linux-stable.git/include/linux/bio.h, branch linux-2.6.30.y

bio: fix bio_kmalloc()

2009-04-22T06:35:10+00:00

Impact: fix bio_kmalloc() and its destruction path

bio_kmalloc() was broken in two ways.

* bvec_alloc_bs() first allocates bvec using kmalloc() and then
  ignores it and allocates again like non-kmalloc bvecs.

* bio_kmalloc_destructor() didn't check for and free bio integrity
  data.

This patch fixes the above problems.  kmalloc patch is separated out
from bio_alloc_bioset() and allocates the requested number of bvecs as
inline bvecs.

* bio_alloc_bioset() no longer takes NULL @bs.  None other than
  bio_kmalloc() used it and outside users can't know how it was
  allocated anyway.

* Define and use BIO_POOL_NONE so that pool index check in
  bvec_free_bs() triggers if inline or kmalloc allocated bvec gets
  there.

* Relocate destructors on top of each allocation function so that how
  they're used is more clear.

Jens Axboe suggested allocating bvecs inline.

Signed-off-by: Tejun Heo 
Signed-off-by: Jens Axboe

block: move bio list helpers into bio.h

2009-04-15T06:28:09+00:00

It's used by DM and MD and generally useful, so move the bio list
helpers into bio.h.

Signed-off-by: Christoph Hellwig 
Acked-by: Alasdair G Kergon 
Signed-off-by: Jens Axboe

block: Add flag for telling the IO schedulers NOT to anticipate more IO

2009-04-06T15:04:54+00:00

By default, CFQ will anticipate more IO from a given io context if the
previously completed IO was sync. This used to be fine, since the only
sync IO was reads and O_DIRECT writes. But with more "normal" sync writes
being used now, we don't want to anticipate for those.

Add a bio/request flag that informs the IO scheduler that this is a sync
request that we should not idle for. Introduce WRITE_ODIRECT specifically
for O_DIRECT writes, and make sure that the other sync writes set this
flag.

Signed-off-by: Jens Axboe 
Signed-off-by: Linus Torvalds

block: add private bio_set for bio integrity allocations

2009-03-24T11:35:17+00:00

The integrity bio allocation needs its own bio_set to avoid violating
the mempool allocation rules and risking deadlocks.

Signed-off-by: Martin K. Petersen 
Signed-off-by: Jens Axboe

block: Add gfp_mask parameter to bio_integrity_clone()

2009-03-14T20:06:51+00:00

Stricter gfp_mask might be required for clone allocation.
For example, request-based dm may clone bio in interrupt context
so it has to use GFP_ATOMIC.

Signed-off-by: Kiyoshi Ueda 
Signed-off-by: Jun'ichi Nomura 
Acked-by: Martin K. Petersen 
Cc: Alasdair G Kergon 
Signed-off-by: Jens Axboe

block: fix bad definition of BIO_RW_SYNC

2009-02-18T09:32:00+00:00

We can't OR shift values, so get rid of BIO_RW_SYNC and use BIO_RW_SYNCIO
and BIO_RW_UNPLUG explicitly. This brings back the behaviour from before
213d9417fec62ef4c3675621b9364a667954d4dd.

Signed-off-by: Jens Axboe

bio.h: If they MUST be inlined, then use __always_inline

2009-02-02T11:41:07+00:00

bvec_kmap_irq() and bvec_kunmap_irq() comments say they MUST be inlined,
so mark them as __always_inline.

Signed-off-by: Alberto Bertogli 
Signed-off-by: Jens Axboe

Fix misleading comment in bio.h

2009-02-02T11:41:07+00:00

The comment says "remember to add offset!", but the function already adds
it.

Signed-off-by: Alberto Bertogli 
Signed-off-by: Jens Axboe

block: add bio_rw_flagged() for testing bio->bi_rw

2009-01-30T11:34:37+00:00

The existing functions for checking bio->bi_rw are badly named. So lets
mirror what we do for bio->bi_flags testing, use a properly named
function so that it's immediately obvious what is being tested.

Maintain compatability names for the old macros, eventually we'll get
rid of these.

Signed-off-by: Jens Axboe

block: seperate bio/request unplug and sync bits

2009-01-30T11:34:37+00:00

Signed-off-by: Jens Axboe