summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c2
-rw-r--r--kernel/cgroup.c23
-rw-r--r--kernel/cred.c25
-rw-r--r--kernel/debug/debug_core.c2
-rw-r--r--kernel/debug/gdbstub.c9
-rw-r--r--kernel/debug/kdb/kdb_main.c7
-rw-r--r--kernel/early_res.c6
-rw-r--r--kernel/module.c4
-rw-r--r--kernel/padata.c755
-rw-r--r--kernel/pm_qos_params.c215
-rw-r--r--kernel/power/hibernate.c24
-rw-r--r--kernel/power/main.c55
-rw-r--r--kernel/power/suspend.c13
-rw-r--r--kernel/power/swap.c4
-rw-r--r--kernel/signal.c9
-rw-r--r--kernel/timer.c13
-rw-r--r--kernel/user_namespace.c44
17 files changed, 882 insertions, 328 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index c71bd26631a2..8296aa516c5a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -407,7 +407,7 @@ static void kauditd_send_skb(struct sk_buff *skb)
audit_hold_skb(skb);
} else
/* drop the extra reference if sent ok */
- kfree_skb(skb);
+ consume_skb(skb);
}
static int kauditd_thread(void *dummy)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3ac6f5b0a64b..a8ce09954404 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1788,6 +1788,29 @@ out:
return retval;
}
+/**
+ * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_current_cg(struct task_struct *tsk)
+{
+ struct cgroupfs_root *root;
+ struct cgroup *cur_cg;
+ int retval = 0;
+
+ cgroup_lock();
+ for_each_active_root(root) {
+ cur_cg = task_cgroup_from_root(current, root);
+ retval = cgroup_attach_task(cur_cg, tsk);
+ if (retval)
+ break;
+ }
+ cgroup_unlock();
+
+ return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg);
+
/*
* Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
* held. May take task_lock of task
diff --git a/kernel/cred.c b/kernel/cred.c
index a2d5504fbcc2..60bc8b1e32e6 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -209,6 +209,31 @@ void exit_creds(struct task_struct *tsk)
}
}
+/**
+ * get_task_cred - Get another task's objective credentials
+ * @task: The task to query
+ *
+ * Get the objective credentials of a task, pinning them so that they can't go
+ * away. Accessing a task's credentials directly is not permitted.
+ *
+ * The caller must also make sure task doesn't get deleted, either by holding a
+ * ref on task or by holding tasklist_lock to prevent it from being unlinked.
+ */
+const struct cred *get_task_cred(struct task_struct *task)
+{
+ const struct cred *cred;
+
+ rcu_read_lock();
+
+ do {
+ cred = __task_cred((task));
+ BUG_ON(!cred);
+ } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage));
+
+ rcu_read_unlock();
+ return cred;
+}
+
/*
* Allocate blank credentials, such that the credentials can be filled in at a
* later date without risk of ENOMEM.
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 5cb7cd1de10c..8bc5eeffec8a 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -605,13 +605,13 @@ cpu_master_loop:
if (dbg_kdb_mode) {
kgdb_connected = 1;
error = kdb_stub(ks);
+ kgdb_connected = 0;
} else {
error = gdb_serial_stub(ks);
}
if (error == DBG_PASS_EVENT) {
dbg_kdb_mode = !dbg_kdb_mode;
- kgdb_connected = 0;
} else if (error == DBG_SWITCH_CPU_EVENT) {
dbg_cpu_switch(cpu, dbg_switch_cpu);
goto cpu_loop;
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 4b17b3269525..e8fd6868682d 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -621,10 +621,8 @@ static void gdb_cmd_query(struct kgdb_state *ks)
switch (remcom_in_buffer[1]) {
case 's':
case 'f':
- if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) {
- error_packet(remcom_out_buffer, -EINVAL);
+ if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10))
break;
- }
i = 0;
remcom_out_buffer[0] = 'm';
@@ -665,10 +663,9 @@ static void gdb_cmd_query(struct kgdb_state *ks)
pack_threadid(remcom_out_buffer + 2, thref);
break;
case 'T':
- if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) {
- error_packet(remcom_out_buffer, -EINVAL);
+ if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16))
break;
- }
+
ks->threadid = 0;
ptr = remcom_in_buffer + 17;
kgdb_hex2long(&ptr, &ks->threadid);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 184cd8209c36..ebe4a287419e 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1820,9 +1820,8 @@ static int kdb_sr(int argc, const char **argv)
{
if (argc != 1)
return KDB_ARGCOUNT;
- sysrq_toggle_support(1);
kdb_trap_printk++;
- handle_sysrq(*argv[1], NULL);
+ __handle_sysrq(*argv[1], NULL, 0);
kdb_trap_printk--;
return 0;
@@ -1883,6 +1882,7 @@ static int kdb_lsmod(int argc, const char **argv)
kdb_printf(" (Loading)");
else
kdb_printf(" (Live)");
+ kdb_printf(" 0x%p", mod->module_core);
#ifdef CONFIG_MODULE_UNLOAD
{
@@ -2291,6 +2291,9 @@ static int kdb_ll(int argc, const char **argv)
while (va) {
char buf[80];
+ if (KDB_FLAG(CMD_INTERRUPT))
+ return 0;
+
sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
diag = kdb_parse(buf);
if (diag)
diff --git a/kernel/early_res.c b/kernel/early_res.c
index 31aa9332ef3f..7bfae887f211 100644
--- a/kernel/early_res.c
+++ b/kernel/early_res.c
@@ -7,6 +7,8 @@
#include <linux/bootmem.h>
#include <linux/mm.h>
#include <linux/early_res.h>
+#include <linux/slab.h>
+#include <linux/kmemleak.h>
/*
* Early reserved memory areas.
@@ -319,6 +321,8 @@ void __init free_early(u64 start, u64 end)
struct early_res *r;
int i;
+ kmemleak_free_part(__va(start), end - start);
+
i = find_overlapped_early(start, end);
r = &early_res[i];
if (i >= max_early_res || r->end != end || r->start != start)
@@ -333,6 +337,8 @@ void __init free_early_partial(u64 start, u64 end)
struct early_res *r;
int i;
+ kmemleak_free_part(__va(start), end - start);
+
if (start == end)
return;
diff --git a/kernel/module.c b/kernel/module.c
index 5d2d28197c82..6c562828c85c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -787,7 +787,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
/* Store the name of the last unloaded module for diagnostic purposes */
strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
- ddebug_remove_module(mod->name);
free_module(mod);
return 0;
@@ -1550,6 +1549,9 @@ static void free_module(struct module *mod)
remove_sect_attrs(mod);
mod_kobject_remove(mod);
+ /* Remove dynamic debug info */
+ ddebug_remove_module(mod->name);
+
/* Arch-specific cleanup. */
module_arch_cleanup(mod);
diff --git a/kernel/padata.c b/kernel/padata.c
index fdd8ae609ce3..751019415d23 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -26,18 +26,19 @@
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/sysfs.h>
#include <linux/rcupdate.h>
-#define MAX_SEQ_NR INT_MAX - NR_CPUS
+#define MAX_SEQ_NR (INT_MAX - NR_CPUS)
#define MAX_OBJ_NUM 1000
static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
{
int cpu, target_cpu;
- target_cpu = cpumask_first(pd->cpumask);
+ target_cpu = cpumask_first(pd->cpumask.pcpu);
for (cpu = 0; cpu < cpu_index; cpu++)
- target_cpu = cpumask_next(target_cpu, pd->cpumask);
+ target_cpu = cpumask_next(target_cpu, pd->cpumask.pcpu);
return target_cpu;
}
@@ -53,26 +54,27 @@ static int padata_cpu_hash(struct padata_priv *padata)
* Hash the sequence numbers to the cpus by taking
* seq_nr mod. number of cpus in use.
*/
- cpu_index = padata->seq_nr % cpumask_weight(pd->cpumask);
+ cpu_index = padata->seq_nr % cpumask_weight(pd->cpumask.pcpu);
return padata_index_to_cpu(pd, cpu_index);
}
-static void padata_parallel_worker(struct work_struct *work)
+static void padata_parallel_worker(struct work_struct *parallel_work)
{
- struct padata_queue *queue;
+ struct padata_parallel_queue *pqueue;
struct parallel_data *pd;
struct padata_instance *pinst;
LIST_HEAD(local_list);
local_bh_disable();
- queue = container_of(work, struct padata_queue, pwork);
- pd = queue->pd;
+ pqueue = container_of(parallel_work,
+ struct padata_parallel_queue, work);
+ pd = pqueue->pd;
pinst = pd->pinst;
- spin_lock(&queue->parallel.lock);
- list_replace_init(&queue->parallel.list, &local_list);
- spin_unlock(&queue->parallel.lock);
+ spin_lock(&pqueue->parallel.lock);
+ list_replace_init(&pqueue->parallel.list, &local_list);
+ spin_unlock(&pqueue->parallel.lock);
while (!list_empty(&local_list)) {
struct padata_priv *padata;
@@ -94,7 +96,7 @@ static void padata_parallel_worker(struct work_struct *work)
* @pinst: padata instance
* @padata: object to be parallelized
* @cb_cpu: cpu the serialization callback function will run on,
- * must be in the cpumask of padata.
+ * must be in the serial cpumask of padata(i.e. cpumask.cbcpu).
*
* The parallelization callback function will run with BHs off.
* Note: Every object which is parallelized by padata_do_parallel
@@ -104,15 +106,18 @@ int padata_do_parallel(struct padata_instance *pinst,
struct padata_priv *padata, int cb_cpu)
{
int target_cpu, err;
- struct padata_queue *queue;
+ struct padata_parallel_queue *queue;
struct parallel_data *pd;
rcu_read_lock_bh();
pd = rcu_dereference(pinst->pd);
- err = 0;
- if (!(pinst->flags & PADATA_INIT))
+ err = -EINVAL;
+ if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
+ goto out;
+
+ if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu))
goto out;
err = -EBUSY;
@@ -122,11 +127,7 @@ int padata_do_parallel(struct padata_instance *pinst,
if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
goto out;
- err = -EINVAL;
- if (!cpumask_test_cpu(cb_cpu, pd->cpumask))
- goto out;
-
- err = -EINPROGRESS;
+ err = 0;
atomic_inc(&pd->refcnt);
padata->pd = pd;
padata->cb_cpu = cb_cpu;
@@ -137,13 +138,13 @@ int padata_do_parallel(struct padata_instance *pinst,
padata->seq_nr = atomic_inc_return(&pd->seq_nr);
target_cpu = padata_cpu_hash(padata);
- queue = per_cpu_ptr(pd->queue, target_cpu);
+ queue = per_cpu_ptr(pd->pqueue, target_cpu);
spin_lock(&queue->parallel.lock);
list_add_tail(&padata->list, &queue->parallel.list);
spin_unlock(&queue->parallel.lock);
- queue_work_on(target_cpu, pinst->wq, &queue->pwork);
+ queue_work_on(target_cpu, pinst->wq, &queue->work);
out:
rcu_read_unlock_bh();
@@ -171,84 +172,52 @@ EXPORT_SYMBOL(padata_do_parallel);
*/
static struct padata_priv *padata_get_next(struct parallel_data *pd)
{
- int cpu, num_cpus, empty, calc_seq_nr;
- int seq_nr, next_nr, overrun, next_overrun;
- struct padata_queue *queue, *next_queue;
+ int cpu, num_cpus;
+ int next_nr, next_index;
+ struct padata_parallel_queue *queue, *next_queue;
struct padata_priv *padata;
struct padata_list *reorder;
- empty = 0;
- next_nr = -1;
- next_overrun = 0;
- next_queue = NULL;
-
- num_cpus = cpumask_weight(pd->cpumask);
-
- for_each_cpu(cpu, pd->cpumask) {
- queue = per_cpu_ptr(pd->queue, cpu);
- reorder = &queue->reorder;
-
- /*
- * Calculate the seq_nr of the object that should be
- * next in this reorder queue.
- */
- overrun = 0;
- calc_seq_nr = (atomic_read(&queue->num_obj) * num_cpus)
- + queue->cpu_index;
+ num_cpus = cpumask_weight(pd->cpumask.pcpu);
- if (unlikely(calc_seq_nr > pd->max_seq_nr)) {
- calc_seq_nr = calc_seq_nr - pd->max_seq_nr - 1;
- overrun = 1;
- }
-
- if (!list_empty(&reorder->list)) {
- padata = list_entry(reorder->list.next,
- struct padata_priv, list);
-
- seq_nr = padata->seq_nr;
- BUG_ON(calc_seq_nr != seq_nr);
- } else {
- seq_nr = calc_seq_nr;
- empty++;
- }
-
- if (next_nr < 0 || seq_nr < next_nr
- || (next_overrun && !overrun)) {
- next_nr = seq_nr;
- next_overrun = overrun;
- next_queue = queue;
- }
+ /*
+ * Calculate the percpu reorder queue and the sequence
+ * number of the next object.
+ */
+ next_nr = pd->processed;
+ next_index = next_nr % num_cpus;
+ cpu = padata_index_to_cpu(pd, next_index);
+ next_queue = per_cpu_ptr(pd->pqueue, cpu);
+
+ if (unlikely(next_nr > pd->max_seq_nr)) {
+ next_nr = next_nr - pd->max_seq_nr - 1;
+ next_index = next_nr % num_cpus;
+ cpu = padata_index_to_cpu(pd, next_index);
+ next_queue = per_cpu_ptr(pd->pqueue, cpu);
+ pd->processed = 0;
}
padata = NULL;
- if (empty == num_cpus)
- goto out;
-
reorder = &next_queue->reorder;
if (!list_empty(&reorder->list)) {
padata = list_entry(reorder->list.next,
struct padata_priv, list);
- if (unlikely(next_overrun)) {
- for_each_cpu(cpu, pd->cpumask) {
- queue = per_cpu_ptr(pd->queue, cpu);
- atomic_set(&queue->num_obj, 0);
- }
- }
+ BUG_ON(next_nr != padata->seq_nr);
spin_lock(&reorder->lock);
list_del_init(&padata->list);
atomic_dec(&pd->reorder_objects);
spin_unlock(&reorder->lock);
- atomic_inc(&next_queue->num_obj);
+ pd->processed++;
goto out;
}
- queue = per_cpu_ptr(pd->queue, smp_processor_id());
+ queue = per_cpu_ptr(pd->pqueue, smp_processor_id());
if (queue->cpu_index == next_queue->cpu_index) {
padata = ERR_PTR(-ENODATA);
goto out;
@@ -262,7 +231,7 @@ out:
static void padata_reorder(struct parallel_data *pd)
{
struct padata_priv *padata;
- struct padata_queue *queue;
+ struct padata_serial_queue *squeue;
struct padata_instance *pinst = pd->pinst;
/*
@@ -301,13 +270,13 @@ static void padata_reorder(struct parallel_data *pd)
return;
}
- queue = per_cpu_ptr(pd->queue, padata->cb_cpu);
+ squeue = per_cpu_ptr(pd->squeue, padata->cb_cpu);
- spin_lock(&queue->serial.lock);
- list_add_tail(&padata->list, &queue->serial.list);
- spin_unlock(&queue->serial.lock);
+ spin_lock(&squeue->serial.lock);
+ list_add_tail(&padata->list, &squeue->serial.list);
+ spin_unlock(&squeue->serial.lock);
- queue_work_on(padata->cb_cpu, pinst->wq, &queue->swork);
+ queue_work_on(padata->cb_cpu, pinst->wq, &squeue->work);
}
spin_unlock_bh(&pd->lock);
@@ -333,19 +302,19 @@ static void padata_reorder_timer(unsigned long arg)
padata_reorder(pd);
}
-static void padata_serial_worker(struct work_struct *work)
+static void padata_serial_worker(struct work_struct *serial_work)
{
- struct padata_queue *queue;
+ struct padata_serial_queue *squeue;
struct parallel_data *pd;
LIST_HEAD(local_list);
local_bh_disable();
- queue = container_of(work, struct padata_queue, swork);
- pd = queue->pd;
+ squeue = container_of(serial_work, struct padata_serial_queue, work);
+ pd = squeue->pd;
- spin_lock(&queue->serial.lock);
- list_replace_init(&queue->serial.list, &local_list);
- spin_unlock(&queue->serial.lock);
+ spin_lock(&squeue->serial.lock);
+ list_replace_init(&squeue->serial.list, &local_list);
+ spin_unlock(&squeue->serial.lock);
while (!list_empty(&local_list)) {
struct padata_priv *padata;
@@ -372,18 +341,18 @@ static void padata_serial_worker(struct work_struct *work)
void padata_do_serial(struct padata_priv *padata)
{
int cpu;
- struct padata_queue *queue;
+ struct padata_parallel_queue *pqueue;
struct parallel_data *pd;
pd = padata->pd;
cpu = get_cpu();
- queue = per_cpu_ptr(pd->queue, cpu);
+ pqueue = per_cpu_ptr(pd->pqueue, cpu);
- spin_lock(&queue->reorder.lock);
+ spin_lock(&pqueue->reorder.lock);
atomic_inc(&pd->reorder_objects);
- list_add_tail(&padata->list, &queue->reorder.list);
- spin_unlock(&queue->reorder.lock);
+ list_add_tail(&padata->list, &pqueue->reorder.list);
+ spin_unlock(&pqueue->reorder.lock);
put_cpu();
@@ -391,52 +360,89 @@ void padata_do_serial(struct padata_priv *padata)
}
EXPORT_SYMBOL(padata_do_serial);
-/* Allocate and initialize the internal cpumask dependend resources. */
-static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
- const struct cpumask *cpumask)
+static int padata_setup_cpumasks(struct parallel_data *pd,
+ const struct cpumask *pcpumask,
+ const struct cpumask *cbcpumask)
{
- int cpu, cpu_index, num_cpus;
- struct padata_queue *queue;
- struct parallel_data *pd;
-
- cpu_index = 0;
+ if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
+ return -ENOMEM;
- pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
- if (!pd)
- goto err;
+ cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_active_mask);
+ if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
+ free_cpumask_var(pd->cpumask.cbcpu);
+ return -ENOMEM;
+ }
- pd->queue = alloc_percpu(struct padata_queue);
- if (!pd->queue)
- goto err_free_pd;
+ cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_active_mask);
+ return 0;
+}
- if (!alloc_cpumask_var(&pd->cpumask, GFP_KERNEL))
- goto err_free_queue;
+static void __padata_list_init(struct padata_list *pd_list)
+{
+ INIT_LIST_HEAD(&pd_list->list);
+ spin_lock_init(&pd_list->lock);
+}
- cpumask_and(pd->cpumask, cpumask, cpu_active_mask);
+/* Initialize all percpu queues used by serial workers */
+static void padata_init_squeues(struct parallel_data *pd)
+{
+ int cpu;
+ struct padata_serial_queue *squeue;
- for_each_cpu(cpu, pd->cpumask) {
- queue = per_cpu_ptr(pd->queue, cpu);
+ for_each_cpu(cpu, pd->cpumask.cbcpu) {
+ squeue = per_cpu_ptr(pd->squeue, cpu);
+ squeue->pd = pd;
+ __padata_list_init(&squeue->serial);
+ INIT_WORK(&squeue->work, padata_serial_worker);
+ }
+}
- queue->pd = pd;
+/* Initialize all percpu queues used by parallel workers */
+static void padata_init_pqueues(struct parallel_data *pd)
+{
+ int cpu_index, num_cpus, cpu;
+ struct padata_parallel_queue *pqueue;
- queue->cpu_index = cpu_index;
+ cpu_index = 0;
+ for_each_cpu(cpu, pd->cpumask.pcpu) {
+ pqueue = per_cpu_ptr(pd->pqueue, cpu);
+ pqueue->pd = pd;
+ pqueue->cpu_index = cpu_index;
cpu_index++;
- INIT_LIST_HEAD(&queue->reorder.list);
- INIT_LIST_HEAD(&queue->parallel.list);
- INIT_LIST_HEAD(&queue->serial.list);
- spin_lock_init(&queue->reorder.lock);
- spin_lock_init(&queue->parallel.lock);
- spin_lock_init(&queue->serial.lock);
-
- INIT_WORK(&queue->pwork, padata_parallel_worker);
- INIT_WORK(&queue->swork, padata_serial_worker);
- atomic_set(&queue->num_obj, 0);
+ __padata_list_init(&pqueue->reorder);
+ __padata_list_init(&pqueue->parallel);
+ INIT_WORK(&pqueue->work, padata_parallel_worker);
+ atomic_set(&pqueue->num_obj, 0);
}
- num_cpus = cpumask_weight(pd->cpumask);
- pd->max_seq_nr = (MAX_SEQ_NR / num_cpus) * num_cpus - 1;
+ num_cpus = cpumask_weight(pd->cpumask.pcpu);
+ pd->max_seq_nr = num_cpus ? (MAX_SEQ_NR / num_cpus) * num_cpus - 1 : 0;
+}
+
+/* Allocate and initialize the internal cpumask dependend resources. */
+static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
+ const struct cpumask *pcpumask,
+ const struct cpumask *cbcpumask)
+{
+ struct parallel_data *pd;
+ pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
+ if (!pd)
+ goto err;
+
+ pd->pqueue = alloc_percpu(struct padata_parallel_queue);
+ if (!pd->pqueue)
+ goto err_free_pd;
+
+ pd->squeue = alloc_percpu(struct padata_serial_queue);
+ if (!pd->squeue)
+ goto err_free_pqueue;
+ if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0)
+ goto err_free_squeue;
+
+ padata_init_pqueues(pd);
+ padata_init_squeues(pd);
setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
atomic_set(&pd->seq_nr, -1);
atomic_set(&pd->reorder_objects, 0);
@@ -446,8 +452,10 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
return pd;
-err_free_queue:
- free_percpu(pd->queue);
+err_free_squeue:
+ free_percpu(pd->squeue);
+err_free_pqueue:
+ free_percpu(pd->pqueue);
err_free_pd:
kfree(pd);
err:
@@ -456,8 +464,10 @@ err:
static void padata_free_pd(struct parallel_data *pd)
{
- free_cpumask_var(pd->cpumask);
- free_percpu(pd->queue);
+ free_cpumask_var(pd->cpumask.pcpu);
+ free_cpumask_var(pd->cpumask.cbcpu);
+ free_percpu(pd->pqueue);
+ free_percpu(pd->squeue);
kfree(pd);
}
@@ -465,11 +475,12 @@ static void padata_free_pd(struct parallel_data *pd)
static void padata_flush_queues(struct parallel_data *pd)
{
int cpu;
- struct padata_queue *queue;
+ struct padata_parallel_queue *pqueue;
+ struct padata_serial_queue *squeue;
- for_each_cpu(cpu, pd->cpumask) {
- queue = per_cpu_ptr(pd->queue, cpu);
- flush_work(&queue->pwork);
+ for_each_cpu(cpu, pd->cpumask.pcpu) {
+ pqueue = per_cpu_ptr(pd->pqueue, cpu);
+ flush_work(&pqueue->work);
}
del_timer_sync(&pd->timer);
@@ -477,19 +488,39 @@ static void padata_flush_queues(struct parallel_data *pd)
if (atomic_read(&pd->reorder_objects))
padata_reorder(pd);
- for_each_cpu(cpu, pd->cpumask) {
- queue = per_cpu_ptr(pd->queue, cpu);
- flush_work(&queue->swork);
+ for_each_cpu(cpu, pd->cpumask.cbcpu) {
+ squeue = per_cpu_ptr(pd->squeue, cpu);
+ flush_work(&squeue->work);
}
BUG_ON(atomic_read(&pd->refcnt) != 0);
}
+static void __padata_start(struct padata_instance *pinst)
+{
+ pinst->flags |= PADATA_INIT;
+}
+
+static void __padata_stop(struct padata_instance *pinst)
+{
+ if (!(pinst->flags & PADATA_INIT))
+ return;
+
+ pinst->flags &= ~PADATA_INIT;
+
+ synchronize_rcu();
+
+ get_online_cpus();
+ padata_flush_queues(pinst->pd);
+ put_online_cpus();
+}
+
/* Replace the internal control stucture with a new one. */
static void padata_replace(struct padata_instance *pinst,
struct parallel_data *pd_new)
{
struct parallel_data *pd_old = pinst->pd;
+ int notification_mask = 0;
pinst->flags |= PADATA_RESET;
@@ -497,41 +528,162 @@ static void padata_replace(struct padata_instance *pinst,
synchronize_rcu();
+ if (!cpumask_equal(pd_old->cpumask.pcpu, pd_new->cpumask.pcpu))
+ notification_mask |= PADATA_CPU_PARALLEL;
+ if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu))
+ notification_mask |= PADATA_CPU_SERIAL;
+
padata_flush_queues(pd_old);
padata_free_pd(pd_old);
+ if (notification_mask)
+ blocking_notifier_call_chain(&pinst->cpumask_change_notifier,
+ notification_mask,
+ &pd_new->cpumask);
+
pinst->flags &= ~PADATA_RESET;
}
/**
- * padata_set_cpumask - set the cpumask that padata should use
+ * padata_register_cpumask_notifier - Registers a notifier that will be called
+ * if either pcpu or cbcpu or both cpumasks change.
*
- * @pinst: padata instance
- * @cpumask: the cpumask to use
+ * @pinst: A poineter to padata instance
+ * @nblock: A pointer to notifier block.
*/
-int padata_set_cpumask(struct padata_instance *pinst,
- cpumask_var_t cpumask)
+int padata_register_cpumask_notifier(struct padata_instance *pinst,
+ struct notifier_block *nblock)
{
+ return blocking_notifier_chain_register(&pinst->cpumask_change_notifier,
+ nblock);
+}
+EXPORT_SYMBOL(padata_register_cpumask_notifier);
+
+/**
+ * padata_unregister_cpumask_notifier - Unregisters cpumask notifier
+ * registered earlier using padata_register_cpumask_notifier
+ *
+ * @pinst: A pointer to data instance.
+ * @nlock: A pointer to notifier block.
+ */
+int padata_unregister_cpumask_notifier(struct padata_instance *pinst,
+ struct notifier_block *nblock)
+{
+ return blocking_notifier_chain_unregister(
+ &pinst->cpumask_change_notifier,
+ nblock);
+}
+EXPORT_SYMBOL(padata_unregister_cpumask_notifier);
+
+
+/* If cpumask contains no active cpu, we mark the instance as invalid. */
+static bool padata_validate_cpumask(struct padata_instance *pinst,
+ const struct cpumask *cpumask)
+{
+ if (!cpumask_intersects(cpumask, cpu_active_mask)) {
+ pinst->flags |= PADATA_INVALID;
+ return false;
+ }
+
+ pinst->flags &= ~PADATA_INVALID;
+ return true;
+}
+
+static int __padata_set_cpumasks(struct padata_instance *pinst,
+ cpumask_var_t pcpumask,
+ cpumask_var_t cbcpumask)
+{
+ int valid;
struct parallel_data *pd;
- int err = 0;
+
+ valid = padata_validate_cpumask(pinst, pcpumask);
+ if (!valid) {
+ __padata_stop(pinst);
+ goto out_replace;
+ }
+
+ valid = padata_validate_cpumask(pinst, cbcpumask);
+ if (!valid)
+ __padata_stop(pinst);
+
+out_replace:
+ pd = padata_alloc_pd(pinst, pcpumask, cbcpumask);
+ if (!pd)
+ return -ENOMEM;
+
+ cpumask_copy(pinst->cpumask.pcpu, pcpumask);
+ cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
+
+ padata_replace(pinst, pd);
+
+ if (valid)
+ __padata_start(pinst);
+
+ return 0;
+}
+
+/**
+ * padata_set_cpumasks - Set both parallel and serial cpumasks. The first
+ * one is used by parallel workers and the second one
+ * by the wokers doing serialization.
+ *
+ * @pinst: padata instance
+ * @pcpumask: the cpumask to use for parallel workers
+ * @cbcpumask: the cpumsak to use for serial workers
+ */
+int padata_set_cpumasks(struct padata_instance *pinst, cpumask_var_t pcpumask,
+ cpumask_var_t cbcpumask)
+{
+ int err;
mutex_lock(&pinst->lock);
+ get_online_cpus();
+ err = __padata_set_cpumasks(pinst, pcpumask, cbcpumask);
+
+ put_online_cpus();
+ mutex_unlock(&pinst->lock);
+
+ return err;
+
+}
+EXPORT_SYMBOL(padata_set_cpumasks);
+
+/**
+ * padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value
+ * equivalent to @cpumask.
+ *
+ * @pinst: padata instance
+ * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding
+ * to parallel and serial cpumasks respectively.
+ * @cpumask: the cpumask to use
+ */
+int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
+ cpumask_var_t cpumask)
+{
+ struct cpumask *serial_mask, *parallel_mask;
+ int err = -EINVAL;
+
+ mutex_lock(&pinst->lock);
get_online_cpus();
- pd = padata_alloc_pd(pinst, cpumask);
- if (!pd) {
- err = -ENOMEM;
- goto out;
+ switch (cpumask_type) {
+ case PADATA_CPU_PARALLEL:
+ serial_mask = pinst->cpumask.cbcpu;
+ parallel_mask = cpumask;
+ break;
+ case PADATA_CPU_SERIAL:
+ parallel_mask = pinst->cpumask.pcpu;
+ serial_mask = cpumask;
+ break;
+ default:
+ goto out;
}
- cpumask_copy(pinst->cpumask, cpumask);
-
- padata_replace(pinst, pd);
+ err = __padata_set_cpumasks(pinst, parallel_mask, serial_mask);
out:
put_online_cpus();
-
mutex_unlock(&pinst->lock);
return err;
@@ -543,30 +695,48 @@ static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
struct parallel_data *pd;
if (cpumask_test_cpu(cpu, cpu_active_mask)) {
- pd = padata_alloc_pd(pinst, pinst->cpumask);
+ pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu,
+ pinst->cpumask.cbcpu);
if (!pd)
return -ENOMEM;
padata_replace(pinst, pd);
+
+ if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) &&
+ padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
+ __padata_start(pinst);
}
return 0;
}
-/**
- * padata_add_cpu - add a cpu to the padata cpumask
+ /**
+ * padata_add_cpu - add a cpu to one or both(parallel and serial)
+ * padata cpumasks.
*
* @pinst: padata instance
* @cpu: cpu to add
+ * @mask: bitmask of flags specifying to which cpumask @cpu shuld be added.
+ * The @mask may be any combination of the following flags:
+ * PADATA_CPU_SERIAL - serial cpumask
+ * PADATA_CPU_PARALLEL - parallel cpumask
*/
-int padata_add_cpu(struct padata_instance *pinst, int cpu)
+
+int padata_add_cpu(struct padata_instance *pinst, int cpu, int mask)
{
int err;
+ if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL)))
+ return -EINVAL;
+
mutex_lock(&pinst->lock);
get_online_cpus();
- cpumask_set_cpu(cpu, pinst->cpumask);
+ if (mask & PADATA_CPU_SERIAL)
+ cpumask_set_cpu(cpu, pinst->cpumask.cbcpu);
+ if (mask & PADATA_CPU_PARALLEL)
+ cpumask_set_cpu(cpu, pinst->cpumask.pcpu);
+
err = __padata_add_cpu(pinst, cpu);
put_online_cpus();
@@ -578,10 +748,16 @@ EXPORT_SYMBOL(padata_add_cpu);
static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
{
- struct parallel_data *pd;
+ struct parallel_data *pd = NULL;
if (cpumask_test_cpu(cpu, cpu_online_mask)) {
- pd = padata_alloc_pd(pinst, pinst->cpumask);
+
+ if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) ||
+ !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu))
+ __padata_stop(pinst);
+
+ pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu,
+ pinst->cpumask.cbcpu);
if (!pd)
return -ENOMEM;
@@ -591,20 +767,32 @@ static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
return 0;
}
-/**
- * padata_remove_cpu - remove a cpu from the padata cpumask
+ /**
+ * padata_remove_cpu - remove a cpu from the one or both(serial and paralell)
+ * padata cpumasks.
*
* @pinst: padata instance
* @cpu: cpu to remove
+ * @mask: bitmask specifying from which cpumask @cpu should be removed
+ * The @mask may be any combination of the following flags:
+ * PADATA_CPU_SERIAL - serial cpumask
+ * PADATA_CPU_PARALLEL - parallel cpumask
*/
-int padata_remove_cpu(struct padata_instance *pinst, int cpu)
+int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask)
{
int err;
+ if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL)))
+ return -EINVAL;
+
mutex_lock(&pinst->lock);
get_online_cpus();
- cpumask_clear_cpu(cpu, pinst->cpumask);
+ if (mask & PADATA_CPU_SERIAL)
+ cpumask_clear_cpu(cpu, pinst->cpumask.cbcpu);
+ if (mask & PADATA_CPU_PARALLEL)
+ cpumask_clear_cpu(cpu, pinst->cpumask.pcpu);
+
err = __padata_remove_cpu(pinst, cpu);
put_online_cpus();
@@ -619,11 +807,20 @@ EXPORT_SYMBOL(padata_remove_cpu);
*
* @pinst: padata instance to start
*/
-void padata_start(struct padata_instance *pinst)
+int padata_start(struct padata_instance *pinst)
{
+ int err = 0;
+
mutex_lock(&pinst->lock);
- pinst->flags |= PADATA_INIT;
+
+ if (pinst->flags & PADATA_INVALID)
+ err =-EINVAL;
+
+ __padata_start(pinst);
+
mutex_unlock(&pinst->lock);
+
+ return err;
}
EXPORT_SYMBOL(padata_start);
@@ -635,12 +832,20 @@ EXPORT_SYMBOL(padata_start);
void padata_stop(struct padata_instance *pinst)
{
mutex_lock(&pinst->lock);
- pinst->flags &= ~PADATA_INIT;
+ __padata_stop(pinst);
mutex_unlock(&pinst->lock);
}
EXPORT_SYMBOL(padata_stop);
#ifdef CONFIG_HOTPLUG_CPU
+
+static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu)
+{
+ return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) ||
+ cpumask_test_cpu(cpu, pinst->cpumask.cbcpu);
+}
+
+
static int padata_cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
@@ -653,7 +858,7 @@ static int padata_cpu_callback(struct notifier_block *nfb,
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- if (!cpumask_test_cpu(cpu, pinst->cpumask))
+ if (!pinst_has_cpu(pinst, cpu))
break;
mutex_lock(&pinst->lock);
err = __padata_add_cpu(pinst, cpu);
@@ -664,7 +869,7 @@ static int padata_cpu_callback(struct notifier_block *nfb,
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
- if (!cpumask_test_cpu(cpu, pinst->cpumask))
+ if (!pinst_has_cpu(pinst, cpu))
break;
mutex_lock(&pinst->lock);
err = __padata_remove_cpu(pinst, cpu);
@@ -675,7 +880,7 @@ static int padata_cpu_callback(struct notifier_block *nfb,
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- if (!cpumask_test_cpu(cpu, pinst->cpumask))
+ if (!pinst_has_cpu(pinst, cpu))
break;
mutex_lock(&pinst->lock);
__padata_remove_cpu(pinst, cpu);
@@ -683,7 +888,7 @@ static int padata_cpu_callback(struct notifier_block *nfb,
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- if (!cpumask_test_cpu(cpu, pinst->cpumask))
+ if (!pinst_has_cpu(pinst, cpu))
break;
mutex_lock(&pinst->lock);
__padata_add_cpu(pinst, cpu);
@@ -694,36 +899,202 @@ static int padata_cpu_callback(struct notifier_block *nfb,
}
#endif
+static void __padata_free(struct padata_instance *pinst)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ unregister_hotcpu_notifier(&pinst->cpu_notifier);
+#endif
+
+ padata_stop(pinst);
+ padata_free_pd(pinst->pd);
+ free_cpumask_var(pinst->cpumask.pcpu);
+ free_cpumask_var(pinst->cpumask.cbcpu);
+ kfree(pinst);
+}
+
+#define kobj2pinst(_kobj) \
+ container_of(_kobj, struct padata_instance, kobj)
+#define attr2pentry(_attr) \
+ container_of(_attr, struct padata_sysfs_entry, attr)
+
+static void padata_sysfs_release(struct kobject *kobj)
+{
+ struct padata_instance *pinst = kobj2pinst(kobj);
+ __padata_free(pinst);
+}
+
+struct padata_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct padata_instance *, struct attribute *, char *);
+ ssize_t (*store)(struct padata_instance *, struct attribute *,
+ const char *, size_t);
+};
+
+static ssize_t show_cpumask(struct padata_instance *pinst,
+ struct attribute *attr, char *buf)
+{
+ struct cpumask *cpumask;
+ ssize_t len;
+
+ mutex_lock(&pinst->lock);
+ if (!strcmp(attr->name, "serial_cpumask"))
+ cpumask = pinst->cpumask.cbcpu;
+ else
+ cpumask = pinst->cpumask.pcpu;
+
+ len = bitmap_scnprintf(buf, PAGE_SIZE, cpumask_bits(cpumask),
+ nr_cpu_ids);
+ if (PAGE_SIZE - len < 2)
+ len = -EINVAL;
+ else
+ len += sprintf(buf + len, "\n");
+
+ mutex_unlock(&pinst->lock);
+ return len;
+}
+
+static ssize_t store_cpumask(struct padata_instance *pinst,
+ struct attribute *attr,
+ const char *buf, size_t count)
+{
+ cpumask_var_t new_cpumask;
+ ssize_t ret;
+ int mask_type;
+
+ if (!alloc_cpumask_var(&new_cpumask, GFP_KERNEL))
+ return -ENOMEM;
+
+ ret = bitmap_parse(buf, count, cpumask_bits(new_cpumask),
+ nr_cpumask_bits);
+ if (ret < 0)
+ goto out;
+
+ mask_type = !strcmp(attr->name, "serial_cpumask") ?
+ PADATA_CPU_SERIAL : PADATA_CPU_PARALLEL;
+ ret = padata_set_cpumask(pinst, mask_type, new_cpumask);
+ if (!ret)
+ ret = count;
+
+out:
+ free_cpumask_var(new_cpumask);
+ return ret;
+}
+
+#define PADATA_ATTR_RW(_name, _show_name, _store_name) \
+ static struct padata_sysfs_entry _name##_attr = \
+ __ATTR(_name, 0644, _show_name, _store_name)
+#define PADATA_ATTR_RO(_name, _show_name) \
+ static struct padata_sysfs_entry _name##_attr = \
+ __ATTR(_name, 0400, _show_name, NULL)
+
+PADATA_ATTR_RW(serial_cpumask, show_cpumask, store_cpumask);
+PADATA_ATTR_RW(parallel_cpumask, show_cpumask, store_cpumask);
+
+/*
+ * Padata sysfs provides the following objects:
+ * serial_cpumask [RW] - cpumask for serial workers
+ * parallel_cpumask [RW] - cpumask for parallel workers
+ */
+static struct attribute *padata_default_attrs[] = {
+ &serial_cpumask_attr.attr,
+ &parallel_cpumask_attr.attr,
+ NULL,
+};
+
+static ssize_t padata_sysfs_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct padata_instance *pinst;
+ struct padata_sysfs_entry *pentry;
+ ssize_t ret = -EIO;
+
+ pinst = kobj2pinst(kobj);
+ pentry = attr2pentry(attr);
+ if (pentry->show)
+ ret = pentry->show(pinst, attr, buf);
+
+ return ret;
+}
+
+static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ struct padata_instance *pinst;
+ struct padata_sysfs_entry *pentry;
+ ssize_t ret = -EIO;
+
+ pinst = kobj2pinst(kobj);
+ pentry = attr2pentry(attr);
+ if (pentry->show)
+ ret = pentry->store(pinst, attr, buf, count);
+
+ return ret;
+}
+
+static const struct sysfs_ops padata_sysfs_ops = {
+ .show = padata_sysfs_show,
+ .store = padata_sysfs_store,
+};
+
+static struct kobj_type padata_attr_type = {
+ .sysfs_ops = &padata_sysfs_ops,
+ .default_attrs = padata_default_attrs,
+ .release = padata_sysfs_release,
+};
+
/**
- * padata_alloc - allocate and initialize a padata instance
+ * padata_alloc_possible - Allocate and initialize padata instance.
+ * Use the cpu_possible_mask for serial and
+ * parallel workers.
*
- * @cpumask: cpumask that padata uses for parallelization
* @wq: workqueue to use for the allocated padata instance
*/
-struct padata_instance *padata_alloc(const struct cpumask *cpumask,
- struct workqueue_struct *wq)
+struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
+{
+ return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
+}
+EXPORT_SYMBOL(padata_alloc_possible);
+
+/**
+ * padata_alloc - allocate and initialize a padata instance and specify
+ * cpumasks for serial and parallel workers.
+ *
+ * @wq: workqueue to use for the allocated padata instance
+ * @pcpumask: cpumask that will be used for padata parallelization
+ * @cbcpumask: cpumask that will be used for padata serialization
+ */
+struct padata_instance *padata_alloc(struct workqueue_struct *wq,
+ const struct cpumask *pcpumask,
+ const struct cpumask *cbcpumask)
{
struct padata_instance *pinst;
- struct parallel_data *pd;
+ struct parallel_data *pd = NULL;
pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL);
if (!pinst)
goto err;
get_online_cpus();
-
- pd = padata_alloc_pd(pinst, cpumask);
- if (!pd)
+ if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
goto err_free_inst;
+ if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
+ free_cpumask_var(pinst->cpumask.pcpu);
+ goto err_free_inst;
+ }
+ if (!padata_validate_cpumask(pinst, pcpumask) ||
+ !padata_validate_cpumask(pinst, cbcpumask))
+ goto err_free_masks;
- if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL))
- goto err_free_pd;
+ pd = padata_alloc_pd(pinst, pcpumask, cbcpumask);
+ if (!pd)
+ goto err_free_masks;
rcu_assign_pointer(pinst->pd, pd);
pinst->wq = wq;
- cpumask_copy(pinst->cpumask, cpumask);
+ cpumask_copy(pinst->cpumask.pcpu, pcpumask);
+ cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
pinst->flags = 0;
@@ -735,12 +1106,15 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask,
put_online_cpus();
+ BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier);
+ kobject_init(&pinst->kobj, &padata_attr_type);
mutex_init(&pinst->lock);
return pinst;
-err_free_pd:
- padata_free_pd(pd);
+err_free_masks:
+ free_cpumask_var(pinst->cpumask.pcpu);
+ free_cpumask_var(pinst->cpumask.cbcpu);
err_free_inst:
kfree(pinst);
put_online_cpus();
@@ -756,19 +1130,6 @@ EXPORT_SYMBOL(padata_alloc);
*/
void padata_free(struct padata_instance *pinst)
{
- padata_stop(pinst);
-
- synchronize_rcu();
-
-#ifdef CONFIG_HOTPLUG_CPU
- unregister_hotcpu_notifier(&pinst->cpu_notifier);
-#endif
- get_online_cpus();
- padata_flush_queues(pinst->pd);
- put_online_cpus();
-
- padata_free_pd(pinst->pd);
- free_cpumask_var(pinst->cpumask);
- kfree(pinst);
+ kobject_put(&pinst->kobj);
}
EXPORT_SYMBOL(padata_free);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index f42d3f737a33..996a4dec5f96 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -48,59 +48,49 @@
* or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
* held, taken with _irqsave. One lock to rule them all
*/
-struct pm_qos_request_list {
- struct list_head list;
- union {
- s32 value;
- s32 usec;
- s32 kbps;
- };
- int pm_qos_class;
+enum pm_qos_type {
+ PM_QOS_MAX, /* return the largest value */
+ PM_QOS_MIN /* return the smallest value */
};
-static s32 max_compare(s32 v1, s32 v2);
-static s32 min_compare(s32 v1, s32 v2);
-
struct pm_qos_object {
- struct pm_qos_request_list requests;
+ struct plist_head requests;
struct blocking_notifier_head *notifiers;
struct miscdevice pm_qos_power_miscdev;
char *name;
s32 default_value;
- atomic_t target_value;
- s32 (*comparitor)(s32, s32);
+ enum pm_qos_type type;
};
+static DEFINE_SPINLOCK(pm_qos_lock);
+
static struct pm_qos_object null_pm_qos;
static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
static struct pm_qos_object cpu_dma_pm_qos = {
- .requests = {LIST_HEAD_INIT(cpu_dma_pm_qos.requests.list)},
+ .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
.notifiers = &cpu_dma_lat_notifier,
.name = "cpu_dma_latency",
.default_value = 2000 * USEC_PER_SEC,
- .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
- .comparitor = min_compare
+ .type = PM_QOS_MIN,
};
static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
static struct pm_qos_object network_lat_pm_qos = {
- .requests = {LIST_HEAD_INIT(network_lat_pm_qos.requests.list)},
+ .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
.notifiers = &network_lat_notifier,
.name = "network_latency",
.default_value = 2000 * USEC_PER_SEC,
- .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
- .comparitor = min_compare
+ .type = PM_QOS_MIN
};
static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier);
static struct pm_qos_object network_throughput_pm_qos = {
- .requests = {LIST_HEAD_INIT(network_throughput_pm_qos.requests.list)},
+ .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
.notifiers = &network_throughput_notifier,
.name = "network_throughput",
.default_value = 0,
- .target_value = ATOMIC_INIT(0),
- .comparitor = max_compare
+ .type = PM_QOS_MAX,
};
@@ -111,8 +101,6 @@ static struct pm_qos_object *pm_qos_array[] = {
&network_throughput_pm_qos
};
-static DEFINE_SPINLOCK(pm_qos_lock);
-
static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
size_t count, loff_t *f_pos);
static int pm_qos_power_open(struct inode *inode, struct file *filp);
@@ -124,46 +112,55 @@ static const struct file_operations pm_qos_power_fops = {
.release = pm_qos_power_release,
};
-/* static helper functions */
-static s32 max_compare(s32 v1, s32 v2)
+/* unlocked internal variant */
+static inline int pm_qos_get_value(struct pm_qos_object *o)
{
- return max(v1, v2);
-}
+ if (plist_head_empty(&o->requests))
+ return o->default_value;
-static s32 min_compare(s32 v1, s32 v2)
-{
- return min(v1, v2);
-}
+ switch (o->type) {
+ case PM_QOS_MIN:
+ return plist_last(&o->requests)->prio;
+ case PM_QOS_MAX:
+ return plist_first(&o->requests)->prio;
-static void update_target(int pm_qos_class)
+ default:
+ /* runtime check for not using enum */
+ BUG();
+ }
+}
+
+static void update_target(struct pm_qos_object *o, struct plist_node *node,
+ int del, int value)
{
- s32 extreme_value;
- struct pm_qos_request_list *node;
unsigned long flags;
- int call_notifier = 0;
+ int prev_value, curr_value;
spin_lock_irqsave(&pm_qos_lock, flags);
- extreme_value = pm_qos_array[pm_qos_class]->default_value;
- list_for_each_entry(node,
- &pm_qos_array[pm_qos_class]->requests.list, list) {
- extreme_value = pm_qos_array[pm_qos_class]->comparitor(
- extreme_value, node->value);
- }
- if (atomic_read(&pm_qos_array[pm_qos_class]->target_value) !=
- extreme_value) {
- call_notifier = 1;
- atomic_set(&pm_qos_array[pm_qos_class]->target_value,
- extreme_value);
- pr_debug(KERN_ERR "new target for qos %d is %d\n", pm_qos_class,
- atomic_read(&pm_qos_array[pm_qos_class]->target_value));
+ prev_value = pm_qos_get_value(o);
+ /* PM_QOS_DEFAULT_VALUE is a signal that the value is unchanged */
+ if (value != PM_QOS_DEFAULT_VALUE) {
+ /*
+ * to change the list, we atomically remove, reinit
+ * with new value and add, then see if the extremal
+ * changed
+ */
+ plist_del(node, &o->requests);
+ plist_node_init(node, value);
+ plist_add(node, &o->requests);
+ } else if (del) {
+ plist_del(node, &o->requests);
+ } else {
+ plist_add(node, &o->requests);
}
+ curr_value = pm_qos_get_value(o);
spin_unlock_irqrestore(&pm_qos_lock, flags);
- if (call_notifier)
- blocking_notifier_call_chain(
- pm_qos_array[pm_qos_class]->notifiers,
- (unsigned long) extreme_value, NULL);
+ if (prev_value != curr_value)
+ blocking_notifier_call_chain(o->notifiers,
+ (unsigned long)curr_value,
+ NULL);
}
static int register_pm_qos_misc(struct pm_qos_object *qos)
@@ -196,10 +193,23 @@ static int find_pm_qos_object_by_minor(int minor)
*/
int pm_qos_request(int pm_qos_class)
{
- return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
+ unsigned long flags;
+ int value;
+
+ spin_lock_irqsave(&pm_qos_lock, flags);
+ value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
+ spin_unlock_irqrestore(&pm_qos_lock, flags);
+
+ return value;
}
EXPORT_SYMBOL_GPL(pm_qos_request);
+int pm_qos_request_active(struct pm_qos_request_list *req)
+{
+ return req->pm_qos_class != 0;
+}
+EXPORT_SYMBOL_GPL(pm_qos_request_active);
+
/**
* pm_qos_add_request - inserts new qos request into the list
* @pm_qos_class: identifies which list of qos request to us
@@ -211,27 +221,23 @@ EXPORT_SYMBOL_GPL(pm_qos_request);
* element as a handle for use in updating and removal. Call needs to save
* this handle for later use.
*/
-struct pm_qos_request_list *pm_qos_add_request(int pm_qos_class, s32 value)
+void pm_qos_add_request(struct pm_qos_request_list *dep,
+ int pm_qos_class, s32 value)
{
- struct pm_qos_request_list *dep;
- unsigned long flags;
+ struct pm_qos_object *o = pm_qos_array[pm_qos_class];
+ int new_value;
- dep = kzalloc(sizeof(struct pm_qos_request_list), GFP_KERNEL);
- if (dep) {
- if (value == PM_QOS_DEFAULT_VALUE)
- dep->value = pm_qos_array[pm_qos_class]->default_value;
- else
- dep->value = value;
- dep->pm_qos_class = pm_qos_class;
-
- spin_lock_irqsave(&pm_qos_lock, flags);
- list_add(&dep->list,
- &pm_qos_array[pm_qos_class]->requests.list);
- spin_unlock_irqrestore(&pm_qos_lock, flags);
- update_target(pm_qos_class);
+ if (pm_qos_request_active(dep)) {
+ WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n");
+ return;
}
-
- return dep;
+ if (value == PM_QOS_DEFAULT_VALUE)
+ new_value = o->default_value;
+ else
+ new_value = value;
+ plist_node_init(&dep->list, new_value);
+ dep->pm_qos_class = pm_qos_class;
+ update_target(o, &dep->list, 0, PM_QOS_DEFAULT_VALUE);
}
EXPORT_SYMBOL_GPL(pm_qos_add_request);
@@ -246,27 +252,28 @@ EXPORT_SYMBOL_GPL(pm_qos_add_request);
* Attempts are made to make this code callable on hot code paths.
*/
void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
- s32 new_value)
+ s32 new_value)
{
- unsigned long flags;
- int pending_update = 0;
s32 temp;
+ struct pm_qos_object *o;
+
+ if (!pm_qos_req) /*guard against callers passing in null */
+ return;
- if (pm_qos_req) { /*guard against callers passing in null */
- spin_lock_irqsave(&pm_qos_lock, flags);
- if (new_value == PM_QOS_DEFAULT_VALUE)
- temp = pm_qos_array[pm_qos_req->pm_qos_class]->default_value;
- else
- temp = new_value;
-
- if (temp != pm_qos_req->value) {
- pending_update = 1;
- pm_qos_req->value = temp;
- }
- spin_unlock_irqrestore(&pm_qos_lock, flags);
- if (pending_update)
- update_target(pm_qos_req->pm_qos_class);
+ if (!pm_qos_request_active(pm_qos_req)) {
+ WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n");
+ return;
}
+
+ o = pm_qos_array[pm_qos_req->pm_qos_class];
+
+ if (new_value == PM_QOS_DEFAULT_VALUE)
+ temp = o->default_value;
+ else
+ temp = new_value;
+
+ if (temp != pm_qos_req->list.prio)
+ update_target(o, &pm_qos_req->list, 0, temp);
}
EXPORT_SYMBOL_GPL(pm_qos_update_request);
@@ -280,19 +287,20 @@ EXPORT_SYMBOL_GPL(pm_qos_update_request);
*/
void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req)
{
- unsigned long flags;
- int qos_class;
+ struct pm_qos_object *o;
if (pm_qos_req == NULL)
return;
/* silent return to keep pcm code cleaner */
- qos_class = pm_qos_req->pm_qos_class;
- spin_lock_irqsave(&pm_qos_lock, flags);
- list_del(&pm_qos_req->list);
- kfree(pm_qos_req);
- spin_unlock_irqrestore(&pm_qos_lock, flags);
- update_target(qos_class);
+ if (!pm_qos_request_active(pm_qos_req)) {
+ WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n");
+ return;
+ }
+
+ o = pm_qos_array[pm_qos_req->pm_qos_class];
+ update_target(o, &pm_qos_req->list, 1, PM_QOS_DEFAULT_VALUE);
+ memset(pm_qos_req, 0, sizeof(*pm_qos_req));
}
EXPORT_SYMBOL_GPL(pm_qos_remove_request);
@@ -340,8 +348,12 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
if (pm_qos_class >= 0) {
- filp->private_data = (void *) pm_qos_add_request(pm_qos_class,
- PM_QOS_DEFAULT_VALUE);
+ struct pm_qos_request_list *req = kzalloc(GFP_KERNEL, sizeof(*req));
+ if (!req)
+ return -ENOMEM;
+
+ pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE);
+ filp->private_data = req;
if (filp->private_data)
return 0;
@@ -353,8 +365,9 @@ static int pm_qos_power_release(struct inode *inode, struct file *filp)
{
struct pm_qos_request_list *req;
- req = (struct pm_qos_request_list *)filp->private_data;
+ req = filp->private_data;
pm_qos_remove_request(req);
+ kfree(req);
return 0;
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index aa9e916da4d5..d26f04e92743 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -277,7 +277,7 @@ static int create_image(int platform_mode)
goto Enable_irqs;
}
- if (hibernation_test(TEST_CORE))
+ if (hibernation_test(TEST_CORE) || !pm_check_wakeup_events())
goto Power_up;
in_suspend = 1;
@@ -288,8 +288,10 @@ static int create_image(int platform_mode)
error);
/* Restore control flow magically appears here */
restore_processor_state();
- if (!in_suspend)
+ if (!in_suspend) {
+ events_check_enabled = false;
platform_leave(platform_mode);
+ }
Power_up:
sysdev_resume();
@@ -328,7 +330,7 @@ int hibernation_snapshot(int platform_mode)
error = platform_begin(platform_mode);
if (error)
- return error;
+ goto Close;
/* Preallocate image memory before shutting down devices. */
error = hibernate_preallocate_memory();
@@ -511,18 +513,24 @@ int hibernation_platform_enter(void)
local_irq_disable();
sysdev_suspend(PMSG_HIBERNATE);
+ if (!pm_check_wakeup_events()) {
+ error = -EAGAIN;
+ goto Power_up;
+ }
+
hibernation_ops->enter();
/* We should never get here */
while (1);
- /*
- * We don't need to reenable the nonboot CPUs or resume consoles, since
- * the system is going to be halted anyway.
- */
+ Power_up:
+ sysdev_resume();
+ local_irq_enable();
+ enable_nonboot_cpus();
+
Platform_finish:
hibernation_ops->finish();
- dpm_suspend_noirq(PMSG_RESTORE);
+ dpm_resume_noirq(PMSG_RESTORE);
Resume_devices:
entering_platform_hibernation = false;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b58800b21fc0..62b0bc6e4983 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -204,6 +204,60 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
power_attr(state);
+#ifdef CONFIG_PM_SLEEP
+/*
+ * The 'wakeup_count' attribute, along with the functions defined in
+ * drivers/base/power/wakeup.c, provides a means by which wakeup events can be
+ * handled in a non-racy way.
+ *
+ * If a wakeup event occurs when the system is in a sleep state, it simply is
+ * woken up. In turn, if an event that would wake the system up from a sleep
+ * state occurs when it is undergoing a transition to that sleep state, the
+ * transition should be aborted. Moreover, if such an event occurs when the
+ * system is in the working state, an attempt to start a transition to the
+ * given sleep state should fail during certain period after the detection of
+ * the event. Using the 'state' attribute alone is not sufficient to satisfy
+ * these requirements, because a wakeup event may occur exactly when 'state'
+ * is being written to and may be delivered to user space right before it is
+ * frozen, so the event will remain only partially processed until the system is
+ * woken up by another event. In particular, it won't cause the transition to
+ * a sleep state to be aborted.
+ *
+ * This difficulty may be overcome if user space uses 'wakeup_count' before
+ * writing to 'state'. It first should read from 'wakeup_count' and store
+ * the read value. Then, after carrying out its own preparations for the system
+ * transition to a sleep state, it should write the stored value to
+ * 'wakeup_count'. If that fails, at least one wakeup event has occured since
+ * 'wakeup_count' was read and 'state' should not be written to. Otherwise, it
+ * is allowed to write to 'state', but the transition will be aborted if there
+ * are any wakeup events detected after 'wakeup_count' was written to.
+ */
+
+static ssize_t wakeup_count_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ unsigned long val;
+
+ return pm_get_wakeup_count(&val) ? sprintf(buf, "%lu\n", val) : -EINTR;
+}
+
+static ssize_t wakeup_count_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned long val;
+
+ if (sscanf(buf, "%lu", &val) == 1) {
+ if (pm_save_wakeup_count(val))
+ return n;
+ }
+ return -EINVAL;
+}
+
+power_attr(wakeup_count);
+#endif /* CONFIG_PM_SLEEP */
+
#ifdef CONFIG_PM_TRACE
int pm_trace_enabled;
@@ -236,6 +290,7 @@ static struct attribute * g[] = {
#endif
#ifdef CONFIG_PM_SLEEP
&pm_async_attr.attr,
+ &wakeup_count_attr.attr,
#ifdef CONFIG_PM_DEBUG
&pm_test_attr.attr,
#endif
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f37cb7dd4402..7335952ee473 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -136,19 +136,19 @@ static int suspend_enter(suspend_state_t state)
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
- return error;
+ goto Platform_finish;
}
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
- goto Platfrom_finish;
+ goto Platform_finish;
}
if (suspend_ops->prepare_late) {
error = suspend_ops->prepare_late();
if (error)
- goto Power_up_devices;
+ goto Platform_wake;
}
if (suspend_test(TEST_PLATFORM))
@@ -163,8 +163,10 @@ static int suspend_enter(suspend_state_t state)
error = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
- if (!suspend_test(TEST_CORE))
+ if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) {
error = suspend_ops->enter(state);
+ events_check_enabled = false;
+ }
sysdev_resume();
}
@@ -178,10 +180,9 @@ static int suspend_enter(suspend_state_t state)
if (suspend_ops->wake)
suspend_ops->wake();
- Power_up_devices:
dpm_resume_noirq(PMSG_RESUME);
- Platfrom_finish:
+ Platform_finish:
if (suspend_ops->finish)
suspend_ops->finish();
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index b0bb21778391..7c3ae83e41d7 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -32,7 +32,7 @@
/*
* The swap map is a data structure used for keeping track of each page
* written to a swap partition. It consists of many swap_map_page
- * structures that contain each an array of MAP_PAGE_SIZE swap entries.
+ * structures that contain each an array of MAP_PAGE_ENTRIES swap entries.
* These structures are stored on the swap and linked together with the
* help of the .next_swap member.
*
@@ -148,7 +148,7 @@ sector_t alloc_swapdev_block(int swap)
/**
* free_all_swap_pages - free swap pages allocated for saving image data.
- * It also frees the extents used to register which swap entres had been
+ * It also frees the extents used to register which swap entries had been
* allocated.
*/
diff --git a/kernel/signal.c b/kernel/signal.c
index 906ae5a1779c..bded65187780 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -637,7 +637,7 @@ static inline bool si_fromuser(const struct siginfo *info)
/*
* Bad permissions for sending the signal
- * - the caller must hold at least the RCU read lock
+ * - the caller must hold the RCU read lock
*/
static int check_kill_permission(int sig, struct siginfo *info,
struct task_struct *t)
@@ -1127,11 +1127,14 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
/*
* send signal info to all the members of a group
- * - the caller must hold the RCU read lock at least
*/
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
- int ret = check_kill_permission(sig, info, p);
+ int ret;
+
+ rcu_read_lock();
+ ret = check_kill_permission(sig, info, p);
+ rcu_read_unlock();
if (!ret && sig)
ret = do_send_sig_info(sig, info, p, true);
diff --git a/kernel/timer.c b/kernel/timer.c
index ee305c8d4e18..efde11e197c4 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -577,6 +577,19 @@ static void __init_timer(struct timer_list *timer,
lockdep_init_map(&timer->lockdep_map, name, key, 0);
}
+void setup_deferrable_timer_on_stack_key(struct timer_list *timer,
+ const char *name,
+ struct lock_class_key *key,
+ void (*function)(unsigned long),
+ unsigned long data)
+{
+ timer->function = function;
+ timer->data = data;
+ init_timer_on_stack_key(timer, name, key);
+ timer_set_deferrable(timer);
+}
+EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key);
+
/**
* init_timer_key - initialize a timer
* @timer: the timer to be initialized
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index b2d70d38dff4..25915832291a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,6 +9,7 @@
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/user_namespace.h>
+#include <linux/highuid.h>
#include <linux/cred.h>
/*
@@ -82,3 +83,46 @@ void free_user_ns(struct kref *kref)
schedule_work(&ns->destroyer);
}
EXPORT_SYMBOL(free_user_ns);
+
+uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid)
+{
+ struct user_namespace *tmp;
+
+ if (likely(to == cred->user->user_ns))
+ return uid;
+
+
+ /* Is cred->user the creator of the target user_ns
+ * or the creator of one of it's parents?
+ */
+ for ( tmp = to; tmp != &init_user_ns;
+ tmp = tmp->creator->user_ns ) {
+ if (cred->user == tmp->creator) {
+ return (uid_t)0;
+ }
+ }
+
+ /* No useful relationship so no mapping */
+ return overflowuid;
+}
+
+gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid)
+{
+ struct user_namespace *tmp;
+
+ if (likely(to == cred->user->user_ns))
+ return gid;
+
+ /* Is cred->user the creator of the target user_ns
+ * or the creator of one of it's parents?
+ */
+ for ( tmp = to; tmp != &init_user_ns;
+ tmp = tmp->creator->user_ns ) {
+ if (cred->user == tmp->creator) {
+ return (gid_t)0;
+ }
+ }
+
+ /* No useful relationship so no mapping */
+ return overflowgid;
+}
OpenPOWER on IntegriCloud