On Thu, 10 Aug 2006 14:36:10 -0500 Dave Kleikamp <shaggy@xxxxxxxxxxxxxx> wrote: > On Thu, 2006-08-10 at 12:23 -0700, Andrew Morton wrote: > > On Thu, 10 Aug 2006 11:51:34 -0700 > > Badari Pulavarty <pbadari@xxxxxxxxxx> wrote: > > > > > Andrew Morton wrote: > > > > Also, JBD is presently feeding into submit_bh() buffer_heads which span two > > > > machine pages, and some device drivers spit the dummy. It'd be better to > > > > fix that once, rather than twice.. > > > > > > > Andrew, > > > > > > I looked at this few days ago. I am not sure how we end up having > > > multiple pages (especially, > > > why we end up having buffers with bh_size > pagesize) ? Do you know why ? > > > > > > > It's one or both of the jbd_kmalloc(bh->b_size) calls in > > fs/jbd/transaction.c. Here we're allocating data to attach to a bh which > > later gets fed into submit_bh(). > > > > Problem is, with CONFIG_DEBUG_SLAB=y, the data which kmalloc() returns can > > be offset by 4 bytes due to redzoning. > > > > Example: if the fs is using a 1k blocksize and we have a 4k pagesize, the > > data coming back from kmalloc may have an address of 0xnnnnxc04, so the > > data which we later feed into submit_bh() will span two pages. > > > > A simple fix would be to replace kmalloc() with a call to alloc_page(). > > We'd need to work out how much memory that will worst-case-waste. If "not > > much" then OK. > > > > If "quite a lot in the worst case" then we'd need something more elaborate. > > Would some like this be okay: > > #ifdef CONFIG_DEBUG_SLAB > return alloc_page(... > #else > return kmalloc(... > #endif > > This keeps it simple, and should be still be efficient in the > non-DEBUG_SLAB case. > I guess that would work OK. It does appear that a lot of people build and distribute CONFIG_DEBUG_SLAB kernels though. Fedora, for one. - To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
