round up to the next power of 2, since our 'let the indices
- * wrap' tachnique works only in this case.
+ * wrap' technique works only in this case.
*/
- if (size & (size - 1)) {
+ if (!is_power_of_2(size)) {
BUG_ON(size > 0x80000000);
size = roundup_pow_of_two(size);
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 41c88fe4050..7fa44133352 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -9,6 +9,7 @@
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
+#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/module.h>
@@ -236,6 +237,7 @@ int kthreadd(void *unused)
ignore_signals(tsk);
set_user_nice(tsk, KTHREAD_NICE_LEVEL);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
+ set_mems_allowed(node_possible_map);
current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index ca634019497..da2072d7381 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -117,9 +117,12 @@ int freeze_processes(void)
if (error)
goto Exit;
printk("done.");
+
+ oom_killer_disable();
Exit:
BUG_ON(in_atomic());
printk("\n");
+
return error;
}
@@ -145,6 +148,8 @@ static void thaw_tasks(bool nosig_only)
void thaw_processes(void)
{
+ oom_killer_enable();
+
printk("Restarting tasks ... ");
thaw_tasks(true);
thaw_tasks(false);
diff --git a/kernel/profile.c b/kernel/profile.c
index 28cf26ad2d2..69911b5745e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -365,7 +365,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info,
node = cpu_to_node(cpu);
per_cpu(cpu_profile_flip, cpu) = 0;
if (!per_cpu(cpu_profile_hits, cpu)[1]) {
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -373,7 +373,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info,
per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
}
if (!per_cpu(cpu_profile_hits, cpu)[0]) {
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -564,14 +564,14 @@ static int create_hash_tables(void)
int node = cpu_to_node(cpu);
struct page *page;
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
0);
if (!page)
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 521ed2004d6..09d7519557d 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -319,6 +319,15 @@ cant_get_ref:
EXPORT_SYMBOL(slow_work_enqueue);
/*
+ * Schedule a cull of the thread pool at some time in the near future
+ */
+static void slow_work_schedule_cull(void)
+{
+ mod_timer(&slow_work_cull_timer,
+ round_jiffies(jiffies + SLOW_WORK_CULL_TIMEOUT));
+}
+
+/*
* Worker thread culling algorithm
*/
static bool slow_work_cull_thread(void)
@@ -335,8 +344,7 @@ static bool slow_work_cull_thread(void)
list_empty(&vslow_work_queue) &&
atomic_read(&slow_work_thread_count) >
slow_work_min_threads) {
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
do_cull = true;
}
}
@@ -393,8 +401,7 @@ static int slow_work_thread(void *_data)
list_empty(&vslow_work_queue) &&
atomic_read(&slow_work_thread_count) >
slow_work_min_threads)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
continue;
}
@@ -458,7 +465,7 @@ static void slow_work_new_thread_execute(struct slow_work *work)
if (atomic_dec_and_test(&slow_work_thread_count))
BUG(); /* we're running on a slow work thread... */
mod_timer(&slow_work_oom_timer,
- jiffies + SLOW_WORK_OOM_TIMEOUT);
+ round_jiffies(jiffies + SLOW_WORK_OOM_TIMEOUT));
} else {
/* ratelimit the starting of new threads */
mod_timer(&slow_work_oom_timer, jiffies + 1);
@@ -502,8 +509,7 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
if (n < 0 && !slow_work_may_not_start_new_thread)
slow_work_enqueue(&slow_work_new_thread);
else if (n > 0)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
}
mutex_unlock(&slow_work_user_lock);
}
@@ -529,8 +535,7 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
atomic_read(&slow_work_thread_count);
if (n < 0)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
}
mutex_unlock(&slow_work_user_lock);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index 438d99a38c8..b3f1097c76f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1113,289 +1113,6 @@ out:
return err;
}
-/*
- * Supplementary group IDs
- */
-
-/* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
-
-struct group_info *groups_alloc(int gidsetsize)
-{
- struct group_info *group_info;
- int nblocks;
- int i;
-
- nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
- /* Make sure we always allocate at least one indirect block pointer */
- nblocks = nblocks ? : 1;
- group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
- if (!group_info)
- return NULL;
- group_info->ngroups = gidsetsize;
- group_info->nblocks = nblocks;
- atomic_set(&group_info->usage, 1);
-
- if (gidsetsize <= NGROUPS_SMALL)
- group_info->blocks[0] = group_info->small_block;
- else {
- for (i = 0; i < nblocks; i++) {
- gid_t *b;
- b = (void *)__get_free_page(GFP_USER);
- if (!b)
- goto out_undo_partial_alloc;
- group_info->blocks[i] = b;
- }
- }
- return group_info;
-
-out_undo_partial_alloc:
- while (--i >= 0) {
- free_page((unsigned long)group_info->blocks[i]);
- }
- kfree(group_info);
- return NULL;
-}
-
-EXPORT_SYMBOL(groups_alloc);
-
-void groups_free(struct group_info *group_info)
-{
- if (group_info->blocks[0] != group_info->small_block) {
- int i;
- for (i = 0; i < group_info->nblocks; i++)
- free_page((unsigned long)group_info->blocks[i]);
- }
- kfree(group_info);
-}
-
-EXPORT_SYMBOL(groups_free);
-
-/* export the group_info to a user-space array */
-static int groups_to_user(gid_t __user *grouplist,
- const struct group_info *group_info)
-{
- int i;
- unsigned int count = group_info->ngroups;
-
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_to_user(grouplist, group_info->blocks[i], len))
- return -EFAULT;
-
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
- }
- return 0;
-}
-
-/* fill a group_info from a user-space array - it must be allocated already */
-static int groups_from_user(struct group_info *group_info,
- gid_t __user *grouplist)
-{
- int i;
- unsigned int count = group_info->ngroups;
-
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_from_user(group_info->blocks[i], grouplist, len))
- return -EFAULT;
-
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
- }
- return 0;
-}
-
-/* a simple Shell sort */
-static void groups_sort(struct group_info *group_info)
-{
- int base, max, stride;
- int gidsetsize = group_info->ngroups;
-
- for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
- ; /* nothing */
- stride /= 3;
-
- while (stride) {
- max = gidsetsize - stride;
- for (base = 0; base < max; base++) {
- int left = base;
- int right = left + stride;
- gid_t tmp = GROUP_AT(group_info, right);
-
- while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
- GROUP_AT(group_info, right) =
- GROUP_AT(group_info, left);
- right = left;
- left -= stride;
- }
- GROUP_AT(group_info, right) = tmp;
- }
- stride /= 3;
- }
-}
-
-/* a simple bsearch */
-int groups_search(const struct group_info *group_info, gid_t grp)
-{
- unsigned int left, right;
-
- if (!group_info)
- return 0;
-
- left = 0;
- right = group_info->ngroups;
- while (left < right) {
- unsigned int mid = (left+right)/2;
- int cmp = grp - GROUP_AT(group_info, mid);
- if (cmp > 0)
- left = mid + 1;
- else if (cmp < 0)
- right = mid;
- else
- return 1;
- }
- return 0;
-}
-
-/**
- * set_groups - Change a group subscription in a set of credentials
- * @new: The newly prepared set of credentials to alter
- * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
- */
-int set_groups(struct cred *new, struct group_info *group_info)
-{
- int retval;
-
- retval = security_task_setgroups(group_info);
- if (retval)
- return retval;
-
- put_group_info(new->group_info);
- groups_sort(group_info);
- get_group_info(group_info);
- new->group_info = group_info;
- return 0;
-}
-
-EXPORT_SYMBOL(set_groups);
-
-/**
- * set_current_groups - Change current's group subscription
- * @group_info: The group list to impose
- *
- * Validate a group subscription and, if valid, impose it upon current's task
- * security record.
- */
-int set_current_groups(struct group_info *group_info)
-{
- struct cred *new;
- int ret;
-
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
-
- ret = set_groups(new, group_info);
- if (ret < 0) {
- abort_creds(new);
- return ret;
- }
-
- return commit_creds(new);
-}
-
-EXPORT_SYMBOL(set_current_groups);
-
-SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
-{
- const struct cred *cred = current_cred();
- int i;
-
- if (gidsetsize < 0)
- return -EINVAL;
-
- /* no need to grab task_lock here; it cannot change */
- i = cred->group_info->ngroups;
- if (gidsetsize) {
- if (i > gidsetsize) {
- i = -EINVAL;
- goto out;
- }
- if (groups_to_user(grouplist, cred->group_info)) {
- i = -EFAULT;
- goto out;
- }
- }
-out:
- return i;
-}
-
-/*
- * SMP: Our groups are copy-on-write. We can set them safely
- * without another task interfering.
- */
-
-SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
-{
- struct group_info *group_info;
- int retval;
-
- if (!capable(CAP_SETGID))
- return -EPERM;
- if ((unsigned)gidsetsize > NGROUPS_MAX)
- return -EINVAL;
-
- group_info = groups_alloc(gidsetsize);
- if (!group_info)
- return -ENOMEM;
- retval = groups_from_user(group_info, grouplist);
- if (retval) {
- put_group_info(group_info);
- return retval;
- }
-
- retval = set_current_groups(group_info);
- put_group_info(group_info);
-
- return retval;
-}
-
-/*
- * Check whether we're fsgid/egid or in the supplemental group..
- */
-int in_group_p(gid_t grp)
-{
- const struct cred *cred = current_cred();
- int retval = 1;
-
- if (grp != cred->fsgid)
- retval = groups_search(cred->group_info, grp);
- return retval;
-}
-
-EXPORT_SYMBOL(in_group_p);
-
-int in_egroup_p(gid_t grp)
-{
- const struct cred *cred = current_cred();
- int retval = 1;
-
- if (grp != cred->egid)
- retval = groups_search(cred->group_info, grp);
- return retval;
-}
-
-EXPORT_SYMBOL(in_egroup_p);
-
DECLARE_RWSEM(uts_sem);
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f5c76b6cd61..ab462b9968d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1337,7 +1337,6 @@ static struct ctl_table vm_table[] = {
.extra2 = &one,
},
#endif
-#ifdef CONFIG_UNEVICTABLE_LRU
{
.ctl_name = CTL_UNNUMBERED,
.procname = "scan_unevictable_pages",
@@ -1346,7 +1345,6 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &scan_unevictable_handler,
},
-#endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt