[RFC] slub: Enable backtrace for create/delete points.

From: Ben Greear <greearb@candelatech.com> This patch attempts to grab a backtrace for the creation and deletion points of the slub object. When a fault is detected, we can then get a better idea of where the item was deleted. This probably ...

Message posted on the October 6th, 2010 - 4:10 PM ET

[PATCH] [RFC] slub tracing: move trace calls out of always inlined functions to reduce kernel code size

Having the trace calls defined in the always inlined kmalloc functions in include/linux/slub_def.h causes a lot of code duplication as the trace functions get instantiated for each kamalloc call site. This can simply be removed by pushing the trace ...

Message posted on the October 13th, 2010 - 12:10 PM ET

[PATCH 0/2] RFC SLUB: increase range of kmalloc slab sizes

This patch increases the range of slab sizes available to kmalloc, adding slabs half way between the existing power of two sized ones, so allowing slightly more efficient use of memory. Most of the new slabs already exist as kmem_cache slabs so only ...

Message posted on the October 13th, 2012 - 1:00 PM ET

[RFC] slub: Per object NUMA support

I am not sure if such a feature is needed/wanted/desired. It would make the object allocation method similar to SLAB instead of relying on page based policy application (which IMHO was the intend of the memory policy system before Paul Jackson got ...

Message posted on the April 15th, 2011 - 4:00 PM ET

[RFC][PATCH] slub: Check for page NULL before doing the node_match check

In the -rt kernel (mrg), we hit the following dump: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff811573f1>] kmem_cache_alloc_node+0x51/0x180 PGD a2d39067 PUD b1641067 PMD 0 Oops: 0000 [#1] PREEMPT ...

Message posted on the January 17th, 2013 - 1:20 PM ET

[rfc PATCH]slub: per cpu partial statistics change

This patch split the cpu_partial_free into 2 parts: cpu_partial_node, PCP refilling times from node partial; and same name cpu_partial_free, PCP refilling times in slab_free slow path. A new statistic 'release_cpu_partial' is added to get PCP ...

Message posted on the February 3rd, 2012 - 3:20 AM ET

[PATCH/RFC] MM slub: add a sysfs entry to show the calculated number of fallback slabs

Add a slub sysfs entry to show the calculated number of fallback slabs. Using the information already available it is straightforward to calculate the number of fallback & full size slabs. We can then track which slabs are particularly effected ...

Message posted on the November 12th, 2010 - 6:30 AM ET

[RFC/PATCH] SLUB: Optimize slab_free() debug check

This patch optimizes slab_free() debug check to use "c->node != NUMA_NO_NODE" instead of "c->node >= 0" because the former generates smaller code on x86-64: Before: 4736: 48 39 70 08 cmp ...

Message posted on the October 2nd, 2010 - 4:50 AM ET

[RFC][PATCH 0/2] Move kmalloc tracepoints out of inlined code

Anyone have any objections to this code? Tracepoints do carry a bit of weight and having them in a common inlined function such as kmalloc() adds a bit of bloat to the kernel. This is an RFC patch (to get comments) and hopefully will be something ...

Message posted on the November 24th, 2010 - 4:30 PM ET

[RFC PATCH 1/4] mm: introduce a safer interface to check whether a page is managed by SLxB

Several subsystems, including memory-failure, swap, sparse, DRBD etc, use PageSlab() to check whether a page is managed by SLAB/SLUB/SLOB. And they treat slab pages differently from pagecache/anonymous pages. But it's unsafe to use PageSlab() to ...

Message posted on the July 3rd, 2012 - 12:10 AM ET

[PATCH] [RFC] um: x86: unbreak build by reintroducing this_cpu_cmpxchg16b_emu

I'm sure fix can be nices, but initial patch should express an idea. The main offender is privileged 'cli'. Thanks! Sergei filename01-RFC-um-x86-unbreak-build-by-reintroducing-this_cpu_c.patch From 59c59c76b0238ff2469bb7f4201b9b88ec436df4 ...

Message posted on the April 6th, 2011 - 5:20 PM ET

[RFC/PATCH 1/2] slub: Break out alloc_kmem_cache_cpus() from kmem_cache_open()

In preparation for sharing per-CPU structures between merged caches, break out alloc_kmem_cache_cpus() from kmem_cache_open() function. Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Linus Torvalds ...

Message posted on the April 25th, 2011 - 1:50 PM ET

[RFC, PATCH] slub: unfreeze_partials() uses a wrong param

unfreeze_partials() calls add_partial(..., 1) while it should use DEACTIVATE_TO_TAIL or DEACTIVATE_TO_HEAD Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> diff --git a/mm/slub.c b/mm/slub.c index 7d2a996..db060b6 100644 a/mm/slub.c +++ ...

Message posted on the November 22nd, 2011 - 10:40 AM ET

[RFC v3 2/5] slab: implement slab object boundaries assertion

Implement slab_access_ok() which checks whether a supplied buffer fully fits in a slab page and whether it overflows a slab object. It uses cache specific information to learn object's boundaries. It doesn't check whether the object is actually ...

Message posted on the July 21st, 2011 - 9:00 AM ET

rfc slub