summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/irq/migration.c26
-rw-r--r--kernel/padata.c88
-rw-r--r--kernel/time/posix-clock.c31
-rw-r--r--kernel/trace/blktrace.c191
-rw-r--r--kernel/trace/bpf_trace.c4
6 files changed, 217 insertions, 127 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fd3fd8d17ef5..01431ef8cf07 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -152,7 +152,7 @@ static int map_create(union bpf_attr *attr)
err = bpf_map_charge_memlock(map);
if (err)
- goto free_map;
+ goto free_map_nouncharge;
err = bpf_map_new_fd(map);
if (err < 0)
@@ -162,6 +162,8 @@ static int map_create(union bpf_attr *attr)
return err;
free_map:
+ bpf_map_uncharge_memlock(map);
+free_map_nouncharge:
map->ops->map_free(map);
return err;
}
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 37ddb7bda651..ec7c7eda0774 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,17 +7,18 @@
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
- struct irq_chip *chip = desc->irq_data.chip;
+ struct irq_data *data = &desc->irq_data;
+ struct irq_chip *chip = data->chip;
- if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+ if (likely(!irqd_is_setaffinity_pending(data)))
return;
- irqd_clr_move_pending(&desc->irq_data);
+ irqd_clr_move_pending(data);
/*
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
*/
- if (irqd_is_per_cpu(&desc->irq_data)) {
+ if (irqd_is_per_cpu(data)) {
WARN_ON(1);
return;
}
@@ -42,9 +43,20 @@ void irq_move_masked_irq(struct irq_data *idata)
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
- irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
-
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+ int ret;
+
+ ret = irq_do_set_affinity(data, desc->pending_mask, false);
+ /*
+ * If the there is a cleanup pending in the underlying
+ * vector management, reschedule the move for the next
+ * interrupt. Leave desc->pending_mask intact.
+ */
+ if (ret == -EBUSY) {
+ irqd_set_move_pending(data);
+ return;
+ }
+ }
cpumask_clear(desc->pending_mask);
}
diff --git a/kernel/padata.c b/kernel/padata.c
index ae036af3f012..c50975f43b34 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -65,15 +65,11 @@ static int padata_cpu_hash(struct parallel_data *pd)
static void padata_parallel_worker(struct work_struct *parallel_work)
{
struct padata_parallel_queue *pqueue;
- struct parallel_data *pd;
- struct padata_instance *pinst;
LIST_HEAD(local_list);
local_bh_disable();
pqueue = container_of(parallel_work,
struct padata_parallel_queue, work);
- pd = pqueue->pd;
- pinst = pd->pinst;
spin_lock(&pqueue->parallel.lock);
list_replace_init(&pqueue->parallel.list, &local_list);
@@ -136,6 +132,7 @@ int padata_do_parallel(struct padata_instance *pinst,
padata->cb_cpu = cb_cpu;
target_cpu = padata_cpu_hash(pd);
+ padata->cpu = target_cpu;
queue = per_cpu_ptr(pd->pqueue, target_cpu);
spin_lock(&queue->parallel.lock);
@@ -159,8 +156,6 @@ EXPORT_SYMBOL(padata_do_parallel);
* A pointer to the control struct of the next object that needs
* serialization, if present in one of the percpu reorder queues.
*
- * NULL, if all percpu reorder queues are empty.
- *
* -EINPROGRESS, if the next object that needs serialization will
* be parallel processed by another cpu and is not yet present in
* the cpu's reorder queue.
@@ -170,25 +165,12 @@ EXPORT_SYMBOL(padata_do_parallel);
*/
static struct padata_priv *padata_get_next(struct parallel_data *pd)
{
- int cpu, num_cpus;
- unsigned int next_nr, next_index;
struct padata_parallel_queue *next_queue;
struct padata_priv *padata;
struct padata_list *reorder;
+ int cpu = pd->cpu;
- num_cpus = cpumask_weight(pd->cpumask.pcpu);
-
- /*
- * Calculate the percpu reorder queue and the sequence
- * number of the next object.
- */
- next_nr = pd->processed;
- next_index = next_nr % num_cpus;
- cpu = padata_index_to_cpu(pd, next_index);
next_queue = per_cpu_ptr(pd->pqueue, cpu);
-
- padata = NULL;
-
reorder = &next_queue->reorder;
spin_lock(&reorder->lock);
@@ -199,7 +181,8 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
list_del_init(&padata->list);
atomic_dec(&pd->reorder_objects);
- pd->processed++;
+ pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1,
+ false);
spin_unlock(&reorder->lock);
goto out;
@@ -222,6 +205,7 @@ static void padata_reorder(struct parallel_data *pd)
struct padata_priv *padata;
struct padata_serial_queue *squeue;
struct padata_instance *pinst = pd->pinst;
+ struct padata_parallel_queue *next_queue;
/*
* We need to ensure that only one cpu can work on dequeueing of
@@ -240,12 +224,11 @@ static void padata_reorder(struct parallel_data *pd)
padata = padata_get_next(pd);
/*
- * All reorder queues are empty, or the next object that needs
- * serialization is parallel processed by another cpu and is
- * still on it's way to the cpu's reorder queue, nothing to
- * do for now.
+ * If the next object that needs serialization is parallel
+ * processed by another cpu and is still on it's way to the
+ * cpu's reorder queue, nothing to do for now.
*/
- if (!padata || PTR_ERR(padata) == -EINPROGRESS)
+ if (PTR_ERR(padata) == -EINPROGRESS)
break;
/*
@@ -254,7 +237,6 @@ static void padata_reorder(struct parallel_data *pd)
* so exit immediately.
*/
if (PTR_ERR(padata) == -ENODATA) {
- del_timer(&pd->timer);
spin_unlock_bh(&pd->lock);
return;
}
@@ -273,28 +255,27 @@ static void padata_reorder(struct parallel_data *pd)
/*
* The next object that needs serialization might have arrived to
- * the reorder queues in the meantime, we will be called again
- * from the timer function if no one else cares for it.
+ * the reorder queues in the meantime.
*
- * Ensure reorder_objects is read after pd->lock is dropped so we see
- * an increment from another task in padata_do_serial. Pairs with
+ * Ensure reorder queue is read after pd->lock is dropped so we see
+ * new objects from another task in padata_do_serial. Pairs with
* smp_mb__after_atomic in padata_do_serial.
*/
smp_mb();
- if (atomic_read(&pd->reorder_objects)
- && !(pinst->flags & PADATA_RESET))
- mod_timer(&pd->timer, jiffies + HZ);
- else
- del_timer(&pd->timer);
- return;
+ next_queue = per_cpu_ptr(pd->pqueue, pd->cpu);
+ if (!list_empty(&next_queue->reorder.list))
+ queue_work(pinst->wq, &pd->reorder_work);
}
-static void padata_reorder_timer(unsigned long arg)
+static void invoke_padata_reorder(struct work_struct *work)
{
- struct parallel_data *pd = (struct parallel_data *)arg;
+ struct parallel_data *pd;
+ local_bh_disable();
+ pd = container_of(work, struct parallel_data, reorder_work);
padata_reorder(pd);
+ local_bh_enable();
}
static void padata_serial_worker(struct work_struct *serial_work)
@@ -341,29 +322,22 @@ static void padata_serial_worker(struct work_struct *serial_work)
*/
void padata_do_serial(struct padata_priv *padata)
{
- int cpu;
- struct padata_parallel_queue *pqueue;
- struct parallel_data *pd;
-
- pd = padata->pd;
-
- cpu = get_cpu();
- pqueue = per_cpu_ptr(pd->pqueue, cpu);
+ struct parallel_data *pd = padata->pd;
+ struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue,
+ padata->cpu);
spin_lock(&pqueue->reorder.lock);
- atomic_inc(&pd->reorder_objects);
list_add_tail(&padata->list, &pqueue->reorder.list);
+ atomic_inc(&pd->reorder_objects);
spin_unlock(&pqueue->reorder.lock);
/*
- * Ensure the atomic_inc of reorder_objects above is ordered correctly
+ * Ensure the addition to the reorder list is ordered correctly
* with the trylock of pd->lock in padata_reorder. Pairs with smp_mb
* in padata_reorder.
*/
smp_mb__after_atomic();
- put_cpu();
-
padata_reorder(pd);
}
EXPORT_SYMBOL(padata_do_serial);
@@ -412,9 +386,14 @@ static void padata_init_pqueues(struct parallel_data *pd)
struct padata_parallel_queue *pqueue;
cpu_index = 0;
- for_each_cpu(cpu, pd->cpumask.pcpu) {
+ for_each_possible_cpu(cpu) {
pqueue = per_cpu_ptr(pd->pqueue, cpu);
- pqueue->pd = pd;
+
+ if (!cpumask_test_cpu(cpu, pd->cpumask.pcpu)) {
+ pqueue->cpu_index = -1;
+ continue;
+ }
+
pqueue->cpu_index = cpu_index;
cpu_index++;
@@ -448,12 +427,13 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
padata_init_pqueues(pd);
padata_init_squeues(pd);
- setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
atomic_set(&pd->seq_nr, -1);
atomic_set(&pd->reorder_objects, 0);
atomic_set(&pd->refcnt, 1);
pd->pinst = pinst;
spin_lock_init(&pd->lock);
+ pd->cpu = cpumask_first(pd->cpumask.pcpu);
+ INIT_WORK(&pd->reorder_work, invoke_padata_reorder);
return pd;
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index e24008c098c6..45a0a26023d4 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -25,8 +25,6 @@
#include <linux/syscalls.h>
#include <linux/uaccess.h>
-static void delete_clock(struct kref *kref);
-
/*
* Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
*/
@@ -168,7 +166,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
err = 0;
if (!err) {
- kref_get(&clk->kref);
+ get_device(clk->dev);
fp->private_data = clk;
}
out:
@@ -184,7 +182,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
if (clk->ops.release)
err = clk->ops.release(clk);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
fp->private_data = NULL;
@@ -206,38 +204,35 @@ static const struct file_operations posix_clock_file_operations = {
#endif
};
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
{
int err;
- kref_init(&clk->kref);
init_rwsem(&clk->rwsem);
cdev_init(&clk->cdev, &posix_clock_file_operations);
+ err = cdev_device_add(&clk->cdev, dev);
+ if (err) {
+ pr_err("%s unable to add device %d:%d\n",
+ dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+ return err;
+ }
clk->cdev.owner = clk->ops.owner;
- err = cdev_add(&clk->cdev, devid, 1);
+ clk->dev = dev;
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(posix_clock_register);
-static void delete_clock(struct kref *kref)
-{
- struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
- if (clk->release)
- clk->release(clk);
-}
-
void posix_clock_unregister(struct posix_clock *clk)
{
- cdev_del(&clk->cdev);
+ cdev_device_del(&clk->cdev, clk->dev);
down_write(&clk->rwsem);
clk->zombie = true;
up_write(&clk->rwsem);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
}
EXPORT_SYMBOL_GPL(posix_clock_unregister);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c39fc68c4778..54be8790941e 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -319,11 +319,12 @@ static void put_probe_ref(void)
static void blk_trace_cleanup(struct blk_trace *bt)
{
+ synchronize_rcu();
blk_trace_free(bt);
put_probe_ref();
}
-int blk_trace_remove(struct request_queue *q)
+static int __blk_trace_remove(struct request_queue *q)
{
struct blk_trace *bt;
@@ -336,6 +337,17 @@ int blk_trace_remove(struct request_queue *q)
return 0;
}
+
+int blk_trace_remove(struct request_queue *q)
+{
+ int ret;
+
+ mutex_lock(&q->blk_trace_mutex);
+ ret = __blk_trace_remove(q);
+ mutex_unlock(&q->blk_trace_mutex);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(blk_trace_remove);
static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
@@ -546,9 +558,8 @@ err:
return ret;
}
-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
- struct block_device *bdev,
- char __user *arg)
+static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev, char __user *arg)
{
struct blk_user_trace_setup buts;
int ret;
@@ -562,11 +573,24 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
return ret;
if (copy_to_user(arg, &buts, sizeof(buts))) {
- blk_trace_remove(q);
+ __blk_trace_remove(q);
return -EFAULT;
}
return 0;
}
+
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
+ char __user *arg)
+{
+ int ret;
+
+ mutex_lock(&q->blk_trace_mutex);
+ ret = __blk_trace_setup(q, name, dev, bdev, arg);
+ mutex_unlock(&q->blk_trace_mutex);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(blk_trace_setup);
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
@@ -595,7 +619,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
return ret;
if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
- blk_trace_remove(q);
+ __blk_trace_remove(q);
return -EFAULT;
}
@@ -603,11 +627,13 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
}
#endif
-int blk_trace_startstop(struct request_queue *q, int start)
+static int __blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (bt == NULL)
return -EINVAL;
@@ -642,8 +668,25 @@ int blk_trace_startstop(struct request_queue *q, int start)
return ret;
}
+
+int blk_trace_startstop(struct request_queue *q, int start)
+{
+ int ret;
+
+ mutex_lock(&q->blk_trace_mutex);
+ ret = __blk_trace_startstop(q, start);
+ mutex_unlock(&q->blk_trace_mutex);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(blk_trace_startstop);
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
* @bdev: the block device
@@ -661,12 +704,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
if (!q)
return -ENXIO;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
switch (cmd) {
case BLKTRACESETUP:
bdevname(bdev, b);
- ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+ ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
case BLKTRACESETUP32:
@@ -677,17 +720,17 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
case BLKTRACESTART:
start = 1;
case BLKTRACESTOP:
- ret = blk_trace_startstop(q, start);
+ ret = __blk_trace_startstop(q, start);
break;
case BLKTRACETEARDOWN:
- ret = blk_trace_remove(q);
+ ret = __blk_trace_remove(q);
break;
default:
ret = -ENOTTY;
break;
}
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
return ret;
}
@@ -698,10 +741,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
**/
void blk_trace_shutdown(struct request_queue *q)
{
- if (q->blk_trace) {
- blk_trace_startstop(q, 0);
- blk_trace_remove(q);
+ mutex_lock(&q->blk_trace_mutex);
+ if (rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex))) {
+ __blk_trace_startstop(q, 0);
+ __blk_trace_remove(q);
}
+
+ mutex_unlock(&q->blk_trace_mutex);
}
/*
@@ -722,11 +769,15 @@ void blk_trace_shutdown(struct request_queue *q)
static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
unsigned int nr_bytes, u32 what)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct task_struct *tsk = current;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
/*
* Use the bio context for all events except ISSUE and
@@ -751,6 +802,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
rq->cmd_flags, what, rq->errors, 0, NULL, tsk);
}
+ rcu_read_unlock();
}
static void blk_add_trace_rq_abort(void *ignore,
@@ -800,11 +852,15 @@ static void blk_add_trace_rq_complete(void *ignore,
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
u32 what, int error)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct task_struct *tsk = current;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
/*
* Not all the pages in the bio are dirtied by the same task but
@@ -817,6 +873,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio->bi_rw, what, error, 0, NULL, tsk);
+ rcu_read_unlock();
}
static void blk_add_trace_bio_bounce(void *ignore,
@@ -861,11 +918,14 @@ static void blk_add_trace_getrq(void *ignore,
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0,
NULL, current);
+ rcu_read_unlock();
}
}
@@ -877,28 +937,36 @@ static void blk_add_trace_sleeprq(void *ignore,
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ,
0, 0, NULL, current);
+ rcu_read_unlock();
}
}
static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL,
current);
+ rcu_read_unlock();
}
static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
unsigned int depth, bool explicit)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(depth);
u32 what;
@@ -911,15 +979,18 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu,
current);
}
+ rcu_read_unlock();
}
static void blk_add_trace_split(void *ignore,
struct request_queue *q, struct bio *bio,
unsigned int pdu)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct task_struct *tsk = current;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(pdu);
@@ -932,6 +1003,7 @@ static void blk_add_trace_split(void *ignore,
bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
bio->bi_error, sizeof(rpdu), &rpdu, tsk);
}
+ rcu_read_unlock();
}
/**
@@ -951,12 +1023,16 @@ static void blk_add_trace_bio_remap(void *ignore,
struct request_queue *q, struct bio *bio,
dev_t dev, sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
struct task_struct *tsk = current;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev);
@@ -970,6 +1046,7 @@ static void blk_add_trace_bio_remap(void *ignore,
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
sizeof(r), &r, tsk);
+ rcu_read_unlock();
}
/**
@@ -990,12 +1067,16 @@ static void blk_add_trace_rq_remap(void *ignore,
struct request *rq, dev_t dev,
sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
struct task_struct *tsk = current;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(disk_devt(rq->rq_disk));
@@ -1009,6 +1090,7 @@ static void blk_add_trace_rq_remap(void *ignore,
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
sizeof(r), &r, tsk);
+ rcu_read_unlock();
}
/**
@@ -1026,11 +1108,15 @@ void blk_add_driver_data(struct request_queue *q,
struct request *rq,
void *data, size_t len)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct task_struct *tsk = current;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
if (bio_has_data(rq->bio) && rq->bio->bi_io_vec &&
rq->bio->bi_io_vec->bv_page &&
@@ -1043,6 +1129,7 @@ void blk_add_driver_data(struct request_queue *q,
else
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
BLK_TA_DRV_DATA, rq->errors, len, data, tsk);
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1534,6 +1621,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
return -EINVAL;
put_probe_ref();
+ synchronize_rcu();
blk_trace_free(bt);
return 0;
}
@@ -1694,6 +1782,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct hd_struct *p = dev_to_part(dev);
struct request_queue *q;
struct block_device *bdev;
+ struct blk_trace *bt;
ssize_t ret = -ENXIO;
bdev = bdget(part_devt(p));
@@ -1704,26 +1793,28 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ ret = sprintf(buf, "%u\n", !!bt);
goto out_unlock_bdev;
}
- if (q->blk_trace == NULL)
+ if (bt == NULL)
ret = sprintf(buf, "disabled\n");
else if (attr == &dev_attr_act_mask)
- ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+ ret = blk_trace_mask2str(buf, bt->act_mask);
else if (attr == &dev_attr_pid)
- ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+ ret = sprintf(buf, "%u\n", bt->pid);
else if (attr == &dev_attr_start_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+ ret = sprintf(buf, "%llu\n", bt->start_lba);
else if (attr == &dev_attr_end_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+ ret = sprintf(buf, "%llu\n", bt->end_lba);
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
@@ -1737,6 +1828,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
struct block_device *bdev;
struct request_queue *q;
struct hd_struct *p;
+ struct blk_trace *bt;
u64 value;
ssize_t ret = -EINVAL;
@@ -1765,10 +1857,12 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- if (!!value == !!q->blk_trace) {
+ if (!!value == !!bt) {
ret = 0;
goto out_unlock_bdev;
}
@@ -1780,22 +1874,25 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
}
ret = 0;
- if (q->blk_trace == NULL)
+ if (bt == NULL) {
ret = blk_trace_setup_queue(q, bdev);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
+ }
if (ret == 0) {
if (attr == &dev_attr_act_mask)
- q->blk_trace->act_mask = value;
+ bt->act_mask = value;
else if (attr == &dev_attr_pid)
- q->blk_trace->pid = value;
+ bt->pid = value;
else if (attr == &dev_attr_start_lba)
- q->blk_trace->start_lba = value;
+ bt->start_lba = value;
else if (attr == &dev_attr_end_lba)
- q->blk_trace->end_lba = value;
+ bt->end_lba = value;
}
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3dd40c736067..a71bdad638d5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -206,6 +206,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
event->pmu->count)
return -EINVAL;
+ if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
+ event->attr.type != PERF_TYPE_RAW))
+ return -EINVAL;
+
/*
* we don't know if the function is run successfully by the
* return value. It can be judged in other places, such as
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-08 18:01:24 +0000