aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c4
-rw-r--r--kernel/audit.h2
-rw-r--r--kernel/auditfilter.c147
-rw-r--r--kernel/auditsc.c342
-rw-r--r--kernel/capability.c46
-rw-r--r--kernel/configs/android-base.config152
-rw-r--r--kernel/configs/android-recommended.config121
-rw-r--r--kernel/cred.c2
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/jump_label.c61
-rw-r--r--kernel/kexec.c3
-rw-r--r--kernel/kexec_core.c69
-rw-r--r--kernel/ksysfs.c6
-rw-r--r--kernel/livepatch/core.c2
-rw-r--r--kernel/module.c122
-rw-r--r--kernel/panic.c13
-rw-r--r--kernel/printk/internal.h16
-rw-r--r--kernel/printk/nmi.c13
-rw-r--r--kernel/printk/printk.c197
-rw-r--r--kernel/ptrace.c4
-rw-r--r--kernel/relay.c34
-rw-r--r--kernel/seccomp.c150
-rw-r--r--kernel/stop_machine.c8
-rw-r--r--kernel/sysctl.c7
-rw-r--r--kernel/task_work.c10
-rw-r--r--kernel/trace/Makefile4
-rw-r--r--kernel/trace/trace_events_hist.c14
-rw-r--r--kernel/user_namespace.c14
28 files changed, 1094 insertions, 471 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 8d528f9930da..a8a91bd2b2a9 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -932,7 +932,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (!audit_enabled && msg_type != AUDIT_USER_AVC)
return 0;
- err = audit_filter_user(msg_type);
+ err = audit_filter(msg_type, AUDIT_FILTER_USER);
if (err == 1) { /* match or error */
err = 0;
if (msg_type == AUDIT_USER_TTY) {
@@ -1379,7 +1379,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
if (audit_initialized != AUDIT_INITIALIZED)
return NULL;
- if (unlikely(audit_filter_type(type)))
+ if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE)))
return NULL;
if (gfp_mask & __GFP_DIRECT_RECLAIM) {
diff --git a/kernel/audit.h b/kernel/audit.h
index a492f4c4e710..431444c3708b 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -331,6 +331,8 @@ extern pid_t audit_sig_pid;
extern kuid_t audit_sig_uid;
extern u32 audit_sig_sid;
+extern int audit_filter(int msgtype, unsigned int listtype);
+
#ifdef CONFIG_AUDITSYSCALL
extern int __audit_signal_info(int sig, struct task_struct *t);
static inline int audit_signal_info(int sig, struct task_struct *t)
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 94ca7b1e5e7e..85d9cac497e4 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1290,113 +1290,72 @@ int audit_compare_dname_path(const char *dname, const char *path, int parentlen)
return strncmp(p, dname, dlen);
}
-static int audit_filter_user_rules(struct audit_krule *rule, int type,
- enum audit_state *state)
+int audit_filter(int msgtype, unsigned int listtype)
{
- int i;
-
- for (i = 0; i < rule->field_count; i++) {
- struct audit_field *f = &rule->fields[i];
- pid_t pid;
- int result = 0;
- u32 sid;
-
- switch (f->type) {
- case AUDIT_PID:
- pid = task_pid_nr(current);
- result = audit_comparator(pid, f->op, f->val);
- break;
- case AUDIT_UID:
- result = audit_uid_comparator(current_uid(), f->op, f->uid);
- break;
- case AUDIT_GID:
- result = audit_gid_comparator(current_gid(), f->op, f->gid);
- break;
- case AUDIT_LOGINUID:
- result = audit_uid_comparator(audit_get_loginuid(current),
- f->op, f->uid);
- break;
- case AUDIT_LOGINUID_SET:
- result = audit_comparator(audit_loginuid_set(current),
- f->op, f->val);
- break;
- case AUDIT_MSGTYPE:
- result = audit_comparator(type, f->op, f->val);
- break;
- case AUDIT_SUBJ_USER:
- case AUDIT_SUBJ_ROLE:
- case AUDIT_SUBJ_TYPE:
- case AUDIT_SUBJ_SEN:
- case AUDIT_SUBJ_CLR:
- if (f->lsm_rule) {
- security_task_getsecid(current, &sid);
- result = security_audit_rule_match(sid,
- f->type,
- f->op,
- f->lsm_rule,
- NULL);
- }
- break;
- }
-
- if (!result)
- return 0;
- }
- switch (rule->action) {
- case AUDIT_NEVER: *state = AUDIT_DISABLED; break;
- case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break;
- }
- return 1;
-}
-
-int audit_filter_user(int type)
-{
- enum audit_state state = AUDIT_DISABLED;
struct audit_entry *e;
- int rc, ret;
-
- ret = 1; /* Audit by default */
-
- rcu_read_lock();
- list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
- rc = audit_filter_user_rules(&e->rule, type, &state);
- if (rc) {
- if (rc > 0 && state == AUDIT_DISABLED)
- ret = 0;
- break;
- }
- }
- rcu_read_unlock();
-
- return ret;
-}
-
-int audit_filter_type(int type)
-{
- struct audit_entry *e;
- int result = 0;
+ int ret = 1; /* Audit by default */
rcu_read_lock();
- if (list_empty(&audit_filter_list[AUDIT_FILTER_TYPE]))
+ if (list_empty(&audit_filter_list[listtype]))
goto unlock_and_return;
+ list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) {
+ int i, result = 0;
- list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TYPE],
- list) {
- int i;
for (i = 0; i < e->rule.field_count; i++) {
struct audit_field *f = &e->rule.fields[i];
- if (f->type == AUDIT_MSGTYPE) {
- result = audit_comparator(type, f->op, f->val);
- if (!result)
- break;
+ pid_t pid;
+ u32 sid;
+
+ switch (f->type) {
+ case AUDIT_PID:
+ pid = task_pid_nr(current);
+ result = audit_comparator(pid, f->op, f->val);
+ break;
+ case AUDIT_UID:
+ result = audit_uid_comparator(current_uid(), f->op, f->uid);
+ break;
+ case AUDIT_GID:
+ result = audit_gid_comparator(current_gid(), f->op, f->gid);
+ break;
+ case AUDIT_LOGINUID:
+ result = audit_uid_comparator(audit_get_loginuid(current),
+ f->op, f->uid);
+ break;
+ case AUDIT_LOGINUID_SET:
+ result = audit_comparator(audit_loginuid_set(current),
+ f->op, f->val);
+ break;
+ case AUDIT_MSGTYPE:
+ result = audit_comparator(msgtype, f->op, f->val);
+ break;
+ case AUDIT_SUBJ_USER:
+ case AUDIT_SUBJ_ROLE:
+ case AUDIT_SUBJ_TYPE:
+ case AUDIT_SUBJ_SEN:
+ case AUDIT_SUBJ_CLR:
+ if (f->lsm_rule) {
+ security_task_getsecid(current, &sid);
+ result = security_audit_rule_match(sid,
+ f->type, f->op, f->lsm_rule, NULL);
+ }
+ break;
+ default:
+ goto unlock_and_return;
}
+ if (result < 0) /* error */
+ goto unlock_and_return;
+ if (!result)
+ break;
+ }
+ if (result > 0) {
+ if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE)
+ ret = 0;
+ break;
}
- if (result)
- goto unlock_and_return;
}
unlock_and_return:
rcu_read_unlock();
- return result;
+ return ret;
}
static int update_lsm_rule(struct audit_krule *r)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 2672d105cffc..5abf1dc1f91c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -72,6 +72,7 @@
#include <linux/compat.h>
#include <linux/ctype.h>
#include <linux/string.h>
+#include <linux/uaccess.h>
#include <uapi/linux/limits.h>
#include "audit.h"
@@ -81,7 +82,8 @@
#define AUDITSC_SUCCESS 1
#define AUDITSC_FAILURE 2
-/* no execve audit message should be longer than this (userspace limits) */
+/* no execve audit message should be longer than this (userspace limits),
+ * see the note near the top of audit_log_execve_info() about this value */
#define MAX_EXECVE_AUDIT_LEN 7500
/* max length to print of cmdline/proctitle value during audit */
@@ -694,8 +696,12 @@ static int audit_filter_rules(struct task_struct *tsk,
ctx->prio = rule->prio;
}
switch (rule->action) {
- case AUDIT_NEVER: *state = AUDIT_DISABLED; break;
- case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break;
+ case AUDIT_NEVER:
+ *state = AUDIT_DISABLED;
+ break;
+ case AUDIT_ALWAYS:
+ *state = AUDIT_RECORD_CONTEXT;
+ break;
}
return 1;
}
@@ -987,184 +993,178 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
return rc;
}
-/*
- * 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 boundary)
- *
- * 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)
+static void audit_log_execve_info(struct audit_context *context,
+ struct audit_buffer **ab)
{
- char arg_num_len_buf[12];
- const char __user *tmp_p = p;
- /* how many digits are in arg_num? 5 is the length of ' a=""' */
- size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
- size_t len, len_left, to_send;
- size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
- unsigned int i, has_cntl = 0, too_long = 0;
- int ret;
-
- /* strnlen_user includes the null we don't want to send */
- len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;
-
- /*
- * 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 (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
- send_sig(SIGKILL, current, 0);
- return -1;
+ long len_max;
+ long len_rem;
+ long len_full;
+ long len_buf;
+ long len_abuf;
+ long len_tmp;
+ bool require_data;
+ bool encode;
+ unsigned int iter;
+ unsigned int arg;
+ char *buf_head;
+ char *buf;
+ const char __user *p = (const char __user *)current->mm->arg_start;
+
+ /* NOTE: this buffer needs to be large enough to hold all the non-arg
+ * data we put in the audit record for this argument (see the
+ * code below) ... at this point in time 96 is plenty */
+ char abuf[96];
+
+ /* NOTE: we set MAX_EXECVE_AUDIT_LEN to a rather arbitrary limit, the
+ * current value of 7500 is not as important as the fact that it
+ * is less than 8k, a setting of 7500 gives us plenty of wiggle
+ * room if we go over a little bit in the logging below */
+ WARN_ON_ONCE(MAX_EXECVE_AUDIT_LEN > 7500);
+ len_max = MAX_EXECVE_AUDIT_LEN;
+
+ /* scratch buffer to hold the userspace args */
+ buf_head = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
+ if (!buf_head) {
+ audit_panic("out of memory for argv string");
+ return;
}
+ buf = buf_head;
- /* walk the whole argument looking for non-ascii chars */
+ audit_log_format(*ab, "argc=%d", context->execve.argc);
+
+ len_rem = len_max;
+ len_buf = 0;
+ len_full = 0;
+ require_data = true;
+ encode = false;
+ iter = 0;
+ arg = 0;
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);
- /*
- * 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 (ret) {
- WARN_ON(1);
- send_sig(SIGKILL, current, 0);
- return -1;
- }
- 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;
- }
+ /* NOTE: we don't ever want to trust this value for anything
+ * serious, but the audit record format insists we
+ * provide an argument length for really long arguments,
+ * e.g. > MAX_EXECVE_AUDIT_LEN, so we have no choice but
+ * to use strncpy_from_user() to obtain this value for
+ * recording in the log, although we don't use it
+ * anywhere here to avoid a double-fetch problem */
+ if (len_full == 0)
+ len_full = strnlen_user(p, MAX_ARG_STRLEN) - 1;
+
+ /* read more data from userspace */
+ if (require_data) {
+ /* can we make more room in the buffer? */
+ if (buf != buf_head) {
+ memmove(buf_head, buf, len_buf);
+ buf = buf_head;
+ }
+
+ /* fetch as much as we can of the argument */
+ len_tmp = strncpy_from_user(&buf_head[len_buf], p,
+ len_max - len_buf);
+ if (len_tmp == -EFAULT) {
+ /* unable to copy from userspace */
+ send_sig(SIGKILL, current, 0);
+ goto out;
+ } else if (len_tmp == (len_max - len_buf)) {
+ /* buffer is not large enough */
+ require_data = true;
+ /* NOTE: if we are going to span multiple
+ * buffers force the encoding so we stand
+ * a chance at a sane len_full value and
+ * consistent record encoding */
+ encode = true;
+ len_full = len_full * 2;
+ p += len_tmp;
+ } else {
+ require_data = false;
+ if (!encode)
+ encode = audit_string_contains_control(
+ buf, len_tmp);
+ /* try to use a trusted value for len_full */
+ if (len_full < len_max)
+ len_full = (encode ?
+ len_tmp * 2 : len_tmp);
+ p += len_tmp + 1;
+ }
+ len_buf += len_tmp;
+ buf_head[len_buf] = '\0';
- /*
- * 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=%zu", 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);
- return -1;
+ /* length of the buffer in the audit record? */
+ len_abuf = (encode ? len_buf * 2 : len_buf + 2);
}
- 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_n_hex(*ab, buf, to_send);
- else
- audit_log_string(*ab, buf);
-
- 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;
-}
-static void audit_log_execve_info(struct audit_context *context,
- struct audit_buffer **ab)
-{
- int i, len;
- size_t len_sent = 0;
- const char __user *p;
- char *buf;
+ /* write as much as we can to the audit log */
+ if (len_buf > 0) {
+ /* NOTE: some magic numbers here - basically if we
+ * can't fit a reasonable amount of data into the
+ * existing audit buffer, flush it and start with
+ * a new buffer */
+ if ((sizeof(abuf) + 8) > len_rem) {
+ len_rem = len_max;
+ audit_log_end(*ab);
+ *ab = audit_log_start(context,
+ GFP_KERNEL, AUDIT_EXECVE);
+ if (!*ab)
+ goto out;
+ }
- p = (const char __user *)current->mm->arg_start;
+ /* create the non-arg portion of the arg record */
+ len_tmp = 0;
+ if (require_data || (iter > 0) ||
+ ((len_abuf + sizeof(abuf)) > len_rem)) {
+ if (iter == 0) {
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d_len=%lu",
+ arg, len_full);
+ }
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d[%d]=", arg, iter++);
+ } else
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d=", arg);
+ WARN_ON(len_tmp >= sizeof(abuf));
+ abuf[sizeof(abuf) - 1] = '\0';
+
+ /* log the arg in the audit record */
+ audit_log_format(*ab, "%s", abuf);
+ len_rem -= len_tmp;
+ len_tmp = len_buf;
+ if (encode) {
+ if (len_abuf > len_rem)
+ len_tmp = len_rem / 2; /* encoding */
+ audit_log_n_hex(*ab, buf, len_tmp);
+ len_rem -= len_tmp * 2;
+ len_abuf -= len_tmp * 2;
+ } else {
+ if (len_abuf > len_rem)
+ len_tmp = len_rem - 2; /* quotes */
+ audit_log_n_string(*ab, buf, len_tmp);
+ len_rem -= len_tmp + 2;
+ /* don't subtract the "2" because we still need
+ * to add quotes to the remaining string */
+ len_abuf -= len_tmp;
+ }
+ len_buf -= len_tmp;
+ buf += len_tmp;
+ }
- audit_log_format(*ab, "argc=%d", context->execve.argc);
+ /* ready to move to the next argument? */
+ if ((len_buf == 0) && !require_data) {
+ arg++;
+ iter = 0;
+ len_full = 0;
+ require_data = true;
+ encode = false;
+ }
+ } while (arg < context->execve.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");
- return;
- }
+ /* NOTE: the caller handles the final audit_log_end() call */
- for (i = 0; i < context->execve.argc; i++) {
- len = audit_log_single_execve_arg(context, ab, i,
- &len_sent, p, buf);
- if (len <= 0)
- break;
- p += len;
- }
- kfree(buf);
+out:
+ kfree(buf_head);
}
static void show_special(struct audit_context *context, int *call_panic)
@@ -1425,7 +1425,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
if (context->pwd.dentry && context->pwd.mnt) {
ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
if (ab) {
- audit_log_d_path(ab, " cwd=", &context->pwd);
+ audit_log_d_path(ab, "cwd=", &context->pwd);
audit_log_end(ab);
}
}
diff --git a/kernel/capability.c b/kernel/capability.c
index 45432b54d5c6..00411c82dac5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
return has_ns_capability_noaudit(t, &init_user_ns, cap);
}
+static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit)
+{
+ int capable;
+
+ if (unlikely(!cap_valid(cap))) {
+ pr_crit("capable() called with invalid cap=%u\n", cap);
+ BUG();
+ }
+
+ capable = audit ? security_capable(current_cred(), ns, cap) :
+ security_capable_noaudit(current_cred(), ns, cap);
+ if (capable == 0) {
+ current->flags |= PF_SUPERPRIV;
+ return true;
+ }
+ return false;
+}
+
/**
* ns_capable - Determine if the current task has a superior capability in effect
* @ns: The usernamespace we want the capability in
@@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
*/
bool ns_capable(struct user_namespace *ns, int cap)
{
- if (unlikely(!cap_valid(cap))) {
- pr_crit("capable() called with invalid cap=%u\n", cap);
- BUG();
- }
-
- if (security_capable(current_cred(), ns, cap) == 0) {
- current->flags |= PF_SUPERPRIV;
- return true;
- }
- return false;
+ return ns_capable_common(ns, cap, true);
}
EXPORT_SYMBOL(ns_capable);
+/**
+ * ns_capable_noaudit - Determine if the current task has a superior capability
+ * (unaudited) in effect
+ * @ns: The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+ return ns_capable_common(ns, cap, false);
+}
+EXPORT_SYMBOL(ns_capable_noaudit);
/**
* capable - Determine if the current task has a superior capability in effect
diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config
new file mode 100644
index 000000000000..9f748ed7bea8
--- /dev/null
+++ b/kernel/configs/android-base.config
@@ -0,0 +1,152 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_DEVKMEM is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_MODULES is not set
+# CONFIG_OABI_COMPAT is not set
+# CONFIG_SYSVIPC is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_ASHMEM=y
+CONFIG_AUDIT=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_EMBEDDED=y
+CONFIG_FB=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_INET_ESP=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IPV6=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_KEY=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_NAT=y
+CONFIG_NO_HZ=y
+CONFIG_PACKET=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PREEMPT=y
+CONFIG_QUOTA=y
+CONFIG_RTC_CLASS=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_STAGING=y
+CONFIG_SWP_EMULATION=y
+CONFIG_SYNC=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_MIDI=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_XFRM_USER=y
diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
new file mode 100644
index 000000000000..e3b953e966d2
--- /dev/null
+++ b/kernel/configs/android-recommended.config
@@ -0,0 +1,121 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_NF_CONNTRACK_SIP is not set
+# CONFIG_PM_WAKELOCKS_GC is not set
+# CONFIG_VT is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_COMPACTION=y
+CONFIG_DEBUG_RODATA=y
+CONFIG_DM_UEVENT=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FUSE_FS=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HIDRAW=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_GPIO=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_ION=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KSM=y
+CONFIG_LOGIG940_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGITECH_FF=y
+CONFIG_MD=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MSDOS_FS=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_PANTHERLORD_FF=y
+CONFIG_PERF_EVENTS=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+CONFIG_POWER_SUPPLY=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_SCHEDSTATS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_TASK_XACCT=y
+CONFIG_TIMER_STATS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UHID=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_USBNET=y
+CONFIG_VFAT_FS=y
diff --git a/kernel/cred.c b/kernel/cred.c
index 0c0cd8a62285..5f264fb5737d 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -689,6 +689,8 @@ EXPORT_SYMBOL(set_security_override_from_ctx);
*/
int set_create_files_as(struct cred *new, struct inode *inode)
{
+ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ return -EINVAL;
new->fsuid = inode->i_uid;
new->fsgid = inode->i_gid;
return security_kernel_create_files_as(new, inode);
diff --git a/kernel/exit.c b/kernel/exit.c
index 84ae830234f8..2f974ae042a6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -715,7 +715,7 @@ static void check_stack_usage(void)
spin_lock(&low_water_lock);
if (free < lowest_to_date) {
- pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n",
+ pr_info("%s (%d) used greatest stack depth: %lu bytes left\n",
current->comm, task_pid_nr(current), free);
lowest_to_date = free;
}
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 0dbea887d625..93ad6c1fb9b6 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -14,6 +14,7 @@
#include <linux/err.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
+#include <linux/bug.h>
#ifdef HAVE_JUMP_LABEL
@@ -56,6 +57,49 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
static void jump_label_update(struct static_key *key);
+/*
+ * There are similar definitions for the !HAVE_JUMP_LABEL case in jump_label.h.
+ * The use of 'atomic_read()' requires atomic.h and its problematic for some
+ * kernel headers such as kernel.h and others. Since static_key_count() is not
+ * used in the branch statements as it is for the !HAVE_JUMP_LABEL case its ok
+ * to have it be a function here. Similarly, for 'static_key_enable()' and
+ * 'static_key_disable()', which require bug.h. This should allow jump_label.h
+ * to be included from most/all places for HAVE_JUMP_LABEL.
+ */
+int static_key_count(struct static_key *key)
+{
+ /*
+ * -1 means the first static_key_slow_inc() is in progress.
+ * static_key_enabled() must return true, so return 1 here.
+ */
+ int n = atomic_read(&key->enabled);
+
+ return n >= 0 ? n : 1;
+}
+EXPORT_SYMBOL_GPL(static_key_count);
+
+void static_key_enable(struct static_key *key)
+{
+ int count = static_key_count(key);
+
+ WARN_ON_ONCE(count < 0 || count > 1);
+
+ if (!count)
+ static_key_slow_inc(key);
+}
+EXPORT_SYMBOL_GPL(static_key_enable);
+
+void static_key_disable(struct static_key *key)
+{
+ int count = static_key_count(key);
+
+ WARN_ON_ONCE(count < 0 || count > 1);
+
+ if (count)
+ static_key_slow_dec(key);
+}
+EXPORT_SYMBOL_GPL(static_key_disable);
+
void static_key_slow_inc(struct static_key *key)
{
int v, v1;
@@ -235,6 +279,18 @@ void __init jump_label_init(void)
struct static_key *key = NULL;
struct jump_entry *iter;
+ /*
+ * Since we are initializing the static_key.enabled field with
+ * with the 'raw' int values (to avoid pulling in atomic.h) in
+ * jump_label.h, let's make sure that is safe. There are only two
+ * cases to check since we initialize to 0 or 1.
+ */
+ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0);
+ BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1);
+
+ if (static_key_initialized)
+ return;
+
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
@@ -284,11 +340,14 @@ static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
+ preempt_disable();
mod = __module_text_address((unsigned long)start);
+ WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+ preempt_enable();
+
if (!mod)
return 0;
- WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
return __jump_label_text_reserved(mod->jump_entries,
mod->jump_entries + mod->num_jump_entries,
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 4384672d3245..980936a90ee6 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -48,7 +48,8 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
if (kexec_on_panic) {
/* Verify we have a valid entry point */
- if ((entry < crashk_res.start) || (entry > crashk_res.end))
+ if ((entry < phys_to_boot_phys(crashk_res.start)) ||
+ (entry > phys_to_boot_phys(crashk_res.end)))
return -EADDRNOTAVAIL;
}
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 56b3ed0927b0..561675589511 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -95,6 +95,12 @@ int kexec_should_crash(struct task_struct *p)
return 0;
}
+int kexec_crash_loaded(void)
+{
+ return !!kexec_crash_image;
+}
+EXPORT_SYMBOL_GPL(kexec_crash_loaded);
+
/*
* When kexec transitions to the new kernel there is a one-to-one
* mapping between physical and virtual addresses. On processors
@@ -140,6 +146,7 @@ int kexec_should_crash(struct task_struct *p)
* allocating pages whose destination address we do not care about.
*/
#define KIMAGE_NO_DEST (-1UL)
+#define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT)
static struct page *kimage_alloc_page(struct kimage *image,
gfp_t gfp_mask,
@@ -147,8 +154,9 @@ static struct page *kimage_alloc_page(struct kimage *image,
int sanity_check_segment_list(struct kimage *image)
{
- int result, i;
+ int i;
unsigned long nr_segments = image->nr_segments;
+ unsigned long total_pages = 0;
/*
* Verify we have good destination addresses. The caller is
@@ -163,16 +171,17 @@ int sanity_check_segment_list(struct kimage *image)
* simply because addresses are changed to page size
* granularity.
*/
- result = -EADDRNOTAVAIL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz;
+ if (mstart > mend)
+ return -EADDRNOTAVAIL;
if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
- return result;
+ return -EADDRNOTAVAIL;
if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
- return result;
+ return -EADDRNOTAVAIL;
}
/* Verify our destination addresses do not overlap.
@@ -180,7 +189,6 @@ int sanity_check_segment_list(struct kimage *image)
* through very weird things can happen with no
* easy explanation as one segment stops on another.
*/
- result = -EINVAL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
unsigned long j;
@@ -194,7 +202,7 @@ int sanity_check_segment_list(struct kimage *image)
pend = pstart + image->segment[j].memsz;
/* Do the segments overlap ? */
if ((mend > pstart) && (mstart < pend))
- return result;
+ return -EINVAL;
}
}
@@ -203,12 +211,26 @@ int sanity_check_segment_list(struct kimage *image)
* and it is easier to check up front than to be surprised
* later on.
*/
- result = -EINVAL;
for (i = 0; i < nr_segments; i++) {
if (image->segment[i].bufsz > image->segment[i].memsz)
- return result;
+ return -EINVAL;
+ }
+
+ /*
+ * Verify that no more than half of memory will be consumed. If the
+ * request from userspace is too large, a large amount of time will be
+ * wasted allocating pages, which can cause a soft lockup.
+ */
+ for (i = 0; i < nr_segments; i++) {
+ if (PAGE_COUNT(image->segment[i].memsz) > totalram_pages / 2)
+ return -EINVAL;
+
+ total_pages += PAGE_COUNT(image->segment[i].memsz);
}
+ if (total_pages > totalram_pages / 2)
+ return -EINVAL;
+
/*
* Verify we have good destination addresses. Normally
* the caller is responsible for making certain we don't
@@ -220,16 +242,15 @@ int sanity_check_segment_list(struct kimage *image)
*/
if (image->type == KEXEC_TYPE_CRASH) {
- result = -EADDRNOTAVAIL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz - 1;
/* Ensure we are within the crash kernel limits */
- if ((mstart < crashk_res.start) ||
- (mend > crashk_res.end))
- return result;
+ if ((mstart < phys_to_boot_phys(crashk_res.start)) ||
+ (mend > phys_to_boot_phys(crashk_res.end)))
+ return -EADDRNOTAVAIL;
}
}
@@ -352,7 +373,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
if (!pages)
break;
- pfn = page_to_pfn(pages);
+ pfn = page_to_boot_pfn(pages);
epfn = pfn + count;
addr = pfn << PAGE_SHIFT;
eaddr = epfn << PAGE_SHIFT;
@@ -478,7 +499,7 @@ static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
return -ENOMEM;
ind_page = page_address(page);
- *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
+ *image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION;
image->entry = ind_page;
image->last_entry = ind_page +
((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
@@ -533,13 +554,13 @@ void kimage_terminate(struct kimage *image)
#define for_each_kimage_entry(image, ptr, entry) \
for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
ptr = (entry & IND_INDIRECTION) ? \
- phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
+ boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
static void kimage_free_entry(kimage_entry_t entry)
{
struct page *page;
- page = pfn_to_page(entry >> PAGE_SHIFT);
+ page = boot_pfn_to_page(entry >> PAGE_SHIFT);
kimage_free_pages(page);
}
@@ -633,7 +654,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
* have a match.
*/
list_for_each_entry(page, &image->dest_pages, lru) {
- addr = page_to_pfn(page) << PAGE_SHIFT;
+ addr = page_to_boot_pfn(page) << PAGE_SHIFT;
if (addr == destination) {
list_del(&page->lru);
return page;
@@ -648,12 +669,12 @@ static struct page *kimage_alloc_page(struct kimage *image,
if (!page)
return NULL;
/* If the page cannot be used file it away */
- if (page_to_pfn(page) >
+ if (page_to_boot_pfn(page) >
(KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
list_add(&page->lru, &image->unusable_pages);
continue;
}
- addr = page_to_pfn(page) << PAGE_SHIFT;
+ addr = page_to_boot_pfn(page) << PAGE_SHIFT;
/* If it is the destination page we want use it */
if (addr == destination)
@@ -676,7 +697,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
struct page *old_page;
old_addr = *old & PAGE_MASK;
- old_page = pfn_to_page(old_addr >> PAGE_SHIFT);
+ old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT);
copy_highpage(page, old_page);
*old = addr | (*old & ~PAGE_MASK);
@@ -732,7 +753,7 @@ static int kimage_load_normal_segment(struct kimage *image,
result = -ENOMEM;
goto out;
}
- result = kimage_add_page(image, page_to_pfn(page)
+ result = kimage_add_page(image, page_to_boot_pfn(page)
<< PAGE_SHIFT);
if (result < 0)
goto out;
@@ -793,7 +814,7 @@ static int kimage_load_crash_segment(struct kimage *image,
char *ptr;
size_t uchunk, mchunk;
- page = pfn_to_page(maddr >> PAGE_SHIFT);
+ page = boot_pfn_to_page(maddr >> PAGE_SHIFT);
if (!page) {
result = -ENOMEM;
goto out;
@@ -921,7 +942,7 @@ void __weak crash_free_reserved_phys_range(unsigned long begin,
unsigned long addr;
for (addr = begin; addr < end; addr += PAGE_SIZE)
- free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+ free_reserved_page(boot_pfn_to_page(addr >> PAGE_SHIFT));
}
int crash_shrink_memory(unsigned long new_size)
@@ -1374,7 +1395,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
void __weak arch_crash_save_vmcoreinfo(void)
{}
-unsigned long __weak paddr_vmcoreinfo_note(void)
+phys_addr_t __weak paddr_vmcoreinfo_note(void)
{
return __pa((unsigned long)(char *)&vmcoreinfo_note);
}
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 152da4a48867..ee1bc1bb8feb 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -101,7 +101,7 @@ KERNEL_ATTR_RO(kexec_loaded);
static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sprintf(buf, "%d\n", !!kexec_crash_image);
+ return sprintf(buf, "%d\n", kexec_crash_loaded());
}
KERNEL_ATTR_RO(kexec_crash_loaded);
@@ -128,8 +128,8 @@ KERNEL_ATTR_RW(kexec_crash_size);
static ssize_t vmcoreinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sprintf(buf, "%lx %x\n",
- paddr_vmcoreinfo_note(),
+ phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
+ return sprintf(buf, "%pa %x\n", &vmcore_base,
(unsigned int)sizeof(vmcoreinfo_note));
}
KERNEL_ATTR_RO(vmcoreinfo);
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 5c2bc1052691..8bbe50704621 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -309,7 +309,7 @@ static int klp_write_object_relocations(struct module *pmod,
break;
}
- module_enable_ro(pmod);
+ module_enable_ro(pmod, true);
return ret;
}
diff --git a/kernel/module.c b/kernel/module.c
index 5f71aa63ed2a..529efae9f481 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -60,6 +60,7 @@
#include <linux/jump_label.h>
#include <linux/pfn.h>
#include <linux/bsearch.h>
+#include <linux/dynamic_debug.h>
#include <uapi/linux/module.h>
#include "module-internal.h"
@@ -264,7 +265,7 @@ static void module_assert_mutex_or_preempt(void)
if (unlikely(!debug_locks))
return;
- WARN_ON(!rcu_read_lock_sched_held() &&
+ WARN_ON_ONCE(!rcu_read_lock_sched_held() &&
!lockdep_is_held(&module_mutex));
#endif
}
@@ -336,7 +337,7 @@ static inline void add_taint_module(struct module *mod, unsigned flag,
* A thread that wants to hold a reference to a module only while it
* is running can call this to safely exit. nfsd and lockd use this.
*/
-void __module_put_and_exit(struct module *mod, long code)
+void __noreturn __module_put_and_exit(struct module *mod, long code)
{
module_put(mod);
do_exit(code);
@@ -1693,8 +1694,7 @@ static int module_add_modinfo_attrs(struct module *mod)
temp_attr = mod->modinfo_attrs;
for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) {
- if (!attr->test ||
- (attr->test && attr->test(mod))) {
+ if (!attr->test || attr->test(mod)) {
memcpy(temp_attr, attr, sizeof(*temp_attr));
sysfs_attr_init(&temp_attr->attr);
error = sysfs_create_file(&mod->mkobj.kobj,
@@ -1858,10 +1858,11 @@ static void mod_sysfs_teardown(struct module *mod)
* from modification and any data from execution.
*
* General layout of module is:
- * [text] [read-only-data] [writable data]
- * text_size -----^ ^ ^
- * ro_size ------------------------| |
- * size -------------------------------------------|
+ * [text] [read-only-data] [ro-after-init] [writable data]
+ * text_size -----^ ^ ^ ^
+ * ro_size ------------------------| | |
+ * ro_after_init_size -----------------------------| |
+ * size -----------------------------------------------------------|
*
* These values are always page-aligned (as is base)
*/
@@ -1884,14 +1885,24 @@ static void frob_rodata(const struct module_layout *layout,
(layout->ro_size - layout->text_size) >> PAGE_SHIFT);
}
+static void frob_ro_after_init(const struct module_layout *layout,
+ int (*set_memory)(unsigned long start, int num_pages))
+{
+ BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1));
+ set_memory((unsigned long)layout->base + layout->ro_size,
+ (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT);
+}
+
static void frob_writable_data(const struct module_layout *layout,
int (*set_memory)(unsigned long start, int num_pages))
{
BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1));
- BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1));
+ BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1));
BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1));
- set_memory((unsigned long)layout->base + layout->ro_size,
- (layout->size - layout->ro_size) >> PAGE_SHIFT);
+ set_memory((unsigned long)layout->base + layout->ro_after_init_size,
+ (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT);
}
/* livepatching wants to disable read-only so it can frob module. */
@@ -1899,21 +1910,26 @@ void module_disable_ro(const struct module *mod)
{
frob_text(&mod->core_layout, set_memory_rw);
frob_rodata(&mod->core_layout, set_memory_rw);
+ frob_ro_after_init(&mod->core_layout, set_memory_rw);
frob_text(&mod->init_layout, set_memory_rw);
frob_rodata(&mod->init_layout, set_memory_rw);
}
-void module_enable_ro(const struct module *mod)
+void module_enable_ro(const struct module *mod, bool after_init)
{
frob_text(&mod->core_layout, set_memory_ro);
frob_rodata(&mod->core_layout, set_memory_ro);
frob_text(&mod->init_layout, set_memory_ro);
frob_rodata(&mod->init_layout, set_memory_ro);
+
+ if (after_init)
+ frob_ro_after_init(&mod->core_layout, set_memory_ro);
}
static void module_enable_nx(const struct module *mod)
{
frob_rodata(&mod->core_layout, set_memory_nx);
+ frob_ro_after_init(&mod->core_layout, set_memory_nx);
frob_writable_data(&mod->core_layout, set_memory_nx);
frob_rodata(&mod->init_layout, set_memory_nx);
frob_writable_data(&mod->init_layout, set_memory_nx);
@@ -1922,6 +1938,7 @@ static void module_enable_nx(const struct module *mod)
static void module_disable_nx(const struct module *mod)
{
frob_rodata(&mod->core_layout, set_memory_x);
+ frob_ro_after_init(&mod->core_layout, set_memory_x);
frob_writable_data(&mod->core_layout, set_memory_x);
frob_rodata(&mod->init_layout, set_memory_x);
frob_writable_data(&mod->init_layout, set_memory_x);
@@ -1964,6 +1981,8 @@ static void disable_ro_nx(const struct module_layout *layout)
frob_text(layout, set_memory_rw);
frob_rodata(layout, set_memory_rw);
frob_rodata(layout, set_memory_x);
+ frob_ro_after_init(layout, set_memory_rw);
+ frob_ro_after_init(layout, set_memory_x);
frob_writable_data(layout, set_memory_x);
}
@@ -2306,6 +2325,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
* finder in the two loops below */
{ SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL },
{ SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL },
+ { SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL },
{ SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL },
{ ARCH_SHF_SMALL | SHF_ALLOC, 0 }
};
@@ -2337,7 +2357,11 @@ static void layout_sections(struct module *mod, struct load_info *info)
mod->core_layout.size = debug_align(mod->core_layout.size);
mod->core_layout.ro_size = mod->core_layout.size;
break;
- case 3: /* whole core */
+ case 2: /* RO after init */
+ mod->core_layout.size = debug_align(mod->core_layout.size);
+ mod->core_layout.ro_after_init_size = mod->core_layout.size;
+ break;
+ case 4: /* whole core */
mod->core_layout.size = debug_align(mod->core_layout.size);
break;
}
@@ -2367,7 +2391,14 @@ static void layout_sections(struct module *mod, struct load_info *info)
mod->init_layout.size = debug_align(mod->init_layout.size);
mod->init_layout.ro_size = mod->init_layout.size;
break;
- case 3: /* whole init */
+ case 2:
+ /*
+ * RO after init doesn't apply to init_layout (only
+ * core_layout), so it just takes the value of ro_size.
+ */
+ mod->init_layout.ro_after_init_size = mod->init_layout.ro_size;
+ break;
+ case 4: /* whole init */
mod->init_layout.size = debug_align(mod->init_layout.size);
break;
}
@@ -2687,13 +2718,18 @@ static inline void kmemleak_load_module(const struct module *mod,
#endif
#ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
int err = -ENOKEY;
const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
const void *mod = info->hdr;
- if (info->len > markerlen &&
+ /*
+ * Require flags == 0, as a module with version information
+ * removed is no longer the module that was signed
+ */
+ if (flags == 0 &&
+ info->len > markerlen &&
memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
/* We truncate the module to discard the signature */
info->len -= markerlen;
@@ -2712,7 +2748,7 @@ static int module_sig_check(struct load_info *info)
return err;
}
#else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
return 0;
}
@@ -2920,8 +2956,12 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
return -ENOEXEC;
}
- if (!get_modinfo(info, "intree"))
+ if (!get_modinfo(info, "intree")) {
+ if (!test_taint(TAINT_OOT_MODULE))
+ pr_warn("%s: loading out-of-tree module taints kernel.\n",
+ mod->name);
add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
+ }
if (get_modinfo(info, "staging")) {
add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
@@ -3090,6 +3130,8 @@ static int move_module(struct module *mod, struct load_info *info)
static int check_module_license_and_versions(struct module *mod)
{
+ int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE);
+
/*
* ndiswrapper is under GPL by itself, but loads proprietary modules.
* Don't use add_taint_module(), as it would prevent ndiswrapper from
@@ -3108,6 +3150,9 @@ static int check_module_license_and_versions(struct module *mod)
add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
LOCKDEP_NOW_UNRELIABLE);
+ if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE))
+ pr_warn("%s: module license taints kernel.\n", mod->name);
+
#ifdef CONFIG_MODVERSIONS
if ((mod->num_syms && !mod->crcs)
|| (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -3155,16 +3200,41 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr,
return 0;
}
+/* module_blacklist is a comma-separated list of module names */
+static char *module_blacklist;
+static bool blacklisted(char *module_name)
+{
+ const char *p;
+ size_t len;
+
+ if (!module_blacklist)
+ return false;
+
+ for (p = module_blacklist; *p; p += len) {
+ len = strcspn(p, ",");
+ if (strlen(module_name) == len && !memcmp(module_name, p, len))
+ return true;
+ if (p[len] == ',')
+ len++;
+ }
+ return false;
+}
+core_param(module_blacklist, module_blacklist, charp, 0400);
+
static struct module *layout_and_allocate(struct load_info *info, int flags)
{
/* Module within temporary copy. */
struct module *mod;
+ unsigned int ndx;
int err;
mod = setup_load_info(info, flags);
if (IS_ERR(mod))
return mod;
+ if (blacklisted(mod->name))
+ return ERR_PTR(-EPERM);
+
err = check_modinfo(mod, info, flags);
if (err)
return ERR_PTR(err);
@@ -3178,6 +3248,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
/* We will do a special allocation for per-cpu sections later. */
info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
+ /*
+ * Mark ro_after_init section with SHF_RO_AFTER_INIT so that
+ * layout_sections() can put it in the right place.
+ * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set.
+ */
+ ndx = find_sec(info, ".data..ro_after_init");
+ if (ndx)
+ info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
+
/* Determine total sizes, and put offsets in sh_entsize. For now
this is done generically; there doesn't appear to be any
special cases for the architectures. */
@@ -3344,12 +3423,14 @@ static noinline int do_init_module(struct module *mod)
/* Switch to core kallsyms now init is done: kallsyms may be walking! */
rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
#endif
+ module_enable_ro(mod, true);
mod_tree_remove_init(mod);
disable_ro_nx(&mod->init_layout);
module_arch_freeing_init(mod);
mod->init_layout.base = NULL;
mod->init_layout.size = 0;
mod->init_layout.ro_size = 0;
+ mod->init_layout.ro_after_init_size = 0;
mod->init_layout.text_size = 0;
/*
* We want to free module_init, but be aware that kallsyms may be
@@ -3441,8 +3522,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
/* This relies on module_mutex for list integrity. */
module_bug_finalize(info->hdr, info->sechdrs, mod);
- /* Set RO and NX regions */
- module_enable_ro(mod);
+ module_enable_ro(mod, false);
module_enable_nx(mod);
/* Mark state as coming so strong_try_module_get() ignores us,
@@ -3498,7 +3578,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
long err;
char *after_dashes;
- err = module_sig_check(info);
+ err = module_sig_check(info, flags);
if (err)
goto free_copy;
diff --git a/kernel/panic.c b/kernel/panic.c
index 8aa74497cc5a..ca8cea1ef673 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -108,6 +108,7 @@ void panic(const char *fmt, ...)
long i, i_next = 0;
int state = 0;
int old_cpu, this_cpu;
+ bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
/*
* Disable local interrupts. This will prevent panic_smp_self_stop
@@ -160,7 +161,7 @@ void panic(const char *fmt, ...)
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (!crash_kexec_post_notifiers) {
+ if (!_crash_kexec_post_notifiers) {
printk_nmi_flush_on_panic();
__crash_kexec(NULL);
}
@@ -191,7 +192,7 @@ void panic(const char *fmt, ...)
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
- if (crash_kexec_post_notifiers)
+ if (_crash_kexec_post_notifiers)
__crash_kexec(NULL);
bust_spinlocks(0);
@@ -571,13 +572,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
core_param(panic, panic_timeout, int, 0644);
core_param(pause_on_oops, pause_on_oops, int, 0644);
core_param(panic_on_warn, panic_on_warn, int, 0644);
-
-static int __init setup_crash_kexec_post_notifiers(char *s)
-{
- crash_kexec_post_notifiers = true;
- return 0;
-}
-early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers);
+core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644);
static int __init oops_setup(char *s)
{
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 7fd2838fa417..5d4505f30083 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -16,9 +16,11 @@
*/
#include <linux/percpu.h>
-typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
+typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
+ va_list args);
-int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
+__printf(2, 0)
+int vprintk_default(int level, const char *fmt, va_list args);
#ifdef CONFIG_PRINTK_NMI
@@ -31,9 +33,10 @@ extern raw_spinlock_t logbuf_lock;
* via per-CPU variable.
*/
DECLARE_PER_CPU(printk_func_t, printk_func);
-static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+__printf(2, 0)
+static inline int vprintk_func(int level, const char *fmt, va_list args)
{
- return this_cpu_read(printk_func)(fmt, args);
+ return this_cpu_read(printk_func)(level, fmt, args);
}
extern atomic_t nmi_message_lost;
@@ -44,9 +47,10 @@ static inline int get_nmi_message_lost(void)
#else /* CONFIG_PRINTK_NMI */
-static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+__printf(2, 0)
+static inline int vprintk_func(int level, const char *fmt, va_list args)
{
- return vprintk_default(fmt, args);
+ return vprintk_default(level, fmt, args);
}
static inline int get_nmi_message_lost(void)
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index b69eb8a2876f..bc3eeb1ae6da 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
* one writer running. But the buffer might get flushed from another
* CPU, so we need to be careful.
*/
-static int vprintk_nmi(const char *fmt, va_list args)
+static int vprintk_nmi(int level, const char *fmt, va_list args)
{
struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
int add = 0;
@@ -79,7 +79,16 @@ again:
if (!len)
smp_rmb();
- add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
+ if (level != LOGLEVEL_DEFAULT) {
+ add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
+ KERN_SOH "%c", '0' + level);
+ add += vsnprintf(s->buffer + len + add,
+ sizeof(s->buffer) - len - add,
+ fmt, args);
+ } else {
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
+ fmt, args);
+ }
/*
* Do it once again if the buffer has been flushed in the meantime.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index d4de33934dac..a5ef95ca18c9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -26,7 +26,6 @@
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
-#include <linux/interrupt.h> /* For in_interrupt() */
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/security.h>
@@ -48,7 +47,7 @@
#include <linux/uio.h>
#include <asm/uaccess.h>
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
@@ -86,6 +85,111 @@ static struct lockdep_map console_lock_dep_map = {
};
#endif
+enum devkmsg_log_bits {
+ __DEVKMSG_LOG_BIT_ON = 0,
+ __DEVKMSG_LOG_BIT_OFF,
+ __DEVKMSG_LOG_BIT_LOCK,
+};
+
+enum devkmsg_log_masks {
+ DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON),
+ DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF),
+ DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK),
+};
+
+/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */
+#define DEVKMSG_LOG_MASK_DEFAULT 0
+
+static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
+
+static int __control_devkmsg(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strncmp(str, "on", 2)) {
+ devkmsg_log = DEVKMSG_LOG_MASK_ON;
+ return 2;
+ } else if (!strncmp(str, "off", 3)) {
+ devkmsg_log = DEVKMSG_LOG_MASK_OFF;
+ return 3;
+ } else if (!strncmp(str, "ratelimit", 9)) {
+ devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
+ return 9;
+ }
+ return -EINVAL;
+}
+
+static int __init control_devkmsg(char *str)
+{
+ if (__control_devkmsg(str) < 0)
+ return 1;
+
+ /*
+ * Set sysctl string accordingly:
+ */
+ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) {
+ memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE);
+ strncpy(devkmsg_log_str, "on", 2);
+ } else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) {
+ memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE);
+ strncpy(devkmsg_log_str, "off", 3);
+ }
+ /* else "ratelimit" which is set by default. */
+
+ /*
+ * Sysctl cannot change it anymore. The kernel command line setting of
+ * this parameter is to force the setting to be permanent throughout the
+ * runtime of the system. This is a precation measure against userspace
+ * trying to be a smarta** and attempting to change it up on us.
+ */
+ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
+
+ return 0;
+}
+__setup("printk.devkmsg=", control_devkmsg);
+
+char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
+
+int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ char old_str[DEVKMSG_STR_MAX_SIZE];
+ unsigned int old;
+ int err;
+
+ if (write) {
+ if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK)
+ return -EINVAL;
+
+ old = devkmsg_log;
+ strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE);
+ }
+
+ err = proc_dostring(table, write, buffer, lenp, ppos);
+ if (err)
+ return err;
+
+ if (write) {
+ err = __control_devkmsg(devkmsg_log_str);
+
+ /*
+ * Do not accept an unknown string OR a known string with
+ * trailing crap...
+ */
+ if (err < 0 || (err + 1 != *lenp)) {
+
+ /* ... and restore old setting. */
+ devkmsg_log = old;
+ strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE);
+
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
/*
* Number of registered extended console drivers.
*
@@ -614,6 +718,7 @@ struct devkmsg_user {
u64 seq;
u32 idx;
enum log_flags prev;
+ struct ratelimit_state rs;
struct mutex lock;
char buf[CONSOLE_EXT_LOG_MAX];
};
@@ -623,11 +728,24 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
char *buf, *line;
int level = default_message_loglevel;
int facility = 1; /* LOG_USER */
+ struct file *file = iocb->ki_filp;
+ struct devkmsg_user *user = file->private_data;
size_t len = iov_iter_count(from);
ssize_t ret = len;
- if (len > LOG_LINE_MAX)
+ if (!user || len > LOG_LINE_MAX)
return -EINVAL;
+
+ /* Ignore when user logging is disabled. */
+ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
+ return len;
+
+ /* Ratelimit when not explicitly enabled. */
+ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) {
+ if (!___ratelimit(&user->rs, current->comm))
+ return ret;
+ }
+
buf = kmalloc(len+1, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
@@ -800,19 +918,24 @@ static int devkmsg_open(struct inode *inode, struct file *file)
struct devkmsg_user *user;
int err;
- /* write-only does not need any file context */
- if ((file->f_flags & O_ACCMODE) == O_WRONLY)
- return 0;
+ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
+ return -EPERM;
- err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
- SYSLOG_FROM_READER);
- if (err)
- return err;
+ /* write-only does not need any file context */
+ if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+ err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+ SYSLOG_FROM_READER);
+ if (err)
+ return err;
+ }
user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
if (!user)
return -ENOMEM;
+ ratelimit_default_init(&user->rs);
+ ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);
+
mutex_init(&user->lock);
raw_spin_lock_irq(&logbuf_lock);
@@ -831,6 +954,8 @@ static int devkmsg_release(struct inode *inode, struct file *file)
if (!user)
return 0;
+ ratelimit_state_exit(&user->rs);
+
mutex_destroy(&user->lock);
kfree(user);
return 0;
@@ -986,6 +1111,11 @@ module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ignore_loglevel,
"ignore loglevel setting (prints all kernel messages to the console)");
+static bool suppress_message_printing(int level)
+{
+ return (level >= console_loglevel && !ignore_loglevel);
+}
+
#ifdef CONFIG_BOOT_PRINTK_DELAY
static int boot_delay; /* msecs delay after each printk during bootup */
@@ -1015,7 +1145,7 @@ static void boot_delay_msec(int level)
unsigned long timeout;
if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
- || (level >= console_loglevel && !ignore_loglevel)) {
+ || suppress_message_printing(level)) {
return;
}
@@ -1439,8 +1569,6 @@ static void call_console_drivers(int level,
trace_console(text, len);
- if (level >= console_loglevel && !ignore_loglevel)
- return;
if (!console_drivers)
return;
@@ -1802,7 +1930,28 @@ asmlinkage int printk_emit(int facility, int level,
}
EXPORT_SYMBOL(printk_emit);
-int vprintk_default(const char *fmt, va_list args)
+#ifdef CONFIG_PRINTK
+#define define_pr_level(func, loglevel) \
+asmlinkage __visible void func(const char *fmt, ...) \
+{ \
+ va_list args; \
+ \
+ va_start(args, fmt); \
+ vprintk_default(loglevel, fmt, args); \
+ va_end(args); \
+} \
+EXPORT_SYMBOL(func)
+
+define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
+define_pr_level(__pr_alert, LOGLEVEL_ALERT);
+define_pr_level(__pr_crit, LOGLEVEL_CRIT);
+define_pr_level(__pr_err, LOGLEVEL_ERR);
+define_pr_level(__pr_warn, LOGLEVEL_WARNING);
+define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
+define_pr_level(__pr_info, LOGLEVEL_INFO);
+#endif
+
+int vprintk_default(int level, const char *fmt, va_list args)
{
int r;
@@ -1812,7 +1961,7 @@ int vprintk_default(const char *fmt, va_list args)
return r;
}
#endif
- r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+ r = vprintk_emit(0, level, NULL, 0, fmt, args);
return r;
}
@@ -1845,7 +1994,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
int r;
va_start(args, fmt);
- r = vprintk_func(fmt, args);
+ r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
va_end(args);
return r;
@@ -1888,6 +2037,7 @@ static void call_console_drivers(int level,
static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev,
bool syslog, char *buf, size_t size) { return 0; }
static size_t cont_print_text(char *text, size_t size) { return 0; }
+static bool suppress_message_printing(int level) { return false; }
/* Still needs to be defined for users */
DEFINE_PER_CPU(printk_func_t, printk_func);
@@ -2167,6 +2317,13 @@ static void console_cont_flush(char *text, size_t size)
if (!cont.len)
goto out;
+ if (suppress_message_printing(cont.level)) {
+ cont.cons = cont.len;
+ if (cont.flushed)
+ cont.len = 0;
+ goto out;
+ }
+
/*
* We still queue earlier records, likely because the console was
* busy. The earlier ones need to be printed before this one, we
@@ -2270,10 +2427,13 @@ skip:
break;
msg = log_from_idx(console_idx);
- if (msg->flags & LOG_NOCONS) {
+ level = msg->level;
+ if ((msg->flags & LOG_NOCONS) ||
+ suppress_message_printing(level)) {
/*
* Skip record we have buffered and already printed
- * directly to the console when we received it.
+ * directly to the console when we received it, and
+ * record that has level above the console loglevel.
*/
console_idx = log_next(console_idx);
console_seq++;
@@ -2287,7 +2447,6 @@ skip:
goto skip;
}
- level = msg->level;
len += msg_print_text(msg, console_prev, false,
text + len, sizeof(text) - len);
if (nr_ext_console_drivers) {
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d49bfa1e53e6..1d3b7665d0be 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -585,8 +585,8 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
return -EINVAL;
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
- if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
- !config_enabled(CONFIG_SECCOMP))
+ if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
+ !IS_ENABLED(CONFIG_SECCOMP))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
diff --git a/kernel/relay.c b/kernel/relay.c
index 04d7cf3ef8cf..d797502140b9 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -451,6 +451,13 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
if (!dentry)
goto free_buf;
relay_set_buf_dentry(buf, dentry);
+ } else {
+ /* Only retrieve global info, nothing more, nothing less */
+ dentry = chan->cb->create_buf_file(NULL, NULL,
+ S_IRUSR, buf,
+ &chan->is_global);
+ if (WARN_ON(dentry))
+ goto free_buf;
}
buf->cpu = cpu;
@@ -562,6 +569,10 @@ static int relay_hotcpu_callback(struct notifier_block *nb,
* attributes specified. The created channel buffer files
* will be named base_filename0...base_filenameN-1. File
* permissions will be %S_IRUSR.
+ *
+ * If opening a buffer (@parent = NULL) that you later wish to register
+ * in a filesystem, call relay_late_setup_files() once the @parent dentry
+ * is available.
*/
struct rchan *relay_open(const char *base_filename,
struct dentry *parent,
@@ -640,8 +651,12 @@ static void __relay_set_buf_dentry(void *info)
*
* Returns 0 if successful, non-zero otherwise.
*
- * Use to setup files for a previously buffer-only channel.
- * Useful to do early tracing in kernel, before VFS is up, for example.
+ * Use to setup files for a previously buffer-only channel created
+ * by relay_open() with a NULL parent dentry.
+ *
+ * For example, this is useful for perfomring early tracing in kernel,
+ * before VFS is up and then exposing the early results once the dentry
+ * is available.
*/
int relay_late_setup_files(struct rchan *chan,
const char *base_filename,
@@ -666,6 +681,20 @@ int relay_late_setup_files(struct rchan *chan,
}
chan->has_base_filename = 1;
chan->parent = parent;
+
+ if (chan->is_global) {
+ err = -EINVAL;
+ if (!WARN_ON_ONCE(!chan->buf[0])) {
+ dentry = relay_create_buf_file(chan, chan->buf[0], 0);
+ if (dentry && !WARN_ON_ONCE(!chan->is_global)) {
+ relay_set_buf_dentry(chan->buf[0], dentry);
+ err = 0;
+ }
+ }
+ mutex_unlock(&relay_channels_mutex);
+ return err;
+ }
+
curr_cpu = get_cpu();
/*
* The CPU hotplug notifier ran before us and created buffers with
@@ -706,6 +735,7 @@ int relay_late_setup_files(struct rchan *chan,
return err;
}
+EXPORT_SYMBOL_GPL(relay_late_setup_files);
/**
* relay_switch_subbuf - switch to a new sub-buffer
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 7002796f14a4..ef6c6c3f9d8a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -173,7 +173,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
*
* Returns valid seccomp BPF response codes.
*/
-static u32 seccomp_run_filters(struct seccomp_data *sd)
+static u32 seccomp_run_filters(const struct seccomp_data *sd)
{
struct seccomp_data sd_local;
u32 ret = SECCOMP_RET_ALLOW;
@@ -347,7 +347,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
struct seccomp_filter *sfilter;
int ret;
- const bool save_orig = config_enabled(CONFIG_CHECKPOINT_RESTORE);
+ const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE);
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
return ERR_PTR(-EINVAL);
@@ -542,7 +542,7 @@ void secure_computing_strict(int this_syscall)
{
int mode = current->seccomp.mode;
- if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+ if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
return;
@@ -554,20 +554,10 @@ void secure_computing_strict(int this_syscall)
BUG();
}
#else
-int __secure_computing(void)
-{
- u32 phase1_result = seccomp_phase1(NULL);
-
- if (likely(phase1_result == SECCOMP_PHASE1_OK))
- return 0;
- else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
- return -1;
- else
- return seccomp_phase2(phase1_result);
-}
#ifdef CONFIG_SECCOMP_FILTER
-static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+ const bool recheck_after_trace)
{
u32 filter_ret, action;
int data;
@@ -599,10 +589,46 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
goto skip;
case SECCOMP_RET_TRACE:
- return filter_ret; /* Save the rest for phase 2. */
+ /* We've been put in this state by the ptracer already. */
+ if (recheck_after_trace)
+ return 0;
+
+ /* ENOSYS these calls if there is no tracer attached. */
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+ syscall_set_return_value(current,
+ task_pt_regs(current),
+ -ENOSYS, 0);
+ goto skip;
+ }
+
+ /* Allow the BPF to provide the event message */
+ ptrace_event(PTRACE_EVENT_SECCOMP, data);
+ /*
+ * The delivery of a fatal signal during event
+ * notification may silently skip tracer notification.
+ * Terminating the task now avoids executing a system
+ * call that may not be intended.
+ */
+ if (fatal_signal_pending(current))
+ do_exit(SIGSYS);
+ /* Check if the tracer forced the syscall to be skipped. */
+ this_syscall = syscall_get_nr(current, task_pt_regs(current));
+ if (this_syscall < 0)
+ goto skip;
+
+ /*
+ * Recheck the syscall, since it may have changed. This
+ * intentionally uses a NULL struct seccomp_data to force
+ * a reload of all registers. This does not goto skip since
+ * a skip would have already been reported.
+ */
+ if (__seccomp_filter(this_syscall, NULL, true))
+ return -1;
+
+ return 0;
case SECCOMP_RET_ALLOW:
- return SECCOMP_PHASE1_OK;
+ return 0;
case SECCOMP_RET_KILL:
default:
@@ -614,96 +640,38 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
skip:
audit_seccomp(this_syscall, 0, action);
- return SECCOMP_PHASE1_SKIP;
+ return -1;
+}
+#else
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+ const bool recheck_after_trace)
+{
+ BUG();
}
#endif
-/**
- * seccomp_phase1() - run fast path seccomp checks on the current syscall
- * @arg sd: The seccomp_data or NULL
- *
- * This only reads pt_regs via the syscall_xyz helpers. The only change
- * it will make to pt_regs is via syscall_set_return_value, and it will
- * only do that if it returns SECCOMP_PHASE1_SKIP.
- *
- * If sd is provided, it will not read pt_regs at all.
- *
- * It may also call do_exit or force a signal; these actions must be
- * safe.
- *
- * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
- * be processed normally.
- *
- * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
- * invoked. In this case, seccomp_phase1 will have set the return value
- * using syscall_set_return_value.
- *
- * If it returns anything else, then the return value should be passed
- * to seccomp_phase2 from a context in which ptrace hooks are safe.
- */
-u32 seccomp_phase1(struct seccomp_data *sd)
+int __secure_computing(const struct seccomp_data *sd)
{
int mode = current->seccomp.mode;
- int this_syscall = sd ? sd->nr :
- syscall_get_nr(current, task_pt_regs(current));
+ int this_syscall;
- if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+ if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
- return SECCOMP_PHASE1_OK;
+ return 0;
+
+ this_syscall = sd ? sd->nr :
+ syscall_get_nr(current, task_pt_regs(current));
switch (mode) {
case SECCOMP_MODE_STRICT:
__secure_computing_strict(this_syscall); /* may call do_exit */
- return SECCOMP_PHASE1_OK;
-#ifdef CONFIG_SECCOMP_FILTER
+ return 0;
case SECCOMP_MODE_FILTER:
- return __seccomp_phase1_filter(this_syscall, sd);
-#endif
+ return __seccomp_filter(this_syscall, sd, false);
default:
BUG();
}
}
-
-/**
- * seccomp_phase2() - finish slow path seccomp work for the current syscall
- * @phase1_result: The return value from seccomp_phase1()
- *
- * This must be called from a context in which ptrace hooks can be used.
- *
- * Returns 0 if the syscall should be processed or -1 to skip the syscall.
- */
-int seccomp_phase2(u32 phase1_result)
-{
- struct pt_regs *regs = task_pt_regs(current);
- u32 action = phase1_result & SECCOMP_RET_ACTION;
- int data = phase1_result & SECCOMP_RET_DATA;
-
- BUG_ON(action != SECCOMP_RET_TRACE);
-
- audit_seccomp(syscall_get_nr(current, regs), 0, action);
-
- /* Skip these calls if there is no tracer. */
- if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
- syscall_set_return_value(current, regs,
- -ENOSYS, 0);
- return -1;
- }
-
- /* Allow the BPF to provide the event message */
- ptrace_event(PTRACE_EVENT_SECCOMP, data);
- /*
- * The delivery of a fatal signal during event
- * notification may silently skip tracer notification.
- * Terminating the task now avoids executing a system
- * call that may not be intended.
- */
- if (fatal_signal_pending(current))
- do_exit(SIGSYS);
- if (syscall_get_nr(current, regs) < 0)
- return -1; /* Explicit request to skip. */
-
- return 0;
-}
#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
long prctl_get_seccomp(void)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index a467e6c28a3b..4a1ca5f6da7e 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
#include <linux/smpboot.h>
#include <linux/atomic.h>
#include <linux/lglock.h>
+#include <linux/nmi.h>
/*
* Structure to determine completion condition and record errors. May
@@ -209,6 +210,13 @@ static int multi_cpu_stop(void *data)
break;
}
ack_state(msdata);
+ } else if (curstate > MULTI_STOP_PREPARE) {
+ /*
+ * At this stage all other CPUs we depend on must spin
+ * in the same loop. Any reason for hard-lockup should
+ * be detected and reported on their side.
+ */
+ touch_nmi_watchdog();
}
} while (curstate != MULTI_STOP_EXIT);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 53954631a4e1..b43d0b27c1fe 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -814,6 +814,13 @@ static struct ctl_table kern_table[] = {
.extra2 = &ten_thousand,
},
{
+ .procname = "printk_devkmsg",
+ .data = devkmsg_log_str,
+ .maxlen = DEVKMSG_STR_MAX_SIZE,
+ .mode = 0644,
+ .proc_handler = devkmsg_sysctl_set_loglvl,
+ },
+ {
.procname = "dmesg_restrict",
.data = &dmesg_restrict,
.maxlen = sizeof(int),
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 6ab4842b00e8..d513051fcca2 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -29,7 +29,7 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
struct callback_head *head;
do {
- head = ACCESS_ONCE(task->task_works);
+ head = READ_ONCE(task->task_works);
if (unlikely(head == &work_exited))
return -ESRCH;
work->next = head;
@@ -57,6 +57,9 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
struct callback_head **pprev = &task->task_works;
struct callback_head *work;
unsigned long flags;
+
+ if (likely(!task->task_works))
+ return NULL;
/*
* If cmpxchg() fails we continue without updating pprev.
* Either we raced with task_work_add() which added the
@@ -64,8 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
- while ((work = ACCESS_ONCE(*pprev))) {
- smp_read_barrier_depends();
+ while ((work = lockless_dereference(*pprev))) {
if (work->func != func)
pprev = &work->next;
else if (cmpxchg(pprev, work, work->next) == work)
@@ -95,7 +97,7 @@ void task_work_run(void)
* work_exited unless the list is empty.
*/
do {
- work = ACCESS_ONCE(task->task_works);
+ work = READ_ONCE(task->task_works);
head = !work && (task->flags & PF_EXITING) ?
&work_exited : NULL;
} while (cmpxchg(&task->task_works, work, head) != work);
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 979e7bfbde7a..d0a1617b52b4 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -1,4 +1,8 @@
+# We are fully aware of the dangers of __builtin_return_address()
+FRAME_CFLAGS := $(call cc-disable-warning,frame-address)
+KBUILD_CFLAGS += $(FRAME_CFLAGS)
+
# Do not instrument the tracer itself:
ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0c05b8a99806..f3a960ed75a1 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1441,6 +1441,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
goto out;
}
+ if (hist_data->attrs->pause)
+ data->paused = true;
+
if (named_data) {
destroy_hist_data(data->private_data);
data->private_data = named_data->private_data;
@@ -1448,9 +1451,6 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
data->ops = &event_hist_trigger_named_ops;
}
- if (hist_data->attrs->pause)
- data->paused = true;
-
if (data->ops->init) {
ret = data->ops->init(data->ops, data);
if (ret < 0)
@@ -1500,9 +1500,9 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
static void hist_unreg_all(struct trace_event_file *file)
{
- struct event_trigger_data *test;
+ struct event_trigger_data *test, *n;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry_safe(test, n, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
list_del_rcu(&test->list);
trace_event_trigger_enable_disable(file, 0);
@@ -1699,9 +1699,9 @@ hist_enable_get_trigger_ops(char *cmd, char *param)
static void hist_enable_unreg_all(struct trace_event_file *file)
{
- struct event_trigger_data *test;
+ struct event_trigger_data *test, *n;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry_safe(test, n, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_HIST_ENABLE) {
list_del_rcu(&test->list);
update_cond_flag(file);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 9bafc211930c..68f594212759 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -938,6 +938,20 @@ bool userns_may_setgroups(const struct user_namespace *ns)
return allowed;
}
+/*
+ * Returns true if @ns is the same namespace as or a descendant of
+ * @target_ns.
+ */
+bool current_in_userns(const struct user_namespace *target_ns)
+{
+ struct user_namespace *ns;
+ for (ns = current_user_ns(); ns; ns = ns->parent) {
+ if (ns == target_ns)
+ return true;
+ }
+ return false;
+}
+
static inline struct user_namespace *to_user_ns(struct ns_common *ns)
{
return container_of(ns, struct user_namespace, ns);
Powered by cgit, Gruvboxed by Blaster4385.