On 2024/1/18 20:39, Gang Li wrote:
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.
Signed-off-by: Gang Li <gang.li@xxxxxxxxx>
Tested-by: David Rientjes <rientjes@xxxxxxxxxx>
---
mm/hugetlb.c | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 98ae108e1fac..effe5539e545 100644
--- 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) {
A small question here, why not pass h->next_nid_to_alloc to
for_each_node_mask_to_alloc()? What's the purpose of the third
parameter of alloc_pool_huge_folio()?
Thanks.
