A-Team_Digital_Solutions/android_kernel_motorola_sm6375
Watch
2
0
Fork
You've already forked android_kernel_motorola_sm6375
 0
mirror of https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git synced 2026-10-28 02:32:09 -04:00
Code Issues Projects Releases Packages Wiki Activity

Merge commit 'v2.6.31-rc6' into core/rcu

Browse source 
Merge reason: the branch was on pre-rc1 .30, update to latest.

Signed-off-by: Ingo Molnar <[email protected]>
This commit is contained in:
Ingo Molnar 2009-08-15 18:55:58 +02:00
commit fa08661af8
2538 changed files with 70259 additions and 36388 deletions
Download patch file Download diff file Expand all files Collapse all files

3
kernel/Makefile
View file

@ -69,7 +69,7 @@ obj-$(CONFIG_IKCONFIG) += configs.o
obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
obj-$(CONFIG_GCOV_KERNEL) += gcov/
obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
@ -95,6 +95,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_X86_DS) += trace/
obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o

6
kernel/acct.c
View file

@ -215,6 +215,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
static int acct_on(char *name)
{
struct file *file;
struct vfsmount *mnt;
int error;
struct pid_namespace *ns;
struct bsd_acct_struct *acct = NULL;
@ -256,11 +257,12 @@ static int acct_on(char *name)
acct = NULL;
}
mnt_pin(file->f_path.mnt);
mnt = file->f_path.mnt;
mnt_pin(mnt);
acct_file_reopen(ns->bacct, file, ns);
spin_unlock(&acct_lock);
mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
mntput(mnt); /* it's pinned, now give up active reference */
kfree(acct);
return 0;

146
kernel/audit.c
View file

@ -115,9 +115,6 @@ static atomic_t audit_lost = ATOMIC_INIT(0);
/* The netlink socket. */
static struct sock *audit_sock;
/* Inotify handle. */
struct inotify_handle *audit_ih;
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@ -136,7 +133,7 @@ static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
/* Serialize requests from userspace. */
static DEFINE_MUTEX(audit_cmd_mutex);
DEFINE_MUTEX(audit_cmd_mutex);
/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
* audit records. Since printk uses a 1024 byte buffer, this buffer
@ -375,6 +372,25 @@ static void audit_hold_skb(struct sk_buff *skb)
kfree_skb(skb);
}
/*
* For one reason or another this nlh isn't getting delivered to the userspace
* audit daemon, just send it to printk.
*/
static void audit_printk_skb(struct sk_buff *skb)
{
struct nlmsghdr *nlh = nlmsg_hdr(skb);
char *data = NLMSG_DATA(nlh);
if (nlh->nlmsg_type != AUDIT_EOE) {
if (printk_ratelimit())
printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, data);
else
audit_log_lost("printk limit exceeded\n");
}
audit_hold_skb(skb);
}
static void kauditd_send_skb(struct sk_buff *skb)
{
int err;
@ -427,14 +443,8 @@ static int kauditd_thread(void *dummy)
if (skb) {
if (audit_pid)
kauditd_send_skb(skb);
else {
if (printk_ratelimit())
printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0));
else
audit_log_lost("printk limit exceeded\n");
audit_hold_skb(skb);
}
else
audit_printk_skb(skb);
} else {
DECLARE_WAITQUEUE(wait, current);
set_current_state(TASK_INTERRUPTIBLE);
@ -495,42 +505,25 @@ int audit_send_list(void *_dest)
return 0;
}
#ifdef CONFIG_AUDIT_TREE
static int prune_tree_thread(void *unused)
{
mutex_lock(&audit_cmd_mutex);
audit_prune_trees();
mutex_unlock(&audit_cmd_mutex);
return 0;
}
void audit_schedule_prune(void)
{
kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
}
#endif
struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
int multi, void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
int len = NLMSG_SPACE(size);
void *data;
int flags = multi ? NLM_F_MULTI : 0;
int t = done ? NLMSG_DONE : type;
skb = alloc_skb(len, GFP_KERNEL);
skb = nlmsg_new(size, GFP_KERNEL);
if (!skb)
return NULL;
nlh = NLMSG_PUT(skb, pid, seq, t, size);
nlh->nlmsg_flags = flags;
data = NLMSG_DATA(nlh);
nlh = NLMSG_NEW(skb, pid, seq, t, size, flags);
data = NLMSG_DATA(nlh);
memcpy(data, payload, size);
return skb;
nlmsg_failure: /* Used by NLMSG_PUT */
nlmsg_failure: /* Used by NLMSG_NEW */
if (skb)
kfree_skb(skb);
return NULL;
@ -926,28 +919,29 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
}
/*
* Get message from skb (based on rtnetlink_rcv_skb). Each message is
* processed by audit_receive_msg. Malformed skbs with wrong length are
* discarded silently.
* Get message from skb. Each message is processed by audit_receive_msg.
* Malformed skbs with wrong length are discarded silently.
*/
static void audit_receive_skb(struct sk_buff *skb)
{
int err;
struct nlmsghdr *nlh;
u32 rlen;
struct nlmsghdr *nlh;
/*
* len MUST be signed for NLMSG_NEXT to be able to dec it below 0
* if the nlmsg_len was not aligned
*/
int len;
int err;
while (skb->len >= NLMSG_SPACE(0)) {
nlh = nlmsg_hdr(skb);
if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
return;
rlen = NLMSG_ALIGN(nlh->nlmsg_len);
if (rlen > skb->len)
rlen = skb->len;
if ((err = audit_receive_msg(skb, nlh))) {
nlh = nlmsg_hdr(skb);
len = skb->len;
while (NLMSG_OK(nlh, len)) {
err = audit_receive_msg(skb, nlh);
/* if err or if this message says it wants a response */
if (err || (nlh->nlmsg_flags & NLM_F_ACK))
netlink_ack(skb, nlh, err);
} else if (nlh->nlmsg_flags & NLM_F_ACK)
netlink_ack(skb, nlh, 0);
skb_pull(skb, rlen);
nlh = NLMSG_NEXT(nlh, len);
}
}
@ -959,13 +953,6 @@ static void audit_receive(struct sk_buff *skb)
mutex_unlock(&audit_cmd_mutex);
}
#ifdef CONFIG_AUDITSYSCALL
static const struct inotify_operations audit_inotify_ops = {
.handle_event = audit_handle_ievent,
.destroy_watch = audit_free_parent,
};
#endif
/* Initialize audit support at boot time. */
static int __init audit_init(void)
{
@ -991,12 +978,6 @@ static int __init audit_init(void)
audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
#ifdef CONFIG_AUDITSYSCALL
audit_ih = inotify_init(&audit_inotify_ops);
if (IS_ERR(audit_ih))
audit_panic("cannot initialize inotify handle");
#endif
for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
INIT_LIST_HEAD(&audit_inode_hash[i]);
@ -1070,18 +1051,20 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
goto err;
}
ab->skb = alloc_skb(AUDIT_BUFSIZ, gfp_mask);
if (!ab->skb)
goto err;
ab->ctx = ctx;
ab->gfp_mask = gfp_mask;
nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0));
nlh->nlmsg_type = type;
nlh->nlmsg_flags = 0;
nlh->nlmsg_pid = 0;
nlh->nlmsg_seq = 0;
ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask);
if (!ab->skb)
goto nlmsg_failure;
nlh = NLMSG_NEW(ab->skb, 0, 0, type, 0, 0);
return ab;
nlmsg_failure: /* Used by NLMSG_NEW */
kfree_skb(ab->skb);
ab->skb = NULL;
err:
audit_buffer_free(ab);
return NULL;
@ -1452,6 +1435,15 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
kfree(pathname);
}
void audit_log_key(struct audit_buffer *ab, char *key)
{
audit_log_format(ab, " key=");
if (key)
audit_log_untrustedstring(ab, key);
else
audit_log_format(ab, "(null)");
}
/**
* audit_log_end - end one audit record
* @ab: the audit_buffer
@ -1475,15 +1467,7 @@ void audit_log_end(struct audit_buffer *ab)
skb_queue_tail(&audit_skb_queue, ab->skb);
wake_up_interruptible(&kauditd_wait);
} else {
if (nlh->nlmsg_type != AUDIT_EOE) {
if (printk_ratelimit()) {
printk(KERN_NOTICE "type=%d %s\n",
nlh->nlmsg_type,
ab->skb->data + NLMSG_SPACE(0));
} else
audit_log_lost("printk limit exceeded\n");
}
audit_hold_skb(ab->skb);
audit_printk_skb(ab->skb);
}
ab->skb = NULL;
}

43
kernel/audit.h
View file

@ -53,18 +53,7 @@ enum audit_state {
};
/* Rule lists */
struct audit_parent;
struct audit_watch {
atomic_t count; /* reference count */
char *path; /* insertion path */
dev_t dev; /* associated superblock device */
unsigned long ino; /* associated inode number */
struct audit_parent *parent; /* associated parent */
struct list_head wlist; /* entry in parent->watches list */
struct list_head rules; /* associated rules */
};
struct audit_watch;
struct audit_tree;
struct audit_chunk;
@ -108,19 +97,28 @@ struct audit_netlink_list {
int audit_send_list(void *);
struct inotify_watch;
/* Inotify handle */
extern struct inotify_handle *audit_ih;
extern void audit_free_parent(struct inotify_watch *);
extern void audit_handle_ievent(struct inotify_watch *, u32, u32, u32,
const char *, struct inode *);
extern int selinux_audit_rule_update(void);
extern struct mutex audit_filter_mutex;
extern void audit_free_rule_rcu(struct rcu_head *);
extern struct list_head audit_filter_list[];
/* audit watch functions */
extern unsigned long audit_watch_inode(struct audit_watch *watch);
extern dev_t audit_watch_dev(struct audit_watch *watch);
extern void audit_put_watch(struct audit_watch *watch);
extern void audit_get_watch(struct audit_watch *watch);
extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op);
extern int audit_add_watch(struct audit_krule *krule);
extern void audit_remove_watch(struct audit_watch *watch);
extern void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list);
extern void audit_inotify_unregister(struct list_head *in_list);
extern char *audit_watch_path(struct audit_watch *watch);
extern struct list_head *audit_watch_rules(struct audit_watch *watch);
extern struct audit_entry *audit_dupe_rule(struct audit_krule *old,
struct audit_watch *watch);
#ifdef CONFIG_AUDIT_TREE
extern struct audit_chunk *audit_tree_lookup(const struct inode *);
extern void audit_put_chunk(struct audit_chunk *);
@ -130,10 +128,9 @@ extern int audit_add_tree_rule(struct audit_krule *);
extern int audit_remove_tree_rule(struct audit_krule *);
extern void audit_trim_trees(void);
extern int audit_tag_tree(char *old, char *new);
extern void audit_schedule_prune(void);
extern void audit_prune_trees(void);
extern const char *audit_tree_path(struct audit_tree *);
extern void audit_put_tree(struct audit_tree *);
extern void audit_kill_trees(struct list_head *);
#else
#define audit_remove_tree_rule(rule) BUG()
#define audit_add_tree_rule(rule) -EINVAL
@ -142,6 +139,7 @@ extern void audit_put_tree(struct audit_tree *);
#define audit_put_tree(tree) (void)0
#define audit_tag_tree(old, new) -EINVAL
#define audit_tree_path(rule) "" /* never called */
#define audit_kill_trees(list) BUG()
#endif
extern char *audit_unpack_string(void **, size_t *, size_t);
@ -160,7 +158,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t)
return 0;
}
extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
extern struct list_head *audit_killed_trees(void);
#else
#define audit_signal_info(s,t) AUDIT_DISABLED
#define audit_filter_inodes(t,c) AUDIT_DISABLED
#endif
extern struct mutex audit_cmd_mutex;

66
kernel/audit_tree.c
View file

@ -2,6 +2,7 @@
#include <linux/inotify.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/kthread.h>
struct audit_tree;
struct audit_chunk;
@ -441,13 +442,11 @@ static void kill_rules(struct audit_tree *tree)
if (rule->tree) {
/* not a half-baked one */
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
audit_log_format(ab, "op=remove rule dir=");
audit_log_format(ab, "op=");
audit_log_string(ab, "remove rule");
audit_log_format(ab, " dir=");
audit_log_untrustedstring(ab, rule->tree->pathname);
if (rule->filterkey) {
audit_log_format(ab, " key=");
audit_log_untrustedstring(ab, rule->filterkey);
} else
audit_log_format(ab, " key=(null)");
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=1", rule->listnr);
audit_log_end(ab);
rule->tree = NULL;
@ -519,6 +518,8 @@ static void trim_marked(struct audit_tree *tree)
}
}
static void audit_schedule_prune(void);
/* called with audit_filter_mutex */
int audit_remove_tree_rule(struct audit_krule *rule)
{
@ -824,10 +825,11 @@ int audit_tag_tree(char *old, char *new)
/*
* That gets run when evict_chunk() ends up needing to kill audit_tree.
* Runs from a separate thread, with audit_cmd_mutex held.
* Runs from a separate thread.
*/
void audit_prune_trees(void)
static int prune_tree_thread(void *unused)
{
mutex_lock(&audit_cmd_mutex);
mutex_lock(&audit_filter_mutex);
while (!list_empty(&prune_list)) {
@ -844,6 +846,40 @@ void audit_prune_trees(void)
}
mutex_unlock(&audit_filter_mutex);
mutex_unlock(&audit_cmd_mutex);
return 0;
}
static void audit_schedule_prune(void)
{
kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
}
/*
* ... and that one is done if evict_chunk() decides to delay until the end
* of syscall. Runs synchronously.
*/
void audit_kill_trees(struct list_head *list)
{
mutex_lock(&audit_cmd_mutex);
mutex_lock(&audit_filter_mutex);
while (!list_empty(list)) {
struct audit_tree *victim;
victim = list_entry(list->next, struct audit_tree, list);
kill_rules(victim);
list_del_init(&victim->list);
mutex_unlock(&audit_filter_mutex);
prune_one(victim);
mutex_lock(&audit_filter_mutex);
}
mutex_unlock(&audit_filter_mutex);
mutex_unlock(&audit_cmd_mutex);
}
/*
@ -854,6 +890,8 @@ void audit_prune_trees(void)
static void evict_chunk(struct audit_chunk *chunk)
{
struct audit_tree *owner;
struct list_head *postponed = audit_killed_trees();
int need_prune = 0;
int n;
if (chunk->dead)
@ -869,15 +907,21 @@ static void evict_chunk(struct audit_chunk *chunk)
owner->root = NULL;
list_del_init(&owner->same_root);
spin_unlock(&hash_lock);
kill_rules(owner);
list_move(&owner->list, &prune_list);
audit_schedule_prune();
if (!postponed) {
kill_rules(owner);
list_move(&owner->list, &prune_list);
need_prune = 1;
} else {
list_move(&owner->list, postponed);
}
spin_lock(&hash_lock);
}
list_del_rcu(&chunk->hash);
for (n = 0; n < chunk->count; n++)
list_del_init(&chunk->owners[n].list);
spin_unlock(&hash_lock);
if (need_prune)
audit_schedule_prune();
mutex_unlock(&audit_filter_mutex);
}

543
kernel/audit_watch.c Normal file
View file

@ -0,0 +1,543 @@
/* audit_watch.c -- watching inodes
*
* Copyright 2003-2009 Red Hat, Inc.
* Copyright 2005 Hewlett-Packard Development Company, L.P.
* Copyright 2005 IBM Corporation
*
* 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/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/inotify.h>
#include <linux/security.h>
#include "audit.h"
/*
* Reference counting:
*
* audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED
* event. Each audit_watch holds a reference to its associated parent.
*
* audit_watch: if added to lists, lifetime is from audit_init_watch() to
* audit_remove_watch(). Additionally, an audit_watch may exist
* temporarily to assist in searching existing filter data. Each
* audit_krule holds a reference to its associated watch.
*/
struct audit_watch {
atomic_t count; /* reference count */
char *path; /* insertion path */
dev_t dev; /* associated superblock device */
unsigned long ino; /* associated inode number */
struct audit_parent *parent; /* associated parent */
struct list_head wlist; /* entry in parent->watches list */
struct list_head rules; /* associated rules */
};
struct audit_parent {
struct list_head ilist; /* entry in inotify registration list */
struct list_head watches; /* associated watches */
struct inotify_watch wdata; /* inotify watch data */
unsigned flags; /* status flags */
};
/* Inotify handle. */
struct inotify_handle *audit_ih;
/*
* audit_parent status flags:
*
* AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to
* a filesystem event to ensure we're adding audit watches to a valid parent.
* Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot
* receive them while we have nameidata, but must be used for IN_MOVE_SELF which
* we can receive while holding nameidata.
*/
#define AUDIT_PARENT_INVALID 0x001
/* Inotify events we care about. */
#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF
static void audit_free_parent(struct inotify_watch *i_watch)
{
struct audit_parent *parent;
parent = container_of(i_watch, struct audit_parent, wdata);
WARN_ON(!list_empty(&parent->watches));
kfree(parent);
}
void audit_get_watch(struct audit_watch *watch)
{
atomic_inc(&watch->count);
}
void audit_put_watch(struct audit_watch *watch)
{
if (atomic_dec_and_test(&watch->count)) {
WARN_ON(watch->parent);
WARN_ON(!list_empty(&watch->rules));
kfree(watch->path);
kfree(watch);
}
}
void audit_remove_watch(struct audit_watch *watch)
{
list_del(&watch->wlist);
put_inotify_watch(&watch->parent->wdata);
watch->parent = NULL;
audit_put_watch(watch); /* match initial get */
}
char *audit_watch_path(struct audit_watch *watch)
{
return watch->path;
}
struct list_head *audit_watch_rules(struct audit_watch *watch)
{
return &watch->rules;
}
unsigned long audit_watch_inode(struct audit_watch *watch)
{
return watch->ino;
}
dev_t audit_watch_dev(struct audit_watch *watch)
{
return watch->dev;
}
/* Initialize a parent watch entry. */
static struct audit_parent *audit_init_parent(struct nameidata *ndp)
{
struct audit_parent *parent;
s32 wd;
parent = kzalloc(sizeof(*parent), GFP_KERNEL);
if (unlikely(!parent))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&parent->watches);
parent->flags = 0;
inotify_init_watch(&parent->wdata);
/* grab a ref so inotify watch hangs around until we take audit_filter_mutex */
get_inotify_watch(&parent->wdata);
wd = inotify_add_watch(audit_ih, &parent->wdata,
ndp->path.dentry->d_inode, AUDIT_IN_WATCH);
if (wd < 0) {
audit_free_parent(&parent->wdata);
return ERR_PTR(wd);
}
return parent;
}
/* Initialize a watch entry. */
static struct audit_watch *audit_init_watch(char *path)
{
struct audit_watch *watch;
watch = kzalloc(sizeof(*watch), GFP_KERNEL);
if (unlikely(!watch))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&watch->rules);
atomic_set(&watch->count, 1);
watch->path = path;
watch->dev = (dev_t)-1;
watch->ino = (unsigned long)-1;
return watch;
}
/* Translate a watch string to kernel respresentation. */
int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op)
{
struct audit_watch *watch;
if (!audit_ih)
return -EOPNOTSUPP;
if (path[0] != '/' || path[len-1] == '/' ||
krule->listnr != AUDIT_FILTER_EXIT ||
op != Audit_equal ||
krule->inode_f || krule->watch || krule->tree)
return -EINVAL;
watch = audit_init_watch(path);
if (IS_ERR(watch))
return PTR_ERR(watch);
audit_get_watch(watch);
krule->watch = watch;
return 0;
}
/* Duplicate the given audit watch. The new watch's rules list is initialized
* to an empty list and wlist is undefined. */
static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
{
char *path;
struct audit_watch *new;
path = kstrdup(old->path, GFP_KERNEL);
if (unlikely(!path))
return ERR_PTR(-ENOMEM);
new = audit_init_watch(path);
if (IS_ERR(new)) {
kfree(path);
goto out;
}
new->dev = old->dev;
new->ino = old->ino;
get_inotify_watch(&old->parent->wdata);
new->parent = old->parent;
out:
return new;
}
static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op)
{
if (audit_enabled) {
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
audit_log_format(ab, "auid=%u ses=%u op=",
audit_get_loginuid(current),
audit_get_sessionid(current));
audit_log_string(ab, op);
audit_log_format(ab, " path=");
audit_log_untrustedstring(ab, w->path);
audit_log_key(ab, r->filterkey);
audit_log_format(ab, " list=%d res=1", r->listnr);
audit_log_end(ab);
}
}
/* Update inode info in audit rules based on filesystem event. */
static void audit_update_watch(struct audit_parent *parent,
const char *dname, dev_t dev,
unsigned long ino, unsigned invalidating)
{
struct audit_watch *owatch, *nwatch, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *oentry, *nentry;
mutex_lock(&audit_filter_mutex);
list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
if (audit_compare_dname_path(dname, owatch->path, NULL))
continue;
/* If the update involves invalidating rules, do the inode-based
* filtering now, so we don't omit records. */
if (invalidating && current->audit_context)
audit_filter_inodes(current, current->audit_context);
nwatch = audit_dupe_watch(owatch);
if (IS_ERR(nwatch)) {
mutex_unlock(&audit_filter_mutex);
audit_panic("error updating watch, skipping");
return;
}
nwatch->dev = dev;
nwatch->ino = ino;
list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) {
oentry = container_of(r, struct audit_entry, rule);
list_del(&oentry->rule.rlist);
list_del_rcu(&oentry->list);
nentry = audit_dupe_rule(&oentry->rule, nwatch);
if (IS_ERR(nentry)) {
list_del(&oentry->rule.list);
audit_panic("error updating watch, removing");
} else {
int h = audit_hash_ino((u32)ino);
list_add(&nentry->rule.rlist, &nwatch->rules);
list_add_rcu(&nentry->list, &audit_inode_hash[h]);
list_replace(&oentry->rule.list,
&nentry->rule.list);
}
audit_watch_log_rule_change(r, owatch, "updated rules");
call_rcu(&oentry->rcu, audit_free_rule_rcu);
}
audit_remove_watch(owatch);
goto add_watch_to_parent; /* event applies to a single watch */
}
mutex_unlock(&audit_filter_mutex);
return;
add_watch_to_parent:
list_add(&nwatch->wlist, &parent->watches);
mutex_unlock(&audit_filter_mutex);
return;
}
/* Remove all watches & rules associated with a parent that is going away. */
static void audit_remove_parent_watches(struct audit_parent *parent)
{
struct audit_watch *w, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *e;
mutex_lock(&audit_filter_mutex);
parent->flags |= AUDIT_PARENT_INVALID;
list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
e = container_of(r, struct audit_entry, rule);
audit_watch_log_rule_change(r, w, "remove rule");
list_del(&r->rlist);
list_del(&r->list);
list_del_rcu(&e->list);
call_rcu(&e->rcu, audit_free_rule_rcu);
}
audit_remove_watch(w);
}
mutex_unlock(&audit_filter_mutex);
}
/* Unregister inotify watches for parents on in_list.
* Generates an IN_IGNORED event. */
void audit_inotify_unregister(struct list_head *in_list)
{
struct audit_parent *p, *n;
list_for_each_entry_safe(p, n, in_list, ilist) {
list_del(&p->ilist);
inotify_rm_watch(audit_ih, &p->wdata);
/* the unpin matching the pin in audit_do_del_rule() */
unpin_inotify_watch(&p->wdata);
}
}
/* Get path information necessary for adding watches. */
static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
{
struct nameidata *ndparent, *ndwatch;
int err;
ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
if (unlikely(!ndparent))
return -ENOMEM;
ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
if (unlikely(!ndwatch)) {
kfree(ndparent);
return -ENOMEM;
}
err = path_lookup(path, LOOKUP_PARENT, ndparent);
if (err) {
kfree(ndparent);
kfree(ndwatch);
return err;
}
err = path_lookup(path, 0, ndwatch);
if (err) {
kfree(ndwatch);
ndwatch = NULL;
}
*ndp = ndparent;
*ndw = ndwatch;
return 0;
}
/* Release resources used for watch path information. */
static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
{
if (ndp) {
path_put(&ndp->path);
kfree(ndp);
}
if (ndw) {
path_put(&ndw->path);
kfree(ndw);
}
}
/* Associate the given rule with an existing parent inotify_watch.
* Caller must hold audit_filter_mutex. */
static void audit_add_to_parent(struct audit_krule *krule,
struct audit_parent *parent)
{
struct audit_watch *w, *watch = krule->watch;
int watch_found = 0;
list_for_each_entry(w, &parent->watches, wlist) {
if (strcmp(watch->path, w->path))
continue;
watch_found = 1;
/* put krule's and initial refs to temporary watch */
audit_put_watch(watch);
audit_put_watch(watch);
audit_get_watch(w);
krule->watch = watch = w;
break;
}
if (!watch_found) {
get_inotify_watch(&parent->wdata);
watch->parent = parent;
list_add(&watch->wlist, &parent->watches);
}
list_add(&krule->rlist, &watch->rules);
}
/* Find a matching watch entry, or add this one.
* Caller must hold audit_filter_mutex. */
int audit_add_watch(struct audit_krule *krule)
{
struct audit_watch *watch = krule->watch;
struct inotify_watch *i_watch;
struct audit_parent *parent;
struct nameidata *ndp = NULL, *ndw = NULL;
int ret = 0;
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
ret = audit_get_nd(watch->path, &ndp, &ndw);
if (ret) {
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
goto error;
}
/* update watch filter fields */
if (ndw) {
watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
watch->ino = ndw->path.dentry->d_inode->i_ino;
}
/* The audit_filter_mutex must not be held during inotify calls because
* we hold it during inotify event callback processing. If an existing
* inotify watch is found, inotify_find_watch() grabs a reference before
* returning.
*/
if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode,
&i_watch) < 0) {
parent = audit_init_parent(ndp);
if (IS_ERR(parent)) {
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
ret = PTR_ERR(parent);
goto error;
}
} else
parent = container_of(i_watch, struct audit_parent, wdata);
mutex_lock(&audit_filter_mutex);
/* parent was moved before we took audit_filter_mutex */
if (parent->flags & AUDIT_PARENT_INVALID)
ret = -ENOENT;
else
audit_add_to_parent(krule, parent);
/* match get in audit_init_parent or inotify_find_watch */
put_inotify_watch(&parent->wdata);
error:
audit_put_nd(ndp, ndw); /* NULL args OK */
return ret;
}
void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list)
{
struct audit_watch *watch = krule->watch;
struct audit_parent *parent = watch->parent;
list_del(&krule->rlist);
if (list_empty(&watch->rules)) {
audit_remove_watch(watch);
if (list_empty(&parent->watches)) {
/* Put parent on the inotify un-registration
* list. Grab a reference before releasing
* audit_filter_mutex, to be released in
* audit_inotify_unregister().
* If filesystem is going away, just leave
* the sucker alone, eviction will take
* care of it. */
if (pin_inotify_watch(&parent->wdata))
list_add(&parent->ilist, list);
}
}
}
/* Update watch data in audit rules based on inotify events. */
static void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask,
u32 cookie, const char *dname, struct inode *inode)
{
struct audit_parent *parent;
parent = container_of(i_watch, struct audit_parent, wdata);
if (mask & (IN_CREATE|IN_MOVED_TO) && inode)
audit_update_watch(parent, dname, inode->i_sb->s_dev,
inode->i_ino, 0);
else if (mask & (IN_DELETE|IN_MOVED_FROM))
audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1);
/* inotify automatically removes the watch and sends IN_IGNORED */
else if (mask & (IN_DELETE_SELF|IN_UNMOUNT))
audit_remove_parent_watches(parent);
/* inotify does not remove the watch, so remove it manually */
else if(mask & IN_MOVE_SELF) {
audit_remove_parent_watches(parent);
inotify_remove_watch_locked(audit_ih, i_watch);
} else if (mask & IN_IGNORED)
put_inotify_watch(i_watch);
}
static const struct inotify_operations audit_inotify_ops = {
.handle_event = audit_handle_ievent,
.destroy_watch = audit_free_parent,
};
static int __init audit_watch_init(void)
{
audit_ih = inotify_init(&audit_inotify_ops);
if (IS_ERR(audit_ih))
audit_panic("cannot initialize inotify handle");
return 0;
}
subsys_initcall(audit_watch_init);

518
kernel/auditfilter.c
View file

@ -27,7 +27,6 @@
#include <linux/namei.h>
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/inotify.h>
#include <linux/security.h>
#include "audit.h"
@ -44,36 +43,6 @@
* be written directly provided audit_filter_mutex is held.
*/
/*
* Reference counting:
*
* audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED
* event. Each audit_watch holds a reference to its associated parent.
*
* audit_watch: if added to lists, lifetime is from audit_init_watch() to
* audit_remove_watch(). Additionally, an audit_watch may exist
* temporarily to assist in searching existing filter data. Each
* audit_krule holds a reference to its associated watch.
*/
struct audit_parent {
struct list_head ilist; /* entry in inotify registration list */
struct list_head watches; /* associated watches */
struct inotify_watch wdata; /* inotify watch data */
unsigned flags; /* status flags */
};
/*
* audit_parent status flags:
*
* AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to
* a filesystem event to ensure we're adding audit watches to a valid parent.
* Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot
* receive them while we have nameidata, but must be used for IN_MOVE_SELF which
* we can receive while holding nameidata.
*/
#define AUDIT_PARENT_INVALID 0x001
/* Audit filter lists, defined in <linux/audit.h> */
struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
LIST_HEAD_INIT(audit_filter_list[0]),
@ -97,41 +66,6 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
DEFINE_MUTEX(audit_filter_mutex);
/* Inotify events we care about. */
#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF
void audit_free_parent(struct inotify_watch *i_watch)
{
struct audit_parent *parent;
parent = container_of(i_watch, struct audit_parent, wdata);
WARN_ON(!list_empty(&parent->watches));
kfree(parent);
}
static inline void audit_get_watch(struct audit_watch *watch)
{
atomic_inc(&watch->count);
}
static void audit_put_watch(struct audit_watch *watch)
{
if (atomic_dec_and_test(&watch->count)) {
WARN_ON(watch->parent);
WARN_ON(!list_empty(&watch->rules));
kfree(watch->path);
kfree(watch);
}
}
static void audit_remove_watch(struct audit_watch *watch)
{
list_del(&watch->wlist);
put_inotify_watch(&watch->parent->wdata);
watch->parent = NULL;
audit_put_watch(watch); /* match initial get */
}
static inline void audit_free_rule(struct audit_entry *e)
{
int i;
@ -156,50 +90,6 @@ void audit_free_rule_rcu(struct rcu_head *head)
audit_free_rule(e);
}
/* Initialize a parent watch entry. */
static struct audit_parent *audit_init_parent(struct nameidata *ndp)
{
struct audit_parent *parent;
s32 wd;
parent = kzalloc(sizeof(*parent), GFP_KERNEL);
if (unlikely(!parent))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&parent->watches);
parent->flags = 0;
inotify_init_watch(&parent->wdata);
/* grab a ref so inotify watch hangs around until we take audit_filter_mutex */
get_inotify_watch(&parent->wdata);
wd = inotify_add_watch(audit_ih, &parent->wdata,
ndp->path.dentry->d_inode, AUDIT_IN_WATCH);
if (wd < 0) {
audit_free_parent(&parent->wdata);
return ERR_PTR(wd);
}
return parent;
}
/* Initialize a watch entry. */
static struct audit_watch *audit_init_watch(char *path)
{
struct audit_watch *watch;
watch = kzalloc(sizeof(*watch), GFP_KERNEL);
if (unlikely(!watch))
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&watch->rules);
atomic_set(&watch->count, 1);
watch->path = path;
watch->dev = (dev_t)-1;
watch->ino = (unsigned long)-1;
return watch;
}
/* Initialize an audit filterlist entry. */
static inline struct audit_entry *audit_init_entry(u32 field_count)
{
@ -260,31 +150,6 @@ static inline int audit_to_inode(struct audit_krule *krule,
return 0;
}
/* Translate a watch string to kernel respresentation. */
static int audit_to_watch(struct audit_krule *krule, char *path, int len,
u32 op)
{
struct audit_watch *watch;
if (!audit_ih)
return -EOPNOTSUPP;
if (path[0] != '/' || path[len-1] == '/' ||
krule->listnr != AUDIT_FILTER_EXIT ||
op != Audit_equal ||
krule->inode_f || krule->watch || krule->tree)
return -EINVAL;
watch = audit_init_watch(path);
if (IS_ERR(watch))
return PTR_ERR(watch);
audit_get_watch(watch);
krule->watch = watch;
return 0;
}
static __u32 *classes[AUDIT_SYSCALL_CLASSES];
int __init audit_register_class(int class, unsigned *list)
@ -766,7 +631,8 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
break;
case AUDIT_WATCH:
data->buflen += data->values[i] =
audit_pack_string(&bufp, krule->watch->path);
audit_pack_string(&bufp,
audit_watch_path(krule->watch));
break;
case AUDIT_DIR:
data->buflen += data->values[i] =
@ -818,7 +684,8 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
return 1;
break;
case AUDIT_WATCH:
if (strcmp(a->watch->path, b->watch->path))
if (strcmp(audit_watch_path(a->watch),
audit_watch_path(b->watch)))
return 1;
break;
case AUDIT_DIR:
@ -844,32 +711,6 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
return 0;
}
/* Duplicate the given audit watch. The new watch's rules list is initialized
* to an empty list and wlist is undefined. */
static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
{
char *path;
struct audit_watch *new;
path = kstrdup(old->path, GFP_KERNEL);
if (unlikely(!path))
return ERR_PTR(-ENOMEM);
new = audit_init_watch(path);
if (IS_ERR(new)) {
kfree(path);
goto out;
}
new->dev = old->dev;
new->ino = old->ino;
get_inotify_watch(&old->parent->wdata);
new->parent = old->parent;
out:
return new;
}
/* Duplicate LSM field information. The lsm_rule is opaque, so must be
* re-initialized. */
static inline int audit_dupe_lsm_field(struct audit_field *df,
@ -904,8 +745,8 @@ static inline int audit_dupe_lsm_field(struct audit_field *df,
* rule with the new rule in the filterlist, then free the old rule.
* The rlist element is undefined; list manipulations are handled apart from
* the initial copy. */
static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
struct audit_watch *watch)
struct audit_entry *audit_dupe_rule(struct audit_krule *old,
struct audit_watch *watch)
{
u32 fcount = old->field_count;
struct audit_entry *entry;
@ -977,137 +818,6 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
return entry;
}
/* Update inode info in audit rules based on filesystem event. */
static void audit_update_watch(struct audit_parent *parent,
const char *dname, dev_t dev,
unsigned long ino, unsigned invalidating)
{
struct audit_watch *owatch, *nwatch, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *oentry, *nentry;
mutex_lock(&audit_filter_mutex);
list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
if (audit_compare_dname_path(dname, owatch->path, NULL))
continue;
/* If the update involves invalidating rules, do the inode-based
* filtering now, so we don't omit records. */
if (invalidating && current->audit_context)
audit_filter_inodes(current, current->audit_context);
nwatch = audit_dupe_watch(owatch);
if (IS_ERR(nwatch)) {
mutex_unlock(&audit_filter_mutex);
audit_panic("error updating watch, skipping");
return;
}
nwatch->dev = dev;
nwatch->ino = ino;
list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) {
oentry = container_of(r, struct audit_entry, rule);
list_del(&oentry->rule.rlist);
list_del_rcu(&oentry->list);
nentry = audit_dupe_rule(&oentry->rule, nwatch);
if (IS_ERR(nentry)) {
list_del(&oentry->rule.list);
audit_panic("error updating watch, removing");
} else {
int h = audit_hash_ino((u32)ino);
list_add(&nentry->rule.rlist, &nwatch->rules);
list_add_rcu(&nentry->list, &audit_inode_hash[h]);
list_replace(&oentry->rule.list,
&nentry->rule.list);
}
call_rcu(&oentry->rcu, audit_free_rule_rcu);
}
if (audit_enabled) {
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_NOFS,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, "auid=%u ses=%u",
audit_get_loginuid(current),
audit_get_sessionid(current));
audit_log_format(ab,
" op=updated rules specifying path=");
audit_log_untrustedstring(ab, owatch->path);
audit_log_format(ab, " with dev=%u ino=%lu\n",
dev, ino);
audit_log_format(ab, " list=%d res=1", r->listnr);
audit_log_end(ab);
}
audit_remove_watch(owatch);
goto add_watch_to_parent; /* event applies to a single watch */
}
mutex_unlock(&audit_filter_mutex);
return;
add_watch_to_parent:
list_add(&nwatch->wlist, &parent->watches);
mutex_unlock(&audit_filter_mutex);
return;
}
/* Remove all watches & rules associated with a parent that is going away. */
static void audit_remove_parent_watches(struct audit_parent *parent)
{
struct audit_watch *w, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *e;
mutex_lock(&audit_filter_mutex);
parent->flags |= AUDIT_PARENT_INVALID;
list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
e = container_of(r, struct audit_entry, rule);
if (audit_enabled) {
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_NOFS,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, "auid=%u ses=%u",
audit_get_loginuid(current),
audit_get_sessionid(current));
audit_log_format(ab, " op=remove rule path=");
audit_log_untrustedstring(ab, w->path);
if (r->filterkey) {
audit_log_format(ab, " key=");
audit_log_untrustedstring(ab,
r->filterkey);
} else
audit_log_format(ab, " key=(null)");
audit_log_format(ab, " list=%d res=1",
r->listnr);
audit_log_end(ab);
}
list_del(&r->rlist);
list_del(&r->list);
list_del_rcu(&e->list);
call_rcu(&e->rcu, audit_free_rule_rcu);
}
audit_remove_watch(w);
}
mutex_unlock(&audit_filter_mutex);
}
/* Unregister inotify watches for parents on in_list.
* Generates an IN_IGNORED event. */
static void audit_inotify_unregister(struct list_head *in_list)
{
struct audit_parent *p, *n;
list_for_each_entry_safe(p, n, in_list, ilist) {
list_del(&p->ilist);
inotify_rm_watch(audit_ih, &p->wdata);
/* the unpin matching the pin in audit_do_del_rule() */
unpin_inotify_watch(&p->wdata);
}
}
/* Find an existing audit rule.
* Caller must hold audit_filter_mutex to prevent stale rule data. */
static struct audit_entry *audit_find_rule(struct audit_entry *entry,
@ -1145,134 +855,6 @@ out:
return found;
}
/* Get path information necessary for adding watches. */
static int audit_get_nd(char *path, struct nameidata **ndp,
struct nameidata **ndw)
{
struct nameidata *ndparent, *ndwatch;
int err;
ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
if (unlikely(!ndparent))
return -ENOMEM;
ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
if (unlikely(!ndwatch)) {
kfree(ndparent);
return -ENOMEM;
}
err = path_lookup(path, LOOKUP_PARENT, ndparent);
if (err) {
kfree(ndparent);
kfree(ndwatch);
return err;
}
err = path_lookup(path, 0, ndwatch);
if (err) {
kfree(ndwatch);
ndwatch = NULL;
}
*ndp = ndparent;
*ndw = ndwatch;
return 0;
}
/* Release resources used for watch path information. */
static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
{
if (ndp) {
path_put(&ndp->path);
kfree(ndp);
}
if (ndw) {
path_put(&ndw->path);
kfree(ndw);
}
}
/* Associate the given rule with an existing parent inotify_watch.
* Caller must hold audit_filter_mutex. */
static void audit_add_to_parent(struct audit_krule *krule,
struct audit_parent *parent)
{
struct audit_watch *w, *watch = krule->watch;
int watch_found = 0;
list_for_each_entry(w, &parent->watches, wlist) {
if (strcmp(watch->path, w->path))
continue;
watch_found = 1;
/* put krule's and initial refs to temporary watch */
audit_put_watch(watch);
audit_put_watch(watch);
audit_get_watch(w);
krule->watch = watch = w;
break;
}
if (!watch_found) {
get_inotify_watch(&parent->wdata);
watch->parent = parent;
list_add(&watch->wlist, &parent->watches);
}
list_add(&krule->rlist, &watch->rules);
}
/* Find a matching watch entry, or add this one.
* Caller must hold audit_filter_mutex. */
static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp,
struct nameidata *ndw)
{
struct audit_watch *watch = krule->watch;
struct inotify_watch *i_watch;
struct audit_parent *parent;
int ret = 0;
/* update watch filter fields */
if (ndw) {
watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
watch->ino = ndw->path.dentry->d_inode->i_ino;
}
/* The audit_filter_mutex must not be held during inotify calls because
* we hold it during inotify event callback processing. If an existing
* inotify watch is found, inotify_find_watch() grabs a reference before
* returning.
*/
mutex_unlock(&audit_filter_mutex);
if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode,
&i_watch) < 0) {
parent = audit_init_parent(ndp);
if (IS_ERR(parent)) {
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
return PTR_ERR(parent);
}
} else
parent = container_of(i_watch, struct audit_parent, wdata);
mutex_lock(&audit_filter_mutex);
/* parent was moved before we took audit_filter_mutex */
if (parent->flags & AUDIT_PARENT_INVALID)
ret = -ENOENT;
else
audit_add_to_parent(krule, parent);
/* match get in audit_init_parent or inotify_find_watch */
put_inotify_watch(&parent->wdata);
return ret;
}
static u64 prio_low = ~0ULL/2;
static u64 prio_high = ~0ULL/2 - 1;
@ -1282,7 +864,6 @@ static inline int audit_add_rule(struct audit_entry *entry)
struct audit_entry *e;
struct audit_watch *watch = entry->rule.watch;
struct audit_tree *tree = entry->rule.tree;
struct nameidata *ndp = NULL, *ndw = NULL;
struct list_head *list;
int h, err;
#ifdef CONFIG_AUDITSYSCALL
@ -1296,8 +877,8 @@ static inline int audit_add_rule(struct audit_entry *entry)
mutex_lock(&audit_filter_mutex);
e = audit_find_rule(entry, &list);
mutex_unlock(&audit_filter_mutex);
if (e) {
mutex_unlock(&audit_filter_mutex);
err = -EEXIST;
/* normally audit_add_tree_rule() will free it on failure */
if (tree)
@ -1305,22 +886,16 @@ static inline int audit_add_rule(struct audit_entry *entry)
goto error;
}
/* Avoid calling path_lookup under audit_filter_mutex. */
if (watch) {
err = audit_get_nd(watch->path, &ndp, &ndw);
if (err)
goto error;
}
mutex_lock(&audit_filter_mutex);
if (watch) {
/* audit_filter_mutex is dropped and re-taken during this call */
err = audit_add_watch(&entry->rule, ndp, ndw);
err = audit_add_watch(&entry->rule);
if (err) {
mutex_unlock(&audit_filter_mutex);
goto error;
}
h = audit_hash_ino((u32)watch->ino);
/* entry->rule.watch may have changed during audit_add_watch() */
watch = entry->rule.watch;
h = audit_hash_ino((u32)audit_watch_inode(watch));
list = &audit_inode_hash[h];
}
if (tree) {
@ -1358,11 +933,9 @@ static inline int audit_add_rule(struct audit_entry *entry)
#endif
mutex_unlock(&audit_filter_mutex);
audit_put_nd(ndp, ndw); /* NULL args OK */
return 0;
error:
audit_put_nd(ndp, ndw); /* NULL args OK */
if (watch)
audit_put_watch(watch); /* tmp watch, matches initial get */
return err;
@ -1372,7 +945,7 @@ error:
static inline int audit_del_rule(struct audit_entry *entry)
{
struct audit_entry *e;
struct audit_watch *watch, *tmp_watch = entry->rule.watch;
struct audit_watch *watch = entry->rule.watch;
struct audit_tree *tree = entry->rule.tree;
struct list_head *list;
LIST_HEAD(inotify_list);
@ -1394,29 +967,8 @@ static inline int audit_del_rule(struct audit_entry *entry)
goto out;
}
watch = e->rule.watch;
if (watch) {
struct audit_parent *parent = watch->parent;
list_del(&e->rule.rlist);
if (list_empty(&watch->rules)) {
audit_remove_watch(watch);
if (list_empty(&parent->watches)) {
/* Put parent on the inotify un-registration
* list. Grab a reference before releasing
* audit_filter_mutex, to be released in
* audit_inotify_unregister().
* If filesystem is going away, just leave
* the sucker alone, eviction will take
* care of it.
*/
if (pin_inotify_watch(&parent->wdata))
list_add(&parent->ilist, &inotify_list);
}
}
}
if (e->rule.watch)
audit_remove_watch_rule(&e->rule, &inotify_list);
if (e->rule.tree)
audit_remove_tree_rule(&e->rule);
@ -1438,8 +990,8 @@ static inline int audit_del_rule(struct audit_entry *entry)
audit_inotify_unregister(&inotify_list);
out:
if (tmp_watch)
audit_put_watch(tmp_watch); /* match initial get */
if (watch)
audit_put_watch(watch); /* match initial get */
if (tree)
audit_put_tree(tree); /* that's the temporary one */
@ -1527,11 +1079,9 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid,
security_release_secctx(ctx, len);
}
}
audit_log_format(ab, " op=%s rule key=", action);
if (rule->filterkey)
audit_log_untrustedstring(ab, rule->filterkey);
else
audit_log_format(ab, "(null)");
audit_log_format(ab, " op=");
audit_log_string(ab, action);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=%d", rule->listnr, res);
audit_log_end(ab);
}
@ -1595,7 +1145,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
return PTR_ERR(entry);
err = audit_add_rule(entry);
audit_log_rule_change(loginuid, sessionid, sid, "add",
audit_log_rule_change(loginuid, sessionid, sid, "add rule",
&entry->rule, !err);
if (err)
@ -1611,7 +1161,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
return PTR_ERR(entry);
err = audit_del_rule(entry);
audit_log_rule_change(loginuid, sessionid, sid, "remove",
audit_log_rule_change(loginuid, sessionid, sid, "remove rule",
&entry->rule, !err);
audit_free_rule(entry);
@ -1793,7 +1343,7 @@ static int update_lsm_rule(struct audit_krule *r)
list_del(&r->list);
} else {
if (watch) {
list_add(&nentry->rule.rlist, &watch->rules);
list_add(&nentry->rule.rlist, audit_watch_rules(watch));
list_del(&r->rlist);
} else if (tree)
list_replace_init(&r->rlist, &nentry->rule.rlist);
@ -1829,27 +1379,3 @@ int audit_update_lsm_rules(void)
return err;
}
/* Update watch data in audit rules based on inotify events. */
void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask,
u32 cookie, const char *dname, struct inode *inode)
{
struct audit_parent *parent;
parent = container_of(i_watch, struct audit_parent, wdata);
if (mask & (IN_CREATE|IN_MOVED_TO) && inode)
audit_update_watch(parent, dname, inode->i_sb->s_dev,
inode->i_ino, 0);
else if (mask & (IN_DELETE|IN_MOVED_FROM))
audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1);
/* inotify automatically removes the watch and sends IN_IGNORED */
else if (mask & (IN_DELETE_SELF|IN_UNMOUNT))
audit_remove_parent_watches(parent);
/* inotify does not remove the watch, so remove it manually */
else if(mask & IN_MOVE_SELF) {
audit_remove_parent_watches(parent);
inotify_remove_watch_locked(audit_ih, i_watch);
} else if (mask & IN_IGNORED)
put_inotify_watch(i_watch);
}

33
kernel/auditsc.c
View file

@ -199,6 +199,7 @@ struct audit_context {
struct audit_tree_refs *trees, *first_trees;
int tree_count;
struct list_head killed_trees;
int type;
union {
@ -548,9 +549,9 @@ static int audit_filter_rules(struct task_struct *tsk,
}
break;
case AUDIT_WATCH:
if (name && rule->watch->ino != (unsigned long)-1)
result = (name->dev == rule->watch->dev &&
name->ino == rule->watch->ino);
if (name && audit_watch_inode(rule->watch) != (unsigned long)-1)
result = (name->dev == audit_watch_dev(rule->watch) &&
name->ino == audit_watch_inode(rule->watch));
break;
case AUDIT_DIR:
if (ctx)
@ -853,6 +854,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state)
if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
return NULL;
audit_zero_context(context, state);
INIT_LIST_HEAD(&context->killed_trees);
return context;
}
@ -1024,8 +1026,8 @@ static int audit_log_single_execve_arg(struct audit_context *context,
{
char arg_num_len_buf[12];
const char __user *tmp_p = p;
/* how many digits are in arg_num? 3 is the length of " a=" */
size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3;
/* how many digits are in arg_num? 5 is the length of ' a=""' */
size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
size_t len, len_left, to_send;
size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
unsigned int i, has_cntl = 0, too_long = 0;
@ -1137,7 +1139,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
if (has_cntl)
audit_log_n_hex(*ab, buf, to_send);
else
audit_log_format(*ab, "\"%s\"", buf);
audit_log_string(*ab, buf);
p += to_send;
len_left -= to_send;
@ -1372,11 +1374,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
audit_log_task_info(ab, tsk);
if (context->filterkey) {
audit_log_format(ab, " key=");
audit_log_untrustedstring(ab, context->filterkey);
} else
audit_log_format(ab, " key=(null)");
audit_log_key(ab, context->filterkey);
audit_log_end(ab);
for (aux = context->aux; aux; aux = aux->next) {
@ -1549,6 +1547,8 @@ void audit_free(struct task_struct *tsk)
/* that can happen only if we are called from do_exit() */
if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
audit_log_exit(context, tsk);
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
audit_free_context(context);
}
@ -1692,6 +1692,9 @@ void audit_syscall_exit(int valid, long return_code)
context->in_syscall = 0;
context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
if (context->previous) {
struct audit_context *new_context = context->previous;
context->previous = NULL;
@ -2525,3 +2528,11 @@ void audit_core_dumps(long signr)
audit_log_format(ab, " sig=%ld", signr);
audit_log_end(ab);
}
struct list_head *audit_killed_trees(void)
{
struct audit_context *ctx = current->audit_context;
if (likely(!ctx || !ctx->in_syscall))
return NULL;
return &ctx->killed_trees;
}

151
kernel/cgroup.c
View file

@ -47,6 +47,7 @@
#include <linux/hash.h>
#include <linux/namei.h>
#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
#include <asm/atomic.h>
@ -734,16 +735,28 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
* reference to css->refcnt. In general, this refcnt is expected to goes down
* to zero, soon.
*
* CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
* CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
*/
DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
wake_up_all(&cgroup_rmdir_waitq);
}
void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
{
css_get(css);
}
void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
{
cgroup_wakeup_rmdir_waiter(css->cgroup);
css_put(css);
}
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long final_bits)
{
@ -960,6 +973,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pids_list);
init_rwsem(&cgrp->pids_mutex);
}
static void init_cgroup_root(struct cgroupfs_root *root)
@ -1357,7 +1371,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
* wake up rmdir() waiter. the rmdir should fail since the cgroup
* is no longer empty.
*/
cgroup_wakeup_rmdir_waiters(cgrp);
cgroup_wakeup_rmdir_waiter(cgrp);
return 0;
}
@ -2201,12 +2215,30 @@ err:
return ret;
}
/*
* Cache pids for all threads in the same pid namespace that are
* opening the same "tasks" file.
*/
struct cgroup_pids {
/* The node in cgrp->pids_list */
struct list_head list;
/* The cgroup those pids belong to */
struct cgroup *cgrp;
/* The namepsace those pids belong to */
struct pid_namespace *ns;
/* Array of process ids in the cgroup */
pid_t *tasks_pids;
/* How many files are using the this tasks_pids array */
int use_count;
/* Length of the current tasks_pids array */
int length;
};
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
/*
* seq_file methods for the "tasks" file. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
@ -2221,45 +2253,47 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
struct cgroup *cgrp = s->private;
struct cgroup_pids *cp = s->private;
struct cgroup *cgrp = cp->cgrp;
int index = 0, pid = *pos;
int *iter;
down_read(&cgrp->pids_mutex);
if (pid) {
int end = cgrp->pids_length;
int end = cp->length;
while (index < end) {
int mid = (index + end) / 2;
if (cgrp->tasks_pids[mid] == pid) {
if (cp->tasks_pids[mid] == pid) {
index = mid;
break;
} else if (cgrp->tasks_pids[mid] <= pid)
} else if (cp->tasks_pids[mid] <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
if (index >= cgrp->pids_length)
if (index >= cp->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
iter = cgrp->tasks_pids + index;
iter = cp->tasks_pids + index;
*pos = *iter;
return iter;
}
static void cgroup_tasks_stop(struct seq_file *s, void *v)
{
struct cgroup *cgrp = s->private;
struct cgroup_pids *cp = s->private;
struct cgroup *cgrp = cp->cgrp;
up_read(&cgrp->pids_mutex);
}
static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
{
struct cgroup *cgrp = s->private;
struct cgroup_pids *cp = s->private;
int *p = v;
int *end = cgrp->tasks_pids + cgrp->pids_length;
int *end = cp->tasks_pids + cp->length;
/*
* Advance to the next pid in the array. If this goes off the
@ -2286,26 +2320,33 @@ static struct seq_operations cgroup_tasks_seq_operations = {
.show = cgroup_tasks_show,
};
static void release_cgroup_pid_array(struct cgroup *cgrp)
static void release_cgroup_pid_array(struct cgroup_pids *cp)
{
struct cgroup *cgrp = cp->cgrp;
down_write(&cgrp->pids_mutex);
BUG_ON(!cgrp->pids_use_count);
if (!--cgrp->pids_use_count) {
kfree(cgrp->tasks_pids);
cgrp->tasks_pids = NULL;
cgrp->pids_length = 0;
BUG_ON(!cp->use_count);
if (!--cp->use_count) {
list_del(&cp->list);
put_pid_ns(cp->ns);
kfree(cp->tasks_pids);
kfree(cp);
}
up_write(&cgrp->pids_mutex);
}
static int cgroup_tasks_release(struct inode *inode, struct file *file)
{
struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
struct seq_file *seq;
struct cgroup_pids *cp;
if (!(file->f_mode & FMODE_READ))
return 0;
release_cgroup_pid_array(cgrp);
seq = file->private_data;
cp = seq->private;
release_cgroup_pid_array(cp);
return seq_release(inode, file);
}
@ -2324,6 +2365,8 @@ static struct file_operations cgroup_tasks_operations = {
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
struct pid_namespace *ns = current->nsproxy->pid_ns;
struct cgroup_pids *cp;
pid_t *pidarray;
int npids;
int retval;
@ -2350,20 +2393,37 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
* array if necessary
*/
down_write(&cgrp->pids_mutex);
kfree(cgrp->tasks_pids);
cgrp->tasks_pids = pidarray;
cgrp->pids_length = npids;
cgrp->pids_use_count++;
list_for_each_entry(cp, &cgrp->pids_list, list) {
if (ns == cp->ns)
goto found;
}
cp = kzalloc(sizeof(*cp), GFP_KERNEL);
if (!cp) {
up_write(&cgrp->pids_mutex);
kfree(pidarray);
return -ENOMEM;
}
cp->cgrp = cgrp;
cp->ns = ns;
get_pid_ns(ns);
list_add(&cp->list, &cgrp->pids_list);
found:
kfree(cp->tasks_pids);
cp->tasks_pids = pidarray;
cp->length = npids;
cp->use_count++;
up_write(&cgrp->pids_mutex);
file->f_op = &cgroup_tasks_operations;
retval = seq_open(file, &cgroup_tasks_seq_operations);
if (retval) {
release_cgroup_pid_array(cgrp);
release_cgroup_pid_array(cp);
return retval;
}
((struct seq_file *)file->private_data)->private = cgrp;
((struct seq_file *)file->private_data)->private = cp;
return 0;
}
@ -2695,34 +2755,43 @@ again:
}
mutex_unlock(&cgroup_mutex);
/*
* In general, subsystem has no css->refcnt after pre_destroy(). But
* in racy cases, subsystem may have to get css->refcnt after
* pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
* make rmdir return -EBUSY too often. To avoid that, we use waitqueue
* for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
* and subsystem's reference count handling. Please see css_get/put
* and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
*/
set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
/*
* Call pre_destroy handlers of subsys. Notify subsystems
* that rmdir() request comes.
*/
ret = cgroup_call_pre_destroy(cgrp);
if (ret)
if (ret) {
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
return ret;
}
mutex_lock(&cgroup_mutex);
parent = cgrp->parent;
if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
mutex_unlock(&cgroup_mutex);
return -EBUSY;
}
/*
* css_put/get is provided for subsys to grab refcnt to css. In typical
* case, subsystem has no reference after pre_destroy(). But, under
* hierarchy management, some *temporal* refcnt can be hold.
* To avoid returning -EBUSY to a user, waitqueue is used. If subsys
* is really busy, it should return -EBUSY at pre_destroy(). wake_up
* is called when css_put() is called and refcnt goes down to 0.
*/
set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
if (!cgroup_clear_css_refs(cgrp)) {
mutex_unlock(&cgroup_mutex);
schedule();
/*
* Because someone may call cgroup_wakeup_rmdir_waiter() before
* prepare_to_wait(), we need to check this flag.
*/
if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
schedule();
finish_wait(&cgroup_rmdir_waitq, &wait);
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
if (signal_pending(current))
@ -3294,7 +3363,7 @@ void __css_put(struct cgroup_subsys_state *css)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
cgroup_wakeup_rmdir_waiters(cgrp);
cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
}

1
kernel/exit.c
View file

@ -12,7 +12,6 @@
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
#include <linux/mnt_namespace.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/security.h>

31
kernel/fork.c
View file

@ -17,7 +17,6 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/mnt_namespace.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
@ -427,6 +426,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0;
mm->core_state = NULL;
mm->nr_ptes = 0;
set_mm_counter(mm, file_rss, 0);
@ -568,18 +568,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
* the value intact in a core dump, and to save the unnecessary
* trouble otherwise. Userland only wants this done for a sys_exit.
*/
if (tsk->clear_child_tid
&& !(tsk->flags & PF_SIGNALED)
&& atomic_read(&mm->mm_users) > 1) {
u32 __user * tidptr = tsk->clear_child_tid;
if (tsk->clear_child_tid) {
if (!(tsk->flags & PF_SIGNALED) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
* not set up a proper pointer then tough luck.
*/
put_user(0, tsk->clear_child_tid);
sys_futex(tsk->clear_child_tid, FUTEX_WAKE,
1, NULL, NULL, 0);
}
tsk->clear_child_tid = NULL;
/*
* We don't check the error code - if userspace has
* not set up a proper pointer then tough luck.
*/
put_user(0, tidptr);
sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
}
}
@ -1269,6 +1269,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
perf_counter_fork(p);
return p;
bad_fork_free_pid:
@ -1408,12 +1409,6 @@ long do_fork(unsigned long clone_flags,
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
} else if (!(clone_flags & CLONE_VM)) {
/*
* vfork will do an exec which will call
* set_task_comm()
*/
perf_counter_fork(p);
}
audit_finish_fork(p);

7
kernel/freezer.c
View file

@ -44,12 +44,19 @@ void refrigerator(void)
recalc_sigpending(); /* We sent fake signal, clean it up */
spin_unlock_irq(&current->sighand->siglock);
/* prevent accounting of that task to load */
current->flags |= PF_FREEZING;
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!frozen(current))
break;
schedule();
}
/* Remove the accounting blocker */
current->flags &= ~PF_FREEZING;
pr_debug("%s left refrigerator\n", current->comm);
__set_current_state(save);
}

74
kernel/futex.c
View file

@ -247,6 +247,7 @@ again:
if (err < 0)
return err;
page = compound_head(page);
lock_page(page);
if (!page->mapping) {
unlock_page(page);
@ -284,6 +285,25 @@ void put_futex_key(int fshared, union futex_key *key)
drop_futex_key_refs(key);
}
/*
* fault_in_user_writeable - fault in user address and verify RW access
* @uaddr: pointer to faulting user space address
*
* Slow path to fixup the fault we just took in the atomic write
* access to @uaddr.
*
* We have no generic implementation of a non destructive write to the
* user address. We know that we faulted in the atomic pagefault
* disabled section so we can as well avoid the #PF overhead by
* calling get_user_pages() right away.
*/
static int fault_in_user_writeable(u32 __user *uaddr)
{
int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
1, 1, 0, NULL, NULL);
return ret < 0 ? ret : 0;
}
/**
* futex_top_waiter() - Return the highest priority waiter on a futex
* @hb: the hash bucket the futex_q's reside in
@ -896,7 +916,6 @@ retry:
retry_private:
op_ret = futex_atomic_op_inuser(op, uaddr2);
if (unlikely(op_ret < 0)) {
u32 dummy;
double_unlock_hb(hb1, hb2);
@ -914,7 +933,7 @@ retry_private:
goto out_put_keys;
}
ret = get_user(dummy, uaddr2);
ret = fault_in_user_writeable(uaddr2);
if (ret)
goto out_put_keys;
@ -991,15 +1010,19 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
* requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
* q: the futex_q
* key: the key of the requeue target futex
* hb: the hash_bucket of the requeue target futex
*
* During futex_requeue, with requeue_pi=1, it is possible to acquire the
* target futex if it is uncontended or via a lock steal. Set the futex_q key
* to the requeue target futex so the waiter can detect the wakeup on the right
* futex, but remove it from the hb and NULL the rt_waiter so it can detect
* atomic lock acquisition. Must be called with the q->lock_ptr held.
* atomic lock acquisition. Set the q->lock_ptr to the requeue target hb->lock
* to protect access to the pi_state to fixup the owner later. Must be called
* with both q->lock_ptr and hb->lock held.
*/
static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
struct futex_hash_bucket *hb)
{
drop_futex_key_refs(&q->key);
get_futex_key_refs(key);
@ -1011,6 +1034,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
WARN_ON(!q->rt_waiter);
q->rt_waiter = NULL;
q->lock_ptr = &hb->lock;
#ifdef CONFIG_DEBUG_PI_LIST
q->list.plist.lock = &hb->lock;
#endif
wake_up_state(q->task, TASK_NORMAL);
}
@ -1069,7 +1097,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
set_waiters);
if (ret == 1)
requeue_pi_wake_futex(top_waiter, key2);
requeue_pi_wake_futex(top_waiter, key2, hb2);
return ret;
}
@ -1204,7 +1232,7 @@ retry_private:
double_unlock_hb(hb1, hb2);
put_futex_key(fshared, &key2);
put_futex_key(fshared, &key1);
ret = get_user(curval2, uaddr2);
ret = fault_in_user_writeable(uaddr2);
if (!ret)
goto retry;
goto out;
@ -1228,8 +1256,15 @@ retry_private:
if (!match_futex(&this->key, &key1))
continue;
WARN_ON(!requeue_pi && this->rt_waiter);
WARN_ON(requeue_pi && !this->rt_waiter);
/*
* FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
* be paired with each other and no other futex ops.
*/
if ((requeue_pi && !this->rt_waiter) ||
(!requeue_pi && this->rt_waiter)) {
ret = -EINVAL;
break;
}
/*
* Wake nr_wake waiters. For requeue_pi, if we acquired the
@ -1254,7 +1289,7 @@ retry_private:
this->task, 1);
if (ret == 1) {
/* We got the lock. */
requeue_pi_wake_futex(this, &key2);
requeue_pi_wake_futex(this, &key2, hb2);
continue;
} else if (ret) {
/* -EDEADLK */
@ -1482,7 +1517,7 @@ retry:
handle_fault:
spin_unlock(q->lock_ptr);
ret = get_user(uval, uaddr);
ret = fault_in_user_writeable(uaddr);
spin_lock(q->lock_ptr);
@ -1807,7 +1842,6 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
{
struct hrtimer_sleeper timeout, *to = NULL;
struct futex_hash_bucket *hb;
u32 uval;
struct futex_q q;
int res, ret;
@ -1909,16 +1943,9 @@ out:
return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
/*
* We have to r/w *(int __user *)uaddr, and we have to modify it
* atomically. Therefore, if we continue to fault after get_user()
* below, we need to handle the fault ourselves, while still holding
* the mmap_sem. This can occur if the uaddr is under contention as
* we have to drop the mmap_sem in order to call get_user().
*/
queue_unlock(&q, hb);
ret = get_user(uval, uaddr);
ret = fault_in_user_writeable(uaddr);
if (ret)
goto out_put_key;
@ -2013,17 +2040,10 @@ out:
return ret;
pi_faulted:
/*
* We have to r/w *(int __user *)uaddr, and we have to modify it
* atomically. Therefore, if we continue to fault after get_user()
* below, we need to handle the fault ourselves, while still holding
* the mmap_sem. This can occur if the uaddr is under contention as
* we have to drop the mmap_sem in order to call get_user().
*/
spin_unlock(&hb->lock);
put_futex_key(fshared, &key);
ret = get_user(uval, uaddr);
ret = fault_in_user_writeable(uaddr);
if (!ret)
goto retry;

6
kernel/futex_compat.c
View file

@ -180,7 +180,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
int cmd = op & FUTEX_CMD_MASK;
if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
cmd == FUTEX_WAIT_BITSET)) {
cmd == FUTEX_WAIT_BITSET ||
cmd == FUTEX_WAIT_REQUEUE_PI)) {
if (get_compat_timespec(&ts, utime))
return -EFAULT;
if (!timespec_valid(&ts))
@ -191,7 +192,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
t = ktime_add_safe(ktime_get(), t);
tp = &t;
}
if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE)
if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
val2 = (int) (unsigned long) utime;
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);

110
kernel/hrtimer.c
View file

@ -191,6 +191,46 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
}
}
/*
* Get the preferred target CPU for NOHZ
*/
static int hrtimer_get_target(int this_cpu, int pinned)
{
#ifdef CONFIG_NO_HZ
if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
int preferred_cpu = get_nohz_load_balancer();
if (preferred_cpu >= 0)
return preferred_cpu;
}
#endif
return this_cpu;
}
/*
* With HIGHRES=y we do not migrate the timer when it is expiring
* before the next event on the target cpu because we cannot reprogram
* the target cpu hardware and we would cause it to fire late.
*
* Called with cpu_base->lock of target cpu held.
*/
static int
hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
{
#ifdef CONFIG_HIGH_RES_TIMERS
ktime_t expires;
if (!new_base->cpu_base->hres_active)
return 0;
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
#else
return 0;
#endif
}
/*
* Switch the timer base to the current CPU when possible.
*/
@ -200,16 +240,8 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
{
struct hrtimer_clock_base *new_base;
struct hrtimer_cpu_base *new_cpu_base;
int cpu, preferred_cpu = -1;
cpu = smp_processor_id();
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
preferred_cpu = get_nohz_load_balancer();
if (preferred_cpu >= 0)
cpu = preferred_cpu;
}
#endif
int this_cpu = smp_processor_id();
int cpu = hrtimer_get_target(this_cpu, pinned);
again:
new_cpu_base = &per_cpu(hrtimer_bases, cpu);
@ -217,7 +249,7 @@ again:
if (base != new_base) {
/*
* We are trying to schedule the timer on the local CPU.
* We are trying to move timer to new_base.
* However we can't change timer's base while it is running,
* so we keep it on the same CPU. No hassle vs. reprogramming
* the event source in the high resolution case. The softirq
@ -233,38 +265,12 @@ again:
spin_unlock(&base->cpu_base->lock);
spin_lock(&new_base->cpu_base->lock);
/* Optimized away for NOHZ=n SMP=n */
if (cpu == preferred_cpu) {
/* Calculate clock monotonic expiry time */
#ifdef CONFIG_HIGH_RES_TIMERS
ktime_t expires = ktime_sub(hrtimer_get_expires(timer),
new_base->offset);
#else
ktime_t expires = hrtimer_get_expires(timer);
#endif
/*
* Get the next event on target cpu from the
* clock events layer.
* This covers the highres=off nohz=on case as well.
*/
ktime_t next = clockevents_get_next_event(cpu);
ktime_t delta = ktime_sub(expires, next);
/*
* We do not migrate the timer when it is expiring
* before the next event on the target cpu because
* we cannot reprogram the target cpu hardware and
* we would cause it to fire late.
*/
if (delta.tv64 < 0) {
cpu = smp_processor_id();
spin_unlock(&new_base->cpu_base->lock);
spin_lock(&base->cpu_base->lock);
timer->base = base;
goto again;
}
if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
cpu = this_cpu;
spin_unlock(&new_base->cpu_base->lock);
spin_lock(&base->cpu_base->lock);
timer->base = base;
goto again;
}
timer->base = new_base;
}
@ -1276,14 +1282,22 @@ void hrtimer_interrupt(struct clock_event_device *dev)
expires_next.tv64 = KTIME_MAX;
spin_lock(&cpu_base->lock);
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
* the migration code. This does not affect enqueueing of
* timers which run their callback and need to be requeued on
* this CPU.
*/
cpu_base->expires_next.tv64 = KTIME_MAX;
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
spin_lock(&cpu_base->lock);
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
@ -1316,11 +1330,15 @@ void hrtimer_interrupt(struct clock_event_device *dev)
__run_hrtimer(timer);
}
spin_unlock(&cpu_base->lock);
base++;
}
/*
* Store the new expiry value so the migration code can verify
* against it.
*/
cpu_base->expires_next = expires_next;
spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {

3
kernel/irq/internals.h
View file

@ -42,8 +42,7 @@ static inline void unregister_handler_proc(unsigned int irq,
extern int irq_select_affinity_usr(unsigned int irq);
extern void
irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
extern void irq_set_thread_affinity(struct irq_desc *desc);
/*
* Debugging printout:

72
kernel/irq/manage.c
View file

@ -80,14 +80,22 @@ int irq_can_set_affinity(unsigned int irq)
return 1;
}
void
irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
* @desc: irq descriptor which has affitnity changed
*
* We just set IRQTF_AFFINITY and delegate the affinity setting
* to the interrupt thread itself. We can not call
* set_cpus_allowed_ptr() here as we hold desc->lock and this
* code can be called from hard interrupt context.
*/
void irq_set_thread_affinity(struct irq_desc *desc)
{
struct irqaction *action = desc->action;
while (action) {
if (action->thread)
set_cpus_allowed_ptr(action->thread, cpumask);
set_bit(IRQTF_AFFINITY, &action->thread_flags);
action = action->next;
}
}
@ -112,7 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
if (desc->status & IRQ_MOVE_PCNTXT) {
if (!desc->chip->set_affinity(irq, cpumask)) {
cpumask_copy(desc->affinity, cpumask);
irq_set_thread_affinity(desc, cpumask);
irq_set_thread_affinity(desc);
}
}
else {
@ -122,7 +130,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
#else
if (!desc->chip->set_affinity(irq, cpumask)) {
cpumask_copy(desc->affinity, cpumask);
irq_set_thread_affinity(desc, cpumask);
irq_set_thread_affinity(desc);
}
#endif
desc->status |= IRQ_AFFINITY_SET;
@ -176,7 +184,7 @@ int irq_select_affinity_usr(unsigned int irq)
spin_lock_irqsave(&desc->lock, flags);
ret = setup_affinity(irq, desc);
if (!ret)
irq_set_thread_affinity(desc, desc->affinity);
irq_set_thread_affinity(desc);
spin_unlock_irqrestore(&desc->lock, flags);
return ret;
@ -443,6 +451,39 @@ static int irq_wait_for_interrupt(struct irqaction *action)
return -1;
}
#ifdef CONFIG_SMP
/*
* Check whether we need to change the affinity of the interrupt thread.
*/
static void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
{
cpumask_var_t mask;
if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
return;
/*
* In case we are out of memory we set IRQTF_AFFINITY again and
* try again next time
*/
if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
set_bit(IRQTF_AFFINITY, &action->thread_flags);
return;
}
spin_lock_irq(&desc->lock);
cpumask_copy(mask, desc->affinity);
spin_unlock_irq(&desc->lock);
set_cpus_allowed_ptr(current, mask);
free_cpumask_var(mask);
}
#else
static inline void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif
/*
* Interrupt handler thread
*/
@ -458,6 +499,8 @@ static int irq_thread(void *data)
while (!irq_wait_for_interrupt(action)) {
irq_thread_check_affinity(desc, action);
atomic_inc(&desc->threads_active);
spin_lock_irq(&desc->lock);
@ -718,7 +761,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action, **action_ptr;
struct task_struct *irqthread;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
@ -766,9 +808,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
desc->chip->disable(irq);
}
irqthread = action->thread;
action->thread = NULL;
spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
@ -776,12 +815,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
/* Make sure it's not being used on another CPU: */
synchronize_irq(irq);
if (irqthread) {
if (!test_bit(IRQTF_DIED, &action->thread_flags))
kthread_stop(irqthread);
put_task_struct(irqthread);
}
#ifdef CONFIG_DEBUG_SHIRQ
/*
* It's a shared IRQ -- the driver ought to be prepared for an IRQ
@ -797,6 +830,13 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
local_irq_restore(flags);
}
#endif
if (action->thread) {
if (!test_bit(IRQTF_DIED, &action->thread_flags))
kthread_stop(action->thread);
put_task_struct(action->thread);
}
return action;
}

2
kernel/irq/migration.c
View file

@ -45,7 +45,7 @@ void move_masked_irq(int irq)
< nr_cpu_ids))
if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
cpumask_copy(desc->affinity, desc->pending_mask);
irq_set_thread_affinity(desc, desc->pending_mask);
irq_set_thread_affinity(desc);
}
cpumask_clear(desc->pending_mask);

4
kernel/irq/numa_migrate.c
View file

@ -107,8 +107,8 @@ out_unlock:
struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
{
/* those all static, do move them */
if (desc->irq < NR_IRQS_LEGACY)
/* those static or target node is -1, do not move them */
if (desc->irq < NR_IRQS_LEGACY || node == -1)
return desc;
if (desc->node != node)

2
kernel/kexec.c
View file

@ -1228,7 +1228,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
} while (*cur++ == ',');
if (*crash_size > 0) {
while (*cur != ' ' && *cur != '@')
while (*cur && *cur != ' ' && *cur != '@')
cur++;
if (*cur == '@') {
cur++;

1
kernel/kmod.c
View file

@ -24,7 +24,6 @@
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/mnt_namespace.h>
#include <linux/completion.h>
#include <linux/file.h>
#include <linux/fdtable.h>

8
kernel/kprobes.c
View file

@ -237,13 +237,9 @@ static int __kprobes collect_garbage_slots(void)
{
struct kprobe_insn_page *kip;
struct hlist_node *pos, *next;
int safety;
/* Ensure no-one is preepmted on the garbages */
mutex_unlock(&kprobe_insn_mutex);
safety = check_safety();
mutex_lock(&kprobe_insn_mutex);
if (safety != 0)
if (check_safety())
return -EAGAIN;
hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
@ -698,7 +694,7 @@ int __kprobes register_kprobe(struct kprobe *p)
p->addr = addr;
preempt_disable();
if (!__kernel_text_address((unsigned long) p->addr) ||
if (!kernel_text_address((unsigned long) p->addr) ||
in_kprobes_functions((unsigned long) p->addr)) {
preempt_enable();
return -EINVAL;

10
kernel/kthread.c
View file

@ -180,10 +180,12 @@ EXPORT_SYMBOL(kthread_bind);
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
* waits for it to exit. Your threadfn() must not call do_exit()
* itself if you use this function! This can also be called after
* kthread_create() instead of calling wake_up_process(): the thread
* will exit without calling threadfn().
* waits for it to exit. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
* If threadfn() may call do_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.

3
kernel/lockdep_proc.c
View file

@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void)
&proc_lockdep_stats_operations);
#ifdef CONFIG_LOCK_STAT
proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations);
proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
&proc_lock_stat_operations);
#endif
return 0;

9
kernel/module.c
View file

@ -1068,7 +1068,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
{
const unsigned long *crc;
if (!find_symbol("module_layout", NULL, &crc, true, false))
if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL,
&crc, true, false))
BUG();
return check_version(sechdrs, versindex, "module_layout", mod, crc);
}
@ -2451,9 +2452,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
return ret;
}
if (ret > 0) {
printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
"it should follow 0/-E convention\n"
KERN_WARNING "%s: loading module anyway...\n",
printk(KERN_WARNING
"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
"%s: loading module anyway...\n",
__func__, mod->name, ret,
__func__);
dump_stack();

1
kernel/panic.c
View file

@ -301,6 +301,7 @@ int oops_may_print(void)
*/
void oops_enter(void)
{
tracing_off();
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
do_oops_enter_exit();

1128
kernel/perf_counter.c
View file

File diff suppressed because it is too large Load diff

7
kernel/posix-cpu-timers.c
View file

@ -521,11 +521,12 @@ void posix_cpu_timers_exit(struct task_struct *tsk)
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
struct task_cputime cputime;
struct signal_struct *const sig = tsk->signal;
thread_group_cputimer(tsk, &cputime);
cleanup_timers(tsk->signal->cpu_timers,
cputime.utime, cputime.stime, cputime.sum_exec_runtime);
cputime_add(tsk->utime, sig->utime),
cputime_add(tsk->stime, sig->stime),
tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
}
static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)

7
kernel/posix-timers.c
View file

@ -202,6 +202,12 @@ static int no_timer_create(struct k_itimer *new_timer)
return -EOPNOTSUPP;
}
static int no_nsleep(const clockid_t which_clock, int flags,
struct timespec *tsave, struct timespec __user *rmtp)
{
return -EOPNOTSUPP;
}
/*
* Return nonzero if we know a priori this clockid_t value is bogus.
*/
@ -254,6 +260,7 @@ static __init int init_posix_timers(void)
.clock_get = posix_get_monotonic_raw,
.clock_set = do_posix_clock_nosettime,
.timer_create = no_timer_create,
.nsleep = no_nsleep,
};
register_posix_clock(CLOCK_REALTIME, &clock_realtime);

1
kernel/power/user.c
View file

@ -23,7 +23,6 @@
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
#include <linux/smp_lock.h>
#include <scsi/scsi_scan.h>
#include <asm/uaccess.h>

5
kernel/profile.c
View file

@ -117,11 +117,12 @@ int __ref profile_init(void)
cpumask_copy(prof_cpu_mask, cpu_possible_mask);
prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
if (prof_buffer)
return 0;
prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
prof_buffer = alloc_pages_exact(buffer_bytes,
GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
if (prof_buffer)
return 0;

4
kernel/ptrace.c
View file

@ -181,8 +181,8 @@ int ptrace_attach(struct task_struct *task)
* interference; SUID, SGID and LSM creds get determined differently
* under ptrace.
*/
retval = mutex_lock_interruptible(&task->cred_guard_mutex);
if (retval < 0)
retval = -ERESTARTNOINTR;
if (mutex_lock_interruptible(&task->cred_guard_mutex))
goto out;
task_lock(task);

2
kernel/resource.c
View file

@ -787,7 +787,7 @@ static int __init reserve_setup(char *str)
static struct resource reserve[MAXRESERVE];
for (;;) {
int io_start, io_num;
unsigned int io_start, io_num;
int x = reserved;
if (get_option (&str, &io_start) != 2)

4
kernel/rtmutex.c
View file

@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
/* We got the lock for task. */
debug_rt_mutex_lock(lock);
rt_mutex_set_owner(lock, task, 0);
spin_unlock(&lock->wait_lock);
rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
if (ret && !waiter->task) {
/*
* Reset the return value. We might have

61
kernel/sched.c
View file

@ -493,6 +493,7 @@ struct rt_rq {
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
#endif
@ -2571,15 +2572,37 @@ static void __sched_fork(struct task_struct *p)
p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
p->se.sum_sleep_runtime = 0;
p->se.sleep_start = 0;
p->se.block_start = 0;
p->se.sleep_max = 0;
p->se.block_max = 0;
p->se.exec_max = 0;
p->se.slice_max = 0;
p->se.wait_max = 0;
p->se.wait_start = 0;
p->se.wait_max = 0;
p->se.wait_count = 0;
p->se.wait_sum = 0;
p->se.sleep_start = 0;
p->se.sleep_max = 0;
p->se.sum_sleep_runtime = 0;
p->se.block_start = 0;
p->se.block_max = 0;
p->se.exec_max = 0;
p->se.slice_max = 0;
p->se.nr_migrations_cold = 0;
p->se.nr_failed_migrations_affine = 0;
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
p->se.nr_wakeups_migrate = 0;
p->se.nr_wakeups_local = 0;
p->se.nr_wakeups_remote = 0;
p->se.nr_wakeups_affine = 0;
p->se.nr_wakeups_affine_attempts = 0;
p->se.nr_wakeups_passive = 0;
p->se.nr_wakeups_idle = 0;
#endif
INIT_LIST_HEAD(&p->rt.run_list);
@ -6541,6 +6564,11 @@ SYSCALL_DEFINE0(sched_yield)
return 0;
}
static inline int should_resched(void)
{
return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
}
static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@ -6560,8 +6588,7 @@ static void __cond_resched(void)
int __sched _cond_resched(void)
{
if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
system_state == SYSTEM_RUNNING) {
if (should_resched()) {
__cond_resched();
return 1;
}
@ -6579,12 +6606,12 @@ EXPORT_SYMBOL(_cond_resched);
*/
int cond_resched_lock(spinlock_t *lock)
{
int resched = need_resched() && system_state == SYSTEM_RUNNING;
int resched = should_resched();
int ret = 0;
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched && need_resched())
if (resched)
__cond_resched();
else
cpu_relax();
@ -6599,7 +6626,7 @@ int __sched cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
if (need_resched() && system_state == SYSTEM_RUNNING) {
if (should_resched()) {
local_bh_enable();
__cond_resched();
local_bh_disable();
@ -7277,6 +7304,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
static void calc_global_load_remove(struct rq *rq)
{
atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
rq->calc_load_active = 0;
}
#endif /* CONFIG_HOTPLUG_CPU */
@ -7503,6 +7531,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
task_rq_unlock(rq, &flags);
get_task_struct(p);
cpu_rq(cpu)->migration_thread = p;
rq->calc_load_update = calc_load_update;
break;
case CPU_ONLINE:
@ -7513,8 +7542,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
/* Update our root-domain */
rq = cpu_rq(cpu);
spin_lock_irqsave(&rq->lock, flags);
rq->calc_load_update = calc_load_update;
rq->calc_load_active = 0;
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@ -9085,7 +9112,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;

15
kernel/sched_cpupri.c
View file

@ -81,8 +81,21 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
if (lowest_mask)
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
/*
* We have to ensure that we have at least one bit
* still set in the array, since the map could have
* been concurrently emptied between the first and
* second reads of vec->mask. If we hit this
* condition, simply act as though we never hit this
* priority level and continue on.
*/
if (cpumask_any(lowest_mask) >= nr_cpu_ids)
continue;
}
return 1;
}

45
kernel/sched_fair.c
View file

@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
return min_vruntime;
}
static inline int entity_before(struct sched_entity *a,
struct sched_entity *b)
{
return (s64)(a->vruntime - b->vruntime) < 0;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return se->vruntime - cfs_rq->min_vruntime;
@ -605,9 +611,13 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
struct task_struct *tsk = NULL;
if (entity_is_task(se))
tsk = task_of(se);
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@ -618,11 +628,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
account_scheduler_latency(tsk, delta >> 10, 1);
if (tsk)
account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@ -633,17 +643,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->block_start = 0;
se->sum_sleep_runtime += delta;
/*
* Blocking time is in units of nanosecs, so shift by 20 to
* get a milliseconds-range estimation of the amount of
* time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
delta >> 20);
if (tsk) {
/*
* Blocking time is in units of nanosecs, so shift by
* 20 to get a milliseconds-range estimation of the
* amount of time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING,
(void *)get_wchan(tsk),
delta >> 20);
}
account_scheduler_latency(tsk, delta >> 10, 0);
}
account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
@ -687,7 +699,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
* all of which have the same weight.
*/
if (sched_feat(NORMALIZED_SLEEPER) &&
task_of(se)->policy != SCHED_IDLE)
(!entity_is_task(se) ||
task_of(se)->policy != SCHED_IDLE))
thresh = calc_delta_fair(thresh, se);
vruntime -= thresh;
@ -1016,7 +1029,7 @@ static void yield_task_fair(struct rq *rq)
/*
* Already in the rightmost position?
*/
if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
if (unlikely(!rightmost || entity_before(rightmost, se)))
return;
/*
@ -1712,7 +1725,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
/* 'curr' will be NULL if the child belongs to a different group */
if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
curr && curr->vruntime < se->vruntime) {
curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.

18
kernel/sched_rt.c
View file

@ -10,6 +10,8 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
#ifdef CONFIG_RT_GROUP_SCHED
#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return rt_rq->rq;
@ -22,6 +24,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
#else /* CONFIG_RT_GROUP_SCHED */
#define rt_entity_is_task(rt_se) (1)
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return container_of(rt_rq, struct rq, rt);
@ -73,7 +77,7 @@ static inline void rt_clear_overload(struct rq *rq)
static void update_rt_migration(struct rt_rq *rt_rq)
{
if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
if (!rt_rq->overloaded) {
rt_set_overload(rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 1;
@ -86,6 +90,12 @@ static void update_rt_migration(struct rt_rq *rt_rq)
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
if (!rt_entity_is_task(rt_se))
return;
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total++;
if (rt_se->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
@ -94,6 +104,12 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
if (!rt_entity_is_task(rt_se))
return;
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total--;
if (rt_se->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;

25
kernel/signal.c
View file

@ -2454,11 +2454,9 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
stack_t oss;
int error;
if (uoss) {
oss.ss_sp = (void __user *) current->sas_ss_sp;
oss.ss_size = current->sas_ss_size;
oss.ss_flags = sas_ss_flags(sp);
}
oss.ss_sp = (void __user *) current->sas_ss_sp;
oss.ss_size = current->sas_ss_size;
oss.ss_flags = sas_ss_flags(sp);
if (uss) {
void __user *ss_sp;
@ -2466,10 +2464,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
int ss_flags;
error = -EFAULT;
if (!access_ok(VERIFY_READ, uss, sizeof(*uss))
|| __get_user(ss_sp, &uss->ss_sp)
|| __get_user(ss_flags, &uss->ss_flags)
|| __get_user(ss_size, &uss->ss_size))
if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
goto out;
error = __get_user(ss_sp, &uss->ss_sp) |
__get_user(ss_flags, &uss->ss_flags) |
__get_user(ss_size, &uss->ss_size);
if (error)
goto out;
error = -EPERM;
@ -2501,13 +2501,16 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
current->sas_ss_size = ss_size;
}
error = 0;
if (uoss) {
error = -EFAULT;
if (copy_to_user(uoss, &oss, sizeof(oss)))
if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss)))
goto out;
error = __put_user(oss.ss_sp, &uoss->ss_sp) |
__put_user(oss.ss_size, &uoss->ss_size) |
__put_user(oss.ss_flags, &uoss->ss_flags);
}
error = 0;
out:
return error;
}

2
kernel/smp.c
View file

@ -57,7 +57,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
return NOTIFY_BAD;
break;
#ifdef CONFIG_CPU_HOTPLUG
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:

64
kernel/softirq.c
View file

@ -345,7 +345,9 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
softirq_vec[nr].action = action;
}
/* Tasklets */
/*
* Tasklets
*/
struct tasklet_head
{
struct tasklet_struct *head;
@ -493,6 +495,66 @@ void tasklet_kill(struct tasklet_struct *t)
EXPORT_SYMBOL(tasklet_kill);
/*
* tasklet_hrtimer
*/
/*
* The trampoline is called when the hrtimer expires. If this is
* called from the hrtimer interrupt then we schedule the tasklet as
* the timer callback function expects to run in softirq context. If
* it's called in softirq context anyway (i.e. high resolution timers
* disabled) then the hrtimer callback is called right away.
*/
static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
{
struct tasklet_hrtimer *ttimer =
container_of(timer, struct tasklet_hrtimer, timer);
if (hrtimer_is_hres_active(timer)) {
tasklet_hi_schedule(&ttimer->tasklet);
return HRTIMER_NORESTART;
}
return ttimer->function(timer);
}
/*
* Helper function which calls the hrtimer callback from
* tasklet/softirq context
*/
static void __tasklet_hrtimer_trampoline(unsigned long data)
{
struct tasklet_hrtimer *ttimer = (void *)data;
enum hrtimer_restart restart;
restart = ttimer->function(&ttimer->timer);
if (restart != HRTIMER_NORESTART)
hrtimer_restart(&ttimer->timer);
}
/**
* tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
* @ttimer: tasklet_hrtimer which is initialized
* @function: hrtimer callback funtion which gets called from softirq context
* @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
* @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
*/
void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t which_clock, enum hrtimer_mode mode)
{
hrtimer_init(&ttimer->timer, which_clock, mode);
ttimer->timer.function = __hrtimer_tasklet_trampoline;
tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
(unsigned long)ttimer);
ttimer->function = function;
}
EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
/*
* Remote softirq bits
*/
DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
EXPORT_PER_CPU_SYMBOL(softirq_work_list);

13
kernel/sysctl.c
View file

@ -335,7 +335,10 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = &proc_dointvec,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
@ -743,6 +746,14 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec,
},
{
.ctl_name = CTL_UNNUMBERED,
.procname = "panic_on_io_nmi",
.data = &panic_on_io_nmi,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec,
},
{
.ctl_name = KERN_BOOTLOADER_TYPE,
.procname = "bootloader_type",

11
kernel/time/clockevents.c
View file

@ -254,15 +254,4 @@ void clockevents_notify(unsigned long reason, void *arg)
spin_unlock(&clockevents_lock);
}
EXPORT_SYMBOL_GPL(clockevents_notify);
ktime_t clockevents_get_next_event(int cpu)
{
struct tick_device *td;
struct clock_event_device *dev;
td = &per_cpu(tick_cpu_device, cpu);
dev = td->evtdev;
return dev->next_event;
}
#endif

2
kernel/time/clocksource.c
View file

@ -513,7 +513,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
* Check to make sure we don't switch to a non-highres capable
* clocksource if the tick code is in oneshot mode (highres or nohz)
*/
if (tick_oneshot_mode_active() &&
if (tick_oneshot_mode_active() && ovr &&
!(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) {
printk(KERN_WARNING "%s clocksource is not HRT compatible. "
"Cannot switch while in HRT/NOHZ mode\n", ovr->name);

16
kernel/time/timer_stats.c
View file

@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex);
/*
* Collection status, active/inactive:
*/
static int __read_mostly active;
int __read_mostly timer_stats_active;
/*
* Beginning/end timestamps of measurement:
@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
struct entry *entry, input;
unsigned long flags;
if (likely(!active))
if (likely(!timer_stats_active))
return;
lock = &per_cpu(lookup_lock, raw_smp_processor_id());
@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
input.timer_flag = timer_flag;
spin_lock_irqsave(lock, flags);
if (!active)
if (!timer_stats_active)
goto out_unlock;
entry = tstat_lookup(&input, comm);
@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v)
/*
* If still active then calculate up to now:
*/
if (active)
if (timer_stats_active)
time_stop = ktime_get();
time = ktime_sub(time_stop, time_start);
@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf,
mutex_lock(&show_mutex);
switch (ctl[0]) {
case '0':
if (active) {
active = 0;
if (timer_stats_active) {
timer_stats_active = 0;
time_stop = ktime_get();
sync_access();
}
break;
case '1':
if (!active) {
if (!timer_stats_active) {
reset_entries();
time_start = ktime_get();
smp_mb();
active = 1;
timer_stats_active = 1;
}
break;
default:

4
kernel/timer.c
View file

@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer)
{
unsigned int flag = 0;
if (likely(!timer->start_site))
return;
if (unlikely(tbase_get_deferrable(timer->base)))
flag |= TIMER_STATS_FLAG_DEFERRABLE;
@ -712,7 +714,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
* networking code - if the timer is re-modified
* to be the same thing then just return:
*/
if (timer->expires == expires && timer_pending(timer))
if (timer_pending(timer) && timer->expires == expires)
return 1;
return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);

6
kernel/trace/Kconfig
View file

@ -226,13 +226,13 @@ config BOOT_TRACER
the timings of the initcalls and traces key events and the identity
of tasks that can cause boot delays, such as context-switches.
Its aim is to be parsed by the /scripts/bootgraph.pl tool to
Its aim is to be parsed by the scripts/bootgraph.pl tool to
produce pretty graphics about boot inefficiencies, giving a visual
representation of the delays during initcalls - but the raw
/debug/tracing/trace text output is readable too.
You must pass in ftrace=initcall to the kernel command line
to enable this on bootup.
You must pass in initcall_debug and ftrace=initcall to the kernel
command line to enable this on bootup.
config TRACE_BRANCH_PROFILING
bool

13
kernel/trace/blktrace.c
View file

@ -22,6 +22,7 @@
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/smp_lock.h>
#include <linux/time.h>
#include <linux/uaccess.h>
@ -266,8 +267,8 @@ static void blk_trace_free(struct blk_trace *bt)
{
debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
debugfs_remove(bt->dir);
relay_close(bt->rchan);
debugfs_remove(bt->dir);
free_percpu(bt->sequence);
free_percpu(bt->msg_data);
kfree(bt);
@ -377,18 +378,8 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
static int blk_remove_buf_file_callback(struct dentry *dentry)
{
struct dentry *parent = dentry->d_parent;
debugfs_remove(dentry);
/*
* this will fail for all but the last file, but that is ok. what we
* care about is the top level buts->name directory going away, when
* the last trace file is gone. Then we don't have to rmdir() that
* manually on trace stop, so it nicely solves the issue with
* force killing of running traces.
*/
debugfs_remove(parent);
return 0;
}

84
kernel/trace/ftrace.c
View file

@ -291,7 +291,9 @@ function_stat_next(void *v, int idx)
pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
again:
rec++;
if (idx != 0)
rec++;
if ((void *)rec >= (void *)&pg->records[pg->index]) {
pg = pg->next;
if (!pg)
@ -766,7 +768,7 @@ static struct tracer_stat function_stats __initdata = {
.stat_show = function_stat_show
};
static void ftrace_profile_debugfs(struct dentry *d_tracer)
static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
{
struct ftrace_profile_stat *stat;
struct dentry *entry;
@ -784,7 +786,6 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
* The files created are permanent, if something happens
* we still do not free memory.
*/
kfree(stat);
WARN(1,
"Could not allocate stat file for cpu %d\n",
cpu);
@ -811,7 +812,7 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
}
#else /* CONFIG_FUNCTION_PROFILER */
static void ftrace_profile_debugfs(struct dentry *d_tracer)
static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
{
}
#endif /* CONFIG_FUNCTION_PROFILER */
@ -1417,10 +1418,20 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
loff_t l;
if (!(iter->flags & FTRACE_ITER_HASH))
*pos = 0;
iter->flags |= FTRACE_ITER_HASH;
return t_hash_next(m, p, pos);
iter->hidx = 0;
for (l = 0; l <= *pos; ) {
p = t_hash_next(m, p, &l);
if (!p)
break;
}
return p;
}
static int t_hash_show(struct seq_file *m, void *v)
@ -1467,8 +1478,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
iter->pg = iter->pg->next;
iter->idx = 0;
goto retry;
} else {
iter->idx = -1;
}
} else {
rec = &iter->pg->records[iter->idx++];
@ -1497,6 +1506,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
loff_t l;
mutex_lock(&ftrace_lock);
/*
@ -1508,23 +1518,21 @@ static void *t_start(struct seq_file *m, loff_t *pos)
if (*pos > 0)
return t_hash_start(m, pos);
iter->flags |= FTRACE_ITER_PRINTALL;
(*pos)++;
return iter;
}
if (iter->flags & FTRACE_ITER_HASH)
return t_hash_start(m, pos);
if (*pos > 0) {
if (iter->idx < 0)
return p;
(*pos)--;
iter->idx--;
iter->pg = ftrace_pages_start;
iter->idx = 0;
for (l = 0; l <= *pos; ) {
p = t_next(m, p, &l);
if (!p)
break;
}
p = t_next(m, p, pos);
if (!p)
if (!p && iter->flags & FTRACE_ITER_FILTER)
return t_hash_start(m, pos);
return p;
@ -1654,7 +1662,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
mutex_lock(&ftrace_regex_lock);
if ((file->f_mode & FMODE_WRITE) &&
!(file->f_flags & O_APPEND))
(file->f_flags & O_TRUNC))
ftrace_filter_reset(enable);
if (file->f_mode & FMODE_READ) {
@ -2500,32 +2508,31 @@ int ftrace_graph_count;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
static void *
g_next(struct seq_file *m, void *v, loff_t *pos)
__g_next(struct seq_file *m, loff_t *pos)
{
unsigned long *array = m->private;
int index = *pos;
(*pos)++;
if (index >= ftrace_graph_count)
if (*pos >= ftrace_graph_count)
return NULL;
return &array[*pos];
}
return &array[index];
static void *
g_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return __g_next(m, pos);
}
static void *g_start(struct seq_file *m, loff_t *pos)
{
void *p = NULL;
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
if (!ftrace_graph_count && !*pos)
return (void *)1;
p = g_next(m, p, pos);
return p;
return __g_next(m, pos);
}
static void g_stop(struct seq_file *m, void *p)
@ -2570,7 +2577,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
!(file->f_flags & O_APPEND)) {
(file->f_flags & O_TRUNC)) {
ftrace_graph_count = 0;
memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
}
@ -2588,6 +2595,14 @@ ftrace_graph_open(struct inode *inode, struct file *file)
return ret;
}
static int
ftrace_graph_release(struct inode *inode, struct file *file)
{
if (file->f_mode & FMODE_READ)
seq_release(inode, file);
return 0;
}
static int
ftrace_set_func(unsigned long *array, int *idx, char *buffer)
{
@ -2717,9 +2732,10 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
}
static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
.release = ftrace_graph_release,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@ -3152,10 +3168,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
goto out;
last_ftrace_enabled = ftrace_enabled;
last_ftrace_enabled = !!ftrace_enabled;
if (ftrace_enabled) {

26
kernel/trace/ring_buffer.c
View file

@ -735,6 +735,7 @@ ring_buffer_free(struct ring_buffer *buffer)
put_online_cpus();
kfree(buffer->buffers);
free_cpumask_var(buffer->cpumask);
kfree(buffer);
@ -1563,6 +1564,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
return NULL;
}
#ifdef CONFIG_TRACING
#define TRACE_RECURSIVE_DEPTH 16
static int trace_recursive_lock(void)
@ -1593,6 +1596,13 @@ static void trace_recursive_unlock(void)
current->trace_recursion--;
}
#else
#define trace_recursive_lock() (0)
#define trace_recursive_unlock() do { } while (0)
#endif
static DEFINE_PER_CPU(int, rb_need_resched);
/**
@ -1776,7 +1786,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
*/
RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
if (!rb_try_to_discard(cpu_buffer, event))
if (rb_try_to_discard(cpu_buffer, event))
goto out;
/*
@ -2374,7 +2384,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
* the box. Return the padding, and we will release
* the current locks, and try again.
*/
rb_advance_reader(cpu_buffer);
return event;
case RINGBUF_TYPE_TIME_EXTEND:
@ -2477,7 +2486,7 @@ static inline int rb_ok_to_lock(void)
* buffer too. A one time deal is all you get from reading
* the ring buffer from an NMI.
*/
if (likely(!in_nmi() && !oops_in_progress))
if (likely(!in_nmi()))
return 1;
tracing_off_permanent();
@ -2510,6 +2519,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
if (dolock)
spin_lock(&cpu_buffer->reader_lock);
event = rb_buffer_peek(buffer, cpu, ts);
if (event && event->type_len == RINGBUF_TYPE_PADDING)
rb_advance_reader(cpu_buffer);
if (dolock)
spin_unlock(&cpu_buffer->reader_lock);
local_irq_restore(flags);
@ -2581,12 +2592,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
spin_lock(&cpu_buffer->reader_lock);
event = rb_buffer_peek(buffer, cpu, ts);
if (!event)
goto out_unlock;
if (event)
rb_advance_reader(cpu_buffer);
rb_advance_reader(cpu_buffer);
out_unlock:
if (dolock)
spin_unlock(&cpu_buffer->reader_lock);
local_irq_restore(flags);
@ -3104,6 +3112,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(ring_buffer_read_page);
#ifdef CONFIG_TRACING
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
@ -3171,6 +3180,7 @@ static __init int rb_init_debugfs(void)
}
fs_initcall(rb_init_debugfs);
#endif
#ifdef CONFIG_HOTPLUG_CPU
static int rb_cpu_notify(struct notifier_block *self,

37
kernel/trace/trace.c
View file

@ -17,6 +17,7 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@ -284,13 +285,12 @@ void trace_wake_up(void)
static int __init set_buf_size(char *str)
{
unsigned long buf_size;
int ret;
if (!str)
return 0;
ret = strict_strtoul(str, 0, &buf_size);
buf_size = memparse(str, &str);
/* nr_entries can not be zero */
if (ret < 0 || buf_size == 0)
if (buf_size == 0)
return 0;
trace_buf_size = buf_size;
return 1;
@ -848,6 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
}
EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
int type,
@ -2031,7 +2032,7 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) &&
!(file->f_flags & O_APPEND)) {
(file->f_flags & O_TRUNC)) {
long cpu = (long) inode->i_private;
if (cpu == TRACE_PIPE_ALL_CPU)
@ -2053,25 +2054,23 @@ static int tracing_open(struct inode *inode, struct file *file)
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
struct tracer *t = m->private;
struct tracer *t = v;
(*pos)++;
if (t)
t = t->next;
m->private = t;
return t;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
struct tracer *t = m->private;
struct tracer *t;
loff_t l = 0;
mutex_lock(&trace_types_lock);
for (; t && l < *pos; t = t_next(m, t, &l))
for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
;
return t;
@ -2107,18 +2106,10 @@ static struct seq_operations show_traces_seq_ops = {
static int show_traces_open(struct inode *inode, struct file *file)
{
int ret;
if (tracing_disabled)
return -ENODEV;
ret = seq_open(file, &show_traces_seq_ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = trace_types;
}
return ret;
return seq_open(file, &show_traces_seq_ops);
}
static ssize_t
@ -3095,7 +3086,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
break;
}
trace_consume(iter);
if (ret != TRACE_TYPE_NO_CONSUME)
trace_consume(iter);
rem -= count;
if (!find_next_entry_inc(iter)) {
rem = 0;
@ -4243,8 +4235,11 @@ static void __ftrace_dump(bool disable_tracing)
iter.pos = -1;
if (find_next_entry_inc(&iter) != NULL) {
print_trace_line(&iter);
trace_consume(&iter);
int ret;
ret = print_trace_line(&iter);
if (ret != TRACE_TYPE_NO_CONSUME)
trace_consume(&iter);
}
trace_printk_seq(&iter.seq);

11
kernel/trace/trace.h
View file

@ -438,10 +438,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
int *ent_cpu, u64 *ent_ts);
void tracing_generic_entry_update(struct trace_entry *entry,
unsigned long flags,
int pc);
void default_wait_pipe(struct trace_iterator *iter);
void poll_wait_pipe(struct trace_iterator *iter);
@ -597,6 +593,7 @@ print_graph_function(struct trace_iterator *iter)
extern struct pid *ftrace_pid_trace;
#ifdef CONFIG_FUNCTION_TRACER
static inline int ftrace_trace_task(struct task_struct *task)
{
if (!ftrace_pid_trace)
@ -604,6 +601,12 @@ static inline int ftrace_trace_task(struct task_struct *task)
return test_tsk_trace_trace(task);
}
#else
static inline int ftrace_trace_task(struct task_struct *task)
{
return 1;
}
#endif
/*
* trace_iterator_flags is an enumeration that defines bit

2
kernel/trace/trace_event_profile.c
View file

@ -14,7 +14,7 @@ int ftrace_profile_enable(int event_id)
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
if (event->id == event_id) {
if (event->id == event_id && event->profile_enable) {
ret = event->profile_enable(event);
break;
}

3
kernel/trace/trace_event_types.h
View file

@ -26,6 +26,9 @@ TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
ftrace_graph_ret_entry, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned long, ret.func, func)
TRACE_FIELD(unsigned long long, ret.calltime, calltime)
TRACE_FIELD(unsigned long long, ret.rettime, rettime)
TRACE_FIELD(unsigned long, ret.overrun, overrun)
TRACE_FIELD(int, ret.depth, depth)
),
TP_RAW_FMT("<-- %lx (%d)")

32
kernel/trace/trace_events.c
View file

@ -300,10 +300,18 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_event_call *call = NULL;
loff_t l;
mutex_lock(&event_mutex);
if (*pos == 0)
m->private = ftrace_events.next;
return t_next(m, NULL, pos);
m->private = ftrace_events.next;
for (l = 0; l <= *pos; ) {
call = t_next(m, NULL, &l);
if (!call)
break;
}
return call;
}
static void *
@ -332,10 +340,18 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
static void *s_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_event_call *call = NULL;
loff_t l;
mutex_lock(&event_mutex);
if (*pos == 0)
m->private = ftrace_events.next;
return s_next(m, NULL, pos);
m->private = ftrace_events.next;
for (l = 0; l <= *pos; ) {
call = s_next(m, NULL, &l);
if (!call)
break;
}
return call;
}
static int t_show(struct seq_file *m, void *v)
@ -360,7 +376,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
!(file->f_flags & O_APPEND))
(file->f_flags & O_TRUNC))
ftrace_clear_events();
seq_ops = inode->i_private;
@ -924,7 +940,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
entry = trace_create_file("enable", 0644, call->dir, call,
enable);
if (call->id)
if (call->id && call->profile_enable)
entry = trace_create_file("id", 0444, call->dir, call,
id);

20
kernel/trace/trace_events_filter.c
View file

@ -624,9 +624,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
return -ENOSPC;
}
filter->preds[filter->n_preds] = pred;
filter->n_preds++;
list_for_each_entry(call, &ftrace_events, list) {
if (!call->define_fields)
@ -643,6 +640,9 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
}
replace_filter_string(call->filter, filter_string);
}
filter->preds[filter->n_preds] = pred;
filter->n_preds++;
out:
return err;
}
@ -1029,12 +1029,17 @@ static int replace_preds(struct event_subsystem *system,
if (elt->op == OP_AND || elt->op == OP_OR) {
pred = create_logical_pred(elt->op);
if (!pred)
return -ENOMEM;
if (call) {
err = filter_add_pred(ps, call, pred);
filter_free_pred(pred);
} else
} else {
err = filter_add_subsystem_pred(ps, system,
pred, filter_string);
if (err)
filter_free_pred(pred);
}
if (err)
return err;
@ -1048,12 +1053,17 @@ static int replace_preds(struct event_subsystem *system,
}
pred = create_pred(elt->op, operand1, operand2);
if (!pred)
return -ENOMEM;
if (call) {
err = filter_add_pred(ps, call, pred);
filter_free_pred(pred);
} else
} else {
err = filter_add_subsystem_pred(ps, system, pred,
filter_string);
if (err)
filter_free_pred(pred);
}
if (err)
return err;

5
kernel/trace/trace_functions.c
View file

@ -302,8 +302,7 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
if (count == -1)
seq_printf(m, ":unlimited\n");
else
seq_printf(m, ":count=%ld", count);
seq_putc(m, '\n');
seq_printf(m, ":count=%ld\n", count);
return 0;
}
@ -364,7 +363,7 @@ ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
out_reg:
ret = register_ftrace_function_probe(glob, ops, count);
return ret;
return ret < 0 ? ret : 0;
}
static struct ftrace_func_command ftrace_traceon_cmd = {

11
kernel/trace/trace_functions_graph.c
View file

@ -843,9 +843,16 @@ print_graph_function(struct trace_iterator *iter)
switch (entry->type) {
case TRACE_GRAPH_ENT: {
struct ftrace_graph_ent_entry *field;
/*
* print_graph_entry() may consume the current event,
* thus @field may become invalid, so we need to save it.
* sizeof(struct ftrace_graph_ent_entry) is very small,
* it can be safely saved at the stack.
*/
struct ftrace_graph_ent_entry *field, saved;
trace_assign_type(field, entry);
return print_graph_entry(field, s, iter);
saved = *field;
return print_graph_entry(&saved, s, iter);
}
case TRACE_GRAPH_RET: {
struct ftrace_graph_ret_entry *field;

3
kernel/trace/trace_output.c
View file

@ -27,8 +27,7 @@ void trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
s->buffer[len] = 0;
seq_puts(m, s->buffer);
seq_write(m, s->buffer, len);
trace_seq_init(s);
}

28
kernel/trace/trace_printk.c
View file

@ -155,25 +155,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
EXPORT_SYMBOL_GPL(__ftrace_vprintk);
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
t_start(struct seq_file *m, loff_t *pos)
{
const char **fmt = m->private;
const char **next = fmt;
(*pos)++;
const char **fmt = __start___trace_bprintk_fmt + *pos;
if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
return NULL;
next = fmt;
m->private = ++next;
return fmt;
}
static void *t_start(struct seq_file *m, loff_t *pos)
static void *t_next(struct seq_file *m, void * v, loff_t *pos)
{
return t_next(m, NULL, pos);
(*pos)++;
return t_start(m, pos);
}
static int t_show(struct seq_file *m, void *v)
@ -182,7 +176,7 @@ static int t_show(struct seq_file *m, void *v)
const char *str = *fmt;
int i;
seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
/*
* Tabs and new lines need to be converted.
@ -224,15 +218,7 @@ static const struct seq_operations show_format_seq_ops = {
static int
ftrace_formats_open(struct inode *inode, struct file *file)
{
int ret;
ret = seq_open(file, &show_format_seq_ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = __start___trace_bprintk_fmt;
}
return ret;
return seq_open(file, &show_format_seq_ops);
}
static const struct file_operations ftrace_formats_fops = {

11
kernel/trace/trace_stack.c
View file

@ -301,17 +301,14 @@ static const struct seq_operations stack_trace_seq_ops = {
static int stack_trace_open(struct inode *inode, struct file *file)
{
int ret;
ret = seq_open(file, &stack_trace_seq_ops);
return ret;
return seq_open(file, &stack_trace_seq_ops);
}
static const struct file_operations stack_trace_fops = {
.open = stack_trace_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
int
@ -326,10 +323,10 @@ stack_trace_sysctl(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
if (ret || !write ||
(last_stack_tracer_enabled == stack_tracer_enabled))
(last_stack_tracer_enabled == !!stack_tracer_enabled))
goto out;
last_stack_tracer_enabled = stack_tracer_enabled;
last_stack_tracer_enabled = !!stack_tracer_enabled;
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);

40
kernel/trace/trace_stat.c
View file

@ -73,7 +73,7 @@ static struct rb_node *release_next(struct rb_node *node)
}
}
static void reset_stat_session(struct stat_session *session)
static void __reset_stat_session(struct stat_session *session)
{
struct rb_node *node = session->stat_root.rb_node;
@ -83,10 +83,17 @@ static void reset_stat_session(struct stat_session *session)
session->stat_root = RB_ROOT;
}
static void reset_stat_session(struct stat_session *session)
{
mutex_lock(&session->stat_mutex);
__reset_stat_session(session);
mutex_unlock(&session->stat_mutex);
}
static void destroy_session(struct stat_session *session)
{
debugfs_remove(session->file);
reset_stat_session(session);
__reset_stat_session(session);
mutex_destroy(&session->stat_mutex);
kfree(session);
}
@ -150,7 +157,7 @@ static int stat_seq_init(struct stat_session *session)
int i;
mutex_lock(&session->stat_mutex);
reset_stat_session(session);
__reset_stat_session(session);
if (!ts->stat_cmp)
ts->stat_cmp = dummy_cmp;
@ -183,7 +190,7 @@ exit:
return ret;
exit_free_rbtree:
reset_stat_session(session);
__reset_stat_session(session);
mutex_unlock(&session->stat_mutex);
return ret;
}
@ -199,17 +206,13 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
mutex_lock(&session->stat_mutex);
/* If we are in the beginning of the file, print the headers */
if (!*pos && session->ts->stat_headers) {
(*pos)++;
if (!*pos && session->ts->stat_headers)
return SEQ_START_TOKEN;
}
node = rb_first(&session->stat_root);
for (i = 0; node && i < *pos; i++)
node = rb_next(node);
(*pos)++;
return node;
}
@ -254,16 +257,21 @@ static const struct seq_operations trace_stat_seq_ops = {
static int tracing_stat_open(struct inode *inode, struct file *file)
{
int ret;
struct seq_file *m;
struct stat_session *session = inode->i_private;
ret = stat_seq_init(session);
if (ret)
return ret;
ret = seq_open(file, &trace_stat_seq_ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = session;
ret = stat_seq_init(session);
if (ret) {
reset_stat_session(session);
return ret;
}
m = file->private_data;
m->private = session;
return ret;
}
@ -274,11 +282,9 @@ static int tracing_stat_release(struct inode *i, struct file *f)
{
struct stat_session *session = i->i_private;
mutex_lock(&session->stat_mutex);
reset_stat_session(session);
mutex_unlock(&session->stat_mutex);
return 0;
return seq_release(i, f);
}
static const struct file_operations tracing_stat_fops = {

5
kernel/wait.c
View file

@ -10,13 +10,14 @@
#include <linux/wait.h>
#include <linux/hash.h>
void init_waitqueue_head(wait_queue_head_t *q)
void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *key)
{
spin_lock_init(&q->lock);
lockdep_set_class(&q->lock, key);
INIT_LIST_HEAD(&q->task_list);
}
EXPORT_SYMBOL(init_waitqueue_head);
EXPORT_SYMBOL(__init_waitqueue_head);
void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
{