hugetlb: pass *next_nid_to_alloc directly to for_each_node_mask_to_alloc

With parallelization of hugetlb allocation across different threads, each
thread works on a differnet node to allocate pages from, instead of all
allocating from a common node h->next_nid_to_alloc.  To address this, it's
necessary to assign a separate next_nid_to_alloc for each thread.

Consequently, the hstate_next_node_to_alloc and
for_each_node_mask_to_alloc have been modified to directly accept a
*next_nid_to_alloc parameter, ensuring thread-specific allocation and
avoiding concurrent access issues.

Link: https://lkml.kernel.org/r/20240222140422.393911-4-gang.li@linux.dev
Signed-off-by: Gang Li <ligang.bdlg@bytedance.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c1de29f2b5a227a42506d2601bb2bc31f33684e6..1c8274f8650ec793762124a54379fff07e8e9b76 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1464,15 +1464,15 @@ static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
  * next node from which to allocate, handling wrap at end of node
  * mask.
  */
-static int hstate_next_node_to_alloc(struct hstate *h,
+static int hstate_next_node_to_alloc(int *next_node,
                                        nodemask_t *nodes_allowed)
 {
        int nid;
 
        VM_BUG_ON(!nodes_allowed);
 
-       nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
-       h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);
+       nid = get_valid_node_allowed(*next_node, nodes_allowed);
+       *next_node = next_node_allowed(nid, nodes_allowed);
 
        return nid;
 }
@@ -1495,10 +1495,10 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
        return nid;
 }
 
-#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask)          \
+#define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask)           \
        for (nr_nodes = nodes_weight(*mask);                            \
                nr_nodes > 0 &&                                         \
-               ((node = hstate_next_node_to_alloc(hs, mask)) || 1);    \
+               ((node = hstate_next_node_to_alloc(next_node, mask)) || 1);     \
                nr_nodes--)
 
 #define for_each_node_mask_to_free(hs, nr_nodes, node, mask)           \
@@ -2350,12 +2350,13 @@ static void prep_and_add_allocated_folios(struct hstate *h,
  */
 static struct folio *alloc_pool_huge_folio(struct hstate *h,
                                        nodemask_t *nodes_allowed,
-                                       nodemask_t *node_alloc_noretry)
+                                       nodemask_t *node_alloc_noretry,
+                                       int *next_node)
 {
        gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
        int nr_nodes, node;
 
-       for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+       for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) {
                struct folio *folio;
 
                folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node,
@@ -3310,7 +3311,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
                goto found;
        }
        /* allocate from next node when distributing huge pages */
-       for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
+       for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) {
                m = memblock_alloc_try_nid_raw(
                                huge_page_size(h), huge_page_size(h),
                                0, MEMBLOCK_ALLOC_ACCESSIBLE, node);
@@ -3679,7 +3680,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
        VM_BUG_ON(delta != -1 && delta != 1);
 
        if (delta < 0) {
-               for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+               for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) {
                        if (h->surplus_huge_pages_node[node])
                                goto found;
                }
@@ -3794,7 +3795,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
                cond_resched();
 
                folio = alloc_pool_huge_folio(h, nodes_allowed,
-                                               node_alloc_noretry);
+                                               node_alloc_noretry,
+                                               &h->next_nid_to_alloc);
                if (!folio) {
                        prep_and_add_allocated_folios(h, &page_list);
                        spin_lock_irq(&hugetlb_lock);