block bits for 2.6.30-rc3
Subsystems (3)
Hi Linus,
A collection of fixes for 2.6.30-rc3. It includes fixes for regressions and bug fixes in general, along with two buglets in CFQ. Please pull.
git://git.kernel.dk/linux-2.6-block.git for-linus
Alexander Beregalov (1):
pktcdvd.h should include mempool.h
Bartlomiej Zolnierkiewicz (1):
block: enable by default support for large devices and files on 32-bit archs
Jeff Moyer (2):
cfq-iosched: make seek_mean converge more quickly
cfq-iosched: use the default seek distance when there aren't enough seek samples
Jens Axboe (1):
block: make blk_abort_queue() ignore non-request based devices
Jerome Marchand (1):
block: simplify I/O stat accounting
Tejun Heo (6):
scatterlist: make sure sg_miter_next() doesn't return 0 sized mappings
block: fix SG_IO vector request data length handling
block: fix queue bounce limit setting
bio: fix bio_kmalloc()
bio: use bio_kmalloc() in copy/map functions
block: include empty disks in /proc/diskstats
block/Kconfig | 11 +++-- block/blk-core.c | 6 ++- block/blk-merge.c | 5 ++- block/blk-settings.c | 20 ++++--- block/blk-sysfs.c | 4 -- block/blk-timeout.c | 6 ++ block/blk.h | 7 +-- block/cfq-iosched.c | 15 +++-- block/genhd.c | 12 +++-- block/scsi_ioctl.c | 13 +++++- fs/bio.c | 124 +++++++++++++++++++++------------------------- include/linux/bio.h | 1 + include/linux/blkdev.h | 3 + include/linux/genhd.h | 1 + include/linux/pktcdvd.h | 1 + lib/scatterlist.c | 9 ++- 16 files changed, 131 insertions(+), 107 deletions(-)
block/Kconfig +7 -4
@@ -26,6 +26,7 @@ if BLOCK config LBD bool "Support for large block devices and files" depends on !64BIT + default y help Enable block devices or files of size 2TB and larger.
@@ -38,11 +39,13 @@ config LBD The ext4 filesystem requires that this feature be enabled in order to support filesystems that have the huge_file feature - enabled. Otherwise, it will refuse to mount any filesystems - that use the huge_file feature, which is enabled by default - by mke2fs.ext4. The GFS2 filesystem also requires this feature. + enabled. Otherwise, it will refuse to mount in the read-write + mode any filesystems that use the huge_file feature, which is + enabled by default by mke2fs.ext4. - If unsure, say N. + The GFS2 filesystem also requires this feature. + + If unsure, say Y. config BLK_DEV_BSG bool "Block layer SG support v4 (EXPERIMENTAL)"
block/blk-core.c +4 -2
@@ -643,7 +643,7 @@ static inline void blk_free_request(struct request_queue *q, struct request *rq) }static struct request * -blk_alloc_request (struct request_queue *q,int rw,int priv,gfp_t gfp_mask) +blk_alloc_request (struct request_queue *q,int flags,int priv,gfp_t gfp_mask) {struct request *rq =mempool_alloc (q->rq.rq_pool, gfp_mask);
@@ -652,7 +652,7 @@ blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)blk_rq_init (q, rq); - rq->cmd_flags = rw |REQ_ALLOCED ; + rq->cmd_flags = flags |REQ_ALLOCED ;if (priv) {if (unlikely (elv_set_request (q, rq, gfp_mask))) {
@@ -792,6 +792,8 @@ static struct request *get_request(struct request_queue *q, int rw_flags,if (priv) rl->elvpriv++; +if (blk_queue_io_stat (q)) + rw_flags |=REQ_IO_STAT ;spin_unlock_irq (q->queue_lock); rq =blk_alloc_request (q, rw_flags, priv, gfp_mask);
block/blk-merge.c +4 -1
@@ -402,7 +402,10 @@ static int attempt_merge(struct request_queue *q, struct request *req,elv_merge_requests (q, req, next); -blk_account_io_merge (req); +/* +* 'next' is going away, so update stats accordingly +*/ +blk_account_io_merge (next); req->ioprio =ioprio_best (req->ioprio, next->ioprio);if (blk_rq_cpu_valid (next))
block/blk-settings.c +11 -9
@@ -156,26 +156,28 @@ EXPORT_SYMBOL(blk_queue_make_request);/** * blk_queue_bounce_limit - set bounce buffer limit for queue -* @q: the request queue for the device -* @dma_addr: bus address limit +* @q: the request queue for the device +* @dma_mask: the maximum address the device can handle * * Description: * Different hardware can have different requirements as to what pages * it can do I/O directly to. A low level driver can call * blk_queue_bounce_limit to have lower memory pages allocated as bounce -* buffers for doing I/O to pages residing above @dma_addr. +* buffers for doing I/O to pages residing above @dma_mask. **/ -void blk_queue_bounce_limit (struct request_queue *q,u64 dma_addr) +void blk_queue_bounce_limit (struct request_queue *q,u64 dma_mask) { -unsigned long b_pfn = dma_addr >>PAGE_SHIFT ; +unsigned long b_pfn = dma_mask >>PAGE_SHIFT ;int dma =0 ; q->bounce_gfp =GFP_NOIO ;#if BITS_PER_LONG ==64 -/* Assume anything <= 4GB can be handled by IOMMU. -Actually some IOMMUs can handle everything, but I don't -know of a way to test this here. */ -if (b_pfn < (min_t (u64,0x100000000UL ,BLK_BOUNCE_HIGH ) >>PAGE_SHIFT )) +/* +* Assume anything <= 4GB can be handled by IOMMU. Actually +* some IOMMUs can handle everything, but I don't know of a +* way to test this here. +*/ +if (b_pfn < (min_t (u64,0xffffffffUL ,BLK_BOUNCE_HIGH ) >>PAGE_SHIFT )) dma =1 ; q->bounce_pfn = max_low_pfn;#else
block/blk-sysfs.c +0 -4
@@ -209,14 +209,10 @@ static ssize_t queue_iostats_store(struct request_queue *q, const char *page,ssize_t ret =queue_var_store (&stats, page, count);spin_lock_irq (q->queue_lock); -elv_quiesce_start (q); -if (stats)queue_flag_set (QUEUE_FLAG_IO_STAT , q);else queue_flag_clear (QUEUE_FLAG_IO_STAT , q); - -elv_quiesce_end (q);spin_unlock_irq (q->queue_lock);return ret;
block/blk-timeout.c +6 -0
@@ -211,6 +211,12 @@ void blk_abort_queue(struct request_queue *q)struct request *rq, *tmp;LIST_HEAD (list); +/* +* Not a request based block device, nothing to abort +*/ +if (!q->request_fn) +return ; +spin_lock_irqsave (q->queue_lock, flags);elv_abort_queue (q);
block/blk.h +1 -6
@@ -114,12 +114,7 @@ static inline int blk_cpu_to_group(int cpu)static inline int blk_do_io_stat (struct request *rq) { -struct gendisk *disk = rq->rq_disk; - -if (!disk || !disk->queue) -return 0 ; - -return blk_queue_io_stat (disk->queue) && (rq->cmd_flags &REQ_ELVPRIV ); +return rq->rq_disk &&blk_rq_io_stat (rq); }#endif
block/cfq-iosched.c +9 -6
@@ -947,14 +947,18 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,return cfqd->last_position - rq->sector; } +#define CIC_SEEK_THR 8 * 1024 +#define CIC_SEEKY (cic) ((cic)->seek_mean > CIC_SEEK_THR) +static inline int cfq_rq_close (struct cfq_data *cfqd,struct request *rq) {struct cfq_io_context *cic = cfqd->active_cic; +sector_t sdist = cic->seek_mean;if (!sample_valid (cic->seek_samples)) -return 0 ; + sdist =CIC_SEEK_THR ; -return cfq_dist_from_last (cfqd, rq) <= cic->seek_mean; +return cfq_dist_from_last (cfqd, rq) <= sdist; } static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1039,9 +1043,6 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,return cfqq; } - -#define CIC_SEEKY (cic) ((cic)->seek_mean > (8 * 1024)) -static void cfq_arm_slice_timer (struct cfq_data *cfqd) {struct cfq_queue *cfqq = cfqd->active_queue;
@@ -1908,7 +1909,9 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,sector_t sdist;u64 total; -if (cic->last_request_pos < rq->sector) +if (!cic->last_request_pos) + sdist =0 ; +else if (cic->last_request_pos < rq->sector) sdist = rq->sector - cic->last_request_pos;else sdist = cic->last_request_pos - rq->sector;
block/genhd.c +8 -4
@@ -98,7 +98,7 @@ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,if (flags &DISK_PITER_REVERSE ) piter->idx = ptbl->len -1 ; -else if (flags &DISK_PITER_INCL_PART0 ) +else if (flags & (DISK_PITER_INCL_PART0 |DISK_PITER_INCL_EMPTY_PART0 )) piter->idx =0 ;else piter->idx =1 ;
@@ -134,7 +134,8 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)/* determine iteration parameters */ if (piter->flags &DISK_PITER_REVERSE ) { inc =-1 ; -if (piter->flags &DISK_PITER_INCL_PART0 ) +if (piter->flags & (DISK_PITER_INCL_PART0 | +DISK_PITER_INCL_EMPTY_PART0 )) end =-1 ;else end =0 ;
@@ -150,7 +151,10 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) part =rcu_dereference (ptbl->part[piter->idx]);if (!part)continue ; -if (!(piter->flags &DISK_PITER_INCL_EMPTY ) && !part->nr_sects) +if (!part->nr_sects && + !(piter->flags &DISK_PITER_INCL_EMPTY ) && + !(piter->flags &DISK_PITER_INCL_EMPTY_PART0 && + piter->idx ==0 ))continue ;get_device (part_to_dev (part));
@@ -1011,7 +1015,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)"\n\n"); */ -disk_part_iter_init (&piter, gp,DISK_PITER_INCL_PART0 ); +disk_part_iter_init (&piter, gp,DISK_PITER_INCL_EMPTY_PART0 );while ((hd =disk_part_iter_next (&piter))) { cpu =part_stat_lock ();part_round_stats (cpu, hd);
block/scsi_ioctl.c +12 -1
@@ -290,6 +290,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,if (hdr->iovec_count) {const int size =sizeof (struct sg_iovec ) * hdr->iovec_count; +size_t iov_data_len;struct sg_iovec *iov; iov =kmalloc (size,GFP_KERNEL );
@@ -304,8 +305,18 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, goto out; } +/* SG_IO howto says that the shorter of the two wins */ + iov_data_len =iov_length ((struct iovec *)iov, + hdr->iovec_count); +if (hdr->dxfer_len < iov_data_len) { + hdr->iovec_count =iov_shorten ((struct iovec *)iov, + hdr->iovec_count, + hdr->dxfer_len); + iov_data_len = hdr->dxfer_len; + } + ret =blk_rq_map_user_iov (q, rq,NULL , iov, hdr->iovec_count, - hdr->dxfer_len,GFP_KERNEL ); + iov_data_len,GFP_KERNEL );kfree (iov); }else if (hdr->dxfer_len) ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,
fs/bio.c +57 -67
185 lines not on this page · raw message
include/linux/bio.h +1 -0
@@ -132,6 +132,7 @@ struct bio {* top 4 bits of bio flags indicate the pool this bio came from */ #define BIO_POOL_BITS (4) +#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1)#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS)#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET)#define BIO_POOL_IDX (bio) ((bio)->bi_flags >> BIO_POOL_OFFSET)
include/linux/blkdev.h +3 -0
@@ -118,6 +118,7 @@ enum rq_flag_bits { __REQ_COPY_USER,/* contains copies of user pages */ __REQ_INTEGRITY,/* integrity metadata has been remapped */ __REQ_NOIDLE,/* Don't anticipate more IO after this one */ + __REQ_IO_STAT,/* account I/O stat */ __REQ_NR_BITS, /* stops here */ };
@@ -145,6 +146,7 @@ enum rq_flag_bits {#define REQ_COPY_USER (1 << __REQ_COPY_USER)#define REQ_INTEGRITY (1 << __REQ_INTEGRITY)#define REQ_NOIDLE (1 << __REQ_NOIDLE) +#define REQ_IO_STAT (1 << __REQ_IO_STAT)#define BLK_MAX_CDB 16
@@ -598,6 +600,7 @@ enum { blk_failfast_transport(rq) || \ blk_failfast_driver(rq))#define blk_rq_started (rq) ((rq)->cmd_flags & REQ_STARTED) +#define blk_rq_io_stat (rq) ((rq)->cmd_flags & REQ_IO_STAT)#define blk_account_rq (rq) (blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq)))
include/linux/genhd.h +1 -0
@@ -214,6 +214,7 @@ static inline void disk_put_part(struct hd_struct *part)#define DISK_PITER_REVERSE (1 << 0)/* iterate in the reverse direction */ #define DISK_PITER_INCL_EMPTY (1 << 1)/* include 0-sized parts */ #define DISK_PITER_INCL_PART0 (1 << 2)/* include partition 0 */ +#define DISK_PITER_INCL_EMPTY_PART0 (1 << 3)/* include empty partition 0 */ struct disk_part_iter {struct gendisk *disk;
include/linux/pktcdvd.h +1 -0
@@ -113,6 +113,7 @@ struct pkt_ctrl_command {#include <linux/cdrom.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/mempool.h> /* default bio write queue congestion marks */ #define PKT_WRITE_CONGESTION_ON 10000
lib/scatterlist.c +6 -3
@@ -347,9 +347,12 @@ bool sg_miter_next(struct sg_mapping_iter *miter)sg_miter_stop (miter);/* get to the next sg if necessary. __offset is adjusted by stop */ -if (miter->__offset == miter->__sg->length && --miter->__nents) { - miter->__sg =sg_next (miter->__sg); - miter->__offset =0 ; +while (miter->__offset == miter->__sg->length) { +if (--miter->__nents) { + miter->__sg =sg_next (miter->__sg); + miter->__offset =0 ; + }else +return false; }/* map the next page */
Signature · 1 line
Jens Axboe
Hello,
Quoted 3 lines
A collection of fixes for 2.6.30-rc3. It includes fixes for regressions and bug fixes in general, along with two buglets in CFQ. Please pull.
What about this bug in CFQ: http://lkml.org/lkml/2009/4/20/68 ?
Do you plan to have it fixed for 2.6.30 or will it wait until 2.6.31?
Thanks,
Signature · 1 line
Damien
Quoted 9 lines · Damien Wyart
Hello,
Quoted 3 lines
A collection of fixes for 2.6.30-rc3. It includes fixes for regressions and bug fixes in general, along with two buglets in CFQ. Please pull.
What about this bug in CFQ: http://lkml.org/lkml/2009/4/20/68 ?
Do you plan to have it fixed for 2.6.30 or will it wait until 2.6.31?
Not sure. In theory we could just do the one-liner and make ->slice_resid negative (like below), but it needs some targetted testing. And given that it's been there for several releases, it's not really a rush to get it fixed for 2.6.30.
But I'll definitely throw it into the testing mix, and if deemed safe enough, get it in there for 2.6.30.
block/cfq-iosched.c +1 -1
@@ -887,7 +887,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,* store what was left of this slice, if the queue idled/timed out */ if (timed_out && !cfq_cfqq_slice_new (cfqq)) { - cfqq->slice_resid = cfqq->slice_end - jiffies; + cfqq->slice_resid = jiffies - cfqq->slice_end;cfq_log_cfqq (cfqd, cfqq,"resid=%ld" , cfqq->slice_resid); }
Signature · 1 line
Jens Axboe
Quoted 24 lines · Jens Axboe
Quoted 9 lines · Damien Wyart
Hello,
Quoted 3 lines
A collection of fixes for 2.6.30-rc3. It includes fixes for regressions and bug fixes in general, along with two buglets in CFQ. Please pull.
What about this bug in CFQ: http://lkml.org/lkml/2009/4/20/68 ?
Do you plan to have it fixed for 2.6.30 or will it wait until 2.6.31?
Not sure. In theory we could just do the one-liner and make ->slice_resid negative (like below), but it needs some targetted testing. And given that it's been there for several releases, it's not really a rush to get it fixed for 2.6.30.
But I'll definitely throw it into the testing mix, and if deemed safe enough, get it in there for 2.6.30.
block/cfq-iosched.c +0
-0
block/cfq-iosched.c __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, · line 892
Quoted 7 lines
block/cfq-iosched.c +1
-1@@ -887,7 +887,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,* store what was left of this slice, if the queue idled/timed out */ if (timed_out && !cfq_cfqq_slice_new (cfqq)) { - cfqq->slice_resid = cfqq->slice_end - jiffies; + cfqq->slice_resid = jiffies - cfqq->slice_end;cfq_log_cfqq (cfqd, cfqq,"resid=%ld" , cfqq->slice_resid); }
BTW, it doesn't even matter for preempted processes, since they get front insertion always. The better fix is probably to just kill ->slice_resid, or at least rethink the logic.
I'll let it sit for 2.6.30 and come up with something alternative (or kill it) for 2.6.31.
Signature · 1 line
Jens Axboe