Messages in this thread Patch in this message | | | Date | Fri, 29 Feb 2008 08:28:48 -0500 | From | Mathieu Desnoyers <> | Subject | [PATCH] Slub Freeoffset check overflow |
| |
* Christoph Lameter (clameter@sgi.com) wrote: > On Thu, 28 Feb 2008, Mathieu Desnoyers wrote: > > > * Christoph Lameter (clameter@sgi.com) wrote: > > > On Thu, 28 Feb 2008, Mathieu Desnoyers wrote: > > > > > > > In short, the we also use the versioning to check for change of slab. > > Then we do not need the page->end field anymore right? I will try > to rediff your patch against current slab-mm and see how we can proceed > from there.
Slub Freeoffset check overflow
Check for overflow of the freeoffset version number.
I just thought adding this check in CONFIG_SLUB_DEBUG makes sense. It's really unlikely that enough interrupt handlers will nest over the slub fast path, and each of them do about a million alloc/free on 32 bits or a huge amount of alloc/free on 64 bits, but just in case, it seems good to warn if we detect we are half-way to a version overflow.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> --- mm/slub.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-)
Index: linux-2.6-lttng/mm/slub.c =================================================================== --- linux-2.6-lttng.orig/mm/slub.c 2008-02-29 08:05:01.000000000 -0500 +++ linux-2.6-lttng/mm/slub.c 2008-02-29 08:16:13.000000000 -0500 @@ -1660,7 +1660,7 @@ static __always_inline void *slab_alloc( */ #ifdef SLUB_FASTPATH - unsigned long freeoffset, newoffset; + unsigned long freeoffset, newoffset, resoffset; c = get_cpu_slab(s, raw_smp_processor_id()); do { @@ -1682,8 +1682,18 @@ static __always_inline void *slab_alloc( newoffset = freeoffset; newoffset &= ~c->off_mask; newoffset |= (unsigned long)object[c->offset] & c->off_mask; - } while (cmpxchg_local(&c->freeoffset, freeoffset, newoffset) - != freeoffset); + resoffset = cmpxchg_local(&c->freeoffset, freeoffset, + newoffset); +#ifdef CONFIG_SLUB_DEBUG + /* + * Just to be paranoid : warn if we detect that enough + * allocations nested on top of us to get the counter to go + * half-way to overflow. That would be insane to do that much + * allocations in interrupt handers, but check it anyway. + */ + WARN_ON(resoffset - freeoffset > -1UL >> 1); +#endif + } while (resoffset != freeoffset); #else unsigned long flags; @@ -1822,7 +1832,7 @@ static __always_inline void slab_free(st struct kmem_cache_cpu *c; #ifdef SLUB_FASTPATH - unsigned long freeoffset, newoffset; + unsigned long freeoffset, newoffset, resoffset; c = get_cpu_slab(s, raw_smp_processor_id()); debug_check_no_locks_freed(object, s->objsize); @@ -1850,8 +1860,18 @@ static __always_inline void slab_free(st newoffset = freeoffset + c->off_mask + 1; newoffset &= ~c->off_mask; newoffset |= (unsigned long)object & c->off_mask; - } while (cmpxchg_local(&c->freeoffset, freeoffset, newoffset) - != freeoffset); + resoffset = cmpxchg_local(&c->freeoffset, freeoffset, + newoffset); +#ifdef CONFIG_SLUB_DEBUG + /* + * Just to be paranoid : warn if we detect that enough + * allocations nested on top of us to get the counter to go + * half-way to overflow. That would be insane to do that much + * allocations in interrupt handers, but check it anyway. + */ + WARN_ON(resoffset - freeoffset > -1UL >> 1); +#endif + } while (resoffset != freeoffset); #else unsigned long flags; -- Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
| |