summaryrefslogtreecommitdiff
path: root/kernel/power
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/power')
-rw-r--r--kernel/power/Kconfig11
-rw-r--r--kernel/power/Makefile4
-rw-r--r--kernel/power/console.c8
-rw-r--r--kernel/power/em_netlink.c308
-rw-r--r--kernel/power/em_netlink.h39
-rw-r--r--kernel/power/em_netlink_autogen.c48
-rw-r--r--kernel/power/em_netlink_autogen.h23
-rw-r--r--kernel/power/energy_model.c90
-rw-r--r--kernel/power/hibernate.c19
-rw-r--r--kernel/power/main.c103
-rw-r--r--kernel/power/power.h1
-rw-r--r--kernel/power/process.c1
-rw-r--r--kernel/power/qos.c106
-rw-r--r--kernel/power/snapshot.c13
-rw-r--r--kernel/power/suspend.c16
-rw-r--r--kernel/power/swap.c278
-rw-r--r--kernel/power/user.c4
17 files changed, 912 insertions, 160 deletions
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 54a623680019..05337f437cca 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -202,6 +202,17 @@ config PM_WAKELOCKS_GC
depends on PM_WAKELOCKS
default y
+config PM_QOS_CPU_SYSTEM_WAKEUP
+ bool "User space interface for CPU system wakeup QoS"
+ depends on CPU_IDLE
+ help
+ Enable this to allow user space via the cpu_wakeup_latency file to
+ specify a CPU system wakeup latency limit.
+
+ This may be particularly useful for platforms supporting multiple low
+ power states for CPUs during system-wide suspend and s2idle in
+ particular.
+
config PM
bool "Device power management core functionality"
help
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 874ad834dc8d..773e2789412b 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -21,4 +21,6 @@ obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
-obj-$(CONFIG_ENERGY_MODEL) += energy_model.o
+obj-$(CONFIG_ENERGY_MODEL) += em.o
+em-y := energy_model.o
+em-$(CONFIG_NET) += em_netlink_autogen.o em_netlink.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 19c48aa5355d..a906a0ac0f9b 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -44,9 +44,10 @@ static LIST_HEAD(pm_vt_switch_list);
* no_console_suspend argument has been passed on the command line, VT
* switches will occur.
*/
-void pm_vt_switch_required(struct device *dev, bool required)
+int pm_vt_switch_required(struct device *dev, bool required)
{
struct pm_vt_switch *entry, *tmp;
+ int ret = 0;
mutex_lock(&vt_switch_mutex);
list_for_each_entry(tmp, &pm_vt_switch_list, head) {
@@ -58,8 +59,10 @@ void pm_vt_switch_required(struct device *dev, bool required)
}
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
+ if (!entry) {
+ ret = -ENOMEM;
goto out;
+ }
entry->required = required;
entry->dev = dev;
@@ -67,6 +70,7 @@ void pm_vt_switch_required(struct device *dev, bool required)
list_add(&entry->head, &pm_vt_switch_list);
out:
mutex_unlock(&vt_switch_mutex);
+ return ret;
}
EXPORT_SYMBOL(pm_vt_switch_required);
diff --git a/kernel/power/em_netlink.c b/kernel/power/em_netlink.c
new file mode 100644
index 000000000000..4b85da138a06
--- /dev/null
+++ b/kernel/power/em_netlink.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Generic netlink for energy model.
+ *
+ * Copyright (c) 2025 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/energy_model.h>
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <uapi/linux/energy_model.h>
+
+#include "em_netlink.h"
+#include "em_netlink_autogen.h"
+
+#define EM_A_PD_CPUS_LEN 256
+
+/*************************** Command encoding ********************************/
+static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data)
+{
+ char cpus_buf[EM_A_PD_CPUS_LEN];
+ int *tot_msg_sz = data;
+ int msg_sz, cpus_sz;
+
+ cpus_sz = snprintf(cpus_buf, sizeof(cpus_buf), "%*pb",
+ cpumask_pr_args(to_cpumask(pd->cpus)));
+
+ msg_sz = nla_total_size(0) + /* EM_A_PDS_PD */
+ nla_total_size(sizeof(u32)) + /* EM_A_PD_PD_ID */
+ nla_total_size_64bit(sizeof(u64)) + /* EM_A_PD_FLAGS */
+ nla_total_size(cpus_sz); /* EM_A_PD_CPUS */
+
+ *tot_msg_sz += nlmsg_total_size(genlmsg_msg_size(msg_sz));
+ return 0;
+}
+
+static int __em_nl_get_pd(struct em_perf_domain *pd, void *data)
+{
+ char cpus_buf[EM_A_PD_CPUS_LEN];
+ struct sk_buff *msg = data;
+ struct nlattr *entry;
+
+ entry = nla_nest_start(msg, EM_A_PDS_PD);
+ if (!entry)
+ goto out_cancel_nest;
+
+ if (nla_put_u32(msg, EM_A_PD_PD_ID, pd->id))
+ goto out_cancel_nest;
+
+ if (nla_put_u64_64bit(msg, EM_A_PD_FLAGS, pd->flags, EM_A_PD_PAD))
+ goto out_cancel_nest;
+
+ snprintf(cpus_buf, sizeof(cpus_buf), "%*pb",
+ cpumask_pr_args(to_cpumask(pd->cpus)));
+ if (nla_put_string(msg, EM_A_PD_CPUS, cpus_buf))
+ goto out_cancel_nest;
+
+ nla_nest_end(msg, entry);
+
+ return 0;
+
+out_cancel_nest:
+ nla_nest_cancel(msg, entry);
+
+ return -EMSGSIZE;
+}
+
+int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct sk_buff *msg;
+ void *hdr;
+ int cmd = info->genlhdr->cmd;
+ int ret = -EMSGSIZE, msg_sz = 0;
+
+ for_each_em_perf_domain(__em_nl_get_pd_size, &msg_sz);
+
+ msg = genlmsg_new(msg_sz, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd);
+ if (!hdr)
+ goto out_free_msg;
+
+ ret = for_each_em_perf_domain(__em_nl_get_pd, msg);
+ if (ret)
+ goto out_cancel_msg;
+
+ genlmsg_end(msg, hdr);
+
+ return genlmsg_reply(msg, info);
+
+out_cancel_msg:
+ genlmsg_cancel(msg, hdr);
+out_free_msg:
+ nlmsg_free(msg);
+
+ return ret;
+}
+
+static struct em_perf_domain *__em_nl_get_pd_table_id(struct nlattr **attrs)
+{
+ struct em_perf_domain *pd;
+ int id;
+
+ if (!attrs[EM_A_PD_TABLE_PD_ID])
+ return NULL;
+
+ id = nla_get_u32(attrs[EM_A_PD_TABLE_PD_ID]);
+ pd = em_perf_domain_get_by_id(id);
+ return pd;
+}
+
+static int __em_nl_get_pd_table_size(const struct em_perf_domain *pd)
+{
+ int id_sz, ps_sz;
+
+ id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */
+ ps_sz = nla_total_size(0) + /* EM_A_PD_TABLE_PS */
+ nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_PERFORMANCE */
+ nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_FREQUENCY */
+ nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_POWER */
+ nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_COST */
+ nla_total_size_64bit(sizeof(u64)); /* EM_A_PS_FLAGS */
+ ps_sz *= pd->nr_perf_states;
+
+ return nlmsg_total_size(genlmsg_msg_size(id_sz + ps_sz));
+}
+
+static int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd)
+{
+ struct em_perf_state *table, *ps;
+ struct nlattr *entry;
+ int i;
+
+ if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id))
+ goto out_err;
+
+ rcu_read_lock();
+ table = em_perf_state_from_pd((struct em_perf_domain *)pd);
+
+ for (i = 0; i < pd->nr_perf_states; i++) {
+ ps = &table[i];
+
+ entry = nla_nest_start(msg, EM_A_PD_TABLE_PS);
+ if (!entry)
+ goto out_unlock_ps;
+
+ if (nla_put_u64_64bit(msg, EM_A_PS_PERFORMANCE,
+ ps->performance, EM_A_PS_PAD))
+ goto out_cancel_ps_nest;
+ if (nla_put_u64_64bit(msg, EM_A_PS_FREQUENCY,
+ ps->frequency, EM_A_PS_PAD))
+ goto out_cancel_ps_nest;
+ if (nla_put_u64_64bit(msg, EM_A_PS_POWER,
+ ps->power, EM_A_PS_PAD))
+ goto out_cancel_ps_nest;
+ if (nla_put_u64_64bit(msg, EM_A_PS_COST,
+ ps->cost, EM_A_PS_PAD))
+ goto out_cancel_ps_nest;
+ if (nla_put_u64_64bit(msg, EM_A_PS_FLAGS,
+ ps->flags, EM_A_PS_PAD))
+ goto out_cancel_ps_nest;
+
+ nla_nest_end(msg, entry);
+ }
+ rcu_read_unlock();
+ return 0;
+
+out_cancel_ps_nest:
+ nla_nest_cancel(msg, entry);
+out_unlock_ps:
+ rcu_read_unlock();
+out_err:
+ return -EMSGSIZE;
+}
+
+int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ int cmd = info->genlhdr->cmd;
+ int msg_sz, ret = -EMSGSIZE;
+ struct em_perf_domain *pd;
+ struct sk_buff *msg;
+ void *hdr;
+
+ pd = __em_nl_get_pd_table_id(info->attrs);
+ if (!pd)
+ return -EINVAL;
+
+ msg_sz = __em_nl_get_pd_table_size(pd);
+
+ msg = genlmsg_new(msg_sz, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd);
+ if (!hdr)
+ goto out_free_msg;
+
+ ret = __em_nl_get_pd_table(msg, pd);
+ if (ret)
+ goto out_free_msg;
+
+ genlmsg_end(msg, hdr);
+ return genlmsg_reply(msg, info);
+
+out_free_msg:
+ nlmsg_free(msg);
+ return ret;
+}
+
+
+/**************************** Event encoding *********************************/
+static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type)
+{
+ struct sk_buff *msg;
+ int msg_sz, ret = -EMSGSIZE;
+ void *hdr;
+
+ if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT))
+ return;
+
+ msg_sz = __em_nl_get_pd_table_size(pd);
+
+ msg = genlmsg_new(msg_sz, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, ntf_type);
+ if (!hdr)
+ goto out_free_msg;
+
+ ret = __em_nl_get_pd_table(msg, pd);
+ if (ret)
+ goto out_free_msg;
+
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL);
+
+ return;
+
+out_free_msg:
+ nlmsg_free(msg);
+ return;
+}
+
+void em_notify_pd_created(const struct em_perf_domain *pd)
+{
+ __em_notify_pd_table(pd, EM_CMD_PD_CREATED);
+}
+
+void em_notify_pd_updated(const struct em_perf_domain *pd)
+{
+ __em_notify_pd_table(pd, EM_CMD_PD_UPDATED);
+}
+
+static int __em_notify_pd_deleted_size(const struct em_perf_domain *pd)
+{
+ int id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */
+
+ return nlmsg_total_size(genlmsg_msg_size(id_sz));
+}
+
+void em_notify_pd_deleted(const struct em_perf_domain *pd)
+{
+ struct sk_buff *msg;
+ void *hdr;
+ int msg_sz;
+
+ if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT))
+ return;
+
+ msg_sz = __em_notify_pd_deleted_size(pd);
+
+ msg = genlmsg_new(msg_sz, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, EM_CMD_PD_DELETED);
+ if (!hdr)
+ goto out_free_msg;
+
+ if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id)) {
+ goto out_free_msg;
+ }
+
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL);
+
+ return;
+
+out_free_msg:
+ nlmsg_free(msg);
+ return;
+}
+
+/**************************** Initialization *********************************/
+static int __init em_netlink_init(void)
+{
+ return genl_register_family(&em_nl_family);
+}
+postcore_initcall(em_netlink_init);
diff --git a/kernel/power/em_netlink.h b/kernel/power/em_netlink.h
new file mode 100644
index 000000000000..583d7f1c3939
--- /dev/null
+++ b/kernel/power/em_netlink.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *
+ * Generic netlink for energy model.
+ *
+ * Copyright (c) 2025 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+#ifndef _EM_NETLINK_H
+#define _EM_NETLINK_H
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_NET)
+int for_each_em_perf_domain(int (*cb)(struct em_perf_domain*, void *),
+ void *data);
+struct em_perf_domain *em_perf_domain_get_by_id(int id);
+void em_notify_pd_created(const struct em_perf_domain *pd);
+void em_notify_pd_deleted(const struct em_perf_domain *pd);
+void em_notify_pd_updated(const struct em_perf_domain *pd);
+#else
+static inline
+int for_each_em_perf_domain(int (*cb)(struct em_perf_domain*, void *),
+ void *data)
+{
+ return -EINVAL;
+}
+static inline
+struct em_perf_domain *em_perf_domain_get_by_id(int id)
+{
+ return NULL;
+}
+
+static inline void em_notify_pd_created(const struct em_perf_domain *pd) {}
+
+static inline void em_notify_pd_deleted(const struct em_perf_domain *pd) {}
+
+static inline void em_notify_pd_updated(const struct em_perf_domain *pd) {}
+#endif
+
+#endif /* _EM_NETLINK_H */
diff --git a/kernel/power/em_netlink_autogen.c b/kernel/power/em_netlink_autogen.c
new file mode 100644
index 000000000000..a7a09ab1d1c2
--- /dev/null
+++ b/kernel/power/em_netlink_autogen.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/em.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "em_netlink_autogen.h"
+
+#include <uapi/linux/energy_model.h>
+
+/* EM_CMD_GET_PD_TABLE - do */
+static const struct nla_policy em_get_pd_table_nl_policy[EM_A_PD_TABLE_PD_ID + 1] = {
+ [EM_A_PD_TABLE_PD_ID] = { .type = NLA_U32, },
+};
+
+/* Ops table for em */
+static const struct genl_split_ops em_nl_ops[] = {
+ {
+ .cmd = EM_CMD_GET_PDS,
+ .doit = em_nl_get_pds_doit,
+ .flags = GENL_CMD_CAP_DO,
+ },
+ {
+ .cmd = EM_CMD_GET_PD_TABLE,
+ .doit = em_nl_get_pd_table_doit,
+ .policy = em_get_pd_table_nl_policy,
+ .maxattr = EM_A_PD_TABLE_PD_ID,
+ .flags = GENL_CMD_CAP_DO,
+ },
+};
+
+static const struct genl_multicast_group em_nl_mcgrps[] = {
+ [EM_NLGRP_EVENT] = { "event", },
+};
+
+struct genl_family em_nl_family __ro_after_init = {
+ .name = EM_FAMILY_NAME,
+ .version = EM_FAMILY_VERSION,
+ .netnsok = true,
+ .parallel_ops = true,
+ .module = THIS_MODULE,
+ .split_ops = em_nl_ops,
+ .n_split_ops = ARRAY_SIZE(em_nl_ops),
+ .mcgrps = em_nl_mcgrps,
+ .n_mcgrps = ARRAY_SIZE(em_nl_mcgrps),
+};
diff --git a/kernel/power/em_netlink_autogen.h b/kernel/power/em_netlink_autogen.h
new file mode 100644
index 000000000000..78ce609641f1
--- /dev/null
+++ b/kernel/power/em_netlink_autogen.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/em.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_EM_GEN_H
+#define _LINUX_EM_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/energy_model.h>
+
+int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info);
+int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info);
+
+enum {
+ EM_NLGRP_EVENT,
+};
+
+extern struct genl_family em_nl_family;
+
+#endif /* _LINUX_EM_GEN_H */
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 5f17d2e8e954..11af9f64aa82 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -17,12 +17,24 @@
#include <linux/sched/topology.h>
#include <linux/slab.h>
+#include "em_netlink.h"
+
/*
* Mutex serializing the registrations of performance domains and letting
* callbacks defined by drivers sleep.
*/
static DEFINE_MUTEX(em_pd_mutex);
+/*
+ * Manage performance domains with IDs. One can iterate the performance domains
+ * through the list and pick one with their associated ID. The mutex serializes
+ * the list access. When holding em_pd_list_mutex, em_pd_mutex should not be
+ * taken to avoid potential deadlock.
+ */
+static DEFINE_IDA(em_pd_ida);
+static LIST_HEAD(em_pd_list);
+static DEFINE_MUTEX(em_pd_list_mutex);
+
static void em_cpufreq_update_efficiencies(struct device *dev,
struct em_perf_state *table);
static void em_check_capacity_update(void);
@@ -116,6 +128,16 @@ static int em_debug_flags_show(struct seq_file *s, void *unused)
}
DEFINE_SHOW_ATTRIBUTE(em_debug_flags);
+static int em_debug_id_show(struct seq_file *s, void *unused)
+{
+ struct em_perf_domain *pd = s->private;
+
+ seq_printf(s, "%d\n", pd->id);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_id);
+
static void em_debug_create_pd(struct device *dev)
{
struct em_dbg_info *em_dbg;
@@ -132,6 +154,8 @@ static void em_debug_create_pd(struct device *dev)
debugfs_create_file("flags", 0444, d, dev->em_pd,
&em_debug_flags_fops);
+ debugfs_create_file("id", 0444, d, dev->em_pd, &em_debug_id_fops);
+
em_dbg = devm_kcalloc(dev, dev->em_pd->nr_perf_states,
sizeof(*em_dbg), GFP_KERNEL);
if (!em_dbg)
@@ -328,6 +352,8 @@ int em_dev_update_perf_domain(struct device *dev,
em_table_free(old_table);
mutex_unlock(&em_pd_mutex);
+
+ em_notify_pd_updated(pd);
return 0;
}
EXPORT_SYMBOL_GPL(em_dev_update_perf_domain);
@@ -396,7 +422,7 @@ static int em_create_pd(struct device *dev, int nr_states,
struct em_perf_table *em_table;
struct em_perf_domain *pd;
struct device *cpu_dev;
- int cpu, ret, num_cpus;
+ int cpu, ret, num_cpus, id;
if (_is_cpu_device(dev)) {
num_cpus = cpumask_weight(cpus);
@@ -420,6 +446,13 @@ static int em_create_pd(struct device *dev, int nr_states,
pd->nr_perf_states = nr_states;
+ INIT_LIST_HEAD(&pd->node);
+
+ id = ida_alloc(&em_pd_ida, GFP_KERNEL);
+ if (id < 0)
+ return -ENOMEM;
+ pd->id = id;
+
em_table = em_table_alloc(pd);
if (!em_table)
goto free_pd;
@@ -444,6 +477,7 @@ free_pd_table:
kfree(em_table);
free_pd:
kfree(pd);
+ ida_free(&em_pd_ida, id);
return -EINVAL;
}
@@ -659,8 +693,16 @@ int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
unlock:
mutex_unlock(&em_pd_mutex);
+ if (ret)
+ return ret;
- return ret;
+ mutex_lock(&em_pd_list_mutex);
+ list_add_tail(&dev->em_pd->node, &em_pd_list);
+ mutex_unlock(&em_pd_list_mutex);
+
+ em_notify_pd_created(dev->em_pd);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(em_dev_register_pd_no_update);
@@ -678,6 +720,12 @@ void em_dev_unregister_perf_domain(struct device *dev)
if (_is_cpu_device(dev))
return;
+ mutex_lock(&em_pd_list_mutex);
+ list_del_init(&dev->em_pd->node);
+ mutex_unlock(&em_pd_list_mutex);
+
+ em_notify_pd_deleted(dev->em_pd);
+
/*
* The mutex separates all register/unregister requests and protects
* from potential clean-up/setup issues in the debugfs directories.
@@ -689,6 +737,8 @@ void em_dev_unregister_perf_domain(struct device *dev)
em_table_free(rcu_dereference_protected(dev->em_pd->em_table,
lockdep_is_held(&em_pd_mutex)));
+ ida_free(&em_pd_ida, dev->em_pd->id);
+
kfree(dev->em_pd);
dev->em_pd = NULL;
mutex_unlock(&em_pd_mutex);
@@ -958,3 +1008,39 @@ void em_rebuild_sched_domains(void)
*/
schedule_work(&rebuild_sd_work);
}
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_NET)
+int for_each_em_perf_domain(int (*cb)(struct em_perf_domain*, void *),
+ void *data)
+{
+ struct em_perf_domain *pd;
+
+ lockdep_assert_not_held(&em_pd_mutex);
+ guard(mutex)(&em_pd_list_mutex);
+
+ list_for_each_entry(pd, &em_pd_list, node) {
+ int ret;
+
+ ret = cb(pd, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+struct em_perf_domain *em_perf_domain_get_by_id(int id)
+{
+ struct em_perf_domain *pd;
+
+ lockdep_assert_not_held(&em_pd_mutex);
+ guard(mutex)(&em_pd_list_mutex);
+
+ list_for_each_entry(pd, &em_pd_list, node) {
+ if (pd->id == id)
+ return pd;
+ }
+
+ return NULL;
+}
+#endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 14e85ff23551..af8d07bafe02 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -706,7 +706,6 @@ static void power_down(void)
#ifdef CONFIG_SUSPEND
if (hibernation_mode == HIBERNATION_SUSPEND) {
- pm_restore_gfp_mask();
error = suspend_devices_and_enter(mem_sleep_current);
if (!error)
goto exit;
@@ -746,9 +745,6 @@ static void power_down(void)
cpu_relax();
exit:
- /* Match the pm_restore_gfp_mask() call in hibernate(). */
- pm_restrict_gfp_mask();
-
/* Restore swap signature. */
error = swsusp_unmark();
if (error)
@@ -824,9 +820,11 @@ int hibernate(void)
if (error)
goto Restore;
- ksys_sync_helper();
- if (filesystem_freeze_enabled)
- filesystems_freeze();
+ error = pm_sleep_fs_sync();
+ if (error)
+ goto Notify;
+
+ filesystems_freeze(filesystem_freeze_enabled);
error = freeze_processes();
if (error)
@@ -896,6 +894,7 @@ int hibernate(void)
freezer_test_done = false;
Exit:
filesystems_thaw();
+ Notify:
pm_notifier_call_chain(PM_POST_HIBERNATION);
Restore:
pm_restore_console();
@@ -932,8 +931,7 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
if (error)
goto restore;
- if (filesystem_freeze_enabled)
- filesystems_freeze();
+ filesystems_freeze(filesystem_freeze_enabled);
error = freeze_processes();
if (error)
@@ -1083,8 +1081,7 @@ static int software_resume(void)
if (error)
goto Restore;
- if (filesystem_freeze_enabled)
- filesystems_freeze();
+ filesystems_freeze(filesystem_freeze_enabled);
pm_pr_dbg("Preparing processes for hibernation restore.\n");
error = freeze_processes();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 3cf2d7e72567..03b2c5495c77 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -18,6 +18,8 @@
#include <linux/suspend.h>
#include <linux/syscalls.h>
#include <linux/pm_runtime.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
#include "power.h"
@@ -31,23 +33,35 @@
* held, unless the suspend/hibernate code is guaranteed not to run in parallel
* with that modification).
*/
+static unsigned int saved_gfp_count;
static gfp_t saved_gfp_mask;
void pm_restore_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&system_transition_mutex));
- if (saved_gfp_mask) {
- gfp_allowed_mask = saved_gfp_mask;
- saved_gfp_mask = 0;
- }
+
+ if (WARN_ON(!saved_gfp_count) || --saved_gfp_count)
+ return;
+
+ gfp_allowed_mask = saved_gfp_mask;
+ saved_gfp_mask = 0;
+
+ pm_pr_dbg("GFP mask restored\n");
}
void pm_restrict_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&system_transition_mutex));
- WARN_ON(saved_gfp_mask);
+
+ if (saved_gfp_count++) {
+ WARN_ON((saved_gfp_mask & ~(__GFP_IO | __GFP_FS)) != gfp_allowed_mask);
+ return;
+ }
+
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
+
+ pm_pr_dbg("GFP mask restricted\n");
}
unsigned int lock_system_sleep(void)
@@ -80,6 +94,61 @@ void ksys_sync_helper(void)
}
EXPORT_SYMBOL_GPL(ksys_sync_helper);
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+/* Wakeup events handling resolution while syncing file systems in jiffies */
+#define PM_FS_SYNC_WAKEUP_RESOLUTION 5
+
+static atomic_t pm_fs_sync_count = ATOMIC_INIT(0);
+static struct workqueue_struct *pm_fs_sync_wq;
+static DECLARE_WAIT_QUEUE_HEAD(pm_fs_sync_wait);
+
+static bool pm_fs_sync_completed(void)
+{
+ return atomic_read(&pm_fs_sync_count) == 0;
+}
+
+static void pm_fs_sync_work_fn(struct work_struct *work)
+{
+ ksys_sync_helper();
+
+ if (atomic_dec_and_test(&pm_fs_sync_count))
+ wake_up(&pm_fs_sync_wait);
+}
+static DECLARE_WORK(pm_fs_sync_work, pm_fs_sync_work_fn);
+
+/**
+ * pm_sleep_fs_sync() - Sync file systems in an interruptible way
+ *
+ * Return: 0 on successful file system sync, or -EBUSY if the file system sync
+ * was aborted.
+ */
+int pm_sleep_fs_sync(void)
+{
+ pm_wakeup_clear(0);
+
+ /*
+ * Take back-to-back sleeps into account by queuing a subsequent fs sync
+ * only if the previous fs sync is running or is not queued. Multiple fs
+ * syncs increase the likelihood of saving the latest files immediately
+ * before sleep.
+ */
+ if (!work_pending(&pm_fs_sync_work)) {
+ atomic_inc(&pm_fs_sync_count);
+ queue_work(pm_fs_sync_wq, &pm_fs_sync_work);
+ }
+
+ while (!pm_fs_sync_completed()) {
+ if (pm_wakeup_pending())
+ return -EBUSY;
+
+ wait_event_timeout(pm_fs_sync_wait, pm_fs_sync_completed(),
+ PM_FS_SYNC_WAKEUP_RESOLUTION);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_SUSPEND || CONFIG_HIBERNATION */
+
/* Routines for PM-transition notifications */
static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
@@ -219,10 +288,10 @@ static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr
power_attr(mem_sleep);
/*
- * sync_on_suspend: invoke ksys_sync_helper() before suspend.
+ * sync_on_suspend: Sync file systems before suspend.
*
- * show() returns whether ksys_sync_helper() is invoked before suspend.
- * store() accepts 0 or 1. 0 disables ksys_sync_helper() and 1 enables it.
+ * show() returns whether file systems sync before suspend is enabled.
+ * store() accepts 0 or 1. 0 disables file systems sync and 1 enables it.
*/
bool sync_on_suspend_enabled = !IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC);
@@ -1054,16 +1123,26 @@ static const struct attribute_group *attr_groups[] = {
struct workqueue_struct *pm_wq;
EXPORT_SYMBOL_GPL(pm_wq);
-static int __init pm_start_workqueue(void)
+static int __init pm_start_workqueues(void)
{
- pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
+ pm_wq = alloc_workqueue("pm", WQ_FREEZABLE | WQ_UNBOUND, 0);
+ if (!pm_wq)
+ return -ENOMEM;
- return pm_wq ? 0 : -ENOMEM;
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+ pm_fs_sync_wq = alloc_ordered_workqueue("pm_fs_sync", 0);
+ if (!pm_fs_sync_wq) {
+ destroy_workqueue(pm_wq);
+ return -ENOMEM;
+ }
+#endif
+
+ return 0;
}
static int __init pm_init(void)
{
- int error = pm_start_workqueue();
+ int error = pm_start_workqueues();
if (error)
return error;
hibernate_image_size_init();
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7ccd709af93f..75b63843886e 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -19,6 +19,7 @@ struct swsusp_info {
} __aligned(PAGE_SIZE);
#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern int pm_sleep_fs_sync(void);
extern bool filesystem_freeze_enabled;
#endif
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 8ff68ebaa1e0..dc0dfc349f22 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -132,6 +132,7 @@ int freeze_processes(void)
if (!pm_freezing)
static_branch_inc(&freezer_active);
+ pm_wakeup_clear(0);
pm_freezing = true;
error = try_to_freeze_tasks(true);
if (!error)
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 4244b069442e..f7d8064e9adc 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -415,6 +415,105 @@ static struct miscdevice cpu_latency_qos_miscdev = {
.fops = &cpu_latency_qos_fops,
};
+#ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP
+/* The CPU system wakeup latency QoS. */
+static struct pm_qos_constraints cpu_wakeup_latency_constraints = {
+ .list = PLIST_HEAD_INIT(cpu_wakeup_latency_constraints.list),
+ .target_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+ .default_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+ .no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+ .type = PM_QOS_MIN,
+};
+
+/**
+ * cpu_wakeup_latency_qos_limit - Current CPU system wakeup latency QoS limit.
+ *
+ * Returns the current CPU system wakeup latency QoS limit that may have been
+ * requested by user space.
+ */
+s32 cpu_wakeup_latency_qos_limit(void)
+{
+ return pm_qos_read_value(&cpu_wakeup_latency_constraints);
+}
+
+static int cpu_wakeup_latency_qos_open(struct inode *inode, struct file *filp)
+{
+ struct pm_qos_request *req;
+
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
+
+ req->qos = &cpu_wakeup_latency_constraints;
+ pm_qos_update_target(req->qos, &req->node, PM_QOS_ADD_REQ,
+ PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
+ filp->private_data = req;
+
+ return 0;
+}
+
+static int cpu_wakeup_latency_qos_release(struct inode *inode,
+ struct file *filp)
+{
+ struct pm_qos_request *req = filp->private_data;
+
+ filp->private_data = NULL;
+ pm_qos_update_target(req->qos, &req->node, PM_QOS_REMOVE_REQ,
+ PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
+ kfree(req);
+
+ return 0;
+}
+
+static ssize_t cpu_wakeup_latency_qos_read(struct file *filp, char __user *buf,
+ size_t count, loff_t *f_pos)
+{
+ s32 value = pm_qos_read_value(&cpu_wakeup_latency_constraints);
+
+ return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
+}
+
+static ssize_t cpu_wakeup_latency_qos_write(struct file *filp,
+ const char __user *buf,
+ size_t count, loff_t *f_pos)
+{
+ struct pm_qos_request *req = filp->private_data;
+ s32 value;
+
+ if (count == sizeof(s32)) {
+ if (copy_from_user(&value, buf, sizeof(s32)))
+ return -EFAULT;
+ } else {
+ int ret;
+
+ ret = kstrtos32_from_user(buf, count, 16, &value);
+ if (ret)
+ return ret;
+ }
+
+ if (value < 0)
+ return -EINVAL;
+
+ pm_qos_update_target(req->qos, &req->node, PM_QOS_UPDATE_REQ, value);
+
+ return count;
+}
+
+static const struct file_operations cpu_wakeup_latency_qos_fops = {
+ .open = cpu_wakeup_latency_qos_open,
+ .release = cpu_wakeup_latency_qos_release,
+ .read = cpu_wakeup_latency_qos_read,
+ .write = cpu_wakeup_latency_qos_write,
+ .llseek = noop_llseek,
+};
+
+static struct miscdevice cpu_wakeup_latency_qos_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "cpu_wakeup_latency",
+ .fops = &cpu_wakeup_latency_qos_fops,
+};
+#endif /* CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP */
+
static int __init cpu_latency_qos_init(void)
{
int ret;
@@ -424,6 +523,13 @@ static int __init cpu_latency_qos_init(void)
pr_err("%s: %s setup failed\n", __func__,
cpu_latency_qos_miscdev.name);
+#ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP
+ ret = misc_register(&cpu_wakeup_latency_qos_miscdev);
+ if (ret < 0)
+ pr_err("%s: %s setup failed\n", __func__,
+ cpu_wakeup_latency_qos_miscdev.name);
+#endif
+
return ret;
}
late_initcall(cpu_latency_qos_init);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 645f42e40478..0a946932d5c1 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -2110,22 +2110,20 @@ asmlinkage __visible int swsusp_save(void)
{
unsigned int nr_pages, nr_highmem;
- pr_info("Creating image:\n");
+ pm_deferred_pr_dbg("Creating image\n");
drain_local_pages(NULL);
nr_pages = count_data_pages();
nr_highmem = count_highmem_pages();
- pr_info("Need to copy %u pages\n", nr_pages + nr_highmem);
+ pm_deferred_pr_dbg("Need to copy %u pages\n", nr_pages + nr_highmem);
if (!enough_free_mem(nr_pages, nr_highmem)) {
- pr_err("Not enough free memory\n");
+ pm_deferred_pr_dbg("Not enough free memory for image creation\n");
return -ENOMEM;
}
- if (swsusp_alloc(&copy_bm, nr_pages, nr_highmem)) {
- pr_err("Memory allocation failed\n");
+ if (swsusp_alloc(&copy_bm, nr_pages, nr_highmem))
return -ENOMEM;
- }
/*
* During allocating of suspend pagedir, new cold pages may appear.
@@ -2144,7 +2142,8 @@ asmlinkage __visible int swsusp_save(void)
nr_zero_pages = nr_pages - nr_copy_pages;
nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);
- pr_info("Image created (%d pages copied, %d zero pages)\n", nr_copy_pages, nr_zero_pages);
+ pm_deferred_pr_dbg("Image created (%d pages copied, %d zero pages)\n",
+ nr_copy_pages, nr_zero_pages);
return 0;
}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4bb4686c1c08..2da4482bb6eb 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -344,10 +344,14 @@ MODULE_PARM_DESC(pm_test_delay,
static int suspend_test(int level)
{
#ifdef CONFIG_PM_DEBUG
+ int i;
+
if (pm_test_level == level) {
pr_info("suspend debug: Waiting for %d second(s).\n",
pm_test_delay);
- mdelay(pm_test_delay * 1000);
+ for (i = 0; i < pm_test_delay && !pm_wakeup_pending(); i++)
+ msleep(1000);
+
return 1;
}
#endif /* !CONFIG_PM_DEBUG */
@@ -375,8 +379,7 @@ static int suspend_prepare(suspend_state_t state)
if (error)
goto Restore;
- if (filesystem_freeze_enabled)
- filesystems_freeze();
+ filesystems_freeze(filesystem_freeze_enabled);
trace_suspend_resume(TPS("freeze_processes"), 0, true);
error = suspend_freeze_processes();
trace_suspend_resume(TPS("freeze_processes"), 0, false);
@@ -590,12 +593,15 @@ static int enter_state(suspend_state_t state)
if (sync_on_suspend_enabled) {
trace_suspend_resume(TPS("sync_filesystems"), 0, true);
- ksys_sync_helper();
+
+ error = pm_sleep_fs_sync();
+ if (error)
+ goto Unlock;
+
trace_suspend_resume(TPS("sync_filesystems"), 0, false);
}
pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
- pm_wakeup_clear(0);
pm_suspend_clear_flags();
error = suspend_prepare(state);
if (error)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 0beff7eeaaba..33a186373bef 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -46,19 +46,18 @@ static bool clean_pages_on_read;
static bool clean_pages_on_decompress;
/*
- * 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_ENTRIES swap entries.
- * These structures are stored on the swap and linked together with the
- * help of the .next_swap member.
+ * 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_ENTRIES swap entries. These
+ * structures are stored on the swap and linked together with the help of the
+ * .next_swap member.
*
- * The swap map is created during suspend. The swap map pages are
- * allocated and populated one at a time, so we only need one memory
- * page to set up the entire structure.
+ * The swap map is created during suspend. The swap map pages are allocated and
+ * populated one at a time, so we only need one memory page to set up the entire
+ * structure.
*
- * During resume we pick up all swap_map_page structures into a list.
+ * During resume we pick up all swap_map_page structures into a list.
*/
-
#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
/*
@@ -89,10 +88,8 @@ struct swap_map_page_list {
};
/*
- * The swap_map_handle structure is used for handling swap in
- * a file-alike way
+ * The swap_map_handle structure is used for handling swap in a file-alike way.
*/
-
struct swap_map_handle {
struct swap_map_page *cur;
struct swap_map_page_list *maps;
@@ -117,10 +114,9 @@ struct swsusp_header {
static struct swsusp_header *swsusp_header;
/*
- * The following functions are used for tracing the allocated
- * swap pages, so that they can be freed in case of an error.
+ * The following functions are used for tracing the allocated swap pages, so
+ * that they can be freed in case of an error.
*/
-
struct swsusp_extent {
struct rb_node node;
unsigned long start;
@@ -170,15 +166,14 @@ static int swsusp_extents_insert(unsigned long swap_offset)
return 0;
}
-/*
- * alloc_swapdev_block - allocate a swap page and register that it has
- * been allocated, so that it can be freed in case of an error.
- */
-
sector_t alloc_swapdev_block(int swap)
{
unsigned long offset;
+ /*
+ * Allocate a swap page and register that it has been allocated, so that
+ * it can be freed in case of an error.
+ */
offset = swp_offset(get_swap_page_of_type(swap));
if (offset) {
if (swsusp_extents_insert(offset))
@@ -189,16 +184,14 @@ sector_t alloc_swapdev_block(int swap)
return 0;
}
-/*
- * free_all_swap_pages - free swap pages allocated for saving image data.
- * It also frees the extents used to register which swap entries had been
- * allocated.
- */
-
void free_all_swap_pages(int swap)
{
struct rb_node *node;
+ /*
+ * Free swap pages allocated for saving image data. It also frees the
+ * extents used to register which swap entries had been allocated.
+ */
while ((node = swsusp_extents.rb_node)) {
struct swsusp_extent *ext;
@@ -303,6 +296,7 @@ static int hib_wait_io(struct hib_bio_batch *hb)
/*
* Saving part
*/
+
static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
{
int error;
@@ -336,16 +330,14 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
*/
unsigned int swsusp_header_flags;
-/**
- * swsusp_swap_check - check if the resume device is a swap device
- * and get its index (if so)
- *
- * This is called before saving image
- */
static int swsusp_swap_check(void)
{
int res;
+ /*
+ * Check if the resume device is a swap device and get its index (if so).
+ * This is called before saving the image.
+ */
if (swsusp_resume_device)
res = swap_type_of(swsusp_resume_device, swsusp_resume_block);
else
@@ -362,13 +354,6 @@ static int swsusp_swap_check(void)
return 0;
}
-/**
- * write_page - Write one page to given swap location.
- * @buf: Address we're writing.
- * @offset: Offset of the swap page we're writing to.
- * @hb: bio completion batch
- */
-
static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
{
gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
@@ -519,17 +504,14 @@ static int swap_writer_finish(struct swap_map_handle *handle,
CMP_HEADER, PAGE_SIZE)
#define CMP_SIZE (CMP_PAGES * PAGE_SIZE)
-/* Maximum number of threads for compression/decompression. */
-#define CMP_THREADS 3
+/* Default number of threads for compression/decompression. */
+#define CMP_THREADS 3
+static unsigned int hibernate_compression_threads = CMP_THREADS;
/* Minimum/maximum number of pages for read buffering. */
#define CMP_MIN_RD_PAGES 1024
#define CMP_MAX_RD_PAGES 8192
-/**
- * save_image - save the suspend image data
- */
-
static int save_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_write)
@@ -585,13 +567,48 @@ struct crc_data {
wait_queue_head_t go; /* start crc update */
wait_queue_head_t done; /* crc update done */
u32 *crc32; /* points to handle's crc32 */
- size_t *unc_len[CMP_THREADS]; /* uncompressed lengths */
- unsigned char *unc[CMP_THREADS]; /* uncompressed data */
+ size_t **unc_len; /* uncompressed lengths */
+ unsigned char **unc; /* uncompressed data */
};
-/*
- * CRC32 update function that runs in its own thread.
- */
+static struct crc_data *alloc_crc_data(int nr_threads)
+{
+ struct crc_data *crc;
+
+ crc = kzalloc(sizeof(*crc), GFP_KERNEL);
+ if (!crc)
+ return NULL;
+
+ crc->unc = kcalloc(nr_threads, sizeof(*crc->unc), GFP_KERNEL);
+ if (!crc->unc)
+ goto err_free_crc;
+
+ crc->unc_len = kcalloc(nr_threads, sizeof(*crc->unc_len), GFP_KERNEL);
+ if (!crc->unc_len)
+ goto err_free_unc;
+
+ return crc;
+
+err_free_unc:
+ kfree(crc->unc);
+err_free_crc:
+ kfree(crc);
+ return NULL;
+}
+
+static void free_crc_data(struct crc_data *crc)
+{
+ if (!crc)
+ return;
+
+ if (crc->thr)
+ kthread_stop(crc->thr);
+
+ kfree(crc->unc_len);
+ kfree(crc->unc);
+ kfree(crc);
+}
+
static int crc32_threadfn(void *data)
{
struct crc_data *d = data;
@@ -616,6 +633,7 @@ static int crc32_threadfn(void *data)
}
return 0;
}
+
/*
* Structure used for data compression.
*/
@@ -635,11 +653,8 @@ struct cmp_data {
};
/* Indicates the image size after compression */
-static atomic_t compressed_size = ATOMIC_INIT(0);
+static atomic64_t compressed_size = ATOMIC_INIT(0);
-/*
- * Compression function that runs in its own thread.
- */
static int compress_threadfn(void *data)
{
struct cmp_data *d = data;
@@ -664,19 +679,13 @@ static int compress_threadfn(void *data)
d->ret = crypto_acomp_compress(d->cr);
d->cmp_len = d->cr->dlen;
- atomic_set(&compressed_size, atomic_read(&compressed_size) + d->cmp_len);
+ atomic64_add(d->cmp_len, &compressed_size);
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
}
-/**
- * save_compressed_image - Save the suspend image data after compression.
- * @handle: Swap map handle to use for saving the image.
- * @snapshot: Image to read data from.
- * @nr_to_write: Number of pages to save.
- */
static int save_compressed_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_write)
@@ -689,21 +698,21 @@ static int save_compressed_image(struct swap_map_handle *handle,
ktime_t start;
ktime_t stop;
size_t off;
- unsigned thr, run_threads, nr_threads;
+ unsigned int thr, run_threads, nr_threads;
unsigned char *page = NULL;
struct cmp_data *data = NULL;
struct crc_data *crc = NULL;
hib_init_batch(&hb);
- atomic_set(&compressed_size, 0);
+ atomic64_set(&compressed_size, 0);
/*
* We'll limit the number of threads for compression to limit memory
* footprint.
*/
nr_threads = num_online_cpus() - 1;
- nr_threads = clamp_val(nr_threads, 1, CMP_THREADS);
+ nr_threads = clamp_val(nr_threads, 1, hibernate_compression_threads);
page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH);
if (!page) {
@@ -719,7 +728,7 @@ static int save_compressed_image(struct swap_map_handle *handle,
goto out_clean;
}
- crc = kzalloc(sizeof(*crc), GFP_KERNEL);
+ crc = alloc_crc_data(nr_threads);
if (!crc) {
pr_err("Failed to allocate crc\n");
ret = -ENOMEM;
@@ -877,19 +886,18 @@ out_finish:
stop = ktime_get();
if (!ret)
ret = err2;
- if (!ret)
+ if (!ret) {
+ swsusp_show_speed(start, stop, nr_to_write, "Wrote");
+ pr_info("Image size after compression: %lld kbytes\n",
+ (atomic64_read(&compressed_size) / 1024));
pr_info("Image saving done\n");
- swsusp_show_speed(start, stop, nr_to_write, "Wrote");
- pr_info("Image size after compression: %d kbytes\n",
- (atomic_read(&compressed_size) / 1024));
+ } else {
+ pr_err("Image saving failed: %d\n", ret);
+ }
out_clean:
hib_finish_batch(&hb);
- if (crc) {
- if (crc->thr)
- kthread_stop(crc->thr);
- kfree(crc);
- }
+ free_crc_data(crc);
if (data) {
for (thr = 0; thr < nr_threads; thr++) {
if (data[thr].thr)
@@ -899,18 +907,12 @@ out_clean:
}
vfree(data);
}
- if (page) free_page((unsigned long)page);
+ if (page)
+ free_page((unsigned long)page);
return ret;
}
-/**
- * enough_swap - Make sure we have enough swap to save the image.
- *
- * Returns TRUE or FALSE after checking the total amount of swap
- * space available from the resume partition.
- */
-
static int enough_swap(unsigned int nr_pages)
{
unsigned int free_swap = count_swap_pages(root_swap, 1);
@@ -923,15 +925,16 @@ static int enough_swap(unsigned int nr_pages)
}
/**
- * swsusp_write - Write entire image and metadata.
- * @flags: flags to pass to the "boot" kernel in the image header
+ * swsusp_write - Write entire image and metadata.
+ * @flags: flags to pass to the "boot" kernel in the image header
+ *
+ * It is important _NOT_ to umount filesystems at this point. We want them
+ * synced (in case something goes wrong) but we DO not want to mark filesystem
+ * clean: it is not. (And it does not matter, if we resume correctly, we'll mark
+ * system clean, anyway.)
*
- * It is important _NOT_ to umount filesystems at this point. We want
- * them synced (in case something goes wrong) but we DO not want to mark
- * filesystem clean: it is not. (And it does not matter, if we resume
- * correctly, we'll mark system clean, anyway.)
+ * Return: 0 on success, negative error code on failure.
*/
-
int swsusp_write(unsigned int flags)
{
struct swap_map_handle handle;
@@ -974,8 +977,8 @@ out_finish:
}
/*
- * The following functions allow us to read data using a swap map
- * in a file-like way.
+ * The following functions allow us to read data using a swap map in a file-like
+ * way.
*/
static void release_swap_reader(struct swap_map_handle *handle)
@@ -1077,12 +1080,6 @@ static int swap_reader_finish(struct swap_map_handle *handle)
return 0;
}
-/**
- * load_image - load the image using the swap map handle
- * @handle and the snapshot handle @snapshot
- * (assume there are @nr_pages pages to load)
- */
-
static int load_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_read)
@@ -1153,9 +1150,6 @@ struct dec_data {
unsigned char cmp[CMP_SIZE]; /* compressed buffer */
};
-/*
- * Decompression function that runs in its own thread.
- */
static int decompress_threadfn(void *data)
{
struct dec_data *d = data;
@@ -1190,12 +1184,6 @@ static int decompress_threadfn(void *data)
return 0;
}
-/**
- * load_compressed_image - Load compressed image data and decompress it.
- * @handle: Swap map handle to use for loading data.
- * @snapshot: Image to copy uncompressed data into.
- * @nr_to_read: Number of pages to load.
- */
static int load_compressed_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_read)
@@ -1223,7 +1211,7 @@ static int load_compressed_image(struct swap_map_handle *handle,
* footprint.
*/
nr_threads = num_online_cpus() - 1;
- nr_threads = clamp_val(nr_threads, 1, CMP_THREADS);
+ nr_threads = clamp_val(nr_threads, 1, hibernate_compression_threads);
page = vmalloc_array(CMP_MAX_RD_PAGES, sizeof(*page));
if (!page) {
@@ -1239,7 +1227,7 @@ static int load_compressed_image(struct swap_map_handle *handle,
goto out_clean;
}
- crc = kzalloc(sizeof(*crc), GFP_KERNEL);
+ crc = alloc_crc_data(nr_threads);
if (!crc) {
pr_err("Failed to allocate crc\n");
ret = -ENOMEM;
@@ -1506,11 +1494,7 @@ out_clean:
hib_finish_batch(&hb);
for (i = 0; i < ring_size; i++)
free_page((unsigned long)page[i]);
- if (crc) {
- if (crc->thr)
- kthread_stop(crc->thr);
- kfree(crc);
- }
+ free_crc_data(crc);
if (data) {
for (thr = 0; thr < nr_threads; thr++) {
if (data[thr].thr)
@@ -1529,8 +1513,9 @@ out_clean:
* swsusp_read - read the hibernation image.
* @flags_p: flags passed by the "frozen" kernel in the image header should
* be written into this memory location
+ *
+ * Return: 0 on success, negative error code on failure.
*/
-
int swsusp_read(unsigned int *flags_p)
{
int error;
@@ -1567,8 +1552,9 @@ static void *swsusp_holder;
/**
* swsusp_check - Open the resume device and check for the swsusp signature.
* @exclusive: Open the resume device exclusively.
+ *
+ * Return: 0 if a valid image is found, negative error code otherwise.
*/
-
int swsusp_check(bool exclusive)
{
void *holder = exclusive ? &swsusp_holder : NULL;
@@ -1618,7 +1604,6 @@ put:
/**
* swsusp_close - close resume device.
*/
-
void swsusp_close(void)
{
if (IS_ERR(hib_resume_bdev_file)) {
@@ -1630,9 +1615,10 @@ void swsusp_close(void)
}
/**
- * swsusp_unmark - Unmark swsusp signature in the resume device
+ * swsusp_unmark - Unmark swsusp signature in the resume device
+ *
+ * Return: 0 on success, negative error code on failure.
*/
-
#ifdef CONFIG_SUSPEND
int swsusp_unmark(void)
{
@@ -1658,8 +1644,46 @@ int swsusp_unmark(void)
}
#endif
+static ssize_t hibernate_compression_threads_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", hibernate_compression_threads);
+}
+
+static ssize_t hibernate_compression_threads_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned long val;
+
+ if (kstrtoul(buf, 0, &val))
+ return -EINVAL;
+
+ if (val < 1)
+ return -EINVAL;
+
+ hibernate_compression_threads = val;
+ return n;
+}
+power_attr(hibernate_compression_threads);
+
+static struct attribute *g[] = {
+ &hibernate_compression_threads_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group attr_group = {
+ .attrs = g,
+};
+
static int __init swsusp_header_init(void)
{
+ int error;
+
+ error = sysfs_create_group(power_kobj, &attr_group);
+ if (error)
+ return -ENOMEM;
+
swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
if (!swsusp_header)
panic("Could not allocate memory for swsusp_header\n");
@@ -1667,3 +1691,19 @@ static int __init swsusp_header_init(void)
}
core_initcall(swsusp_header_init);
+
+static int __init hibernate_compression_threads_setup(char *str)
+{
+ int rc = kstrtouint(str, 0, &hibernate_compression_threads);
+
+ if (rc)
+ return rc;
+
+ if (hibernate_compression_threads < 1)
+ hibernate_compression_threads = CMP_THREADS;
+
+ return 1;
+
+}
+
+__setup("hibernate_compression_threads=", hibernate_compression_threads_setup);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 3f9e3efb9f6e..4401cfe26e5c 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -278,7 +278,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
if (data->frozen)
break;
- ksys_sync_helper();
+ error = pm_sleep_fs_sync();
+ if (error)
+ break;
error = freeze_processes();
if (error)
generated by cgit (git 2.34.1) at 2025-12-03 17:36:12 +0000