summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--block/bfq-iosched.c275
-rw-r--r--block/bfq-iosched.h14
-rw-r--r--block/bio.c61
-rw-r--r--block/blk-core.c22
-rw-r--r--block/blk-merge.c8
-rw-r--r--block/blk-mq-sched.c45
-rw-r--r--block/blk-mq-sched.h2
-rw-r--r--block/blk-mq-tag.c2
-rw-r--r--block/blk-mq.c2
-rw-r--r--block/blk-sysfs.c3
-rw-r--r--block/blk-throttle.c13
-rw-r--r--block/blk.h3
-rw-r--r--block/bounce.c49
-rw-r--r--block/elevator.c101
-rw-r--r--block/kyber-iosched.c190
-rw-r--r--drivers/block/drbd/drbd_bitmap.c4
-rw-r--r--drivers/block/drbd/drbd_int.h10
-rw-r--r--drivers/block/drbd/drbd_main.c71
-rw-r--r--drivers/block/drbd/drbd_receiver.c6
-rw-r--r--drivers/block/drbd/drbd_req.c4
-rw-r--r--drivers/block/drbd/drbd_req.h2
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c12
-rw-r--r--drivers/block/nbd.c26
-rw-r--r--drivers/block/pktcdvd.c50
-rw-r--r--drivers/lightnvm/pblk-core.c30
-rw-r--r--drivers/lightnvm/pblk-init.c72
-rw-r--r--drivers/lightnvm/pblk-read.c4
-rw-r--r--drivers/lightnvm/pblk-recovery.c2
-rw-r--r--drivers/lightnvm/pblk-write.c8
-rw-r--r--drivers/lightnvm/pblk.h14
-rw-r--r--drivers/md/bcache/bcache.h10
-rw-r--r--drivers/md/bcache/bset.c13
-rw-r--r--drivers/md/bcache/bset.h2
-rw-r--r--drivers/md/bcache/btree.c4
-rw-r--r--drivers/md/bcache/io.c4
-rw-r--r--drivers/md/bcache/request.c18
-rw-r--r--drivers/md/bcache/super.c38
-rw-r--r--drivers/md/dm-bio-prison-v1.c13
-rw-r--r--drivers/md/dm-bio-prison-v2.c13
-rw-r--r--drivers/md/dm-cache-target.c25
-rw-r--r--drivers/md/dm-core.h4
-rw-r--r--drivers/md/dm-crypt.c60
-rw-r--r--drivers/md/dm-integrity.c15
-rw-r--r--drivers/md/dm-io.c29
-rw-r--r--drivers/md/dm-kcopyd.c22
-rw-r--r--drivers/md/dm-log-userspace-base.c19
-rw-r--r--drivers/md/dm-region-hash.c23
-rw-r--r--drivers/md/dm-rq.c2
-rw-r--r--drivers/md/dm-snap.c17
-rw-r--r--drivers/md/dm-thin.c32
-rw-r--r--drivers/md/dm-verity-fec.c55
-rw-r--r--drivers/md/dm-verity-fec.h8
-rw-r--r--drivers/md/dm-zoned-target.c13
-rw-r--r--drivers/md/dm.c55
-rw-r--r--drivers/md/md-faulty.c2
-rw-r--r--drivers/md/md-linear.c2
-rw-r--r--drivers/md/md-multipath.c17
-rw-r--r--drivers/md/md-multipath.h2
-rw-r--r--drivers/md/md.c61
-rw-r--r--drivers/md/md.h4
-rw-r--r--drivers/md/raid0.c5
-rw-r--r--drivers/md/raid1.c76
-rw-r--r--drivers/md/raid1.h6
-rw-r--r--drivers/md/raid10.c60
-rw-r--r--drivers/md/raid10.h6
-rw-r--r--drivers/md/raid5-cache.c43
-rw-r--r--drivers/md/raid5-ppl.c42
-rw-r--r--drivers/md/raid5.c12
-rw-r--r--drivers/md/raid5.h2
-rw-r--r--drivers/nvme/host/core.c3
-rw-r--r--drivers/nvme/host/fc.c3
-rw-r--r--drivers/target/target_core_iblock.c14
-rw-r--r--drivers/target/target_core_iblock.h2
-rw-r--r--fs/block_dev.c9
-rw-r--r--fs/btrfs/extent_io.c25
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_aops.h2
-rw-r--r--fs/xfs/xfs_super.c11
-rw-r--r--include/linux/bio.h11
-rw-r--r--include/linux/blk-mq.h3
-rw-r--r--include/linux/blkdev.h2
-rw-r--r--include/linux/elevator.h2
-rw-r--r--include/linux/pktcdvd.h2
83 files changed, 1002 insertions, 1028 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b622e73a326a..495b9ddb3355 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -49,9 +49,39 @@
*
* In particular, to provide these low-latency guarantees, BFQ
* explicitly privileges the I/O of two classes of time-sensitive
- * applications: interactive and soft real-time. This feature enables
- * BFQ to provide applications in these classes with a very low
- * latency. Finally, BFQ also features additional heuristics for
+ * applications: interactive and soft real-time. In more detail, BFQ
+ * behaves this way if the low_latency parameter is set (default
+ * configuration). This feature enables BFQ to provide applications in
+ * these classes with a very low latency.
+ *
+ * To implement this feature, BFQ constantly tries to detect whether
+ * the I/O requests in a bfq_queue come from an interactive or a soft
+ * real-time application. For brevity, in these cases, the queue is
+ * said to be interactive or soft real-time. In both cases, BFQ
+ * privileges the service of the queue, over that of non-interactive
+ * and non-soft-real-time queues. This privileging is performed,
+ * mainly, by raising the weight of the queue. So, for brevity, we
+ * call just weight-raising periods the time periods during which a
+ * queue is privileged, because deemed interactive or soft real-time.
+ *
+ * The detection of soft real-time queues/applications is described in
+ * detail in the comments on the function
+ * bfq_bfqq_softrt_next_start. On the other hand, the detection of an
+ * interactive queue works as follows: a queue is deemed interactive
+ * if it is constantly non empty only for a limited time interval,
+ * after which it does become empty. The queue may be deemed
+ * interactive again (for a limited time), if it restarts being
+ * constantly non empty, provided that this happens only after the
+ * queue has remained empty for a given minimum idle time.
+ *
+ * By default, BFQ computes automatically the above maximum time
+ * interval, i.e., the time interval after which a constantly
+ * non-empty queue stops being deemed interactive. Since a queue is
+ * weight-raised while it is deemed interactive, this maximum time
+ * interval happens to coincide with the (maximum) duration of the
+ * weight-raising for interactive queues.
+ *
+ * Finally, BFQ also features additional heuristics for
* preserving both a low latency and a high throughput on NCQ-capable,
* rotational or flash-based devices, and to get the job done quickly
* for applications consisting in many I/O-bound processes.
@@ -61,14 +91,14 @@
* 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
- * formulas of the guarantees and formal proofs of all the properties.
- * With respect to the version of BFQ presented in these papers, this
- * implementation adds a few more heuristics, such as the one that
- * guarantees a low latency to soft real-time applications, and a
- * hierarchical extension based on H-WF2Q+.
+ * 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 formulas of the guarantees and formal proofs of all the
+ * properties. With respect to the version of BFQ presented in these
+ * papers, this implementation adds a few more heuristics, such as the
+ * ones that guarantee a low latency to interactive and soft real-time
+ * applications, and a hierarchical extension based on H-WF2Q+.
*
* B-WF2Q+ is based on WF2Q+, which is described in [2], together with
* H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
@@ -218,56 +248,46 @@ static struct kmem_cache *bfq_pool;
#define BFQ_RATE_SHIFT 16
/*
- * By default, BFQ computes the duration of the weight raising for
- * interactive applications automatically, using the following formula:
- * duration = (R / r) * T, where r is the peak rate of the device, and
- * R and T are two reference parameters.
- * In particular, R is the peak rate of the reference device (see
- * below), and T is a reference time: given the systems that are
- * likely to be installed on the reference device according to its
- * speed class, T is about the maximum time needed, under BFQ and
- * while reading two files in parallel, to load typical large
- * applications on these systems (see the comments on
- * max_service_from_wr below, for more details on how T is obtained).
- * In practice, the slower/faster the device at hand is, the more/less
- * it takes to load applications with respect to the reference device.
- * Accordingly, the longer/shorter BFQ grants weight raising to
- * interactive applications.
+ * When configured for computing the duration of the weight-raising
+ * for interactive queues automatically (see the comments at the
+ * beginning of this file), BFQ does it using the following formula:
+ * duration = (ref_rate / r) * ref_wr_duration,
+ * where r is the peak rate of the device, and ref_rate and
+ * ref_wr_duration are two reference parameters. In particular,
+ * ref_rate is the peak rate of the reference storage device (see
+ * below), and ref_wr_duration is about the maximum time needed, with
+ * BFQ and while reading two files in parallel, to load typical large
+ * applications on the reference device (see the comments on
+ * max_service_from_wr below, for more details on how ref_wr_duration
+ * is obtained). In practice, the slower/faster the device at hand
+ * is, the more/less it takes to load applications with respect to the
+ * reference device. Accordingly, the longer/shorter BFQ grants
+ * weight raising to interactive applications.
*
- * BFQ uses four different reference pairs (R, T), depending on:
- * . whether the device is rotational or non-rotational;
- * . whether the device is slow, such as old or portable HDDs, as well as
- * SD cards, or fast, such as newer HDDs and SSDs.
+ * BFQ uses two different reference pairs (ref_rate, ref_wr_duration),
+ * depending on whether the device is rotational or non-rotational.
*
- * The device's speed class is dynamically (re)detected in
- * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ * In the following definitions, ref_rate[0] and ref_wr_duration[0]
+ * are the reference values for a rotational device, whereas
+ * ref_rate[1] and ref_wr_duration[1] are the reference values for a
+ * non-rotational device. The reference rates are not the actual peak
+ * rates of the devices used as a reference, but slightly lower
+ * values. The reason for using slightly lower values is that the
+ * peak-rate estimator tends to yield slightly lower values than the
+ * actual peak rate (it can yield the actual peak rate only if there
+ * is only one process doing I/O, and the process does sequential
+ * I/O).
*
- * In the following definitions, R_slow[0]/R_fast[0] and
- * T_slow[0]/T_fast[0] are the reference values for a slow/fast
- * rotational device, whereas R_slow[1]/R_fast[1] and
- * T_slow[1]/T_fast[1] are the reference values for a slow/fast
- * non-rotational device. Finally, device_speed_thresh are the
- * thresholds used to switch between speed classes. The reference
- * rates are not the actual peak rates of the devices used as a
- * reference, but slightly lower values. The reason for using these
- * slightly lower values is that the peak-rate estimator tends to
- * yield slightly lower values than the actual peak rate (it can yield
- * the actual peak rate only if there is only one process doing I/O,
- * and the process does sequential I/O).
- *
- * Both the reference peak rates and the thresholds are measured in
- * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ * The reference peak rates are measured in sectors/usec, left-shifted
+ * by BFQ_RATE_SHIFT.
*/
-static int R_slow[2] = {1000, 10700};
-static int R_fast[2] = {14000, 33000};
+static int ref_rate[2] = {14000, 33000};
/*
- * To improve readability, a conversion function is used to initialize the
- * following arrays, which entails that they can be initialized only in a
- * function.
+ * To improve readability, a conversion function is used to initialize
+ * the following array, which entails that the array can be
+ * initialized only in a function.
*/
-static int T_slow[2];
-static int T_fast[2];
-static int device_speed_thresh[2];
+static int ref_wr_duration[2];
/*
* BFQ uses the above-detailed, time-based weight-raising mechanism to
@@ -852,26 +872,30 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
if (bfqd->bfq_wr_max_time > 0)
return bfqd->bfq_wr_max_time;
- dur = bfqd->RT_prod;
+ dur = bfqd->rate_dur_prod;
do_div(dur, bfqd->peak_rate);
/*
- * Limit duration between 3 and 13 seconds. Tests show that
- * higher values than 13 seconds often yield the opposite of
- * the desired result, i.e., worsen responsiveness by letting
- * non-interactive and non-soft-real-time applications
- * preserve weight raising for a too long time interval.
+ * Limit duration between 3 and 25 seconds. The upper limit
+ * has been conservatively set after the following worst case:
+ * on a QEMU/KVM virtual machine
+ * - running in a slow PC
+ * - with a virtual disk stacked on a slow low-end 5400rpm HDD
+ * - serving a heavy I/O workload, such as the sequential reading
+ * of several files
+ * mplayer took 23 seconds to start, if constantly weight-raised.
+ *
+ * As for higher values than that accomodating the above bad
+ * scenario, tests show that higher values would often yield
+ * the opposite of the desired result, i.e., would worsen
+ * responsiveness by allowing non-interactive applications to
+ * preserve weight raising for too long.
*
* On the other end, lower values than 3 seconds make it
* difficult for most interactive tasks to complete their jobs
* before weight-raising finishes.
*/
- if (dur > msecs_to_jiffies(13000))
- dur = msecs_to_jiffies(13000);
- else if (dur < msecs_to_jiffies(3000))
- dur = msecs_to_jiffies(3000);
-
- return dur;
+ return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000));
}
/* switch back from soft real-time to interactive weight raising */
@@ -1339,15 +1363,6 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
}
/*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
- return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
* Return the farthest past time instant according to jiffies
* macros.
*/
@@ -1491,7 +1506,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
in_burst = bfq_bfqq_in_large_burst(bfqq);
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
!in_burst &&
- time_is_before_jiffies(bfqq->soft_rt_next_start);
+ time_is_before_jiffies(bfqq->soft_rt_next_start) &&
+ bfqq->dispatched == 0;
*interactive = !in_burst && idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
@@ -1839,16 +1855,26 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
}
}
+/*
+ * This function is called to notify the scheduler that the requests
+ * rq and 'next' have been merged, with 'next' going away. BFQ
+ * exploits this hook to address the following issue: if 'next' has a
+ * fifo_time lower that rq, then the fifo_time of rq must be set to
+ * the value of 'next', to not forget the greater age of 'next'.
+ *
+ * NOTE: in this function we assume that rq is in a bfq_queue, basing
+ * on that rq is picked from the hash table q->elevator->hash, which,
+ * in its turn, is filled only with I/O requests present in
+ * bfq_queues, while BFQ is in use for the request queue q. In fact,
+ * the function that fills this hash table (elv_rqhash_add) is called
+ * only by bfq_insert_request.
+ */
static void bfq_requests_merged(struct request_queue *q, struct request *rq,
struct request *next)
{
struct bfq_queue *bfqq = bfq_init_rq(rq),
*next_bfqq = bfq_init_rq(next);
- if (!RB_EMPTY_NODE(&rq->rb_node))
- goto end;
- spin_lock_irq(&bfqq->bfqd->lock);
-
/*
* If next and rq belong to the same bfq_queue and next is older
* than rq, then reposition rq in the fifo (by substituting next
@@ -1869,11 +1895,6 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
if (bfqq->next_rq == next)
bfqq->next_rq = rq;
- bfq_remove_request(q, next);
- bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
-
- spin_unlock_irq(&bfqq->bfqd->lock);
-end:
bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
}
@@ -2455,37 +2476,15 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
/*
* Update parameters related to throughput and responsiveness, as a
* function of the estimated peak rate. See comments on
- * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ * bfq_calc_max_budget(), and on the ref_wr_duration array.
*/
static void update_thr_responsiveness_params(struct bfq_data *bfqd)
{
- int dev_type = blk_queue_nonrot(bfqd->queue);
-
- if (bfqd->bfq_user_max_budget == 0)
+ if (bfqd->bfq_user_max_budget == 0) {
bfqd->bfq_max_budget =
bfq_calc_max_budget(bfqd);
-
- if (bfqd->device_speed == BFQ_BFQD_FAST &&
- bfqd->peak_rate < device_speed_thresh[dev_type]) {
- bfqd->device_speed = BFQ_BFQD_SLOW;
- bfqd->RT_prod = R_slow[dev_type] *
- T_slow[dev_type];
- } else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
- bfqd->peak_rate > device_speed_thresh[dev_type]) {
- bfqd->device_speed = BFQ_BFQD_FAST;
- bfqd->RT_prod = R_fast[dev_type] *
- T_fast[dev_type];
+ bfq_log(bfqd, "new max_budget = %d", bfqd->bfq_max_budget);
}
-
- bfq_log(bfqd,
-"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
- dev_type == 0 ? "ROT" : "NONROT",
- bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
- bfqd->device_speed == BFQ_BFQD_FAST ?
- (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
- (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
- (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
- BFQ_RATE_SHIFT);
}
static void bfq_reset_rate_computation(struct bfq_data *bfqd,
@@ -3215,23 +3214,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
bfq_bfqq_softrt_next_start(bfqd, bfqq);
else {
/*
- * The application is still waiting for the
- * completion of one or more requests:
- * prevent it from possibly being incorrectly
- * deemed as soft real-time by setting its
- * soft_rt_next_start to infinity. In fact,
- * without this assignment, the application
- * would be incorrectly deemed as soft
- * real-time if:
- * 1) it issued a new request before the
- * completion of all its in-flight
- * requests, and
- * 2) at that time, its soft_rt_next_start
- * happened to be in the past.
- */
- bfqq->soft_rt_next_start =
- bfq_greatest_from_now();
- /*
* Schedule an update of soft_rt_next_start to when
* the task may be discovered to be isochronous.
*/
@@ -5274,14 +5256,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->wr_busy_queues = 0;
/*
- * Begin by assuming, optimistically, that the device is a
- * high-speed one, and that its peak rate is equal to 2/3 of
- * the highest reference rate.
+ * Begin by assuming, optimistically, that the device peak
+ * rate is equal to 2/3 of the highest reference rate.
*/
- bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
- T_fast[blk_queue_nonrot(bfqd->queue)];
- bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
- bfqd->device_speed = BFQ_BFQD_FAST;
+ bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] *
+ ref_wr_duration[blk_queue_nonrot(bfqd->queue)];
+ bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
spin_lock_init(&bfqd->lock);
@@ -5589,8 +5569,8 @@ static int __init bfq_init(void)
/*
* Times to load large popular applications for the typical
* systems installed on the reference devices (see the
- * comments before the definitions of the next two
- * arrays). Actually, we use slightly slower values, as the
+ * comments before the definition of the next
+ * array). Actually, we use slightly lower values, as the
* estimated peak rate tends to be smaller than the actual
* peak rate. The reason for this last fact is that estimates
* are computed over much shorter time intervals than the long
@@ -5599,25 +5579,8 @@ static int __init bfq_init(void)
* scheduler cannot rely on a peak-rate-evaluation workload to
* be run for a long time.
*/
- T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
- T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
- T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
- T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
-
- /*
- * Thresholds that determine the switch between speed classes
- * (see the comments before the definition of the array
- * device_speed_thresh). These thresholds are biased towards
- * transitions to the fast class. This is safer than the
- * opposite bias. In fact, a wrong transition to the slow
- * class results in short weight-raising periods, because the
- * speed of the device then tends to be higher that the
- * reference peak rate. On the opposite end, a wrong
- * transition to the fast class tends to increase
- * weight-raising periods, because of the opposite reason.
- */
- device_speed_thresh[0] = (4 * R_slow[0]) / 3;
- device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+ ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+ ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */
ret = elv_register(&iosched_bfq_mq);
if (ret)
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index faac509cb35e..0f712e03b035 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -399,11 +399,6 @@ struct bfq_io_cq {
struct bfq_ttime saved_ttime;
};
-enum bfq_device_speed {
- BFQ_BFQD_FAST,
- BFQ_BFQD_SLOW,
-};
-
/**
* struct bfq_data - per-device data structure.
*
@@ -611,12 +606,11 @@ struct bfq_data {
/* Max service-rate for a soft real-time queue, in sectors/sec */
unsigned int bfq_wr_max_softrt_rate;
/*
- * Cached value of the product R*T, used for computing the
- * maximum duration of weight raising automatically.
+ * Cached value of the product ref_rate*ref_wr_duration, used
+ * for computing the maximum duration of weight raising
+ * automatically.
*/
- u64 RT_prod;
- /* device-speed class for the low-latency heuristic */
- enum bfq_device_speed device_speed;
+ u64 rate_dur_prod;
/* fallback dummy bfqq for extreme OOM conditions */
struct bfq_queue oom_bfqq;
diff --git a/block/bio.c b/block/bio.c
index 0a4df92cd689..595663e0281a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1908,22 +1908,26 @@ void bioset_exit(struct bio_set *bs)
}
EXPORT_SYMBOL(bioset_exit);
-void bioset_free(struct bio_set *bs)
-{
- bioset_exit(bs);
- kfree(bs);
-}
-EXPORT_SYMBOL(bioset_free);
-
/**
* bioset_init - Initialize a bio_set
+ * @bs: pool to initialize
* @pool_size: Number of bio and bio_vecs to cache in the mempool
* @front_pad: Number of bytes to allocate in front of the returned bio
* @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
* and %BIOSET_NEED_RESCUER
*
- * Similar to bioset_create(), but initializes a passed-in bioset instead of
- * separately allocating it.
+ * Description:
+ * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ * to ask for a number of bytes to be allocated in front of the bio.
+ * Front pad allocation is useful for embedding the bio inside
+ * another structure, to avoid allocating extra data to go with the bio.
+ * Note that the bio must be embedded at the END of that structure always,
+ * or things will break badly.
+ * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
+ * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast().
+ * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
+ * dispatch queued requests when the mempool runs out of space.
+ *
*/
int bioset_init(struct bio_set *bs,
unsigned int pool_size,
@@ -1963,45 +1967,6 @@ bad:
}
EXPORT_SYMBOL(bioset_init);
-/**
- * bioset_create - Create a bio_set
- * @pool_size: Number of bio and bio_vecs to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
- * and %BIOSET_NEED_RESCUER
- *
- * Description:
- * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- * to ask for a number of bytes to be allocated in front of the bio.
- * Front pad allocation is useful for embedding the bio inside
- * another structure, to avoid allocating extra data to go with the bio.
- * Note that the bio must be embedded at the END of that structure always,
- * or things will break badly.
- * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
- * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast().
- * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
- * dispatch queued requests when the mempool runs out of space.
- *
- */
-struct bio_set *bioset_create(unsigned int pool_size,
- unsigned int front_pad,
- int flags)
-{
- struct bio_set *bs;
-
- bs = kzalloc(sizeof(*bs), GFP_KERNEL);
- if (!bs)
- return NULL;
-
- if (bioset_init(bs, pool_size, front_pad, flags)) {
- kfree(bs);
- return NULL;
- }
-
- return bs;
-}
-EXPORT_SYMBOL(bioset_create);
-
#ifdef CONFIG_BLK_CGROUP
/**
diff --git a/block/blk-core.c b/block/blk-core.c
index cee03cad99f2..cd573a33a6f3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -992,18 +992,24 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
spinlock_t *lock)
{
struct request_queue *q;
+ int ret;
q = kmem_cache_alloc_node(blk_requestq_cachep,
gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
+ INIT_LIST_HEAD(&q->queue_head);
+ q->last_merge = NULL;
+ q->end_sector = 0;
+ q->boundary_rq = NULL;
+
q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
if (q->id < 0)
goto fail_q;
- q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!q->bio_split)
+ ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto fail_id;
q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
@@ -1075,7 +1081,7 @@ fail_bdi:
fail_stats:
bdi_put(q->backing_dev_info);
fail_split:
- bioset_free(q->bio_split);
+ bioset_exit(&q->bio_split);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
@@ -1169,16 +1175,8 @@ int blk_init_allocated_queue(struct request_queue *q)
q->sg_reserved_size = INT_MAX;
- /* Protect q->elevator from elevator_change */
- mutex_lock(&q->sysfs_lock);
-
- /* init elevator */
- if (elevator_init(q, NULL)) {
- mutex_unlock(&q->sysfs_lock);
+ if (elevator_init(q))
goto out_exit_flush_rq;
- }
-
- mutex_unlock(&q->sysfs_lock);
return 0;
out_exit_flush_rq:
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 5573d0fbec53..d70ab08820e5 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -188,16 +188,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
- split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_ZEROES:
- split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_SAME:
- split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs);
break;
default:
- split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs);
break;
}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 25c14c58385c..b1f06088cee5 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -268,19 +268,16 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
*/
-static bool blk_mq_attempt_merge(struct request_queue *q,
- struct blk_mq_ctx *ctx, struct bio *bio)
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+ struct bio *bio)
{
struct request *rq;
int checked = 8;
- lockdep_assert_held(&ctx->lock);
-
- list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+ list_for_each_entry_reverse(rq, list, queuelist) {
bool merged = false;
if (!checked--)
@@ -305,13 +302,30 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
continue;
}
- if (merged)
- ctx->rq_merged++;
return merged;
}
return false;
}
+EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
+
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+ struct blk_mq_ctx *ctx, struct bio *bio)
+{
+ lockdep_assert_held(&ctx->lock);
+
+ if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) {
+ ctx->rq_merged++;
+ return true;
+ }
+
+ return false;
+}
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
@@ -633,14 +647,3 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
blk_mq_sched_tags_teardown(q);
q->elevator = NULL;
}
-
-int blk_mq_sched_init(struct request_queue *q)
-{
- int ret;
-
- mutex_lock(&q->sysfs_lock);
- ret = elevator_init(q, NULL);
- mutex_unlock(&q->sysfs_lock);
-
- return ret;
-}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 1e9c9018ace1..0cb8f938dff9 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -33,8 +33,6 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx);
-int blk_mq_sched_init(struct request_queue *q);
-
static inline bool
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index a4e58fc28a06..70356a2a11ab 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
* test and set the bit before assining ->rqs[].
*/
rq = tags->rqs[bitnr];
- if (rq)
+ if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
iter_data->fn(rq, iter_data->data, reserved);
return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3d3952301b3e..6332940ca118 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2573,7 +2573,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
int ret;
- ret = blk_mq_sched_init(q);
+ ret = elevator_init_mq(q);
if (ret)
return ERR_PTR(ret);
}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 31347e31daa3..94987b1f69e1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -824,8 +824,7 @@ static void __blk_release_queue(struct work_struct *work)
if (q->mq_ops)
blk_mq_debugfs_unregister(q);
- if (q->bio_split)
- bioset_free(q->bio_split);
+ bioset_exit(&q->bio_split);
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index f63d88c92c3a..82282e6fdcf8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -819,7 +819,7 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
return false;
- return 1;
+ return true;
}
/* Trim the used slices and adjust slice start accordingly */
@@ -929,7 +929,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
if (wait)
*wait = jiffy_wait;
- return 0;
+ return false;
}
static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
@@ -972,7 +972,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
if (wait)
*wait = jiffy_wait;
- return 0;
+ return false;
}
/*
@@ -1022,7 +1022,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
tg_with_in_iops_limit(tg, bio, &iops_wait)) {
if (wait)
*wait = 0;
- return 1;
+ return true;
}
max_wait = max(bps_wait, iops_wait);
@@ -1033,7 +1033,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
if (time_before(tg->slice_end[rw], jiffies + max_wait))
throtl_extend_slice(tg, rw, jiffies + max_wait);
- return 0;
+ return false;
}
static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
@@ -1207,7 +1207,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
while (1) {
struct throtl_grp *tg = throtl_rb_first(parent_sq);
- struct throtl_service_queue *sq = &tg->service_queue;
+ struct throtl_service_queue *sq;
if (!tg)
break;
@@ -1219,6 +1219,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
nr_disp += throtl_dispatch_tg(tg);
+ sq = &tg->service_queue;
if (sq->nr_queued[0] || sq->nr_queued[1])
tg_update_disptime(tg);
diff --git a/block/blk.h b/block/blk.h
index eaf1a8e87d11..8d23aea96ce9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -231,6 +231,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
}
+int elevator_init(struct request_queue *);
+int elevator_init_mq(struct request_queue *q);
+void elevator_exit(struct request_queue *, struct elevator_queue *);
int elv_register_queue(struct request_queue *q);
void elv_unregister_queue(struct request_queue *q);
diff --git a/block/bounce.c b/block/bounce.c
index fea9c8146d82..fd31347b7836 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -28,28 +28,29 @@
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
-static struct bio_set *bounce_bio_set, *bounce_bio_split;
-static mempool_t *page_pool, *isa_page_pool;
+static struct bio_set bounce_bio_set, bounce_bio_split;
+static mempool_t page_pool, isa_page_pool;
#if defined(CONFIG_HIGHMEM)
static __init int init_emergency_pool(void)
{
+ int ret;
#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
if (max_pfn <= max_low_pfn)
return 0;
#endif
- page_pool = mempool_create_page_pool(POOL_SIZE, 0);
- BUG_ON(!page_pool);
+ ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0);
+ BUG_ON(ret);
pr_info("pool size: %d pages\n", POOL_SIZE);
- bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- BUG_ON(!bounce_bio_set);
- if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+ ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ BUG_ON(ret);
+ if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE))
BUG_ON(1);
- bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- BUG_ON(!bounce_bio_split);
+ ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0);
+ BUG_ON(ret);
return 0;
}
@@ -91,12 +92,14 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
*/
int init_emergency_isa_pool(void)
{
- if (isa_page_pool)
+ int ret;
+
+ if (mempool_initialized(&isa_page_pool))
return 0;
- isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
- mempool_free_pages, (void *) 0);
- BUG_ON(!isa_page_pool);
+ ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa,
+ mempool_free_pages, (void *) 0);
+ BUG_ON(ret);
pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
return 0;
@@ -163,13 +166,13 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
static void bounce_end_io_write(struct bio *bio)
{
- bounce_end_io(bio, page_pool);
+ bounce_end_io(bio, &page_pool);
}
static void bounce_end_io_write_isa(struct bio *bio)
{
- bounce_end_io(bio, isa_page_pool);
+ bounce_end_io(bio, &isa_page_pool);
}
static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
@@ -184,12 +187,12 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
static void bounce_end_io_read(struct bio *bio)
{
- __bounce_end_io_read(bio, page_pool);
+ __bounce_end_io_read(bio, &page_pool);
}
static void bounce_end_io_read_isa(struct bio *bio)
{
- __bounce_end_io_read(bio, isa_page_pool);
+ __bounce_end_io_read(bio, &isa_page_pool);
}
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
@@ -214,13 +217,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
return;
if (!passthrough && sectors < bio_sectors(*bio_orig)) {
- bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+ bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
bio_chain(bio, *bio_orig);
generic_make_request(*bio_orig);
*bio_orig = bio;
}
bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
- bounce_bio_set);
+ &bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
@@ -247,7 +250,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
bio->bi_flags |= (1 << BIO_BOUNCED);
- if (pool == page_pool) {
+ if (pool == &page_pool) {
bio->bi_end_io = bounce_end_io_write;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read;
@@ -279,10 +282,10 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
if (!(q->bounce_gfp & GFP_DMA)) {
if (q->limits.bounce_pfn >= blk_max_pfn)
return;
- pool = page_pool;
+ pool = &page_pool;
} else {
- BUG_ON(!isa_page_pool);
- pool = isa_page_pool;
+ BUG_ON(!mempool_initialized(&isa_page_pool));
+ pool = &isa_page_pool;
}
/*
diff --git a/block/elevator.c b/block/elevator.c
index e87e9b43aba0..fa828b5bfd4b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -199,76 +199,46 @@ static void elevator_release(struct kobject *kobj)
kfree(e);
}
-int elevator_init(struct request_queue *q, char *name)
+/*
+ * Use the default elevator specified by config boot param for non-mq devices,
+ * or by config option. Don't try to load modules as we could be running off
+ * async and request_module() isn't allowed from async.
+ */
+int elevator_init(struct request_queue *q)
{
struct elevator_type *e = NULL;
- int err;
+ int err = 0;
/*
* q->sysfs_lock must be held to provide mutual exclusion between
* elevator_switch() and here.
*/
- lockdep_assert_held(&q->sysfs_lock);
-
+ mutex_lock(&q->sysfs_lock);
if (unlikely(q->elevator))
- return 0;
-
- INIT_LIST_HEAD(&q->queue_head);
- q->last_merge = NULL;
- q->end_sector = 0;
- q->boundary_rq = NULL;
-
- if (name) {
- e = elevator_get(q, name, true);
- if (!e)
- return -EINVAL;
- }
+ goto out_unlock;
- /*
- * Use the default elevator specified by config boot param for
- * non-mq devices, or by config option. Don't try to load modules
- * as we could be running off async and request_module() isn't
- * allowed from async.
- */
- if (!e && !q->mq_ops && *chosen_elevator) {
+ if (*chosen_elevator) {
e = elevator_get(q, chosen_elevator, false);
if (!e)
printk(KERN_ERR "I/O scheduler %s not found\n",
chosen_elevator);
}
+ if (!e)
+ e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
if (!e) {
- /*
- * For blk-mq devices, we default to using mq-deadline,
- * if available, for single queue devices. If deadline
- * isn't available OR we have multiple queues, default
- * to "none".
- */
- if (q->mq_ops) {
- if (q->nr_hw_queues == 1)
- e = elevator_get(q, "mq-deadline", false);
- if (!e)
- return 0;
- } else
- e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
-
- if (!e) {
- printk(KERN_ERR
- "Default I/O scheduler not found. " \
- "Using noop.\n");
- e = elevator_get(q, "noop", false);
- }
+ printk(KERN_ERR
+ "Default I/O scheduler not found. Using noop.\n");
+ e = elevator_get(q, "noop", false);
}
- if (e->uses_mq)
- err = blk_mq_init_sched(q, e);
- else
- err = e->ops.sq.elevator_init_fn(q, e);
+ err = e->ops.sq.elevator_init_fn(q, e);
if (err)
elevator_put(e);
+out_unlock:
+ mutex_unlock(&q->sysfs_lock);
return err;
}
-EXPORT_SYMBOL(elevator_init);
void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
@@ -281,7 +251,6 @@ void elevator_exit(struct request_queue *q, struct elevator_queue *e)
kobject_put(&e->kobj);
}
-EXPORT_SYMBOL(elevator_exit);
static inline void __elv_rqhash_del(struct request *rq)
{
@@ -1005,6 +974,40 @@ out:
}
/*
+ * For blk-mq devices, we default to using mq-deadline, if available, for single
+ * queue devices. If deadline isn't available OR we have multiple queues,
+ * default to "none".
+ */
+int elevator_init_mq(struct request_queue *q)
+{
+ struct elevator_type *e;
+ int err = 0;
+
+ if (q->nr_hw_queues != 1)
+ return 0;
+
+ /*
+ * q->sysfs_lock must be held to provide mutual exclusion between
+ * elevator_switch() and here.
+ */
+ mutex_lock(&q->sysfs_lock);
+ if (unlikely(q->elevator))
+ goto out_unlock;
+
+ e = elevator_get(q, "mq-deadline", false);
+ if (!e)
+ goto out_unlock;
+
+ err = blk_mq_init_sched(q, e);
+ if (err)
+ elevator_put(e);
+out_unlock:
+ mutex_unlock(&q->sysfs_lock);
+ return err;
+}
+
+
+/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
* need for the new one. this way we have a chance of going back to the old
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 5b33dc394cc7..a1660bafc912 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -72,6 +72,19 @@ static const unsigned int kyber_batch_size[] = {
[KYBER_OTHER] = 8,
};
+/*
+ * There is a same mapping between ctx & hctx and kcq & khd,
+ * we use request->mq_ctx->index_hw to index the kcq in khd.
+ */
+struct kyber_ctx_queue {
+ /*
+ * Used to ensure operations on rq_list and kcq_map to be an atmoic one.
+ * Also protect the rqs on rq_list when merge.
+ */
+ spinlock_t lock;
+ struct list_head rq_list[KYBER_NUM_DOMAINS];
+} ____cacheline_aligned_in_smp;
+
struct kyber_queue_data {
struct request_queue *q;
@@ -99,6 +112,8 @@ struct kyber_hctx_data {
struct list_head rqs[KYBER_NUM_DOMAINS];
unsigned int cur_domain;
unsigned int batching;
+ struct kyber_ctx_queue *kcqs;
+ struct sbitmap kcq_map[KYBER_NUM_DOMAINS];
wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS];
atomic_t wait_index[KYBER_NUM_DOMAINS];
@@ -107,10 +122,8 @@ struct kyber_hctx_data {
static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
void *key);
-static int rq_sched_domain(const struct request *rq)
+static unsigned int kyber_sched_domain(unsigned int op)
{
- unsigned int op = rq->cmd_flags;
-
if ((op & REQ_OP_MASK) == REQ_OP_READ)
return KYBER_READ;
else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
@@ -284,6 +297,11 @@ static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
}
+static int kyber_bucket_fn(const struct request *rq)
+{
+ return kyber_sched_domain(rq->cmd_flags);
+}
+
static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
{
struct kyber_queue_data *kqd;
@@ -297,7 +315,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
goto err;
kqd->q = q;
- kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+ kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, kyber_bucket_fn,
KYBER_NUM_DOMAINS, kqd);
if (!kqd->cb)
goto err_kqd;
@@ -376,6 +394,15 @@ static void kyber_exit_sched(struct elevator_queue *e)
kfree(kqd);
}
+static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq)
+{
+ unsigned int i;
+
+ spin_lock_init(&kcq->lock);
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+ INIT_LIST_HEAD(&kcq->rq_list[i]);
+}
+
static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
@@ -386,6 +413,24 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
if (!khd)
return -ENOMEM;
+ khd->kcqs = kmalloc_array_node(hctx->nr_ctx,
+ sizeof(struct kyber_ctx_queue),
+ GFP_KERNEL, hctx->numa_node);
+ if (!khd->kcqs)
+ goto err_khd;
+
+ for (i = 0; i < hctx->nr_ctx; i++)
+ kyber_ctx_queue_init(&khd->kcqs[i]);
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx,
+ ilog2(8), GFP_KERNEL, hctx->numa_node)) {
+ while (--i >= 0)
+ sbitmap_free(&khd->kcq_map[i]);
+ goto err_kcqs;
+ }
+ }
+
spin_lock_init(&khd->lock);
for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
@@ -405,10 +450,22 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
kqd->async_depth);
return 0;
+
+err_kcqs:
+ kfree(khd->kcqs);
+err_khd:
+ kfree(khd);
+ return -ENOMEM;
}
static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ int i;
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+ sbitmap_free(&khd->kcq_map[i]);
+ kfree(khd->kcqs);
kfree(hctx->sched_data);
}
@@ -430,7 +487,7 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
nr = rq_get_domain_token(rq);
if (nr != -1) {
- sched_domain = rq_sched_domain(rq);
+ sched_domain = kyber_sched_domain(rq->cmd_flags);
sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
rq->mq_ctx->cpu);
}
@@ -449,11 +506,51 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
}
}
+static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue);
+ struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw];
+ unsigned int sched_domain = kyber_sched_domain(bio->bi_opf);
+ struct list_head *rq_list = &kcq->rq_list[sched_domain];
+ bool merged;
+
+ spin_lock(&kcq->lock);
+ merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio);
+ spin_unlock(&kcq->lock);
+ blk_mq_put_ctx(ctx);
+
+ return merged;
+}
+
static void kyber_prepare_request(struct request *rq, struct bio *bio)
{
rq_set_domain_token(rq, -1);
}
+static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
+ struct list_head *rq_list, bool at_head)
+{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ struct request *rq, *next;
+
+ list_for_each_entry_safe(rq, next, rq_list, queuelist) {
+ unsigned int sched_domain = kyber_sched_domain(rq->cmd_flags);
+ struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw];
+ struct list_head *head = &kcq->rq_list[sched_domain];
+
+ spin_lock(&kcq->lock);
+ if (at_head)
+ list_move(&rq->queuelist, head);
+ else
+ list_move_tail(&rq->queuelist, head);
+ sbitmap_set_bit(&khd->kcq_map[sched_domain],
+ rq->mq_ctx->index_hw);
+ blk_mq_sched_request_inserted(rq);
+ spin_unlock(&kcq->lock);
+ }
+}
+
static void kyber_finish_request(struct request *rq)
{
struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
@@ -472,7 +569,7 @@ static void kyber_completed_request(struct request *rq)
* Check if this request met our latency goal. If not, quickly gather
* some statistics and start throttling.
*/
- sched_domain = rq_sched_domain(rq);
+ sched_domain = kyber_sched_domain(rq->cmd_flags);
switch (sched_domain) {
case KYBER_READ:
target = kqd->read_lat_nsec;
@@ -498,19 +595,38 @@ static void kyber_completed_request(struct request *rq)
blk_stat_activate_msecs(kqd->cb, 10);
}
-static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
- struct blk_mq_hw_ctx *hctx)
+struct flush_kcq_data {
+ struct kyber_hctx_data *khd;
+ unsigned int sched_domain;
+ struct list_head *list;
+};
+
+static bool flush_busy_kcq(struct sbitmap *sb, unsigned int bitnr, void *data)
{
- LIST_HEAD(rq_list);
- struct request *rq, *next;
+ struct flush_kcq_data *flush_data = data;
+ struct kyber_ctx_queue *kcq = &flush_data->khd->kcqs[bitnr];
- blk_mq_flush_busy_ctxs(hctx, &rq_list);
- list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
- unsigned int sched_domain;
+ spin_lock(&kcq->lock);
+ list_splice_tail_init(&kcq->rq_list[flush_data->sched_domain],
+ flush_data->list);
+ sbitmap_clear_bit(sb, bitnr);
+ spin_unlock(&kcq->lock);
- sched_domain = rq_sched_domain(rq);
- list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
- }
+ return true;
+}
+
+static void kyber_flush_busy_kcqs(struct kyber_hctx_data *khd,
+ unsigned int sched_domain,
+ struct list_head *list)
+{
+ struct flush_kcq_data data = {
+ .khd = khd,
+ .sched_domain = sched_domain,
+ .list = list,
+ };
+
+ sbitmap_for_each_set(&khd->kcq_map[sched_domain],
+ flush_busy_kcq, &data);
}
static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
@@ -573,26 +689,23 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
static struct request *
kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
struct kyber_hctx_data *khd,
- struct blk_mq_hw_ctx *hctx,
- bool *flushed)
+ struct blk_mq_hw_ctx *hctx)
{
struct list_head *rqs;
struct request *rq;
int nr;
rqs = &khd->rqs[khd->cur_domain];
- rq = list_first_entry_or_null(rqs, struct request, queuelist);
/*
- * If there wasn't already a pending request and we haven't flushed the
- * software queues yet, flush the software queues and check again.
+ * If we already have a flushed request, then we just need to get a
+ * token for it. Otherwise, if there are pending requests in the kcqs,
+ * flush the kcqs, but only if we can get a token. If not, we should
+ * leave the requests in the kcqs so that they can be merged. Note that
+ * khd->lock serializes the flushes, so if we observed any bit set in
+ * the kcq_map, we will always get a request.
*/
- if (!rq && !*flushed) {
- kyber_flush_busy_ctxs(khd, hctx);
- *flushed = true;
- rq = list_first_entry_or_null(rqs, struct request, queuelist);
- }
-
+ rq = list_first_entry_or_null(rqs, struct request, queuelist);
if (rq) {
nr = kyber_get_domain_token(kqd, khd, hctx);
if (nr >= 0) {
@@ -601,6 +714,16 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
list_del_init(&rq->queuelist);
return rq;
}
+ } else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) {
+ nr = kyber_get_domain_token(kqd, khd, hctx);
+ if (nr >= 0) {
+ kyber_flush_busy_kcqs(khd, khd->cur_domain, rqs);
+ rq = list_first_entry(rqs, struct request, queuelist);
+ khd->batching++;
+ rq_set_domain_token(rq, nr);
+ list_del_init(&rq->queuelist);
+ return rq;
+ }
}
/* There were either no pending requests or no tokens. */
@@ -611,7 +734,6 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
struct kyber_hctx_data *khd = hctx->sched_data;
- bool flushed = false;
struct request *rq;
int i;
@@ -622,7 +744,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
* from the batch.
*/
if (khd->batching < kyber_batch_size[khd->cur_domain]) {
- rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
if (rq)
goto out;
}
@@ -643,7 +765,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
else
khd->cur_domain++;
- rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
if (rq)
goto out;
}
@@ -660,10 +782,12 @@ static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
int i;
for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
- if (!list_empty_careful(&khd->rqs[i]))
+ if (!list_empty_careful(&khd->rqs[i]) ||
+ sbitmap_any_bit_set(&khd->kcq_map[i]))
return true;
}
- return sbitmap_any_bit_set(&hctx->ctx_map);
+
+ return false;
}
#define KYBER_LAT_SHOW_STORE(op) \
@@ -834,7 +958,9 @@ static struct elevator_type kyber_sched = {
.init_hctx = kyber_init_hctx,
.exit_hctx = kyber_exit_hctx,
.limit_depth = kyber_limit_depth,
+ .bio_merge = kyber_bio_merge,
.prepare_request = kyber_prepare_request,
+ .insert_requests = kyber_insert_requests,
.finish_request = kyber_finish_request,
.requeue_request = kyber_finish_request,
.completed_request = kyber_completed_request,
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index d82237d534cf..11a85b740327 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -977,7 +977,7 @@ static void drbd_bm_endio(struct bio *bio)
bm_page_unlock_io(device, idx);
if (ctx->flags & BM_AIO_COPY_PAGES)
- mempool_free(bio->bi_io_vec[0].bv_page, drbd_md_io_page_pool);
+ mempool_free(bio->bi_io_vec[0].bv_page, &drbd_md_io_page_pool);
bio_put(bio);
@@ -1014,7 +1014,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
bm_set_page_unchanged(b->bm_pages[page_nr]);
if (ctx->flags & BM_AIO_COPY_PAGES) {
- page = mempool_alloc(drbd_md_io_page_pool,
+ page = mempool_alloc(&drbd_md_io_page_pool,
GFP_NOIO | __GFP_HIGHMEM);
copy_highpage(page, b->bm_pages[page_nr]);
bm_store_page_idx(page, page_nr);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 06ecee1b528e..21b4186add6f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1405,8 +1405,8 @@ extern struct kmem_cache *drbd_request_cache;
extern struct kmem_cache *drbd_ee_cache; /* peer requests */
extern struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */
extern struct kmem_cache *drbd_al_ext_cache; /* activity log extents */
-extern mempool_t *drbd_request_mempool;
-extern mempool_t *drbd_ee_mempool;
+extern mempool_t drbd_request_mempool;
+extern mempool_t drbd_ee_mempool;
/* drbd's page pool, used to buffer data received from the peer,
* or data requested by the peer.
@@ -1432,16 +1432,16 @@ extern wait_queue_head_t drbd_pp_wait;
* 128 should be plenty, currently we probably can get away with as few as 1.
*/
#define DRBD_MIN_POOL_PAGES 128
-extern mempool_t *drbd_md_io_page_pool;
+extern mempool_t drbd_md_io_page_pool;
/* We also need to make sure we get a bio
* when we need it for housekeeping purposes */
-extern struct bio_set *drbd_md_io_bio_set;
+extern struct bio_set drbd_md_io_bio_set;
/* to allocate from that set */
extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
/* And a bio_set for cloning */
-extern struct bio_set *drbd_io_bio_set;
+extern struct bio_set drbd_io_bio_set;
extern struct mutex resources_mutex;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index e6ec831ad472..a233e71e58ff 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -124,11 +124,11 @@ struct kmem_cache *drbd_request_cache;
struct kmem_cache *drbd_ee_cache; /* peer requests */
struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */
struct kmem_cache *drbd_al_ext_cache; /* activity log extents */
-mempool_t *drbd_request_mempool;
-mempool_t *drbd_ee_mempool;
-mempool_t *drbd_md_io_page_pool;
-struct bio_set *drbd_md_io_bio_set;
-struct bio_set *drbd_io_bio_set;
+mempool_t drbd_request_mempool;
+mempool_t drbd_ee_mempool;
+mempool_t drbd_md_io_page_pool;
+struct bio_set drbd_md_io_bio_set;
+struct bio_set drbd_io_bio_set;
/* I do not use a standard mempool, because:
1) I want to hand out the pre-allocated objects first.
@@ -153,10 +153,10 @@ struct bio *bio_alloc_drbd(gfp_t gfp_mask)
{
struct bio *bio;
- if (!drbd_md_io_bio_set)
+ if (!bioset_initialized(&drbd_md_io_bio_set))
return bio_alloc(gfp_mask, 1);
- bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
+ bio = bio_alloc_bioset(gfp_mask, 1, &drbd_md_io_bio_set);
if (!bio)
return NULL;
return bio;
@@ -2097,16 +2097,11 @@ static void drbd_destroy_mempools(void)
/* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */
- if (drbd_io_bio_set)
- bioset_free(drbd_io_bio_set);
- if (drbd_md_io_bio_set)
- bioset_free(drbd_md_io_bio_set);
- if (drbd_md_io_page_pool)
- mempool_destroy(drbd_md_io_page_pool);
- if (drbd_ee_mempool)
- mempool_destroy(drbd_ee_mempool);
- if (drbd_request_mempool)
- mempool_destroy(drbd_request_mempool);
+ bioset_exit(&drbd_io_bio_set);
+ bioset_exit(&drbd_md_io_bio_set);
+ mempool_exit(&drbd_md_io_page_pool);
+ mempool_exit(&drbd_ee_mempool);
+ mempool_exit(&drbd_request_mempool);
if (drbd_ee_cache)
kmem_cache_destroy(drbd_ee_cache);
if (drbd_request_cache)
@@ -2116,11 +2111,6 @@ static void drbd_destroy_mempools(void)
if (drbd_al_ext_cache)
kmem_cache_destroy(drbd_al_ext_cache);
- drbd_io_bio_set = NULL;
- drbd_md_io_bio_set = NULL;
- drbd_md_io_page_pool = NULL;
- drbd_ee_mempool = NULL;
- drbd_request_mempool = NULL;
drbd_ee_cache = NULL;
drbd_request_cache = NULL;
drbd_bm_ext_cache = NULL;
@@ -2133,18 +2123,7 @@ static int drbd_create_mempools(void)
{
struct page *page;
const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count;
- int i;
-
- /* prepare our caches and mempools */
- drbd_request_mempool = NULL;
- drbd_ee_cache = NULL;
- drbd_request_cache = NULL;
- drbd_bm_ext_cache = NULL;
- drbd_al_ext_cache = NULL;
- drbd_pp_pool = NULL;
- drbd_md_io_page_pool = NULL;
- drbd_md_io_bio_set = NULL;
- drbd_io_bio_set = NULL;
+ int i, ret;
/* caches */
drbd_request_cache = kmem_cache_create(
@@ -2168,26 +2147,26 @@ static int drbd_create_mempools(void)
goto Enomem;
/* mempools */
- drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (drbd_io_bio_set == NULL)
+ ret = bioset_init(&drbd_io_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret)
goto Enomem;
- drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0,
- BIOSET_NEED_BVECS);
- if (drbd_md_io_bio_set == NULL)
+ ret = bioset_init(&drbd_md_io_bio_set, DRBD_MIN_POOL_PAGES, 0,
+ BIOSET_NEED_BVECS);
+ if (ret)
goto Enomem;
- drbd_md_io_page_pool = mempool_create_page_pool(DRBD_MIN_POOL_PAGES, 0);
- if (drbd_md_io_page_pool == NULL)
+ ret = mempool_init_page_pool(&drbd_md_io_page_pool, DRBD_MIN_POOL_PAGES, 0);
+ if (ret)
goto Enomem;
- drbd_request_mempool = mempool_create_slab_pool(number,
- drbd_request_cache);
- if (drbd_request_mempool == NULL)
+ ret = mempool_init_slab_pool(&drbd_request_mempool, number,
+ drbd_request_cache);
+ if (ret)
goto Enomem;
- drbd_ee_mempool = mempool_create_slab_pool(number, drbd_ee_cache);
- if (drbd_ee_mempool == NULL)
+ ret = mempool_init_slab_pool(&drbd_ee_mempool, number, drbd_ee_cache);
+ if (ret)
goto Enomem;
/* drbd's page pool */
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c72dee0ef083..be9450f5ad1c 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -378,7 +378,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
if (drbd_insert_fault(device, DRBD_FAULT_AL_EE))
return NULL;
- peer_req = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
+ peer_req = mempool_alloc(&drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
if (!peer_req) {
if (!(gfp_mask & __GFP_NOWARN))
drbd_err(device, "%s: allocation failed\n", __func__);
@@ -409,7 +409,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
return peer_req;
fail:
- mempool_free(peer_req, drbd_ee_mempool);
+ mempool_free(peer_req, &drbd_ee_mempool);
return NULL;
}
@@ -426,7 +426,7 @@ void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *
peer_req->flags &= ~EE_CALL_AL_COMPLETE_IO;
drbd_al_complete_io(device, &peer_req->i);
}
- mempool_free(peer_req, drbd_ee_mempool);
+ mempool_free(peer_req, &drbd_ee_mempool);
}
int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list)
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index a500e738d929..a47e4987ee46 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -55,7 +55,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
{
struct drbd_request *req;
- req = mempool_alloc(drbd_request_mempool, GFP_NOIO);
+ req = mempool_alloc(&drbd_request_mempool, GFP_NOIO);
if (!req)
return NULL;
memset(req, 0, sizeof(*req));
@@ -184,7 +184,7 @@ void drbd_req_destroy(struct kref *kref)
}
}
- mempool_free(req, drbd_request_mempool);
+ mempool_free(req, &drbd_request_mempool);
}
static void wake_all_senders(struct drbd_connection *connection)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index cb97b3b30962..94c654020f0f 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -269,7 +269,7 @@ enum drbd_req_state_bits {
static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
{
struct bio *bio;
- bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
+ bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set);
req->private_bio = bio;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 95657b814543..c73626decb46 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2725,15 +2725,11 @@ static void mtip_softirq_done_fn(struct request *rq)
blk_mq_end_request(rq, cmd->status);
}
-static void mtip_abort_cmd(struct request *req, void *data,
- bool reserved)
+static void mtip_abort_cmd(struct request *req, void *data, bool reserved)
{
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
struct driver_data *dd = data;
- if (!blk_mq_request_started(req))
- return;
-
dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
clear_bit(req->tag, dd->port->cmds_to_issue);
@@ -2741,14 +2737,10 @@ static void mtip_abort_cmd(struct request *req, void *data,
mtip_softirq_done_fn(req);
}
-static void mtip_queue_cmd(struct request *req, void *data,
- bool reserved)
+static void mtip_queue_cmd(struct request *req, void *data, bool reserved)
{
struct driver_data *dd = data;
- if (!blk_mq_request_started(req))
- return;
-
set_bit(req->tag, dd->port->cmds_to_issue);
blk_abort_request(req);
}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8860b24098bc..3ed1ef8ee528 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -216,7 +216,15 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
}
if (!nsock->dead) {
kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
- atomic_dec(&nbd->config->live_connections);
+ if (atomic_dec_return(&nbd->config->live_connections) == 0) {
+ if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED,
+ &nbd->config->runtime_flags)) {
+ set_bit(NBD_DISCONNECTED,
+ &nbd->config->runtime_flags);
+ dev_info(nbd_to_dev(nbd),
+ "Disconnected due to user request.\n");
+ }
+ }
}
nsock->dead = true;
nsock->pending = NULL;
@@ -310,7 +318,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
if (config->num_connections > 1) {
dev_err_ratelimited(nbd_to_dev(nbd),
- "Connection timed out, retrying\n");
+ "Connection timed out, retrying (%d/%d alive)\n",
+ atomic_read(&config->live_connections),
+ config->num_connections);
/*
* Hooray we have more connections, requeue this IO, the submit
* path will put it on a real connection.
@@ -666,11 +676,8 @@ static void recv_work(struct work_struct *work)
static void nbd_clear_req(struct request *req, void *data, bool reserved)
{
- struct nbd_cmd *cmd;
+ struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
- if (!blk_mq_request_started(req))
- return;
- cmd = blk_mq_rq_to_pdu(req);
cmd->status = BLK_STS_IOERR;
blk_mq_complete_request(req);
}
@@ -733,10 +740,9 @@ static int wait_for_reconnect(struct nbd_device *nbd)
return 0;
if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
return 0;
- wait_event_timeout(config->conn_wait,
- atomic_read(&config->live_connections),
- config->dead_conn_timeout);
- return atomic_read(&config->live_connections);
+ return wait_event_timeout(config->conn_wait,
+ atomic_read(&config->live_connections) > 0,
+ config->dead_conn_timeout) > 0;
}
static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 2f2d476ffc31..1a2c0101cfcb 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -97,8 +97,8 @@ static int pktdev_major;
static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
-static mempool_t *psd_pool;
-static struct bio_set *pkt_bio_set;
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
@@ -631,7 +631,7 @@ static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
{
rb_erase(&node->rb_node, &pd->bio_queue);
- mempool_free(node, pd->rb_pool);
+ mempool_free(node, &pd->rb_pool);
pd->bio_queue_size--;
BUG_ON(pd->bio_queue_size < 0);
}
@@ -2303,14 +2303,14 @@ static void pkt_end_io_read_cloned(struct bio *bio)
psd->bio->bi_status = bio->bi_status;
bio_put(bio);
bio_endio(psd->bio);
- mempool_free(psd, psd_pool);
+ mempool_free(psd, &psd_pool);
pkt_bio_finished(pd);
}
static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
{
- struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set);
- struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
+ struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, &pkt_bio_set);
+ struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
psd->pd = pd;
psd->bio = bio;
@@ -2381,7 +2381,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
/*
* No matching packet found. Store the bio in the work queue.
*/
- node = mempool_alloc(pd->rb_pool, GFP_NOIO);
+ node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
node->bio = bio;
spin_lock(&pd->lock);
BUG_ON(pd->bio_queue_size < 0);
@@ -2451,7 +2451,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
split = bio_split(bio, last_zone -
bio->bi_iter.bi_sector,
- GFP_NOIO, pkt_bio_set);
+ GFP_NOIO, &pkt_bio_set);
bio_chain(split, bio);
} else {
split = bio;
@@ -2707,9 +2707,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
if (!pd)
goto out_mutex;
- pd->rb_pool = mempool_create_kmalloc_pool(PKT_RB_POOL_SIZE,
- sizeof(struct pkt_rb_node));
- if (!pd->rb_pool)
+ ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+ sizeof(struct pkt_rb_node));
+ if (ret)
goto out_mem;
INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
@@ -2766,7 +2766,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
out_mem2:
put_disk(disk);
out_mem:
- mempool_destroy(pd->rb_pool);
+ mempool_exit(&pd->rb_pool);
kfree(pd);
out_mutex:
mutex_unlock(&ctl_mutex);
@@ -2817,7 +2817,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
blk_cleanup_queue(pd->disk->queue);
put_disk(pd->disk);
- mempool_destroy(pd->rb_pool);
+ mempool_exit(&pd->rb_pool);
kfree(pd);
/* This is safe: open() is still holding a reference. */
@@ -2914,14 +2914,14 @@ static int __init pkt_init(void)
mutex_init(&ctl_mutex);
- psd_pool = mempool_create_kmalloc_pool(PSD_POOL_SIZE,
- sizeof(struct packet_stacked_data));
- if (!psd_pool)
- return -ENOMEM;
- pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!pkt_bio_set) {
- mempool_destroy(psd_pool);
- return -ENOMEM;
+ ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+ sizeof(struct packet_stacked_data));
+ if (ret)
+ return ret;
+ ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret) {
+ mempool_exit(&psd_pool);
+ return ret;
}
ret = register_blkdev(pktdev_major, DRIVER_NAME);
@@ -2954,8 +2954,8 @@ out_misc:
out:
unregister_blkdev(pktdev_major, DRIVER_NAME);
out2:
- mempool_destroy(psd_pool);
- bioset_free(pkt_bio_set);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
return ret;
}
@@ -2968,8 +2968,8 @@ static void __exit pkt_exit(void)
pkt_sysfs_cleanup();
unregister_blkdev(pktdev_major, DRIVER_NAME);
- mempool_destroy(psd_pool);
- bioset_free(pkt_bio_set);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
}
MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 94d5d97c9d8a..934341b10493 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -40,7 +40,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
}
kfree(ppa);
- mempool_free(line_ws, pblk->gen_ws_pool);
+ mempool_free(line_ws, &pblk->gen_ws_pool);
}
static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
@@ -102,7 +102,7 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
struct pblk *pblk = rqd->private;
__pblk_end_io_erase(pblk, rqd);
- mempool_free(rqd, pblk->e_rq_pool);
+ mempool_free(rqd, &pblk->e_rq_pool);
}
/*
@@ -237,15 +237,15 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type)
switch (type) {
case PBLK_WRITE:
case PBLK_WRITE_INT:
- pool = pblk->w_rq_pool;
+ pool = &pblk->w_rq_pool;
rq_size = pblk_w_rq_size;
break;
case PBLK_READ:
- pool = pblk->r_rq_pool;
+ pool = &pblk->r_rq_pool;
rq_size = pblk_g_rq_size;
break;
default:
- pool = pblk->e_rq_pool;
+ pool = &pblk->e_rq_pool;
rq_size = pblk_g_rq_size;
}
@@ -265,13 +265,13 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
case PBLK_WRITE:
kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
case PBLK_WRITE_INT:
- pool = pblk->w_rq_pool;
+ pool = &pblk->w_rq_pool;
break;
case PBLK_READ:
- pool = pblk->r_rq_pool;
+ pool = &pblk->r_rq_pool;
break;
case PBLK_ERASE:
- pool = pblk->e_rq_pool;
+ pool = &pblk->e_rq_pool;
break;
default:
pr_err("pblk: trying to free unknown rqd type\n");
@@ -292,7 +292,7 @@ void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
for (i = off; i < nr_pages + off; i++) {
bv = bio->bi_io_vec[i];
- mempool_free(bv.bv_page, pblk->page_bio_pool);
+ mempool_free(bv.bv_page, &pblk->page_bio_pool);
}
}
@@ -304,12 +304,12 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
int i, ret;
for (i = 0; i < nr_pages; i++) {
- page = mempool_alloc(pblk->page_bio_pool, flags);
+ page = mempool_alloc(&pblk->page_bio_pool, flags);
ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
if (ret != PBLK_EXPOSED_PAGE_SIZE) {
pr_err("pblk: could not add page to bio\n");
- mempool_free(page, pblk->page_bio_pool);
+ mempool_free(page, &pblk->page_bio_pool);
goto err;
}
}
@@ -1593,7 +1593,7 @@ static void pblk_line_put_ws(struct work_struct *work)
struct pblk_line *line = line_put_ws->line;
__pblk_line_put(pblk, line);
- mempool_free(line_put_ws, pblk->gen_ws_pool);
+ mempool_free(line_put_ws, &pblk->gen_ws_pool);
}
void pblk_line_put(struct kref *ref)
@@ -1610,7 +1610,7 @@ void pblk_line_put_wq(struct kref *ref)
struct pblk *pblk = line->pblk;
struct pblk_line_ws *line_put_ws;
- line_put_ws = mempool_alloc(pblk->gen_ws_pool, GFP_ATOMIC);
+ line_put_ws = mempool_alloc(&pblk->gen_ws_pool, GFP_ATOMIC);
if (!line_put_ws)
return;
@@ -1752,7 +1752,7 @@ void pblk_line_close_ws(struct work_struct *work)
struct pblk_line *line = line_ws->line;
pblk_line_close(pblk, line);
- mempool_free(line_ws, pblk->gen_ws_pool);
+ mempool_free(line_ws, &pblk->gen_ws_pool);
}
void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
@@ -1761,7 +1761,7 @@ void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
{
struct pblk_line_ws *line_ws;
- line_ws = mempool_alloc(pblk->gen_ws_pool, gfp_mask);
+ line_ws = mempool_alloc(&pblk->gen_ws_pool, gfp_mask);
line_ws->pblk = pblk;
line_ws->line = line;
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 91a5bc2556a3..9a984abd3dfe 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -23,7 +23,7 @@
static struct kmem_cache *pblk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
*pblk_w_rq_cache;
static DECLARE_RWSEM(pblk_lock);
-struct bio_set *pblk_bio_set;
+struct bio_set pblk_bio_set;
static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
struct bio *bio)
@@ -341,7 +341,7 @@ static int pblk_core_init(struct pblk *pblk)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
- int max_write_ppas;
+ int ret, max_write_ppas;
atomic64_set(&pblk->user_wa, 0);
atomic64_set(&pblk->pad_wa, 0);
@@ -375,33 +375,33 @@ static int pblk_core_init(struct pblk *pblk)
goto fail_free_pad_dist;
/* Internal bios can be at most the sectors signaled by the device. */
- pblk->page_bio_pool = mempool_create_page_pool(NVM_MAX_VLBA, 0);
- if (!pblk->page_bio_pool)
+ ret = mempool_init_page_pool(&pblk->page_bio_pool, NVM_MAX_VLBA, 0);
+ if (ret)
goto free_global_caches;
- pblk->gen_ws_pool = mempool_create_slab_pool(PBLK_GEN_WS_POOL_SIZE,
- pblk_ws_cache);
- if (!pblk->gen_ws_pool)
+ ret = mempool_init_slab_pool(&pblk->gen_ws_pool, PBLK_GEN_WS_POOL_SIZE,
+ pblk_ws_cache);
+ if (ret)
goto free_page_bio_pool;
- pblk->rec_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_rec_cache);
- if (!pblk->rec_pool)
+ ret = mempool_init_slab_pool(&pblk->rec_pool, geo->all_luns,
+ pblk_rec_cache);
+ if (ret)
goto free_gen_ws_pool;
- pblk->r_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_g_rq_cache);
- if (!pblk->r_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->r_rq_pool, geo->all_luns,
+ pblk_g_rq_cache);
+ if (ret)
goto free_rec_pool;
- pblk->e_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_g_rq_cache);
- if (!pblk->e_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->e_rq_pool, geo->all_luns,
+ pblk_g_rq_cache);
+ if (ret)
goto free_r_rq_pool;
- pblk->w_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_w_rq_cache);
- if (!pblk->w_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->w_rq_pool, geo->all_luns,
+ pblk_w_rq_cache);
+ if (ret)
goto free_e_rq_pool;
pblk->close_wq = alloc_workqueue("pblk-close-wq",
@@ -433,17 +433,17 @@ free_bb_wq:
free_close_wq:
destroy_workqueue(pblk->close_wq);
free_w_rq_pool:
- mempool_destroy(pblk->w_rq_pool);
+ mempool_exit(&pblk->w_rq_pool);
free_e_rq_pool:
- mempool_destroy(pblk->e_rq_pool);
+ mempool_exit(&pblk->e_rq_pool);
free_r_rq_pool:
- mempool_destroy(pblk->r_rq_pool);
+ mempool_exit(&pblk->r_rq_pool);
free_rec_pool:
- mempool_destroy(pblk->rec_pool);
+ mempool_exit(&pblk->rec_pool);
free_gen_ws_pool:
- mempool_destroy(pblk->gen_ws_pool);
+ mempool_exit(&pblk->gen_ws_pool);
free_page_bio_pool:
- mempool_destroy(pblk->page_bio_pool);
+ mempool_exit(&pblk->page_bio_pool);
free_global_caches:
pblk_free_global_caches(pblk);
fail_free_pad_dist:
@@ -462,12 +462,12 @@ static void pblk_core_free(struct pblk *pblk)
if (pblk->bb_wq)
destroy_workqueue(pblk->bb_wq);
- mempool_destroy(pblk->page_bio_pool);
- mempool_destroy(pblk->gen_ws_pool);
- mempool_destroy(pblk->rec_pool);
- mempool_destroy(pblk->r_rq_pool);
- mempool_destroy(pblk->e_rq_pool);
- mempool_destroy(pblk->w_rq_pool);
+ mempool_exit(&pblk->page_bio_pool);
+ mempool_exit(&pblk->gen_ws_pool);
+ mempool_exit(&pblk->rec_pool);
+ mempool_exit(&pblk->r_rq_pool);
+ mempool_exit(&pblk->e_rq_pool);
+ mempool_exit(&pblk->w_rq_pool);
pblk_free_global_caches(pblk);
kfree(pblk->pad_dist);
@@ -1297,18 +1297,18 @@ static int __init pblk_module_init(void)
{
int ret;
- pblk_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!pblk_bio_set)
- return -ENOMEM;
+ ret = bioset_init(&pblk_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret)
+ return ret;
ret = nvm_register_tgt_type(&tt_pblk);
if (ret)
- bioset_free(pblk_bio_set);
+ bioset_exit(&pblk_bio_set);
return ret;
}
static void pblk_module_exit(void)
{
- bioset_free(pblk_bio_set);
+ bioset_exit(&pblk_bio_set);
nvm_unregister_tgt_type(&tt_pblk);
}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 9eee10f69df0..c844ffb6aead 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -294,7 +294,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
kunmap_atomic(src_p);
kunmap_atomic(dst_p);
- mempool_free(src_bv.bv_page, pblk->page_bio_pool);
+ mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
} while (hole < nr_secs);
@@ -429,7 +429,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
struct bio *int_bio = NULL;
/* Clone read bio to deal with read errors internally */
- int_bio = bio_clone_fast(bio, GFP_KERNEL, pblk_bio_set);
+ int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
if (!int_bio) {
pr_err("pblk: could not clone read bio\n");
goto fail_end_io;
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3e079c2afa6e..364ad52a5bfb 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -60,7 +60,7 @@ void pblk_submit_rec(struct work_struct *work)
goto err;
}
- mempool_free(recovery, pblk->rec_pool);
+ mempool_free(recovery, &pblk->rec_pool);
return;
err:
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 3e6f1ebd743a..aef7fa2d401d 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -122,7 +122,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
if (unlikely(nr_ppas == 1))
ppa_list = &rqd->ppa_addr;
- recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
+ recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
INIT_LIST_HEAD(&recovery->failed);
@@ -134,7 +134,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
/* Logic error */
if (bit > c_ctx->nr_valid) {
WARN_ONCE(1, "pblk: corrupted write request\n");
- mempool_free(recovery, pblk->rec_pool);
+ mempool_free(recovery, &pblk->rec_pool);
goto out;
}
@@ -142,7 +142,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
if (!entry) {
pr_err("pblk: could not scan entry on write failure\n");
- mempool_free(recovery, pblk->rec_pool);
+ mempool_free(recovery, &pblk->rec_pool);
goto out;
}
@@ -156,7 +156,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
if (ret) {
pr_err("pblk: could not recover from write failure\n");
- mempool_free(recovery, pblk->rec_pool);
+ mempool_free(recovery, &pblk->rec_pool);
goto out;
}
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9c682acfc5d1..feafa4de264d 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -664,12 +664,12 @@ struct pblk {
struct list_head compl_list;
- mempool_t *page_bio_pool;
- mempool_t *gen_ws_pool;
- mempool_t *rec_pool;
- mempool_t *r_rq_pool;
- mempool_t *w_rq_pool;
- mempool_t *e_rq_pool;
+ mempool_t page_bio_pool;
+ mempool_t gen_ws_pool;
+ mempool_t rec_pool;
+ mempool_t r_rq_pool;
+ mempool_t w_rq_pool;
+ mempool_t e_rq_pool;
struct workqueue_struct *close_wq;
struct workqueue_struct *bb_wq;
@@ -841,7 +841,7 @@ void pblk_write_should_kick(struct pblk *pblk);
/*
* pblk read path
*/
-extern struct bio_set *pblk_bio_set;
+extern struct bio_set pblk_bio_set;
int pblk_submit_read(struct pblk *pblk, struct bio *bio);
int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
/*
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 6220cbda55c1..d6bf294f3907 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -269,7 +269,7 @@ struct bcache_device {
atomic_t *stripe_sectors_dirty;
unsigned long *full_dirty_stripes;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
unsigned data_csum:1;
@@ -530,9 +530,9 @@ struct cache_set {
struct closure sb_write;
struct semaphore sb_write_mutex;
- mempool_t *search;
- mempool_t *bio_meta;
- struct bio_set *bio_split;
+ mempool_t search;
+ mempool_t bio_meta;
+ struct bio_set bio_split;
/* For the btree cache */
struct shrinker shrink;
@@ -657,7 +657,7 @@ struct cache_set {
* A btree node on disk could have too many bsets for an iterator to fit
* on the stack - have to dynamically allocate them
*/
- mempool_t *fill_iter;
+ mempool_t fill_iter;
struct bset_sort_state sort;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 579c696a5fe0..f3403b45bc28 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1118,8 +1118,7 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
void bch_bset_sort_state_free(struct bset_sort_state *state)
{
- if (state->pool)
- mempool_destroy(state->pool);
+ mempool_exit(&state->pool);
}
int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
@@ -1129,11 +1128,7 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
state->page_order = page_order;
state->crit_factor = int_sqrt(1 << page_order);
- state->pool = mempool_create_page_pool(1, page_order);
- if (!state->pool)
- return -ENOMEM;
-
- return 0;
+ return mempool_init_page_pool(&state->pool, 1, page_order);
}
EXPORT_SYMBOL(bch_bset_sort_state_init);
@@ -1191,7 +1186,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
BUG_ON(order > state->page_order);
- outp = mempool_alloc(state->pool, GFP_NOIO);
+ outp = mempool_alloc(&state->pool, GFP_NOIO);
out = page_address(outp);
used_mempool = true;
order = state->page_order;
@@ -1220,7 +1215,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
}
if (used_mempool)
- mempool_free(virt_to_page(out), state->pool);
+ mempool_free(virt_to_page(out), &state->pool);
else
free_pages((unsigned long) out, order);
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 0c24280f3b98..b867f2200495 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -347,7 +347,7 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
/* Sorting */
struct bset_sort_state {
- mempool_t *pool;
+ mempool_t pool;
unsigned page_order;
unsigned crit_factor;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 17936b2dc7d6..2a0968c04e21 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -204,7 +204,7 @@ void bch_btree_node_read_done(struct btree *b)
struct bset *i = btree_bset_first(b);
struct btree_iter *iter;
- iter = mempool_alloc(b->c->fill_iter, GFP_NOIO);
+ iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
iter->size = b->c->sb.bucket_size / b->c->sb.block_size;
iter->used = 0;
@@ -271,7 +271,7 @@ void bch_btree_node_read_done(struct btree *b)
bch_bset_init_next(&b->keys, write_block(b),
bset_magic(&b->c->sb));
out:
- mempool_free(iter, b->c->fill_iter);
+ mempool_free(iter, &b->c->fill_iter);
return;
err:
set_btree_node_io_error(b);
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 2ddf8515e6a5..9612873afee2 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -17,12 +17,12 @@
void bch_bbio_free(struct bio *bio, struct cache_set *c)
{
struct bbio *b = container_of(bio, struct bbio, bio);
- mempool_free(b, c->bio_meta);
+ mempool_free(b, &c->bio_meta);
}
struct bio *bch_bbio_alloc(struct cache_set *c)
{
- struct bbio *b = mempool_alloc(c->bio_meta, GFP_NOIO);
+ struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO);
struct bio *bio = &b->bio;
bio_init(bio, bio->bi_inline_vecs, bucket_pages(c));
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 8e3e8655ed63..ae67f5fa8047 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -213,7 +213,7 @@ static void bch_data_insert_start(struct closure *cl)
do {
unsigned i;
struct bkey *k;
- struct bio_set *split = op->c->bio_split;
+ struct bio_set *split = &op->c->bio_split;
/* 1 for the device pointer and 1 for the chksum */
if (bch_keylist_realloc(&op->insert_keys,
@@ -548,7 +548,7 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
n = bio_next_split(bio, min_t(uint64_t, INT_MAX,
KEY_OFFSET(k) - bio->bi_iter.bi_sector),
- GFP_NOIO, s->d->bio_split);
+ GFP_NOIO, &s->d->bio_split);
bio_key = &container_of(n, struct bbio, bio)->key;
bch_bkey_copy_single_ptr(bio_key, k, ptr);
@@ -707,7 +707,7 @@ static void search_free(struct closure *cl)
bio_complete(s);
closure_debug_destroy(cl);
- mempool_free(s, s->d->c->search);
+ mempool_free(s, &s->d->c->search);
}
static inline struct search *search_alloc(struct bio *bio,
@@ -715,7 +715,7 @@ static inline struct search *search_alloc(struct bio *bio,
{
struct search *s;
- s = mempool_alloc(d->c->search, GFP_NOIO);
+ s = mempool_alloc(&d->c->search, GFP_NOIO);
closure_init(&s->cl, NULL);
do_bio_hook(s, bio, request_endio);
@@ -864,7 +864,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
s->cache_missed = 1;
if (s->cache_miss || s->iop.bypass) {
- miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+ miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
goto out_submit;
}
@@ -887,14 +887,14 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
s->iop.replace = true;
- miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+ miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
/* btree_search_recurse()'s btree iterator is no good anymore */
ret = miss == bio ? MAP_DONE : -EINTR;
cache_bio = bio_alloc_bioset(GFP_NOWAIT,
DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
- dc->disk.bio_split);
+ &dc->disk.bio_split);
if (!cache_bio)
goto out_submit;
@@ -1008,7 +1008,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
struct bio *flush;
flush = bio_alloc_bioset(GFP_NOIO, 0,
- dc->disk.bio_split);
+ &dc->disk.bio_split);
if (!flush) {
s->iop.status = BLK_STS_RESOURCE;
goto insert_data;
@@ -1021,7 +1021,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
closure_bio_submit(s->iop.c, flush, cl);
}
} else {
- s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
+ s->iop.bio = bio_clone_fast(bio, GFP_NOIO, &dc->disk.bio_split);
/* I/O request sent to backing device */
bio->bi_end_io = backing_request_endio;
closure_bio_submit(s->iop.c, bio, cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index bd438e96b742..a31e55bcc4e5 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -753,8 +753,7 @@ static void bcache_device_free(struct bcache_device *d)
put_disk(d->disk);
}
- if (d->bio_split)
- bioset_free(d->bio_split);
+ bioset_exit(&d->bio_split);
kvfree(d->full_dirty_stripes);
kvfree(d->stripe_sectors_dirty);
@@ -796,9 +795,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
if (idx < 0)
return idx;
- if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
- BIOSET_NEED_BVECS |
- BIOSET_NEED_RESCUER)) ||
+ if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
!(d->disk = alloc_disk(BCACHE_MINORS))) {
ida_simple_remove(&bcache_device_idx, idx);
return -ENOMEM;
@@ -1500,14 +1498,10 @@ static void cache_set_free(struct closure *cl)
if (c->moving_gc_wq)
destroy_workqueue(c->moving_gc_wq);
- if (c->bio_split)
- bioset_free(c->bio_split);
- if (c->fill_iter)
- mempool_destroy(c->fill_iter);
- if (c->bio_meta)
- mempool_destroy(c->bio_meta);
- if (c->search)
- mempool_destroy(c->search);
+ bioset_exit(&c->bio_split);
+ mempool_exit(&c->fill_iter);
+ mempool_exit(&c->bio_meta);
+ mempool_exit(&c->search);
kfree(c->devices);
mutex_lock(&bch_register_lock);
@@ -1718,21 +1712,17 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
INIT_LIST_HEAD(&c->btree_cache_freed);
INIT_LIST_HEAD(&c->data_buckets);
- c->search = mempool_create_slab_pool(32, bch_search_cache);
- if (!c->search)
- goto err;
-
iter_size = (sb->bucket_size / sb->block_size + 1) *
sizeof(struct btree_iter_set);
if (!(c->devices = kzalloc(c->nr_uuids * sizeof(void *), GFP_KERNEL)) ||
- !(c->bio_meta = mempool_create_kmalloc_pool(2,
- sizeof(struct bbio) + sizeof(struct bio_vec) *
- bucket_pages(c))) ||
- !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
- !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio),
- BIOSET_NEED_BVECS |
- BIOSET_NEED_RESCUER)) ||
+ mempool_init_slab_pool(&c->search, 32, bch_search_cache) ||
+ mempool_init_kmalloc_pool(&c->bio_meta, 2,
+ sizeof(struct bbio) + sizeof(struct bio_vec) *
+ bucket_pages(c)) ||
+ mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) ||
+ bioset_init(&c->bio_split, 4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
!(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
!(c->moving_gc_wq = alloc_workqueue("bcache_gc",
WQ_MEM_RECLAIM, 0)) ||
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index 874841f0fc83..8e33a3808368 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -19,7 +19,7 @@
struct dm_bio_prison {
spinlock_t lock;
- mempool_t *cell_pool;
+ mempool_t cell_pool;
struct rb_root cells;
};
@@ -34,14 +34,15 @@ static struct kmem_cache *_cell_cache;
struct dm_bio_prison *dm_bio_prison_create(void)
{
struct dm_bio_prison *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+ int ret;
if (!prison)
return NULL;
spin_lock_init(&prison->lock);
- prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
- if (!prison->cell_pool) {
+ ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+ if (ret) {
kfree(prison);
return NULL;
}
@@ -54,21 +55,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create);
void dm_bio_prison_destroy(struct dm_bio_prison *prison)
{
- mempool_destroy(prison->cell_pool);
+ mempool_exit(&prison->cell_pool);
kfree(prison);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_destroy);
struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, gfp_t gfp)
{
- return mempool_alloc(prison->cell_pool, gfp);
+ return mempool_alloc(&prison->cell_pool, gfp);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell);
void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
struct dm_bio_prison_cell *cell)
{
- mempool_free(cell, prison->cell_pool);
+ mempool_free(cell, &prison->cell_pool);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell);
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index 8ce3a1a588cf..601b1569206a 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -21,7 +21,7 @@ struct dm_bio_prison_v2 {
struct workqueue_struct *wq;
spinlock_t lock;
- mempool_t *cell_pool;
+ mempool_t cell_pool;
struct rb_root cells;
};
@@ -36,6 +36,7 @@ static struct kmem_cache *_cell_cache;
struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
{
struct dm_bio_prison_v2 *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+ int ret;
if (!prison)
return NULL;
@@ -43,8 +44,8 @@ struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
prison->wq = wq;
spin_lock_init(&prison->lock);
- prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
- if (!prison->cell_pool) {
+ ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+ if (ret) {
kfree(prison);
return NULL;
}
@@ -57,21 +58,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create_v2);
void dm_bio_prison_destroy_v2(struct dm_bio_prison_v2 *prison)
{
- mempool_destroy(prison->cell_pool);
+ mempool_exit(&prison->cell_pool);
kfree(prison);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_destroy_v2);
struct dm_bio_prison_cell_v2 *dm_bio_prison_alloc_cell_v2(struct dm_bio_prison_v2 *prison, gfp_t gfp)
{
- return mempool_alloc(prison->cell_pool, gfp);
+ return mempool_alloc(&prison->cell_pool, gfp);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell_v2);
void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison,
struct dm_bio_prison_cell_v2 *cell)
{
- mempool_free(cell, prison->cell_pool);
+ mempool_free(cell, &prison->cell_pool);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell_v2);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index da208638fba4..001c71248246 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -447,9 +447,9 @@ struct cache {
struct work_struct migration_worker;
struct delayed_work waker;
struct dm_bio_prison_v2 *prison;
- struct bio_set *bs;
+ struct bio_set bs;
- mempool_t *migration_pool;
+ mempool_t migration_pool;
struct dm_cache_policy *policy;
unsigned policy_nr_args;
@@ -550,7 +550,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache)
{
struct dm_cache_migration *mg;
- mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+ mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
if (!mg)
return NULL;
@@ -569,7 +569,7 @@ static void free_migration(struct dm_cache_migration *mg)
if (atomic_dec_and_test(&cache->nr_allocated_migrations))
wake_up(&cache->migration_wait);
- mempool_free(mg, cache->migration_pool);
+ mempool_free(mg, &cache->migration_pool);
}
/*----------------------------------------------------------------*/
@@ -924,7 +924,7 @@ static void issue_op(struct bio *bio, void *context)
static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio,
dm_oblock_t oblock, dm_cblock_t cblock)
{
- struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs);
+ struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, &cache->bs);
BUG_ON(!origin_bio);
@@ -2011,7 +2011,7 @@ static void destroy(struct cache *cache)
{
unsigned i;
- mempool_destroy(cache->migration_pool);
+ mempool_exit(&cache->migration_pool);
if (cache->prison)
dm_bio_prison_destroy_v2(cache->prison);
@@ -2047,8 +2047,7 @@ static void destroy(struct cache *cache)
kfree(cache->ctr_args[i]);
kfree(cache->ctr_args);
- if (cache->bs)
- bioset_free(cache->bs);
+ bioset_exit(&cache->bs);
kfree(cache);
}
@@ -2498,8 +2497,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
cache->features = ca->features;
if (writethrough_mode(cache)) {
/* Create bioset for writethrough bios issued to origin */
- cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!cache->bs)
+ r = bioset_init(&cache->bs, BIO_POOL_SIZE, 0, 0);
+ if (r)
goto bad;
}
@@ -2630,9 +2629,9 @@ static int cache_create(struct cache_args *ca, struct cache **result)
goto bad;
}
- cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE,
- migration_cache);
- if (!cache->migration_pool) {
+ r = mempool_init_slab_pool(&cache->migration_pool, MIGRATION_POOL_SIZE,
+ migration_cache);
+ if (r) {
*error = "Error creating cache's migration mempool";
goto bad;
}
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3222e21cbbf8..f21c5d21bf1b 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -91,8 +91,8 @@ struct mapped_device {
/*
* io objects are allocated from here.
*/
- struct bio_set *io_bs;
- struct bio_set *bs;
+ struct bio_set io_bs;
+ struct bio_set bs;
/*
* freeze/thaw support require holding onto a super block
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 44ff473dab3e..eaf6b279accb 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -143,14 +143,14 @@ struct crypt_config {
* pool for per bio private data, crypto requests,
* encryption requeusts/buffer pages and integrity tags
*/
- mempool_t *req_pool;
- mempool_t *page_pool;
- mempool_t *tag_pool;
+ mempool_t req_pool;
+ mempool_t page_pool;
+ mempool_t tag_pool;
unsigned tag_pool_max_sectors;
struct percpu_counter n_allocated_pages;
- struct bio_set *bs;
+ struct bio_set bs;
struct mutex bio_alloc_lock;
struct workqueue_struct *io_queue;
@@ -1245,7 +1245,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
if (!ctx->r.req)
- ctx->r.req = mempool_alloc(cc->req_pool, GFP_NOIO);
+ ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
@@ -1262,7 +1262,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
struct convert_context *ctx)
{
if (!ctx->r.req_aead)
- ctx->r.req_aead = mempool_alloc(cc->req_pool, GFP_NOIO);
+ ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
@@ -1290,7 +1290,7 @@ static void crypt_free_req_skcipher(struct crypt_config *cc,
struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
if ((struct skcipher_request *)(io + 1) != req)
- mempool_free(req, cc->req_pool);
+ mempool_free(req, &cc->req_pool);
}
static void crypt_free_req_aead(struct crypt_config *cc,
@@ -1299,7 +1299,7 @@ static void crypt_free_req_aead(struct crypt_config *cc,
struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
if ((struct aead_request *)(io + 1) != req)
- mempool_free(req, cc->req_pool);
+ mempool_free(req, &cc->req_pool);
}
static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_bio)
@@ -1409,7 +1409,7 @@ retry:
if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
mutex_lock(&cc->bio_alloc_lock);
- clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
+ clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs);
if (!clone)
goto out;
@@ -1418,7 +1418,7 @@ retry:
remaining_size = size;
for (i = 0; i < nr_iovecs; i++) {
- page = mempool_alloc(cc->page_pool, gfp_mask);
+ page = mempool_alloc(&cc->page_pool, gfp_mask);
if (!page) {
crypt_free_buffer_pages(cc, clone);
bio_put(clone);
@@ -1453,7 +1453,7 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
bio_for_each_segment_all(bv, clone, i) {
BUG_ON(!bv->bv_page);
- mempool_free(bv->bv_page, cc->page_pool);
+ mempool_free(bv->bv_page, &cc->page_pool);
}
}
@@ -1492,7 +1492,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
crypt_free_req(cc, io->ctx.r.req, base_bio);
if (unlikely(io->integrity_metadata_from_pool))
- mempool_free(io->integrity_metadata, io->cc->tag_pool);
+ mempool_free(io->integrity_metadata, &io->cc->tag_pool);
else
kfree(io->integrity_metadata);
@@ -1565,7 +1565,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
* biovecs we don't need to worry about the block layer
* modifying the biovec array; so leverage bio_clone_fast().
*/
- clone = bio_clone_fast(io->base_bio, gfp, cc->bs);
+ clone = bio_clone_fast(io->base_bio, gfp, &cc->bs);
if (!clone)
return 1;
@@ -2219,17 +2219,16 @@ static void crypt_dtr(struct dm_target *ti)
crypt_free_tfms(cc);
- if (cc->bs)
- bioset_free(cc->bs);
+ bioset_exit(&cc->bs);
- mempool_destroy(cc->page_pool);
- mempool_destroy(cc->req_pool);
- mempool_destroy(cc->tag_pool);
-
- if (cc->page_pool)
+ if (mempool_initialized(&cc->page_pool))
WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
percpu_counter_destroy(&cc->n_allocated_pages);
+ mempool_exit(&cc->page_pool);
+ mempool_exit(&cc->req_pool);
+ mempool_exit(&cc->tag_pool);
+
if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
cc->iv_gen_ops->dtr(cc);
@@ -2743,8 +2742,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
iv_size_padding = align_mask;
}
- ret = -ENOMEM;
-
/* ...| IV + padding | original IV | original sec. number | bio tag offset | */
additional_req_size = sizeof(struct dm_crypt_request) +
iv_size_padding + cc->iv_size +
@@ -2752,8 +2749,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
sizeof(uint64_t) +
sizeof(unsigned int);
- cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + additional_req_size);
- if (!cc->req_pool) {
+ ret = mempool_init_kmalloc_pool(&cc->req_pool, MIN_IOS, cc->dmreq_start + additional_req_size);
+ if (ret) {
ti->error = "Cannot allocate crypt request mempool";
goto bad;
}
@@ -2762,14 +2759,14 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
ARCH_KMALLOC_MINALIGN);
- cc->page_pool = mempool_create(BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
- if (!cc->page_pool) {
+ ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+ if (ret) {
ti->error = "Cannot allocate page mempool";
goto bad;
}
- cc->bs = bioset_create(MIN_IOS, 0, BIOSET_NEED_BVECS);
- if (!cc->bs) {
+ ret = bioset_init(&cc->bs, MIN_IOS, 0, BIOSET_NEED_BVECS);
+ if (ret) {
ti->error = "Cannot allocate crypt bioset";
goto bad;
}
@@ -2806,11 +2803,10 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
if (!cc->tag_pool_max_sectors)
cc->tag_pool_max_sectors = 1;
- cc->tag_pool = mempool_create_kmalloc_pool(MIN_IOS,
+ ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS,
cc->tag_pool_max_sectors * cc->on_disk_tag_size);
- if (!cc->tag_pool) {
+ if (ret) {
ti->error = "Cannot allocate integrity tags mempool";
- ret = -ENOMEM;
goto bad;
}
@@ -2903,7 +2899,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
if (bio_sectors(bio) > cc->tag_pool_max_sectors)
dm_accept_partial_bio(bio, cc->tag_pool_max_sectors);
- io->integrity_metadata = mempool_alloc(cc->tag_pool, GFP_NOIO);
+ io->integrity_metadata = mempool_alloc(&cc->tag_pool, GFP_NOIO);
io->integrity_metadata_from_pool = true;
}
}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 77d9fe58dae2..20f5bc1c7484 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -142,7 +142,7 @@ struct dm_integrity_c {
unsigned tag_size;
__s8 log2_tag_size;
sector_t start;
- mempool_t *journal_io_mempool;
+ mempool_t journal_io_mempool;
struct dm_io_client *io;
struct dm_bufio_client *bufio;
struct workqueue_struct *metadata_wq;
@@ -1817,7 +1817,7 @@ static void complete_copy_from_journal(unsigned long error, void *context)
struct journal_completion *comp = io->comp;
struct dm_integrity_c *ic = comp->ic;
remove_range(ic, &io->range);
- mempool_free(io, ic->journal_io_mempool);
+ mempool_free(io, &ic->journal_io_mempool);
if (unlikely(error != 0))
dm_integrity_io_error(ic, "copying from journal", -EIO);
complete_journal_op(comp);
@@ -1886,7 +1886,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
}
next_loop = k - 1;
- io = mempool_alloc(ic->journal_io_mempool, GFP_NOIO);
+ io = mempool_alloc(&ic->journal_io_mempool, GFP_NOIO);
io->comp = &comp;
io->range.logical_sector = sec;
io->range.n_sectors = (k - j) << ic->sb->log2_sectors_per_block;
@@ -1918,7 +1918,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
if (j == k) {
remove_range_unlocked(ic, &io->range);
spin_unlock_irq(&ic->endio_wait.lock);
- mempool_free(io, ic->journal_io_mempool);
+ mempool_free(io, &ic->journal_io_mempool);
goto skip_io;
}
for (l = j; l < k; l++) {
@@ -2980,9 +2980,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto bad;
}
- ic->journal_io_mempool = mempool_create_slab_pool(JOURNAL_IO_MEMPOOL, journal_io_cache);
- if (!ic->journal_io_mempool) {
- r = -ENOMEM;
+ r = mempool_init_slab_pool(&ic->journal_io_mempool, JOURNAL_IO_MEMPOOL, journal_io_cache);
+ if (r) {
ti->error = "Cannot allocate mempool";
goto bad;
}
@@ -3196,7 +3195,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
destroy_workqueue(ic->writer_wq);
if (ic->bufio)
dm_bufio_client_destroy(ic->bufio);
- mempool_destroy(ic->journal_io_mempool);
+ mempool_exit(&ic->journal_io_mempool);
if (ic->io)
dm_io_client_destroy(ic->io);
if (ic->dev)
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index a8d914d5abbe..53c6ed0eaa1f 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -22,8 +22,8 @@
#define DM_IO_MAX_REGIONS BITS_PER_LONG
struct dm_io_client {
- mempool_t *pool;
- struct bio_set *bios;
+ mempool_t pool;
+ struct bio_set bios;
};
/*
@@ -49,32 +49,33 @@ struct dm_io_client *dm_io_client_create(void)
{
struct dm_io_client *client;
unsigned min_ios = dm_get_reserved_bio_based_ios();
+ int ret;
client = kmalloc(sizeof(*client), GFP_KERNEL);
if (!client)
return ERR_PTR(-ENOMEM);
- client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
- if (!client->pool)
+ ret = mempool_init_slab_pool(&client->pool, min_ios, _dm_io_cache);
+ if (ret)
goto bad;
- client->bios = bioset_create(min_ios, 0, BIOSET_NEED_BVECS);
- if (!client->bios)
+ ret = bioset_init(&client->bios, min_ios, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto bad;
return client;
bad:
- mempool_destroy(client->pool);
+ mempool_exit(&client->pool);
kfree(client);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL(dm_io_client_create);
void dm_io_client_destroy(struct dm_io_client *client)
{
- mempool_destroy(client->pool);
- bioset_free(client->bios);
+ mempool_exit(&client->pool);
+ bioset_exit(&client->bios);
kfree(client);
}
EXPORT_SYMBOL(dm_io_client_destroy);
@@ -120,7 +121,7 @@ static void complete_io(struct io *io)
invalidate_kernel_vmap_range(io->vma_invalidate_address,
io->vma_invalidate_size);
- mempool_free(io, io->client->pool);
+ mempool_free(io, &io->client->pool);
fn(error_bits, context);
}
@@ -344,7 +345,7 @@ static void do_region(int op, int op_flags, unsigned region,
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
}
- bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
+ bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios);
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
bio_set_dev(bio, where->bdev);
bio->bi_end_io = endio;
@@ -442,7 +443,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
init_completion(&sio.wait);
- io = mempool_alloc(client->pool, GFP_NOIO);
+ io = mempool_alloc(&client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
@@ -474,7 +475,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
return -EIO;
}
- io = mempool_alloc(client->pool, GFP_NOIO);
+ io = mempool_alloc(&client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index e6e7c686646d..c89a675a2aac 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -47,7 +47,7 @@ struct dm_kcopyd_client {
wait_queue_head_t destroyq;
atomic_t nr_jobs;
- mempool_t *job_pool;
+ mempool_t job_pool;
struct workqueue_struct *kcopyd_wq;
struct work_struct kcopyd_work;
@@ -479,7 +479,7 @@ static int run_complete_job(struct kcopyd_job *job)
*/
if (job->master_job == job) {
mutex_destroy(&job->lock);
- mempool_free(job, kc->job_pool);
+ mempool_free(job, &kc->job_pool);
}
fn(read_err, write_err, context);
@@ -751,7 +751,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
* Allocate an array of jobs consisting of one master job
* followed by SPLIT_COUNT sub jobs.
*/
- job = mempool_alloc(kc->job_pool, GFP_NOIO);
+ job = mempool_alloc(&kc->job_pool, GFP_NOIO);
mutex_init(&job->lock);
/*
@@ -835,7 +835,7 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc,
{
struct kcopyd_job *job;
- job = mempool_alloc(kc->job_pool, GFP_NOIO);
+ job = mempool_alloc(&kc->job_pool, GFP_NOIO);
memset(job, 0, sizeof(struct kcopyd_job));
job->kc = kc;
@@ -879,7 +879,7 @@ int kcopyd_cancel(struct kcopyd_job *job, int block)
*---------------------------------------------------------------*/
struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle)
{
- int r = -ENOMEM;
+ int r;
struct dm_kcopyd_client *kc;
kc = kmalloc(sizeof(*kc), GFP_KERNEL);
@@ -892,14 +892,16 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
INIT_LIST_HEAD(&kc->pages_jobs);
kc->throttle = throttle;
- kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache);
- if (!kc->job_pool)
+ r = mempool_init_slab_pool(&kc->job_pool, MIN_JOBS, _job_cache);
+ if (r)
goto bad_slab;
INIT_WORK(&kc->kcopyd_work, do_work);
kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM, 0);
- if (!kc->kcopyd_wq)
+ if (!kc->kcopyd_wq) {
+ r = -ENOMEM;
goto bad_workqueue;
+ }
kc->pages = NULL;
kc->nr_reserved_pages = kc->nr_free_pages = 0;
@@ -923,7 +925,7 @@ bad_io_client:
bad_client_pages:
destroy_workqueue(kc->kcopyd_wq);
bad_workqueue:
- mempool_destroy(kc->job_pool);
+ mempool_exit(&kc->job_pool);
bad_slab:
kfree(kc);
@@ -942,7 +944,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc)
destroy_workqueue(kc->kcopyd_wq);
dm_io_client_destroy(kc->io_client);
client_free_pages(kc);
- mempool_destroy(kc->job_pool);
+ mempool_exit(&kc->job_pool);
kfree(kc);
}
EXPORT_SYMBOL(dm_kcopyd_client_destroy);
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 53b7b06d0aa8..52090bee17c2 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -76,7 +76,7 @@ struct log_c {
*/
uint32_t integrated_flush;
- mempool_t *flush_entry_pool;
+ mempool_t flush_entry_pool;
};
static struct kmem_cache *_flush_entry_cache;
@@ -249,11 +249,10 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
goto out;
}
- lc->flush_entry_pool = mempool_create_slab_pool(FLUSH_ENTRY_POOL_SIZE,
- _flush_entry_cache);
- if (!lc->flush_entry_pool) {
+ r = mempool_init_slab_pool(&lc->flush_entry_pool, FLUSH_ENTRY_POOL_SIZE,
+ _flush_entry_cache);
+ if (r) {
DMERR("Failed to create flush_entry_pool");
- r = -ENOMEM;
goto out;
}
@@ -313,7 +312,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
out:
kfree(devices_rdata);
if (r) {
- mempool_destroy(lc->flush_entry_pool);
+ mempool_exit(&lc->flush_entry_pool);
kfree(lc);
kfree(ctr_str);
} else {
@@ -342,7 +341,7 @@ static void userspace_dtr(struct dm_dirty_log *log)
if (lc->log_dev)
dm_put_device(lc->ti, lc->log_dev);
- mempool_destroy(lc->flush_entry_pool);
+ mempool_exit(&lc->flush_entry_pool);
kfree(lc->usr_argv_str);
kfree(lc);
@@ -570,7 +569,7 @@ static int userspace_flush(struct dm_dirty_log *log)
int mark_list_is_empty;
int clear_list_is_empty;
struct dm_dirty_log_flush_entry *fe, *tmp_fe;
- mempool_t *flush_entry_pool = lc->flush_entry_pool;
+ mempool_t *flush_entry_pool = &lc->flush_entry_pool;
spin_lock_irqsave(&lc->flush_lock, flags);
list_splice_init(&lc->mark_list, &mark_list);
@@ -653,7 +652,7 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
struct dm_dirty_log_flush_entry *fe;
/* Wait for an allocation, but _never_ fail */
- fe = mempool_alloc(lc->flush_entry_pool, GFP_NOIO);
+ fe = mempool_alloc(&lc->flush_entry_pool, GFP_NOIO);
BUG_ON(!fe);
spin_lock_irqsave(&lc->flush_lock, flags);
@@ -687,7 +686,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
* to cause the region to be resync'ed when the
* device is activated next time.
*/
- fe = mempool_alloc(lc->flush_entry_pool, GFP_ATOMIC);
+ fe = mempool_alloc(&lc->flush_entry_pool, GFP_ATOMIC);
if (!fe) {
DMERR("Failed to allocate memory to clear region.");
return;
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 85c32b22a420..43149eb49375 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -63,7 +63,7 @@ struct dm_region_hash {
/* hash table */
rwlock_t hash_lock;
- mempool_t *region_pool;
+ mempool_t region_pool;
unsigned mask;
unsigned nr_buckets;
unsigned prime;
@@ -169,6 +169,7 @@ struct dm_region_hash *dm_region_hash_create(
struct dm_region_hash *rh;
unsigned nr_buckets, max_buckets;
size_t i;
+ int ret;
/*
* Calculate a suitable number of buckets for our hash
@@ -220,9 +221,9 @@ struct dm_region_hash *dm_region_hash_create(
INIT_LIST_HEAD(&rh->failed_recovered_regions);
rh->flush_failure = 0;
- rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
- sizeof(struct dm_region));
- if (!rh->region_pool) {
+ ret = mempool_init_kmalloc_pool(&rh->region_pool, MIN_REGIONS,
+ sizeof(struct dm_region));
+ if (ret) {
vfree(rh->buckets);
kfree(rh);
rh = ERR_PTR(-ENOMEM);
@@ -242,14 +243,14 @@ void dm_region_hash_destroy(struct dm_region_hash *rh)
list_for_each_entry_safe(reg, nreg, rh->buckets + h,
hash_list) {
BUG_ON(atomic_read(&reg->pending));
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
}
if (rh->log)
dm_dirty_log_destroy(rh->log);
- mempool_destroy(rh->region_pool);
+ mempool_exit(&rh->region_pool);
vfree(rh->buckets);
kfree(rh);
}
@@ -287,7 +288,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
{
struct dm_region *reg, *nreg;
- nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
+ nreg = mempool_alloc(&rh->region_pool, GFP_ATOMIC);
if (unlikely(!nreg))
nreg = kmalloc(sizeof(*nreg), GFP_NOIO | __GFP_NOFAIL);
@@ -303,7 +304,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
reg = __rh_lookup(rh, region);
if (reg)
/* We lost the race. */
- mempool_free(nreg, rh->region_pool);
+ mempool_free(nreg, &rh->region_pool);
else {
__rh_insert(rh, nreg);
if (nreg->state == DM_RH_CLEAN) {
@@ -481,17 +482,17 @@ void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled)
list_for_each_entry_safe(reg, next, &recovered, list) {
rh->log->type->clear_region(rh->log, reg->key);
complete_resync_work(reg, 1);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
list_for_each_entry_safe(reg, next, &failed_recovered, list) {
complete_resync_work(reg, errors_handled ? 0 : 1);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
list_for_each_entry_safe(reg, next, &clean, list) {
rh->log->type->clear_region(rh->log, reg->key);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
rh->log->type->flush(rh->log);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 1c18f335da04..6e547b8dd298 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -433,7 +433,7 @@ static int setup_clone(struct request *clone, struct request *rq,
{
int r;
- r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+ r = blk_rq_prep_clone(clone, rq, &tio->md->bs, gfp_mask,
dm_rq_bio_constructor, tio);
if (r)
return r;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 216035be5661..b11ddc55f297 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -87,7 +87,7 @@ struct dm_snapshot {
*/
struct list_head out_of_order_list;
- mempool_t *pending_pool;
+ mempool_t pending_pool;
struct dm_exception_table pending;
struct dm_exception_table complete;
@@ -682,7 +682,7 @@ static void free_completed_exception(struct dm_exception *e)
static struct dm_snap_pending_exception *alloc_pending_exception(struct dm_snapshot *s)
{
- struct dm_snap_pending_exception *pe = mempool_alloc(s->pending_pool,
+ struct dm_snap_pending_exception *pe = mempool_alloc(&s->pending_pool,
GFP_NOIO);
atomic_inc(&s->pending_exceptions_count);
@@ -695,7 +695,7 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe)
{
struct dm_snapshot *s = pe->snap;
- mempool_free(pe, s->pending_pool);
+ mempool_free(pe, &s->pending_pool);
smp_mb__before_atomic();
atomic_dec(&s->pending_exceptions_count);
}
@@ -1196,10 +1196,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad_kcopyd;
}
- s->pending_pool = mempool_create_slab_pool(MIN_IOS, pending_cache);
- if (!s->pending_pool) {
+ r = mempool_init_slab_pool(&s->pending_pool, MIN_IOS, pending_cache);
+ if (r) {
ti->error = "Could not allocate mempool for pending exceptions";
- r = -ENOMEM;
goto bad_pending_pool;
}
@@ -1259,7 +1258,7 @@ bad_read_metadata:
unregister_snapshot(s);
bad_load_and_register:
- mempool_destroy(s->pending_pool);
+ mempool_exit(&s->pending_pool);
bad_pending_pool:
dm_kcopyd_client_destroy(s->kcopyd_client);
@@ -1355,7 +1354,7 @@ static void snapshot_dtr(struct dm_target *ti)
while (atomic_read(&s->pending_exceptions_count))
msleep(1);
/*
- * Ensure instructions in mempool_destroy aren't reordered
+ * Ensure instructions in mempool_exit aren't reordered
* before atomic_read.
*/
smp_mb();
@@ -1367,7 +1366,7 @@ static void snapshot_dtr(struct dm_target *ti)
__free_exceptions(s);
- mempool_destroy(s->pending_pool);
+ mempool_exit(&s->pending_pool);
dm_exception_store_destroy(s->store);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index b11107497d2e..6c923824ec91 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -260,7 +260,7 @@ struct pool {
struct dm_deferred_set *all_io_ds;
struct dm_thin_new_mapping *next_mapping;
- mempool_t *mapping_pool;
+ mempool_t mapping_pool;
process_bio_fn process_bio;
process_bio_fn process_discard;
@@ -917,7 +917,7 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
{
cell_error(m->tc->pool, m->cell);
list_del(&m->list);
- mempool_free(m, m->tc->pool->mapping_pool);
+ mempool_free(m, &m->tc->pool->mapping_pool);
}
static void process_prepared_mapping(struct dm_thin_new_mapping *m)
@@ -961,7 +961,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
out:
list_del(&m->list);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
}
/*----------------------------------------------------------------*/
@@ -971,7 +971,7 @@ static void free_discard_mapping(struct dm_thin_new_mapping *m)
struct thin_c *tc = m->tc;
if (m->cell)
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, tc->pool->mapping_pool);
+ mempool_free(m, &tc->pool->mapping_pool);
}
static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
@@ -999,7 +999,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
bio_endio(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, tc->pool->mapping_pool);
+ mempool_free(m, &tc->pool->mapping_pool);
}
/*----------------------------------------------------------------*/
@@ -1092,7 +1092,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
metadata_operation_failed(pool, "dm_thin_remove_range", r);
bio_io_error(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
return;
}
@@ -1105,7 +1105,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
metadata_operation_failed(pool, "dm_pool_inc_data_range", r);
bio_io_error(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
return;
}
@@ -1150,7 +1150,7 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
bio_endio(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
}
static void process_prepared(struct pool *pool, struct list_head *head,
@@ -1196,7 +1196,7 @@ static int ensure_next_mapping(struct pool *pool)
if (pool->next_mapping)
return 0;
- pool->next_mapping = mempool_alloc(pool->mapping_pool, GFP_ATOMIC);
+ pool->next_mapping = mempool_alloc(&pool->mapping_pool, GFP_ATOMIC);
return pool->next_mapping ? 0 : -ENOMEM;
}
@@ -2835,8 +2835,8 @@ static void __pool_destroy(struct pool *pool)
destroy_workqueue(pool->wq);
if (pool->next_mapping)
- mempool_free(pool->next_mapping, pool->mapping_pool);
- mempool_destroy(pool->mapping_pool);
+ mempool_free(pool->next_mapping, &pool->mapping_pool);
+ mempool_exit(&pool->mapping_pool);
dm_deferred_set_destroy(pool->shared_read_ds);
dm_deferred_set_destroy(pool->all_io_ds);
kfree(pool);
@@ -2931,11 +2931,11 @@ static struct pool *pool_create(struct mapped_device *pool_md,
}
pool->next_mapping = NULL;
- pool->mapping_pool = mempool_create_slab_pool(MAPPING_POOL_SIZE,
- _new_mapping_cache);
- if (!pool->mapping_pool) {
+ r = mempool_init_slab_pool(&pool->mapping_pool, MAPPING_POOL_SIZE,
+ _new_mapping_cache);
+ if (r) {
*error = "Error creating pool's mapping mempool";
- err_p = ERR_PTR(-ENOMEM);
+ err_p = ERR_PTR(r);
goto bad_mapping_pool;
}
@@ -2955,7 +2955,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
return pool;
bad_sort_array:
- mempool_destroy(pool->mapping_pool);
+ mempool_exit(&pool->mapping_pool);
bad_mapping_pool:
dm_deferred_set_destroy(pool->all_io_ds);
bad_all_io_ds:
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index e13f90832b6b..86405869f1af 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -309,13 +309,13 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
unsigned n;
if (!fio->rs)
- fio->rs = mempool_alloc(v->fec->rs_pool, GFP_NOIO);
+ fio->rs = mempool_alloc(&v->fec->rs_pool, GFP_NOIO);
fec_for_each_prealloc_buffer(n) {
if (fio->bufs[n])
continue;
- fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOWAIT);
+ fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOWAIT);
if (unlikely(!fio->bufs[n])) {
DMERR("failed to allocate FEC buffer");
return -ENOMEM;
@@ -327,7 +327,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
if (fio->bufs[n])
continue;
- fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOWAIT);
+ fio->bufs[n] = mempool_alloc(&v->fec->extra_pool, GFP_NOWAIT);
/* we can manage with even one buffer if necessary */
if (unlikely(!fio->bufs[n]))
break;
@@ -335,7 +335,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
fio->nbufs = n;
if (!fio->output)
- fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO);
+ fio->output = mempool_alloc(&v->fec->output_pool, GFP_NOIO);
return 0;
}
@@ -493,15 +493,15 @@ void verity_fec_finish_io(struct dm_verity_io *io)
if (!verity_fec_is_enabled(io->v))
return;
- mempool_free(fio->rs, f->rs_pool);
+ mempool_free(fio->rs, &f->rs_pool);
fec_for_each_prealloc_buffer(n)
- mempool_free(fio->bufs[n], f->prealloc_pool);
+ mempool_free(fio->bufs[n], &f->prealloc_pool);
fec_for_each_extra_buffer(fio, n)
- mempool_free(fio->bufs[n], f->extra_pool);
+ mempool_free(fio->bufs[n], &f->extra_pool);
- mempool_free(fio->output, f->output_pool);
+ mempool_free(fio->output, &f->output_pool);
}
/*
@@ -549,9 +549,9 @@ void verity_fec_dtr(struct dm_verity *v)
if (!verity_fec_is_enabled(v))
goto out;
- mempool_destroy(f->rs_pool);
- mempool_destroy(f->prealloc_pool);
- mempool_destroy(f->extra_pool);
+ mempool_exit(&f->rs_pool);
+ mempool_exit(&f->prealloc_pool);
+ mempool_exit(&f->extra_pool);
kmem_cache_destroy(f->cache);
if (f->data_bufio)
@@ -675,6 +675,7 @@ int verity_fec_ctr(struct dm_verity *v)
struct dm_verity_fec *f = v->fec;
struct dm_target *ti = v->ti;
u64 hash_blocks;
+ int ret;
if (!verity_fec_is_enabled(v)) {
verity_fec_dtr(v);
@@ -770,11 +771,11 @@ int verity_fec_ctr(struct dm_verity *v)
}
/* Preallocate an rs_control structure for each worker thread */
- f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc,
- fec_rs_free, (void *) v);
- if (!f->rs_pool) {
+ ret = mempool_init(&f->rs_pool, num_online_cpus(), fec_rs_alloc,
+ fec_rs_free, (void *) v);
+ if (ret) {
ti->error = "Cannot allocate RS pool";
- return -ENOMEM;
+ return ret;
}
f->cache = kmem_cache_create("dm_verity_fec_buffers",
@@ -786,26 +787,26 @@ int verity_fec_ctr(struct dm_verity *v)
}
/* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */
- f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() *
- DM_VERITY_FEC_BUF_PREALLOC,
- f->cache);
- if (!f->prealloc_pool) {
+ ret = mempool_init_slab_pool(&f->prealloc_pool, num_online_cpus() *
+ DM_VERITY_FEC_BUF_PREALLOC,
+ f->cache);
+ if (ret) {
ti->error = "Cannot allocate FEC buffer prealloc pool";
- return -ENOMEM;
+ return ret;
}
- f->extra_pool = mempool_create_slab_pool(0, f->cache);
- if (!f->extra_pool) {
+ ret = mempool_init_slab_pool(&f->extra_pool, 0, f->cache);
+ if (ret) {
ti->error = "Cannot allocate FEC buffer extra pool";
- return -ENOMEM;
+ return ret;
}
/* Preallocate an output buffer for each thread */
- f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(),
- 1 << v->data_dev_block_bits);
- if (!f->output_pool) {
+ ret = mempool_init_kmalloc_pool(&f->output_pool, num_online_cpus(),
+ 1 << v->data_dev_block_bits);
+ if (ret) {
ti->error = "Cannot allocate FEC output pool";
- return -ENOMEM;
+ return ret;
}
/* Reserve space for our per-bio data */
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index bb31ce87a933..6ad803b2b36c 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -46,10 +46,10 @@ struct dm_verity_fec {
sector_t hash_blocks; /* blocks covered after v->hash_start */
unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */
unsigned char rsn; /* N of RS(M, N) */
- mempool_t *rs_pool; /* mempool for fio->rs */
- mempool_t *prealloc_pool; /* mempool for preallocated buffers */
- mempool_t *extra_pool; /* mempool for extra buffers */
- mempool_t *output_pool; /* mempool for output */
+ mempool_t rs_pool; /* mempool for fio->rs */
+ mempool_t prealloc_pool; /* mempool for preallocated buffers */
+ mempool_t extra_pool; /* mempool for extra buffers */
+ mempool_t output_pool; /* mempool for output */
struct kmem_cache *cache; /* cache for buffers */
};
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index e73b0776683c..30602d15ad9a 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -57,7 +57,7 @@ struct dmz_target {
struct workqueue_struct *chunk_wq;
/* For cloned BIOs to zones */
- struct bio_set *bio_set;
+ struct bio_set bio_set;
/* For flush */
spinlock_t flush_lock;
@@ -121,7 +121,7 @@ static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone,
}
/* Partial BIO: we need to clone the BIO */
- clone = bio_clone_fast(bio, GFP_NOIO, dmz->bio_set);
+ clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
if (!clone)
return -ENOMEM;
@@ -779,10 +779,9 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift;
/* Zone BIO */
- dmz->bio_set = bioset_create(DMZ_MIN_BIOS, 0, 0);
- if (!dmz->bio_set) {
+ ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0);
+ if (ret) {
ti->error = "Create BIO set failed";
- ret = -ENOMEM;
goto err_meta;
}
@@ -828,7 +827,7 @@ err_cwq:
destroy_workqueue(dmz->chunk_wq);
err_bio:
mutex_destroy(&dmz->chunk_lock);
- bioset_free(dmz->bio_set);
+ bioset_exit(&dmz->bio_set);
err_meta:
dmz_dtr_metadata(dmz->metadata);
err_dev:
@@ -858,7 +857,7 @@ static void dmz_dtr(struct dm_target *ti)
dmz_dtr_metadata(dmz->metadata);
- bioset_free(dmz->bio_set);
+ bioset_exit(&dmz->bio_set);
dmz_put_zoned_device(ti);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4ea404dbcf0b..7dc0c5ef7cf8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -148,8 +148,8 @@ static int dm_numa_node = DM_NUMA_NODE;
* For mempools pre-allocation at the table loading time.
*/
struct dm_md_mempools {
- struct bio_set *bs;
- struct bio_set *io_bs;
+ struct bio_set bs;
+ struct bio_set io_bs;
};
struct table_device {
@@ -537,7 +537,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
struct dm_target_io *tio;
struct bio *clone;
- clone = bio_alloc_bioset(GFP_NOIO, 0, md->io_bs);
+ clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs);
if (!clone)
return NULL;
@@ -572,7 +572,7 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci, struct dm_target *t
/* the dm_target_io embedded in ci->io is available */
tio = &ci->io->tio;
} else {
- struct bio *clone = bio_alloc_bioset(gfp_mask, 0, ci->io->md->bs);
+ struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs);
if (!clone)
return NULL;
@@ -1582,7 +1582,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
* won't be affected by this reassignment.
*/
struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
- md->queue->bio_split);
+ &md->queue->bio_split);
ci.io->orig_bio = b;
bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
bio_chain(b, bio);
@@ -1784,10 +1784,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
destroy_workqueue(md->wq);
if (md->kworker_task)
kthread_stop(md->kworker_task);
- if (md->bs)
- bioset_free(md->bs);
- if (md->io_bs)
- bioset_free(md->io_bs);
+ bioset_exit(&md->bs);
+ bioset_exit(&md->io_bs);
if (md->dax_dev) {
kill_dax(md->dax_dev);
@@ -1964,16 +1962,10 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
* If so, reload bioset because front_pad may have changed
* because a different table was loaded.
*/
- if (md->bs) {
- bioset_free(md->bs);
- md->bs = NULL;
- }
- if (md->io_bs) {
- bioset_free(md->io_bs);
- md->io_bs = NULL;
- }
+ bioset_exit(&md->bs);
+ bioset_exit(&md->io_bs);
- } else if (md->bs) {
+ } else if (bioset_initialized(&md->bs)) {
/*
* There's no need to reload with request-based dm
* because the size of front_pad doesn't change.
@@ -1985,12 +1977,14 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
goto out;
}
- BUG_ON(!p || md->bs || md->io_bs);
+ BUG_ON(!p ||
+ bioset_initialized(&md->bs) ||
+ bioset_initialized(&md->io_bs));
md->bs = p->bs;
- p->bs = NULL;
+ memset(&p->bs, 0, sizeof(p->bs));
md->io_bs = p->io_bs;
- p->io_bs = NULL;
+ memset(&p->io_bs, 0, sizeof(p->io_bs));
out:
/* mempool bind completed, no longer need any mempools in the table */
dm_table_free_md_mempools(t);
@@ -2904,6 +2898,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
unsigned int pool_size = 0;
unsigned int front_pad, io_front_pad;
+ int ret;
if (!pools)
return NULL;
@@ -2915,10 +2910,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
io_front_pad = roundup(front_pad, __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
- pools->io_bs = bioset_create(pool_size, io_front_pad, 0);
- if (!pools->io_bs)
+ ret = bioset_init(&pools->io_bs, pool_size, io_front_pad, 0);
+ if (ret)
goto out;
- if (integrity && bioset_integrity_create(pools->io_bs, pool_size))
+ if (integrity && bioset_integrity_create(&pools->io_bs, pool_size))
goto out;
break;
case DM_TYPE_REQUEST_BASED:
@@ -2931,11 +2926,11 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
BUG();
}
- pools->bs = bioset_create(pool_size, front_pad, 0);
- if (!pools->bs)
+ ret = bioset_init(&pools->bs, pool_size, front_pad, 0);
+ if (ret)
goto out;
- if (integrity && bioset_integrity_create(pools->bs, pool_size))
+ if (integrity && bioset_integrity_create(&pools->bs, pool_size))
goto out;
return pools;
@@ -2951,10 +2946,8 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
if (!pools)
return;
- if (pools->bs)
- bioset_free(pools->bs);
- if (pools->io_bs)
- bioset_free(pools->io_bs);
+ bioset_exit(&pools->bs);
+ bioset_exit(&pools->io_bs);
kfree(pools);
}
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
index 38264b38420f..c2fdf899de14 100644
--- a/drivers/md/md-faulty.c
+++ b/drivers/md/md-faulty.c
@@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
}
}
if (failit) {
- struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ struct bio *b = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
bio_set_dev(b, conf->rdev->bdev);
b->bi_private = bio;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 4964323d936b..d45c697c0ebe 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -269,7 +269,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
if (unlikely(bio_end_sector(bio) > end_sector)) {
/* This bio crosses a device boundary, so we have to split it */
struct bio *split = bio_split(bio, end_sector - bio_sector,
- GFP_NOIO, mddev->bio_set);
+ GFP_NOIO, &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 0a7e99d62c69..f71fcdb9b39c 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -80,7 +80,7 @@ static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
bio->bi_status = status;
bio_endio(bio);
- mempool_free(mp_bh, conf->pool);
+ mempool_free(mp_bh, &conf->pool);
}
static void multipath_end_request(struct bio *bio)
@@ -117,7 +117,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
return true;
}
- mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
+ mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
@@ -125,7 +125,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_io_error(bio);
- mempool_free(mp_bh, conf->pool);
+ mempool_free(mp_bh, &conf->pool);
return true;
}
multipath = conf->multipaths + mp_bh->path;
@@ -378,6 +378,7 @@ static int multipath_run (struct mddev *mddev)
struct multipath_info *disk;
struct md_rdev *rdev;
int working_disks;
+ int ret;
if (md_check_no_bitmap(mddev))
return -EINVAL;
@@ -431,9 +432,9 @@ static int multipath_run (struct mddev *mddev)
}
mddev->degraded = conf->raid_disks - working_disks;
- conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
- sizeof(struct multipath_bh));
- if (conf->pool == NULL)
+ ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
+ sizeof(struct multipath_bh));
+ if (ret)
goto out_free_conf;
mddev->thread = md_register_thread(multipathd, mddev,
@@ -455,7 +456,7 @@ static int multipath_run (struct mddev *mddev)
return 0;
out_free_conf:
- mempool_destroy(conf->pool);
+ mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
@@ -467,7 +468,7 @@ static void multipath_free(struct mddev *mddev, void *priv)
{
struct mpconf *conf = priv;
- mempool_destroy(conf->pool);
+ mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
}
diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h
index 0adb941f485a..b3099e5fc4d7 100644
--- a/drivers/md/md-multipath.h
+++ b/drivers/md/md-multipath.h
@@ -13,7 +13,7 @@ struct mpconf {
spinlock_t device_lock;
struct list_head retry_list;
- mempool_t *pool;
+ mempool_t pool;
};
/*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c208c01f63a5..fc692b7128bb 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -193,10 +193,10 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
{
struct bio *b;
- if (!mddev || !mddev->bio_set)
+ if (!mddev || !bioset_initialized(&mddev->bio_set))
return bio_alloc(gfp_mask, nr_iovecs);
- b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
+ b = bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
if (!b)
return NULL;
return b;
@@ -205,10 +205,10 @@ EXPORT_SYMBOL_GPL(bio_alloc_mddev);
static struct bio *md_bio_alloc_sync(struct mddev *mddev)
{
- if (!mddev || !mddev->sync_set)
+ if (!mddev || !bioset_initialized(&mddev->sync_set))
return bio_alloc(GFP_NOIO, 1);
- return bio_alloc_bioset(GFP_NOIO, 1, mddev->sync_set);
+ return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
}
/*
@@ -510,7 +510,10 @@ static void mddev_delayed_delete(struct work_struct *ws);
static void mddev_put(struct mddev *mddev)
{
- struct bio_set *bs = NULL, *sync_bs = NULL;
+ struct bio_set bs, sync_bs;
+
+ memset(&bs, 0, sizeof(bs));
+ memset(&sync_bs, 0, sizeof(sync_bs));
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
@@ -521,8 +524,8 @@ static void mddev_put(struct mddev *mddev)
list_del_init(&mddev->all_mddevs);
bs = mddev->bio_set;
sync_bs = mddev->sync_set;
- mddev->bio_set = NULL;
- mddev->sync_set = NULL;
+ memset(&mddev->bio_set, 0, sizeof(mddev->bio_set));
+ memset(&mddev->sync_set, 0, sizeof(mddev->sync_set));
if (mddev->gendisk) {
/* We did a probe so need to clean up. Call
* queue_work inside the spinlock so that
@@ -535,10 +538,8 @@ static void mddev_put(struct mddev *mddev)
kfree(mddev);
}
spin_unlock(&all_mddevs_lock);
- if (bs)
- bioset_free(bs);
- if (sync_bs)
- bioset_free(sync_bs);
+ bioset_exit(&bs);
+ bioset_exit(&sync_bs);
}
static void md_safemode_timeout(struct timer_list *t);
@@ -2123,7 +2124,7 @@ int md_integrity_register(struct mddev *mddev)
bdev_get_integrity(reference->bdev));
pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
- if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
+ if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
pr_err("md: failed to create integrity pool for %s\n",
mdname(mddev));
return -EINVAL;
@@ -5497,17 +5498,15 @@ int md_run(struct mddev *mddev)
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
- if (mddev->bio_set == NULL) {
- mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!mddev->bio_set)
- return -ENOMEM;
+ if (!bioset_initialized(&mddev->bio_set)) {
+ err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (err)
+ return err;
}
- if (mddev->sync_set == NULL) {
- mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!mddev->sync_set) {
- err = -ENOMEM;
+ if (!bioset_initialized(&mddev->sync_set)) {
+ err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (err)
goto abort;
- }
}
spin_lock(&pers_lock);
@@ -5668,14 +5667,8 @@ int md_run(struct mddev *mddev)
return 0;
abort:
- if (mddev->bio_set) {
- bioset_free(mddev->bio_set);
- mddev->bio_set = NULL;
- }
- if (mddev->sync_set) {
- bioset_free(mddev->sync_set);
- mddev->sync_set = NULL;
- }
+ bioset_exit(&mddev->bio_set);
+ bioset_exit(&mddev->sync_set);
return err;
}
@@ -5888,14 +5881,8 @@ void md_stop(struct mddev *mddev)
* This is called from dm-raid
*/
__md_stop(mddev);
- if (mddev->bio_set) {
- bioset_free(mddev->bio_set);
- mddev->bio_set = NULL;
- }
- if (mddev->sync_set) {
- bioset_free(mddev->sync_set);
- mddev->sync_set = NULL;
- }
+ bioset_exit(&mddev->bio_set);
+ bioset_exit(&mddev->sync_set);
}
EXPORT_SYMBOL_GPL(md_stop);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index fbc925cce810..3507cab22cb6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -452,8 +452,8 @@ struct mddev {
struct attribute_group *to_remove;
- struct bio_set *bio_set;
- struct bio_set *sync_set; /* for sync operations like
+ struct bio_set bio_set;
+ struct bio_set sync_set; /* for sync operations like
* metadata and bitmap writes
*/
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 584c10347267..65ae47a02218 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -479,7 +479,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
if (bio_end_sector(bio) > zone->zone_end) {
struct bio *split = bio_split(bio,
zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -582,7 +582,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
sector = bio_sector;
if (sectors < bio_sectors(bio)) {
- struct bio *split = bio_split(bio, sectors, GFP_NOIO, mddev->bio_set);
+ struct bio *split = bio_split(bio, sectors, GFP_NOIO,
+ &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e9e3308cb0a7..bad28520719b 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -221,7 +221,7 @@ static void free_r1bio(struct r1bio *r1_bio)
struct r1conf *conf = r1_bio->mddev->private;
put_all_bios(conf, r1_bio);
- mempool_free(r1_bio, conf->r1bio_pool);
+ mempool_free(r1_bio, &conf->r1bio_pool);
}
static void put_buf(struct r1bio *r1_bio)
@@ -236,7 +236,7 @@ static void put_buf(struct r1bio *r1_bio)
rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
}
- mempool_free(r1_bio, conf->r1buf_pool);
+ mempool_free(r1_bio, &conf->r1buf_pool);
lower_barrier(conf, sect);
}
@@ -1178,7 +1178,7 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
- r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+ r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
/* Ensure no bio records IO_BLOCKED */
memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
init_r1bio(r1_bio, mddev, bio);
@@ -1268,7 +1268,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- gfp, conf->bio_split);
+ gfp, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1278,7 +1278,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
r1_bio->read_disk = rdisk;
- read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+ read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
r1_bio->bios[rdisk] = read_bio;
@@ -1439,7 +1439,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- GFP_NOIO, conf->bio_split);
+ GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1479,9 +1479,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (r1_bio->behind_master_bio)
mbio = bio_clone_fast(r1_bio->behind_master_bio,
- GFP_NOIO, mddev->bio_set);
+ GFP_NOIO, &mddev->bio_set);
else
- mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
if (r1_bio->behind_master_bio) {
if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
@@ -1657,8 +1657,7 @@ static void close_sync(struct r1conf *conf)
_allow_barrier(conf, idx);
}
- mempool_destroy(conf->r1buf_pool);
- conf->r1buf_pool = NULL;
+ mempool_exit(&conf->r1buf_pool);
}
static int raid1_spare_active(struct mddev *mddev)
@@ -2348,10 +2347,10 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
wbio = bio_clone_fast(r1_bio->behind_master_bio,
GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
} else {
wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
}
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
@@ -2564,17 +2563,15 @@ static int init_resync(struct r1conf *conf)
int buffs;
buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
- BUG_ON(conf->r1buf_pool);
- conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free,
- conf->poolinfo);
- if (!conf->r1buf_pool)
- return -ENOMEM;
- return 0;
+ BUG_ON(mempool_initialized(&conf->r1buf_pool));
+
+ return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
+ r1buf_pool_free, conf->poolinfo);
}
static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
{
- struct r1bio *r1bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+ struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO);
struct resync_pages *rps;
struct bio *bio;
int i;
@@ -2617,7 +2614,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
int idx = sector_to_idx(sector_nr);
int page_idx = 0;
- if (!conf->r1buf_pool)
+ if (!mempool_initialized(&conf->r1buf_pool))
if (init_resync(conf))
return 0;
@@ -2953,14 +2950,13 @@ static struct r1conf *setup_conf(struct mddev *mddev)
if (!conf->poolinfo)
goto abort;
conf->poolinfo->raid_disks = mddev->raid_disks * 2;
- conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
- r1bio_pool_free,
- conf->poolinfo);
- if (!conf->r1bio_pool)
+ err = mempool_init(&conf->r1bio_pool, NR_RAID1_BIOS, r1bio_pool_alloc,
+ r1bio_pool_free, conf->poolinfo);
+ if (err)
goto abort;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (err)
goto abort;
conf->poolinfo->mddev = mddev;
@@ -3033,7 +3029,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
abort:
if (conf) {
- mempool_destroy(conf->r1bio_pool);
+ mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
@@ -3041,8 +3037,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
return ERR_PTR(err);
@@ -3144,7 +3139,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
{
struct r1conf *conf = priv;
- mempool_destroy(conf->r1bio_pool);
+ mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
@@ -3152,8 +3147,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
@@ -3199,13 +3193,17 @@ static int raid1_reshape(struct mddev *mddev)
* At the same time, we "pack" the devices so that all the missing
* devices have the higher raid_disk numbers.
*/
- mempool_t *newpool, *oldpool;
+ mempool_t newpool, oldpool;
struct pool_info *newpoolinfo;
struct raid1_info *newmirrors;
struct r1conf *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
int d, d2;
+ int ret;
+
+ memset(&newpool, 0, sizeof(newpool));
+ memset(&oldpool, 0, sizeof(oldpool));
/* Cannot change chunk_size, layout, or level */
if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3237,17 +3235,17 @@ static int raid1_reshape(struct mddev *mddev)
newpoolinfo->mddev = mddev;
newpoolinfo->raid_disks = raid_disks * 2;
- newpool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
- r1bio_pool_free, newpoolinfo);
- if (!newpool) {
+ ret = mempool_init(&newpool, NR_RAID1_BIOS, r1bio_pool_alloc,
+ r1bio_pool_free, newpoolinfo);
+ if (ret) {
kfree(newpoolinfo);
- return -ENOMEM;
+ return ret;
}
newmirrors = kzalloc(sizeof(struct raid1_info) * raid_disks * 2,
GFP_KERNEL);
if (!newmirrors) {
kfree(newpoolinfo);
- mempool_destroy(newpool);
+ mempool_exit(&newpool);
return -ENOMEM;
}
@@ -3287,7 +3285,7 @@ static int raid1_reshape(struct mddev *mddev)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- mempool_destroy(oldpool);
+ mempool_exit(&oldpool);
return 0;
}
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index eb84bc68e2fd..e7ccad898736 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -118,10 +118,10 @@ struct r1conf {
* mempools - it changes when the array grows or shrinks
*/
struct pool_info *poolinfo;
- mempool_t *r1bio_pool;
- mempool_t *r1buf_pool;
+ mempool_t r1bio_pool;
+ mempool_t r1buf_pool;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* temporary buffer to synchronous IO when attempting to repair
* a read error.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3c60774c8430..37d4b236b81b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -291,14 +291,14 @@ static void free_r10bio(struct r10bio *r10_bio)
struct r10conf *conf = r10_bio->mddev->private;
put_all_bios(conf, r10_bio);
- mempool_free(r10_bio, conf->r10bio_pool);
+ mempool_free(r10_bio, &conf->r10bio_pool);
}
static void put_buf(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
- mempool_free(r10_bio, conf->r10buf_pool);
+ mempool_free(r10_bio, &conf->r10buf_pool);
lower_barrier(conf);
}
@@ -1204,7 +1204,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
(unsigned long long)r10_bio->sector);
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- gfp, conf->bio_split);
+ gfp, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1213,7 +1213,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
}
slot = r10_bio->read_slot;
- read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+ read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
r10_bio->devs[slot].bio = read_bio;
r10_bio->devs[slot].rdev = rdev;
@@ -1261,7 +1261,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
} else
rdev = conf->mirrors[devnum].rdev;
- mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
if (replacement)
r10_bio->devs[n_copy].repl_bio = mbio;
else
@@ -1509,7 +1509,7 @@ retry_write:
if (r10_bio->sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, r10_bio->sectors,
- GFP_NOIO, conf->bio_split);
+ GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1533,7 +1533,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
struct r10conf *conf = mddev->private;
struct r10bio *r10_bio;
- r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+ r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
r10_bio->sectors = sectors;
@@ -1732,8 +1732,7 @@ static void close_sync(struct r10conf *conf)
wait_barrier(conf);
allow_barrier(conf);
- mempool_destroy(conf->r10buf_pool);
- conf->r10buf_pool = NULL;
+ mempool_exit(&conf->r10buf_pool);
}
static int raid10_spare_active(struct mddev *mddev)
@@ -2583,7 +2582,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
- wbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
wbio->bi_iter.bi_sector = wsector +
@@ -2816,25 +2815,25 @@ static void raid10d(struct md_thread *thread)
static int init_resync(struct r10conf *conf)
{
- int buffs;
- int i;
+ int ret, buffs, i;
buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
- BUG_ON(conf->r10buf_pool);
+ BUG_ON(mempool_initialized(&conf->r10buf_pool));
conf->have_replacement = 0;
for (i = 0; i < conf->geo.raid_disks; i++)
if (conf->mirrors[i].replacement)
conf->have_replacement = 1;
- conf->r10buf_pool = mempool_create(buffs, r10buf_pool_alloc, r10buf_pool_free, conf);
- if (!conf->r10buf_pool)
- return -ENOMEM;
+ ret = mempool_init(&conf->r10buf_pool, buffs,
+ r10buf_pool_alloc, r10buf_pool_free, conf);
+ if (ret)
+ return ret;
conf->next_resync = 0;
return 0;
}
static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
{
- struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ struct r10bio *r10bio = mempool_alloc(&conf->r10buf_pool, GFP_NOIO);
struct rsync_pages *rp;
struct bio *bio;
int nalloc;
@@ -2945,7 +2944,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t chunk_mask = conf->geo.chunk_mask;
int page_idx = 0;
- if (!conf->r10buf_pool)
+ if (!mempool_initialized(&conf->r10buf_pool))
if (init_resync(conf))
return 0;
@@ -3699,13 +3698,13 @@ static struct r10conf *setup_conf(struct mddev *mddev)
conf->geo = geo;
conf->copies = copies;
- conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
- r10bio_pool_free, conf);
- if (!conf->r10bio_pool)
+ err = mempool_init(&conf->r10bio_pool, NR_RAID10_BIOS, r10bio_pool_alloc,
+ r10bio_pool_free, conf);
+ if (err)
goto out;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (err)
goto out;
calc_sectors(conf, mddev->dev_sectors);
@@ -3733,6 +3732,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
init_waitqueue_head(&conf->wait_barrier);
atomic_set(&conf->nr_pending, 0);
+ err = -ENOMEM;
conf->thread = md_register_thread(raid10d, mddev, "raid10");
if (!conf->thread)
goto out;
@@ -3742,11 +3742,10 @@ static struct r10conf *setup_conf(struct mddev *mddev)
out:
if (conf) {
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
return ERR_PTR(err);
@@ -3953,7 +3952,7 @@ static int raid10_run(struct mddev *mddev)
out_free_conf:
md_unregister_thread(&mddev->thread);
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf);
@@ -3966,13 +3965,12 @@ static void raid10_free(struct mddev *mddev, void *priv)
{
struct r10conf *conf = priv;
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf->mirrors_old);
kfree(conf->mirrors_new);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
@@ -4543,7 +4541,7 @@ read_more:
* on all the target devices.
*/
// FIXME
- mempool_free(r10_bio, conf->r10buf_pool);
+ mempool_free(r10_bio, &conf->r10buf_pool);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
return sectors_done;
}
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index e2e8840de9bf..d3eaaf3eb1bc 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -93,10 +93,10 @@ struct r10conf {
*/
wait_queue_head_t wait_barrier;
- mempool_t *r10bio_pool;
- mempool_t *r10buf_pool;
+ mempool_t r10bio_pool;
+ mempool_t r10buf_pool;
struct page *tmppage;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* When taking over an array from a different personality, we store
* the new thread here until we fully activate the array.
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3c65f52b68f5..2b775abf377b 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -125,9 +125,9 @@ struct r5l_log {
struct list_head no_mem_stripes; /* pending stripes, -ENOMEM */
struct kmem_cache *io_kc;
- mempool_t *io_pool;
- struct bio_set *bs;
- mempool_t *meta_pool;
+ mempool_t io_pool;
+ struct bio_set bs;
+ mempool_t meta_pool;
struct md_thread *reclaim_thread;
unsigned long reclaim_target; /* number of space that need to be
@@ -579,7 +579,7 @@ static void r5l_log_endio(struct bio *bio)
md_error(log->rdev->mddev, log->rdev);
bio_put(bio);
- mempool_free(io->meta_page, log->meta_pool);
+ mempool_free(io->meta_page, &log->meta_pool);
spin_lock_irqsave(&log->io_list_lock, flags);
__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
@@ -748,7 +748,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
static struct bio *r5l_bio_alloc(struct r5l_log *log)
{
- struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
+ struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio_set_dev(bio, log->rdev->bdev);
@@ -780,7 +780,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
struct r5l_io_unit *io;
struct r5l_meta_block *block;
- io = mempool_alloc(log->io_pool, GFP_ATOMIC);
+ io = mempool_alloc(&log->io_pool, GFP_ATOMIC);
if (!io)
return NULL;
memset(io, 0, sizeof(*io));
@@ -791,7 +791,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
bio_list_init(&io->flush_barriers);
io->state = IO_UNIT_RUNNING;
- io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO);
+ io->meta_page = mempool_alloc(&log->meta_pool, GFP_NOIO);
block = page_address(io->meta_page);
clear_page(block);
block->magic = cpu_to_le32(R5LOG_MAGIC);
@@ -1223,7 +1223,7 @@ static bool r5l_complete_finished_ios(struct r5l_log *log)
log->next_checkpoint = io->log_start;
list_del(&io->log_sibling);
- mempool_free(io, log->io_pool);
+ mempool_free(io, &log->io_pool);
r5l_run_no_mem_stripe(log);
found = true;
@@ -1647,7 +1647,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
{
struct page *page;
- ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, log->bs);
+ ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
if (!ctx->ra_bio)
return -ENOMEM;
@@ -3066,6 +3066,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
struct request_queue *q = bdev_get_queue(rdev->bdev);
struct r5l_log *log;
char b[BDEVNAME_SIZE];
+ int ret;
pr_debug("md/raid:%s: using device %s as journal\n",
mdname(conf->mddev), bdevname(rdev->bdev, b));
@@ -3111,16 +3112,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
if (!log->io_kc)
goto io_kc;
- log->io_pool = mempool_create_slab_pool(R5L_POOL_SIZE, log->io_kc);
- if (!log->io_pool)
+ ret = mempool_init_slab_pool(&log->io_pool, R5L_POOL_SIZE, log->io_kc);
+ if (ret)
goto io_pool;
- log->bs = bioset_create(R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!log->bs)
+ ret = bioset_init(&log->bs, R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto io_bs;
- log->meta_pool = mempool_create_page_pool(R5L_POOL_SIZE, 0);
- if (!log->meta_pool)
+ ret = mempool_init_page_pool(&log->meta_pool, R5L_POOL_SIZE, 0);
+ if (ret)
goto out_mempool;
spin_lock_init(&log->tree_lock);
@@ -3155,11 +3156,11 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
rcu_assign_pointer(conf->log, NULL);
md_unregister_thread(&log->reclaim_thread);
reclaim_thread:
- mempool_destroy(log->meta_pool);
+ mempool_exit(&log->meta_pool);
out_mempool:
- bioset_free(log->bs);
+ bioset_exit(&log->bs);
io_bs:
- mempool_destroy(log->io_pool);
+ mempool_exit(&log->io_pool);
io_pool:
kmem_cache_destroy(log->io_kc);
io_kc:
@@ -3178,9 +3179,9 @@ void r5l_exit_log(struct r5conf *conf)
wake_up(&conf->mddev->sb_wait);
flush_work(&log->disable_writeback_work);
md_unregister_thread(&log->reclaim_thread);
- mempool_destroy(log->meta_pool);
- bioset_free(log->bs);
- mempool_destroy(log->io_pool);
+ mempool_exit(&log->meta_pool);
+ bioset_exit(&log->bs);
+ mempool_exit(&log->io_pool);
kmem_cache_destroy(log->io_kc);
kfree(log);
}
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 42890a08375b..3a7c36326589 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -105,9 +105,9 @@ struct ppl_conf {
atomic64_t seq; /* current log write sequence number */
struct kmem_cache *io_kc;
- mempool_t *io_pool;
- struct bio_set *bs;
- struct bio_set *flush_bs;
+ mempool_t io_pool;
+ struct bio_set bs;
+ struct bio_set flush_bs;
/* used only for recovery */
int recovered_entries;
@@ -244,7 +244,7 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
struct ppl_header *pplhdr;
struct page *header_page;
- io = mempool_alloc(ppl_conf->io_pool, GFP_NOWAIT);
+ io = mempool_alloc(&ppl_conf->io_pool, GFP_NOWAIT);
if (!io)
return NULL;
@@ -503,7 +503,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
struct bio *prev = bio;
bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
- ppl_conf->bs);
+ &ppl_conf->bs);
bio->bi_opf = prev->bi_opf;
bio_copy_dev(bio, prev);
bio->bi_iter.bi_sector = bio_end_sector(prev);
@@ -570,7 +570,7 @@ static void ppl_io_unit_finished(struct ppl_io_unit *io)
list_del(&io->log_sibling);
spin_unlock(&log->io_list_lock);
- mempool_free(io, ppl_conf->io_pool);
+ mempool_free(io, &ppl_conf->io_pool);
spin_lock(&ppl_conf->no_mem_stripes_lock);
if (!list_empty(&ppl_conf->no_mem_stripes)) {
@@ -642,7 +642,7 @@ static void ppl_do_flush(struct ppl_io_unit *io)
struct bio *bio;
char b[BDEVNAME_SIZE];
- bio = bio_alloc_bioset(GFP_NOIO, 0, ppl_conf->flush_bs);
+ bio = bio_alloc_bioset(GFP_NOIO, 0, &ppl_conf->flush_bs);
bio_set_dev(bio, bdev);
bio->bi_private = io;
bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
@@ -1246,11 +1246,9 @@ static void __ppl_exit_log(struct ppl_conf *ppl_conf)
kfree(ppl_conf->child_logs);
- if (ppl_conf->bs)
- bioset_free(ppl_conf->bs);
- if (ppl_conf->flush_bs)
- bioset_free(ppl_conf->flush_bs);
- mempool_destroy(ppl_conf->io_pool);
+ bioset_exit(&ppl_conf->bs);
+ bioset_exit(&ppl_conf->flush_bs);
+ mempool_exit(&ppl_conf->io_pool);
kmem_cache_destroy(ppl_conf->io_kc);
kfree(ppl_conf);
@@ -1387,24 +1385,18 @@ int ppl_init_log(struct r5conf *conf)
goto err;
}
- ppl_conf->io_pool = mempool_create(conf->raid_disks, ppl_io_pool_alloc,
- ppl_io_pool_free, ppl_conf->io_kc);
- if (!ppl_conf->io_pool) {
- ret = -ENOMEM;
+ ret = mempool_init(&ppl_conf->io_pool, conf->raid_disks, ppl_io_pool_alloc,
+ ppl_io_pool_free, ppl_conf->io_kc);
+ if (ret)
goto err;
- }
- ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS);
- if (!ppl_conf->bs) {
- ret = -ENOMEM;
+ ret = bioset_init(&ppl_conf->bs, conf->raid_disks, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto err;
- }
- ppl_conf->flush_bs = bioset_create(conf->raid_disks, 0, 0);
- if (!ppl_conf->flush_bs) {
- ret = -ENOMEM;
+ ret = bioset_init(&ppl_conf->flush_bs, conf->raid_disks, 0, 0);
+ if (ret)
goto err;
- }
ppl_conf->count = conf->raid_disks;
ppl_conf->child_logs = kcalloc(ppl_conf->count, sizeof(struct ppl_log),
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index be117d0a65a8..a2e64989b01f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5192,7 +5192,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
/*
* use bio_clone_fast to make a copy of the bio
*/
- align_bi = bio_clone_fast(raid_bio, GFP_NOIO, mddev->bio_set);
+ align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
if (!align_bi)
return 0;
/*
@@ -5277,7 +5277,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
if (sectors < bio_sectors(raid_bio)) {
struct r5conf *conf = mddev->private;
- split = bio_split(raid_bio, sectors, GFP_NOIO, conf->bio_split);
+ split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split);
bio_chain(split, raid_bio);
generic_make_request(raid_bio);
raid_bio = split;
@@ -6773,8 +6773,7 @@ static void free_conf(struct r5conf *conf)
if (conf->disks[i].extra_page)
put_page(conf->disks[i].extra_page);
kfree(conf->disks);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf->stripe_hashtbl);
kfree(conf->pending_data);
kfree(conf);
@@ -6853,6 +6852,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
int i;
int group_cnt, worker_cnt_per_group;
struct r5worker_group *new_group;
+ int ret;
if (mddev->new_level != 5
&& mddev->new_level != 4
@@ -6950,8 +6950,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
goto abort;
}
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ ret = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (ret)
goto abort;
conf->mddev = mddev;
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 3f8da26032ac..72e75ba6abf0 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -669,7 +669,7 @@ struct r5conf {
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
struct disk_info *disks;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* When taking over an array from a different personality, we store
* the new thread here until we fully activate the array.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1ae77428a1a5..ef2a0af41fde 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -251,9 +251,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_rq);
void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
- if (!blk_mq_request_started(req))
- return;
-
dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
"Cancelling I/O %d", req->tag);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index ac35a80f5532..0bad65803271 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2393,9 +2393,6 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
- if (!blk_mq_request_started(req))
- return;
-
__nvme_fc_abort_op(ctrl, op);
}
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 44cacd001aa6..ce1321a5cb7b 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -94,8 +94,8 @@ static int iblock_configure_device(struct se_device *dev)
return -EINVAL;
}
- ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!ib_dev->ibd_bio_set) {
+ ret = bioset_init(&ib_dev->ibd_bio_set, IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret) {
pr_err("IBLOCK: Unable to create bioset\n");
goto out;
}
@@ -141,7 +141,7 @@ static int iblock_configure_device(struct se_device *dev)
bi = bdev_get_integrity(bd);
if (bi) {
- struct bio_set *bs = ib_dev->ibd_bio_set;
+ struct bio_set *bs = &ib_dev->ibd_bio_set;
if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-IP") ||
!strcmp(bi->profile->name, "T10-DIF-TYPE1-IP")) {
@@ -174,8 +174,7 @@ static int iblock_configure_device(struct se_device *dev)
out_blkdev_put:
blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
out_free_bioset:
- bioset_free(ib_dev->ibd_bio_set);
- ib_dev->ibd_bio_set = NULL;
+ bioset_exit(&ib_dev->ibd_bio_set);
out:
return ret;
}
@@ -199,8 +198,7 @@ static void iblock_destroy_device(struct se_device *dev)
if (ib_dev->ibd_bd != NULL)
blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
- if (ib_dev->ibd_bio_set != NULL)
- bioset_free(ib_dev->ibd_bio_set);
+ bioset_exit(&ib_dev->ibd_bio_set);
}
static unsigned long long iblock_emulate_read_cap_with_block_size(
@@ -332,7 +330,7 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num, int op,
if (sg_num > BIO_MAX_PAGES)
sg_num = BIO_MAX_PAGES;
- bio = bio_alloc_bioset(GFP_NOIO, sg_num, ib_dev->ibd_bio_set);
+ bio = bio_alloc_bioset(GFP_NOIO, sg_num, &ib_dev->ibd_bio_set);
if (!bio) {
pr_err("Unable to allocate memory for bio\n");
return NULL;
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index b4aeb2584ad4..9cc3843404d4 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -22,7 +22,7 @@ struct iblock_dev {
struct se_device dev;
unsigned char ibd_udev_path[SE_UDEV_PATH_LEN];
u32 ibd_flags;
- struct bio_set *ibd_bio_set;
+ struct bio_set ibd_bio_set;
struct block_device *ibd_bd;
bool ibd_readonly;
} ____cacheline_aligned;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 81c57c14fae8..bef6934b6189 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -272,7 +272,7 @@ struct blkdev_dio {
struct bio bio;
};
-static struct bio_set *blkdev_dio_pool __read_mostly;
+static struct bio_set blkdev_dio_pool;
static void blkdev_bio_end_io(struct bio *bio)
{
@@ -334,7 +334,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
- bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, blkdev_dio_pool);
+ bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
bio_get(bio); /* extra ref for the completion handler */
dio = container_of(bio, struct blkdev_dio, bio);
@@ -432,10 +432,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
static __init int blkdev_init(void)
{
- blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
- if (!blkdev_dio_pool)
- return -ENOMEM;
- return 0;
+ return bioset_init(&blkdev_dio_pool, 4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
}
module_init(blkdev_init);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e99b329002cf..56d32bb462f9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -26,7 +26,7 @@
static struct kmem_cache *extent_state_cache;
static struct kmem_cache *extent_buffer_cache;
-static struct bio_set *btrfs_bioset;
+static struct bio_set btrfs_bioset;
static inline bool extent_state_in_tree(const struct extent_state *state)
{
@@ -162,20 +162,18 @@ int __init extent_io_init(void)
if (!extent_buffer_cache)
goto free_state_cache;
- btrfs_bioset = bioset_create(BIO_POOL_SIZE,
- offsetof(struct btrfs_io_bio, bio),
- BIOSET_NEED_BVECS);
- if (!btrfs_bioset)
+ if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
+ offsetof(struct btrfs_io_bio, bio),
+ BIOSET_NEED_BVECS))
goto free_buffer_cache;
- if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE))
+ if (bioset_integrity_create(&btrfs_bioset, BIO_POOL_SIZE))
goto free_bioset;
return 0;
free_bioset:
- bioset_free(btrfs_bioset);
- btrfs_bioset = NULL;
+ bioset_exit(&btrfs_bioset);
free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
@@ -198,8 +196,7 @@ void __cold extent_io_exit(void)
rcu_barrier();
kmem_cache_destroy(extent_state_cache);
kmem_cache_destroy(extent_buffer_cache);
- if (btrfs_bioset)
- bioset_free(btrfs_bioset);
+ bioset_exit(&btrfs_bioset);
}
void extent_io_tree_init(struct extent_io_tree *tree,
@@ -2679,7 +2676,7 @@ struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte)
{
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = first_byte >> 9;
btrfs_io_bio_init(btrfs_io_bio(bio));
@@ -2692,7 +2689,7 @@ struct bio *btrfs_bio_clone(struct bio *bio)
struct bio *new;
/* Bio allocation backed by a bioset does not fail */
- new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset);
+ new = bio_clone_fast(bio, GFP_NOFS, &btrfs_bioset);
btrfs_bio = btrfs_io_bio(new);
btrfs_io_bio_init(btrfs_bio);
btrfs_bio->iter = bio->bi_iter;
@@ -2704,7 +2701,7 @@ struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs)
struct bio *bio;
/* Bio allocation backed by a bioset does not fail */
- bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, &btrfs_bioset);
btrfs_io_bio_init(btrfs_io_bio(bio));
return bio;
}
@@ -2715,7 +2712,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
struct btrfs_io_bio *btrfs_bio;
/* this will never fail when it's backed by a bioset */
- bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset);
+ bio = bio_clone_fast(orig, GFP_NOFS, &btrfs_bioset);
ASSERT(bio);
btrfs_bio = btrfs_io_bio(bio);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0ab824f574ed..102463543db3 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -594,7 +594,7 @@ xfs_alloc_ioend(
struct xfs_ioend *ioend;
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, xfs_ioend_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
xfs_init_bio_from_bh(bio, bh);
ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 69346d460dfa..694c85b03813 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -18,7 +18,7 @@
#ifndef __XFS_AOPS_H__
#define __XFS_AOPS_H__
-extern struct bio_set *xfs_ioend_bioset;
+extern struct bio_set xfs_ioend_bioset;
/*
* Types of I/O for bmap clustering and I/O completion tracking.
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d71424052917..f643d76db516 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -63,7 +63,7 @@
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
-struct bio_set *xfs_ioend_bioset;
+struct bio_set xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
@@ -1845,10 +1845,9 @@ MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
{
- xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
+ if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
offsetof(struct xfs_ioend, io_inline_bio),
- BIOSET_NEED_BVECS);
- if (!xfs_ioend_bioset)
+ BIOSET_NEED_BVECS))
goto out;
xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
@@ -1997,7 +1996,7 @@ xfs_init_zones(void)
out_destroy_log_ticket_zone:
kmem_zone_destroy(xfs_log_ticket_zone);
out_free_ioend_bioset:
- bioset_free(xfs_ioend_bioset);
+ bioset_exit(&xfs_ioend_bioset);
out:
return -ENOMEM;
}
@@ -2029,7 +2028,7 @@ xfs_destroy_zones(void)
kmem_zone_destroy(xfs_btree_cur_zone);
kmem_zone_destroy(xfs_bmap_free_item_zone);
kmem_zone_destroy(xfs_log_ticket_zone);
- bioset_free(xfs_ioend_bioset);
+ bioset_exit(&xfs_ioend_bioset);
}
STATIC int __init
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 98b175cc00d5..810a8bee8f85 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -410,14 +410,12 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
return bio_split(bio, sectors, gfp, bs);
}
-extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
-extern void bioset_exit(struct bio_set *);
-extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags);
enum {
BIOSET_NEED_BVECS = BIT(0),
BIOSET_NEED_RESCUER = BIT(1),
};
-extern void bioset_free(struct bio_set *);
+extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
+extern void bioset_exit(struct bio_set *);
extern int biovec_init_pool(mempool_t *pool, int pool_entries);
extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
@@ -760,6 +758,11 @@ struct biovec_slab {
struct kmem_cache *slab;
};
+static inline bool bioset_initialized(struct bio_set *bs)
+{
+ return bs->bio_slab != NULL;
+}
+
/*
* a small number of entries is fine, not going to be performance critical.
* basically we just need to survive
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ebc34a5686dc..fb355173f3c7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -259,7 +259,8 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
void blk_mq_complete_request(struct request *rq);
-
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+ struct bio *bio);
bool blk_mq_queue_stopped(struct request_queue *q);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4efd9af62e25..bca3a92eb55f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -652,7 +652,7 @@ struct request_queue {
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
#ifdef CONFIG_BLK_DEBUG_FS
struct dentry *debugfs_dir;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 6d9e230dffd2..a02deea30185 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -218,8 +218,6 @@ extern void elv_unregister(struct elevator_type *);
extern ssize_t elv_iosched_show(struct request_queue *, char *);
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
-extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct request_queue *, struct elevator_queue *);
extern bool elv_bio_merge_ok(struct request *, struct bio *);
extern struct elevator_queue *elevator_alloc(struct request_queue *,
struct elevator_type *);
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 93d142ad1528..174601554b06 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -186,7 +186,7 @@ struct pktcdvd_device
sector_t current_sector; /* Keep track of where the elevator is */
atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */
/* needs to be run. */
- mempool_t *rb_pool; /* mempool for pkt_rb_node allocations */
+ mempool_t rb_pool; /* mempool for pkt_rb_node allocations */
struct packet_iosched iosched;
struct gendisk *disk;