Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block
Pull blk-mq irq/cpu mapping updates from Jens Axboe:
"This is the block-irq topic branch for 4.9-rc. It's mostly from
Christoph, and it allows drivers to specify their own mappings, and
more importantly, to share the blk-mq mappings with the IRQ affinity
mappings. It's a good step towards making this work better out of the
box"
* 'for-4.9/block-irq' of git://git.kernel.dk/linux-block:
blk_mq: linux/blk-mq.h does not include all the headers it depends on
blk-mq: kill unused blk_mq_create_mq_map()
blk-mq: get rid of the cpumask in struct blk_mq_tags
nvme: remove the post_scan callout
nvme: switch to use pci_alloc_irq_vectors
blk-mq: provide a default queue mapping for PCI device
blk-mq: allow the driver to pass in a queue mapping
blk-mq: remove ->map_queue
blk-mq: only allocate a single mq_map per tag_set
blk-mq: don't redistribute hardware queues on a CPU hotplug event
diff --git a/block/Kconfig b/block/Kconfig
index 5136ad4..1d4d624 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -125,4 +125,9 @@
depends on BLOCK && COMPAT
default y
+config BLK_MQ_PCI
+ bool
+ depends on BLOCK && PCI
+ default y
+
source block/Kconfig.iosched
diff --git a/block/Makefile b/block/Makefile
index 9eda232..37a0d93 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -22,4 +22,4 @@
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
diff --git a/block/blk-flush.c b/block/blk-flush.c
index d308def..6a14b68 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -232,7 +232,7 @@
/* release the tag's ownership to the req cloned from */
spin_lock_irqsave(&fq->mq_flush_lock, flags);
- hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+ hctx = blk_mq_map_queue(q, flush_rq->mq_ctx->cpu);
blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
flush_rq->tag = -1;
}
@@ -325,7 +325,7 @@
flush_rq->tag = first_rq->tag;
fq->orig_rq = first_rq;
- hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+ hctx = blk_mq_map_queue(q, first_rq->mq_ctx->cpu);
blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
}
@@ -358,7 +358,7 @@
unsigned long flags;
struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
/*
* After populating an empty queue, kick it to avoid stall. Read
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index d0634bc..19b1d9c 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -31,14 +31,16 @@
return cpu;
}
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
- const struct cpumask *online_mask)
+int blk_mq_map_queues(struct blk_mq_tag_set *set)
{
+ unsigned int *map = set->mq_map;
+ unsigned int nr_queues = set->nr_hw_queues;
+ const struct cpumask *online_mask = cpu_online_mask;
unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
cpumask_var_t cpus;
if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
- return 1;
+ return -ENOMEM;
cpumask_clear(cpus);
nr_cpus = nr_uniq_cpus = 0;
@@ -86,23 +88,6 @@
return 0;
}
-unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
-{
- unsigned int *map;
-
- /* If cpus are offline, map them to first hctx */
- map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
- set->numa_node);
- if (!map)
- return NULL;
-
- if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
- return map;
-
- kfree(map);
- return NULL;
-}
-
/*
* We have no quick way of doing reverse lookups. This is only used at
* queue init time, so runtime isn't important.
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
new file mode 100644
index 0000000..966c216
--- /dev/null
+++ b/block/blk-mq-pci.c
@@ -0,0 +1,47 @@
+/*
+ * 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/kobject.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+
+/**
+ * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
+ * @set: tagset to provide the mapping for
+ * @pdev: PCI device associated with @set.
+ *
+ * This function assumes the PCI device @pdev 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_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
+{
+ const struct cpumask *mask;
+ unsigned int queue, cpu;
+
+ for (queue = 0; queue < set->nr_hw_queues; queue++) {
+ mask = pci_irq_get_affinity(pdev, queue);
+ if (!mask)
+ return -EINVAL;
+
+ for_each_cpu(cpu, mask)
+ set->mq_map[cpu] = queue;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index cef618f..dcf5ce3 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -141,8 +141,7 @@
io_schedule();
data->ctx = blk_mq_get_ctx(data->q);
- data->hctx = data->q->mq_ops->map_queue(data->q,
- data->ctx->cpu);
+ data->hctx = blk_mq_map_queue(data->q, data->ctx->cpu);
if (data->flags & BLK_MQ_REQ_RESERVED) {
bt = &data->hctx->tags->breserved_tags;
} else {
@@ -399,11 +398,6 @@
if (!tags)
return NULL;
- if (!zalloc_cpumask_var(&tags->cpumask, GFP_KERNEL)) {
- kfree(tags);
- return NULL;
- }
-
tags->nr_tags = total_tags;
tags->nr_reserved_tags = reserved_tags;
@@ -414,7 +408,6 @@
{
sbitmap_queue_free(&tags->bitmap_tags);
sbitmap_queue_free(&tags->breserved_tags);
- free_cpumask_var(tags->cpumask);
kfree(tags);
}
@@ -453,7 +446,7 @@
int hwq = 0;
if (q->mq_ops) {
- hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+ hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
hwq = hctx->queue_num;
}
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 09f4cc0..d166273 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -17,8 +17,6 @@
struct request **rqs;
struct list_head page_list;
-
- cpumask_var_t cpumask;
};
diff --git a/block/blk-mq.c b/block/blk-mq.c
index dc5f47f..b65f572 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -224,7 +224,7 @@
return ERR_PTR(ret);
ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
blk_mq_put_ctx(ctx);
@@ -319,11 +319,7 @@
void blk_mq_free_request(struct request *rq)
{
- struct blk_mq_hw_ctx *hctx;
- struct request_queue *q = rq->q;
-
- hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
- blk_mq_free_hctx_request(hctx, rq);
+ blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
@@ -1058,9 +1054,7 @@
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx;
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
spin_lock(&ctx->lock);
__blk_mq_insert_request(hctx, rq, at_head);
@@ -1077,12 +1071,10 @@
bool from_schedule)
{
- struct blk_mq_hw_ctx *hctx;
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
trace_block_unplug(q, depth, !from_schedule);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
/*
* preemption doesn't flush plug list, so it's possible ctx->cpu is
* offline now
@@ -1216,7 +1208,7 @@
blk_queue_enter_live(q);
ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
if (rw_is_sync(bio_op(bio), bio->bi_opf))
op_flags |= REQ_SYNC;
@@ -1235,8 +1227,7 @@
{
int ret;
struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
- rq->mq_ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
struct blk_mq_queue_data bd = {
.rq = rq,
.list = NULL,
@@ -1440,15 +1431,6 @@
return cookie;
}
-/*
- * Default mapping to a software queue, since we use one per CPU.
- */
-struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, const int cpu)
-{
- return q->queue_hw_ctx[q->mq_map[cpu]];
-}
-EXPORT_SYMBOL(blk_mq_map_queue);
-
static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
struct blk_mq_tags *tags, unsigned int hctx_idx)
{
@@ -1757,7 +1739,7 @@
if (!cpu_online(i))
continue;
- hctx = q->mq_ops->map_queue(q, i);
+ hctx = blk_mq_map_queue(q, i);
/*
* Set local node, IFF we have more than one hw queue. If
@@ -1795,7 +1777,7 @@
continue;
ctx = per_cpu_ptr(q->queue_ctx, i);
- hctx = q->mq_ops->map_queue(q, i);
+ hctx = blk_mq_map_queue(q, i);
cpumask_set_cpu(i, hctx->cpumask);
ctx->index_hw = hctx->nr_ctx;
@@ -1824,7 +1806,6 @@
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
- cpumask_copy(hctx->tags->cpumask, hctx->cpumask);
/*
* Set the map size to the number of mapped software queues.
* This is more accurate and more efficient than looping
@@ -1918,7 +1899,6 @@
kfree(hctx);
}
- kfree(q->mq_map);
q->mq_map = NULL;
kfree(q->queue_hw_ctx);
@@ -2017,9 +1997,7 @@
if (!q->queue_hw_ctx)
goto err_percpu;
- q->mq_map = blk_mq_make_queue_map(set);
- if (!q->mq_map)
- goto err_map;
+ q->mq_map = set->mq_map;
blk_mq_realloc_hw_ctxs(set, q);
if (!q->nr_hw_queues)
@@ -2069,8 +2047,6 @@
return q;
err_hctxs:
- kfree(q->mq_map);
-err_map:
kfree(q->queue_hw_ctx);
err_percpu:
free_percpu(q->queue_ctx);
@@ -2102,8 +2078,6 @@
blk_mq_sysfs_unregister(q);
- blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask);
-
/*
* redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
* we should change hctx numa_node according to new topology (this
@@ -2242,12 +2216,6 @@
return 0;
}
-struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags)
-{
- return tags->cpumask;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
-
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
@@ -2256,6 +2224,8 @@
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
+ int ret;
+
BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
if (!set->nr_hw_queues)
@@ -2265,7 +2235,7 @@
if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
return -EINVAL;
- if (!set->ops->queue_rq || !set->ops->map_queue)
+ if (!set->ops->queue_rq)
return -EINVAL;
if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
@@ -2294,17 +2264,35 @@
if (!set->tags)
return -ENOMEM;
- if (blk_mq_alloc_rq_maps(set))
- goto enomem;
+ ret = -ENOMEM;
+ set->mq_map = kzalloc_node(sizeof(*set->mq_map) * nr_cpu_ids,
+ GFP_KERNEL, set->numa_node);
+ if (!set->mq_map)
+ goto out_free_tags;
+
+ if (set->ops->map_queues)
+ ret = set->ops->map_queues(set);
+ else
+ ret = blk_mq_map_queues(set);
+ if (ret)
+ goto out_free_mq_map;
+
+ ret = blk_mq_alloc_rq_maps(set);
+ if (ret)
+ goto out_free_mq_map;
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
-enomem:
+
+out_free_mq_map:
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+out_free_tags:
kfree(set->tags);
set->tags = NULL;
- return -ENOMEM;
+ return ret;
}
EXPORT_SYMBOL(blk_mq_alloc_tag_set);
@@ -2317,6 +2305,9 @@
blk_mq_free_rq_map(set, set->tags[i], i);
}
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+
kfree(set->tags);
set->tags = NULL;
}
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 9b15d2e..df6474c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -45,11 +45,15 @@
/*
* CPU -> queue mappings
*/
-extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
-extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
- const struct cpumask *online_mask);
+int blk_mq_map_queues(struct blk_mq_tag_set *set);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
+static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
+ int cpu)
+{
+ return q->queue_hw_ctx[q->mq_map[cpu]];
+}
+
/*
* sysfs helpers
*/
diff --git a/block/blk.h b/block/blk.h
index c37492f..74444c4 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -39,14 +39,9 @@
static inline struct blk_flush_queue *blk_get_flush_queue(
struct request_queue *q, struct blk_mq_ctx *ctx)
{
- struct blk_mq_hw_ctx *hctx;
-
- if (!q->mq_ops)
- return q->fq;
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
- return hctx->fq;
+ if (q->mq_ops)
+ return blk_mq_map_queue(q, ctx->cpu)->fq;
+ return q->fq;
}
static inline void __blk_get_queue(struct request_queue *q)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c9f2107..cbdb3b1 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1703,7 +1703,6 @@
static struct blk_mq_ops loop_mq_ops = {
.queue_rq = loop_queue_rq,
- .map_queue = blk_mq_map_queue,
.init_request = loop_init_request,
};
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 88c4685..3cfd879 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3895,7 +3895,6 @@
static struct blk_mq_ops mtip_mq_ops = {
.queue_rq = mtip_queue_rq,
- .map_queue = blk_mq_map_queue,
.init_request = mtip_init_cmd,
.exit_request = mtip_free_cmd,
.complete = mtip_softirq_done_fn,
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ccfcfc1..ba405b5 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -881,7 +881,6 @@
static struct blk_mq_ops nbd_mq_ops = {
.queue_rq = nbd_queue_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nbd_init_request,
.timeout = nbd_xmit_timeout,
};
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 91e1de8..ba6f4a2e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -394,7 +394,6 @@
static struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
- .map_queue = blk_mq_map_queue,
.init_hctx = null_init_hctx,
.complete = null_softirq_done_fn,
};
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 6c6519f..c1f84df 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3621,7 +3621,6 @@
static struct blk_mq_ops rbd_mq_ops = {
.queue_rq = rbd_queue_rq,
- .map_queue = blk_mq_map_queue,
.init_request = rbd_init_request,
};
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 93b1aaa..2dc5c96 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -542,7 +542,6 @@
static struct blk_mq_ops virtio_mq_ops = {
.queue_rq = virtio_queue_rq,
- .map_queue = blk_mq_map_queue,
.complete = virtblk_request_done,
.init_request = virtblk_init_request,
};
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 88ef6d4..9908597 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -909,7 +909,6 @@
static struct blk_mq_ops blkfront_mq_ops = {
.queue_rq = blkif_queue_rq,
- .map_queue = blk_mq_map_queue,
};
static void blkif_set_queue_limits(struct blkfront_info *info)
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 182b679..5eacce1 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -938,7 +938,6 @@
static struct blk_mq_ops dm_mq_ops = {
.queue_rq = dm_mq_queue_rq,
- .map_queue = blk_mq_map_queue,
.complete = dm_softirq_done,
.init_request = dm_mq_init_request,
};
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index ebf46ad..d1e6931 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -351,7 +351,6 @@
static struct blk_mq_ops ubiblock_mq_ops = {
.queue_rq = ubiblock_queue_rq,
.init_request = ubiblock_init_request,
- .map_queue = blk_mq_map_queue,
};
static DEFINE_IDR(ubiblock_minor_idr);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4669c05..329381a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1851,9 +1851,6 @@
list_sort(NULL, &ctrl->namespaces, ns_cmp);
mutex_unlock(&ctrl->namespaces_mutex);
kfree(id);
-
- if (ctrl->ops->post_scan)
- ctrl->ops->post_scan(ctrl);
}
void nvme_queue_scan(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b0a9ec6..d47f5a5 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -185,7 +185,6 @@
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int (*reset_ctrl)(struct nvme_ctrl *ctrl);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
- void (*post_scan)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
int (*delete_ctrl)(struct nvme_ctrl *ctrl);
const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 60f7eab..68ef187 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -16,6 +16,7 @@
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/errno.h>
@@ -88,7 +89,6 @@
unsigned max_qid;
int q_depth;
u32 db_stride;
- struct msix_entry *entry;
void __iomem *bar;
struct work_struct reset_work;
struct work_struct remove_work;
@@ -201,6 +201,11 @@
nvme_iod_alloc_size(dev, NVME_INT_BYTES(dev), NVME_INT_PAGES);
}
+static int nvmeq_irq(struct nvme_queue *nvmeq)
+{
+ return pci_irq_vector(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector);
+}
+
static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int hctx_idx)
{
@@ -263,6 +268,13 @@
return 0;
}
+static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nvme_dev *dev = set->driver_data;
+
+ return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev));
+}
+
/**
* __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
* @nvmeq: The queue to use
@@ -960,7 +972,7 @@
spin_unlock_irq(&nvmeq->q_lock);
return 1;
}
- vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+ vector = nvmeq_irq(nvmeq);
nvmeq->dev->online_queues--;
nvmeq->cq_vector = -1;
spin_unlock_irq(&nvmeq->q_lock);
@@ -968,7 +980,6 @@
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
blk_mq_stop_hw_queues(nvmeq->dev->ctrl.admin_q);
- irq_set_affinity_hint(vector, NULL);
free_irq(vector, nvmeq);
return 0;
@@ -1075,15 +1086,14 @@
return NULL;
}
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
- const char *name)
+static int queue_request_irq(struct nvme_queue *nvmeq)
{
if (use_threaded_interrupts)
- return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
- nvme_irq_check, nvme_irq, IRQF_SHARED,
- name, nvmeq);
- return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
- IRQF_SHARED, name, nvmeq);
+ return request_threaded_irq(nvmeq_irq(nvmeq), nvme_irq_check,
+ nvme_irq, IRQF_SHARED, nvmeq->irqname, nvmeq);
+ else
+ return request_irq(nvmeq_irq(nvmeq), nvme_irq, IRQF_SHARED,
+ nvmeq->irqname, nvmeq);
}
static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1114,7 +1124,7 @@
if (result < 0)
goto release_cq;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
@@ -1131,7 +1141,6 @@
static struct blk_mq_ops nvme_mq_admin_ops = {
.queue_rq = nvme_queue_rq,
.complete = nvme_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_hctx = nvme_admin_init_hctx,
.exit_hctx = nvme_admin_exit_hctx,
.init_request = nvme_admin_init_request,
@@ -1141,9 +1150,9 @@
static struct blk_mq_ops nvme_mq_ops = {
.queue_rq = nvme_queue_rq,
.complete = nvme_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_hctx = nvme_init_hctx,
.init_request = nvme_init_request,
+ .map_queues = nvme_pci_map_queues,
.timeout = nvme_timeout,
.poll = nvme_poll,
};
@@ -1234,7 +1243,7 @@
goto free_nvmeq;
nvmeq->cq_vector = 0;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ result = queue_request_irq(nvmeq);
if (result) {
nvmeq->cq_vector = -1;
goto free_nvmeq;
@@ -1382,7 +1391,7 @@
{
struct nvme_queue *adminq = dev->queues[0];
struct pci_dev *pdev = to_pci_dev(dev->dev);
- int result, i, vecs, nr_io_queues, size;
+ int result, nr_io_queues, size;
nr_io_queues = num_online_cpus();
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
@@ -1417,29 +1426,18 @@
}
/* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, adminq);
+ free_irq(pci_irq_vector(pdev, 0), adminq);
/*
* If we enable msix early due to not intx, disable it again before
* setting up the full range we need.
*/
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
-
- for (i = 0; i < nr_io_queues; i++)
- dev->entry[i].entry = i;
- vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
- if (vecs < 0) {
- vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
- if (vecs < 0) {
- vecs = 1;
- } else {
- for (i = 0; i < vecs; i++)
- dev->entry[i].vector = i + pdev->irq;
- }
- }
+ pci_free_irq_vectors(pdev);
+ nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
+ PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
+ if (nr_io_queues <= 0)
+ return -EIO;
+ dev->max_qid = nr_io_queues;
/*
* Should investigate if there's a performance win from allocating
@@ -1447,10 +1445,8 @@
* path to scale better, even if the receive path is limited by the
* number of interrupts.
*/
- nr_io_queues = vecs;
- dev->max_qid = nr_io_queues;
- result = queue_request_irq(dev, adminq, adminq->irqname);
+ result = queue_request_irq(adminq);
if (result) {
adminq->cq_vector = -1;
goto free_queues;
@@ -1462,23 +1458,6 @@
return result;
}
-static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
-{
- struct nvme_dev *dev = to_nvme_dev(ctrl);
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq->tags));
- }
-}
-
static void nvme_del_queue_end(struct request *req, int error)
{
struct nvme_queue *nvmeq = req->end_io_data;
@@ -1615,15 +1594,9 @@
* interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
* adjust this later.
*/
- if (pci_enable_msix(pdev, dev->entry, 1)) {
- pci_enable_msi(pdev);
- dev->entry[0].vector = pdev->irq;
- }
-
- if (!dev->entry[0].vector) {
- result = -ENODEV;
- goto disable;
- }
+ result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+ if (result < 0)
+ return result;
cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
@@ -1665,10 +1638,7 @@
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
+ pci_free_irq_vectors(pdev);
if (pci_is_enabled(pdev)) {
pci_disable_pcie_error_reporting(pdev);
@@ -1743,7 +1713,6 @@
if (dev->ctrl.admin_q)
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
- kfree(dev->entry);
kfree(dev);
}
@@ -1887,7 +1856,6 @@
.reg_read64 = nvme_pci_reg_read64,
.reset_ctrl = nvme_pci_reset_ctrl,
.free_ctrl = nvme_pci_free_ctrl,
- .post_scan = nvme_pci_post_scan,
.submit_async_event = nvme_pci_submit_async_event,
};
@@ -1920,10 +1888,6 @@
dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
if (!dev)
return -ENOMEM;
- dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
- GFP_KERNEL, node);
- if (!dev->entry)
- goto free;
dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
GFP_KERNEL, node);
if (!dev->queues)
@@ -1964,7 +1928,6 @@
nvme_dev_unmap(dev);
free:
kfree(dev->queues);
- kfree(dev->entry);
kfree(dev);
return result;
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2863229..5a83881 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1480,7 +1480,6 @@
static struct blk_mq_ops nvme_rdma_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_rdma_init_request,
.exit_request = nvme_rdma_exit_request,
.reinit_request = nvme_rdma_reinit_request,
@@ -1492,7 +1491,6 @@
static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_rdma_init_admin_request,
.exit_request = nvme_rdma_exit_admin_request,
.reinit_request = nvme_rdma_reinit_request,
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 395e60d..d5df77d 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -273,7 +273,6 @@
static struct blk_mq_ops nvme_loop_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_request,
.init_hctx = nvme_loop_init_hctx,
.timeout = nvme_loop_timeout,
@@ -282,7 +281,6 @@
static struct blk_mq_ops nvme_loop_admin_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_admin_request,
.init_hctx = nvme_loop_init_admin_hctx,
.timeout = nvme_loop_timeout,
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index c71344a..2cca9cf 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2077,7 +2077,6 @@
}
static struct blk_mq_ops scsi_mq_ops = {
- .map_queue = blk_mq_map_queue,
.queue_rq = scsi_queue_rq,
.complete = scsi_softirq_done,
.timeout = scsi_timeout,
diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h
new file mode 100644
index 0000000..6ab5952
--- /dev/null
+++ b/include/linux/blk-mq-pci.h
@@ -0,0 +1,9 @@
+#ifndef _LINUX_BLK_MQ_PCI_H
+#define _LINUX_BLK_MQ_PCI_H
+
+struct blk_mq_tag_set;
+struct pci_dev;
+
+int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev);
+
+#endif /* _LINUX_BLK_MQ_PCI_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 5daa0ef..ef6aebf 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -62,6 +62,7 @@
};
struct blk_mq_tag_set {
+ unsigned int *mq_map;
struct blk_mq_ops *ops;
unsigned int nr_hw_queues;
unsigned int queue_depth; /* max hw supported */
@@ -85,7 +86,6 @@
};
typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
-typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
@@ -99,6 +99,7 @@
bool);
typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int);
+typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
struct blk_mq_ops {
@@ -108,11 +109,6 @@
queue_rq_fn *queue_rq;
/*
- * Map to specific hardware queue
- */
- map_queue_fn *map_queue;
-
- /*
* Called on request timeout
*/
timeout_fn *timeout;
@@ -144,6 +140,8 @@
init_request_fn *init_request;
exit_request_fn *exit_request;
reinit_request_fn *reinit_request;
+
+ map_queues_fn *map_queues;
};
enum {
@@ -199,7 +197,6 @@
struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op,
unsigned int flags, unsigned int hctx_idx);
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
-struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags);
enum {
BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -218,7 +215,6 @@
return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
}
-struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
int blk_mq_request_started(struct request *rq);
void blk_mq_start_request(struct request *rq);