OpenCloudOS-Kernel/include/linux/blkdev.h

1572 lines
45 KiB
C
Raw Normal View History

#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H
#include <linux/sched.h>
#ifdef CONFIG_BLOCK
#include <linux/major.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/mempool.h>
#include <linux/bio.h>
#include <linux/stringify.h>
#include <linux/gfp.h>
#include <linux/bsg.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <asm/scatterlist.h>
struct module;
struct scsi_ioctl_command;
struct request_queue;
struct elevator_queue;
struct request_pm_state;
struct blk_trace;
struct request;
struct sg_io_hdr;
struct bsg_job;
struct blkcg_gq;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
/*
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
#define BLKCG_MAX_POLS 2
struct request;
typedef void (rq_end_io_fn)(struct request *, int);
#define BLK_RL_SYNCFULL (1U << 0)
#define BLK_RL_ASYNCFULL (1U << 1)
struct request_list {
struct request_queue *q; /* the queue this rl belongs to */
blkcg: implement per-blkg request allocation Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer <rni@google.com>. v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-06-27 06:05:44 +08:00
#ifdef CONFIG_BLK_CGROUP
struct blkcg_gq *blkg; /* blkg this request pool belongs to */
#endif
/*
* count[], starved[], and wait[] are indexed by
* BLK_RW_SYNC/BLK_RW_ASYNC
*/
int count[2];
int starved[2];
mempool_t *rq_pool;
wait_queue_head_t wait[2];
unsigned int flags;
};
/*
* request command types
*/
enum rq_cmd_type_bits {
REQ_TYPE_FS = 1, /* fs request */
REQ_TYPE_BLOCK_PC, /* scsi command */
REQ_TYPE_SENSE, /* sense request */
REQ_TYPE_PM_SUSPEND, /* suspend request */
REQ_TYPE_PM_RESUME, /* resume request */
REQ_TYPE_PM_SHUTDOWN, /* shutdown request */
REQ_TYPE_SPECIAL, /* driver defined type */
/*
* for ATA/ATAPI devices. this really doesn't belong here, ide should
* use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
* private REQ_LB opcodes to differentiate what type of request this is
*/
REQ_TYPE_ATA_TASKFILE,
REQ_TYPE_ATA_PC,
};
#define BLK_MAX_CDB 16
/*
* try to put the fields that are referenced together in the same cacheline.
* if you modify this structure, be sure to check block/blk-core.c:blk_rq_init()
* as well!
*/
struct request {
struct list_head queuelist;
struct call_single_data csd;
struct request_queue *q;
unsigned int cmd_flags;
enum rq_cmd_type_bits cmd_type;
unsigned long atomic_flags;
int cpu;
/* the following two fields are internal, NEVER access directly */
unsigned int __data_len; /* total data len */
sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
struct hlist_node hash; /* merge hash */
/*
* The rb_node is only used inside the io scheduler, requests
* are pruned when moved to the dispatch queue. So let the
* completion_data share space with the rb_node.
*/
union {
struct rb_node rb_node; /* sort/lookup */
void *completion_data;
};
/*
blkio: Fix blkio crash during rq stat update blkio + cfq was crashing even when two sequential readers were put in two separate cgroups (group_isolation=0). The reason being that cfqq can migrate across groups based on its being sync-noidle or not, it can happen that at request insertion time, cfqq belonged to one cfqg and at request dispatch time, it belonged to root group. In this case request stats per cgroup can go wrong and it also runs into BUG_ON(). This patch implements rq stashing away a cfq group pointer and not relying on cfqq->cfqg pointer alone for rq stat accounting. [ 65.163523] ------------[ cut here ]------------ [ 65.164301] kernel BUG at block/blk-cgroup.c:117! [ 65.164301] invalid opcode: 0000 [#1] SMP [ 65.164301] last sysfs file: /sys/devices/pci0000:00/0000:00:05.0/0000:60:00.1/host9/rport-9:0-0/target9:0:0/9:0:0:2/block/sde/stat [ 65.164301] CPU 1 [ 65.164301] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 65.164301] [ 65.164301] Pid: 4505, comm: fio Not tainted 2.6.34-rc4-blk-for-35 #34 0A98h/HP xw8600 Workstation [ 65.164301] RIP: 0010:[<ffffffff8121924f>] [<ffffffff8121924f>] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP: 0018:ffff8800ba5a79e8 EFLAGS: 00010046 [ 65.164301] RAX: 0000000000000096 RBX: ffff8800bb268d60 RCX: 0000000000000000 [ 65.164301] RDX: ffff8800bb268eb8 RSI: 0000000000000000 RDI: ffff8800bb268e00 [ 65.164301] RBP: ffff8800ba5a7a08 R08: 0000000000000064 R09: 0000000000000001 [ 65.164301] R10: 0000000000079640 R11: ffff8800a0bd5bf0 R12: ffff8800bab4af01 [ 65.164301] R13: ffff8800bab4af00 R14: ffff8800bb1d8928 R15: 0000000000000000 [ 65.164301] FS: 00007f18f75056f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 65.164301] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.164301] CR2: 000000000040e7f0 CR3: 00000000ba52b000 CR4: 00000000000006e0 [ 65.164301] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 65.164301] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 65.164301] Process fio (pid: 4505, threadinfo ffff8800ba5a6000, task ffff8800ba45ae80) [ 65.164301] Stack: [ 65.164301] ffff8800ba5a7a08 ffff8800ba722540 ffff8800bab4af68 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba5a7a38 ffffffff8121d814 ffff8800ba722540 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba722540 ffff8800a08f6800 ffff8800ba5a7a68 ffffffff8121d8ca [ 65.164301] Call Trace: [ 65.164301] [<ffffffff8121d814>] cfq_remove_request+0xe4/0x116 [ 65.164301] [<ffffffff8121d8ca>] cfq_dispatch_insert+0x84/0xe1 [ 65.164301] [<ffffffff8121e833>] cfq_dispatch_requests+0x767/0x8e8 [ 65.164301] [<ffffffff8120e524>] ? submit_bio+0xc3/0xcc [ 65.164301] [<ffffffff810ad657>] ? sync_page_killable+0x0/0x35 [ 65.164301] [<ffffffff8120ea8d>] blk_peek_request+0x191/0x1a7 [ 65.164301] [<ffffffffa000109c>] ? dm_get_live_table+0x44/0x4f [dm_mod] [ 65.164301] [<ffffffffa0002799>] dm_request_fn+0x38/0x14c [dm_mod] [ 65.164301] [<ffffffff810ad657>] ? sync_page_killable+0x0/0x35 [ 65.164301] [<ffffffff8120f600>] __generic_unplug_device+0x32/0x37 [ 65.164301] [<ffffffff8120f8a0>] generic_unplug_device+0x2e/0x3c [ 65.164301] [<ffffffffa00011a6>] dm_unplug_all+0x42/0x5b [dm_mod] [ 65.164301] [<ffffffff8120b063>] blk_unplug+0x29/0x2d [ 65.164301] [<ffffffff8120b079>] blk_backing_dev_unplug+0x12/0x14 [ 65.164301] [<ffffffff81108a82>] block_sync_page+0x35/0x39 [ 65.164301] [<ffffffff810ad64e>] sync_page+0x41/0x4a [ 65.164301] [<ffffffff810ad665>] sync_page_killable+0xe/0x35 [ 65.164301] [<ffffffff81589027>] __wait_on_bit_lock+0x46/0x8f [ 65.164301] [<ffffffff810ad52d>] __lock_page_killable+0x66/0x6d [ 65.164301] [<ffffffff81055fd4>] ? wake_bit_function+0x0/0x33 [ 65.164301] [<ffffffff810ad560>] lock_page_killable+0x2c/0x2e [ 65.164301] [<ffffffff810aebfd>] generic_file_aio_read+0x361/0x4f0 [ 65.164301] [<ffffffff810e906c>] do_sync_read+0xcb/0x108 [ 65.164301] [<ffffffff811e32a3>] ? security_file_permission+0x16/0x18 [ 65.164301] [<ffffffff810e96d3>] vfs_read+0xab/0x108 [ 65.164301] [<ffffffff810e97f0>] sys_read+0x4a/0x6e [ 65.164301] [<ffffffff81002b5b>] system_call_fastpath+0x16/0x1b [ 65.164301] Code: 00 74 1c 48 8b 8b 60 01 00 00 48 85 c9 75 04 0f 0b eb fe 48 ff c9 48 89 8b 60 01 00 00 eb 1a 48 8b 8b 58 01 00 00 48 85 c9 75 04 <0f> 0b eb fe 48 ff c9 48 89 8b 58 01 00 00 45 84 e4 74 16 48 8b [ 65.164301] RIP [<ffffffff8121924f>] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP <ffff8800ba5a79e8> [ 65.164301] ---[ end trace 1b2b828753032e68 ]--- Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-21 23:44:16 +08:00
* Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it. Flush requests are
* never put on the IO scheduler. So let the flush fields share
* space with the elevator data.
*/
union {
struct {
struct io_cq *icq;
void *priv[2];
} elv;
struct {
unsigned int seq;
struct list_head list;
block: fix flush machinery for stacking drivers with differring flush flags Commit ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae, block: reimplement FLUSH/FUA to support merge, introduced a performance regression when running any sort of fsyncing workload using dm-multipath and certain storage (in our case, an HP EVA). The test I ran was fs_mark, and it dropped from ~800 files/sec on ext4 to ~100 files/sec. It turns out that dm-multipath always advertised flush+fua support, and passed commands on down the stack, where those flags used to get stripped off. The above commit changed that behavior: static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; while (1) { - while (!list_empty(&q->queue_head)) { + if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || - (rq->cmd_flags & REQ_FLUSH_SEQ)) - return rq; - rq = blk_do_flush(q, rq); - if (rq) - return rq; + return rq; } Note that previously, a command would come in here, have REQ_FLUSH|REQ_FUA set, and then get handed off to blk_do_flush: struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned int fflags = q->flush_flags; /* may change, cache it */ bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; ... if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { rq->cmd_flags &= ~REQ_FLUSH; if (!has_fua) rq->cmd_flags &= ~REQ_FUA; return rq; } So, the flush machinery was bypassed in such cases (q->flush_flags == 0 && rq->cmd_flags & (REQ_FLUSH|REQ_FUA)). Now, however, we don't get into the flush machinery at all. Instead, __elv_next_request just hands a request with flush and fua bits set to the scsi_request_fn, even if the underlying request_queue does not support flush or fua. The agreed upon approach is to fix the flush machinery to allow stacking. While this isn't used in practice (since there is only one request-based dm target, and that target will now reflect the flush flags of the underlying device), it does future-proof the solution, and make it function as designed. In order to make this work, I had to add a field to the struct request, inside the flush structure (to store the original req->end_io). Shaohua had suggested overloading the union with rb_node and completion_data, but the completion data is used by device mapper and can also be used by other drivers. So, I didn't see a way around the additional field. I tested this patch on an HP EVA with both ext4 and xfs, and it recovers the lost performance. Comments and other testers, as always, are appreciated. Cheers, Jeff Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-08-16 03:37:25 +08:00
rq_end_io_fn *saved_end_io;
} flush;
};
struct gendisk *rq_disk;
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 23:57:38 +08:00
struct hd_struct *part;
unsigned long start_time;
#ifdef CONFIG_BLK_CGROUP
blkcg: implement per-blkg request allocation Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer <rni@google.com>. v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-06-27 06:05:44 +08:00
struct request_list *rl; /* rl this rq is alloced from */
unsigned long long start_time_ns;
unsigned long long io_start_time_ns; /* when passed to hardware */
#endif
/* Number of scatter-gather DMA addr+len pairs after
* physical address coalescing is performed.
*/
unsigned short nr_phys_segments;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
unsigned short nr_integrity_segments;
#endif
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;
/*
* when request is used as a packet command carrier
*/
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;
block: add rq->resid_len rq->data_len served two purposes - the length of data buffer on issue and the residual count on completion. This duality creates some headaches. First of all, block layer and low level drivers can't really determine what rq->data_len contains while a request is executing. It could be the total request length or it coulde be anything else one of the lower layers is using to keep track of residual count. This complicates things because blk_rq_bytes() and thus [__]blk_end_request_all() relies on rq->data_len for PC commands. Drivers which want to report residual count should first cache the total request length, update rq->data_len and then complete the request with the cached data length. Secondly, it makes requests default to reporting full residual count, ie. reporting that no data transfer occurred. The residual count is an exception not the norm; however, the driver should clear rq->data_len to zero to signify the normal cases while leaving it alone means no data transfer occurred at all. This reverse default behavior complicates code unnecessarily and renders block PC on some drivers (ide-tape/floppy) unuseable. This patch adds rq->resid_len which is used only for residual count. While at it, remove now unnecessasry blk_rq_bytes() caching in ide_pc_intr() as rq->data_len is not changed anymore. Boaz : spotted missing conversion in osd Sergei : spotted too early conversion to blk_rq_bytes() in ide-tape [ Impact: cleanup residual count handling, report 0 resid by default ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Mike Miller <mike.miller@hp.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Doug Gilbert <dgilbert@interlog.com> Cc: Mike Miller <mike.miller@hp.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Darrick J. Wong <djwong@us.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:37 +08:00
unsigned int resid_len; /* residual count */
void *sense;
unsigned long deadline;
struct list_head timeout_list;
unsigned int timeout;
int retries;
/*
* completion callback.
*/
rq_end_io_fn *end_io;
void *end_io_data;
/* for bidi */
struct request *next_rq;
};
static inline unsigned short req_get_ioprio(struct request *req)
{
return req->ioprio;
}
/*
* State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
* requests. Some step values could eventually be made generic.
*/
struct request_pm_state
{
/* PM state machine step value, currently driver specific */
int pm_step;
/* requested PM state value (S1, S2, S3, S4, ...) */
u32 pm_state;
void* data; /* for driver use */
};
#include <linux/elevator.h>
typedef void (request_fn_proc) (struct request_queue *q);
typedef void (make_request_fn) (struct request_queue *q, struct bio *bio);
typedef int (prep_rq_fn) (struct request_queue *, struct request *);
typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
struct bio_vec;
struct bvec_merge_data {
struct block_device *bi_bdev;
sector_t bi_sector;
unsigned bi_size;
unsigned long bi_rw;
};
typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
struct bio_vec *);
typedef void (softirq_done_fn)(struct request *);
typedef int (dma_drain_needed_fn)(struct request *);
block: add lld busy state exporting interface This patch adds an new interface, blk_lld_busy(), to check lld's busy state from the block layer. blk_lld_busy() calls down into low-level drivers for the checking if the drivers set q->lld_busy_fn() using blk_queue_lld_busy(). This resolves a performance problem on request stacking devices below. Some drivers like scsi mid layer stop dispatching request when they detect busy state on its low-level device like host/target/device. It allows other requests to stay in the I/O scheduler's queue for a chance of merging. Request stacking drivers like request-based dm should follow the same logic. However, there is no generic interface for the stacked device to check if the underlying device(s) are busy. If the request stacking driver dispatches and submits requests to the busy underlying device, the requests will stay in the underlying device's queue without a chance of merging. This causes performance problem on burst I/O load. With this patch, busy state of the underlying device is exported via q->lld_busy_fn(). So the request stacking driver can check it and stop dispatching requests if busy. The underlying device driver must return the busy state appropriately: 1: when the device driver can't process requests immediately. 0: when the device driver can process requests immediately, including abnormal situations where the device driver needs to kill all requests. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-10-01 22:12:15 +08:00
typedef int (lld_busy_fn) (struct request_queue *q);
typedef int (bsg_job_fn) (struct bsg_job *);
enum blk_eh_timer_return {
BLK_EH_NOT_HANDLED,
BLK_EH_HANDLED,
BLK_EH_RESET_TIMER,
};
typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *);
enum blk_queue_state {
Queue_down,
Queue_up,
};
struct blk_queue_tag {
struct request **tag_index; /* map of busy tags */
unsigned long *tag_map; /* bit map of free/busy tags */
int busy; /* current depth */
int max_depth; /* what we will send to device */
[PATCH] blk: fix tag shrinking (revive real_max_size) My patch in commit fa72b903f75e4f0f0b2c2feed093005167da4023 incorrectly removed blk_queue_tag->real_max_depth. The original resize implementation was incorrect in the following points. * actual allocation size of tag_index was shorter than real_max_size, but assumed to be of the same size, possibly causing memory access beyond the allocated area. * bits in tag_map between max_deptn and real_max_depth were initialized to 1's, making the tags permanently reserved. In an attempt to fix above two bugs, I had removed allocation optimization in init_tag_map and real_max_size. Tag map/index were allocated and freed immediately during resize. Unfortunately, I wasn't considering that tag map/index can be resized dynamically with tags beyond new_depth active. This led to accessing freed area after shrinking tags and led to the following bug reporting thread on linux-scsi. http://marc.theaimsgroup.com/?l=linux-scsi&m=112319898111885&w=2 To fix the problem, I've revived real_max_depth without allocation optimization in init_tag_map, and Andrew Vasquez confirmed that the problem was fixed. As Jens is not going to be available for a week, he asked me to make sure that this patch reaches you. http://marc.theaimsgroup.com/?l=linux-scsi&m=112325778530886&w=2 Also, a comment was added to make sure that real_max_size is needed for dynamic shrinking. Signed-off-by: Tejun Heo <htejun@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-06 04:28:11 +08:00
int real_max_depth; /* what the array can hold */
atomic_t refcnt; /* map can be shared */
};
#define BLK_SCSI_MAX_CMDS (256)
#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
struct queue_limits {
unsigned long bounce_pfn;
unsigned long seg_boundary_mask;
unsigned int max_hw_sectors;
unsigned int max_sectors;
unsigned int max_segment_size;
unsigned int physical_block_size;
unsigned int alignment_offset;
unsigned int io_min;
unsigned int io_opt;
unsigned int max_discard_sectors;
unsigned int max_write_same_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned short logical_block_size;
unsigned short max_segments;
unsigned short max_integrity_segments;
unsigned char misaligned;
unsigned char discard_misaligned;
unsigned char cluster;
unsigned char discard_zeroes_data;
};
struct request_queue {
/*
* Together with queue_head for cacheline sharing
*/
struct list_head queue_head;
struct request *last_merge;
struct elevator_queue *elevator;
int nr_rqs[2]; /* # allocated [a]sync rqs */
int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */
/*
blkcg: implement per-blkg request allocation Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer <rni@google.com>. v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-06-27 06:05:44 +08:00
* If blkcg is not used, @q->root_rl serves all requests. If blkcg
* is used, root blkg allocates from @q->root_rl and all other
* blkgs from their own blkg->rl. Which one to use should be
* determined using bio_request_list().
*/
blkcg: implement per-blkg request allocation Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer <rni@google.com>. v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-06-27 06:05:44 +08:00
struct request_list root_rl;
request_fn_proc *request_fn;
make_request_fn *make_request_fn;
prep_rq_fn *prep_rq_fn;
unprep_rq_fn *unprep_rq_fn;
merge_bvec_fn *merge_bvec_fn;
softirq_done_fn *softirq_done_fn;
rq_timed_out_fn *rq_timed_out_fn;
dma_drain_needed_fn *dma_drain_needed;
block: add lld busy state exporting interface This patch adds an new interface, blk_lld_busy(), to check lld's busy state from the block layer. blk_lld_busy() calls down into low-level drivers for the checking if the drivers set q->lld_busy_fn() using blk_queue_lld_busy(). This resolves a performance problem on request stacking devices below. Some drivers like scsi mid layer stop dispatching request when they detect busy state on its low-level device like host/target/device. It allows other requests to stay in the I/O scheduler's queue for a chance of merging. Request stacking drivers like request-based dm should follow the same logic. However, there is no generic interface for the stacked device to check if the underlying device(s) are busy. If the request stacking driver dispatches and submits requests to the busy underlying device, the requests will stay in the underlying device's queue without a chance of merging. This causes performance problem on burst I/O load. With this patch, busy state of the underlying device is exported via q->lld_busy_fn(). So the request stacking driver can check it and stop dispatching requests if busy. The underlying device driver must return the busy state appropriately: 1: when the device driver can't process requests immediately. 0: when the device driver can process requests immediately, including abnormal situations where the device driver needs to kill all requests. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-10-01 22:12:15 +08:00
lld_busy_fn *lld_busy_fn;
/*
* Dispatch queue sorting
*/
sector_t end_sector;
struct request *boundary_rq;
/*
* Delayed queue handling
*/
struct delayed_work delay_work;
struct backing_dev_info backing_dev_info;
/*
* The queue owner gets to use this for whatever they like.
* ll_rw_blk doesn't touch it.
*/
void *queuedata;
/*
* various queue flags, see QUEUE_* below
*/
unsigned long queue_flags;
/*
* ida allocated id for this queue. Used to index queues from
* ioctx.
*/
int id;
/*
* queue needs bounce pages for pages above this limit
*/
gfp_t bounce_gfp;
/*
* protects queue structures from reentrancy. ->__queue_lock should
* _never_ be used directly, it is queue private. always use
* ->queue_lock.
*/
spinlock_t __queue_lock;
spinlock_t *queue_lock;
/*
* queue kobject
*/
struct kobject kobj;
#ifdef CONFIG_PM_RUNTIME
struct device *dev;
int rpm_status;
unsigned int nr_pending;
#endif
/*
* queue settings
*/
unsigned long nr_requests; /* Max # of requests */
unsigned int nr_congestion_on;
unsigned int nr_congestion_off;
unsigned int nr_batching;
unsigned int dma_drain_size;
void *dma_drain_buffer;
unsigned int dma_pad_mask;
unsigned int dma_alignment;
struct blk_queue_tag *queue_tags;
struct list_head tag_busy_list;
unsigned int nr_sorted;
unsigned int in_flight[2];
/*
* Number of active block driver functions for which blk_drain_queue()
* must wait. Must be incremented around functions that unlock the
* queue_lock internally, e.g. scsi_request_fn().
*/
unsigned int request_fn_active;
unsigned int rq_timeout;
struct timer_list timeout;
struct list_head timeout_list;
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS);
struct blkcg_gq *root_blkg;
struct list_head blkg_list;
#endif
struct queue_limits limits;
/*
* sg stuff
*/
unsigned int sg_timeout;
unsigned int sg_reserved_size;
int node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct blk_trace *blk_trace;
#endif
/*
* for flush operations
*/
unsigned int flush_flags;
unsigned int flush_not_queueable:1;
unsigned int flush_queue_delayed:1;
block: reimplement FLUSH/FUA to support merge The current FLUSH/FUA support has evolved from the implementation which had to perform queue draining. As such, sequencing is done queue-wide one flush request after another. However, with the draining requirement gone, there's no reason to keep the queue-wide sequential approach. This patch reimplements FLUSH/FUA support such that each FLUSH/FUA request is sequenced individually. The actual FLUSH execution is double buffered and whenever a request wants to execute one for either PRE or POSTFLUSH, it queues on the pending queue. Once certain conditions are met, a flush request is issued and on its completion all pending requests proceed to the next sequence. This allows arbitrary merging of different type of flushes. How they are merged can be primarily controlled and tuned by adjusting the above said 'conditions' used to determine when to issue the next flush. This is inspired by Darrick's patches to merge multiple zero-data flushes which helps workloads with highly concurrent fsync requests. * As flush requests are never put on the IO scheduler, request fields used for flush share space with rq->rb_node. rq->completion_data is moved out of the union. This increases the request size by one pointer. As rq->elevator_private* are used only by the iosched too, it is possible to reduce the request size further. However, to do that, we need to modify request allocation path such that iosched data is not allocated for flush requests. * FLUSH/FUA processing happens on insertion now instead of dispatch. - Comments updated as per Vivek and Mike. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: "Darrick J. Wong" <djwong@us.ibm.com> Cc: Shaohua Li <shli@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-25 19:43:54 +08:00
unsigned int flush_pending_idx:1;
unsigned int flush_running_idx:1;
unsigned long flush_pending_since;
struct list_head flush_queue[2];
struct list_head flush_data_in_flight;
struct request flush_rq;
struct mutex sysfs_lock;
int bypass_depth;
#if defined(CONFIG_BLK_DEV_BSG)
bsg_job_fn *bsg_job_fn;
int bsg_job_size;
struct bsg_class_device bsg_dev;
#endif
#ifdef CONFIG_BLK_CGROUP
struct list_head all_q_node;
#endif
#ifdef CONFIG_BLK_DEV_THROTTLING
/* Throttle data */
struct throtl_data *td;
#endif
struct rcu_head rcu_head;
};
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */
#define QUEUE_FLAG_STOPPED 2 /* queue is stopped */
#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */
#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */
#define QUEUE_FLAG_DYING 5 /* queue being torn down */
#define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */
#define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */
#define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */
#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */
#define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */
#define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */
#define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT 13 /* do IO stats */
#define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */
#define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */
#define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */
#define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */
#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */
#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
(1 << QUEUE_FLAG_SAME_COMP) | \
(1 << QUEUE_FLAG_ADD_RANDOM))
static inline void queue_lockdep_assert_held(struct request_queue *q)
{
if (q->queue_lock)
lockdep_assert_held(q->queue_lock);
}
static inline void queue_flag_set_unlocked(unsigned int flag,
struct request_queue *q)
{
__set_bit(flag, &q->queue_flags);
}
static inline int queue_flag_test_and_clear(unsigned int flag,
struct request_queue *q)
{
queue_lockdep_assert_held(q);
if (test_bit(flag, &q->queue_flags)) {
__clear_bit(flag, &q->queue_flags);
return 1;
}
return 0;
}
static inline int queue_flag_test_and_set(unsigned int flag,
struct request_queue *q)
{
queue_lockdep_assert_held(q);
if (!test_bit(flag, &q->queue_flags)) {
__set_bit(flag, &q->queue_flags);
return 0;
}
return 1;
}
static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
{
queue_lockdep_assert_held(q);
__set_bit(flag, &q->queue_flags);
}
static inline void queue_flag_clear_unlocked(unsigned int flag,
struct request_queue *q)
{
__clear_bit(flag, &q->queue_flags);
}
static inline int queue_in_flight(struct request_queue *q)
{
return q->in_flight[0] + q->in_flight[1];
}
static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
{
queue_lockdep_assert_held(q);
__clear_bit(flag, &q->queue_flags);
}
#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
#define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
#define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
#define blk_queue_noxmerges(q) \
test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
block: add a queue flag for request stacking support This patch adds a queue flag to indicate the block device can be used for request stacking. Request stacking drivers need to stack their devices on top of only devices of which q->request_fn is functional. Since bio stacking drivers (e.g. md, loop) basically initialize their queue using blk_alloc_queue() and don't set q->request_fn, the check of (q->request_fn == NULL) looks enough for that purpose. However, dm will become both types of stacking driver (bio-based and request-based). And dm will always set q->request_fn even if the dm device is bio-based of which q->request_fn is not functional actually. So we need something else to distinguish the type of the device. Adding a queue flag is a solution for that. The reason why dm always sets q->request_fn is to keep the compatibility of dm user-space tools. Currently, all dm user-space tools are using bio-based dm without specifying the type of the dm device they use. To use request-based dm without changing such tools, the kernel must decide the type of the dm device automatically. The automatic type decision can't be done at the device creation time and needs to be deferred until such tools load a mapping table, since the actual type is decided by dm target type included in the mapping table. So a dm device has to be initialized using blk_init_queue() so that we can load either type of table. Then, all queue stuffs are set (e.g. q->request_fn) and we have no element to distinguish that it is bio-based or request-based, even after a table is loaded and the type of the device is decided. By the way, some stuffs of the queue (e.g. request_list, elevator) are needless when the dm device is used as bio-based. But the memory size is not so large (about 20[KB] per queue on ia64), so I hope the memory loss can be acceptable for bio-based dm users. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 22:46:13 +08:00
#define blk_queue_stackable(q) \
test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \
test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags))
#define blk_noretry_request(rq) \
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
REQ_FAILFAST_DRIVER))
#define blk_account_rq(rq) \
(((rq)->cmd_flags & REQ_STARTED) && \
((rq)->cmd_type == REQ_TYPE_FS))
#define blk_pm_request(rq) \
((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \
(rq)->cmd_type == REQ_TYPE_PM_RESUME)
#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1)
#define blk_bidi_rq(rq) ((rq)->next_rq != NULL)
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-12 06:40:30 +08:00
/* rq->queuelist of dequeued request must be list_empty() */
#define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist))
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
#define rq_data_dir(rq) ((rq)->cmd_flags & 1)
static inline unsigned int blk_queue_cluster(struct request_queue *q)
{
return q->limits.cluster;
}
/*
* We regard a request as sync, if either a read or a sync write
*/
static inline bool rw_is_sync(unsigned int rw_flags)
{
return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC);
}
static inline bool rq_is_sync(struct request *rq)
{
return rw_is_sync(rq->cmd_flags);
}
static inline bool blk_rl_full(struct request_list *rl, bool sync)
{
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
return rl->flags & flag;
}
static inline void blk_set_rl_full(struct request_list *rl, bool sync)
{
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
rl->flags |= flag;
}
static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
{
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
rl->flags &= ~flag;
}
static inline bool rq_mergeable(struct request *rq)
{
if (rq->cmd_type != REQ_TYPE_FS)
return false;
if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
return false;
return true;
}
static inline bool blk_check_merge_flags(unsigned int flags1,
unsigned int flags2)
{
if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD))
return false;
if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
return false;
if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
return false;
return true;
}
static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
{
if (bio_data(a) == bio_data(b))
return true;
return false;
}
/*
* q->prep_rq_fn return values
*/
#define BLKPREP_OK 0 /* serve it */
#define BLKPREP_KILL 1 /* fatal error, kill */
#define BLKPREP_DEFER 2 /* leave on queue */
extern unsigned long blk_max_low_pfn, blk_max_pfn;
/*
* standard bounce addresses:
*
* BLK_BOUNCE_HIGH : bounce all highmem pages
* BLK_BOUNCE_ANY : don't bounce anything
* BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary
*/
#if BITS_PER_LONG == 32
#define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT)
#else
#define BLK_BOUNCE_HIGH -1ULL
#endif
#define BLK_BOUNCE_ANY (-1ULL)
#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24))
/*
* default timeout for SG_IO if none specified
*/
#define BLK_DEFAULT_SG_TIMEOUT (60 * HZ)
#define BLK_MIN_SG_TIMEOUT (7 * HZ)
#ifdef CONFIG_BOUNCE
extern int init_emergency_isa_pool(void);
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
#else
static inline int init_emergency_isa_pool(void)
{
return 0;
}
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
{
}
#endif /* CONFIG_MMU */
struct rq_map_data {
struct page **pages;
int page_order;
int nr_entries;
unsigned long offset;
int null_mapped;
block: fix sg SG_DXFER_TO_FROM_DEV regression I overlooked SG_DXFER_TO_FROM_DEV support when I converted sg to use the block layer mapping API (2.6.28). Douglas Gilbert explained SG_DXFER_TO_FROM_DEV: http://www.spinics.net/lists/linux-scsi/msg37135.html = The semantics of SG_DXFER_TO_FROM_DEV were: - copy user space buffer to kernel (LLD) buffer - do SCSI command which is assumed to be of the DATA_IN (data from device) variety. This would overwrite some or all of the kernel buffer - copy kernel (LLD) buffer back to the user space. The idea was to detect short reads by filling the original user space buffer with some marker bytes ("0xec" it would seem in this report). The "resid" value is a better way of detecting short reads but that was only added this century and requires co-operation from the LLD. = This patch changes the block layer mapping API to support this semantics. This simply adds another field to struct rq_map_data and enables __bio_copy_iov() to copy data from user space even with READ requests. It's better to add the flags field and kills null_mapped and the new from_user fields in struct rq_map_data but that approach makes it difficult to send this patch to stable trees because st and osst drivers use struct rq_map_data (they were converted to use the block layer in 2.6.29 and 2.6.30). Well, I should clean up the block layer mapping API. zhou sf reported this regiression and tested this patch: http://www.spinics.net/lists/linux-scsi/msg37128.html http://www.spinics.net/lists/linux-scsi/msg37168.html Reported-by: zhou sf <sxzzsf@gmail.com> Tested-by: zhou sf <sxzzsf@gmail.com> Cc: stable@kernel.org Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-09 20:46:53 +08:00
int from_user;
};
struct req_iterator {
int i;
struct bio *bio;
};
/* This should not be used directly - use rq_for_each_segment */
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 16:03:10 +08:00
#define for_each_bio(_bio) \
for (; _bio; _bio = _bio->bi_next)
#define __rq_for_each_bio(_bio, rq) \
if ((rq->bio)) \
for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
#define rq_for_each_segment(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bio_for_each_segment(bvl, _iter.bio, _iter.i)
#define rq_iter_last(rq, _iter) \
(_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1)
#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
#endif
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
extern void rq_flush_dcache_pages(struct request *rq);
#else
static inline void rq_flush_dcache_pages(struct request *rq)
{
}
#endif
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
extern void generic_make_request(struct bio *bio);
extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_put_request(struct request *);
extern void __blk_put_request(struct request_queue *, struct request *);
extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
extern struct request *blk_make_request(struct request_queue *, struct bio *,
gfp_t);
extern void blk_requeue_request(struct request_queue *, struct request *);
extern void blk_add_request_payload(struct request *rq, struct page *page,
unsigned int len);
extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
block: add lld busy state exporting interface This patch adds an new interface, blk_lld_busy(), to check lld's busy state from the block layer. blk_lld_busy() calls down into low-level drivers for the checking if the drivers set q->lld_busy_fn() using blk_queue_lld_busy(). This resolves a performance problem on request stacking devices below. Some drivers like scsi mid layer stop dispatching request when they detect busy state on its low-level device like host/target/device. It allows other requests to stay in the I/O scheduler's queue for a chance of merging. Request stacking drivers like request-based dm should follow the same logic. However, there is no generic interface for the stacked device to check if the underlying device(s) are busy. If the request stacking driver dispatches and submits requests to the busy underlying device, the requests will stay in the underlying device's queue without a chance of merging. This causes performance problem on burst I/O load. With this patch, busy state of the underlying device is exported via q->lld_busy_fn(). So the request stacking driver can check it and stop dispatching requests if busy. The underlying device driver must return the busy state appropriately: 1: when the device driver can't process requests immediately. 0: when the device driver can process requests immediately, including abnormal situations where the device driver needs to kill all requests. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-10-01 22:12:15 +08:00
extern int blk_lld_busy(struct request_queue *q);
block: add request clone interface (v2) This patch adds the following 2 interfaces for request-stacking drivers: - blk_rq_prep_clone(struct request *clone, struct request *orig, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio*, void *), void *data) * Clones bios in the original request to the clone request (bio_ctr is called for each cloned bios.) * Copies attributes of the original request to the clone request. The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. - blk_rq_unprep_clone(struct request *clone) * Frees cloned bios from the clone request. Request stacking drivers (e.g. request-based dm) need to make a clone request for a submitted request and dispatch it to other devices. To allocate request for the clone, request stacking drivers may not be able to use blk_get_request() because the allocation may be done in an irq-disabled context. So blk_rq_prep_clone() takes a request allocated by the caller as an argument. For each clone bio in the clone request, request stacking drivers should be able to set up their own completion handler. So blk_rq_prep_clone() takes a callback function which is called for each clone bio, and a pointer for private data which is passed to the callback. NOTE: blk_rq_prep_clone() doesn't copy any actual data of the original request. Pages are shared between original bios and cloned bios. So caller must not complete the original request before the clone request. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-06-11 19:10:16 +08:00
extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio_set *bs, gfp_t gfp_mask,
int (*bio_ctr)(struct bio *, struct bio *, void *),
void *data);
extern void blk_rq_unprep_clone(struct request *rq);
extern int blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
extern void blk_delay_queue(struct request_queue *, unsigned long);
extern void blk_recount_segments(struct request_queue *, struct bio *);
block: fail SCSI passthrough ioctls on partition devices Linux allows executing the SG_IO ioctl on a partition or LVM volume, and will pass the command to the underlying block device. This is well-known, but it is also a large security problem when (via Unix permissions, ACLs, SELinux or a combination thereof) a program or user needs to be granted access only to part of the disk. This patch lets partitions forward a small set of harmless ioctls; others are logged with printk so that we can see which ioctls are actually sent. In my tests only CDROM_GET_CAPABILITY actually occurred. Of course it was being sent to a (partition on a) hard disk, so it would have failed with ENOTTY and the patch isn't changing anything in practice. Still, I'm treating it specially to avoid spamming the logs. In principle, this restriction should include programs running with CAP_SYS_RAWIO. If for example I let a program access /dev/sda2 and /dev/sdb, it still should not be able to read/write outside the boundaries of /dev/sda2 independent of the capabilities. However, for now programs with CAP_SYS_RAWIO will still be allowed to send the ioctls. Their actions will still be logged. This patch does not affect the non-libata IDE driver. That driver however already tests for bd != bd->bd_contains before issuing some ioctl; it could be restricted further to forbid these ioctls even for programs running with CAP_SYS_ADMIN/CAP_SYS_RAWIO. Cc: linux-scsi@vger.kernel.org Cc: Jens Axboe <axboe@kernel.dk> Cc: James Bottomley <JBottomley@parallels.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> [ Make it also print the command name when warning - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 23:01:28 +08:00
extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
unsigned int, void __user *);
extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
unsigned int, void __user *);
extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
struct scsi_ioctl_command __user *);
extern void blk_queue_bio(struct request_queue *q, struct bio *bio);
/*
* A queue has just exitted congestion. Note this in the global counter of
* congested queues, and wake up anyone who was waiting for requests to be
* put back.
*/
static inline void blk_clear_queue_congested(struct request_queue *q, int sync)
{
clear_bdi_congested(&q->backing_dev_info, sync);
}
/*
* A queue has just entered congestion. Flag that in the queue's VM-visible
* state flags and increment the global gounter of congested queues.
*/
static inline void blk_set_queue_congested(struct request_queue *q, int sync)
{
set_bdi_congested(&q->backing_dev_info, sync);
}
extern void blk_start_queue(struct request_queue *q);
extern void blk_stop_queue(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
extern void __blk_stop_queue(struct request_queue *q);
extern void __blk_run_queue(struct request_queue *q);
extern void blk_run_queue(struct request_queue *);
extern void blk_run_queue_async(struct request_queue *q);
extern int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long,
gfp_t);
extern int blk_rq_unmap_user(struct bio *);
extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, struct sg_iovec *, int,
unsigned int, gfp_t);
extern int blk_execute_rq(struct request_queue *, struct gendisk *,
struct request *, int);
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
struct request *, int, rq_end_io_fn *);
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
return bdev->bd_disk->queue;
}
/*
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 16:48:17 +08:00
* blk_rq_pos() : the current sector
* blk_rq_bytes() : bytes left in the entire request
* blk_rq_cur_bytes() : bytes left in the current segment
* blk_rq_err_bytes() : bytes left till the next error boundary
* blk_rq_sectors() : sectors left in the entire request
* blk_rq_cur_sectors() : sectors left in the current segment
*/
static inline sector_t blk_rq_pos(const struct request *rq)
{
return rq->__sector;
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:41 +08:00
}
static inline unsigned int blk_rq_bytes(const struct request *rq)
{
return rq->__data_len;
}
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:41 +08:00
static inline int blk_rq_cur_bytes(const struct request *rq)
{
return rq->bio ? bio_cur_bytes(rq->bio) : 0;
}
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 16:48:17 +08:00
extern unsigned int blk_rq_err_bytes(const struct request *rq);
static inline unsigned int blk_rq_sectors(const struct request *rq)
{
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:41 +08:00
return blk_rq_bytes(rq) >> 9;
}
static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
{
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:41 +08:00
return blk_rq_cur_bytes(rq) >> 9;
}
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
unsigned int cmd_flags)
{
if (unlikely(cmd_flags & REQ_DISCARD))
block: fix max discard sectors limit linux-v3.8-rc1 and later support for plug for blkdev_issue_discard with commit 0cfbcafcae8b7364b5fa96c2b26ccde7a3a296a9 (block: add plug for blkdev_issue_discard ) For example, 1) DISCARD rq-1 with size size 4GB 2) DISCARD rq-2 with size size 1GB If these 2 discard requests get merged, final request size will be 5GB. In this case, request's __data_len field may overflow as it can store max 4GB(unsigned int). This issue was observed while doing mkfs.f2fs on 5GB SD card: https://lkml.org/lkml/2013/4/1/292 Info: sector size = 512 Info: total sectors = 11370496 (in 512bytes) Info: zone aligned segment0 blkaddr: 512 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 mkfs process gets stuck in D state and I see the following in the dmesg: [ 257.789733] __end_that: dev mmcblk0: type=1, flags=122c8081 [ 257.789764] sector 4194304, nr/cnr 2981888/4294959104 [ 257.789764] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 [ 257.794921] request botched: dev mmcblk0: type=1, flags=122c8081 [ 257.794921] sector 4194304, nr/cnr 2981888/4294959104 [ 257.794921] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 This patch fixes this issue. Reported-by: Max Filippov <jcmvbkbc@gmail.com> Signed-off-by: James Bottomley <JBottomley@Parallels.com> Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com> Tested-by: Max Filippov <jcmvbkbc@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-04-24 22:52:50 +08:00
return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
if (unlikely(cmd_flags & REQ_WRITE_SAME))
return q->limits.max_write_same_sectors;
return q->limits.max_sectors;
}
static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
{
struct request_queue *q = rq->q;
if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
return q->limits.max_hw_sectors;
return blk_queue_get_max_sectors(q, rq->cmd_flags);
}
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 10:54:16 +08:00
/*
* Request issue related functions.
*/
extern struct request *blk_peek_request(struct request_queue *q);
extern void blk_start_request(struct request *rq);
extern struct request *blk_fetch_request(struct request_queue *q);
/*
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 10:05:18 +08:00
* Request completion related functions.
*
* blk_update_request() completes given number of bytes and updates
* the request without completing it.
*
2009-04-23 10:05:19 +08:00
* blk_end_request() and friends. __blk_end_request() must be called
* with the request queue spinlock acquired.
*
* Several drivers define their own end_request and call
* blk_end_request() for parts of the original function.
* This prevents code duplication in drivers.
*/
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 10:05:18 +08:00
extern bool blk_update_request(struct request *rq, int error,
unsigned int nr_bytes);
extern bool blk_end_request(struct request *rq, int error,
unsigned int nr_bytes);
extern void blk_end_request_all(struct request *rq, int error);
extern bool blk_end_request_cur(struct request *rq, int error);
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 16:48:17 +08:00
extern bool blk_end_request_err(struct request *rq, int error);
extern bool __blk_end_request(struct request *rq, int error,
unsigned int nr_bytes);
extern void __blk_end_request_all(struct request *rq, int error);
extern bool __blk_end_request_cur(struct request *rq, int error);
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 16:48:17 +08:00
extern bool __blk_end_request_err(struct request *rq, int error);
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 10:05:18 +08:00
extern void blk_complete_request(struct request *);
extern void __blk_complete_request(struct request *);
extern void blk_abort_request(struct request *);
extern void blk_unprep_request(struct request *);
/*
* Access functions for manipulating queue properties
*/
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
spinlock_t *lock, int node_id);
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
request_fn_proc *, spinlock_t *);
extern void blk_cleanup_queue(struct request_queue *);
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_limits_max_hw_sectors(struct queue_limits *, unsigned int);
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
extern void blk_queue_max_segments(struct request_queue *, unsigned short);
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 void blk_queue_max_write_same_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
extern void blk_set_default_limits(struct queue_limits *lim);
extern void blk_set_stacking_limits(struct queue_limits *lim);
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t offset);
extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
sector_t offset);
extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
sector_t offset);
extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
extern int blk_queue_dma_drain(struct request_queue *q,
dma_drain_needed_fn *dma_drain_needed,
void *buf, unsigned int size);
block: add lld busy state exporting interface This patch adds an new interface, blk_lld_busy(), to check lld's busy state from the block layer. blk_lld_busy() calls down into low-level drivers for the checking if the drivers set q->lld_busy_fn() using blk_queue_lld_busy(). This resolves a performance problem on request stacking devices below. Some drivers like scsi mid layer stop dispatching request when they detect busy state on its low-level device like host/target/device. It allows other requests to stay in the I/O scheduler's queue for a chance of merging. Request stacking drivers like request-based dm should follow the same logic. However, there is no generic interface for the stacked device to check if the underlying device(s) are busy. If the request stacking driver dispatches and submits requests to the busy underlying device, the requests will stay in the underlying device's queue without a chance of merging. This causes performance problem on burst I/O load. With this patch, busy state of the underlying device is exported via q->lld_busy_fn(). So the request stacking driver can check it and stop dispatching requests if busy. The underlying device driver must return the busy state appropriately: 1: when the device driver can't process requests immediately. 0: when the device driver can process requests immediately, including abnormal situations where the device driver needs to kill all requests. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-10-01 22:12:15 +08:00
extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn);
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn);
extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist);
extern void blk_dump_rq_flags(struct request *, char *);
extern long nr_blockdev_pages(void);
bool __must_check blk_get_queue(struct request_queue *);
struct request_queue *blk_alloc_queue(gfp_t);
struct request_queue *blk_alloc_queue_node(gfp_t, int);
extern void blk_put_queue(struct request_queue *);
/*
* block layer runtime pm functions
*/
#ifdef CONFIG_PM_RUNTIME
extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
extern int blk_pre_runtime_suspend(struct request_queue *q);
extern void blk_post_runtime_suspend(struct request_queue *q, int err);
extern void blk_pre_runtime_resume(struct request_queue *q);
extern void blk_post_runtime_resume(struct request_queue *q, int err);
#else
static inline void blk_pm_runtime_init(struct request_queue *q,
struct device *dev) {}
static inline int blk_pre_runtime_suspend(struct request_queue *q)
{
return -ENOSYS;
}
static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
static inline void blk_pre_runtime_resume(struct request_queue *q) {}
static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
#endif
/*
* blk_plug permits building a queue of related requests by holding the I/O
* fragments for a short period. This allows merging of sequential requests
* into single larger request. As the requests are moved from a per-task list to
* the device's request_queue in a batch, this results in improved scalability
* as the lock contention for request_queue lock is reduced.
*
* It is ok not to disable preemption when adding the request to the plug list
* or when attempting a merge, because blk_schedule_flush_list() will only flush
* the plug list when the task sleeps by itself. For details, please see
* schedule() where blk_schedule_flush_plug() is called.
*/
struct blk_plug {
unsigned long magic; /* detect uninitialized use-cases */
struct list_head list; /* requests */
struct list_head cb_list; /* md requires an unplug callback */
};
#define BLK_MAX_REQUEST_COUNT 16
struct blk_plug_cb;
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
struct blk_plug_cb {
struct list_head list;
blk_plug_cb_fn callback;
void *data;
};
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
void *data, int size);
extern void blk_start_plug(struct blk_plug *);
extern void blk_finish_plug(struct blk_plug *);
extern void blk_flush_plug_list(struct blk_plug *, bool);
static inline void blk_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
if (plug)
blk_flush_plug_list(plug, false);
}
static inline void blk_schedule_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
if (plug)
blk_flush_plug_list(plug, true);
}
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
return plug && (!list_empty(&plug->list) || !list_empty(&plug->cb_list));
}
/*
* tag stuff
*/
#define blk_rq_tagged(rq) ((rq)->cmd_flags & REQ_QUEUED)
extern int blk_queue_start_tag(struct request_queue *, struct request *);
extern struct request *blk_queue_find_tag(struct request_queue *, int);
extern void blk_queue_end_tag(struct request_queue *, struct request *);
extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *);
extern void blk_queue_free_tags(struct request_queue *);
extern int blk_queue_resize_tags(struct request_queue *, int);
extern void blk_queue_invalidate_tags(struct request_queue *);
extern struct blk_queue_tag *blk_init_tags(int);
extern void blk_free_tags(struct blk_queue_tag *);
static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
int tag)
{
if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
return NULL;
return bqt->tag_index[tag];
}
#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */
extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct page *page);
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask);
static inline int sb_issue_discard(struct super_block *sb, sector_t block,
sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
{
return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
nr_blocks << (sb->s_blocksize_bits - 9),
gfp_mask, flags);
}
static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
sector_t nr_blocks, gfp_t gfp_mask)
{
return blkdev_issue_zeroout(sb->s_bdev,
block << (sb->s_blocksize_bits - 9),
nr_blocks << (sb->s_blocksize_bits - 9),
gfp_mask);
}
extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
enum blk_default_limits {
BLK_MAX_SEGMENTS = 128,
BLK_SAFE_MAX_SECTORS = 255,
BLK_DEF_MAX_SECTORS = 1024,
BLK_MAX_SEGMENT_SIZE = 65536,
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
};
block: fix setting of max_segment_size and seg_boundary mask Fix setting of max_segment_size and seg_boundary mask for stacked md/dm devices. When stacking devices (LVM over MD over SCSI) some of the request queue parameters are not set up correctly in some cases by default, namely max_segment_size and and seg_boundary mask. If you create MD device over SCSI, these attributes are zeroed. Problem become when there is over this mapping next device-mapper mapping - queue attributes are set in DM this way: request_queue max_segment_size seg_boundary_mask SCSI 65536 0xffffffff MD RAID1 0 0 LVM 65536 -1 (64bit) Unfortunately bio_add_page (resp. bio_phys_segments) calculates number of physical segments according to these parameters. During the generic_make_request() is segment cout recalculated and can increase bio->bi_phys_segments count over the allowed limit. (After bio_clone() in stack operation.) Thi is specially problem in CCISS driver, where it produce OOPS here BUG_ON(creq->nr_phys_segments > MAXSGENTRIES); (MAXSEGENTRIES is 31 by default.) Sometimes even this command is enough to cause oops: dd iflag=direct if=/dev/<vg>/<lv> of=/dev/null bs=128000 count=10 This command generates bios with 250 sectors, allocated in 32 4k-pages (last page uses only 1024 bytes). For LVM layer, it allocates bio with 31 segments (still OK for CCISS), unfortunatelly on lower layer it is recalculated to 32 segments and this violates CCISS restriction and triggers BUG_ON(). The patch tries to fix it by: * initializing attributes above in queue request constructor blk_queue_make_request() * make sure that blk_queue_stack_limits() inherits setting (DM uses its own function to set the limits because it blk_queue_stack_limits() was introduced later. It should probably switch to use generic stack limit function too.) * sets the default seg_boundary value in one place (blkdev.h) * use this mask as default in DM (instead of -1, which differs in 64bit) Bugs related to this: https://bugzilla.redhat.com/show_bug.cgi?id=471639 http://bugzilla.kernel.org/show_bug.cgi?id=8672 Signed-off-by: Milan Broz <mbroz@redhat.com> Reviewed-by: Alasdair G Kergon <agk@redhat.com> Cc: Neil Brown <neilb@suse.de> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Tejun Heo <htejun@gmail.com> Cc: Mike Miller <mike.miller@hp.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-03 19:55:08 +08:00
#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
static inline unsigned long queue_bounce_pfn(struct request_queue *q)
{
return q->limits.bounce_pfn;
}
static inline unsigned long queue_segment_boundary(struct request_queue *q)
{
return q->limits.seg_boundary_mask;
}
static inline unsigned int queue_max_sectors(struct request_queue *q)
{
return q->limits.max_sectors;
}
static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
{
return q->limits.max_hw_sectors;
}
static inline unsigned short queue_max_segments(struct request_queue *q)
{
return q->limits.max_segments;
}
static inline unsigned int queue_max_segment_size(struct request_queue *q)
{
return q->limits.max_segment_size;
}
static inline unsigned short queue_logical_block_size(struct request_queue *q)
{
int retval = 512;
if (q && q->limits.logical_block_size)
retval = q->limits.logical_block_size;
return retval;
}
static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
{
return queue_logical_block_size(bdev_get_queue(bdev));
}
static inline unsigned int queue_physical_block_size(struct request_queue *q)
{
return q->limits.physical_block_size;
}
static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
{
return queue_physical_block_size(bdev_get_queue(bdev));
}
static inline unsigned int queue_io_min(struct request_queue *q)
{
return q->limits.io_min;
}
static inline int bdev_io_min(struct block_device *bdev)
{
return queue_io_min(bdev_get_queue(bdev));
}
static inline unsigned int queue_io_opt(struct request_queue *q)
{
return q->limits.io_opt;
}
static inline int bdev_io_opt(struct block_device *bdev)
{
return queue_io_opt(bdev_get_queue(bdev));
}
static inline int queue_alignment_offset(struct request_queue *q)
{
if (q->limits.misaligned)
return -1;
return q->limits.alignment_offset;
}
static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
{
unsigned int granularity = max(lim->physical_block_size, lim->io_min);
unsigned int alignment = (sector << 9) & (granularity - 1);
return (granularity + lim->alignment_offset - alignment)
& (granularity - 1);
}
static inline int bdev_alignment_offset(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q->limits.misaligned)
return -1;
if (bdev != bdev->bd_contains)
return bdev->bd_part->alignment_offset;
return q->limits.alignment_offset;
}
static inline int queue_discard_alignment(struct request_queue *q)
{
if (q->limits.discard_misaligned)
return -1;
return q->limits.discard_alignment;
}
static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
{
blk: avoid divide-by-zero with zero discard granularity Commit 8dd2cb7e880d ("block: discard granularity might not be power of 2") changed a couple of 'binary and' operations into modulus operations. Which turned the harmless case of a zero discard_granularity into a possible divide-by-zero. The code also had a much more subtle bug: it was doing the modulus of a value in bytes using 'sector_t'. That was always conceptually wrong, but didn't actually matter back when the code assumed a power-of-two granularity: we only looked at the low bits anyway. But with potentially arbitrary sector numbers, using a 'sector_t' to express bytes is very very wrong: depending on configuration it limits the starting offset of the device to just 32 bits, and any overflow would result in a wrong value if the modulus wasn't a power-of-two. So re-write the code to not only protect against the divide-by-zero, but to do the starting sector arithmetic in sectors, and using the proper types. [ For any mathematicians out there: it also looks monumentally stupid to do the 'modulo granularity' operation *twice*, never mind having a "+ granularity" in the second modulus op. But that's the easiest way to avoid negative values or overflow, and it is how the original code was done. ] Reported-by: Ingo Molnar <mingo@kernel.org> Reported-by: Doug Anderson <dianders@chromium.org> Cc: Neil Brown <neilb@suse.de> Cc: Shaohua Li <shli@fusionio.com> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-19 23:18:35 +08:00
unsigned int alignment, granularity, offset;
if (!lim->max_discard_sectors)
return 0;
blk: avoid divide-by-zero with zero discard granularity Commit 8dd2cb7e880d ("block: discard granularity might not be power of 2") changed a couple of 'binary and' operations into modulus operations. Which turned the harmless case of a zero discard_granularity into a possible divide-by-zero. The code also had a much more subtle bug: it was doing the modulus of a value in bytes using 'sector_t'. That was always conceptually wrong, but didn't actually matter back when the code assumed a power-of-two granularity: we only looked at the low bits anyway. But with potentially arbitrary sector numbers, using a 'sector_t' to express bytes is very very wrong: depending on configuration it limits the starting offset of the device to just 32 bits, and any overflow would result in a wrong value if the modulus wasn't a power-of-two. So re-write the code to not only protect against the divide-by-zero, but to do the starting sector arithmetic in sectors, and using the proper types. [ For any mathematicians out there: it also looks monumentally stupid to do the 'modulo granularity' operation *twice*, never mind having a "+ granularity" in the second modulus op. But that's the easiest way to avoid negative values or overflow, and it is how the original code was done. ] Reported-by: Ingo Molnar <mingo@kernel.org> Reported-by: Doug Anderson <dianders@chromium.org> Cc: Neil Brown <neilb@suse.de> Cc: Shaohua Li <shli@fusionio.com> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-19 23:18:35 +08:00
/* Why are these in bytes, not sectors? */
alignment = lim->discard_alignment >> 9;
granularity = lim->discard_granularity >> 9;
if (!granularity)
return 0;
/* Offset of the partition start in 'granularity' sectors */
offset = sector_div(sector, granularity);
/* And why do we do this modulus *again* in blkdev_issue_discard()? */
offset = (granularity + alignment - offset) % granularity;
/* Turn it back into bytes, gaah */
return offset << 9;
}
static inline int bdev_discard_alignment(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (bdev != bdev->bd_contains)
return bdev->bd_part->discard_alignment;
return q->limits.discard_alignment;
}
static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
{
if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
return 1;
return 0;
}
static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
{
return queue_discard_zeroes_data(bdev_get_queue(bdev));
}
static inline unsigned int bdev_write_same(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
return q->limits.max_write_same_sectors;
return 0;
}
static inline int queue_dma_alignment(struct request_queue *q)
{
return q ? q->dma_alignment : 511;
}
static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
unsigned int len)
{
unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
return !(addr & alignment) && !(len & alignment);
}
/* assumes size > 256 */
static inline unsigned int blksize_bits(unsigned int size)
{
unsigned int bits = 8;
do {
bits++;
size >>= 1;
} while (size > 256);
return bits;
}
static inline unsigned int block_size(struct block_device *bdev)
{
return bdev->bd_block_size;
}
static inline bool queue_flush_queueable(struct request_queue *q)
{
return !q->flush_not_queueable;
}
typedef struct {struct page *v;} Sector;
unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);
static inline void put_dev_sector(Sector p)
{
page_cache_release(p.v);
}
struct work_struct;
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
#ifdef CONFIG_BLK_CGROUP
/*
* This should not be using sched_clock(). A real patch is in progress
* to fix this up, until that is in place we need to disable preemption
* around sched_clock() in this function and set_io_start_time_ns().
*/
static inline void set_start_time_ns(struct request *req)
{
preempt_disable();
req->start_time_ns = sched_clock();
preempt_enable();
}
static inline void set_io_start_time_ns(struct request *req)
{
preempt_disable();
req->io_start_time_ns = sched_clock();
preempt_enable();
}
2010-04-09 14:31:19 +08:00
static inline uint64_t rq_start_time_ns(struct request *req)
{
return req->start_time_ns;
}
static inline uint64_t rq_io_start_time_ns(struct request *req)
{
return req->io_start_time_ns;
}
#else
static inline void set_start_time_ns(struct request *req) {}
static inline void set_io_start_time_ns(struct request *req) {}
2010-04-09 14:31:19 +08:00
static inline uint64_t rq_start_time_ns(struct request *req)
{
return 0;
}
static inline uint64_t rq_io_start_time_ns(struct request *req)
{
return 0;
}
#endif
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
MODULE_ALIAS("block-major-" __stringify(major) "-*")
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define INTEGRITY_FLAG_READ 2 /* verify data integrity on read */
#define INTEGRITY_FLAG_WRITE 4 /* generate data integrity on write */
struct blk_integrity_exchg {
void *prot_buf;
void *data_buf;
sector_t sector;
unsigned int data_size;
unsigned short sector_size;
const char *disk_name;
};
typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);
struct blk_integrity {
integrity_gen_fn *generate_fn;
integrity_vrfy_fn *verify_fn;
integrity_set_tag_fn *set_tag_fn;
integrity_get_tag_fn *get_tag_fn;
unsigned short flags;
unsigned short tuple_size;
unsigned short sector_size;
unsigned short tag_size;
const char *name;
struct kobject kobj;
};
extern bool blk_integrity_is_initialized(struct gendisk *);
extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
extern void blk_integrity_unregister(struct gendisk *);
extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
struct scatterlist *);
extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
extern int blk_integrity_merge_rq(struct request_queue *, struct request *,
struct request *);
extern int blk_integrity_merge_bio(struct request_queue *, struct request *,
struct bio *);
static inline
struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
{
return bdev->bd_disk->integrity;
}
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
{
return disk->integrity;
}
static inline int blk_integrity_rq(struct request *rq)
{
if (rq->bio == NULL)
return 0;
return bio_integrity(rq->bio);
}
static inline void blk_queue_max_integrity_segments(struct request_queue *q,
unsigned int segs)
{
q->limits.max_integrity_segments = segs;
}
static inline unsigned short
queue_max_integrity_segments(struct request_queue *q)
{
return q->limits.max_integrity_segments;
}
#else /* CONFIG_BLK_DEV_INTEGRITY */
struct bio;
struct block_device;
struct gendisk;
struct blk_integrity;
static inline int blk_integrity_rq(struct request *rq)
{
return 0;
}
static inline int blk_rq_count_integrity_sg(struct request_queue *q,
struct bio *b)
{
return 0;
}
static inline int blk_rq_map_integrity_sg(struct request_queue *q,
struct bio *b,
struct scatterlist *s)
{
return 0;
}
static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
{
return 0;
}
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
{
return NULL;
}
static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
{
return 0;
}
static inline int blk_integrity_register(struct gendisk *d,
struct blk_integrity *b)
{
return 0;
}
static inline void blk_integrity_unregister(struct gendisk *d)
{
}
static inline void blk_queue_max_integrity_segments(struct request_queue *q,
unsigned int segs)
{
}
static inline unsigned short queue_max_integrity_segments(struct request_queue *q)
{
return 0;
}
static inline int blk_integrity_merge_rq(struct request_queue *rq,
struct request *r1,
struct request *r2)
{
return 0;
}
static inline int blk_integrity_merge_bio(struct request_queue *rq,
struct request *r,
struct bio *b)
{
return 0;
}
static inline bool blk_integrity_is_initialized(struct gendisk *g)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
struct block_device_operations {
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*direct_access) (struct block_device *, sector_t,
void **, unsigned long *);
implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-12-09 03:57:37 +08:00
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
int (*media_changed) (struct gendisk *);
void (*unlock_native_capacity) (struct gendisk *);
int (*revalidate_disk) (struct gendisk *);
int (*getgeo)(struct block_device *, struct hd_geometry *);
/* this callback is with swap_lock and sometimes page table lock held */
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
struct module *owner;
};
extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
unsigned long);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#else /* CONFIG_BLOCK */
/*
* stubs for when the block layer is configured out
*/
#define buffer_heads_over_limit 0
static inline long nr_blockdev_pages(void)
{
return 0;
}
struct blk_plug {
};
static inline void blk_start_plug(struct blk_plug *plug)
{
}
static inline void blk_finish_plug(struct blk_plug *plug)
{
}
static inline void blk_flush_plug(struct task_struct *task)
{
}
static inline void blk_schedule_flush_plug(struct task_struct *task)
{
}
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
return false;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif /* CONFIG_BLOCK */
#endif