summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile50
-rw-r--r--kernel/audit.c153
-rw-r--r--kernel/audit.h3
-rw-r--r--kernel/auditfilter.c3
-rw-r--r--kernel/auditsc.c133
-rw-r--r--kernel/bounds.c2
-rw-r--r--kernel/cgroup.c42
-rw-r--r--kernel/cpuset.c8
-rw-r--r--kernel/extable.c4
-rw-r--r--kernel/irq/settings.h7
-rw-r--r--kernel/irq/spurious.c12
-rw-r--r--kernel/modsign_certificate.S12
-rw-r--r--kernel/modsign_pubkey.c104
-rw-r--r--kernel/module-internal.h2
-rw-r--r--kernel/module_signing.c11
-rw-r--r--kernel/padata.c9
-rw-r--r--kernel/power/snapshot.c3
-rw-r--r--kernel/power/user.c1
-rw-r--r--kernel/system_certificates.S10
-rw-r--r--kernel/system_keyring.c105
-rw-r--r--kernel/taskstats.c38
-rw-r--r--kernel/trace/ftrace.c64
-rw-r--r--kernel/user.c4
-rw-r--r--kernel/user_namespace.c6
-rw-r--r--kernel/workqueue.c50
25 files changed, 532 insertions, 304 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 09a9c94f42bd..bbaf7d59c1bb 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -41,8 +41,9 @@ ifneq ($(CONFIG_SMP),y)
obj-y += up.o
endif
obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
obj-$(CONFIG_KEXEC) += kexec.o
@@ -122,19 +123,52 @@ targets += timeconst.h
$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
$(call if_changed,bc)
-ifeq ($(CONFIG_MODULE_SIG),y)
+###############################################################################
+#
+# Roll all the X.509 certificates that we can find together and pull them into
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
#
-# Pull the signing certificate and any extra certificates into the kernel
+# We look in the source root and the build root for all files whose name ends
+# in ".x509". Unfortunately, this will generate duplicate filenames, so we
+# have make canonicalise the pathnames and then sort them to discard the
+# duplicates.
#
+###############################################################################
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
+X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+ $(or $(realpath $(CERT)),$(CERT))))
+
+ifeq ($(X509_CERTIFICATES),)
+$(warning *** No X.509 certificates found ***)
+endif
+
+ifneq ($(wildcard $(obj)/.x509.list),)
+ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
+$(info X.509 certificate list changed)
+$(shell rm $(obj)/.x509.list)
+endif
+endif
+
+kernel/system_certificates.o: $(obj)/x509_certificate_list
-quiet_cmd_touch = TOUCH $@
- cmd_touch = touch $@
+quiet_cmd_x509certs = CERTS $@
+ cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)")
-extra_certificates:
- $(call cmd,touch)
+targets += $(obj)/x509_certificate_list
+$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
+ $(call if_changed,x509certs)
-kernel/modsign_certificate.o: signing_key.x509 extra_certificates
+targets += $(obj)/.x509.list
+$(obj)/.x509.list:
+ @echo $(X509_CERTIFICATES) >$@
+clean-files := x509_certificate_list .x509.list
+endif
+
+ifeq ($(CONFIG_MODULE_SIG),y)
###############################################################################
#
# If module signing is requested, say by allyesconfig, but a key has not been
diff --git a/kernel/audit.c b/kernel/audit.c
index 7b0e23a740ce..906ae5a0233a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -60,7 +60,6 @@
#ifdef CONFIG_SECURITY
#include <linux/security.h>
#endif
-#include <net/netlink.h>
#include <linux/freezer.h>
#include <linux/tty.h>
#include <linux/pid_namespace.h>
@@ -140,6 +139,17 @@ static struct task_struct *kauditd_task;
static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
+static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
+ .mask = -1,
+ .features = 0,
+ .lock = 0,};
+
+static char *audit_feature_names[2] = {
+ "only_unset_loginuid",
+ "loginuid_immutable",
+};
+
+
/* Serialize requests from userspace. */
DEFINE_MUTEX(audit_cmd_mutex);
@@ -584,6 +594,8 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
return -EOPNOTSUPP;
case AUDIT_GET:
case AUDIT_SET:
+ case AUDIT_GET_FEATURE:
+ case AUDIT_SET_FEATURE:
case AUDIT_LIST_RULES:
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
@@ -613,7 +625,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
int rc = 0;
uid_t uid = from_kuid(&init_user_ns, current_uid());
- if (!audit_enabled) {
+ if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
*ab = NULL;
return rc;
}
@@ -628,6 +640,94 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
return rc;
}
+int is_audit_feature_set(int i)
+{
+ return af.features & AUDIT_FEATURE_TO_MASK(i);
+}
+
+
+static int audit_get_feature(struct sk_buff *skb)
+{
+ u32 seq;
+
+ seq = nlmsg_hdr(skb)->nlmsg_seq;
+
+ audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
+ &af, sizeof(af));
+
+ return 0;
+}
+
+static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature,
+ u32 old_lock, u32 new_lock, int res)
+{
+ struct audit_buffer *ab;
+
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+ audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d",
+ audit_feature_names[which], !!old_feature, !!new_feature,
+ !!old_lock, !!new_lock, res);
+ audit_log_end(ab);
+}
+
+static int audit_set_feature(struct sk_buff *skb)
+{
+ struct audit_features *uaf;
+ int i;
+
+ BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > sizeof(audit_feature_names)/sizeof(audit_feature_names[0]));
+ uaf = nlmsg_data(nlmsg_hdr(skb));
+
+ /* if there is ever a version 2 we should handle that here */
+
+ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+ u32 feature = AUDIT_FEATURE_TO_MASK(i);
+ u32 old_feature, new_feature, old_lock, new_lock;
+
+ /* if we are not changing this feature, move along */
+ if (!(feature & uaf->mask))
+ continue;
+
+ old_feature = af.features & feature;
+ new_feature = uaf->features & feature;
+ new_lock = (uaf->lock | af.lock) & feature;
+ old_lock = af.lock & feature;
+
+ /* are we changing a locked feature? */
+ if ((af.lock & feature) && (new_feature != old_feature)) {
+ audit_log_feature_change(i, old_feature, new_feature,
+ old_lock, new_lock, 0);
+ return -EPERM;
+ }
+ }
+ /* nothing invalid, do the changes */
+ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+ u32 feature = AUDIT_FEATURE_TO_MASK(i);
+ u32 old_feature, new_feature, old_lock, new_lock;
+
+ /* if we are not changing this feature, move along */
+ if (!(feature & uaf->mask))
+ continue;
+
+ old_feature = af.features & feature;
+ new_feature = uaf->features & feature;
+ old_lock = af.lock & feature;
+ new_lock = (uaf->lock | af.lock) & feature;
+
+ if (new_feature != old_feature)
+ audit_log_feature_change(i, old_feature, new_feature,
+ old_lock, new_lock, 1);
+
+ if (new_feature)
+ af.features |= feature;
+ else
+ af.features &= ~feature;
+ af.lock |= new_lock;
+ }
+
+ return 0;
+}
+
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
u32 seq;
@@ -659,6 +759,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
switch (msg_type) {
case AUDIT_GET:
+ memset(&status_set, 0, sizeof(status_set));
status_set.enabled = audit_enabled;
status_set.failure = audit_failure;
status_set.pid = audit_pid;
@@ -670,7 +771,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
&status_set, sizeof(status_set));
break;
case AUDIT_SET:
- if (nlh->nlmsg_len < sizeof(struct audit_status))
+ if (nlmsg_len(nlh) < sizeof(struct audit_status))
return -EINVAL;
status_get = (struct audit_status *)data;
if (status_get->mask & AUDIT_STATUS_ENABLED) {
@@ -699,6 +800,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
err = audit_set_backlog_limit(status_get->backlog_limit);
break;
+ case AUDIT_GET_FEATURE:
+ err = audit_get_feature(skb);
+ if (err)
+ return err;
+ break;
+ case AUDIT_SET_FEATURE:
+ err = audit_set_feature(skb);
+ if (err)
+ return err;
+ break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
@@ -715,7 +826,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
}
audit_log_common_recv_msg(&ab, msg_type);
if (msg_type != AUDIT_USER_TTY)
- audit_log_format(ab, " msg='%.1024s'",
+ audit_log_format(ab, " msg='%.*s'",
+ AUDIT_MESSAGE_TEXT_MAX,
(char *)data);
else {
int size;
@@ -818,7 +930,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct task_struct *tsk = current;
spin_lock(&tsk->sighand->siglock);
- s.enabled = tsk->signal->audit_tty != 0;
+ s.enabled = tsk->signal->audit_tty;
s.log_passwd = tsk->signal->audit_tty_log_passwd;
spin_unlock(&tsk->sighand->siglock);
@@ -832,7 +944,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
- memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+ memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
if ((s.enabled != 0 && s.enabled != 1) ||
(s.log_passwd != 0 && s.log_passwd != 1))
return -EINVAL;
@@ -1067,13 +1179,6 @@ static void wait_for_auditd(unsigned long sleep_time)
remove_wait_queue(&audit_backlog_wait, &wait);
}
-/* Obtain an audit buffer. This routine does locking to obtain the
- * audit buffer, but then no locking is required for calls to
- * audit_log_*format. If the tsk is a task that is currently in a
- * syscall, then the syscall is marked as auditable and an audit record
- * will be written at syscall exit. If there is no associated task, tsk
- * should be NULL. */
-
/**
* audit_log_start - obtain an audit buffer
* @ctx: audit_context (may be NULL)
@@ -1389,7 +1494,7 @@ void audit_log_session_info(struct audit_buffer *ab)
u32 sessionid = audit_get_sessionid(current);
uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
- audit_log_format(ab, " auid=%u ses=%u\n", auid, sessionid);
+ audit_log_format(ab, " auid=%u ses=%u", auid, sessionid);
}
void audit_log_key(struct audit_buffer *ab, char *key)
@@ -1536,6 +1641,26 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
}
}
+ /* log the audit_names record type */
+ audit_log_format(ab, " nametype=");
+ switch(n->type) {
+ case AUDIT_TYPE_NORMAL:
+ audit_log_format(ab, "NORMAL");
+ break;
+ case AUDIT_TYPE_PARENT:
+ audit_log_format(ab, "PARENT");
+ break;
+ case AUDIT_TYPE_CHILD_DELETE:
+ audit_log_format(ab, "DELETE");
+ break;
+ case AUDIT_TYPE_CHILD_CREATE:
+ audit_log_format(ab, "CREATE");
+ break;
+ default:
+ audit_log_format(ab, "UNKNOWN");
+ break;
+ }
+
audit_log_fcaps(ab, n);
audit_log_end(ab);
}
diff --git a/kernel/audit.h b/kernel/audit.h
index 123c9b7c3979..b779642b29af 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -197,6 +197,9 @@ struct audit_context {
int fd;
int flags;
} mmap;
+ struct {
+ int argc;
+ } execve;
};
int fds[2];
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index f7aee8be7fb2..51f3fd4c1ed3 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -343,6 +343,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
case AUDIT_DEVMINOR:
case AUDIT_EXIT:
case AUDIT_SUCCESS:
+ case AUDIT_INODE:
/* bit ops are only useful on syscall args */
if (f->op == Audit_bitmask || f->op == Audit_bittest)
return -EINVAL;
@@ -423,7 +424,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
f->lsm_rule = NULL;
/* Support legacy tests for a valid loginuid */
- if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
+ if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
f->type = AUDIT_LOGINUID_SET;
f->val = 0;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 9845cb32b60a..90594c9f7552 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -95,13 +95,6 @@ struct audit_aux_data {
/* Number of target pids per aux struct. */
#define AUDIT_AUX_PIDS 16
-struct audit_aux_data_execve {
- struct audit_aux_data d;
- int argc;
- int envc;
- struct mm_struct *mm;
-};
-
struct audit_aux_data_pids {
struct audit_aux_data d;
pid_t target_pid[AUDIT_AUX_PIDS];
@@ -121,12 +114,6 @@ struct audit_aux_data_bprm_fcaps {
struct audit_cap_data new_pcap;
};
-struct audit_aux_data_capset {
- struct audit_aux_data d;
- pid_t pid;
- struct audit_cap_data cap;
-};
-
struct audit_tree_refs {
struct audit_tree_refs *next;
struct audit_chunk *c[31];
@@ -566,7 +553,7 @@ static int audit_filter_rules(struct task_struct *tsk,
break;
case AUDIT_INODE:
if (name)
- result = (name->ino == f->val);
+ result = audit_comparator(name->ino, f->op, f->val);
else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_comparator(n->ino, f->op, f->val)) {
@@ -943,8 +930,10 @@ int audit_alloc(struct task_struct *tsk)
return 0; /* Return if not auditing. */
state = audit_filter_task(tsk, &key);
- if (state == AUDIT_DISABLED)
+ if (state == AUDIT_DISABLED) {
+ clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
+ }
if (!(context = audit_alloc_context(state))) {
kfree(key);
@@ -1149,20 +1138,16 @@ static int audit_log_single_execve_arg(struct audit_context *context,
}
static void audit_log_execve_info(struct audit_context *context,
- struct audit_buffer **ab,
- struct audit_aux_data_execve *axi)
+ struct audit_buffer **ab)
{
int i, len;
size_t 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;
+ p = (const char __user *)current->mm->arg_start;
- audit_log_format(*ab, "argc=%d", axi->argc);
+ audit_log_format(*ab, "argc=%d", context->execve.argc);
/*
* we need some kernel buffer to hold the userspace args. Just
@@ -1176,7 +1161,7 @@ static void audit_log_execve_info(struct audit_context *context,
return;
}
- for (i = 0; i < axi->argc; i++) {
+ for (i = 0; i < context->execve.argc; i++) {
len = audit_log_single_execve_arg(context, ab, i,
&len_sent, p, buf);
if (len <= 0)
@@ -1279,6 +1264,9 @@ static void show_special(struct audit_context *context, int *call_panic)
audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
context->mmap.flags);
break; }
+ case AUDIT_EXECVE: {
+ audit_log_execve_info(context, &ab);
+ break; }
}
audit_log_end(ab);
}
@@ -1325,11 +1313,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
switch (aux->type) {
- case AUDIT_EXECVE: {
- struct audit_aux_data_execve *axi = (void *)aux;
- audit_log_execve_info(context, &ab, axi);
- break; }
-
case AUDIT_BPRM_FCAPS: {
struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
audit_log_format(ab, "fver=%x", axs->fcap_ver);
@@ -1964,6 +1947,43 @@ int auditsc_get_stamp(struct audit_context *ctx,
/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);
+static int audit_set_loginuid_perm(kuid_t loginuid)
+{
+ /* if we are unset, we don't need privs */
+ if (!audit_loginuid_set(current))
+ return 0;
+ /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
+ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
+ return -EPERM;
+ /* it is set, you need permission */
+ if (!capable(CAP_AUDIT_CONTROL))
+ return -EPERM;
+ /* reject if this is not an unset and we don't allow that */
+ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid))
+ return -EPERM;
+ return 0;
+}
+
+static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
+ unsigned int oldsessionid, unsigned int sessionid,
+ int rc)
+{
+ struct audit_buffer *ab;
+ uid_t uid, ologinuid, nloginuid;
+
+ uid = from_kuid(&init_user_ns, task_uid(current));
+ ologinuid = from_kuid(&init_user_ns, koldloginuid);
+ nloginuid = from_kuid(&init_user_ns, kloginuid),
+
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+ if (!ab)
+ return;
+ audit_log_format(ab, "pid=%d uid=%u old auid=%u new auid=%u old "
+ "ses=%u new ses=%u res=%d", current->pid, uid, ologinuid,
+ nloginuid, oldsessionid, sessionid, !rc);
+ audit_log_end(ab);
+}
+
/**
* audit_set_loginuid - set current task's audit_context loginuid
* @loginuid: loginuid value
@@ -1975,37 +1995,26 @@ static atomic_t session_id = ATOMIC_INIT(0);
int audit_set_loginuid(kuid_t loginuid)
{
struct task_struct *task = current;
- struct audit_context *context = task->audit_context;
- unsigned int sessionid;
+ unsigned int oldsessionid, sessionid = (unsigned int)-1;
+ kuid_t oldloginuid;
+ int rc;
-#ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE
- if (audit_loginuid_set(task))
- return -EPERM;
-#else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
- if (!capable(CAP_AUDIT_CONTROL))
- return -EPERM;
-#endif /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
+ oldloginuid = audit_get_loginuid(current);
+ oldsessionid = audit_get_sessionid(current);
- sessionid = atomic_inc_return(&session_id);
- if (context && context->in_syscall) {
- struct audit_buffer *ab;
+ rc = audit_set_loginuid_perm(loginuid);
+ if (rc)
+ goto out;
+
+ /* are we setting or clearing? */
+ if (uid_valid(loginuid))
+ sessionid = atomic_inc_return(&session_id);
- 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,
- from_kuid(&init_user_ns, task_uid(task)),
- from_kuid(&init_user_ns, task->loginuid),
- from_kuid(&init_user_ns, loginuid),
- task->sessionid, sessionid);
- audit_log_end(ab);
- }
- }
task->sessionid = sessionid;
task->loginuid = loginuid;
- return 0;
+out:
+ audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
+ return rc;
}
/**
@@ -2126,22 +2135,12 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo
context->ipc.has_perm = 1;
}
-int __audit_bprm(struct linux_binprm *bprm)
+void __audit_bprm(struct linux_binprm *bprm)
{
- struct audit_aux_data_execve *ax;
struct audit_context *context = current->audit_context;
- ax = kmalloc(sizeof(*ax), GFP_KERNEL);
- if (!ax)
- return -ENOMEM;
-
- ax->argc = bprm->argc;
- ax->envc = bprm->envc;
- ax->mm = bprm->mm;
- ax->d.type = AUDIT_EXECVE;
- ax->d.next = context->aux;
- context->aux = (void *)ax;
- return 0;
+ context->type = AUDIT_EXECVE;
+ context->execve.argc = bprm->argc;
}
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 578782ef6ae1..5253204afdca 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -11,7 +11,7 @@
#include <linux/kbuild.h>
#include <linux/page_cgroup.h>
#include <linux/log2.h>
-#include <linux/spinlock.h>
+#include <linux/spinlock_types.h>
void foo(void)
{
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e0839bcd48c8..8b729c278b64 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -90,6 +90,14 @@ static DEFINE_MUTEX(cgroup_mutex);
static DEFINE_MUTEX(cgroup_root_mutex);
/*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions. Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
+/*
* Generate an array of cgroup subsystem pointers. At boot time, this is
* populated with the built in subsystems, and modular subsystems are
* registered after that. The mutable section of this array is protected by
@@ -191,6 +199,7 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
+static int cgroup_file_release(struct inode *inode, struct file *file);
/**
* cgroup_css - obtain a cgroup's css for the specified subsystem
@@ -871,7 +880,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
INIT_WORK(&cgrp->destroy_work, cgroup_free_fn);
- schedule_work(&cgrp->destroy_work);
+ queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
}
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -895,11 +904,6 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
iput(inode);
}
-static int cgroup_delete(const struct dentry *d)
-{
- return 1;
-}
-
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
@@ -1486,7 +1490,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
{
static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
- .d_delete = cgroup_delete,
+ .d_delete = always_delete_dentry,
};
struct inode *inode =
@@ -2426,7 +2430,7 @@ static const struct file_operations cgroup_seqfile_operations = {
.read = seq_read,
.write = cgroup_file_write,
.llseek = seq_lseek,
- .release = single_release,
+ .release = cgroup_file_release,
};
static int cgroup_file_open(struct inode *inode, struct file *file)
@@ -2487,6 +2491,8 @@ static int cgroup_file_release(struct inode *inode, struct file *file)
ret = cft->release(inode, file);
if (css->ss)
css_put(css);
+ if (file->f_op == &cgroup_seqfile_operations)
+ single_release(inode, file);
return ret;
}
@@ -4254,7 +4260,7 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
* css_put(). dput() requires process context which we don't have.
*/
INIT_WORK(&css->destroy_work, css_free_work_fn);
- schedule_work(&css->destroy_work);
+ queue_work(cgroup_destroy_wq, &css->destroy_work);
}
static void css_release(struct percpu_ref *ref)
@@ -4544,7 +4550,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_killed_work_fn);
- schedule_work(&css->destroy_work);
+ queue_work(cgroup_destroy_wq, &css->destroy_work);
}
/**
@@ -5068,6 +5074,22 @@ out:
return err;
}
+static int __init cgroup_wq_init(void)
+{
+ /*
+ * There isn't much point in executing destruction path in
+ * parallel. Good chunk is serialized with cgroup_mutex anyway.
+ * Use 1 for @max_active.
+ *
+ * We would prefer to do this in cgroup_init() above, but that
+ * is called before init_workqueues(): so leave this until after.
+ */
+ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+ BUG_ON(!cgroup_destroy_wq);
+ return 0;
+}
+core_initcall(cgroup_wq_init);
+
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6bf981e13c43..4772034b4b17 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1033,8 +1033,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
need_loop = task_has_mempolicy(tsk) ||
!nodes_intersects(*newmems, tsk->mems_allowed);
- if (need_loop)
+ if (need_loop) {
+ local_irq_disable();
write_seqcount_begin(&tsk->mems_allowed_seq);
+ }
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -1042,8 +1044,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
tsk->mems_allowed = *newmems;
- if (need_loop)
+ if (need_loop) {
write_seqcount_end(&tsk->mems_allowed_seq);
+ local_irq_enable();
+ }
task_unlock(tsk);
}
diff --git a/kernel/extable.c b/kernel/extable.c
index 832cb28105bb..763faf037ec1 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -61,7 +61,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
static inline int init_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_sinittext &&
- addr <= (unsigned long)_einittext)
+ addr < (unsigned long)_einittext)
return 1;
return 0;
}
@@ -69,7 +69,7 @@ static inline int init_kernel_text(unsigned long addr)
int core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
- addr <= (unsigned long)_etext)
+ addr < (unsigned long)_etext)
return 1;
if (system_state == SYSTEM_BOOTING &&
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 1162f1030f18..3320b84cc60f 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,6 +14,7 @@ enum {
_IRQ_NO_BALANCING = IRQ_NO_BALANCING,
_IRQ_NESTED_THREAD = IRQ_NESTED_THREAD,
_IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID,
+ _IRQ_IS_POLLED = IRQ_IS_POLLED,
_IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
};
@@ -26,6 +27,7 @@ enum {
#define IRQ_NOAUTOEN GOT_YOU_MORON
#define IRQ_NESTED_THREAD GOT_YOU_MORON
#define IRQ_PER_CPU_DEVID GOT_YOU_MORON
+#define IRQ_IS_POLLED GOT_YOU_MORON
#undef IRQF_MODIFY_MASK
#define IRQF_MODIFY_MASK GOT_YOU_MORON
@@ -147,3 +149,8 @@ static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_NESTED_THREAD;
}
+
+static inline bool irq_settings_is_polled(struct irq_desc *desc)
+{
+ return desc->status_use_accessors & _IRQ_IS_POLLED;
+}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7b5f012bde9d..a1d8cc63b56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -67,8 +67,13 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
raw_spin_lock(&desc->lock);
- /* PER_CPU and nested thread interrupts are never polled */
- if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+ /*
+ * PER_CPU, nested thread interrupts and interrupts explicitely
+ * marked polled are excluded from polling.
+ */
+ if (irq_settings_is_per_cpu(desc) ||
+ irq_settings_is_nested_thread(desc) ||
+ irq_settings_is_polled(desc))
goto out;
/*
@@ -268,7 +273,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
void note_interrupt(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
- if (desc->istate & IRQS_POLL_INPROGRESS)
+ if (desc->istate & IRQS_POLL_INPROGRESS ||
+ irq_settings_is_polled(desc))
return;
/* we get here again via the threaded handler */
diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S
deleted file mode 100644
index 4a9a86d12c8b..000000000000
--- a/kernel/modsign_certificate.S
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <linux/export.h>
-
-#define GLOBAL(name) \
- .globl VMLINUX_SYMBOL(name); \
- VMLINUX_SYMBOL(name):
-
- .section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
- .incbin "signing_key.x509"
- .incbin "extra_certificates"
-GLOBAL(modsign_certificate_list_end)
diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c
deleted file mode 100644
index 7cbd4507a7e6..000000000000
--- a/kernel/modsign_pubkey.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/* Public keys for module signature verification
- *
- * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cred.h>
-#include <linux/err.h>
-#include <keys/asymmetric-type.h>
-#include "module-internal.h"
-
-struct key *modsign_keyring;
-
-extern __initconst const u8 modsign_certificate_list[];
-extern __initconst const u8 modsign_certificate_list_end[];
-
-/*
- * We need to make sure ccache doesn't cache the .o file