summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/audit.c30
-rw-r--r--kernel/audit.h1
-rw-r--r--kernel/audit_tree.c6
-rw-r--r--kernel/audit_watch.c4
-rw-r--r--kernel/auditfilter.c56
-rw-r--r--kernel/auditsc.c28
-rw-r--r--kernel/bpf/Makefile6
-rw-r--r--kernel/bpf/core.c9
-rw-r--r--kernel/context_tracking.c40
-rw-r--r--kernel/cpu.c14
-rw-r--r--kernel/events/core.c15
-rw-r--r--kernel/events/hw_breakpoint.c7
-rw-r--r--kernel/freezer.c9
-rw-r--r--kernel/futex.c36
-rw-r--r--kernel/gcov/Kconfig2
-rw-r--r--kernel/kmod.c76
-rw-r--r--kernel/power/hibernate.c8
-rw-r--r--kernel/power/process.c57
-rw-r--r--kernel/power/qos.c27
-rw-r--r--kernel/rcu/tree.c15
-rw-r--r--kernel/rcu/tree.h1
-rw-r--r--kernel/rcu/tree_plugin.h33
-rw-r--r--kernel/sched/core.c47
-rw-r--r--kernel/sched/deadline.c41
-rw-r--r--kernel/sched/fair.c21
-rw-r--r--kernel/sysctl.c3
-rw-r--r--kernel/time/clockevents.c2
-rw-r--r--kernel/time/posix-timers.c1
-rw-r--r--kernel/trace/ftrace.c54
-rw-r--r--kernel/trace/trace_syscalls.c8
31 files changed, 410 insertions, 249 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index dc5c77544fd6..17ea6d4a9a24 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -86,7 +86,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_TRACEPOINTS) += trace/
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-$(CONFIG_CPU_PM) += cpu_pm.o
-obj-$(CONFIG_NET) += bpf/
+obj-$(CONFIG_BPF) += bpf/
obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/audit.c b/kernel/audit.c
index ba2ff5a5c600..80983df92cd4 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -126,7 +126,7 @@ static atomic_t audit_lost = ATOMIC_INIT(0);
/* The netlink socket. */
static struct sock *audit_sock;
-int audit_net_id;
+static int audit_net_id;
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -724,7 +724,7 @@ static int audit_get_feature(struct sk_buff *skb)
seq = nlmsg_hdr(skb)->nlmsg_seq;
- audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
+ audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af));
return 0;
}
@@ -750,7 +750,7 @@ 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]));
+ BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names));
uaf = nlmsg_data(nlmsg_hdr(skb));
/* if there is ever a version 2 we should handle that here */
@@ -1301,19 +1301,9 @@ err:
*/
unsigned int audit_serial(void)
{
- static DEFINE_SPINLOCK(serial_lock);
- static unsigned int serial = 0;
+ static atomic_t serial = ATOMIC_INIT(0);
- unsigned long flags;
- unsigned int ret;
-
- spin_lock_irqsave(&serial_lock, flags);
- do {
- ret = ++serial;
- } while (unlikely(!ret));
- spin_unlock_irqrestore(&serial_lock, flags);
-
- return ret;
+ return atomic_add_return(1, &serial);
}
static inline void audit_get_stamp(struct audit_context *ctx,
@@ -1681,7 +1671,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
}
}
-void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
+static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
{
kernel_cap_t *perm = &name->fcap.permitted;
kernel_cap_t *inh = &name->fcap.inheritable;
@@ -1860,7 +1850,7 @@ EXPORT_SYMBOL(audit_log_task_context);
void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
- char name[sizeof(tsk->comm)];
+ char comm[sizeof(tsk->comm)];
struct mm_struct *mm = tsk->mm;
char *tty;
@@ -1894,9 +1884,8 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
from_kgid(&init_user_ns, cred->fsgid),
tty, audit_get_sessionid(tsk));
- get_task_comm(name, tsk);
audit_log_format(ab, " comm=");
- audit_log_untrustedstring(ab, name);
+ audit_log_untrustedstring(ab, get_task_comm(comm, tsk));
if (mm) {
down_read(&mm->mmap_sem);
@@ -1959,6 +1948,7 @@ void audit_log_end(struct audit_buffer *ab)
} else {
struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
+ nlh->nlmsg_len = ab->skb->len;
kauditd_send_multicast_skb(ab->skb);
/*
@@ -1970,7 +1960,7 @@ void audit_log_end(struct audit_buffer *ab)
* protocol between the kaudit kernel subsystem and the auditd
* userspace code.
*/
- nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN;
+ nlh->nlmsg_len -= NLMSG_HDRLEN;
if (audit_pid) {
skb_queue_tail(&audit_skb_queue, ab->skb);
diff --git a/kernel/audit.h b/kernel/audit.h
index 7bb65730c890..3cdffad5a1d9 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -222,7 +222,6 @@ extern void audit_copy_inode(struct audit_names *name,
const struct inode *inode);
extern void audit_log_cap(struct audit_buffer *ab, char *prefix,
kernel_cap_t *cap);
-extern void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name);
extern void audit_log_name(struct audit_context *context,
struct audit_names *n, struct path *path,
int record_num, int *call_panic);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 135944a7b28a..e242e3a9864a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -449,7 +449,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
return 0;
}
-static void audit_log_remove_rule(struct audit_krule *rule)
+static void audit_tree_log_remove_rule(struct audit_krule *rule)
{
struct audit_buffer *ab;
@@ -457,7 +457,7 @@ static void audit_log_remove_rule(struct audit_krule *rule)
if (unlikely(!ab))
return;
audit_log_format(ab, "op=");
- audit_log_string(ab, "remove rule");
+ audit_log_string(ab, "remove_rule");
audit_log_format(ab, " dir=");
audit_log_untrustedstring(ab, rule->tree->pathname);
audit_log_key(ab, rule->filterkey);
@@ -476,7 +476,7 @@ static void kill_rules(struct audit_tree *tree)
list_del_init(&rule->rlist);
if (rule->tree) {
/* not a half-baked one */
- audit_log_remove_rule(rule);
+ audit_tree_log_remove_rule(rule);
rule->tree = NULL;
list_del_rcu(&entry->list);
list_del(&entry->rule.list);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 70b4554d2fbe..ad9c1682f616 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -314,7 +314,7 @@ static void audit_update_watch(struct audit_parent *parent,
&nentry->rule.list);
}
- audit_watch_log_rule_change(r, owatch, "updated rules");
+ audit_watch_log_rule_change(r, owatch, "updated_rules");
call_rcu(&oentry->rcu, audit_free_rule_rcu);
}
@@ -342,7 +342,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
e = container_of(r, struct audit_entry, rule);
- audit_watch_log_rule_change(r, w, "remove rule");
+ audit_watch_log_rule_change(r, w, "remove_rule");
list_del(&r->rlist);
list_del(&r->list);
list_del_rcu(&e->list);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index c447cd9848d1..3598e13f2a65 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -71,6 +71,24 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
DEFINE_MUTEX(audit_filter_mutex);
+static void audit_free_lsm_field(struct audit_field *f)
+{
+ switch (f->type) {
+ case AUDIT_SUBJ_USER:
+ case AUDIT_SUBJ_ROLE:
+ case AUDIT_SUBJ_TYPE:
+ case AUDIT_SUBJ_SEN:
+ case AUDIT_SUBJ_CLR:
+ case AUDIT_OBJ_USER:
+ case AUDIT_OBJ_ROLE:
+ case AUDIT_OBJ_TYPE:
+ case AUDIT_OBJ_LEV_LOW:
+ case AUDIT_OBJ_LEV_HIGH:
+ kfree(f->lsm_str);
+ security_audit_rule_free(f->lsm_rule);
+ }
+}
+
static inline void audit_free_rule(struct audit_entry *e)
{
int i;
@@ -80,11 +98,8 @@ static inline void audit_free_rule(struct audit_entry *e)
if (erule->watch)
audit_put_watch(erule->watch);
if (erule->fields)
- for (i = 0; i < erule->field_count; i++) {
- struct audit_field *f = &erule->fields[i];
- kfree(f->lsm_str);
- security_audit_rule_free(f->lsm_rule);
- }
+ for (i = 0; i < erule->field_count; i++)
+ audit_free_lsm_field(&erule->fields[i]);
kfree(erule->fields);
kfree(erule->filterkey);
kfree(e);
@@ -148,7 +163,7 @@ static inline int audit_to_inode(struct audit_krule *krule,
struct audit_field *f)
{
if (krule->listnr != AUDIT_FILTER_EXIT ||
- krule->watch || krule->inode_f || krule->tree ||
+ krule->inode_f || krule->watch || krule->tree ||
(f->op != Audit_equal && f->op != Audit_not_equal))
return -EINVAL;
@@ -422,10 +437,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
f->type = data->fields[i];
f->val = data->values[i];
- f->uid = INVALID_UID;
- f->gid = INVALID_GID;
- f->lsm_str = NULL;
- f->lsm_rule = NULL;
/* Support legacy tests for a valid loginuid */
if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
@@ -1053,30 +1064,27 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data,
int err = 0;
struct audit_entry *entry;
+ entry = audit_data_to_entry(data, datasz);
+ if (IS_ERR(entry))
+ return PTR_ERR(entry);
+
switch (type) {
case AUDIT_ADD_RULE:
- entry = audit_data_to_entry(data, datasz);
- if (IS_ERR(entry))
- return PTR_ERR(entry);
-
err = audit_add_rule(entry);
- audit_log_rule_change("add rule", &entry->rule, !err);
- if (err)
- audit_free_rule(entry);
+ audit_log_rule_change("add_rule", &entry->rule, !err);
break;
case AUDIT_DEL_RULE:
- entry = audit_data_to_entry(data, datasz);
- if (IS_ERR(entry))
- return PTR_ERR(entry);
-
err = audit_del_rule(entry);
- audit_log_rule_change("remove rule", &entry->rule, !err);
- audit_free_rule(entry);
+ audit_log_rule_change("remove_rule", &entry->rule, !err);
break;
default:
- return -EINVAL;
+ err = -EINVAL;
+ WARN_ON(1);
}
+ if (err || type == AUDIT_DEL_RULE)
+ audit_free_rule(entry);
+
return err;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 7208c1df248d..e420a0c41b5f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -67,6 +67,7 @@
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
+#include <asm/syscall.h>
#include <linux/capability.h>
#include <linux/fs_struct.h>
#include <linux/compat.h>
@@ -125,14 +126,6 @@ struct audit_tree_refs {
struct audit_chunk *c[31];
};
-static inline int open_arg(int flags, int mask)
-{
- int n = ACC_MODE(flags);
- if (flags & (O_TRUNC | O_CREAT))
- n |= AUDIT_PERM_WRITE;
- return n & mask;
-}
-
static int audit_match_perm(struct audit_context *ctx, int mask)
{
unsigned n;
@@ -1505,7 +1498,6 @@ void __audit_free(struct task_struct *tsk)
/**
* audit_syscall_entry - fill in an audit record at syscall entry
- * @arch: architecture type
* @major: major syscall type (function)
* @a1: additional syscall register 1
* @a2: additional syscall register 2
@@ -1520,9 +1512,8 @@ void __audit_free(struct task_struct *tsk)
* will only be written if another part of the kernel requests that it
* be written).
*/
-void __audit_syscall_entry(int arch, int major,
- unsigned long a1, unsigned long a2,
- unsigned long a3, unsigned long a4)
+void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
+ unsigned long a3, unsigned long a4)
{
struct task_struct *tsk = current;
struct audit_context *context = tsk->audit_context;
@@ -1536,7 +1527,7 @@ void __audit_syscall_entry(int arch, int major,
if (!audit_enabled)
return;
- context->arch = arch;
+ context->arch = syscall_get_arch();
context->major = major;
context->argv[0] = a1;
context->argv[1] = a2;
@@ -2433,6 +2424,7 @@ static void audit_log_task(struct audit_buffer *ab)
kgid_t gid;
unsigned int sessionid;
struct mm_struct *mm = current->mm;
+ char comm[sizeof(current->comm)];
auid = audit_get_loginuid(current);
sessionid = audit_get_sessionid(current);
@@ -2445,7 +2437,7 @@ static void audit_log_task(struct audit_buffer *ab)
sessionid);
audit_log_task_context(ab);
audit_log_format(ab, " pid=%d comm=", task_pid_nr(current));
- audit_log_untrustedstring(ab, current->comm);
+ audit_log_untrustedstring(ab, get_task_comm(comm, current));
if (mm) {
down_read(&mm->mmap_sem);
if (mm->exe_file)
@@ -2488,11 +2480,9 @@ void __audit_seccomp(unsigned long syscall, long signr, int code)
if (unlikely(!ab))
return;
audit_log_task(ab);
- audit_log_format(ab, " sig=%ld", signr);
- audit_log_format(ab, " syscall=%ld", syscall);
- audit_log_format(ab, " compat=%d", is_compat_task());
- audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));
- audit_log_format(ab, " code=0x%x", code);
+ audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x",
+ signr, syscall_get_arch(), syscall, is_compat_task(),
+ KSTK_EIP(current), code);
audit_log_end(ab);
}
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 45427239f375..0daf7f6ae7df 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
-obj-y := core.o syscall.o verifier.o
-
+obj-y := core.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o
ifdef CONFIG_TEST_BPF
-obj-y += test_stub.o
+obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f0c30c59b317..d6594e457a25 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -655,3 +655,12 @@ void bpf_prog_free(struct bpf_prog *fp)
schedule_work(&aux->work);
}
EXPORT_SYMBOL_GPL(bpf_prog_free);
+
+/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
+ * skb_copy_bits(), so provide a weak definition of it for NET-less config.
+ */
+int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
+ int len)
+{
+ return -EFAULT;
+}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 5664985c46a0..937ecdfdf258 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -107,46 +107,6 @@ void context_tracking_user_enter(void)
}
NOKPROBE_SYMBOL(context_tracking_user_enter);
-#ifdef CONFIG_PREEMPT
-/**
- * preempt_schedule_context - preempt_schedule called by tracing
- *
- * The tracing infrastructure uses preempt_enable_notrace to prevent
- * recursion and tracing preempt enabling caused by the tracing
- * infrastructure itself. But as tracing can happen in areas coming
- * from userspace or just about to enter userspace, a preempt enable
- * can occur before user_exit() is called. This will cause the scheduler
- * to be called when the system is still in usermode.
- *
- * To prevent this, the preempt_enable_notrace will use this function
- * instead of preempt_schedule() to exit user context if needed before
- * calling the scheduler.
- */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
-{
- enum ctx_state prev_ctx;
-
- if (likely(!preemptible()))
- return;
-
- /*
- * Need to disable preemption in case user_exit() is traced
- * and the tracer calls preempt_enable_notrace() causing
- * an infinite recursion.
- */
- preempt_disable_notrace();
- prev_ctx = exception_enter();
- preempt_enable_no_resched_notrace();
-
- preempt_schedule();
-
- preempt_disable_notrace();
- exception_exit(prev_ctx);
- preempt_enable_notrace();
-}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_PREEMPT */
-
/**
* context_tracking_user_exit - Inform the context tracking that the CPU is
* exiting userspace mode and entering the kernel.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 356450f09c1f..90a3d017b90c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -64,6 +64,8 @@ static struct {
* an ongoing cpu hotplug operation.
*/
int refcount;
+ /* And allows lockless put_online_cpus(). */
+ atomic_t puts_pending;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
@@ -113,7 +115,11 @@ void put_online_cpus(void)
{
if (cpu_hotplug.active_writer == current)
return;
- mutex_lock(&cpu_hotplug.lock);
+ if (!mutex_trylock(&cpu_hotplug.lock)) {
+ atomic_inc(&cpu_hotplug.puts_pending);
+ cpuhp_lock_release();
+ return;
+ }
if (WARN_ON(!cpu_hotplug.refcount))
cpu_hotplug.refcount++; /* try to fix things up */
@@ -155,6 +161,12 @@ void cpu_hotplug_begin(void)
cpuhp_lock_acquire();
for (;;) {
mutex_lock(&cpu_hotplug.lock);
+ if (atomic_read(&cpu_hotplug.puts_pending)) {
+ int delta;
+
+ delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
+ cpu_hotplug.refcount -= delta;
+ }
if (likely(!cpu_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1425d07018de..2b02c9fda790 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6071,11 +6071,6 @@ static int perf_swevent_init(struct perf_event *event)
return 0;
}
-static int perf_swevent_event_idx(struct perf_event *event)
-{
- return 0;
-}
-
static struct pmu perf_swevent = {
.task_ctx_nr = perf_sw_context,
@@ -6085,8 +6080,6 @@ static struct pmu perf_swevent = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
-
- .event_idx = perf_swevent_event_idx,
};
#ifdef CONFIG_EVENT_TRACING
@@ -6204,8 +6197,6 @@ static struct pmu perf_tracepoint = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
-
- .event_idx = perf_swevent_event_idx,
};
static inline void perf_tp_register(void)
@@ -6431,8 +6422,6 @@ static struct pmu perf_cpu_clock = {
.start = cpu_clock_event_start,
.stop = cpu_clock_event_stop,
.read = cpu_clock_event_read,
-
- .event_idx = perf_swevent_event_idx,
};
/*
@@ -6511,8 +6500,6 @@ static struct pmu perf_task_clock = {
.start = task_clock_event_start,
.stop = task_clock_event_stop,
.read = task_clock_event_read,
-
- .event_idx = perf_swevent_event_idx,
};
static void perf_pmu_nop_void(struct pmu *pmu)
@@ -6542,7 +6529,7 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
static int perf_event_idx_default(struct perf_event *event)
{
- return event->hw.idx + 1;
+ return 0;
}
/*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 1559fb0b9296..9803a6600d49 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -605,11 +605,6 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
bp->hw.state = PERF_HES_STOPPED;
}
-static int hw_breakpoint_event_idx(struct perf_event *bp)
-{
- return 0;
-}
-
static struct pmu perf_breakpoint = {
.task_ctx_nr = perf_sw_context, /* could eventually get its own */
@@ -619,8 +614,6 @@ static struct pmu perf_breakpoint = {
.start = hw_breakpoint_start,
.stop = hw_breakpoint_stop,
.read = hw_breakpoint_pmu_read,
-
- .event_idx = hw_breakpoint_event_idx,
};
int __init init_hw_breakpoint(void)
diff --git a/kernel/freezer.c b/kernel/freezer.c
index aa6a8aadb911..a8900a3bc27a 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p)
if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK))
return false;
+ if (test_thread_flag(TIF_MEMDIE))
+ return false;
+
if (pm_nosig_freezing || cgroup_freezing(p))
return true;
@@ -147,12 +150,6 @@ void __thaw_task(struct task_struct *p)
{
unsigned long flags;
- /*
- * Clear freezing and kick @p if FROZEN. Clearing is guaranteed to
- * be visible to @p as waking up implies wmb. Waking up inside
- * freezer_lock also prevents wakeups from leaking outside
- * refrigerator.
- */
spin_lock_irqsave(&freezer_lock, flags);
if (frozen(p))
wake_up_process(p);
diff --git a/kernel/futex.c b/kernel/futex.c
index f3a3a071283c..63678b573d61 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -143,9 +143,8 @@
*
* Where (A) orders the waiters increment and the futex value read through
* atomic operations (see hb_waiters_inc) and where (B) orders the write
- * to futex and the waiters read -- this is done by the barriers in
- * get_futex_key_refs(), through either ihold or atomic_inc, depending on the
- * futex type.
+ * to futex and the waiters read -- this is done by the barriers for both
+ * shared and private futexes in get_futex_key_refs().
*
* This yields the following case (where X:=waiters, Y:=futex):
*
@@ -344,13 +343,20 @@ static void get_futex_key_refs(union futex_key *key)
futex_get_mm(key); /* implies MB (B) */
break;
default:
+ /*
+ * Private futexes do not hold reference on an inode or
+ * mm, therefore the only purpose of calling get_futex_key_refs
+ * is because we need the barrier for the lockless waiter check.
+ */
smp_mb(); /* explicit MB (B) */
}
}
/*
* Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
+ * The hash bucket spinlock must not be held. This is
+ * a no-op for private futexes, see comment in the get
+ * counterpart.
*/
static void drop_futex_key_refs(union futex_key *key)
{
@@ -641,8 +647,14 @@ static struct futex_pi_state * alloc_pi_state(void)
return pi_state;
}
+/*
+ * Must be called with the hb lock held.
+ */
static void free_pi_state(struct futex_pi_state *pi_state)
{
+ if (!pi_state)
+ return;
+
if (!atomic_dec_and_test(&pi_state->refcount))
return;
@@ -1521,15 +1533,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
}
retry:
- if (pi_state != NULL) {
- /*
- * We will have to lookup the pi_state again, so free this one
- * to keep the accounting correct.
- */
- free_pi_state(pi_state);
- pi_state = NULL;
- }
-
ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
@@ -1619,6 +1622,8 @@ retry_private:
case 0:
break;
case -EFAULT:
+ free_pi_state(pi_state);
+ pi_state = NULL;
double_unlock_hb(hb1, hb2);
hb_waiters_dec(hb2);
put_futex_key(&key2);
@@ -1634,6 +1639,8 @@ retry_private:
* exit to complete.
* - The user space value changed.
*/
+ free_pi_state(pi_state);
+ pi_state = NULL;
double_unlock_hb(hb1, hb2);
hb_waiters_dec(hb2);
put_futex_key(&key2);
@@ -1710,6 +1717,7 @@ retry_private:
}
out_unlock:
+ free_pi_state(pi_state);
double_unlock_hb(hb1, hb2);
hb_waiters_dec(hb2);
@@ -1727,8 +1735,6 @@ out_put_keys:
out_put_key1:
put_futex_key(&key1);
out:
- if (pi_state != NULL)
- free_pi_state(pi_state);
return ret ? ret : task_count;
}
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index cf66c5c8458e..3b7408759bdf 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -35,7 +35,7 @@ config GCOV_KERNEL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
depends on GCOV_KERNEL
- depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM
+ depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM || ARM64
default n
---help---
This options activates profiling for the entire kernel.
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 8637e041a247..80f7a6d00519 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -196,12 +196,34 @@ int __request_module(bool wait, const char *fmt, ...)
EXPORT_SYMBOL(__request_module);
#endif /* CONFIG_MODULES */
+static void call_usermodehelper_freeinfo(struct subprocess_info *info)
+{
+ if (info->cleanup)
+ (*info->cleanup)(info);
+ kfree(info);
+}
+
+static void umh_complete(struct subprocess_info *sub_info)
+{
+ struct completion *comp = xchg(&sub_info->complete, NULL);
+ /*
+ * See call_usermodehelper_exec(). If xchg() returns NULL
+ * we own sub_info, the UMH_KILLABLE caller has gone away
+ * or the caller used UMH_NO_WAIT.
+ */
+ if (comp)
+ complete(comp);
+ else
+ call_usermodehelper_freeinfo(sub_info);
+}
+
/*
* This is the task which runs the usermode application
*/
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
+ int wait = sub_info->wait & ~UMH_KILLABLE;
struct cred *new;
int retval;
@@ -221,7 +243,7 @@ static int ____call_usermodehelper(void *data)
retval = -ENOMEM;
new = prepare_kernel_cred(current);
if (!new)
- goto fail;
+ goto out;
spin_lock(&umh_sysctl_lock);
new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
@@ -233,7 +255,7 @@ static int ____call_usermodehelper(void *data)
retval = sub_info->init(sub_info, new);
if (retval) {
abort_creds(new);
- goto fail;
+ goto out;
}
}
@@ -242,12 +264,13 @@ static int ____call_usermodehelper(void *data)
retval = do_execve(getname_kernel(sub_info->path),
(const char __user *const __user *)sub_info->argv,
(const char __user *const __user *)sub_info->envp);
+out:
+ sub_info->retval = retval;
+ /* wait_for_helper() will call umh_complete if UHM_WAIT_PROC. */
+ if (wait != UMH_WAIT_PROC)
+ umh_complete(sub_info);
if (!retval)
return 0;
-
- /* Exec failed? */
-fail:
- sub_info->retval = retval;
do_exit(0);
}
@@ -258,26 +281,6 @@ static int call_helper(void *data)
return ____call_usermodehelper(data);
}
-static void call_usermodehelper_freeinfo(struct subprocess_info *info)
-{
- if (info->cleanup)
- (*info->cleanup)(info);
- kfree(info);
-}
-
-static void umh_complete(struct subprocess_info *sub_info)
-{
- struct completion *comp = xchg(&sub_info->complete, NULL);
- /*
- * See call_usermodehelper_exec(). If xchg() returns NULL
- * we own sub_info, the UMH_KILLABLE caller has gone away.
- */
- if (comp)
- complete(comp);
- else
- call_usermodehelper_freeinfo(sub_info);
-}
-
/* Keventd can't block, but this (a child) can. */
static int wait_for_helper(void *data)
{
@@ -336,18 +339,8 @@ static void __call_usermodehelper(struct work_struct *work)
kmod_thread_locker = NULL;
}
- switch (wait) {
- case UMH_NO_WAIT:
- call_usermodehelper_freeinfo(sub_info);
- break;
-
- case UMH_WAIT_PROC:
- if (pid > 0)
- break;
- /* FALLTHROUGH */
- case UMH_WAIT_EXEC:
- if (pid < 0)
- sub_info->retval = pid;
+ if (pid < 0) {
+ sub_info->retval = pid;
umh_complete(sub_info);
}
}
@@ -588,7 +581,12 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
goto out;
}
- sub_info->complete = &done;
+ /*
+ * Set the completion pointer only if there is a waiter.
+ * This makes it possible to use umh_complete to free
+ * the data structure in case of UMH_NO_WAIT.
+ */
+ sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done;
sub_info->wait = wait;
queue_work(khelper_wq, &sub_info->work);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index a9dfa79b6bab..1f35a3478f3c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -502,8 +502,14 @@ int hibernation_restore(int platform_mode)
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
- dpm_resume_end(PMSG_RECOVER);
+ /*
+ * The above should either succeed and jump to the new kernel,
+ * or return with an error. Otherwise things are just
+ * undefined, so let's be paranoid.
+ */
+ BUG_ON(!error);
}
+ dpm_resume_end(PMSG_RECOVER);
pm_restore_gfp_mask();
resume_console();
pm_restore_console();
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7b323221b9ee..5a6ec8678b9a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -46,13 +46,13 @@ static int try_to_freeze_tasks(bool user_only)
while (true) {
todo = 0;
read_lock(&tasklist_lock);
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (p == current || !freeze_task(p))
continue;
if (!freezer_should_skip(p))
todo++;
- } while_each_thread(g, p);
+ }
read_unlock(&tasklist_lock);
if (!user_only) {
@@ -93,11 +93,11 @@ static int try_to_freeze_tasks(bool user_only)
if (!wakeup) {
read_lock(&tasklist_lock);
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (p != current && !freezer_should_skip(p)
&& freezing(p) && !frozen(p))
sched_show_task(p);
- } while_each_thread(g, p);
+ }
read_unlock(&tasklist_lock);
}
} else {
@@ -108,6 +108,30 @@ static int try_to_freeze_tasks(bool user_only)
return todo ? -EBUSY : 0;
}
+static bool __check_frozen_processes(void)
+{
+ struct task_struct *g, *p;
+
+ for_each_process_thread(g, p)
+ if (p != current && !freezer_should_skip(p) && !frozen(p))
+ return false;
+
+ return true;
+}
+
+/*
+ * Returns true if all freezable tasks (except for current) are frozen already
+ */
+static bool check_frozen_processes(void)
+{
+ bool ret;
+
+ read_lock(&tasklist_lock);
+ ret = __check_frozen_processes();
+ read_unlock(&tasklist_lock);
+ return ret;
+}
+
/**
* freeze_processes - Signal user space processes to enter the refrigerator.
* The current thread will not be frozen. The same process that calls
@@ -118,6 +142,7 @@ static int try_to_freeze_tasks(bool user_only)
int freeze_processes(void)
{
int error;
+ int oom_kills_saved;
error = __usermodehelper_disable(UMH_FREEZING);
if (error)
@@ -132,11 +157,25 @@ int freeze_processes(void)
pm_wakeup_clear();
printk("Freezing user space processes ... ");
pm_freezing = true;
+ oom_kills_saved = oom_kills_count();
error = try_to_freeze_tasks(true);
if (!error) {
- printk("done.");
__usermodehelper_set_disable_depth(UMH_DISABLED);
oom_killer_disable();
+
+ /*
+ * There might have been an OOM kill while we were
+ * freezing tasks and the killed task might be still
+ * on the way out so we have to double check for race.
+ */
+ if (oom_kills_count() != oom_kills_saved &&
+ !check_frozen_processes()) {
+ __usermodehelper_set_disable_depth(UMH_ENABLED);
+ printk("OOM in progress.");
+ error = -EBUSY;
+ } else {
+ printk("done.");
+ }
}
printk("\n");
BUG_ON(in_atomic());
@@ -191,11 +230,11 @@ void thaw_processes(void)
thaw_workqueues();
read_lock(&tasklist_lock);
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
/* No other threads should have PF_SUSPEND_TASK set */
WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK));
__thaw_task(p);
- } while_each_thread(g, p);
+ }
read_unlock(&tasklist_lock);
WARN_ON(!(curr->flags & PF_SUSPEND_TASK));
@@ -218,10 +257,10 @@ void thaw_kernel_threads(void)
thaw_workqueues();
read_lock(&tasklist_lock);
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (p->flags & (PF_KTHREAD | PF_WQ_WORKER))
__thaw_task(p);
- } while_each_thread(g, p);
+ }
read_unlock(&tasklist_lock);
schedule();
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 884b77058864..5f4c006c4b1e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -105,11 +105,27 @@ static struct pm_qos_object network_throughput_pm_qos = {
};
+static BLOCKING_NOTIFIER_HEAD(memory_bandwidth_notifier);
+static struct pm_qos_constraints memory_bw_constraints = {
+ .list = PLIST_HEAD_INIT(memory_bw_constraints.list),
+ .target_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE,
+ .default_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE,
+ .type = PM_QOS_SUM,
+ .notifiers = &memory_bandwidth_notifier,
+};
+static struct pm_qos_object memory_bandwidth_pm_qos = {
+ .constraints = &memory_bw_constraints,
+ .name = "memory_bandwidth",
+};
+
+
static struct pm_qos_object *pm_qos_array[] = {
&null_pm_qos,
&cpu_dma_pm_qos,
&network_lat_pm_qos,
- &network_throughput_pm_qos
+ &network_throughput_pm_qos,
+ &memory_bandwidth_pm_qos,
};
static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
@@ -130,6 +146,9 @@ static const struct file_operations pm_qos_power_fops = {
/* unlocked internal variant */
static inline int pm_qos_get_value(struct pm_qos_constraints *c)
{
+ struct plist_node *node;
+ int total_value = 0;
+
if (plist_head_empty(&c->list))
return c->no_constraint_value;
@@ -140,6 +159,12 @@ static inline int pm_qos_get_value(struct pm_qos_constraints *c)
case PM_QOS_MAX:
return plist_last(&c->list)->prio;
+ case PM_QOS_SUM:
+ plist_for_each(node, &c->list)
+ total_value += node->prio;
+
+ return total_value;
+
default:
/* runtime check for not using enum */
BUG();
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 133e47223095..9815447d22e0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3299,11 +3299,16 @@ static void _rcu_barrier(struct rcu_state *rsp)
continue;
rdp = per_cpu_ptr(rsp->rda, cpu);
if (rcu_is_nocb_cpu(cpu)) {
- _rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
- rsp->n_barrier_done);
- atomic_inc(&rsp->barrier_cpu_count);
- __call_rcu(&rdp->barrier_head, rcu_barrier_callback,
- rsp, cpu, 0);
+ if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
+ _rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
+ rsp->n_barrier_done);
+ } else {
+ _rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+ rsp->n_barrier_done);
+ atomic_inc(&rsp->barrier_cpu_count);
+ __call_rcu(&rdp->barrier_head,
+ rcu_barrier_callback, rsp, cpu, 0);
+ }
} else if (ACCESS_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d03764652d91..bbdc45d8d74f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -587,6 +587,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void);
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 387dd4599344..c1d7f27bd38f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2050,6 +2050,33 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
}
/*
+ * Does the specified CPU need an RCU callback for the specified flavor
+ * of rcu_barrier()?
+ */
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_head *rhp;
+
+ /* No-CBs CPUs might have callbacks on any of three lists. */
+ rhp = ACCESS_ONCE(rdp->nocb_head);
+ if (!rhp)
+ rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+ if (!rhp)
+ rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+
+ /* Having no rcuo kthread but CBs after scheduler starts is bad! */
+ if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+ /* RCU callback enqueued before CPU first came online??? */
+ pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
+ cpu, rhp->func);
+ WARN_ON_ONCE(1);
+ }
+
+ return !!rhp;
+}
+
+/*
* Enqueue the specified string of rcu_head structures onto the specified
* CPU's no-CBs lists. The CPU is specified by rdp, the head of the
* string by rhp, and the tail of the string by rhtp. The non-lazy/lazy
@@ -2642,6 +2669,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+ WARN_ON_ONCE(1); /* Should be dead code. */
+ return false;
+}
+
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44999505e1bf..240157c13ddc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2951,6 +2951,47 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+{
+ enum ctx_state prev_ctx;
+
+ if (likely(!preemptible()))
+ return;
+
+ do {
+ __preempt_count_add(PREEMPT_ACTIVE);
+ /*
+ * Needs preempt disabled in case user_exit() is traced
+ * and the tracer calls preempt_enable_notrace() causing
+ * an infinite recursion.
+ */
+ prev_ctx = exception_enter();
+ __schedule();
+ exception_exit(prev_ctx);
+
+ __preempt_count_sub(PREEMPT_ACTIVE);
+ barrier();
+ } while (need_resched());
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_CONTEXT_TRACKING */
+
#endif /* CONFIG_PREEMPT */
/*
@@ -7833,6 +7874,11 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
sched_offline_group(tg);
}
+static void cpu_cgroup_fork(struct task_struct *task)
+{
+ sched_move_task(task);
+}
+
static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
@@ -8205,6 +8251,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
.css_free = cpu_cgroup_css_free,
.css_online = cpu_cgroup_css_online,
.css_offline = cpu_cgroup_css_offline,
+ .fork = cpu_cgroup_fork,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 256e577faf1b..5285332392d5 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -518,12 +518,20 @@ again:
}
/*
- * We need to take care of a possible races here. In fact, the
- * task might have changed its scheduling policy to something
- * different from SCHED_DEADLINE or changed its reservation
- * parameters (through sched_setattr()).
+ * We need to take care of several possible races here:
+ *
+ * - the task might have changed its scheduling policy
+ * to something different than SCHED_DEADLINE
+ * - the task might have changed its reservation parameters
+ * (through sched_setattr())
+ * - the task might have been boosted by someone else and
+ * might be in the boosting/deboosting path
+ *
+ * In all this cases we bail out, as the task is already
+ * in the runqueue or is going to be enqueued back anyway.
*/
- if (!dl_task(p) || dl_se->dl_new)
+ if (!dl_task(p) || dl_se->dl_new ||
+ dl_se->dl_boosted || !dl_se->dl_throttled)
goto unlock;
sched_clock_tick();
@@ -532,7 +540,7 @@ again:
dl_se->dl_yielded = 0;
if (task_on_rq_queued(p)) {
enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
- if (task_has_dl_policy(rq->curr))
+ if (dl_task(rq->curr))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
@@ -847,8 +855,19 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
* smaller than our one... OTW we keep our runtime and
* deadline.
*/
- if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+ if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) {
pi_se = &pi_task->dl;
+ } else if (!dl_prio(p->normal_prio)) {
+ /*
+ * Special case in which we have a !SCHED_DEADLINE task
+ * that is going to be deboosted, but exceedes its
+ * runtime while doing so. No point in replenishing
+ * it, as it's going to return back to its original
+ * scheduling class after this.
+ */
+ BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+ return;
+ }
/*
* If p is throttled, we do nothing. In fact, if it exhausted
@@ -1607,8 +1626,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
/* Only reschedule if pushing failed */
check_resched = 0;
#endif /* CONFIG_SMP */
- if (check_resched && task_has_dl_policy(rq->curr))
- check_preempt_curr_dl(rq, p, 0);
+ if (check_resched) {
+ if (dl_task(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ else
+ resched_curr(rq);
+ }
}
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf3e708..34baa60f8a7b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -828,11 +828,12 @@ static unsigned int task_nr_scan_windows(struct task_struct *p)
static unsigned int task_scan_min(struct task_struct *p)
{
+ unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
unsigned int scan, floor;
unsigned int windows = 1;
- if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
- windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+ if (scan_size < MAX_SCAN_WINDOW)
+ windows = MAX_SCAN_WINDOW / scan_size;
floor = 1000 / windows;
scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
@@ -1164,9 +1165,19 @@ static void task_numa_compare(struct task_numa_env *env,
long moveimp = imp;
rcu_read_lock();
- cur = ACCESS_ONCE(dst_rq->curr);
- if (cur->pid == 0) /* idle */
+
+ raw_spin_lock_irq(&dst_rq->lock);
+ cur = dst_rq->curr;
+ /*
+ * No need to move the exiting task, and this ensures that ->curr
+ * wasn't reaped and thus get_task_struct() in task_numa_assign()
+ * is safe under RCU read lock.
+ * Note that rcu_read_lock() itself can't protect from the final
+ * put_task_struct() after the last schedule().
+ */
+ if ((cur->flags & PF_EXITING) || is_idle_task(cur))
cur = NULL;
+ raw_spin_unlock_irq(&dst_rq->lock);
/*
* "imp" is the fault differential for the source task between the
@@ -1520,7 +1531,7 @@ static void update_task_scan_period(struct task_struct *p,
* scanning faster if shared accesses dominate as it may
* simply bounce migrations uselessly
*/
- ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+ ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aada6d9fe74..15f2511a1b7c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -387,7 +387,8 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_numa_balancing_scan_size,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "numa_balancing",
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 9c94c19f1305..55449909f114 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -72,7 +72,7 @@ static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
* Also omit the add if it would overflow the u64 boundary.
*/
if ((~0ULL - clc > rnd) &&
- (!ismax || evt->mult <= (1U << evt->shift)))
+ (!ismax || evt->mult <= (1ULL << evt->shift)))
clc += rnd;
do_div(clc, evt->mult);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 42b463ad90f2..31ea01f42e1f 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -636,6 +636,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
goto out;
}
} else {
+ memset(&event.sigev_value, 0, sizeof(event.sigev_value));
event.sigev_notify = SIGEV_SIGNAL;
event.sigev_signo = SIGALRM;
event.sigev_value.sival_int = new_timer->it_id;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fb186b9ddf51..31c90fec4158 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1925,8 +1925,16 @@ ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
* when we are adding another op to the rec or removing the
* current one. Thus, if the op is being added, we can
* ignore it because it hasn't attached itself to the rec
- * yet. That means we just need to find the op that has a
- * trampoline and is not beeing added.
+ * yet.
+ *
+ * If an ops is being modified (hooking to different functions)
+ * then we don't care about the new functions that are being
+ * added, just the old ones (that are probably being removed).
+ *
+ * If we are adding an ops to a function that already is using
+ * a trampoline, it needs to be removed (trampolines are only
+ * for single ops connected), then an ops that is not being
+ * modified also needs to be checked.
*/
do_for_each_ftrace_op(op, ftrace_ops_list) {
@@ -1940,17 +1948,23 @@ ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
if (op->flags & FTRACE_OPS_FL_ADDING)
continue;
+
/*
- * If the ops is not being added and has a trampoline,
- * then it must be the one that we want!
+ * If the ops is being modified and is in the old
+ * hash, then it is probably being removed from this
+ * function.
*/
- if (hash_contains_ip(ip, op->func_hash))
- return op;
-
- /* If the ops is being modified, it may be in the old hash. */
if ((op->flags & FTRACE_OPS_FL_MODIFYING) &&
hash_contains_ip(ip, &op->old_hash))
return op;
+ /*
+ * If the ops is not being added or modified, and it's
+ * in its normal filter hash, then this must be the one
+ * we want!
+ */
+ if (!(op->flags & FTRACE_OPS_FL_MODIFYING) &&
+ hash_contains_ip(ip, op->func_hash))
+ return op;
} while_for_each_ftrace_op(op);
@@ -2293,10 +2307,13 @@ static void ftrace_run_update_code(int command)
FTRACE_WARN_ON(ret);
}
-static void ftrace_run_modify_code(struct ftrace_ops *ops, int command)
+static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
+ struct ftrace_hash *old_hash)
{
ops->flags |= FTRACE_OPS_FL_MODIFYING;
+ ops->old_hash.filter_hash = old_hash;
ftrace_run_update_code(command);
+ ops->old_hash.filter_hash = NULL;
ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
}
@@ -3340,7 +3357,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
static int ftrace_probe_registered;
-static void __enable_ftrace_function_probe(void)
+static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash)
{
int ret;
int i;
@@ -3348,7 +3365,8 @@ static void __enable_ftrace_function_probe(void)
if (ftrace_probe_registered) {
/* still need to update the function call sites */
if (ftrace_enabled)
- ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS);
+ ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+ old_hash);
return;
}
@@ -3477,13 +3495,14 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
} while_for_each_ftrace_rec();
ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+ __enable_ftrace_function_probe(old_hash);
+
if (!ret)
free_ftrace_hash_rcu(old_hash);
else
count = ret;
- __enable_ftrace_function_probe();
-
out_unlock:
mutex_unlock(&ftrace_lock);
out:
@@ -3764,10 +3783,11 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
return add_hash_entry(hash, ip);
}
-static void ftrace_ops_update_code(struct ftrace_ops *ops)
+static void ftrace_ops_update_code(struct ftrace_ops *ops,
+ struct ftrace_hash *old_hash)
{
if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
- ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS);
+ ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
}
static int
@@ -3813,7 +3833,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
old_hash = *orig_hash;
ret = ftrace_hash_move(ops, enable, orig_hash, hash);
if (!ret) {
- ftrace_ops_update_code(ops);
+ ftrace_ops_update_code(ops, old_hash);
free_ftrace_hash_rcu(old_hash);
}
mutex_unlock(&ftrace_lock);
@@ -4058,7 +4078,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
ret = ftrace_hash_move(iter->ops, filter_hash,
orig_hash, iter->hash);
if (!ret) {
- ftrace_ops_update_code(iter->ops);
+ ftrace_ops_update_code(iter->ops, old_hash);
free_ftrace_hash_rcu(old_hash);
}
mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4dc8b79c5f75..29228c4d5696 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
@@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
int syscall_nr;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
@@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
@@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-05 05:48:57 +0000