summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile6
-rw-r--r--kernel/audit.c49
-rw-r--r--kernel/audit.h3
-rw-r--r--kernel/audit_tree.c92
-rw-r--r--kernel/audit_watch.c14
-rw-r--r--kernel/auditsc.c15
-rw-r--r--kernel/bpf/core.c12
-rw-r--r--kernel/events/core.c41
-rw-r--r--kernel/irq/dummychip.c1
-rw-r--r--kernel/kexec.c2
-rw-r--r--kernel/locking/rtmutex.c12
-rw-r--r--kernel/module.c3
-rw-r--r--kernel/rcu/tree.c16
-rw-r--r--kernel/relay.c4
-rw-r--r--kernel/sched/core.c74
-rw-r--r--kernel/sched/idle.c16
-rw-r--r--kernel/time/clockevents.c6
-rw-r--r--kernel/time/hrtimer.c14
-rw-r--r--kernel/trace/trace.c2
-rw-r--r--kernel/trace/trace_events.c4
-rw-r--r--kernel/trace/trace_output.c3
-rw-r--r--kernel/trace/trace_uprobe.c2
-rw-r--r--kernel/watchdog.c20
23 files changed, 231 insertions, 180 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 0f8f8b0bc1bf..60c302cfb4d3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -197,9 +197,9 @@ x509.genkey:
@echo >>x509.genkey "x509_extensions = myexts"
@echo >>x509.genkey
@echo >>x509.genkey "[ req_distinguished_name ]"
- @echo >>x509.genkey "O = Magrathea"
- @echo >>x509.genkey "CN = Glacier signing key"
- @echo >>x509.genkey "emailAddress = slartibartfast@magrathea.h2g2"
+ @echo >>x509.genkey "#O = Unspecified company"
+ @echo >>x509.genkey "CN = Build time autogenerated kernel key"
+ @echo >>x509.genkey "#emailAddress = unspecified.user@unspecified.company"
@echo >>x509.genkey
@echo >>x509.genkey "[ myexts ]"
@echo >>x509.genkey "basicConstraints=critical,CA:FALSE"
diff --git a/kernel/audit.c b/kernel/audit.c
index 72ab759a0b43..1c13e4267de6 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -43,6 +43,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/file.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/atomic.h>
@@ -107,6 +108,7 @@ static u32 audit_rate_limit;
* When set to zero, this means unlimited. */
static u32 audit_backlog_limit = 64;
#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static u32 audit_backlog_wait_time_master = AUDIT_BACKLOG_WAIT_TIME;
static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
static u32 audit_backlog_wait_overflow = 0;
@@ -338,13 +340,13 @@ static int audit_set_backlog_limit(u32 limit)
static int audit_set_backlog_wait_time(u32 timeout)
{
return audit_do_config_change("audit_backlog_wait_time",
- &audit_backlog_wait_time, timeout);
+ &audit_backlog_wait_time_master, timeout);
}
static int audit_set_enabled(u32 state)
{
int rc;
- if (state < AUDIT_OFF || state > AUDIT_LOCKED)
+ if (state > AUDIT_LOCKED)
return -EINVAL;
rc = audit_do_config_change("audit_enabled", &audit_enabled, state);
@@ -663,7 +665,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
case AUDIT_MAKE_EQUIV:
/* Only support auditd and auditctl in initial pid namespace
* for now. */
- if ((task_active_pid_ns(current) != &init_pid_ns))
+ if (task_active_pid_ns(current) != &init_pid_ns)
return -EPERM;
if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
@@ -834,7 +836,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.lost = atomic_read(&audit_lost);
s.backlog = skb_queue_len(&audit_skb_queue);
s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL;
- s.backlog_wait_time = audit_backlog_wait_time;
+ s.backlog_wait_time = audit_backlog_wait_time_master;
audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
@@ -877,8 +879,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) {
if (sizeof(s) > (size_t)nlh->nlmsg_len)
return -EINVAL;
- if (s.backlog_wait_time < 0 ||
- s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
+ if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
return -EINVAL;
err = audit_set_backlog_wait_time(s.backlog_wait_time);
if (err < 0)
@@ -1385,7 +1386,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
return NULL;
}
- audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+ if (!reserve)
+ audit_backlog_wait_time = audit_backlog_wait_time_master;
ab = audit_buffer_alloc(ctx, gfp_mask, type);
if (!ab) {
@@ -1759,7 +1761,7 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
} else
audit_log_format(ab, " name=(null)");
- if (n->ino != (unsigned long)-1) {
+ if (n->ino != (unsigned long)-1)
audit_log_format(ab, " inode=%lu"
" dev=%02x:%02x mode=%#ho"
" ouid=%u ogid=%u rdev=%02x:%02x",
@@ -1771,7 +1773,6 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
from_kgid(&init_user_ns, n->gid),
MAJOR(n->rdev),
MINOR(n->rdev));
- }
if (n->osid != 0) {
char *ctx = NULL;
u32 len;
@@ -1838,11 +1839,29 @@ error_path:
}
EXPORT_SYMBOL(audit_log_task_context);
+void audit_log_d_path_exe(struct audit_buffer *ab,
+ struct mm_struct *mm)
+{
+ struct file *exe_file;
+
+ if (!mm)
+ goto out_null;
+
+ exe_file = get_mm_exe_file(mm);
+ if (!exe_file)
+ goto out_null;
+
+ audit_log_d_path(ab, " exe=", &exe_file->f_path);
+ fput(exe_file);
+ return;
+out_null:
+ audit_log_format(ab, " exe=(null)");
+}
+
void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
char comm[sizeof(tsk->comm)];
- struct mm_struct *mm = tsk->mm;
char *tty;
if (!ab)
@@ -1878,13 +1897,7 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, get_task_comm(comm, tsk));
- if (mm) {
- down_read(&mm->mmap_sem);
- if (mm->exe_file)
- audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
- up_read(&mm->mmap_sem);
- } else
- audit_log_format(ab, " exe=(null)");
+ audit_log_d_path_exe(ab, tsk->mm);
audit_log_task_context(ab);
}
EXPORT_SYMBOL(audit_log_task_info);
@@ -1915,7 +1928,7 @@ void audit_log_link_denied(const char *operation, struct path *link)
/* Generate AUDIT_PATH record with object. */
name->type = AUDIT_TYPE_NORMAL;
- audit_copy_inode(name, link->dentry, link->dentry->d_inode);
+ audit_copy_inode(name, link->dentry, d_backing_inode(link->dentry));
audit_log_name(current->audit_context, name, link, 0, NULL);
out:
kfree(name);
diff --git a/kernel/audit.h b/kernel/audit.h
index 1caa0d345d90..d641f9bb3ed0 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -257,6 +257,9 @@ extern struct list_head audit_filter_list[];
extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
+extern void audit_log_d_path_exe(struct audit_buffer *ab,
+ struct mm_struct *mm);
+
/* audit watch functions */
#ifdef CONFIG_AUDIT_WATCH
extern void audit_put_watch(struct audit_watch *watch);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 2e0c97427b33..b0f9877273fc 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -37,6 +37,7 @@ struct audit_chunk {
static LIST_HEAD(tree_list);
static LIST_HEAD(prune_list);
+static struct task_struct *prune_thread;
/*
* One struct chunk is attached to each inode of interest.
@@ -576,7 +577,7 @@ int audit_remove_tree_rule(struct audit_krule *rule)
static int compare_root(struct vfsmount *mnt, void *arg)
{
- return mnt->mnt_root->d_inode == arg;
+ return d_backing_inode(mnt->mnt_root) == arg;
}
void audit_trim_trees(void)
@@ -648,7 +649,58 @@ void audit_put_tree(struct audit_tree *tree)
static int tag_mount(struct vfsmount *mnt, void *arg)
{
- return tag_chunk(mnt->mnt_root->d_inode, arg);
+ return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+}
+
+/*
+ * That gets run when evict_chunk() ends up needing to kill audit_tree.
+ * Runs from a separate thread.
+ */
+static int prune_tree_thread(void *unused)
+{
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (list_empty(&prune_list))
+ schedule();
+ __set_current_state(TASK_RUNNING);
+
+ mutex_lock(&audit_cmd_mutex);
+ mutex_lock(&audit_filter_mutex);
+
+ while (!list_empty(&prune_list)) {
+ struct audit_tree *victim;
+
+ victim = list_entry(prune_list.next,
+ struct audit_tree, list);
+ list_del_init(&victim->list);
+
+ mutex_unlock(&audit_filter_mutex);
+
+ prune_one(victim);
+
+ mutex_lock(&audit_filter_mutex);
+ }
+
+ mutex_unlock(&audit_filter_mutex);
+ mutex_unlock(&audit_cmd_mutex);
+ }
+ return 0;
+}
+
+static int audit_launch_prune(void)
+{
+ if (prune_thread)
+ return 0;
+ prune_thread = kthread_create(prune_tree_thread, NULL,
+ "audit_prune_tree");
+ if (IS_ERR(prune_thread)) {
+ pr_err("cannot start thread audit_prune_tree");
+ prune_thread = NULL;
+ return -ENOMEM;
+ } else {
+ wake_up_process(prune_thread);
+ return 0;
+ }
}
/* called with audit_filter_mutex */
@@ -674,6 +726,12 @@ int audit_add_tree_rule(struct audit_krule *rule)
/* do not set rule->tree yet */
mutex_unlock(&audit_filter_mutex);
+ if (unlikely(!prune_thread)) {
+ err = audit_launch_prune();
+ if (err)
+ goto Err;
+ }
+
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
@@ -811,36 +869,10 @@ int audit_tag_tree(char *old, char *new)
return failed;
}
-/*
- * That gets run when evict_chunk() ends up needing to kill audit_tree.
- * Runs from a separate thread.
- */
-static int prune_tree_thread(void *unused)
-{
- mutex_lock(&audit_cmd_mutex);
- mutex_lock(&audit_filter_mutex);
-
- while (!list_empty(&prune_list)) {
- struct audit_tree *victim;
-
- victim = list_entry(prune_list.next, struct audit_tree, list);
- list_del_init(&victim->list);
-
- mutex_unlock(&audit_filter_mutex);
-
- prune_one(victim);
-
- mutex_lock(&audit_filter_mutex);
- }
-
- mutex_unlock(&audit_filter_mutex);
- mutex_unlock(&audit_cmd_mutex);
- return 0;
-}
static void audit_schedule_prune(void)
{
- kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
+ wake_up_process(prune_thread);
}
/*
@@ -907,9 +939,9 @@ static void evict_chunk(struct audit_chunk *chunk)
for (n = 0; n < chunk->count; n++)
list_del_init(&chunk->owners[n].list);
spin_unlock(&hash_lock);
+ mutex_unlock(&audit_filter_mutex);
if (need_prune)
audit_schedule_prune();
- mutex_unlock(&audit_filter_mutex);
}
static int audit_tree_handle_event(struct fsnotify_group *group,
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index ad9c1682f616..6e30024d9aac 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -146,7 +146,7 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
/* Initialize a parent watch entry. */
static struct audit_parent *audit_init_parent(struct path *path)
{
- struct inode *inode = path->dentry->d_inode;
+ struct inode *inode = d_backing_inode(path->dentry);
struct audit_parent *parent;
int ret;
@@ -361,11 +361,11 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
struct dentry *d = kern_path_locked(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
- mutex_unlock(&parent->dentry->d_inode->i_mutex);
- if (d->d_inode) {
+ mutex_unlock(&d_backing_inode(parent->dentry)->i_mutex);
+ if (d_is_positive(d)) {
/* update watch filter fields */
- watch->dev = d->d_inode->i_sb->s_dev;
- watch->ino = d->d_inode->i_ino;
+ watch->dev = d_backing_inode(d)->i_sb->s_dev;
+ watch->ino = d_backing_inode(d)->i_ino;
}
dput(d);
return 0;
@@ -426,7 +426,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
return ret;
/* either find an old parent or attach a new one */
- parent = audit_find_parent(parent_path.dentry->d_inode);
+ parent = audit_find_parent(d_backing_inode(parent_path.dentry));
if (!parent) {
parent = audit_init_parent(&parent_path);
if (IS_ERR(parent)) {
@@ -482,7 +482,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
switch (data_type) {
case (FSNOTIFY_EVENT_PATH):
- inode = ((struct path *)data)->dentry->d_inode;
+ inode = d_backing_inode(((struct path *)data)->dentry);
break;
case (FSNOTIFY_EVENT_INODE):
inode = (struct inode *)data;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index dc4ae70a7413..9fb9d1cb83ce 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1629,7 +1629,7 @@ retry:
rcu_read_lock();
seq = read_seqbegin(&rename_lock);
for(;;) {
- struct inode *inode = d->d_inode;
+ struct inode *inode = d_backing_inode(d);
if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
struct audit_chunk *chunk;
chunk = audit_tree_lookup(inode);
@@ -1754,7 +1754,7 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
unsigned int flags)
{
struct audit_context *context = current->audit_context;
- const struct inode *inode = dentry->d_inode;
+ const struct inode *inode = d_backing_inode(dentry);
struct audit_names *n;
bool parent = flags & AUDIT_INODE_PARENT;
@@ -1853,7 +1853,7 @@ void __audit_inode_child(const struct inode *parent,
const unsigned char type)
{
struct audit_context *context = current->audit_context;
- const struct inode *inode = dentry->d_inode;
+ const struct inode *inode = d_backing_inode(dentry);
const char *dname = dentry->d_name.name;
struct audit_names *n, *found_parent = NULL, *found_child = NULL;
@@ -2361,7 +2361,6 @@ static void audit_log_task(struct audit_buffer *ab)
kuid_t auid, uid;
kgid_t gid;
unsigned int sessionid;
- struct mm_struct *mm = current->mm;
char comm[sizeof(current->comm)];
auid = audit_get_loginuid(current);
@@ -2376,13 +2375,7 @@ static void audit_log_task(struct audit_buffer *ab)
audit_log_task_context(ab);
audit_log_format(ab, " pid=%d comm=", task_pid_nr(current));
audit_log_untrustedstring(ab, get_task_comm(comm, current));
- if (mm) {
- down_read(&mm->mmap_sem);
- if (mm->exe_file)
- audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
- up_read(&mm->mmap_sem);
- } else
- audit_log_format(ab, " exe=(null)");
+ audit_log_d_path_exe(ab, current->mm);
}
/**
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4139a0f8b558..54f0e7fcd0e2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -357,8 +357,8 @@ select_insn:
ALU64_MOD_X:
if (unlikely(SRC == 0))
return 0;
- tmp = DST;
- DST = do_div(tmp, SRC);
+ div64_u64_rem(DST, SRC, &tmp);
+ DST = tmp;
CONT;
ALU_MOD_X:
if (unlikely(SRC == 0))
@@ -367,8 +367,8 @@ select_insn:
DST = do_div(tmp, (u32) SRC);
CONT;
ALU64_MOD_K:
- tmp = DST;
- DST = do_div(tmp, IMM);
+ div64_u64_rem(DST, IMM, &tmp);
+ DST = tmp;
CONT;
ALU_MOD_K:
tmp = (u32) DST;
@@ -377,7 +377,7 @@ select_insn:
ALU64_DIV_X:
if (unlikely(SRC == 0))
return 0;
- do_div(DST, SRC);
+ DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
if (unlikely(SRC == 0))
@@ -387,7 +387,7 @@ select_insn:
DST = (u32) tmp;
CONT;
ALU64_DIV_K:
- do_div(DST, IMM);
+ DST = div64_u64(DST, IMM);
CONT;
ALU_DIV_K:
tmp = (u32) DST;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 81aa3a4ece9f..1a3bf48743ce 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -913,10 +913,30 @@ static void put_ctx(struct perf_event_context *ctx)
* Those places that change perf_event::ctx will hold both
* perf_event_ctx::mutex of the 'old' and 'new' ctx value.
*
- * Lock ordering is by mutex address. There is one other site where
- * perf_event_context::mutex nests and that is put_event(). But remember that
- * that is a parent<->child context relation, and migration does not affect
- * children, therefore these two orderings should not interact.
+ * Lock ordering is by mutex address. There are two other sites where
+ * perf_event_context::mutex nests and those are:
+ *
+ * - perf_event_exit_task_context() [ child , 0 ]
+ * __perf_event_exit_task()
+ * sync_child_event()
+ * put_event() [ parent, 1 ]
+ *
+ * - perf_event_init_context() [ parent, 0 ]
+ * inherit_task_group()
+ * inherit_group()
+ * inherit_event()
+ * perf_event_alloc()
+ * perf_init_event()
+ * perf_try_init_event() [ child , 1 ]
+ *
+ * While it appears there is an obvious deadlock here -- the parent and child
+ * nesting levels are inverted between the two. This is in fact safe because
+ * life-time rules separate them. That is an exiting task cannot fork, and a
+ * spawning task cannot (yet) exit.
+ *
+ * But remember that that these are parent<->child context relations, and
+ * migration does not affect children, therefore these two orderings should not
+ * interact.
*
* The change in perf_event::ctx does not affect children (as claimed above)
* because the sys_perf_event_open() case will install a new event and break
@@ -3657,9 +3677,6 @@ static void perf_remove_from_owner(struct perf_event *event)
}
}
-/*
- * Called when the last reference to the file is gone.
- */
static void put_event(struct perf_event *event)
{
struct perf_event_context *ctx;
@@ -3697,6 +3714,9 @@ int perf_event_release_kernel(struct perf_event *event)
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+/*
+ * Called when the last reference to the file is gone.
+ */
static int perf_release(struct inode *inode, struct file *file)
{
put_event(file->private_data);
@@ -7364,7 +7384,12 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
return -ENODEV;
if (event->group_leader != event) {
- ctx = perf_event_ctx_lock(event->group_leader);
+ /*
+ * This ctx->mutex can nest when we're called through
+ * inheritance. See the perf_event_ctx_lock_nested() comment.
+ */
+ ctx = perf_event_ctx_lock_nested(event->group_leader,
+ SINGLE_DEPTH_NESTING);
BUG_ON(!ctx);
}
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 988dc58e8847..2feb6feca0cc 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -57,5 +57,6 @@ struct irq_chip dummy_irq_chip = {
.irq_ack = noop,
.irq_mask = noop,
.irq_unmask = noop,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
};
EXPORT_SYMBOL_GPL(dummy_irq_chip);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 38c25b1f2fd5..7a36fdcca5bf 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -707,7 +707,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
do {
unsigned long pfn, epfn, addr, eaddr;
- pages = kimage_alloc_pages(GFP_KERNEL, order);
+ pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
if (!pages)
break;
pfn = page_to_pfn(pages);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index b73279367087..b025295f4966 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
}
/*
- * Called by sched_setscheduler() to check whether the priority change
- * is overruled by a possible priority boosting.
+ * Called by sched_setscheduler() to get the priority which will be
+ * effective after the change.
*/
-int rt_mutex_check_prio(struct task_struct *task, int newprio)
+int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
{
if (!task_has_pi_waiters(task))
- return 0;
+ return newprio;
- return task_top_pi_waiter(task)->task->prio <= newprio;
+ if (task_top_pi_waiter(task)->task->prio <= newprio)
+ return task_top_pi_waiter(task)->task->prio;
+ return newprio;
}
/*
diff --git a/kernel/module.c b/kernel/module.c
index 42a1d2afb217..cfc9e843a924 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3370,6 +3370,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
module_bug_cleanup(mod);
mutex_unlock(&module_mutex);
+ blocking_notifier_call_chain(&module_notify_list,
+ MODULE_STATE_GOING, mod);
+
/* we can't deallocate the module until we clear memory protection */
unset_module_init_ro_nx(mod);
unset_module_core_ro_nx(mod);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 233165da782f..8cf7304b2867 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -162,11 +162,14 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
module_param(kthread_prio, int, 0644);
-/* Delay in jiffies for grace-period initialization delays. */
-static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT)
- ? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
- : 0;
+/* Delay in jiffies for grace-period initialization delays, debug only. */
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
module_param(gp_init_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+static const int gp_init_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */
/*
* Track the rcutorture test sequence number and the update version
@@ -1843,9 +1846,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
- if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) &&
- gp_init_delay > 0 &&
- !(rsp->gpnum % (rcu_num_nodes * 10)))
+ if (gp_init_delay > 0 &&
+ !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
schedule_timeout_uninterruptible(gp_init_delay);
}
diff --git a/kernel/relay.c b/kernel/relay.c
index 5a56d3c8dc03..e9dbaeb8fd65 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -407,7 +407,7 @@ static inline void relay_set_buf_dentry(struct rchan_buf *buf,
struct dentry *dentry)
{
buf->dentry = dentry;
- buf->dentry->d_inode->i_size = buf->early_bytes;
+ d_inode(buf->dentry)->i_size = buf->early_bytes;
}
static struct dentry *relay_create_buf_file(struct rchan *chan,
@@ -733,7 +733,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
buf->padding[old_subbuf] = buf->prev_padding;
buf->subbufs_produced++;
if (buf->dentry)
- buf->dentry->d_inode->i_size +=
+ d_inode(buf->dentry)->i_size +=
buf->chan->subbuf_size -
buf->padding[old_subbuf];
else
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9123a82cbb6..123673291ffb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
rq_clock_skip_update(rq, true);
}
-static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
-
-void register_task_migration_notifier(struct notifier_block *n)
-{
- atomic_notifier_chain_register(&task_migration_notifier, n);
-}
-
#ifdef CONFIG_SMP
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
@@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
trace_sched_migrate_task(p, new_cpu);
if (task_cpu(p) != new_cpu) {
- struct task_migration_notifier tmn;
-
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
-
- tmn.task = p;
- tmn.from_cpu = task_cpu(p);
- tmn.to_cpu = new_cpu;
-
- atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
}
__set_task_cpu(p, new_cpu);
@@ -3315,15 +3300,18 @@ static void __setscheduler_params(struct task_struct *p,
/* Actually do priority change: must hold pi & rq lock. */
static void __setscheduler(struct rq *rq, struct task_struct *p,
- const struct sched_attr *attr)
+ const struct sched_attr *attr, bool keep_boost)
{
__setscheduler_params(p, attr);
/*
- * If we get here, there was no pi waiters boosting the
- * task. It is safe to use the normal prio.
+ * Keep a potential priority boosting if called from
+ * sched_setscheduler().
*/
- p->prio = normal_prio(p);
+ if (keep_boost)
+ p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+ else
+ p->prio = normal_prio(p);
if (dl_prio(p->prio))
p->sched_class = &dl_sched_class;
@@ -3423,7 +3411,7 @@ static int __sched_setscheduler(struct task_struct *p,
int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
MAX_RT_PRIO - 1 - attr->sched_priority;
int retval, oldprio, oldpolicy = -1, queued, running;
- int policy = attr->sched_policy;
+ int new_effective_prio, policy = attr->sched_policy;
unsigned long flags;
const struct sched_class *prev_class;
struct rq *rq;
@@ -3605,15 +3593,14 @@ change:
oldprio = p->prio;
/*
- * Special case for priority boosted tasks.
- *
- * If the new priority is lower or equal (user space view)
- * than the current (boosted) priority, we just store the new
+ * Take priority boosted tasks into account. If the new
+ * effective priority is unchanged, we just store the new
* normal parameters and do not touch the scheduler class and
* the runqueue. This will be done when the task deboost
* itself.
*/
- if (rt_mutex_check_prio(p, newprio)) {
+ new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+ if (new_effective_prio == oldprio) {
__setscheduler_params(p, attr);
task_rq_unlock(rq, p, &flags);
return 0;
@@ -3627,7 +3614,7 @@ change:
put_prev_task(rq, p);
prev_class = p->sched_class;
- __setscheduler(rq, p, attr);
+ __setscheduler(rq, p, attr, true);
if (running)
p->sched_class->set_curr_task(rq);
@@ -4402,10 +4389,7 @@ long __sched io_schedule_timeout(long timeout)
long ret;
current->in_iowait = 1;
- if (old_iowait)
- blk_schedule_flush_plug(current);
- else
- blk_flush_plug(current);
+ blk_schedule_flush_plug(current);
delayacct_blkio_start();
rq = raw_rq();
@@ -7012,27 +6996,23 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
unsigned long flags;
long cpu = (long)hcpu;
struct dl_bw *dl_b;
+ bool overflow;
+ int cpus;
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
case CPU_DOWN_PREPARE:
- /* explicitly allow suspend */
- if (!(action & CPU_TASKS_FROZEN)) {
- bool overflow;
- int cpus;
-
- rcu_read_lock_sched();
- dl_b = dl_bw_of(cpu);
+ rcu_read_lock_sched();
+ dl_b = dl_bw_of(cpu);
- raw_spin_lock_irqsave(&dl_b->lock, flags);
- cpus = dl_bw_cpus(cpu);
- overflow = __dl_overflow(dl_b, cpus, 0, 0);
- raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
- rcu_read_unlock_sched();
+ rcu_read_unlock_sched();
- if (overflow)
- return notifier_from_errno(-EBUSY);
- }
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
cpuset_update_active_cpus(false);
break;
case CPU_DOWN_PREPARE_FROZEN:
@@ -7361,7 +7341,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
queued = task_on_rq_queued(p);
if (queued)
dequeue_task(rq, p, 0);
- __setscheduler(rq, p, &attr);
+ __setscheduler(rq, p, &attr, false);
if (queued) {
enqueue_task(rq, p, 0);
resched_curr(rq);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index deef1caa94c6..fefcb1fa5160 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -81,7 +81,6 @@ static void cpuidle_idle_call(void)
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
- unsigned int broadcast;
bool reflect;
/*
@@ -150,17 +149,6 @@ static void cpuidle_idle_call(void)
goto exit_idle;
}
- broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP;
-
- /*
- * Tell the time framework to switch to a broadcast timer
- * because our local timer will be shutdown. If a local timer
- * is used from another cpu as a broadcast timer, this call may
- * fail if it is not available
- */
- if (broadcast && tick_broadcast_enter())
- goto use_default;
-
/* Take note of the planned idle state. */
idle_set_state(this_rq(), &drv->states[next_state]);
@@ -174,8 +162,8 @@ static void cpuidle_idle_call(void)
/* The cpu is no longer idle or about to enter idle. */
idle_set_state(this_rq(), NULL);
- if (broadcast)
- tick_broadcast_exit();
+ if (entered_state == -EBUSY)
+ goto use_default;
/*
* Give the governor an opportunity to reflect on the outcome
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 11dc22a6983b..637a09461c1d 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -117,11 +117,7 @@ static int __clockevents_set_state(struct clock_event_device *dev,
/* Transition with new state-specific callbacks */
switch (state) {
case CLOCK_EVT_STATE_DETACHED:
- /*
- * This is an internal state, which is guaranteed to go from
- * SHUTDOWN to DETACHED. No driver interaction required.
- */
- return 0;
+ /* The clockevent device is getting replaced. Shut it down. */
case CLOCK_EVT_STATE_SHUTDOWN:
return dev->set_state_shutdown(dev);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 76d4bd962b19..93ef7190bdea 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -266,21 +266,23 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
/*
* Divide a ktime value by a nanosecond value
*/
-u64 __ktime_divns(const ktime_t kt, s64 div)
+s64 __ktime_divns(const ktime_t kt, s64 div)
{
- u64 dclc;
int sft = 0;
+ s64 dclc;
+ u64 tmp;
dclc = ktime_to_ns(kt);
+ tmp = dclc < 0 ? -dclc : dclc;
+
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
div >>= 1;
}
- dclc >>= sft;
- do_div(dclc, (unsigned long) div);
-
- return dclc;
+ tmp >>= sft;
+ do_div(tmp, (unsigned long) div);
+ return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
#endif /* BITS_PER_LONG >= 64 */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 91eecaaa43e0..05330494a0df 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6079,7 +6079,7 @@ trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
struct dentry *ret = trace_create_file(name, mode, parent, data, fops);
if (ret) /* See tracing_get_cpu() */
- ret->d_inode->i_cdev = (void *)(cpu + 1);
+ d_inode(ret)->i_cdev = (void *)(cpu + 1);
return ret;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3ab69fb72b85..c4de47fc5cca 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -494,8 +494,8 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
if (dir) {
spin_lock(&dir->d_lock); /* probably unneeded */
list_for_each_entry(child, &dir->d_subdirs, d_child) {
- if (child->d_inode) /* probably unneeded */
- child->d_inode->i_private = NULL;
+ if (d_really_is_positive(child)) /* probably unneeded */
+ d_inode(child)->i_private = NULL;
}
spin_unlock(&dir->d_lock);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 692bf7184c8c..25a086bcb700 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -178,12 +178,13 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
EXPORT_SYMBOL(ftrace_print_hex_seq);
const char *
-ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len,
+ftrace_print_array_seq(struct trace_seq *p, const void *buf, int count,
size_t el_size)
{
const char *ret = trace_seq_buffer_ptr(p);
const char *prefix = "";
void *ptr = (void *)buf;
+ size_t buf_len = count * el_size;
trace_seq_putc(p, '{');
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d60fe62ec4fa..6dd022c7b5bc 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -443,7 +443,7 @@ static int create_trace_uprobe(int argc, char **argv)
if (ret)
goto fail_address_parse;
- inode = igrab(path.dentry->d_inode);
+ inode = igrab(d_inode(path.dentry));
path_put(&path);
if (!inode || !S_ISREG(inode->i_mode)) {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 2316f50b07a4..581a68a04c64 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -41,6 +41,8 @@
#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
+static DEFINE_MUTEX(watchdog_proc_mutex);
+
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
#else
@@ -608,26 +610,36 @@ void watchdog_nmi_enable_all(void)
{
int cpu;
- if (!watchdog_user_enabled)
- return;
+ mutex_lock(&watchdog_proc_mutex);
+
+ if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+ goto unlock;
get_online_cpus();
for_each_online_cpu(cpu)
watchdog_nmi_enable(cpu);
put_online_cpus();
+
+unlock:
+ mutex_unlock(&watchdog_proc_mutex);
}
void watchdog_nmi_disable_all(void)
{
int cpu;
+ mutex_lock(&watchdog_proc_mutex);
+
if (!watchdog_running)
- return;
+ goto unlock;
get_online_cpus();
for_each_online_cpu(cpu)
watchdog_nmi_disable(cpu);
put_online_cpus();
+
+unlock:
+ mutex_unlock(&watchdog_proc_mutex);
}
#else
static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
@@ -744,8 +756,6 @@ static int proc_watchdog_update(void)
}
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
/*
* common function for watchdog, nmi_watchdog and soft_watchdog parameter
*
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-05 22:06:40 +0100