xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
派生 0
代码 工单 合并请求 工作流 软件包 项目 发布 百科 活动

Merge branches 'release', 'acpica', 'bugzilla-10224', 'bugzilla-9772', 'bugzilla-9916', 'ec', 'eeepc', 'idle', 'misc', 'pm-legacy', 'sysfs-links-2.6.26', 'thermal', 'thinkpad' and 'video' into release

浏览代码
这个提交包含在：
Len Brown
2008-04-30 13:58:00 -04:00
父节点 75a44ce00b 729b2bdbfa 2f67a0695d 51ae796f7f ce52ddf58c e1faa9da28 36a9135865 9448b0d43e 99bda83e8b 1071695f17 7aa0f1a8b1 68f12ae5d7 66fb9d120e
当前提交 96916090f4
共修改 6071 个文件，包含 355934 行新增和 268411 行删除
下载 Patch 文件 下载 Diff 文件 展开所有文件 折叠所有文件

3
kernel/Makefile
查看文件

@@ -8,7 +8,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
signal.o sys.o kmod.o workqueue.o pid.o \
rcupdate.o extable.o params.o posix-timers.o \
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
hrtimer.o rwsem.o nsproxy.o srcu.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o
obj-$(CONFIG_SYSCTL) += sysctl_check.o
@@ -53,6 +53,7 @@ obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o

24
kernel/audit.c
查看文件

@@ -21,7 +21,7 @@
*
* Written by Rickard E. (Rik) Faith <faith@redhat.com>
*
* Goals: 1) Integrate fully with SELinux.
* Goals: 1) Integrate fully with Security Modules.
* 2) Minimal run-time overhead:
* a) Minimal when syscall auditing is disabled (audit_enable=0).
* b) Small when syscall auditing is enabled and no audit record
@@ -55,7 +55,6 @@
#include <net/netlink.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/selinux.h>
#include <linux/inotify.h>
#include <linux/freezer.h>
#include <linux/tty.h>
@@ -265,13 +264,13 @@ static int audit_log_config_change(char *function_name, int new, int old,
char *ctx = NULL;
u32 len;
rc = selinux_sid_to_string(sid, &ctx, &len);
rc = security_secid_to_secctx(sid, &ctx, &len);
if (rc) {
audit_log_format(ab, " sid=%u", sid);
allow_changes = 0; /* Something weird, deny request */
} else {
audit_log_format(ab, " subj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
audit_log_format(ab, " res=%d", allow_changes);
@@ -550,12 +549,13 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type,
audit_log_format(*ab, "user pid=%d uid=%u auid=%u",
pid, uid, auid);
if (sid) {
rc = selinux_sid_to_string(sid, &ctx, &len);
rc = security_secid_to_secctx(sid, &ctx, &len);
if (rc)
audit_log_format(*ab, " ssid=%u", sid);
else
else {
audit_log_format(*ab, " subj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
return rc;
@@ -758,18 +758,18 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
break;
}
case AUDIT_SIGNAL_INFO:
err = selinux_sid_to_string(audit_sig_sid, &ctx, &len);
err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
if (err)
return err;
sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
if (!sig_data) {
kfree(ctx);
security_release_secctx(ctx, len);
return -ENOMEM;
}
sig_data->uid = audit_sig_uid;
sig_data->pid = audit_sig_pid;
memcpy(sig_data->ctx, ctx, len);
kfree(ctx);
security_release_secctx(ctx, len);
audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO,
0, 0, sig_data, sizeof(*sig_data) + len);
kfree(sig_data);
@@ -881,10 +881,6 @@ static int __init audit_init(void)
audit_enabled = audit_default;
audit_ever_enabled |= !!audit_default;
/* Register the callback with selinux. This callback will be invoked
* when a new policy is loaded. */
selinux_audit_set_callback(&selinux_audit_rule_update);
audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
#ifdef CONFIG_AUDITSYSCALL

25
kernel/audit.h
查看文件

@@ -65,34 +65,9 @@ struct audit_watch {
struct list_head rules; /* associated rules */
};
struct audit_field {
u32 type;
u32 val;
u32 op;
char *se_str;
struct selinux_audit_rule *se_rule;
};
struct audit_tree;
struct audit_chunk;
struct audit_krule {
int vers_ops;
u32 flags;
u32 listnr;
u32 action;
u32 mask[AUDIT_BITMASK_SIZE];
u32 buflen; /* for data alloc on list rules */
u32 field_count;
char *filterkey; /* ties events to rules */
struct audit_field *fields;
struct audit_field *arch_f; /* quick access to arch field */
struct audit_field *inode_f; /* quick access to an inode field */
struct audit_watch *watch; /* associated watch */
struct audit_tree *tree; /* associated watched tree */
struct list_head rlist; /* entry in audit_{watch,tree}.rules list */
};
struct audit_entry {
struct list_head list;
struct rcu_head rcu;

99
kernel/auditfilter.c
查看文件

@@ -28,7 +28,7 @@
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/inotify.h>
#include <linux/selinux.h>
#include <linux/security.h>
#include "audit.h"
/*
@@ -38,7 +38,7 @@
* Synchronizes writes and blocking reads of audit's filterlist
* data. Rcu is used to traverse the filterlist and access
* contents of structs audit_entry, audit_watch and opaque
* selinux rules during filtering. If modified, these structures
* LSM rules during filtering. If modified, these structures
* must be copied and replace their counterparts in the filterlist.
* An audit_parent struct is not accessed during filtering, so may
* be written directly provided audit_filter_mutex is held.
@@ -139,8 +139,8 @@ static inline void audit_free_rule(struct audit_entry *e)
if (e->rule.fields)
for (i = 0; i < e->rule.field_count; i++) {
struct audit_field *f = &e->rule.fields[i];
kfree(f->se_str);
selinux_audit_rule_free(f->se_rule);
kfree(f->lsm_str);
security_audit_rule_free(f->lsm_rule);
}
kfree(e->rule.fields);
kfree(e->rule.filterkey);
@@ -554,8 +554,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
f->op = data->fieldflags[i] & AUDIT_OPERATORS;
f->type = data->fields[i];
f->val = data->values[i];
f->se_str = NULL;
f->se_rule = NULL;
f->lsm_str = NULL;
f->lsm_rule = NULL;
switch(f->type) {
case AUDIT_PID:
case AUDIT_UID:
@@ -597,12 +597,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
goto exit_free;
entry->rule.buflen += f->val;
err = selinux_audit_rule_init(f->type, f->op, str,
&f->se_rule);
err = security_audit_rule_init(f->type, f->op, str,
(void **)&f->lsm_rule);
/* Keep currently invalid fields around in case they
* become valid after a policy reload. */
if (err == -EINVAL) {
printk(KERN_WARNING "audit rule for selinux "
printk(KERN_WARNING "audit rule for LSM "
"\'%s\' is invalid\n", str);
err = 0;
}
@@ -610,7 +610,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
kfree(str);
goto exit_free;
} else
f->se_str = str;
f->lsm_str = str;
break;
case AUDIT_WATCH:
str = audit_unpack_string(&bufp, &remain, f->val);
@@ -754,7 +754,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
data->buflen += data->values[i] =
audit_pack_string(&bufp, f->se_str);
audit_pack_string(&bufp, f->lsm_str);
break;
case AUDIT_WATCH:
data->buflen += data->values[i] =
@@ -806,7 +806,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
if (strcmp(a->fields[i].se_str, b->fields[i].se_str))
if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str))
return 1;
break;
case AUDIT_WATCH:
@@ -862,28 +862,28 @@ out:
return new;
}
/* Duplicate selinux field information. The se_rule is opaque, so must be
/* Duplicate LSM field information. The lsm_rule is opaque, so must be
* re-initialized. */
static inline int audit_dupe_selinux_field(struct audit_field *df,
static inline int audit_dupe_lsm_field(struct audit_field *df,
struct audit_field *sf)
{
int ret = 0;
char *se_str;
char *lsm_str;
/* our own copy of se_str */
se_str = kstrdup(sf->se_str, GFP_KERNEL);
if (unlikely(!se_str))
/* our own copy of lsm_str */
lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL);
if (unlikely(!lsm_str))
return -ENOMEM;
df->se_str = se_str;
df->lsm_str = lsm_str;
/* our own (refreshed) copy of se_rule */
ret = selinux_audit_rule_init(df->type, df->op, df->se_str,
&df->se_rule);
/* our own (refreshed) copy of lsm_rule */
ret = security_audit_rule_init(df->type, df->op, df->lsm_str,
(void **)&df->lsm_rule);
/* Keep currently invalid fields around in case they
* become valid after a policy reload. */
if (ret == -EINVAL) {
printk(KERN_WARNING "audit rule for selinux \'%s\' is "
"invalid\n", df->se_str);
printk(KERN_WARNING "audit rule for LSM \'%s\' is "
"invalid\n", df->lsm_str);
ret = 0;
}
@@ -891,7 +891,7 @@ static inline int audit_dupe_selinux_field(struct audit_field *df,
}
/* Duplicate an audit rule. This will be a deep copy with the exception
* of the watch - that pointer is carried over. The selinux specific fields
* of the watch - that pointer is carried over. The LSM specific fields
* will be updated in the copy. The point is to be able to replace the old
* rule with the new rule in the filterlist, then free the old rule.
* The rlist element is undefined; list manipulations are handled apart from
@@ -930,7 +930,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
new->tree = old->tree;
memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount);
/* deep copy this information, updating the se_rule fields, because
/* deep copy this information, updating the lsm_rule fields, because
* the originals will all be freed when the old rule is freed. */
for (i = 0; i < fcount; i++) {
switch (new->fields[i].type) {
@@ -944,7 +944,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
err = audit_dupe_selinux_field(&new->fields[i],
err = audit_dupe_lsm_field(&new->fields[i],
&old->fields[i]);
break;
case AUDIT_FILTERKEY:
@@ -1515,11 +1515,12 @@ static void audit_log_rule_change(uid_t loginuid, u32 sid, char *action,
if (sid) {
char *ctx = NULL;
u32 len;
if (selinux_sid_to_string(sid, &ctx, &len))
if (security_secid_to_secctx(sid, &ctx, &len))
audit_log_format(ab, " ssid=%u", sid);
else
else {
audit_log_format(ab, " subj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
audit_log_format(ab, " op=%s rule key=", action);
if (rule->filterkey)
@@ -1761,38 +1762,12 @@ unlock_and_return:
return result;
}
/* Check to see if the rule contains any selinux fields. Returns 1 if there
are selinux fields specified in the rule, 0 otherwise. */
static inline int audit_rule_has_selinux(struct audit_krule *rule)
{
int i;
for (i = 0; i < rule->field_count; i++) {
struct audit_field *f = &rule->fields[i];
switch (f->type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
return 1;
}
}
return 0;
}
/* This function will re-initialize the se_rule field of all applicable rules.
* It will traverse the filter lists serarching for rules that contain selinux
/* This function will re-initialize the lsm_rule field of all applicable rules.
* It will traverse the filter lists serarching for rules that contain LSM
* specific filter fields. When such a rule is found, it is copied, the
* selinux field is re-initialized, and the old rule is replaced with the
* LSM field is re-initialized, and the old rule is replaced with the
* updated rule. */
int selinux_audit_rule_update(void)
int audit_update_lsm_rules(void)
{
struct audit_entry *entry, *n, *nentry;
struct audit_watch *watch;
@@ -1804,7 +1779,7 @@ int selinux_audit_rule_update(void)
for (i = 0; i < AUDIT_NR_FILTERS; i++) {
list_for_each_entry_safe(entry, n, &audit_filter_list[i], list) {
if (!audit_rule_has_selinux(&entry->rule))
if (!security_audit_rule_known(&entry->rule))
continue;
watch = entry->rule.watch;
@@ -1815,7 +1790,7 @@ int selinux_audit_rule_update(void)
* return value */
if (!err)
err = PTR_ERR(nentry);
audit_panic("error updating selinux filters");
audit_panic("error updating LSM filters");
if (watch)
list_del(&entry->rule.rlist);
list_del_rcu(&entry->list);

74
kernel/auditsc.c
查看文件

@@ -61,7 +61,6 @@
#include <linux/security.h>
#include <linux/list.h>
#include <linux/tty.h>
#include <linux/selinux.h>
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
@@ -528,14 +527,14 @@ static int audit_filter_rules(struct task_struct *tsk,
match for now to avoid losing information that
may be wanted. An error message will also be
logged upon error */
if (f->se_rule) {
if (f->lsm_rule) {
if (need_sid) {
selinux_get_task_sid(tsk, &sid);
security_task_getsecid(tsk, &sid);
need_sid = 0;
}
result = selinux_audit_rule_match(sid, f->type,
result = security_audit_rule_match(sid, f->type,
f->op,
f->se_rule,
f->lsm_rule,
ctx);
}
break;
@@ -546,18 +545,18 @@ static int audit_filter_rules(struct task_struct *tsk,
case AUDIT_OBJ_LEV_HIGH:
/* The above note for AUDIT_SUBJ_USER...AUDIT_SUBJ_CLR
also applies here */
if (f->se_rule) {
if (f->lsm_rule) {
/* Find files that match */
if (name) {
result = selinux_audit_rule_match(
result = security_audit_rule_match(
name->osid, f->type, f->op,
f->se_rule, ctx);
f->lsm_rule, ctx);
} else if (ctx) {
for (j = 0; j < ctx->name_count; j++) {
if (selinux_audit_rule_match(
if (security_audit_rule_match(
ctx->names[j].osid,
f->type, f->op,
f->se_rule, ctx)) {
f->lsm_rule, ctx)) {
++result;
break;
}
@@ -570,7 +569,7 @@ static int audit_filter_rules(struct task_struct *tsk,
aux = aux->next) {
if (aux->type == AUDIT_IPC) {
struct audit_aux_data_ipcctl *axi = (void *)aux;
if (selinux_audit_rule_match(axi->osid, f->type, f->op, f->se_rule, ctx)) {
if (security_audit_rule_match(axi->osid, f->type, f->op, f->lsm_rule, ctx)) {
++result;
break;
}
@@ -885,11 +884,11 @@ void audit_log_task_context(struct audit_buffer *ab)
int error;
u32 sid;
selinux_get_task_sid(current, &sid);
security_task_getsecid(current, &sid);
if (!sid)
return;
error = selinux_sid_to_string(sid, &ctx, &len);
error = security_secid_to_secctx(sid, &ctx, &len);
if (error) {
if (error != -EINVAL)
goto error_path;
@@ -897,7 +896,7 @@ void audit_log_task_context(struct audit_buffer *ab)
}
audit_log_format(ab, " subj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
return;
error_path:
@@ -941,7 +940,7 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
u32 sid, char *comm)
{
struct audit_buffer *ab;
char *s = NULL;
char *ctx = NULL;
u32 len;
int rc = 0;
@@ -951,15 +950,16 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, auid,
uid, sessionid);
if (selinux_sid_to_string(sid, &s, &len)) {
if (security_secid_to_secctx(sid, &ctx, &len)) {
audit_log_format(ab, " obj=(none)");
rc = 1;
} else
audit_log_format(ab, " obj=%s", s);
} else {
audit_log_format(ab, " obj=%s", ctx);
security_release_secctx(ctx, len);
}
audit_log_format(ab, " ocomm=");
audit_log_untrustedstring(ab, comm);
audit_log_end(ab);
kfree(s);
return rc;
}
@@ -1271,14 +1271,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
if (axi->osid != 0) {
char *ctx = NULL;
u32 len;
if (selinux_sid_to_string(
if (security_secid_to_secctx(
axi->osid, &ctx, &len)) {
audit_log_format(ab, " osid=%u",
axi->osid);
call_panic = 1;
} else
} else {
audit_log_format(ab, " obj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
break; }
@@ -1392,13 +1393,14 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
if (n->osid != 0) {
char *ctx = NULL;
u32 len;
if (selinux_sid_to_string(
if (security_secid_to_secctx(
n->osid, &ctx, &len)) {
audit_log_format(ab, " osid=%u", n->osid);
call_panic = 2;
} else
} else {
audit_log_format(ab, " obj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
audit_log_end(ab);
@@ -1775,7 +1777,7 @@ static void audit_copy_inode(struct audit_names *name, const struct inode *inode
name->uid = inode->i_uid;
name->gid = inode->i_gid;
name->rdev = inode->i_rdev;
selinux_get_inode_sid(inode, &name->osid);
security_inode_getsecid(inode, &name->osid);
}
/**
@@ -2190,8 +2192,7 @@ int __audit_ipc_obj(struct kern_ipc_perm *ipcp)
ax->uid = ipcp->uid;
ax->gid = ipcp->gid;
ax->mode = ipcp->mode;
selinux_get_ipc_sid(ipcp, &ax->osid);
security_ipc_getsecid(ipcp, &ax->osid);
ax->d.type = AUDIT_IPC;
ax->d.next = context->aux;
context->aux = (void *)ax;
@@ -2343,7 +2344,7 @@ void __audit_ptrace(struct task_struct *t)
context->target_auid = audit_get_loginuid(t);
context->target_uid = t->uid;
context->target_sessionid = audit_get_sessionid(t);
selinux_get_task_sid(t, &context->target_sid);
security_task_getsecid(t, &context->target_sid);
memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
}
@@ -2371,7 +2372,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
audit_sig_uid = tsk->loginuid;
else
audit_sig_uid = tsk->uid;
selinux_get_task_sid(tsk, &audit_sig_sid);
security_task_getsecid(tsk, &audit_sig_sid);
}
if (!audit_signals || audit_dummy_context())
return 0;
@@ -2384,7 +2385,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
ctx->target_auid = audit_get_loginuid(t);
ctx->target_uid = t->uid;
ctx->target_sessionid = audit_get_sessionid(t);
selinux_get_task_sid(t, &ctx->target_sid);
security_task_getsecid(t, &ctx->target_sid);
memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
return 0;
}
@@ -2405,7 +2406,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
axp->target_uid[axp->pid_count] = t->uid;
axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
selinux_get_task_sid(t, &axp->target_sid[axp->pid_count]);
security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
axp->pid_count++;
@@ -2435,16 +2436,17 @@ void audit_core_dumps(long signr)
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
auid, current->uid, current->gid, sessionid);
selinux_get_task_sid(current, &sid);
security_task_getsecid(current, &sid);
if (sid) {
char *ctx = NULL;
u32 len;
if (selinux_sid_to_string(sid, &ctx, &len))
if (security_secid_to_secctx(sid, &ctx, &len))
audit_log_format(ab, " ssid=%u", sid);
else
else {
audit_log_format(ab, " subj=%s", ctx);
kfree(ctx);
security_release_secctx(ctx, len);
}
}
audit_log_format(ab, " pid=%d comm=", current->pid);
audit_log_untrustedstring(ab, current->comm);

23
kernel/bounds.c 普通文件
查看文件

@@ -0,0 +1,23 @@
/*
* Generate definitions needed by the preprocessor.
* This code generates raw asm output which is post-processed
* to extract and format the required data.
*/
#define __GENERATING_BOUNDS_H
/* Include headers that define the enum constants of interest */
#include <linux/page-flags.h>
#include <linux/mmzone.h>
#define DEFINE(sym, val) \
asm volatile("\n->" #sym " %0 " #val : : "i" (val))
#define BLANK() asm volatile("\n->" : : )
void foo(void)
{
/* The enum constants to put into include/linux/bounds.h */
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
/* End of constants */
}

7
kernel/cgroup.c
查看文件

@@ -1722,7 +1722,12 @@ void cgroup_enable_task_cg_lists(void)
use_task_css_set_links = 1;
do_each_thread(g, p) {
task_lock(p);
if (list_empty(&p->cg_list))
/*
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
*/
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
list_add(&p->cg_list, &p->cgroups->tasks);
task_unlock(p);
} while_each_thread(g, p);

17
kernel/compat.c
查看文件

@@ -47,15 +47,14 @@ static long compat_nanosleep_restart(struct restart_block *restart)
mm_segment_t oldfs;
long ret;
rmtp = (struct compat_timespec __user *)(restart->arg1);
restart->arg1 = (unsigned long)&rmt;
restart->nanosleep.rmtp = (struct timespec __user *) &rmt;
oldfs = get_fs();
set_fs(KERNEL_DS);
ret = hrtimer_nanosleep_restart(restart);
set_fs(oldfs);
if (ret) {
restart->arg1 = (unsigned long)rmtp;
rmtp = restart->nanosleep.compat_rmtp;
if (rmtp && put_compat_timespec(&rmt, rmtp))
return -EFAULT;
@@ -89,7 +88,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
= &current_thread_info()->restart_block;
restart->fn = compat_nanosleep_restart;
restart->arg1 = (unsigned long)rmtp;
restart->nanosleep.compat_rmtp = rmtp;
if (rmtp && put_compat_timespec(&rmt, rmtp))
return -EFAULT;
@@ -446,7 +445,7 @@ asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
if (retval)
return retval;
return sched_setaffinity(pid, new_mask);
return sched_setaffinity(pid, &new_mask);
}
asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
@@ -607,9 +606,9 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
long err;
mm_segment_t oldfs;
struct timespec tu;
struct compat_timespec *rmtp = (struct compat_timespec *)(restart->arg1);
struct compat_timespec *rmtp = restart->nanosleep.compat_rmtp;
restart->arg1 = (unsigned long) &tu;
restart->nanosleep.rmtp = (struct timespec __user *) &tu;
oldfs = get_fs();
set_fs(KERNEL_DS);
err = clock_nanosleep_restart(restart);
@@ -621,7 +620,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
if (err == -ERESTART_RESTARTBLOCK) {
restart->fn = compat_clock_nanosleep_restart;
restart->arg1 = (unsigned long) rmtp;
restart->nanosleep.compat_rmtp = rmtp;
}
return err;
}
@@ -652,7 +651,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
if (err == -ERESTART_RESTARTBLOCK) {
restart = &current_thread_info()->restart_block;
restart->fn = compat_clock_nanosleep_restart;
restart->arg1 = (unsigned long) rmtp;
restart->nanosleep.compat_rmtp = rmtp;
}
return err;
}

6
kernel/cpu.c
查看文件

@@ -232,9 +232,9 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
/* Ensure that we are not runnable on dying cpu */
old_allowed = current->cpus_allowed;
tmp = CPU_MASK_ALL;
cpus_setall(tmp);
cpu_clear(cpu, tmp);
set_cpus_allowed(current, tmp);
set_cpus_allowed_ptr(current, &tmp);
p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
@@ -268,7 +268,7 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
out_thread:
err = kthread_stop(p);
out_allowed:
set_cpus_allowed(current, old_allowed);
set_cpus_allowed_ptr(current, &old_allowed);
out_release:
cpu_hotplug_done();
return err;

125
kernel/cpuset.c
查看文件

@@ -98,6 +98,9 @@ struct cpuset {
/* partition number for rebuild_sched_domains() */
int pn;
/* for custom sched domain */
int relax_domain_level;
/* used for walking a cpuset heirarchy */
struct list_head stack_list;
};
@@ -478,6 +481,16 @@ static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
}
static void
update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
{
if (!dattr)
return;
if (dattr->relax_domain_level < c->relax_domain_level)
dattr->relax_domain_level = c->relax_domain_level;
return;
}
/*
* rebuild_sched_domains()
*
@@ -553,12 +566,14 @@ static void rebuild_sched_domains(void)
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
cpumask_t *doms; /* resulting partition; i.e. sched domains */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms; /* number of sched domains in result */
int nslot; /* next empty doms[] cpumask_t slot */
q = NULL;
csa = NULL;
doms = NULL;
dattr = NULL;
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
@@ -566,6 +581,11 @@ static void rebuild_sched_domains(void)
doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
if (!doms)
goto rebuild;
dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
if (dattr) {
*dattr = SD_ATTR_INIT;
update_domain_attr(dattr, &top_cpuset);
}
*doms = top_cpuset.cpus_allowed;
goto rebuild;
}
@@ -622,6 +642,7 @@ restart:
doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
if (!doms)
goto rebuild;
dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);
for (nslot = 0, i = 0; i < csn; i++) {
struct cpuset *a = csa[i];
@@ -644,12 +665,15 @@ restart:
}
cpus_clear(*dp);
if (dattr)
*(dattr + nslot) = SD_ATTR_INIT;
for (j = i; j < csn; j++) {
struct cpuset *b = csa[j];
if (apn == b->pn) {
cpus_or(*dp, *dp, b->cpus_allowed);
b->pn = -1;
update_domain_attr(dattr, b);
}
}
nslot++;
@@ -660,7 +684,7 @@ restart:
rebuild:
/* Have scheduler rebuild sched domains */
get_online_cpus();
partition_sched_domains(ndoms, doms);
partition_sched_domains(ndoms, doms, dattr);
put_online_cpus();
done:
@@ -668,6 +692,7 @@ done:
kfifo_free(q);
kfree(csa);
/* Don't kfree(doms) -- partition_sched_domains() does that. */
/* Don't kfree(dattr) -- partition_sched_domains() does that. */
}
static inline int started_after_time(struct task_struct *t1,
@@ -729,7 +754,7 @@ int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan)
*/
void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan)
{
set_cpus_allowed(tsk, (cgroup_cs(scan->cg))->cpus_allowed);
set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed));
}
/**
@@ -916,7 +941,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
cs->mems_generation = cpuset_mems_generation++;
mutex_unlock(&callback_mutex);
cpuset_being_rebound = cs; /* causes mpol_copy() rebind */
cpuset_being_rebound = cs; /* causes mpol_dup() rebind */
fudge = 10; /* spare mmarray[] slots */
fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */
@@ -967,7 +992,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
* rebind the vma mempolicies of each mm in mmarray[] to their
* new cpuset, and release that mm. The mpol_rebind_mm()
* call takes mmap_sem, which we couldn't take while holding
* tasklist_lock. Forks can happen again now - the mpol_copy()
* tasklist_lock. Forks can happen again now - the mpol_dup()
* cpuset_being_rebound check will catch such forks, and rebind
* their vma mempolicies too. Because we still hold the global
* cgroup_mutex, we know that no other rebind effort will
@@ -1011,6 +1036,21 @@ static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
return 0;
}
static int update_relax_domain_level(struct cpuset *cs, char *buf)
{
int val = simple_strtol(buf, NULL, 10);
if (val < 0)
val = -1;
if (val != cs->relax_domain_level) {
cs->relax_domain_level = val;
rebuild_sched_domains();
}
return 0;
}
/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
@@ -1178,7 +1218,7 @@ static void cpuset_attach(struct cgroup_subsys *ss,
mutex_lock(&callback_mutex);
guarantee_online_cpus(cs, &cpus);
set_cpus_allowed(tsk, cpus);
set_cpus_allowed_ptr(tsk, &cpus);
mutex_unlock(&callback_mutex);
from = oldcs->mems_allowed;
@@ -1202,6 +1242,7 @@ typedef enum {
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_SCHED_LOAD_BALANCE,
FILE_SCHED_RELAX_DOMAIN_LEVEL,
FILE_MEMORY_PRESSURE_ENABLED,
FILE_MEMORY_PRESSURE,
FILE_SPREAD_PAGE,
@@ -1224,7 +1265,8 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
return -E2BIG;
/* +1 for nul-terminator */
if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
buffer = kmalloc(nbytes + 1, GFP_KERNEL);
if (!buffer)
return -ENOMEM;
if (copy_from_user(buffer, userbuf, nbytes)) {
@@ -1256,6 +1298,9 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
case FILE_SCHED_LOAD_BALANCE:
retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, buffer);
break;
case FILE_SCHED_RELAX_DOMAIN_LEVEL:
retval = update_relax_domain_level(cs, buffer);
break;
case FILE_MEMORY_MIGRATE:
retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
break;
@@ -1354,6 +1399,9 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
case FILE_SCHED_LOAD_BALANCE:
*s++ = is_sched_load_balance(cs) ? '1' : '0';
break;
case FILE_SCHED_RELAX_DOMAIN_LEVEL:
s += sprintf(s, "%d", cs->relax_domain_level);
break;
case FILE_MEMORY_MIGRATE:
*s++ = is_memory_migrate(cs) ? '1' : '0';
break;
@@ -1424,6 +1472,13 @@ static struct cftype cft_sched_load_balance = {
.private = FILE_SCHED_LOAD_BALANCE,
};
static struct cftype cft_sched_relax_domain_level = {
.name = "sched_relax_domain_level",
.read = cpuset_common_file_read,
.write = cpuset_common_file_write,
.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
};
static struct cftype cft_memory_migrate = {
.name = "memory_migrate",
.read = cpuset_common_file_read,
@@ -1475,6 +1530,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
return err;
if ((err = cgroup_add_file(cont, ss, &cft_sched_load_balance)) < 0)
return err;
if ((err = cgroup_add_file(cont, ss,
&cft_sched_relax_domain_level)) < 0)
return err;
if ((err = cgroup_add_file(cont, ss, &cft_memory_pressure)) < 0)
return err;
if ((err = cgroup_add_file(cont, ss, &cft_spread_page)) < 0)
@@ -1555,10 +1613,11 @@ static struct cgroup_subsys_state *cpuset_create(
if (is_spread_slab(parent))
set_bit(CS_SPREAD_SLAB, &cs->flags);
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cs->cpus_allowed = CPU_MASK_NONE;
cs->mems_allowed = NODE_MASK_NONE;
cpus_clear(cs->cpus_allowed);
nodes_clear(cs->mems_allowed);
cs->mems_generation = cpuset_mems_generation++;
fmeter_init(&cs->fmeter);
cs->relax_domain_level = -1;
cs->parent = parent;
number_of_cpusets++;
@@ -1625,12 +1684,13 @@ int __init cpuset_init(void)
{
int err = 0;
top_cpuset.cpus_allowed = CPU_MASK_ALL;
top_cpuset.mems_allowed = NODE_MASK_ALL;
cpus_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
fmeter_init(&top_cpuset.fmeter);
top_cpuset.mems_generation = cpuset_mems_generation++;
set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
top_cpuset.relax_domain_level = -1;
err = register_filesystem(&cpuset_fs_type);
if (err < 0)
@@ -1844,6 +1904,7 @@ void __init cpuset_init_smp(void)
* cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
* @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
* @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
*
* Description: Returns the cpumask_t cpus_allowed of the cpuset
* attached to the specified @tsk. Guaranteed to return some non-empty
@@ -1851,35 +1912,27 @@ void __init cpuset_init_smp(void)
* tasks cpuset.
**/
cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
{
cpumask_t mask;
mutex_lock(&callback_mutex);
mask = cpuset_cpus_allowed_locked(tsk);
cpuset_cpus_allowed_locked(tsk, pmask);
mutex_unlock(&callback_mutex);
return mask;
}
/**
* cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
* Must be called with callback_mutex held.
**/
cpumask_t cpuset_cpus_allowed_locked(struct task_struct *tsk)
void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask)
{
cpumask_t mask;
task_lock(tsk);
guarantee_online_cpus(task_cs(tsk), &mask);
guarantee_online_cpus(task_cs(tsk), pmask);
task_unlock(tsk);
return mask;
}
void cpuset_init_current_mems_allowed(void)
{
current->mems_allowed = NODE_MASK_ALL;
nodes_setall(current->mems_allowed);
}
/**
@@ -1906,22 +1959,14 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
}
/**
* cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
* @zl: the zonelist to be checked
* cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed
* @nodemask: the nodemask to be checked
*
* Are any of the nodes on zonelist zl allowed in current->mems_allowed?
* Are any of the nodes in the nodemask allowed in current->mems_allowed?
*/
int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
{
int i;
for (i = 0; zl->zones[i]; i++) {
int nid = zone_to_nid(zl->zones[i]);
if (node_isset(nid, current->mems_allowed))
return 1;
}
return 0;
return nodes_intersects(*nodemask, current->mems_allowed);
}
/*
@@ -2261,8 +2306,16 @@ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
m->count += cpumask_scnprintf(m->buf + m->count, m->size - m->count,
task->cpus_allowed);
seq_printf(m, "\n");
seq_printf(m, "Cpus_allowed_list:\t");
m->count += cpulist_scnprintf(m->buf + m->count, m->size - m->count,
task->cpus_allowed);
seq_printf(m, "\n");
seq_printf(m, "Mems_allowed:\t");
m->count += nodemask_scnprintf(m->buf + m->count, m->size - m->count,
task->mems_allowed);
seq_printf(m, "\n");
seq_printf(m, "Mems_allowed_list:\t");
m->count += nodelist_scnprintf(m->buf + m->count, m->size - m->count,
task->mems_allowed);
seq_printf(m, "\n");
}

35
kernel/exit.c
查看文件

@@ -507,10 +507,9 @@ void put_files_struct(struct files_struct *files)
}
}
EXPORT_SYMBOL(put_files_struct);
void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
void reset_files_struct(struct files_struct *files)
{
struct task_struct *tsk = current;
struct files_struct *old;
old = tsk->files;
@@ -519,9 +518,8 @@ void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
task_unlock(tsk);
put_files_struct(old);
}
EXPORT_SYMBOL(reset_files_struct);
static void __exit_files(struct task_struct *tsk)
void exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
@@ -533,12 +531,7 @@ static void __exit_files(struct task_struct *tsk)
}
}
void exit_files(struct task_struct *tsk)
{
__exit_files(tsk);
}
static void __put_fs_struct(struct fs_struct *fs)
void put_fs_struct(struct fs_struct *fs)
{
/* No need to hold fs->lock if we are killing it */
if (atomic_dec_and_test(&fs->count)) {
@@ -550,12 +543,7 @@ static void __put_fs_struct(struct fs_struct *fs)
}
}
void put_fs_struct(struct fs_struct *fs)
{
__put_fs_struct(fs);
}
static void __exit_fs(struct task_struct *tsk)
void exit_fs(struct task_struct *tsk)
{
struct fs_struct * fs = tsk->fs;
@@ -563,15 +551,10 @@ static void __exit_fs(struct task_struct *tsk)
task_lock(tsk);
tsk->fs = NULL;
task_unlock(tsk);
__put_fs_struct(fs);
put_fs_struct(fs);
}
}
void exit_fs(struct task_struct *tsk)
{
__exit_fs(tsk);
}
EXPORT_SYMBOL_GPL(exit_fs);
/*
@@ -967,8 +950,8 @@ NORET_TYPE void do_exit(long code)
if (group_dead)
acct_process();
exit_sem(tsk);
__exit_files(tsk);
__exit_fs(tsk);
exit_files(tsk);
exit_fs(tsk);
check_stack_usage();
exit_thread();
cgroup_exit(tsk, 1);
@@ -984,7 +967,7 @@ NORET_TYPE void do_exit(long code)
proc_exit_connector(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
mpol_free(tsk->mempolicy);
mpol_put(tsk->mempolicy);
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX

101
kernel/fork.c
查看文件

@@ -132,6 +132,14 @@ void __put_task_struct(struct task_struct *tsk)
free_task(tsk);
}
/*
* macro override instead of weak attribute alias, to workaround
* gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
*/
#ifndef arch_task_cache_init
#define arch_task_cache_init()
#endif
void __init fork_init(unsigned long mempages)
{
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
@@ -144,6 +152,9 @@ void __init fork_init(unsigned long mempages)
ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL);
#endif
/* do the arch specific task caches init */
arch_task_cache_init();
/*
* The default maximum number of threads is set to a safe
* value: the thread structures can take up at most half
@@ -163,6 +174,13 @@ void __init fork_init(unsigned long mempages)
init_task.signal->rlim[RLIMIT_NPROC];
}
int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
return 0;
}
static struct task_struct *dup_task_struct(struct task_struct *orig)
{
struct task_struct *tsk;
@@ -181,15 +199,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
return NULL;
}
*tsk = *orig;
err = arch_dup_task_struct(tsk, orig);
if (err)
goto out;
tsk->stack = ti;
err = prop_local_init_single(&tsk->dirties);
if (err) {
free_thread_info(ti);
free_task_struct(tsk);
return NULL;
}
if (err)
goto out;
setup_thread_stack(tsk, orig);
@@ -205,6 +223,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
#endif
tsk->splice_pipe = NULL;
return tsk;
out:
free_thread_info(ti);
free_task_struct(tsk);
return NULL;
}
#ifdef CONFIG_MMU
@@ -256,7 +279,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
pol = mpol_copy(vma_policy(mpnt));
pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
@@ -498,7 +521,7 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
static struct mm_struct *dup_mm(struct task_struct *tsk)
struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
@@ -782,12 +805,6 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
goto out;
}
/*
* Note: we may be using current for both targets (See exec.c)
* This works because we cache current->files (old) as oldf. Don't
* break this.
*/
tsk->files = NULL;
newf = dup_fd(oldf, &error);
if (!newf)
goto out;
@@ -823,34 +840,6 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
/*
* Helper to unshare the files of the current task.
* We don't want to expose copy_files internals to
* the exec layer of the kernel.
*/
int unshare_files(void)
{
struct files_struct *files = current->files;
int rc;
BUG_ON(!files);
/* This can race but the race causes us to copy when we don't
need to and drop the copy */
if(atomic_read(&files->count) == 1)
{
atomic_inc(&files->count);
return 0;
}
rc = copy_files(0, current);
if(rc)
current->files = files;
return rc;
}
EXPORT_SYMBOL(unshare_files);
static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
{
struct sighand_struct *sig;
@@ -1127,7 +1116,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->audit_context = NULL;
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
@@ -1385,7 +1374,7 @@ bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
@@ -1788,3 +1777,27 @@ bad_unshare_cleanup_thread:
bad_unshare_out:
return err;
}
/*
* Helper to unshare the files of the current task.
* We don't want to expose copy_files internals to
* the exec layer of the kernel.
*/
int unshare_files(struct files_struct **displaced)
{
struct task_struct *task = current;
struct files_struct *copy = NULL;
int error;
error = unshare_fd(CLONE_FILES, &copy);
if (error || !copy) {
*displaced = NULL;
return error;
}
*displaced = task->files;
task_lock(task);
task->files = copy;
task_unlock(task);
return 0;
}

129
kernel/hrtimer.c
查看文件

@@ -590,7 +590,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
timer->state = HRTIMER_STATE_PENDING;
raise_softirq(HRTIMER_SOFTIRQ);
return 1;
default:
BUG();
@@ -633,6 +632,11 @@ static int hrtimer_switch_to_hres(void)
return 1;
}
static inline void hrtimer_raise_softirq(void)
{
raise_softirq(HRTIMER_SOFTIRQ);
}
#else
static inline int hrtimer_hres_active(void) { return 0; }
@@ -651,6 +655,7 @@ static inline int hrtimer_reprogram(struct hrtimer *timer,
{
return 0;
}
static inline void hrtimer_raise_softirq(void) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
@@ -850,7 +855,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
int ret;
int ret, raise;
base = lock_hrtimer_base(timer, &flags);
@@ -884,8 +889,18 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
enqueue_hrtimer(timer, new_base,
new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
/*
* The timer may be expired and moved to the cb_pending
* list. We can not raise the softirq with base lock held due
* to a possible deadlock with runqueue lock.
*/
raise = timer->state == HRTIMER_STATE_PENDING;
unlock_hrtimer_base(timer, &flags);
if (raise)
hrtimer_raise_softirq();
return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_start);
@@ -1080,8 +1095,19 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
* If the timer was rearmed on another CPU, reprogram
* the event device.
*/
if (timer->base->first == &timer->node)
hrtimer_reprogram(timer, timer->base);
struct hrtimer_clock_base *base = timer->base;
if (base->first == &timer->node &&
hrtimer_reprogram(timer, base)) {
/*
* Timer is expired. Thus move it from tree to
* pending list again.
*/
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
}
}
}
spin_unlock_irq(&cpu_base->lock);
@@ -1238,51 +1264,50 @@ void hrtimer_run_pending(void)
/*
* Called from hardirq context every jiffy
*/
static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
int index)
{
struct rb_node *node;
struct hrtimer_clock_base *base = &cpu_base->clock_base[index];
if (!base->first)
return;
if (base->get_softirq_time)
base->softirq_time = base->get_softirq_time();
spin_lock(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(node, struct hrtimer, node);
if (base->softirq_time.tv64 <= timer->expires.tv64)
break;
if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
__remove_hrtimer(timer, base, HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
continue;
}
__run_hrtimer(timer);
}
spin_unlock(&cpu_base->lock);
}
void hrtimer_run_queues(void)
{
struct rb_node *node;
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
int i;
struct hrtimer_clock_base *base;
int index, gettime = 1;
if (hrtimer_hres_active())
return;
hrtimer_get_softirq_time(cpu_base);
for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
base = &cpu_base->clock_base[index];
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
run_hrtimer_queue(cpu_base, i);
if (!base->first)
continue;
if (base->get_softirq_time)
base->softirq_time = base->get_softirq_time();
else if (gettime) {
hrtimer_get_softirq_time(cpu_base);
gettime = 0;
}
spin_lock(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(node, struct hrtimer, node);
if (base->softirq_time.tv64 <= timer->expires.tv64)
break;
if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
continue;
}
__run_hrtimer(timer);
}
spin_unlock(&cpu_base->lock);
}
}
/*
@@ -1354,13 +1379,13 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
struct hrtimer_sleeper t;
struct timespec __user *rmtp;
hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
hrtimer_init(&t.timer, restart->nanosleep.index, HRTIMER_MODE_ABS);
t.timer.expires.tv64 = restart->nanosleep.expires;
if (do_nanosleep(&t, HRTIMER_MODE_ABS))
return 0;
rmtp = (struct timespec __user *)restart->arg1;
rmtp = restart->nanosleep.rmtp;
if (rmtp) {
int ret = update_rmtp(&t.timer, rmtp);
if (ret <= 0)
@@ -1394,10 +1419,9 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
restart = &current_thread_info()->restart_block;
restart->fn = hrtimer_nanosleep_restart;
restart->arg0 = (unsigned long) t.timer.base->index;
restart->arg1 = (unsigned long) rmtp;
restart->arg2 = t.timer.expires.tv64 & 0xFFFFFFFF;
restart->arg3 = t.timer.expires.tv64 >> 32;
restart->nanosleep.index = t.timer.base->index;
restart->nanosleep.rmtp = rmtp;
restart->nanosleep.expires = t.timer.expires.tv64;
return -ERESTART_RESTARTBLOCK;
}
@@ -1425,7 +1449,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
int i;
spin_lock_init(&cpu_base->lock);
lockdep_set_class(&cpu_base->lock, &cpu_base->lock_key);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
cpu_base->clock_base[i].cpu_base = cpu_base;
@@ -1466,16 +1489,16 @@ static void migrate_hrtimers(int cpu)
tick_cancel_sched_timer(cpu);
local_irq_disable();
double_spin_lock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
spin_lock(&new_base->lock);
spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
migrate_hrtimer_list(&old_base->clock_base[i],
&new_base->clock_base[i]);
}
double_spin_unlock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
spin_unlock(&old_base->lock);
spin_unlock(&new_base->lock);
local_irq_enable();
put_cpu_var(hrtimer_bases);
}

2
kernel/irq/chip.c
查看文件

@@ -47,7 +47,7 @@ void dynamic_irq_init(unsigned int irq)
desc->irq_count = 0;
desc->irqs_unhandled = 0;
#ifdef CONFIG_SMP
desc->affinity = CPU_MASK_ALL;
cpus_setall(desc->affinity);
#endif
spin_unlock_irqrestore(&desc->lock, flags);
}

4
kernel/kexec.c
查看文件

@@ -29,7 +29,6 @@
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/system.h>
#include <asm/semaphore.h>
#include <asm/sections.h>
/* Per cpu memory for storing cpu states in case of system crash. */
@@ -1406,6 +1405,9 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
VMCOREINFO_NUMBER(NR_FREE_PAGES);
VMCOREINFO_NUMBER(PG_lru);
VMCOREINFO_NUMBER(PG_private);
VMCOREINFO_NUMBER(PG_swapcache);
arch_crash_save_vmcoreinfo();

1700
kernel/kgdb.c 普通文件
查看文件

文件差异内容过多而无法显示 加载差异

2
kernel/kmod.c
查看文件

@@ -165,7 +165,7 @@ static int ____call_usermodehelper(void *data)
}
/* We can run anywhere, unlike our parent keventd(). */
set_cpus_allowed(current, CPU_MASK_ALL);
set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
/*
* Our parent is keventd, which runs with elevated scheduling priority.

357
kernel/kprobes.c
查看文件

@@ -72,6 +72,18 @@ DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */
DEFINE_SPINLOCK(kretprobe_lock); /* Protects kretprobe_inst_table */
static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
/*
* Normally, functions that we'd want to prohibit kprobes in, are marked
* __kprobes. But, there are cases where such functions already belong to
* a different section (__sched for preempt_schedule)
*
* For such cases, we now have a blacklist
*/
struct kprobe_blackpoint kprobe_blacklist[] = {
{"preempt_schedule",},
{NULL} /* Terminator */
};
#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
/*
* kprobe->ainsn.insn points to the copy of the instruction to be
@@ -417,6 +429,21 @@ static inline void free_rp_inst(struct kretprobe *rp)
}
}
static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
{
unsigned long flags;
struct kretprobe_instance *ri;
struct hlist_node *pos, *next;
/* No race here */
spin_lock_irqsave(&kretprobe_lock, flags);
hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
ri->rp = NULL;
hlist_del(&ri->uflist);
}
spin_unlock_irqrestore(&kretprobe_lock, flags);
free_rp_inst(rp);
}
/*
* Keep all fields in the kprobe consistent
*/
@@ -492,9 +519,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
static int __kprobes in_kprobes_functions(unsigned long addr)
{
struct kprobe_blackpoint *kb;
if (addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end)
return -EINVAL;
/*
* If there exists a kprobe_blacklist, verify and
* fail any probe registration in the prohibited area
*/
for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
if (kb->start_addr) {
if (addr >= kb->start_addr &&
addr < (kb->start_addr + kb->range))
return -EINVAL;
}
}
return 0;
}
@@ -555,6 +595,7 @@ static int __kprobes __register_kprobe(struct kprobe *p,
}
p->nmissed = 0;
INIT_LIST_HEAD(&p->list);
mutex_lock(&kprobe_mutex);
old_p = get_kprobe(p->addr);
if (old_p) {
@@ -581,35 +622,28 @@ out:
return ret;
}
int __kprobes register_kprobe(struct kprobe *p)
/*
* Unregister a kprobe without a scheduler synchronization.
*/
static int __kprobes __unregister_kprobe_top(struct kprobe *p)
{
return __register_kprobe(p, (unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_kprobe(struct kprobe *p)
{
struct module *mod;
struct kprobe *old_p, *list_p;
int cleanup_p;
mutex_lock(&kprobe_mutex);
old_p = get_kprobe(p->addr);
if (unlikely(!old_p)) {
mutex_unlock(&kprobe_mutex);
return;
}
if (unlikely(!old_p))
return -EINVAL;
if (p != old_p) {
list_for_each_entry_rcu(list_p, &old_p->list, list)
if (list_p == p)
/* kprobe p is a valid probe */
goto valid_p;
mutex_unlock(&kprobe_mutex);
return;
return -EINVAL;
}
valid_p:
if (old_p == p ||
(old_p->pre_handler == aggr_pre_handler &&
p->list.next == &old_p->list && p->list.prev == &old_p->list)) {
list_is_singular(&old_p->list))) {
/*
* Only probe on the hash list. Disarm only if kprobes are
* enabled - otherwise, the breakpoint would already have
@@ -618,45 +652,99 @@ valid_p:
if (kprobe_enabled)
arch_disarm_kprobe(p);
hlist_del_rcu(&old_p->hlist);
cleanup_p = 1;
} else {
if (p->break_handler)
old_p->break_handler = NULL;
if (p->post_handler) {
list_for_each_entry_rcu(list_p, &old_p->list, list) {
if ((list_p != p) && (list_p->post_handler))
goto noclean;
}
old_p->post_handler = NULL;
}
noclean:
list_del_rcu(&p->list);
cleanup_p = 0;
}
return 0;
}
mutex_unlock(&kprobe_mutex);
static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
{
struct module *mod;
struct kprobe *old_p;
synchronize_sched();
if (p->mod_refcounted) {
mod = module_text_address((unsigned long)p->addr);
if (mod)
module_put(mod);
}
if (cleanup_p) {
if (p != old_p) {
list_del_rcu(&p->list);
if (list_empty(&p->list) || list_is_singular(&p->list)) {
if (!list_empty(&p->list)) {
/* "p" is the last child of an aggr_kprobe */
old_p = list_entry(p->list.next, struct kprobe, list);
list_del(&p->list);
kfree(old_p);
}
arch_remove_kprobe(p);
} else {
mutex_lock(&kprobe_mutex);
if (p->break_handler)
old_p->break_handler = NULL;
if (p->post_handler){
list_for_each_entry_rcu(list_p, &old_p->list, list){
if (list_p->post_handler){
cleanup_p = 2;
break;
}
}
if (cleanup_p == 0)
old_p->post_handler = NULL;
}
mutex_unlock(&kprobe_mutex);
}
}
static int __register_kprobes(struct kprobe **kps, int num,
unsigned long called_from)
{
int i, ret = 0;
if (num <= 0)
return -EINVAL;
for (i = 0; i < num; i++) {
ret = __register_kprobe(kps[i], called_from);
if (ret < 0 && i > 0) {
unregister_kprobes(kps, i);
break;
}
}
return ret;
}
/*
* Registration and unregistration functions for kprobe.
*/
int __kprobes register_kprobe(struct kprobe *p)
{
return __register_kprobes(&p, 1,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_kprobe(struct kprobe *p)
{
unregister_kprobes(&p, 1);
}
int __kprobes register_kprobes(struct kprobe **kps, int num)
{
return __register_kprobes(kps, num,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_kprobes(struct kprobe **kps, int num)
{
int i;
if (num <= 0)
return;
mutex_lock(&kprobe_mutex);
for (i = 0; i < num; i++)
if (__unregister_kprobe_top(kps[i]) < 0)
kps[i]->addr = NULL;
mutex_unlock(&kprobe_mutex);
synchronize_sched();
for (i = 0; i < num; i++)
if (kps[i]->addr)
__unregister_kprobe_bottom(kps[i]);
}
static struct notifier_block kprobe_exceptions_nb = {
.notifier_call = kprobe_exceptions_notify,
.priority = 0x7fffffff /* we need to be notified first */
@@ -667,24 +755,69 @@ unsigned long __weak arch_deref_entry_point(void *entry)
return (unsigned long)entry;
}
static int __register_jprobes(struct jprobe **jps, int num,
unsigned long called_from)
{
struct jprobe *jp;
int ret = 0, i;
if (num <= 0)
return -EINVAL;
for (i = 0; i < num; i++) {
unsigned long addr;
jp = jps[i];
addr = arch_deref_entry_point(jp->entry);
if (!kernel_text_address(addr))
ret = -EINVAL;
else {
/* Todo: Verify probepoint is a function entry point */
jp->kp.pre_handler = setjmp_pre_handler;
jp->kp.break_handler = longjmp_break_handler;
ret = __register_kprobe(&jp->kp, called_from);
}
if (ret < 0 && i > 0) {
unregister_jprobes(jps, i);
break;
}
}
return ret;
}
int __kprobes register_jprobe(struct jprobe *jp)
{
unsigned long addr = arch_deref_entry_point(jp->entry);
if (!kernel_text_address(addr))
return -EINVAL;
/* Todo: Verify probepoint is a function entry point */
jp->kp.pre_handler = setjmp_pre_handler;
jp->kp.break_handler = longjmp_break_handler;
return __register_kprobe(&jp->kp,
return __register_jprobes(&jp, 1,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_jprobe(struct jprobe *jp)
{
unregister_kprobe(&jp->kp);
unregister_jprobes(&jp, 1);
}
int __kprobes register_jprobes(struct jprobe **jps, int num)
{
return __register_jprobes(jps, num,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_jprobes(struct jprobe **jps, int num)
{
int i;
if (num <= 0)
return;
mutex_lock(&kprobe_mutex);
for (i = 0; i < num; i++)
if (__unregister_kprobe_top(&jps[i]->kp) < 0)
jps[i]->kp.addr = NULL;
mutex_unlock(&kprobe_mutex);
synchronize_sched();
for (i = 0; i < num; i++) {
if (jps[i]->kp.addr)
__unregister_kprobe_bottom(&jps[i]->kp);
}
}
#ifdef CONFIG_KRETPROBES
@@ -725,7 +858,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
return 0;
}
int __kprobes register_kretprobe(struct kretprobe *rp)
static int __kprobes __register_kretprobe(struct kretprobe *rp,
unsigned long called_from)
{
int ret = 0;
struct kretprobe_instance *inst;
@@ -771,46 +905,101 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
rp->nmissed = 0;
/* Establish function entry probe point */
if ((ret = __register_kprobe(&rp->kp,
(unsigned long)__builtin_return_address(0))) != 0)
ret = __register_kprobe(&rp->kp, called_from);
if (ret != 0)
free_rp_inst(rp);
return ret;
}
static int __register_kretprobes(struct kretprobe **rps, int num,
unsigned long called_from)
{
int ret = 0, i;
if (num <= 0)
return -EINVAL;
for (i = 0; i < num; i++) {
ret = __register_kretprobe(rps[i], called_from);
if (ret < 0 && i > 0) {
unregister_kretprobes(rps, i);
break;
}
}
return ret;
}
int __kprobes register_kretprobe(struct kretprobe *rp)
{
return __register_kretprobes(&rp, 1,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
unregister_kretprobes(&rp, 1);
}
int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
return __register_kretprobes(rps, num,
(unsigned long)__builtin_return_address(0));
}
void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
int i;
if (num <= 0)
return;
mutex_lock(&kprobe_mutex);
for (i = 0; i < num; i++)
if (__unregister_kprobe_top(&rps[i]->kp) < 0)
rps[i]->kp.addr = NULL;
mutex_unlock(&kprobe_mutex);
synchronize_sched();
for (i = 0; i < num; i++) {
if (rps[i]->kp.addr) {
__unregister_kprobe_bottom(&rps[i]->kp);
cleanup_rp_inst(rps[i]);
}
}
}
#else /* CONFIG_KRETPROBES */
int __kprobes register_kretprobe(struct kretprobe *rp)
{
return -ENOSYS;
}
int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
return -ENOSYS;
}
void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
}
void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
}
static int __kprobes pre_handler_kretprobe(struct kprobe *p,
struct pt_regs *regs)
{
return 0;
}
#endif /* CONFIG_KRETPROBES */
void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
unsigned long flags;
struct kretprobe_instance *ri;
struct hlist_node *pos, *next;
unregister_kprobe(&rp->kp);
/* No race here */
spin_lock_irqsave(&kretprobe_lock, flags);
hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
ri->rp = NULL;
hlist_del(&ri->uflist);
}
spin_unlock_irqrestore(&kretprobe_lock, flags);
free_rp_inst(rp);
}
static int __init init_kprobes(void)
{
int i, err = 0;
unsigned long offset = 0, size = 0;
char *modname, namebuf[128];
const char *symbol_name;
void *addr;
struct kprobe_blackpoint *kb;
/* FIXME allocate the probe table, currently defined statically */
/* initialize all list heads */
@@ -819,6 +1008,28 @@ static int __init init_kprobes(void)
INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
}
/*
* Lookup and populate the kprobe_blacklist.
*
* Unlike the kretprobe blacklist, we'll need to determine
* the range of addresses that belong to the said functions,
* since a kprobe need not necessarily be at the beginning
* of a function.
*/
for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
kprobe_lookup_name(kb->name, addr);
if (!addr)
continue;
kb->start_addr = (unsigned long)addr;
symbol_name = kallsyms_lookup(kb->start_addr,
&size, &offset, &modname, namebuf);
if (!symbol_name)
kb->range = 0;
else
kb->range = size;
}
if (kretprobe_blacklist_size) {
/* lookup the function address from its name */
for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
@@ -1066,8 +1277,12 @@ module_init(init_kprobes);
EXPORT_SYMBOL_GPL(register_kprobe);
EXPORT_SYMBOL_GPL(unregister_kprobe);
EXPORT_SYMBOL_GPL(register_kprobes);
EXPORT_SYMBOL_GPL(unregister_kprobes);
EXPORT_SYMBOL_GPL(register_jprobe);
EXPORT_SYMBOL_GPL(unregister_jprobe);
EXPORT_SYMBOL_GPL(register_jprobes);
EXPORT_SYMBOL_GPL(unregister_jprobes);
#ifdef CONFIG_KPROBES
EXPORT_SYMBOL_GPL(jprobe_return);
#endif
@@ -1075,4 +1290,6 @@ EXPORT_SYMBOL_GPL(jprobe_return);
#ifdef CONFIG_KPROBES
EXPORT_SYMBOL_GPL(register_kretprobe);
EXPORT_SYMBOL_GPL(unregister_kretprobe);
EXPORT_SYMBOL_GPL(register_kretprobes);
EXPORT_SYMBOL_GPL(unregister_kretprobes);
#endif

2
kernel/kthread.c
查看文件

@@ -13,7 +13,6 @@
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <asm/semaphore.h>
#define KTHREAD_NICE_LEVEL (-5)
@@ -180,6 +179,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
wait_task_inactive(k);
set_task_cpu(k, cpu);
k->cpus_allowed = cpumask_of_cpu(cpu);
k->rt.nr_cpus_allowed = 1;
}
EXPORT_SYMBOL(kthread_bind);

27
kernel/latencytop.c
查看文件

@@ -64,8 +64,8 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
return;
for (i = 0; i < MAXLR; i++) {
int q;
int same = 1;
int q, same = 1;
/* Nothing stored: */
if (!latency_record[i].backtrace[0]) {
if (firstnonnull > i)
@@ -73,12 +73,15 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
continue;
}
for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
if (latency_record[i].backtrace[q] !=
lat->backtrace[q])
unsigned long record = lat->backtrace[q];
if (latency_record[i].backtrace[q] != record) {
same = 0;
if (same && lat->backtrace[q] == 0)
break;
if (same && lat->backtrace[q] == ULONG_MAX)
}
/* 0 and ULONG_MAX entries mean end of backtrace: */
if (record == 0 || record == ULONG_MAX)
break;
}
if (same) {
@@ -143,14 +146,18 @@ account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
for (i = 0; i < LT_SAVECOUNT ; i++) {
struct latency_record *mylat;
int same = 1;
mylat = &tsk->latency_record[i];
for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
if (mylat->backtrace[q] !=
lat.backtrace[q])
unsigned long record = lat.backtrace[q];
if (mylat->backtrace[q] != record) {
same = 0;
if (same && lat.backtrace[q] == 0)
break;
if (same && lat.backtrace[q] == ULONG_MAX)
}
/* 0 and ULONG_MAX entries mean end of backtrace: */
if (record == 0 || record == ULONG_MAX)
break;
}
if (same) {

3
kernel/module.c
查看文件

@@ -43,7 +43,6 @@
#include <linux/mutex.h>
#include <linux/unwind.h>
#include <asm/uaccess.h>
#include <asm/semaphore.h>
#include <asm/cacheflush.h>
#include <linux/license.h>
#include <asm/sections.h>
@@ -664,7 +663,7 @@ static void free_module(struct module *mod);
static void wait_for_zero_refcount(struct module *mod)
{
/* Since we might sleep for some time, drop the semaphore first */
/* Since we might sleep for some time, release the mutex first */
mutex_unlock(&module_mutex);
for (;;) {
DEBUGP("Looking at refcount...\n");

2
kernel/pid_namespace.c
查看文件

@@ -92,7 +92,7 @@ static struct pid_namespace *create_pid_namespace(int level)
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
for (i = 1; i < PIDMAP_ENTRIES; i++) {
ns->pidmap[i].page = 0;
ns->pidmap[i].page = NULL;
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
}

30
kernel/posix-cpu-timers.c
查看文件

@@ -1087,45 +1087,45 @@ static void check_process_timers(struct task_struct *tsk,
maxfire = 20;
prof_expires = cputime_zero;
while (!list_empty(timers)) {
struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
if (!--maxfire || cputime_lt(ptime, t->expires.cpu)) {
prof_expires = t->expires.cpu;
if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
prof_expires = tl->expires.cpu;
break;
}
t->firing = 1;
list_move_tail(&t->entry, firing);
tl->firing = 1;
list_move_tail(&tl->entry, firing);
}
++timers;
maxfire = 20;
virt_expires = cputime_zero;
while (!list_empty(timers)) {
struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
if (!--maxfire || cputime_lt(utime, t->expires.cpu)) {
virt_expires = t->expires.cpu;
if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) {
virt_expires = tl->expires.cpu;
break;
}
t->firing = 1;
list_move_tail(&t->entry, firing);
tl->firing = 1;
list_move_tail(&tl->entry, firing);
}
++timers;
maxfire = 20;
sched_expires = 0;
while (!list_empty(timers)) {
struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
if (!--maxfire || sum_sched_runtime < t->expires.sched) {
sched_expires = t->expires.sched;
if (!--maxfire || sum_sched_runtime < tl->expires.sched) {
sched_expires = tl->expires.sched;
break;
}
t->firing = 1;
list_move_tail(&t->entry, firing);
tl->firing = 1;
list_move_tail(&tl->entry, firing);
}
/*

1
kernel/posix-timers.c
查看文件

@@ -37,7 +37,6 @@
#include <linux/mutex.h>
#include <asm/uaccess.h>
#include <asm/semaphore.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>

10
kernel/power/Kconfig
查看文件

@@ -19,16 +19,6 @@ config PM
will issue the hlt instruction if nothing is to be done, thereby
sending the processor to sleep and saving power.
config PM_LEGACY
bool "Legacy Power Management API (DEPRECATED)"
depends on PM
default n
---help---
Support for pm_register() and friends. This old API is obsoleted
by the driver model.
If unsure, say N.
config PM_DEBUG
bool "Power Management Debug Support"
depends on PM

1
kernel/power/Makefile
查看文件

@@ -4,7 +4,6 @@ EXTRA_CFLAGS += -DDEBUG
endif
obj-y := main.o
obj-$(CONFIG_PM_LEGACY) += pm.o
obj-$(CONFIG_PM_SLEEP) += process.o console.o
obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o

27
kernel/power/console.c
查看文件

@@ -7,17 +7,39 @@
#include <linux/vt_kern.h>
#include <linux/kbd_kern.h>
#include <linux/console.h>
#include <linux/module.h>
#include "power.h"
#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
static int orig_fgconsole, orig_kmsg;
static int disable_vt_switch;
/*
* Normally during a suspend, we allocate a new console and switch to it.
* When we resume, we switch back to the original console. This switch
* can be slow, so on systems where the framebuffer can handle restoration
* of video registers anyways, there's little point in doing the console
* switch. This function allows you to disable it by passing it '0'.
*/
void pm_set_vt_switch(int do_switch)
{
acquire_console_sem();
disable_vt_switch = !do_switch;
release_console_sem();
}
EXPORT_SYMBOL(pm_set_vt_switch);
int pm_prepare_console(void)
{
acquire_console_sem();
if (disable_vt_switch) {
release_console_sem();
return 0;
}
orig_fgconsole = fg_console;
if (vc_allocate(SUSPEND_CONSOLE)) {
@@ -50,9 +72,12 @@ int pm_prepare_console(void)
void pm_restore_console(void)
{
acquire_console_sem();
if (disable_vt_switch) {
release_console_sem();
return;
}
set_console(orig_fgconsole);
release_console_sem();
kmsg_redirect = orig_kmsg;
return;
}
#endif

205
kernel/power/pm.c
查看文件

@@ -1,205 +0,0 @@
/*
* pm.c - Power management interface
*
* Copyright (C) 2000 Andrew Henroid
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/pm.h>
#include <linux/pm_legacy.h>
#include <linux/interrupt.h>
#include <linux/mutex.h>
/*
* Locking notes:
* pm_devs_lock can be a semaphore providing pm ops are not called
* from an interrupt handler (already a bad idea so no change here). Each
* change must be protected so that an unlink of an entry doesn't clash
* with a pm send - which is permitted to sleep in the current architecture
*
* Module unloads clashing with pm events now work out safely, the module
* unload path will block until the event has been sent. It may well block
* until a resume but that will be fine.
*/
static DEFINE_MUTEX(pm_devs_lock);
static LIST_HEAD(pm_devs);
/**
* pm_register - register a device with power management
* @type: device type
* @id: device ID
* @callback: callback function
*
* Add a device to the list of devices that wish to be notified about
* power management events. A &pm_dev structure is returned on success,
* on failure the return is %NULL.
*
* The callback function will be called in process context and
* it may sleep.
*/
struct pm_dev *pm_register(pm_dev_t type,
unsigned long id,
pm_callback callback)
{
struct pm_dev *dev = kzalloc(sizeof(struct pm_dev), GFP_KERNEL);
if (dev) {
dev->type = type;
dev->id = id;
dev->callback = callback;
mutex_lock(&pm_devs_lock);
list_add(&dev->entry, &pm_devs);
mutex_unlock(&pm_devs_lock);
}
return dev;
}
/**
* pm_send - send request to a single device
* @dev: device to send to
* @rqst: power management request
* @data: data for the callback
*
* Issue a power management request to a given device. The
* %PM_SUSPEND and %PM_RESUME events are handled specially. The
* data field must hold the intended next state. No call is made
* if the state matches.
*
* BUGS: what stops two power management requests occurring in parallel
* and conflicting.
*
* WARNING: Calling pm_send directly is not generally recommended, in
* particular there is no locking against the pm_dev going away. The
* caller must maintain all needed locking or have 'inside knowledge'
* on the safety. Also remember that this function is not locked against
* pm_unregister. This means that you must handle SMP races on callback
* execution and unload yourself.
*/
static int pm_send(struct pm_dev *dev, pm_request_t rqst, void *data)
{
int status = 0;
unsigned long prev_state, next_state;
if (in_interrupt())
BUG();
switch (rqst) {
case PM_SUSPEND:
case PM_RESUME:
prev_state = dev->state;
next_state = (unsigned long) data;
if (prev_state != next_state) {
if (dev->callback)
status = (*dev->callback)(dev, rqst, data);
if (!status) {
dev->state = next_state;
dev->prev_state = prev_state;
}
}
else {
dev->prev_state = prev_state;
}
break;
default:
if (dev->callback)
status = (*dev->callback)(dev, rqst, data);
break;
}
return status;
}
/*
* Undo incomplete request
*/
static void pm_undo_all(struct pm_dev *last)
{
struct list_head *entry = last->entry.prev;
while (entry != &pm_devs) {
struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
if (dev->state != dev->prev_state) {
/* previous state was zero (running) resume or
* previous state was non-zero (suspended) suspend
*/
pm_request_t undo = (dev->prev_state
? PM_SUSPEND:PM_RESUME);
pm_send(dev, undo, (void*) dev->prev_state);
}
entry = entry->prev;
}
}
/**
* pm_send_all - send request to all managed devices
* @rqst: power management request
* @data: data for the callback
*
* Issue a power management request to a all devices. The
* %PM_SUSPEND events are handled specially. Any device is
* permitted to fail a suspend by returning a non zero (error)
* value from its callback function. If any device vetoes a
* suspend request then all other devices that have suspended
* during the processing of this request are restored to their
* previous state.
*
* WARNING: This function takes the pm_devs_lock. The lock is not dropped until
* the callbacks have completed. This prevents races against pm locking
* functions, races against module unload pm_unregister code. It does
* mean however that you must not issue pm_ functions within the callback
* or you will deadlock and users will hate you.
*
* Zero is returned on success. If a suspend fails then the status
* from the device that vetoes the suspend is returned.
*
* BUGS: what stops two power management requests occurring in parallel
* and conflicting.
*/
int pm_send_all(pm_request_t rqst, void *data)
{
struct list_head *entry;
mutex_lock(&pm_devs_lock);
entry = pm_devs.next;
while (entry != &pm_devs) {
struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
if (dev->callback) {
int status = pm_send(dev, rqst, data);
if (status) {
/* return devices to previous state on
* failed suspend request
*/
if (rqst == PM_SUSPEND)
pm_undo_all(dev);
mutex_unlock(&pm_devs_lock);
return status;
}
}
entry = entry->next;
}
mutex_unlock(&pm_devs_lock);
return 0;
}
EXPORT_SYMBOL(pm_register);
EXPORT_SYMBOL(pm_send_all);

1
kernel/profile.c
查看文件

@@ -23,7 +23,6 @@
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <asm/sections.h>
#include <asm/semaphore.h>
#include <asm/irq_regs.h>
#include <asm/ptrace.h>

55
kernel/ptrace.c
查看文件

@@ -323,9 +323,8 @@ static int ptrace_setoptions(struct task_struct *child, long data)
return (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
}
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t __user * data)
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
{
siginfo_t lastinfo;
int error = -ESRCH;
read_lock(&tasklist_lock);
@@ -333,31 +332,25 @@ static int ptrace_getsiginfo(struct task_struct *child, siginfo_t __user * data)
error = -EINVAL;
spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
lastinfo = *child->last_siginfo;
*info = *child->last_siginfo;
error = 0;
}
spin_unlock_irq(&child->sighand->siglock);
}
read_unlock(&tasklist_lock);
if (!error)
return copy_siginfo_to_user(data, &lastinfo);
return error;
}
static int ptrace_setsiginfo(struct task_struct *child, siginfo_t __user * data)
static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
{
siginfo_t newinfo;
int error = -ESRCH;
if (copy_from_user(&newinfo, data, sizeof (siginfo_t)))
return -EFAULT;
read_lock(&tasklist_lock);
if (likely(child->sighand != NULL)) {
error = -EINVAL;
spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
*child->last_siginfo = newinfo;
*child->last_siginfo = *info;
error = 0;
}
spin_unlock_irq(&child->sighand->siglock);
@@ -424,6 +417,7 @@ int ptrace_request(struct task_struct *child, long request,
long addr, long data)
{
int ret = -EIO;
siginfo_t siginfo;
switch (request) {
case PTRACE_PEEKTEXT:
@@ -442,12 +436,22 @@ int ptrace_request(struct task_struct *child, long request,
case PTRACE_GETEVENTMSG:
ret = put_user(child->ptrace_message, (unsigned long __user *) data);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, (siginfo_t __user *) data);
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
ret = copy_siginfo_to_user((siginfo_t __user *) data,
&siginfo);
break;
case PTRACE_SETSIGINFO:
ret = ptrace_setsiginfo(child, (siginfo_t __user *) data);
if (copy_from_user(&siginfo, (siginfo_t __user *) data,
sizeof siginfo))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
break;
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
@@ -608,7 +612,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data)
return (copied == sizeof(data)) ? 0 : -EIO;
}
#ifdef CONFIG_COMPAT
#if defined CONFIG_COMPAT && defined __ARCH_WANT_COMPAT_SYS_PTRACE
#include <linux/compat.h>
int compat_ptrace_request(struct task_struct *child, compat_long_t request,
@@ -616,6 +620,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
{
compat_ulong_t __user *datap = compat_ptr(data);
compat_ulong_t word;
siginfo_t siginfo;
int ret;
switch (request) {
@@ -638,6 +643,23 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
ret = put_user((compat_ulong_t) child->ptrace_message, datap);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
ret = copy_siginfo_to_user32(
(struct compat_siginfo __user *) datap,
&siginfo);
break;
case PTRACE_SETSIGINFO:
memset(&siginfo, 0, sizeof siginfo);
if (copy_siginfo_from_user32(
&siginfo, (struct compat_siginfo __user *) datap))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
break;
default:
ret = ptrace_request(child, request, addr, data);
}
@@ -645,7 +667,6 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
return ret;
}
#ifdef __ARCH_WANT_COMPAT_SYS_PTRACE
asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
compat_long_t addr, compat_long_t data)
{
@@ -688,6 +709,4 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
unlock_kernel();
return ret;
}
#endif /* __ARCH_WANT_COMPAT_SYS_PTRACE */
#endif /* CONFIG_COMPAT */
#endif /* CONFIG_COMPAT && __ARCH_WANT_COMPAT_SYS_PTRACE */

4
kernel/rcupreempt.c
查看文件

@@ -1007,10 +1007,10 @@ void __synchronize_sched(void)
if (sched_getaffinity(0, &oldmask) < 0)
oldmask = cpu_possible_map;
for_each_online_cpu(cpu) {
sched_setaffinity(0, cpumask_of_cpu(cpu));
sched_setaffinity(0, &cpumask_of_cpu(cpu));
schedule();
}
sched_setaffinity(0, oldmask);
sched_setaffinity(0, &oldmask);
}
EXPORT_SYMBOL_GPL(__synchronize_sched);

15
kernel/rcutorture.c
查看文件

@@ -723,9 +723,10 @@ static int rcu_idle_cpu; /* Force all torture tasks off this CPU */
*/
static void rcu_torture_shuffle_tasks(void)
{
cpumask_t tmp_mask = CPU_MASK_ALL;
cpumask_t tmp_mask;
int i;
cpus_setall(tmp_mask);
get_online_cpus();
/* No point in shuffling if there is only one online CPU (ex: UP) */
@@ -737,25 +738,27 @@ static void rcu_torture_shuffle_tasks(void)
if (rcu_idle_cpu != -1)
cpu_clear(rcu_idle_cpu, tmp_mask);
set_cpus_allowed(current, tmp_mask);
set_cpus_allowed_ptr(current, &tmp_mask);
if (reader_tasks) {
for (i = 0; i < nrealreaders; i++)
if (reader_tasks[i])
set_cpus_allowed(reader_tasks[i], tmp_mask);
set_cpus_allowed_ptr(reader_tasks[i],
&tmp_mask);
}
if (fakewriter_tasks) {
for (i = 0; i < nfakewriters; i++)
if (fakewriter_tasks[i])
set_cpus_allowed(fakewriter_tasks[i], tmp_mask);
set_cpus_allowed_ptr(fakewriter_tasks[i],
&tmp_mask);
}
if (writer_task)
set_cpus_allowed(writer_task, tmp_mask);
set_cpus_allowed_ptr(writer_task, &tmp_mask);
if (stats_task)
set_cpus_allowed(stats_task, tmp_mask);
set_cpus_allowed_ptr(stats_task, &tmp_mask);
if (rcu_idle_cpu == -1)
rcu_idle_cpu = num_online_cpus() - 1;

18
kernel/resource.c
查看文件

@@ -486,6 +486,24 @@ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t
EXPORT_SYMBOL(adjust_resource);
/**
* resource_alignment - calculate resource's alignment
* @res: resource pointer
*
* Returns alignment on success, 0 (invalid alignment) on failure.
*/
resource_size_t resource_alignment(struct resource *res)
{
switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
case IORESOURCE_SIZEALIGN:
return res->end - res->start + 1;
case IORESOURCE_STARTALIGN:
return res->start;
default:
return 0;
}
}
/*
* This is compatibility stuff for IO resources.
*

1867
kernel/sched.c
查看文件

文件差异内容过多而无法显示 加载差异

36
kernel/sched_debug.c
查看文件

@@ -67,14 +67,24 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
(long long)(p->nvcsw + p->nivcsw),
p->prio);
#ifdef CONFIG_SCHEDSTATS
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld\n",
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
SPLIT_NS(p->se.vruntime),
SPLIT_NS(p->se.sum_exec_runtime),
SPLIT_NS(p->se.sum_sleep_runtime));
#else
SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld\n",
SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
#endif
#ifdef CONFIG_CGROUP_SCHED
{
char path[64];
cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
SEQ_printf(m, " %s", path);
}
#endif
SEQ_printf(m, "\n");
}
static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
@@ -109,7 +119,21 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
struct sched_entity *last;
unsigned long flags;
SEQ_printf(m, "\ncfs_rq\n");
#if !defined(CONFIG_CGROUP_SCHED) || !defined(CONFIG_USER_SCHED)
SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
#else
char path[128] = "";
struct cgroup *cgroup = NULL;
struct task_group *tg = cfs_rq->tg;
if (tg)
cgroup = tg->css.cgroup;
if (cgroup)
cgroup_path(cgroup, path, sizeof(path));
SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
#endif
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
SPLIT_NS(cfs_rq->exec_clock));
@@ -143,6 +167,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
#endif
SEQ_printf(m, " .%-30s: %ld\n", "nr_spread_over",
cfs_rq->nr_spread_over);
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares);
#endif
#endif
}
static void print_cpu(struct seq_file *m, int cpu)
@@ -214,7 +243,6 @@ static int sched_debug_show(struct seq_file *m, void *v)
PN(sysctl_sched_latency);
PN(sysctl_sched_min_granularity);
PN(sysctl_sched_wakeup_granularity);
PN(sysctl_sched_batch_wakeup_granularity);
PN(sysctl_sched_child_runs_first);
P(sysctl_sched_features);
#undef PN

598
kernel/sched_fair.c
查看文件

@@ -62,24 +62,14 @@ const_debug unsigned int sysctl_sched_child_runs_first = 1;
unsigned int __read_mostly sysctl_sched_compat_yield;
/*
* SCHED_BATCH wake-up granularity.
* SCHED_OTHER wake-up granularity.
* (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
/*
* SCHED_OTHER wake-up granularity.
* (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
@@ -87,6 +77,11 @@ const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
* CFS operations on generic schedulable entities:
*/
static inline struct task_struct *task_of(struct sched_entity *se)
{
return container_of(se, struct task_struct, se);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
@@ -98,6 +93,54 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return p->se.cfs_rq;
}
/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
return se->cfs_rq;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
* another cpu ('this_cpu')
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
return 1;
return 0;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return se->parent;
}
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
@@ -107,13 +150,49 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
#define entity_is_task(se) 1
#endif /* CONFIG_FAIR_GROUP_SCHED */
#define for_each_sched_entity(se) \
for (; se; se = NULL)
static inline struct task_struct *task_of(struct sched_entity *se)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return container_of(se, struct task_struct, se);
return &task_rq(p)->cfs;
}
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return NULL;
}
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return &cpu_rq(this_cpu)->cfs;
}
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
return 1;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
/**************************************************************
* Scheduling class tree data structure manipulation methods:
@@ -254,6 +333,34 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
}
#endif
/*
* delta *= w / rw
*/
static inline unsigned long
calc_delta_weight(unsigned long delta, struct sched_entity *se)
{
for_each_sched_entity(se) {
delta = calc_delta_mine(delta,
se->load.weight, &cfs_rq_of(se)->load);
}
return delta;
}
/*
* delta *= rw / w
*/
static inline unsigned long
calc_delta_fair(unsigned long delta, struct sched_entity *se)
{
for_each_sched_entity(se) {
delta = calc_delta_mine(delta,
cfs_rq_of(se)->load.weight, &se->load);
}
return delta;
}
/*
* The idea is to set a period in which each task runs once.
*
@@ -283,29 +390,54 @@ static u64 __sched_period(unsigned long nr_running)
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return calc_delta_mine(__sched_period(cfs_rq->nr_running),
se->load.weight, &cfs_rq->load);
return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
}
/*
* We calculate the vruntime slice.
* We calculate the vruntime slice of a to be inserted task
*
* vs = s/w = p/rw
* vs = s*rw/w = p
*/
static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
{
u64 vslice = __sched_period(nr_running);
vslice *= NICE_0_LOAD;
do_div(vslice, rq_weight);
return vslice;
}
static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return __sched_vslice(cfs_rq->load.weight + se->load.weight,
cfs_rq->nr_running + 1);
unsigned long nr_running = cfs_rq->nr_running;
if (!se->on_rq)
nr_running++;
return __sched_period(nr_running);
}
/*
* The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
* that it favours >=0 over <0.
*
* -20 |
* |
* 0 --------+-------
* .'
* 19 .'
*
*/
static unsigned long
calc_delta_asym(unsigned long delta, struct sched_entity *se)
{
struct load_weight lw = {
.weight = NICE_0_LOAD,
.inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
};
for_each_sched_entity(se) {
struct load_weight *se_lw = &se->load;
if (se->load.weight < NICE_0_LOAD)
se_lw = &lw;
delta = calc_delta_mine(delta,
cfs_rq_of(se)->load.weight, se_lw);
}
return delta;
}
/*
@@ -322,11 +454,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
delta_exec_weighted = delta_exec;
if (unlikely(curr->load.weight != NICE_0_LOAD)) {
delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
&curr->load);
}
delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
}
@@ -413,20 +541,43 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
* Scheduling class queueing methods:
*/
#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
static void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
cfs_rq->task_weight += weight;
}
#else
static inline void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
}
#endif
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
inc_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se))
add_cfs_task_weight(cfs_rq, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
list_add(&se->group_node, &cfs_rq->tasks);
}
static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
dec_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se))
add_cfs_task_weight(cfs_rq, -se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
list_del_init(&se->group_node);
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -510,8 +661,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
if (!initial) {
/* sleeps upto a single latency don't count. */
if (sched_feat(NEW_FAIR_SLEEPERS))
vruntime -= sysctl_sched_latency;
if (sched_feat(NEW_FAIR_SLEEPERS)) {
if (sched_feat(NORMALIZED_SLEEPER))
vruntime -= calc_delta_weight(sysctl_sched_latency, se);
else
vruntime -= sysctl_sched_latency;
}
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
@@ -627,20 +782,16 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *
pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
s64 diff, gran;
if (!cfs_rq->next)
return se;
diff = cfs_rq->next->vruntime - se->vruntime;
if (diff < 0)
return se;
gran = calc_delta_fair(sysctl_sched_wakeup_granularity, &cfs_rq->load);
if (diff > gran)
if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
return se;
return cfs_rq->next;
@@ -708,101 +859,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
* CFS operations on tasks:
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return p->se.cfs_rq;
}
/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
return se->cfs_rq;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
* another cpu ('this_cpu')
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
return 1;
return 0;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return se->parent;
}
#else /* CONFIG_FAIR_GROUP_SCHED */
#define for_each_sched_entity(se) \
for (; se; se = NULL)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return &task_rq(p)->cfs;
}
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return NULL;
}
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return &cpu_rq(this_cpu)->cfs;
}
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
return 1;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
@@ -916,7 +972,7 @@ static void yield_task_fair(struct rq *rq)
/*
* Already in the rightmost position?
*/
if (unlikely(rightmost->vruntime < se->vruntime))
if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
return;
/*
@@ -955,7 +1011,9 @@ static int wake_idle(int cpu, struct task_struct *p)
return cpu;
for_each_domain(cpu, sd) {
if (sd->flags & SD_WAKE_IDLE) {
if ((sd->flags & SD_WAKE_IDLE)
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
if (idle_cpu(i)) {
@@ -1099,6 +1157,58 @@ out:
}
#endif /* CONFIG_SMP */
static unsigned long wakeup_gran(struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
/*
* More easily preempt - nice tasks, while not making it harder for
* + nice tasks.
*/
gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
return gran;
}
/*
* Should 'se' preempt 'curr'.
*
* |s1
* |s2
* |s3
* g
* |<--->|c
*
* w(c, s1) = -1
* w(c, s2) = 0
* w(c, s3) = 1
*
*/
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
{
s64 gran, vdiff = curr->vruntime - se->vruntime;
if (vdiff < 0)
return -1;
gran = wakeup_gran(curr);
if (vdiff > gran)
return 1;
return 0;
}
/* return depth at which a sched entity is present in the hierarchy */
static inline int depth_se(struct sched_entity *se)
{
int depth = 0;
for_each_sched_entity(se)
depth++;
return depth;
}
/*
* Preempt the current task with a newly woken task if needed:
@@ -1108,7 +1218,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
unsigned long gran;
int se_depth, pse_depth;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
@@ -1133,20 +1243,33 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
if (!sched_feat(WAKEUP_PREEMPT))
return;
/*
* preemption test can be made between sibling entities who are in the
* same cfs_rq i.e who have a common parent. Walk up the hierarchy of
* both tasks until we find their ancestors who are siblings of common
* parent.
*/
/* First walk up until both entities are at same depth */
se_depth = depth_se(se);
pse_depth = depth_se(pse);
while (se_depth > pse_depth) {
se_depth--;
se = parent_entity(se);
}
while (pse_depth > se_depth) {
pse_depth--;
pse = parent_entity(pse);
}
while (!is_same_group(se, pse)) {
se = parent_entity(se);
pse = parent_entity(pse);
}
gran = sysctl_sched_wakeup_granularity;
/*
* More easily preempt - nice tasks, while not making
* it harder for + nice tasks.
*/
if (unlikely(se->load.weight > NICE_0_LOAD))
gran = calc_delta_fair(gran, &se->load);
if (pse->vruntime + gran < se->vruntime)
if (wakeup_preempt_entity(se, pse) == 1)
resched_task(curr);
}
@@ -1197,15 +1320,27 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
* the current task:
*/
static struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
struct task_struct *p;
struct task_struct *p = NULL;
struct sched_entity *se;
if (!curr)
if (next == &cfs_rq->tasks)
return NULL;
p = rb_entry(curr, struct task_struct, se.run_node);
cfs_rq->rb_load_balance_curr = rb_next(curr);
/* Skip over entities that are not tasks */
do {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
} while (next != &cfs_rq->tasks && !entity_is_task(se));
if (next == &cfs_rq->tasks)
return NULL;
cfs_rq->balance_iterator = next;
if (entity_is_task(se))
p = task_of(se);
return p;
}
@@ -1214,85 +1349,100 @@ static struct task_struct *load_balance_start_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}
static struct task_struct *load_balance_next_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
static unsigned long
__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move, struct sched_domain *sd,
enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
struct cfs_rq *cfs_rq)
{
struct rq_iterator cfs_rq_iterator;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
cfs_rq_iterator.arg = cfs_rq;
return balance_tasks(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &cfs_rq_iterator);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr;
struct task_struct *p;
if (!cfs_rq->nr_running || !first_fair(cfs_rq))
return MAX_PRIO;
curr = cfs_rq->curr;
if (!curr)
curr = __pick_next_entity(cfs_rq);
p = task_of(curr);
return p->prio;
}
#endif
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
struct cfs_rq *busy_cfs_rq;
long rem_load_move = max_load_move;
struct rq_iterator cfs_rq_iterator;
int busiest_cpu = cpu_of(busiest);
struct task_group *tg;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
#ifdef CONFIG_FAIR_GROUP_SCHED
struct cfs_rq *this_cfs_rq;
rcu_read_lock();
list_for_each_entry(tg, &task_groups, list) {
long imbalance;
unsigned long maxload;
unsigned long this_weight, busiest_weight;
long rem_load, max_load, moved_load;
this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
if (imbalance <= 0)
/*
* empty group
*/
if (!aggregate(tg, sd)->task_weight)
continue;
/* Don't pull more than imbalance/2 */
imbalance /= 2;
maxload = min(rem_load_move, imbalance);
rem_load = rem_load_move * aggregate(tg, sd)->rq_weight;
rem_load /= aggregate(tg, sd)->load + 1;
*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
#else
# define maxload rem_load_move
#endif
/*
* pass busy_cfs_rq argument into
* load_balance_[start|next]_fair iterators
*/
cfs_rq_iterator.arg = busy_cfs_rq;
rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
maxload, sd, idle, all_pinned,
this_best_prio,
&cfs_rq_iterator);
this_weight = tg->cfs_rq[this_cpu]->task_weight;
busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight;
if (rem_load_move <= 0)
imbalance = (busiest_weight - this_weight) / 2;
if (imbalance < 0)
imbalance = busiest_weight;
max_load = max(rem_load, imbalance);
moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
max_load, sd, idle, all_pinned, this_best_prio,
tg->cfs_rq[busiest_cpu]);
if (!moved_load)
continue;
move_group_shares(tg, sd, busiest_cpu, this_cpu);
moved_load *= aggregate(tg, sd)->load;
moved_load /= aggregate(tg, sd)->rq_weight + 1;
rem_load_move -= moved_load;
if (rem_load_move < 0)
break;
}
rcu_read_unlock();
return max_load_move - rem_load_move;
}
#else
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
return __load_balance_fair(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &busiest->cfs);
}
#endif
static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
@@ -1461,16 +1611,40 @@ static const struct sched_class fair_sched_class = {
};
#ifdef CONFIG_SCHED_DEBUG
static void
print_cfs_rq_tasks(struct seq_file *m, struct cfs_rq *cfs_rq, int depth)
{
struct sched_entity *se;
if (!cfs_rq)
return;
list_for_each_entry_rcu(se, &cfs_rq->tasks, group_node) {
int i;
for (i = depth; i; i--)
seq_puts(m, " ");
seq_printf(m, "%lu %s %lu\n",
se->load.weight,
entity_is_task(se) ? "T" : "G",
calc_delta_weight(SCHED_LOAD_SCALE, se)
);
if (!entity_is_task(se))
print_cfs_rq_tasks(m, group_cfs_rq(se), depth + 1);
}
}
static void print_cfs_stats(struct seq_file *m, int cpu)
{
struct cfs_rq *cfs_rq;
#ifdef CONFIG_FAIR_GROUP_SCHED
print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
#endif
rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
seq_printf(m, "\nWeight tree:\n");
print_cfs_rq_tasks(m, &cpu_rq(cpu)->cfs, 1);
rcu_read_unlock();
}
#endif

10
kernel/sched_features.h 普通文件
查看文件

@@ -0,0 +1,10 @@
SCHED_FEAT(NEW_FAIR_SLEEPERS, 1)
SCHED_FEAT(WAKEUP_PREEMPT, 1)
SCHED_FEAT(START_DEBIT, 1)
SCHED_FEAT(AFFINE_WAKEUPS, 1)
SCHED_FEAT(CACHE_HOT_BUDDY, 1)
SCHED_FEAT(SYNC_WAKEUPS, 1)
SCHED_FEAT(HRTICK, 1)
SCHED_FEAT(DOUBLE_TICK, 0)
SCHED_FEAT(NORMALIZED_SLEEPER, 1)
SCHED_FEAT(DEADLINE, 1)

227
kernel/sched_rt.c
查看文件

@@ -62,7 +62,12 @@ static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
if (!rt_rq->tg)
return RUNTIME_INF;
return rt_rq->tg->rt_runtime;
return rt_rq->rt_runtime;
}
static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}
#define for_each_leaf_rt_rq(rt_rq, rq) \
@@ -127,14 +132,39 @@ static int rt_se_boosted(struct sched_rt_entity *rt_se)
return p->prio != p->normal_prio;
}
#ifdef CONFIG_SMP
static inline cpumask_t sched_rt_period_mask(void)
{
return cpu_rq(smp_processor_id())->rd->span;
}
#else
static inline cpumask_t sched_rt_period_mask(void)
{
return cpu_online_map;
}
#endif
static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu];
}
static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
return &rt_rq->tg->rt_bandwidth;
}
#else
static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
if (sysctl_sched_rt_runtime == -1)
return RUNTIME_INF;
return rt_rq->rt_runtime;
}
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
return ktime_to_ns(def_rt_bandwidth.rt_period);
}
#define for_each_leaf_rt_rq(rt_rq, rq) \
@@ -173,6 +203,102 @@ static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
return rt_rq->rt_throttled;
}
static inline cpumask_t sched_rt_period_mask(void)
{
return cpu_online_map;
}
static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
return &cpu_rq(cpu)->rt;
}
static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
return &def_rt_bandwidth;
}
#endif
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
{
int i, idle = 1;
cpumask_t span;
if (rt_b->rt_runtime == RUNTIME_INF)
return 1;
span = sched_rt_period_mask();
for_each_cpu_mask(i, span) {
int enqueue = 0;
struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
struct rq *rq = rq_of_rt_rq(rt_rq);
spin_lock(&rq->lock);
if (rt_rq->rt_time) {
u64 runtime;
spin_lock(&rt_rq->rt_runtime_lock);
runtime = rt_rq->rt_runtime;
rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
rt_rq->rt_throttled = 0;
enqueue = 1;
}
if (rt_rq->rt_time || rt_rq->rt_nr_running)
idle = 0;
spin_unlock(&rt_rq->rt_runtime_lock);
}
if (enqueue)
sched_rt_rq_enqueue(rt_rq);
spin_unlock(&rq->lock);
}
return idle;
}
#ifdef CONFIG_SMP
static int balance_runtime(struct rt_rq *rt_rq)
{
struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
int i, weight, more = 0;
u64 rt_period;
weight = cpus_weight(rd->span);
spin_lock(&rt_b->rt_runtime_lock);
rt_period = ktime_to_ns(rt_b->rt_period);
for_each_cpu_mask(i, rd->span) {
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
s64 diff;
if (iter == rt_rq)
continue;
spin_lock(&iter->rt_runtime_lock);
diff = iter->rt_runtime - iter->rt_time;
if (diff > 0) {
do_div(diff, weight);
if (rt_rq->rt_runtime + diff > rt_period)
diff = rt_period - rt_rq->rt_runtime;
iter->rt_runtime -= diff;
rt_rq->rt_runtime += diff;
more = 1;
if (rt_rq->rt_runtime == rt_period) {
spin_unlock(&iter->rt_runtime_lock);
break;
}
}
spin_unlock(&iter->rt_runtime_lock);
}
spin_unlock(&rt_b->rt_runtime_lock);
return more;
}
#endif
static inline int rt_se_prio(struct sched_rt_entity *rt_se)
@@ -197,12 +323,24 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
if (rt_rq->rt_throttled)
return rt_rq_throttled(rt_rq);
if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
return 0;
#ifdef CONFIG_SMP
if (rt_rq->rt_time > runtime) {
struct rq *rq = rq_of_rt_rq(rt_rq);
int more;
rq->rt_throttled = 1;
spin_unlock(&rt_rq->rt_runtime_lock);
more = balance_runtime(rt_rq);
spin_lock(&rt_rq->rt_runtime_lock);
if (more)
runtime = sched_rt_runtime(rt_rq);
}
#endif
if (rt_rq->rt_time > runtime) {
rt_rq->rt_throttled = 1;
if (rt_rq_throttled(rt_rq)) {
sched_rt_rq_dequeue(rt_rq);
return 1;
@@ -212,29 +350,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
return 0;
}
static void update_sched_rt_period(struct rq *rq)
{
struct rt_rq *rt_rq;
u64 period;
while (rq->clock > rq->rt_period_expire) {
period = (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
rq->rt_period_expire += period;
for_each_leaf_rt_rq(rt_rq, rq) {
u64 runtime = sched_rt_runtime(rt_rq);
rt_rq->rt_time -= min(rt_rq->rt_time, runtime);
if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
rt_rq->rt_throttled = 0;
sched_rt_rq_enqueue(rt_rq);
}
}
rq->rt_throttled = 0;
}
}
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
@@ -259,9 +374,15 @@ static void update_curr_rt(struct rq *rq)
curr->se.exec_start = rq->clock;
cpuacct_charge(curr, delta_exec);
rt_rq->rt_time += delta_exec;
if (sched_rt_runtime_exceeded(rt_rq))
resched_task(curr);
for_each_sched_rt_entity(rt_se) {
rt_rq = rt_rq_of_se(rt_se);
spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_time += delta_exec;
if (sched_rt_runtime_exceeded(rt_rq))
resched_task(curr);
spin_unlock(&rt_rq->rt_runtime_lock);
}
}
static inline
@@ -284,6 +405,11 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
#ifdef CONFIG_RT_GROUP_SCHED
if (rt_se_boosted(rt_se))
rt_rq->rt_nr_boosted++;
if (rt_rq->tg)
start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
#else
start_rt_bandwidth(&def_rt_bandwidth);
#endif
}
@@ -353,27 +479,21 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
/*
* Because the prio of an upper entry depends on the lower
* entries, we must remove entries top - down.
*
* XXX: O(1/2 h^2) because we can only walk up, not down the chain.
* doesn't matter much for now, as h=2 for GROUP_SCHED.
*/
static void dequeue_rt_stack(struct task_struct *p)
{
struct sched_rt_entity *rt_se, *top_se;
struct sched_rt_entity *rt_se, *back = NULL;
/*
* dequeue all, top - down.
*/
do {
rt_se = &p->rt;
top_se = NULL;
for_each_sched_rt_entity(rt_se) {
if (on_rt_rq(rt_se))
top_se = rt_se;
}
if (top_se)
dequeue_rt_entity(top_se);
} while (top_se);
rt_se = &p->rt;
for_each_sched_rt_entity(rt_se) {
rt_se->back = back;
back = rt_se;
}
for (rt_se = back; rt_se; rt_se = rt_se->back) {
if (on_rt_rq(rt_se))
dequeue_rt_entity(rt_se);
}
}
/*
@@ -393,6 +513,8 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
*/
for_each_sched_rt_entity(rt_se)
enqueue_rt_entity(rt_se);
inc_cpu_load(rq, p->se.load.weight);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -412,6 +534,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
if (rt_rq && rt_rq->rt_nr_running)
enqueue_rt_entity(rt_se);
}
dec_cpu_load(rq, p->se.load.weight);
}
/*
@@ -1001,7 +1125,8 @@ move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
return 0;
}
static void set_cpus_allowed_rt(struct task_struct *p, cpumask_t *new_mask)
static void set_cpus_allowed_rt(struct task_struct *p,
const cpumask_t *new_mask)
{
int weight = cpus_weight(*new_mask);

8
kernel/sched_stats.h
查看文件

@@ -9,6 +9,11 @@
static int show_schedstat(struct seq_file *seq, void *v)
{
int cpu;
int mask_len = NR_CPUS/32 * 9;
char *mask_str = kmalloc(mask_len, GFP_KERNEL);
if (mask_str == NULL)
return -ENOMEM;
seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
seq_printf(seq, "timestamp %lu\n", jiffies);
@@ -36,9 +41,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
preempt_disable();
for_each_domain(cpu, sd) {
enum cpu_idle_type itype;
char mask_str[NR_CPUS];
cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
cpumask_scnprintf(mask_str, mask_len, sd->span);
seq_printf(seq, "domain%d %s", dcount++, mask_str);
for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
itype++) {

264
kernel/semaphore.c 普通文件
查看文件

@@ -0,0 +1,264 @@
/*
* Copyright (c) 2008 Intel Corporation
* Author: Matthew Wilcox <willy@linux.intel.com>
*
* Distributed under the terms of the GNU GPL, version 2
*
* This file implements counting semaphores.
* A counting semaphore may be acquired 'n' times before sleeping.
* See mutex.c for single-acquisition sleeping locks which enforce
* rules which allow code to be debugged more easily.
*/
/*
* Some notes on the implementation:
*
* The spinlock controls access to the other members of the semaphore.
* down_trylock() and up() can be called from interrupt context, so we
* have to disable interrupts when taking the lock. It turns out various
* parts of the kernel expect to be able to use down() on a semaphore in
* interrupt context when they know it will succeed, so we have to use
* irqsave variants for down(), down_interruptible() and down_killable()
* too.
*
* The ->count variable represents how many more tasks can acquire this
* semaphore. If it's zero, there may be tasks waiting on the wait_list.
*/
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/semaphore.h>
#include <linux/spinlock.h>
static noinline void __down(struct semaphore *sem);
static noinline int __down_interruptible(struct semaphore *sem);
static noinline int __down_killable(struct semaphore *sem);
static noinline int __down_timeout(struct semaphore *sem, long jiffies);
static noinline void __up(struct semaphore *sem);
/**
* down - acquire the semaphore
* @sem: the semaphore to be acquired
*
* Acquires the semaphore. If no more tasks are allowed to acquire the
* semaphore, calling this function will put the task to sleep until the
* semaphore is released.
*
* Use of this function is deprecated, please use down_interruptible() or
* down_killable() instead.
*/
void down(struct semaphore *sem)
{
unsigned long flags;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
__down(sem);
spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(down);
/**
* down_interruptible - acquire the semaphore unless interrupted
* @sem: the semaphore to be acquired
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the sleep is interrupted by a signal, this function will return -EINTR.
* If the semaphore is successfully acquired, this function returns 0.
*/
int down_interruptible(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_interruptible(sem);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_interruptible);
/**
* down_killable - acquire the semaphore unless killed
* @sem: the semaphore to be acquired
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the sleep is interrupted by a fatal signal, this function will return
* -EINTR. If the semaphore is successfully acquired, this function returns
* 0.
*/
int down_killable(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_killable(sem);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_killable);
/**
* down_trylock - try to acquire the semaphore, without waiting
* @sem: the semaphore to be acquired
*
* Try to acquire the semaphore atomically. Returns 0 if the mutex has
* been acquired successfully or 1 if it it cannot be acquired.
*
* NOTE: This return value is inverted from both spin_trylock and
* mutex_trylock! Be careful about this when converting code.
*
* Unlike mutex_trylock, this function can be used from interrupt context,
* and the semaphore can be released by any task or interrupt.
*/
int down_trylock(struct semaphore *sem)
{
unsigned long flags;
int count;
spin_lock_irqsave(&sem->lock, flags);
count = sem->count - 1;
if (likely(count >= 0))
sem->count = count;
spin_unlock_irqrestore(&sem->lock, flags);
return (count < 0);
}
EXPORT_SYMBOL(down_trylock);
/**
* down_timeout - acquire the semaphore within a specified time
* @sem: the semaphore to be acquired
* @jiffies: how long to wait before failing
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the semaphore is not released within the specified number of jiffies,
* this function returns -ETIME. It returns 0 if the semaphore was acquired.
*/
int down_timeout(struct semaphore *sem, long jiffies)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_timeout(sem, jiffies);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_timeout);
/**
* up - release the semaphore
* @sem: the semaphore to release
*
* Release the semaphore. Unlike mutexes, up() may be called from any
* context and even by tasks which have never called down().
*/
void up(struct semaphore *sem)
{
unsigned long flags;
spin_lock_irqsave(&sem->lock, flags);
if (likely(list_empty(&sem->wait_list)))
sem->count++;
else
__up(sem);
spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(up);
/* Functions for the contended case */
struct semaphore_waiter {
struct list_head list;
struct task_struct *task;
int up;
};
/*
* Because this function is inlined, the 'state' parameter will be
* constant, and thus optimised away by the compiler. Likewise the
* 'timeout' parameter for the cases without timeouts.
*/
static inline int __sched __down_common(struct semaphore *sem, long state,
long timeout)
{
struct task_struct *task = current;
struct semaphore_waiter waiter;
list_add_tail(&waiter.list, &sem->wait_list);
waiter.task = task;
waiter.up = 0;
for (;;) {
if (state == TASK_INTERRUPTIBLE && signal_pending(task))
goto interrupted;
if (state == TASK_KILLABLE && fatal_signal_pending(task))
goto interrupted;
if (timeout <= 0)
goto timed_out;
__set_task_state(task, state);
spin_unlock_irq(&sem->lock);
timeout = schedule_timeout(timeout);
spin_lock_irq(&sem->lock);
if (waiter.up)
return 0;
}
timed_out:
list_del(&waiter.list);
return -ETIME;
interrupted:
list_del(&waiter.list);
return -EINTR;
}
static noinline void __sched __down(struct semaphore *sem)
{
__down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_interruptible(struct semaphore *sem)
{
return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_killable(struct semaphore *sem)
{
return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies)
{
return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies);
}
static noinline void __sched __up(struct semaphore *sem)
{
struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
struct semaphore_waiter, list);
list_del(&waiter->list);
waiter->up = 1;
wake_up_process(waiter->task);
}

75
kernel/signal.c
查看文件

@@ -220,7 +220,7 @@ void flush_signals(struct task_struct *t)
unsigned long flags;
spin_lock_irqsave(&t->sighand->siglock, flags);
clear_tsk_thread_flag(t,TIF_SIGPENDING);
clear_tsk_thread_flag(t, TIF_SIGPENDING);
flush_sigqueue(&t->pending);
flush_sigqueue(&t->signal->shared_pending);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
@@ -424,7 +424,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
}
if (signr &&
((info->si_code & __SI_MASK) == __SI_TIMER) &&
info->si_sys_private){
info->si_sys_private) {
/*
* Release the siglock to ensure proper locking order
* of timer locks outside of siglocks. Note, we leave
@@ -1757,6 +1757,45 @@ static int do_signal_stop(int signr)
return 1;
}
static int ptrace_signal(int signr, siginfo_t *info,
struct pt_regs *regs, void *cookie)
{
if (!(current->ptrace & PT_PTRACED))
return signr;
ptrace_signal_deliver(regs, cookie);
/* Let the debugger run. */
ptrace_stop(signr, 0, info);
/* We're back. Did the debugger cancel the sig? */
signr = current->exit_code;
if (signr == 0)
return signr;
current->exit_code = 0;
/* Update the siginfo structure if the signal has
changed. If the debugger wanted something
specific in the siginfo structure then it should
have updated *info via PTRACE_SETSIGINFO. */
if (signr != info->si_signo) {
info->si_signo = signr;
info->si_errno = 0;
info->si_code = SI_USER;
info->si_pid = task_pid_vnr(current->parent);
info->si_uid = current->parent->uid;
}
/* If the (new) signal is now blocked, requeue it. */
if (sigismember(&current->blocked, signr)) {
specific_send_sig_info(signr, info, current);
signr = 0;
}
return signr;
}
int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
struct pt_regs *regs, void *cookie)
{
@@ -1785,36 +1824,10 @@ relock:
if (!signr)
break; /* will return 0 */
if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
ptrace_signal_deliver(regs, cookie);
/* Let the debugger run. */
ptrace_stop(signr, 0, info);
/* We're back. Did the debugger cancel the sig? */
signr = current->exit_code;
if (signr == 0)
if (signr != SIGKILL) {
signr = ptrace_signal(signr, info, regs, cookie);
if (!signr)
continue;
current->exit_code = 0;
/* Update the siginfo structure if the signal has
changed. If the debugger wanted something
specific in the siginfo structure then it should
have updated *info via PTRACE_SETSIGINFO. */
if (signr != info->si_signo) {
info->si_signo = signr;
info->si_errno = 0;
info->si_code = SI_USER;
info->si_pid = task_pid_vnr(current->parent);
info->si_uid = current->parent->uid;
}
/* If the (new) signal is now blocked, requeue it. */
if (sigismember(&current->blocked, signr)) {
specific_send_sig_info(signr, info, current);
continue;
}
}
ka = &current->sighand->action[signr-1];

63
kernel/softirq.c
查看文件

@@ -356,7 +356,8 @@ void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
/* Tasklets */
struct tasklet_head
{
struct tasklet_struct *list;
struct tasklet_struct *head;
struct tasklet_struct **tail;
};
/* Some compilers disobey section attribute on statics when not
@@ -369,8 +370,9 @@ void __tasklet_schedule(struct tasklet_struct *t)
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
t->next = NULL;
*__get_cpu_var(tasklet_vec).tail = t;
__get_cpu_var(tasklet_vec).tail = &(t->next);
raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_restore(flags);
}
@@ -382,8 +384,9 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
t->next = NULL;
*__get_cpu_var(tasklet_hi_vec).tail = t;
__get_cpu_var(tasklet_hi_vec).tail = &(t->next);
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_restore(flags);
}
@@ -395,8 +398,9 @@ static void tasklet_action(struct softirq_action *a)
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = NULL;
list = __get_cpu_var(tasklet_vec).head;
__get_cpu_var(tasklet_vec).head = NULL;
__get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head;
local_irq_enable();
while (list) {
@@ -416,8 +420,9 @@ static void tasklet_action(struct softirq_action *a)
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
t->next = NULL;
*__get_cpu_var(tasklet_vec).tail = t;
__get_cpu_var(tasklet_vec).tail = &(t->next);
__raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_enable();
}
@@ -428,8 +433,9 @@ static void tasklet_hi_action(struct softirq_action *a)
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = NULL;
list = __get_cpu_var(tasklet_hi_vec).head;
__get_cpu_var(tasklet_hi_vec).head = NULL;
__get_cpu_var(tasklet_hi_vec).tail = &__get_cpu_var(tasklet_hi_vec).head;
local_irq_enable();
while (list) {
@@ -449,8 +455,9 @@ static void tasklet_hi_action(struct softirq_action *a)
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
t->next = NULL;
*__get_cpu_var(tasklet_hi_vec).tail = t;
__get_cpu_var(tasklet_hi_vec).tail = &(t->next);
__raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
}
@@ -487,6 +494,15 @@ EXPORT_SYMBOL(tasklet_kill);
void __init softirq_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
per_cpu(tasklet_vec, cpu).tail =
&per_cpu(tasklet_vec, cpu).head;
per_cpu(tasklet_hi_vec, cpu).tail =
&per_cpu(tasklet_hi_vec, cpu).head;
}
open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
}
@@ -555,9 +571,12 @@ void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
return;
/* CPU is dead, so no lock needed. */
for (i = &per_cpu(tasklet_vec, cpu).list; *i; i = &(*i)->next) {
for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
if (*i == t) {
*i = t->next;
/* If this was the tail element, move the tail ptr */
if (*i == NULL)
per_cpu(tasklet_vec, cpu).tail = i;
return;
}
}
@@ -566,20 +585,20 @@ void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
static void takeover_tasklets(unsigned int cpu)
{
struct tasklet_struct **i;
/* CPU is dead, so no lock needed. */
local_irq_disable();
/* Find end, append list for that CPU. */
for (i = &__get_cpu_var(tasklet_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_vec, cpu).list;
per_cpu(tasklet_vec, cpu).list = NULL;
*__get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).head;
__get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).tail;
per_cpu(tasklet_vec, cpu).head = NULL;
per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
raise_softirq_irqoff(TASKLET_SOFTIRQ);
for (i = &__get_cpu_var(tasklet_hi_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_hi_vec, cpu).list;
per_cpu(tasklet_hi_vec, cpu).list = NULL;
*__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).head;
__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).tail;
per_cpu(tasklet_hi_vec, cpu).head = NULL;
per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();

6
kernel/stop_machine.c
查看文件

@@ -11,7 +11,6 @@
#include <linux/interrupt.h>
#include <asm/atomic.h>
#include <asm/semaphore.h>
#include <asm/uaccess.h>
/* Since we effect priority and affinity (both of which are visible
@@ -35,7 +34,7 @@ static int stopmachine(void *cpu)
int irqs_disabled = 0;
int prepared = 0;
set_cpus_allowed(current, cpumask_of_cpu((int)(long)cpu));
set_cpus_allowed_ptr(current, &cpumask_of_cpu((int)(long)cpu));
/* Ack: we are alive */
smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */
@@ -135,8 +134,7 @@ static void restart_machine(void)
preempt_enable_no_resched();
}
struct stop_machine_data
{
struct stop_machine_data {
int (*fn)(void *);
void *data;
struct completion done;

40
kernel/sys.c
查看文件

@@ -67,6 +67,12 @@
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef GET_TSC_CTL
# define GET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-EINVAL)
#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
@@ -1626,10 +1632,9 @@ asmlinkage long sys_umask(int mask)
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
long error;
long uninitialized_var(error);
error = security_task_prctl(option, arg2, arg3, arg4, arg5);
if (error)
if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
return error;
switch (option) {
@@ -1682,17 +1687,6 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
error = -EINVAL;
break;
case PR_GET_KEEPCAPS:
if (current->keep_capabilities)
error = 1;
break;
case PR_SET_KEEPCAPS:
if (arg2 != 0 && arg2 != 1) {
error = -EINVAL;
break;
}
current->keep_capabilities = arg2;
break;
case PR_SET_NAME: {
struct task_struct *me = current;
unsigned char ncomm[sizeof(me->comm)];
@@ -1726,18 +1720,12 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
case PR_SET_SECCOMP:
error = prctl_set_seccomp(arg2);
break;
case PR_CAPBSET_READ:
if (!cap_valid(arg2))
return -EINVAL;
return !!cap_raised(current->cap_bset, arg2);
case PR_CAPBSET_DROP:
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
return cap_prctl_drop(arg2);
#else
return -EINVAL;
#endif
case PR_GET_TSC:
error = GET_TSC_CTL(arg2);
break;
case PR_SET_TSC:
error = SET_TSC_CTL(arg2);
break;
default:
error = -EINVAL;
break;

15
kernel/sysctl.c
查看文件

@@ -268,17 +268,6 @@ static struct ctl_table kern_table[] = {
.extra1 = &min_wakeup_granularity_ns,
.extra2 = &max_wakeup_granularity_ns,
},
{
.ctl_name = CTL_UNNUMBERED,
.procname = "sched_batch_wakeup_granularity_ns",
.data = &sysctl_sched_batch_wakeup_granularity,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &min_wakeup_granularity_ns,
.extra2 = &max_wakeup_granularity_ns,
},
{
.ctl_name = CTL_UNNUMBERED,
.procname = "sched_child_runs_first",
@@ -318,7 +307,7 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_sched_rt_period,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec,
.proc_handler = &sched_rt_handler,
},
{
.ctl_name = CTL_UNNUMBERED,
@@ -326,7 +315,7 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_sched_rt_runtime,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec,
.proc_handler = &sched_rt_handler,
},
{
.ctl_name = CTL_UNNUMBERED,

1
kernel/time.c
查看文件

@@ -379,6 +379,7 @@ void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec)
ts->tv_sec = sec;
ts->tv_nsec = nsec;
}
EXPORT_SYMBOL(set_normalized_timespec);
/**
* ns_to_timespec - Convert nanoseconds to timespec

30
kernel/time/clocksource.c
查看文件

@@ -141,8 +141,16 @@ static void clocksource_watchdog(unsigned long data)
}
if (!list_empty(&watchdog_list)) {
__mod_timer(&watchdog_timer,
watchdog_timer.expires + WATCHDOG_INTERVAL);
/*
* Cycle through CPUs to check if the CPUs stay
* synchronized to each other.
*/
int next_cpu = next_cpu(raw_smp_processor_id(), cpu_online_map);
if (next_cpu >= NR_CPUS)
next_cpu = first_cpu(cpu_online_map);
watchdog_timer.expires += WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, next_cpu);
}
spin_unlock(&watchdog_lock);
}
@@ -164,7 +172,8 @@ static void clocksource_check_watchdog(struct clocksource *cs)
if (!started && watchdog) {
watchdog_last = watchdog->read();
watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
add_timer(&watchdog_timer);
add_timer_on(&watchdog_timer,
first_cpu(cpu_online_map));
}
} else {
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
@@ -185,7 +194,8 @@ static void clocksource_check_watchdog(struct clocksource *cs)
watchdog_last = watchdog->read();
watchdog_timer.expires =
jiffies + WATCHDOG_INTERVAL;
add_timer(&watchdog_timer);
add_timer_on(&watchdog_timer,
first_cpu(cpu_online_map));
}
}
}
@@ -221,6 +231,18 @@ void clocksource_resume(void)
spin_unlock_irqrestore(&clocksource_lock, flags);
}
/**
* clocksource_touch_watchdog - Update watchdog
*
* Update the watchdog after exception contexts such as kgdb so as not
* to incorrectly trip the watchdog.
*
*/
void clocksource_touch_watchdog(void)
{
clocksource_resume_watchdog();
}
/**
* clocksource_get_next - Returns the selected clocksource
*

4
kernel/time/tick-broadcast.c
查看文件

@@ -14,7 +14,7 @@
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
@@ -262,7 +262,7 @@ out:
void tick_broadcast_on_off(unsigned long reason, int *oncpu)
{
if (!cpu_isset(*oncpu, cpu_online_map))
printk(KERN_ERR "tick-braodcast: ignoring broadcast for "
printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
"offline CPU #%d\n", *oncpu);
else
smp_call_function_single(*oncpu, tick_do_broadcast_on_off,

4
kernel/time/tick-common.c
查看文件

@@ -14,12 +14,14 @@
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/tick.h>
#include <asm/irq_regs.h>
#include "tick-internal.h"
/*

2
kernel/time/tick-oneshot.c
查看文件

@@ -14,7 +14,7 @@
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>

12
kernel/time/tick-sched.c
查看文件

@@ -158,9 +158,8 @@ void tick_nohz_stop_idle(int cpu)
}
}
static ktime_t tick_nohz_start_idle(int cpu)
static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, delta;
now = ktime_get();
@@ -192,7 +191,6 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
void tick_nohz_stop_sched_tick(void)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
unsigned long rt_jiffies;
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
@@ -201,8 +199,8 @@ void tick_nohz_stop_sched_tick(void)
local_irq_save(flags);
cpu = smp_processor_id();
now = tick_nohz_start_idle(cpu);
ts = &per_cpu(tick_cpu_sched, cpu);
now = tick_nohz_start_idle(ts);
/*
* If this cpu is offline and it is the one which updates
@@ -222,7 +220,6 @@ void tick_nohz_stop_sched_tick(void)
if (need_resched())
goto end;
cpu = smp_processor_id();
if (unlikely(local_softirq_pending())) {
static int ratelimit;
@@ -245,10 +242,6 @@ void tick_nohz_stop_sched_tick(void)
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
rt_jiffies = rt_needs_cpu(cpu);
if (rt_jiffies && rt_jiffies < delta_jiffies)
delta_jiffies = rt_jiffies;
if (rcu_needs_cpu(cpu))
delta_jiffies = 1;
/*
@@ -400,6 +393,7 @@ void tick_nohz_restart_sched_tick(void)
sub_preempt_count(HARDIRQ_OFFSET);
}
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
*/

2
kernel/time/timekeeping.c
查看文件

@@ -178,6 +178,7 @@ static void change_clocksource(void)
if (clock == new)
return;
new->cycle_last = 0;
now = clocksource_read(new);
nsec = __get_nsec_offset();
timespec_add_ns(&xtime, nsec);
@@ -295,6 +296,7 @@ static int timekeeping_resume(struct sys_device *dev)
timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
update_xtime_cache(0);
/* re-base the last cycle value */
clock->cycle_last = 0;
clock->cycle_last = clocksource_read(clock);
clock->error = 0;
timekeeping_suspended = 0;

16
kernel/timer.c
查看文件

@@ -1228,13 +1228,6 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info)
return 0;
}
/*
* lockdep: we want to track each per-CPU base as a separate lock-class,
* but timer-bases are kmalloc()-ed, so we need to attach separate
* keys to them:
*/
static struct lock_class_key base_lock_keys[NR_CPUS];
static int __cpuinit init_timers_cpu(int cpu)
{
int j;
@@ -1277,7 +1270,6 @@ static int __cpuinit init_timers_cpu(int cpu)
}
spin_lock_init(&base->lock);
lockdep_set_class(&base->lock, base_lock_keys + cpu);
for (j = 0; j < TVN_SIZE; j++) {
INIT_LIST_HEAD(base->tv5.vec + j);
@@ -1316,8 +1308,8 @@ static void __cpuinit migrate_timers(int cpu)
new_base = get_cpu_var(tvec_bases);
local_irq_disable();
double_spin_lock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
spin_lock(&new_base->lock);
spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
BUG_ON(old_base->running_timer);
@@ -1330,8 +1322,8 @@ static void __cpuinit migrate_timers(int cpu)
migrate_timer_list(new_base, old_base->tv5.vec + i);
}
double_spin_unlock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
spin_unlock(&old_base->lock);
spin_unlock(&new_base->lock);
local_irq_enable();
put_cpu_var(tvec_bases);
}

30
kernel/user.c
查看文件

@@ -101,7 +101,7 @@ static int sched_create_user(struct user_struct *up)
{
int rc = 0;
up->tg = sched_create_group();
up->tg = sched_create_group(&root_task_group);
if (IS_ERR(up->tg))
rc = -ENOMEM;
@@ -193,6 +193,33 @@ static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
static struct kobj_attribute cpu_rt_runtime_attr =
__ATTR(cpu_rt_runtime, 0644, cpu_rt_runtime_show, cpu_rt_runtime_store);
static ssize_t cpu_rt_period_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
struct user_struct *up = container_of(kobj, struct user_struct, kobj);
return sprintf(buf, "%lu\n", sched_group_rt_period(up->tg));
}
static ssize_t cpu_rt_period_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t size)
{
struct user_struct *up = container_of(kobj, struct user_struct, kobj);
unsigned long rt_period;
int rc;
sscanf(buf, "%lu", &rt_period);
rc = sched_group_set_rt_period(up->tg, rt_period);
return (rc ? rc : size);
}
static struct kobj_attribute cpu_rt_period_attr =
__ATTR(cpu_rt_period, 0644, cpu_rt_period_show, cpu_rt_period_store);
#endif
/* default attributes per uid directory */
@@ -202,6 +229,7 @@ static struct attribute *uids_attributes[] = {
#endif
#ifdef CONFIG_RT_GROUP_SCHED
&cpu_rt_runtime_attr.attr,
&cpu_rt_period_attr.attr,
#endif
NULL
};

2
kernel/workqueue.c
查看文件

@@ -219,6 +219,7 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct timer_list *timer = &dwork->timer;
struct work_struct *work = &dwork->work;
timer_stats_timer_set_start_info(&dwork->timer);
if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
BUG_ON(timer_pending(timer));
BUG_ON(!list_empty(&work->entry));
@@ -580,6 +581,7 @@ EXPORT_SYMBOL(schedule_delayed_work);
int schedule_delayed_work_on(int cpu,
struct delayed_work *dwork, unsigned long delay)
{
timer_stats_timer_set_start_info(&dwork->timer);
return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);