mempolicy: alloc_pages_mpol() for NUMA policy without vma

Shrink shmem's stack usage by eliminating the pseudo-vma from its folio
allocation.  alloc_pages_mpol(gfp, order, pol, ilx, nid) becomes the
principal actor for passing mempolicy choice down to __alloc_pages(),
rather than vma_alloc_folio(gfp, order, vma, addr, hugepage).

vma_alloc_folio() and alloc_pages() remain, but as wrappers around
alloc_pages_mpol().  alloc_pages_bulk_*() untouched, except to provide the
additional args to policy_nodemask(), which subsumes policy_node(). 
Cleanup throughout, cutting out some unhelpful "helpers".

It would all be much simpler without MPOL_INTERLEAVE, but that adds a
dynamic to the constant mpol: complicated by v3.6 commit 09c231c
("tmpfs: distribute interleave better across nodes"), which added ino bias
to the interleave, hidden from mm/mempolicy.c until this commit.

Hence "ilx" throughout, the "interleave index".  Originally I thought it
could be done just with nid, but that's wrong: the nodemask may come from
the shared policy layer below a shmem vma, or it may come from the task
layer above a shmem vma; and without the final nodemask then nodeid cannot
be decided.  And how ilx is applied depends also on page order.

The interleave index is almost always irrelevant unless MPOL_INTERLEAVE:
with one exception in alloc_pages_mpol(), where the NO_INTERLEAVE_INDEX
passed down from vma-less alloc_pages() is also used as hint not to use
THP-style hugepage allocation - to avoid the overhead of a hugepage arg
(though I don't understand why we never just added a GFP bit for THP - if
it actually needs a different allocation strategy from other pages of the
same order).  vma_alloc_folio() still carries its hugepage arg here, but
it is not used, and should be removed when agreed.

get_vma_policy() no longer allows a NULL vma: over time I believe we've
eradicated all the places which used to need it e.g.  swapoff and madvise
used to pass NULL vma to read_swap_cache_async(), but now know the vma.

[[email protected]: handle NULL mpol being passed to __read_swap_cache_async()]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Hugh Dickins <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Huang Ying <[email protected]>
Cc: Kefeng Wang <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Nhat Pham <[email protected]>
Cc: Sidhartha Kumar <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Tejun heo <[email protected]>
Cc: Vishal Moola (Oracle) <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Yosry Ahmed <[email protected]>
Cc: Domenico Cerasuolo <[email protected]>
Cc: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

fs/proc/task_mmu.c

@@ -2673,8 +2673,9 @@ static int show_numa_map(struct seq_file *m, void *v)
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
-	struct mempolicy *pol;
 	char buffer[64];
+	struct mempolicy *pol;
+	pgoff_t ilx;
 	int nid;
 
 	if (!mm)
@@ -2683,7 +2684,7 @@ static int show_numa_map(struct seq_file *m, void *v)
 	/* Ensure we start with an empty set of numa_maps statistics. */
 	memset(md, 0, sizeof(*md));
 
-	pol = __get_vma_policy(vma, vma->vm_start);
+	pol = __get_vma_policy(vma, vma->vm_start, &ilx);
 	if (pol) {
 		mpol_to_str(buffer, sizeof(buffer), pol);
 		mpol_cond_put(pol);

include/linux/gfp.h

@@ -8,6 +8,7 @@
 #include <linux/topology.h>
 
 struct vm_area_struct;
+struct mempolicy;
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -262,14 +263,21 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 
 #ifdef CONFIG_NUMA
 struct page *alloc_pages(gfp_t gfp, unsigned int order);
-struct folio *folio_alloc(gfp_t gfp, unsigned order);
+struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx, int nid);
+struct folio *folio_alloc(gfp_t gfp, unsigned int order);
 struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, bool hugepage);
 #else
 static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
 	return alloc_pages_node(numa_node_id(), gfp_mask, order);
 }
+static inline struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx, int nid)
+{
+	return alloc_pages(gfp, order);
+}
 static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
 {
 	return __folio_alloc_node(gfp, order, numa_node_id());

include/linux/mempolicy.h

@@ -17,6 +17,8 @@
 
 struct mm_struct;
 
+#define NO_INTERLEAVE_INDEX (-1UL)	/* use task il_prev for interleaving */
+
 #ifdef CONFIG_NUMA
 
 /*
@@ -126,7 +128,9 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
-		unsigned long addr);
+		unsigned long addr, pgoff_t *ilx);
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+		unsigned long addr, int order, pgoff_t *ilx);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
@@ -140,8 +144,6 @@ extern int huge_node(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_in_oom_domain(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
-
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -179,6 +181,11 @@ extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
 
 struct mempolicy {};
 
+static inline struct mempolicy *get_task_policy(struct task_struct *p)
+{
+	return NULL;
+}
+
 static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
 	return true;
@@ -213,6 +220,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx)
 	return NULL;
 }
 
+static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+				unsigned long addr, int order, pgoff_t *ilx)
+{
+	*ilx = 0;
+	return NULL;
+}
+
 static inline int
 vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
 {

include/linux/mm.h

@@ -619,7 +619,7 @@ struct vm_operations_struct {
 	 * policy.
 	 */
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
-					unsigned long addr);
+					unsigned long addr, pgoff_t *ilx);
 #endif
 	/*
 	 * Called by vm_normal_page() for special PTEs to find the

ipc/shm.c

@@ -562,30 +562,25 @@ static unsigned long shm_pagesize(struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_NUMA
-static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
+	struct shm_file_data *sfd = shm_file_data(vma->vm_file);
 	int err = 0;
 
 	if (sfd->vm_ops->set_policy)
-		err = sfd->vm_ops->set_policy(vma, new);
+		err = sfd->vm_ops->set_policy(vma, mpol);
 	return err;
 }
 
 static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
-					unsigned long addr)
+					unsigned long addr, pgoff_t *ilx)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
-	struct mempolicy *pol = NULL;
+	struct shm_file_data *sfd = shm_file_data(vma->vm_file);
+	struct mempolicy *mpol = vma->vm_policy;
 
 	if (sfd->vm_ops->get_policy)
-		pol = sfd->vm_ops->get_policy(vma, addr);
-	else if (vma->vm_policy)
-		pol = vma->vm_policy;
-
-	return pol;
+		mpol = sfd->vm_ops->get_policy(vma, addr, ilx);
+	return mpol;
 }
 #endif