#include <linux/blkdev.h>
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
#include <linux/gcd.h>
+ #include <linux/lcm.h>
#include <linux/jiffies.h>
+#include <linux/gfp.h>
#include "blk.h"
}
EXPORT_SYMBOL(blk_queue_stack_limits);
- static unsigned int lcm(unsigned int a, unsigned int b)
- {
- if (a && b)
- return (a * b) / gcd(a, b);
- else if (b)
- return b;
-
- return a;
- }
-
/**
* blk_stack_limits - adjust queue_limits for stacked devices
* @t: the stacking driver limits (top device)
* Functions related to sysfs handling
*/
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
return queue_var_show(max_sectors_kb, (page));
}
+ static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+ {
+ return queue_var_show(queue_max_segments(q), (page));
+ }
+
+ static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+ {
+ if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+ return queue_var_show(queue_max_segment_size(q), (page));
+
+ return queue_var_show(PAGE_CACHE_SIZE, (page));
+ }
+
static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
{
return queue_var_show(queue_logical_block_size(q), page);
.show = queue_max_hw_sectors_show,
};
+ static struct queue_sysfs_entry queue_max_segments_entry = {
+ .attr = {.name = "max_segments", .mode = S_IRUGO },
+ .show = queue_max_segments_show,
+ };
+
+ static struct queue_sysfs_entry queue_max_segment_size_entry = {
+ .attr = {.name = "max_segment_size", .mode = S_IRUGO },
+ .show = queue_max_segment_size_show,
+ };
+
static struct queue_sysfs_entry queue_iosched_entry = {
.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
.show = elv_iosched_show,
&queue_ra_entry.attr,
&queue_max_hw_sectors_entry.attr,
&queue_max_sectors_entry.attr,
+ &queue_max_segments_entry.attr,
+ &queue_max_segment_size_entry.attr,
&queue_iosched_entry.attr,
&queue_hw_sector_size_entry.attr,
&queue_logical_block_size_entry.attr,
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*/
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/jiffies.h>
#define CFQ_SERVICE_SHIFT 12
#define CFQQ_SEEK_THR (sector_t)(8 * 100)
+ #define CFQQ_CLOSE_THR (sector_t)(8 * 1024)
#define CFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
#define CFQQ_SEEKY(cfqq) (hweight32(cfqq->seek_history) > 32/8)
unsigned int major, minor;
cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+ if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ cfqg->blkg.dev = MKDEV(major, minor);
+ goto done;
+ }
if (cfqg || !create)
goto done;
struct cfq_queue *cfqq)
{
if (cfqq) {
- cfq_log_cfqq(cfqd, cfqq, "set_active");
+ cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+ cfqd->serving_prio, cfqd->serving_type);
cfqq->slice_start = 0;
cfqq->dispatch_start = jiffies;
cfqq->allocated_slice = 0;
}
static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
- struct request *rq, bool for_preempt)
+ struct request *rq)
{
- return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
+ return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
}
static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
* will contain the closest sector.
*/
__cfqq = rb_entry(parent, struct cfq_queue, p_node);
- if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
if (blk_rq_pos(__cfqq->next_rq) < sector)
return NULL;
__cfqq = rb_entry(node, struct cfq_queue, p_node);
- if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+ if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
return NULL;
{
struct cfq_queue *cfqq;
+ if (cfq_class_idle(cur_cfqq))
+ return NULL;
if (!cfq_cfqq_sync(cur_cfqq))
return NULL;
if (CFQQ_SEEKY(cur_cfqq))
* Otherwise, we do only if they are the last ones
* in their service tree.
*/
- return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
+ if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+ return 1;
+ cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+ service_tree->count);
+ return 0;
}
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
* time slice.
*/
if (sample_valid(cic->ttime_samples) &&
- (cfqq->slice_end - jiffies < cic->ttime_mean))
+ (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+ cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+ cic->ttime_mean);
return;
+ }
cfq_mark_cfqq_wait_request(cfqq);
slice = max(slice, 2 * cfqd->cfq_slice_idle);
slice = max_t(unsigned, slice, CFQ_MIN_TT);
+ cfq_log(cfqd, "workload slice:%d", slice);
cfqd->workload_expires = jiffies + slice;
cfqd->noidle_tree_requires_idle = false;
}
struct cfq_queue *cfqq;
int dispatched = 0;
- while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+ /* Expire the timeslice of the current active queue first */
+ cfq_slice_expired(cfqd, 0);
+ while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+ __cfq_set_active_queue(cfqd, cfqq);
dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+ }
- cfq_slice_expired(cfqd, 0);
BUG_ON(cfqd->busy_queues);
cfq_log(cfqd, "forced_dispatch=%d", dispatched);
* if this request is as-good as one we would expect from the
* current cfqq, let it preempt
*/
- if (cfq_rq_close(cfqd, cfqq, rq, true))
+ if (cfq_rq_close(cfqd, cfqq, rq))
return true;
return false;
if (cfq_should_wait_busy(cfqd, cfqq)) {
cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
cfq_mark_cfqq_wait_busy(cfqq);
+ cfq_log_cfqq(cfqd, cfqq, "will busy wait");
}
/*
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/drbd.h>
+#include <linux/slab.h>
#include <asm/kmap_types.h>
#include "drbd_int.h"
size_t bm_words;
size_t bm_number_of_pages;
sector_t bm_dev_capacity;
- struct semaphore bm_change; /* serializes resize operations */
+ struct mutex bm_change; /* serializes resize operations */
atomic_t bm_async_io;
wait_queue_head_t bm_io_wait;
return;
}
- trylock_failed = down_trylock(&b->bm_change);
+ trylock_failed = !mutex_trylock(&b->bm_change);
if (trylock_failed) {
dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n",
b->bm_task == mdev->receiver.task ? "receiver" :
b->bm_task == mdev->asender.task ? "asender" :
b->bm_task == mdev->worker.task ? "worker" : "?");
- down(&b->bm_change);
+ mutex_lock(&b->bm_change);
}
if (__test_and_set_bit(BM_LOCKED, &b->bm_flags))
dev_err(DEV, "FIXME bitmap already locked in bm_lock\n");
b->bm_why = NULL;
b->bm_task = NULL;
- up(&b->bm_change);
+ mutex_unlock(&b->bm_change);
}
/* word offset to long pointer */
if (!b)
return -ENOMEM;
spin_lock_init(&b->bm_lock);
- init_MUTEX(&b->bm_change);
+ mutex_init(&b->bm_change);
init_waitqueue_head(&b->bm_io_wait);
mdev->bitmap = b;
#include <linux/buffer_head.h> /* for invalidate_bdev() */
#include <linux/completion.h>
#include <linux/highmem.h>
-#include <linux/gfp.h>
#include <linux/kthread.h>
#include <linux/splice.h>
if (ret)
goto fail;
+ file_update_time(file);
+
transfer_result = lo_do_transfer(lo, WRITE, page, offset,
bvec->bv_page, bv_offs, size, IV);
copied = size;
//#define DEBUG
#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/virtio.h>
set_capacity(vblk->disk, cap);
/* We can handle whatever the host told us to handle. */
- blk_queue_max_phys_segments(q, vblk->sg_elems-2);
- blk_queue_max_hw_segments(q, vblk->sg_elems-2);
+ blk_queue_max_segments(q, vblk->sg_elems-2);
/* No need to bounce any requests */
blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
/* No real sector limit. */
- blk_queue_max_sectors(q, -1U);
+ blk_queue_max_hw_sectors(q, -1U);
/* Host can optionally specify maximum segment size and number of
* segments. */
#include <linux/mutex.h>
#include <linux/string_helpers.h>
#include <linux/async.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
{
struct request_queue *q = sdkp->disk->queue;
unsigned int sector_sz = sdkp->device->sector_size;
- const int vpd_len = 32;
+ const int vpd_len = 64;
unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
if (!buffer ||
{
unsigned char *buffer;
u16 rot;
- const int vpd_len = 32;
+ const int vpd_len = 64;
buffer = kmalloc(vpd_len, GFP_KERNEL);
blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
gd->driverfs_dev = &sdp->sdev_gendev;
- gd->flags = GENHD_FL_EXT_DEVT | GENHD_FL_DRIVERFS;
+ gd->flags = GENHD_FL_EXT_DEVT;
if (sdp->removable)
gd->flags |= GENHD_FL_REMOVABLE;
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
return ret;
}
- static void unpin_sb_for_writeback(struct super_block **psb)
+ static void unpin_sb_for_writeback(struct super_block *sb)
{
- struct super_block *sb = *psb;
-
- if (sb) {
- up_read(&sb->s_umount);
- put_super(sb);
- *psb = NULL;
- }
+ up_read(&sb->s_umount);
+ put_super(sb);
}
+ enum sb_pin_state {
+ SB_PINNED,
+ SB_NOT_PINNED,
+ SB_PIN_FAILED
+ };
+
/*
* For WB_SYNC_NONE writeback, the caller does not have the sb pinned
* before calling writeback. So make sure that we do pin it, so it doesn't
* go away while we are writing inodes from it.
- *
- * Returns 0 if the super was successfully pinned (or pinning wasn't needed),
- * 1 if we failed.
*/
- static int pin_sb_for_writeback(struct writeback_control *wbc,
- struct inode *inode, struct super_block **psb)
+ static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
+ struct super_block *sb)
{
- struct super_block *sb = inode->i_sb;
-
- /*
- * If this sb is already pinned, nothing more to do. If not and
- * *psb is non-NULL, unpin the old one first
- */
- if (sb == *psb)
- return 0;
- else if (*psb)
- unpin_sb_for_writeback(psb);
-
/*
* Caller must already hold the ref for this
*/
if (wbc->sync_mode == WB_SYNC_ALL) {
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- return 0;
+ return SB_NOT_PINNED;
}
-
spin_lock(&sb_lock);
sb->s_count++;
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root) {
spin_unlock(&sb_lock);
- goto pinned;
+ return SB_PINNED;
}
/*
* umounted, drop rwsem again and fall through to failure
*/
up_read(&sb->s_umount);
}
-
sb->s_count--;
spin_unlock(&sb_lock);
- return 1;
- pinned:
- *psb = sb;
- return 0;
+ return SB_PIN_FAILED;
}
- static void writeback_inodes_wb(struct bdi_writeback *wb,
- struct writeback_control *wbc)
+ /*
+ * Write a portion of b_io inodes which belong to @sb.
+ * If @wbc->sb != NULL, then find and write all such
+ * inodes. Otherwise write only ones which go sequentially
+ * in reverse order.
+ * Return 1, if the caller writeback routine should be
+ * interrupted. Otherwise return 0.
+ */
+ static int writeback_sb_inodes(struct super_block *sb,
+ struct bdi_writeback *wb,
+ struct writeback_control *wbc)
{
- struct super_block *sb = wbc->sb, *pin_sb = NULL;
- const unsigned long start = jiffies; /* livelock avoidance */
-
- spin_lock(&inode_lock);
-
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
- queue_io(wb, wbc->older_than_this);
-
while (!list_empty(&wb->b_io)) {
- struct inode *inode = list_entry(wb->b_io.prev,
- struct inode, i_list);
long pages_skipped;
-
- /*
- * super block given and doesn't match, skip this inode
- */
- if (sb && sb != inode->i_sb) {
+ struct inode *inode = list_entry(wb->b_io.prev,
+ struct inode, i_list);
+ if (wbc->sb && sb != inode->i_sb) {
+ /* super block given and doesn't
+ match, skip this inode */
redirty_tail(inode);
continue;
}
-
+ if (sb != inode->i_sb)
+ /* finish with this superblock */
+ return 0;
if (inode->i_state & (I_NEW | I_WILL_FREE)) {
requeue_io(inode);
continue;
}
-
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
*/
- if (inode_dirtied_after(inode, start))
- break;
-
- if (pin_sb_for_writeback(wbc, inode, &pin_sb)) {
- requeue_io(inode);
- continue;
- }
+ if (inode_dirtied_after(inode, wbc->wb_start))
+ return 1;
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
spin_lock(&inode_lock);
if (wbc->nr_to_write <= 0) {
wbc->more_io = 1;
- break;
+ return 1;
}
if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
+ /* b_io is empty */
+ return 1;
+ }
+
+ static void writeback_inodes_wb(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
+ {
+ int ret = 0;
+
+ wbc->wb_start = jiffies; /* livelock avoidance */
+ spin_lock(&inode_lock);
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
- unpin_sb_for_writeback(&pin_sb);
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
+ struct inode, i_list);
+ struct super_block *sb = inode->i_sb;
+ enum sb_pin_state state;
+ if (wbc->sb && sb != wbc->sb) {
+ /* super block given and doesn't
+ match, skip this inode */
+ redirty_tail(inode);
+ continue;
+ }
+ state = pin_sb_for_writeback(wbc, sb);
+
+ if (state == SB_PIN_FAILED) {
+ requeue_io(inode);
+ continue;
+ }
+ ret = writeback_sb_inodes(sb, wb, wbc);
+
+ if (state == SB_PINNED)
+ unpin_sb_for_writeback(sb);
+ if (ret)
+ break;
+ }
spin_unlock(&inode_lock);
/* Leave any unwritten inodes on b_io */
}