summaryrefslogtreecommitdiff
path: root/include/linux
AgeCommit message (Collapse)AuthorFilesLines
2008-12-30virtio: use LGUEST_VRING_ALIGN instead of relying on pagesizeRusty Russell1-0/+4
This doesn't really matter, since lguest is i386 only at the moment, but we could actually choose a different value. (lguest doesn't have a guarenteed ABI). Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30virtio: Don't use PAGE_SIZE for vring alignment in virtio_pci.Rusty Russell1-0/+4
That doesn't work for non-4k guests which are now appearing. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30virtio: rename 'pagesize' arg to vring_init/vring_sizeRusty Russell1-6/+6
It's really the alignment desired for consumer/producer separation; historically this x86 pagesize, but with PowerPC it'll still be x86 pagesize. And in theory lguest could choose a different value. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30virtio: Don't use PAGE_SIZE in virtio_pci.cRusty Russell1-0/+4
The virtio PCI devices don't depend on the guest page size. This matters now PowerPC virtio is gaining ground (they like 64k pages). Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30cpumask: Use nr_cpu_ids in seq_cpumaskRusty Russell1-1/+1
Impact: cleanup, futureproof nr_cpu_ids is the (badly named) runtime limit on possible CPU numbers; ie. the variable version of NR_CPUS. With the new cpumask operators, only bits less than this are defined. So we should use it everywhere, rather than NR_CPUS. Eventually this will make it possible to allocate cpumasks of the minimal length at runtime. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Ingo Molnar <mingo@elte.hu>
2008-12-30cpumask: smp_call_function_many()Rusty Russell1-7/+8
Impact: Implementation change to remove cpumask_t from stack. Actually change smp_call_function_mask() to smp_call_function_many(). We avoid cpumasks on the stack in this version. (S390 has its own version, but that's going away apparently). We have to do some dancing to figure out if 0 or 1 other cpus are in the mask supplied and the online mask without allocating a tmp cpumask. It's still fairly cheap. We allocate the cpumask at the end of the call_function_data structure: if allocation fails we fallback to smp_call_function_single rather than using the baroque quiescing code (which needs a cpumask on stack). (Thanks to Hiroshi Shimamoto for spotting several bugs in previous versions!) Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com> Cc: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com> Cc: npiggin@suse.de Cc: axboe@kernel.dk
2008-12-30cpumask: make set_cpu_*/init_cpu_* out-of-lineRusty Russell1-46/+7
They're only for use in boot/cpu hotplug code anyway, and this avoids the use of deprecated cpu_*_map. Stephen Rothwell points out that gcc 4.2.4 (on powerpc at least) didn't like the cast away of const anyway: include/linux/cpumask.h: In function 'set_cpu_possible': include/linux/cpumask.h:1052: warning: passing argument 2 of 'cpumask_set_cpu' discards qualifiers from pointer target type So this kills two birds with one stone. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30cpumask: make cpumask.h eat its own dogfood.Rusty Russell1-37/+38
Changes: 1) cpumask_t to struct cpumask, 2) cpus_weight_nr to cpumask_weight, 3) cpu_isset to cpumask_test_cpu, 4) ->bits to cpumask_bits() 5) cpu_*_map to cpu_*_mask. 6) for_each_cpu_mask_nr to for_each_cpu Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30cpumask: switch over to cpu_online/possible/active/present_mask: coreRusty Russell1-46/+29
Impact: cleanup This implements the obsolescent cpu_online_map in terms of cpu_online_mask, rather than the other way around. Same for the other maps. The documentation comments are also updated to refer to _mask rather than _map. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com>
2008-12-30bitmap: fix seq_bitmap and seq_cpumask to take const pointerRusty Russell1-2/+3
Impact: cleanup seq_bitmap just calls bitmap_scnprintf on the bits: that arg can be const. Similarly, seq_cpumask just calls seq_bitmap. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30bitmap: test for constant as well as small size for inline versionsRusty Russell1-16/+19
Impact: reduce text size bitmap_zero et al have a fastpath for nbits <= BITS_PER_LONG, but this should really only apply where the nbits is known at compile time. This only saves about 1200 bytes on an allyesconfig kernel, but with cpumasks going variable that number will increase. text data bss dec hex filename 35327852 5035607 6782976 47146435 2cf65c3 vmlinux-before 35326640 5035607 6782976 47145223 2cf6107 vmlinux-after Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2008-12-30cpumask: make CONFIG_NR_CPUS always valid.Rusty Russell1-8/+8
Impact: cleanup Currently we have NR_CPUS, which is 1 on UP, and CONFIG_NR_CPUS on SMP. If we make CONFIG_NR_CPUS always valid (and always 1 on !SMP), we can skip the middleman. This also allows us to find and check all the unaudited NR_CPUS usage as we prepare for v. large NR_CPUS. To avoid breaking every arch, we cheat and do this for the moment in the header if the arch doesn't. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Mike Travis <travis@sgi.com>
2008-12-30Merge branch 'master' of ↵Rusty Russell88-918/+2852
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6
2008-12-29V4L/DVB (9530): Add new pixel format VYUY 16 bits wide.Robert Jarzmik1-0/+1
There were already 3 YUV formats defined : - YUYV - YVYU - UYVY The only left combination is VYUY, which is added in this patch. Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2008-12-29ide: move Power Management support to ide-pm.cBartlomiej Zolnierkiewicz1-0/+8
There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29ide: rework handling of serialized ports (v2)Bartlomiej Zolnierkiewicz1-1/+0
* hpt366: set IDE_HFLAG_SERIALIZE in ->host_flags if needed in init_hwif_hpt366(). Remove HPT_SERIALIZE_IO while at it. * Set IDE_HFLAG_SERIALIZE in ->host_flags if needed in ide_init_port(). * Convert init_irq() to use IDE_HFLAG_SERIALIZE together with hwif->host to find out ports which need to be serialized. * Remove no longer needed save_match() and ide_hwif_t.serialized. v2: * Set host's ->host_flags field instead of port's copy. This patch should fix the incorrect grouping of port(s) from host(s) that need serialization with port(s) that happen to use the same IRQ(s) but are from the host(s) that don't need it. Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29cy82c693: remove superfluous ide_cy82c693 chipset typeBartlomiej Zolnierkiewicz1-2/+1
Since CY82C693 doesn't require serialization we may as well use the default ide_pci chipset type. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29trm290: add IDE_HFLAG_TRM290 host flagBartlomiej Zolnierkiewicz1-1/+3
* Add IDE_HFLAG_TRM290 host flag and use it in ide_build_dmatable(). * Remove no longer needed ide_trm290 chipset type. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29ide: add ->max_sectors field to struct ide_port_infoBartlomiej Zolnierkiewicz1-2/+3
* Add ->max_sectors field to struct ide_port_info to allow host drivers to specify value used for hwif->rqsize (if smaller than the default). * Convert pdc202xx_old to use ->max_sectors and remove no longer needed IDE_HFLAG_RQSIZE_256 flag. There should be no functional changes caused by this patch. Acked-by: Sergei Shtyltov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29rz1000: apply chipset quirks early (v2)Bartlomiej Zolnierkiewicz1-2/+1
* Use pci_name(dev) instead of hwif->name in init_hwif_rz1000(). * init_hwif_rz1000() -> rz1000_init_chipset(). Update rz1000_init_one() to use rz1000_init_chipset() and add now required rz1000_remove(). * Remove superfluous ide_rz1000 chipset type. v2: * unsigned int rz1000_init_chipset() -> int rz1000_disable_readahead() per Sergei's suggestion. Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29ide: always set nIEN on idle devicesBartlomiej Zolnierkiewicz1-1/+0
* Set nIEN for previous port/device in ide_do_request() also if port uses a non-shared IRQ. * Remove no longer needed ide_hwif_t.sharing_irq. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29cmd64x: set IDE_HFLAG_SERIALIZE explictly for CMD646Bartlomiej Zolnierkiewicz1-1/+1
* Set IDE_HFLAG_SERIALIZE explictly for CMD646. * Remove no longer needed ide_cmd646 chipset type (which has a nice side-effect of fixing handling of unexpected IRQs). Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29ide-cd: remove obsolete seek optimizationBartlomiej Zolnierkiewicz1-4/+0
It doesn't make much sense nowadays and is problematic on some drives. Cc: Borislav Petkov <petkovbb@googlemail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29ide: replace the global ide_lock spinlock by per-hwgroup spinlocks (v2)Bartlomiej Zolnierkiewicz1-5/+7
Now that (almost) all host drivers have been fixed not to abuse ide_lock and core code usage of ide_lock has been sanitized we may safely replace ide_lock by per-hwgroup locks. This patch is partially based on earlier patch from Ravikiran G Thirumalai. While at it: - don't use deprecated HWIF() and HWGROUP() macros - update locking documentation in ide.h v2: Add missing spin_lock_init(&hwgroup->lock). (Noticed by Elias Oltmanns) Cc: Vaibhav V. Nivargi <vaibhav.nivargi@gmail.com> Cc: Alok N. Kataria <alokk@calsoftinc.com> Cc: Shai Fultheim <shai@scalex86.org> Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org> Cc: Elias Oltmanns <eo@nebensachen.de> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-12-29sched: create "pushable_tasks" list to limit pushing to one attemptGregory Haskins2-0/+2
The RT scheduler employs a "push/pull" design to actively balance tasks within the system (on a per disjoint cpuset basis). When a task is awoken, it is immediately determined if there are any lower priority cpus which should be preempted. This is opposed to the way normal SCHED_OTHER tasks behave, which will wait for a periodic rebalancing operation to occur before spreading out load. When a particular RQ has more than 1 active RT task, it is said to be in an "overloaded" state. Once this occurs, the system enters the active balancing mode, where it will try to push the task away, or persuade a different cpu to pull it over. The system will stay in this state until the system falls back below the <= 1 queued RT task per RQ. However, the current implementation suffers from a limitation in the push logic. Once overloaded, all tasks (other than current) on the RQ are analyzed on every push operation, even if it was previously unpushable (due to affinity, etc). Whats more, the operation stops at the first task that is unpushable and will not look at items lower in the queue. This causes two problems: 1) We can have the same tasks analyzed over and over again during each push, which extends out the fast path in the scheduler for no gain. Consider a RQ that has dozens of tasks that are bound to a core. Each one of those tasks will be encountered and skipped for each push operation while they are queued. 2) There may be lower-priority tasks under the unpushable task that could have been successfully pushed, but will never be considered until either the unpushable task is cleared, or a pull operation succeeds. The net result is a potential latency source for mid priority tasks. This patch aims to rectify these two conditions by introducing a new priority sorted list: "pushable_tasks". A task is added to the list each time a task is activated or preempted. It is removed from the list any time it is deactivated, made current, or fails to push. This works because a task only needs to be attempted to push once. After an initial failure to push, the other cpus will eventually try to pull the task when the conditions are proper. This also solves the problem that we don't completely analyze all tasks due to encountering an unpushable tasks. Now every task will have a push attempted (when appropriate). This reduces latency both by shorting the critical section of the rq->lock for certain workloads, and by making sure the algorithm considers all eligible tasks in the system. [ rostedt: added a couple more BUG_ONs ] Signed-off-by: Gregory Haskins <ghaskins@novell.com> Acked-by: Steven Rostedt <srostedt@redhat.com>
2008-12-29plist: fix PLIST_NODE_INIT to work with debug enabledGregory Haskins1-3/+6
It seems that PLIST_NODE_INIT breaks if used and DEBUG_PI_LIST is defined. Since there are no current users of PLIST_NODE_INIT, this has gone undetected. This patch fixes the build issue that enables the DEBUG_PI_LIST later in the series when we use it in init_task.h Signed-off-by: Gregory Haskins <ghaskins@novell.com>
2008-12-29sched: add sched_class->needs_post_schedule() memberGregory Haskins1-0/+1
We currently run class->post_schedule() outside of the rq->lock, which means that we need to test for the need to post_schedule outside of the lock to avoid a forced reacquistion. This is currently not a problem as we only look at rq->rt.overloaded. However, we want to enhance this going forward to look at more state to reduce the need to post_schedule to a bare minimum set. Therefore, we introduce a new member-func called needs_post_schedule() which tests for the post_schedule condtion without actually performing the work. Therefore it is safe to call this function before the rq->lock is released, because we are guaranteed not to drop the lock at an intermediate point (such as what post_schedule() may do). We will use this later in the series [ rostedt: removed paranoid BUG_ON ] Signed-off-by: Gregory Haskins <ghaskins@novell.com>
2008-12-29Merge branch 'topic/kmemtrace' of ↵Ingo Molnar5-20/+204
git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6 into tracing/kmemtrace
2008-12-29kmemtrace: Better alternative to "kmemtrace: fix printk format warnings".Eduard - Gabriel Munteanu1-1/+2
Fix the problem "kmemtrace: fix printk format warnings" attempted to fix, but resulted in marker-probe format mismatch warnings. Instead of carrying size_t into probes, we get rid of it by casting to unsigned long, just as we did with gfp_t. This way, we don't need to change marker format strings and we don't have to rely on other format specifiers like "%zu", making for consistent use of more generic data types (since there are no format specifiers for gfp_t, for example). Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29kmemtrace: SLUB hooks.Eduard - Gabriel Munteanu1-3/+50
This adds hooks for the SLUB allocator, to allow tracing with kmemtrace. Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29kmemtrace: SLOB hooks.Eduard - Gabriel Munteanu1-4/+5
This adds hooks for the SLOB allocator, to allow tracing with kmemtrace. We also convert some inline functions to __always_inline to make sure _RET_IP_, which expands to __builtin_return_address(0), always works as expected. Acked-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29kmemtrace: SLAB hooks.Eduard - Gabriel Munteanu1-9/+59
This adds hooks for the SLAB allocator, to allow tracing with kmemtrace. We also convert some inline functions to __always_inline to make sure _RET_IP_, which expands to __builtin_return_address(0), always works as expected. Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29kmemtrace: Core implementation.Eduard - Gabriel Munteanu1-0/+85
kmemtrace provides tracing for slab allocator functions, such as kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected data is then fed to the userspace application in order to analyse allocation hotspots, internal fragmentation and so on, making it possible to see how well an allocator performs, as well as debug and profile kernel code. Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29SLUB: Replace __builtin_return_address(0) with _RET_IP_.Eduard - Gabriel Munteanu1-4/+4
This patch replaces __builtin_return_address(0) with _RET_IP_, since a previous patch moved _RET_IP_ and _THIS_IP_ to include/linux/kernel.h and they're widely available now. This makes for shorter and easier to read code. [penberg@cs.helsinki.fi: remove _RET_IP_ casts to void pointer] Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29Input: map_to_7segment.h - convert to __inline__ for userspaceMike Frysinger1-1/+1
Use __inline__ rather than inline for map_to_seg7() since it is exported to userspace. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
2008-12-29locking, percpu counters: introduce separate lock classesPeter Zijlstra1-4/+10
Impact: fix lockdep false positives Classify percpu_counter instances similar to regular lock objects -- that is, per instantiation site. The networking code has increased its use of percpu_counters, which leads to false positives if they are treated as a single class. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-29DMI: add dmi_matchJiri Slaby1-0/+3
Add a wrapper for testing system_info which will handle also NULL system infos. This will be used by the ata PIIX driver. Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Cc: Alexandru Romanescu <a_romanescu@yahoo.co.uk> Cc: Tejun Heo <tj@kernel.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
2008-12-29sparseirq: move __weak symbols into separate compilation unitYinghai Lu2-3/+6
GCC has a bug with __weak alias functions: if the functions are in the same compilation unit as their call site, GCC can decide to inline them - and thus rob the linker of the opportunity to override the weak alias with the real thing. So move all the IRQ handling related __weak symbols to kernel/irq/chip.c. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-29Merge branch 'topic/failslab' into for-linusPekka Enberg1-0/+9
Conflicts: mm/slub.c Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29Merge branches 'topic/fixes', 'topic/cleanups' and 'topic/documentation' ↵Pekka Enberg1-4/+4
into for-linus
2008-12-29slab: Fix comment on #endifPascal Terjan1-1/+1
This #endif in slab.h is described as closing the inner block while it's for the big CONFIG_NUMA one. That makes reading the code a bit harder. This trivial patch fixes the comment. Signed-off-by: Pascal Terjan <pterjan@mandriva.com> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29SLUB: failslab supportAkinobu Mita1-0/+9
Currently fault-injection capability for SLAB allocator is only available to SLAB. This patch makes it available to SLUB, too. [penberg@cs.helsinki.fi: unify slab and slub implementations] Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2008-12-29Merge branch 'linus' into perfcounters/coreIngo Molnar87-910/+2852
Conflicts: fs/exec.c include/linux/init_task.h Simple context conflicts.
2008-12-29DRM: add mode setting supportDave Airlie1-0/+4
Add mode setting support to the DRM layer. This is a fairly big chunk of work that allows DRM drivers to provide full output control and configuration capabilities to userspace. It was motivated by several factors: - the fb layer's APIs aren't suited for anything but simple configurations - coordination between the fb layer, DRM layer, and various userspace drivers is poor to non-existent (radeonfb excepted) - user level mode setting drivers makes displaying panic & oops messages more difficult - suspend/resume of graphics state is possible in many more configurations with kernel level support This commit just adds the core DRM part of the mode setting APIs. Driver specific commits using these new structure and APIs will follow. Co-authors: Jesse Barnes <jbarnes@virtuousgeek.org>, Jakob Bornecrantz <jakob@tungstengraphics.com> Contributors: Alan Hourihane <alanh@tungstengraphics.com>, Maarten Maathuis <madman2003@gmail.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Eric Anholt <eric@anholt.net> Signed-off-by: Dave Airlie <airlied@redhat.com>
2008-12-29Get rid of CONFIG_LSFJens Axboe1-8/+3
We have two seperate config entries for large devices/files. One is CONFIG_LBD that guards just the devices, the other is CONFIG_LSF that handles large files. This doesn't make a lot of sense, you typically want both or none. So get rid of CONFIG_LSF and change CONFIG_LBD wording to indicate that it covers both. Acked-by: Jean Delvare <khali@linux-fr.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-29block: add one-hit cache for disk partition lookupJens Axboe1-0/+1
disk_map_sector_rcu() returns a partition from a sector offset, which we use for IO statistics on a per-partition basis. The lookup itself is an O(N) list lookup, where N is the number of partitions. This actually hurts performance quite a bit, even on the lower end partitions. On higher numbered partitions, it can get pretty bad. Solve this by adding a one-hit cache for partition lookup. This makes the lookup O(1) for the case where we do most IO to one partition. Even for mixed partition workloads, amortized cost is pretty close to O(1) since the natural IO batching makes the one-hit cache last for lots of IOs. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-29block: get rid of elevator_t typedefJens Axboe2-6/+5
Just use struct elevator_queue everywhere instead. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-29aio: make the lookup_ioctx() locklessJens Axboe2-3/+7
The mm->ioctx_list is currently protected by a reader-writer lock, so we always grab that lock on the read side for doing ioctx lookups. As the workload is extremely reader biased, turn this into an rcu hlist so we can make lookup_ioctx() lockless. Get rid of the rwlock and use a spinlock for providing update side exclusion. There's usually only 1 entry on this list, so it doesn't make sense to look into fancier data structures. Reviewed-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-29bio: add support for inlining a number of bio_vecs inside the bioJens Axboe1-0/+12
When we go and allocate a bio for IO, we actually do two allocations. One for the bio itself, and one for the bi_io_vec that holds the actual pages we are interested in. This feature inlines a definable amount of io vecs inside the bio itself, so we eliminate the bio_vec array allocation for IO's up to a certain size. It defaults to 4 vecs, which is typically 16k of IO. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-12-29bio: allow individual slabs in the bio_setJens Axboe1-1/+5
Instead of having a global bio slab cache, add a reference to one in each bio_set that is created. This allows for personalized slabs in each bio_set, so that they can have bios of different sizes. This means we can personalize the bios we return. File systems may want to embed the bio inside another structure, to avoid allocation more items (and stuffing them in ->bi_private) after the get a bio. Or we may want to embed a number of bio_vecs directly at the end of a bio, to avoid doing two allocations to return a bio. This is now possible. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>