xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'timers/urgent' into timers/core

Browse Source 
Pick up urgent fixes to apply dependent cleanup patch
This commit is contained in:
Thomas Gleixner
2018-05-02 16:11:12 +02:00
parent 1cfd904f16 7dba33c634
commit 604a98f1df
674 changed files with 8481 additions and 4801 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
kernel/bpf/core.c
View File

@@ -1572,13 +1572,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
return cnt;
}
static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
u32 *prog_ids,
u32 request_cnt)
{
int i = 0;
for (; *prog; prog++) {
if (*prog == &dummy_bpf_prog.prog)
continue;
prog_ids[i] = (*prog)->aux->id;
if (++i == request_cnt) {
prog++;
break;
}
}
return !!(*prog);
}
int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
__u32 __user *prog_ids, u32 cnt)
{
struct bpf_prog **prog;
unsigned long err = 0;
u32 i = 0, *ids;
bool nospc;
u32 *ids;
/* users of this function are doing:
* cnt = bpf_prog_array_length();
@@ -1595,16 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
return -ENOMEM;
rcu_read_lock();
prog = rcu_dereference(progs)->progs;
for (; *prog; prog++) {
if (*prog == &dummy_bpf_prog.prog)
continue;
ids[i] = (*prog)->aux->id;
if (++i == cnt) {
prog++;
break;
}
}
nospc = !!(*prog);
nospc = bpf_prog_array_copy_core(prog, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
@@ -1683,22 +1693,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
}
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
__u32 __user *prog_ids, u32 request_cnt,
__u32 __user *prog_cnt)
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
struct bpf_prog **prog;
u32 cnt = 0;
if (array)
cnt = bpf_prog_array_length(array);
if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
return -EFAULT;
*prog_cnt = cnt;
/* return early if user requested only program count or nothing to copy */
if (!request_cnt || !cnt)
return 0;
return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
prog = rcu_dereference_check(array, 1)->progs;
return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
: 0;
}
static void bpf_prog_free_deferred(struct work_struct *work)

3
kernel/bpf/sockmap.c
View File

@@ -1442,9 +1442,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
if (attr->value_size > KMALLOC_MAX_SIZE)
return ERR_PTR(-E2BIG);
err = bpf_tcp_ulp_register();
if (err && err != -EEXIST)
return ERR_PTR(err);

25
kernel/events/callchain.c
View File

@@ -119,23 +119,20 @@ int get_callchain_buffers(int event_max_stack)
goto exit;
}
if (count > 1) {
/* If the allocation failed, give up */
if (!callchain_cpus_entries)
err = -ENOMEM;
/*
* If requesting per event more than the global cap,
* return a different error to help userspace figure
* this out.
*
* And also do it here so that we have &callchain_mutex held.
*/
if (event_max_stack > sysctl_perf_event_max_stack)
err = -EOVERFLOW;
/*
* If requesting per event more than the global cap,
* return a different error to help userspace figure
* this out.
*
* And also do it here so that we have &callchain_mutex held.
*/
if (event_max_stack > sysctl_perf_event_max_stack) {
err = -EOVERFLOW;
goto exit;
}
err = alloc_callchain_buffers();
if (count == 1)
err = alloc_callchain_buffers();
exit:
if (err)
atomic_dec(&nr_callchain_events);

8
kernel/events/core.c
View File

@@ -7587,6 +7587,10 @@ static void perf_event_switch(struct task_struct *task,
},
};
if (!sched_in && task->state == TASK_RUNNING)
switch_event.event_id.header.misc |=
PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
perf_iterate_sb(perf_event_switch_output,
&switch_event,
NULL);
@@ -10205,9 +10209,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
* __u16 sample size limit.
*/
if (attr->sample_stack_user >= USHRT_MAX)
ret = -EINVAL;
return -EINVAL;
else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
ret = -EINVAL;
return -EINVAL;
}
if (!attr->sample_max_stack)

3
kernel/fork.c
View File

@@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
if (!s)
continue;
#ifdef CONFIG_DEBUG_KMEMLEAK
/* Clear stale pointers from reused stack. */
memset(s->addr, 0, THREAD_SIZE);
#endif
tsk->stack_vm_area = s;
return s->addr;
}

2
kernel/kprobes.c
View File

@@ -2428,7 +2428,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
struct kprobe_blacklist_entry *ent =
list_entry(v, struct kprobe_blacklist_entry, list);
seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr,
seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
(void *)ent->end_addr, (void *)ent->start_addr);
return 0;
}

108
kernel/livepatch/shadow.c
View File

@@ -113,8 +113,10 @@ void *klp_shadow_get(void *obj, unsigned long id)
}
EXPORT_SYMBOL_GPL(klp_shadow_get);
static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
size_t size, gfp_t gfp_flags, bool warn_on_exist)
static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id,
size_t size, gfp_t gfp_flags,
klp_shadow_ctor_t ctor, void *ctor_data,
bool warn_on_exist)
{
struct klp_shadow *new_shadow;
void *shadow_data;
@@ -125,18 +127,15 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
if (shadow_data)
goto exists;
/* Allocate a new shadow variable for use inside the lock below */
/*
* Allocate a new shadow variable. Fill it with zeroes by default.
* More complex setting can be done by @ctor function. But it is
* called only when the buffer is really used (under klp_shadow_lock).
*/
new_shadow = kzalloc(size + sizeof(*new_shadow), gfp_flags);
if (!new_shadow)
return NULL;
new_shadow->obj = obj;
new_shadow->id = id;
/* Initialize the shadow variable if data provided */
if (data)
memcpy(new_shadow->data, data, size);
/* Look for <obj, id> again under the lock */
spin_lock_irqsave(&klp_shadow_lock, flags);
shadow_data = klp_shadow_get(obj, id);
@@ -150,6 +149,22 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
goto exists;
}
new_shadow->obj = obj;
new_shadow->id = id;
if (ctor) {
int err;
err = ctor(obj, new_shadow->data, ctor_data);
if (err) {
spin_unlock_irqrestore(&klp_shadow_lock, flags);
kfree(new_shadow);
pr_err("Failed to construct shadow variable <%p, %lx> (%d)\n",
obj, id, err);
return NULL;
}
}
/* No <obj, id> found, so attach the newly allocated one */
hash_add_rcu(klp_shadow_hash, &new_shadow->node,
(unsigned long)new_shadow->obj);
@@ -170,26 +185,32 @@ exists:
* klp_shadow_alloc() - allocate and add a new shadow variable
* @obj: pointer to parent object
* @id: data identifier
* @data: pointer to data to attach to parent
* @size: size of attached data
* @gfp_flags: GFP mask for allocation
* @ctor: custom constructor to initialize the shadow data (optional)
* @ctor_data: pointer to any data needed by @ctor (optional)
*
* Allocates @size bytes for new shadow variable data using @gfp_flags
* and copies @size bytes from @data into the new shadow variable's own
* data space. If @data is NULL, @size bytes are still allocated, but
* no copy is performed. The new shadow variable is then added to the
* global hashtable.
* Allocates @size bytes for new shadow variable data using @gfp_flags.
* The data are zeroed by default. They are further initialized by @ctor
* function if it is not NULL. The new shadow variable is then added
* to the global hashtable.
*
* If an existing <obj, id> shadow variable can be found, this routine
* will issue a WARN, exit early and return NULL.
* If an existing <obj, id> shadow variable can be found, this routine will
* issue a WARN, exit early and return NULL.
*
* This function guarantees that the constructor function is called only when
* the variable did not exist before. The cost is that @ctor is called
* in atomic context under a spin lock.
*
* Return: the shadow variable data element, NULL on duplicate or
* failure.
*/
void *klp_shadow_alloc(void *obj, unsigned long id, void *data,
size_t size, gfp_t gfp_flags)
void *klp_shadow_alloc(void *obj, unsigned long id,
size_t size, gfp_t gfp_flags,
klp_shadow_ctor_t ctor, void *ctor_data)
{
return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, true);
return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
ctor, ctor_data, true);
}
EXPORT_SYMBOL_GPL(klp_shadow_alloc);
@@ -197,37 +218,51 @@ EXPORT_SYMBOL_GPL(klp_shadow_alloc);
* klp_shadow_get_or_alloc() - get existing or allocate a new shadow variable
* @obj: pointer to parent object
* @id: data identifier
* @data: pointer to data to attach to parent
* @size: size of attached data
* @gfp_flags: GFP mask for allocation
* @ctor: custom constructor to initialize the shadow data (optional)
* @ctor_data: pointer to any data needed by @ctor (optional)
*
* Returns a pointer to existing shadow data if an <obj, id> shadow
* variable is already present. Otherwise, it creates a new shadow
* variable like klp_shadow_alloc().
*
* This function guarantees that only one shadow variable exists with
* the given @id for the given @obj. It also guarantees that the shadow
* variable will be initialized by the given @data only when it did not
* exist before.
* This function guarantees that only one shadow variable exists with the given
* @id for the given @obj. It also guarantees that the constructor function
* will be called only when the variable did not exist before. The cost is
* that @ctor is called in atomic context under a spin lock.
*
* Return: the shadow variable data element, NULL on failure.
*/
void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
size_t size, gfp_t gfp_flags)
void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
size_t size, gfp_t gfp_flags,
klp_shadow_ctor_t ctor, void *ctor_data)
{
return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, false);
return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
ctor, ctor_data, false);
}
EXPORT_SYMBOL_GPL(klp_shadow_get_or_alloc);
static void klp_shadow_free_struct(struct klp_shadow *shadow,
klp_shadow_dtor_t dtor)
{
hash_del_rcu(&shadow->node);
if (dtor)
dtor(shadow->obj, shadow->data);
kfree_rcu(shadow, rcu_head);
}
/**
* klp_shadow_free() - detach and free a <obj, id> shadow variable
* @obj: pointer to parent object
* @id: data identifier
* @dtor: custom callback that can be used to unregister the variable
* and/or free data that the shadow variable points to (optional)
*
* This function releases the memory for this <obj, id> shadow variable
* instance, callers should stop referencing it accordingly.
*/
void klp_shadow_free(void *obj, unsigned long id)
void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor)
{
struct klp_shadow *shadow;
unsigned long flags;
@@ -239,8 +274,7 @@ void klp_shadow_free(void *obj, unsigned long id)
(unsigned long)obj) {
if (klp_shadow_match(shadow, obj, id)) {
hash_del_rcu(&shadow->node);
kfree_rcu(shadow, rcu_head);
klp_shadow_free_struct(shadow, dtor);
break;
}
}
@@ -252,11 +286,13 @@ EXPORT_SYMBOL_GPL(klp_shadow_free);
/**
* klp_shadow_free_all() - detach and free all <*, id> shadow variables
* @id: data identifier
* @dtor: custom callback that can be used to unregister the variable
* and/or free data that the shadow variable points to (optional)
*
* This function releases the memory for all <*, id> shadow variable
* instances, callers should stop referencing them accordingly.
*/
void klp_shadow_free_all(unsigned long id)
void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor)
{
struct klp_shadow *shadow;
unsigned long flags;
@@ -266,10 +302,8 @@ void klp_shadow_free_all(unsigned long id)
/* Delete all <*, id> from hash */
hash_for_each(klp_shadow_hash, i, shadow, node) {
if (klp_shadow_match(shadow, shadow->obj, id)) {
hash_del_rcu(&shadow->node);
kfree_rcu(shadow, rcu_head);
}
if (klp_shadow_match(shadow, shadow->obj, id))
klp_shadow_free_struct(shadow, dtor);
}
spin_unlock_irqrestore(&klp_shadow_lock, flags);

3
kernel/module.c
View File

@@ -1472,7 +1472,8 @@ static ssize_t module_sect_show(struct module_attribute *mattr,
{
struct module_sect_attr *sattr =
container_of(mattr, struct module_sect_attr, mattr);
return sprintf(buf, "0x%pK\n", (void *)sattr->address);
return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
(void *)sattr->address : NULL);
}
static void free_sect_attrs(struct module_sect_attrs *sect_attrs)

20
kernel/sysctl_binary.c
View File

@@ -704,24 +704,6 @@ static const struct bin_table bin_net_netfilter_table[] = {
{}
};
static const struct bin_table bin_net_irda_table[] = {
{ CTL_INT, NET_IRDA_DISCOVERY, "discovery" },
{ CTL_STR, NET_IRDA_DEVNAME, "devname" },
{ CTL_INT, NET_IRDA_DEBUG, "debug" },
{ CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" },
{ CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" },
{ CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" },
{ CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" },
{ CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" },
{ CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" },
{ CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" },
{ CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" },
{ CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" },
{ CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" },
{ CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" },
{}
};
static const struct bin_table bin_net_table[] = {
{ CTL_DIR, NET_CORE, "core", bin_net_core_table },
/* NET_ETHER not used */
@@ -743,7 +725,7 @@ static const struct bin_table bin_net_table[] = {
{ CTL_DIR, NET_LLC, "llc", bin_net_llc_table },
{ CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table },
/* NET_DCCP "dccp" no longer used */
{ CTL_DIR, NET_IRDA, "irda", bin_net_irda_table },
/* NET_IRDA "irda" no longer used */
{ CTL_INT, 2089, "nf_conntrack_max" },
{}
};

63
kernel/time/clocksource.c
View File

@@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock);
static int watchdog_running;
static atomic_t watchdog_reset_pending;
static void inline clocksource_watchdog_lock(unsigned long *flags)
{
spin_lock_irqsave(&watchdog_lock, *flags);
}
static void inline clocksource_watchdog_unlock(unsigned long *flags)
{
spin_unlock_irqrestore(&watchdog_lock, *flags);
}
static int clocksource_watchdog_kthread(void *data);
static void __clocksource_change_rating(struct clocksource *cs, int rating);
@@ -142,9 +152,19 @@ static void __clocksource_unstable(struct clocksource *cs)
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
/*
* If the clocksource is registered clocksource_watchdog_kthread() will
* re-rate and re-select.
*/
if (list_empty(&cs->list)) {
cs->rating = 0;
return;
}
if (cs->mark_unstable)
cs->mark_unstable(cs);
/* kick clocksource_watchdog_kthread() */
if (finished_booting)
schedule_work(&watchdog_work);
}
@@ -153,10 +173,8 @@ static void __clocksource_unstable(struct clocksource *cs)
* clocksource_mark_unstable - mark clocksource unstable via watchdog
* @cs: clocksource to be marked unstable
*
* This function is called instead of clocksource_change_rating from
* cpu hotplug code to avoid a deadlock between the clocksource mutex
* and the cpu hotplug mutex. It defers the update of the clocksource
* to the watchdog thread.
* This function is called by the x86 TSC code to mark clocksources as unstable;
* it defers demotion and re-selection to a kthread.
*/
void clocksource_mark_unstable(struct clocksource *cs)
{
@@ -164,7 +182,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
spin_lock_irqsave(&watchdog_lock, flags);
if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
if (list_empty(&cs->wd_list))
if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
list_add(&cs->wd_list, &watchdog_list);
__clocksource_unstable(cs);
}
@@ -319,9 +337,8 @@ static void clocksource_resume_watchdog(void)
static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
unsigned long flags;
INIT_LIST_HEAD(&cs->wd_list);
spin_lock_irqsave(&watchdog_lock, flags);
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a clocksource to be watched. */
list_add(&cs->wd_list, &watchdog_list);
@@ -331,7 +348,6 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
spin_unlock_irqrestore(&watchdog_lock, flags);
}
static void clocksource_select_watchdog(bool fallback)
@@ -373,9 +389,6 @@ static void clocksource_select_watchdog(bool fallback)
static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
unsigned long flags;
spin_lock_irqsave(&watchdog_lock, flags);
if (cs != watchdog) {
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a watched clocksource. */
@@ -384,21 +397,19 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs)
clocksource_stop_watchdog();
}
}
spin_unlock_irqrestore(&watchdog_lock, flags);
}
static int __clocksource_watchdog_kthread(void)
{
struct clocksource *cs, *tmp;
unsigned long flags;
LIST_HEAD(unstable);
int select = 0;
spin_lock_irqsave(&watchdog_lock, flags);
list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
list_del_init(&cs->wd_list);
list_add(&cs->wd_list, &unstable);
__clocksource_change_rating(cs, 0);
select = 1;
}
if (cs->flags & CLOCK_SOURCE_RESELECT) {
@@ -410,11 +421,6 @@ static int __clocksource_watchdog_kthread(void)
clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
/* Needs to be done outside of watchdog lock */
list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
list_del_init(&cs->wd_list);
__clocksource_change_rating(cs, 0);
}
return select;
}
@@ -447,6 +453,9 @@ static inline int __clocksource_watchdog_kthread(void) { return 0; }
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
void clocksource_mark_unstable(struct clocksource *cs) { }
static void inline clocksource_watchdog_lock(unsigned long *flags) { }
static void inline clocksource_watchdog_unlock(unsigned long *flags) { }
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
/**
@@ -779,14 +788,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
*/
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{
unsigned long flags;
/* Initialize mult/shift and max_idle_ns */
__clocksource_update_freq_scale(cs, scale, freq);
/* Add clocksource to the clocksource list */
mutex_lock(&clocksource_mutex);
clocksource_watchdog_lock(&flags);
clocksource_enqueue(cs);
clocksource_enqueue_watchdog(cs);
clocksource_watchdog_unlock(&flags);
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
@@ -808,8 +822,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
unsigned long flags;
mutex_lock(&clocksource_mutex);
clocksource_watchdog_lock(&flags);
__clocksource_change_rating(cs, rating);
clocksource_watchdog_unlock(&flags);
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
@@ -821,6 +840,8 @@ EXPORT_SYMBOL(clocksource_change_rating);
*/
static int clocksource_unbind(struct clocksource *cs)
{
unsigned long flags;
if (clocksource_is_watchdog(cs)) {
/* Select and try to install a replacement watchdog. */
clocksource_select_watchdog(true);
@@ -834,8 +855,12 @@ static int clocksource_unbind(struct clocksource *cs)
if (curr_clocksource == cs)
return -EBUSY;
}
clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
clocksource_watchdog_unlock(&flags);
return 0;
}

16
kernel/time/hrtimer.c
View File

@@ -90,6 +90,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
{
.index = HRTIMER_BASE_BOOTTIME,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
},
{
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
@@ -105,6 +110,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
{
.index = HRTIMER_BASE_BOOTTIME_SOFT,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
},
{
.index = HRTIMER_BASE_TAI_SOFT,
.clockid = CLOCK_TAI,
@@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
[CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC,
[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
@@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
offs_real, offs_tai);
offs_real, offs_boot, offs_tai);
base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
return now;

4
kernel/time/posix-cpu-timers.c
View File

@@ -1205,10 +1205,12 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
u64 *newval, u64 *oldval)
{
u64 now;
int ret;
WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
ret = cpu_timer_sample_group(clock_idx, tsk, &now);
if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) {
if (oldval && ret != -EINVAL) {
/*
* We are setting itimer. The *oldval is absolute and we update
* it to be relative, *newval argument is relative and we update

2
kernel/time/posix-stubs.c
View File

@@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
case CLOCK_BOOTTIME:
get_monotonic_boottime64(tp);
break;
case CLOCK_MONOTONIC_ACTIVE:
ktime_get_active_ts64(tp);
default:
return -EINVAL;
}

26
kernel/time/posix-timers.c
View File

@@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
return 0;
}
static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
timekeeping_clocktai64(tp);
get_monotonic_boottime64(tp);
return 0;
}
static int posix_get_monotonic_active(clockid_t which_clock,
struct timespec64 *tp)
static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
ktime_get_active_ts64(tp);
timekeeping_clocktai64(tp);
return 0;
}
@@ -1327,9 +1326,19 @@ static const struct k_clock clock_tai = {
.timer_arm = common_hrtimer_arm,
};
static const struct k_clock clock_monotonic_active = {
static const struct k_clock clock_boottime = {
.clock_getres = posix_get_hrtimer_res,
.clock_get = posix_get_monotonic_active,
.clock_get = posix_get_boottime,
.nsleep = common_nsleep,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
.timer_get = common_timer_get,
.timer_del = common_timer_del,
.timer_rearm = common_hrtimer_rearm,
.timer_forward = common_hrtimer_forward,
.timer_remaining = common_hrtimer_remaining,
.timer_try_to_cancel = common_hrtimer_try_to_cancel,
.timer_arm = common_hrtimer_arm,
};
static const struct k_clock * const posix_clocks[] = {
@@ -1340,11 +1349,10 @@ static const struct k_clock * const posix_clocks[] = {
[CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw,
[CLOCK_REALTIME_COARSE] = &clock_realtime_coarse,
[CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse,
[CLOCK_BOOTTIME] = &clock_monotonic,
[CLOCK_BOOTTIME] = &clock_boottime,
[CLOCK_REALTIME_ALARM] = &alarm_clock,
[CLOCK_BOOTTIME_ALARM] = &alarm_clock,
[CLOCK_TAI] = &clock_tai,
[CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active,
};
static const struct k_clock *clockid_to_kclock(const clockid_t id)

15
kernel/time/tick-common.c
View File

@@ -419,19 +419,6 @@ void tick_suspend_local(void)
clockevents_shutdown(td->evtdev);
}
static void tick_forward_next_period(void)
{
ktime_t delta, now = ktime_get();
u64 n;
delta = ktime_sub(now, tick_next_period);
n = ktime_divns(delta, tick_period);
tick_next_period += n * tick_period;
if (tick_next_period < now)
tick_next_period += tick_period;
tick_sched_forward_next_period();
}
/**
* tick_resume_local - Resume the local tick device
*
@@ -444,8 +431,6 @@ void tick_resume_local(void)
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
bool broadcast = tick_resume_check_broadcast();
tick_forward_next_period();
clockevents_tick_resume(td->evtdev);
if (!broadcast) {
if (td->mode == TICKDEV_MODE_PERIODIC)

6
kernel/time/tick-internal.h
View File

@@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
#endif /* !(BROADCAST && ONESHOT) */
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
extern void tick_sched_forward_next_period(void);
#else
static inline void tick_sched_forward_next_period(void) { }
#endif
/* NO_HZ_FULL internal */
#ifdef CONFIG_NO_HZ_FULL
extern void tick_nohz_init(void);

11
kernel/time/tick-oneshot.c
View File

@@ -82,16 +82,15 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
!tick_device_is_functional(dev)) {
printk(KERN_INFO "Clockevents: "
"could not switch to one-shot mode:");
pr_info("Clockevents: could not switch to one-shot mode:");
if (!dev) {
printk(" no tick device\n");
pr_cont(" no tick device\n");
} else {
if (!tick_device_is_functional(dev))
printk(" %s is not functional.\n", dev->name);
pr_cont(" %s is not functional.\n", dev->name);
else
printk(" %s does not support one-shot mode.\n",
dev->name);
pr_cont(" %s does not support one-shot mode.\n",
dev->name);
}
return -EINVAL;
}

19
kernel/time/tick-sched.c
View File

@@ -51,15 +51,6 @@ struct tick_sched *tick_get_tick_sched(int cpu)
*/
static ktime_t last_jiffies_update;
/*
* Called after resume. Make sure that jiffies are not fast forwarded due to
* clock monotonic being forwarded by the suspended time.
*/
void tick_sched_forward_next_period(void)
{
last_jiffies_update = tick_next_period;
}
/*
* Must be called with interrupts disabled !
*/
@@ -804,12 +795,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
return;
}
hrtimer_set_expires(&ts->sched_timer, tick);
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
else
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
} else {
hrtimer_set_expires(&ts->sched_timer, tick);
tick_program_event(tick, 1);
}
}
static void tick_nohz_retain_tick(struct tick_sched *ts)

85
kernel/time/timekeeping.c
View File

@@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
/* Update both bases so mono and raw stay coupled. */
tk->tkr_mono.base += delta;
tk->tkr_raw.base += delta;
/* Accumulate time spent in suspend */
tk->time_suspended += delta;
tk->offs_boot = ktime_add(tk->offs_boot, delta);
}
/*
@@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void)
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
/**
* ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
*
* To keep it NMI safe since we're accessing from tracing, we're not using a
* separate timekeeper with updates to monotonic clock and boot offset
* protected with seqlocks. This has the following minor side effects:
*
* (1) Its possible that a timestamp be taken after the boot offset is updated
* but before the timekeeper is updated. If this happens, the new boot offset
* is added to the old timekeeping making the clock appear to update slightly
* earlier:
* CPU 0 CPU 1
* timekeeping_inject_sleeptime64()
* __timekeeping_inject_sleeptime(tk, delta);
* timestamp();
* timekeeping_update(tk, TK_CLEAR_NTP...);
*
* (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
* partially updated. Since the tk->offs_boot update is a rare event, this
* should be a rare occurrence which postprocessing should be able to handle.
*/
u64 notrace ktime_get_boot_fast_ns(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
}
EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
/*
* See comment for __ktime_get_fast_ns() vs. timestamp ordering
*/
@@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
static ktime_t *offsets[TK_OFFS_MAX] = {
[TK_OFFS_REAL] = &tk_core.timekeeper.offs_real,
[TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot,
[TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai,
};
@@ -860,39 +886,6 @@ void ktime_get_ts64(struct timespec64 *ts)
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);
/**
* ktime_get_active_ts64 - Get the active non-suspended monotonic clock
* @ts: pointer to timespec variable
*
* The function calculates the monotonic clock from the realtime clock and
* the wall_to_monotonic offset, subtracts the accumulated suspend time and
* stores the result in normalized timespec64 format in the variable
* pointed to by @ts.
*/
void ktime_get_active_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
struct timespec64 tomono, tsusp;
u64 nsec, nssusp;
unsigned int seq;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
ts->tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(&tk->tkr_mono);
tomono = tk->wall_to_monotonic;
nssusp = tk->time_suspended;
} while (read_seqcount_retry(&tk_core.seq, seq));
ts->tv_sec += tomono.tv_sec;
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsec + tomono.tv_nsec);
tsusp = ns_to_timespec64(nssusp);
*ts = timespec64_sub(*ts, tsusp);
}
/**
* ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
*
@@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
return;
}
tk_xtime_add(tk, delta);
tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
tk_debug_account_sleep_time(delta);
}
@@ -2125,7 +2119,7 @@ out:
void getboottime64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended);
ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
*ts = ktime_to_timespec64(t);
}
@@ -2139,13 +2133,6 @@ unsigned long get_seconds(void)
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
return timespec64_to_timespec(tk_xtime(tk));
}
struct timespec64 current_kernel_time64(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
@@ -2195,6 +2182,7 @@ void do_timer(unsigned long ticks)
* ktime_get_update_offsets_now - hrtimer helper
* @cwsseq: pointer to check and store the clock was set sequence number
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets if the
@@ -2204,7 +2192,7 @@ void do_timer(unsigned long ticks)
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
ktime_t *offs_tai)
ktime_t *offs_boot, ktime_t *offs_tai)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
@@ -2221,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
if (*cwsseq != tk->clock_was_set_seq) {
*cwsseq = tk->clock_was_set_seq;
*offs_real = tk->offs_real;
*offs_boot = tk->offs_boot;
*offs_tai = tk->offs_tai;
}

1
kernel/time/timekeeping.h
View File

@@ -6,6 +6,7 @@
*/
extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
ktime_t *offs_real,
ktime_t *offs_boot,
ktime_t *offs_tai);
extern int timekeeping_valid_for_hres(void);

25
kernel/trace/bpf_trace.c
View File

@@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
struct perf_event_query_bpf __user *uquery = info;
struct perf_event_query_bpf query = {};
u32 *ids, prog_cnt, ids_len;
int ret;
if (!capable(CAP_SYS_ADMIN))
@@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
return -EINVAL;
if (copy_from_user(&query, uquery, sizeof(query)))
return -EFAULT;
if (query.ids_len > BPF_TRACE_MAX_PROGS)
ids_len = query.ids_len;
if (ids_len > BPF_TRACE_MAX_PROGS)
return -E2BIG;
ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
if (!ids)
return -ENOMEM;
/*
* The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
* is required when user only wants to check for uquery->prog_cnt.
* There is no need to check for it since the case is handled
* gracefully in bpf_prog_array_copy_info.
*/
mutex_lock(&bpf_event_mutex);
ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
uquery->ids,
query.ids_len,
&uquery->prog_cnt);
ids,
ids_len,
&prog_cnt);
mutex_unlock(&bpf_event_mutex);
if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
ret = -EFAULT;
kfree(ids);
return ret;
}

2
kernel/trace/trace.c
View File

@@ -1165,7 +1165,7 @@ static struct {
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
{ ktime_get_mono_fast_ns, "boot", 1 },
{ ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};

2
kernel/trace/trace_entries.h
View File

@@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
__field( unsigned int, seqnum )
),
F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
__entry->seqnum,
__entry->tv_sec,
__entry->tv_nsec,

14
kernel/trace/trace_events_filter.c
View File

@@ -1499,14 +1499,14 @@ static int process_preds(struct trace_event_call *call,
return ret;
}
if (!nr_preds) {
prog = NULL;
} else {
prog = predicate_parse(filter_string, nr_parens, nr_preds,
if (!nr_preds)
return -EINVAL;
prog = predicate_parse(filter_string, nr_parens, nr_preds,
parse_pred, call, pe);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
if (IS_ERR(prog))
return PTR_ERR(prog);
rcu_assign_pointer(filter->prog, prog);
return 0;
}

2
kernel/trace/trace_kprobe.c
View File

@@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
if (ret == 0)
tk->tp.flags |= TP_FLAG_REGISTERED;
else {
pr_warn("Could not insert probe at %s+%lu: %d\n",
trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;