• Hugh Dickins's avatar
    ksm: shrink 32-bit rmap_item back to 32 bytes · bc56620b
    Hugh Dickins authored
    Think of struct rmap_item as an extension of struct page (restricted to
    MADV_MERGEABLE areas): there may be a lot of them, we need to keep them
    small, especially on 32-bit architectures of limited lowmem.
    Siting "int nid" after "unsigned int checksum" works nicely on 64-bit,
    making no change to its 64-byte struct rmap_item; but bloats the 32-bit
    struct rmap_item from (nicely cache-aligned) 32 bytes to 36 bytes, which
    rounds up to 40 bytes once allocated from slab.  We'd better avoid that.
    Hey, I only just remembered that the anon_vma pointer in struct
    rmap_item has no purpose until the rmap_item is hung from a stable tree
    node (which has its own nid field); and rmap_item's nid field no purpose
    than to say which tree root to tell rb_erase() when unlinking from an
    unstable tree.
    Double them up in a union.  There's just one place where we set anon_vma
    early (when we already hold mmap_sem): now we must remove tree_rmap_item
    from its unstable tree there, before overwriting nid.  No need to
    spatter BUG()s around: we'd be seeing oopses if this were wrong.
    Signed-off-by: default avatarHugh Dickins <hughd@google.com>
    Cc: Mel Gorman <mgorman@suse.de>
    Cc: Petr Holasek <pholasek@redhat.com>
    Cc: Andrea Arcangeli <aarcange@redhat.com>
    Cc: Izik Eidus <izik.eidus@ravellosystems.com>
    Cc: Johannes Weiner <hannes@cmpxchg.org>
    Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
    Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
ksm.c 65.1 KB