summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c434
-rw-r--r--kernel/auditfilter.c54
-rw-r--r--kernel/auditsc.c349
-rw-r--r--kernel/futex.c42
-rw-r--r--kernel/futex_compat.c3
-rw-r--r--kernel/hrtimer.c2
-rw-r--r--kernel/softlockup.c30
-rw-r--r--kernel/sysctl.c11
-rw-r--r--kernel/time.c1
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/time/timekeeping.c6
-rw-r--r--kernel/time/timer_list.c2
12 files changed, 532 insertions, 404 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 801c946..c8555b1 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -66,10 +66,11 @@
* (Initialization happens after skb_init is called.) */
static int audit_initialized;
-/* 0 - no auditing
- * 1 - auditing enabled
- * 2 - auditing enabled and configuration is locked/unchangeable. */
+#define AUDIT_OFF 0
+#define AUDIT_ON 1
+#define AUDIT_LOCKED 2
int audit_enabled;
+int audit_ever_enabled;
/* Default state when kernel boots without any parameters. */
static int audit_default;
@@ -152,8 +153,10 @@ struct audit_buffer {
static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
{
- struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
- nlh->nlmsg_pid = pid;
+ if (ab) {
+ struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
+ nlh->nlmsg_pid = pid;
+ }
}
void audit_panic(const char *message)
@@ -163,7 +166,8 @@ void audit_panic(const char *message)
case AUDIT_FAIL_SILENT:
break;
case AUDIT_FAIL_PRINTK:
- printk(KERN_ERR "audit: %s\n", message);
+ if (printk_ratelimit())
+ printk(KERN_ERR "audit: %s\n", message);
break;
case AUDIT_FAIL_PANIC:
panic("audit: %s\n", message);
@@ -231,161 +235,107 @@ void audit_log_lost(const char *message)
}
if (print) {
- printk(KERN_WARNING
- "audit: audit_lost=%d audit_rate_limit=%d audit_backlog_limit=%d\n",
- atomic_read(&audit_lost),
- audit_rate_limit,
- audit_backlog_limit);
+ if (printk_ratelimit())
+ printk(KERN_WARNING
+ "audit: audit_lost=%d audit_rate_limit=%d "
+ "audit_backlog_limit=%d\n",
+ atomic_read(&audit_lost),
+ audit_rate_limit,
+ audit_backlog_limit);
audit_panic(message);
}
}
-static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid)
+static int audit_log_config_change(char *function_name, int new, int old,
+ uid_t loginuid, u32 sid, int allow_changes)
{
- int res, rc = 0, old = audit_rate_limit;
-
- /* check if we are locked */
- if (audit_enabled == 2)
- res = 0;
- else
- res = 1;
+ struct audit_buffer *ab;
+ int rc = 0;
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+ audit_log_format(ab, "%s=%d old=%d by auid=%u", function_name, new,
+ old, loginuid);
if (sid) {
char *ctx = NULL;
u32 len;
- if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) {
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_rate_limit=%d old=%d by auid=%u"
- " subj=%s res=%d",
- limit, old, loginuid, ctx, res);
+
+ rc = selinux_sid_to_string(sid, &ctx, &len);
+ if (rc) {
+ audit_log_format(ab, " sid=%u", sid);
+ allow_changes = 0; /* Something weird, deny request */
+ } else {
+ audit_log_format(ab, " subj=%s", ctx);
kfree(ctx);
- } else
- res = 0; /* Something weird, deny request */
+ }
}
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_rate_limit=%d old=%d by auid=%u res=%d",
- limit, old, loginuid, res);
-
- /* If we are allowed, make the change */
- if (res == 1)
- audit_rate_limit = limit;
- /* Not allowed, update reason */
- else if (rc == 0)
- rc = -EPERM;
+ audit_log_format(ab, " res=%d", allow_changes);
+ audit_log_end(ab);
return rc;
}
-static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid)
+static int audit_do_config_change(char *function_name, int *to_change,
+ int new, uid_t loginuid, u32 sid)
{
- int res, rc = 0, old = audit_backlog_limit;
+ int allow_changes, rc = 0, old = *to_change;
/* check if we are locked */
- if (audit_enabled == 2)
- res = 0;
+ if (audit_enabled == AUDIT_LOCKED)
+ allow_changes = 0;
else
- res = 1;
+ allow_changes = 1;
- if (sid) {
- char *ctx = NULL;
- u32 len;
- if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) {
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_backlog_limit=%d old=%d by auid=%u"
- " subj=%s res=%d",
- limit, old, loginuid, ctx, res);
- kfree(ctx);
- } else
- res = 0; /* Something weird, deny request */
+ if (audit_enabled != AUDIT_OFF) {
+ rc = audit_log_config_change(function_name, new, old,
+ loginuid, sid, allow_changes);
+ if (rc)
+ allow_changes = 0;
}
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_backlog_limit=%d old=%d by auid=%u res=%d",
- limit, old, loginuid, res);
/* If we are allowed, make the change */
- if (res == 1)
- audit_backlog_limit = limit;
+ if (allow_changes == 1)
+ *to_change = new;
/* Not allowed, update reason */
else if (rc == 0)
rc = -EPERM;
return rc;
}
-static int audit_set_enabled(int state, uid_t loginuid, u32 sid)
+static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid)
+{
+ return audit_do_config_change("audit_rate_limit", &audit_rate_limit,
+ limit, loginuid, sid);
+}
+
+static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid)
{
- int res, rc = 0, old = audit_enabled;
+ return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit,
+ limit, loginuid, sid);
+}
- if (state < 0 || state > 2)
+static int audit_set_enabled(int state, uid_t loginuid, u32 sid)
+{
+ int rc;
+ if (state < AUDIT_OFF || state > AUDIT_LOCKED)
return -EINVAL;
- /* check if we are locked */
- if (audit_enabled == 2)
- res = 0;
- else
- res = 1;
+ rc = audit_do_config_change("audit_enabled", &audit_enabled, state,
+ loginuid, sid);
- if (sid) {
- char *ctx = NULL;
- u32 len;
- if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) {
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_enabled=%d old=%d by auid=%u"
- " subj=%s res=%d",
- state, old, loginuid, ctx, res);
- kfree(ctx);
- } else
- res = 0; /* Something weird, deny request */
- }
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_enabled=%d old=%d by auid=%u res=%d",
- state, old, loginuid, res);
+ if (!rc)
+ audit_ever_enabled |= !!state;
- /* If we are allowed, make the change */
- if (res == 1)
- audit_enabled = state;
- /* Not allowed, update reason */
- else if (rc == 0)
- rc = -EPERM;
return rc;
}
static int audit_set_failure(int state, uid_t loginuid, u32 sid)
{
- int res, rc = 0, old = audit_failure;
-
if (state != AUDIT_FAIL_SILENT
&& state != AUDIT_FAIL_PRINTK
&& state != AUDIT_FAIL_PANIC)
return -EINVAL;
- /* check if we are locked */
- if (audit_enabled == 2)
- res = 0;
- else
- res = 1;
-
- if (sid) {
- char *ctx = NULL;
- u32 len;
- if ((rc = selinux_sid_to_string(sid, &ctx, &len)) == 0) {
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_failure=%d old=%d by auid=%u"
- " subj=%s res=%d",
- state, old, loginuid, ctx, res);
- kfree(ctx);
- } else
- res = 0; /* Something weird, deny request */
- }
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_failure=%d old=%d by auid=%u res=%d",
- state, old, loginuid, res);
-
- /* If we are allowed, make the change */
- if (res == 1)
- audit_failure = state;
- /* Not allowed, update reason */
- else if (rc == 0)
- rc = -EPERM;
- return rc;
+ return audit_do_config_change("audit_failure", &audit_failure, state,
+ loginuid, sid);
}
static int kauditd_thread(void *dummy)
@@ -405,7 +355,11 @@ static int kauditd_thread(void *dummy)
audit_pid = 0;
}
} else {
- printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0));
+ if (printk_ratelimit())
+ printk(KERN_NOTICE "%s\n", skb->data +
+ NLMSG_SPACE(0));
+ else
+ audit_log_lost("printk limit exceeded\n");
kfree_skb(skb);
}
} else {
@@ -573,6 +527,33 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
return err;
}
+static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type,
+ u32 pid, u32 uid, uid_t auid, u32 sid)
+{
+ int rc = 0;
+ char *ctx = NULL;
+ u32 len;
+
+ if (!audit_enabled) {
+ *ab = NULL;
+ return rc;
+ }
+
+ *ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
+ audit_log_format(*ab, "user pid=%d uid=%u auid=%u",
+ pid, uid, auid);
+ if (sid) {
+ rc = selinux_sid_to_string(sid, &ctx, &len);
+ if (rc)
+ audit_log_format(*ab, " ssid=%u", sid);
+ else
+ audit_log_format(*ab, " subj=%s", ctx);
+ kfree(ctx);
+ }
+
+ return rc;
+}
+
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
u32 uid, pid, seq, sid;
@@ -583,7 +564,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
u16 msg_type = nlh->nlmsg_type;
uid_t loginuid; /* loginuid of sender */
struct audit_sig_info *sig_data;
- char *ctx;
+ char *ctx = NULL;
u32 len;
err = audit_netlink_ok(skb, msg_type);
@@ -634,23 +615,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err < 0) return err;
}
if (status_get->mask & AUDIT_STATUS_PID) {
- int old = audit_pid;
- if (sid) {
- if ((err = selinux_sid_to_string(
- sid, &ctx, &len)))
- return err;
- else
- audit_log(NULL, GFP_KERNEL,
- AUDIT_CONFIG_CHANGE,
- "audit_pid=%d old=%d by auid=%u subj=%s",
- status_get->pid, old,
- loginuid, ctx);
- kfree(ctx);
- } else
- audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
- "audit_pid=%d old=%d by auid=%u",
- status_get->pid, old, loginuid);
- audit_pid = status_get->pid;
+ int new_pid = status_get->pid;
+
+ if (audit_enabled != AUDIT_OFF)
+ audit_log_config_change("audit_pid", new_pid,
+ audit_pid, loginuid,
+ sid, 1);
+
+ audit_pid = new_pid;
}
if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
err = audit_set_rate_limit(status_get->rate_limit,
@@ -673,64 +645,35 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err)
break;
}
- ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
- if (ab) {
- audit_log_format(ab,
- "user pid=%d uid=%u auid=%u",
- pid, uid, loginuid);
- if (sid) {
- if (selinux_sid_to_string(
- sid, &ctx, &len)) {
- audit_log_format(ab,
- " ssid=%u", sid);
- /* Maybe call audit_panic? */
- } else
- audit_log_format(ab,
- " subj=%s", ctx);
- kfree(ctx);
- }
- if (msg_type != AUDIT_USER_TTY)
- audit_log_format(ab, " msg='%.1024s'",
- (char *)data);
- else {
- int size;
-
- audit_log_format(ab, " msg=");
- size = nlmsg_len(nlh);
- audit_log_n_untrustedstring(ab, size,
- data);
- }
- audit_set_pid(ab, pid);
- audit_log_end(ab);
+ audit_log_common_recv_msg(&ab, msg_type, pid, uid,
+ loginuid, sid);
+
+ if (msg_type != AUDIT_USER_TTY)
+ audit_log_format(ab, " msg='%.1024s'",
+ (char *)data);
+ else {
+ int size;
+
+ audit_log_format(ab, " msg=");
+ size = nlmsg_len(nlh);
+ audit_log_n_untrustedstring(ab, size,
+ data);
}
+ audit_set_pid(ab, pid);
+ audit_log_end(ab);
}
break;
case AUDIT_ADD:
case AUDIT_DEL:
if (nlmsg_len(nlh) < sizeof(struct audit_rule))
return -EINVAL;
- if (audit_enabled == 2) {
- ab = audit_log_start(NULL, GFP_KERNEL,
- AUDIT_CONFIG_CHANGE);
- if (ab) {
- audit_log_format(ab,
- "pid=%d uid=%u auid=%u",
- pid, uid, loginuid);
- if (sid) {
- if (selinux_sid_to_string(
- sid, &ctx, &len)) {
- audit_log_format(ab,
- " ssid=%u", sid);
- /* Maybe call audit_panic? */
- } else
- audit_log_format(ab,
- " subj=%s", ctx);
- kfree(ctx);
- }
- audit_log_format(ab, " audit_enabled=%d res=0",
- audit_enabled);
- audit_log_end(ab);
- }
+ if (audit_enabled == AUDIT_LOCKED) {
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid,
+ uid, loginuid, sid);
+
+ audit_log_format(ab, " audit_enabled=%d res=0",
+ audit_enabled);
+ audit_log_end(ab);
return -EPERM;
}
/* fallthrough */
@@ -743,28 +686,13 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
case AUDIT_DEL_RULE:
if (nlmsg_len(nlh) < sizeof(struct audit_rule_data))
return -EINVAL;
- if (audit_enabled == 2) {
- ab = audit_log_start(NULL, GFP_KERNEL,
- AUDIT_CONFIG_CHANGE);
- if (ab) {
- audit_log_format(ab,
- "pid=%d uid=%u auid=%u",
- pid, uid, loginuid);
- if (sid) {
- if (selinux_sid_to_string(
- sid, &ctx, &len)) {
- audit_log_format(ab,
- " ssid=%u", sid);
- /* Maybe call audit_panic? */
- } else
- audit_log_format(ab,
- " subj=%s", ctx);
- kfree(ctx);
- }
- audit_log_format(ab, " audit_enabled=%d res=0",
- audit_enabled);
- audit_log_end(ab);
- }
+ if (audit_enabled == AUDIT_LOCKED) {
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid,
+ uid, loginuid, sid);
+
+ audit_log_format(ab, " audit_enabled=%d res=0",
+ audit_enabled);
+ audit_log_end(ab);
return -EPERM;
}
/* fallthrough */
@@ -775,19 +703,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
break;
case AUDIT_TRIM:
audit_trim_trees();
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
- if (!ab)
- break;
- audit_log_format(ab, "auid=%u", loginuid);
- if (sid) {
- u32 len;
- ctx = NULL;
- if (selinux_sid_to_string(sid, &ctx, &len))
- audit_log_format(ab, " ssid=%u", sid);
- else
- audit_log_format(ab, " subj=%s", ctx);
- kfree(ctx);
- }
+
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid,
+ uid, loginuid, sid);
+
audit_log_format(ab, " op=trim res=1");
audit_log_end(ab);
break;
@@ -817,22 +736,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
/* OK, here comes... */
err = audit_tag_tree(old, new);
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
- if (!ab) {
- kfree(old);
- kfree(new);
- break;
- }
- audit_log_format(ab, "auid=%u", loginuid);
- if (sid) {
- u32 len;
- ctx = NULL;
- if (selinux_sid_to_string(sid, &ctx, &len))
- audit_log_format(ab, " ssid=%u", sid);
- else
- audit_log_format(ab, " subj=%s", ctx);
- kfree(ctx);
- }
+ audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid,
+ uid, loginuid, sid);
+
audit_log_format(ab, " op=make_equiv old=");
audit_log_untrustedstring(ab, old);
audit_log_format(ab, " new=");
@@ -965,6 +871,7 @@ static int __init audit_init(void)
skb_queue_head_init(&audit_skb_queue);
audit_initialized = 1;
audit_enabled = audit_default;
+ audit_ever_enabled |= !!audit_default;
/* Register the callback with selinux. This callback will be invoked
* when a new policy is loaded. */
@@ -992,8 +899,10 @@ static int __init audit_enable(char *str)
printk(KERN_INFO "audit: %s%s\n",
audit_default ? "enabled" : "disabled",
audit_initialized ? "" : " (after initialization)");
- if (audit_initialized)
+ if (audit_initialized) {
audit_enabled = audit_default;
+ audit_ever_enabled |= !!audit_default;
+ }
return 1;
}
@@ -1130,7 +1039,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
{
struct audit_buffer *ab = NULL;
struct timespec t;
- unsigned int serial;
+ unsigned int uninitialized_var(serial);
int reserve;
unsigned long timeout_start = jiffies;
@@ -1164,7 +1073,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
remove_wait_queue(&audit_backlog_wait, &wait);
continue;
}
- if (audit_rate_check())
+ if (audit_rate_check() && printk_ratelimit())
printk(KERN_WARNING
"audit: audit_backlog=%d > "
"audit_backlog_limit=%d\n",
@@ -1249,6 +1158,7 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
goto out;
len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2);
}
+ va_end(args2);
if (len > 0)
skb_put(skb, len);
out:
@@ -1350,6 +1260,21 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen,
}
/**
+ * audit_string_contains_control - does a string need to be logged in hex
+ * @string - string to be checked
+ * @len - max length of the string to check
+ */
+int audit_string_contains_control(const char *string, size_t len)
+{
+ const unsigned char *p;
+ for (p = string; p < (const unsigned char *)string + len && *p; p++) {
+ if (*p == '"' || *p < 0x21 || *p > 0x7f)
+ return 1;
+ }
+ return 0;
+}
+
+/**
* audit_log_n_untrustedstring - log a string that may contain random characters
* @ab: audit_buffer
* @len: lenth of string (not including trailing null)
@@ -1363,19 +1288,13 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen,
* The caller specifies the number of characters in the string to log, which may
* or may not be the entire string.
*/
-const char *audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len,
- const char *string)
+void audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len,
+ const char *string)
{
- const unsigned char *p;
-
- for (p = string; p < (const unsigned char *)string + len && *p; p++) {
- if (*p == '"' || *p < 0x21 || *p > 0x7f) {
- audit_log_hex(ab, string, len);
- return string + len + 1;
- }
- }
- audit_log_n_string(ab, len, string);
- return p + 1;
+ if (audit_string_contains_control(string, len))
+ audit_log_hex(ab, string, len);
+ else
+ audit_log_n_string(ab, len, string);
}
/**
@@ -1386,9 +1305,9 @@ const char *audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len,
* Same as audit_log_n_untrustedstring(), except that strlen is used to
* determine string length.
*/
-const char *audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
+void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
{
- return audit_log_n_untrustedstring(ab, strlen(string), string);
+ audit_log_n_untrustedstring(ab, strlen(string), string);
}
/* This is a helper-function to print the escaped d_path */
@@ -1437,8 +1356,11 @@ void audit_log_end(struct audit_buffer *ab)
skb_queue_tail(&audit_skb_queue, ab->skb);
ab->skb = NULL;
wake_up_interruptible(&kauditd_wait);
+ } else if (printk_ratelimit()) {
+ struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
+ printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, ab->skb->data + NLMSG_SPACE(0));
} else {
- printk(KERN_NOTICE "%s\n", ab->skb->data + NLMSG_SPACE(0));
+ audit_log_lost("printk limit exceeded\n");
}
}
audit_buffer_free(ab);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 5d96f2c..6f19fd4 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -95,6 +95,8 @@ extern struct inotify_handle *audit_ih;
/* Inotify events we care about. */
#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF
+extern int audit_enabled;
+
void audit_free_parent(struct inotify_watch *i_watch)
{
struct audit_parent *parent;
@@ -974,7 +976,6 @@ static void audit_update_watch(struct audit_parent *parent,
struct audit_watch *owatch, *nwatch, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *oentry, *nentry;
- struct audit_buffer *ab;
mutex_lock(&audit_filter_mutex);
list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
@@ -1014,13 +1015,18 @@ static void audit_update_watch(struct audit_parent *parent,
call_rcu(&oentry->rcu, audit_free_rule_rcu);
}
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
- 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);
-
+ if (audit_enabled) {
+ struct audit_buffer *ab;
+ ab = audit_log_start(NULL, GFP_KERNEL,
+ AUDIT_CONFIG_CHANGE);
+ 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 */
}
@@ -1039,25 +1045,28 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
struct audit_watch *w, *nextw;
struct audit_krule *r, *nextr;
struct audit_entry *e;
- struct audit_buffer *ab;
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);
-
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
- 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);
-
+ if (audit_enabled) {
+ struct audit_buffer *ab;
+ ab = audit_log_start(NULL, GFP_KERNEL,
+ AUDIT_CONFIG_CHANGE);
+ 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_rcu(&e->list);
call_rcu(&e->rcu, audit_free_rule_rcu);
@@ -1495,6 +1504,9 @@ static void audit_log_rule_change(uid_t loginuid, u32 sid, char *action,
{
struct audit_buffer *ab;
+ if (!audit_enabled)
+ return;
+
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (!ab)
return;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index bce9ecd..1c06ecf 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -70,6 +70,7 @@
#include "audit.h"
extern struct list_head audit_filter_list[];
+extern int audit_ever_enabled;
/* AUDIT_NAMES is the number of slots we reserve in the audit_context
* for saving names from getname(). */
@@ -78,6 +79,9 @@ extern struct list_head audit_filter_list[];
/* Indicates that audit should log the full pathname. */
#define AUDIT_NAME_FULL -1
+/* no execve audit message should be longer than this (userspace limits) */
+#define MAX_EXECVE_AUDIT_LEN 7500
+
/* number of audit rules */
int audit_n_rules;
@@ -176,7 +180,11 @@ struct audit_aux_data_fd_pair {
struct audit_aux_data_pids {
struct audit_aux_data d;
pid_t target_pid[AUDIT_AUX_PIDS];
+ uid_t target_auid[AUDIT_AUX_PIDS];
+ uid_t target_uid[AUDIT_AUX_PIDS];
+ unsigned int target_sessionid[AUDIT_AUX_PIDS];
u32 target_sid[AUDIT_AUX_PIDS];
+ char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN];
int pid_count;
};
@@ -192,7 +200,6 @@ struct audit_context {
enum audit_state state;
unsigned int serial; /* serial number for record */
struct timespec ctime; /* time of syscall entry */
- uid_t loginuid; /* login uid (identity) */
int major; /* syscall number */
unsigned long argv[4]; /* syscall arguments */
int return_valid; /* return code is valid */
@@ -215,7 +222,11 @@ struct audit_context {
int arch;
pid_t target_pid;
+ uid_t target_auid;
+ uid_t target_uid;
+ unsigned int target_sessionid;
u32 target_sid;
+ char target_comm[TASK_COMM_LEN];
struct audit_tree_refs *trees, *first_trees;
int tree_count;
@@ -506,7 +517,7 @@ static int audit_filter_rules(struct task_struct *tsk,
case AUDIT_LOGINUID:
result = 0;
if (ctx)
- result = audit_comparator(ctx->loginuid, f->op, f->val);
+ result = audit_comparator(tsk->loginuid, f->op, f->val);
break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
@@ -702,7 +713,24 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
if (likely(!context))
return NULL;
context->return_valid = return_valid;
- context->return_code = return_code;
+
+ /*
+ * we need to fix up the return code in the audit logs if the actual
+ * return codes are later going to be fixed up by the arch specific
+ * signal handlers
+ *
+ * This is actually a test for:
+ * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
+ * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
+ *
+ * but is faster than a bunch of ||
+ */
+ if (unlikely(return_code <= -ERESTARTSYS) &&
+ (return_code >= -ERESTART_RESTARTBLOCK) &&
+ (return_code != -ENOIOCTLCMD))
+ context->return_code = -EINTR;
+ else
+ context->return_code = return_code;
if (context->in_syscall && !context->dummy && !context->auditable) {
enum audit_state state;
@@ -783,11 +811,8 @@ static inline void audit_free_aux(struct audit_context *context)
static inline void audit_zero_context(struct audit_context *context,
enum audit_state state)
{
- uid_t loginuid = context->loginuid;
-
memset(context, 0, sizeof(*context));
context->state = state;
- context->loginuid = loginuid;
}
static inline struct audit_context *audit_alloc_context(enum audit_state state)
@@ -814,7 +839,7 @@ int audit_alloc(struct task_struct *tsk)
struct audit_context *context;
enum audit_state state;
- if (likely(!audit_enabled))
+ if (likely(!audit_ever_enabled))
return 0; /* Return if not auditing. */
state = audit_filter_task(tsk);
@@ -826,11 +851,6 @@ int audit_alloc(struct task_struct *tsk)
return -ENOMEM;
}
- /* Preserve login uid */
- context->loginuid = -1;
- if (current->audit_context)
- context->loginuid = current->audit_context->loginuid;
-
tsk->audit_context = context;
set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
@@ -922,7 +942,8 @@ static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk
}
static int audit_log_pid_context(struct audit_context *context, pid_t pid,
- u32 sid)
+ uid_t auid, uid_t uid, unsigned int sessionid,
+ u32 sid, char *comm)
{
struct audit_buffer *ab;
char *s = NULL;
@@ -931,68 +952,204 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID);
if (!ab)
- return 1;
+ return rc;
+ audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, auid,
+ uid, sessionid);
if (selinux_sid_to_string(sid, &s, &len)) {
- audit_log_format(ab, "opid=%d obj=(none)", pid);
+ audit_log_format(ab, " obj=(none)");
rc = 1;
} else
- audit_log_format(ab, "opid=%d obj=%s", pid, s);
+ audit_log_format(ab, " obj=%s", s);
+ audit_log_format(ab, " ocomm=");
+ audit_log_untrustedstring(ab, comm);
audit_log_end(ab);
kfree(s);
return rc;
}
-static void audit_log_execve_info(struct audit_buffer *ab,
- struct audit_aux_data_execve *axi)
+/*
+ * to_send and len_sent accounting are very loose estimates. We aren't
+ * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being
+ * within about 500 bytes (next page boundry)
+ *
+ * why snprintf? an int is up to 12 digits long. if we just assumed when
+ * logging that a[%d]= was going to be 16 characters long we would be wasting
+ * space in every audit message. In one 7500 byte message we can log up to
+ * about 1000 min size arguments. That comes down to about 50% waste of space
+ * if we didn't do the snprintf to find out how long arg_num_len was.
+ */
+static int audit_log_single_execve_arg(struct audit_context *context,
+ struct audit_buffer **ab,
+ int arg_num,
+ size_t *len_sent,
+ const char __user *p,
+ char *buf)
{
- int i;
- long len, ret;
- const char __user *p;
- char *buf;
+ 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=\n */
+ size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3;
+ 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;
+ int ret;
+
+ /* strnlen_user includes the null we don't want to send */
+ len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;
- if (axi->mm != current->mm)
- return; /* execve failed, no additional info */
-
- p = (const char __user *)axi->mm->arg_start;
+ /*
+ * We just created this mm, if we can't find the strings
+ * we just copied into it something is _very_ wrong. Similar
+ * for strings that are too long, we should not have created
+ * any.
+ */
+ if (unlikely((len = -1) || len > MAX_ARG_STRLEN - 1)) {
+ WARN_ON(1);
+ send_sig(SIGKILL, current, 0);
+ }
- for (i = 0; i < axi->argc; i++, p += len) {
- len = strnlen_user(p, MAX_ARG_STRLEN);
+ /* walk the whole argument looking for non-ascii chars */
+ do {
+ if (len_left > MAX_EXECVE_AUDIT_LEN)
+ to_send = MAX_EXECVE_AUDIT_LEN;
+ else
+ to_send = len_left;
+ ret = copy_from_user(buf, tmp_p, to_send);
/*
- * We just created this mm, if we can't find the strings
- * we just copied into it something is _very_ wrong. Similar
- * for strings that are too long, we should not have created
- * any.
+ * There is no reason for this copy to be short. We just
+ * copied them here, and the mm hasn't been exposed to user-
+ * space yet.
*/
- if (!len || len > MAX_ARG_STRLEN) {
+ if (ret) {
WARN_ON(1);
send_sig(SIGKILL, current, 0);
}
-
- buf = kmalloc(len, GFP_KERNEL);
- if (!buf) {
- audit_panic("out of memory for argv string\n");
+ buf[to_send] = '\0';
+ has_cntl = audit_string_contains_control(buf, to_send);
+ if (has_cntl) {
+ /*
+ * hex messages get logged as 2 bytes, so we can only
+ * send half as much in each message
+ */
+ max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2;
break;
}
+ len_left -= to_send;
+ tmp_p += to_send;
+ } while (len_left > 0);
+
+ len_left = len;
+
+ if (len > max_execve_audit_len)
+ too_long = 1;
+
+ /* rewalk the argument actually logging the message */
+ for (i = 0; len_left > 0; i++) {
+ int room_left;
+
+ if (len_left > max_execve_audit_len)
+ to_send = max_execve_audit_len;
+ else
+ to_send = len_left;
+
+ /* do we have space left to send this argument in this ab? */
+ room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent;
+ if (has_cntl)
+ room_left -= (to_send * 2);
+ else
+ room_left -= to_send;
+ if (room_left < 0) {
+ *len_sent = 0;
+ audit_log_end(*ab);
+ *ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE);
+ if (!*ab)
+ return 0;
+ }
- ret = copy_from_user(buf, p, len);
/*
- * There is no reason for this copy to be short. We just
- * copied them here, and the mm hasn't been exposed to user-
- * space yet.
+ * first record needs to say how long the original string was
+ * so we can be sure nothing was lost.
+ */
+ if ((i == 0) && (too_long))
+ audit_log_format(*ab, "a%d_len=%ld ", arg_num,
+ has_cntl ? 2*len : len);
+
+ /*
+ * normally arguments are small enough to fit and we already
+ * filled buf above when we checked for control characters
+ * so don't bother with another copy_from_user
*/
+ if (len >= max_execve_audit_len)
+ ret = copy_from_user(buf, p, to_send);
+ else
+ ret = 0;
if (ret) {
WARN_ON(1);
send_sig(SIGKILL, current, 0);
}
+ buf[to_send] = '\0';
+
+ /* actually log it */
+ audit_log_format(*ab, "a%d", arg_num);
+ if (too_long)
+ audit_log_format(*ab, "[%d]", i);
+ audit_log_format(*ab, "=");
+ if (has_cntl)
+ audit_log_hex(*ab, buf, to_send);
+ else
+ audit_log_format(*ab, "\"%s\"", buf);
+ audit_log_format(*ab, "\n");
+
+ p += to_send;
+ len_left -= to_send;
+ *len_sent += arg_num_len;
+ if (has_cntl)
+ *len_sent += to_send * 2;
+ else
+ *len_sent += to_send;
+ }
+ /* include the null we didn't log */
+ return len + 1;
+}
- audit_log_format(ab, "a%d=", i);
- audit_log_untrustedstring(ab, buf);
- audit_log_format(ab, "\n");
+static void audit_log_execve_info(struct audit_context *context,
+ struct audit_buffer **ab,
+ struct audit_aux_data_execve *axi)
+{
+ int i;
+ size_t len, len_sent = 0;
+ const char __user *p;
+ char *buf;
+
+ if (axi->mm != current->mm)
+ return; /* execve failed, no additional info */
+
+ p = (const char __user *)axi->mm->arg_start;
+
+ audit_log_format(*ab, "argc=%d ", axi->argc);
+
+ /*
+ * we need some kernel buffer to hold the userspace args. Just
+ * allocate one big one rather than allocating one of the right size
+ * for every single argument inside audit_log_single_execve_arg()
+ * should be <8k allocation so should be pretty safe.
+ */
+ buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
+ if (!buf) {
+ audit_panic("out of memory for argv string\n");
+ return;
+ }
- kfree(buf);
+ for (i = 0; i < axi->argc; i++) {
+ len = audit_log_single_execve_arg(context, ab, i,
+ &len_sent, p, buf);
+ if (len <= 0)
+ break;
+ p += len;
}
+ kfree(buf);
}
static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
@@ -1039,7 +1196,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
" a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
" ppid=%d pid=%d auid=%u uid=%u gid=%u"
" euid=%u suid=%u fsuid=%u"
- " egid=%u sgid=%u fsgid=%u tty=%s",
+ " egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
context->argv[0],
context->argv[1],
context->argv[2],
@@ -1047,11 +1204,12 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
context->name_count,
context->ppid,
context->pid,
- context->loginuid,
+ tsk->loginuid,
context->uid,
context->gid,
context->euid, context->suid, context->fsuid,
- context->egid, context->sgid, context->fsgid, tty);
+ context->egid, context->sgid, context->fsgid, tty,
+ tsk->sessionid);
mutex_unlock(&tty_mutex);
@@ -1135,7 +1293,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
case AUDIT_EXECVE: {
struct audit_aux_data_execve *axi = (void *)aux;
- audit_log_execve_info(ab, axi);
+ audit_log_execve_info(context, &ab, axi);
break; }
case AUDIT_SOCKETCALL: {
@@ -1168,13 +1326,19 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
for (i = 0; i < axs->pid_count; i++)
if (audit_log_pid_context(context, axs->target_pid[i],
- axs->target_sid[i]))
+ axs->target_auid[i],
+ axs->target_uid[i],
+ axs->target_sessionid[i],
+ axs->target_sid[i],
+ axs->target_comm[i]))
call_panic = 1;
}
if (context->target_pid &&
audit_log_pid_context(context, context->target_pid,
- context->target_sid))
+ context->target_auid, context->target_uid,
+ context->target_sessionid,
+ context->target_sid, context->target_comm))
call_panic = 1;
if (context->pwd && context->pwdmnt) {
@@ -1242,6 +1406,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
audit_log_end(ab);
}
+
+ /* Send end of event record to help user space know we are finished */
+ ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
+ if (ab)
+ audit_log_end(ab);
if (call_panic)
audit_panic("error converting sid to string");
}
@@ -1766,6 +1935,9 @@ void auditsc_get_stamp(struct audit_context *ctx,
ctx->auditable = 1;
}
+/* global counter which is incremented every time something logs in */
+static atomic_t session_id = ATOMIC_INIT(0);
+
/**
* audit_set_loginuid - set a task's audit_context loginuid
* @task: task whose audit context is being modified
@@ -1777,41 +1949,29 @@ void auditsc_get_stamp(struct audit_context *ctx,
*/
int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
{
+ unsigned int sessionid = atomic_inc_return(&session_id);
struct audit_context *context = task->audit_context;
- if (context) {
- /* Only log if audit is enabled */
- if (context->in_syscall) {
- struct audit_buffer *ab;
-
- 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",
- task->pid, task->uid,
- context->loginuid, loginuid);
- audit_log_end(ab);
- }
+ if (context && context->in_syscall) {
+ struct audit_buffer *ab;
+
+ 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"
+ " old ses=%u new ses=%u",
+ task->pid, task->uid,
+ task->loginuid, loginuid,
+ task->sessionid, sessionid);
+ audit_log_end(ab);
}
- context->loginuid = loginuid;
}
+ task->sessionid = sessionid;
+ task->loginuid = loginuid;
return 0;
}
/**
- * audit_get_loginuid - get the loginuid for an audit_context
- * @ctx: the audit_context
- *
- * Returns the context's loginuid or -1 if @ctx is NULL.
- */
-uid_t audit_get_loginuid(struct audit_context *ctx)
-{
- return ctx ? ctx->loginuid : -1;
-}
-
-EXPORT_SYMBOL(audit_get_loginuid);
-
-/**
* __audit_mq_open - record audit data for a POSIX MQ open
* @oflag: open flag
* @mode: mode bits
@@ -2070,8 +2230,6 @@ int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode
return 0;
}
-int audit_argv_kb = 32;
-
int audit_bprm(struct linux_binprm *bprm)
{
struct audit_aux_data_execve *ax;
@@ -2080,14 +2238,6 @@ int audit_bprm(struct linux_binprm *bprm)
if (likely(!audit_enabled || !context || context->dummy))
return 0;
- /*
- * Even though the stack code doesn't limit the arg+env size any more,
- * the audit code requires that _all_ arguments be logged in a single
- * netlink skb. Hence cap it :-(
- */
- if (bprm->argv_len > (audit_argv_kb << 10))
- return -E2BIG;
-
ax = kmalloc(sizeof(*ax), GFP_KERNEL);
if (!ax)
return -ENOMEM;
@@ -2193,7 +2343,11 @@ void __audit_ptrace(struct task_struct *t)
struct audit_context *context = current->audit_context;
context->target_pid = t->pid;
+ context->target_auid = audit_get_loginuid(t);
+ context->target_uid = t->uid;
+ context->target_sessionid = audit_get_sessionid(t);
selinux_get_task_sid(t, &context->target_sid);
+ memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
}
/**
@@ -2216,8 +2370,8 @@ int __audit_signal_info(int sig, struct task_struct *t)
if (audit_pid && t->tgid == audit_pid) {
if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) {
audit_sig_pid = tsk->pid;
- if (ctx)
- audit_sig_uid = ctx->loginuid;
+ if (tsk->loginuid != -1)
+ audit_sig_uid = tsk->loginuid;
else
audit_sig_uid = tsk->uid;
selinux_get_task_sid(tsk, &audit_sig_sid);
@@ -2230,7 +2384,11 @@ int __audit_signal_info(int sig, struct task_struct *t)
* in audit_context */
if (!ctx->target_pid) {
ctx->target_pid = t->tgid;
+ ctx->target_auid = audit_get_loginuid(t);
+ ctx->target_uid = t->uid;
+ ctx->target_sessionid = audit_get_sessionid(t);
selinux_get_task_sid(t, &ctx->target_sid);
+ memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
return 0;
}
@@ -2247,7 +2405,11 @@ int __audit_signal_info(int sig, struct task_struct *t)
BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS);
axp->target_pid[axp->pid_count] = t->tgid;
+ axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
+ axp->target_uid[axp->pid_count] = t->uid;
+ axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
selinux_get_task_sid(t, &axp->target_sid[axp->pid_count]);
+ memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
axp->pid_count++;
return 0;
@@ -2264,6 +2426,8 @@ void audit_core_dumps(long signr)
{
struct audit_buffer *ab;
u32 sid;
+ uid_t auid = audit_get_loginuid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
if (!audit_enabled)
return;
@@ -2272,9 +2436,8 @@ void audit_core_dumps(long signr)
return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
- audit_log_format(ab, "auid=%u uid=%u gid=%u",
- audit_get_loginuid(current->audit_context),
- current->uid, current->gid);
+ audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
+ auid, current->uid, current->gid, sessionid);
selinux_get_task_sid(current, &sid);
if (sid) {
char *ctx = NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index db9824d..a6baaec 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -109,6 +109,9 @@ struct futex_q {
/* Optional priority inheritance state: */
struct futex_pi_state *pi_state;
struct task_struct *task;
+
+ /* Bitset for the optional bitmasked wakeup */
+ u32 bitset;
};
/*
@@ -722,7 +725,7 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
* to this virtual address:
*/
static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
- int nr_wake)
+ int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@@ -730,6 +733,9 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
union futex_key key;
int ret;
+ if (!bitset)
+ return -EINVAL;
+
futex_lock_mm(fshared);
ret = get_futex_key(uaddr, fshared, &key);
@@ -746,6 +752,11 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
ret = -EINVAL;
break;
}
+
+ /* Check if one of the bits is set in both bitsets */
+ if (!(this->bitset & bitset))
+ continue;
+
wake_futex(this);
if (++ret >= nr_wake)
break;
@@ -1156,7 +1167,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
static long futex_wait_restart(struct restart_block *restart);
static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
- u32 val, ktime_t *abs_time)
+ u32 val, ktime_t *abs_time, u32 bitset)
{
struct task_struct *curr = current;
DECLARE_WAITQUEUE(wait, curr);
@@ -1167,7 +1178,11 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
struct hrtimer_sleeper t;
int rem = 0;
+ if (!bitset)
+ return -EINVAL;
+
q.pi_state = NULL;
+ q.bitset = bitset;
retry:
futex_lock_mm(fshared);
@@ -1252,6 +1267,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
t.timer.expires = *abs_time;
hrtimer_start(&t.timer, t.timer.expires, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&t.timer))
+ t.task = NULL;
/*
* the timer could have already expired, in which
@@ -1293,6 +1310,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
restart->futex.uaddr = (u32 *)uaddr;
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
+ restart->futex.bitset = bitset;
restart->futex.flags = 0;
if (fshared)
@@ -1319,7 +1337,8 @@ static long futex_wait_restart(struct restart_block *restart)
restart->fn = do_no_restart_syscall;
if (restart->futex.flags & FLAGS_SHARED)
fshared = &current->mm->mmap_sem;
- return (long)futex_wait(uaddr, fshared, restart->futex.val, &t);
+ return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
+ restart->futex.bitset);
}
@@ -1535,9 +1554,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
owner = rt_mutex_owner(&q.pi_state->pi_mutex);
res = fixup_pi_state_owner(uaddr, &q, owner);
- WARN_ON(rt_mutex_owner(&q.pi_state->pi_mutex) !=
- owner);
-
/* propagate -EFAULT, if the fixup failed */
if (res)
ret = res;
@@ -1943,7 +1959,8 @@ retry:
* PI futexes happens in exit_pi_state():
*/
if (!pi && (uval & FUTEX_WAITERS))
- futex_wake(uaddr, &curr->mm->mmap_sem, 1);
+ futex_wake(uaddr, &curr->mm->mmap_sem, 1,
+ FUTEX_BITSET_MATCH_ANY);
}
return 0;
}
@@ -2043,10 +2060,14 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
switch (cmd) {
case FUTEX_WAIT:
- ret = futex_wait(uaddr, fshared, val, timeout);
+ val3 = FUTEX_BITSET_MATCH_ANY;
+ case FUTEX_WAIT_BITSET:
+ ret = futex_wait(uaddr, fshared, val, timeout, val3);
break;
case FUTEX_WAKE:
- ret = futex_wake(uaddr, fshared, val);
+ val3 = FUTEX_BITSET_MATCH_ANY;
+ case FUTEX_WAKE_BITSET:
+ ret = futex_wake(uaddr, fshared, val, val3);
break;
case FUTEX_FD:
/* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */
@@ -2086,7 +2107,8 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
u32 val2 = 0;
int cmd = op & FUTEX_CMD_MASK;
- if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) {
+ if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
+ cmd == FUTEX_WAIT_BITSET)) {
if (copy_from_user(&ts, utime, sizeof(ts)) != 0)
return -EFAULT;
if (!timespec_valid(&ts))
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 0a43def..133d558d 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -167,7 +167,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
int val2 = 0;
int cmd = op & FUTEX_CMD_MASK;
- if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) {
+ if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
+ cmd == FUTEX_WAIT_BITSET)) {
if (get_compat_timespec(&ts, utime))
return -EFAULT;
if (!timespec_valid(&ts))
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index bd5d6b5..1069998 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1315,6 +1315,8 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
} while (t->task && !signal_pending(current));
+ __set_current_state(TASK_RUNNING);
+
return t->task == NULL;
}
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index c1d7655..7c2da88 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -101,6 +101,10 @@ void softlockup_tick(void)
now = get_timestamp(this_cpu);
+ /* Wake up the high-prio watchdog task every second: */
+ if (now > (touch_timestamp + 1))
+ wake_up_process(per_cpu(watchdog_task, this_cpu));
+
/* Warn about unreasonable delays: */
if (now <= (touch_timestamp + softlockup_thresh))
return;
@@ -191,11 +195,11 @@ static void check_hung_uninterruptible_tasks(int this_cpu)
read_lock(&tasklist_lock);
do_each_thread(g, t) {
if (!--max_count)
- break;
+ goto unlock;
if (t->state & TASK_UNINTERRUPTIBLE)
check_hung_task(t, now);
} while_each_thread(g, t);
-
+ unlock:
read_unlock(&tasklist_lock);
}
@@ -218,14 +222,19 @@ static int watchdog(void *__bind_cpu)
* debug-printout triggers in softlockup_tick().
*/
while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
touch_softlockup_watchdog();
- msleep_interruptible(10000);
+ schedule();
+
+ if (kthread_should_stop())
+ break;
if (this_cpu != check_cpu)
continue;
if (sysctl_hung_task_timeout_secs)
check_hung_uninterruptible_tasks(this_cpu);
+
}
return 0;
@@ -259,13 +268,6 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
wake_up_process(per_cpu(watchdog_task, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- if (!per_cpu(watchdog_task, hotcpu))
- break;
- /* Unbind so it can run. Fall thru. */
- kthread_bind(per_cpu(watchdog_task, hotcpu),
- any_online_cpu(cpu_online_map));
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
if (hotcpu == check_cpu) {
@@ -275,6 +277,14 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
check_cpu = any_online_cpu(temp_cpu_online_map);
}
break;
+
+ case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
+ if (!per_cpu(watchdog_task, hotcpu))
+ break;
+ /* Unbind so it can run. Fall thru. */
+ kthread_bind(per_cpu(watchdog_task, hotcpu),
+ any_online_cpu(cpu_online_map));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
p = per_cpu(watchdog_task, hotcpu);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 357b68b..7cb1ac3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -81,7 +81,6 @@ extern int percpu_pagelist_fraction;
extern int compat_log;
extern int maps_protect;
extern int sysctl_stat_interval;
-extern int audit_argv_kb;
extern int latencytop_enabled;
/* Constants used for minimum and maximum */
@@ -390,16 +389,6 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec,
},
-#ifdef CONFIG_AUDITSYSCALL
- {
- .ctl_name = CTL_UNNUMBERED,
- .procname = "audit_argv_kb",
- .data = &audit_argv_kb,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
-#endif
{
.ctl_name = KERN_CORE_PATTERN,
.procname = "core_pattern",
diff --git a/kernel/time.c b/kernel/time.c
index 09d3c45..4064c05 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -129,6 +129,7 @@ static inline void warp_clock(void)
write_seqlock_irq(&xtime_lock);
wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
xtime.tv_sec += sys_tz.tz_minuteswest * 60;
+ update_xtime_cache(0);
write_sequnlock_irq(&xtime_lock);
clock_was_set();
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 63f24b5..88267f0 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -137,6 +137,7 @@ void tick_nohz_update_jiffies(void)
cpu_clear(cpu, nohz_cpu_mask);
now = ktime_get();
+ ts->idle_waketime = now;
local_irq_save(flags);
tick_do_update_jiffies64(now);
@@ -400,6 +401,7 @@ void tick_nohz_restart_sched_tick(void)
* Cancel the scheduled timer and restore the tick
*/
ts->tick_stopped = 0;
+ ts->idle_exittime = now;
hrtimer_cancel(&ts->sched_timer);
ts->sched_timer.expires = ts->idle_tick;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 092a236..cd5dbc4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -47,7 +47,7 @@ struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
static unsigned long total_sleep_time; /* seconds */
static struct timespec xtime_cache __attribute__ ((aligned (16)));
-static inline void update_xtime_cache(u64 nsec)
+void update_xtime_cache(u64 nsec)
{
xtime_cache = xtime;
timespec_add_ns(&xtime_cache, nsec);
@@ -145,6 +145,7 @@ int do_settimeofday(struct timespec *tv)
set_normalized_timespec(&xtime, sec, nsec);
set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
+ update_xtime_cache(0);
clock->error = 0;
ntp_clear();
@@ -252,8 +253,8 @@ void __init timekeeping_init(void)
xtime.tv_nsec = 0;
set_normalized_timespec(&wall_to_monotonic,
-xtime.tv_sec, -xtime.tv_nsec);
+ update_xtime_cache(0);
total_sleep_time = 0;
-
write_sequnlock_irqrestore(&xtime_lock, flags);
}
@@ -290,6 +291,7 @@ static int timekeeping_resume(struct sys_device *dev)
}
/* Make sure that we have the correct xtime reference */
timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
+ update_xtime_cache(0);
/* re-base the last cycle value */
clock->cycle_last = clocksource_read(clock);
clock->error = 0;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 12c5f4c..d3d94c1 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -166,6 +166,8 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
P(idle_calls);
P(idle_sleeps);
P_ns(idle_entrytime);
+ P_ns(idle_waketime);
+ P_ns(idle_exittime);
P_ns(idle_sleeptime);
P(last_jiffies);
P(next_jiffies);
OpenPOWER on IntegriCloud