WSL2-Linux-Kernel/include/linux/bio.h

795 строки
20 KiB
C
Исходник Обычный вид История

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2001 Jens Axboe <axboe@suse.de>
*/
#ifndef __LINUX_BIO_H
#define __LINUX_BIO_H
#include <linux/mempool.h>
#include <linux/ioprio.h>
/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
#include <linux/blk_types.h>
#include <linux/uio.h>
#define BIO_DEBUG
#ifdef BIO_DEBUG
#define BIO_BUG_ON BUG_ON
#else
#define BIO_BUG_ON
#endif
#define BIO_MAX_VECS 256U
static inline unsigned int bio_max_segs(unsigned int nr_segs)
{
return min(nr_segs, BIO_MAX_VECS);
}
#define bio_prio(bio) (bio)->bi_ioprio
#define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio)
#define bio_iter_iovec(bio, iter) \
bvec_iter_bvec((bio)->bi_io_vec, (iter))
#define bio_iter_page(bio, iter) \
bvec_iter_page((bio)->bi_io_vec, (iter))
#define bio_iter_len(bio, iter) \
bvec_iter_len((bio)->bi_io_vec, (iter))
#define bio_iter_offset(bio, iter) \
bvec_iter_offset((bio)->bi_io_vec, (iter))
#define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter)
#define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter)
#define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter)
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 05:19:00 +04:00
#define bvec_iter_sectors(iter) ((iter).bi_size >> 9)
#define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter)))
#define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter)
#define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter)
/*
* Return the data direction, READ or WRITE.
*/
#define bio_data_dir(bio) \
(op_is_write(bio_op(bio)) ? WRITE : READ)
/*
* Check whether this bio carries any data or not. A NULL bio is allowed.
*/
static inline bool bio_has_data(struct bio *bio)
{
if (bio &&
bio->bi_iter.bi_size &&
bio_op(bio) != REQ_OP_DISCARD &&
bio_op(bio) != REQ_OP_SECURE_ERASE &&
bio_op(bio) != REQ_OP_WRITE_ZEROES)
return true;
return false;
}
static inline bool bio_no_advance_iter(const struct bio *bio)
{
return bio_op(bio) == REQ_OP_DISCARD ||
bio_op(bio) == REQ_OP_SECURE_ERASE ||
bio_op(bio) == REQ_OP_WRITE_SAME ||
bio_op(bio) == REQ_OP_WRITE_ZEROES;
}
static inline bool bio_mergeable(struct bio *bio)
{
if (bio->bi_opf & REQ_NOMERGE_FLAGS)
return false;
return true;
}
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 17:24:41 +04:00
static inline unsigned int bio_cur_bytes(struct bio *bio)
{
if (bio_has_data(bio))
return bio_iovec(bio).bv_len;
else /* dataless requests such as discard */
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 02:44:27 +04:00
return bio->bi_iter.bi_size;
}
static inline void *bio_data(struct bio *bio)
{
if (bio_has_data(bio))
return page_address(bio_page(bio)) + bio_offset(bio);
return NULL;
}
/**
* bio_full - check if the bio is full
* @bio: bio to check
* @len: length of one segment to be added
*
* Return true if @bio is full and one segment with @len bytes can't be
* added to the bio, otherwise return false
*/
static inline bool bio_full(struct bio *bio, unsigned len)
{
if (bio->bi_vcnt >= bio->bi_max_vecs)
return true;
if (bio->bi_iter.bi_size > UINT_MAX - len)
return true;
return false;
}
static inline bool bio_next_segment(const struct bio *bio,
struct bvec_iter_all *iter)
{
if (iter->idx >= bio->bi_vcnt)
return false;
bvec_advance(&bio->bi_io_vec[iter->idx], iter);
return true;
}
/*
* drivers should _never_ use the all version - the bio may have been split
* before it got to the driver and the driver won't own all of it
*/
#define bio_for_each_segment_all(bvl, bio, iter) \
for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); )
static inline void bio_advance_iter(const struct bio *bio,
struct bvec_iter *iter, unsigned int bytes)
{
iter->bi_sector += bytes >> 9;
if (bio_no_advance_iter(bio))
iter->bi_size -= bytes;
else
bvec_iter_advance(bio->bi_io_vec, iter, bytes);
/* TODO: It is reasonable to complete bio with error here. */
}
/* @bytes should be less or equal to bvec[i->bi_idx].bv_len */
static inline void bio_advance_iter_single(const struct bio *bio,
struct bvec_iter *iter,
unsigned int bytes)
{
iter->bi_sector += bytes >> 9;
if (bio_no_advance_iter(bio))
iter->bi_size -= bytes;
else
bvec_iter_advance_single(bio->bi_io_vec, iter, bytes);
}
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 05:19:00 +04:00
#define __bio_for_each_segment(bvl, bio, iter, start) \
for (iter = (start); \
(iter).bi_size && \
((bvl = bio_iter_iovec((bio), (iter))), 1); \
bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 05:19:00 +04:00
#define bio_for_each_segment(bvl, bio, iter) \
__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
#define __bio_for_each_bvec(bvl, bio, iter, start) \
for (iter = (start); \
(iter).bi_size && \
((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \
bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
/* iterate over multi-page bvec */
#define bio_for_each_bvec(bvl, bio, iter) \
__bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter)
/*
* Iterate over all multi-page bvecs. Drivers shouldn't use this version for the
* same reasons as bio_for_each_segment_all().
*/
#define bio_for_each_bvec_all(bvl, bio, i) \
for (i = 0, bvl = bio_first_bvec_all(bio); \
i < (bio)->bi_vcnt; i++, bvl++) \
#define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len)
static inline unsigned bio_segments(struct bio *bio)
{
unsigned segs = 0;
struct bio_vec bv;
struct bvec_iter iter;
/*
* We special case discard/write same/write zeroes, because they
* interpret bi_size differently:
*/
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
case REQ_OP_WRITE_ZEROES:
return 0;
case REQ_OP_WRITE_SAME:
return 1;
default:
break;
}
bio_for_each_segment(bv, bio, iter)
segs++;
return segs;
}
/*
* get a reference to a bio, so it won't disappear. the intended use is
* something like:
*
* bio_get(bio);
* submit_bio(rw, bio);
* if (bio->bi_flags ...)
* do_something
* bio_put(bio);
*
* without the bio_get(), it could potentially complete I/O before submit_bio
* returns. and then bio would be freed memory when if (bio->bi_flags ...)
* runs
*/
static inline void bio_get(struct bio *bio)
{
bio->bi_flags |= (1 << BIO_REFFED);
smp_mb__before_atomic();
atomic_inc(&bio->__bi_cnt);
}
static inline void bio_cnt_set(struct bio *bio, unsigned int count)
{
if (count != 1) {
bio->bi_flags |= (1 << BIO_REFFED);
smp_mb();
}
atomic_set(&bio->__bi_cnt, count);
}
static inline bool bio_flagged(struct bio *bio, unsigned int bit)
{
return (bio->bi_flags & (1U << bit)) != 0;
}
static inline void bio_set_flag(struct bio *bio, unsigned int bit)
{
bio->bi_flags |= (1U << bit);
}
static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
{
bio->bi_flags &= ~(1U << bit);
}
static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
{
block: return the correct bvec when checking for gaps After commit 07173c3ec276 ("block: enable multipage bvecs"), a bvec can have multiple pages. But bio_will_gap() still assumes one page bvec while checking for merging. If the pages in the bvec go across the seg_boundary_mask, this check for merging can potentially succeed if only the 1st page is tested, and can fail if all the pages are tested. Later, when SCSI builds the SG list the same check for merging is done in __blk_segment_map_sg_merge() with all the pages in the bvec tested. This time the check may fail if the pages in bvec go across the seg_boundary_mask (but tested okay in bio_will_gap() earlier, so those BIOs were merged). If this check fails, we end up with a broken SG list for drivers assuming the SG list not having offsets in intermediate pages. This results in incorrect pages written to the disk. Fix this by returning the multi-page bvec when testing gaps for merging. Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: Ming Lei <ming.lei@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 07173c3ec276 ("block: enable multipage bvecs") Signed-off-by: Long Li <longli@microsoft.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/1623094445-22332-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-07 22:34:05 +03:00
*bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
}
static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
{
struct bvec_iter iter = bio->bi_iter;
int idx;
block: return the correct bvec when checking for gaps After commit 07173c3ec276 ("block: enable multipage bvecs"), a bvec can have multiple pages. But bio_will_gap() still assumes one page bvec while checking for merging. If the pages in the bvec go across the seg_boundary_mask, this check for merging can potentially succeed if only the 1st page is tested, and can fail if all the pages are tested. Later, when SCSI builds the SG list the same check for merging is done in __blk_segment_map_sg_merge() with all the pages in the bvec tested. This time the check may fail if the pages in bvec go across the seg_boundary_mask (but tested okay in bio_will_gap() earlier, so those BIOs were merged). If this check fails, we end up with a broken SG list for drivers assuming the SG list not having offsets in intermediate pages. This results in incorrect pages written to the disk. Fix this by returning the multi-page bvec when testing gaps for merging. Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: Ming Lei <ming.lei@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 07173c3ec276 ("block: enable multipage bvecs") Signed-off-by: Long Li <longli@microsoft.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/1623094445-22332-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-07 22:34:05 +03:00
bio_get_first_bvec(bio, bv);
if (bv->bv_len == bio->bi_iter.bi_size)
return; /* this bio only has a single bvec */
bio_advance_iter(bio, &iter, iter.bi_size);
if (!iter.bi_bvec_done)
idx = iter.bi_idx - 1;
else /* in the middle of bvec */
idx = iter.bi_idx;
*bv = bio->bi_io_vec[idx];
/*
* iter.bi_bvec_done records actual length of the last bvec
* if this bio ends in the middle of one io vector
*/
if (iter.bi_bvec_done)
bv->bv_len = iter.bi_bvec_done;
}
static inline struct bio_vec *bio_first_bvec_all(struct bio *bio)
{
WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
return bio->bi_io_vec;
}
static inline struct page *bio_first_page_all(struct bio *bio)
{
return bio_first_bvec_all(bio)->bv_page;
}
static inline struct bio_vec *bio_last_bvec_all(struct bio *bio)
{
WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
return &bio->bi_io_vec[bio->bi_vcnt - 1];
}
enum bip_flags {
BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */
BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */
BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */
BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */
BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */
};
/*
* bio integrity payload
*/
struct bio_integrity_payload {
struct bio *bip_bio; /* parent bio */
struct bvec_iter bip_iter;
unsigned short bip_vcnt; /* # of integrity bio_vecs */
unsigned short bip_max_vcnt; /* integrity bio_vec slots */
unsigned short bip_flags; /* control flags */
struct bvec_iter bio_iter; /* for rewinding parent bio */
struct work_struct bip_work; /* I/O completion */
struct bio_vec *bip_vec;
struct bio_vec bip_inline_vecs[];/* embedded bvec array */
};
#if defined(CONFIG_BLK_DEV_INTEGRITY)
static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
{
if (bio->bi_opf & REQ_INTEGRITY)
return bio->bi_integrity;
return NULL;
}
static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
if (bip)
return bip->bip_flags & flag;
return false;
}
static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
{
return bip->bip_iter.bi_sector;
}
static inline void bip_set_seed(struct bio_integrity_payload *bip,
sector_t seed)
{
bip->bip_iter.bi_sector = seed;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
void bio_trim(struct bio *bio, sector_t offset, sector_t size);
extern struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs);
/**
* bio_next_split - get next @sectors from a bio, splitting if necessary
* @bio: bio to split
* @sectors: number of sectors to split from the front of @bio
* @gfp: gfp mask
* @bs: bio set to allocate from
*
* Returns a bio representing the next @sectors of @bio - if the bio is smaller
* than @sectors, returns the original bio unchanged.
*/
static inline struct bio *bio_next_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
{
if (sectors >= bio_sectors(bio))
return bio;
return bio_split(bio, sectors, gfp, bs);
}
enum {
BIOSET_NEED_BVECS = BIT(0),
BIOSET_NEED_RESCUER = BIT(1),
BIOSET_PERCPU_CACHE = BIT(2),
};
extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
extern void bioset_exit(struct bio_set *);
extern int biovec_init_pool(mempool_t *pool, int pool_entries);
extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs,
struct bio_set *bs);
struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
struct bio_set *bs);
struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs);
extern void bio_put(struct bio *);
extern void __bio_clone_fast(struct bio *, struct bio *);
extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
extern struct bio_set fs_bio_set;
static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
{
return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
}
extern blk_qc_t submit_bio(struct bio *);
extern void bio_endio(struct bio *);
static inline void bio_io_error(struct bio *bio)
{
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
}
static inline void bio_wouldblock_error(struct bio *bio)
{
bio_set_flag(bio, BIO_QUIET);
bio->bi_status = BLK_STS_AGAIN;
bio_endio(bio);
}
/*
* Calculate number of bvec segments that should be allocated to fit data
* pointed by @iter. If @iter is backed by bvec it's going to be reused
* instead of allocating a new one.
*/
static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs)
{
if (iov_iter_is_bvec(iter))
return 0;
return iov_iter_npages(iter, max_segs);
}
struct request_queue;
extern int submit_bio_wait(struct bio *bio);
extern void bio_advance(struct bio *, unsigned);
extern void bio_init(struct bio *bio, struct bio_vec *table,
unsigned short max_vecs);
block: provide bio_uninit() free freeing integrity/task associations Wen reports significant memory leaks with DIF and O_DIRECT: "With nvme devive + T10 enabled, On a system it has 256GB and started logging /proc/meminfo & /proc/slabinfo for every minute and in an hour it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute leaking. /proc/meminfo | grep SUnreclaim... SUnreclaim: 6752128 kB SUnreclaim: 6874880 kB SUnreclaim: 7238080 kB .... SUnreclaim: 22307264 kB SUnreclaim: 22485888 kB SUnreclaim: 22720256 kB When testcases with T10 enabled call into __blkdev_direct_IO_simple, code doesn't free memory allocated by bio_integrity_alloc. The patch fixes the issue. HTX has been run with +60 hours without failure." Since __blkdev_direct_IO_simple() allocates the bio on the stack, it doesn't go through the regular bio free. This means that any ancillary data allocated with the bio through the stack is not freed. Hence, we can leak the integrity data associated with the bio, if the device is using DIF/DIX. Fix this by providing a bio_uninit() and export it, so that we can use it to free this data. Note that this is a minimal fix for this issue. Any current user of bio's that are allocated outside of bio_alloc_bioset() suffers from this issue, most notably some drivers. We will fix those in a more comprehensive patch for 4.13. This also means that the commit marked as being fixed by this isn't the real culprit, it's just the most obvious one out there. Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-29 00:30:13 +03:00
extern void bio_uninit(struct bio *);
extern void bio_reset(struct bio *);
void bio_chain(struct bio *, struct bio *);
extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
unsigned int, unsigned int);
int bio_add_zone_append_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset);
bool __bio_try_merge_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int off, bool *same_page);
void __bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int off);
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
void bio_release_pages(struct bio *bio, bool mark_dirty);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
void bio_truncate(struct bio *bio, unsigned new_size);
void guard_bio_eod(struct bio *bio);
void zero_fill_bio(struct bio *bio);
extern const char *bio_devname(struct bio *bio, char *buffer);
#define bio_set_dev(bio, bdev) \
do { \
bio_clear_flag(bio, BIO_REMAPPED); \
if ((bio)->bi_bdev != (bdev)) \
bio_clear_flag(bio, BIO_THROTTLED); \
(bio)->bi_bdev = (bdev); \
bio_associate_blkg(bio); \
} while (0)
#define bio_copy_dev(dst, src) \
do { \
bio_clear_flag(dst, BIO_REMAPPED); \
(dst)->bi_bdev = (src)->bi_bdev; \
bio_clone_blkg_association(dst, src); \
} while (0)
#define bio_dev(bio) \
disk_devt((bio)->bi_bdev->bd_disk)
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-06 01:15:27 +04:00
#ifdef CONFIG_BLK_CGROUP
void bio_associate_blkg(struct bio *bio);
void bio_associate_blkg_from_css(struct bio *bio,
struct cgroup_subsys_state *css);
void bio_clone_blkg_association(struct bio *dst, struct bio *src);
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-06 01:15:27 +04:00
#else /* CONFIG_BLK_CGROUP */
static inline void bio_associate_blkg(struct bio *bio) { }
static inline void bio_associate_blkg_from_css(struct bio *bio,
struct cgroup_subsys_state *css)
{ }
static inline void bio_clone_blkg_association(struct bio *dst,
struct bio *src) { }
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-06 01:15:27 +04:00
#endif /* CONFIG_BLK_CGROUP */
/*
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
*
* A bio_list anchors a singly-linked list of bios chained through the bi_next
* member of the bio. The bio_list also caches the last list member to allow
* fast access to the tail.
*/
struct bio_list {
struct bio *head;
struct bio *tail;
};
static inline int bio_list_empty(const struct bio_list *bl)
{
return bl->head == NULL;
}
static inline void bio_list_init(struct bio_list *bl)
{
bl->head = bl->tail = NULL;
}
blk-mq: new multi-queue block IO queueing mechanism Linux currently has two models for block devices: - The classic request_fn based approach, where drivers use struct request units for IO. The block layer provides various helper functionalities to let drivers share code, things like tag management, timeout handling, queueing, etc. - The "stacked" approach, where a driver squeezes in between the block layer and IO submitter. Since this bypasses the IO stack, driver generally have to manage everything themselves. With drivers being written for new high IOPS devices, the classic request_fn based driver doesn't work well enough. The design dates back to when both SMP and high IOPS was rare. It has problems with scaling to bigger machines, and runs into scaling issues even on smaller machines when you have IOPS in the hundreds of thousands per device. The stacked approach is then most often selected as the model for the driver. But this means that everybody has to re-invent everything, and along with that we get all the problems again that the shared approach solved. This commit introduces blk-mq, block multi queue support. The design is centered around per-cpu queues for queueing IO, which then funnel down into x number of hardware submission queues. We might have a 1:1 mapping between the two, or it might be an N:M mapping. That all depends on what the hardware supports. blk-mq provides various helper functions, which include: - Scalable support for request tagging. Most devices need to be able to uniquely identify a request both in the driver and to the hardware. The tagging uses per-cpu caches for freed tags, to enable cache hot reuse. - Timeout handling without tracking request on a per-device basis. Basically the driver should be able to get a notification, if a request happens to fail. - Optional support for non 1:1 mappings between issue and submission queues. blk-mq can redirect IO completions to the desired location. - Support for per-request payloads. Drivers almost always need to associate a request structure with some driver private command structure. Drivers can tell blk-mq this at init time, and then any request handed to the driver will have the required size of memory associated with it. - Support for merging of IO, and plugging. The stacked model gets neither of these. Even for high IOPS devices, merging sequential IO reduces per-command overhead and thus increases bandwidth. For now, this is provided as a potential 3rd queueing model, with the hope being that, as it matures, it can replace both the classic and stacked model. That would get us back to having just 1 real model for block devices, leaving the stacked approach to dm/md devices (as it was originally intended). Contributions in this patch from the following people: Shaohua Li <shli@fusionio.com> Alexander Gordeev <agordeev@redhat.com> Christoph Hellwig <hch@infradead.org> Mike Christie <michaelc@cs.wisc.edu> Matias Bjorling <m@bjorling.me> Jeff Moyer <jmoyer@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 12:20:05 +04:00
#define BIO_EMPTY_LIST { NULL, NULL }
#define bio_list_for_each(bio, bl) \
for (bio = (bl)->head; bio; bio = bio->bi_next)
static inline unsigned bio_list_size(const struct bio_list *bl)
{
unsigned sz = 0;
struct bio *bio;
bio_list_for_each(bio, bl)
sz++;
return sz;
}
static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
{
bio->bi_next = NULL;
if (bl->tail)
bl->tail->bi_next = bio;
else
bl->head = bio;
bl->tail = bio;
}
static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
{
bio->bi_next = bl->head;
bl->head = bio;
if (!bl->tail)
bl->tail = bio;
}
static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
{
if (!bl2->head)
return;
if (bl->tail)
bl->tail->bi_next = bl2->head;
else
bl->head = bl2->head;
bl->tail = bl2->tail;
}
static inline void bio_list_merge_head(struct bio_list *bl,
struct bio_list *bl2)
{
if (!bl2->head)
return;
if (bl->head)
bl2->tail->bi_next = bl->head;
else
bl->tail = bl2->tail;
bl->head = bl2->head;
}
static inline struct bio *bio_list_peek(struct bio_list *bl)
{
return bl->head;
}
static inline struct bio *bio_list_pop(struct bio_list *bl)
{
struct bio *bio = bl->head;
if (bio) {
bl->head = bl->head->bi_next;
if (!bl->head)
bl->tail = NULL;
bio->bi_next = NULL;
}
return bio;
}
static inline struct bio *bio_list_get(struct bio_list *bl)
{
struct bio *bio = bl->head;
bl->head = bl->tail = NULL;
return bio;
}
/*
* Increment chain count for the bio. Make sure the CHAIN flag update
* is visible before the raised count.
*/
static inline void bio_inc_remaining(struct bio *bio)
{
bio_set_flag(bio, BIO_CHAIN);
smp_mb__before_atomic();
atomic_inc(&bio->__bi_remaining);
}
/*
* bio_set is used to allow other portions of the IO system to
* allocate their own private memory pools for bio and iovec structures.
* These memory pools in turn all allocate from the bio_slab
* and the bvec_slabs[].
*/
#define BIO_POOL_SIZE 2
struct bio_set {
struct kmem_cache *bio_slab;
unsigned int front_pad;
/*
* per-cpu bio alloc cache
*/
struct bio_alloc_cache __percpu *cache;
mempool_t bio_pool;
mempool_t bvec_pool;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
mempool_t bio_integrity_pool;
mempool_t bvec_integrity_pool;
#endif
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-11 01:33:46 +04:00
unsigned int back_pad;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-11 01:33:46 +04:00
/*
* Deadlock avoidance for stacking block drivers: see comments in
* bio_alloc_bioset() for details
*/
spinlock_t rescue_lock;
struct bio_list rescue_list;
struct work_struct rescue_work;
struct workqueue_struct *rescue_workqueue;
/*
* Hot un-plug notifier for the per-cpu cache, if used
*/
struct hlist_node cpuhp_dead;
};
static inline bool bioset_initialized(struct bio_set *bs)
{
return bs->bio_slab != NULL;
}
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define bip_for_each_vec(bvl, bip, iter) \
for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \
for_each_bio(_bio) \
bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
extern bool bio_integrity_prep(struct bio *);
extern void bio_integrity_advance(struct bio *, unsigned int);
extern void bio_integrity_trim(struct bio *);
extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
extern int bioset_integrity_create(struct bio_set *, int);
extern void bioset_integrity_free(struct bio_set *);
extern void bio_integrity_init(void);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline void *bio_integrity(struct bio *bio)
{
return NULL;
}
static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
{
return 0;
}
static inline void bioset_integrity_free (struct bio_set *bs)
{
return;
}
static inline bool bio_integrity_prep(struct bio *bio)
{
return true;
}
static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
gfp_t gfp_mask)
{
return 0;
}
static inline void bio_integrity_advance(struct bio *bio,
unsigned int bytes_done)
{
return;
}
static inline void bio_integrity_trim(struct bio *bio)
{
return;
}
static inline void bio_integrity_init(void)
{
return;
}
static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
{
return false;
}
static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp,
unsigned int nr)
{
return ERR_PTR(-EINVAL);
}
static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
/*
* Mark a bio as polled. Note that for async polled IO, the caller must
* expect -EWOULDBLOCK if we cannot allocate a request (or other resources).
* We cannot block waiting for requests on polled IO, as those completions
* must be found by the caller. This is different than IRQ driven IO, where
* it's safe to wait for IO to complete.
*/
static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
{
bio->bi_opf |= REQ_HIPRI;
if (!is_sync_kiocb(kiocb))
bio->bi_opf |= REQ_NOWAIT;
}
struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
#endif /* __LINUX_BIO_H */