diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 442a6e937b19..3db9a04aec6e 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -289,3 +289,5 @@ ENTRY(sys_call_table)
.long sys_add_key
.long sys_request_key
.long sys_keyctl
+ .long sys_ioprio_set
+ .long sys_ioprio_get /* 290 */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index b1d5d3d5276c..785a51b0ad8e 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1577,8 +1577,8 @@ sys_call_table:
data8 sys_add_key
data8 sys_request_key
data8 sys_keyctl
- data8 sys_ni_syscall
- data8 sys_ni_syscall // 1275
+ data8 sys_ioprio_set
+ data8 sys_ioprio_get // 1275
data8 sys_set_zone_reclaim
data8 sys_ni_syscall
data8 sys_ni_syscall
diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
index b6a63a49a232..191a8def3bdb 100644
--- a/arch/ppc/kernel/misc.S
+++ b/arch/ppc/kernel/misc.S
@@ -1449,3 +1449,5 @@ _GLOBAL(sys_call_table)
.long sys_request_key /* 270 */
.long sys_keyctl
.long sys_waitid
+ .long sys_ioprio_set
+ .long sys_ioprio_get
diff --git a/drivers/block/as-iosched.c b/drivers/block/as-iosched.c
index 3410b4d294b9..91aeb678135d 100644
--- a/drivers/block/as-iosched.c
+++ b/drivers/block/as-iosched.c
@@ -1806,7 +1806,8 @@ static void as_put_request(request_queue_t *q, struct request *rq)
rq->elevator_private = NULL;
}
-static int as_set_request(request_queue_t *q, struct request *rq, int gfp_mask)
+static int as_set_request(request_queue_t *q, struct request *rq,
+ struct bio *bio, int gfp_mask)
{
struct as_data *ad = q->elevator->elevator_data;
struct as_rq *arq = mempool_alloc(ad->arq_pool, gfp_mask);
@@ -1827,7 +1828,7 @@ static int as_set_request(request_queue_t *q, struct request *rq, int gfp_mask)
return 1;
}
-static int as_may_queue(request_queue_t *q, int rw)
+static int as_may_queue(request_queue_t *q, int rw, struct bio *bio)
{
int ret = ELV_MQUEUE_MAY;
struct as_data *ad = q->elevator->elevator_data;
diff --git a/drivers/block/cfq-iosched.c b/drivers/block/cfq-iosched.c
index 3ac47dde64da..35f6e569d5e5 100644
--- a/drivers/block/cfq-iosched.c
+++ b/drivers/block/cfq-iosched.c
@@ -21,22 +21,33 @@
#include <linux/hash.h>
#include <linux/rbtree.h>
#include <linux/mempool.h>
-
-static unsigned long max_elapsed_crq;
-static unsigned long max_elapsed_dispatch;
+#include <linux/ioprio.h>
+#include <linux/writeback.h>
/*
* tunables
*/
static int cfq_quantum = 4; /* max queue in one round of service */
static int cfq_queued = 8; /* minimum rq allocate limit per-queue*/
-static int cfq_service = HZ; /* period over which service is avg */
-static int cfq_fifo_expire_r = HZ / 2; /* fifo timeout for sync requests */
-static int cfq_fifo_expire_w = 5 * HZ; /* fifo timeout for async requests */
-static int cfq_fifo_rate = HZ / 8; /* fifo expiry rate */
+static int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
static int cfq_back_max = 16 * 1024; /* maximum backwards seek, in KiB */
static int cfq_back_penalty = 2; /* penalty of a backwards seek */
+static int cfq_slice_sync = HZ / 10;
+static int cfq_slice_async = HZ / 50;
+static int cfq_slice_async_rq = 2;
+static int cfq_slice_idle = HZ / 50;
+
+#define CFQ_IDLE_GRACE (HZ / 10)
+#define CFQ_SLICE_SCALE (5)
+
+#define CFQ_KEY_ASYNC (0)
+
+/*
+ * disable queueing at the driver/hardware level
+ */
+static int cfq_max_depth = 1;
+
/*
* for the hash of cfqq inside the cfqd
*/
@@ -55,6 +66,7 @@ static int cfq_back_penalty = 2; /* penalty of a backwards seek */
#define list_entry_hash(ptr) hlist_entry((ptr), struct cfq_rq, hash)
#define list_entry_cfqq(ptr) list_entry((ptr), struct cfq_queue, cfq_list)
+#define list_entry_fifo(ptr) list_entry((ptr), struct request, queuelist)
#define RQ_DATA(rq) (rq)->elevator_private
@@ -75,78 +87,101 @@ static int cfq_back_penalty = 2; /* penalty of a backwards seek */
#define rb_entry_crq(node) rb_entry((node), struct cfq_rq, rb_node)
#define rq_rb_key(rq) (rq)->sector
-/*
- * threshold for switching off non-tag accounting
- */
-#define CFQ_MAX_TAG (4)
-
-/*
- * sort key types and names
- */
-enum {
- CFQ_KEY_PGID,
- CFQ_KEY_TGID,
- CFQ_KEY_UID,
- CFQ_KEY_GID,
- CFQ_KEY_LAST,
-};
-
-static char *cfq_key_types[] = { "pgid", "tgid", "uid", "gid", NULL };
-
static kmem_cache_t *crq_pool;
static kmem_cache_t *cfq_pool;
static kmem_cache_t *cfq_ioc_pool;
+#define CFQ_PRIO_LISTS IOPRIO_BE_NR
+#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define cfq_class_be(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_BE)
+#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define cfq_cfqq_sync(cfqq) ((cfqq)->key != CFQ_KEY_ASYNC)
+
+/*
+ * Per block device queue structure
+ */
struct cfq_data {
- struct list_head rr_list;
+ atomic_t ref;
+ request_queue_t *queue;
+
+ /*
+ * rr list of queues with requests and the count of them
+ */
+ struct list_head rr_list[CFQ_PRIO_LISTS];
+ struct list_head busy_rr;
+ struct list_head cur_rr;
+ struct list_head idle_rr;
+ unsigned int busy_queues;
+
+ /*
+ * non-ordered list of empty cfqq's
+ */
struct list_head empty_list;
+ /*
+ * cfqq lookup hash
+ */
struct hlist_head *cfq_hash;
- struct hlist_head *crq_hash;
- /* queues on rr_list (ie they have pending requests */
- unsigned int busy_queues;
+ /*
+ * global crq hash for all queues
+ */
+ struct hlist_head *crq_hash;
unsigned int max_queued;
- atomic_t ref;
-
- int key_type;
-
mempool_t *crq_pool;
- request_queue_t *queue;
+ int rq_in_driver;
+
+ /*
+ * schedule slice state info
+ */
+ /*
+ * idle window management
+ */
+ struct timer_list idle_slice_timer;
+ struct work_struct unplug_work;
+
+ struct cfq_queue *active_queue;
+ struct cfq_io_context *active_cic;
+ int cur_prio, cur_end_prio;
+ unsigned int dispatch_slice;
+
+ struct timer_list idle_class_timer;
sector_t last_sector;
+ unsigned long last_end_request;
- int rq_in_driver;
+ unsigned int rq_starved;
/*
* tunables, see top of file
*/
unsigned int cfq_quantum;
unsigned int cfq_queued;
- unsigned int cfq_fifo_expire_r;
- unsigned int cfq_fifo_expire_w;
- unsigned int cfq_fifo_batch_expire;
+ unsigned int cfq_fifo_expire[2];
unsigned int cfq_back_penalty;
unsigned int cfq_back_max;
- unsigned int find_best_crq;
-
- unsigned int cfq_tagged;
+ unsigned int cfq_slice[2];
+ unsigned int cfq_slice_async_rq;
+ unsigned int cfq_slice_idle;
+ unsigned int cfq_max_depth;
};
+/*
+ * Per process-grouping structure
+ */
struct cfq_queue {
/* reference count */
atomic_t ref;
/* parent cfq_data */
struct cfq_data *cfqd;
- /* hash of mergeable requests */
+ /* cfqq lookup hash */
struct hlist_node cfq_hash;
/* hash key */
- unsigned long key;
- /* whether queue is on rr (or empty) list */
- int on_rr;
+ unsigned int key;
/* on either rr or empty list of cfqd */
struct list_head cfq_list;
/* sorted list of pending requests */
@@ -158,21 +193,35 @@ struct cfq_queue {
/* currently allocated requests */
int allocated[2];
/* fifo list of requests in sort_list */
- struct list_head fifo[2];
- /* last time fifo expired */
- unsigned long last_fifo_expire;
+ struct list_head fifo;
- int key_type;
-
- unsigned long service_start;
- unsigned long service_used;
-
- unsigned int max_rate;
+ unsigned long slice_start;
+ unsigned long slice_end;
+ unsigned long slice_left;
+ unsigned long service_last;
/* number of requests that have been handed to the driver */
int in_flight;
- /* number of currently allocated requests */
- int alloc_limit[2];
+
+ /* io prio of this group */
+ unsigned short ioprio, org_ioprio;
+ unsigned short ioprio_class, org_ioprio_class;
+
+ /* whether queue is on rr (or empty) list */
+ unsigned on_rr : 1;
+ /* idle slice, waiting for new request submission */
+ unsigned wait_request : 1;
+ /* set when wait_request gets set, reset on first rq alloc */
+ unsigned must_alloc : 1;
+ /* only gets one must_alloc per slice */
+ unsigned must_alloc_slice : 1;
+ /* idle slice, request added, now waiting to dispatch it */
+ unsigned must_dispatch : 1;
+ /* fifo expire per-slice */
+ unsigned fifo_expire : 1;
+
+ unsigned idle_window : 1;
+ unsigned prio_changed : 1;
};
struct cfq_rq {
@@ -184,42 +233,17 @@ struct cfq_rq {
struct cfq_queue *cfq_queue;
struct cfq_io_context *io_context;
- unsigned long service_start;
- unsigned long queue_start;
-
- unsigned int in_flight : 1;
- unsigned int accounted : 1;
- unsigned int is_sync : 1;
- unsigned int is_write : 1;
+ unsigned in_flight : 1;
+ unsigned accounted : 1;
+ unsigned is_sync : 1;
+ unsigned requeued : 1;
};
-static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned long);
+static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int);
static void cfq_dispatch_sort(request_queue_t *, struct cfq_rq *);
-static void cfq_update_next_crq(struct cfq_rq *);
static void cfq_put_cfqd(struct cfq_data *cfqd);
-/*
- * what the fairness is based on (ie how processes are grouped and
- * differentiated)
- */
-static inline unsigned long
-cfq_hash_key(struct cfq_data *cfqd, struct task_struct *tsk)
-{
- /*
- * optimize this so that ->key_type is the offset into the struct
- */
- switch (cfqd->key_type) {
- case CFQ_KEY_PGID:
- return process_group(tsk);
- default:
- case CFQ_KEY_TGID:
- return tsk->tgid;
- case CFQ_KEY_UID:
- return tsk->uid;
- case CFQ_KEY_GID:
- return tsk->gid;
- }
-}
+#define process_sync(tsk) ((tsk)->flags & PF_SYNCWRITE)
/*
* lots of deadline iosched dupes, can be abstracted later...
@@ -235,16 +259,12 @@ static void cfq_remove_merge_hints(request_queue_t *q, struct cfq_rq *crq)
if (q->last_merge == crq->request)
q->last_merge = NULL;
-
- cfq_update_next_crq(crq);
}
static inline void cfq_add_crq_hash(struct cfq_data *cfqd, struct cfq_rq *crq)
{
const int hash_idx = CFQ_MHASH_FN(rq_hash_key(crq->request));
- BUG_ON(!hlist_unhashed(&crq->hash));
-
hlist_add_head(&crq->hash, &cfqd->crq_hash[hash_idx]);
}
@@ -257,8 +277,6 @@ static struct request *cfq_find_rq_hash(struct cfq_data *cfqd, sector_t offset)
struct cfq_rq *crq = list_entry_hash(entry);
struct request *__rq = crq->request;
- BUG_ON(hlist_unhashed(&crq->hash));
-
if (!rq_mergeable(__rq)) {
cfq_del_crq_hash(crq);
continue;
@@ -287,36 +305,16 @@ cfq_choose_req(struct cfq_data *cfqd, struct cfq_rq *crq1, struct cfq_rq *crq2)
return crq2;
if (crq2 == NULL)
return crq1;
+ if (crq1->requeued)
+ return crq1;
+ if (crq2->requeued)
+ return crq2;
s1 = crq1->request->sector;
s2 = crq2->request->sector;
last = cfqd->last_sector;
-#if 0
- if (!list_empty(&cfqd->queue->queue_head)) {
- struct list_head *entry = &cfqd->queue->queue_head;
- unsigned long distance = ~0UL;
- struct request *rq;
-
- while ((entry = entry->prev) != &cfqd->queue->queue_head) {
- rq = list_entry_rq(entry);
-
- if (blk_barrier_rq(rq))
- break;
-
- if (distance < abs(s1 - rq->sector + rq->nr_sectors)) {
- distance = abs(s1 - rq->sector +rq->nr_sectors);
- last = rq->sector + rq->nr_sectors;
- }
- if (distance < abs(s2 - rq->sector + rq->nr_sectors)) {
- distance = abs(s2 - rq->sector +rq->nr_sectors);
- last = rq->sector + rq->nr_sectors;
- }
- }
- }
-#endif
-
/*
* by definition, 1KiB is 2 sectors
*/
@@ -377,11 +375,13 @@ cfq_find_next_crq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct cfq_rq *crq_next = NULL, *crq_prev = NULL;
struct rb_node *rbnext, *rbprev;
- if (!ON_RB(&last->rb_node))
- return NULL;
-
- if ((rbnext = rb_next(&last->rb_node)) == NULL)
+ if (ON_RB(&last->rb_node))
+ rbnext = rb_next(&last->rb_node);
+ else {
rbnext = rb_first(&cfqq->sort_list);
+ if (rbnext == &last->rb_node)
+ rbnext = NULL;
+ }
rbprev = rb_prev(&last->rb_node);
@@ -401,67 +401,53 @@ static void cfq_update_next_crq(struct cfq_rq *crq)
cfqq->next_crq = cfq_find_next_crq(cfqq->cfqd, cfqq, crq);
}
-static int cfq_check_sort_rr_list(struct cfq_queue *cfqq)
+static void cfq_resort_rr_list(struct cfq_queue *cfqq, int preempted)
{
- struct list_head *head = &cfqq->cfqd->rr_list;
- struct list_head *next, *prev;
+ struct cfq_data *cfqd = cfqq->cfqd;
+ struct list_head *list, *entry;
- /*
- * list might still be ordered
- */
- next = cfqq->cfq_list.next;
- if (next != head) {
- struct cfq_queue *cnext = list_entry_cfqq(next);
-
- if (cfqq->service_used > cnext->service_used)
- return 1;
- }
-
- prev = cfqq->cfq_list.prev;
- if (prev != head) {
- struct cfq_queue *cprev = list_entry_cfqq(prev);
-
- if (cfqq->service_used < cprev->service_used)
- return 1;
- }
-
- return 0;
-}
-
-static void cfq_sort_rr_list(struct cfq_queue *cfqq, int new_queue)
-{
- struct list_head *entry = &cfqq->cfqd->rr_list;
-
- if (!cfqq->on_rr)
- return;
- if (!new_queue && !cfq_check_sort_rr_list(cfqq))
- return;
+ BUG_ON(!cfqq->on_rr);
list_del(&cfqq->cfq_list);
+ if (cfq_class_rt(cfqq))
+ list = &cfqd->cur_rr;
+ else if (cfq_class_idle(cfqq))
+ list = &cfqd->idle_rr;
+ else {
+ /*
+ * if cfqq has requests in flight, don't allow it to be
+ * found in cfq_set_active_queue before it has finished them.
+ * this is done to increase fairness between a process that
+ * has lots of io pending vs one that only generates one
+ * sporadically or synchronously
+ */
+ if (cfqq->in_flight)
+ list = &cfqd->busy_rr;
+ else
+ list = &cfqd->rr_list[cfqq->ioprio];
+ }
+
/*
- * sort by our mean service_used, sub-sort by in-flight requests
+ * if queue was preempted, just add to front to be fair. busy_rr
+ * isn't sorted.
*/
- while ((entry = entry->prev) != &cfqq->cfqd->rr_list) {
+ if (preempted || list == &cfqd->busy_rr) {
+ list_add(&cfqq->cfq_list, list);
+ return;
+ }
+
+ /*
+ * sort by when queue was last serviced
+ */
+ entry = list;
+ while ((entry = entry->prev) != list) {
struct cfq_queue *__cfqq = list_entry_cfqq(entry);
- if (cfqq->service_used > __cfqq->service_used)
+ if (!__cfqq->service_last)
+ break;
+ if (time_before(__cfqq->service_last, cfqq->service_last))
break;
- else if (cfqq->service_used == __cfqq->service_used) {
- struct list_head *prv;
-
- while ((prv = entry->prev) != &cfqq->cfqd->rr_list) {
- __cfqq = list_entry_cfqq(prv);
-
- WARN_ON(__cfqq->service_used > cfqq->service_used);
- if (cfqq->service_used != __cfqq->service_used)
- break;
- if (cfqq->in_flight > __cfqq->in_flight)
- break;
-
- entry = prv;
- }
- }
}
list_add(&cfqq->cfq_list, entry);
@@ -469,28 +455,24 @@ static void cfq_sort_rr_list(struct cfq_queue *cfqq, int new_queue)
/*
* add to busy list of queues for service, trying to be fair in ordering
- * the pending list according to requests serviced
+ * the pending list according to last request service
*/
static inline void
-cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq, int requeue)
{
- /*
- * it's currently on the empty list
- */
+ BUG_ON(cfqq->on_rr);
cfqq->on_rr = 1;
cfqd->busy_queues++;
- if (time_after(jiffies, cfqq->service_start + cfq_service))
- cfqq->service_used >>= 3;
-
- cfq_sort_rr_list(cfqq, 1);
+ cfq_resort_rr_list(cfqq, requeue);
}
static inline void
cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- list_move(&cfqq->cfq_list, &cfqd->empty_list);
+ BUG_ON(!cfqq->on_rr);
cfqq->on_rr = 0;
+ list_move(&cfqq->cfq_list, &cfqd->empty_list);
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
@@ -505,16 +487,17 @@ static inline void cfq_del_crq_rb(struct cfq_rq *crq)
if (ON_RB(&crq->rb_node)) {
struct cfq_data *cfqd = cfqq->cfqd;
+ const int sync = crq->is_sync;
- BUG_ON(!cfqq->queued[crq->is_sync]);
+ BUG_ON(!cfqq->queued[sync]);
+ cfqq->queued[sync]--;
cfq_update_next_crq(crq);
- cfqq->queued[crq->is_sync]--;
rb_erase(&crq->rb_node, &cfqq->sort_list);
RB_CLEAR_COLOR(&crq->rb_node);
- if (RB_EMPTY(&cfqq->sort_list) && cfqq->on_rr)
+ if (cfqq->on_rr && RB_EMPTY(&cfqq->sort_list))
cfq_del_cfqq_rr(cfqd, cfqq);
}
}
@@ -562,7 +545,7 @@ static void cfq_add_crq_rb(struct cfq_rq *crq)
rb_insert_color(&crq->rb_node, &cfqq->sort_list);
if (!cfqq->on_rr)
- cfq_add_cfqq_rr(cfqd, cfqq);
+ cfq_add_cfqq_rr(cfqd, cfqq, crq->requeued);
/*
* check if this request is a better next-serve candidate
@@ -581,11 +564,10 @@ cfq_reposition_crq_rb(struct cfq_queue *cfqq, struct cfq_rq *crq)
cfq_add_crq_rb(crq);
}
-static struct request *
-cfq_find_rq_rb(struct cfq_data *cfqd, sector_t sector)
+static struct request *cfq_find_rq_rb(struct cfq_data *cfqd, sector_t sector)
+
{
- const unsigned long key = cfq_hash_key(cfqd, current);
- struct cfq_queue *cfqq = cfq_find_cfq_hash(cfqd, key);
+ struct cfq_queue *cfqq = cfq_find_cfq_hash(cfqd, current->pid);
struct rb_node *n;
if (!cfqq)
@@ -609,20 +591,23 @@ out:
static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
{
+ struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_rq *crq = RQ_DATA(rq);
if (crq) {
struct cfq_queue *cfqq = crq->cfq_queue;
- if (cfqq->cfqd->cfq_tagged) {
- cfqq->service_used--;
- cfq_sort_rr_list(cfqq, 0);
- }
-
if (crq->accounted) {
crq->accounted = 0;
- cfqq->cfqd->rq_in_driver--;
+ WARN_ON(!cfqd->rq_in_driver);
+ cfqd->rq_in_driver--;
}
+ if (crq->in_flight) {
+ crq->in_flight = 0;
+ WARN_ON(!cfqq->in_flight);
+ cfqq->in_flight--;
+ }
+ crq->requeued = 1;
}
}
@@ -640,11 +625,10 @@ static void cfq_remove_request(request_queue_t *q, struct request *rq)
struct cfq_rq *crq = RQ_DATA(rq);
if (crq) {
- cfq_remove_merge_hints(q, crq);
list_del_init(&rq->queuelist);
+ cfq_del_crq_rb(crq);
+ cfq_remove_merge_hints(q, crq);
- if (crq->cfq_queue)
- cfq_del_crq_rb(crq);
}
}
@@ -662,21 +646,15 @@ cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
}
__rq = cfq_find_rq_hash(cfqd, bio->bi_sector);
- if (__rq) {
- BUG_ON(__rq->sector + __rq->nr_sectors != bio->bi_sector);
-
- if (elv_rq_merge_ok(__rq, bio)) {
- ret = ELEVATOR_BACK_MERGE;
- goto out;
- }
+ if (__rq && elv_rq_merge_ok(__rq, bio)) {
+ ret = ELEVATOR_BACK_MERGE;
+ goto out;
}
__rq = cfq_find_rq_rb(cfqd, bio->bi_sector + bio_sectors(bio));
- if (__rq) {
- if (elv_rq_merge_ok(__rq, bio)) {
- ret = ELEVATOR_FRONT_MERGE;
- goto out;
- }
+ if (__rq && elv_rq_merge_ok(__rq, bio)) {
+ ret = ELEVATOR_FRONT_MERGE;
+ goto out;
}
return ELEVATOR_NO_MERGE;
@@ -709,20 +687,194 @@ static void
cfq_merged_requests(request_queue_t *q, struct request *rq,
struct request *next)
{
- struct cfq_rq *crq = RQ_DATA(rq);
- struct cfq_rq *cnext = RQ_DATA(next);
-
cfq_merged_request(q, rq);
- if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist)) {
- if (time_before(cnext->queue_start, crq->queue_start)) {
- list_move(&rq->queuelist, &next->queuelist);
- crq->queue_start = cnext->queue_start;
+ /*
+ * reposition in fifo if next is older than rq
+ */
+ if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+ time_before(next->start_time, rq->start_time))
+ list_move(&rq->queuelist, &next->queuelist);
+
+ cfq_remove_request(q, next);
+}
+
+static inline void
+__cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ if (cfqq) {
+ /*
+ * stop potential idle class queues waiting service
+ */
+ del_timer(&cfqd->idle_class_timer);
+
+ cfqq->slice_start = jiffies;
+ cfqq->slice_end = 0;
+ cfqq->slice_left = 0;
+ cfqq->must_alloc_slice = 0;
+ cfqq->fifo_expire = 0;
+ }
+
+ cfqd->active_queue = cfqq;
+}
+
+/*
+ * 0
+ * 0,1
+ * 0,1,2
+ * 0,1,2,3
+ * 0,1,2,3,4
+ * 0,1,2,3,4,5
+ * 0,1,2,3,4,5,6
+ * 0,1,2,3,4,5,6,7
+ */
+static int cfq_get_next_prio_level(struct cfq_data *cfqd)
+{
+ int prio, wrap;
+
+ prio = -1;
+ wrap = 0;
+ do {
+ int p;
+
+ for (p = cfqd->cur_prio; p <= cfqd->cur_end_prio; p++) {
+ if (!list_empty(&cfqd->rr_list[p])) {
+ prio = p;
+ break;
+ }
+ }
+
+ if (prio != -1)
+ break;
+ cfqd->cur_prio = 0;
+ if (++cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
+ cfqd->cur_end_prio = 0;
+ if (wrap)
+ break;
+ wrap = 1;
+ }
+ } while (1);
+
+ if (unlikely(prio == -1))
+ return -1;
+
+ BUG_ON(prio >= CFQ_PRIO_LISTS);
+
+ list_splice_init(&cfqd->rr_list[prio], &cfqd->cur_rr);
+
+ cfqd->cur_prio = prio + 1;
+ if (cfqd->cur_prio > cfqd->cur_end_prio) {
+ cfqd->cur_end_prio = cfqd->cur_prio;
+ cfqd->cur_prio = 0;
+ }
+ if (cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
+ cfqd->cur_prio = 0;
+ cfqd->cur_end_prio = 0;
+ }
+
+ return prio;
+}
+
+static void cfq_set_active_queue(struct cfq_data *cfqd)
+{
+ struct cfq_queue *cfqq = NULL;
+
+ /*
+ * if current list is non-empty, grab first entry. if it is empty,
+ * get next prio level and grab first entry then if any are spliced
+ */
+ if (!list_empty(&cfqd->cur_rr) || cfq_get_next_prio_level(cfqd) != -1)
+ cfqq = list_entry_cfqq(cfqd->cur_rr.next);
+
+ /*
+ * if we have idle queues and no rt or be queues had pending
+ * requests, either allow immediate service if the grace period
+ * has passed or arm the idle grace timer
+ */
+ if (!cfqq && !list_empty(&cfqd->idle_rr)) {
+ unsigned long end = cfqd->last_end_request + CFQ_IDLE_GRACE;
+
+ if (time_after_eq(jiffies, end))
+ cfqq = list_entry_cfqq(cfqd->idle_rr.next);
+ else
+ mod_timer(&cfqd->idle_class_timer, end);
+ }
+
+ __cfq_set_active_queue(cfqd, cfqq);
+}
+
+/*
+ * current cfqq expired its slice (or was too idle), select new one
+ */
+static inline void cfq_slice_expired(struct cfq_data *cfqd, int preempted)
+{
+ struct cfq_queue *cfqq = cfqd->active_queue;
+
+ if (cfqq) {
+ unsigned long now = jiffies;
+
+ if (cfqq->wait_request)
+ del_timer(&cfqd->idle_slice_timer);
+
+ if (!preempted && !cfqq->in_flight)
+ cfqq->service_last = now;
+
+ cfqq->must_dispatch = 0;
+ cfqq->wait_request = 0;
+
+ /*
+ * store what was left of this slice, if the queue idled out
+ * or was preempted
+ */
+ if (time_after(now, cfqq->slice_end))
+ cfqq->slice_left = now - cfqq->slice_end;
+ else
+ cfqq->slice_left = 0;
+
+ if (cfqq->on_rr)
+ cfq_resort_rr_list(cfqq, preempted);
+
+ cfqd->active_queue = NULL;
+
+ if (cfqd->active_cic) {
+ put_io_context(cfqd->active_cic->ioc);
+ cfqd->active_cic = NULL;
}
}
- cfq_update_next_crq(cnext);
- cfq_remove_request(q, next);
+ cfqd->dispatch_slice = 0;
+}
+
+static int cfq_arm_slice_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+
+{
+ WARN_ON(!RB_EMPTY(&cfqq->sort_list));
+ WARN_ON(cfqq != cfqd->active_queue);
+
+ /*
+ * idle is disabled, either manually or by past process history
+ */
+ if (!cfqd->cfq_slice_idle)
+ return 0;
+ if (!cfqq->idle_window)
+ return 0;
+ /*
+ * task has exited, don't wait
+ */
+ if (cfqd->active_cic && !cfqd->active_cic->ioc->task)
+ return 0;
+
+ cfqq->wait_request = 1;
+ cfqq->must_alloc = 1;
+
+ if (!timer_pending(&cfqd->idle_slice_timer)) {
+ unsigned long slice_left = cfqq->slice_end - 1;
+
+ cfqd->idle_slice_timer.expires = min(jiffies + cfqd->cfq_slice_idle, slice_left);
+ add_timer(&cfqd->idle_slice_timer);
+ }
+
+ return 1;
}
/*
@@ -738,31 +890,39 @@ static void cfq_dispatch_sort(request_queue_t *q, struct cfq_rq *crq)
struct request *__rq;
sector_t last;
- cfq_del_crq_rb(crq);
- cfq_remove_merge_hints(q, crq);
list_del(&crq->request->queuelist);
last = cfqd->last_sector;
- while ((entry = entry->prev) != head) {
- __rq = list_entry_rq(entry);
+ list_for_each_entry_reverse(__rq, head, queuelist) {
+ struct cfq_rq *__crq = RQ_DATA(__rq);
- if (blk_barrier_rq(crq->request))
+ if (blk_barrier_rq(__rq))
break;
- if (!blk_fs_request(crq->request))
+ if (!blk_fs_request(__rq))
+ break;
+ if (__crq->requeued)
break;
- if (crq->request->sector > __rq->sector)
+ if (__rq->sector <= crq->request->sector)
break;
if (__rq->sector > last && crq->request->sector < last) {
- last = crq->request->sector;
+ last = crq->request->sector + crq->request->nr_sectors;
break;
}
+ entry = &__rq->queuelist;
}
cfqd->last_sector = last;
+
+ cfqq->next_crq = cfq_find_next_crq(cfqd, cfqq, crq);
+
+ cfq_del_crq_rb(crq);
+ cfq_remove_merge_hints(q, crq);
+
crq->in_flight = 1;
+ crq->requeued = 0;
cfqq->in_flight++;
- list_add(&crq->request->queuelist, entry);
+ list_add_tail(&crq->request->queuelist, entry);
}
/*
@@ -771,105 +931,176 @@ static void cfq_dispatch_sort(request_queue_t *q, struct cfq_rq *crq)
static inline struct cfq_rq *cfq_check_fifo(struct cfq_queue *cfqq)
{
struct cfq_data *cfqd = cfqq->cfqd;
- const int reads = !list_empty(&cfqq->fifo[0]);
- const int writes = !list_empty(&cfqq->fifo[1]);
- unsigned long now = jiffies;
+ struct request *rq;
struct cfq_rq *crq;
- if (time_before(now, cfqq->last_fifo_expire + cfqd->cfq_fifo_batch_expire))
+ if (cfqq->fifo_expire)
return NULL;
- crq = RQ_DATA(list_entry(cfqq->fifo[0].next, struct request, queuelist));
- if (reads && time_after(now, crq->queue_start + cfqd->cfq_fifo_expire_r)) {
- cfqq->last_fifo_expire = now;
- return crq;
- }
+ if (!list_empty(&cfqq->fifo)) {
+ int fifo = cfq_cfqq_sync(cfqq);
- crq = RQ_DATA(list_entry(cfqq->fifo[1].next, struct request, queuelist));
- if (writes && time_after(now, crq->queue_start + cfqd->cfq_fifo_expire_w)) {
- cfqq->last_fifo_expire = now;
- return crq;
+ crq = RQ_DATA(list_entry_fifo(cfqq->fifo.next));
+ rq = crq->request;
+ if (time_after(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo])) {
+ cfqq->fifo_expire = 1;
+ return crq;
+ }
}
return NULL;
}
/*
- * dispatch a single request from given queue
+ * Scale schedule slice based on io priority
*/
-static inline void
-cfq_dispatch_request(request_queue_t *q, struct cfq_data *cfqd,
- struct cfq_queue *cfqq)
+static inline int
+cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- struct cfq_rq *crq;
+ const int base_slice = cfqd->cfq_slice[cfq_cfqq_sync(cfqq)];
- /*
- * follow expired path, else get first next available
- */
- if ((crq = cfq_check_fifo(cfqq)) == NULL) {
- if (cfqd->find_best_crq)
- crq = cfqq->next_crq;
- else
- crq = rb_entry_crq(rb_first(&cfqq->sort_list));
- }
+ WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
- cfqd->last_sector = crq->request->sector + crq->request->nr_sectors;
-
- /*
- * finally, insert request into driver list
- */
- cfq_dispatch_sort(q, crq);
+ return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - cfqq->ioprio));
}
-static int cfq_dispatch_requests(request_queue_t *q, int max_dispatch)
+static inline void
+cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+}
+
+static inline int
+cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ const int base_rq = cfqd->cfq_slice_async_rq;
+
+ WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
+
+ return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
+}
+
+/*
+ * get next queue for service
+ */
+static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd, int force)
+{
+ unsigned long now = jiffies;
+ struct cfq_queue *cfqq;
+
+ cfqq = cfqd->active_queue;
+ if (!cfqq)
+ goto new_queue;
+
+ /*
+ * slice has expired
+ */
+ if (!cfqq->must_dispatch && time_after(jiffies, cfqq->slice_end))
+ goto new_queue;
+
+ /*
+ * if queue has requests, dispatch one. if not, check if
+ * enough slice is left to wait for one
+ */
+ if (!RB_EMPTY(&cfqq->sort_list))
+ goto keep_queue;
+ else if (!force && cfq_cfqq_sync(cfqq) &&
+ time_before(now, cfqq->slice_end)) {
+ if (cfq_arm_slice_timer(cfqd, cfqq))
+ return NULL;
+ }
+
+new_queue:
+ cfq_slice_expired(cfqd, 0);
+ cfq_set_active_queue(cfqd);
+keep_queue:
+ return cfqd->active_queue;
+}
+
+static int
+__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ int max_dispatch)
+{
+ int dispatched = 0;
+
+ BUG_ON(RB_EMPTY(&cfqq->sort_list));
+
+ do {
+ struct cfq_rq *crq;
+
+ /*
+ * follow expired path, else get first next available
+ */
+ if ((crq = cfq_check_fifo(cfqq)) == NULL)
+ crq = cfqq->next_crq;
+
+ /*
+ * finally, insert request into driver dispatch list
+ */
+ cfq_dispatch_sort(cfqd->queue, crq);
+
+ cfqd->dispatch_slice++;
+ dispatched++;
+
+ if (!cfqd->active_cic) {
+ atomic_inc(&crq->io_context->ioc->refcount);
+ cfqd->active_cic = crq->io_context;
+ }
+
+ if (RB_EMPTY(&cfqq->sort_list))
+ break;
+
+ } while (dispatched < max_dispatch);
+
+ /*
+ * if slice end isn't set yet, set it. if at least one request was
+ * sync, use the sync time slice value
+ */
+ if (!cfqq->slice_end)
+ cfq_set_prio_slice(cfqd, cfqq);
+
+ /*
+ * expire an async queue immediately if it has used up its slice. idle
+ * queue always expire after 1 dispatch round.
+ */
+ if ((!cfq_cfqq_sync(cfqq) &&
+ cfqd->dispatch_slice >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+ cfq_class_idle(cfqq))
+ cfq_slice_expired(cfqd, 0);
+
+ return dispatched;
+}
+
+static int
+cfq_dispatch_requests(request_queue_t *q, int max_dispatch, int force)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq;
- struct list_head *entry, *tmp;
- int queued, busy_queues, first_round;
- if (list_empty(&cfqd->rr_list))
+ if (!cfqd->busy_queues)
return 0;
- queued = 0;
- first_round = 1;
-restart:
- busy_queues = 0;
- list_for_each_safe(entry, tmp, &cfqd->rr_list) {
- cfqq = list_entry_cfqq(entry);
+ cfqq = cfq_select_queue(cfqd, force);
+ if (cfqq) {
+ cfqq->wait_request = 0;
+ cfqq->must_dispatch = 0;
+ del_timer(&cfqd->idle_slice_timer);
- BUG_ON(RB_EMPTY(&cfqq->sort_list));
+ if (cfq_class_idle(cfqq))
+ max_dispatch = 1;
- /*
- * first round of queueing, only select from queues that
- * don't already have io in-flight
- */
- if (first_round && cfqq->in_flight)
- continue;
-
- cfq_dispatch_request(q, cfqd, cfqq);
-
- if (!RB_EMPTY(&cfqq->sort_list))
- busy_queues++;
-
- queued++;
+ return __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
}
- if ((queued < max_dispatch) && (busy_queues || first_round)) {
- first_round = 0;
- goto restart;
- }
-
- return queued;
+ return 0;
}
static inline void cfq_account_dispatch(struct cfq_rq *crq)
{
struct cfq_queue *cfqq = crq->cfq_queue;
struct cfq_data *cfqd = cfqq->cfqd;
- unsigned long now, elapsed;
- if (!blk_fs_request(crq->request))
+ if (unlikely(!blk_fs_request(crq->request)))
return;
/*
@@ -879,65 +1110,34 @@ static inline void cfq_account_dispatch(struct cfq_rq *crq)
if (crq->accounted)
return;
- now = jiffies;
- if (cfqq->service_start == ~0UL)
- cfqq->service_start = now;
-
- /*
- * on drives with tagged command queueing, command turn-around time
- * doesn't necessarily reflect the time spent processing this very
- * command inside the drive. so do the accounting differently there,
- * by just sorting on the number of requests
- */
- if (cfqd->cfq_tagged) {
- if (time_after(now, cfqq->service_start + cfq_service)) {
- cfqq->service_start = now;
- cfqq->service_used /= 10;
- }
-
- cfqq->service_used++;
- cfq_sort_rr_list(cfqq, 0);
- }
-
- elapsed = now - crq->queue_start;
- if (elapsed > max_elapsed_dispatch)
- max_elapsed_dispatch = elapsed;
-
crq->accounted = 1;
- crq->service_start = now;
-
- if (++cfqd->rq_in_driver >= CFQ_MAX_TAG && !cfqd->cfq_tagged) {
- cfqq->cfqd->cfq_tagged = 1;
- printk("cfq: depth %d reached, tagging now on\n", CFQ_MAX_TAG);
- }
+ cfqd->rq_in_driver++;
}
static inline void
cfq_account_completion(struct cfq_queue *cfqq, struct cfq_rq *crq)
{
struct cfq_data *cfqd = cfqq->cfqd;
+ unsigned long now;
if (!crq->accounted)
return;
+ now = jiffies;
+
WARN_ON(!cfqd->rq_in_driver);
cfqd->rq_in_driver--;
- if (!cfqd->cfq_tagged) {
- unsigned long now = jiffies;
- unsigned long duration = now - crq->service_start;
+ if (!cfq_class_idle(cfqq))
+ cfqd->last_end_request = now;
- if (time_after(now, cfqq->service_start + cfq_service)) {
- cfqq->service_start = now;
- cfqq->service_used >>= 3;
- }
-
- cfqq->service_used += duration;
- cfq_sort_rr_list(cfqq, 0);
-
- if (duration > max_elapsed_crq)
- max_elapsed_crq = duration;
+ if (!cfqq->in_flight && cfqq->on_rr) {
+ cfqq->service_last = now;
+ cfq_resort_rr_list(cfqq, 0);
}
+
+ if (crq->is_sync)
+ crq->io_context->last_end_request = now;
}
static struct request *cfq_next_request(request_queue_t *q)
@@ -950,7 +1150,15 @@ static struct request *cfq_next_request(request_queue_t *q)
dispatch:
rq = list_entry_rq(q->queue_head.next);
- if ((crq = RQ_DATA(rq)) != NULL) {
+ crq = RQ_DATA(rq);
+ if (crq) {
+ /*
+ * if idle window is disabled, allow queue buildup
+ */
+ if (!crq->in_flight && !crq->cfq_queue->idle_window &&
+ cfqd->rq_in_driver >= cfqd->cfq_max_depth)
+ return NULL;
+
cfq_remove_merge_hints(q, crq);
cfq_account_dispatch(crq);
}
@@ -958,7 +1166,7 @@ dispatch:
return rq;
}
- if (cfq_dispatch_requests(q, cfqd->cfq_quantum))
+ if (cfq_dispatch_requests(q, cfqd->cfq_quantum, 0))
goto dispatch;
return NULL;
@@ -972,14 +1180,22 @@ dispatch:
*/
static void cfq_put_queue(struct cfq_queue *cfqq)
{
- BUG_ON(!atomic_read(&cfqq->ref));
+ struct cfq_data *cfqd = cfqq->cfqd;
+
+ BUG_ON(atomic_read(&cfqq->ref) <= 0);
if (!atomic_dec_and_test(&cfqq->ref))
return;
BUG_ON(rb_first(&cfqq->sort_list));
+ BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
BUG_ON(cfqq->on_rr);
+ if (unlikely(cfqd->active_queue == cfqq)) {
+ cfq_slice_expired(cfqd, 0);
+ kblockd_schedule_work(&cfqd->unplug_work);
+ }
+
cfq_put_cfqd(cfqq->cfqd);
/*
@@ -991,7 +1207,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
}
static inline struct cfq_queue *
-__cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned long key, const int hashval)
+__cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, const int hashval)
{
struct hlist_head *hash_list = &cfqd->cfq_hash[hashval];
struct hlist_node *entry, *next;
@@ -1007,190 +1223,166 @@ __cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned long key, const int hashval)
}
static struct cfq_queue *
-cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned long key)
+cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key)
{
return __cfq_find_cfq_hash(cfqd, key, hash_long(key, CFQ_QHASH_SHIFT));
}
-static inline void
-cfq_rehash_cfqq(struct cfq_data *cfqd, struct cfq_queue **cfqq,
- struct cfq_io_context *cic)
-{
- unsigned long hashkey = cfq_hash_key(cfqd, current);
- unsigned long hashval = hash_long(hashkey, CFQ_QHASH_SHIFT);
- struct cfq_queue *__cfqq;
- unsigned long flags;
-
- spin_lock_irqsave(cfqd->queue->queue_lock, flags);
-
- hlist_del(&(*cfqq)->cfq_hash);
-
- __cfqq = __cfq_find_cfq_hash(cfqd, hashkey, hashval);
- if (!__cfqq || __cfqq == *cfqq) {
- __cfqq = *cfqq;
- hlist_add_head(&__cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
- __cfqq->key_type = cfqd->key_type;
- } else {
- atomic_inc(&__cfqq->ref);
- cic->cfqq = __cfqq;
- cfq_put_queue(*cfqq);
- *cfqq = __cfqq;
- }
-
- cic->cfqq = __cfqq;
- spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
-}
-
static void cfq_free_io_context(struct cfq_io_context *cic)
{
+ struct cfq_io_context *__cic;
+ struct list_head *entry, *next;
+
+ list_for_each_safe(entry, next, &cic->list) {
+ __cic = list_entry(entry, struct cfq_io_context, list);
+ kmem_cache_free(cfq_ioc_pool, __cic);
+ }
+
kmem_cache_free(cfq_ioc_pool, cic);
}
/*
- * locking hierarchy is: io_context lock -> queue locks
+ * Called with interrupts disabled
+ */
+static void cfq_exit_single_io_context(struct cfq_io_context *cic)
+{
+ struct cfq_data *cfqd = cic->cfqq->cfqd;
+ request_queue_t *q = cfqd->queue;
+
+ WARN_ON(!irqs_disabled());
+
+ spin_lock(q->queue_lock);
+
+ if (unlikely(cic->cfqq == cfqd->active_queue)) {
+ cfq_slice_expired(cfqd, 0);
+ kblockd_schedule_work(&cfqd->unplug_work);
+ }
+
+ cfq_put_queue(cic->cfqq);
+ cic->cfqq = NULL;
+ spin_unlock(q->queue_lock);
+}
+
+/*
+ * Another task may update the task cic list, if it is doing a queue lookup
+ * on its behalf. cfq_cic_lock excludes such concurrent updates
*/
static void cfq_exit_io_context(struct cfq_io_context *cic)
{
- struct cfq_queue *cfqq = cic->cfqq;
- struct list_head *entry = &cic->list;
- request_queue_t *q;
+ struct cfq_io_context *__cic;
+ struct list_head *entry;
unsigned long flags;
+ local_irq_save(flags);
+
/*
* put the reference this task is holding to the various queues
*/
- spin_lock_irqsave(&cic->ioc->lock, flags);
- while ((entry = cic->list.next) != &cic->list) {
- struct cfq_io_context *__cic;
-
+ list_for_each(entry, &cic->list) {
__cic = list_entry(entry, struct cfq_io_context, list);
- list_del(entry);
-
- q = __cic->cfqq->cfqd->queue;
- spin_lock(q->queue_lock);
- cfq_put_queue(__cic->cfqq);
- spin_unlock(q->queue_lock);
+ cfq_exit_single_io_context(__cic);
}
- q = cfqq->cfqd->queue;
- spin_lock(q->queue_lock);
- cfq_put_queue(cfqq);
- spin_unlock(q->queue_lock);
-
- cic->cfqq = NULL;
- spin_unlock_irqrestore(&cic->ioc->lock, flags);
+ cfq_exit_single_io_context(cic);
+ local_irq_restore(flags);
}
-static struct cfq_io_context *cfq_alloc_io_context(int gfp_flags)
+static struct cfq_io_context *
+cfq_alloc_io_context(struct cfq_data *cfqd, int gfp_mask)
{
- struct cfq_io_context *cic = kmem_cache_alloc(cfq_ioc_pool, gfp_flags);
+ struct cfq_io_context *cic = kmem_cache_alloc(cfq_ioc_pool, gfp_mask);
if (cic) {
- cic->dtor = cfq_free_io_context;
- cic->exit = cfq_exit_io_context;
INIT_LIST_HEAD(&cic->list);
cic->cfqq = NULL;
+ cic->key = NULL;
+ cic->last_end_request = jiffies;
+ cic->ttime_total = 0;
+ cic->ttime_samples = 0;
+ cic->ttime_mean = 0;
+ cic->dtor = cfq_free_io_context;
+ cic->exit = cfq_exit_io_context;
}
return cic;
}
+static void cfq_init_prio_data(struct cfq_queue *cfqq)
+{
+ struct task_struct *tsk = current;
+ int ioprio_class;
+
+ if (!cfqq->prio_changed)
+ return;
+
+ ioprio_class = IOPRIO_PRIO_CLASS(tsk->ioprio);
+ switch (ioprio_class) {
+ default:
+ printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+ case IOPRIO_CLASS_NONE:
+ /*
+ * no prio set, place us in the middle of the BE classes
+ */
+ cfqq->ioprio = task_nice_ioprio(tsk);
+ cfqq->ioprio_class = IOPRIO_CLASS_BE;
+ break;
+ case IOPRIO_CLASS_RT:
+ cfqq->ioprio = task_ioprio(tsk);
+ cfqq->ioprio_class = IOPRIO_CLASS_RT;
+ break;
+ case IOPRIO_CLASS_BE:
+ cfqq->ioprio = task_ioprio(tsk);
+ cfqq->ioprio_class = IOPRIO_CLASS_BE;
+ break;
+ case IOPRIO_CLASS_IDLE:
+ cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
+ cfqq->ioprio = 7;
+ cfqq->idle_window = 0;
+ break;
+ }
+
+ /*
+ * keep track of original prio settings in case we have to temporarily
+ * elevate the priority of this queue
+ */
+ cfqq->org_ioprio = cfqq->ioprio;
+ cfqq->org_ioprio_class = cfqq->ioprio_class;
+
+ if (cfqq->on_rr)
+ cfq_resort_rr_list(cfqq, 0);
+
+ cfqq->prio_changed = 0;
+}
+
+static inline void changed_ioprio(struct cfq_queue *cfqq)
+{
+ if (cfqq) {
+ struct cfq_data *cfqd = cfqq->cfqd;
+
+ spin_lock(cfqd->queue->queue_lock);
+ cfqq->prio_changed = 1;
+ cfq_init_prio_data(cfqq);
+ spin_unlock(cfqd->queue->queue_lock);
+ }
+}
+
/*
- * Setup general io context and cfq io context. There can be several cfq
- * io contexts per general io context, if this process is doing io to more
- * than one device managed by cfq. Note that caller is holding a reference to
- * cfqq, so we don't need to worry about it disappearing
+ * callback from sys_ioprio_set, irqs are disabled
*/
-static struct cfq_io_context *
-cfq_get_io_context(struct cfq_queue **cfqq, int gfp_flags)
+static int cfq_ioc_set_ioprio(struct io_context *ioc, unsigned int ioprio)
{
- struct cfq_data *cfqd = (*cfqq)->cfqd;
- struct cfq_queue *__cfqq = *cfqq;
- struct cfq_io_context *cic;
- struct io_context *ioc;
+ struct cfq_io_context *cic = ioc->cic;
- might_sleep_if(gfp_flags & __GFP_WAIT);
+ changed_ioprio(cic->cfqq);
- ioc = get_io_context(gfp_flags);
- if (!ioc)
- return NULL;
+ list_for_each_entry(cic, &cic->list, list)
+ changed_ioprio(cic->cfqq);
- if ((cic = ioc->cic) == NULL) {
- cic = cfq_alloc_io_context(gfp_flags);
-
- if (cic == NULL)
- goto err;
-
- ioc->cic = cic;
- cic->ioc = ioc;
- cic->cfqq = __cfqq;
- atomic_inc(&__cfqq->ref);
- } else {
- struct cfq_io_context *__cic;
- unsigned long flags;
-
- /*
- * since the first cic on the list is actually the head
- * itself, need to check this here or we'll duplicate an
- * cic per ioc for no reason
- */
- if (cic->cfqq == __cfqq)
- goto out;
-
- /*
- * cic exists, check if we already are there. linear search
- * should be ok here, the list will usually not be more than
- * 1 or a few entries long
- */
- spin_lock_irqsave(&ioc->lock, flags);
- list_for_each_entry(__cic, &cic->list, list) {
- /*
- * this process is already holding a reference to
- * this queue, so no need to get one more
- */
- if (__cic->cfqq == __cfqq) {
- cic = __cic;
- spin_unlock_irqrestore(&ioc->lock, flags);
- goto out;
- }
- }
- spin_unlock_irqrestore(&ioc->lock, flags);
-
- /*
- * nope, process doesn't have a cic assoicated with this
- * cfqq yet. get a new one and add to list
- */
- __cic = cfq_alloc_io_context(gfp_flags);
- if (__cic == NULL)
- goto err;
-
- __cic->ioc = ioc;
- __cic->cfqq = __cfqq;
- atomic_inc(&__cfqq->ref);
- spin_lock_irqsave(&ioc->lock, flags);
- list_add(&__cic->list, &cic->list);
- spin_unlock_irqrestore(&ioc->lock, flags);
-
- cic = __cic;
- *cfqq = __cfqq;
- }
-
-out:
- /*
- * if key_type has been changed on the fly, we lazily rehash
- * each queue at lookup time
- */
- if ((*cfqq)->key_type != cfqd->key_type)
- cfq_rehash_cfqq(cfqd, cfqq, cic);
-
- return cic;
-err:
- put_io_context(ioc);
- return NULL;
+ return 0;
}
static struct cfq_queue *
-__cfq_get_queue(struct cfq_data *cfqd, unsigned long key, int gfp_mask)
+cfq_get_queue(struct cfq_data *cfqd, unsigned int key, int gfp_mask)
{
const int hashval = hash_long(key, CFQ_QHASH_SHIFT);
struct cfq_queue *cfqq, *new_cfqq = NULL;
@@ -1202,15 +1394,15 @@ retry:
if (new_cfqq) {
cfqq = new_cfqq;
new_cfqq = NULL;
- } else {
+ } else if (gfp_mask & __GFP_WAIT) {
spin_unlock_irq(cfqd->queue->queue_lock);
new_cfqq = kmem_cache_alloc(cfq_pool, gfp_mask);
spin_lock_irq(cfqd->queue->queue_lock);
-
- if (!new_cfqq && !(gfp_mask & __GFP_WAIT))
- goto out;
-
goto retry;
+ } else {
+ cfqq = kmem_cache_alloc(cfq_pool, gfp_mask);
+ if (!cfqq)
+ goto out;
}
memset(cfqq, 0, sizeof(*cfqq));
@@ -1218,16 +1410,22 @@ retry:
INIT_HLIST_NODE(&cfqq->cfq_hash);
INIT_LIST_HEAD(&cfqq->cfq_list);
RB_CLEAR_ROOT(&cfqq->sort_list);
- INIT_LIST_HEAD(&cfqq->fifo[0]);
- INIT_LIST_HEAD(&cfqq->fifo[1]);
+ INIT_LIST_HEAD(&cfqq->fifo);
cfqq->key = key;
hlist_add_head(&cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
atomic_set(&cfqq->ref, 0);
cfqq->cfqd = cfqd;
atomic_inc(&cfqd->ref);
- cfqq->key_type = cfqd->key_type;
- cfqq->service_start = ~0UL;
+ cfqq->service_last = 0;
+ /*
+ * set ->slice_left to allow preemption for a new process
+ */
+ cfqq->slice_left = 2 * cfqd->cfq_slice_idle;
+ cfqq->idle_window = 1;
+ cfqq->ioprio = -1;
+ cfqq->ioprio_class = -1;
+ cfqq->prio_changed = 1;
}
if (new_cfqq)
@@ -1239,55 +1437,306 @@ out:
return cfqq;
}
-static void cfq_enqueue(struct cfq_data *cfqd, struct cfq_rq *crq)
+/*
+ * Setup general io context and cfq io context. There can be several cfq
+ * io contexts per general io context, if this process is doing io to more
+ * than one device managed by cfq. Note that caller is holding a reference to
+ * cfqq, so we don't need to worry about it disappearing
+ */
+static struct cfq_io_context *
+cfq_get_io_context(struct cfq_data *cfqd, pid_t pid, int gfp_mask)
{
- crq->is_sync = 0;
- if (rq_data_dir(crq->request) == READ || current->flags & PF_SYNCWRITE)
- crq->is_sync = 1;
+ struct io_context *ioc = NULL;
+ struct cfq_io_context *cic;
+
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+ ioc = get_io_context(gfp_mask);
+ if (!ioc)
+ return NULL;
+
+ if ((cic = ioc->cic) == NULL) {
+ cic = cfq_alloc_io_context(cfqd, gfp_mask);
+
+ if (cic == NULL)
+ goto err;
+
+ /*
+ * manually increment generic io_context usage count, it
+ * cannot go away since we are already holding one ref to it
+ */
+ ioc->cic = cic;
+ ioc->set_ioprio = cfq_ioc_set_ioprio;
+ cic->ioc = ioc;
+ cic->key = cfqd;
+ atomic_inc(&cfqd->ref);
+ } else {
+ struct cfq_io_context *__cic;
+
+ /*
+ * the first cic on the list is actually the head itself
+ */
+ if (cic->key == cfqd)
+ goto out;
+
+ /*
+ * cic exists, check if we already are there. linear search
+ * should be ok here, the list will usually not be more than
+ * 1 or a few entries long
+ */
+ list_for_each_entry(__cic, &cic->list, list) {
+ /*
+ * this process is already holding a reference to
+ * this queue, so no need to get one more
+ */
+ if (__cic->key == cfqd) {
+ cic = __cic;
+ goto out;
+ }
+ }
+
+ /*
+ * nope, process doesn't have a cic assoicated with this
+ * cfqq yet. get a new one and add to list
+ */
+ __cic = cfq_alloc_io_context(cfqd, gfp_mask);
+ if (__cic == NULL)
+ goto err;
+
+ __cic->ioc = ioc;
+ __cic->key = cfqd;
+ atomic_inc(&cfqd->ref);
+ list_add(&__cic->list, &cic->list);
+ cic = __cic;
+ }
+
+out:
+ return cic;
+err:
+ put_io_context(ioc);
+ return NULL;
+}
+
+static void
+cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
+{
+ unsigned long elapsed, ttime;
+
+ /*
+ * if this context already has stuff queued, thinktime is from
+ * last queue not last end
+ */
+#if 0
+ if (time_after(cic->last_end_request, cic->last_queue))
+ elapsed = jiffies - cic->last_end_request;
+ else
+ elapsed = jiffies - cic->last_queue;
+#else
+ elapsed = jiffies - cic->last_end_request;
+#endif
+
+ ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle);
+
+ cic->ttime_samples = (7*cic->ttime_samples + 256) / 8;
+ cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8;
+ cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples;
+}
+
+#define sample_valid(samples) ((samples) > 80)
+
+/*
+ * Disable idle window if the process thinks too long or seeks so much that
+ * it doesn't matter
+ */
+static void
+cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ struct cfq_io_context *cic)
+{
+ int enable_idle = cfqq->idle_window;
+
+ if (!cic->ioc->task || !cfqd->cfq_slice_idle)
+ enable_idle = 0;
+ else if (sample_valid(cic->ttime_samples)) {
+ if (cic->ttime_mean > cfqd->cfq_slice_idle)
+ enable_idle = 0;
+ else
+ enable_idle = 1;
+ }
+
+ cfqq->idle_window = enable_idle;
+}
+
+
+/*
+ * Check if new_cfqq should preempt the currently active queue. Return 0 for
+ * no or if we aren't sure, a 1 will cause a preempt.
+ */
+static int
+cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
+ struct cfq_rq *crq)
+{
+ struct cfq_queue *cfqq = cfqd->active_queue;
+
+ if (cfq_class_idle(new_cfqq))
+ return 0;
+
+ if (!cfqq)
+ return 1;
+
+ if (cfq_class_idle(cfqq))
+ return 1;
+ if (!new_cfqq->wait_request)
+ return 0;
+ /*
+ * if it doesn't have slice left, forget it
+ */
+ if (new_cfqq->slice_left < cfqd->cfq_slice_idle)
+ return 0;
+ if (crq->is_sync && !cfq_cfqq_sync(cfqq))
+ return 1;
+
+ return 0;
+}
+
+/*
+ * cfqq preempts the active queue. if we allowed preempt with no slice left,
+ * let it have half of its nominal slice.
+ */
+static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ struct cfq_queue *__cfqq, *next;
+
+ list_for_each_entry_safe(__cfqq, next, &cfqd->cur_rr, cfq_list)
+ cfq_resort_rr_list(__cfqq, 1);
+
+ if (!cfqq->slice_left)
+ cfqq->slice_left = cfq_prio_to_slice(cfqd, cfqq) / 2;
+
+ cfqq->slice_end = cfqq->slice_left + jiffies;
+ cfq_slice_expired(cfqd, 1);
+ __cfq_set_active_queue(cfqd, cfqq);
+}
+
+/*
+ * should really be a ll_rw_blk.c helper
+ */
+static void cfq_start_queueing(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+ request_queue_t *q = cfqd->queue;
+
+ if (!blk_queue_plugged(q))
+ q->request_fn(q);
+ else
+ __generic_unplug_device(q);
+}
+
+/*
+ * Called when a new fs request (crq) is added (to cfqq). Check if there's
+ * something we should do about it
+ */
+static void
+cfq_crq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ struct cfq_rq *crq)
+{
+ const int sync = crq->is_sync;
+
+ cfqq->next_crq = cfq_choose_req(cfqd, cfqq->next_crq, crq);
+
+ if (sync) {
+ struct cfq_io_context *cic = crq->io_context;
+
+ cfq_update_io_thinktime(cfqd, cic);
+ cfq_update_idle_window(cfqd, cfqq, cic);
+
+ cic->last_queue = jiffies;
+ }
+
+ if (cfqq == cfqd->active_queue) {
+ /*
+ * if we are waiting for a request for this queue, let it rip
+ * immediately and flag that we must not expire this queue
+ * just now
+ */
+ if (cfqq->wait_request) {
+ cfqq->must_dispatch = 1;
+ del_timer(&cfqd->idle_slice_timer);
+ cfq_start_queueing(cfqd, cfqq);
+ }
+ } else if (cfq_should_preempt(cfqd, cfqq, crq)) {
+ /*
+ * not the active queue - expire current slice if it is
+ * idle and has expired it's mean thinktime or this new queue
+ * has some old slice time left and is of higher priority
+ */
+ cfq_preempt_queue(cfqd, cfqq);
+ cfqq->must_dispatch = 1;
+ cfq_start_queueing(cfqd, cfqq);
+ }
+}
+
+static void cfq_enqueue(struct cfq_data *cfqd, struct request *rq)
+{
+ struct cfq_rq *crq = RQ_DATA(rq);
+ struct cfq_queue *cfqq = crq->cfq_queue;
+
+ cfq_init_prio_data(cfqq);
cfq_add_crq_rb(crq);
- crq->queue_start = jiffies;
- list_add_tail(&crq->request->queuelist, &crq->cfq_queue->fifo[crq->is_sync]);
+ list_add_tail(&rq->queuelist, &cfqq->fifo);
+
+ if (rq_mergeable(rq)) {
+ cfq_add_crq_hash(cfqd, crq);
+
+ if (!cfqd->queue->last_merge)
+ cfqd->queue->last_merge = rq;
+ }
+
+ cfq_crq_enqueued(cfqd, cfqq, crq);
}
static void
cfq_insert_request(request_queue_t *q, struct request *rq, int where)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- struct cfq_rq *crq = RQ_DATA(rq);
switch (where) {
case ELEVATOR_INSERT_BACK:
- while (cfq_dispatch_requests(q, cfqd->cfq_quantum))
+ while (cfq_dispatch_requests(q, INT_MAX, 1))
;
list_add_tail(&rq->queuelist, &q->queue_head);
+ /*
+ * If we were idling with pending requests on
+ * inactive cfqqs, force dispatching will
+ * remove the idle timer and the queue won't
+ * be kicked by __make_request() afterward.
+ * Kick it here.
+ */
+ kblockd_schedule_work(&cfqd->unplug_work);
break;
case ELEVATOR_INSERT_FRONT:
list_add(&rq->queuelist, &q->queue_head);
break;
case ELEVATOR_INSERT_SORT:
BUG_ON(!blk_fs_request(rq));
- cfq_enqueue(cfqd, crq);
+ cfq_enqueue(cfqd, rq);
break;
default:
printk("%s: bad insert point %d\n", __FUNCTION__,where);
return;
}
+}
- if (rq_mergeable(rq)) {
- cfq_add_crq_hash(cfqd, crq);
-
- if (!q->last_merge)
- q->last_merge = rq;
- }
+static inline int cfq_pending_requests(struct cfq_data *cfqd)
+{
+ return !list_empty(&cfqd->queue->queue_head) || cfqd->busy_queues;
}
static int cfq_queue_empty(request_queue_t *q)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- return list_empty(&q->queue_head) && list_empty(&cfqd->rr_list);
+ return !cfq_pending_requests(cfqd);
}
static void cfq_completed_request(request_queue_t *q, struct request *rq)
@@ -1332,51 +1781,132 @@ cfq_latter_request(request_queue_t *q, struct request *rq)
return NULL;
}
-static int cfq_may_queue(request_queue_t *q, int rw)
+/*
+ * we temporarily boost lower priority queues if they are holding fs exclusive
+ * resources. they are boosted to normal prio (CLASS_BE/4)
+ */
+static void cfq_prio_boost(struct cfq_queue *cfqq)
{
- struct cfq_data *cfqd = q->elevator->elevator_data;
- struct cfq_queue *cfqq;
- int ret = ELV_MQUEUE_MAY;
+ const int ioprio_class = cfqq->ioprio_class;
+ const int ioprio = cfqq->ioprio;
- if (current->flags & PF_MEMALLOC)
- return ELV_MQUEUE_MAY;
-
- cfqq = cfq_find_cfq_hash(cfqd, cfq_hash_key(cfqd, current));
- if (cfqq) {
- int limit = cfqd->max_queued;
-
- if (cfqq->allocated[rw] < cfqd->cfq_queued)
- return ELV_MQUEUE_MUST;
-
- if (cfqd->busy_queues)
- limit = q->nr_requests / cfqd->busy_queues;
-
- if (limit < cfqd->cfq_queued)
- limit = cfqd->cfq_queued;
- else if (limit > cfqd->max_queued)
- limit = cfqd->max_queued;
-
- if (cfqq->allocated[rw] >= limit) {
- if (limit > cfqq->alloc_limit[rw])
- cfqq->alloc_limit[rw] = limit;
-
- ret = ELV_MQUEUE_NO;
- }
+ if (has_fs_excl()) {
+ /*
+ * boost idle prio on transactions that would lock out other
+ * users of the filesystem
+ */
+ if (cfq_class_idle(cfqq))
+ cfqq->ioprio_class = IOPRIO_CLASS_BE;
+ if (cfqq->ioprio > IOPRIO_NORM)
+ cfqq->ioprio = IOPRIO_NORM;
+ } else {
+ /*
+ * check if we need to unboost the queue
+ */
+ if (cfqq->ioprio_class != cfqq->org_ioprio_class)
+ cfqq->ioprio_class = cfqq->org_ioprio_class;
+ if (cfqq->ioprio != cfqq->org_ioprio)
+ cfqq->ioprio = cfqq->org_ioprio;
}
- return ret;
+ /*
+ * refile between round-robin lists if we moved the priority class
+ */
+ if ((ioprio_class != cfqq->ioprio_class || ioprio != cfqq->ioprio) &&
+ cfqq->on_rr)
+ cfq_resort_rr_list(cfqq, 0);
+}
+
+static inline pid_t cfq_queue_pid(struct task_struct *task, int rw)
+{
+ if (rw == READ || process_sync(task))
+ return task->pid;
+
+ return CFQ_KEY_ASYNC;
+}
+
+static inline int
+__cfq_may_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+ struct task_struct *task, int rw)
+{
+ if (cfqq->wait_request && cfqq->must_alloc)
+ return ELV_MQUEUE_MUST;
+
+ return ELV_MQUEUE_MAY;
+#if 0
+ if (!cfqq || task->flags & PF_MEMALLOC)
+ return ELV_MQUEUE_MAY;
+ if (!cfqq->allocated[rw] || cfqq->must_alloc) {
+ if (cfqq->wait_request)
+ return ELV_MQUEUE_MUST;
+
+ /*
+ * only allow 1 ELV_MQUEUE_MUST per slice, otherwise we
+ * can quickly flood the queue with writes from a single task
+ */
+ if (rw == READ || !cfqq->must_alloc_slice) {
+ cfqq->must_alloc_slice = 1;
+ return ELV_MQUEUE_MUST;
+ }
+
+ return ELV_MQUEUE_MAY;
+ }
+ if (cfq_class_idle(cfqq))
+ return ELV_MQUEUE_NO;
+ if (cfqq->allocated[rw] >= cfqd->max_queued) {
+ struct io_context *ioc = get_io_context(GFP_ATOMIC);
+ int ret = ELV_MQUEUE_NO;
+
+ if (ioc && ioc->nr_batch_requests)
+ ret = ELV_MQUEUE_MAY;
+
+ put_io_context(ioc);
+ return ret;
+ }
+
+ return ELV_MQUEUE_MAY;
+#endif
+}
+
+static int cfq_may_queue(request_queue_t *q, int rw, struct bio *bio)
+{
+ struct cfq_data *cfqd = q->elevator->elevator_data;
+ struct task_struct *tsk = current;
+ struct cfq_queue *cfqq;
+
+ /*
+ * don't force setup of a queue from here, as a call to may_queue
+ * does not necessarily imply that a request actually will be queued.
+ * so just lookup a possibly existing queue, or return 'may queue'
+ * if that fails
+ */
+ cfqq = cfq_find_cfq_hash(cfqd, cfq_queue_pid(tsk, rw));
+ if (cfqq) {
+ cfq_init_prio_data(cfqq);
+ cfq_prio_boost(cfqq);
+
+ return __cfq_may_queue(cfqd, cfqq, tsk, rw);
+ }
+
+ return ELV_MQUEUE_MAY;
}
static void cfq_check_waiters(request_queue_t *q, struct cfq_queue *cfqq)
{
+ struct cfq_data *cfqd = q->elevator->elevator_data;
struct request_list *rl = &q->rq;
- const int write = waitqueue_active(&rl->wait[WRITE]);
- const int read = waitqueue_active(&rl->wait[READ]);
- if (read && cfqq->allocated[READ] < cfqq->alloc_limit[READ])
- wake_up(&rl->wait[READ]);
- if (write && cfqq->allocated[WRITE] < cfqq->alloc_limit[WRITE])
- wake_up(&rl->wait[WRITE]);
+ if (cfqq->allocated[READ] <= cfqd->max_queued || cfqd->rq_starved) {
+ smp_mb();
+ if (waitqueue_active(&rl->wait[READ]))
+ wake_up(&rl->wait[READ]);
+ }
+
+ if (cfqq->allocated[WRITE] <= cfqd->max_queued || cfqd->rq_starved) {
+ smp_mb();
+ if (waitqueue_active(&rl->wait[WRITE]))
+ wake_up(&rl->wait[WRITE]);
+ }
}
/*
@@ -1389,69 +1919,59 @@ static void cfq_put_request(request_queue_t *q, struct request *rq)
if (crq) {
struct cfq_queue *cfqq = crq->cfq_queue;
+ const int rw = rq_data_dir(rq);
- BUG_ON(q->last_merge == rq);
- BUG_ON(!hlist_unhashed(&crq->hash));
+ BUG_ON(!cfqq->allocated[rw]);
+ cfqq->allocated[rw]--;
- if (crq->io_context)
- put_io_context(crq->io_context->ioc);
-
- BUG_ON(!cfqq->allocated[crq->is_write]);
- cfqq->allocated[crq->is_write]--;
+ put_io_context(crq->io_context->ioc);
mempool_free(crq, cfqd->crq_pool);
rq->elevator_private = NULL;
- smp_mb();
cfq_check_waiters(q, cfqq);
cfq_put_queue(cfqq);
}
}
/*
- * Allocate cfq data structures associated with this request. A queue and
+ * Allocate cfq data structures associated with this request.
*/
-static int cfq_set_request(request_queue_t *q, struct request *rq, int gfp_mask)
+static int
+cfq_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
+ int gfp_mask)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_io_context *cic;
const int rw = rq_data_dir(rq);
- struct cfq_queue *cfqq, *saved_cfqq;
+ struct cfq_queue *cfqq;
struct cfq_rq *crq;
unsigned long flags;
might_sleep_if(gfp_mask & __GFP_WAIT);
+ cic = cfq_get_io_context(cfqd, cfq_queue_pid(current, rw), gfp_mask);
+
spin_lock_irqsave(q->queue_lock, flags);
- cfqq = __cfq_get_queue(cfqd, cfq_hash_key(cfqd, current), gfp_mask);
- if (!cfqq)
- goto out_lock;
+ if (!cic)
+ goto queue_fail;
-repeat:
- if (cfqq->allocated[rw] >= cfqd->max_queued)
- goto out_lock;
+ if (!cic->cfqq) {
+ cfqq = cfq_get_queue(cfqd, current->pid, gfp_mask);
+ if (!cfqq)
+ goto queue_fail;
+
+ cic->cfqq = cfqq;
+ } else
+ cfqq = cic->cfqq;
cfqq->allocated[rw]++;
+ cfqq->must_alloc = 0;
+ cfqd->rq_starved = 0;
+ atomic_inc(&cfqq->ref);
spin_unlock_irqrestore(q->queue_lock, flags);
- /*
- * if hashing type has changed, the cfq_queue might change here.
- */
- saved_cfqq = cfqq;
- cic = cfq_get_io_context(&cfqq, gfp_mask);
- if (!cic)
- goto err;
-
- /*
- * repeat allocation checks on queue change
- */
- if (unlikely(saved_cfqq != cfqq)) {
- spin_lock_irqsave(q->queue_lock, flags);
- saved_cfqq->allocated[rw]--;
- goto repeat;
- }
-
crq = mempool_alloc(cfqd->crq_pool, gfp_mask);
if (crq) {
RB_CLEAR(&crq->rb_node);
@@ -1460,24 +1980,130 @@ repeat:
INIT_HLIST_NODE(&crq->hash);
crq->cfq_queue = cfqq;
crq->io_context = cic;
- crq->service_start = crq->queue_start = 0;
- crq->in_flight = crq->accounted = crq->is_sync = 0;
- crq->is_write = rw;
+ crq->in_flight = crq->accounted = 0;
+ crq->is_sync = (rw == READ || process_sync(current));
+ crq->requeued = 0;
rq->elevator_private = crq;
- cfqq->alloc_limit[rw] = 0;
return 0;
}
- put_io_context(cic->ioc);
-err:
spin_lock_irqsave(q->queue_lock, flags);
cfqq->allocated[rw]--;
+ if (!(cfqq->allocated[0] + cfqq->allocated[1]))
+ cfqq->must_alloc = 1;
cfq_put_queue(cfqq);
-out_lock:
+queue_fail:
+ if (cic)
+ put_io_context(cic->ioc);
+ /*
+ * mark us rq allocation starved. we need to kickstart the process
+ * ourselves if there are no pending requests that can do it for us.
+ * that would be an extremely rare OOM situation
+ */
+ cfqd->rq_starved = 1;
+ kblockd_schedule_work(&cfqd->unplug_work);
spin_unlock_irqrestore(q->queue_lock, flags);
return 1;
}
+static void cfq_kick_queue(void *data)
+{
+ request_queue_t *q = data;
+ struct cfq_data *cfqd = q->elevator->elevator_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ if (cfqd->rq_starved) {
+ struct request_list *rl = &q->rq;
+
+ /*
+ * we aren't guaranteed to get a request after this, but we
+ * have to be opportunistic
+ */
+ smp_mb();
+ if (waitqueue_active(&rl->wait[READ]))
+ wake_up(&rl->wait[READ]);
+ if (waitqueue_active(&rl->wait[WRITE]))
+ wake_up(&rl->wait[WRITE]);
+ }
+
+ blk_remove_plug(q);
+ q->request_fn(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+/*
+ * Timer running if the active_queue is currently idling inside its time slice
+ */
+static void cfq_idle_slice_timer(unsigned long data)
+{
+ struct cfq_data *cfqd = (struct cfq_data *) data;
+ struct cfq_queue *cfqq;
+ unsigned long flags;
+
+ spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+
+ if ((cfqq = cfqd->active_queue) != NULL) {
+ unsigned long now = jiffies;
+
+ /*
+ * expired
+ */
+ if (time_after(now, cfqq->slice_end))
+ goto expire;
+
+ /*
+ * only expire and reinvoke request handler, if there are
+ * other queues with pending requests
+ */
+ if (!cfq_pending_requests(cfqd)) {
+ cfqd->idle_slice_timer.expires = min(now + cfqd->cfq_slice_idle, cfqq->slice_end);
+ add_timer(&cfqd->idle_slice_timer);
+ goto out_cont;
+ }
+
+ /*
+ * not expired and it has a request pending, let it dispatch
+ */
+ if (!RB_EMPTY(&cfqq->sort_list)) {
+ cfqq->must_dispatch = 1;
+ goto out_kick;
+ }
+ }
+expire:
+ cfq_slice_expired(cfqd, 0);
+out_kick:
+ if (cfq_pending_requests(cfqd))
+ kblockd_schedule_work(&cfqd->unplug_work);
+out_cont:
+ spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+/*
+ * Timer running if an idle class queue is waiting for service
+ */
+static void cfq_idle_class_timer(unsigned long data)
+{
+ struct cfq_data *cfqd = (struct cfq_data *) data;
+ unsigned long flags, end;
+
+ spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+
+ /*
+ * race with a non-idle queue, reset timer
+ */
+ end = cfqd->last_end_request + CFQ_IDLE_GRACE;
+ if (!time_after_eq(jiffies, end)) {
+ cfqd->idle_class_timer.expires = end;
+ add_timer(&cfqd->idle_class_timer);
+ } else
+ kblockd_schedule_work(&cfqd->unplug_work);
+
+ spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+
static void cfq_put_cfqd(struct cfq_data *cfqd)
{
request_queue_t *q = cfqd->queue;
@@ -1485,6 +2111,8 @@ static void cfq_put_cfqd(struct cfq_data *cfqd)
if (!atomic_dec_and_test(&cfqd->ref))
return;
+ blk_sync_queue(q);
+
blk_put_queue(q);
mempool_destroy(cfqd->crq_pool);
@@ -1495,7 +2123,11 @@ static void cfq_put_cfqd(struct cfq_data *cfqd)
static void cfq_exit_queue(elevator_t *e)
{
- cfq_put_cfqd(e->elevator_data);
+ struct cfq_data *cfqd = e->elevator_data;
+
+ del_timer_sync(&cfqd->idle_slice_timer);
+ del_timer_sync(&cfqd->idle_class_timer);
+ cfq_put_cfqd(cfqd);
}
static int cfq_init_queue(request_queue_t *q, elevator_t *e)
@@ -1508,7 +2140,13 @@ static int cfq_init_queue(request_queue_t *q, elevator_t *e)
return -ENOMEM;
memset(cfqd, 0, sizeof(*cfqd));
- INIT_LIST_HEAD(&cfqd->rr_list);
+
+ for (i = 0; i < CFQ_PRIO_LISTS; i++)
+ INIT_LIST_HEAD(&cfqd->rr_list[i]);
+
+ INIT_LIST_HEAD(&cfqd->busy_rr);
+ INIT_LIST_HEAD(&cfqd->cur_rr);
+ INIT_LIST_HEAD(&cfqd->idle_rr);
INIT_LIST_HEAD(&cfqd->empty_list);
cfqd->crq_hash = kmalloc(sizeof(struct hlist_head) * CFQ_MHASH_ENTRIES, GFP_KERNEL);
@@ -1533,25 +2171,32 @@ static int cfq_init_queue(request_queue_t *q, elevator_t *e)
cfqd->queue = q;
atomic_inc(&q->refcnt);
- /*
- * just set it to some high value, we want anyone to be able to queue
- * some requests. fairness is handled differently
- */
- q->nr_requests = 1024;
- cfqd->max_queued = q->nr_requests / 16;
+ cfqd->max_queued = q->nr_requests / 4;
q->nr_batching = cfq_queued;
- cfqd->key_type = CFQ_KEY_TGID;
- cfqd->find_best_crq = 1;
+
+ init_timer(&cfqd->idle_slice_timer);
+ cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
+ cfqd->idle_slice_timer.data = (unsigned long) cfqd;
+
+ init_timer(&cfqd->idle_class_timer);
+ cfqd->idle_class_timer.function = cfq_idle_class_timer;
+ cfqd->idle_class_timer.data = (unsigned long) cfqd;
+
+ INIT_WORK(&cfqd->unplug_work, cfq_kick_queue, q);
+
atomic_set(&cfqd->ref, 1);
cfqd->cfq_queued = cfq_queued;
cfqd->cfq_quantum = cfq_quantum;
- cfqd->cfq_fifo_expire_r = cfq_fifo_expire_r;
- cfqd->cfq_fifo_expire_w = cfq_fifo_expire_w;
- cfqd->cfq_fifo_batch_expire = cfq_fifo_rate;
+ cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
+ cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
cfqd->cfq_back_max = cfq_back_max;
cfqd->cfq_back_penalty = cfq_back_penalty;
-
+ cfqd->cfq_slice[0] = cfq_slice_async;
+ cfqd->cfq_slice[1] = cfq_slice_sync;
+ cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
+ cfqd->cfq_slice_idle = cfq_slice_idle;
+ cfqd->cfq_max_depth = cfq_max_depth;
return 0;
out_crqpool:
kfree(cfqd->cfq_hash);
@@ -1595,7 +2240,6 @@ fail:
return -ENOMEM;
}
-
/*
* sysfs parts below -->
*/
@@ -1620,45 +2264,6 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
return count;
}
-static ssize_t
-cfq_clear_elapsed(struct cfq_data *cfqd, const char *page, size_t count)
-{
- max_elapsed_dispatch = max_elapsed_crq = 0;
- return count;
-}
-
-static ssize_t
-cfq_set_key_type(struct cfq_data *cfqd, const char *page, size_t count)
-{
- spin_lock_irq(cfqd->queue->queue_lock);
- if (!strncmp(page, "pgid", 4))
- cfqd->key_type = CFQ_KEY_PGID;
- else if (!strncmp(page, "tgid", 4))
- cfqd->key_type = CFQ_KEY_TGID;
- else if (!strncmp(page, "uid", 3))
- cfqd->key_type = CFQ_KEY_UID;
- else if (!strncmp(page, "gid", 3))
- cfqd->key_type = CFQ_KEY_GID;
- spin_unlock_irq(cfqd->queue->queue_lock);
- return count;
-}
-
-static ssize_t
-cfq_read_key_type(struct cfq_data *cfqd, char *page)
-{
- ssize_t len = 0;
- int i;
-
- for (i = CFQ_KEY_PGID; i < CFQ_KEY_LAST; i++) {
- if (cfqd->key_type == i)
- len += sprintf(page+len, "[%s] ", cfq_key_types[i]);
- else
- len += sprintf(page+len, "%s ", cfq_key_types[i]);
- }
- len += sprintf(page+len, "\n");
- return len;
-}
-
#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
static ssize_t __FUNC(struct cfq_data *cfqd, char *page) \
{ \
@@ -1669,12 +2274,15 @@ static ssize_t __FUNC(struct cfq_data *cfqd, char *page) \
}
SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
SHOW_FUNCTION(cfq_queued_show, cfqd->cfq_queued, 0);
-SHOW_FUNCTION(cfq_fifo_expire_r_show, cfqd->cfq_fifo_expire_r, 1);
-SHOW_FUNCTION(cfq_fifo_expire_w_show, cfqd->cfq_fifo_expire_w, 1);
-SHOW_FUNCTION(cfq_fifo_batch_expire_show, cfqd->cfq_fifo_batch_expire, 1);
-SHOW_FUNCTION(cfq_find_best_show, cfqd->find_best_crq, 0);
+SHOW_FUNCTION(cfq_fifo_expire_sync_show, cfqd->cfq_fifo_expire[1], 1);
+SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
SHOW_FUNCTION(cfq_back_max_show, cfqd->cfq_back_max, 0);
SHOW_FUNCTION(cfq_back_penalty_show, cfqd->cfq_back_penalty, 0);
+SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
+SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
+SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
+SHOW_FUNCTION(cfq_max_depth_show, cfqd->cfq_max_depth, 0);
#undef SHOW_FUNCTION
#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
@@ -1694,12 +2302,15 @@ static ssize_t __FUNC(struct cfq_data *cfqd, const char *page, size_t count) \
}
STORE_FUNCTION(cfq_quantum_store, &cfqd->cfq_quantum, 1, UINT_MAX, 0);
STORE_FUNCTION(cfq_queued_store, &cfqd->cfq_queued, 1, UINT_MAX, 0);
-STORE_FUNCTION(cfq_fifo_expire_r_store, &cfqd->cfq_fifo_expire_r, 1, UINT_MAX, 1);
-STORE_FUNCTION(cfq_fifo_expire_w_store, &cfqd->cfq_fifo_expire_w, 1, UINT_MAX, 1);
-STORE_FUNCTION(cfq_fifo_batch_expire_store, &cfqd->cfq_fifo_batch_expire, 0, UINT_MAX, 1);
-STORE_FUNCTION(cfq_find_best_store, &cfqd->find_best_crq, 0, 1, 0);
+STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1, UINT_MAX, 1);
+STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_back_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
STORE_FUNCTION(cfq_back_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
+STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
+STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
+STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0);
+STORE_FUNCTION(cfq_max_depth_store, &cfqd->cfq_max_depth, 1, UINT_MAX, 0);
#undef STORE_FUNCTION
static struct cfq_fs_entry cfq_quantum_entry = {
@@ -1712,25 +2323,15 @@ static struct cfq_fs_entry cfq_queued_entry = {
.show = cfq_queued_show,
.store = cfq_queued_store,
};
-static struct cfq_fs_entry cfq_fifo_expire_r_entry = {
+static struct cfq_fs_entry cfq_fifo_expire_sync_entry = {
.attr = {.name = "fifo_expire_sync", .mode = S_IRUGO | S_IWUSR },
- .show = cfq_fifo_expire_r_show,
- .store = cfq_fifo_expire_r_store,
+ .show = cfq_fifo_expire_sync_show,
+ .store = cfq_fifo_expire_sync_store,
};
-static struct cfq_fs_entry cfq_fifo_expire_w_entry = {
+static struct cfq_fs_entry cfq_fifo_expire_async_entry = {
.attr = {.name = "fifo_expire_async", .mode = S_IRUGO | S_IWUSR },
- .show = cfq_fifo_expire_w_show,
- .store = cfq_fifo_expire_w_store,
-};
-static struct cfq_fs_entry cfq_fifo_batch_expire_entry = {
- .attr = {.name = "fifo_batch_expire", .mode = S_IRUGO | S_IWUSR },
- .show = cfq_fifo_batch_expire_show,
- .store = cfq_fifo_batch_expire_store,
-};
-static struct cfq_fs_entry cfq_find_best_entry = {
- .attr = {.name = "find_best_crq", .mode = S_IRUGO | S_IWUSR },
- .show = cfq_find_best_show,
- .store = cfq_find_best_store,
+ .show = cfq_fifo_expire_async_show,
+ .store = cfq_fifo_expire_async_store,
};
static struct cfq_fs_entry cfq_back_max_entry = {
.attr = {.name = "back_seek_max", .mode = S_IRUGO | S_IWUSR },
@@ -1742,27 +2343,43 @@ static struct cfq_fs_entry cfq_back_penalty_entry = {
.show = cfq_back_penalty_show,
.store = cfq_back_penalty_store,
};
-static struct cfq_fs_entry cfq_clear_elapsed_entry = {
- .attr = {.name = "clear_elapsed", .mode = S_IWUSR },
- .store = cfq_clear_elapsed,
+static struct cfq_fs_entry cfq_slice_sync_entry = {
+ .attr = {.name = "slice_sync", .mode = S_IRUGO | S_IWUSR },
+ .show = cfq_slice_sync_show,
+ .store = cfq_slice_sync_store,
};
-static struct cfq_fs_entry cfq_key_type_entry = {
- .attr = {.name = "key_type", .mode = S_IRUGO | S_IWUSR },
- .show = cfq_read_key_type,
- .store = cfq_set_key_type,
+static struct cfq_fs_entry cfq_slice_async_entry = {
+ .attr = {.name = "slice_async", .mode = S_IRUGO | S_IWUSR },
+ .show = cfq_slice_async_show,
+ .store = cfq_slice_async_store,
+};
+static struct cfq_fs_entry cfq_slice_async_rq_entry = {
+ .attr = {.name = "slice_async_rq", .mode = S_IRUGO | S_IWUSR },
+ .show = cfq_slice_async_rq_show,
+ .store = cfq_slice_async_rq_store,
+};
+static struct cfq_fs_entry cfq_slice_idle_entry = {
+ .attr = {.name = "slice_idle", .mode = S_IRUGO | S_IWUSR },
+ .show = cfq_slice_idle_show,
+ .store = cfq_slice_idle_store,
+};
+static struct cfq_fs_entry cfq_max_depth_entry = {
+ .attr = {.name = "max_depth", .mode = S_IRUGO | S_IWUSR },
+ .show = cfq_max_depth_show,
+ .store = cfq_max_depth_store,
};
-
static struct attribute *default_attrs[] = {
&cfq_quantum_entry.attr,
&cfq_queued_entry.attr,
- &cfq_fifo_expire_r_entry.attr,
- &cfq_fifo_expire_w_entry.attr,
- &cfq_fifo_batch_expire_entry.attr,
- &cfq_key_type_entry.attr,
- &cfq_find_best_entry.attr,
+ &cfq_fifo_expire_sync_entry.attr,
+ &cfq_fifo_expire_async_entry.attr,
&cfq_back_max_entry.attr,
&cfq_back_penalty_entry.attr,
- &cfq_clear_elapsed_entry.attr,
+ &cfq_slice_sync_entry.attr,
+ &cfq_slice_async_entry.attr,
+ &cfq_slice_async_rq_entry.attr,
+ &cfq_slice_idle_entry.attr,
+ &cfq_max_depth_entry.attr,
NULL,
};
@@ -1832,21 +2449,46 @@ static int __init cfq_init(void)
{
int ret;
+ /*
+ * could be 0 on HZ < 1000 setups
+ */
+ if (!cfq_slice_async)
+ cfq_slice_async = 1;
+ if (!cfq_slice_idle)
+ cfq_slice_idle = 1;
+
if (cfq_slab_setup())
return -ENOMEM;
ret = elv_register(&iosched_cfq);
- if (!ret) {
- __module_get(THIS_MODULE);
- return 0;
- }
+ if (ret)
+ cfq_slab_kill();
- cfq_slab_kill();
return ret;
}
static void __exit cfq_exit(void)
{
+ struct task_struct *g, *p;
+ unsigned long flags;
+
+ read_lock_irqsave(&tasklist_lock, flags);
+
+ /*
+ * iterate each process in the system, removing our io_context
+ */
+ do_each_thread(g, p) {
+ struct io_context *ioc = p->io_context;
+
+ if (ioc && ioc->cic) {
+ ioc->cic->exit(ioc->cic);
+ cfq_free_io_context(ioc->cic);
+ ioc->cic = NULL;
+ }
+ } while_each_thread(g, p);
+
+ read_unlock_irqrestore(&tasklist_lock, flags);
+
cfq_slab_kill();
elv_unregister(&iosched_cfq);
}
diff --git a/drivers/block/deadline-iosched.c b/drivers/block/deadline-iosched.c
index 4bc2fea73273..ff5201e02153 100644
--- a/drivers/block/deadline-iosched.c
+++ b/drivers/block/deadline-iosched.c
@@ -760,7 +760,8 @@ static void deadline_put_request(request_queue_t *q, struct request *rq)
}
static int
-deadline_set_request(request_queue_t *q, struct request *rq, int gfp_mask)
+deadline_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
+ int gfp_mask)
{
struct deadline_data *dd = q->elevator->elevator_data;
struct deadline_rq *drq;
diff --git a/drivers/block/elevator.c b/drivers/block/elevator.c
index f831f08f839c..98f0126a2deb 100644
--- a/drivers/block/elevator.c
+++ b/drivers/block/elevator.c
@@ -486,12 +486,13 @@ struct request *elv_former_request(request_queue_t *q, struct request *rq)
return NULL;
}
-int elv_set_request(request_queue_t *q, struct request *rq, int gfp_mask)
+int elv_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
+ int gfp_mask)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_set_req_fn)
- return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
+ return e->ops->elevator_set_req_fn(q, rq, bio, gfp_mask);
rq->elevator_private = NULL;
return 0;
@@ -505,12 +506,12 @@ void elv_put_request(request_queue_t *q, struct request *rq)
e->ops->elevator_put_req_fn(q, rq);
}
-int elv_may_queue(request_queue_t *q, int rw)
+int elv_may_queue(request_queue_t *q, int rw, struct bio *bio)
{
elevator_t *e = q->elevator;
if (e->ops->elevator_may_queue_fn)
- return e->ops->elevator_may_queue_fn(q, rw);
+ return e->ops->elevator_may_queue_fn(q, rw, bio);
return ELV_MQUEUE_MAY;
}
diff --git a/drivers/block/ll_rw_blk.c b/drivers/block/ll_rw_blk.c
index 60e64091de1b..234fdcfbdf01 100644
--- a/drivers/block/ll_rw_blk.c
+++ b/drivers/block/ll_rw_blk.c
@@ -276,6 +276,7 @@ static inline void rq_init(request_queue_t *q, struct request *rq)
rq->errors = 0;
rq->rq_status = RQ_ACTIVE;
rq->bio = rq->biotail = NULL;
+ rq->ioprio = 0;
rq->buffer = NULL;
rq->ref_count = 1;
rq->q = q;
@@ -1442,11 +1443,7 @@ void __generic_unplug_device(request_queue_t *q)
if (!blk_remove_plug(q))
return;
- /*
- * was plugged, fire request_fn if queue has stuff to do
- */
- if (elv_next_request(q))
- q->request_fn(q);
+ q->request_fn(q);
}
EXPORT_SYMBOL(__generic_unplug_device);
@@ -1776,8 +1773,8 @@ static inline void blk_free_request(request_queue_t *q, struct request *rq)
mempool_free(rq, q->rq.rq_pool);
}
-static inline struct request *blk_alloc_request(request_queue_t *q, int rw,
- int gfp_mask)
+static inline struct request *
+blk_alloc_request(request_queue_t *q, int rw, struct bio *bio, int gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
@@ -1790,7 +1787,7 @@ static inline struct request *blk_alloc_request(request_queue_t *q, int rw,
*/
rq->flags = rw;
- if (!elv_set_request(q, rq, gfp_mask))
+ if (!elv_set_request(q, rq, bio, gfp_mask))
return rq;
mempool_free(rq, q->rq.rq_pool);
@@ -1872,7 +1869,8 @@ static void freed_request(request_queue_t *q, int rw)
/*
* Get a free request, queue_lock must not be held
*/
-static struct request *get_request(request_queue_t *q, int rw, int gfp_mask)
+static struct request *get_request(request_queue_t *q, int rw, struct bio *bio,
+ int gfp_mask)
{
struct request *rq = NULL;
struct request_list *rl = &q->rq;
@@ -1895,7 +1893,7 @@ static struct request *get_request(request_queue_t *q, int rw, int gfp_mask)
}
}
- switch (elv_may_queue(q, rw)) {
+ switch (elv_may_queue(q, rw, bio)) {
case ELV_MQUEUE_NO:
goto rq_starved;
case ELV_MQUEUE_MAY:
@@ -1920,7 +1918,7 @@ get_rq:
set_queue_congested(q, rw);
spin_unlock_irq(q->queue_lock);
- rq = blk_alloc_request(q, rw, gfp_mask);
+ rq = blk_alloc_request(q, rw, bio, gfp_mask);
if (!rq) {
/*
* Allocation failed presumably due to memory. Undo anything
@@ -1961,7 +1959,8 @@ out:
* No available requests for this queue, unplug the device and wait for some
* requests to become available.
*/
-static struct request *get_request_wait(request_queue_t *q, int rw)
+static struct request *get_request_wait(request_queue_t *q, int rw,
+ struct bio *bio)
{
DEFINE_WAIT(wait);
struct request *rq;
@@ -1972,7 +1971,7 @@ static struct request *get_request_wait(request_queue_t *q, int rw)
prepare_to_wait_exclusive(&rl->wait[rw], &wait,
TASK_UNINTERRUPTIBLE);
- rq = get_request(q, rw, GFP_NOIO);
+ rq = get_request(q, rw, bio, GFP_NOIO);
if (!rq) {
struct io_context *ioc;
@@ -2003,9 +2002,9 @@ struct request *blk_get_request(request_queue_t *q, int rw, int gfp_mask)
BUG_ON(rw != READ && rw != WRITE);
if (gfp_mask & __GFP_WAIT)
- rq = get_request_wait(q, rw);
+ rq = get_request_wait(q, rw, NULL);
else
- rq = get_request(q, rw, gfp_mask);
+ rq = get_request(q, rw, NULL, gfp_mask);
return rq;
}
@@ -2333,7 +2332,6 @@ static void __blk_put_request(request_queue_t *q, struct request *req)
return;
req->rq_status = RQ_INACTIVE;
- req->q = NULL;
req->rl = NULL;
/*
@@ -2462,6 +2460,8 @@ static int attempt_merge(request_queue_t *q, struct request *req,
req->rq_disk->in_flight--;
}
+ req->ioprio = ioprio_best(req->ioprio, next->ioprio);
+
__blk_put_request(q, next);
return 1;
}
@@ -2514,11 +2514,13 @@ static int __make_request(request_queue_t *q, struct bio *bio)
{
struct request *req, *freereq = NULL;
int el_ret, rw, nr_sectors, cur_nr_sectors, barrier, err, sync;
+ unsigned short prio;
sector_t sector;
sector = bio->bi_sector;
nr_sectors = bio_sectors(bio);
cur_nr_sectors = bio_cur_sectors(bio);
+ prio = bio_prio(bio);
rw = bio_data_dir(bio);
sync = bio_sync(bio);
@@ -2559,6 +2561,7 @@ again:
req->biotail->bi_next = bio;
req->biotail = bio;
req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->ioprio = ioprio_best(req->ioprio, prio);
drive_stat_acct(req, nr_sectors, 0);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req);
@@ -2583,6 +2586,7 @@ again:
req->hard_cur_sectors = cur_nr_sectors;
req->sector = req->hard_sector = sector;
req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->ioprio = ioprio_best(req->ioprio, prio);
drive_stat_acct(req, nr_sectors, 0);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req);
@@ -2610,7 +2614,7 @@ get_rq:
freereq = NULL;
} else {
spin_unlock_irq(q->queue_lock);
- if ((freereq = get_request(q, rw, GFP_ATOMIC)) == NULL) {
+ if ((freereq = get_request(q, rw, bio, GFP_ATOMIC)) == NULL) {
/*
* READA bit set
*/
@@ -2618,7 +2622,7 @@ get_rq:
if (bio_rw_ahead(bio))
goto end_io;
- freereq = get_request_wait(q, rw);
+ freereq = get_request_wait(q, rw, bio);
}
goto again;
}
@@ -2646,6 +2650,7 @@ get_rq:
req->buffer = bio_data(bio); /* see ->buffer comment above */
req->waiting = NULL;
req->bio = req->biotail = bio;
+ req->ioprio = prio;
req->rq_disk = bio->bi_bdev->bd_disk;
req->start_time = jiffies;
@@ -2674,7 +2679,7 @@ static inline void blk_partition_remap(struct bio *bio)
if (bdev != bdev->bd_contains) {
struct hd_struct *p = bdev->bd_part;
- switch (bio->bi_rw) {
+ switch (bio_data_dir(bio)) {
case READ:
p->read_sectors += bio_sectors(bio);
p->reads++;
@@ -2693,6 +2698,7 @@ void blk_finish_queue_drain(request_queue_t *q)
{
struct request_list *rl = &q->rq;
struct request *rq;
+ int requeued = 0;
spin_lock_irq(q->queue_lock);
clear_bit(QUEUE_FLAG_DRAIN, &q->queue_flags);
@@ -2701,9 +2707,13 @@ void blk_finish_queue_drain(request_queue_t *q)
rq = list_entry_rq(q->drain_list.next);
list_del_init(&rq->queuelist);
- __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 1);
+ elv_requeue_request(q, rq);
+ requeued++;
}
+ if (requeued)
+ q->request_fn(q);
+
spin_unlock_irq(q->queue_lock);
wake_up(&rl->wait[0]);
@@ -2900,7 +2910,7 @@ void submit_bio(int rw, struct bio *bio)
BIO_BUG_ON(!bio->bi_size);
BIO_BUG_ON(!bio->bi_io_vec);
- bio->bi_rw = rw;
+ bio->bi_rw |= rw;
if (rw & WRITE)
mod_page_state(pgpgout, count);
else
@@ -3257,8 +3267,11 @@ void exit_io_context(void)
struct io_context *ioc;
local_irq_save(flags);
+ task_lock(current);
ioc = current->io_context;
current->io_context = NULL;
+ ioc->task = NULL;
+ task_unlock(current);
local_irq_restore(flags);
if (ioc->aic && ioc->aic->exit)
@@ -3293,12 +3306,12 @@ struct io_context *get_io_context(int gfp_flags)
ret = kmem_cache_alloc(iocontext_cachep, gfp_flags);
if (ret) {
atomic_set(&ret->refcount, 1);
- ret->pid = tsk->pid;
+ ret->task = current;
+ ret->set_ioprio = NULL;
ret->last_waited = jiffies; /* doesn't matter... */
ret->nr_batch_requests = 0; /* because this is 0 */
ret->aic = NULL;
ret->cic = NULL;
- spin_lock_init(&ret->lock);
local_irq_save(flags);
diff --git a/fs/Makefile b/fs/Makefile
index fc92e59e9faf..20edcf28bfd2 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,6 +10,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \
ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
+ ioprio.o
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_COMPAT) += compat.o
diff --git a/fs/ioprio.c b/fs/ioprio.c
new file mode 100644
index 000000000000..663e420636d6
--- /dev/null
+++ b/fs/ioprio.c
@@ -0,0 +1,172 @@
+/*
+ * fs/ioprio.c
+ *
+ * Copyright (C) 2004 Jens Axboe <axboe@suse.de>
+ *
+ * Helper functions for setting/querying io priorities of processes. The
+ * system calls closely mimmick getpriority/setpriority, see the man page for
+ * those. The prio argument is a composite of prio class and prio data, where
+ * the data argument has meaning within that class. The standard scheduling
+ * classes have 8 distinct prio levels, with 0 being the highest prio and 7
+ * being the lowest.
+ *
+ * IOW, setting BE scheduling class with prio 2 is done ala:
+ *
+ * unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2;
+ *
+ * ioprio_set(PRIO_PROCESS, pid, prio);
+ *
+ * See also Documentation/block/ioprio.txt
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/ioprio.h>
+#include <linux/blkdev.h>
+
+static int set_task_ioprio(struct task_struct *task, int ioprio)
+{
+ struct io_context *ioc;
+
+ if (task->uid != current->euid &&
+ task->uid != current->uid && !capable(CAP_SYS_NICE))
+ return -EPERM;
+
+ task_lock(task);
+
+ task->ioprio = ioprio;
+
+ ioc = task->io_context;
+ if (ioc && ioc->set_ioprio)
+ ioc->set_ioprio(ioc, ioprio);
+
+ task_unlock(task);
+ return 0;
+}
+
+asmlinkage int sys_ioprio_set(int which, int who, int ioprio)
+{
+ int class = IOPRIO_PRIO_CLASS(ioprio);
+ int data = IOPRIO_PRIO_DATA(ioprio);
+ struct task_struct *p, *g;
+ struct user_struct *user;
+ int ret;
+
+ switch (class) {
+ case IOPRIO_CLASS_RT:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ /* fall through, rt has prio field too */
+ case IOPRIO_CLASS_BE:
+ if (data >= IOPRIO_BE_NR || data < 0)
+ return -EINVAL;
+
+ break;
+ case IOPRIO_CLASS_IDLE:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ ret = -ESRCH;
+ read_lock_irq(&tasklist_lock);
+ switch (which) {
+ case IOPRIO_WHO_PROCESS:
+ if (!who)
+ p = current;
+ else
+ p = find_task_by_pid(who);
+ if (p)
+ ret = set_task_ioprio(p, ioprio);
+ break;
+ case IOPRIO_WHO_PGRP:
+ if (!who)
+ who = process_group(current);
+ do_each_task_pid(who, PIDTYPE_PGID, p) {
+ ret = set_task_ioprio(p, ioprio);
+ if (ret)
+ break;
+ } while_each_task_pid(who, PIDTYPE_PGID, p);
+ break;
+ case IOPRIO_WHO_USER:
+ if (!who)
+ user = current->user;
+ else
+ user = find_user(who);
+
+ if (!user)
+ break;
+
+ do_each_thread(g, p) {
+ if (p->uid != who)
+ continue;
+ ret = set_task_ioprio(p, ioprio);
+ if (ret)
+ break;
+ } while_each_thread(g, p);
+
+ if (who)
+ free_uid(user);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ read_unlock_irq(&tasklist_lock);
+ return ret;
+}
+
+asmlinkage int sys_ioprio_get(int which, int who)
+{
+ struct task_struct *g, *p;
+ struct user_struct *user;
+ int ret = -ESRCH;
+
+ read_lock_irq(&tasklist_lock);
+ switch (which) {
+ case IOPRIO_WHO_PROCESS:
+ if (!who)
+ p = current;
+ else
+ p = find_task_by_pid(who);
+ if (p)
+ ret = p->ioprio;
+ break;
+ case IOPRIO_WHO_PGRP:
+ if (!who)
+ who = process_group(current);
+ do_each_task_pid(who, PIDTYPE_PGID, p) {
+ if (ret == -ESRCH)
+ ret = p->ioprio;
+ else
+ ret = ioprio_best(ret, p->ioprio);
+ } while_each_task_pid(who, PIDTYPE_PGID, p);
+ break;
+ case IOPRIO_WHO_USER:
+ if (!who)
+ user = current->user;
+ else
+ user = find_user(who);
+
+ if (!user)
+ break;
+
+ do_each_thread(g, p) {
+ if (p->uid != user->uid)
+ continue;
+ if (ret == -ESRCH)
+ ret = p->ioprio;
+ else
+ ret = ioprio_best(ret, p->ioprio);
+ } while_each_thread(g, p);
+
+ if (who)
+ free_uid(user);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ read_unlock_irq(&tasklist_lock);
+ return ret;
+}
+
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 7b87707acc36..d1bcf0da6728 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -645,18 +645,22 @@ struct buffer_chunk {
static void write_chunk(struct buffer_chunk *chunk) {
int i;
+ get_fs_excl();
for (i = 0; i < chunk->nr ; i++) {
submit_logged_buffer(chunk->bh[i]) ;
}
chunk->nr = 0;
+ put_fs_excl();
}
static void write_ordered_chunk(struct buffer_chunk *chunk) {
int i;
+ get_fs_excl();
for (i = 0; i < chunk->nr ; i++) {
submit_ordered_buffer(chunk->bh[i]) ;
}
chunk->nr = 0;
+ put_fs_excl();
}
static int add_to_chunk(struct buffer_chunk *chunk, struct buffer_head *bh,
@@ -918,6 +922,8 @@ static int flush_commit_list(struct super_block *s, struct reiserfs_journal_list
return 0 ;
}
+ get_fs_excl();
+
/* before we can put our commit blocks on disk, we have to make sure everyone older than
** us is on disk too
*/
@@ -1055,6 +1061,7 @@ put_jl:
if (retval)
reiserfs_abort (s, retval, "Journal write error in %s", __FUNCTION__);
+ put_fs_excl();
return retval;
}
@@ -1251,6 +1258,8 @@ static int flush_journal_list(struct super_block *s,
return 0 ;
}
+ get_fs_excl();
+
/* if all the work is already done, get out of here */
if (atomic_read(&(jl->j_nonzerolen)) <= 0 &&
atomic_read(&(jl->j_commit_left)) <= 0) {
@@ -1450,6 +1459,7 @@ flush_older_and_return:
put_journal_list(s, jl);
if (flushall)
up(&journal->j_flush_sem);
+ put_fs_excl();
return err ;
}
@@ -2719,6 +2729,7 @@ relock:
th->t_trans_id = journal->j_trans_id ;
unlock_journal(p_s_sb) ;
INIT_LIST_HEAD (&th->t_list);
+ get_fs_excl();
return 0 ;
out_fail:
@@ -3526,6 +3537,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, struct super_b
BUG_ON (th->t_refcount > 1);
BUG_ON (!th->t_trans_id);
+ put_fs_excl();
current->journal_info = th->t_handle_save;
reiserfs_check_lock_depth(p_s_sb, "journal end");
if (journal->j_len == 0) {
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index 176413fb9ae3..e25e4c71a879 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -294,8 +294,10 @@
#define __NR_add_key 286
#define __NR_request_key 287
#define __NR_keyctl 288
+#define __NR_ioprio_set 289
+#define __NR_ioprio_get 290
-#define NR_syscalls 289
+#define NR_syscalls 291
/*
* user-visible error numbers are in the range -1 - -128: see
diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h
index f7f43ec2483a..517f1649ee64 100644
--- a/include/asm-ia64/unistd.h
+++ b/include/asm-ia64/unistd.h
@@ -263,6 +263,8 @@
#define __NR_add_key 1271
#define __NR_request_key 1272
#define __NR_keyctl 1273
+#define __NR_ioprio_set 1274
+#define __NR_ioprio_get 1275
#define __NR_set_zone_reclaim 1276
#ifdef __KERNEL__
diff --git a/include/asm-ppc/unistd.h b/include/asm-ppc/unistd.h
index cc51e5c9acc2..e8b79220b29c 100644
--- a/include/asm-ppc/unistd.h
+++ b/include/asm-ppc/unistd.h
@@ -277,8 +277,10 @@
#define __NR_request_key 270
#define __NR_keyctl 271
#define __NR_waitid 272
+#define __NR_ioprio_set 273
+#define __NR_ioprio_get 274
-#define __NR_syscalls 273
+#define __NR_syscalls 275
#define __NR(n) #n
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index d767adcbf0ff..6560439a83e4 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -561,8 +561,12 @@ __SYSCALL(__NR_add_key, sys_add_key)
__SYSCALL(__NR_request_key, sys_request_key)
#define __NR_keyctl 250
__SYSCALL(__NR_keyctl, sys_keyctl)
+#define __NR_ioprio_set 251
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 252
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
-#define __NR_syscall_max __NR_keyctl
+#define __NR_syscall_max __NR_ioprio_get
#ifndef __NO_STUBS
/* user-visible error numbers are in the range -1 - -4095 */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 038022763f09..36ef29fa0d8b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -22,6 +22,7 @@
#include <linux/highmem.h>
#include <linux/mempool.h>
+#include <linux/ioprio.h>
/* Platforms may set this to teach the BIO layer about IOMMU hardware. */
#include <asm/io.h>
@@ -149,6 +150,19 @@ struct bio {
#define BIO_RW_FAILFAST 3
#define BIO_RW_SYNC 4
+/*
+ * upper 16 bits of bi_rw define the io priority of this bio
+ */
+#define BIO_PRIO_SHIFT (8 * sizeof(unsigned long) - IOPRIO_BITS)
+#define bio_prio(bio) ((bio)->bi_rw >> BIO_PRIO_SHIFT)
+#define bio_prio_valid(bio) ioprio_valid(bio_prio(bio))
+
+#define bio_set_prio(bio, prio) do { \
+ WARN_ON(prio >= (1 << IOPRIO_BITS)); \
+ (bio)->bi_rw &= ((1UL << BIO_PRIO_SHIFT) - 1); \
+ (bio)->bi_rw |= ((unsigned long) (prio) << BIO_PRIO_SHIFT); \
+} while (0)
+
/*
* various member access, note that bio_data should of course not be used
* on highmem page vectors
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b54a0348a890..21a8674cd149 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -54,16 +54,23 @@ struct as_io_context {
struct cfq_queue;
struct cfq_io_context {
- void (*dtor)(struct cfq_io_context *);
- void (*exit)(struct cfq_io_context *);
-
- struct io_context *ioc;
-
/*
* circular list of cfq_io_contexts belonging to a process io context
*/
struct list_head list;
struct cfq_queue *cfqq;
+ void *key;
+
+ struct io_context *ioc;
+
+ unsigned long last_end_request;
+ unsigned long last_queue;
+ unsigned long ttime_total;
+ unsigned long ttime_samples;
+ unsigned long ttime_mean;
+
+ void (*dtor)(struct cfq_io_context *);
+ void (*exit)(struct cfq_io_context *);
};
/*
@@ -73,7 +80,9 @@ struct cfq_io_context {
*/
struct io_context {
atomic_t refcount;
- pid_t pid;
+ struct task_struct *task;
+
+ int (*set_ioprio)(struct io_context *, unsigned int);
/*
* For request batching
@@ -81,8 +90,6 @@ struct io_context {
unsigned long last_waited; /* Time last woken after wait for request */
int nr_batch_requests; /* Number of requests left in the batch */
- spinlock_t lock;
-
struct as_io_context *aic;
struct cfq_io_context *cic;
};
@@ -134,6 +141,8 @@ struct request {
void *elevator_private;
+ unsigned short ioprio;
+
int rq_status; /* should split this into a few status bits */
struct gendisk *rq_disk;
int errors;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index ee54f81faad5..ea6bbc2d7407 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -16,9 +16,9 @@ typedef void (elevator_remove_req_fn) (request_queue_t *, struct request *);
typedef void (elevator_requeue_req_fn) (request_queue_t *, struct request *);
typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct request *);
typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *);
-typedef int (elevator_may_queue_fn) (request_queue_t *, int);
+typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *);
-typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, int);
+typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, int);
typedef void (elevator_put_req_fn) (request_queue_t *, struct request *);
typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *);
@@ -96,9 +96,9 @@ extern struct request *elv_former_request(request_queue_t *, struct request *);
extern struct request *elv_latter_request(request_queue_t *, struct request *);
extern int elv_register_queue(request_queue_t *q);
extern void elv_unregister_queue(request_queue_t *q);
-extern int elv_may_queue(request_queue_t *, int);
+extern int elv_may_queue(request_queue_t *, int, struct bio *);
extern void elv_completed_request(request_queue_t *, struct request *);
-extern int elv_set_request(request_queue_t *, struct request *, int);
+extern int elv_set_request(request_queue_t *, struct request *, struct bio *, int);
extern void elv_put_request(request_queue_t *, struct request *);
/*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3ae8e37bdfc8..047bde30836a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -213,6 +213,7 @@ extern int dir_notify_enable;
#include <linux/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
+#include <linux/sched.h>
#include <asm/atomic.h>
#include <asm/semaphore.h>
@@ -822,16 +823,34 @@ enum {
#define vfs_check_frozen(sb, level) \
wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
+static inline void get_fs_excl(void)
+{
+ atomic_inc(¤t->fs_excl);
+}
+
+static inline void put_fs_excl(void)
+{
+ atomic_dec(¤t->fs_excl);
+}
+
+static inline int has_fs_excl(void)
+{
+ return atomic_read(¤t->fs_excl);
+}
+
+
/*
* Superblock locking.
*/
static inline void lock_super(struct super_block * sb)
{
+ get_fs_excl();
down(&sb->s_lock);
}
static inline void unlock_super(struct super_block * sb)
{
+ put_fs_excl();
up(&sb->s_lock);
}
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 03206a425d7a..c727c195a91a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -81,6 +81,7 @@ extern struct group_info init_groups;
.mm = NULL, \
.active_mm = &init_mm, \
.run_list = LIST_HEAD_INIT(tsk.run_list), \
+ .ioprio = 0, \
.time_slice = HZ, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
.ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \
@@ -110,6 +111,7 @@ extern struct group_info init_groups;
.proc_lock = SPIN_LOCK_UNLOCKED, \
.journal_info = NULL, \
.cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
+ .fs_excl = ATOMIC_INIT(0), \
}
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
new file mode 100644
index 000000000000..7811300d88ee
--- /dev/null
+++ b/include/linux/ioprio.h
@@ -0,0 +1,87 @@
+#ifndef IOPRIO_H
+#define IOPRIO_H
+
+#include <linux/sched.h>
+
+/*
+ * Gives us 8 prio classes with 13-bits of data for each class
+ */
+#define IOPRIO_BITS (16)
+#define IOPRIO_CLASS_SHIFT (13)
+#define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1)
+
+#define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT)
+#define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK)
+
+#define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE)
+
+/*
+ * These are the io priority groups as implemented by CFQ. RT is the realtime
+ * class, it always gets premium service. BE is the best-effort scheduling
+ * class, the default for any process. IDLE is the idle scheduling class, it
+ * is only served when no one else is using the disk.
+ */
+enum {
+ IOPRIO_CLASS_NONE,
+ IOPRIO_CLASS_RT,
+ IOPRIO_CLASS_BE,
+ IOPRIO_CLASS_IDLE,
+};
+
+/*
+ * 8 best effort priority levels are supported
+ */
+#define IOPRIO_BE_NR (8)
+
+asmlinkage int sys_ioprio_set(int, int, int);
+asmlinkage int sys_ioprio_get(int, int);
+
+enum {
+ IOPRIO_WHO_PROCESS = 1,
+ IOPRIO_WHO_PGRP,
+ IOPRIO_WHO_USER,
+};
+
+/*
+ * if process has set io priority explicitly, use that. if not, convert
+ * the cpu scheduler nice value to an io priority
+ */
+#define IOPRIO_NORM (4)
+static inline int task_ioprio(struct task_struct *task)
+{
+ WARN_ON(!ioprio_valid(task->ioprio));
+ return IOPRIO_PRIO_DATA(task->ioprio);
+}
+
+static inline int task_nice_ioprio(struct task_struct *task)
+{
+ return (task_nice(task) + 20) / 5;
+}
+
+/*
+ * For inheritance, return the highest of the two given priorities
+ */
+static inline int ioprio_best(unsigned short aprio, unsigned short bprio)
+{
+ unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
+ unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+
+ if (!ioprio_valid(aprio))
+ return bprio;
+ if (!ioprio_valid(bprio))
+ return aprio;
+
+ if (aclass == IOPRIO_CLASS_NONE)
+ aclass = IOPRIO_CLASS_BE;
+ if (bclass == IOPRIO_CLASS_NONE)
+ bclass = IOPRIO_CLASS_BE;
+
+ if (aclass == bclass)
+ return min(aprio, bprio);
+ if (aclass > bclass)
+ return bprio;
+ else
+ return aprio;
+}
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9530b1903160..ff48815bd3a2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -608,6 +608,8 @@ struct task_struct {
struct list_head run_list;
prio_array_t *array;
+ unsigned short ioprio;
+
unsigned long sleep_avg;
unsigned long long timestamp, last_ran;
unsigned long long sched_time; /* sched_clock time spent running */
@@ -763,6 +765,7 @@ struct task_struct {
nodemask_t mems_allowed;
int cpuset_mems_generation;
#endif
+ atomic_t fs_excl; /* holding fs exclusive resources */
};
static inline pid_t process_group(struct task_struct *tsk)
@@ -1112,7 +1115,8 @@ extern void unhash_process(struct task_struct *p);
/*
* Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
- * subscriptions and synchronises with wait4(). Also used in procfs.
+ * subscriptions and synchronises with wait4(). Also used in procfs. Also
+ * pins the final release of task.io_context.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 1262cb43c3ab..d5c3fe1bf33d 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -14,11 +14,13 @@ extern struct list_head inode_unused;
* Yes, writeback.h requires sched.h
* No, sched.h is not included from here.
*/
-static inline int current_is_pdflush(void)
+static inline int task_is_pdflush(struct task_struct *task)
{
- return current->flags & PF_FLUSHER;
+ return task->flags & PF_FLUSHER;
}
+#define current_is_pdflush() task_is_pdflush(current)
+
/*
* fs/fs-writeback.c
*/
diff --git a/kernel/exit.c b/kernel/exit.c
index 3ebcd60a19c6..9d1b10ed0135 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -784,6 +784,8 @@ fastcall NORET_TYPE void do_exit(long code)
profile_task_exit(tsk);
+ WARN_ON(atomic_read(&tsk->fs_excl));
+
if (unlikely(in_interrupt()))
panic("Aiee, killing interrupt handler!");
if (unlikely(!tsk->pid))
diff --git a/kernel/fork.c b/kernel/fork.c
index 2c7806873bfd..cdef6cea8900 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1090,6 +1090,11 @@ static task_t *copy_process(unsigned long clone_flags,
spin_unlock(¤t->sighand->siglock);
}
+ /*
+ * inherit ioprio
+ */
+ p->ioprio = current->ioprio;
+
SET_LINKS(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
diff --git a/kernel/sched.c b/kernel/sched.c
index a07cff90d849..e2b0d3e4dd06 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3448,15 +3448,7 @@ int task_nice(const task_t *p)
{
return TASK_NICE(p);
}
-
-/*
- * The only users of task_nice are binfmt_elf and binfmt_elf32.
- * binfmt_elf is no longer modular, but binfmt_elf32 still is.
- * Therefore, task_nice is needed if there is a compat_mode.
- */
-#ifdef CONFIG_COMPAT
EXPORT_SYMBOL_GPL(task_nice);
-#endif
/**
* idle_cpu - is a given cpu idle currently?