On Wed 18-03-15 14:38:47, Mel Gorman wrote: > On Wed, Mar 18, 2015 at 03:09:26PM +0100, Michal Hocko wrote: > > page_cache_read has been historically using page_cache_alloc_cold to > > allocate a new page. This means that mapping_gfp_mask is used as the > > base for the gfp_mask. Many filesystems are setting this mask to > > GFP_NOFS to prevent from fs recursion issues. page_cache_read is, > > however, not called from the fs layer so it doesn't need this > > protection. Even ceph and ocfs2 which call filemap_fault from their > > fault handlers seem to be OK because they are not taking any fs lock > > before invoking generic implementation. > > > > The protection might be even harmful. There is a strong push to fail > > GFP_NOFS allocations rather than loop within allocator indefinitely with > > a very limited reclaim ability. Once we start failing those requests > > the OOM killer might be triggered prematurely because the page cache > > allocation failure is propagated up the page fault path and end up in > > pagefault_out_of_memory. > > > > Use GFP_KERNEL mask instead because it is safe from the reclaim > > recursion POV. We are already doing GFP_KERNEL allocations down > > add_to_page_cache_lru path. > > > > Reported-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx> > > Signed-off-by: Michal Hocko <mhocko@xxxxxxx> > > I'm very far behind after LSF/MM so do not know where this came out of > but it loses addressing restriction hints from the driver such as > > drivers/gpu/drm/gma500/gem.c: mapping_set_gfp_mask(r->gem.filp->f_mapping, GFP_KERNEL | __GFP_DMA32); OK, I have missed these drivers. Scratch the patch for now I will think about it more. Thanks! -- Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>