</address>
</affiliation>
</author>
+ <author>
+ <firstname>William</firstname>
+ <surname>Cohen</surname>
+ <affiliation>
+ <address>
+ <email>wcohen@redhat.com</email>
+ </address>
+ </affiliation>
+ </author>
</authorgroup>
<legalnotice>
!Iinclude/trace/events/signal.h
</chapter>
+ <chapter id="block">
+ <title>Block IO</title>
+!Iinclude/trace/events/block.h
+ </chapter>
</book>
As mentioned, there is no virtual mapping of a bio. For DMA, this is
not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
PIO drivers (or drivers that need to revert to PIO transfer once in a
while (IDE for example)), where the CPU is doing the actual data
transfer a virtual mapping is needed. If the driver supports highmem I/O,
Protection. If in doubt, say N.
config BLK_CGROUP
- tristate
+ tristate "Block cgroup support"
depends on CGROUPS
+ depends on CFQ_GROUP_IOSCHED
default n
---help---
Generic block IO controller cgroup interface. This is the common
#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>
}
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)
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,
#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");
}
/*
spin_unlock(&elv_list_lock);
- sprintf(elv, "%s-iosched", name);
+ snprintf(elv, sizeof(elv), "%s-iosched", name);
request_module("%s", elv);
spin_lock(&elv_list_lock);
Controller->RequestQueue[n] = RequestQueue;
blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
RequestQueue->queuedata = Controller;
- blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit);
blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
disk->queue = RequestQueue;
put_ldev(mdev);
}
+/* sector to word */
#define S2W(s) ((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))
+
/* activity log to on disk bitmap -- prepare bio unless that sector
* is already covered by previously prepared bios */
static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
{
struct bio *bio;
struct page *page;
- sector_t on_disk_sector = enr + mdev->ldev->md.md_offset
- + mdev->ldev->md.bm_offset;
+ sector_t on_disk_sector;
unsigned int page_offset = PAGE_SIZE;
int offset;
int i = 0;
int err = -ENOMEM;
+ /* We always write aligned, full 4k blocks,
+ * so we can ignore the logical_block_size (for now) */
+ enr &= ~7U;
+ on_disk_sector = enr + mdev->ldev->md.md_offset
+ + mdev->ldev->md.bm_offset;
+
+ D_ASSERT(!(on_disk_sector & 7U));
+
/* Check if that enr is already covered by an already created bio.
* Caution, bios[] is not NULL terminated,
* but only initialized to all NULL.
offset = S2W(enr);
drbd_bm_get_lel(mdev, offset,
- min_t(size_t, S2W(1), drbd_bm_words(mdev) - offset),
+ min_t(size_t, S2W(8), drbd_bm_words(mdev) - offset),
kmap(page) + page_offset);
kunmap(page);
bio->bi_bdev = mdev->ldev->md_bdev;
bio->bi_sector = on_disk_sector;
- if (bio_add_page(bio, page, MD_SECTOR_SIZE, page_offset) != MD_SECTOR_SIZE)
+ if (bio_add_page(bio, page, 4096, page_offset) != 4096)
goto out_put_page;
atomic_inc(&wc->count);
/* ok, ->resync is there. */
for (i = 0; i < mdev->resync->nr_elements; i++) {
e = lc_element_by_index(mdev->resync, i);
- bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
+ bm_ext = lc_entry(e, struct bm_extent, lce);
if (bm_ext->lce.lc_number == LC_FREE)
continue;
if (bm_ext->lce.lc_number == mdev->resync_wenr) {
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;
[P_OV_REQUEST] = "OVRequest",
[P_OV_REPLY] = "OVReply",
[P_OV_RESULT] = "OVResult",
+ [P_CSUM_RS_REQUEST] = "CsumRSRequest",
+ [P_RS_IS_IN_SYNC] = "CsumRSIsInSync",
+ [P_COMPRESSED_BITMAP] = "CBitmap",
[P_MAX_CMD] = NULL,
};
char csums_alg[SHARED_SECRET_MAX];
} __packed;
+enum drbd_conn_flags {
+ CF_WANT_LOSE = 1,
+ CF_DRY_RUN = 2,
+};
+
struct p_protocol {
struct p_header head;
u32 protocol;
u32 after_sb_0p;
u32 after_sb_1p;
u32 after_sb_2p;
- u32 want_lose;
+ u32 conn_flags;
u32 two_primaries;
/* Since protocol version 87 and higher. */
* while this is set. */
RESIZE_PENDING, /* Size change detected locally, waiting for the response from
* the peer, if it changed there as well. */
+ CONN_DRY_RUN, /* Expect disconnect after resync handshake. */
+ GOT_PING_ACK, /* set when we receive a ping_ack packet, misc wait gets woken */
};
struct drbd_bitmap; /* opaque for drbd_conf */
int drbd_send_protocol(struct drbd_conf *mdev)
{
struct p_protocol *p;
- int size, rv;
+ int size, cf, rv;
size = sizeof(struct p_protocol);
p->after_sb_0p = cpu_to_be32(mdev->net_conf->after_sb_0p);
p->after_sb_1p = cpu_to_be32(mdev->net_conf->after_sb_1p);
p->after_sb_2p = cpu_to_be32(mdev->net_conf->after_sb_2p);
- p->want_lose = cpu_to_be32(mdev->net_conf->want_lose);
p->two_primaries = cpu_to_be32(mdev->net_conf->two_primaries);
+ cf = 0;
+ if (mdev->net_conf->want_lose)
+ cf |= CF_WANT_LOSE;
+ if (mdev->net_conf->dry_run) {
+ if (mdev->agreed_pro_version >= 92)
+ cf |= CF_DRY_RUN;
+ else {
+ dev_err(DEV, "--dry-run is not supported by peer");
+ return 0;
+ }
+ }
+ p->conn_flags = cpu_to_be32(cf);
+
if (mdev->agreed_pro_version >= 87)
strcpy(p->integrity_alg, mdev->net_conf->integrity_alg);
void drbd_free_sock(struct drbd_conf *mdev)
{
if (mdev->data.socket) {
+ mutex_lock(&mdev->data.mutex);
kernel_sock_shutdown(mdev->data.socket, SHUT_RDWR);
sock_release(mdev->data.socket);
mdev->data.socket = NULL;
+ mutex_unlock(&mdev->data.mutex);
}
if (mdev->meta.socket) {
+ mutex_lock(&mdev->meta.mutex);
kernel_sock_shutdown(mdev->meta.socket, SHUT_RDWR);
sock_release(mdev->meta.socket);
mdev->meta.socket = NULL;
+ mutex_unlock(&mdev->meta.mutex);
}
}
}
if (r == SS_NO_UP_TO_DATE_DISK && force &&
- (mdev->state.disk == D_INCONSISTENT ||
- mdev->state.disk == D_OUTDATED)) {
+ (mdev->state.disk < D_UP_TO_DATE &&
+ mdev->state.disk >= D_INCONSISTENT)) {
mask.disk = D_MASK;
val.disk = D_UP_TO_DATE;
forced = 1;
}
reply->ret_code =
- drbd_set_role(mdev, R_PRIMARY, primary_args.overwrite_peer);
+ drbd_set_role(mdev, R_PRIMARY, primary_args.primary_force);
return 0;
}
drbd_md_set_sector_offsets(mdev, nbc);
+ /* allocate a second IO page if logical_block_size != 512 */
+ logical_block_size = bdev_logical_block_size(nbc->md_bdev);
+ if (logical_block_size == 0)
+ logical_block_size = MD_SECTOR_SIZE;
+
+ if (logical_block_size != MD_SECTOR_SIZE) {
+ if (!mdev->md_io_tmpp) {
+ struct page *page = alloc_page(GFP_NOIO);
+ if (!page)
+ goto force_diskless_dec;
+
+ dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
+ logical_block_size, MD_SECTOR_SIZE);
+ dev_warn(DEV, "Workaround engaged (has performance impact).\n");
+
+ mdev->md_io_tmpp = page;
+ }
+ }
+
if (!mdev->bitmap) {
if (drbd_bm_init(mdev)) {
retcode = ERR_NOMEM;
goto force_diskless_dec;
}
- /* allocate a second IO page if logical_block_size != 512 */
- logical_block_size = bdev_logical_block_size(nbc->md_bdev);
- if (logical_block_size == 0)
- logical_block_size = MD_SECTOR_SIZE;
-
- if (logical_block_size != MD_SECTOR_SIZE) {
- if (!mdev->md_io_tmpp) {
- struct page *page = alloc_page(GFP_NOIO);
- if (!page)
- goto force_diskless_dec;
-
- dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
- logical_block_size, MD_SECTOR_SIZE);
- dev_warn(DEV, "Workaround engaged (has performance impact).\n");
-
- mdev->md_io_tmpp = page;
- }
- }
-
/* Reset the "barriers don't work" bits here, then force meta data to
* be written, to ensure we determine if barriers are supported. */
if (nbc->dc.no_md_flush)
}
if (hg == -100) {
+ /* FIXME this log message is not correct if we end up here
+ * after an attempted attach on a diskless node.
+ * We just refuse to attach -- well, we drop the "connection"
+ * to that disk, in a way... */
dev_alert(DEV, "Split-Brain detected, dropping connection!\n");
drbd_khelper(mdev, "split-brain");
return C_MASK;
}
}
+ if (mdev->net_conf->dry_run || test_bit(CONN_DRY_RUN, &mdev->flags)) {
+ if (hg == 0)
+ dev_info(DEV, "dry-run connect: No resync, would become Connected immediately.\n");
+ else
+ dev_info(DEV, "dry-run connect: Would become %s, doing a %s resync.",
+ drbd_conn_str(hg > 0 ? C_SYNC_SOURCE : C_SYNC_TARGET),
+ abs(hg) >= 2 ? "full" : "bit-map based");
+ return C_MASK;
+ }
+
if (abs(hg) >= 2) {
dev_info(DEV, "Writing the whole bitmap, full sync required after drbd_sync_handshake.\n");
if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from sync_handshake"))
struct p_protocol *p = (struct p_protocol *)h;
int header_size, data_size;
int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p;
- int p_want_lose, p_two_primaries;
+ int p_want_lose, p_two_primaries, cf;
char p_integrity_alg[SHARED_SECRET_MAX] = "";
header_size = sizeof(*p) - sizeof(*h);
p_after_sb_0p = be32_to_cpu(p->after_sb_0p);
p_after_sb_1p = be32_to_cpu(p->after_sb_1p);
p_after_sb_2p = be32_to_cpu(p->after_sb_2p);
- p_want_lose = be32_to_cpu(p->want_lose);
p_two_primaries = be32_to_cpu(p->two_primaries);
+ cf = be32_to_cpu(p->conn_flags);
+ p_want_lose = cf & CF_WANT_LOSE;
+
+ clear_bit(CONN_DRY_RUN, &mdev->flags);
+
+ if (cf & CF_DRY_RUN)
+ set_bit(CONN_DRY_RUN, &mdev->flags);
if (p_proto != mdev->net_conf->wire_protocol) {
dev_err(DEV, "incompatible communication protocols\n");
put_ldev(mdev);
if (nconn == C_MASK) {
+ nconn = C_CONNECTED;
if (mdev->state.disk == D_NEGOTIATING) {
drbd_force_state(mdev, NS(disk, D_DISKLESS));
- nconn = C_CONNECTED;
} else if (peer_state.disk == D_NEGOTIATING) {
dev_err(DEV, "Disk attach process on the peer node was aborted.\n");
peer_state.disk = D_DISKLESS;
+ real_peer_disk = D_DISKLESS;
} else {
+ if (test_and_clear_bit(CONN_DRY_RUN, &mdev->flags))
+ return FALSE;
D_ASSERT(oconn == C_WF_REPORT_PARAMS);
drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
return FALSE;
/* asender does not clean up anything. it must not interfere, either */
drbd_thread_stop(&mdev->asender);
-
- mutex_lock(&mdev->data.mutex);
drbd_free_sock(mdev);
- mutex_unlock(&mdev->data.mutex);
spin_lock_irq(&mdev->req_lock);
_drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
{
/* restore idle timeout */
mdev->meta.socket->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ;
+ if (!test_and_set_bit(GOT_PING_ACK, &mdev->flags))
+ wake_up(&mdev->misc_wait);
return TRUE;
}
if (eq) {
drbd_set_in_sync(mdev, e->sector, e->size);
- mdev->rs_same_csum++;
+ /* rs_same_csums unit is BM_BLOCK_SIZE */
+ mdev->rs_same_csum += e->size >> BM_BLOCK_SHIFT;
ok = drbd_send_ack(mdev, P_RS_IS_IN_SYNC, e);
} else {
inc_rs_pending(mdev);
return retcode;
}
+static void ping_peer(struct drbd_conf *mdev)
+{
+ clear_bit(GOT_PING_ACK, &mdev->flags);
+ request_ping(mdev);
+ wait_event(mdev->misc_wait,
+ test_bit(GOT_PING_ACK, &mdev->flags) || mdev->state.conn < C_CONNECTED);
+}
+
/**
* drbd_start_resync() - Start the resync process
* @mdev: DRBD device.
_drbd_pause_after(mdev);
}
write_unlock_irq(&global_state_lock);
- drbd_state_unlock(mdev);
put_ldev(mdev);
if (r == SS_SUCCESS) {
if (mdev->rs_total == 0) {
/* Peer still reachable? Beware of failing before-resync-target handlers! */
- request_ping(mdev);
- __set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(mdev->net_conf->ping_timeo*HZ/9); /* 9 instead 10 */
+ ping_peer(mdev);
drbd_resync_finished(mdev);
- return;
}
/* ns.conn may already be != mdev->state.conn,
drbd_md_sync(mdev);
}
+ drbd_state_unlock(mdev);
}
int drbd_worker(struct drbd_thread *thi)
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;
&& (j++ < PCD_SPIN))
udelay(PCD_DELAY);
- if ((r & (IDE_ERR & stop)) || (j >= PCD_SPIN)) {
+ if ((r & (IDE_ERR & stop)) || (j > PCD_SPIN)) {
s = read_reg(cd, 7);
e = read_reg(cd, 1);
p = read_reg(cd, 2);
- if (j >= PCD_SPIN)
+ if (j > PCD_SPIN)
e |= 0x100;
if (fun)
printk("%s: %s %s: alt=0x%x stat=0x%x err=0x%x"
&& (j++ < PF_SPIN))
udelay(PF_SPIN_DEL);
- if ((r & (STAT_ERR & stop)) || (j >= PF_SPIN)) {
+ if ((r & (STAT_ERR & stop)) || (j > PF_SPIN)) {
s = read_reg(pf, 7);
e = read_reg(pf, 1);
p = read_reg(pf, 2);
- if (j >= PF_SPIN)
+ if (j > PF_SPIN)
e |= 0x100;
if (fun)
printk("%s: %s %s: alt=0x%x stat=0x%x err=0x%x"
&& (j++ < PT_SPIN))
udelay(PT_SPIN_DEL);
- if ((r & (STAT_ERR & stop)) || (j >= PT_SPIN)) {
+ if ((r & (STAT_ERR & stop)) || (j > PT_SPIN)) {
s = read_reg(pi, 7);
e = read_reg(pi, 1);
p = read_reg(pi, 2);
- if (j >= PT_SPIN)
+ if (j > PT_SPIN)
e |= 0x100;
if (fun)
printk("%s: %s %s: alt=0x%x stat=0x%x err=0x%x"
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. */
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;
.bi_rw = bio->bi_rw,
};
- if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+ if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
prev->bv_len -= len;
return 0;
}
* merge_bvec_fn() returns number of bytes it can accept
* at this offset
*/
- if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
+ if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
bvec->bv_page = NULL;
bvec->bv_len = 0;
bvec->bv_offset = 0;
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;
- unpin_sb_for_writeback(&pin_sb);
+ 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);
+
+ 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 */
}
struct request {
struct list_head queuelist;
struct call_single_data csd;
- int cpu;
struct request_queue *q;
enum rq_cmd_type_bits cmd_type;
unsigned long atomic_flags;
+ int cpu;
+
/* the following two fields are internal, NEVER access directly */
- sector_t __sector; /* sector cursor */
unsigned int __data_len; /* total data len */
+ sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
unsigned short ioprio;
+ int ref_count;
+
void *special; /* opaque pointer available for LLD use */
char *buffer; /* kaddr of the current segment if available */
int tag;
int errors;
- int ref_count;
-
/*
* when request is used as a packet command carrier
*/
- unsigned short cmd_len;
unsigned char __cmd[BLK_MAX_CDB];
unsigned char *cmd;
+ unsigned short cmd_len;
unsigned int extra_len; /* length of alignment and padding */
unsigned int sense_len;
extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
extern void blk_queue_bounce_limit(struct request_queue *, u64);
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
-
-/* Temporary compatibility wrapper */
-static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max)
-{
- blk_queue_max_hw_sectors(q, max);
-}
-
extern void blk_queue_max_segments(struct request_queue *, unsigned short);
-
-static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max)
-{
- blk_queue_max_segments(q, max);
-}
-
-static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max)
-{
- blk_queue_max_segments(q, max);
-}
-
-
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
extern void blk_queue_max_discard_sectors(struct request_queue *q,
unsigned int max_discard_sectors);
extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
-#define MAX_PHYS_SEGMENTS 128
-#define MAX_HW_SEGMENTS 128
-#define SAFE_MAX_SECTORS 255
-#define MAX_SEGMENT_SIZE 65536
-
enum blk_default_limits {
BLK_MAX_SEGMENTS = 128,
BLK_SAFE_MAX_SECTORS = 255,
#define REL_VERSION "8.3.7"
#define API_VERSION 88
#define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 91
+#define PRO_VERSION_MAX 92
enum drbd_io_error_p {
#endif
NL_PACKET(primary, 1,
- NL_BIT( 1, T_MAY_IGNORE, overwrite_peer)
+ NL_BIT( 1, T_MAY_IGNORE, primary_force)
)
NL_PACKET(secondary, 2, )
NL_BIT( 41, T_MAY_IGNORE, always_asbp)
NL_BIT( 61, T_MAY_IGNORE, no_cork)
NL_BIT( 62, T_MANDATORY, auto_sndbuf_size)
+ NL_BIT( 70, T_MANDATORY, dry_run)
)
NL_PACKET(disconnect, 6, )
};
#define GENHD_FL_REMOVABLE 1
-#define GENHD_FL_DRIVERFS 2
+/* 2 is unused */
#define GENHD_FL_MEDIA_CHANGE_NOTIFY 4
#define GENHD_FL_CD 8
#define GENHD_FL_UP 16
#define to_i2o_driver(drv) container_of(drv,struct i2o_driver, driver)
#define to_i2o_device(dev) container_of(dev, struct i2o_device, device)
#define to_i2o_controller(dev) container_of(dev, struct i2o_controller, device)
-#define kobj_to_i2o_device(kobj) to_i2o_device(container_of(kobj, struct device, kobj))
/**
* i2o_out_to_virt - Turn an I2O message to a virtual address
--- /dev/null
+#ifndef _LCM_H
+#define _LCM_H
+
+#include <linux/compiler.h>
+
+unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__;
+
+#endif /* _LCM_H */
enum writeback_sync_modes sync_mode;
unsigned long *older_than_this; /* If !NULL, only write back inodes
older than this */
+ unsigned long wb_start; /* Time writeback_inodes_wb was
+ called. This is needed to avoid
+ extra jobs and livelock */
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
__entry->nr_sector, __entry->errors)
);
+/**
+ * block_rq_abort - abort block operation request
+ * @q: queue containing the block operation request
+ * @rq: block IO operation request
+ *
+ * Called immediately after pending block IO operation request @rq in
+ * queue @q is aborted. The fields in the operation request @rq
+ * can be examined to determine which device and sectors the pending
+ * operation would access.
+ */
DEFINE_EVENT(block_rq_with_error, block_rq_abort,
TP_PROTO(struct request_queue *q, struct request *rq),
TP_ARGS(q, rq)
);
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @q: queue holding operation
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q. For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
TP_PROTO(struct request_queue *q, struct request *rq),
TP_ARGS(q, rq)
);
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @q: queue containing the block operation request
+ * @rq: block operations request
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver. If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
DEFINE_EVENT(block_rq_with_error, block_rq_complete,
TP_PROTO(struct request_queue *q, struct request *rq),
__entry->nr_sector, __entry->comm)
);
+/**
+ * block_rq_insert - insert block operation request into queue
+ * @q: target queue
+ * @rq: block IO operation request
+ *
+ * Called immediately before block operation request @rq is inserted
+ * into queue @q. The fields in the operation request @rq struct can
+ * be examined to determine which device and sectors the pending
+ * operation would access.
+ */
DEFINE_EVENT(block_rq, block_rq_insert,
TP_PROTO(struct request_queue *q, struct request *rq),
TP_ARGS(q, rq)
);
+/**
+ * block_rq_issue - issue pending block IO request operation to device driver
+ * @q: queue holding operation
+ * @rq: block IO operation operation request
+ *
+ * Called when block operation request @rq from queue @q is sent to a
+ * device driver for processing.
+ */
DEFINE_EVENT(block_rq, block_rq_issue,
TP_PROTO(struct request_queue *q, struct request *rq),
TP_ARGS(q, rq)
);
+/**
+ * block_bio_bounce - used bounce buffer when processing block operation
+ * @q: queue holding the block operation
+ * @bio: block operation
+ *
+ * A bounce buffer was used to handle the block operation @bio in @q.
+ * This occurs when hardware limitations prevent a direct transfer of
+ * data between the @bio data memory area and the IO device. Use of a
+ * bounce buffer requires extra copying of data and decreases
+ * performance.
+ */
TRACE_EVENT(block_bio_bounce,
TP_PROTO(struct request_queue *q, struct bio *bio),
__entry->nr_sector, __entry->comm)
);
+/**
+ * block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
+ * @bio: block operation completed
+ *
+ * This tracepoint indicates there is no further work to do on this
+ * block IO operation @bio.
+ */
TRACE_EVENT(block_bio_complete,
TP_PROTO(struct request_queue *q, struct bio *bio),
__entry->nr_sector, __entry->comm)
);
+/**
+ * block_bio_backmerge - merging block operation to the end of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block request @bio to the end of an existing block request
+ * in queue @q.
+ */
DEFINE_EVENT(block_bio, block_bio_backmerge,
TP_PROTO(struct request_queue *q, struct bio *bio),
TP_ARGS(q, bio)
);
+/**
+ * block_bio_frontmerge - merging block operation to the beginning of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block IO operation @bio to the beginning of an existing block
+ * operation in queue @q.
+ */
DEFINE_EVENT(block_bio, block_bio_frontmerge,
TP_PROTO(struct request_queue *q, struct bio *bio),
TP_ARGS(q, bio)
);
+/**
+ * block_bio_queue - putting new block IO operation in queue
+ * @q: queue holding operation
+ * @bio: new block operation
+ *
+ * About to place the block IO operation @bio into queue @q.
+ */
DEFINE_EVENT(block_bio, block_bio_queue,
TP_PROTO(struct request_queue *q, struct bio *bio),
__entry->nr_sector, __entry->comm)
);
+/**
+ * block_getrq - get a free request entry in queue for block IO operations
+ * @q: queue for operations
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * A request struct for queue @q has been allocated to handle the
+ * block IO operation @bio.
+ */
DEFINE_EVENT(block_get_rq, block_getrq,
TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
TP_ARGS(q, bio, rw)
);
+/**
+ * block_sleeprq - waiting to get a free request entry in queue for block IO operation
+ * @q: queue for operation
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * In the case where a request struct cannot be provided for queue @q
+ * the process needs to wait for an request struct to become
+ * available. This tracepoint event is generated each time the
+ * process goes to sleep waiting for request struct become available.
+ */
DEFINE_EVENT(block_get_rq, block_sleeprq,
TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
TP_ARGS(q, bio, rw)
);
+/**
+ * block_plug - keep operations requests in request queue
+ * @q: request queue to plug
+ *
+ * Plug the request queue @q. Do not allow block operation requests
+ * to be sent to the device driver. Instead, accumulate requests in
+ * the queue to improve throughput performance of the block device.
+ */
TRACE_EVENT(block_plug,
TP_PROTO(struct request_queue *q),
TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
);
+/**
+ * block_unplug_timer - timed release of operations requests in queue to device driver
+ * @q: request queue to unplug
+ *
+ * Unplug the request queue @q because a timer expired and allow block
+ * operation requests to be sent to the device driver.
+ */
DEFINE_EVENT(block_unplug, block_unplug_timer,
TP_PROTO(struct request_queue *q),
TP_ARGS(q)
);
+/**
+ * block_unplug_io - release of operations requests in request queue
+ * @q: request queue to unplug
+ *
+ * Unplug request queue @q because device driver is scheduled to work
+ * on elements in the request queue.
+ */
DEFINE_EVENT(block_unplug, block_unplug_io,
TP_PROTO(struct request_queue *q),
TP_ARGS(q)
);
+/**
+ * block_split - split a single bio struct into two bio structs
+ * @q: queue containing the bio
+ * @bio: block operation being split
+ * @new_sector: The starting sector for the new bio
+ *
+ * The bio request @bio in request queue @q needs to be split into two
+ * bio requests. The newly created @bio request starts at
+ * @new_sector. This split may be required due to hardware limitation
+ * such as operation crossing device boundaries in a RAID system.
+ */
TRACE_EVENT(block_split,
TP_PROTO(struct request_queue *q, struct bio *bio,
__entry->comm)
);
+/**
+ * block_remap - map request for a partition to the raw device
+ * @q: queue holding the operation
+ * @bio: revised operation
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * An operation for a partition on a block device has been mapped to the
+ * raw block device.
+ */
TRACE_EVENT(block_remap,
TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
(unsigned long long)__entry->old_sector)
);
+/**
+ * block_rq_remap - map request for a block operation request
+ * @q: queue holding the operation
+ * @rq: block IO operation request
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * The block operation request @rq in @q has been remapped. The block
+ * operation request @rq holds the current information and @from hold
+ * the original sector.
+ */
TRACE_EVENT(block_rq_remap,
TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev,
obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
- string_helpers.o gcd.o list_sort.o
+ string_helpers.o gcd.o lcm.o list_sort.o
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
CFLAGS_kobject.o += -DDEBUG
--- /dev/null
+#include <linux/kernel.h>
+#include <linux/gcd.h>
+#include <linux/module.h>
+
+/* Lowest common multiple */
+unsigned long lcm(unsigned long a, unsigned long b)
+{
+ if (a && b)
+ return (a * b) / gcd(a, b);
+ else if (b)
+ return b;
+
+ return a;
+}
+EXPORT_SYMBOL_GPL(lcm);
static __init int bdi_class_init(void)
{
bdi_class = class_create(THIS_MODULE, "bdi");
+ if (IS_ERR(bdi_class))
+ return PTR_ERR(bdi_class);
+
bdi_class->dev_attrs = bdi_dev_attrs;
bdi_debug_init();
return 0;
projects / deliverable / linux.git / commitdiff
