summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/Kconfig5
-rw-r--r--block/Makefile1
-rw-r--r--block/blk-cgroup.c1
-rw-r--r--block/blk-core.c28
-rw-r--r--block/blk-ioc.c45
-rw-r--r--block/blk-map.c1
-rw-r--r--block/blk-mq-sched.c16
-rw-r--r--block/blk-mq-sysfs.c40
-rw-r--r--block/blk-mq-tag.c2
-rw-r--r--block/blk-mq-tag.h6
-rw-r--r--block/blk-mq-virtio.c54
-rw-r--r--block/blk-mq.c150
-rw-r--r--block/blk-mq.h12
-rw-r--r--block/blk-softirq.c1
-rw-r--r--block/blk-sysfs.c2
-rw-r--r--block/cfq-iosched.c1
-rw-r--r--block/elevator.c2
-rw-r--r--block/genhd.c32
-rw-r--r--block/ioprio.c3
-rw-r--r--block/sed-opal.c10
20 files changed, 273 insertions, 139 deletions
diff --git a/block/Kconfig b/block/Kconfig
index a2a92e57a87d..e9f780f815f5 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -189,4 +189,9 @@ config BLK_MQ_PCI
depends on BLOCK && PCI
default y
+config BLK_MQ_VIRTIO
+ bool
+ depends on BLOCK && VIRTIO
+ default y
+
source block/Kconfig.iosched
diff --git a/block/Makefile b/block/Makefile
index 2ad7c304e3f5..081bb680789b 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o
obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o
+obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o
obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o
obj-$(CONFIG_BLK_WBT) += blk-wbt.o
obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 295e98c2c8cc..bbe7ee00bd3d 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -17,6 +17,7 @@
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
+#include <linux/sched/signal.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
diff --git a/block/blk-core.c b/block/blk-core.c
index b9e857f4afe8..0eeb99ef654f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -578,9 +578,6 @@ void blk_cleanup_queue(struct request_queue *q)
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
- bdi_unregister(q->backing_dev_info);
- put_disk_devt(q->disk_devt);
-
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
@@ -2018,17 +2015,34 @@ blk_qc_t generic_make_request(struct bio *bio)
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
if (likely(blk_queue_enter(q, false) == 0)) {
+ struct bio_list hold;
+ struct bio_list lower, same;
+
+ /* Create a fresh bio_list for all subordinate requests */
+ hold = bio_list_on_stack;
+ bio_list_init(&bio_list_on_stack);
ret = q->make_request_fn(q, bio);
blk_queue_exit(q);
- bio = bio_list_pop(current->bio_list);
+ /* sort new bios into those for a lower level
+ * and those for the same level
+ */
+ bio_list_init(&lower);
+ bio_list_init(&same);
+ while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL)
+ if (q == bdev_get_queue(bio->bi_bdev))
+ bio_list_add(&same, bio);
+ else
+ bio_list_add(&lower, bio);
+ /* now assemble so we handle the lowest level first */
+ bio_list_merge(&bio_list_on_stack, &lower);
+ bio_list_merge(&bio_list_on_stack, &same);
+ bio_list_merge(&bio_list_on_stack, &hold);
} else {
- struct bio *bio_next = bio_list_pop(current->bio_list);
-
bio_io_error(bio);
- bio = bio_next;
}
+ bio = bio_list_pop(current->bio_list);
} while (bio);
current->bio_list = NULL; /* deactivate */
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b12f9c87b4c3..63898d229cb9 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -7,6 +7,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
+#include <linux/sched/task.h>
#include "blk.h"
@@ -36,8 +37,8 @@ static void icq_free_icq_rcu(struct rcu_head *head)
}
/*
- * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
- * mq.
+ * Exit an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
*/
static void ioc_exit_icq(struct io_cq *icq)
{
@@ -54,7 +55,10 @@ static void ioc_exit_icq(struct io_cq *icq)
icq->flags |= ICQ_EXITED;
}
-/* Release an icq. Called with both ioc and q locked. */
+/*
+ * Release an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
+ */
static void ioc_destroy_icq(struct io_cq *icq)
{
struct io_context *ioc = icq->ioc;
@@ -62,7 +66,6 @@ static void ioc_destroy_icq(struct io_cq *icq)
struct elevator_type *et = q->elevator->type;
lockdep_assert_held(&ioc->lock);
- lockdep_assert_held(q->queue_lock);
radix_tree_delete(&ioc->icq_tree, icq->q->id);
hlist_del_init(&icq->ioc_node);
@@ -222,24 +225,40 @@ void exit_io_context(struct task_struct *task)
put_io_context_active(ioc);
}
+static void __ioc_clear_queue(struct list_head *icq_list)
+{
+ unsigned long flags;
+
+ while (!list_empty(icq_list)) {
+ struct io_cq *icq = list_entry(icq_list->next,
+ struct io_cq, q_node);
+ struct io_context *ioc = icq->ioc;
+
+ spin_lock_irqsave(&ioc->lock, flags);
+ ioc_destroy_icq(icq);
+ spin_unlock_irqrestore(&ioc->lock, flags);
+ }
+}
+
/**
* ioc_clear_queue - break any ioc association with the specified queue
* @q: request_queue being cleared
*
- * Walk @q->icq_list and exit all io_cq's. Must be called with @q locked.
+ * Walk @q->icq_list and exit all io_cq's.
*/
void ioc_clear_queue(struct request_queue *q)
{
- lockdep_assert_held(q->queue_lock);
+ LIST_HEAD(icq_list);
- while (!list_empty(&q->icq_list)) {
- struct io_cq *icq = list_entry(q->icq_list.next,
- struct io_cq, q_node);
- struct io_context *ioc = icq->ioc;
+ spin_lock_irq(q->queue_lock);
+ list_splice_init(&q->icq_list, &icq_list);
- spin_lock(&ioc->lock);
- ioc_destroy_icq(icq);
- spin_unlock(&ioc->lock);
+ if (q->mq_ops) {
+ spin_unlock_irq(q->queue_lock);
+ __ioc_clear_queue(&icq_list);
+ } else {
+ __ioc_clear_queue(&icq_list);
+ spin_unlock_irq(q->queue_lock);
}
}
diff --git a/block/blk-map.c b/block/blk-map.c
index 2f18c2a0be1b..3b5cb863318f 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -2,6 +2,7 @@
* Functions related to mapping data to requests
*/
#include <linux/kernel.h>
+#include <linux/sched/task_stack.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 98c7b061781e..09af8ff18719 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -110,15 +110,14 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
struct blk_mq_alloc_data *data)
{
struct elevator_queue *e = q->elevator;
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
struct request *rq;
blk_queue_enter_live(q);
- ctx = blk_mq_get_ctx(q);
- hctx = blk_mq_map_queue(q, ctx->cpu);
-
- blk_mq_set_alloc_data(data, q, data->flags, ctx, hctx);
+ data->q = q;
+ if (likely(!data->ctx))
+ data->ctx = blk_mq_get_ctx(q);
+ if (likely(!data->hctx))
+ data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
if (e) {
data->flags |= BLK_MQ_REQ_INTERNAL;
@@ -135,8 +134,6 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
rq = __blk_mq_alloc_request(data, op);
} else {
rq = __blk_mq_alloc_request(data, op);
- if (rq)
- data->hctx->tags->rqs[rq->tag] = rq;
}
if (rq) {
@@ -454,7 +451,8 @@ int blk_mq_sched_setup(struct request_queue *q)
*/
ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->sched_tags = blk_mq_alloc_rq_map(set, i, q->nr_requests, 0);
+ hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
+ q->nr_requests, set->reserved_tags);
if (!hctx->sched_tags) {
ret = -ENOMEM;
break;
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 295e69670c39..d745ab81033a 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -17,6 +17,15 @@ static void blk_mq_sysfs_release(struct kobject *kobj)
{
}
+static void blk_mq_hw_sysfs_release(struct kobject *kobj)
+{
+ struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
+ kobj);
+ free_cpumask_var(hctx->cpumask);
+ kfree(hctx->ctxs);
+ kfree(hctx);
+}
+
struct blk_mq_ctx_sysfs_entry {
struct attribute attr;
ssize_t (*show)(struct blk_mq_ctx *, char *);
@@ -200,7 +209,7 @@ static struct kobj_type blk_mq_ctx_ktype = {
static struct kobj_type blk_mq_hw_ktype = {
.sysfs_ops = &blk_mq_hw_sysfs_ops,
.default_attrs = default_hw_ctx_attrs,
- .release = blk_mq_sysfs_release,
+ .release = blk_mq_hw_sysfs_release,
};
static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -242,24 +251,15 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
- int i, j;
+ int i;
- queue_for_each_hw_ctx(q, hctx, i) {
+ queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
- hctx_for_each_ctx(hctx, ctx, j)
- kobject_put(&ctx->kobj);
-
- kobject_put(&hctx->kobj);
- }
-
blk_mq_debugfs_unregister_hctxs(q);
kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
kobject_del(&q->mq_kobj);
- kobject_put(&q->mq_kobj);
-
kobject_put(&dev->kobj);
q->mq_sysfs_init_done = false;
@@ -277,7 +277,19 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
}
-static void blk_mq_sysfs_init(struct request_queue *q)
+void blk_mq_sysfs_deinit(struct request_queue *q)
+{
+ struct blk_mq_ctx *ctx;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ ctx = per_cpu_ptr(q->queue_ctx, cpu);
+ kobject_put(&ctx->kobj);
+ }
+ kobject_put(&q->mq_kobj);
+}
+
+void blk_mq_sysfs_init(struct request_queue *q)
{
struct blk_mq_ctx *ctx;
int cpu;
@@ -297,8 +309,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
blk_mq_disable_hotplug();
- blk_mq_sysfs_init(q);
-
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
goto out;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 54c84363c1b2..e48bc2c72615 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -181,7 +181,7 @@ found_tag:
void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
struct blk_mq_ctx *ctx, unsigned int tag)
{
- if (tag >= tags->nr_reserved_tags) {
+ if (!blk_mq_tag_is_reserved(tags, tag)) {
const int real_tag = tag - tags->nr_reserved_tags;
BUG_ON(real_tag >= tags->nr_tags);
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 63497423c5cd..5cb51e53cc03 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -85,4 +85,10 @@ static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
hctx->tags->rqs[tag] = rq;
}
+static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
+ unsigned int tag)
+{
+ return tag < tags->nr_reserved_tags;
+}
+
#endif
diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c
new file mode 100644
index 000000000000..c3afbca11299
--- /dev/null
+++ b/block/blk-mq-virtio.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2016 Christoph Hellwig.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <linux/device.h>
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/module.h>
+#include "blk-mq.h"
+
+/**
+ * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device
+ * @set: tagset to provide the mapping for
+ * @vdev: virtio device associated with @set.
+ * @first_vec: first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the virtio device @vdev has at least as many available
+ * interrupt vetors as @set has queues. It will then queuery the vector
+ * corresponding to each queue for it's affinity mask and built queue mapping
+ * that maps a queue to the CPUs that have irq affinity for the corresponding
+ * vector.
+ */
+int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+ struct virtio_device *vdev, int first_vec)
+{
+ const struct cpumask *mask;
+ unsigned int queue, cpu;
+
+ if (!vdev->config->get_vq_affinity)
+ goto fallback;
+
+ for (queue = 0; queue < set->nr_hw_queues; queue++) {
+ mask = vdev->config->get_vq_affinity(vdev, first_vec + queue);
+ if (!mask)
+ goto fallback;
+
+ for_each_cpu(cpu, mask)
+ set->mq_map[cpu] = queue;
+ }
+
+ return 0;
+fallback:
+ return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9e6b064e5339..159187a28d66 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -20,6 +20,8 @@
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
+#include <linux/sched/signal.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>
@@ -75,10 +77,20 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
-static void blk_mq_freeze_queue_wait(struct request_queue *q)
+void blk_mq_freeze_queue_wait(struct request_queue *q)
{
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
+
+int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
+ unsigned long timeout)
+{
+ return wait_event_timeout(q->mq_freeze_wq,
+ percpu_ref_is_zero(&q->q_usage_counter),
+ timeout);
+}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
/*
* Guarantee no request is in use, so we can change any data structure of
@@ -234,6 +246,7 @@ struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
}
rq->tag = tag;
rq->internal_tag = -1;
+ data->hctx->tags->rqs[rq->tag] = rq;
}
blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
@@ -273,10 +286,9 @@ EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
unsigned int flags, unsigned int hctx_idx)
{
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
+ struct blk_mq_alloc_data alloc_data = { .flags = flags };
struct request *rq;
- struct blk_mq_alloc_data alloc_data;
+ unsigned int cpu;
int ret;
/*
@@ -299,25 +311,23 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
* Check if the hardware context is actually mapped to anything.
* If not tell the caller that it should skip this queue.
*/
- hctx = q->queue_hw_ctx[hctx_idx];
- if (!blk_mq_hw_queue_mapped(hctx)) {
- ret = -EXDEV;
- goto out_queue_exit;
- }
- ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
-
- blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
- rq = __blk_mq_alloc_request(&alloc_data, rw);
- if (!rq) {
- ret = -EWOULDBLOCK;
- goto out_queue_exit;
+ alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
+ if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
+ blk_queue_exit(q);
+ return ERR_PTR(-EXDEV);
}
+ cpu = cpumask_first(alloc_data.hctx->cpumask);
+ alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
- return rq;
+ rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
-out_queue_exit:
+ blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
- return ERR_PTR(ret);
+
+ if (!rq)
+ return ERR_PTR(-EWOULDBLOCK);
+
+ return rq;
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
@@ -852,6 +862,9 @@ done:
return true;
}
+ if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
+ data.flags |= BLK_MQ_REQ_RESERVED;
+
rq->tag = blk_mq_get_tag(&data);
if (rq->tag >= 0) {
if (blk_mq_tag_busy(data.hctx)) {
@@ -865,12 +878,9 @@ done:
return false;
}
-static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
+static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
+ struct request *rq)
{
- if (rq->tag == -1 || rq->internal_tag == -1)
- return;
-
blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
rq->tag = -1;
@@ -880,6 +890,26 @@ static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
}
}
+static void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
+ struct request *rq)
+{
+ if (rq->tag == -1 || rq->internal_tag == -1)
+ return;
+
+ __blk_mq_put_driver_tag(hctx, rq);
+}
+
+static void blk_mq_put_driver_tag(struct request *rq)
+{
+ struct blk_mq_hw_ctx *hctx;
+
+ if (rq->tag == -1 || rq->internal_tag == -1)
+ return;
+
+ hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+ __blk_mq_put_driver_tag(hctx, rq);
+}
+
/*
* If we fail getting a driver tag because all the driver tags are already
* assigned and on the dispatch list, BUT the first entry does not have a
@@ -989,7 +1019,19 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
bd.rq = rq;
bd.list = dptr;
- bd.last = list_empty(list);
+
+ /*
+ * Flag last if we have no more requests, or if we have more
+ * but can't assign a driver tag to it.
+ */
+ if (list_empty(list))
+ bd.last = true;
+ else {
+ struct request *nxt;
+
+ nxt = list_first_entry(list, struct request, queuelist);
+ bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
+ }
ret = q->mq_ops->queue_rq(hctx, &bd);
switch (ret) {
@@ -997,7 +1039,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
queued++;
break;
case BLK_MQ_RQ_QUEUE_BUSY:
- blk_mq_put_driver_tag(hctx, rq);
+ blk_mq_put_driver_tag_hctx(hctx, rq);
list_add(&rq->queuelist, list);
__blk_mq_requeue_request(rq);
break;
@@ -1027,6 +1069,13 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
* that is where we will continue on next queue run.
*/
if (!list_empty(list)) {
+ /*
+ * If we got a driver tag for the next request already,
+ * free it again.
+ */
+ rq = list_first_entry(list, struct request, queuelist);
+ blk_mq_put_driver_tag(rq);
+
spin_lock(&hctx->lock);
list_splice_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
@@ -1713,16 +1762,20 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
unsigned int reserved_tags)
{
struct blk_mq_tags *tags;
+ int node;
+
+ node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+ if (node == NUMA_NO_NODE)
+ node = set->numa_node;
- tags = blk_mq_init_tags(nr_tags, reserved_tags,
- set->numa_node,
+ tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
if (!tags)
return NULL;
tags->rqs = kzalloc_node(nr_tags * sizeof(struct request *),
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
- set->numa_node);
+ node);
if (!tags->rqs) {
blk_mq_free_tags(tags);
return NULL;
@@ -1730,7 +1783,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
tags->static_rqs = kzalloc_node(nr_tags * sizeof(struct request *),
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
- set->numa_node);
+ node);
if (!tags->static_rqs) {
kfree(tags->rqs);
blk_mq_free_tags(tags);
@@ -1750,6 +1803,11 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
{
unsigned int i, j, entries_per_page, max_order = 4;
size_t rq_size, left;
+ int node;
+
+ node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+ if (node == NUMA_NO_NODE)
+ node = set->numa_node;
INIT_LIST_HEAD(&tags->page_list);
@@ -1771,7 +1829,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
this_order--;
do {
- page = alloc_pages_node(set->numa_node,
+ page = alloc_pages_node(node,
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
this_order);
if (page)
@@ -1804,7 +1862,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
if (set->ops->init_request) {
if (set->ops->init_request(set->driver_data,
rq, hctx_idx, i,
- set->numa_node)) {
+ node)) {
tags->static_rqs[i] = NULL;
goto fail;
}
@@ -1897,16 +1955,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
}
}
-static void blk_mq_free_hw_queues(struct request_queue *q,
- struct blk_mq_tag_set *set)
-{
- struct blk_mq_hw_ctx *hctx;
- unsigned int i;
-
- queue_for_each_hw_ctx(q, hctx, i)
- free_cpumask_var(hctx->cpumask);
-}
-
static int blk_mq_init_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -1987,7 +2035,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
struct blk_mq_hw_ctx *hctx;
- memset(__ctx, 0, sizeof(*__ctx));
__ctx->cpu = i;
spin_lock_init(&__ctx->lock);
INIT_LIST_HEAD(&__ctx->rq_list);
@@ -2199,15 +2246,19 @@ void blk_mq_release(struct request_queue *q)
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
continue;
- kfree(hctx->ctxs);
- kfree(hctx);
+ kobject_put(&hctx->kobj);
}
q->mq_map = NULL;
kfree(q->queue_hw_ctx);
- /* ctx kobj stays in queue_ctx */
+ /*
+ * release .mq_kobj and sw queue's kobject now because
+ * both share lifetime with request queue.
+ */
+ blk_mq_sysfs_deinit(q);
+
free_percpu(q->queue_ctx);
}
@@ -2272,10 +2323,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
if (hctx->tags)
blk_mq_free_map_and_requests(set, j);
blk_mq_exit_hctx(q, set, hctx, j);
- free_cpumask_var(hctx->cpumask);
kobject_put(&hctx->kobj);
- kfree(hctx->ctxs);
- kfree(hctx);
hctxs[j] = NULL;
}
@@ -2294,6 +2342,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
if (!q->queue_ctx)
goto err_exit;
+ /* init q->mq_kobj and sw queues' kobjects */
+ blk_mq_sysfs_init(q);
+
q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
GFP_KERNEL, set->numa_node);
if (!q->queue_hw_ctx)
@@ -2384,7 +2435,6 @@ void blk_mq_free_queue(struct request_queue *q)
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
- blk_mq_free_hw_queues(q, set);
}
/* Basically redo blk_mq_init_queue with queue frozen */
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 24b2256186f3..b79f9a7d8cf6 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -77,6 +77,8 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
/*
* sysfs helpers
*/
+extern void blk_mq_sysfs_init(struct request_queue *q);
+extern void blk_mq_sysfs_deinit(struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
@@ -146,16 +148,6 @@ struct blk_mq_alloc_data {
struct blk_mq_hw_ctx *hctx;
};
-static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
- struct request_queue *q, unsigned int flags,
- struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx)
-{
- data->q = q;
- data->flags = flags;
- data->ctx = ctx;
- data->hctx = hctx;
-}
-
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
if (data->flags & BLK_MQ_REQ_INTERNAL)
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 06cf9807f49a..87b7df4851bf 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -9,6 +9,7 @@
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/sched.h>
+#include <linux/sched/topology.h>
#include "blk.h"
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 002af836aa87..c44b321335f3 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -815,9 +815,7 @@ static void blk_release_queue(struct kobject *kobj)
blkcg_exit_queue(q);
if (q->elevator) {
- spin_lock_irq(q->queue_lock);
ioc_clear_queue(q);
- spin_unlock_irq(q->queue_lock);
elevator_exit(q->elevator);
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 137944777859..440b95ee593c 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -8,6 +8,7 @@
*/
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/sched/clock.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/ktime.h>
diff --git a/block/elevator.c b/block/elevator.c
index ac1c9f481a98..01139f549b5b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -983,9 +983,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
if (old_registered)
elv_unregister_queue(q);
- spin_lock_irq(q->queue_lock);
ioc_clear_queue(q);
- spin_unlock_irq(q->queue_lock);
}
/* allocate, init and register new elevator */
diff --git a/block/genhd.c b/block/genhd.c
index 2f444b87a5f2..a9c516a8b37d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -572,20 +572,6 @@ exit:
disk_part_iter_exit(&piter);
}
-void put_disk_devt(struct disk_devt *disk_devt)
-{
- if (disk_devt && atomic_dec_and_test(&disk_devt->count))
- disk_devt->release(disk_devt);
-}
-EXPORT_SYMBOL(put_disk_devt);
-
-void get_disk_devt(struct disk_devt *disk_devt)
-{
- if (disk_devt)
- atomic_inc(&disk_devt->count);
-}
-EXPORT_SYMBOL(get_disk_devt);
-
/**
* device_add_disk - add partitioning information to kernel list
* @parent: parent device for the disk
@@ -626,13 +612,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
disk_alloc_events(disk);
- /*
- * Take a reference on the devt and assign it to queue since it
- * must not be reallocated while the bdi is registered
- */
- disk->queue->disk_devt = disk->disk_devt;
- get_disk_devt(disk->disk_devt);
-
/* Register BDI before referencing it from bdev */
bdi = disk->queue->backing_dev_info;
bdi_register_owner(bdi, disk_to_dev(disk));
@@ -681,7 +660,16 @@ void del_gendisk(struct gendisk *disk)
disk->flags &= ~GENHD_FL_UP;
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
- blk_unregister_queue(disk);
+ if (disk->queue) {
+ /*
+ * Unregister bdi before releasing device numbers (as they can
+ * get reused and we'd get clashes in sysfs).
+ */
+ bdi_unregister(disk->queue->backing_dev_info);
+ blk_unregister_queue(disk);
+ } else {
+ WARN_ON(1);
+ }
blk_unregister_region(disk_devt(disk), disk->minors);
part_stat_set_all(&disk->part0, 0);
diff --git a/block/ioprio.c b/block/ioprio.c
index 3790669232ff..0c47a00f92a8 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -23,8 +23,11 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ioprio.h>
+#include <linux/cred.h>
#include <linux/blkdev.h>
#include <linux/capability.h>
+#include <linux/sched/user.h>
+#include <linux/sched/task.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/pid_namespace.h>
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 1e18dca360fc..14035f826b5e 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1023,7 +1023,6 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
static int gen_key(struct opal_dev *dev, void *data)
{
- const u8 *method;
u8 uid[OPAL_UID_LENGTH];
int err = 0;
@@ -1031,7 +1030,6 @@ static int gen_key(struct opal_dev *dev, void *data)
set_comid(dev, dev->comid);
memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
- method = opalmethod[OPAL_GENKEY];
kfree(dev->prev_data);
dev->prev_data = NULL;
@@ -1669,7 +1667,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
{
u8 lr_buffer[OPAL_UID_LENGTH];
- const u8 *method;
struct opal_lock_unlock *lkul = data;
u8 read_locked = 1, write_locked = 1;
int err = 0;
@@ -1677,7 +1674,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
clear_opal_cmd(dev);
set_comid(dev, dev->comid);
- method = opalmethod[OPAL_SET];
if (build_locking_range(lr_buffer, sizeof(lr_buffer),
lkul->session.opal_key.lr) < 0)
return -ERANGE;
@@ -1733,14 +1729,12 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
{
u8 lr_buffer[OPAL_UID_LENGTH];
u8 read_locked = 1, write_locked = 1;
- const u8 *method;
struct opal_lock_unlock *lkul = data;
int ret;
clear_opal_cmd(dev);
set_comid(dev, dev->comid);
- method = opalmethod[OPAL_SET];
if (build_locking_range(lr_buffer, sizeof(lr_buffer),
lkul->session.opal_key.lr) < 0)
return -ERANGE;
@@ -2133,7 +2127,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
pr_err("Locking state was not RO or RW\n");
return -EINVAL;
}
- if (lk_unlk->session.who < OPAL_USER1 &&
+ if (lk_unlk->session.who < OPAL_USER1 ||
lk_unlk->session.who > OPAL_USER9) {
pr_err("Authority was not within the range of users: %d\n",
lk_unlk->session.who);
@@ -2316,7 +2310,7 @@ static int opal_activate_user(struct opal_dev *dev,
int ret;
/* We can't activate Admin1 it's active as manufactured */
- if (opal_session->who < OPAL_USER1 &&
+ if (opal_session->who < OPAL_USER1 ||
opal_session->who > OPAL_USER9) {
pr_err("Who was not a valid user: %d\n", opal_session->who);
return -EINVAL;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-16 00:56:19 +0100