* Suren Baghdasaryan <sur...@google.com> [250822 16:25]:
> On Wed, Jul 23, 2025 at 6:35 AM Vlastimil Babka <vba...@suse.cz> wrote:
> >
> > From: "Liam R. Howlett" <liam.howl...@oracle.com>
> >
> > The fast path through a write will require replacing a single node in
> > the tree.  Using a sheaf (32 nodes) is too heavy for the fast path, so
> > special case the node store operation by just allocating one node in the
> > maple state.
> >
> > Signed-off-by: Liam R. Howlett <liam.howl...@oracle.com>
> > Signed-off-by: Vlastimil Babka <vba...@suse.cz>
> > ---
> >  include/linux/maple_tree.h |  4 +++-
> >  lib/maple_tree.c           | 47 
> > ++++++++++++++++++++++++++++++++++++++++------
> >  2 files changed, 44 insertions(+), 7 deletions(-)
> >
> > diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
> > index 
> > 3cf1ae9dde7ce43fa20ae400c01fefad048c302e..61eb5e7d09ad0133978e3ac4b2af66710421e769
> >  100644
> > --- a/include/linux/maple_tree.h
> > +++ b/include/linux/maple_tree.h
> > @@ -443,6 +443,7 @@ struct ma_state {
> >         unsigned long min;              /* The minimum index of this node - 
> > implied pivot min */
> >         unsigned long max;              /* The maximum index of this node - 
> > implied pivot max */
> >         struct slab_sheaf *sheaf;       /* Allocated nodes for this 
> > operation */
> > +       struct maple_node *alloc;       /* allocated nodes */
> >         unsigned long node_request;
> >         enum maple_status status;       /* The status of the state (active, 
> > start, none, etc) */
> >         unsigned char depth;            /* depth of tree descent during 
> > write */
> > @@ -491,8 +492,9 @@ struct ma_wr_state {
> >                 .status = ma_start,                                     \
> >                 .min = 0,                                               \
> >                 .max = ULONG_MAX,                                       \
> > -               .node_request= 0,                                       \
> >                 .sheaf = NULL,                                          \
> > +               .alloc = NULL,                                          \
> > +               .node_request= 0,                                       \
> >                 .mas_flags = 0,                                         \
> >                 .store_type = wr_invalid,                               \
> >         }
> > diff --git a/lib/maple_tree.c b/lib/maple_tree.c
> > index 
> > 3c3c14a76d98ded3b619c178d64099b464a2ca23..9aa782b1497f224e7366ebbd65f997523ee0c8ab
> >  100644
> > --- a/lib/maple_tree.c
> > +++ b/lib/maple_tree.c
> > @@ -1101,16 +1101,23 @@ static int mas_ascend(struct ma_state *mas)
> >   *
> >   * Return: A pointer to a maple node.
> >   */
> > -static inline struct maple_node *mas_pop_node(struct ma_state *mas)
> > +static __always_inline struct maple_node *mas_pop_node(struct ma_state 
> > *mas)
> >  {
> >         struct maple_node *ret;
> >
> > +       if (mas->alloc) {
> > +               ret = mas->alloc;
> > +               mas->alloc = NULL;
> > +               goto out;
> > +       }
> > +
> >         if (WARN_ON_ONCE(!mas->sheaf))
> >                 return NULL;
> >
> >         ret = kmem_cache_alloc_from_sheaf(maple_node_cache, GFP_NOWAIT, 
> > mas->sheaf);
> > -       memset(ret, 0, sizeof(*ret));
> >
> > +out:
> > +       memset(ret, 0, sizeof(*ret));
> >         return ret;
> >  }
> >
> > @@ -1121,9 +1128,34 @@ static inline struct maple_node *mas_pop_node(struct 
> > ma_state *mas)
> >   */
> >  static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
> >  {
> > -       if (unlikely(mas->sheaf)) {
> > -               unsigned long refill = mas->node_request;
> > +       if (!mas->node_request)
> > +               return;
> > +
> > +       if (mas->node_request == 1) {
> > +               if (mas->sheaf)
> > +                       goto use_sheaf;
> > +
> > +               if (mas->alloc)
> > +                       return;
> >
> > +               mas->alloc = mt_alloc_one(gfp);
> > +               if (!mas->alloc)
> > +                       goto error;
> > +
> > +               mas->node_request = 0;
> > +               return;
> > +       }
> > +
> > +use_sheaf:
> > +       if (unlikely(mas->alloc)) {
> 
> When would this condition happen?


This would be the case if we have one node allocated and requested more
than one node.  That is, a chained request for nodes that ends up having
the alloc set and requesting a sheaf.

> Do we really need to free mas->alloc
> here or it can be reused for the next 1-node allocation?

Most calls end in mas_destroy() so that won't happen today.

We could reduce the number of allocations requested to the sheaf and let
the code find the mas->alloc first and use that.

But remember, we are getting into this situation where code did a
mas_preallocate() then figured they needed to do something else (error
recovery, or changed the vma flags and now it can merge..) and will now
need additional nodes.  So this is a rare case, so I figured just free
it was the safest thing.


> > +               mt_free_one(mas->alloc);
> > +               mas->alloc = NULL;
> > +       }
> > +
> > +       if (mas->sheaf) {
> > +               unsigned long refill;
> > +
> > +               refill = mas->node_request;
> >                 if(kmem_cache_sheaf_size(mas->sheaf) >= refill) {
> >                         mas->node_request = 0;
> >                         return;
> > @@ -5386,8 +5418,11 @@ void mas_destroy(struct ma_state *mas)
> >         mas->node_request = 0;
> >         if (mas->sheaf)
> >                 mt_return_sheaf(mas->sheaf);
> > -
> >         mas->sheaf = NULL;
> > +
> > +       if (mas->alloc)
> > +               mt_free_one(mas->alloc);
> > +       mas->alloc = NULL;
> >  }
> >  EXPORT_SYMBOL_GPL(mas_destroy);
> >
> > @@ -6074,7 +6109,7 @@ bool mas_nomem(struct ma_state *mas, gfp_t gfp)
> >                 mas_alloc_nodes(mas, gfp);
> >         }
> >
> > -       if (!mas->sheaf)
> > +       if (!mas->sheaf && !mas->alloc)
> >                 return false;
> >
> >         mas->status = ma_start;
> >
> > --
> > 2.50.1
> >

Reply via email to