summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/Kconfig8
-rw-r--r--block/blk-barrier.c2
-rw-r--r--block/blk-core.c100
-rw-r--r--block/blk-integrity.c25
-rw-r--r--block/blk-sysfs.c58
-rw-r--r--block/blk.h8
-rw-r--r--block/blktrace.c728
-rw-r--r--block/cfq-iosched.c39
8 files changed, 861 insertions, 107 deletions
diff --git a/block/Kconfig b/block/Kconfig
index 0cbb3b88b59a..7cdaa1d72252 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -50,6 +50,8 @@ config BLK_DEV_IO_TRACE
select RELAY
select DEBUG_FS
select TRACEPOINTS
+ select TRACING
+ select STACKTRACE
help
Say Y here if you want to be able to trace the block layer actions
on a given queue. Tracing allows you to see any traffic happening
@@ -58,6 +60,12 @@ config BLK_DEV_IO_TRACE
git://git.kernel.dk/blktrace.git
+ Tracing also is possible using the ftrace interface, e.g.:
+
+ echo 1 > /sys/block/sda/sda1/trace/enable
+ echo blk > /sys/kernel/debug/tracing/current_tracer
+ cat /sys/kernel/debug/tracing/trace_pipe
+
If unsure, say N.
config BLK_DEV_BSG
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 8eba4e43bb0c..f7dae57e6cab 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -302,7 +302,7 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
* Description:
* Issue a flush for the block device in question. Caller can supply
* room for storing the error offset in case of a flush error, if they
- * wish to. Caller must run wait_for_completion() on its own.
+ * wish to.
*/
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
diff --git a/block/blk-core.c b/block/blk-core.c
index a824e49c0d0a..29bcfac6c688 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,11 +64,12 @@ static struct workqueue_struct *kblockd_workqueue;
static void drive_stat_acct(struct request *rq, int new_io)
{
+ struct gendisk *disk = rq->rq_disk;
struct hd_struct *part;
int rw = rq_data_dir(rq);
int cpu;
- if (!blk_fs_request(rq) || !rq->rq_disk)
+ if (!blk_fs_request(rq) || !disk || !blk_do_io_stat(disk->queue))
return;
cpu = part_stat_lock();
@@ -599,8 +600,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
- q->queue_flags = (1 << QUEUE_FLAG_CLUSTER |
- 1 << QUEUE_FLAG_STACKABLE);
+ q->queue_flags = QUEUE_FLAG_DEFAULT;
q->queue_lock = lock;
blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
@@ -1125,6 +1125,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
if (bio_sync(bio))
req->cmd_flags |= REQ_RW_SYNC;
+ if (bio_unplug(bio))
+ req->cmd_flags |= REQ_UNPLUG;
if (bio_rw_meta(bio))
req->cmd_flags |= REQ_RW_META;
@@ -1141,6 +1143,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
int el_ret, nr_sectors;
const unsigned short prio = bio_prio(bio);
const int sync = bio_sync(bio);
+ const int unplug = bio_unplug(bio);
int rw_flags;
nr_sectors = bio_sectors(bio);
@@ -1244,7 +1247,7 @@ get_rq:
blk_plug_device(q);
add_request(q, req);
out:
- if (sync || blk_queue_nonrot(q))
+ if (unplug || blk_queue_nonrot(q))
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
return 0;
@@ -1448,6 +1451,11 @@ static inline void __generic_make_request(struct bio *bio)
err = -EOPNOTSUPP;
goto end_io;
}
+ if (bio_barrier(bio) && bio_has_data(bio) &&
+ (q->next_ordered == QUEUE_ORDERED_NONE)) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
ret = q->make_request_fn(q, bio);
} while (ret);
@@ -1655,6 +1663,55 @@ void blkdev_dequeue_request(struct request *req)
}
EXPORT_SYMBOL(blkdev_dequeue_request);
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+ struct gendisk *disk = req->rq_disk;
+
+ if (!disk || !blk_do_io_stat(disk->queue))
+ return;
+
+ if (blk_fs_request(req)) {
+ const int rw = rq_data_dir(req);
+ struct hd_struct *part;
+ int cpu;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(req->rq_disk, req->sector);
+ part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+ part_stat_unlock();
+ }
+}
+
+static void blk_account_io_done(struct request *req)
+{
+ struct gendisk *disk = req->rq_disk;
+
+ if (!disk || !blk_do_io_stat(disk->queue))
+ return;
+
+ /*
+ * Account IO completion. bar_rq isn't accounted as a normal
+ * IO on queueing nor completion. Accounting the containing
+ * request is enough.
+ */
+ if (blk_fs_request(req) && req != &req->q->bar_rq) {
+ unsigned long duration = jiffies - req->start_time;
+ const int rw = rq_data_dir(req);
+ struct hd_struct *part;
+ int cpu;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(disk, req->sector);
+
+ part_stat_inc(cpu, part, ios[rw]);
+ part_stat_add(cpu, part, ticks[rw], duration);
+ part_round_stats(cpu, part);
+ part_dec_in_flight(part);
+
+ part_stat_unlock();
+ }
+}
+
/**
* __end_that_request_first - end I/O on a request
* @req: the request being processed
@@ -1690,16 +1747,7 @@ static int __end_that_request_first(struct request *req, int error,
(unsigned long long)req->sector);
}
- if (blk_fs_request(req) && req->rq_disk) {
- const int rw = rq_data_dir(req);
- struct hd_struct *part;
- int cpu;
-
- cpu = part_stat_lock();
- part = disk_map_sector_rcu(req->rq_disk, req->sector);
- part_stat_add(cpu, part, sectors[rw], nr_bytes >> 9);
- part_stat_unlock();
- }
+ blk_account_io_completion(req, nr_bytes);
total_bytes = bio_nbytes = 0;
while ((bio = req->bio) != NULL) {
@@ -1779,8 +1827,6 @@ static int __end_that_request_first(struct request *req, int error,
*/
static void end_that_request_last(struct request *req, int error)
{
- struct gendisk *disk = req->rq_disk;
-
if (blk_rq_tagged(req))
blk_queue_end_tag(req->q, req);
@@ -1792,27 +1838,7 @@ static void end_that_request_last(struct request *req, int error)
blk_delete_timer(req);
- /*
- * Account IO completion. bar_rq isn't accounted as a normal
- * IO on queueing nor completion. Accounting the containing
- * request is enough.
- */
- if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
- unsigned long duration = jiffies - req->start_time;
- const int rw = rq_data_dir(req);
- struct hd_struct *part;
- int cpu;
-
- cpu = part_stat_lock();
- part = disk_map_sector_rcu(disk, req->sector);
-
- part_stat_inc(cpu, part, ios[rw]);
- part_stat_add(cpu, part, ticks[rw], duration);
- part_round_stats(cpu, part);
- part_dec_in_flight(part);
-
- part_stat_unlock();
- }
+ blk_account_io_done(req);
if (req->end_io)
req->end_io(req, error);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 61a8e2f8fdd0..91fa8e06b6a5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -309,24 +309,24 @@ static struct kobj_type integrity_ktype = {
/**
* blk_integrity_register - Register a gendisk as being integrity-capable
* @disk: struct gendisk pointer to make integrity-aware
- * @template: integrity profile
+ * @template: optional integrity profile to register
*
* Description: When a device needs to advertise itself as being able
* to send/receive integrity metadata it must use this function to
* register the capability with the block layer. The template is a
* blk_integrity struct with values appropriate for the underlying
- * hardware. See Documentation/block/data-integrity.txt.
+ * hardware. If template is NULL the new profile is allocated but
+ * not filled out. See Documentation/block/data-integrity.txt.
*/
int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
{
struct blk_integrity *bi;
BUG_ON(disk == NULL);
- BUG_ON(template == NULL);
if (disk->integrity == NULL) {
bi = kmem_cache_alloc(integrity_cachep,
- GFP_KERNEL | __GFP_ZERO);
+ GFP_KERNEL | __GFP_ZERO);
if (!bi)
return -1;
@@ -346,13 +346,16 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
bi = disk->integrity;
/* Use the provided profile as template */
- bi->name = template->name;
- bi->generate_fn = template->generate_fn;
- bi->verify_fn = template->verify_fn;
- bi->tuple_size = template->tuple_size;
- bi->set_tag_fn = template->set_tag_fn;
- bi->get_tag_fn = template->get_tag_fn;
- bi->tag_size = template->tag_size;
+ if (template != NULL) {
+ bi->name = template->name;
+ bi->generate_fn = template->generate_fn;
+ bi->verify_fn = template->verify_fn;
+ bi->tuple_size = template->tuple_size;
+ bi->set_tag_fn = template->set_tag_fn;
+ bi->get_tag_fn = template->get_tag_fn;
+ bi->tag_size = template->tag_size;
+ } else
+ bi->name = "unsupported";
return 0;
}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a29cb788e408..e29ddfc73cf4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -130,6 +130,27 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
return queue_var_show(max_hw_sectors_kb, (page));
}
+static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
+{
+ return queue_var_show(!blk_queue_nonrot(q), page);
+}
+
+static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
+ size_t count)
+{
+ unsigned long nm;
+ ssize_t ret = queue_var_store(&nm, page, count);
+
+ spin_lock_irq(q->queue_lock);
+ if (nm)
+ queue_flag_clear(QUEUE_FLAG_NONROT, q);
+ else
+ queue_flag_set(QUEUE_FLAG_NONROT, q);
+ spin_unlock_irq(q->queue_lock);
+
+ return ret;
+}
+
static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
{
return queue_var_show(blk_queue_nomerges(q), page);
@@ -146,8 +167,8 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
queue_flag_set(QUEUE_FLAG_NOMERGES, q);
else
queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
-
spin_unlock_irq(q->queue_lock);
+
return ret;
}
@@ -176,6 +197,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
return ret;
}
+static ssize_t queue_iostats_show(struct request_queue *q, char *page)
+{
+ return queue_var_show(blk_queue_io_stat(q), page);
+}
+
+static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
+ size_t count)
+{
+ unsigned long stats;
+ ssize_t ret = queue_var_store(&stats, page, count);
+
+ spin_lock_irq(q->queue_lock);
+ if (stats)
+ queue_flag_set(QUEUE_FLAG_IO_STAT, q);
+ else
+ queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+ spin_unlock_irq(q->queue_lock);
+
+ return ret;
+}
+
static struct queue_sysfs_entry queue_requests_entry = {
.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
.show = queue_requests_show,
@@ -210,6 +252,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
.show = queue_hw_sector_size_show,
};
+static struct queue_sysfs_entry queue_nonrot_entry = {
+ .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+ .show = queue_nonrot_show,
+ .store = queue_nonrot_store,
+};
+
static struct queue_sysfs_entry queue_nomerges_entry = {
.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
.show = queue_nomerges_show,
@@ -222,6 +270,12 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = {
.store = queue_rq_affinity_store,
};
+static struct queue_sysfs_entry queue_iostats_entry = {
+ .attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+ .show = queue_iostats_show,
+ .store = queue_iostats_store,
+};
+
static struct attribute *default_attrs[] = {
&queue_requests_entry.attr,
&queue_ra_entry.attr,
@@ -229,8 +283,10 @@ static struct attribute *default_attrs[] = {
&queue_max_sectors_entry.attr,
&queue_iosched_entry.attr,
&queue_hw_sector_size_entry.attr,
+ &queue_nonrot_entry.attr,
&queue_nomerges_entry.attr,
&queue_rq_affinity_entry.attr,
+ &queue_iostats_entry.attr,
NULL,
};
diff --git a/block/blk.h b/block/blk.h
index 6e1ed40534e9..0dce92c37496 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -108,4 +108,12 @@ static inline int blk_cpu_to_group(int cpu)
#endif
}
+static inline int blk_do_io_stat(struct request_queue *q)
+{
+ if (q)
+ return blk_queue_io_stat(q);
+
+ return 0;
+}
+
#endif
diff --git a/block/blktrace.c b/block/blktrace.c
index b0a2cae886db..3f25425ade12 100644
--- a/block/blktrace.c
+++ b/block/blktrace.c
@@ -25,9 +25,27 @@
#include <linux/time.h>
#include <trace/block.h>
#include <asm/uaccess.h>
+#include <../kernel/trace/trace_output.h>
static unsigned int blktrace_seq __read_mostly = 1;
+static struct trace_array *blk_tr;
+static int __read_mostly blk_tracer_enabled;
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_BLK_OPT_CLASSIC 0x1
+
+static struct tracer_opt blk_tracer_opts[] = {
+ /* Default disable the minimalistic output */
+ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) },
+ { }
+};
+
+static struct tracer_flags blk_tracer_flags = {
+ .val = 0,
+ .opts = blk_tracer_opts,
+};
+
/* Global reference count of probes */
static DEFINE_MUTEX(blk_probe_mutex);
static atomic_t blk_probes_ref = ATOMIC_INIT(0);
@@ -43,6 +61,9 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
{
struct blk_io_trace *t;
+ if (!bt->rchan)
+ return;
+
t = relay_reserve(bt->rchan, sizeof(*t) + len);
if (t) {
const int cpu = smp_processor_id();
@@ -90,6 +111,16 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
unsigned long flags;
char *buf;
+ if (blk_tr) {
+ va_start(args, fmt);
+ ftrace_vprintk(fmt, args);
+ va_end(args);
+ return;
+ }
+
+ if (!bt->msg_data)
+ return;
+
local_irq_save(flags);
buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
va_start(args, fmt);
@@ -131,13 +162,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
int rw, u32 what, int error, int pdu_len, void *pdu_data)
{
struct task_struct *tsk = current;
+ struct ring_buffer_event *event = NULL;
struct blk_io_trace *t;
unsigned long flags;
unsigned long *sequence;
pid_t pid;
- int cpu;
+ int cpu, pc = 0;
- if (unlikely(bt->trace_state != Blktrace_running))
+ if (unlikely(bt->trace_state != Blktrace_running ||
+ !blk_tracer_enabled))
return;
what |= ddir_act[rw & WRITE];
@@ -150,6 +183,24 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
pid = tsk->pid;
if (unlikely(act_log_check(bt, what, sector, pid)))
return;
+ cpu = raw_smp_processor_id();
+
+ if (blk_tr) {
+ struct trace_entry *ent;
+ tracing_record_cmdline(current);
+
+ event = ring_buffer_lock_reserve(blk_tr->buffer,
+ sizeof(*t) + pdu_len, &flags);
+ if (!event)
+ return;
+
+ ent = ring_buffer_event_data(event);
+ t = (struct blk_io_trace *)ent;
+ pc = preempt_count();
+ tracing_generic_entry_update(ent, 0, pc);
+ ent->type = TRACE_BLK;
+ goto record_it;
+ }
/*
* A word about the locking here - we disable interrupts to reserve
@@ -163,23 +214,33 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
if (t) {
- cpu = smp_processor_id();
sequence = per_cpu_ptr(bt->sequence, cpu);
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
t->sequence = ++(*sequence);
t->time = ktime_to_ns(ktime_get());
+ t->cpu = cpu;
+ t->pid = pid;
+record_it:
t->sector = sector;
t->bytes = bytes;
t->action = what;
- t->pid = pid;
t->device = bt->dev;
- t->cpu = cpu;
t->error = error;
t->pdu_len = pdu_len;
if (pdu_len)
memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
+
+ if (blk_tr) {
+ ring_buffer_unlock_commit(blk_tr->buffer, event, flags);
+ if (pid != 0 &&
+ !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC) &&
+ (trace_flags & TRACE_ITER_STACKTRACE) != 0)
+ __trace_stack(blk_tr, NULL, flags, 5, pc);
+ trace_wake_up();
+ return;
+ }
}
local_irq_restore(flags);
@@ -187,59 +248,12 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
static struct dentry *blk_tree_root;
static DEFINE_MUTEX(blk_tree_mutex);
-static unsigned int root_users;
-
-static inline void blk_remove_root(void)
-{
- if (blk_tree_root) {
- debugfs_remove(blk_tree_root);
- blk_tree_root = NULL;
- }
-}
-
-static void blk_remove_tree(struct dentry *dir)
-{
- mutex_lock(&blk_tree_mutex);
- debugfs_remove(dir);
- if (--root_users == 0)
- blk_remove_root();
- mutex_unlock(&blk_tree_mutex);
-}
-
-static struct dentry *blk_create_tree(const char *blk_name)
-{
- struct dentry *dir = NULL;
- int created = 0;
-
- mutex_lock(&blk_tree_mutex);
-
- if (!blk_tree_root) {
- blk_tree_root = debugfs_create_dir("block", NULL);
- if (!blk_tree_root)
- goto err;
- created = 1;
- }
-
- dir = debugfs_create_dir(blk_name, blk_tree_root);
- if (dir)
- root_users++;
- else {
- /* Delete root only if we created it */
- if (created)
- blk_remove_root();
- }
-
-err:
- mutex_unlock(&blk_tree_mutex);
- return dir;
-}
static void blk_trace_cleanup(struct blk_trace *bt)
{
- relay_close(bt->rchan);
debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
- blk_remove_tree(bt->dir);
+ relay_close(bt->rchan);
free_percpu(bt->sequence);
free_percpu(bt->msg_data);
kfree(bt);
@@ -346,7 +360,18 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
static int blk_remove_buf_file_callback(struct dentry *dentry)
{
+ struct dentry *parent = dentry->d_parent;
debugfs_remove(dentry);
+
+ /*
+ * this will fail for all but the last file, but that is ok. what we
+ * care about is the top level buts->name directory going away, when
+ * the last trace file is gone. Then we don't have to rmdir() that
+ * manually on trace stop, so it nicely solves the issue with
+ * force killing of running traces.
+ */
+
+ debugfs_remove(parent);
return 0;
}
@@ -404,7 +429,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
goto err;
ret = -ENOENT;
- dir = blk_create_tree(buts->name);
+
+ if (!blk_tree_root) {
+ blk_tree_root = debugfs_create_dir("block", NULL);
+ if (!blk_tree_root)
+ return -ENOMEM;
+ }
+
+ dir = debugfs_create_dir(buts->name, blk_tree_root);
+
if (!dir)
goto err;
@@ -458,8 +491,6 @@ probe_err:
atomic_dec(&blk_probes_ref);
mutex_unlock(&blk_probe_mutex);
err:
- if (dir)
- blk_remove_tree(dir);
if (bt) {
if (bt->msg_file)
debugfs_remove(bt->msg_file);
@@ -888,3 +919,588 @@ static void blk_unregister_tracepoints(void)
tracepoint_synchronize_unregister();
}
+
+/*
+ * struct blk_io_tracer formatting routines
+ */
+
+static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
+{
+ int i = 0;
+
+ if (t->action & BLK_TC_DISCARD)
+ rwbs[i++] = 'D';
+ else if (t->action & BLK_TC_WRITE)
+ rwbs[i++] = 'W';
+ else if (t->bytes)
+ rwbs[i++] = 'R';
+ else
+ rwbs[i++] = 'N';
+
+ if (t->action & BLK_TC_AHEAD)
+ rwbs[i++] = 'A';
+ if (t->action & BLK_TC_BARRIER)
+ rwbs[i++] = 'B';
+ if (t->action & BLK_TC_SYNC)
+ rwbs[i++] = 'S';
+ if (t->action & BLK_TC_META)
+ rwbs[i++] = 'M';
+
+ rwbs[i] = '\0';
+}
+
+static inline
+const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent)
+{
+ return (const struct blk_io_trace *)ent;
+}
+
+static inline const void *pdu_start(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent) + 1;
+}
+
+static inline u32 t_sec(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->bytes >> 9;
+}
+
+static inline unsigned long long t_sector(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->sector;
+}
+
+static inline __u16 t_error(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->sector;
+}
+
+static __u64 get_pdu_int(const struct trace_entry *ent)
+{
+ const __u64 *val = pdu_start(ent);
+ return be64_to_cpu(*val);
+}
+
+static void get_pdu_remap(const struct trace_entry *ent,
+ struct blk_io_trace_remap *r)
+{
+ const struct blk_io_trace_remap *__r = pdu_start(ent);
+ __u64 sector = __r->sector;
+
+ r->device = be32_to_cpu(__r->device);
+ r->device_from = be32_to_cpu(__r->device_from);
+ r->sector = be64_to_cpu(sector);
+}
+
+static int blk_log_action_iter(struct trace_iterator *iter, const char *act)
+{
+ char rwbs[6];
+ unsigned long long ts = ns2usecs(iter->ts);
+ unsigned long usec_rem = do_div(ts, USEC_PER_SEC);
+ unsigned secs = (unsigned long)ts;
+ const struct trace_entry *ent = iter->ent;
+ const struct blk_io_trace *t = (const struct blk_io_trace *)ent;
+
+ fill_rwbs(rwbs, t);
+
+ return trace_seq_printf(&iter->seq,
+ "%3d,%-3d %2d %5d.%06lu %5u %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), iter->cpu,
+ secs, usec_rem, ent->pid, act, rwbs);
+}
+
+static int blk_log_action_seq(struct trace_seq *s, const struct blk_io_trace *t,
+ const char *act)
+{
+ char rwbs[6];
+ fill_rwbs(rwbs, t);
+ return trace_seq_printf(s, "%3d,%-3d %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), act, rwbs);
+}
+
+static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
+{
+ const char *cmd = trace_find_cmdline(ent->pid);
+
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%s]\n",
+ t_sector(ent), t_sec(ent), cmd);
+ return trace_seq_printf(s, "[%s]\n", cmd);
+}
+
+static int blk_log_with_error(struct trace_seq *s,
+ const struct trace_entry *ent)
+{
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent),
+ t_sec(ent), t_error(ent));
+ return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent));
+}
+
+static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
+{
+ struct blk_io_trace_remap r = { .device = 0, };
+
+ get_pdu_remap(ent, &r);
+ return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
+ t_sector(ent),
+ t_sec(ent), MAJOR(r.device), MINOR(r.device),
+ (unsigned long long)r.sector);
+}
+
+static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
+{
+ return trace_seq_printf(s, "[%s]\n", trace_find_cmdline(ent->pid));
+}
+
+static int blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
+{
+ return trace_seq_printf(s, "[%s] %llu\n", trace_find_cmdline(ent->pid),
+ get_pdu_int(ent));
+}
+
+static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
+{
+ return trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
+ get_pdu_int(ent), trace_find_cmdline(ent->pid));
+}
+
+/*
+ * struct tracer operations
+ */
+
+static void blk_tracer_print_header(struct seq_file *m)
+{
+ if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
+ return;
+ seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n"
+ "# | | | | | |\n");
+}
+
+static void blk_tracer_start(struct trace_array *tr)
+{
+ tracing_reset_online_cpus(tr);
+
+ mutex_lock(&blk_probe_mutex);
+ if (atomic_add_return(1, &blk_probes_ref) == 1)
+ if (blk_register_tracepoints())
+ atomic_dec(&blk_probes_ref);
+ mutex_unlock(&blk_probe_mutex);
+}
+
+static int blk_tracer_init(struct trace_array *tr)
+{
+ blk_tr = tr;
+ blk_tracer_start(tr);
+ mutex_lock(&blk_probe_mutex);
+ blk_tracer_enabled++;
+ mutex_unlock(&blk_probe_mutex);
+ return 0;
+}
+
+static void blk_tracer_stop(struct trace_array *tr)
+{
+ mutex_lock(&blk_probe_mutex);
+ if (atomic_dec_and_test(&blk_probes_ref))
+ blk_unregister_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
+}
+
+static void blk_tracer_reset(struct trace_array *tr)
+{
+ if (!atomic_read(&blk_probes_ref))
+ return;
+
+ mutex_lock(&blk_probe_mutex);
+ blk_tracer_enabled--;
+ WARN_ON(blk_tracer_enabled < 0);
+ mutex_unlock(&blk_probe_mutex);
+
+ blk_tracer_stop(tr);
+}
+
+static struct {
+ const char *act[2];
+ int (*print)(struct trace_seq *s, const struct trace_entry *ent);
+} what2act[] __read_mostly = {
+ [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic },
+ [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic },
+ [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic },
+ [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic },
+ [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic },
+ [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error },
+ [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic },
+ [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error },
+ [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug },
+ [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug },
+ [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug },
+ [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic },
+ [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split },
+ [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic },
+ [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap },
+};
+
+static int blk_trace_event_print(struct trace_seq *s, struct trace_entry *ent,
+ int flags)
+{
+ const struct blk_io_trace *t = (struct blk_io_trace *)ent;
+ const u16 what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+ int ret;
+
+ if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
+ ret = trace_seq_printf(s, "Bad pc action %x\n", what);
+ else {
+ const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
+ ret = blk_log_action_seq(s, t, what2act[what].act[long_act]);
+ if (ret)
+ ret = what2act[what].print(s, ent);
+ }
+
+ return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
+{
+ const struct blk_io_trace *t;
+ u16 what;
+ int ret;
+
+ if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
+ return TRACE_TYPE_UNHANDLED;
+
+ t = (const struct blk_io_trace *)iter->ent;
+ what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+
+ if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
+ ret = trace_seq_printf(&iter->seq, "Bad pc action %x\n", what);
+ else {
+ const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
+ ret = blk_log_action_iter(iter, what2act[what].act[long_act]);
+ if (ret)
+ ret = what2act[what].print(&iter->seq, iter->ent);
+ }
+
+ return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct tracer blk_tracer __read_mostly = {
+ .name = "blk",
+ .init = blk_tracer_init,
+ .reset = blk_tracer_reset,
+ .start = blk_tracer_start,
+ .stop = blk_tracer_stop,
+ .print_header = blk_tracer_print_header,
+ .print_line = blk_tracer_print_line,
+ .flags = &blk_tracer_flags,
+};
+
+static struct trace_event trace_blk_event = {
+ .type = TRACE_BLK,
+ .trace = blk_trace_event_print,
+ .latency_trace = blk_trace_event_print,
+ .raw = trace_nop_print,
+ .hex = trace_nop_print,
+ .binary = trace_nop_print,
+};
+
+static int __init init_blk_tracer(void)
+{
+ if (!register_ftrace_event(&trace_blk_event)) {
+ pr_warning("Warning: could not register block events\n");
+ return 1;
+ }
+
+ if (register_tracer(&blk_tracer) != 0) {
+ pr_warning("Warning: could not register the block tracer\n");
+ unregister_ftrace_event(&trace_blk_event);
+ return 1;
+ }
+
+ return 0;
+}
+
+device_initcall(init_blk_tracer);
+
+static int blk_trace_remove_queue(struct request_queue *q)
+{
+ struct blk_trace *bt;
+
+ bt = xchg(&q->blk_trace, NULL);
+ if (bt == NULL)
+ return -EINVAL;
+
+ kfree(bt);
+ return 0;
+}
+
+/*
+ * Setup everything required to start tracing
+ */
+static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
+{
+ struct blk_trace *old_bt, *bt = NULL;
+ int ret;
+
+ ret = -ENOMEM;
+ bt = kzalloc(sizeof(*bt), GFP_KERNEL);
+ if (!bt)
+ goto err;
+
+ bt->dev = dev;
+ bt->act_mask = (u16)-1;
+ bt->end_lba = -1ULL;
+ bt->trace_state = Blktrace_running;
+
+ old_bt = xchg(&q->blk_trace, bt);
+ if (old_bt != NULL) {
+ (void)xchg(&q->blk_trace, old_bt);
+ kfree(bt);
+ ret = -EBUSY;
+ }
+ return 0;
+err:
+ return ret;
+}
+
+/*
+ * sysfs interface to enable and configure tracing
+ */
+
+static ssize_t sysfs_blk_trace_enable_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct block_device *bdev;
+ ssize_t ret = -ENXIO;
+
+ lock_kernel();
+ bdev = bdget(part_devt(p));
+ if (bdev != NULL) {
+ struct request_queue *q = bdev_get_queue(bdev);
+
+ if (q != NULL) {
+ mutex_lock(&bdev->bd_mutex);
+ ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ mutex_unlock(&bdev->bd_mutex);
+ }
+
+ bdput(bdev);
+ }
+
+ unlock_kernel();
+ return ret;
+}
+
+static ssize_t sysfs_blk_trace_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct block_device *bdev;
+ struct request_queue *q;
+ struct hd_struct *p;
+ int value;
+ ssize_t ret = -ENXIO;
+
+ if (count == 0 || sscanf(buf, "%d", &value) != 1)
+ goto out;
+
+ lock_kernel();
+ p = dev_to_part(dev);
+ bdev = bdget(part_devt(p));
+ if (bdev == NULL)
+ goto out_unlock_kernel;
+
+ q = bdev_get_queue(bdev);
+ if (q == NULL)
+ goto out_bdput;
+
+ mutex_lock(&bdev->bd_mutex);
+ if (value)
+ ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ else
+ ret = blk_trace_remove_queue(q);
+ mutex_unlock(&bdev->bd_mutex);
+
+ if (ret == 0)
+ ret = count;
+out_bdput:
+ bdput(bdev);
+out_unlock_kernel:
+ unlock_kernel();
+out:
+ return ret;
+}
+
+static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count);
+#define BLK_TRACE_DEVICE_ATTR(_name) \
+ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \
+ sysfs_blk_trace_attr_show, \
+ sysfs_blk_trace_attr_store)
+
+static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR,
+ sysfs_blk_trace_enable_show, sysfs_blk_trace_enable_store);
+static BLK_TRACE_DEVICE_ATTR(act_mask);
+static BLK_TRACE_DEVICE_ATTR(pid);
+static BLK_TRACE_DEVICE_ATTR(start_lba);
+static BLK_TRACE_DEVICE_ATTR(end_lba);
+
+static struct attribute *blk_trace_attrs[] = {
+ &dev_attr_enable.attr,
+ &dev_attr_act_mask.attr,
+ &dev_attr_pid.attr,
+ &dev_attr_start_lba.attr,
+ &dev_attr_end_lba.attr,
+ NULL
+};
+
+struct attribute_group blk_trace_attr_group = {
+ .name = "trace",
+ .attrs = blk_trace_attrs,
+};
+
+static int blk_str2act_mask(const char *str)
+{
+ int mask = 0;
+ char *copy = kstrdup(str, GFP_KERNEL), *s;
+
+ if (copy == NULL)
+ return -ENOMEM;
+
+ s = strstrip(copy);
+
+ while (1) {
+ char *sep = strchr(s, ',');
+
+ if (sep != NULL)
+ *sep = '\0';
+
+ if (strcasecmp(s, "barrier") == 0)
+ mask |= BLK_TC_BARRIER;
+ else if (strcasecmp(s, "complete") == 0)
+ mask |= BLK_TC_COMPLETE;
+ else if (strcasecmp(s, "fs") == 0)
+ mask |= BLK_TC_FS;
+ else if (strcasecmp(s, "issue") == 0)
+ mask |= BLK_TC_ISSUE;
+ else if (strcasecmp(s, "pc") == 0)
+ mask |= BLK_TC_PC;
+ else if (strcasecmp(s, "queue") == 0)
+ mask |= BLK_TC_QUEUE;
+ else if (strcasecmp(s, "read") == 0)
+ mask |= BLK_TC_READ;
+ else if (strcasecmp(s, "requeue") == 0)
+ mask |= BLK_TC_REQUEUE;
+ else if (strcasecmp(s, "sync") == 0)
+ mask |= BLK_TC_SYNC;
+ else if (strcasecmp(s, "write") == 0)
+ mask |= BLK_TC_WRITE;
+
+ if (sep == NULL)
+ break;
+
+ s = sep + 1;
+ }
+ kfree(copy);
+
+ return mask;
+}
+
+static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q;
+ struct block_device *bdev;
+ ssize_t ret = -ENXIO;
+
+ lock_kernel();
+ bdev = bdget(part_devt(p));
+ if (bdev == NULL)
+ goto out_unlock_kernel;
+
+ q = bdev_get_queue(bdev);
+ if (q == NULL)
+ goto out_bdput;
+ mutex_lock(&bdev->bd_mutex);
+ if (q->blk_trace == NULL)
+ ret = sprintf(buf, "disabled\n");
+ else if (attr == &dev_attr_act_mask)
+ ret = sprintf(buf, "%#x\n", q->blk_trace->act_mask);
+ else if (attr == &dev_attr_pid)
+ ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+ else if (attr == &dev_attr_start_lba)
+ ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+ else if (attr == &dev_attr_end_lba)
+ ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+ mutex_unlock(&bdev->bd_mutex);
+out_bdput:
+ bdput(bdev);
+out_unlock_kernel:
+ unlock_kernel();
+ return ret;
+}
+
+static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct block_device *bdev;
+ struct request_queue *q;
+ struct hd_struct *p;
+ u64 value;
+ ssize_t ret = -ENXIO;
+
+ if (count == 0)
+ goto out;
+
+ if (attr == &dev_attr_act_mask) {
+ if (sscanf(buf, "%llx", &value) != 1) {
+ /* Assume it is a list of trace category names */
+ value = blk_str2act_mask(buf);
+ if (value < 0)
+ goto out;
+ }
+ } else if (sscanf(buf, "%llu", &value) != 1)
+ goto out;
+
+ lock_kernel();
+ p = dev_to_part(dev);
+ bdev = bdget(part_devt(p));
+ if (bdev == NULL)
+ goto out_unlock_kernel;
+
+ q = bdev_get_queue(bdev);
+ if (q == NULL)
+ goto out_bdput;
+
+ mutex_lock(&bdev->bd_mutex);
+ ret = 0;
+ if (q->blk_trace == NULL)
+ ret = blk_trace_setup_queue(q, bdev->bd_dev);
+
+ if (ret == 0) {
+ if (attr == &dev_attr_act_mask)
+ q->blk_trace->act_mask = value;
+ else if (attr == &dev_attr_pid)
+ q->blk_trace->pid = value;
+ else if (attr == &dev_attr_start_lba)
+ q->blk_trace->start_lba = value;
+ else if (attr == &dev_attr_end_lba)
+ q->blk_trace->end_lba = value;
+ ret = count;
+ }
+ mutex_unlock(&bdev->bd_mutex);
+out_bdput:
+ bdput(bdev);
+out_unlock_kernel:
+ unlock_kernel();
+out:
+ return ret;
+}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index e8525fa72823..664ebfd092ec 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -84,6 +84,11 @@ struct cfq_data {
*/
struct cfq_rb_root service_tree;
unsigned int busy_queues;
+ /*
+ * Used to track any pending rt requests so we can pre-empt current
+ * non-RT cfqq in service when this value is non-zero.
+ */
+ unsigned int busy_rt_queues;
int rq_in_driver;
int sync_flight;
@@ -562,6 +567,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
BUG_ON(cfq_cfqq_on_rr(cfqq));
cfq_mark_cfqq_on_rr(cfqq);
cfqd->busy_queues++;
+ if (cfq_class_rt(cfqq))
+ cfqd->busy_rt_queues++;
cfq_resort_rr_list(cfqd, cfqq);
}
@@ -581,6 +588,8 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
+ if (cfq_class_rt(cfqq))
+ cfqd->busy_rt_queues--;
}
/*
@@ -1005,6 +1014,20 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
goto expire;
/*
+ * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+ * cfqq.
+ */
+ if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+ /*
+ * We simulate this as cfqq timed out so that it gets to bank
+ * the remaining of its time slice.
+ */
+ cfq_log_cfqq(cfqd, cfqq, "preempt");
+ cfq_slice_expired(cfqd, 1);
+ goto new_queue;
+ }
+
+ /*
* The active queue has requests and isn't expired, allow it to
* dispatch.
*/
@@ -1067,6 +1090,13 @@ __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
if (RB_EMPTY_ROOT(&cfqq->sort_list))
break;
+ /*
+ * If there is a non-empty RT cfqq waiting for current
+ * cfqq's timeslice to complete, pre-empt this cfqq
+ */
+ if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
+ break;
+
} while (dispatched < max_dispatch);
/*
@@ -1801,6 +1831,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
if (rq_is_meta(rq) && !cfqq->meta_pending)
return 1;
+ /*
+ * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+ */
+ if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+ return 1;
+
if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
return 0;
@@ -1870,7 +1906,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
/*
* 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
+ * has some old slice time left and is of higher priority or
+ * this new queue is RT and the current one is BE
*/
cfq_preempt_queue(cfqd, cfqq);
cfq_mark_cfqq_must_dispatch(cfqq);