aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile5
-rw-r--r--kernel/acct.c6
-rw-r--r--kernel/audit.c146
-rw-r--r--kernel/audit.h43
-rw-r--r--kernel/audit_tree.c72
-rw-r--r--kernel/audit_watch.c543
-rw-r--r--kernel/auditfilter.c518
-rw-r--r--kernel/auditsc.c33
-rw-r--r--kernel/cgroup.c17
-rw-r--r--kernel/cpu.c13
-rw-r--r--kernel/cpuset.c260
-rw-r--r--kernel/cred.c4
-rw-r--r--kernel/exit.c295
-rw-r--r--kernel/fork.c16
-rw-r--r--kernel/futex.c45
-rw-r--r--kernel/gcov/Kconfig48
-rw-r--r--kernel/gcov/Makefile3
-rw-r--r--kernel/gcov/base.c148
-rw-r--r--kernel/gcov/fs.c673
-rw-r--r--kernel/gcov/gcc_3_4.c447
-rw-r--r--kernel/gcov/gcov.h128
-rw-r--r--kernel/groups.c288
-rw-r--r--kernel/hrtimer.c60
-rw-r--r--kernel/irq/handle.c13
-rw-r--r--kernel/irq/manage.c2
-rw-r--r--kernel/kallsyms.c134
-rw-r--r--kernel/kexec.c14
-rw-r--r--kernel/kfifo.c4
-rw-r--r--kernel/kmod.c1
-rw-r--r--kernel/kprobes.c6
-rw-r--r--kernel/kthread.c82
-rw-r--r--kernel/module.c88
-rw-r--r--kernel/nsproxy.c19
-rw-r--r--kernel/params.c46
-rw-r--r--kernel/perf_counter.c727
-rw-r--r--kernel/pid.c17
-rw-r--r--kernel/pid_namespace.c24
-rw-r--r--kernel/power/Kconfig4
-rw-r--r--kernel/power/Makefile5
-rw-r--r--kernel/power/hibernate.c (renamed from kernel/power/disk.c)34
-rw-r--r--kernel/power/hibernate_nvs.c135
-rw-r--r--kernel/power/main.c521
-rw-r--r--kernel/power/power.h25
-rw-r--r--kernel/power/poweroff.c2
-rw-r--r--kernel/power/process.c5
-rw-r--r--kernel/power/snapshot.c80
-rw-r--r--kernel/power/suspend.c300
-rw-r--r--kernel/power/suspend_test.c187
-rw-r--r--kernel/power/swsusp.c198
-rw-r--r--kernel/power/user.c1
-rw-r--r--kernel/printk.c33
-rw-r--r--kernel/profile.c14
-rw-r--r--kernel/ptrace.c168
-rw-r--r--kernel/rcutree.c3
-rw-r--r--kernel/res_counter.c12
-rw-r--r--kernel/resource.c2
-rw-r--r--kernel/rtmutex.c2
-rw-r--r--kernel/sched.c75
-rw-r--r--kernel/sched_cpupri.c10
-rw-r--r--kernel/sched_debug.c6
-rw-r--r--kernel/sched_fair.c3
-rw-r--r--kernel/signal.c34
-rw-r--r--kernel/slow-work.c27
-rw-r--r--kernel/softirq.c12
-rw-r--r--kernel/sys.c283
-rw-r--r--kernel/sysctl.c51
-rw-r--r--kernel/time/clockevents.c14
-rw-r--r--kernel/time/clocksource.c23
-rw-r--r--kernel/time/tick-broadcast.c2
-rw-r--r--kernel/time/tick-oneshot.c17
-rw-r--r--kernel/time/tick-sched.c19
-rw-r--r--kernel/time/timekeeping.c7
-rw-r--r--kernel/time/timer_stats.c16
-rw-r--r--kernel/timer.c54
-rw-r--r--kernel/trace/Kconfig24
-rw-r--r--kernel/trace/blktrace.c22
-rw-r--r--kernel/trace/ftrace.c67
-rw-r--r--kernel/trace/kmemtrace.c2
-rw-r--r--kernel/trace/ring_buffer.c323
-rw-r--r--kernel/trace/ring_buffer_benchmark.c45
-rw-r--r--kernel/trace/trace.c55
-rw-r--r--kernel/trace/trace.h7
-rw-r--r--kernel/trace/trace_event_types.h3
-rw-r--r--kernel/trace/trace_events.c28
-rw-r--r--kernel/trace/trace_events_filter.c37
-rw-r--r--kernel/trace/trace_functions.c11
-rw-r--r--kernel/trace/trace_functions_graph.c36
-rw-r--r--kernel/trace/trace_output.c3
-rw-r--r--kernel/trace/trace_printk.c26
-rw-r--r--kernel/trace/trace_stack.c4
-rw-r--r--kernel/trace/trace_stat.c6
-rw-r--r--kernel/trace/trace_sysprof.c3
-rw-r--r--kernel/user.c67
-rw-r--r--kernel/utsname.c13
94 files changed, 5238 insertions, 2916 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 90b53f6dc22..2093a691f1c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
async.o
+obj-y += groups.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
@@ -68,8 +69,9 @@ 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-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += kgdb.o
@@ -94,6 +96,7 @@ obj-$(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
diff --git a/kernel/acct.c b/kernel/acct.c
index 7afa3156416..9f3391090b3 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -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;
diff --git a/kernel/audit.c b/kernel/audit.c
index 9442c3533ba..defc2e6f1e3 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -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;
}
diff --git a/kernel/audit.h b/kernel/audit.h
index 16f18cac661..208687be4f3 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -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;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 6e7351739a8..2451dc6f328 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -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)
{
@@ -568,7 +569,7 @@ void audit_trim_trees(void)
if (err)
goto skip_it;
- root_mnt = collect_mounts(path.mnt, path.dentry);
+ root_mnt = collect_mounts(&path);
path_put(&path);
if (!root_mnt)
goto skip_it;
@@ -660,7 +661,7 @@ int audit_add_tree_rule(struct audit_krule *rule)
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
- mnt = collect_mounts(path.mnt, path.dentry);
+ mnt = collect_mounts(&path);
path_put(&path);
if (!mnt) {
err = -ENOMEM;
@@ -720,7 +721,7 @@ int audit_tag_tree(char *old, char *new)
err = kern_path(new, 0, &path);
if (err)
return err;
- tagged = collect_mounts(path.mnt, path.dentry);
+ tagged = collect_mounts(&path);
path_put(&path);
if (!tagged)
return -ENOMEM;
@@ -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);
}
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
new file mode 100644
index 00000000000..0e96dbc60ea
--- /dev/null
+++ b/kernel/audit_watch.c
@@ -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);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 713098ee5a0..a70604047f3 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -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);
-}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 7d6ac7c1f41..68d3c6a0ecd 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -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;
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a7267bfd376..3737a682cdf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,6 +46,7 @@
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
+#include <linux/smp_lock.h>
#include <asm/atomic.h>
@@ -842,6 +843,11 @@ static int parse_cgroupfs_options(char *data,
struct cgroup_sb_opts *opts)
{
char *token, *o = data ?: "all";
+ unsigned long mask = (unsigned long)-1;
+
+#ifdef CONFIG_CPUSETS
+ mask = ~(1UL << cpuset_subsys_id);
+#endif
opts->subsys_bits = 0;
opts->flags = 0;
@@ -886,6 +892,15 @@ static int parse_cgroupfs_options(char *data,
}
}
+ /*
+ * Option noprefix was introduced just for backward compatibility
+ * with the old cpuset, so we allow noprefix only if mounting just
+ * the cpuset subsystem.
+ */
+ if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
+ (opts->subsys_bits & mask))
+ return -EINVAL;
+
/* We can't have an empty hierarchy */
if (!opts->subsys_bits)
return -EINVAL;
@@ -900,6 +915,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_sb_opts opts;
+ lock_kernel();
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
@@ -927,6 +943,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
kfree(opts.release_agent);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ unlock_kernel();
return ret;
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 395b6974dc8..8ce10043e4a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -34,14 +34,11 @@ static struct {
* an ongoing cpu hotplug operation.
*/
int refcount;
-} cpu_hotplug;
-
-void __init cpu_hotplug_init(void)
-{
- cpu_hotplug.active_writer = NULL;
- mutex_init(&cpu_hotplug.lock);
- cpu_hotplug.refcount = 0;
-}
+} cpu_hotplug = {
+ .active_writer = NULL,
+ .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
+ .refcount = 0,
+};
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 026faccca86..7e75a41bd50 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -97,12 +97,6 @@ struct cpuset {
struct cpuset *parent; /* my parent */
- /*
- * Copy of global cpuset_mems_generation as of the most
- * recent time this cpuset changed its mems_allowed.
- */
- int mems_generation;
-
struct fmeter fmeter; /* memory_pressure filter */
/* partition number for rebuild_sched_domains() */
@@ -176,27 +170,6 @@ static inline int is_spread_slab(const struct cpuset *cs)
return test_bit(CS_SPREAD_SLAB, &cs->flags);
}
-/*
- * Increment this integer everytime any cpuset changes its
- * mems_allowed value. Users of cpusets can track this generation
- * number, and avoid having to lock and reload mems_allowed unless
- * the cpuset they're using changes generation.
- *
- * A single, global generation is needed because cpuset_attach_task() could
- * reattach a task to a different cpuset, which must not have its
- * generation numbers aliased with those of that tasks previous cpuset.
- *
- * Generations are needed for mems_allowed because one task cannot
- * modify another's memory placement. So we must enable every task,
- * on every visit to __alloc_pages(), to efficiently check whether
- * its current->cpuset->mems_allowed has changed, requiring an update
- * of its current->mems_allowed.
- *
- * Since writes to cpuset_mems_generation are guarded by the cgroup lock
- * there is no need to mark it atomic.
- */
-static int cpuset_mems_generation;
-
static struct cpuset top_cpuset = {
.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
};
@@ -228,8 +201,9 @@ static struct cpuset top_cpuset = {
* If a task is only holding callback_mutex, then it has read-only
* access to cpusets.
*
- * The task_struct fields mems_allowed and mems_generation may only
- * be accessed in the context of that task, so require no locks.
+ * Now, the task_struct fields mems_allowed and mempolicy may be changed
+ * by other task, we use alloc_lock in the task_struct fields to protect
+ * them.
*
* The cpuset_common_file_read() handlers only hold callback_mutex across
* small pieces of code, such as when reading out possibly multi-word
@@ -331,75 +305,22 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
}
-/**
- * cpuset_update_task_memory_state - update task memory placement
- *
- * If the current tasks cpusets mems_allowed changed behind our
- * backs, update current->mems_allowed, mems_generation and task NUMA
- * mempolicy to the new value.
- *
- * Task mempolicy is updated by rebinding it relative to the
- * current->cpuset if a task has its memory placement changed.
- * Do not call this routine if in_interrupt().
- *
- * Call without callback_mutex or task_lock() held. May be
- * called with or without cgroup_mutex held. Thanks in part to
- * 'the_top_cpuset_hack', the task's cpuset pointer will never
- * be NULL. This routine also might acquire callback_mutex during
- * call.
- *
- * Reading current->cpuset->mems_generation doesn't need task_lock
- * to guard the current->cpuset derefence, because it is guarded
- * from concurrent freeing of current->cpuset using RCU.
- *
- * The rcu_dereference() is technically probably not needed,
- * as I don't actually mind if I see a new cpuset pointer but
- * an old value of mems_generation. However this really only
- * matters on alpha systems using cpusets heavily. If I dropped
- * that rcu_dereference(), it would save them a memory barrier.
- * For all other arch's, rcu_dereference is a no-op anyway, and for
- * alpha systems not using cpusets, another planned optimization,
- * avoiding the rcu critical section for tasks in the root cpuset
- * which is statically allocated, so can't vanish, will make this
- * irrelevant. Better to use RCU as intended, than to engage in
- * some cute trick to save a memory barrier that is impossible to
- * test, for alpha systems using cpusets heavily, which might not
- * even exist.
- *
- * This routine is needed to update the per-task mems_allowed data,
- * within the tasks context, when it is trying to allocate memory
- * (in various mm/mempolicy.c routines) and notices that some other
- * task has been modifying its cpuset.
+/*
+ * update task's spread flag if cpuset's page/slab spread flag is set
+ *
+ * Called with callback_mutex/cgroup_mutex held
*/
-
-void cpuset_update_task_memory_state(void)
+static void cpuset_update_task_spread_flag(struct cpuset *cs,
+ struct task_struct *tsk)
{
- int my_cpusets_mem_gen;
- struct task_struct *tsk = current;
- struct cpuset *cs;
-
- rcu_read_lock();
- my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
- rcu_read_unlock();
-
- if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
- mutex_lock(&callback_mutex);
- task_lock(tsk);
- cs = task_cs(tsk); /* Maybe changed when task not locked */
- guarantee_online_mems(cs, &tsk->mems_allowed);
- tsk->cpuset_mems_generation = cs->mems_generation;
- if (is_spread_page(cs))
- tsk->flags |= PF_SPREAD_PAGE;
- else
- tsk->flags &= ~PF_SPREAD_PAGE;
- if (is_spread_slab(cs))
- tsk->flags |= PF_SPREAD_SLAB;
- else
- tsk->flags &= ~PF_SPREAD_SLAB;
- task_unlock(tsk);
- mutex_unlock(&callback_mutex);
- mpol_rebind_task(tsk, &tsk->mems_allowed);
- }
+ if (is_spread_page(cs))
+ tsk->flags |= PF_SPREAD_PAGE;
+ else
+ tsk->flags &= ~PF_SPREAD_PAGE;
+ if (is_spread_slab(cs))
+ tsk->flags |= PF_SPREAD_SLAB;
+ else
+ tsk->flags &= ~PF_SPREAD_SLAB;
}
/*
@@ -1007,14 +928,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
* migrating memory region.
- *
- * We call cpuset_update_task_memory_state() before hacking
- * our tasks mems_allowed, so that we are assured of being in
- * sync with our tasks cpuset, and in particular, callbacks to
- * cpuset_update_task_memory_state() from nested page allocations
- * won't see any mismatch of our cpuset and task mems_generation
- * values, so won't overwrite our hacked tasks mems_allowed
- * nodemask.
*/
static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
@@ -1022,22 +935,37 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
{
struct task_struct *tsk = current;
- cpuset_update_task_memory_state();
-
- mutex_lock(&callback_mutex);
tsk->mems_allowed = *to;
- mutex_unlock(&callback_mutex);
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
- mutex_lock(&callback_mutex);
guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
- mutex_unlock(&callback_mutex);
}
/*
- * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new
- * nodes if memory_migrate flag is set. Called with cgroup_mutex held.
+ * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy
+ * @tsk: the task to change
+ * @newmems: new nodes that the task will be set
+ *
+ * In order to avoid seeing no nodes if the old and new nodes are disjoint,
+ * we structure updates as setting all new allowed nodes, then clearing newly
+ * disallowed ones.
+ *
+ * Called with task's alloc_lock held
+ */
+static void cpuset_change_task_nodemask(struct task_struct *tsk,
+ nodemask_t *newmems)
+{
+ nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+ mpol_rebind_task(tsk, &tsk->mems_allowed);
+ mpol_rebind_task(tsk, newmems);
+ tsk->mems_allowed = *newmems;
+}
+
+/*
+ * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy
+ * of it to cpuset's new mems_allowed, and migrate pages to new nodes if
+ * memory_migrate flag is set. Called with cgroup_mutex held.
*/
static void cpuset_change_nodemask(struct task_struct *p,
struct cgroup_scanner *scan)
@@ -1046,12 +974,19 @@ static void cpuset_change_nodemask(struct task_struct *p,
struct cpuset *cs;
int migrate;
const nodemask_t *oldmem = scan->data;
+ nodemask_t newmems;
+
+ cs = cgroup_cs(scan->cg);
+ guarantee_online_mems(cs, &newmems);
+
+ task_lock(p);
+ cpuset_change_task_nodemask(p, &newmems);
+ task_unlock(p);
mm = get_task_mm(p);
if (!mm)
return;
- cs = cgroup_cs(scan->cg);
migrate = is_memory_migrate(cs);
mpol_rebind_mm(mm, &cs->mems_allowed);
@@ -1104,10 +1039,10 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
/*
* Handle user request to change the 'mems' memory placement
* of a cpuset. Needs to validate the request, update the
- * cpusets mems_allowed and mems_generation, and for each
- * task in the cpuset, rebind any vma mempolicies and if
- * the cpuset is marked 'memory_migrate', migrate the tasks
- * pages to the new memory.
+ * cpusets mems_allowed, and for each task in the cpuset,
+ * update mems_allowed and rebind task's mempolicy and any vma
+ * mempolicies and if the cpuset is marked 'memory_migrate',
+ * migrate the tasks pages to the new memory.
*
* Call with cgroup_mutex held. May take callback_mutex during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
@@ -1160,7 +1095,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
mutex_lock(&callback_mutex);
cs->mems_allowed = trialcs->mems_allowed;
- cs->mems_generation = cpuset_mems_generation++;
mutex_unlock(&callback_mutex);
update_tasks_nodemask(cs, &oldmem, &heap);
@@ -1193,6 +1127,46 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
}
/*
+ * cpuset_change_flag - make a task's spread flags the same as its cpuset's
+ * @tsk: task to be updated
+ * @scan: struct cgroup_scanner containing the cgroup of the task
+ *
+ * Called by cgroup_scan_tasks() for each task in a cgroup.
+ *
+ * We don't need to re-check for the cgroup/cpuset membership, since we're
+ * holding cgroup_lock() at this point.
+ */
+static void cpuset_change_flag(struct task_struct *tsk,
+ struct cgroup_scanner *scan)
+{
+ cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk);
+}
+
+/*
+ * update_tasks_flags - update the spread flags of tasks in the cpuset.
+ * @cs: the cpuset in which each task's spread flags needs to be changed
+ * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ *
+ * Called with cgroup_mutex held
+ *
+ * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
+ * calling callback functions for each.
+ *
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
+ */
+static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
+{
+ struct cgroup_scanner scan;
+
+ scan.cg = cs->css.cgroup;
+ scan.test_task = NULL;
+ scan.process_task = cpuset_change_flag;
+ scan.heap = heap;
+ cgroup_scan_tasks(&scan);
+}
+
+/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (see cpuset_flagbits_t)
* cs: the cpuset to update
@@ -1205,8 +1179,10 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on)
{
struct cpuset *trialcs;
- int err;
int balance_flag_changed;
+ int spread_flag_changed;
+ struct ptr_heap heap;
+ int err;
trialcs = alloc_trial_cpuset(cs);
if (!trialcs)
@@ -1221,9 +1197,16 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
if (err < 0)
goto out;
+ err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
+ if (err < 0)
+ goto out;
+
balance_flag_changed = (is_sched_load_balance(cs) !=
is_sched_load_balance(trialcs));
+ spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
+ || (is_spread_page(cs) != is_spread_page(trialcs)));
+
mutex_lock(&callback_mutex);
cs->flags = trialcs->flags;
mutex_unlock(&callback_mutex);
@@ -1231,6 +1214,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
async_rebuild_sched_domains();
+ if (spread_flag_changed)
+ update_tasks_flags(cs, &heap);
+ heap_free(&heap);
out:
free_trial_cpuset(trialcs);
return err;
@@ -1372,15 +1358,20 @@ static void cpuset_attach(struct cgroup_subsys *ss,
if (cs == &top_cpuset) {
cpumask_copy(cpus_attach, cpu_possible_mask);
+ to = node_possible_map;
} else {
- mutex_lock(&callback_mutex);
guarantee_online_cpus(cs, cpus_attach);
- mutex_unlock(&callback_mutex);
+ guarantee_online_mems(cs, &to);
}
err = set_cpus_allowed_ptr(tsk, cpus_attach);
if (err)
return;
+ task_lock(tsk);
+ cpuset_change_task_nodemask(tsk, &to);
+ task_unlock(tsk);
+ cpuset_update_task_spread_flag(cs, tsk);
+
from = oldcs->mems_allowed;
to = cs->mems_allowed;
mm = get_task_mm(tsk);
@@ -1442,11 +1433,9 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
break;
case FILE_SPREAD_PAGE:
retval = update_flag(CS_SPREAD_PAGE, cs, val);
- cs->mems_generation = cpuset_mems_generation++;
break;
case FILE_SPREAD_SLAB:
retval = update_flag(CS_SPREAD_SLAB, cs, val);
- cs->mems_generation = cpuset_mems_generation++;
break;
default:
retval = -EINVAL;
@@ -1786,8 +1775,6 @@ static struct cgroup_subsys_state *cpuset_create(
struct cpuset *parent;
if (!cont->parent) {
- /* This is early initialization for the top cgroup */
- top_cpuset.mems_generation = cpuset_mems_generation++;
return &top_cpuset.css;
}
parent = cgroup_cs(cont->parent);
@@ -1799,7 +1786,6 @@ static struct cgroup_subsys_state *cpuset_create(
return ERR_PTR(-ENOMEM);
}
- cpuset_update_task_memory_state();
cs->flags = 0;
if (is_spread_page(parent))
set_bit(CS_SPREAD_PAGE, &cs->flags);
@@ -1808,7 +1794,6 @@ static struct cgroup_subsys_state *cpuset_create(
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cpumask_clear(cs->cpus_allowed);
nodes_clear(cs->mems_allowed);
- cs->mems_generation = cpuset_mems_generation++;
fmeter_init(&cs->fmeter);
cs->relax_domain_level = -1;
@@ -1827,8 +1812,6 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
struct cpuset *cs = cgroup_cs(cont);
- cpuset_update_task_memory_state();
-
if (is_sched_load_balance(cs))
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
@@ -1849,21 +1832,6 @@ struct cgroup_subsys cpuset_subsys = {
.early_init = 1,
};
-/*
- * cpuset_init_early - just enough so that the calls to
- * cpuset_update_task_memory_state() in early init code
- * are harmless.
- */
-
-int __init cpuset_init_early(void)
-{
- alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
-
- top_cpuset.mems_generation = cpuset_mems_generation++;
- return 0;
-}
-
-
/**
* cpuset_init - initialize cpusets at system boot
*
@@ -1874,11 +1842,13 @@ int __init cpuset_init(void)
{
int err = 0;
+ if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
+ BUG();
+
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
fmeter_init(&top_cpuset.fmeter);
- top_cpuset.mems_generation = cpuset_mems_generation++;
set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
top_cpuset.relax_domain_level = -1;
diff --git a/kernel/cred.c b/kernel/cred.c
index 3a039189d70..1bb4d7e5d61 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -167,7 +167,7 @@ EXPORT_SYMBOL(prepare_creds);
/*
* Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_exec_mutex
+ * - The caller must hold current->cred_guard_mutex
*/
struct cred *prepare_exec_creds(void)
{
@@ -276,7 +276,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
struct cred *new;
int ret;
- mutex_init(&p->cred_exec_mutex);
+ mutex_init(&p->cred_guard_mutex);
if (
#ifdef CONFIG_KEYS
diff --git a/kernel/exit.c b/kernel/exit.c
index 49cdf6946f3..869dc221733 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -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>
@@ -375,9 +374,8 @@ static void set_special_pids(struct pid *pid)
}
/*
- * Let kernel threads use this to say that they
- * allow a certain signal (since daemonize() will
- * have disabled all of them by default).
+ * Let kernel threads use this to say that they allow a certain signal.
+ * Must not be used if kthread was cloned with CLONE_SIGHAND.
*/
int allow_signal(int sig)
{
@@ -385,14 +383,14 @@ int allow_signal(int sig)
return -EINVAL;
spin_lock_irq(&current->sighand->siglock);
+ /* This is only needed for daemonize()'ed kthreads */
sigdelset(&current->blocked, sig);
- if (!current->mm) {
- /* Kernel threads handle their own signals.
- Let the signal code know it'll be handled, so
- that they don't get converted to SIGKILL or
- just silently dropped */
- current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
- }
+ /*
+ * Kernel threads handle their own signals. Let the signal code
+ * know it'll be handled, so that they don't get converted to
+ * SIGKILL or just silently dropped.
+ */
+ current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
return 0;
@@ -591,7 +589,7 @@ retry:
/*
* Search in the siblings
*/
- list_for_each_entry(c, &p->parent->children, sibling) {
+ list_for_each_entry(c, &p->real_parent->children, sibling) {
if (c->mm == mm)
goto assign_new_owner;
}
@@ -758,7 +756,7 @@ static void reparent_thread(struct task_struct *father, struct task_struct *p,
p->exit_signal = SIGCHLD;
/* If it has exited notify the new parent about this child's death. */
- if (!p->ptrace &&
+ if (!task_ptrace(p) &&
p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
do_notify_parent(p, p->exit_signal);
if (task_detached(p)) {
@@ -783,7 +781,7 @@ static void forget_original_parent(struct task_struct *father)
list_for_each_entry_safe(p, n, &father->children, sibling) {
p->real_parent = reaper;
if (p->parent == father) {
- BUG_ON(p->ptrace);
+ BUG_ON(task_ptrace(p));
p->parent = p->real_parent;
}
reparent_thread(father, p, &dead_children);
@@ -1081,6 +1079,18 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
return 0;
}
+struct wait_opts {
+ enum pid_type wo_type;
+ int wo_flags;
+ struct pid *wo_pid;
+
+ struct siginfo __user *wo_info;
+ int __user *wo_stat;
+ struct rusage __user *wo_rusage;
+
+ int notask_error;
+};
+
static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
struct pid *pid = NULL;
@@ -1091,13 +1101,12 @@ static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
return pid;
}
-static int eligible_child(enum pid_type type, struct pid *pid, int options,
- struct task_struct *p)
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
{
int err;
- if (type < PIDTYPE_MAX) {
- if (task_pid_type(p, type) != pid)
+ if (wo->wo_type < PIDTYPE_MAX) {
+ if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
return 0;
}
@@ -1106,8 +1115,8 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
* set; otherwise, wait for non-clone children *only*. (Note:
* A "clone" child here is one that reports to its parent
* using a signal other than SIGCHLD.) */
- if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
- && !(options & __WALL))
+ if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
+ && !(wo->wo_flags & __WALL))
return 0;
err = security_task_wait(p);
@@ -1117,14 +1126,15 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
return 1;
}
-static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
- int why, int status,
- struct siginfo __user *infop,
- struct rusage __user *rusagep)
+static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
+ pid_t pid, uid_t uid, int why, int status)
{
- int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
+ struct siginfo __user *infop;
+ int retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
put_task_struct(p);
+ infop = wo->wo_info;
if (!retval)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval)
@@ -1148,19 +1158,18 @@ static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_zombie(struct task_struct *p, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
{
unsigned long state;
int retval, status, traced;
pid_t pid = task_pid_vnr(p);
uid_t uid = __task_cred(p)->uid;
+ struct siginfo __user *infop;
- if (!likely(options & WEXITED))
+ if (!likely(wo->wo_flags & WEXITED))
return 0;
- if (unlikely(options & WNOWAIT)) {
+ if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
int why, status;
@@ -1173,8 +1182,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
status = exit_code & 0x7f;
}
- return wait_noreap_copyout(p, pid, uid, why,
- status, infop, ru);
+ return wait_noreap_copyout(wo, p, pid, uid, why, status);
}
/*
@@ -1188,11 +1196,13 @@ static int wait_task_zombie(struct task_struct *p, int options,
}
traced = ptrace_reparented(p);
-
- if (likely(!traced)) {
+ /*
+ * It can be ptraced but not reparented, check
+ * !task_detached() to filter out sub-threads.
+ */
+ if (likely(!traced) && likely(!task_detached(p))) {
struct signal_struct *psig;
struct signal_struct *sig;
- struct task_cputime cputime;
/*
* The resource counters for the group leader are in its
@@ -1205,26 +1215,23 @@ static int wait_task_zombie(struct task_struct *p, int options,
* p->signal fields, because they are only touched by
* __exit_signal, which runs with tasklist_lock
* write-locked anyway, and so is excluded here. We do
- * need to protect the access to p->parent->signal fields,
+ * need to protect the access to parent->signal fields,
* as other threads in the parent group can be right
* here reaping other children at the same time.
- *
- * We use thread_group_cputime() to get times for the thread
- * group, which consolidates times for all threads in the
- * group including the group leader.
*/
- thread_group_cputime(p, &cputime);
- spin_lock_irq(&p->parent->sighand->siglock);
- psig = p->parent->signal;
+ spin_lock_irq(&p->real_parent->sighand->siglock);
+ psig = p->real_parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
- cputime_add(cputime.utime,
- sig->cutime));
+ cputime_add(p->utime,
+ cputime_add(sig->utime,
+ sig->cutime)));
psig->cstime =
cputime_add(psig->cstime,
- cputime_add(cputime.stime,
- sig->cstime));
+ cputime_add(p->stime,
+ cputime_add(sig->stime,
+ sig->cstime)));
psig->cgtime =
cputime_add(psig->cgtime,
cputime_add(p->gtime,
@@ -1246,7 +1253,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
sig->oublock + sig->coublock;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
- spin_unlock_irq(&p->parent->sighand->siglock);
+ spin_unlock_irq(&p->real_parent->sighand->siglock);
}
/*
@@ -1255,11 +1262,14 @@ static int wait_task_zombie(struct task_struct *p, int options,
*/
read_unlock(&tasklist_lock);
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
? p->signal->group_exit_code : p->exit_code;
- if (!retval && stat_addr)
- retval = put_user(status, stat_addr);
+ if (!retval && wo->wo_stat)
+ retval = put_user(status, wo->wo_stat);
+
+ infop = wo->wo_info;
if (!retval && infop)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval && infop)
@@ -1327,15 +1337,18 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace)
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_stopped(int ptrace, struct task_struct *p,
- int options, struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_stopped(struct wait_opts *wo,
+ int ptrace, struct task_struct *p)
{
+ struct siginfo __user *infop;
int retval, exit_code, *p_code, why;
uid_t uid = 0; /* unneeded, required by compiler */
pid_t pid;
- if (!(options & WUNTRACED))
+ /*
+ * Traditionally we see ptrace'd stopped tasks regardless of options.
+ */
+ if (!ptrace && !(wo->wo_flags & WUNTRACED))
return 0;
exit_code = 0;
@@ -1349,7 +1362,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
if (!exit_code)
goto unlock_sig;
- if (!unlikely(options & WNOWAIT))
+ if (!unlikely(wo->wo_flags & WNOWAIT))
*p_code = 0;
/* don't need the RCU readlock here as we're holding a spinlock */
@@ -1371,14 +1384,15 @@ unlock_sig:
why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
read_unlock(&tasklist_lock);
- if (unlikely(options & WNOWAIT))
- return wait_noreap_copyout(p, pid, uid,
- why, exit_code,
- infop, ru);
+ if (unlikely(wo->wo_flags & WNOWAIT))
+ return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
- if (!retval && stat_addr)
- retval = put_user((exit_code << 8) | 0x7f, stat_addr);
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
+ if (!retval && wo->wo_stat)
+ retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat);
+
+ infop = wo->wo_info;
if (!retval && infop)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval && infop)
@@ -1405,15 +1419,13 @@ unlock_sig:
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_continued(struct task_struct *p, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
{
int retval;
pid_t pid;
uid_t uid;
- if (!unlikely(options & WCONTINUED))
+ if (!unlikely(wo->wo_flags & WCONTINUED))
return 0;
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
@@ -1425,7 +1437,7 @@ static int wait_task_continued(struct task_struct *p, int options,
spin_unlock_irq(&p->sighand->siglock);
return 0;
}
- if (!unlikely(options & WNOWAIT))
+ if (!unlikely(wo->wo_flags & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
uid = __task_cred(p)->uid;
spin_unlock_irq(&p->sighand->siglock);
@@ -1434,17 +1446,17 @@ static int wait_task_continued(struct task_struct *p, int options,
get_task_struct(p);
read_unlock(&tasklist_lock);
- if (!infop) {
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+ if (!wo->wo_info) {
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
put_task_struct(p);
- if (!retval && stat_addr)
- retval = put_user(0xffff, stat_addr);
+ if (!retval && wo->wo_stat)
+ retval = put_user(0xffff, wo->wo_stat);
if (!retval)
retval = pid;
} else {
- retval = wait_noreap_copyout(p, pid, uid,
- CLD_CONTINUED, SIGCONT,
- infop, ru);
+ retval = wait_noreap_copyout(wo, p, pid, uid,
+ CLD_CONTINUED, SIGCONT);
BUG_ON(retval == 0);
}
@@ -1454,19 +1466,16 @@ static int wait_task_continued(struct task_struct *p, int options,
/*
* Consider @p for a wait by @parent.
*
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue;
- * then *@notask_error is 0 if @p is an eligible child,
+ * then ->notask_error is 0 if @p is an eligible child,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int wait_consider_task(struct task_struct *parent, int ptrace,
- struct task_struct *p, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
+ int ptrace, struct task_struct *p)
{
- int ret = eligible_child(type, pid, options, p);
+ int ret = eligible_child(wo, p);
if (!ret)
return ret;
@@ -1478,16 +1487,17 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
* to look for security policy problems, rather
* than for mysterious wait bugs.
*/
- if (*notask_error)
- *notask_error = ret;
+ if (wo->notask_error)
+ wo->notask_error = ret;
+ return 0;
}
- if (likely(!ptrace) && unlikely(p->ptrace)) {
+ if (likely(!ptrace) && unlikely(task_ptrace(p))) {
/*
* This child is hidden by ptrace.
* We aren't allowed to see it now, but eventually we will.
*/
- *notask_error = 0;
+ wo->notask_error = 0;
return 0;
}
@@ -1498,34 +1508,30 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
* We don't reap group leaders with subthreads.
*/
if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
- return wait_task_zombie(p, options, infop, stat_addr, ru);
+ return wait_task_zombie(wo, p);
/*
* It's stopped or running now, so it might
* later continue, exit, or stop again.
*/
- *notask_error = 0;
+ wo->notask_error = 0;
if (task_stopped_code(p, ptrace))
- return wait_task_stopped(ptrace, p, options,
- infop, stat_addr, ru);
+ return wait_task_stopped(wo, ptrace, p);
- return wait_task_continued(p, options, infop, stat_addr, ru);
+ return wait_task_continued(wo, p);
}
/*
* Do the work of do_wait() for one thread in the group, @tsk.
*
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue; then
- * *@notask_error is 0 if there were any eligible children,
+ * ->notask_error is 0 if there were any eligible children,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int do_wait_thread(struct task_struct *tsk, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
@@ -1534,9 +1540,7 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error,
* Do not consider detached threads.
*/
if (!task_detached(p)) {
- int ret = wait_consider_task(tsk, 0, p, notask_error,
- type, pid, options,
- infop, stat_addr, ru);
+ int ret = wait_consider_task(wo, tsk, 0, p);
if (ret)
return ret;
}
@@ -1545,22 +1549,12 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error,
return 0;
}
-static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
- /*
- * Traditionally we see ptrace'd stopped tasks regardless of options.
- */
- options |= WUNTRACED;
-
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
- int ret = wait_consider_task(tsk, 1, p, notask_error,
- type, pid, options,
- infop, stat_addr, ru);
+ int ret = wait_consider_task(wo, tsk, 1, p);
if (ret)
return ret;
}
@@ -1568,65 +1562,59 @@ static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
return 0;
}
-static long do_wait(enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static long do_wait(struct wait_opts *wo)
{
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int retval;
- trace_sched_process_wait(pid);
+ trace_sched_process_wait(wo->wo_pid);
add_wait_queue(&current->signal->wait_chldexit,&wait);
repeat:
/*
* If there is nothing that can match our critiera just get out.
- * We will clear @retval to zero if we see any child that might later
- * match our criteria, even if we are not able to reap it yet.
+ * We will clear ->notask_error to zero if we see any child that
+ * might later match our criteria, even if we are not able to reap
+ * it yet.
*/
- retval = -ECHILD;
- if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
- goto end;
+ wo->notask_error = -ECHILD;
+ if ((wo->wo_type < PIDTYPE_MAX) &&
+ (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+ goto notask;
- current->state = TASK_INTERRUPTIBLE;
+ set_current_state(TASK_INTERRUPTIBLE);
read_lock(&tasklist_lock);
tsk = current;
do {
- int tsk_result = do_wait_thread(tsk, &retval,
- type, pid, options,
- infop, stat_addr, ru);
- if (!tsk_result)
- tsk_result = ptrace_do_wait(tsk, &retval,
- type, pid, options,
- infop, stat_addr, ru);
- if (tsk_result) {
- /*
- * tasklist_lock is unlocked and we have a final result.
- */
- retval = tsk_result;
+ retval = do_wait_thread(wo, tsk);
+ if (retval)
+ goto end;
+
+ retval = ptrace_do_wait(wo, tsk);
+ if (retval)
goto end;
- }
- if (options & __WNOTHREAD)
+ if (wo->wo_flags & __WNOTHREAD)
break;
- tsk = next_thread(tsk);
- BUG_ON(tsk->signal != current->signal);
- } while (tsk != current);
+ } while_each_thread(current, tsk);
read_unlock(&tasklist_lock);
- if (!retval && !(options & WNOHANG)) {
+notask:
+ retval = wo->notask_error;
+ if (!retval && !(wo->wo_flags & WNOHANG)) {
retval = -ERESTARTSYS;
if (!signal_pending(current)) {
schedule();
goto repeat;
}
}
-
end:
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(&current->signal->wait_chldexit,&wait);
- if (infop) {
+ if (wo->wo_info) {
+ struct siginfo __user *infop = wo->wo_info;
+
if (retval > 0)
retval = 0;
else {
@@ -1655,6 +1643,7 @@ end:
SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
infop, int, options, struct rusage __user *, ru)
{
+ struct wait_opts wo;
struct pid *pid = NULL;
enum pid_type type;
long ret;
@@ -1684,7 +1673,14 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
if (type < PIDTYPE_MAX)
pid = find_get_pid(upid);
- ret = do_wait(type, pid, options, infop, NULL, ru);
+
+ wo.wo_type = type;
+ wo.wo_pid = pid;
+ wo.wo_flags = options;
+ wo.wo_info = infop;
+ wo.wo_stat = NULL;
+ wo.wo_rusage = ru;
+ ret = do_wait(&wo);
put_pid(pid);
/* avoid REGPARM breakage on x86: */
@@ -1695,6 +1691,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
int, options, struct rusage __user *, ru)
{
+ struct wait_opts wo;
struct pid *pid = NULL;
enum pid_type type;
long ret;
@@ -1716,7 +1713,13 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
pid = find_get_pid(upid);
}
- ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
+ wo.wo_type = type;
+ wo.wo_pid = pid;
+ wo.wo_flags = options | WEXITED;
+ wo.wo_info = NULL;
+ wo.wo_stat = stat_addr;
+ wo.wo_rusage = ru;
+ ret = do_wait(&wo);
put_pid(pid);
/* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index 4430eb1376f..bd295922887 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -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>
@@ -178,7 +177,7 @@ void __init fork_init(unsigned long mempages)
/* create a slab on which task_structs can be allocated */
task_struct_cachep =
kmem_cache_create("task_struct", sizeof(struct task_struct),
- ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL);
+ ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
#endif
/* do the arch specific task caches init */
@@ -1029,7 +1028,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
- clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
@@ -1470,20 +1468,20 @@ void __init proc_caches_init(void)
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU,
- sighand_ctor);
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+ SLAB_NOTRACK, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
files_cachep = kmem_cache_create("files_cache",
sizeof(struct files_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
fs_cachep = kmem_cache_create("fs_cache",
sizeof(struct fs_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
mm_cachep = kmem_cache_create("mm_struct",
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
mmap_init();
}
diff --git a/kernel/futex.c b/kernel/futex.c
index 80b5ce71659..794c862125f 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -284,6 +284,25 @@ 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 +915,6 @@ 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 +932,7 @@ retry_private:
goto out_put_keys;
}
- ret = get_user(dummy, uaddr2);
+ ret = fault_in_user_writeable(uaddr2);
if (ret)
goto out_put_keys;
@@ -1204,7 +1222,7 @@ 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;
@@ -1482,7 +1500,7 @@ 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 +1825,6 @@ 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 +1926,9 @@ 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 +2023,10 @@ 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;
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
new file mode 100644
index 00000000000..22e9dcfaa3d
--- /dev/null
+++ b/kernel/gcov/Kconfig
@@ -0,0 +1,48 @@
+menu "GCOV-based kernel profiling"
+
+config GCOV_KERNEL
+ bool "Enable gcov-based kernel profiling"
+ depends on DEBUG_FS && CONSTRUCTORS
+ default n
+ ---help---
+ This option enables gcov-based code profiling (e.g. for code coverage
+ measurements).
+
+ If unsure, say N.
+
+ Additionally specify CONFIG_GCOV_PROFILE_ALL=y to get profiling data
+ for the entire kernel. To enable profiling for specific files or
+ directories, add a line similar to the following to the respective
+ Makefile:
+
+ For a single file (e.g. main.o):
+ GCOV_PROFILE_main.o := y
+
+ For all files in one directory:
+ GCOV_PROFILE := y
+
+ To exclude files from being profiled even when CONFIG_GCOV_PROFILE_ALL
+ is specified, use:
+
+ GCOV_PROFILE_main.o := n
+ and:
+ GCOV_PROFILE := n
+
+ Note that the debugfs filesystem has to be mounted to access
+ profiling data.
+
+config GCOV_PROFILE_ALL
+ bool "Profile entire Kernel"
+ depends on GCOV_KERNEL
+ depends on S390 || X86
+ default n
+ ---help---
+ This options activates profiling for the entire kernel.
+
+ If unsure, say N.
+
+ Note that a kernel compiled with profiling flags will be significantly
+ larger and run slower. Also be sure to exclude files from profiling
+ which are not linked to the kernel image to prevent linker errors.
+
+endmenu
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
new file mode 100644
index 00000000000..3f761001d51
--- /dev/null
+++ b/kernel/gcov/Makefile
@@ -0,0 +1,3 @@
+EXTRA_CFLAGS := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
+
+obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
new file mode 100644
index 00000000000..9b22d03cc58
--- /dev/null
+++ b/kernel/gcov/base.c
@@ -0,0 +1,148 @@
+/*
+ * This code maintains a list of active profiling data structures.
+ *
+ * Copyright IBM Corp. 2009
+ * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ * Uses gcc-internal data definitions.
+ * Based on the gcov-kernel patch by:
+ * Hubertus Franke <frankeh@us.ibm.com>
+ * Nigel Hinds <nhinds@us.ibm.com>
+ * Rajan Ravindran <rajancr@us.ibm.com>
+ * Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ * Paul Larson
+ */
+
+#define pr_fmt(fmt) "gcov: " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include "gcov.h"
+
+static struct gcov_info *gcov_info_head;
+static int gcov_events_enabled;
+static DEFINE_MUTEX(gcov_lock);
+
+/*
+ * __gcov_init is called by gcc-generated constructor code for each object
+ * file compiled with -fprofile-arcs.
+ */
+void __gcov_init(struct gcov_info *info)
+{
+ static unsigned int gcov_version;
+
+ mutex_lock(&gcov_lock);
+ if (gcov_version == 0) {
+ gcov_version = info->version;
+ /*
+ * Printing gcc's version magic may prove useful for debugging
+ * incompatibility reports.
+ */
+ pr_info("version magic: 0x%x\n", gcov_version);
+ }
+ /*
+ * Add new profiling data structure to list and inform event
+ * listener.
+ */
+ info->next = gcov_info_head;
+ gcov_info_head = info;
+ if (gcov_events_enabled)
+ gcov_event(GCOV_ADD, info);
+ mutex_unlock(&gcov_lock);
+}
+EXPORT_SYMBOL(__gcov_init);
+
+/*
+ * These functions may be referenced by gcc-generated profiling code but serve
+ * no function for kernel profiling.
+ */
+void __gcov_flush(void)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_flush);
+
+void __gcov_merge_add(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_add);
+
+void __gcov_merge_single(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_single);
+
+void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_delta);
+
+/**
+ * gcov_enable_events - enable event reporting through gcov_event()
+ *
+ * Turn on reporting of profiling data load/unload-events through the
+ * gcov_event() callback. Also replay all previous events once. This function
+ * is needed because some events are potentially generated too early for the
+ * callback implementation to handle them initially.
+ */
+void gcov_enable_events(void)
+{
+ struct gcov_info *info;
+
+ mutex_lock(&gcov_lock);
+ gcov_events_enabled = 1;
+ /* Perform event callback for previously registered entries. */
+ for (info = gcov_info_head; info; info = info->next)
+ gcov_event(GCOV_ADD, info);
+ mutex_unlock(&gcov_lock);
+}
+
+#ifdef CONFIG_MODULES
+static inline int within(void *addr, void *start, unsigned long size)
+{
+ return ((addr >= start) && (addr < start + size));
+}
+
+/* Update list and generate events when modules are unloaded. */
+static int gcov_module_notifier(struct notifier_block *nb, unsigned long event,
+ void *data)
+{
+ struct module *mod = data;
+ struct gcov_info *info;
+ struct gcov_info *prev;
+
+ if (event != MODULE_STATE_GOING)
+ return NOTIFY_OK;
+ mutex_lock(&gcov_lock);
+ prev = NULL;
+ /* Remove entries located in module from linked list. */
+ for (info = gcov_info_head; info; info = info->next) {
+ if (within(info, mod->module_core, mod->core_size)) {
+ if (prev)
+ prev->next = info->next;
+ else
+ gcov_info_head = info->next;
+ if (gcov_events_enabled)
+ gcov_event(GCOV_REMOVE, info);
+ } else
+ prev = info;
+ }
+ mutex_unlock(&gcov_lock);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block gcov_nb = {
+ .notifier_call = gcov_module_notifier,
+};
+
+static int __init gcov_init(void)
+{
+ return register_module_notifier(&gcov_nb);
+}
+device_initcall(gcov_init);
+#endif /* CONFIG_MODULES */
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
new file mode 100644
index 00000000000..ef3c3f88a7a
--- /dev/null
+++ b/kernel/gcov/fs.c
@@ -0,0 +1,673 @@
+/*
+ * This code exports profiling data as debugfs files to userspace.
+ *
+ * Copyright IBM Corp. 2009
+ * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ * Uses gcc-internal data definitions.
+ * Based on the gcov-kernel patch by:
+ * Hubertus Franke <frankeh@us.ibm.com>
+ * Nigel Hinds <nhinds@us.ibm.com>
+ * Rajan Ravindran <rajancr@us.ibm.com>
+ * Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ * Paul Larson
+ * Yi CDL Yang
+ */
+
+#define pr_fmt(fmt) "gcov: " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include "gcov.h"
+
+/**
+ * struct gcov_node - represents a debugfs entry
+ * @list: list head for child node list
+ * @children: child nodes
+ * @all: list head for list of all nodes
+ * @parent: parent node
+ * @info: associated profiling data structure if not a directory
+ * @ghost: when an object file containing profiling data is unloaded we keep a
+ * copy of the profiling data here to allow collecting coverage data
+ * for cleanup code. Such a node is called a "ghost".
+ * @dentry: main debugfs entry, either a directory or data file
+ * @links: associated symbolic links
+ * @name: data file basename
+ *
+ * struct gcov_node represents an entity within the gcov/ subdirectory
+ * of debugfs. There are directory and data file nodes. The latter represent
+ * the actual synthesized data file plus any associated symbolic links which
+ * are needed by the gcov tool to work correctly.
+ */
+struct gcov_node {
+ struct list_head list;
+ struct list_head children;
+ struct list_head all;
+ struct gcov_node *parent;
+ struct gcov_info *info;
+ struct gcov_info *ghost;
+ struct dentry *dentry;
+ struct dentry **links;
+ char name[0];
+};
+
+static const char objtree[] = OBJTREE;
+static const char srctree[] = SRCTREE;
+static struct gcov_node root_node;
+static struct dentry *reset_dentry;
+static LIST_HEAD(all_head);
+static DEFINE_MUTEX(node_lock);
+
+/* If non-zero, keep copies of profiling data for unloaded modules. */
+static int gcov_persist = 1;
+
+static int __init gcov_persist_setup(char *str)
+{
+ unsigned long val;
+
+ if (strict_strtoul(str, 0, &val)) {
+ pr_warning("invalid gcov_persist parameter '%s'\n", str);
+ return 0;
+ }
+ gcov_persist = val;
+ pr_info("setting gcov_persist to %d\n", gcov_persist);
+
+ return 1;
+}
+__setup("gcov_persist=", gcov_persist_setup);
+
+/*
+ * seq_file.start() implementation for gcov data files. Note that the
+ * gcov_iterator interface is designed to be more restrictive than seq_file
+ * (no start from arbitrary position, etc.), to simplify the iterator
+ * implementation.
+ */
+static void *gcov_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ loff_t i;
+
+ gcov_iter_start(seq->private);
+ for (i = 0; i < *pos; i++) {
+ if (gcov_iter_next(seq->private))
+ return NULL;
+ }
+ return seq->private;
+}
+
+/* seq_file.next() implementation for gcov data files. */
+static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos)
+{
+ struct gcov_iterator *iter = data;
+
+ if (gcov_iter_next(iter))
+ return NULL;
+ (*pos)++;
+
+ return iter;
+}
+
+/* seq_file.show() implementation for gcov data files. */
+static int gcov_seq_show(struct seq_file *seq, void *data)
+{
+ struct gcov_iterator *iter = data;
+
+ if (gcov_iter_write(iter, seq))
+ return -EINVAL;
+ return 0;
+}
+
+static void gcov_seq_stop(struct seq_file *seq, void *data)
+{
+ /* Unused. */
+}
+
+static const struct seq_operations gcov_seq_ops = {
+ .start = gcov_seq_start,
+ .next = gcov_seq_next,
+ .show = gcov_seq_show,
+ .stop = gcov_seq_stop,
+};
+
+/*
+ * Return the profiling data set for a given node. This can either be the
+ * original profiling data structure or a duplicate (also called "ghost")
+ * in case the associated object file has been unloaded.
+ */
+static struct gcov_info *get_node_info(struct gcov_node *node)
+{
+ if (node->info)
+ return node->info;
+
+ return node->ghost;
+}
+
+/*
+ * open() implementation for gcov data files. Create a copy of the profiling
+ * data set and initialize the iterator and seq_file interface.
+ */
+static int gcov_seq_open(struct inode *inode, struct file *file)
+{
+ struct gcov_node *node = inode->i_private;
+ struct gcov_iterator *iter;
+ struct seq_file *seq;
+ struct gcov_info *info;
+ int rc = -ENOMEM;
+
+ mutex_lock(&node_lock);
+ /*
+ * Read from a profiling data copy to minimize reference tracking
+ * complexity and concurrent access.
+ */
+ info = gcov_info_dup(get_node_info(node));
+ if (!info)
+ goto out_unlock;
+ iter = gcov_iter_new(info);
+ if (!iter)
+ goto err_free_info;
+ rc = seq_open(file, &gcov_seq_ops);
+ if (rc)
+ goto err_free_iter_info;
+ seq = file->private_data;
+ seq->private = iter;
+out_unlock:
+ mutex_unlock(&node_lock);
+ return rc;
+
+err_free_iter_info:
+ gcov_iter_free(iter);
+err_free_info:
+ gcov_info_free(info);
+ goto out_unlock;
+}
+
+/*
+ * release() implementation for gcov data files. Release resources allocated
+ * by open().
+ */
+static int gcov_seq_release(struct inode *inode, struct file *file)
+{
+ struct gcov_iterator *iter;
+ struct gcov_info *info;
+ struct seq_file *seq;
+
+ seq = file->private_data;
+ iter = seq->private;
+ info = gcov_iter_get_info(iter);
+ gcov_iter_free(iter);
+ gcov_info_free(info);
+ seq_release(inode, file);
+
+ return 0;
+}
+
+/*
+ * Find a node by the associated data file name. Needs to be called with
+ * node_lock held.
+ */
+static struct gcov_node *get_node_by_name(const char *name)
+{
+ struct gcov_node *node;
+ struct gcov_info *info;
+
+ list_for_each_entry(node, &all_head, all) {
+ info = get_node_info(node);
+ if (info && (strcmp(info->filename, name) == 0))
+ return node;
+ }
+
+ return NULL;
+}
+
+static void remove_node(struct gcov_node *node);
+
+/*
+ * write() implementation for gcov data files. Reset profiling data for the
+ * associated file. If the object file has been unloaded (i.e. this is
+ * a "ghost" node), remove the debug fs node as well.
+ */
+static ssize_t gcov_seq_write(struct file *file, const char __user *addr,
+ size_t len, loff_t *pos)
+{
+ struct seq_file *seq;
+ struct gcov_info *info;
+ struct gcov_node *node;
+
+ seq = file->private_data;
+ info = gcov_iter_get_info(seq->private);
+ mutex_lock(&node_lock);
+ node = get_node_by_name(info->filename);
+ if (node) {
+ /* Reset counts or remove node for unloaded modules. */
+ if (node->ghost)
+ remove_node(node);
+ else
+ gcov_info_reset(node->info);
+ }
+ /* Reset counts for open file. */
+ gcov_info_reset(info);
+ mutex_unlock(&node_lock);
+
+ return len;
+}
+
+/*
+ * Given a string <path> representing a file path of format:
+ * path/to/file.gcda
+ * construct and return a new string:
+ * <dir/>path/to/file.<ext>
+ */
+static char *link_target(const char *dir, const char *path, const char *ext)
+{
+ char *target;
+ char *old_ext;
+ char *copy;
+
+ copy = kstrdup(path, GFP_KERNEL);
+ if (!copy)
+ return NULL;
+ old_ext = strrchr(copy, '.');
+ if (old_ext)
+ *old_ext = '\0';
+ if (dir)
+ target = kasprintf(GFP_KERNEL, "%s/%s.%s", dir, copy, ext);
+ else
+ target = kasprintf(GFP_KERNEL, "%s.%s", copy, ext);
+ kfree(copy);
+
+ return target;
+}
+
+/*
+ * Construct a string representing the symbolic link target for the given
+ * gcov data file name and link type. Depending on the link type and the
+ * location of the data file, the link target can either point to a
+ * subdirectory of srctree, objtree or in an external location.
+ */
+static char *get_link_target(const char *filename, const struct gcov_link *ext)
+{
+ const char *rel;
+ char *result;
+
+ if (strncmp(filename, objtree, strlen(objtree)) == 0) {
+ rel = filename + strlen(objtree) + 1;
+ if (ext->dir == SRC_TREE)
+ result = link_target(srctree, rel, ext->ext);
+ else
+ result = link_target(objtree, rel, ext->ext);
+ } else {
+ /* External compilation. */
+ result = link_target(NULL, filename, ext->ext);
+ }
+
+ return result;
+}
+
+#define SKEW_PREFIX ".tmp_"
+
+/*
+ * For a filename .tmp_filename.ext return filename.ext. Needed to compensate
+ * for filename skewing caused by the mod-versioning mechanism.
+ */
+static const char *deskew(const char *basename)
+{
+ if (strncmp(basename, SKEW_PREFIX, sizeof(SKEW_PREFIX) - 1) == 0)
+ return basename + sizeof(SKEW_PREFIX) - 1;
+ return basename;
+}
+
+/*
+ * Create links to additional files (usually .c and .gcno files) which the
+ * gcov tool expects to find in the same directory as the gcov data file.
+ */
+static void add_links(struct gcov_node *node, struct dentry *parent)
+{
+ char *basename;
+ char *target;
+ int num;
+ int i;
+
+ for (num = 0; gcov_link[num].ext; num++)
+ /* Nothing. */;
+ node->links = kcalloc(num, sizeof(struct dentry *), GFP_KERNEL);
+ if (!node->links)
+ return;
+ for (i = 0; i < num; i++) {
+ target = get_link_target(get_node_info(node)->filename,
+ &gcov_link[i]);
+ if (!target)
+ goto out_err;
+ basename = strrchr(target, '/');
+ if (!basename)
+ goto out_err;
+ basename++;
+ node->links[i] = debugfs_create_symlink(deskew(basename),
+ parent, target);
+ if (!node->links[i])
+ goto out_err;
+ kfree(target);
+ }
+
+ return;
+out_err:
+ kfree(target);
+ while (i-- > 0)
+ debugfs_remove(node->links[i]);
+ kfree(node->links);
+ node->links = NULL;
+}
+
+static const struct file_operations gcov_data_fops = {
+ .open = gcov_seq_open,
+ .release = gcov_seq_release,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .write = gcov_seq_write,
+};
+
+/* Basic initialization of a new node. */
+static void init_node(struct gcov_node *node, struct gcov_info *info,
+ const char *name, struct gcov_node *parent)
+{
+ INIT_LIST_HEAD(&node->list);
+ INIT_LIST_HEAD(&node->children);
+ INIT_LIST_HEAD(&node->all);
+ node->info = info;
+ node->parent = parent;
+ if (name)
+ strcpy(node->name, name);
+}
+
+/*
+ * Create a new node and associated debugfs entry. Needs to be called with
+ * node_lock held.
+ */
+static struct gcov_node *new_node(struct gcov_node *parent,
+ struct gcov_info *info, const char *name)
+{
+ struct gcov_node *node;
+
+ node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL);
+ if (!node) {
+ pr_warning("out of memory\n");
+ return NULL;
+ }
+ init_node(node, info, name, parent);
+ /* Differentiate between gcov data file nodes and directory nodes. */
+ if (info) {
+ node->dentry = debugfs_create_file(deskew(node->name), 0600,
+ parent->dentry, node, &gcov_data_fops);
+ } else
+ node->dentry = debugfs_create_dir(node->name, parent->dentry);
+ if (!node->dentry) {
+ pr_warning("could not create file\n");
+ kfree(node);
+ return NULL;
+ }
+ if (info)
+ add_links(node, parent->dentry);
+ list_add(&node->list, &parent->children);
+ list_add(&node->all, &all_head);
+
+ return node;
+}
+
+/* Remove symbolic links associated with node. */
+static void remove_links(struct gcov_node *node)
+{
+ int i;
+
+ if (!node->links)
+ return;
+ for (i = 0; gcov_link[i].ext; i++)
+ debugfs_remove(node->links[i]);
+ kfree(node->links);
+ node->links = NULL;
+}
+
+/*
+ * Remove node from all lists and debugfs and release associated resources.
+ * Needs to be called with node_lock held.
+ */
+static void release_node(struct gcov_node *node)
+{
+ list_del(&node->list);
+ list_del(&node->all);
+ debugfs_remove(node->dentry);
+ remove_links(node);
+ if (node->ghost)
+ gcov_info_free(node->ghost);
+ kfree(node);
+}
+
+/* Release node and empty parents. Needs to be called with node_lock held. */
+static void remove_node(struct gcov_node *node)
+{
+ struct gcov_node *parent;
+
+ while ((node != &root_node) && list_empty(&node->children)) {
+ parent = node->parent;
+ release_node(node);
+ node = parent;
+ }
+}
+
+/*
+ * Find child node with given basename. Needs to be called with node_lock
+ * held.
+ */
+static struct gcov_node *get_child_by_name(struct gcov_node *parent,
+ const char *name)
+{
+ struct gcov_node *node;
+
+ list_for_each_entry(node, &parent->children, list) {
+ if (strcmp(node->name, name) == 0)
+ return node;
+ }
+
+ return NULL;
+}
+
+/*
+ * write() implementation for reset file. Reset all profiling data to zero
+ * and remove ghost nodes.
+ */
+static ssize_t reset_write(struct file *file, const char __user *addr,
+ size_t len, loff_t *pos)
+{
+ struct gcov_node *node;
+
+ mutex_lock(&node_lock);
+restart:
+ list_for_each_entry(node, &all_head, all) {
+ if (node->info)
+ gcov_info_reset(node->info);
+ else if (list_empty(&node->children)) {
+ remove_node(node);
+ /* Several nodes may have gone - restart loop. */
+ goto restart;
+ }
+ }
+ mutex_unlock(&node_lock);
+
+ return len;
+}
+
+/* read() implementation for reset file. Unused. */
+static ssize_t reset_read(struct file *file, char __user *addr, size_t len,
+ loff_t *pos)
+{
+ /* Allow read operation so that a recursive copy won't fail. */
+ return 0;
+}
+
+static const struct file_operations gcov_reset_fops = {
+ .write = reset_write,
+ .read = reset_read,
+};
+
+/*
+ * Create a node for a given profiling data set and add it to all lists and
+ * debugfs. Needs to be called with node_lock held.
+ */
+static void add_node(struct gcov_info *info)
+{
+ char *filename;
+ char *curr;
+ char *next;
+ struct gcov_node *parent;
+ struct gcov_node *node;
+
+ filename = kstrdup(info->filename, GFP_KERNEL);
+ if (!filename)
+ return;
+ parent = &root_node;
+ /* Create directory nodes along the path. */
+ for (curr = filename; (next = strchr(curr, '/')); curr = next + 1) {
+ if (curr == next)
+ continue;
+ *next = 0;
+ if (strcmp(curr, ".") == 0)
+ continue;
+ if (strcmp(curr, "..") == 0) {
+ if (!parent->parent)
+ goto err_remove;
+ parent = parent->parent;
+ continue;
+ }
+ node = get_child_by_name(parent, curr);
+ if (!node) {
+ node = new_node(parent, NULL, curr);
+ if (!node)
+ goto err_remove;
+ }
+ parent = node;
+ }
+ /* Create file node. */
+ node = new_node(parent, info, curr);
+ if (!node)
+ goto err_remove;
+out:
+ kfree(filename);
+ return;
+
+err_remove:
+ remove_node(parent);
+ goto out;
+}
+
+/*
+ * The profiling data set associated with this node is being unloaded. Store a
+ * copy of the profiling data and turn this node into a "ghost".
+ */
+static int ghost_node(struct gcov_node *node)
+{
+ node->ghost = gcov_info_dup(node->info);
+ if (!node->ghost) {
+ pr_warning("could not save data for '%s' (out of memory)\n",
+ node->info->filename);
+ return -ENOMEM;
+ }
+ node->info = NULL;
+
+ return 0;
+}
+
+/*
+ * Profiling data for this node has been loaded again. Add profiling data
+ * from previous instantiation and turn this node into a regular node.
+ */
+static void revive_node(struct gcov_node *node, struct gcov_info *info)
+{
+ if (gcov_info_is_compatible(node->ghost, info))
+ gcov_info_add(info, node->ghost);
+ else {
+ pr_warning("discarding saved data for '%s' (version changed)\n",
+ info->filename);
+ }
+ gcov_info_free(node->ghost);
+ node->ghost = NULL;
+ node->info = info;
+}
+
+/*
+ * Callback to create/remove profiling files when code compiled with
+ * -fprofile-arcs is loaded/unloaded.
+ */
+void gcov_event(enum gcov_action action, struct gcov_info *info)
+{
+ struct gcov_node *node;
+
+ mutex_lock(&node_lock);
+ node = get_node_by_name(info->filename);
+ switch (action) {
+ case GCOV_ADD:
+ /* Add new node or revive ghost. */
+ if (!node) {
+ add_node(info);
+ break;
+ }
+ if (gcov_persist)
+ revive_node(node, info);
+ else {
+ pr_warning("could not add '%s' (already exists)\n",
+ info->filename);
+ }
+ break;
+ case GCOV_REMOVE:
+ /* Remove node or turn into ghost. */
+ if (!node) {
+ pr_warning("could not remove '%s' (not found)\n",
+ info->filename);
+ break;
+ }
+ if (gcov_persist) {
+ if (!ghost_node(node))
+ break;
+ }
+ remove_node(node);
+ break;
+ }
+ mutex_unlock(&node_lock);
+}
+
+/* Create debugfs entries. */
+static __init int gcov_fs_init(void)
+{
+ int rc = -EIO;
+
+ init_node(&root_node, NULL, NULL, NULL);
+ /*
+ * /sys/kernel/debug/gcov will be parent for the reset control file
+ * and all profiling files.
+ */
+ root_node.dentry = debugfs_create_dir("gcov", NULL);
+ if (!root_node.dentry)
+ goto err_remove;
+ /*
+ * Create reset file which resets all profiling counts when written
+ * to.
+ */
+ reset_dentry = debugfs_create_file("reset", 0600, root_node.dentry,
+ NULL, &gcov_reset_fops);
+ if (!reset_dentry)
+ goto err_remove;
+ /* Replay previous events to get our fs hierarchy up-to-date. */
+ gcov_enable_events();
+ return 0;
+
+err_remove:
+ pr_err("init failed\n");
+ if (root_node.dentry)
+ debugfs_remove(root_node.dentry);
+
+ return rc;
+}
+device_initcall(gcov_fs_init);
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
new file mode 100644
index 00000000000..ae5bb426003
--- /dev/null
+++ b/kernel/gcov/gcc_3_4.c
@@ -0,0 +1,447 @@
+/*
+ * This code provides functions to handle gcc's profiling data format
+ * introduced with gcc 3.4. Future versions of gcc may change the gcov
+ * format (as happened before), so all format-specific information needs
+ * to be kept modular and easily exchangeable.
+ *
+ * This file is based on gcc-internal definitions. Functions and data
+ * structures are defined to be compatible with gcc counterparts.
+ * For a better understanding, refer to gcc source: gcc/gcov-io.h.
+ *
+ * Copyright IBM Corp. 2009
+ * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ * Uses gcc-internal data definitions.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include "gcov.h"
+
+/* Symbolic links to be created for each profiling data file. */
+const struct gcov_link gcov_link[] = {
+ { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */
+ { 0, NULL},
+};
+
+/*
+ * Determine whether a counter is active. Based on gcc magic. Doesn't change
+ * at run-time.
+ */
+static int counter_active(struct gcov_info *info, unsigned int type)
+{
+ return (1 << type) & info->ctr_mask;
+}
+
+/* Determine number of active counters. Based on gcc magic. */
+static unsigned int num_counter_active(struct gcov_info *info)
+{
+ unsigned int i;
+ unsigned int result = 0;
+
+ for (i = 0; i < GCOV_COUNTERS; i++) {
+ if (counter_active(info, i))
+ result++;
+ }
+ return result;
+}
+
+/**
+ * gcov_info_reset - reset profiling data to zero
+ * @info: profiling data set
+ */
+void gcov_info_reset(struct gcov_info *info)
+{
+ unsigned int active = num_counter_active(info);
+ unsigned int i;
+
+ for (i = 0; i < active; i++) {
+ memset(info->counts[i].values, 0,
+ info->counts[i].num * sizeof(gcov_type));
+ }
+}
+
+/**
+ * gcov_info_is_compatible - check if profiling data can be added
+ * @info1: first profiling data set
+ * @info2: second profiling data set
+ *
+ * Returns non-zero if profiling data can be added, zero otherwise.
+ */
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
+{
+ return (info1->stamp == info2->stamp);
+}
+
+/**
+ * gcov_info_add - add up profiling data
+ * @dest: profiling data set to which data is added
+ * @source: profiling data set which is added
+ *
+ * Adds profiling counts of @source to @dest.
+ */
+void gcov_info_add(struct gcov_info *dest, struct gcov_info *source)
+{
+ unsigned int i;
+ unsigned int j;
+
+ for (i = 0; i < num_counter_active(dest); i++) {
+ for (j = 0; j < dest->counts[i].num; j++) {
+ dest->counts[i].values[j] +=
+ source->counts[i].values[j];
+ }
+ }
+}
+
+/* Get size of function info entry. Based on gcc magic. */
+static size_t get_fn_size(struct gcov_info *info)
+{
+ size_t size;
+
+ size = sizeof(struct gcov_fn_info) + num_counter_active(info) *
+ sizeof(unsigned int);
+ if (__alignof__(struct gcov_fn_info) > sizeof(unsigned int))
+ size = ALIGN(size, __alignof__(struct gcov_fn_info));
+ return size;
+}
+
+/* Get address of function info entry. Based on gcc magic. */
+static struct gcov_fn_info *get_fn_info(struct gcov_info *info, unsigned int fn)
+{
+ return (struct gcov_fn_info *)
+ ((char *) info->functions + fn * get_fn_size(info));
+}
+
+/**
+ * gcov_info_dup - duplicate profiling data set
+ * @info: profiling data set to duplicate
+ *
+ * Return newly allocated duplicate on success, %NULL on error.
+ */
+struct gcov_info *gcov_info_dup(struct gcov_info *info)
+{
+ struct gcov_info *dup;
+ unsigned int i;
+ unsigned int active;
+
+ /* Duplicate gcov_info. */
+ active = num_counter_active(info);
+ dup = kzalloc(sizeof(struct gcov_info) +
+ sizeof(struct gcov_ctr_info) * active, GFP_KERNEL);
+ if (!dup)
+ return NULL;
+ dup->version = info->version;
+ dup->stamp = info->stamp;
+ dup->n_functions = info->n_functions;
+ dup->ctr_mask = info->ctr_mask;
+ /* Duplicate filename. */
+ dup->filename = kstrdup(info->filename, GFP_KERNEL);
+ if (!dup->filename)
+ goto err_free;
+ /* Duplicate table of functions. */
+ dup->functions = kmemdup(info->functions, info->n_functions *
+ get_fn_size(info), GFP_KERNEL);
+ if (!dup->functions)
+ goto err_free;
+ /* Duplicate counter arrays. */
+ for (i = 0; i < active ; i++) {
+ struct gcov_ctr_info *ctr = &info->counts[i];
+ size_t size = ctr->num * sizeof(gcov_type);
+
+ dup->counts[i].num = ctr->num;
+ dup->counts[i].merge = ctr->merge;
+ dup->counts[i].values = vmalloc(size);
+ if (!dup->counts[i].values)
+ goto err_free;
+ memcpy(dup->counts[i].values, ctr->values, size);
+ }
+ return dup;
+
+err_free:
+ gcov_info_free(dup);
+ return NULL;
+}
+
+/**
+ * gcov_info_free - release memory for profiling data set duplicate
+ * @info: profiling data set duplicate to free
+ */
+void gcov_info_free(struct gcov_info *info)
+{
+ unsigned int active = num_counter_active(info);
+ unsigned int i;
+
+ for (i = 0; i < active ; i++)
+ vfree(info->counts[i].values);
+ kfree(info->functions);
+ kfree(info->filename);
+ kfree(info);
+}
+
+/**
+ * struct type_info - iterator helper array
+ * @ctr_type: counter type
+ * @offset: index of the first value of the current function for this type
+ *
+ * This array is needed to convert the in-memory data format into the in-file
+ * data format:
+ *
+ * In-memory:
+ * for each counter type
+ * for each function
+ * values
+ *
+ * In-file:
+ * for each function
+ * for each counter type
+ * values
+ *
+ * See gcc source gcc/gcov-io.h for more information on data organization.
+ */
+struct type_info {
+ int ctr_type;
+ unsigned int offset;
+};
+
+/**
+ * struct gcov_iterator - specifies current file position in logical records
+ * @info: associated profiling data
+ * @record: record type
+ * @function: function number
+ * @type: counter type
+ * @count: index into values array
+ * @num_types: number of counter types
+ * @type_info: helper array to get values-array offset for current function
+ */
+struct gcov_iterator {
+ struct gcov_info *info;
+
+ int record;
+ unsigned int function;
+ unsigned int type;
+ unsigned int count;
+
+ int num_types;
+ struct type_info type_info[0];
+};
+
+static struct gcov_fn_info *get_func(struct gcov_iterator *iter)
+{
+ return get_fn_info(iter->info, iter->function);
+}
+
+static struct type_info *get_type(struct gcov_iterator *iter)
+{
+ return &iter->type_info[iter->type];
+}
+
+/**
+ * gcov_iter_new - allocate and initialize profiling data iterator
+ * @info: profiling data set to be iterated
+ *
+ * Return file iterator on success, %NULL otherwise.
+ */
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
+{
+ struct gcov_iterator *iter;
+
+ iter = kzalloc(sizeof(struct gcov_iterator) +
+ num_counter_active(info) * sizeof(struct type_info),
+ GFP_KERNEL);
+ if (iter)
+ iter->info = info;
+
+ return iter;
+}
+
+/**
+ * gcov_iter_free - release memory for iterator
+ * @iter: file iterator to free
+ */
+void gcov_iter_free(struct gcov_iterator *iter)
+{
+ kfree(iter);
+}
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
+{
+ return iter->info;
+}
+
+/**
+ * gcov_iter_start - reset file iterator to starting position
+ * @iter: file iterator
+ */
+void gcov_iter_start(struct gcov_iterator *iter)
+{
+ int i;
+
+ iter->record = 0;
+ iter->function = 0;
+ iter->type = 0;
+ iter->count = 0;
+ iter->num_types = 0;
+ for (i = 0; i < GCOV_COUNTERS; i++) {
+ if (counter_active(iter->info, i)) {
+ iter->type_info[iter->num_types].ctr_type = i;
+ iter->type_info[iter->num_types++].offset = 0;
+ }
+ }
+}
+
+/* Mapping of logical record number to actual file content. */
+#define RECORD_FILE_MAGIC 0
+#define RECORD_GCOV_VERSION 1
+#define RECORD_TIME_STAMP 2
+#define RECORD_FUNCTION_TAG 3
+#define RECORD_FUNCTON_TAG_LEN 4
+#define RECORD_FUNCTION_IDENT 5
+#define RECORD_FUNCTION_CHECK 6
+#define RECORD_COUNT_TAG 7
+#define RECORD_COUNT_LEN 8
+#define RECORD_COUNT 9
+
+/**
+ * gcov_iter_next - advance file iterator to next logical record
+ * @iter: file iterator
+ *
+ * Return zero if new position is valid, non-zero if iterator has reached end.
+ */
+int gcov_iter_next(struct gcov_iterator *iter)
+{
+ switch (iter->record) {
+ case RECORD_FILE_MAGIC:
+ case RECORD_GCOV_VERSION:
+ case RECORD_FUNCTION_TAG:
+ case RECORD_FUNCTON_TAG_LEN:
+ case RECORD_FUNCTION_IDENT:
+ case RECORD_COUNT_TAG:
+ /* Advance to next record */
+ iter->record++;
+ break;
+ case RECORD_COUNT:
+ /* Advance to next count */
+ iter->count++;
+ /* fall through */
+ case RECORD_COUNT_LEN:
+ if (iter->count < get_func(iter)->n_ctrs[iter->type]) {
+ iter->record = 9;
+ break;
+ }
+ /* Advance to next counter type */
+ get_type(iter)->offset += iter->count;
+ iter->count = 0;
+ iter->type++;
+ /* fall through */
+ case RECORD_FUNCTION_CHECK:
+ if (iter->type < iter->num_types) {
+ iter->record = 7;
+ break;
+ }
+ /* Advance to next function */
+ iter->type = 0;
+ iter->function++;
+ /* fall through */
+ case RECORD_TIME_STAMP:
+ if (iter->function < iter->info->n_functions)
+ iter->record = 3;
+ else
+ iter->record = -1;
+ break;
+ }
+ /* Check for EOF. */
+ if (iter->record == -1)
+ return -EINVAL;
+ else
+ return 0;
+}
+
+/**
+ * seq_write_gcov_u32 - write 32 bit number in gcov format to seq_file
+ * @seq: seq_file handle
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file.
+ */
+static int seq_write_gcov_u32(struct seq_file *seq, u32 v)
+{
+ return seq_write(seq, &v, sizeof(v));
+}
+
+/**
+ * seq_write_gcov_u64 - write 64 bit number in gcov format to seq_file
+ * @seq: seq_file handle
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. 64 bit numbers are stored as two 32 bit numbers, the low part
+ * first.
+ */
+static int seq_write_gcov_u64(struct seq_file *seq, u64 v)
+{
+ u32 data[2];
+
+ data[0] = (v & 0xffffffffUL);
+ data[1] = (v >> 32);
+ return seq_write(seq, data, sizeof(data));
+}
+
+/**
+ * gcov_iter_write - write data for current pos to seq_file
+ * @iter: file iterator
+ * @seq: seq_file handle
+ *
+ * Return zero on success, non-zero otherwise.
+ */
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
+{
+ int rc = -EINVAL;
+
+ switch (iter->record) {
+ case RECORD_FILE_MAGIC:
+ rc = seq_write_gcov_u32(seq, GCOV_DATA_MAGIC);
+ break;
+ case RECORD_GCOV_VERSION:
+ rc = seq_write_gcov_u32(seq, iter->info->version);
+ break;
+ case RECORD_TIME_STAMP:
+ rc = seq_write_gcov_u32(seq, iter->info->stamp);
+ break;
+ case RECORD_FUNCTION_TAG:
+ rc = seq_write_gcov_u32(seq, GCOV_TAG_FUNCTION);
+ break;
+ case RECORD_FUNCTON_TAG_LEN:
+ rc = seq_write_gcov_u32(seq, 2);
+ break;
+ case RECORD_FUNCTION_IDENT:
+ rc = seq_write_gcov_u32(seq, get_func(iter)->ident);
+ break;
+ case RECORD_FUNCTION_CHECK:
+ rc = seq_write_gcov_u32(seq, get_func(iter)->checksum);
+ break;
+ case RECORD_COUNT_TAG:
+ rc = seq_write_gcov_u32(seq,
+ GCOV_TAG_FOR_COUNTER(get_type(iter)->ctr_type));
+ break;
+ case RECORD_COUNT_LEN:
+ rc = seq_write_gcov_u32(seq,
+ get_func(iter)->n_ctrs[iter->type] * 2);
+ break;
+ case RECORD_COUNT:
+ rc = seq_write_gcov_u64(seq,
+ iter->info->counts[iter->type].
+ values[iter->count + get_type(iter)->offset]);
+ break;
+ }
+ return rc;
+}
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
new file mode 100644
index 00000000000..060073ebf7a
--- /dev/null
+++ b/kernel/gcov/gcov.h
@@ -0,0 +1,128 @@
+/*
+ * Profiling infrastructure declarations.
+ *
+ * This file is based on gcc-internal definitions. Data structures are
+ * defined to be compatible with gcc counterparts. For a better
+ * understanding, refer to gcc source: gcc/gcov-io.h.
+ *
+ * Copyright IBM Corp. 2009
+ * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ * Uses gcc-internal data definitions.
+ */
+
+#ifndef GCOV_H
+#define GCOV_H GCOV_H
+
+#include <linux/types.h>
+
+/*
+ * Profiling data types used for gcc 3.4 and above - these are defined by
+ * gcc and need to be kept as close to the original definition as possible to
+ * remain compatible.
+ */
+#define GCOV_COUNTERS 5
+#define GCOV_DATA_MAGIC ((unsigned int) 0x67636461)
+#define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000)
+#define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000)
+#define GCOV_TAG_FOR_COUNTER(count) \
+ (GCOV_TAG_COUNTER_BASE + ((unsigned int) (count) << 17))
+
+#if BITS_PER_LONG >= 64
+typedef long gcov_type;
+#else
+typedef long long gcov_type;
+#endif
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @ident: object file-unique function identifier
+ * @checksum: function checksum
+ * @n_ctrs: number of values per counter type belonging to this function
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ */
+struct gcov_fn_info {
+ unsigned int ident;
+ unsigned int checksum;
+ unsigned int n_ctrs[0];
+};
+
+/**
+ * struct gcov_ctr_info - profiling data per counter type
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ * @merge: merge function for counter values of this type (unused)
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+ unsigned int num;
+ gcov_type *values;
+ void (*merge)(gcov_type *, unsigned int);
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: time stamp
+ * @filename: name of the associated gcov data file
+ * @n_functions: number of instrumented functions
+ * @functions: function data
+ * @ctr_mask: mask specifying which counter types are active
+ * @counts: counter data per counter type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+ unsigned int version;
+ struct gcov_info *next;
+ unsigned int stamp;
+ const char *filename;
+ unsigned int n_functions;
+ const struct gcov_fn_info *functions;
+ unsigned int ctr_mask;
+ struct gcov_ctr_info counts[0];
+};
+
+/* Base interface. */
+enum gcov_action {
+ GCOV_ADD,
+ GCOV_REMOVE,
+};
+
+void gcov_event(enum gcov_action action, struct gcov_info *info);
+void gcov_enable_events(void);
+
+/* Iterator control. */
+struct seq_file;
+struct gcov_iterator;
+
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info);
+void gcov_iter_free(struct gcov_iterator *iter);
+void gcov_iter_start(struct gcov_iterator *iter);
+int gcov_iter_next(struct gcov_iterator *iter);
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq);
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter);
+
+/* gcov_info control. */
+void gcov_info_reset(struct gcov_info *info);
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2);
+void gcov_info_add(struct gcov_info *dest, struct gcov_info *source);
+struct gcov_info *gcov_info_dup(struct gcov_info *info);
+void gcov_info_free(struct gcov_info *info);
+
+struct gcov_link {
+ enum {
+ OBJ_TREE,
+ SRC_TREE,
+ } dir;
+ const char *ext;
+};
+extern const struct gcov_link gcov_link[];
+
+#endif /* GCOV_H */
diff --git a/kernel/groups.c b/kernel/groups.c
new file mode 100644
index 00000000000..2b45b2ee396
--- /dev/null
+++ b/kernel/groups.c
@@ -0,0 +1,288 @@
+/*
+ * Supplementary group IDs
+ */
+#include <linux/cred.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <asm/uaccess.h>
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+
+struct group_info *groups_alloc(int gidsetsize)
+{
+ struct group_info *group_info;
+ int nblocks;
+ int i;
+
+ nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
+ /* Make sure we always allocate at least one indirect block pointer */
+ nblocks = nblocks ? : 1;
+ group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
+ if (!group_info)
+ return NULL;
+ group_info->ngroups = gidsetsize;
+ group_info->nblocks = nblocks;
+ atomic_set(&group_info->usage, 1);
+
+ if (gidsetsize <= NGROUPS_SMALL)
+ group_info->blocks[0] = group_info->small_block;
+ else {
+ for (i = 0; i < nblocks; i++) {
+ gid_t *b;
+ b = (void *)__get_free_page(GFP_USER);
+ if (!b)
+ goto out_undo_partial_alloc;
+ group_info->blocks[i] = b;
+ }
+ }
+ return group_info;
+
+out_undo_partial_alloc:
+ while (--i >= 0) {
+ free_page((unsigned long)group_info->blocks[i]);
+ }
+ kfree(group_info);
+ return NULL;
+}
+
+EXPORT_SYMBOL(groups_alloc);
+
+void groups_free(struct group_info *group_info)
+{
+ if (group_info->blocks[0] != group_info->small_block) {
+ int i;
+ for (i = 0; i < group_info->nblocks; i++)
+ free_page((unsigned long)group_info->blocks[i]);
+ }
+ kfree(group_info);
+}
+
+EXPORT_SYMBOL(groups_free);
+
+/* export the group_info to a user-space array */
+static int groups_to_user(gid_t __user *grouplist,
+ const struct group_info *group_info)
+{
+ int i;
+ unsigned int count = group_info->ngroups;
+
+ for (i = 0; i < group_info->nblocks; i++) {
+ unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+ unsigned int len = cp_count * sizeof(*grouplist);
+
+ if (copy_to_user(grouplist, group_info->blocks[i], len))
+ return -EFAULT;
+
+ grouplist += NGROUPS_PER_BLOCK;
+ count -= cp_count;
+ }
+ return 0;
+}
+
+/* fill a group_info from a user-space array - it must be allocated already */
+static int groups_from_user(struct group_info *group_info,
+ gid_t __user *grouplist)
+{
+ int i;
+ unsigned int count = group_info->ngroups;
+
+ for (i = 0; i < group_info->nblocks; i++) {
+ unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
+ unsigned int len = cp_count * sizeof(*grouplist);
+
+ if (copy_from_user(group_info->blocks[i], grouplist, len))
+ return -EFAULT;
+
+ grouplist += NGROUPS_PER_BLOCK;
+ count -= cp_count;
+ }
+ return 0;
+}
+
+/* a simple Shell sort */
+static void groups_sort(struct group_info *group_info)
+{
+ int base, max, stride;
+ int gidsetsize = group_info->ngroups;
+
+ for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
+ ; /* nothing */
+ stride /= 3;
+
+ while (stride) {
+ max = gidsetsize - stride;
+ for (base = 0; base < max; base++) {
+ int left = base;
+ int right = left + stride;
+ gid_t tmp = GROUP_AT(group_info, right);
+
+ while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
+ GROUP_AT(group_info, right) =
+ GROUP_AT(group_info, left);
+ right = left;
+ left -= stride;
+ }
+ GROUP_AT(group_info, right) = tmp;
+ }
+ stride /= 3;
+ }
+}
+
+/* a simple bsearch */
+int groups_search(const struct group_info *group_info, gid_t grp)
+{
+ unsigned int left, right;
+
+ if (!group_info)
+ return 0;
+
+ left = 0;
+ right = group_info->ngroups;
+ while (left < right) {
+ unsigned int mid = (left+right)/2;
+ int cmp = grp - GROUP_AT(group_info, mid);
+ if (cmp > 0)
+ left = mid + 1;
+ else if (cmp < 0)
+ right = mid;
+ else
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * set_groups - Change a group subscription in a set of credentials
+ * @new: The newly prepared set of credentials to alter
+ * @group_info: The group list to install
+ *
+ * Validate a group subscription and, if valid, insert it into a set
+ * of credentials.
+ */
+int set_groups(struct cred *new, struct group_info *group_info)
+{
+ int retval;
+
+ retval = security_task_setgroups(group_info);
+ if (retval)
+ return retval;
+
+ put_group_info(new->group_info);
+ groups_sort(group_info);
+ get_group_info(group_info);
+ new->group_info = group_info;
+ return 0;
+}
+
+EXPORT_SYMBOL(set_groups);
+
+/**
+ * set_current_groups - Change current's group subscription
+ * @group_info: The group list to impose
+ *
+ * Validate a group subscription and, if valid, impose it upon current's task
+ * security record.
+ */
+int set_current_groups(struct group_info *group_info)
+{
+ struct cred *new;
+ int ret;
+
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+
+ ret = set_groups(new, group_info);
+ if (ret < 0) {
+ abort_creds(new);
+ return ret;
+ }
+
+ return commit_creds(new);
+}
+
+EXPORT_SYMBOL(set_current_groups);
+
+SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+ const struct cred *cred = current_cred();
+ int i;
+
+ if (gidsetsize < 0)
+ return -EINVAL;
+
+ /* no need to grab task_lock here; it cannot change */
+ i = cred->group_info->ngroups;
+ if (gidsetsize) {
+ if (i > gidsetsize) {
+ i = -EINVAL;
+ goto out;
+ }
+ if (groups_to_user(grouplist, cred->group_info)) {
+ i = -EFAULT;
+ goto out;
+ }
+ }
+out:
+ return i;
+}
+
+/*
+ * SMP: Our groups are copy-on-write. We can set them safely
+ * without another task interfering.
+ */
+
+SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
+{
+ struct group_info *group_info;
+ int retval;
+
+ if (!capable(CAP_SETGID))
+ return -EPERM;
+ if ((unsigned)gidsetsize > NGROUPS_MAX)
+ return -EINVAL;
+
+ group_info = groups_alloc(gidsetsize);
+ if (!group_info)
+ return -ENOMEM;
+ retval = groups_from_user(group_info, grouplist);
+ if (retval) {
+ put_group_info(group_info);
+ return retval;
+ }
+
+ retval = set_current_groups(group_info);
+ put_group_info(group_info);
+
+ return retval;
+}
+
+/*
+ * Check whether we're fsgid/egid or in the supplemental group..
+ */
+int in_group_p(gid_t grp)
+{
+ const struct cred *cred = current_cred();
+ int retval = 1;
+
+ if (grp != cred->fsgid)
+ retval = groups_search(cred->group_info, grp);
+ return retval;
+}
+
+EXPORT_SYMBOL(in_group_p);
+
+int in_egroup_p(gid_t grp)
+{
+ const struct cred *cred = current_cred();
+ int retval = 1;
+
+ if (grp != cred->egid)
+ retval = groups_search(cred->group_info, grp);
+ return retval;
+}
+
+EXPORT_SYMBOL(in_egroup_p);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cb8a15c1958..9002958a96e 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -43,6 +43,8 @@
#include <linux/seq_file.h>
#include <linux/err.h>
#include <linux/debugobjects.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
#include <asm/uaccess.h>
@@ -193,12 +195,24 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
* Switch the timer base to the current CPU when possible.
*/
static inline struct hrtimer_clock_base *
-switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
+ int pinned)
{
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
- new_cpu_base = &__get_cpu_var(hrtimer_bases);
+again:
+ new_cpu_base = &per_cpu(hrtimer_bases, cpu);
new_base = &new_cpu_base->clock_base[base->index];
if (base != new_base) {
@@ -218,6 +232,40 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
timer->base = NULL;
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;
+ }
+ }
timer->base = new_base;
}
return new_base;
@@ -235,7 +283,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
return base;
}
-# define switch_hrtimer_base(t, b) (b)
+# define switch_hrtimer_base(t, b, p) (b)
#endif /* !CONFIG_SMP */
@@ -332,6 +380,8 @@ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
return res;
}
+EXPORT_SYMBOL_GPL(ktime_add_safe);
+
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static struct debug_obj_descr hrtimer_debug_descr;
@@ -907,9 +957,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
ret = remove_hrtimer(timer, base);
/* Switch the timer base, if necessary: */
- new_base = switch_hrtimer_base(timer, base);
+ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
- if (mode == HRTIMER_MODE_REL) {
+ if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, new_base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a60018402f4..065205bdd92 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -45,7 +45,7 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
static void __init init_irq_default_affinity(void)
{
- alloc_bootmem_cpumask_var(&irq_default_affinity);
+ alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
cpumask_setall(irq_default_affinity);
}
#else
@@ -150,6 +150,7 @@ int __init early_irq_init(void)
{
struct irq_desc *desc;
int legacy_count;
+ int node;
int i;
init_irq_default_affinity();
@@ -160,20 +161,20 @@ int __init early_irq_init(void)
desc = irq_desc_legacy;
legacy_count = ARRAY_SIZE(irq_desc_legacy);
+ node = first_online_node;
/* allocate irq_desc_ptrs array based on nr_irqs */
- irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+ irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
/* allocate based on nr_cpu_ids */
- /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
- kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
- sizeof(int));
+ kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
+ sizeof(int), GFP_NOWAIT, node);
for (i = 0; i < legacy_count; i++) {
desc[i].irq = i;
desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
- alloc_desc_masks(&desc[i], 0, true);
+ alloc_desc_masks(&desc[i], node, true);
init_desc_masks(&desc[i]);
irq_desc_ptrs[i] = desc + i;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index aaf5c9d0577..50da6767290 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -856,7 +856,7 @@ EXPORT_SYMBOL(free_irq);
* still called in hard interrupt context and has to check
* whether the interrupt originates from the device. If yes it
* needs to disable the interrupt on the device and return
- * IRQ_THREAD_WAKE which will wake up the handler thread and run
+ * IRQ_WAKE_THREAD which will wake up the handler thread and run
* @thread_fn. This split handler design is necessary to support
* shared interrupts.
*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 374faf9bfdc..3a29dbe7898 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,12 +30,16 @@
#define all_var 0
#endif
-/* These will be re-linked against their real values during the second link stage */
+/*
+ * These will be re-linked against their real values
+ * during the second link stage.
+ */
extern const unsigned long kallsyms_addresses[] __attribute__((weak));
extern const u8 kallsyms_names[] __attribute__((weak));
-/* tell the compiler that the count isn't in the small data section if the arch
- * has one (eg: FRV)
+/*
+ * Tell the compiler that the count isn't in the small data section if the arch
+ * has one (eg: FRV).
*/
extern const unsigned long kallsyms_num_syms
__attribute__((weak, section(".rodata")));
@@ -75,31 +79,37 @@ static int is_ksym_addr(unsigned long addr)
return is_kernel_text(addr) || is_kernel_inittext(addr);
}
-/* expand a compressed symbol data into the resulting uncompressed string,
- given the offset to where the symbol is in the compressed stream */
+/*
+ * Expand a compressed symbol data into the resulting uncompressed string,
+ * given the offset to where the symbol is in the compressed stream.
+ */
static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
{
int len, skipped_first = 0;
const u8 *tptr, *data;
- /* get the compressed symbol length from the first symbol byte */
+ /* Get the compressed symbol length from the first symbol byte. */
data = &kallsyms_names[off];
len = *data;
data++;
- /* update the offset to return the offset for the next symbol on
- * the compressed stream */
+ /*
+ * Update the offset to return the offset for the next symbol on
+ * the compressed stream.
+ */
off += len + 1;
- /* for every byte on the compressed symbol data, copy the table
- entry for that byte */
- while(len) {
- tptr = &kallsyms_token_table[ kallsyms_token_index[*data] ];
+ /*
+ * For every byte on the compressed symbol data, copy the table
+ * entry for that byte.
+ */
+ while (len) {
+ tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
data++;
len--;
while (*tptr) {
- if(skipped_first) {
+ if (skipped_first) {
*result = *tptr;
result++;
} else
@@ -110,36 +120,46 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
*result = '\0';
- /* return to offset to the next symbol */
+ /* Return to offset to the next symbol. */
return off;
}
-/* get symbol type information. This is encoded as a single char at the
- * begining of the symbol name */
+/*
+ * Get symbol type information. This is encoded as a single char at the
+ * beginning of the symbol name.
+ */
static char kallsyms_get_symbol_type(unsigned int off)
{
- /* get just the first code, look it up in the token table, and return the
- * first char from this token */
- return kallsyms_token_table[ kallsyms_token_index[ kallsyms_names[off+1] ] ];
+ /*
+ * Get just the first code, look it up in the token table,
+ * and return the first char from this token.
+ */
+ return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
}
-/* find the offset on the compressed stream given and index in the
- * kallsyms array */
+/*
+ * Find the offset on the compressed stream given and index in the
+ * kallsyms array.
+ */
static unsigned int get_symbol_offset(unsigned long pos)
{
const u8 *name;
int i;
- /* use the closest marker we have. We have markers every 256 positions,
- * so that should be close enough */
- name = &kallsyms_names[ kallsyms_markers[pos>>8] ];
+ /*
+ * Use the closest marker we have. We have markers every 256 positions,
+ * so that should be close enough.
+ */
+ name = &kallsyms_names[kallsyms_markers[pos >> 8]];
- /* sequentially scan all the symbols up to the point we're searching for.
- * Every symbol is stored in a [<len>][<len> bytes of data] format, so we
- * just need to add the len to the current pointer for every symbol we
- * wish to skip */
- for(i = 0; i < (pos&0xFF); i++)
+ /*
+ * Sequentially scan all the symbols up to the point we're searching
+ * for. Every symbol is stored in a [<len>][<len> bytes of data] format,
+ * so we just need to add the len to the current pointer for every
+ * symbol we wish to skip.
+ */
+ for (i = 0; i < (pos & 0xFF); i++)
name = name + (*name) + 1;
return name - kallsyms_names;
@@ -190,7 +210,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
/* This kernel should never had been booted. */
BUG_ON(!kallsyms_addresses);
- /* do a binary search on the sorted kallsyms_addresses array */
+ /* Do a binary search on the sorted kallsyms_addresses array. */
low = 0;
high = kallsyms_num_syms;
@@ -203,15 +223,15 @@ static unsigned long get_symbol_pos(unsigned long addr,
}
/*
- * search for the first aliased symbol. Aliased
- * symbols are symbols with the same address
+ * Search for the first aliased symbol. Aliased
+ * symbols are symbols with the same address.
*/
while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
--low;
symbol_start = kallsyms_addresses[low];
- /* Search for next non-aliased symbol */
+ /* Search for next non-aliased symbol. */
for (i = low + 1; i < kallsyms_num_syms; i++) {
if (kallsyms_addresses[i] > symbol_start) {
symbol_end = kallsyms_addresses[i];
@@ -219,7 +239,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
}
}
- /* if we found no next symbol, we use the end of the section */
+ /* If we found no next symbol, we use the end of the section. */
if (!symbol_end) {
if (is_kernel_inittext(addr))
symbol_end = (unsigned long)_einittext;
@@ -252,10 +272,10 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
/*
* Lookup an address
- * - modname is set to NULL if it's in the kernel
- * - we guarantee that the returned name is valid until we reschedule even if
- * it resides in a module
- * - we also guarantee that modname will be valid until rescheduled
+ * - modname is set to NULL if it's in the kernel.
+ * - We guarantee that the returned name is valid until we reschedule even if.
+ * It resides in a module.
+ * - We also guarantee that modname will be valid until rescheduled.
*/
const char *kallsyms_lookup(unsigned long addr,
unsigned long *symbolsize,
@@ -276,7 +296,7 @@ const char *kallsyms_lookup(unsigned long addr,
return namebuf;
}
- /* see if it's in a module */
+ /* See if it's in a module. */
return module_address_lookup(addr, symbolsize, offset, modname,
namebuf);
}
@@ -294,7 +314,7 @@ int lookup_symbol_name(unsigned long addr, char *symname)
kallsyms_expand_symbol(get_symbol_offset(pos), symname);
return 0;
}
- /* see if it's in a module */
+ /* See if it's in a module. */
return lookup_module_symbol_name(addr, symname);
}
@@ -313,7 +333,7 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
modname[0] = '\0';
return 0;
}
- /* see if it's in a module */
+ /* See if it's in a module. */
return lookup_module_symbol_attrs(addr, size, offset, modname, name);
}
@@ -342,6 +362,7 @@ int sprint_symbol(char *buffer, unsigned long address)
return len;
}
+EXPORT_SYMBOL_GPL(sprint_symbol);
/* Look up a kernel symbol and print it to the kernel messages. */
void __print_symbol(const char *fmt, unsigned long address)
@@ -352,13 +373,13 @@ void __print_symbol(const char *fmt, unsigned long address)
printk(fmt, buffer);
}
+EXPORT_SYMBOL(__print_symbol);
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
-struct kallsym_iter
-{
+struct kallsym_iter {
loff_t pos;
unsigned long value;
- unsigned int nameoff; /* If iterating in core kernel symbols */
+ unsigned int nameoff; /* If iterating in core kernel symbols. */
char type;
char name[KSYM_NAME_LEN];
char module_name[MODULE_NAME_LEN];
@@ -404,7 +425,7 @@ static int update_iter(struct kallsym_iter *iter, loff_t pos)
iter->pos = pos;
return get_ksymbol_mod(iter);
}
-
+
/* If we're not on the desired position, reset to new position. */
if (pos != iter->pos)
reset_iter(iter, pos);
@@ -439,23 +460,25 @@ static int s_show(struct seq_file *m, void *p)
{
struct kallsym_iter *iter = m->private;
- /* Some debugging symbols have no name. Ignore them. */
+ /* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
if (iter->module_name[0]) {
char type;
- /* Label it "global" if it is exported,
- * "local" if not exported. */
+ /*
+ * Label it "global" if it is exported,
+ * "local" if not exported.
+ */
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
seq_printf(m, "%0*lx %c %s\t[%s]\n",
- (int)(2*sizeof(void*)),
+ (int)(2 * sizeof(void *)),
iter->value, type, iter->name, iter->module_name);
} else
seq_printf(m, "%0*lx %c %s\n",
- (int)(2*sizeof(void*)),
+ (int)(2 * sizeof(void *)),
iter->value, iter->type, iter->name);
return 0;
}
@@ -469,9 +492,11 @@ static const struct seq_operations kallsyms_op = {
static int kallsyms_open(struct inode *inode, struct file *file)
{
- /* We keep iterator in m->private, since normal case is to
+ /*
+ * We keep iterator in m->private, since normal case is to
* s_start from where we left off, so we avoid doing
- * using get_symbol_offset for every symbol */
+ * using get_symbol_offset for every symbol.
+ */
struct kallsym_iter *iter;
int ret;
@@ -500,7 +525,4 @@ static int __init kallsyms_init(void)
proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
return 0;
}
-__initcall(kallsyms_init);
-
-EXPORT_SYMBOL(__print_symbol);
-EXPORT_SYMBOL_GPL(sprint_symbol);
+device_initcall(kallsyms_init);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index e4983770913..ae1c35201cc 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1448,17 +1448,17 @@ int kernel_kexec(void)
goto Restore_console;
}
suspend_console();
- error = device_suspend(PMSG_FREEZE);
+ error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Resume_console;
- /* At this point, device_suspend() has been called,
- * but *not* device_power_down(). We *must*
- * device_power_down() now. Otherwise, drivers for
+ /* At this point, dpm_suspend_start() has been called,
+ * but *not* dpm_suspend_noirq(). We *must* call
+ * dpm_suspend_noirq() now. Otherwise, drivers for
* some devices (e.g. interrupt controllers) become
* desynchronized with the actual state of the
* hardware at resume time, and evil weirdness ensues.
*/
- error = device_power_down(PMSG_FREEZE);
+ error = dpm_suspend_noirq(PMSG_FREEZE);
if (error)
goto Resume_devices;
error = disable_nonboot_cpus();
@@ -1486,9 +1486,9 @@ int kernel_kexec(void)
local_irq_enable();
Enable_cpus:
enable_nonboot_cpus();
- device_power_up(PMSG_RESTORE);
+ dpm_resume_noirq(PMSG_RESTORE);
Resume_devices:
- device_resume(PMSG_RESTORE);
+ dpm_resume_end(PMSG_RESTORE);
Resume_console:
resume_console();
thaw_processes();
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index bc41ad0f24f..26539e3228e 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -72,9 +72,9 @@ struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
/*
* round up to the next power of 2, since our 'let the indices
- * wrap' tachnique works only in this case.
+ * wrap' technique works only in this case.
*/
- if (size & (size - 1)) {
+ if (!is_power_of_2(size)) {
BUG_ON(size > 0x80000000);
size = roundup_pow_of_two(size);
}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 7e95bedb2bf..385c31a1bdb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -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>
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c0fa54b276d..16b5739c516 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -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) {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 41c88fe4050..9b1a7de2697 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -9,6 +9,7 @@
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
+#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/module.h>
@@ -26,7 +27,6 @@ struct kthread_create_info
/* Information passed to kthread() from kthreadd. */
int (*threadfn)(void *data);
void *data;
- struct completion started;
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
@@ -35,17 +35,13 @@ struct kthread_create_info
struct list_head list;
};
-struct kthread_stop_info
-{
- struct task_struct *k;
- int err;
- struct completion done;
+struct kthread {
+ int should_stop;
+ struct completion exited;
};
-/* Thread stopping is done by setthing this var: lock serializes
- * multiple kthread_stop calls. */
-static DEFINE_MUTEX(kthread_stop_lock);
-static struct kthread_stop_info kthread_stop_info;
+#define to_kthread(tsk) \
+ container_of((tsk)->vfork_done, struct kthread, exited)
/**
* kthread_should_stop - should this kthread return now?
@@ -56,36 +52,35 @@ static struct kthread_stop_info kthread_stop_info;
*/
int kthread_should_stop(void)
{
- return (kthread_stop_info.k == current);
+ return to_kthread(current)->should_stop;
}
EXPORT_SYMBOL(kthread_should_stop);
static int kthread(void *_create)
{
+ /* Copy data: it's on kthread's stack */
struct kthread_create_info *create = _create;
- int (*threadfn)(void *data);
- void *data;
- int ret = -EINTR;
+ int (*threadfn)(void *data) = create->threadfn;
+ void *data = create->data;
+ struct kthread self;
+ int ret;
- /* Copy data: it's on kthread's stack */
- threadfn = create->threadfn;
- data = create->data;
+ self.should_stop = 0;
+ init_completion(&self.exited);
+ current->vfork_done = &self.exited;
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
- complete(&create->started);
+ complete(&create->done);
schedule();
- if (!kthread_should_stop())
+ ret = -EINTR;
+ if (!self.should_stop)
ret = threadfn(data);
- /* It might have exited on its own, w/o kthread_stop. Check. */
- if (kthread_should_stop()) {
- kthread_stop_info.err = ret;
- complete(&kthread_stop_info.done);
- }
- return 0;
+ /* we can't just return, we must preserve "self" on stack */
+ do_exit(ret);
}
static void create_kthread(struct kthread_create_info *create)
@@ -94,11 +89,10 @@ static void create_kthread(struct kthread_create_info *create)
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
- if (pid < 0)
+ if (pid < 0) {
create->result = ERR_PTR(pid);
- else
- wait_for_completion(&create->started);
- complete(&create->done);
+ complete(&create->done);
+ }
}
/**
@@ -129,7 +123,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
create.threadfn = threadfn;
create.data = data;
- init_completion(&create.started);
init_completion(&create.done);
spin_lock(&kthread_create_lock);
@@ -197,30 +190,22 @@ EXPORT_SYMBOL(kthread_bind);
*/
int kthread_stop(struct task_struct *k)
{
+ struct kthread *kthread;
int ret;
- mutex_lock(&kthread_stop_lock);
-
- /* It could exit after stop_info.k set, but before wake_up_process. */
- get_task_struct(k);
-
trace_sched_kthread_stop(k);
+ get_task_struct(k);
- /* Must init completion *before* thread sees kthread_stop_info.k */
- init_completion(&kthread_stop_info.done);
- smp_wmb();
+ kthread = to_kthread(k);
+ barrier(); /* it might have exited */
+ if (k->vfork_done != NULL) {
+ kthread->should_stop = 1;
+ wake_up_process(k);
+ wait_for_completion(&kthread->exited);
+ }
+ ret = k->exit_code;
- /* Now set kthread_should_stop() to true, and wake it up. */
- kthread_stop_info.k = k;
- wake_up_process(k);
put_task_struct(k);
-
- /* Once it dies, reset stop ptr, gather result and we're done. */
- wait_for_completion(&kthread_stop_info.done);
- kthread_stop_info.k = NULL;
- ret = kthread_stop_info.err;
- mutex_unlock(&kthread_stop_lock);
-
trace_sched_kthread_stop_ret(ret);
return ret;
@@ -236,6 +221,7 @@ int kthreadd(void *unused)
ignore_signals(tsk);
set_user_nice(tsk, KTHREAD_NICE_LEVEL);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
+ set_mems_allowed(node_possible_map);
current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
diff --git a/kernel/module.c b/kernel/module.c
index 2383e60fcf3..0a049837008 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -53,6 +53,7 @@
#include <linux/ftrace.h>
#include <linux/async.h>
#include <linux/percpu.h>
+#include <linux/kmemleak.h>
#if 0
#define DEBUGP printk
@@ -73,6 +74,9 @@ DEFINE_MUTEX(module_mutex);
EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
+/* Block module loading/unloading? */
+int modules_disabled = 0;
+
/* Waiting for a module to finish initializing? */
static DECLARE_WAIT_QUEUE_HEAD(module_wq);
@@ -430,6 +434,7 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
unsigned long extra;
unsigned int i;
void *ptr;
+ int cpu;
if (align > PAGE_SIZE) {
printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
@@ -459,6 +464,11 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
if (!split_block(i, size))
return NULL;
+ /* add the per-cpu scanning areas */
+ for_each_possible_cpu(cpu)
+ kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
+ GFP_KERNEL);
+
/* Mark allocated */
pcpu_size[i] = -pcpu_size[i];
return ptr;
@@ -473,6 +483,7 @@ static void percpu_modfree(void *freeme)
{
unsigned int i;
void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
+ int cpu;
/* First entry is core kernel percpu data. */
for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
@@ -484,6 +495,10 @@ static void percpu_modfree(void *freeme)
BUG();
free:
+ /* remove the per-cpu scanning areas */
+ for_each_possible_cpu(cpu)
+ kmemleak_free(freeme + per_cpu_offset(cpu));
+
/* Merge with previous? */
if (pcpu_size[i-1] >= 0) {
pcpu_size[i-1] += pcpu_size[i];
@@ -778,7 +793,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
char name[MODULE_NAME_LEN];
int ret, forced = 0;
- if (!capable(CAP_SYS_MODULE))
+ if (!capable(CAP_SYS_MODULE) || modules_disabled)
return -EPERM;
if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0)
@@ -1876,6 +1891,36 @@ static void *module_alloc_update_bounds(unsigned long size)
return ret;
}
+#ifdef CONFIG_DEBUG_KMEMLEAK
+static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
+ Elf_Shdr *sechdrs, char *secstrings)
+{
+ unsigned int i;
+
+ /* only scan the sections containing data */
+ kmemleak_scan_area(mod->module_core, (unsigned long)mod -
+ (unsigned long)mod->module_core,
+ sizeof(struct module), GFP_KERNEL);
+
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (!(sechdrs[i].sh_flags & SHF_ALLOC))
+ continue;
+ if (strncmp(secstrings + sechdrs[i].sh_name, ".data", 5) != 0
+ && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0)
+ continue;
+
+ kmemleak_scan_area(mod->module_core, sechdrs[i].sh_addr -
+ (unsigned long)mod->module_core,
+ sechdrs[i].sh_size, GFP_KERNEL);
+ }
+}
+#else
+static inline void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
+ Elf_Shdr *sechdrs, char *secstrings)
+{
+}
+#endif
+
/* Allocate and load the module: note that size of section 0 is always
zero, and we rely on this for optional sections. */
static noinline struct module *load_module(void __user *umod,
@@ -2046,6 +2091,12 @@ static noinline struct module *load_module(void __user *umod,
/* Do the allocs. */
ptr = module_alloc_update_bounds(mod->core_size);
+ /*
+ * The pointer to this block is stored in the module structure
+ * which is inside the block. Just mark it as not being a
+ * leak.
+ */
+ kmemleak_not_leak(ptr);
if (!ptr) {
err = -ENOMEM;
goto free_percpu;
@@ -2054,6 +2105,13 @@ static noinline struct module *load_module(void __user *umod,
mod->module_core = ptr;
ptr = module_alloc_update_bounds(mod->init_size);
+ /*
+ * The pointer to this block is stored in the module structure
+ * which is inside the block. This block doesn't need to be
+ * scanned as it contains data and code that will be freed
+ * after the module is initialized.
+ */
+ kmemleak_ignore(ptr);
if (!ptr && mod->init_size) {
err = -ENOMEM;
goto free_core;
@@ -2084,6 +2142,7 @@ static noinline struct module *load_module(void __user *umod,
}
/* Module has been moved. */
mod = (void *)sechdrs[modindex].sh_addr;
+ kmemleak_load_module(mod, hdr, sechdrs, secstrings);
#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
@@ -2157,6 +2216,10 @@ static noinline struct module *load_module(void __user *umod,
mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings,
"__kcrctab_unused_gpl");
#endif
+#ifdef CONFIG_CONSTRUCTORS
+ mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors",
+ sizeof(*mod->ctors), &mod->num_ctors);
+#endif
#ifdef CONFIG_MARKERS
mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers",
@@ -2330,6 +2393,17 @@ static noinline struct module *load_module(void __user *umod,
goto free_hdr;
}
+/* Call module constructors. */
+static void do_mod_ctors(struct module *mod)
+{
+#ifdef CONFIG_CONSTRUCTORS
+ unsigned long i;
+
+ for (i = 0; i < mod->num_ctors; i++)
+ mod->ctors[i]();
+#endif
+}
+
/* This is where the real work happens */
SYSCALL_DEFINE3(init_module, void __user *, umod,
unsigned long, len, const char __user *, uargs)
@@ -2338,7 +2412,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
int ret = 0;
/* Must have permission */
- if (!capable(CAP_SYS_MODULE))
+ if (!capable(CAP_SYS_MODULE) || modules_disabled)
return -EPERM;
/* Only one module load at a time, please */
@@ -2358,6 +2432,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_COMING, mod);
+ do_mod_ctors(mod);
/* Start the module */
if (mod->init != NULL)
ret = do_one_initcall(mod->init);
@@ -2376,9 +2451,9 @@ 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();
@@ -2396,6 +2471,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
mutex_lock(&module_mutex);
/* Drop initial reference. */
module_put(mod);
+ trim_init_extable(mod);
module_free(mod, mod->module_init);
mod->module_init = NULL;
mod->init_size = 0;
@@ -2839,7 +2915,7 @@ void print_modules(void)
struct module *mod;
char buf[8];
- printk("Modules linked in:");
+ printk(KERN_DEFAULT "Modules linked in:");
/* Most callers should already have preempt disabled, but make sure */
preempt_disable();
list_for_each_entry_rcu(mod, &modules, list)
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 63598dca2d0..09b4ff9711b 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -26,19 +26,14 @@ static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
-/*
- * creates a copy of "orig" with refcount 1.
- */
-static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig)
+static inline struct nsproxy *create_nsproxy(void)
{
- struct nsproxy *ns;
+ struct nsproxy *nsproxy;
- ns = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
- if (ns) {
- memcpy(ns, orig, sizeof(struct nsproxy));
- atomic_set(&ns->count, 1);
- }
- return ns;
+ nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
+ if (nsproxy)
+ atomic_set(&nsproxy->count, 1);
+ return nsproxy;
}
/*
@@ -52,7 +47,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
struct nsproxy *new_nsp;
int err;
- new_nsp = clone_nsproxy(tsk->nsproxy);
+ new_nsp = create_nsproxy();
if (!new_nsp)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/params.c b/kernel/params.c
index de273ec85bd..7f6912ced2b 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,9 +24,6 @@
#include <linux/err.h>
#include <linux/slab.h>
-/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */
-#define KPARAM_KMALLOCED 0x80000000
-
#if 0
#define DEBUGP printk
#else
@@ -220,13 +217,13 @@ int param_set_charp(const char *val, struct kernel_param *kp)
return -ENOSPC;
}
- if (kp->perm & KPARAM_KMALLOCED)
+ if (kp->flags & KPARAM_KMALLOCED)
kfree(*(char **)kp->arg);
/* This is a hack. We can't need to strdup in early boot, and we
* don't need to; this mangled commandline is preserved. */
if (slab_is_available()) {
- kp->perm |= KPARAM_KMALLOCED;
+ kp->flags |= KPARAM_KMALLOCED;
*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
if (!kp->arg)
return -ENOMEM;
@@ -241,44 +238,63 @@ int param_get_charp(char *buffer, struct kernel_param *kp)
return sprintf(buffer, "%s", *((char **)kp->arg));
}
+/* Actually could be a bool or an int, for historical reasons. */
int param_set_bool(const char *val, struct kernel_param *kp)
{
+ bool v;
+
/* No equals means "set"... */
if (!val) val = "1";
/* One of =[yYnN01] */
switch (val[0]) {
case 'y': case 'Y': case '1':
- *(int *)kp->arg = 1;
- return 0;
+ v = true;
+ break;
case 'n': case 'N': case '0':
- *(int *)kp->arg = 0;
- return 0;
+ v = false;
+ break;
+ default:
+ return -EINVAL;
}
- return -EINVAL;
+
+ if (kp->flags & KPARAM_ISBOOL)
+ *(bool *)kp->arg = v;
+ else
+ *(int *)kp->arg = v;
+ return 0;
}
int param_get_bool(char *buffer, struct kernel_param *kp)
{
+ bool val;
+ if (kp->flags & KPARAM_ISBOOL)
+ val = *(bool *)kp->arg;
+ else
+ val = *(int *)kp->arg;
+
/* Y and N chosen as being relatively non-coder friendly */
- return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'Y' : 'N');
+ return sprintf(buffer, "%c", val ? 'Y' : 'N');
}
+/* This one must be bool. */
int param_set_invbool(const char *val, struct kernel_param *kp)
{
- int boolval, ret;
+ int ret;
+ bool boolval;
struct kernel_param dummy;
dummy.arg = &boolval;
+ dummy.flags = KPARAM_ISBOOL;
ret = param_set_bool(val, &dummy);
if (ret == 0)
- *(int *)kp->arg = !boolval;
+ *(bool *)kp->arg = !boolval;
return ret;
}
int param_get_invbool(char *buffer, struct kernel_param *kp)
{
- return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'N' : 'Y');
+ return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y');
}
/* We break the rule and mangle the string. */
@@ -591,7 +607,7 @@ void destroy_params(const struct kernel_param *params, unsigned num)
unsigned int i;
for (i = 0; i < num; i++)
- if (params[i].perm & KPARAM_KMALLOCED)
+ if (params[i].flags & KPARAM_KMALLOCED)
kfree(*(char **)params[i].arg);
}
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index ef5d8a5b245..a641eb753b8 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -124,7 +124,7 @@ void perf_enable(void)
static void get_ctx(struct perf_counter_context *ctx)
{
- atomic_inc(&ctx->refcount);
+ WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
}
static void free_ctx(struct rcu_head *head)
@@ -175,6 +175,11 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
spin_unlock_irqrestore(&ctx->lock, *flags);
goto retry;
}
+
+ if (!atomic_inc_not_zero(&ctx->refcount)) {
+ spin_unlock_irqrestore(&ctx->lock, *flags);
+ ctx = NULL;
+ }
}
rcu_read_unlock();
return ctx;
@@ -193,7 +198,6 @@ static struct perf_counter_context *perf_pin_task_context(struct task_struct *ta
ctx = perf_lock_task_context(task, &flags);
if (ctx) {
++ctx->pin_count;
- get_ctx(ctx);
spin_unlock_irqrestore(&ctx->lock, flags);
}
return ctx;
@@ -232,6 +236,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
list_add_rcu(&counter->event_entry, &ctx->event_list);
ctx->nr_counters++;
+ if (counter->attr.inherit_stat)
+ ctx->nr_stat++;
}
/*
@@ -246,6 +252,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
if (list_empty(&counter->list_entry))
return;
ctx->nr_counters--;
+ if (counter->attr.inherit_stat)
+ ctx->nr_stat--;
list_del_init(&counter->list_entry);
list_del_rcu(&counter->event_entry);
@@ -1002,6 +1010,81 @@ static int context_equiv(struct perf_counter_context *ctx1,
&& !ctx1->pin_count && !ctx2->pin_count;
}
+static void __perf_counter_read(void *counter);
+
+static void __perf_counter_sync_stat(struct perf_counter *counter,
+ struct perf_counter *next_counter)
+{
+ u64 value;
+
+ if (!counter->attr.inherit_stat)
+ return;
+
+ /*
+ * Update the counter value, we cannot use perf_counter_read()
+ * because we're in the middle of a context switch and have IRQs
+ * disabled, which upsets smp_call_function_single(), however
+ * we know the counter must be on the current CPU, therefore we
+ * don't need to use it.
+ */
+ switch (counter->state) {
+ case PERF_COUNTER_STATE_ACTIVE:
+ __perf_counter_read(counter);
+ break;
+
+ case PERF_COUNTER_STATE_INACTIVE:
+ update_counter_times(counter);
+ break;
+
+ default:
+ break;
+ }
+
+ /*
+ * In order to keep per-task stats reliable we need to flip the counter
+ * values when we flip the contexts.
+ */
+ value = atomic64_read(&next_counter->count);
+ value = atomic64_xchg(&counter->count, value);
+ atomic64_set(&next_counter->count, value);
+
+ swap(counter->total_time_enabled, next_counter->total_time_enabled);
+ swap(counter->total_time_running, next_counter->total_time_running);
+
+ /*
+ * Since we swizzled the values, update the user visible data too.
+ */
+ perf_counter_update_userpage(counter);
+ perf_counter_update_userpage(next_counter);
+}
+
+#define list_next_entry(pos, member) \
+ list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+ struct perf_counter_context *next_ctx)
+{
+ struct perf_counter *counter, *next_counter;
+
+ if (!ctx->nr_stat)
+ return;
+
+ counter = list_first_entry(&ctx->event_list,
+ struct perf_counter, event_entry);
+
+ next_counter = list_first_entry(&next_ctx->event_list,
+ struct perf_counter, event_entry);
+
+ while (&counter->event_entry != &ctx->event_list &&
+ &next_counter->event_entry != &next_ctx->event_list) {
+
+ __perf_counter_sync_stat(counter, next_counter);
+
+ counter = list_next_entry(counter, event_entry);
+ next_counter = list_next_entry(counter, event_entry);
+ }
+}
+
/*
* Called from scheduler to remove the counters of the current task,
* with interrupts disabled.
@@ -1057,6 +1140,8 @@ void perf_counter_task_sched_out(struct task_struct *task,
ctx->task = next;
next_ctx->task = task;
do_switch = 0;
+
+ perf_counter_sync_stat(ctx, next_ctx);
}
spin_unlock(&next_ctx->lock);
spin_unlock(&ctx->lock);
@@ -1283,7 +1368,7 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
if (!interrupts) {
perf_disable();
counter->pmu->disable(counter);
- atomic_set(&hwc->period_left, 0);
+ atomic64_set(&hwc->period_left, 0);
counter->pmu->enable(counter);
perf_enable();
}
@@ -1344,9 +1429,56 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
}
/*
+ * Enable all of a task's counters that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_counter_enable_on_exec(struct task_struct *task)
+{
+ struct perf_counter_context *ctx;
+ struct perf_counter *counter;
+ unsigned long flags;
+ int enabled = 0;
+
+ local_irq_save(flags);
+ ctx = task->perf_counter_ctxp;
+ if (!ctx || !ctx->nr_counters)
+ goto out;
+
+ __perf_counter_task_sched_out(ctx);
+
+ spin_lock(&ctx->lock);
+
+ list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+ if (!counter->attr.enable_on_exec)
+ continue;
+ counter->attr.enable_on_exec = 0;
+ if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+ continue;
+ counter->state = PERF_COUNTER_STATE_INACTIVE;
+ counter->tstamp_enabled =
+ ctx->time - counter->total_time_enabled;
+ enabled = 1;
+ }
+
+ /*
+ * Unclone this context if we enabled any counter.
+ */
+ if (enabled && ctx->parent_ctx) {
+ put_ctx(ctx->parent_ctx);
+ ctx->parent_ctx = NULL;
+ }
+
+ spin_unlock(&ctx->lock);
+
+ perf_counter_task_sched_in(task, smp_processor_id());
+ out:
+ local_irq_restore(flags);
+}
+
+/*
* Cross CPU call to read the hardware counter
*/
-static void __read(void *info)
+static void __perf_counter_read(void *info)
{
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
@@ -1368,7 +1500,7 @@ static u64 perf_counter_read(struct perf_counter *counter)
*/
if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
smp_call_function_single(counter->oncpu,
- __read, counter, 1);
+ __perf_counter_read, counter, 1);
} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
update_counter_times(counter);
}
@@ -1459,11 +1591,6 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
put_ctx(parent_ctx);
ctx->parent_ctx = NULL; /* no longer a clone */
}
- /*
- * Get an extra reference before dropping the lock so that
- * this context won't get freed if the task exits.
- */
- get_ctx(ctx);
spin_unlock_irqrestore(&ctx->lock, flags);
}
@@ -1509,11 +1636,13 @@ static void free_counter(struct perf_counter *counter)
{
perf_pending_sync(counter);
- atomic_dec(&nr_counters);
- if (counter->attr.mmap)
- atomic_dec(&nr_mmap_counters);
- if (counter->attr.comm)
- atomic_dec(&nr_comm_counters);
+ if (!counter->parent) {
+ atomic_dec(&nr_counters);
+ if (counter->attr.mmap)
+ atomic_dec(&nr_mmap_counters);
+ if (counter->attr.comm)
+ atomic_dec(&nr_comm_counters);
+ }
if (counter->destroy)
counter->destroy(counter);
@@ -1553,7 +1682,7 @@ static int perf_release(struct inode *inode, struct file *file)
static ssize_t
perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
{
- u64 values[3];
+ u64 values[4];
int n;
/*
@@ -1620,22 +1749,6 @@ static void perf_counter_reset(struct perf_counter *counter)
perf_counter_update_userpage(counter);
}
-static void perf_counter_for_each_sibling(struct perf_counter *counter,
- void (*func)(struct perf_counter *))
-{
- struct perf_counter_context *ctx = counter->ctx;
- struct perf_counter *sibling;
-
- WARN_ON_ONCE(ctx->parent_ctx);
- mutex_lock(&ctx->mutex);
- counter = counter->group_leader;
-
- func(counter);
- list_for_each_entry(sibling, &counter->sibling_list, list_entry)
- func(sibling);
- mutex_unlock(&ctx->mutex);
-}
-
/*
* Holding the top-level counter's child_mutex means that any
* descendant process that has inherited this counter will block
@@ -1658,14 +1771,18 @@ static void perf_counter_for_each_child(struct perf_counter *counter,
static void perf_counter_for_each(struct perf_counter *counter,
void (*func)(struct perf_counter *))
{
- struct perf_counter *child;
+ struct perf_counter_context *ctx = counter->ctx;
+ struct perf_counter *sibling;
- WARN_ON_ONCE(counter->ctx->parent_ctx);
- mutex_lock(&counter->child_mutex);
- perf_counter_for_each_sibling(counter, func);
- list_for_each_entry(child, &counter->child_list, child_list)
- perf_counter_for_each_sibling(child, func);
- mutex_unlock(&counter->child_mutex);
+ WARN_ON_ONCE(ctx->parent_ctx);
+ mutex_lock(&ctx->mutex);
+ counter = counter->group_leader;
+
+ perf_counter_for_each_child(counter, func);
+ func(counter);
+ list_for_each_entry(sibling, &counter->sibling_list, list_entry)
+ perf_counter_for_each_child(counter, func);
+ mutex_unlock(&ctx->mutex);
}
static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
@@ -1764,6 +1881,14 @@ int perf_counter_task_disable(void)
return 0;
}
+static int perf_counter_index(struct perf_counter *counter)
+{
+ if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+ return 0;
+
+ return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
+}
+
/*
* Callers need to ensure there can be no nesting of this function, otherwise
* the seqlock logic goes bad. We can not serialize this because the arch
@@ -1788,11 +1913,17 @@ void perf_counter_update_userpage(struct perf_counter *counter)
preempt_disable();
++userpg->lock;
barrier();
- userpg->index = counter->hw.idx;
+ userpg->index = perf_counter_index(counter);
userpg->offset = atomic64_read(&counter->count);
if (counter->state == PERF_COUNTER_STATE_ACTIVE)
userpg->offset -= atomic64_read(&counter->hw.prev_count);
+ userpg->time_enabled = counter->total_time_enabled +
+ atomic64_read(&counter->child_total_time_enabled);
+
+ userpg->time_running = counter->total_time_running +
+ atomic64_read(&counter->child_total_time_running);
+
barrier();
++userpg->lock;
preempt_enable();
@@ -1806,6 +1937,12 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
struct perf_mmap_data *data;
int ret = VM_FAULT_SIGBUS;
+ if (vmf->flags & FAULT_FLAG_MKWRITE) {
+ if (vmf->pgoff == 0)
+ ret = 0;
+ return ret;
+ }
+
rcu_read_lock();
data = rcu_dereference(counter->data);
if (!data)
@@ -1819,9 +1956,16 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if ((unsigned)nr > data->nr_pages)
goto unlock;
+ if (vmf->flags & FAULT_FLAG_WRITE)
+ goto unlock;
+
vmf->page = virt_to_page(data->data_pages[nr]);
}
+
get_page(vmf->page);
+ vmf->page->mapping = vma->vm_file->f_mapping;
+ vmf->page->index = vmf->pgoff;
+
ret = 0;
unlock:
rcu_read_unlock();
@@ -1874,6 +2018,14 @@ fail:
return -ENOMEM;
}
+static void perf_mmap_free_page(unsigned long addr)
+{
+ struct page *page = virt_to_page((void *)addr);
+
+ page->mapping = NULL;
+ __free_page(page);
+}
+
static void __perf_mmap_data_free(struct rcu_head *rcu_head)
{
struct perf_mmap_data *data;
@@ -1881,9 +2033,10 @@ static void __perf_mmap_data_free(struct rcu_head *rcu_head)
data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
- free_page((unsigned long)data->user_page);
+ perf_mmap_free_page((unsigned long)data->user_page);
for (i = 0; i < data->nr_pages; i++)
- free_page((unsigned long)data->data_pages[i]);
+ perf_mmap_free_page((unsigned long)data->data_pages[i]);
+
kfree(data);
}
@@ -1920,9 +2073,10 @@ static void perf_mmap_close(struct vm_area_struct *vma)
}
static struct vm_operations_struct perf_mmap_vmops = {
- .open = perf_mmap_open,
- .close = perf_mmap_close,
- .fault = perf_mmap_fault,
+ .open = perf_mmap_open,
+ .close = perf_mmap_close,
+ .fault = perf_mmap_fault,
+ .page_mkwrite = perf_mmap_fault,
};
static int perf_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1936,7 +2090,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
long user_extra, extra;
int ret = 0;
- if (!(vma->vm_flags & VM_SHARED) || (vma->vm_flags & VM_WRITE))
+ if (!(vma->vm_flags & VM_SHARED))
return -EINVAL;
vma_size = vma->vm_end - vma->vm_start;
@@ -1995,10 +2149,12 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
atomic_long_add(user_extra, &user->locked_vm);
vma->vm_mm->locked_vm += extra;
counter->data->nr_locked = extra;
+ if (vma->vm_flags & VM_WRITE)
+ counter->data->writable = 1;
+
unlock:
mutex_unlock(&counter->mmap_mutex);
- vma->vm_flags &= ~VM_MAYWRITE;
vma->vm_flags |= VM_RESERVED;
vma->vm_ops = &perf_mmap_vmops;
@@ -2175,11 +2331,38 @@ struct perf_output_handle {
unsigned long head;
unsigned long offset;
int nmi;
- int overflow;
+ int sample;
int locked;
unsigned long flags;
};
+static bool perf_output_space(struct perf_mmap_data *data,
+ unsigned int offset, unsigned int head)
+{
+ unsigned long tail;
+ unsigned long mask;
+
+ if (!data->writable)
+ return true;
+
+ mask = (data->nr_pages << PAGE_SHIFT) - 1;
+ /*
+ * Userspace could choose to issue a mb() before updating the tail
+ * pointer. So that all reads will be completed before the write is
+ * issued.
+ */
+ tail = ACCESS_ONCE(data->user_page->data_tail);
+ smp_rmb();
+
+ offset = (offset - tail) & mask;
+ head = (head - tail) & mask;
+
+ if ((int)(head - offset) < 0)
+ return false;
+
+ return true;
+}
+
static void perf_output_wakeup(struct perf_output_handle *handle)
{
atomic_set(&handle->data->poll, POLL_IN);
@@ -2270,12 +2453,57 @@ out:
local_irq_restore(handle->flags);
}
+static void perf_output_copy(struct perf_output_handle *handle,
+ const void *buf, unsigned int len)
+{
+ unsigned int pages_mask;
+ unsigned int offset;
+ unsigned int size;
+ void **pages;
+
+ offset = handle->offset;
+ pages_mask = handle->data->nr_pages - 1;
+ pages = handle->data->data_pages;
+
+ do {
+ unsigned int page_offset;
+ int nr;
+
+ nr = (offset >> PAGE_SHIFT) & pages_mask;
+ page_offset = offset & (PAGE_SIZE - 1);
+ size = min_t(unsigned int, PAGE_SIZE - page_offset, len);
+
+ memcpy(pages[nr] + page_offset, buf, size);
+
+ len -= size;
+ buf += size;
+ offset += size;
+ } while (len);
+
+ handle->offset = offset;
+
+ /*
+ * Check we didn't copy past our reservation window, taking the
+ * possible unsigned int wrap into account.
+ */
+ WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
+}
+
+#define perf_output_put(handle, x) \
+ perf_output_copy((handle), &(x), sizeof(x))
+
static int perf_output_begin(struct perf_output_handle *handle,
struct perf_counter *counter, unsigned int size,
- int nmi, int overflow)
+ int nmi, int sample)
{
struct perf_mmap_data *data;
unsigned int offset, head;
+ int have_lost;
+ struct {
+ struct perf_event_header header;
+ u64 id;
+ u64 lost;
+ } lost_event;
/*
* For inherited counters we send all the output towards the parent.
@@ -2288,19 +2516,25 @@ static int perf_output_begin(struct perf_output_handle *handle,
if (!data)
goto out;
- handle->data = data;
- handle->counter = counter;
- handle->nmi = nmi;
- handle->overflow = overflow;
+ handle->data = data;
+ handle->counter = counter;
+ handle->nmi = nmi;
+ handle->sample = sample;
if (!data->nr_pages)
goto fail;
+ have_lost = atomic_read(&data->lost);
+ if (have_lost)
+ size += sizeof(lost_event);
+
perf_output_lock(handle);
do {
offset = head = atomic_long_read(&data->head);
head += size;
+ if (unlikely(!perf_output_space(data, offset, head)))
+ goto fail;
} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);
handle->offset = offset;
@@ -2309,55 +2543,27 @@ static int perf_output_begin(struct perf_output_handle *handle,
if ((offset >> PAGE_SHIFT) != (head >> PAGE_SHIFT))
atomic_set(&data->wakeup, 1);
+ if (have_lost) {
+ lost_event.header.type = PERF_EVENT_LOST;
+ lost_event.header.misc = 0;
+ lost_event.header.size = sizeof(lost_event);
+ lost_event.id = counter->id;
+ lost_event.lost = atomic_xchg(&data->lost, 0);
+
+ perf_output_put(handle, lost_event);
+ }
+
return 0;
fail:
- perf_output_wakeup(handle);
+ atomic_inc(&data->lost);
+ perf_output_unlock(handle);
out:
rcu_read_unlock();
return -ENOSPC;
}
-static void perf_output_copy(struct perf_output_handle *handle,
- const void *buf, unsigned int len)
-{
- unsigned int pages_mask;
- unsigned int offset;
- unsigned int size;
- void **pages;
-
- offset = handle->offset;
- pages_mask = handle->data->nr_pages - 1;
- pages = handle->data->data_pages;
-
- do {
- unsigned int page_offset;
- int nr;
-
- nr = (offset >> PAGE_SHIFT) & pages_mask;
- page_offset = offset & (PAGE_SIZE - 1);
- size = min_t(unsigned int, PAGE_SIZE - page_offset, len);
-
- memcpy(pages[nr] + page_offset, buf, size);
-
- len -= size;
- buf += size;
- offset += size;
- } while (len);
-
- handle->offset = offset;
-
- /*
- * Check we didn't copy past our reservation window, taking the
- * possible unsigned int wrap into account.
- */
- WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
-}
-
-#define perf_output_put(handle, x) \
- perf_output_copy((handle), &(x), sizeof(x))
-
static void perf_output_end(struct perf_output_handle *handle)
{
struct perf_counter *counter = handle->counter;
@@ -2365,7 +2571,7 @@ static void perf_output_end(struct perf_output_handle *handle)
int wakeup_events = counter->attr.wakeup_events;
- if (handle->overflow && wakeup_events) {
+ if (handle->sample && wakeup_events) {
int events = atomic_inc_return(&data->events);
if (events >= wakeup_events) {
atomic_sub(wakeup_events, &data->events);
@@ -2421,15 +2627,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
u32 cpu, reserved;
} cpu_entry;
- header.type = 0;
+ header.type = PERF_EVENT_SAMPLE;
header.size = sizeof(header);
- header.misc = PERF_EVENT_MISC_OVERFLOW;
+ header.misc = 0;
header.misc |= perf_misc_flags(data->regs);
if (sample_type & PERF_SAMPLE_IP) {
ip = perf_instruction_pointer(data->regs);
- header.type |= PERF_SAMPLE_IP;
header.size += sizeof(ip);
}
@@ -2438,7 +2643,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
tid_entry.pid = perf_counter_pid(counter, current);
tid_entry.tid = perf_counter_tid(counter, current);
- header.type |= PERF_SAMPLE_TID;
header.size += sizeof(tid_entry);
}
@@ -2448,34 +2652,25 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
*/
time = sched_clock();
- header.type |= PERF_SAMPLE_TIME;
header.size += sizeof(u64);
}
- if (sample_type & PERF_SAMPLE_ADDR) {
- header.type |= PERF_SAMPLE_ADDR;
+ if (sample_type & PERF_SAMPLE_ADDR)
header.size += sizeof(u64);
- }
- if (sample_type & PERF_SAMPLE_ID) {
- header.type |= PERF_SAMPLE_ID;
+ if (sample_type & PERF_SAMPLE_ID)
header.size += sizeof(u64);
- }
if (sample_type & PERF_SAMPLE_CPU) {
- header.type |= PERF_SAMPLE_CPU;
header.size += sizeof(cpu_entry);
cpu_entry.cpu = raw_smp_processor_id();
}
- if (sample_type & PERF_SAMPLE_PERIOD) {
- header.type |= PERF_SAMPLE_PERIOD;
+ if (sample_type & PERF_SAMPLE_PERIOD)
header.size += sizeof(u64);
- }
if (sample_type & PERF_SAMPLE_GROUP) {
- header.type |= PERF_SAMPLE_GROUP;
header.size += sizeof(u64) +
counter->nr_siblings * sizeof(group_entry);
}
@@ -2485,10 +2680,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
if (callchain) {
callchain_size = (1 + callchain->nr) * sizeof(u64);
-
- header.type |= PERF_SAMPLE_CALLCHAIN;
header.size += callchain_size;
- }
+ } else
+ header.size += sizeof(u64);
}
ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2539,9 +2733,75 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
}
}
- if (callchain)
- perf_output_copy(&handle, callchain, callchain_size);
+ if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+ if (callchain)
+ perf_output_copy(&handle, callchain, callchain_size);
+ else {
+ u64 nr = 0;
+ perf_output_put(&handle, nr);
+ }
+ }
+
+ perf_output_end(&handle);
+}
+
+/*
+ * read event
+ */
+
+struct perf_read_event {
+ struct perf_event_header header;
+
+ u32 pid;
+ u32 tid;
+ u64 value;
+ u64 format[3];
+};
+
+static void
+perf_counter_read_event(struct perf_counter *counter,
+ struct task_struct *task)
+{
+ struct perf_output_handle handle;
+ struct perf_read_event event = {
+ .header = {
+ .type = PERF_EVENT_READ,
+ .misc = 0,
+ .size = sizeof(event) - sizeof(event.format),
+ },
+ .pid = perf_counter_pid(counter, task),
+ .tid = perf_counter_tid(counter, task),
+ .value = atomic64_read(&counter->count),
+ };
+ int ret, i = 0;
+
+ if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+ event.header.size += sizeof(u64);
+ event.format[i++] = counter->total_time_enabled;
+ }
+
+ if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+ event.header.size += sizeof(u64);
+ event.format[i++] = counter->total_time_running;
+ }
+
+ if (counter->attr.read_format & PERF_FORMAT_ID) {
+ u64 id;
+
+ event.header.size += sizeof(u64);
+ if (counter->parent)
+ id = counter->parent->id;
+ else
+ id = counter->id;
+
+ event.format[i++] = id;
+ }
+
+ ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+ if (ret)
+ return;
+ perf_output_copy(&handle, &event, event.header.size);
perf_output_end(&handle);
}
@@ -2736,6 +2996,9 @@ void perf_counter_comm(struct task_struct *task)
{
struct perf_comm_event comm_event;
+ if (task->perf_counter_ctxp)
+ perf_counter_enable_on_exec(task);
+
if (!atomic_read(&nr_comm_counters))
return;
@@ -2970,7 +3233,7 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
}
/*
- * Generic counter overflow handling.
+ * Generic counter overflow handling, sampling.
*/
int perf_counter_overflow(struct perf_counter *counter, int nmi,
@@ -3109,20 +3372,15 @@ static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
}
static void perf_swcounter_overflow(struct perf_counter *counter,
- int nmi, struct pt_regs *regs, u64 addr)
+ int nmi, struct perf_sample_data *data)
{
- struct perf_sample_data data = {
- .regs = regs,
- .addr = addr,
- .period = counter->hw.last_period,
- };
+ data->period = counter->hw.last_period;
perf_swcounter_update(counter);
perf_swcounter_set_period(counter);
- if (perf_counter_overflow(counter, nmi, &data))
+ if (perf_counter_overflow(counter, nmi, data))
/* soft-disable the counter */
;
-
}
static int perf_swcounter_is_counting(struct perf_counter *counter)
@@ -3187,18 +3445,18 @@ static int perf_swcounter_match(struct perf_counter *counter,
}
static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
- int nmi, struct pt_regs *regs, u64 addr)
+ int nmi, struct perf_sample_data *data)
{
int neg = atomic64_add_negative(nr, &counter->hw.count);
- if (counter->hw.sample_period && !neg && regs)
- perf_swcounter_overflow(counter, nmi, regs, addr);
+ if (counter->hw.sample_period && !neg && data->regs)
+ perf_swcounter_overflow(counter, nmi, data);
}
static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
- enum perf_type_id type, u32 event,
- u64 nr, int nmi, struct pt_regs *regs,
- u64 addr)
+ enum perf_type_id type,
+ u32 event, u64 nr, int nmi,
+ struct perf_sample_data *data)
{
struct perf_counter *counter;
@@ -3207,8 +3465,8 @@ static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
rcu_read_lock();
list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
- if (perf_swcounter_match(counter, type, event, regs))
- perf_swcounter_add(counter, nr, nmi, regs, addr);
+ if (perf_swcounter_match(counter, type, event, data->regs))
+ perf_swcounter_add(counter, nr, nmi, data);
}
rcu_read_unlock();
}
@@ -3227,9 +3485,9 @@ static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
return &cpuctx->recursion[0];
}
-static void __perf_swcounter_event(enum perf_type_id type, u32 event,
- u64 nr, int nmi, struct pt_regs *regs,
- u64 addr)
+static void do_perf_swcounter_event(enum perf_type_id type, u32 event,
+ u64 nr, int nmi,
+ struct perf_sample_data *data)
{
struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
int *recursion = perf_swcounter_recursion_context(cpuctx);
@@ -3242,7 +3500,7 @@ static void __perf_swcounter_event(enum perf_type_id type, u32 event,
barrier();
perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
- nr, nmi, regs, addr);
+ nr, nmi, data);
rcu_read_lock();
/*
* doesn't really matter which of the child contexts the
@@ -3250,7 +3508,7 @@ static void __perf_swcounter_event(enum perf_type_id type, u32 event,
*/
ctx = rcu_dereference(current->perf_counter_ctxp);
if (ctx)
- perf_swcounter_ctx_event(ctx, type, event, nr, nmi, regs, addr);
+ perf_swcounter_ctx_event(ctx, type, event, nr, nmi, data);
rcu_read_unlock();
barrier();
@@ -3260,10 +3518,15 @@ out:
put_cpu_var(perf_cpu_context);
}
-void
-perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+ struct pt_regs *regs, u64 addr)
{
- __perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs, addr);
+ struct perf_sample_data data = {
+ .regs = regs,
+ .addr = addr,
+ };
+
+ do_perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, &data);
}
static void perf_swcounter_read(struct perf_counter *counter)
@@ -3404,36 +3667,18 @@ static const struct pmu perf_ops_task_clock = {
.read = task_clock_perf_counter_read,
};
-/*
- * Software counter: cpu migrations
- */
-void perf_counter_task_migration(struct task_struct *task, int cpu)
-{
- struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
- struct perf_counter_context *ctx;
-
- perf_swcounter_ctx_event(&cpuctx->ctx, PERF_TYPE_SOFTWARE,
- PERF_COUNT_SW_CPU_MIGRATIONS,
- 1, 1, NULL, 0);
-
- ctx = perf_pin_task_context(task);
- if (ctx) {
- perf_swcounter_ctx_event(ctx, PERF_TYPE_SOFTWARE,
- PERF_COUNT_SW_CPU_MIGRATIONS,
- 1, 1, NULL, 0);
- perf_unpin_context(ctx);
- }
-}
-
#ifdef CONFIG_EVENT_PROFILE
void perf_tpcounter_event(int event_id)
{
- struct pt_regs *regs = get_irq_regs();
+ struct perf_sample_data data = {
+ .regs = get_irq_regs();
+ .addr = 0,
+ };
- if (!regs)
- regs = task_pt_regs(current);
+ if (!data.regs)
+ data.regs = task_pt_regs(current);
- __perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs, 0);
+ do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, &data);
}
EXPORT_SYMBOL_GPL(perf_tpcounter_event);
@@ -3465,9 +3710,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
}
#endif
+atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_counter_destroy(struct perf_counter *counter)
+{
+ u64 event = counter->attr.config;
+
+ WARN_ON(counter->parent);
+
+ atomic_dec(&perf_swcounter_enabled[event]);
+}
+
static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
{
const struct pmu *pmu = NULL;
+ u64 event = counter->attr.config;
/*
* Software counters (currently) can't in general distinguish
@@ -3476,7 +3733,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
* to be kernel events, and page faults are never hypervisor
* events.
*/
- switch (counter->attr.config) {
+ switch (event) {
case PERF_COUNT_SW_CPU_CLOCK:
pmu = &perf_ops_cpu_clock;
@@ -3497,6 +3754,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
case PERF_COUNT_SW_CONTEXT_SWITCHES:
case PERF_COUNT_SW_CPU_MIGRATIONS:
+ if (!counter->parent) {
+ atomic_inc(&perf_swcounter_enabled[event]);
+ counter->destroy = sw_perf_counter_destroy;
+ }
pmu = &perf_ops_generic;
break;
}
@@ -3512,6 +3773,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
int cpu,
struct perf_counter_context *ctx,
struct perf_counter *group_leader,
+ struct perf_counter *parent_counter,
gfp_t gfpflags)
{
const struct pmu *pmu;
@@ -3547,6 +3809,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
counter->ctx = ctx;
counter->oncpu = -1;
+ counter->parent = parent_counter;
+
counter->ns = get_pid_ns(current->nsproxy->pid_ns);
counter->id = atomic64_inc_return(&perf_counter_id);
@@ -3570,12 +3834,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
goto done;
- if (attr->type == PERF_TYPE_RAW) {
- pmu = hw_perf_counter_init(counter);
- goto done;
- }
-
switch (attr->type) {
+ case PERF_TYPE_RAW:
case PERF_TYPE_HARDWARE:
case PERF_TYPE_HW_CACHE:
pmu = hw_perf_counter_init(counter);
@@ -3588,6 +3848,9 @@ perf_counter_alloc(struct perf_counter_attr *attr,
case PERF_TYPE_TRACEPOINT:
pmu = tp_perf_counter_init(counter);
break;
+
+ default:
+ break;
}
done:
err = 0;
@@ -3605,15 +3868,96 @@ done:
counter->pmu = pmu;
- atomic_inc(&nr_counters);
- if (counter->attr.mmap)
- atomic_inc(&nr_mmap_counters);
- if (counter->attr.comm)
- atomic_inc(&nr_comm_counters);
+ if (!counter->parent) {
+ atomic_inc(&nr_counters);
+ if (counter->attr.mmap)
+ atomic_inc(&nr_mmap_counters);
+ if (counter->attr.comm)
+ atomic_inc(&nr_comm_counters);
+ }
return counter;
}
+static int perf_copy_attr(struct perf_counter_attr __user *uattr,
+ struct perf_counter_attr *attr)
+{
+ int ret;
+ u32 size;
+
+ if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
+ return -EFAULT;
+
+ /*
+ * zero the full structure, so that a short copy will be nice.
+ */
+ memset(attr, 0, sizeof(*attr));
+
+ ret = get_user(size, &uattr->size);
+ if (ret)
+ return ret;
+
+ if (size > PAGE_SIZE) /* silly large */
+ goto err_size;
+
+ if (!size) /* abi compat */
+ size = PERF_ATTR_SIZE_VER0;
+
+ if (size < PERF_ATTR_SIZE_VER0)
+ goto err_size;
+
+ /*
+ * If we're handed a bigger struct than we know of,
+ * ensure all the unknown bits are 0.
+ */
+ if (size > sizeof(*attr)) {
+ unsigned long val;
+ unsigned long __user *addr;
+ unsigned long __user *end;
+
+ addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
+ sizeof(unsigned long));
+ end = PTR_ALIGN((void __user *)uattr + size,
+ sizeof(unsigned long));
+
+ for (; addr < end; addr += sizeof(unsigned long)) {
+ ret = get_user(val, addr);
+ if (ret)
+ return ret;
+ if (val)
+ goto err_size;
+ }
+ }
+
+ ret = copy_from_user(attr, uattr, size);
+ if (ret)
+ return -EFAULT;
+
+ /*
+ * If the type exists, the corresponding creation will verify
+ * the attr->config.
+ */
+ if (attr->type >= PERF_TYPE_MAX)
+ return -EINVAL;
+
+ if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
+ return -EINVAL;
+
+ if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
+ return -EINVAL;
+
+ if (attr->read_format & ~(PERF_FORMAT_MAX-1))
+ return -EINVAL;
+
+out:
+ return ret;
+
+err_size:
+ put_user(sizeof(*attr), &uattr->size);
+ ret = -E2BIG;
+ goto out;
+}
+
/**
* sys_perf_counter_open - open a performance counter, associate it to a task/cpu
*
@@ -3623,7 +3967,7 @@ done:
* @group_fd: group leader counter fd
*/
SYSCALL_DEFINE5(perf_counter_open,
- const struct perf_counter_attr __user *, attr_uptr,
+ struct perf_counter_attr __user *, attr_uptr,
pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
{
struct perf_counter *counter, *group_leader;
@@ -3639,8 +3983,9 @@ SYSCALL_DEFINE5(perf_counter_open,
if (flags)
return -EINVAL;
- if (copy_from_user(&attr, attr_uptr, sizeof(attr)) != 0)
- return -EFAULT;
+ ret = perf_copy_attr(attr_uptr, &attr);
+ if (ret)
+ return ret;
if (!attr.exclude_kernel) {
if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
@@ -3692,7 +4037,7 @@ SYSCALL_DEFINE5(perf_counter_open,
}
counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
- GFP_KERNEL);
+ NULL, GFP_KERNEL);
ret = PTR_ERR(counter);
if (IS_ERR(counter))
goto err_put_context;
@@ -3758,7 +4103,8 @@ inherit_counter(struct perf_counter *parent_counter,
child_counter = perf_counter_alloc(&parent_counter->attr,
parent_counter->cpu, child_ctx,
- group_leader, GFP_KERNEL);
+ group_leader, parent_counter,
+ GFP_KERNEL);
if (IS_ERR(child_counter))
return child_counter;
get_ctx(child_ctx);
@@ -3781,12 +4127,6 @@ inherit_counter(struct perf_counter *parent_counter,
*/
add_counter_to_ctx(child_counter, child_ctx);
- child_counter->parent = parent_counter;
- /*
- * inherit into child's child as well:
- */
- child_counter->attr.inherit = 1;
-
/*
* Get a reference to the parent filp - we will fput it
* when the child counter exits. This is safe to do because
@@ -3830,10 +4170,14 @@ static int inherit_group(struct perf_counter *parent_counter,
}
static void sync_child_counter(struct perf_counter *child_counter,
- struct perf_counter *parent_counter)
+ struct task_struct *child)
{
+ struct perf_counter *parent_counter = child_counter->parent;
u64 child_val;
+ if (child_counter->attr.inherit_stat)
+ perf_counter_read_event(child_counter, child);
+
child_val = atomic64_read(&child_counter->count);
/*
@@ -3862,7 +4206,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
static void
__perf_counter_exit_task(struct perf_counter *child_counter,
- struct perf_counter_context *child_ctx)
+ struct perf_counter_context *child_ctx,
+ struct task_struct *child)
{
struct perf_counter *parent_counter;
@@ -3876,7 +4221,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter,
* counters need to be zapped - but otherwise linger.
*/
if (parent_counter) {
- sync_child_counter(child_counter, parent_counter);
+ sync_child_counter(child_counter, child);
free_counter(child_counter);
}
}
@@ -3938,7 +4283,7 @@ void perf_counter_exit_task(struct task_struct *child)
again:
list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
list_entry)
- __perf_counter_exit_task(child_counter, child_ctx);
+ __perf_counter_exit_task(child_counter, child_ctx, child);
/*
* If the last counter was a group counter, it will have appended all
diff --git a/kernel/pid.c b/kernel/pid.c
index b2e5f78fd28..31310b5d3f5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -378,26 +378,15 @@ EXPORT_SYMBOL(pid_task);
/*
* Must be called under rcu_read_lock() or with tasklist_lock read-held.
*/
-struct task_struct *find_task_by_pid_type_ns(int type, int nr,
- struct pid_namespace *ns)
+struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
- return pid_task(find_pid_ns(nr, ns), type);
+ return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
-EXPORT_SYMBOL(find_task_by_pid_type_ns);
-
struct task_struct *find_task_by_vpid(pid_t vnr)
{
- return find_task_by_pid_type_ns(PIDTYPE_PID, vnr,
- current->nsproxy->pid_ns);
-}
-EXPORT_SYMBOL(find_task_by_vpid);
-
-struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
-{
- return find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns);
+ return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns);
}
-EXPORT_SYMBOL(find_task_by_pid_ns);
struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 2d1001b4858..821722ae58a 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -67,9 +67,10 @@ err_alloc:
return NULL;
}
-static struct pid_namespace *create_pid_namespace(unsigned int level)
+static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
{
struct pid_namespace *ns;
+ unsigned int level = parent_pid_ns->level + 1;
int i;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
@@ -86,6 +87,7 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
kref_init(&ns->kref);
ns->level = level;
+ ns->parent = get_pid_ns(parent_pid_ns);
set_bit(0, ns->pidmap[0].page);
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -114,25 +116,11 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
{
- struct pid_namespace *new_ns;
-
- BUG_ON(!old_ns);
- new_ns = get_pid_ns(old_ns);
if (!(flags & CLONE_NEWPID))
- goto out;
-
- new_ns = ERR_PTR(-EINVAL);
+ return get_pid_ns(old_ns);
if (flags & CLONE_THREAD)
- goto out_put;
-
- new_ns = create_pid_namespace(old_ns->level + 1);
- if (!IS_ERR(new_ns))
- new_ns->parent = get_pid_ns(old_ns);
-
-out_put:
- put_pid_ns(old_ns);
-out:
- return new_ns;
+ return ERR_PTR(-EINVAL);
+ return create_pid_namespace(old_ns);
}
void free_pid_ns(struct kref *kref)
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 23bd4daeb96..72067cbdb37 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -116,9 +116,13 @@ config SUSPEND_FREEZER
Turning OFF this setting is NOT recommended! If in doubt, say Y.
+config HIBERNATION_NVS
+ bool
+
config HIBERNATION
bool "Hibernation (aka 'suspend to disk')"
depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+ select HIBERNATION_NVS if HAS_IOMEM
---help---
Enable the suspend to disk (STD) functionality, which is usually
called "hibernation" in user interfaces. STD checkpoints the
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 720ea4f781b..c3b81c30e5d 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -6,6 +6,9 @@ endif
obj-$(CONFIG_PM) += main.o
obj-$(CONFIG_PM_SLEEP) += console.o
obj-$(CONFIG_FREEZER) += process.o
-obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o
+obj-$(CONFIG_SUSPEND) += suspend.o
+obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o
+obj-$(CONFIG_HIBERNATION) += swsusp.o hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
diff --git a/kernel/power/disk.c b/kernel/power/hibernate.c
index 5cb080e7eeb..81d2e746489 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/hibernate.c
@@ -1,12 +1,12 @@
/*
- * kernel/power/disk.c - Suspend-to-disk support.
+ * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
* Copyright (c) 2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc.
*
* This file is released under the GPLv2.
- *
*/
#include <linux/suspend.h>
@@ -215,13 +215,13 @@ static int create_image(int platform_mode)
if (error)
return error;
- /* At this point, device_suspend() has been called, but *not*
- * device_power_down(). We *must* call device_power_down() now.
+ /* At this point, dpm_suspend_start() has been called, but *not*
+ * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
* Otherwise, drivers for some devices (e.g. interrupt controllers)
* become desynchronized with the actual state of the hardware
* at resume time, and evil weirdness ensues.
*/
- error = device_power_down(PMSG_FREEZE);
+ error = dpm_suspend_noirq(PMSG_FREEZE);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down, "
"aborting hibernation\n");
@@ -262,7 +262,7 @@ static int create_image(int platform_mode)
Power_up:
sysdev_resume();
- /* NOTE: device_power_up() is just a resume() for devices
+ /* NOTE: dpm_resume_noirq() is just a resume() for devices
* that suspended with irqs off ... no overall powerup.
*/
@@ -275,7 +275,7 @@ static int create_image(int platform_mode)
Platform_finish:
platform_finish(platform_mode);
- device_power_up(in_suspend ?
+ dpm_resume_noirq(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
return error;
@@ -304,7 +304,7 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
- error = device_suspend(PMSG_FREEZE);
+ error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -315,7 +315,7 @@ int hibernation_snapshot(int platform_mode)
/* Control returns here after successful restore */
Resume_devices:
- device_resume(in_suspend ?
+ dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
resume_console();
Close:
@@ -339,7 +339,7 @@ static int resume_target_kernel(bool platform_mode)
{
int error;
- error = device_power_down(PMSG_QUIESCE);
+ error = dpm_suspend_noirq(PMSG_QUIESCE);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down, "
"aborting resume\n");
@@ -394,7 +394,7 @@ static int resume_target_kernel(bool platform_mode)
Cleanup:
platform_restore_cleanup(platform_mode);
- device_power_up(PMSG_RECOVER);
+ dpm_resume_noirq(PMSG_RECOVER);
return error;
}
@@ -414,10 +414,10 @@ int hibernation_restore(int platform_mode)
pm_prepare_console();
suspend_console();
- error = device_suspend(PMSG_QUIESCE);
+ error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
- device_resume(PMSG_RECOVER);
+ dpm_resume_end(PMSG_RECOVER);
}
resume_console();
pm_restore_console();
@@ -447,14 +447,14 @@ int hibernation_platform_enter(void)
entering_platform_hibernation = true;
suspend_console();
- error = device_suspend(PMSG_HIBERNATE);
+ error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
hibernation_ops->recover();
goto Resume_devices;
}
- error = device_power_down(PMSG_HIBERNATE);
+ error = dpm_suspend_noirq(PMSG_HIBERNATE);
if (error)
goto Resume_devices;
@@ -479,11 +479,11 @@ int hibernation_platform_enter(void)
Platofrm_finish:
hibernation_ops->finish();
- device_power_up(PMSG_RESTORE);
+ dpm_suspend_noirq(PMSG_RESTORE);
Resume_devices:
entering_platform_hibernation = false;
- device_resume(PMSG_RESTORE);
+ dpm_resume_end(PMSG_RESTORE);
resume_console();
Close:
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/hibernate_nvs.c
new file mode 100644
index 00000000000..39ac698ef83
--- /dev/null
+++ b/kernel/power/hibernate_nvs.c
@@ -0,0 +1,135 @@
+/*
+ * linux/kernel/power/hibernate_nvs.c - Routines for handling NVS memory
+ *
+ * Copyright (C) 2008,2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume. The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+ unsigned long phys_start;
+ unsigned int size;
+ void *kaddr;
+ void *data;
+ struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ * hibernate_nvs_register - register platform NVS memory region to save
+ * @start - physical address of the region
+ * @size - size of the region
+ *
+ * The NVS region need not be page-aligned (both ends) and we arrange
+ * things so that the data from page-aligned addresses in this region will
+ * be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+ struct nvs_page *entry, *next;
+
+ while (size > 0) {
+ unsigned int nr_bytes;
+
+ entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+ if (!entry)
+ goto Error;
+
+ list_add_tail(&entry->node, &nvs_list);
+ entry->phys_start = start;
+ nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+ entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+ start += entry->size;
+ size -= entry->size;
+ }
+ return 0;
+
+ Error:
+ list_for_each_entry_safe(entry, next, &nvs_list, node) {
+ list_del(&entry->node);
+ kfree(entry);
+ }
+ return -ENOMEM;
+}
+
+/**
+ * hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+ struct nvs_page *entry;
+
+ list_for_each_entry(entry, &nvs_list, node)
+ if (entry->data) {
+ free_page((unsigned long)entry->data);
+ entry->data = NULL;
+ if (entry->kaddr) {
+ iounmap(entry->kaddr);
+ entry->kaddr = NULL;
+ }
+ }
+}
+
+/**
+ * hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+ struct nvs_page *entry;
+
+ list_for_each_entry(entry, &nvs_list, node) {
+ entry->data = (void *)__get_free_page(GFP_KERNEL);
+ if (!entry->data) {
+ hibernate_nvs_free();
+ return -ENOMEM;
+ }
+ }
+ return 0;
+}
+
+/**
+ * hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+ struct nvs_page *entry;
+
+ printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+ list_for_each_entry(entry, &nvs_list, node)
+ if (entry->data) {
+ entry->kaddr = ioremap(entry->phys_start, entry->size);
+ memcpy(entry->data, entry->kaddr, entry->size);
+ }
+}
+
+/**
+ * hibernate_nvs_restore - restore NVS memory regions
+ *
+ * This function is going to be called with interrupts disabled, so it
+ * cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+ struct nvs_page *entry;
+
+ printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+ list_for_each_entry(entry, &nvs_list, node)
+ if (entry->data)
+ memcpy(entry->kaddr, entry->data, entry->size);
+}
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 868028280d1..f710e36930c 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -8,20 +8,9 @@
*
*/
-#include <linux/module.h>
-#include <linux/suspend.h>
#include <linux/kobject.h>
#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/kmod.h>
-#include <linux/init.h>
-#include <linux/console.h>
-#include <linux/cpu.h>
#include <linux/resume-trace.h>
-#include <linux/freezer.h>
-#include <linux/vmstat.h>
-#include <linux/syscalls.h>
#include "power.h"
@@ -119,373 +108,6 @@ power_attr(pm_test);
#endif /* CONFIG_PM_SLEEP */
-#ifdef CONFIG_SUSPEND
-
-static int suspend_test(int level)
-{
-#ifdef CONFIG_PM_DEBUG
- if (pm_test_level == level) {
- printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
- mdelay(5000);
- return 1;
- }
-#endif /* !CONFIG_PM_DEBUG */
- return 0;
-}
-
-#ifdef CONFIG_PM_TEST_SUSPEND
-
-/*
- * We test the system suspend code by setting an RTC wakealarm a short
- * time in the future, then suspending. Suspending the devices won't
- * normally take long ... some systems only need a few milliseconds.
- *
- * The time it takes is system-specific though, so when we test this
- * during system bootup we allow a LOT of time.
- */
-#define TEST_SUSPEND_SECONDS 5
-
-static unsigned long suspend_test_start_time;
-
-static void suspend_test_start(void)
-{
- /* FIXME Use better timebase than "jiffies", ideally a clocksource.
- * What we want is a hardware counter that will work correctly even
- * during the irqs-are-off stages of the suspend/resume cycle...
- */
- suspend_test_start_time = jiffies;
-}
-
-static void suspend_test_finish(const char *label)
-{
- long nj = jiffies - suspend_test_start_time;
- unsigned msec;
-
- msec = jiffies_to_msecs(abs(nj));
- pr_info("PM: %s took %d.%03d seconds\n", label,
- msec / 1000, msec % 1000);
-
- /* Warning on suspend means the RTC alarm period needs to be
- * larger -- the system was sooo slooowwww to suspend that the
- * alarm (should have) fired before the system went to sleep!
- *
- * Warning on either suspend or resume also means the system
- * has some performance issues. The stack dump of a WARN_ON
- * is more likely to get the right attention than a printk...
- */
- WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
-}
-
-#else
-
-static void suspend_test_start(void)
-{
-}
-
-static void suspend_test_finish(const char *label)
-{
-}
-
-#endif
-
-/* This is just an arbitrary number */
-#define FREE_PAGE_NUMBER (100)
-
-static struct platform_suspend_ops *suspend_ops;
-
-/**
- * suspend_set_ops - Set the global suspend method table.
- * @ops: Pointer to ops structure.
- */
-
-void suspend_set_ops(struct platform_suspend_ops *ops)
-{
- mutex_lock(&pm_mutex);
- suspend_ops = ops;
- mutex_unlock(&pm_mutex);
-}
-
-/**
- * suspend_valid_only_mem - generic memory-only valid callback
- *
- * Platform drivers that implement mem suspend only and only need
- * to check for that in their .valid callback can use this instead
- * of rolling their own .valid callback.
- */
-int suspend_valid_only_mem(suspend_state_t state)
-{
- return state == PM_SUSPEND_MEM;
-}
-
-/**
- * suspend_prepare - Do prep work before entering low-power state.
- *
- * This is common code that is called for each state that we're entering.
- * Run suspend notifiers, allocate a console and stop all processes.
- */
-static int suspend_prepare(void)
-{
- int error;
- unsigned int free_pages;
-
- if (!suspend_ops || !suspend_ops->enter)
- return -EPERM;
-
- pm_prepare_console();
-
- error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
- if (error)
- goto Finish;
-
- error = usermodehelper_disable();
- if (error)
- goto Finish;
-
- if (suspend_freeze_processes()) {
- error = -EAGAIN;
- goto Thaw;
- }
-
- free_pages = global_page_state(NR_FREE_PAGES);
- if (free_pages < FREE_PAGE_NUMBER) {
- pr_debug("PM: free some memory\n");
- shrink_all_memory(FREE_PAGE_NUMBER - free_pages);
- if (nr_free_pages() < FREE_PAGE_NUMBER) {
- error = -ENOMEM;
- printk(KERN_ERR "PM: No enough memory\n");
- }
- }
- if (!error)
- return 0;
-
- Thaw:
- suspend_thaw_processes();
- usermodehelper_enable();
- Finish:
- pm_notifier_call_chain(PM_POST_SUSPEND);
- pm_restore_console();
- return error;
-}
-
-/* default implementation */
-void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
-{
- local_irq_disable();
-}
-
-/* default implementation */
-void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
-{
- local_irq_enable();
-}
-
-/**
- * suspend_enter - enter the desired system sleep state.
- * @state: state to enter
- *
- * This function should be called after devices have been suspended.
- */
-static int suspend_enter(suspend_state_t state)
-{
- int error;
-
- if (suspend_ops->prepare) {
- error = suspend_ops->prepare();
- if (error)
- return error;
- }
-
- error = device_power_down(PMSG_SUSPEND);
- if (error) {
- printk(KERN_ERR "PM: Some devices failed to power down\n");
- goto Platfrom_finish;
- }
-
- if (suspend_ops->prepare_late) {
- error = suspend_ops->prepare_late();
- if (error)
- goto Power_up_devices;
- }
-
- if (suspend_test(TEST_PLATFORM))
- goto Platform_wake;
-
- error = disable_nonboot_cpus();
- if (error || suspend_test(TEST_CPUS))
- goto Enable_cpus;
-
- arch_suspend_disable_irqs();
- BUG_ON(!irqs_disabled());
-
- error = sysdev_suspend(PMSG_SUSPEND);
- if (!error) {
- if (!suspend_test(TEST_CORE))
- error = suspend_ops->enter(state);
- sysdev_resume();
- }
-
- arch_suspend_enable_irqs();
- BUG_ON(irqs_disabled());
-
- Enable_cpus:
- enable_nonboot_cpus();
-
- Platform_wake:
- if (suspend_ops->wake)
- suspend_ops->wake();
-
- Power_up_devices:
- device_power_up(PMSG_RESUME);
-
- Platfrom_finish:
- if (suspend_ops->finish)
- suspend_ops->finish();
-
- return error;
-}
-
-/**
- * suspend_devices_and_enter - suspend devices and enter the desired system
- * sleep state.
- * @state: state to enter
- */
-int suspend_devices_and_enter(suspend_state_t state)
-{
- int error;
-
- if (!suspend_ops)
- return -ENOSYS;
-
- if (suspend_ops->begin) {
- error = suspend_ops->begin(state);
- if (error)
- goto Close;
- }
- suspend_console();
- suspend_test_start();
- error = device_suspend(PMSG_SUSPEND);
- if (error) {
- printk(KERN_ERR "PM: Some devices failed to suspend\n");
- goto Recover_platform;
- }
- suspend_test_finish("suspend devices");
- if (suspend_test(TEST_DEVICES))
- goto Recover_platform;
-
- suspend_enter(state);
-
- Resume_devices:
- suspend_test_start();
- device_resume(PMSG_RESUME);
- suspend_test_finish("resume devices");
- resume_console();
- Close:
- if (suspend_ops->end)
- suspend_ops->end();
- return error;
-
- Recover_platform:
- if (suspend_ops->recover)
- suspend_ops->recover();
- goto Resume_devices;
-}
-
-/**
- * suspend_finish - Do final work before exiting suspend sequence.
- *
- * Call platform code to clean up, restart processes, and free the
- * console that we've allocated. This is not called for suspend-to-disk.
- */
-static void suspend_finish(void)
-{
- suspend_thaw_processes();
- usermodehelper_enable();
- pm_notifier_call_chain(PM_POST_SUSPEND);
- pm_restore_console();
-}
-
-
-
-
-static const char * const pm_states[PM_SUSPEND_MAX] = {
- [PM_SUSPEND_STANDBY] = "standby",
- [PM_SUSPEND_MEM] = "mem",
-};
-
-static inline int valid_state(suspend_state_t state)
-{
- /* All states need lowlevel support and need to be valid
- * to the lowlevel implementation, no valid callback
- * implies that none are valid. */
- if (!suspend_ops || !suspend_ops->valid || !suspend_ops->valid(state))
- return 0;
- return 1;
-}
-
-
-/**
- * enter_state - Do common work of entering low-power state.
- * @state: pm_state structure for state we're entering.
- *
- * Make sure we're the only ones trying to enter a sleep state. Fail
- * if someone has beat us to it, since we don't want anything weird to
- * happen when we wake up.
- * Then, do the setup for suspend, enter the state, and cleaup (after
- * we've woken up).
- */
-static int enter_state(suspend_state_t state)
-{
- int error;
-
- if (!valid_state(state))
- return -ENODEV;
-
- if (!mutex_trylock(&pm_mutex))
- return -EBUSY;
-
- printk(KERN_INFO "PM: Syncing filesystems ... ");
- sys_sync();
- printk("done.\n");
-
- pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
- error = suspend_prepare();
- if (error)
- goto Unlock;
-
- if (suspend_test(TEST_FREEZER))
- goto Finish;
-
- pr_debug("PM: Entering %s sleep\n", pm_states[state]);
- error = suspend_devices_and_enter(state);
-
- Finish:
- pr_debug("PM: Finishing wakeup.\n");
- suspend_finish();
- Unlock:
- mutex_unlock(&pm_mutex);
- return error;
-}
-
-
-/**
- * pm_suspend - Externally visible function for suspending system.
- * @state: Enumerated value of state to enter.
- *
- * Determine whether or not value is within range, get state
- * structure, and enter (above).
- */
-
-int pm_suspend(suspend_state_t state)
-{
- if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
- return enter_state(state);
- return -EINVAL;
-}
-
-EXPORT_SYMBOL(pm_suspend);
-
-#endif /* CONFIG_SUSPEND */
-
struct kobject *power_kobj;
/**
@@ -498,7 +120,6 @@ struct kobject *power_kobj;
* store() accepts one of those strings, translates it into the
* proper enumerated value, and initiates a suspend transition.
*/
-
static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
@@ -596,7 +217,6 @@ static struct attribute_group attr_group = {
.attrs = g,
};
-
static int __init pm_init(void)
{
power_kobj = kobject_create_and_add("power", NULL);
@@ -606,144 +226,3 @@ static int __init pm_init(void)
}
core_initcall(pm_init);
-
-
-#ifdef CONFIG_PM_TEST_SUSPEND
-
-#include <linux/rtc.h>
-
-/*
- * To test system suspend, we need a hands-off mechanism to resume the
- * system. RTCs wake alarms are a common self-contained mechanism.
- */
-
-static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
-{
- static char err_readtime[] __initdata =
- KERN_ERR "PM: can't read %s time, err %d\n";
- static char err_wakealarm [] __initdata =
- KERN_ERR "PM: can't set %s wakealarm, err %d\n";
- static char err_suspend[] __initdata =
- KERN_ERR "PM: suspend test failed, error %d\n";
- static char info_test[] __initdata =
- KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
-
- unsigned long now;
- struct rtc_wkalrm alm;
- int status;
-
- /* this may fail if the RTC hasn't been initialized */
- status = rtc_read_time(rtc, &alm.time);
- if (status < 0) {
- printk(err_readtime, dev_name(&rtc->dev), status);
- return;
- }
- rtc_tm_to_time(&alm.time, &now);
-
- memset(&alm, 0, sizeof alm);
- rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
- alm.enabled = true;
-
- status = rtc_set_alarm(rtc, &alm);
- if (status < 0) {
- printk(err_wakealarm, dev_name(&rtc->dev), status);
- return;
- }
-
- if (state == PM_SUSPEND_MEM) {
- printk(info_test, pm_states[state]);
- status = pm_suspend(state);
- if (status == -ENODEV)
- state = PM_SUSPEND_STANDBY;
- }
- if (state == PM_SUSPEND_STANDBY) {
- printk(info_test, pm_states[state]);
- status = pm_suspend(state);
- }
- if (status < 0)
- printk(err_suspend, status);
-
- /* Some platforms can't detect that the alarm triggered the
- * wakeup, or (accordingly) disable it after it afterwards.
- * It's supposed to give oneshot behavior; cope.
- */
- alm.enabled = false;
- rtc_set_alarm(rtc, &alm);
-}
-
-static int __init has_wakealarm(struct device *dev, void *name_ptr)
-{
- struct rtc_device *candidate = to_rtc_device(dev);
-
- if (!candidate->ops->set_alarm)
- return 0;
- if (!device_may_wakeup(candidate->dev.parent))
- return 0;
-
- *(const char **)name_ptr = dev_name(dev);
- return 1;
-}
-
-/*
- * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
- * at startup time. They're normally disabled, for faster boot and because
- * we can't know which states really work on this particular system.
- */
-static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
-
-static char warn_bad_state[] __initdata =
- KERN_WARNING "PM: can't test '%s' suspend state\n";
-
-static int __init setup_test_suspend(char *value)
-{
- unsigned i;
-
- /* "=mem" ==> "mem" */
- value++;
- for (i = 0; i < PM_SUSPEND_MAX; i++) {
- if (!pm_states[i])
- continue;
- if (strcmp(pm_states[i], value) != 0)
- continue;
- test_state = (__force suspend_state_t) i;
- return 0;
- }
- printk(warn_bad_state, value);
- return 0;
-}
-__setup("test_suspend", setup_test_suspend);
-
-static int __init test_suspend(void)
-{
- static char warn_no_rtc[] __initdata =
- KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
-
- char *pony = NULL;
- struct rtc_device *rtc = NULL;
-
- /* PM is initialized by now; is that state testable? */
- if (test_state == PM_SUSPEND_ON)
- goto done;
- if (!valid_state(test_state)) {
- printk(warn_bad_state, pm_states[test_state]);
- goto done;
- }
-
- /* RTCs have initialized by now too ... can we use one? */
- class_find_device(rtc_class, NULL, &pony, has_wakealarm);
- if (pony)
- rtc = rtc_class_open(pony);
- if (!rtc) {
- printk(warn_no_rtc);
- goto done;
- }
-
- /* go for it */
- test_wakealarm(rtc, test_state);
- rtc_class_close(rtc);
-done:
- return 0;
-}
-late_initcall(test_suspend);
-
-#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 46b5ec7a3af..26d5a26f82e 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -45,7 +45,7 @@ static inline char *check_image_kernel(struct swsusp_info *info)
*/
#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT)
-/* kernel/power/disk.c */
+/* kernel/power/hibernate.c */
extern int hibernation_snapshot(int platform_mode);
extern int hibernation_restore(int platform_mode);
extern int hibernation_platform_enter(void);
@@ -74,7 +74,7 @@ extern asmlinkage int swsusp_arch_resume(void);
extern int create_basic_memory_bitmaps(void);
extern void free_basic_memory_bitmaps(void);
-extern unsigned int count_data_pages(void);
+extern int swsusp_shrink_memory(void);
/**
* Auxiliary structure used for reading the snapshot image data and
@@ -147,9 +147,8 @@ extern int swsusp_swap_in_use(void);
*/
#define SF_PLATFORM_MODE 1
-/* kernel/power/disk.c */
+/* kernel/power/hibernate.c */
extern int swsusp_check(void);
-extern int swsusp_shrink_memory(void);
extern void swsusp_free(void);
extern int swsusp_read(unsigned int *flags_p);
extern int swsusp_write(unsigned int flags);
@@ -161,22 +160,36 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
unsigned int, char *);
#ifdef CONFIG_SUSPEND
-/* kernel/power/main.c */
+/* kernel/power/suspend.c */
+extern const char *const pm_states[];
+
+extern bool valid_state(suspend_state_t state);
extern int suspend_devices_and_enter(suspend_state_t state);
+extern int enter_state(suspend_state_t state);
#else /* !CONFIG_SUSPEND */
static inline int suspend_devices_and_enter(suspend_state_t state)
{
return -ENOSYS;
}
+static inline int enter_state(suspend_state_t state) { return -ENOSYS; }
+static inline bool valid_state(suspend_state_t state) { return false; }
#endif /* !CONFIG_SUSPEND */
+#ifdef CONFIG_PM_TEST_SUSPEND
+/* kernel/power/suspend_test.c */
+extern void suspend_test_start(void);
+extern void suspend_test_finish(const char *label);
+#else /* !CONFIG_PM_TEST_SUSPEND */
+static inline void suspend_test_start(void) {}
+static inline void suspend_test_finish(const char *label) {}
+#endif /* !CONFIG_PM_TEST_SUSPEND */
+
#ifdef CONFIG_PM_SLEEP
/* kernel/power/main.c */
extern int pm_notifier_call_chain(unsigned long val);
#endif
#ifdef CONFIG_HIGHMEM
-unsigned int count_highmem_pages(void);
int restore_highmem(void);
#else
static inline unsigned int count_highmem_pages(void) { return 0; }
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 97890831e1b..e8b33700627 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -34,7 +34,7 @@ static struct sysrq_key_op sysrq_poweroff_op = {
.handler = handle_poweroff,
.help_msg = "powerOff",
.action_msg = "Power Off",
- .enable_mask = SYSRQ_ENABLE_BOOT,
+ .enable_mask = SYSRQ_ENABLE_BOOT,
};
static int pm_sysrq_init(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index ca634019497..da2072d7381 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -117,9 +117,12 @@ int freeze_processes(void)
if (error)
goto Exit;
printk("done.");
+
+ oom_killer_disable();
Exit:
BUG_ON(in_atomic());
printk("\n");
+
return error;
}
@@ -145,6 +148,8 @@ static void thaw_tasks(bool nosig_only)
void thaw_processes(void)
{
+ oom_killer_enable();
+
printk("Restarting tasks ... ");
thaw_tasks(true);
thaw_tasks(false);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 33e2e4a819f..523a451b45d 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -39,6 +39,14 @@ static int swsusp_page_is_free(struct page *);
static void swsusp_set_page_forbidden(struct page *);
static void swsusp_unset_page_forbidden(struct page *);
+/*
+ * Preferred image size in bytes (tunable via /sys/power/image_size).
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
+ */
+unsigned long image_size = 500 * 1024 * 1024;
+
/* List of PBEs needed for restoring the pages that were allocated before
* the suspend and included in the suspend image, but have also been
* allocated by the "resume" kernel, so their contents cannot be written
@@ -840,7 +848,7 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
* pages.
*/
-unsigned int count_highmem_pages(void)
+static unsigned int count_highmem_pages(void)
{
struct zone *zone;
unsigned int n = 0;
@@ -902,7 +910,7 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn)
* pages.
*/
-unsigned int count_data_pages(void)
+static unsigned int count_data_pages(void)
{
struct zone *zone;
unsigned long pfn, max_zone_pfn;
@@ -1058,6 +1066,74 @@ void swsusp_free(void)
buffer = NULL;
}
+/**
+ * swsusp_shrink_memory - Try to free as much memory as needed
+ *
+ * ... but do not OOM-kill anyone
+ *
+ * Notice: all userland should be stopped before it is called, or
+ * livelock is possible.
+ */
+
+#define SHRINK_BITE 10000
+static inline unsigned long __shrink_memory(long tmp)
+{
+ if (tmp > SHRINK_BITE)
+ tmp = SHRINK_BITE;
+ return shrink_all_memory(tmp);
+}
+
+int swsusp_shrink_memory(void)
+{
+ long tmp;
+ struct zone *zone;
+ unsigned long pages = 0;
+ unsigned int i = 0;
+ char *p = "-\\|/";
+ struct timeval start, stop;
+
+ printk(KERN_INFO "PM: Shrinking memory... ");
+ do_gettimeofday(&start);
+ do {
+ long size, highmem_size;
+
+ highmem_size = count_highmem_pages();
+ size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
+ tmp = size;
+ size += highmem_size;
+ for_each_populated_zone(zone) {
+ tmp += snapshot_additional_pages(zone);
+ if (is_highmem(zone)) {
+ highmem_size -=
+ zone_page_state(zone, NR_FREE_PAGES);
+ } else {
+ tmp -= zone_page_state(zone, NR_FREE_PAGES);
+ tmp += zone->lowmem_reserve[ZONE_NORMAL];
+ }
+ }
+
+ if (highmem_size < 0)
+ highmem_size = 0;
+
+ tmp += highmem_size;
+ if (tmp > 0) {
+ tmp = __shrink_memory(tmp);
+ if (!tmp)
+ return -ENOMEM;
+ pages += tmp;
+ } else if (size > image_size / PAGE_SIZE) {
+ tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
+ pages += tmp;
+ }
+ printk("\b%c", p[i++%4]);
+ } while (tmp > 0);
+ do_gettimeofday(&stop);
+ printk("\bdone (%lu pages freed)\n", pages);
+ swsusp_show_speed(&start, &stop, pages, "Freed");
+
+ return 0;
+}
+
#ifdef CONFIG_HIGHMEM
/**
* count_pages_for_highmem - compute the number of non-highmem pages
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
new file mode 100644
index 00000000000..6f10dfc2d3e
--- /dev/null
+++ b/kernel/power/suspend.c
@@ -0,0 +1,300 @@
+/*
+ * kernel/power/suspend.c - Suspend to RAM and standby functionality.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/syscalls.h>
+
+#include "power.h"
+
+const char *const pm_states[PM_SUSPEND_MAX] = {
+ [PM_SUSPEND_STANDBY] = "standby",
+ [PM_SUSPEND_MEM] = "mem",
+};
+
+static struct platform_suspend_ops *suspend_ops;
+
+/**
+ * suspend_set_ops - Set the global suspend method table.
+ * @ops: Pointer to ops structure.
+ */
+void suspend_set_ops(struct platform_suspend_ops *ops)
+{
+ mutex_lock(&pm_mutex);
+ suspend_ops = ops;
+ mutex_unlock(&pm_mutex);
+}
+
+bool valid_state(suspend_state_t state)
+{
+ /*
+ * All states need lowlevel support and need to be valid to the lowlevel
+ * implementation, no valid callback implies that none are valid.
+ */
+ return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
+/**
+ * suspend_valid_only_mem - generic memory-only valid callback
+ *
+ * Platform drivers that implement mem suspend only and only need
+ * to check for that in their .valid callback can use this instead
+ * of rolling their own .valid callback.
+ */
+int suspend_valid_only_mem(suspend_state_t state)
+{
+ return state == PM_SUSPEND_MEM;
+}
+
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+ if (pm_test_level == level) {
+ printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+ mdelay(5000);
+ return 1;
+ }
+#endif /* !CONFIG_PM_DEBUG */
+ return 0;
+}
+
+/**
+ * suspend_prepare - Do prep work before entering low-power state.
+ *
+ * This is common code that is called for each state that we're entering.
+ * Run suspend notifiers, allocate a console and stop all processes.
+ */
+static int suspend_prepare(void)
+{
+ int error;
+
+ if (!suspend_ops || !suspend_ops->enter)
+ return -EPERM;
+
+ pm_prepare_console();
+
+ error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
+ if (error)
+ goto Finish;
+
+ error = usermodehelper_disable();
+ if (error)
+ goto Finish;
+
+ error = suspend_freeze_processes();
+ if (!error)
+ return 0;
+
+ suspend_thaw_processes();
+ usermodehelper_enable();
+ Finish:
+ pm_notifier_call_chain(PM_POST_SUSPEND);
+ pm_restore_console();
+ return error;
+}
+
+/* default implementation */
+void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
+{
+ local_irq_disable();
+}
+
+/* default implementation */
+void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
+{
+ local_irq_enable();
+}
+
+/**
+ * suspend_enter - enter the desired system sleep state.
+ * @state: state to enter
+ *
+ * This function should be called after devices have been suspended.
+ */
+static int suspend_enter(suspend_state_t state)
+{
+ int error;
+
+ if (suspend_ops->prepare) {
+ error = suspend_ops->prepare();
+ if (error)
+ return error;
+ }
+
+ error = dpm_suspend_noirq(PMSG_SUSPEND);
+ if (error) {
+ printk(KERN_ERR "PM: Some devices failed to power down\n");
+ goto Platfrom_finish;
+ }
+
+ if (suspend_ops->prepare_late) {
+ error = suspend_ops->prepare_late();
+ if (error)
+ goto Power_up_devices;
+ }
+
+ if (suspend_test(TEST_PLATFORM))
+ goto Platform_wake;
+
+ error = disable_nonboot_cpus();
+ if (error || suspend_test(TEST_CPUS))
+ goto Enable_cpus;
+
+ arch_suspend_disable_irqs();
+ BUG_ON(!irqs_disabled());
+
+ error = sysdev_suspend(PMSG_SUSPEND);
+ if (!error) {
+ if (!suspend_test(TEST_CORE))
+ error = suspend_ops->enter(state);
+ sysdev_resume();
+ }
+
+ arch_suspend_enable_irqs();
+ BUG_ON(irqs_disabled());
+
+ Enable_cpus:
+ enable_nonboot_cpus();
+
+ Platform_wake:
+ if (suspend_ops->wake)
+ suspend_ops->wake();
+
+ Power_up_devices:
+ dpm_resume_noirq(PMSG_RESUME);
+
+ Platfrom_finish:
+ if (suspend_ops->finish)
+ suspend_ops->finish();
+
+ return error;
+}
+
+/**
+ * suspend_devices_and_enter - suspend devices and enter the desired system
+ * sleep state.
+ * @state: state to enter
+ */
+int suspend_devices_and_enter(suspend_state_t state)
+{
+ int error;
+
+ if (!suspend_ops)
+ return -ENOSYS;
+
+ if (suspend_ops->begin) {
+ error = suspend_ops->begin(state);
+ if (error)
+ goto Close;
+ }
+ suspend_console();
+ suspend_test_start();
+ error = dpm_suspend_start(PMSG_SUSPEND);
+ if (error) {
+ printk(KERN_ERR "PM: Some devices failed to suspend\n");
+ goto Recover_platform;
+ }
+ suspend_test_finish("suspend devices");
+ if (suspend_test(TEST_DEVICES))
+ goto Recover_platform;
+
+ suspend_enter(state);
+
+ Resume_devices:
+ suspend_test_start();
+ dpm_resume_end(PMSG_RESUME);
+ suspend_test_finish("resume devices");
+ resume_console();
+ Close:
+ if (suspend_ops->end)
+ suspend_ops->end();
+ return error;
+
+ Recover_platform:
+ if (suspend_ops->recover)
+ suspend_ops->recover();
+ goto Resume_devices;
+}
+
+/**
+ * suspend_finish - Do final work before exiting suspend sequence.
+ *
+ * Call platform code to clean up, restart processes, and free the
+ * console that we've allocated. This is not called for suspend-to-disk.
+ */
+static void suspend_finish(void)
+{
+ suspend_thaw_processes();
+ usermodehelper_enable();
+ pm_notifier_call_chain(PM_POST_SUSPEND);
+ pm_restore_console();
+}
+
+/**
+ * enter_state - Do common work of entering low-power state.
+ * @state: pm_state structure for state we're entering.
+ *
+ * Make sure we're the only ones trying to enter a sleep state. Fail
+ * if someone has beat us to it, since we don't want anything weird to
+ * happen when we wake up.
+ * Then, do the setup for suspend, enter the state, and cleaup (after
+ * we've woken up).
+ */
+int enter_state(suspend_state_t state)
+{
+ int error;
+
+ if (!valid_state(state))
+ return -ENODEV;
+
+ if (!mutex_trylock(&pm_mutex))
+ return -EBUSY;
+
+ printk(KERN_INFO "PM: Syncing filesystems ... ");
+ sys_sync();
+ printk("done.\n");
+
+ pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+ error = suspend_prepare();
+ if (error)
+ goto Unlock;
+
+ if (suspend_test(TEST_FREEZER))
+ goto Finish;
+
+ pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+ error = suspend_devices_and_enter(state);
+
+ Finish:
+ pr_debug("PM: Finishing wakeup.\n");
+ suspend_finish();
+ Unlock:
+ mutex_unlock(&pm_mutex);
+ return error;
+}
+
+/**
+ * pm_suspend - Externally visible function for suspending system.
+ * @state: Enumerated value of state to enter.
+ *
+ * Determine whether or not value is within range, get state
+ * structure, and enter (above).
+ */
+int pm_suspend(suspend_state_t state)
+{
+ if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
+ return enter_state(state);
+ return -EINVAL;
+}
+EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
new file mode 100644
index 00000000000..17d8bb1acf9
--- /dev/null
+++ b/kernel/power/suspend_test.c
@@ -0,0 +1,187 @@
+/*
+ * kernel/power/suspend_test.c - Suspend to RAM and standby test facility.
+ *
+ * Copyright (c) 2009 Pavel Machek <pavel@ucw.cz>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/rtc.h>
+
+#include "power.h"
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending. Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS 5
+
+static unsigned long suspend_test_start_time;
+
+void suspend_test_start(void)
+{
+ /* FIXME Use better timebase than "jiffies", ideally a clocksource.
+ * What we want is a hardware counter that will work correctly even
+ * during the irqs-are-off stages of the suspend/resume cycle...
+ */
+ suspend_test_start_time = jiffies;
+}
+
+void suspend_test_finish(const char *label)
+{
+ long nj = jiffies - suspend_test_start_time;
+ unsigned msec;
+
+ msec = jiffies_to_msecs(abs(nj));
+ pr_info("PM: %s took %d.%03d seconds\n", label,
+ msec / 1000, msec % 1000);
+
+ /* Warning on suspend means the RTC alarm period needs to be
+ * larger -- the system was sooo slooowwww to suspend that the
+ * alarm (should have) fired before the system went to sleep!
+ *
+ * Warning on either suspend or resume also means the system
+ * has some performance issues. The stack dump of a WARN_ON
+ * is more likely to get the right attention than a printk...
+ */
+ WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
+}
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system. RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+ static char err_readtime[] __initdata =
+ KERN_ERR "PM: can't read %s time, err %d\n";
+ static char err_wakealarm [] __initdata =
+ KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+ static char err_suspend[] __initdata =
+ KERN_ERR "PM: suspend test failed, error %d\n";
+ static char info_test[] __initdata =
+ KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+ unsigned long now;
+ struct rtc_wkalrm alm;
+ int status;
+
+ /* this may fail if the RTC hasn't been initialized */
+ status = rtc_read_time(rtc, &alm.time);
+ if (status < 0) {
+ printk(err_readtime, dev_name(&rtc->dev), status);
+ return;
+ }
+ rtc_tm_to_time(&alm.time, &now);
+
+ memset(&alm, 0, sizeof alm);
+ rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+ alm.enabled = true;
+
+ status = rtc_set_alarm(rtc, &alm);
+ if (status < 0) {
+ printk(err_wakealarm, dev_name(&rtc->dev), status);
+ return;
+ }
+
+ if (state == PM_SUSPEND_MEM) {
+ printk(info_test, pm_states[state]);
+ status = pm_suspend(state);
+ if (status == -ENODEV)
+ state = PM_SUSPEND_STANDBY;
+ }
+ if (state == PM_SUSPEND_STANDBY) {
+ printk(info_test, pm_states[state]);
+ status = pm_suspend(state);
+ }
+ if (status < 0)
+ printk(err_suspend, status);
+
+ /* Some platforms can't detect that the alarm triggered the
+ * wakeup, or (accordingly) disable it after it afterwards.
+ * It's supposed to give oneshot behavior; cope.
+ */
+ alm.enabled = false;
+ rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+ struct rtc_device *candidate = to_rtc_device(dev);
+
+ if (!candidate->ops->set_alarm)
+ return 0;
+ if (!device_may_wakeup(candidate->dev.parent))
+ return 0;
+
+ *(const char **)name_ptr = dev_name(dev);
+ return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time. They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+ KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+ unsigned i;
+
+ /* "=mem" ==> "mem" */
+ value++;
+ for (i = 0; i < PM_SUSPEND_MAX; i++) {
+ if (!pm_states[i])
+ continue;
+ if (strcmp(pm_states[i], value) != 0)
+ continue;
+ test_state = (__force suspend_state_t) i;
+ return 0;
+ }
+ printk(warn_bad_state, value);
+ return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+ static char warn_no_rtc[] __initdata =
+ KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+ char *pony = NULL;
+ struct rtc_device *rtc = NULL;
+
+ /* PM is initialized by now; is that state testable? */
+ if (test_state == PM_SUSPEND_ON)
+ goto done;
+ if (!valid_state(test_state)) {
+ printk(warn_bad_state, pm_states[test_state]);
+ goto done;
+ }
+
+ /* RTCs have initialized by now too ... can we use one? */
+ class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+ if (pony)
+ rtc = rtc_class_open(pony);
+ if (!rtc) {
+ printk(warn_no_rtc);
+ goto done;
+ }
+
+ /* go for it */
+ test_wakealarm(rtc, test_state);
+ rtc_class_close(rtc);
+done:
+ return 0;
+}
+late_initcall(test_suspend);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 78c35047586..6a07f4dbf2f 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -55,14 +55,6 @@
#include "power.h"
-/*
- * Preferred image size in bytes (tunable via /sys/power/image_size).
- * When it is set to N, swsusp will do its best to ensure the image
- * size will not exceed N bytes, but if that is impossible, it will
- * try to create the smallest image possible.
- */
-unsigned long image_size = 500 * 1024 * 1024;
-
int in_suspend __nosavedata = 0;
/**
@@ -194,193 +186,3 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
centisecs / 100, centisecs % 100,
kps / 1000, (kps % 1000) / 10);
}
-
-/**
- * swsusp_shrink_memory - Try to free as much memory as needed
- *
- * ... but do not OOM-kill anyone
- *
- * Notice: all userland should be stopped before it is called, or
- * livelock is possible.
- */
-
-#define SHRINK_BITE 10000
-static inline unsigned long __shrink_memory(long tmp)
-{
- if (tmp > SHRINK_BITE)
- tmp = SHRINK_BITE;
- return shrink_all_memory(tmp);
-}
-
-int swsusp_shrink_memory(void)
-{
- long tmp;
- struct zone *zone;
- unsigned long pages = 0;
- unsigned int i = 0;
- char *p = "-\\|/";
- struct timeval start, stop;
-
- printk(KERN_INFO "PM: Shrinking memory... ");
- do_gettimeofday(&start);
- do {
- long size, highmem_size;
-
- highmem_size = count_highmem_pages();
- size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
- tmp = size;
- size += highmem_size;
- for_each_populated_zone(zone) {
- tmp += snapshot_additional_pages(zone);
- if (is_highmem(zone)) {
- highmem_size -=
- zone_page_state(zone, NR_FREE_PAGES);
- } else {
- tmp -= zone_page_state(zone, NR_FREE_PAGES);
- tmp += zone->lowmem_reserve[ZONE_NORMAL];
- }
- }
-
- if (highmem_size < 0)
- highmem_size = 0;
-
- tmp += highmem_size;
- if (tmp > 0) {
- tmp = __shrink_memory(tmp);
- if (!tmp)
- return -ENOMEM;
- pages += tmp;
- } else if (size > image_size / PAGE_SIZE) {
- tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
- pages += tmp;
- }
- printk("\b%c", p[i++%4]);
- } while (tmp > 0);
- do_gettimeofday(&stop);
- printk("\bdone (%lu pages freed)\n", pages);
- swsusp_show_speed(&start, &stop, pages, "Freed");
-
- return 0;
-}
-
-/*
- * Platforms, like ACPI, may want us to save some memory used by them during
- * hibernation and to restore the contents of this memory during the subsequent
- * resume. The code below implements a mechanism allowing us to do that.
- */
-
-struct nvs_page {
- unsigned long phys_start;
- unsigned int size;
- void *kaddr;
- void *data;
- struct list_head node;
-};
-
-static LIST_HEAD(nvs_list);
-
-/**
- * hibernate_nvs_register - register platform NVS memory region to save
- * @start - physical address of the region
- * @size - size of the region
- *
- * The NVS region need not be page-aligned (both ends) and we arrange
- * things so that the data from page-aligned addresses in this region will
- * be copied into separate RAM pages.
- */
-int hibernate_nvs_register(unsigned long start, unsigned long size)
-{
- struct nvs_page *entry, *next;
-
- while (size > 0) {
- unsigned int nr_bytes;
-
- entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
- if (!entry)
- goto Error;
-
- list_add_tail(&entry->node, &nvs_list);
- entry->phys_start = start;
- nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
- entry->size = (size < nr_bytes) ? size : nr_bytes;
-
- start += entry->size;
- size -= entry->size;
- }
- return 0;
-
- Error:
- list_for_each_entry_safe(entry, next, &nvs_list, node) {
- list_del(&entry->node);
- kfree(entry);
- }
- return -ENOMEM;
-}
-
-/**
- * hibernate_nvs_free - free data pages allocated for saving NVS regions
- */
-void hibernate_nvs_free(void)
-{
- struct nvs_page *entry;
-
- list_for_each_entry(entry, &nvs_list, node)
- if (entry->data) {
- free_page((unsigned long)entry->data);
- entry->data = NULL;
- if (entry->kaddr) {
- iounmap(entry->kaddr);
- entry->kaddr = NULL;
- }
- }
-}
-
-/**
- * hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
- */
-int hibernate_nvs_alloc(void)
-{
- struct nvs_page *entry;
-
- list_for_each_entry(entry, &nvs_list, node) {
- entry->data = (void *)__get_free_page(GFP_KERNEL);
- if (!entry->data) {
- hibernate_nvs_free();
- return -ENOMEM;
- }
- }
- return 0;
-}
-
-/**
- * hibernate_nvs_save - save NVS memory regions
- */
-void hibernate_nvs_save(void)
-{
- struct nvs_page *entry;
-
- printk(KERN_INFO "PM: Saving platform NVS memory\n");
-
- list_for_each_entry(entry, &nvs_list, node)
- if (entry->data) {
- entry->kaddr = ioremap(entry->phys_start, entry->size);
- memcpy(entry->data, entry->kaddr, entry->size);
- }
-}
-
-/**
- * hibernate_nvs_restore - restore NVS memory regions
- *
- * This function is going to be called with interrupts disabled, so it
- * cannot iounmap the virtual addresses used to access the NVS region.
- */
-void hibernate_nvs_restore(void)
-{
- struct nvs_page *entry;
-
- printk(KERN_INFO "PM: Restoring platform NVS memory\n");
-
- list_for_each_entry(entry, &nvs_list, node)
- if (entry->data)
- memcpy(entry->kaddr, entry->data, entry->size);
-}
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ed97375daae..bf0014d6a5f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -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>
diff --git a/kernel/printk.c b/kernel/printk.c
index 5052b5497c6..b4d97b54c1e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -687,20 +687,35 @@ asmlinkage int vprintk(const char *fmt, va_list args)
sizeof(printk_buf) - printed_len, fmt, args);
+ p = printk_buf;
+
+ /* Do we have a loglevel in the string? */
+ if (p[0] == '<') {
+ unsigned char c = p[1];
+ if (c && p[2] == '>') {
+ switch (c) {
+ case '0' ... '7': /* loglevel */
+ current_log_level = c - '0';
+ /* Fallthrough - make sure we're on a new line */
+ case 'd': /* KERN_DEFAULT */
+ if (!new_text_line) {
+ emit_log_char('\n');
+ new_text_line = 1;
+ }
+ /* Fallthrough - skip the loglevel */
+ case 'c': /* KERN_CONT */
+ p += 3;
+ break;
+ }
+ }
+ }
+
/*
* Copy the output into log_buf. If the caller didn't provide
* appropriate log level tags, we insert them here
*/
- for (p = printk_buf; *p; p++) {
+ for ( ; *p; p++) {
if (new_text_line) {
- /* If a token, set current_log_level and skip over */
- if (p[0] == '<' && p[1] >= '0' && p[1] <= '7' &&
- p[2] == '>') {
- current_log_level = p[1] - '0';
- p += 3;
- printed_len -= 3;
- }
-
/* Always output the token */
emit_log_char('<');
emit_log_char(current_log_level + '0');
diff --git a/kernel/profile.c b/kernel/profile.c
index 7724e0409ba..69911b5745e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -111,12 +111,6 @@ int __ref profile_init(void)
/* only text is profiled */
prof_len = (_etext - _stext) >> prof_shift;
buffer_bytes = prof_len*sizeof(atomic_t);
- if (!slab_is_available()) {
- prof_buffer = alloc_bootmem(buffer_bytes);
- alloc_bootmem_cpumask_var(&prof_cpu_mask);
- cpumask_copy(prof_cpu_mask, cpu_possible_mask);
- return 0;
- }
if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
return -ENOMEM;
@@ -371,7 +365,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info,
node = cpu_to_node(cpu);
per_cpu(cpu_profile_flip, cpu) = 0;
if (!per_cpu(cpu_profile_hits, cpu)[1]) {
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -379,7 +373,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info,
per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
}
if (!per_cpu(cpu_profile_hits, cpu)[0]) {
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -570,14 +564,14 @@ static int create_hash_tables(void)
int node = cpu_to_node(cpu);
struct page *page;
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
0);
if (!page)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 2442d140bd9..082c320e4db 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -167,66 +167,82 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
int ptrace_attach(struct task_struct *task)
{
int retval;
- unsigned long flags;
audit_ptrace(task);
retval = -EPERM;
+ if (unlikely(task->flags & PF_KTHREAD))
+ goto out;
if (same_thread_group(task, current))
goto out;
- /* Protect exec's credential calculations against our interference;
- * SUID, SGID and LSM creds get determined differently under ptrace.
+ /*
+ * Protect exec's credential calculations against our interference;
+ * interference; SUID, SGID and LSM creds get determined differently
+ * under ptrace.
*/
- retval = mutex_lock_interruptible(&task->cred_exec_mutex);
- if (retval < 0)
+ retval = -ERESTARTNOINTR;
+ if (mutex_lock_interruptible(&task->cred_guard_mutex))
goto out;
- retval = -EPERM;
-repeat:
- /*
- * Nasty, nasty.
- *
- * We want to hold both the task-lock and the
- * tasklist_lock for writing at the same time.
- * But that's against the rules (tasklist_lock
- * is taken for reading by interrupts on other
- * cpu's that may have task_lock).
- */
task_lock(task);
- if (!write_trylock_irqsave(&tasklist_lock, flags)) {
- task_unlock(task);
- do {
- cpu_relax();
- } while (!write_can_lock(&tasklist_lock));
- goto repeat;
- }
-
- if (!task->mm)
- goto bad;
- /* the same process cannot be attached many times */
- if (task->ptrace & PT_PTRACED)
- goto bad;
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+ task_unlock(task);
if (retval)
- goto bad;
+ goto unlock_creds;
- /* Go */
- task->ptrace |= PT_PTRACED;
+ write_lock_irq(&tasklist_lock);
+ retval = -EPERM;
+ if (unlikely(task->exit_state))
+ goto unlock_tasklist;
+ if (task->ptrace)
+ goto unlock_tasklist;
+
+ task->ptrace = PT_PTRACED;
if (capable(CAP_SYS_PTRACE))
task->ptrace |= PT_PTRACE_CAP;
__ptrace_link(task, current);
-
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
-bad:
- write_unlock_irqrestore(&tasklist_lock, flags);
- task_unlock(task);
- mutex_unlock(&task->cred_exec_mutex);
+
+ retval = 0;
+unlock_tasklist:
+ write_unlock_irq(&tasklist_lock);
+unlock_creds:
+ mutex_unlock(&task->cred_guard_mutex);
out:
return retval;
}
+/**
+ * ptrace_traceme -- helper for PTRACE_TRACEME
+ *
+ * Performs checks and sets PT_PTRACED.
+ * Should be used by all ptrace implementations for PTRACE_TRACEME.
+ */
+int ptrace_traceme(void)
+{
+ int ret = -EPERM;
+
+ write_lock_irq(&tasklist_lock);
+ /* Are we already being traced? */
+ if (!current->ptrace) {
+ ret = security_ptrace_traceme(current->parent);
+ /*
+ * Check PF_EXITING to ensure ->real_parent has not passed
+ * exit_ptrace(). Otherwise we don't report the error but
+ * pretend ->real_parent untraces us right after return.
+ */
+ if (!ret && !(current->real_parent->flags & PF_EXITING)) {
+ current->ptrace = PT_PTRACED;
+ __ptrace_link(current, current->real_parent);
+ }
+ }
+ write_unlock_irq(&tasklist_lock);
+
+ return ret;
+}
+
/*
* Called with irqs disabled, returns true if childs should reap themselves.
*/
@@ -408,37 +424,33 @@ static int ptrace_setoptions(struct task_struct *child, long data)
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
{
+ unsigned long flags;
int error = -ESRCH;
- read_lock(&tasklist_lock);
- if (likely(child->sighand != NULL)) {
+ if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
- spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
*info = *child->last_siginfo;
error = 0;
}
- spin_unlock_irq(&child->sighand->siglock);
+ unlock_task_sighand(child, &flags);
}
- read_unlock(&tasklist_lock);
return error;
}
static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
{
+ unsigned long flags;
int error = -ESRCH;
- read_lock(&tasklist_lock);
- if (likely(child->sighand != NULL)) {
+ if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
- spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
*child->last_siginfo = *info;
error = 0;
}
- spin_unlock_irq(&child->sighand->siglock);
+ unlock_task_sighand(child, &flags);
}
- read_unlock(&tasklist_lock);
return error;
}
@@ -565,72 +577,16 @@ int ptrace_request(struct task_struct *child, long request,
return ret;
}
-/**
- * ptrace_traceme -- helper for PTRACE_TRACEME
- *
- * Performs checks and sets PT_PTRACED.
- * Should be used by all ptrace implementations for PTRACE_TRACEME.
- */
-int ptrace_traceme(void)
-{
- int ret = -EPERM;
-
- /*
- * Are we already being traced?
- */
-repeat:
- task_lock(current);
- if (!(current->ptrace & PT_PTRACED)) {
- /*
- * See ptrace_attach() comments about the locking here.
- */
- unsigned long flags;
- if (!write_trylock_irqsave(&tasklist_lock, flags)) {
- task_unlock(current);
- do {
- cpu_relax();
- } while (!write_can_lock(&tasklist_lock));
- goto repeat;
- }
-
- ret = security_ptrace_traceme(current->parent);
-
- /*
- * Check PF_EXITING to ensure ->real_parent has not passed
- * exit_ptrace(). Otherwise we don't report the error but
- * pretend ->real_parent untraces us right after return.
- */
- if (!ret && !(current->real_parent->flags & PF_EXITING)) {
- current->ptrace |= PT_PTRACED;
- __ptrace_link(current, current->real_parent);
- }
-
- write_unlock_irqrestore(&tasklist_lock, flags);
- }
- task_unlock(current);
- return ret;
-}
-
-/**
- * ptrace_get_task_struct -- grab a task struct reference for ptrace
- * @pid: process id to grab a task_struct reference of
- *
- * This function is a helper for ptrace implementations. It checks
- * permissions and then grabs a task struct for use of the actual
- * ptrace implementation.
- *
- * Returns the task_struct for @pid or an ERR_PTR() on failure.
- */
-struct task_struct *ptrace_get_task_struct(pid_t pid)
+static struct task_struct *ptrace_get_task_struct(pid_t pid)
{
struct task_struct *child;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
child = find_task_by_vpid(pid);
if (child)
get_task_struct(child);
+ rcu_read_unlock();
- read_unlock(&tasklist_lock);
if (!child)
return ERR_PTR(-ESRCH);
return child;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0dccfbba6d2..7717b95c202 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1533,7 +1533,7 @@ void __init __rcu_init(void)
int j;
struct rcu_node *rnp;
- printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+ printk(KERN_INFO "Hierarchical RCU implementation.\n");
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -1546,7 +1546,6 @@ void __init __rcu_init(void)
rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
/* Register notifier for non-boot CPUs */
register_cpu_notifier(&rcu_nb);
- printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
}
module_param(blimit, int, 0);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index bf8e7534c80..e1338f07431 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -18,7 +18,7 @@
void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
- counter->limit = (unsigned long long)LLONG_MAX;
+ counter->limit = RESOURCE_MAX;
counter->parent = parent;
}
@@ -133,6 +133,16 @@ int res_counter_memparse_write_strategy(const char *buf,
unsigned long long *res)
{
char *end;
+
+ /* return RESOURCE_MAX(unlimited) if "-1" is specified */
+ if (*buf == '-') {
+ *res = simple_strtoull(buf + 1, &end, 10);
+ if (*res != 1 || *end != '\0')
+ return -EINVAL;
+ *res = RESOURCE_MAX;
+ return 0;
+ }
+
/* FIXME - make memparse() take const char* args */
*res = memparse((char *)buf, &end);
if (*end != '\0')
diff --git a/kernel/resource.c b/kernel/resource.c
index ac5f3a36923..78b087221c1 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -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)
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 820c5af44f3..fcd107a78c5 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -902,7 +902,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
* Returns:
* 0 on success
* -EINTR when interrupted by a signal
- * -ETIMEOUT when the timeout expired
+ * -ETIMEDOUT when the timeout expired
* -EDEADLK when the lock would deadlock (when deadlock detection is on)
*/
int
diff --git a/kernel/sched.c b/kernel/sched.c
index 5b3f6ec1b0b..01f55ada359 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -69,7 +69,6 @@
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
-#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
@@ -241,7 +240,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
hard = hrtimer_get_expires(&rt_b->rt_period_timer);
delta = ktime_to_ns(ktime_sub(hard, soft));
__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
- HRTIMER_MODE_ABS, 0);
+ HRTIMER_MODE_ABS_PINNED, 0);
}
spin_unlock(&rt_b->rt_runtime_lock);
}
@@ -1156,7 +1155,7 @@ static __init void init_hrtick(void)
static void hrtick_start(struct rq *rq, u64 delay)
{
__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
- HRTIMER_MODE_REL, 0);
+ HRTIMER_MODE_REL_PINNED, 0);
}
static inline void init_hrtick(void)
@@ -1979,7 +1978,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
if (task_hot(p, old_rq->clock, NULL))
schedstat_inc(p, se.nr_forced2_migrations);
#endif
- perf_counter_task_migration(p, new_cpu);
+ perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+ 1, 1, NULL, 0);
}
p->se.vruntime -= old_cfsrq->min_vruntime -
new_cfsrq->min_vruntime;
@@ -2193,6 +2193,7 @@ void kick_process(struct task_struct *p)
smp_send_reschedule(cpu);
preempt_enable();
}
+EXPORT_SYMBOL_GPL(kick_process);
/*
* Return a low guess at the load of a migration-source cpu weighted
@@ -4397,6 +4398,11 @@ static struct {
.load_balancer = ATOMIC_INIT(-1),
};
+int get_nohz_load_balancer(void)
+{
+ return atomic_read(&nohz.load_balancer);
+}
+
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/**
* lowest_flag_domain - Return lowest sched_domain containing flag.
@@ -6535,6 +6541,11 @@ 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
@@ -6554,8 +6565,7 @@ 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;
}
@@ -6573,12 +6583,12 @@ 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();
@@ -6593,7 +6603,7 @@ 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();
@@ -7040,7 +7050,7 @@ static int migration_thread(void *data)
if (cpu_is_offline(cpu)) {
spin_unlock_irq(&rq->lock);
- goto wait_to_die;
+ break;
}
if (rq->active_balance) {
@@ -7066,16 +7076,7 @@ static int migration_thread(void *data)
complete(&req->done);
}
__set_current_state(TASK_RUNNING);
- return 0;
-wait_to_die:
- /* Wait for kthread_stop */
- set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
- schedule();
- set_current_state(TASK_INTERRUPTIBLE);
- }
- __set_current_state(TASK_RUNNING);
return 0;
}
@@ -7489,6 +7490,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
rq = task_rq_lock(p, &flags);
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
task_rq_unlock(rq, &flags);
+ get_task_struct(p);
cpu_rq(cpu)->migration_thread = p;
break;
@@ -7519,6 +7521,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
kthread_bind(cpu_rq(cpu)->migration_thread,
cpumask_any(cpu_online_mask));
kthread_stop(cpu_rq(cpu)->migration_thread);
+ put_task_struct(cpu_rq(cpu)->migration_thread);
cpu_rq(cpu)->migration_thread = NULL;
break;
@@ -7528,6 +7531,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
migrate_live_tasks(cpu);
rq = cpu_rq(cpu);
kthread_stop(rq->migration_thread);
+ put_task_struct(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
spin_lock_irq(&rq->lock);
@@ -7823,26 +7827,23 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
free_rootdomain(old_rd);
}
-static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
+static int init_rootdomain(struct root_domain *rd, bool bootmem)
{
+ gfp_t gfp = GFP_KERNEL;
+
memset(rd, 0, sizeof(*rd));
- if (bootmem) {
- alloc_bootmem_cpumask_var(&def_root_domain.span);
- alloc_bootmem_cpumask_var(&def_root_domain.online);
- alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
- cpupri_init(&rd->cpupri, true);
- return 0;
- }
+ if (bootmem)
+ gfp = GFP_NOWAIT;
- if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->span, gfp))
goto out;
- if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->online, gfp))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->rto_mask, gfp))
goto free_online;
- if (cpupri_init(&rd->cpupri, false) != 0)
+ if (cpupri_init(&rd->cpupri, bootmem) != 0)
goto free_rto_mask;
return 0;
@@ -9032,6 +9033,8 @@ void __init sched_init_smp(void)
}
#endif /* CONFIG_SMP */
+const_debug unsigned int sysctl_timer_migration = 1;
+
int in_sched_functions(unsigned long addr)
{
return in_lock_functions(addr) ||
@@ -9166,7 +9169,7 @@ void __init sched_init(void)
* we use alloc_bootmem().
*/
if (alloc_size) {
- ptr = (unsigned long)alloc_bootmem(alloc_size);
+ ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
init_task_group.se = (struct sched_entity **)ptr;
@@ -9357,13 +9360,13 @@ void __init sched_init(void)
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+ alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_bootmem_cpumask_var(&nohz.cpu_mask);
- alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
+ alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_bootmem_cpumask_var(&cpu_isolated_map);
+ alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
perf_counter_init();
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 344712a5e3e..e6c251790dd 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -152,10 +152,14 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
*
* Returns: -ENOMEM if memory fails.
*/
-int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
+int cpupri_init(struct cpupri *cp, bool bootmem)
{
+ gfp_t gfp = GFP_KERNEL;
int i;
+ if (bootmem)
+ gfp = GFP_NOWAIT;
+
memset(cp, 0, sizeof(*cp));
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
@@ -163,9 +167,7 @@ int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
spin_lock_init(&vec->lock);
vec->count = 0;
- if (bootmem)
- alloc_bootmem_cpumask_var(&vec->mask);
- else if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&vec->mask, gfp))
goto cleanup;
}
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 467ca72f165..70c7e0b7994 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -162,7 +162,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
spread, rq0_min_vruntime, spread0;
- struct rq *rq = &per_cpu(runqueues, cpu);
+ struct rq *rq = cpu_rq(cpu);
struct sched_entity *last;
unsigned long flags;
@@ -191,7 +191,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
if (last)
max_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
- rq0_min_vruntime = per_cpu(runqueues, 0).cfs.min_vruntime;
+ rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
spin_unlock_irqrestore(&rq->lock, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
SPLIT_NS(MIN_vruntime));
@@ -248,7 +248,7 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
static void print_cpu(struct seq_file *m, int cpu)
{
- struct rq *rq = &per_cpu(runqueues, cpu);
+ struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_X86
{
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5f9650e8fe7..ba7fd6e9556 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -430,12 +430,13 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
for_each_sched_entity(se) {
struct load_weight *load;
+ struct load_weight lw;
cfs_rq = cfs_rq_of(se);
load = &cfs_rq->load;
if (unlikely(!se->on_rq)) {
- struct load_weight lw = cfs_rq->load;
+ lw = cfs_rq->load;
update_load_add(&lw, se->load.weight);
load = &lw;
diff --git a/kernel/signal.c b/kernel/signal.c
index dba6ae99978..ccf1ceedaeb 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -247,14 +247,19 @@ void flush_sigqueue(struct sigpending *queue)
/*
* Flush all pending signals for a task.
*/
+void __flush_signals(struct task_struct *t)
+{
+ clear_tsk_thread_flag(t, TIF_SIGPENDING);
+ flush_sigqueue(&t->pending);
+ flush_sigqueue(&t->signal->shared_pending);
+}
+
void flush_signals(struct task_struct *t)
{
unsigned long flags;
spin_lock_irqsave(&t->sighand->siglock, flags);
- clear_tsk_thread_flag(t, TIF_SIGPENDING);
- flush_sigqueue(&t->pending);
- flush_sigqueue(&t->signal->shared_pending);
+ __flush_signals(t);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
}
@@ -827,6 +832,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
{
struct sigpending *pending;
struct sigqueue *q;
+ int override_rlimit;
trace_sched_signal_send(sig, t);
@@ -858,9 +864,13 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
make sure at least one signal gets delivered and don't
pass on the info struct. */
- q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
- (is_si_special(info) ||
- info->si_code >= 0)));
+ if (sig < SIGRTMIN)
+ override_rlimit = (is_si_special(info) || info->si_code >= 0);
+ else
+ override_rlimit = 0;
+
+ q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
+ override_rlimit);
if (q) {
list_add_tail(&q->list, &pending->list);
switch ((unsigned long) info) {
@@ -1400,7 +1410,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
/* do_notify_parent_cldstop should have been called instead. */
BUG_ON(task_is_stopped_or_traced(tsk));
- BUG_ON(!tsk->ptrace &&
+ BUG_ON(!task_ptrace(tsk) &&
(tsk->group_leader != tsk || !thread_group_empty(tsk)));
info.si_signo = sig;
@@ -1439,7 +1449,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
psig = tsk->parent->sighand;
spin_lock_irqsave(&psig->siglock, flags);
- if (!tsk->ptrace && sig == SIGCHLD &&
+ if (!task_ptrace(tsk) && sig == SIGCHLD &&
(psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
(psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
/*
@@ -1476,7 +1486,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
struct task_struct *parent;
struct sighand_struct *sighand;
- if (tsk->ptrace & PT_PTRACED)
+ if (task_ptrace(tsk))
parent = tsk->parent;
else {
tsk = tsk->group_leader;
@@ -1489,7 +1499,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
* see comment in do_notify_parent() abot the following 3 lines
*/
rcu_read_lock();
- info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+ info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
info.si_uid = __task_cred(tsk)->uid;
rcu_read_unlock();
@@ -1525,7 +1535,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
static inline int may_ptrace_stop(void)
{
- if (!likely(current->ptrace & PT_PTRACED))
+ if (!likely(task_ptrace(current)))
return 0;
/*
* Are we in the middle of do_coredump?
@@ -1743,7 +1753,7 @@ static int do_signal_stop(int signr)
static int ptrace_signal(int signr, siginfo_t *info,
struct pt_regs *regs, void *cookie)
{
- if (!(current->ptrace & PT_PTRACED))
+ if (!task_ptrace(current))
return signr;
ptrace_signal_deliver(regs, cookie);
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index b28d19135f4..09d7519557d 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -319,6 +319,15 @@ cant_get_ref:
EXPORT_SYMBOL(slow_work_enqueue);
/*
+ * Schedule a cull of the thread pool at some time in the near future
+ */
+static void slow_work_schedule_cull(void)
+{
+ mod_timer(&slow_work_cull_timer,
+ round_jiffies(jiffies + SLOW_WORK_CULL_TIMEOUT));
+}
+
+/*
* Worker thread culling algorithm
*/
static bool slow_work_cull_thread(void)
@@ -335,8 +344,7 @@ static bool slow_work_cull_thread(void)
list_empty(&vslow_work_queue) &&
atomic_read(&slow_work_thread_count) >
slow_work_min_threads) {
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
do_cull = true;
}
}
@@ -372,8 +380,8 @@ static int slow_work_thread(void *_data)
vsmax *= atomic_read(&slow_work_thread_count);
vsmax /= 100;
- prepare_to_wait(&slow_work_thread_wq, &wait,
- TASK_INTERRUPTIBLE);
+ prepare_to_wait_exclusive(&slow_work_thread_wq, &wait,
+ TASK_INTERRUPTIBLE);
if (!freezing(current) &&
!slow_work_threads_should_exit &&
!slow_work_available(vsmax) &&
@@ -393,8 +401,7 @@ static int slow_work_thread(void *_data)
list_empty(&vslow_work_queue) &&
atomic_read(&slow_work_thread_count) >
slow_work_min_threads)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
continue;
}
@@ -458,7 +465,7 @@ static void slow_work_new_thread_execute(struct slow_work *work)
if (atomic_dec_and_test(&slow_work_thread_count))
BUG(); /* we're running on a slow work thread... */
mod_timer(&slow_work_oom_timer,
- jiffies + SLOW_WORK_OOM_TIMEOUT);
+ round_jiffies(jiffies + SLOW_WORK_OOM_TIMEOUT));
} else {
/* ratelimit the starting of new threads */
mod_timer(&slow_work_oom_timer, jiffies + 1);
@@ -502,8 +509,7 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
if (n < 0 && !slow_work_may_not_start_new_thread)
slow_work_enqueue(&slow_work_new_thread);
else if (n > 0)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
}
mutex_unlock(&slow_work_user_lock);
}
@@ -529,8 +535,7 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
atomic_read(&slow_work_thread_count);
if (n < 0)
- mod_timer(&slow_work_cull_timer,
- jiffies + SLOW_WORK_CULL_TIMEOUT);
+ slow_work_schedule_cull();
}
mutex_unlock(&slow_work_user_lock);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 258885a543d..3a94905fa5d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -213,6 +213,7 @@ restart:
do {
if (pending & 1) {
int prev_count = preempt_count();
+ kstat_incr_softirqs_this_cpu(h - softirq_vec);
trace_softirq_entry(h, softirq_vec);
h->action(h);
@@ -382,6 +383,17 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
EXPORT_SYMBOL(__tasklet_hi_schedule);
+void __tasklet_hi_schedule_first(struct tasklet_struct *t)
+{
+ BUG_ON(!irqs_disabled());
+
+ t->next = __get_cpu_var(tasklet_hi_vec).head;
+ __get_cpu_var(tasklet_hi_vec).head = t;
+ __raise_softirq_irqoff(HI_SOFTIRQ);
+}
+
+EXPORT_SYMBOL(__tasklet_hi_schedule_first);
+
static void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
diff --git a/kernel/sys.c b/kernel/sys.c
index 438d99a38c8..b3f1097c76f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1113,289 +1113,6 @@ out:
return err;
}
-/*
- * Supplementary group IDs
- */
-
-/* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
-
-struct group_info *groups_alloc(int gidsetsize)
-{
- struct group_info *group_info;
- int nblocks;
- int i;
-
- nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
- /* Make sure we always allocate at least one indirect block pointer */
- nblocks = nblocks ? : 1;
- group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
- if (!group_info)
- return NULL;
- group_info->ngroups = gidsetsize;
- group_info->nblocks = nblocks;
- atomic_set(&group_info->usage, 1);
-
- if (gidsetsize <= NGROUPS_SMALL)
- group_info->blocks[0] = group_info->small_block;
- else {
- for (i = 0; i < nblocks; i++) {
- gid_t *b;
- b = (void *)__get_free_page(GFP_USER);
- if (!b)
- goto out_undo_partial_alloc;
- group_info->blocks[i] = b;
- }
- }
- return group_info;
-
-out_undo_partial_alloc:
- while (--i >= 0) {
- free_page((unsigned long)group_info->blocks[i]);
- }
- kfree(group_info);
- return NULL;
-}
-
-EXPORT_SYMBOL(groups_alloc);
-
-void groups_free(struct group_info *group_info)
-{
- if (group_info->blocks[0] != group_info->small_block) {
- int i;
- for (i = 0; i < group_info->nblocks; i++)
- free_page((unsigned long)group_info->blocks[i]);
- }
- kfree(group_info);
-}
-
-EXPORT_SYMBOL(groups_free);
-
-/* export the group_info to a user-space array */
-static int groups_to_user(gid_t __user *grouplist,
- const struct group_info *group_info)
-{
- int i;
- unsigned int count = group_info->ngroups;
-
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_to_user(grouplist, group_info->blocks[i], len))
- return -EFAULT;
-
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
- }
- return 0;
-}
-
-/* fill a group_info from a user-space array - it must be allocated already */
-static int groups_from_user(struct group_info *group_info,
- gid_t __user *grouplist)
-{
- int i;
- unsigned int count = group_info->ngroups;
-
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_from_user(group_info->blocks[i], grouplist, len))
- return -EFAULT;
-
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
- }
- return 0;
-}
-
-/* a simple Shell sort */
-static void groups_sort(struct group_info *group_info)
-{
- int base, max, stride;
- int gidsetsize = group_info->ngroups;
-
- for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
- ; /* nothing */
- stride /= 3;
-
- while (stride) {
- max = gidsetsize - stride;
- for (base = 0; base < max; base++) {
- int left = base;
- int right = left + stride;
- gid_t tmp = GROUP_AT(group_info, right);
-
- while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
- GROUP_AT(group_info, right) =
- GROUP_AT(group_info, left);
- right = left;
- left -= stride;
- }
- GROUP_AT(group_info, right) = tmp;
- }
- stride /= 3;
- }
-}
-
-/* a simple bsearch */
-int groups_search(const struct group_info *group_info, gid_t grp)
-{
- unsigned int left, right;
-
- if (!group_info)
- return 0;
-
- left = 0;
- right = group_info->ngroups;
- while (left < right) {
- unsigned int mid = (left+right)/2;
- int cmp = grp - GROUP_AT(group_info, mid);
- if (cmp > 0)
- left = mid + 1;
- else if (cmp < 0)
- right = mid;
- else
- return 1;
- }
- return 0;
-}
-
-/**
- * set_groups - Change a group subscription in a set of credentials
- * @new: The newly prepared set of credentials to alter
- * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
- */
-int set_groups(struct cred *new, struct group_info *group_info)
-{
- int retval;
-
- retval = security_task_setgroups(group_info);
- if (retval)
- return retval;
-
- put_group_info(new->group_info);
- groups_sort(group_info);
- get_group_info(group_info);
- new->group_info = group_info;
- return 0;
-}
-
-EXPORT_SYMBOL(set_groups);
-
-/**
- * set_current_groups - Change current's group subscription
- * @group_info: The group list to impose
- *
- * Validate a group subscription and, if valid, impose it upon current's task
- * security record.
- */
-int set_current_groups(struct group_info *group_info)
-{
- struct cred *new;
- int ret;
-
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
-
- ret = set_groups(new, group_info);
- if (ret < 0) {
- abort_creds(new);
- return ret;
- }
-
- return commit_creds(new);
-}
-
-EXPORT_SYMBOL(set_current_groups);
-
-SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
-{
- const struct cred *cred = current_cred();
- int i;
-
- if (gidsetsize < 0)
- return -EINVAL;
-
- /* no need to grab task_lock here; it cannot change */
- i = cred->group_info->ngroups;
- if (gidsetsize) {
- if (i > gidsetsize) {
- i = -EINVAL;
- goto out;
- }
- if (groups_to_user(grouplist, cred->group_info)) {
- i = -EFAULT;
- goto out;
- }
- }
-out:
- return i;
-}
-
-/*
- * SMP: Our groups are copy-on-write. We can set them safely
- * without another task interfering.
- */
-
-SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
-{
- struct group_info *group_info;
- int retval;
-
- if (!capable(CAP_SETGID))
- return -EPERM;
- if ((unsigned)gidsetsize > NGROUPS_MAX)
- return -EINVAL;
-
- group_info = groups_alloc(gidsetsize);
- if (!group_info)
- return -ENOMEM;
- retval = groups_from_user(group_info, grouplist);
- if (retval) {
- put_group_info(group_info);
- return retval;
- }
-
- retval = set_current_groups(group_info);
- put_group_info(group_info);
-
- return retval;
-}
-
-/*
- * Check whether we're fsgid/egid or in the supplemental group..
- */
-int in_group_p(gid_t grp)
-{
- const struct cred *cred = current_cred();
- int retval = 1;
-
- if (grp != cred->fsgid)
- retval = groups_search(cred->group_info, grp);
- return retval;
-}
-
-EXPORT_SYMBOL(in_group_p);
-
-int in_egroup_p(gid_t grp)
-{
- const struct cred *cred = current_cred();
- int retval = 1;
-
- if (grp != cred->egid)
- retval = groups_search(cred->group_info, grp);
- return retval;
-}
-
-EXPORT_SYMBOL(in_egroup_p);
-
DECLARE_RWSEM(uts_sem);
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a7e4eb0525b..98e02328c67 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -27,6 +27,7 @@
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/utsname.h>
+#include <linux/kmemcheck.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/init.h>
@@ -115,6 +116,7 @@ static int ngroups_max = NGROUPS_MAX;
#ifdef CONFIG_MODULES
extern char modprobe_path[];
+extern int modules_disabled;
#endif
#ifdef CONFIG_CHR_DEV_SG
extern int sg_big_buff;
@@ -327,6 +329,17 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "timer_migration",
+ .data = &sysctl_timer_migration,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#endif
{
.ctl_name = CTL_UNNUMBERED,
@@ -535,6 +548,17 @@ static struct ctl_table kern_table[] = {
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "modules_disabled",
+ .data = &modules_disabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ /* only handle a transition from default "0" to "1" */
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &one,
+ },
#endif
#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
{
@@ -723,6 +747,14 @@ static struct ctl_table kern_table[] = {
.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",
.data = &bootloader_type,
@@ -947,6 +979,17 @@ static struct ctl_table kern_table[] = {
.proc_handler = &proc_dointvec,
},
#endif
+#ifdef CONFIG_KMEMCHECK
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "kmemcheck",
+ .data = &kmemcheck_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
+
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
@@ -1260,7 +1303,6 @@ static struct ctl_table vm_table[] = {
.strategy = &sysctl_jiffies,
},
#endif
-#ifdef CONFIG_SECURITY
{
.ctl_name = CTL_UNNUMBERED,
.procname = "mmap_min_addr",
@@ -1269,7 +1311,6 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &proc_doulongvec_minmax,
},
-#endif
#ifdef CONFIG_NUMA
{
.ctl_name = CTL_UNNUMBERED,
@@ -1307,7 +1348,6 @@ static struct ctl_table vm_table[] = {
.extra2 = &one,
},
#endif
-#ifdef CONFIG_UNEVICTABLE_LRU
{
.ctl_name = CTL_UNNUMBERED,
.procname = "scan_unevictable_pages",
@@ -1316,7 +1356,6 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &scan_unevictable_handler,
},
-#endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
@@ -2255,7 +2294,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
void *data)
{
#define TMPBUFLEN 21
- int *i, vleft, first=1, neg, val;
+ int *i, vleft, first = 1, neg;
unsigned long lval;
size_t left, len;
@@ -2308,8 +2347,6 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
len = p-buf;
if ((len < left) && *p && !isspace(*p))
break;
- if (neg)
- val = -val;
s += len;
left -= len;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index d13be216a79..1ad6dd46111 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -18,6 +18,7 @@
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysdev.h>
+#include <linux/tick.h>
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
@@ -54,6 +55,7 @@ unsigned long clockevent_delta2ns(unsigned long latch,
return (unsigned long) clc;
}
+EXPORT_SYMBOL_GPL(clockevent_delta2ns);
/**
* clockevents_set_mode - set the operating mode of a clock event device
@@ -187,6 +189,7 @@ void clockevents_register_device(struct clock_event_device *dev)
spin_unlock(&clockevents_lock);
}
+EXPORT_SYMBOL_GPL(clockevents_register_device);
/*
* Noop handler when we shut down an event device
@@ -251,4 +254,15 @@ 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
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index ecfd7b5187e..592bf584d1d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -402,9 +402,6 @@ int clocksource_register(struct clocksource *c)
unsigned long flags;
int ret;
- /* save mult_orig on registration */
- c->mult_orig = c->mult;
-
spin_lock_irqsave(&clocksource_lock, flags);
ret = clocksource_enqueue(c);
if (!ret)
@@ -512,6 +509,18 @@ 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() &&
+ !(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);
+ ovr = NULL;
+ override_name[0] = 0;
+ }
+
/* Reselect, when the override name has changed */
if (ovr != clocksource_override) {
clocksource_override = ovr;
@@ -540,7 +549,13 @@ sysfs_show_available_clocksources(struct sys_device *dev,
spin_lock_irq(&clocksource_lock);
list_for_each_entry(src, &clocksource_list, list) {
- count += snprintf(buf + count,
+ /*
+ * Don't show non-HRES clocksource if the tick code is
+ * in one shot mode (highres=on or nohz=on)
+ */
+ if (!tick_oneshot_mode_active() ||
+ (src->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+ count += snprintf(buf + count,
max((ssize_t)PAGE_SIZE - count, (ssize_t)0),
"%s ", src->name);
}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 118a3b3b3f9..877dbedc311 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -27,7 +27,7 @@
* timer stops in C3 state.
*/
-struct tick_device tick_broadcast_device;
+static struct tick_device tick_broadcast_device;
/* FIXME: Use cpumask_var_t. */
static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
static DECLARE_BITMAP(tmpmask, NR_CPUS);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 2e8de678e76..a96c0e2b89c 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -128,6 +128,23 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
return 0;
}
+/**
+ * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ *
+ * returns 1 when either nohz or highres are enabled. otherwise 0.
+ */
+int tick_oneshot_mode_active(void)
+{
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+ ret = __get_cpu_var(tick_cpu_device).mode == TICKDEV_MODE_ONESHOT;
+ local_irq_restore(flags);
+
+ return ret;
+}
+
#ifdef CONFIG_HIGH_RES_TIMERS
/**
* tick_init_highres - switch to high resolution mode
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index d3f1ef4d5cb..e0f59a21c06 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -222,6 +222,15 @@ void tick_nohz_stop_sched_tick(int inidle)
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
+
+ /*
+ * Call to tick_nohz_start_idle stops the last_update_time from being
+ * updated. Thus, it must not be called in the event we are called from
+ * irq_exit() with the prior state different than idle.
+ */
+ if (!inidle && !ts->inidle)
+ goto end;
+
now = tick_nohz_start_idle(ts);
/*
@@ -239,9 +248,6 @@ void tick_nohz_stop_sched_tick(int inidle)
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
- if (!inidle && !ts->inidle)
- goto end;
-
ts->inidle = 1;
if (need_resched())
@@ -349,7 +355,7 @@ void tick_nohz_stop_sched_tick(int inidle)
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
- HRTIMER_MODE_ABS);
+ HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
goto out;
@@ -395,7 +401,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start_expires(&ts->sched_timer,
- HRTIMER_MODE_ABS);
+ HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
break;
@@ -698,7 +704,8 @@ void tick_setup_sched_timer(void)
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
- hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS);
+ hrtimer_start_expires(&ts->sched_timer,
+ HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
break;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 52a8bf8931f..e8c77d9c633 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -77,6 +77,10 @@ static void clocksource_forward_now(void)
clock->cycle_last = cycle_now;
nsec = cyc2ns(clock, cycle_delta);
+
+ /* If arch requires, add in gettimeoffset() */
+ nsec += arch_gettimeoffset();
+
timespec_add_ns(&xtime, nsec);
nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
@@ -111,6 +115,9 @@ void getnstimeofday(struct timespec *ts)
/* convert to nanoseconds: */
nsecs = cyc2ns(clock, cycle_delta);
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
+
} while (read_seqretry(&xtime_lock, seq));
timespec_add_ns(ts, nsecs);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index c994530d166..4cde8b9c716 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -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:
diff --git a/kernel/timer.c b/kernel/timer.c
index c01e568935e..0b36b9e5cc8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -38,6 +38,7 @@
#include <linux/tick.h>
#include <linux/kallsyms.h>
#include <linux/perf_counter.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -379,6 +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;
@@ -605,13 +608,12 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
}
static inline int
-__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
+__mod_timer(struct timer_list *timer, unsigned long expires,
+ bool pending_only, int pinned)
{
struct tvec_base *base, *new_base;
unsigned long flags;
- int ret;
-
- ret = 0;
+ int ret = 0 , cpu;
timer_stats_timer_set_start_info(timer);
BUG_ON(!timer->function);
@@ -630,6 +632,18 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
new_base = __get_cpu_var(tvec_bases);
+ cpu = smp_processor_id();
+
+#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
+ if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
+ int preferred_cpu = get_nohz_load_balancer();
+
+ if (preferred_cpu >= 0)
+ cpu = preferred_cpu;
+ }
+#endif
+ new_base = per_cpu(tvec_bases, cpu);
+
if (base != new_base) {
/*
* We are trying to schedule the timer on the local CPU.
@@ -669,7 +683,7 @@ out_unlock:
*/
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
{
- return __mod_timer(timer, expires, true);
+ return __mod_timer(timer, expires, true, TIMER_NOT_PINNED);
}
EXPORT_SYMBOL(mod_timer_pending);
@@ -703,11 +717,33 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
if (timer->expires == expires && timer_pending(timer))
return 1;
- return __mod_timer(timer, expires, false);
+ return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
}
EXPORT_SYMBOL(mod_timer);
/**
+ * mod_timer_pinned - modify a timer's timeout
+ * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer_pinned() is a way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ * and not allow the timer to be migrated to a different CPU.
+ *
+ * mod_timer_pinned(timer, expires) is equivalent to:
+ *
+ * del_timer(timer); timer->expires = expires; add_timer(timer);
+ */
+int mod_timer_pinned(struct timer_list *timer, unsigned long expires)
+{
+ if (timer->expires == expires && timer_pending(timer))
+ return 1;
+
+ return __mod_timer(timer, expires, false, TIMER_PINNED);
+}
+EXPORT_SYMBOL(mod_timer_pinned);
+
+/**
* add_timer - start a timer
* @timer: the timer to be added
*
@@ -757,6 +793,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
wake_up_idle_cpu(cpu);
spin_unlock_irqrestore(&base->lock, flags);
}
+EXPORT_SYMBOL_GPL(add_timer_on);
/**
* del_timer - deactive a timer.
@@ -1016,6 +1053,9 @@ cascade:
index = slot = timer_jiffies & TVN_MASK;
do {
list_for_each_entry(nte, varp->vec + slot, entry) {
+ if (tbase_get_deferrable(nte->base))
+ continue;
+
found = 1;
if (time_before(nte->expires, expires))
expires = nte->expires;
@@ -1306,7 +1346,7 @@ signed long __sched schedule_timeout(signed long timeout)
expire = timeout + jiffies;
setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
- __mod_timer(&timer, expire, false);
+ __mod_timer(&timer, expire, false, TIMER_NOT_PINNED);
schedule();
del_singleshot_timer_sync(&timer);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 4a13e5a01ce..019f380fd76 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -18,6 +18,13 @@ config HAVE_FUNCTION_TRACER
config HAVE_FUNCTION_GRAPH_TRACER
bool
+config HAVE_FUNCTION_GRAPH_FP_TEST
+ bool
+ help
+ An arch may pass in a unique value (frame pointer) to both the
+ entering and exiting of a function. On exit, the value is compared
+ and if it does not match, then it will panic the kernel.
+
config HAVE_FUNCTION_TRACE_MCOUNT_TEST
bool
help
@@ -121,6 +128,7 @@ config FUNCTION_GRAPH_TRACER
bool "Kernel Function Graph Tracer"
depends on HAVE_FUNCTION_GRAPH_TRACER
depends on FUNCTION_TRACER
+ depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
default y
help
Enable the kernel to trace a function at both its return
@@ -147,7 +155,7 @@ config IRQSOFF_TRACER
disabled by default and can be runtime (re-)started
via:
- echo 0 > /debugfs/tracing/tracing_max_latency
+ echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
(Note that kernel size and overhead increases with this option
enabled. This option and the preempt-off timing option can be
@@ -168,7 +176,7 @@ config PREEMPT_TRACER
disabled by default and can be runtime (re-)started
via:
- echo 0 > /debugfs/tracing/tracing_max_latency
+ echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
(Note that kernel size and overhead increases with this option
enabled. This option and the irqs-off timing option can be
@@ -218,13 +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
@@ -261,7 +269,7 @@ config PROFILE_ANNOTATED_BRANCHES
This tracer profiles all the the likely and unlikely macros
in the kernel. It will display the results in:
- /debugfs/tracing/profile_annotated_branch
+ /sys/kernel/debug/tracing/profile_annotated_branch
Note: this will add a significant overhead, only turn this
on if you need to profile the system's use of these macros.
@@ -274,7 +282,7 @@ config PROFILE_ALL_BRANCHES
taken in the kernel is recorded whether it hit or miss.
The results will be displayed in:
- /debugfs/tracing/profile_branch
+ /sys/kernel/debug/tracing/profile_branch
This option also enables the likely/unlikely profiler.
@@ -323,7 +331,7 @@ config STACK_TRACER
select KALLSYMS
help
This special tracer records the maximum stack footprint of the
- kernel and displays it in debugfs/tracing/stack_trace.
+ kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
This tracer works by hooking into every function call that the
kernel executes, and keeping a maximum stack depth value and
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7bd6a9893c2..1090b0aed9b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -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>
@@ -669,12 +670,12 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
if (blk_pc_request(rq)) {
what |= BLK_TC_ACT(BLK_TC_PC);
- __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
- rq->cmd_len, rq->cmd);
+ __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
+ what, rq->errors, rq->cmd_len, rq->cmd);
} else {
what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
- rw, what, rq->errors, 0, NULL);
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rw,
+ what, rq->errors, 0, NULL);
}
}
@@ -881,11 +882,11 @@ void blk_add_driver_data(struct request_queue *q,
return;
if (blk_pc_request(rq))
- __blk_add_trace(bt, 0, rq->data_len, 0, BLK_TA_DRV_DATA,
- rq->errors, len, data);
+ __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
+ BLK_TA_DRV_DATA, rq->errors, len, data);
else
- __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
- 0, BLK_TA_DRV_DATA, rq->errors, len, data);
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
+ BLK_TA_DRV_DATA, rq->errors, len, data);
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1724,10 +1725,7 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
if (blk_discard_rq(rq))
rw |= (1 << BIO_RW_DISCARD);
- if (blk_pc_request(rq))
- bytes = rq->data_len;
- else
- bytes = rq->hard_nr_sectors << 9;
+ bytes = blk_rq_bytes(rq);
blk_fill_rwbs(rwbs, rw, bytes);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bb60732ade0..bce9e01a29c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -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)
@@ -1224,6 +1226,13 @@ static void ftrace_shutdown(int command)
return;
ftrace_start_up--;
+ /*
+ * Just warn in case of unbalance, no need to kill ftrace, it's not
+ * critical but the ftrace_call callers may be never nopped again after
+ * further ftrace uses.
+ */
+ WARN_ON_ONCE(ftrace_start_up < 0);
+
if (!ftrace_start_up)
command |= FTRACE_DISABLE_CALLS;
@@ -1410,10 +1419,20 @@ 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)
@@ -1460,8 +1479,6 @@ 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++];
@@ -1490,6 +1507,7 @@ 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);
/*
@@ -1501,23 +1519,21 @@ 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;
@@ -2493,32 +2509,31 @@ 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)
@@ -3145,10 +3160,10 @@ 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) {
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 86cdf671d7e..1edaa9516e8 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -186,7 +186,7 @@ static int kmem_trace_init(struct trace_array *tr)
int cpu;
kmemtrace_array = tr;
- for_each_cpu_mask(cpu, cpu_possible_map)
+ for_each_cpu(cpu, cpu_possible_mask)
tracing_reset(tr, cpu);
kmemtrace_start_probes();
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2e642b2b725..bf27bb7a63e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -10,6 +10,7 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
+#include <linux/kmemcheck.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
@@ -205,6 +206,7 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
#define RB_ALIGNMENT 4U
#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */
/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
@@ -414,6 +416,8 @@ struct ring_buffer_per_cpu {
unsigned long overrun;
unsigned long read;
local_t entries;
+ local_t committing;
+ local_t commits;
u64 write_stamp;
u64 read_stamp;
atomic_t record_disabled;
@@ -617,12 +621,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
kfree(cpu_buffer);
}
-/*
- * Causes compile errors if the struct buffer_page gets bigger
- * than the struct page.
- */
-extern int ring_buffer_page_too_big(void);
-
#ifdef CONFIG_HOTPLUG_CPU
static int rb_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu);
@@ -645,11 +643,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
int bsize;
int cpu;
- /* Paranoid! Optimizes out when all is well */
- if (sizeof(struct buffer_page) > sizeof(struct page))
- ring_buffer_page_too_big();
-
-
/* keep it in its own cache line */
buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
GFP_KERNEL);
@@ -665,8 +658,8 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
buffer->reader_lock_key = key;
/* need at least two pages */
- if (buffer->pages == 1)
- buffer->pages++;
+ if (buffer->pages < 2)
+ buffer->pages = 2;
/*
* In case of non-hotplug cpu, if the ring-buffer is allocated
@@ -1010,12 +1003,12 @@ rb_event_index(struct ring_buffer_event *event)
{
unsigned long addr = (unsigned long)event;
- return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
+ return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
}
static inline int
-rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
- struct ring_buffer_event *event)
+rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
{
unsigned long addr = (unsigned long)event;
unsigned long index;
@@ -1028,31 +1021,6 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
}
static void
-rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
- struct ring_buffer_event *event)
-{
- unsigned long addr = (unsigned long)event;
- unsigned long index;
-
- index = rb_event_index(event);
- addr &= PAGE_MASK;
-
- while (cpu_buffer->commit_page->page != (void *)addr) {
- if (RB_WARN_ON(cpu_buffer,
- cpu_buffer->commit_page == cpu_buffer->tail_page))
- return;
- cpu_buffer->commit_page->page->commit =
- cpu_buffer->commit_page->write;
- rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
- cpu_buffer->write_stamp =
- cpu_buffer->commit_page->page->time_stamp;
- }
-
- /* Now set the commit to the event's index */
- local_set(&cpu_buffer->commit_page->page->commit, index);
-}
-
-static void
rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
/*
@@ -1170,6 +1138,60 @@ static unsigned rb_calculate_event_length(unsigned length)
return length;
}
+static inline void
+rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *tail_page,
+ unsigned long tail, unsigned long length)
+{
+ struct ring_buffer_event *event;
+
+ /*
+ * Only the event that crossed the page boundary
+ * must fill the old tail_page with padding.
+ */
+ if (tail >= BUF_PAGE_SIZE) {
+ local_sub(length, &tail_page->write);
+ return;
+ }
+
+ event = __rb_page_index(tail_page, tail);
+ kmemcheck_annotate_bitfield(event, bitfield);
+
+ /*
+ * If this event is bigger than the minimum size, then
+ * we need to be careful that we don't subtract the
+ * write counter enough to allow another writer to slip
+ * in on this page.
+ * We put in a discarded commit instead, to make sure
+ * that this space is not used again.
+ *
+ * If we are less than the minimum size, we don't need to
+ * worry about it.
+ */
+ if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+ /* No room for any events */
+
+ /* Mark the rest of the page with padding */
+ rb_event_set_padding(event);
+
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
+ return;
+ }
+
+ /* Put in a discarded event */
+ event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ event->time_delta = 1;
+ /* Account for this as an entry */
+ local_inc(&tail_page->entries);
+ local_inc(&cpu_buffer->entries);
+
+ /* Set write to end of buffer */
+ length = (tail + length) - BUF_PAGE_SIZE;
+ local_sub(length, &tail_page->write);
+}
static struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1179,7 +1201,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
{
struct buffer_page *next_page, *head_page, *reader_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
- struct ring_buffer_event *event;
bool lock_taken = false;
unsigned long flags;
@@ -1264,26 +1285,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
cpu_buffer->tail_page->page->time_stamp = *ts;
}
- /*
- * The actual tail page has moved forward.
- */
- if (tail < BUF_PAGE_SIZE) {
- /* Mark the rest of the page with padding */
- event = __rb_page_index(tail_page, tail);
- rb_event_set_padding(event);
- }
-
- /* Set the write back to the previous setting */
- local_sub(length, &tail_page->write);
-
- /*
- * If this was a commit entry that failed,
- * increment that too
- */
- if (tail_page == cpu_buffer->commit_page &&
- tail == rb_commit_index(cpu_buffer)) {
- rb_set_commit_to_write(cpu_buffer);
- }
+ rb_reset_tail(cpu_buffer, tail_page, tail, length);
__raw_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);
@@ -1293,7 +1295,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
out_reset:
/* reset write */
- local_sub(length, &tail_page->write);
+ rb_reset_tail(cpu_buffer, tail_page, tail, length);
if (likely(lock_taken))
__raw_spin_unlock(&cpu_buffer->lock);
@@ -1323,10 +1325,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* We reserved something on the buffer */
- if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
- return NULL;
-
event = __rb_page_index(tail_page, tail);
+ kmemcheck_annotate_bitfield(event, bitfield);
rb_update_event(event, type, length);
/* The passed in type is zero for DATA */
@@ -1334,11 +1334,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
local_inc(&tail_page->entries);
/*
- * If this is a commit and the tail is zero, then update
- * this page's time stamp.
+ * If this is the first commit on the page, then update
+ * its timestamp.
*/
- if (!tail && rb_is_commit(cpu_buffer, event))
- cpu_buffer->commit_page->page->time_stamp = *ts;
+ if (!tail)
+ tail_page->page->time_stamp = *ts;
return event;
}
@@ -1407,16 +1407,16 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
return -EAGAIN;
/* Only a commited time event can update the write stamp */
- if (rb_is_commit(cpu_buffer, event)) {
+ if (rb_event_is_commit(cpu_buffer, event)) {
/*
- * If this is the first on the page, then we need to
- * update the page itself, and just put in a zero.
+ * If this is the first on the page, then it was
+ * updated with the page itself. Try to discard it
+ * and if we can't just make it zero.
*/
if (rb_event_index(event)) {
event->time_delta = *delta & TS_MASK;
event->array[0] = *delta >> TS_SHIFT;
} else {
- cpu_buffer->commit_page->page->time_stamp = *ts;
/* try to discard, since we do not need this */
if (!rb_try_to_discard(cpu_buffer, event)) {
/* nope, just zero it */
@@ -1442,6 +1442,44 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
return ret;
}
+static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ local_inc(&cpu_buffer->committing);
+ local_inc(&cpu_buffer->commits);
+}
+
+static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ unsigned long commits;
+
+ if (RB_WARN_ON(cpu_buffer,
+ !local_read(&cpu_buffer->committing)))
+ return;
+
+ again:
+ commits = local_read(&cpu_buffer->commits);
+ /* synchronize with interrupts */
+ barrier();
+ if (local_read(&cpu_buffer->committing) == 1)
+ rb_set_commit_to_write(cpu_buffer);
+
+ local_dec(&cpu_buffer->committing);
+
+ /* synchronize with interrupts */
+ barrier();
+
+ /*
+ * Need to account for interrupts coming in between the
+ * updating of the commit page and the clearing of the
+ * committing counter.
+ */
+ if (unlikely(local_read(&cpu_buffer->commits) != commits) &&
+ !local_read(&cpu_buffer->committing)) {
+ local_inc(&cpu_buffer->committing);
+ goto again;
+ }
+}
+
static struct ring_buffer_event *
rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long length)
@@ -1451,6 +1489,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
int commit = 0;
int nr_loops = 0;
+ rb_start_commit(cpu_buffer);
+
length = rb_calculate_event_length(length);
again:
/*
@@ -1463,7 +1503,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
* Bail!
*/
if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
- return NULL;
+ goto out_fail;
ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
@@ -1494,7 +1534,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
if (commit == -EBUSY)
- return NULL;
+ goto out_fail;
if (commit == -EAGAIN)
goto again;
@@ -1508,30 +1548,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
if (unlikely(PTR_ERR(event) == -EAGAIN))
goto again;
- if (!event) {
- if (unlikely(commit))
- /*
- * Ouch! We needed a timestamp and it was commited. But
- * we didn't get our event reserved.
- */
- rb_set_commit_to_write(cpu_buffer);
- return NULL;
- }
+ if (!event)
+ goto out_fail;
- /*
- * If the timestamp was commited, make the commit our entry
- * now so that we will update it when needed.
- */
- if (unlikely(commit))
- rb_set_commit_event(cpu_buffer, event);
- else if (!rb_is_commit(cpu_buffer, event))
+ if (!rb_event_is_commit(cpu_buffer, event))
delta = 0;
event->time_delta = delta;
return event;
+
+ out_fail:
+ rb_end_commit(cpu_buffer);
+ return NULL;
}
+#ifdef CONFIG_TRACING
+
#define TRACE_RECURSIVE_DEPTH 16
static int trace_recursive_lock(void)
@@ -1562,6 +1595,13 @@ 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);
/**
@@ -1639,13 +1679,14 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
{
local_inc(&cpu_buffer->entries);
- /* Only process further if we own the commit */
- if (!rb_is_commit(cpu_buffer, event))
- return;
-
- cpu_buffer->write_stamp += event->time_delta;
+ /*
+ * The event first in the commit queue updates the
+ * time stamp.
+ */
+ if (rb_event_is_commit(cpu_buffer, event))
+ cpu_buffer->write_stamp += event->time_delta;
- rb_set_commit_to_write(cpu_buffer);
+ rb_end_commit(cpu_buffer);
}
/**
@@ -1734,15 +1775,15 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
/* The event is discarded regardless */
rb_event_discard(event);
+ cpu = smp_processor_id();
+ cpu_buffer = buffer->buffers[cpu];
+
/*
* This must only be called if the event has not been
* committed yet. Thus we can assume that preemption
* is still disabled.
*/
- RB_WARN_ON(buffer, preemptible());
-
- cpu = smp_processor_id();
- cpu_buffer = buffer->buffers[cpu];
+ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
if (!rb_try_to_discard(cpu_buffer, event))
goto out;
@@ -1753,13 +1794,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
*/
local_inc(&cpu_buffer->entries);
out:
- /*
- * If a write came in and pushed the tail page
- * we still need to update the commit pointer
- * if we were the commit.
- */
- if (rb_is_commit(cpu_buffer, event))
- rb_set_commit_to_write(cpu_buffer);
+ rb_end_commit(cpu_buffer);
trace_recursive_unlock();
@@ -2443,6 +2478,21 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
+static inline int rb_ok_to_lock(void)
+{
+ /*
+ * If an NMI die dumps out the content of the ring buffer
+ * do not grab locks. We also permanently disable the ring
+ * 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))
+ return 1;
+
+ tracing_off_permanent();
+ return 0;
+}
+
/**
* ring_buffer_peek - peek at the next event to be read
* @buffer: The ring buffer to read
@@ -2458,14 +2508,20 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct ring_buffer_event *event;
unsigned long flags;
+ int dolock;
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
+ dolock = rb_ok_to_lock();
again:
- spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
event = rb_buffer_peek(buffer, cpu, ts);
- spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
@@ -2517,6 +2573,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event = NULL;
unsigned long flags;
+ int dolock;
+
+ dolock = rb_ok_to_lock();
again:
/* might be called in atomic */
@@ -2526,7 +2585,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
goto out;
cpu_buffer = buffer->buffers[cpu];
- spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
event = rb_buffer_peek(buffer, cpu, ts);
if (!event)
@@ -2535,7 +2596,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
rb_advance_reader(cpu_buffer);
out_unlock:
- spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
out:
preempt_enable();
@@ -2677,6 +2740,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->overrun = 0;
cpu_buffer->read = 0;
local_set(&cpu_buffer->entries, 0);
+ local_set(&cpu_buffer->committing, 0);
+ local_set(&cpu_buffer->commits, 0);
cpu_buffer->write_stamp = 0;
cpu_buffer->read_stamp = 0;
@@ -2731,12 +2796,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset);
int ring_buffer_empty(struct ring_buffer *buffer)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+ int dolock;
int cpu;
+ int ret;
+
+ dolock = rb_ok_to_lock();
/* yes this is racy, but if you don't like the race, lock the buffer */
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
- if (!rb_per_cpu_empty(cpu_buffer))
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
+ ret = rb_per_cpu_empty(cpu_buffer);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
+
+ if (!ret)
return 0;
}
@@ -2752,14 +2830,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty);
int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+ int dolock;
int ret;
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 1;
+ dolock = rb_ok_to_lock();
+
cpu_buffer = buffer->buffers[cpu];
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
ret = rb_per_cpu_empty(cpu_buffer);
-
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
return ret;
}
@@ -3026,6 +3113,7 @@ 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)
@@ -3093,6 +3181,7 @@ 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,
@@ -3105,7 +3194,7 @@ static int rb_cpu_notify(struct notifier_block *self,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- if (cpu_isset(cpu, *buffer->cpumask))
+ if (cpumask_test_cpu(cpu, buffer->cpumask))
return NOTIFY_OK;
buffer->buffers[cpu] =
@@ -3116,7 +3205,7 @@ static int rb_cpu_notify(struct notifier_block *self,
return NOTIFY_OK;
}
smp_wmb();
- cpu_set(cpu, *buffer->cpumask);
+ cpumask_set_cpu(cpu, buffer->cpumask);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 8d68e149a8b..573d3cc762c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -102,8 +102,10 @@ static enum event_status read_page(int cpu)
event = (void *)&rpage->data[i];
switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
- /* We don't expect any padding */
- KILL_TEST();
+ /* failed writes may be discarded events */
+ if (!event->time_delta)
+ KILL_TEST();
+ inc = event->array[0] + 4;
break;
case RINGBUF_TYPE_TIME_EXTEND:
inc = 8;
@@ -119,7 +121,7 @@ static enum event_status read_page(int cpu)
KILL_TEST();
break;
}
- inc = event->array[0];
+ inc = event->array[0] + 4;
break;
default:
entry = ring_buffer_event_data(event);
@@ -201,7 +203,7 @@ static void ring_buffer_producer(void)
* Hammer the buffer for 10 secs (this may
* make the system stall)
*/
- pr_info("Starting ring buffer hammer\n");
+ trace_printk("Starting ring buffer hammer\n");
do_gettimeofday(&start_tv);
do {
struct ring_buffer_event *event;
@@ -237,7 +239,7 @@ static void ring_buffer_producer(void)
#endif
} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
- pr_info("End ring buffer hammer\n");
+ trace_printk("End ring buffer hammer\n");
if (consumer) {
/* Init both completions here to avoid races */
@@ -260,49 +262,50 @@ static void ring_buffer_producer(void)
overruns = ring_buffer_overruns(buffer);
if (kill_test)
- pr_info("ERROR!\n");
- pr_info("Time: %lld (usecs)\n", time);
- pr_info("Overruns: %lld\n", overruns);
+ trace_printk("ERROR!\n");
+ trace_printk("Time: %lld (usecs)\n", time);
+ trace_printk("Overruns: %lld\n", overruns);
if (disable_reader)
- pr_info("Read: (reader disabled)\n");
+ trace_printk("Read: (reader disabled)\n");
else
- pr_info("Read: %ld (by %s)\n", read,
+ trace_printk("Read: %ld (by %s)\n", read,
read_events ? "events" : "pages");
- pr_info("Entries: %lld\n", entries);
- pr_info("Total: %lld\n", entries + overruns + read);
- pr_info("Missed: %ld\n", missed);
- pr_info("Hit: %ld\n", hit);
+ trace_printk("Entries: %lld\n", entries);
+ trace_printk("Total: %lld\n", entries + overruns + read);
+ trace_printk("Missed: %ld\n", missed);
+ trace_printk("Hit: %ld\n", hit);
/* Convert time from usecs to millisecs */
do_div(time, USEC_PER_MSEC);
if (time)
hit /= (long)time;
else
- pr_info("TIME IS ZERO??\n");
+ trace_printk("TIME IS ZERO??\n");
- pr_info("Entries per millisec: %ld\n", hit);
+ trace_printk("Entries per millisec: %ld\n", hit);
if (hit) {
/* Calculate the average time in nanosecs */
avg = NSEC_PER_MSEC / hit;
- pr_info("%ld ns per entry\n", avg);
+ trace_printk("%ld ns per entry\n", avg);
}
if (missed) {
if (time)
missed /= (long)time;
- pr_info("Total iterations per millisec: %ld\n", hit + missed);
+ trace_printk("Total iterations per millisec: %ld\n",
+ hit + missed);
/* it is possible that hit + missed will overflow and be zero */
if (!(hit + missed)) {
- pr_info("hit + missed overflowed and totalled zero!\n");
+ trace_printk("hit + missed overflowed and totalled zero!\n");
hit--; /* make it non zero */
}
/* Caculate the average time in nanosecs */
avg = NSEC_PER_MSEC / (hit + missed);
- pr_info("%ld ns per entry\n", avg);
+ trace_printk("%ld ns per entry\n", avg);
}
}
@@ -353,7 +356,7 @@ static int ring_buffer_producer_thread(void *arg)
ring_buffer_producer();
- pr_info("Sleeping for 10 secs\n");
+ trace_printk("Sleeping for 10 secs\n");
set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout(HZ * SLEEP_TIME);
__set_current_state(TASK_RUNNING);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8acd9b81a5d..8bc8d8afea6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -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;
@@ -344,7 +344,7 @@ static raw_spinlock_t ftrace_max_lock =
/*
* Copy the new maximum trace into the separate maximum-trace
* structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /debugfs/tracing/latency_trace)
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
*/
static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
@@ -2053,25 +2053,23 @@ 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 +2105,10 @@ 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
@@ -2191,11 +2181,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
return -ENOMEM;
- mutex_lock(&tracing_cpumask_update_lock);
err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
if (err)
goto err_unlock;
+ mutex_lock(&tracing_cpumask_update_lock);
+
local_irq_disable();
__raw_spin_lock(&ftrace_max_lock);
for_each_tracing_cpu(cpu) {
@@ -2223,8 +2214,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
return count;
err_unlock:
- mutex_unlock(&tracing_cpumask_update_lock);
- free_cpumask_var(tracing_cpumask);
+ free_cpumask_var(tracing_cpumask_new);
return err;
}
@@ -2414,21 +2404,20 @@ static const struct file_operations tracing_iter_fops = {
static const char readme_msg[] =
"tracing mini-HOWTO:\n\n"
- "# mkdir /debug\n"
- "# mount -t debugfs nodev /debug\n\n"
- "# cat /debug/tracing/available_tracers\n"
+ "# mount -t debugfs nodev /sys/kernel/debug\n\n"
+ "# cat /sys/kernel/debug/tracing/available_tracers\n"
"wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
- "# cat /debug/tracing/current_tracer\n"
+ "# cat /sys/kernel/debug/tracing/current_tracer\n"
"nop\n"
- "# echo sched_switch > /debug/tracing/current_tracer\n"
- "# cat /debug/tracing/current_tracer\n"
+ "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
+ "# cat /sys/kernel/debug/tracing/current_tracer\n"
"sched_switch\n"
- "# cat /debug/tracing/trace_options\n"
+ "# cat /sys/kernel/debug/tracing/trace_options\n"
"noprint-parent nosym-offset nosym-addr noverbose\n"
- "# echo print-parent > /debug/tracing/trace_options\n"
- "# echo 1 > /debug/tracing/tracing_enabled\n"
- "# cat /debug/tracing/trace > /tmp/trace.txt\n"
- "# echo 0 > /debug/tracing/tracing_enabled\n"
+ "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
+ "# echo 1 > /sys/kernel/debug/tracing/tracing_enabled\n"
+ "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n"
+ "# echo 0 > /sys/kernel/debug/tracing/tracing_enabled\n"
;
static ssize_t
@@ -3627,7 +3616,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
struct trace_seq *s;
unsigned long cnt;
- s = kmalloc(sizeof(*s), GFP_ATOMIC);
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return ENOMEM;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6e735d4771f..3548ae5cc78 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -597,6 +597,7 @@ 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 +605,12 @@ 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
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index 5e32e375134..6db005e1248 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -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)")
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aa08be69a1b..53c8fd376a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -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)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index db6e54bdb59..936c621bbf4 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -27,8 +27,6 @@
#include "trace.h"
#include "trace_output.h"
-static DEFINE_MUTEX(filter_mutex);
-
enum filter_op_ids
{
OP_OR,
@@ -178,7 +176,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
static int filter_pred_strloc(struct filter_pred *pred, void *event,
int val1, int val2)
{
- int str_loc = *(int *)(event + pred->offset);
+ unsigned short str_loc = *(unsigned short *)(event + pred->offset);
char *addr = (char *)(event + str_loc);
int cmp, match;
@@ -294,12 +292,12 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
struct event_filter *filter = call->filter;
- mutex_lock(&filter_mutex);
+ mutex_lock(&event_mutex);
if (filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
trace_seq_printf(s, "none\n");
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
}
void print_subsystem_event_filter(struct event_subsystem *system,
@@ -307,12 +305,12 @@ void print_subsystem_event_filter(struct event_subsystem *system,
{
struct event_filter *filter = system->filter;
- mutex_lock(&filter_mutex);
+ mutex_lock(&event_mutex);
if (filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
trace_seq_printf(s, "none\n");
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
}
static struct ftrace_event_field *
@@ -381,6 +379,7 @@ void destroy_preds(struct ftrace_event_call *call)
filter_free_pred(filter->preds[i]);
}
kfree(filter->preds);
+ kfree(filter->filter_string);
kfree(filter);
call->filter = NULL;
}
@@ -433,7 +432,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
filter->n_preds = 0;
}
- mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
if (!call->define_fields)
continue;
@@ -443,7 +441,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
remove_filter_string(call->filter);
}
}
- mutex_unlock(&event_mutex);
}
static int filter_add_pred_fn(struct filter_parse_state *ps,
@@ -546,6 +543,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
filter_pred_fn_t fn;
unsigned long long val;
int string_type;
+ int ret;
pred->fn = filter_pred_none;
@@ -581,7 +579,11 @@ static int filter_add_pred(struct filter_parse_state *ps,
pred->not = 1;
return filter_add_pred_fn(ps, call, pred, fn);
} else {
- if (strict_strtoull(pred->str_val, 0, &val)) {
+ if (field->is_signed)
+ ret = strict_strtoll(pred->str_val, 0, &val);
+ else
+ ret = strict_strtoull(pred->str_val, 0, &val);
+ if (ret) {
parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
return -EINVAL;
}
@@ -625,7 +627,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
filter->preds[filter->n_preds] = pred;
filter->n_preds++;
- mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
if (!call->define_fields)
@@ -636,14 +637,12 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
err = filter_add_pred(ps, call, pred);
if (err) {
- mutex_unlock(&event_mutex);
filter_free_subsystem_preds(system);
parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
goto out;
}
replace_filter_string(call->filter, filter_string);
}
- mutex_unlock(&event_mutex);
out:
return err;
}
@@ -1070,12 +1069,12 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
struct filter_parse_state *ps;
- mutex_lock(&filter_mutex);
+ mutex_lock(&event_mutex);
if (!strcmp(strstrip(filter_string), "0")) {
filter_disable_preds(call);
remove_filter_string(call->filter);
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
return 0;
}
@@ -1103,7 +1102,7 @@ out:
postfix_clear(ps);
kfree(ps);
out_unlock:
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
return err;
}
@@ -1115,12 +1114,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
struct filter_parse_state *ps;
- mutex_lock(&filter_mutex);
+ mutex_lock(&event_mutex);
if (!strcmp(strstrip(filter_string), "0")) {
filter_free_subsystem_preds(system);
remove_filter_string(system->filter);
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
return 0;
}
@@ -1148,7 +1147,7 @@ out:
postfix_clear(ps);
kfree(ps);
out_unlock:
- mutex_unlock(&filter_mutex);
+ mutex_unlock(&event_mutex);
return err;
}
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index c9a0b7df44f..7402144bff2 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -193,9 +193,11 @@ static void tracing_start_function_trace(void)
static void tracing_stop_function_trace(void)
{
ftrace_function_enabled = 0;
- /* OK if they are not registered */
- unregister_ftrace_function(&trace_stack_ops);
- unregister_ftrace_function(&trace_ops);
+
+ if (func_flags.val & TRACE_FUNC_OPT_STACK)
+ unregister_ftrace_function(&trace_stack_ops);
+ else
+ unregister_ftrace_function(&trace_ops);
}
static int func_set_flag(u32 old_flags, u32 bit, int set)
@@ -300,8 +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;
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 8b592418d8b..d2249abafb5 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -57,7 +57,8 @@ static struct tracer_flags tracer_flags = {
/* Add a function return address to the trace stack on thread info.*/
int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+ unsigned long frame_pointer)
{
unsigned long long calltime;
int index;
@@ -85,6 +86,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
current->ret_stack[index].subtime = 0;
+ current->ret_stack[index].fp = frame_pointer;
*depth = index;
return 0;
@@ -92,7 +94,8 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
/* Retrieve a function return address to the trace stack on thread info.*/
static void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
+ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
+ unsigned long frame_pointer)
{
int index;
@@ -106,6 +109,31 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
return;
}
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+ /*
+ * The arch may choose to record the frame pointer used
+ * and check it here to make sure that it is what we expect it
+ * to be. If gcc does not set the place holder of the return
+ * address in the frame pointer, and does a copy instead, then
+ * the function graph trace will fail. This test detects this
+ * case.
+ *
+ * Currently, x86_32 with optimize for size (-Os) makes the latest
+ * gcc do the above.
+ */
+ if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
+ ftrace_graph_stop();
+ WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
+ " from func %pF return to %lx\n",
+ current->ret_stack[index].fp,
+ frame_pointer,
+ (void *)current->ret_stack[index].func,
+ current->ret_stack[index].ret);
+ *ret = (unsigned long)panic;
+ return;
+ }
+#endif
+
*ret = current->ret_stack[index].ret;
trace->func = current->ret_stack[index].func;
trace->calltime = current->ret_stack[index].calltime;
@@ -117,12 +145,12 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
* Send the trace to the ring-buffer.
* @return the original return address.
*/
-unsigned long ftrace_return_to_handler(void)
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
{
struct ftrace_graph_ret trace;
unsigned long ret;
- ftrace_pop_return_trace(&trace, &ret);
+ ftrace_pop_return_trace(&trace, &ret, frame_pointer);
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
barrier();
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 7938f3ae93e..e0c2545622e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -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);
}
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 9bece9687b6..7b627811082 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -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)
@@ -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 = {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2d7aebd71db..e644af91012 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -326,10 +326,10 @@ 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);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index c00643733f4..e66f5e49334 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -199,17 +199,13 @@ 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;
}
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index e04b76cc238..f6693969287 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -203,7 +203,8 @@ static void start_stack_timer(void *unused)
hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hrtimer->function = stack_trace_timer_fn;
- hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL);
+ hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+ HRTIMER_MODE_REL_PINNED);
}
static void start_stack_timers(void)
diff --git a/kernel/user.c b/kernel/user.c
index 850e0ba41c1..2c000e7132a 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -75,21 +75,6 @@ static void uid_hash_remove(struct user_struct *up)
put_user_ns(up->user_ns);
}
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
-{
- struct user_struct *user;
- struct hlist_node *h;
-
- hlist_for_each_entry(user, h, hashent, uidhash_node) {
- if (user->uid == uid) {
- atomic_inc(&user->__count);
- return user;
- }
- }
-
- return NULL;
-}
-
#ifdef CONFIG_USER_SCHED
static void sched_destroy_user(struct user_struct *up)
@@ -119,6 +104,23 @@ static int sched_create_user(struct user_struct *up) { return 0; }
#if defined(CONFIG_USER_SCHED) && defined(CONFIG_SYSFS)
+static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
+{
+ struct user_struct *user;
+ struct hlist_node *h;
+
+ hlist_for_each_entry(user, h, hashent, uidhash_node) {
+ if (user->uid == uid) {
+ /* possibly resurrect an "almost deleted" object */
+ if (atomic_inc_return(&user->__count) == 1)
+ cancel_delayed_work(&user->work);
+ return user;
+ }
+ }
+
+ return NULL;
+}
+
static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */
static DEFINE_MUTEX(uids_mutex);
@@ -283,12 +285,12 @@ int __init uids_sysfs_init(void)
return uids_user_create(&root_user);
}
-/* work function to remove sysfs directory for a user and free up
+/* delayed work function to remove sysfs directory for a user and free up
* corresponding structures.
*/
static void cleanup_user_struct(struct work_struct *w)
{
- struct user_struct *up = container_of(w, struct user_struct, work);
+ struct user_struct *up = container_of(w, struct user_struct, work.work);
unsigned long flags;
int remove_user = 0;
@@ -297,15 +299,12 @@ static void cleanup_user_struct(struct work_struct *w)
*/
uids_mutex_lock();
- local_irq_save(flags);
-
- if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) {
+ spin_lock_irqsave(&uidhash_lock, flags);
+ if (atomic_read(&up->__count) == 0) {
uid_hash_remove(up);
remove_user = 1;
- spin_unlock_irqrestore(&uidhash_lock, flags);
- } else {
- local_irq_restore(flags);
}
+ spin_unlock_irqrestore(&uidhash_lock, flags);
if (!remove_user)
goto done;
@@ -331,16 +330,28 @@ done:
*/
static void free_user(struct user_struct *up, unsigned long flags)
{
- /* restore back the count */
- atomic_inc(&up->__count);
spin_unlock_irqrestore(&uidhash_lock, flags);
-
- INIT_WORK(&up->work, cleanup_user_struct);
- schedule_work(&up->work);
+ INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
+ schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
}
#else /* CONFIG_USER_SCHED && CONFIG_SYSFS */
+static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
+{
+ struct user_struct *user;
+ struct hlist_node *h;
+
+ hlist_for_each_entry(user, h, hashent, uidhash_node) {
+ if (user->uid == uid) {
+ atomic_inc(&user->__count);
+ return user;
+ }
+ }
+
+ return NULL;
+}
+
int uids_sysfs_init(void) { return 0; }
static inline int uids_user_create(struct user_struct *up) { return 0; }
static inline void uids_mutex_lock(void) { }
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 815237a55af..8a82b4b8ea5 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -15,6 +15,16 @@
#include <linux/err.h>
#include <linux/slab.h>
+static struct uts_namespace *create_uts_ns(void)
+{
+ struct uts_namespace *uts_ns;
+
+ uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+ if (uts_ns)
+ kref_init(&uts_ns->kref);
+ return uts_ns;
+}
+
/*
* Clone a new ns copying an original utsname, setting refcount to 1
* @old_ns: namespace to clone
@@ -24,14 +34,13 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
{
struct uts_namespace *ns;
- ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+ ns = create_uts_ns();
if (!ns)
return ERR_PTR(-ENOMEM);
down_read(&uts_sem);
memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
up_read(&uts_sem);
- kref_init(&ns->kref);
return ns;
}