Commit 55a1ab56 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A smaller collection of fixes that should go into -rc1. This contains:

   - A fix from Christoph, fixing a regression with the WRITE_SAME and
     partial completions. Caused a BUG() on ppc.

   - Fixup for __blk_mq_stop_hw_queues(), it should be static. From
     Colin.

   - Removal of dmesg error messages on elevator switching, when invoked
     from sysfs. From me.

   - Fix for blk-stat, using this_cpu_ptr() in a section only protected
     by rcu_read_lock(). This breaks when PREEMPT_RCU is enabled. From
     me.

   - Two fixes for BFQ from Paolo, one fixing a crash and one updating
     the documentation.

   - An error handling lightnvm memory leak, from Rakesh.

   - The previous blk-mq hot unplug lock reversal depends on the CPU
     hotplug rework that isn't in mainline yet. This caused a lockdep
     splat when people unplugged CPUs with blk-mq devices. From Wanpeng.

   - A regression fix for DIF/DIX on blk-mq. From Wen"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: handle partial completions for special payload requests
  blk-mq: NVMe 512B/4K+T10 DIF/DIX format returns I/O error on dd with split op
  blk-stat: don't use this_cpu_ptr() in a preemptable section
  elevator: remove redundant warnings on IO scheduler switch
  block, bfq: stress that low_latency must be off to get max throughput
  block, bfq: use pointer entity->sched_data only if set
  nvme: lightnvm: fix memory leak
  blk-mq: make __blk_mq_stop_hw_queues static
  lightnvm: remove unused rq parameter of nvme_nvm_rqtocmd() to kill warning
  block/mq: fix potential deadlock during cpu hotplug
parents 9786e34e ed6565e7
......@@ -11,6 +11,13 @@ controllers), BFQ's main features are:
groups (switching back to time distribution when needed to keep
throughput high).
In its default configuration, BFQ privileges latency over
throughput. So, when needed for achieving a lower latency, BFQ builds
schedules that may lead to a lower throughput. If your main or only
goal, for a given device, is to achieve the maximum-possible
throughput at all times, then do switch off all low-latency heuristics
for that device, by setting low_latency to 0. Full details in Section 3.
On average CPUs, the current version of BFQ can handle devices
performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
reference, 30-50 KIOPS correspond to very high bandwidths with
......@@ -375,11 +382,19 @@ default, low latency mode is enabled. If enabled, interactive and soft
real-time applications are privileged and experience a lower latency,
as explained in more detail in the description of how BFQ works.
DO NOT enable this mode if you need full control on bandwidth
DISABLE this mode if you need full control on bandwidth
distribution. In fact, if it is enabled, then BFQ automatically
increases the bandwidth share of privileged applications, as the main
means to guarantee a lower latency to them.
In addition, as already highlighted at the beginning of this document,
DISABLE this mode if your only goal is to achieve a high throughput.
In fact, privileging the I/O of some application over the rest may
entail a lower throughput. To achieve the highest-possible throughput
on a non-rotational device, setting slice_idle to 0 may be needed too
(at the cost of giving up any strong guarantee on fairness and low
latency).
timeout_sync
------------
......
......@@ -56,6 +56,11 @@
* rotational or flash-based devices, and to get the job done quickly
* for applications consisting in many I/O-bound processes.
*
* NOTE: if the main or only goal, with a given device, is to achieve
* the maximum-possible throughput at all times, then do switch off
* all low-latency heuristics for that device, by setting low_latency
* to 0.
*
* BFQ is described in [1], where also a reference to the initial, more
* theoretical paper on BFQ can be found. The interested reader can find
* in the latter paper full details on the main algorithm, as well as
......
......@@ -1114,12 +1114,21 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
{
struct bfq_sched_data *sd = entity->sched_data;
struct bfq_service_tree *st = bfq_entity_service_tree(entity);
int is_in_service = entity == sd->in_service_entity;
struct bfq_service_tree *st;
bool is_in_service;
if (!entity->on_st) /* entity never activated, or already inactive */
return false;
/*
* If we get here, then entity is active, which implies that
* bfq_group_set_parent has already been invoked for the group
* represented by entity. Therefore, the field
* entity->sched_data has been set, and we can safely use it.
*/
st = bfq_entity_service_tree(entity);
is_in_service = entity == sd->in_service_entity;
if (is_in_service)
bfq_calc_finish(entity, entity->service);
......
......@@ -2644,8 +2644,6 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
return false;
}
WARN_ON_ONCE(req->rq_flags & RQF_SPECIAL_PAYLOAD);
req->__data_len -= total_bytes;
/* update sector only for requests with clear definition of sector */
......@@ -2658,17 +2656,19 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
}
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
}
if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
}
/* recalculate the number of segments */
blk_recalc_rq_segments(req);
/* recalculate the number of segments */
blk_recalc_rq_segments(req);
}
return true;
}
......
......@@ -1236,7 +1236,7 @@ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
{
struct blk_mq_hw_ctx *hctx;
int i;
......@@ -1554,13 +1554,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
blk_queue_split(q, &bio, q->bio_split);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
blk_queue_split(q, &bio, q->bio_split);
if (!is_flush_fua && !blk_queue_nomerges(q) &&
blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
return BLK_QC_T_NONE;
......@@ -2341,15 +2341,15 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
mutex_lock(&all_q_mutex);
get_online_cpus();
mutex_lock(&all_q_mutex);
list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q, cpu_online_mask);
put_online_cpus();
mutex_unlock(&all_q_mutex);
put_online_cpus();
if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
int ret;
......
......@@ -96,13 +96,16 @@ void blk_stat_add(struct request *rq)
rcu_read_lock();
list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
if (blk_stat_is_active(cb)) {
bucket = cb->bucket_fn(rq);
if (bucket < 0)
continue;
stat = &this_cpu_ptr(cb->cpu_stat)[bucket];
__blk_stat_add(stat, value);
}
if (!blk_stat_is_active(cb))
continue;
bucket = cb->bucket_fn(rq);
if (bucket < 0)
continue;
stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
__blk_stat_add(stat, value);
put_cpu_ptr(cb->cpu_stat);
}
rcu_read_unlock();
}
......
......@@ -1062,10 +1062,8 @@ static int __elevator_change(struct request_queue *q, const char *name)
strlcpy(elevator_name, name, sizeof(elevator_name));
e = elevator_get(strstrip(elevator_name), true);
if (!e) {
printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
if (!e)
return -EINVAL;
}
if (q->elevator &&
!strcmp(elevator_name, q->elevator->type->elevator_name)) {
......@@ -1105,7 +1103,6 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
if (!ret)
return count;
printk(KERN_ERR "elevator: switch to %s failed\n", name);
return ret;
}
......
......@@ -367,7 +367,8 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
if (unlikely(elba > nvmdev->total_secs)) {
pr_err("nvm: L2P data from device is out of bounds!\n");
return -EINVAL;
ret = -EINVAL;
goto out;
}
/* Transform physical address to target address space */
......@@ -464,8 +465,8 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas,
return ret;
}
static inline void nvme_nvm_rqtocmd(struct request *rq, struct nvm_rq *rqd,
struct nvme_ns *ns, struct nvme_nvm_command *c)
static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns,
struct nvme_nvm_command *c)
{
c->ph_rw.opcode = rqd->opcode;
c->ph_rw.nsid = cpu_to_le32(ns->ns_id);
......@@ -503,7 +504,7 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
if (!cmd)
return -ENOMEM;
nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
nvme_nvm_rqtocmd(rqd, ns, cmd);
rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0, NVME_QID_ANY);
if (IS_ERR(rq)) {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment