aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c128
-rw-r--r--kernel/auditsc.c327
-rw-r--r--kernel/cpuset.c11
-rw-r--r--kernel/exit.c8
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/module.c11
-rw-r--r--kernel/params.c10
-rw-r--r--kernel/power/Kconfig2
-rw-r--r--kernel/power/disk.c6
-rw-r--r--kernel/power/power.h7
-rw-r--r--kernel/power/swsusp.c29
-rw-r--r--kernel/printk.c7
-rw-r--r--kernel/sched.c8
-rw-r--r--kernel/signal.c34
-rw-r--r--kernel/sys.c55
-rw-r--r--kernel/timer.c9
16 files changed, 437 insertions, 218 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 7f0699790d4..83096b67510 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -79,6 +79,8 @@ static int audit_rate_limit;
/* Number of outstanding audit_buffers allowed. */
static int audit_backlog_limit = 64;
+static int audit_backlog_wait_time = 60 * HZ;
+static int audit_backlog_wait_overflow = 0;
/* The identity of the user shutting down the audit system. */
uid_t audit_sig_uid = -1;
@@ -106,18 +108,12 @@ static LIST_HEAD(audit_freelist);
static struct sk_buff_head audit_skb_queue;
static struct task_struct *kauditd_task;
static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
-
-/* There are three lists of rules -- one to search at task creation
- * time, one to search at syscall entry time, and another to search at
- * syscall exit time. */
-static LIST_HEAD(audit_tsklist);
-static LIST_HEAD(audit_entlist);
-static LIST_HEAD(audit_extlist);
+static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
/* The netlink socket is only to be read by 1 CPU, which lets us assume
* that list additions and deletions never happen simultaneously in
* auditsc.c */
-static DECLARE_MUTEX(audit_netlink_sem);
+DECLARE_MUTEX(audit_netlink_sem);
/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
* audit records. Since printk uses a 1024 byte buffer, this buffer
@@ -137,6 +133,7 @@ struct audit_buffer {
struct list_head list;
struct sk_buff *skb; /* formatted skb ready to send */
struct audit_context *ctx; /* NULL or associated context */
+ int gfp_mask;
};
static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
@@ -145,11 +142,6 @@ static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
nlh->nlmsg_pid = pid;
}
-struct audit_entry {
- struct list_head list;
- struct audit_rule rule;
-};
-
static void audit_panic(const char *message)
{
switch (audit_failure)
@@ -233,7 +225,7 @@ static int audit_set_rate_limit(int limit, uid_t loginuid)
{
int old = audit_rate_limit;
audit_rate_limit = limit;
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
"audit_rate_limit=%d old=%d by auid=%u",
audit_rate_limit, old, loginuid);
return old;
@@ -243,7 +235,7 @@ static int audit_set_backlog_limit(int limit, uid_t loginuid)
{
int old = audit_backlog_limit;
audit_backlog_limit = limit;
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
"audit_backlog_limit=%d old=%d by auid=%u",
audit_backlog_limit, old, loginuid);
return old;
@@ -255,7 +247,7 @@ static int audit_set_enabled(int state, uid_t loginuid)
if (state != 0 && state != 1)
return -EINVAL;
audit_enabled = state;
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
"audit_enabled=%d old=%d by auid=%u",
audit_enabled, old, loginuid);
return old;
@@ -269,7 +261,7 @@ static int audit_set_failure(int state, uid_t loginuid)
&& state != AUDIT_FAIL_PANIC)
return -EINVAL;
audit_failure = state;
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
"audit_failure=%d old=%d by auid=%u",
audit_failure, old, loginuid);
return old;
@@ -281,6 +273,7 @@ int kauditd_thread(void *dummy)
while (1) {
skb = skb_dequeue(&audit_skb_queue);
+ wake_up(&audit_backlog_wait);
if (skb) {
if (audit_pid) {
int err = netlink_unicast(audit_sock, skb, audit_pid, 0);
@@ -290,7 +283,7 @@ int kauditd_thread(void *dummy)
audit_pid = 0;
}
} else {
- printk(KERN_ERR "%s\n", skb->data + NLMSG_SPACE(0));
+ printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0));
kfree_skb(skb);
}
} else {
@@ -423,7 +416,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (status_get->mask & AUDIT_STATUS_PID) {
int old = audit_pid;
audit_pid = status_get->pid;
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
"audit_pid=%d old=%d by auid=%u",
audit_pid, old, loginuid);
}
@@ -435,15 +428,21 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG:
- ab = audit_log_start(NULL, msg_type);
- if (!ab)
- break; /* audit_panic has been called */
- audit_log_format(ab,
- "user pid=%d uid=%u auid=%u"
- " msg='%.1024s'",
- pid, uid, loginuid, (char *)data);
- audit_set_pid(ab, pid);
- audit_log_end(ab);
+ if (!audit_enabled && msg_type != AUDIT_USER_AVC)
+ return 0;
+
+ err = audit_filter_user(&NETLINK_CB(skb), msg_type);
+ if (err == 1) {
+ err = 0;
+ ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
+ if (ab) {
+ audit_log_format(ab,
+ "user pid=%d uid=%u auid=%u msg='%.1024s'",
+ pid, uid, loginuid, (char *)data);
+ audit_set_pid(ab, pid);
+ audit_log_end(ab);
+ }
+ }
break;
case AUDIT_ADD:
case AUDIT_DEL:
@@ -523,7 +522,7 @@ static int __init audit_init(void)
skb_queue_head_init(&audit_skb_queue);
audit_initialized = 1;
audit_enabled = audit_default;
- audit_log(NULL, AUDIT_KERNEL, "initialized");
+ audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
return 0;
}
__initcall(audit_init);
@@ -561,7 +560,7 @@ static void audit_buffer_free(struct audit_buffer *ab)
}
static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
- int gfp_mask, int type)
+ unsigned int __nocast gfp_mask, int type)
{
unsigned long flags;
struct audit_buffer *ab = NULL;
@@ -587,6 +586,7 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
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;
@@ -606,26 +606,27 @@ err:
* (timestamp,serial) tuple is unique for each syscall and is live from
* syscall entry to syscall exit.
*
- * Atomic values are only guaranteed to be 24-bit, so we count down.
- *
* NOTE: Another possibility is to store the formatted records off the
* audit context (for those records that have a context), and emit them
* all at syscall exit. However, this could delay the reporting of
* significant errors until syscall exit (or never, if the system
* halts). */
+
unsigned int audit_serial(void)
{
- static atomic_t serial = ATOMIC_INIT(0xffffff);
- unsigned int a, b;
+ static spinlock_t serial_lock = SPIN_LOCK_UNLOCKED;
+ static unsigned int serial = 0;
+
+ unsigned long flags;
+ unsigned int ret;
+ spin_lock_irqsave(&serial_lock, flags);
do {
- a = atomic_read(&serial);
- if (atomic_dec_and_test(&serial))
- atomic_set(&serial, 0xffffff);
- b = atomic_read(&serial);
- } while (b != a - 1);
+ ret = ++serial;
+ } while (unlikely(!ret));
+ spin_unlock_irqrestore(&serial_lock, flags);
- return 0xffffff - b;
+ return ret;
}
static inline void audit_get_stamp(struct audit_context *ctx,
@@ -645,17 +646,43 @@ static inline void audit_get_stamp(struct audit_context *ctx,
* syscall, then the syscall is marked as auditable and an audit record
* will be written at syscall exit. If there is no associated task, tsk
* should be NULL. */
-struct audit_buffer *audit_log_start(struct audit_context *ctx, int type)
+
+struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask,
+ int type)
{
struct audit_buffer *ab = NULL;
struct timespec t;
unsigned int serial;
+ int reserve;
+ unsigned long timeout_start = jiffies;
if (!audit_initialized)
return NULL;
- if (audit_backlog_limit
- && skb_queue_len(&audit_skb_queue) > audit_backlog_limit) {
+ if (gfp_mask & __GFP_WAIT)
+ reserve = 0;
+ else
+ reserve = 5; /* Allow atomic callers to go up to five
+ entries over the normal backlog limit */
+
+ while (audit_backlog_limit
+ && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
+ if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time
+ && time_before(jiffies, timeout_start + audit_backlog_wait_time)) {
+
+ /* Wait for auditd to drain the queue a little */
+ DECLARE_WAITQUEUE(wait, current);
+ set_current_state(TASK_INTERRUPTIBLE);
+ add_wait_queue(&audit_backlog_wait, &wait);
+
+ if (audit_backlog_limit &&
+ skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
+ schedule_timeout(timeout_start + audit_backlog_wait_time - jiffies);
+
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&audit_backlog_wait, &wait);
+ continue;
+ }
if (audit_rate_check())
printk(KERN_WARNING
"audit: audit_backlog=%d > "
@@ -663,10 +690,12 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int type)
skb_queue_len(&audit_skb_queue),
audit_backlog_limit);
audit_log_lost("backlog limit exceeded");
+ audit_backlog_wait_time = audit_backlog_wait_overflow;
+ wake_up(&audit_backlog_wait);
return NULL;
}
- ab = audit_buffer_alloc(ctx, GFP_ATOMIC, type);
+ ab = audit_buffer_alloc(ctx, gfp_mask, type);
if (!ab) {
audit_log_lost("out of memory in audit_log_start");
return NULL;
@@ -690,7 +719,7 @@ static inline int audit_expand(struct audit_buffer *ab, int extra)
{
struct sk_buff *skb = ab->skb;
int ret = pskb_expand_head(skb, skb_headroom(skb), extra,
- GFP_ATOMIC);
+ ab->gfp_mask);
if (ret < 0) {
audit_log_lost("out of memory in audit_expand");
return 0;
@@ -809,7 +838,7 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
audit_log_format(ab, " %s", prefix);
/* We will allow 11 spaces for ' (deleted)' to be appended */
- path = kmalloc(PATH_MAX+11, GFP_KERNEL);
+ path = kmalloc(PATH_MAX+11, ab->gfp_mask);
if (!path) {
audit_log_format(ab, "<no memory>");
return;
@@ -841,7 +870,7 @@ void audit_log_end(struct audit_buffer *ab)
ab->skb = NULL;
wake_up_interruptible(&kauditd_wait);
} else {
- printk("%s\n", ab->skb->data + NLMSG_SPACE(0));
+ printk(KERN_NOTICE "%s\n", ab->skb->data + NLMSG_SPACE(0));
}
}
audit_buffer_free(ab);
@@ -850,12 +879,13 @@ void audit_log_end(struct audit_buffer *ab)
/* Log an audit record. This is a convenience function that calls
* audit_log_start, audit_log_vformat, and audit_log_end. It may be
* called in any context. */
-void audit_log(struct audit_context *ctx, int type, const char *fmt, ...)
+void audit_log(struct audit_context *ctx, int gfp_mask, int type,
+ const char *fmt, ...)
{
struct audit_buffer *ab;
va_list args;
- ab = audit_log_start(ctx, type);
+ ab = audit_log_start(ctx, gfp_mask, type);
if (ab) {
va_start(args, fmt);
audit_log_vformat(ab, fmt, args);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e75f84e1a1a..88696f639aa 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -39,6 +39,9 @@
#include <linux/audit.h>
#include <linux/personality.h>
#include <linux/time.h>
+#include <linux/kthread.h>
+#include <linux/netlink.h>
+#include <linux/compiler.h>
#include <asm/unistd.h>
/* 0 = no checking
@@ -95,6 +98,7 @@ struct audit_names {
uid_t uid;
gid_t gid;
dev_t rdev;
+ unsigned flags;
};
struct audit_aux_data {
@@ -167,9 +171,16 @@ struct audit_context {
/* There are three lists of rules -- one to search at task creation
* time, one to search at syscall entry time, and another to search at
* syscall exit time. */
-static LIST_HEAD(audit_tsklist);
-static LIST_HEAD(audit_entlist);
-static LIST_HEAD(audit_extlist);
+static struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
+ LIST_HEAD_INIT(audit_filter_list[0]),
+ LIST_HEAD_INIT(audit_filter_list[1]),
+ LIST_HEAD_INIT(audit_filter_list[2]),
+ LIST_HEAD_INIT(audit_filter_list[3]),
+ LIST_HEAD_INIT(audit_filter_list[4]),
+#if AUDIT_NR_FILTERS != 5
+#error Fix audit_filter_list initialiser
+#endif
+};
struct audit_entry {
struct list_head list;
@@ -179,9 +190,36 @@ struct audit_entry {
extern int audit_pid;
+/* Copy rule from user-space to kernel-space. Called from
+ * audit_add_rule during AUDIT_ADD. */
+static inline int audit_copy_rule(struct audit_rule *d, struct audit_rule *s)
+{
+ int i;
+
+ if (s->action != AUDIT_NEVER
+ && s->action != AUDIT_POSSIBLE
+ && s->action != AUDIT_ALWAYS)
+ return -1;
+ if (s->field_count < 0 || s->field_count > AUDIT_MAX_FIELDS)
+ return -1;
+ if ((s->flags & ~AUDIT_FILTER_PREPEND) >= AUDIT_NR_FILTERS)
+ return -1;
+
+ d->flags = s->flags;
+ d->action = s->action;
+ d->field_count = s->field_count;
+ for (i = 0; i < d->field_count; i++) {
+ d->fields[i] = s->fields[i];
+ d->values[i] = s->values[i];
+ }
+ for (i = 0; i < AUDIT_BITMASK_SIZE; i++) d->mask[i] = s->mask[i];
+ return 0;
+}
+
/* Check to see if two rules are identical. It is called from
+ * audit_add_rule during AUDIT_ADD and
* audit_del_rule during AUDIT_DEL. */
-static int audit_compare_rule(struct audit_rule *a, struct audit_rule *b)
+static inline int audit_compare_rule(struct audit_rule *a, struct audit_rule *b)
{
int i;
@@ -210,19 +248,37 @@ static int audit_compare_rule(struct audit_rule *a, struct audit_rule *b)
/* Note that audit_add_rule and audit_del_rule are called via
* audit_receive() in audit.c, and are protected by
* audit_netlink_sem. */
-static inline int audit_add_rule(struct audit_entry *entry,
- struct list_head *list)
+static inline int audit_add_rule(struct audit_rule *rule,
+ struct list_head *list)
{
- if (entry->rule.flags & AUDIT_PREPEND) {
- entry->rule.flags &= ~AUDIT_PREPEND;
+ struct audit_entry *entry;
+
+ /* Do not use the _rcu iterator here, since this is the only
+ * addition routine. */
+ list_for_each_entry(entry, list, list) {
+ if (!audit_compare_rule(rule, &entry->rule)) {
+ return -EEXIST;
+ }
+ }
+
+ if (!(entry = kmalloc(sizeof(*entry), GFP_KERNEL)))
+ return -ENOMEM;
+ if (audit_copy_rule(&entry->rule, rule)) {
+ kfree(entry);
+ return -EINVAL;
+ }
+
+ if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
+ entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
list_add_rcu(&entry->list, list);
} else {
list_add_tail_rcu(&entry->list, list);
}
+
return 0;
}
-static void audit_free_rule(struct rcu_head *head)
+static inline void audit_free_rule(struct rcu_head *head)
{
struct audit_entry *e = container_of(head, struct audit_entry, rcu);
kfree(e);
@@ -245,82 +301,82 @@ static inline int audit_del_rule(struct audit_rule *rule,
return 0;
}
}
- return -EFAULT; /* No matching rule */
+ return -ENOENT; /* No matching rule */
}
-/* Copy rule from user-space to kernel-space. Called during
- * AUDIT_ADD. */
-static int audit_copy_rule(struct audit_rule *d, struct audit_rule *s)
+static int audit_list_rules(void *_dest)
{
+ int pid, seq;
+ int *dest = _dest;
+ struct audit_entry *entry;
int i;
- if (s->action != AUDIT_NEVER
- && s->action != AUDIT_POSSIBLE
- && s->action != AUDIT_ALWAYS)
- return -1;
- if (s->field_count < 0 || s->field_count > AUDIT_MAX_FIELDS)
- return -1;
+ pid = dest[0];
+ seq = dest[1];
+ kfree(dest);
- d->flags = s->flags;
- d->action = s->action;
- d->field_count = s->field_count;
- for (i = 0; i < d->field_count; i++) {
- d->fields[i] = s->fields[i];
- d->values[i] = s->values[i];
+ down(&audit_netlink_sem);
+
+ /* The *_rcu iterators not needed here because we are
+ always called with audit_netlink_sem held. */
+ for (i=0; i<AUDIT_NR_FILTERS; i++) {
+ list_for_each_entry(entry, &audit_filter_list[i], list)
+ audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
+ &entry->rule, sizeof(entry->rule));
}
- for (i = 0; i < AUDIT_BITMASK_SIZE; i++) d->mask[i] = s->mask[i];
+ audit_send_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0);
+
+ up(&audit_netlink_sem);
return 0;
}
int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
uid_t loginuid)
{
- u32 flags;
- struct audit_entry *entry;
+ struct task_struct *tsk;
+ int *dest;
int err = 0;
+ unsigned listnr;
switch (type) {
case AUDIT_LIST:
- /* The *_rcu iterators not needed here because we are
- always called with audit_netlink_sem held. */
- list_for_each_entry(entry, &audit_tsklist, list)
- audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
- &entry->rule, sizeof(entry->rule));
- list_for_each_entry(entry, &audit_entlist, list)
- audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
- &entry->rule, sizeof(entry->rule));
- list_for_each_entry(entry, &audit_extlist, list)
- audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
- &entry->rule, sizeof(entry->rule));
- audit_send_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0);
+ /* We can't just spew out the rules here because we might fill
+ * the available socket buffer space and deadlock waiting for
+ * auditctl to read from it... which isn't ever going to
+ * happen if we're actually running in the context of auditctl
+ * trying to _send_ the stuff */
+
+ dest = kmalloc(2 * sizeof(int), GFP_KERNEL);
+ if (!dest)
+ return -ENOMEM;
+ dest[0] = pid;
+ dest[1] = seq;
+
+ tsk = kthread_run(audit_list_rules, dest, "audit_list_rules");
+ if (IS_ERR(tsk)) {
+ kfree(dest);
+ err = PTR_ERR(tsk);
+ }
break;
case AUDIT_ADD:
- if (!(entry = kmalloc(sizeof(*entry), GFP_KERNEL)))
- return -ENOMEM;
- if (audit_copy_rule(&entry->rule, data)) {
- kfree(entry);
+ listnr =((struct audit_rule *)data)->flags & ~AUDIT_FILTER_PREPEND;
+ if (listnr >= AUDIT_NR_FILTERS)
return -EINVAL;
- }
- flags = entry->rule.flags;
- if (!err && (flags & AUDIT_PER_TASK))
- err = audit_add_rule(entry, &audit_tsklist);
- if (!err && (flags & AUDIT_AT_ENTRY))
- err = audit_add_rule(entry, &audit_entlist);
- if (!err && (flags & AUDIT_AT_EXIT))
- err = audit_add_rule(entry, &audit_extlist);
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
- "auid=%u added an audit rule\n", loginuid);
+
+ err = audit_add_rule(data, &audit_filter_list[listnr]);
+ if (!err)
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
+ "auid=%u added an audit rule\n", loginuid);
break;
case AUDIT_DEL:
- flags =((struct audit_rule *)data)->flags;
- if (!err && (flags & AUDIT_PER_TASK))
- err = audit_del_rule(data, &audit_tsklist);
- if (!err && (flags & AUDIT_AT_ENTRY))
- err = audit_del_rule(data, &audit_entlist);
- if (!err && (flags & AUDIT_AT_EXIT))
- err = audit_del_rule(data, &audit_extlist);
- audit_log(NULL, AUDIT_CONFIG_CHANGE,
- "auid=%u removed an audit rule\n", loginuid);
+ listnr =((struct audit_rule *)data)->flags & ~AUDIT_FILTER_PREPEND;
+ if (listnr >= AUDIT_NR_FILTERS)
+ return -EINVAL;
+
+ err = audit_del_rule(data, &audit_filter_list[listnr]);
+ if (!err)
+ audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
+ "auid=%u removed an audit rule\n", loginuid);
break;
default:
return -EINVAL;
@@ -384,8 +440,12 @@ static int audit_filter_rules(struct task_struct *tsk,
result = (ctx->return_code == value);
break;
case AUDIT_SUCCESS:
- if (ctx && ctx->return_valid)
- result = (ctx->return_valid == AUDITSC_SUCCESS);
+ if (ctx && ctx->return_valid) {
+ if (value)
+ result = (ctx->return_valid == AUDITSC_SUCCESS);
+ else
+ result = (ctx->return_valid == AUDITSC_FAILURE);
+ }
break;
case AUDIT_DEVMAJOR:
if (ctx) {
@@ -454,7 +514,7 @@ static enum audit_state audit_filter_task(struct task_struct *tsk)
enum audit_state state;
rcu_read_lock();
- list_for_each_entry_rcu(e, &audit_tsklist, list) {
+ list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
rcu_read_unlock();
return state;
@@ -474,20 +534,84 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
struct list_head *list)
{
struct audit_entry *e;
+ enum audit_state state;
+
+ if (audit_pid && tsk->tgid == audit_pid)
+ return AUDIT_DISABLED;
+
+ rcu_read_lock();
+ if (!list_empty(list)) {
+ int word = AUDIT_WORD(ctx->major);
+ int bit = AUDIT_BIT(ctx->major);
+
+ list_for_each_entry_rcu(e, list, list) {
+ if ((e->rule.mask[word] & bit) == bit
+ && audit_filter_rules(tsk, &e->rule, ctx, &state)) {
+ rcu_read_unlock();
+ return state;
+ }
+ }
+ }
+ rcu_read_unlock();
+ return AUDIT_BUILD_CONTEXT;
+}
+
+static int audit_filter_user_rules(struct netlink_skb_parms *cb,
+ struct audit_rule *rule,
+ enum audit_state *state)
+{
+ int i;
+
+ for (i = 0; i < rule->field_count; i++) {
+ u32 field = rule->fields[i] & ~AUDIT_NEGATE;
+ u32 value = rule->values[i];
+ int result = 0;
+
+ switch (field) {
+ case AUDIT_PID:
+ result = (cb->creds.pid == value);
+ break;
+ case AUDIT_UID:
+ result = (cb->creds.uid == value);
+ break;
+ case AUDIT_GID:
+ result = (cb->creds.gid == value);
+ break;
+ case AUDIT_LOGINUID:
+ result = (cb->loginuid == value);
+ break;
+ }
+
+ if (rule->fields[i] & AUDIT_NEGATE)
+ result = !result;
+ if (!result)
+ return 0;
+ }
+ switch (rule->action) {
+ case AUDIT_NEVER: *state = AUDIT_DISABLED; break;
+ case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT; break;
+ case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break;
+ }
+ return 1;
+}
+
+int audit_filter_user(struct netlink_skb_parms *cb, int type)
+{
+ struct audit_entry *e;
enum audit_state state;
- int word = AUDIT_WORD(ctx->major);
- int bit = AUDIT_BIT(ctx->major);
+ int ret = 1;
rcu_read_lock();
- list_for_each_entry_rcu(e, list, list) {
- if ((e->rule.mask[word] & bit) == bit
- && audit_filter_rules(tsk, &e->rule, ctx, &state)) {
- rcu_read_unlock();
- return state;
+ list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
+ if (audit_filter_user_rules(cb, &e->rule, &state)) {
+ if (state == AUDIT_DISABLED)
+ ret = 0;
+ break;
}
}
rcu_read_unlock();
- return AUDIT_BUILD_CONTEXT;
+
+ return ret; /* Audit by default */
}
/* This should be called with task_lock() held. */
@@ -504,7 +628,7 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
if (context->in_syscall && !context->auditable) {
enum audit_state state;
- state = audit_filter_syscall(tsk, context, &audit_extlist);
+ state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
if (state == AUDIT_RECORD_CONTEXT)
context->auditable = 1;
}
@@ -679,13 +803,13 @@ static void audit_log_task_info(struct audit_buffer *ab)
up_read(&mm->mmap_sem);
}
-static void audit_log_exit(struct audit_context *context)
+static void audit_log_exit(struct audit_context *context, unsigned int gfp_mask)
{
int i;
struct audit_buffer *ab;
struct audit_aux_data *aux;
- ab = audit_log_start(context, AUDIT_SYSCALL);
+ ab = audit_log_start(context, gfp_mask, AUDIT_SYSCALL);
if (!ab)
return; /* audit_panic has been called */
audit_log_format(ab, "arch=%x syscall=%d",
@@ -717,7 +841,7 @@ static void audit_log_exit(struct audit_context *context)
for (aux = context->aux; aux; aux = aux->next) {
- ab = audit_log_start(context, aux->type);
+ ab = audit_log_start(context, GFP_KERNEL, aux->type);
if (!ab)
continue; /* audit_panic has been called */
@@ -754,14 +878,14 @@ static void audit_log_exit(struct audit_context *context)
}
if (context->pwd && context->pwdmnt) {
- ab = audit_log_start(context, AUDIT_CWD);
+ ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
if (ab) {
audit_log_d_path(ab, "cwd=", context->pwd, context->pwdmnt);
audit_log_end(ab);
}
}
for (i = 0; i < context->name_count; i++) {
- ab = audit_log_start(context, AUDIT_PATH);
+ ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
if (!ab)
continue; /* audit_panic has been called */
@@ -770,6 +894,8 @@ static void audit_log_exit(struct audit_context *context)
audit_log_format(ab, " name=");
audit_log_untrustedstring(ab, context->names[i].name);
}
+ audit_log_format(ab, " flags=%x\n", context->names[i].flags);
+
if (context->names[i].ino != (unsigned long)-1)
audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o"
" ouid=%u ogid=%u rdev=%02x:%02x",
@@ -799,9 +925,11 @@ void audit_free(struct task_struct *tsk)
return;
/* Check for system calls that do not go through the exit
- * function (e.g., exit_group), then free context block. */
- if (context->in_syscall && context->auditable && context->pid != audit_pid)
- audit_log_exit(context);
+ * function (e.g., exit_group), then free context block.
+ * We use GFP_ATOMIC here because we might be doing this
+ * in the context of the idle thread */
+ if (context->in_syscall && context->auditable)
+ audit_log_exit(context, GFP_ATOMIC);
audit_free_context(context);
}
@@ -876,11 +1004,11 @@ void audit_syscall_entry(struct task_struct *tsk, int arch, int major,
state = context->state;
if (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT)
- state = audit_filter_syscall(tsk, context, &audit_entlist);
+ state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
if (likely(state == AUDIT_DISABLED))
return;
- context->serial = audit_serial();
+ context->serial = 0;
context->ctime = CURRENT_TIME;
context->in_syscall = 1;
context->auditable = !!(state == AUDIT_RECORD_CONTEXT);
@@ -903,10 +1031,10 @@ void audit_syscall_exit(struct task_struct *tsk, int valid, long return_code)
/* Not having a context here is ok, since the parent may have
* called __put_task_struct. */
if (likely(!context))
- return;
+ goto out;
- if (context->in_syscall && context->auditable && context->pid != audit_pid)
- audit_log_exit(context);
+ if (context->in_syscall && context->auditable)
+ audit_log_exit(context, GFP_KERNEL);
context->in_syscall = 0;
context->auditable = 0;
@@ -919,9 +1047,9 @@ void audit_syscall_exit(struct task_struct *tsk, int valid, long return_code)
} else {
audit_free_names(context);
audit_free_aux(context);
- audit_zero_context(context, context->state);
tsk->audit_context = context;
}
+ out:
put_task_struct(tsk);
}
@@ -996,7 +1124,7 @@ void audit_putname(const char *name)
/* Store the inode and device from a lookup. Called from
* fs/namei.c:path_lookup(). */
-void audit_inode(const char *name, const struct inode *inode)
+void audit_inode(const char *name, const struct inode *inode, unsigned flags)
{
int idx;
struct audit_context *context = current->audit_context;
@@ -1022,17 +1150,20 @@ void audit_inode(const char *name, const struct inode *inode)
++context->ino_count;
#endif
}
- context->names[idx].ino = inode->i_ino;
- context->names[idx].dev = inode->i_sb->s_dev;
- context->names[idx].mode = inode->i_mode;
- context->names[idx].uid = inode->i_uid;
- context->names[idx].gid = inode->i_gid;
- context->names[idx].rdev = inode->i_rdev;
+ context->names[idx].flags = flags;
+ context->names[idx].ino = inode->i_ino;
+ context->names[idx].dev = inode->i_sb->s_dev;
+ context->names[idx].mode = inode->i_mode;
+ context->names[idx].uid = inode->i_uid;
+ context->names[idx].gid = inode->i_gid;
+ context->names[idx].rdev = inode->i_rdev;
}
void auditsc_get_stamp(struct audit_context *ctx,
struct timespec *t, unsigned int *serial)
{
+ if (!ctx->serial)
+ ctx->serial = audit_serial();
t->tv_sec = ctx->ctime.tv_sec;
t->tv_nsec = ctx->ctime.tv_nsec;
*serial = ctx->serial;
@@ -1044,7 +1175,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
if (task->audit_context) {
struct audit_buffer *ab;
- ab = audit_log_start(NULL, AUDIT_LOGIN);
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
if (ab) {
audit_log_format(ab, "login pid=%d uid=%u "
"old auid=%u new auid=%u",
@@ -1153,7 +1284,7 @@ void audit_signal_info(int sig, struct task_struct *t)
extern pid_t audit_sig_pid;
extern uid_t audit_sig_uid;
- if (unlikely(audit_pid && t->pid == audit_pid)) {
+ if (unlikely(audit_pid && t->tgid == audit_pid)) {
if (sig == SIGTERM || sig == SIGHUP) {
struct audit_context *ctx = current->audit_context;
audit_sig_pid = current->pid;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 79866bc6b3a..45a5719a010 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -968,8 +968,6 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
char *page;
ssize_t retval = 0;
char *s;
- char *start;
- size_t n;
if (!(page = (char *)__get_free_page(GFP_KERNEL)))
return -ENOMEM;
@@ -999,14 +997,7 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
*s++ = '\n';
*s = '\0';
- /* Do nothing if *ppos is at the eof or beyond the eof. */
- if (s - page <= *ppos)
- return 0;
-
- start = page + *ppos;
- n = s - start;
- retval = n - copy_to_user(buf, start, min(n, nbytes));
- *ppos += retval;
+ retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
out:
free_page((unsigned long)page);
return retval;
diff --git a/kernel/exit.c b/kernel/exit.c
index 6d2089a1bce..43077732619 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -371,6 +371,12 @@ static inline void close_files(struct files_struct * files)
struct fdtable *fdt;
j = 0;
+
+ /*
+ * It is safe to dereference the fd table without RCU or
+ * ->file_lock because this is the last reference to the
+ * files structure.
+ */
fdt = files_fdtable(files);
for (;;) {
unsigned long set;
@@ -1197,7 +1203,7 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap,
exit_code = p->exit_code;
if (unlikely(!exit_code) ||
- unlikely(p->state > TASK_STOPPED))
+ unlikely(p->state & TASK_TRACED))
goto bail_ref;
return wait_noreap_copyout(p, pid, uid,
why, (exit_code << 8) | 0x7f,
diff --git a/kernel/fork.c b/kernel/fork.c
index 8149f360288..533ce27f4b2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1062,7 +1062,8 @@ static task_t *copy_process(unsigned long clone_flags,
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
- if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed)))
+ if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
+ !cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/*
diff --git a/kernel/module.c b/kernel/module.c
index 4b39d3793c7..ff5c500ab62 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/moduleloader.h>
#include <linux/init.h>
+#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/elf.h>
@@ -498,7 +499,7 @@ static inline int try_force(unsigned int flags)
{
int ret = (flags & O_TRUNC);
if (ret)
- tainted |= TAINT_FORCED_MODULE;
+ add_taint(TAINT_FORCED_MODULE);
return ret;
}
#else
@@ -897,7 +898,7 @@ static int check_version(Elf_Shdr *sechdrs,
if (!(tainted & TAINT_FORCED_MODULE)) {
printk("%s: no version for \"%s\" found: kernel tainted.\n",
mod->name, symname);
- tainted |= TAINT_FORCED_MODULE;
+ add_taint(TAINT_FORCED_MODULE);
}
return 1;
}
@@ -1352,7 +1353,7 @@ static void set_license(struct module *mod, const char *license)
if (!mod->license_gplok && !(tainted & TAINT_PROPRIETARY_MODULE)) {
printk(KERN_WARNING "%s: module license '%s' taints kernel.\n",
mod->name, license);
- tainted |= TAINT_PROPRIETARY_MODULE;
+ add_taint(TAINT_PROPRIETARY_MODULE);
}
}
@@ -1610,7 +1611,7 @@ static struct module *load_module(void __user *umod,
modmagic = get_modinfo(sechdrs, infoindex, "vermagic");
/* This is allowed: modprobe --force will invalidate it. */
if (!modmagic) {
- tainted |= TAINT_FORCED_MODULE;
+ add_taint(TAINT_FORCED_MODULE);
printk(KERN_WARNING "%s: no version magic, tainting kernel.\n",
mod->name);
} else if (!same_magic(modmagic, vermagic)) {
@@ -1739,7 +1740,7 @@ static struct module *load_module(void __user *umod,
(mod->num_gpl_syms && !gplcrcindex)) {
printk(KERN_WARNING "%s: No versions for exported symbols."
" Tainting kernel.\n", mod->name);
- tainted |= TAINT_FORCED_MODULE;
+ add_taint(TAINT_FORCED_MODULE);
}
#endif
diff --git a/kernel/params.c b/kernel/params.c
index fbf173215fd..1a8614bac5d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -80,8 +80,6 @@ static char *next_arg(char *args, char **param, char **val)
int in_quote = 0, quoted = 0;
char *next;
- /* Chew any extra spaces */
- while (*args == ' ') args++;
if (*args == '"') {
args++;
in_quote = 1;
@@ -121,6 +119,10 @@ static char *next_arg(char *args, char **param, char **val)
next = args + i + 1;
} else
next = args + i;
+
+ /* Chew up trailing spaces. */
+ while (*next == ' ')
+ next++;
return next;
}
@@ -135,6 +137,10 @@ int parse_args(const char *name,
DEBUGP("Parsing ARGS: %s\n", args);
+ /* Chew leading spaces */
+ while (*args == ' ')
+ args++;
+
while (*args) {
int ret;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 396c7873e80..46a5e5acff9 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -29,7 +29,7 @@ config PM_DEBUG
config SOFTWARE_SUSPEND
bool "Software Suspend"
- depends on PM && SWAP && (X86 || ((FVR || PPC32) && !SMP))
+ depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FVR || PPC32) && !SMP)
---help---
Enable the possibility of suspending the machine.
It doesn't need APM.
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 2d8bf054d03..761956e813f 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -17,12 +17,12 @@
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/mount.h>
+#include <linux/pm.h>
#include "power.h"
extern suspend_disk_method_t pm_disk_mode;
-extern struct pm_ops * pm_ops;
extern int swsusp_suspend(void);
extern int swsusp_write(void);
@@ -49,13 +49,11 @@ dev_t swsusp_resume_device;
static void power_down(suspend_disk_method_t mode)
{
- unsigned long flags;
int error = 0;
- local_irq_save(flags);
switch(mode) {
case PM_DISK_PLATFORM:
- device_shutdown();
+ kernel_power_off_prepare();
error = pm_ops->enter(PM_SUSPEND_DISK);
break;
case PM_DISK_SHUTDOWN:
diff --git a/kernel/power/power.h b/kernel/power/power.h
index cd6a3493cc0..6748de23e83 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -1,7 +1,7 @@
#include <linux/suspend.h>
#include <linux/utsname.h>
-/* With SUSPEND_CONSOLE defined, it suspend looks *really* cool, but
+/* With SUSPEND_CONSOLE defined suspend looks *really* cool, but
we probably do not take enough locks for switching consoles, etc,
so bad things might happen.
*/
@@ -9,6 +9,9 @@
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
#endif
+#define MAX_PBES ((PAGE_SIZE - sizeof(struct new_utsname) \
+ - 4 - 3*sizeof(unsigned long) - sizeof(int) \
+ - sizeof(void *)) / sizeof(swp_entry_t))
struct swsusp_info {
struct new_utsname uts;
@@ -18,7 +21,7 @@ struct swsusp_info {
unsigned long image_pages;
unsigned long pagedir_pages;
suspend_pagedir_t * suspend_pagedir;
- swp_entry_t pagedir[768];
+ swp_entry_t pagedir[MAX_PBES];
} __attribute__((aligned(PAGE_SIZE)));
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index d967e875ee8..acf79ac1cb6 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -363,7 +363,7 @@ static void lock_swapdevices(void)
}
/**
- * write_swap_page - Write one page to a fresh swap location.
+ * write_page - Write one page to a fresh swap location.
* @addr: Address we're writing.
* @loc: Place to store the entry we used.
*
@@ -402,15 +402,14 @@ static int write_page(unsigned long addr, swp_entry_t * loc)
static void data_free(void)
{
swp_entry_t entry;
- int i;
+ struct pbe * p;
- for (i = 0; i < nr_copy_pages; i++) {
- entry = (pagedir_nosave + i)->swap_address;
+ for_each_pbe(p, pagedir_nosave) {
+ entry = p->swap_address;
if (entry.val)
swap_free(entry);
else
break;
- (pagedir_nosave + i)->swap_address = (swp_entry_t){0};
}
}
@@ -863,6 +862,9 @@ static int alloc_image_pages(void)
return 0;
}
+/* Free pages we allocated for suspend. Suspend pages are alocated
+ * before atomic copy, so we need to free them after resume.
+ */
void swsusp_free(void)
{
BUG_ON(PageNosave(virt_to_page(pagedir_save)));
@@ -918,6 +920,7 @@ static int swsusp_alloc(void)
pagedir_nosave = NULL;
nr_copy_pages = calc_nr(nr_copy_pages);
+ nr_copy_pages_check = nr_copy_pages;
pr_debug("suspend: (pages needed: %d + %d free: %d)\n",
nr_copy_pages, PAGES_FOR_IO, nr_free_pages());
@@ -928,6 +931,10 @@ static int swsusp_alloc(void)
if (!enough_swap())
return -ENOSPC;
+ if (MAX_PBES < nr_copy_pages / PBES_PER_PAGE +
+ !!(nr_copy_pages % PBES_PER_PAGE))
+ return -ENOSPC;
+
if (!(pagedir_save = alloc_pagedir(nr_copy_pages))) {
printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
return -ENOMEM;
@@ -940,7 +947,6 @@ static int swsusp_alloc(void)
return error;
}
- nr_copy_pages_check = nr_copy_pages;
return 0;
}
@@ -1213,8 +1219,9 @@ static struct pbe * swsusp_pagedir_relocate(struct pbe *pblist)
free_pagedir(pblist);
free_eaten_memory();
pblist = NULL;
- }
- else
+ /* Is this even worth handling? It should never ever happen, and we
+ have just lost user's state, anyway... */
+ } else
printk("swsusp: Relocated %d pages\n", rel);
return pblist;
@@ -1434,9 +1441,9 @@ static int read_pagedir(struct pbe *pblist)
}
if (error)
- free_page((unsigned long)pblist);
-
- BUG_ON(i != swsusp_info.pagedir_pages);
+ free_pagedir(pblist);
+ else
+ BUG_ON(i != swsusp_info.pagedir_pages);
return error;
}
diff --git a/kernel/printk.c b/kernel/printk.c
index a967605bc2e..4b8f0f9230a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -488,6 +488,11 @@ static int __init printk_time_setup(char *str)
__setup("time", printk_time_setup);
+__attribute__((weak)) unsigned long long printk_clock(void)
+{
+ return sched_clock();
+}
+
/*
* This is printk. It can be called from any context. We want it to work.
*
@@ -565,7 +570,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
loglev_char = default_message_loglevel
+ '0';
}
- t = sched_clock();
+ t = printk_clock();
nanosec_rem = do_div(t, 1000000000);
tlen = sprintf(tbuf,
"<%c>[%5lu.%06lu] ",
diff --git a/kernel/sched.c b/kernel/sched.c
index 81b3a96ed2d..1f31a528fdb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -294,6 +294,10 @@ static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ /* this is a valid case when another task releases the spinlock */
+ rq->lock.owner = current;
+#endif
spin_unlock_irq(&rq->lock);
}
@@ -1529,10 +1533,6 @@ static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
* Manfred Spraul <manfred@colorfullife.com>
*/
prev_task_flags = prev->flags;
-#ifdef CONFIG_DEBUG_SPINLOCK
- /* this is a valid case when another task releases the spinlock */
- rq->lock.owner = current;
-#endif
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
if (mm)
diff --git a/kernel/signal.c b/kernel/signal.c
index b92c3c9f8b9..619b027e92b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -936,34 +936,31 @@ force_sig_specific(int sig, struct task_struct *t)
* as soon as they're available, so putting the signal on the shared queue
* will be equivalent to sending it to one such thread.
*/
-#define wants_signal(sig, p, mask) \
- (!sigismember(&(p)->blocked, sig) \
- && !((p)->state & mask) \
- && !((p)->flags & PF_EXITING) \
- && (task_curr(p) || !signal_pending(p)))
-
+static inline int wants_signal(int sig, struct task_struct *p)
+{
+ if (sigismember(&p->blocked, sig))
+ return 0;
+ if (p->flags & PF_EXITING)
+ return 0;
+ if (sig == SIGKILL)
+ return 1;
+ if (p->state & (TASK_STOPPED | TASK_TRACED))
+ return 0;
+ return task_curr(p) || !signal_pending(p);
+}
static void
__group_complete_signal(int sig, struct task_struct *p)
{
- unsigned int mask;
struct task_struct *t;
/*
- * Don't bother traced and stopped tasks (but
- * SIGKILL will punch through that).
- */
- mask = TASK_STOPPED | TASK_TRACED;
- if (sig == SIGKILL)
- mask = 0;
-
- /*
* Now find a thread we can wake up to take the signal off the queue.
*
* If the main thread wants the signal, it gets first crack.
* Probably the least surprising to the average bear.
*/
- if (wants_signal(sig, p, mask))
+ if (wants_signal(sig, p))
t = p;
else if (thread_group_empty(p))
/*
@@ -981,7 +978,7 @@ __group_complete_signal(int sig, struct task_struct *p)
t = p->signal->curr_target = p;
BUG_ON(t->tgid != p->tgid);
- while (!wants_signal(sig, t, mask)) {
+ while (!wants_signal(sig, t)) {
t = next_thread(t);
if (t == p->signal->curr_target)
/*
@@ -1766,7 +1763,8 @@ do_signal_stop(int signr)
* stop is always done with the siglock held,
* so this check has no races.
*/
- if (t->state < TASK_STOPPED) {
+ if (!t->exit_state &&
+ !(t->state & (TASK_STOPPED|TASK_TRACED))) {
stop_count++;
signal_wake_up(t, 0);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index c80412be230..2fa1ed18123 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -361,17 +361,35 @@ out_unlock:
return retval;
}
+/**
+ * emergency_restart - reboot the system
+ *
+ * Without shutting down any hardware or taking any locks
+ * reboot the system. This is called when we know we are in
+ * trouble so this is our best effort to reboot. This is
+ * safe to call in interrupt context.
+ */
void emergency_restart(void)
{
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
-void kernel_restart(char *cmd)
+/**
+ * kernel_restart - reboot the system
+ *
+ * Shutdown everything and perform a clean reboot.
+ * This is not safe to call in interrupt context.
+ */
+void kernel_restart_prepare(char *cmd)
{
notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
device_shutdown();
+}
+void kernel_restart(char *cmd)
+{
+ kernel_restart_prepare(cmd);
if (!cmd) {
printk(KERN_EMERG "Restarting system.\n");
} else {
@@ -382,6 +400,12 @@ void kernel_restart(char *cmd)
}
EXPORT_SYMBOL_GPL(kernel_restart);
+/**
+ * kernel_kexec - reboot the system
+ *
+ * Move into place and start executing a preloaded standalone
+ * executable. If nothing was preloaded return an error.
+ */
void kernel_kexec(void)
{
#ifdef CONFIG_KEXEC
@@ -390,9 +414,7 @@ void kernel_kexec(void)
if (!image) {
return;
}
- notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
- system_state = SYSTEM_RESTART;
- device_shutdown();
+ kernel_restart_prepare(NULL);
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
machine_kexec(image);
@@ -400,21 +422,39 @@ void kernel_kexec(void)
}
EXPORT_SYMBOL_GPL(kernel_kexec);
-void kernel_halt(void)
+/**
+ * kernel_halt - halt the system
+ *
+ * Shutdown everything and perform a clean system halt.
+ */
+void kernel_halt_prepare(void)
{
notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL);
system_state = SYSTEM_HALT;
device_shutdown();
+}
+void kernel_halt(void)
+{
+ kernel_halt_prepare();
printk(KERN_EMERG "System halted.\n");
machine_halt();
}
EXPORT_SYMBOL_GPL(kernel_halt);
-void kernel_power_off(void)
+/**
+ * kernel_power_off - power_off the system
+ *
+ * Shutdown everything and perform a clean system power_off.
+ */
+void kernel_power_off_prepare(void)
{
notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL);
system_state = SYSTEM_POWER_OFF;
device_shutdown();
+}
+void kernel_power_off(void)
+{
+ kernel_power_off_prepare();
printk(KERN_EMERG "Power down.\n");
machine_power_off();
}
@@ -1728,8 +1768,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
error = put_user(current->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
- if (current->mm->dumpable)
- error = 1;
+ error = current->mm->dumpable;
break;
case PR_SET_DUMPABLE:
if (arg2 < 0 || arg2 > 2) {
diff --git a/kernel/timer.c b/kernel/timer.c
index f4152fcd9f8..3ba10fa35b6 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1151,19 +1151,22 @@ fastcall signed long __sched schedule_timeout(signed long timeout)
out:
return timeout < 0 ? 0 : timeout;
}
-
EXPORT_SYMBOL(schedule_timeout);
+/*
+ * We can use __set_current_state() here because schedule_timeout() calls
+ * schedule() unconditionally.
+ */
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
- set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_INTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_interruptible);
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
- set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(TASK_UNINTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-10 07:31:32 +0000