The patch titled
Subject: hugetlb: perform vmemmap optimization on a list of pages
has been added to the -mm mm-unstable branch. Its filename is
hugetlb-perform-vmemmap-optimization-on-a-list-of-pages.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-perform-vmemmap-optimization-on-a-list-of-pages.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: perform vmemmap optimization on a list of pages
Date: Wed, 18 Oct 2023 19:31:05 -0700
When adding hugetlb pages to the pool, we first create a list of the
allocated pages before adding to the pool. Pass this list of pages to a
new routine hugetlb_vmemmap_optimize_folios() for vmemmap optimization.
Due to significant differences in vmemmmap initialization for bootmem
allocated hugetlb pages, a new routine prep_and_add_bootmem_folios is
created.
We also modify the routine vmemmap_should_optimize() to check for pages
that are already optimized. There are code paths that might request
vmemmap optimization twice and we want to make sure this is not attempted.
Link: https://lkml.kernel.org/r/20231019023113.345257-4-mike.kravetz@xxxxxxxxxx
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reviewed-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: Barry Song <21cnbao@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: James Houghton <jthoughton@xxxxxxxxxx>
Cc: Joao Martins <joao.m.martins@xxxxxxxxxx>
Cc: Konrad Dybcio <konradybcio@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
Cc: Usama Arif <usama.arif@xxxxxxxxxxxxx>
Cc: Xiongchun Duan <duanxiongchun@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 43 +++++++++++++++++++++++++++++++++--------
mm/hugetlb_vmemmap.c | 11 ++++++++++
mm/hugetlb_vmemmap.h | 5 ++++
3 files changed, 51 insertions(+), 8 deletions(-)
--- a/mm/hugetlb.c~hugetlb-perform-vmemmap-optimization-on-a-list-of-pages
+++ a/mm/hugetlb.c
@@ -2282,6 +2282,9 @@ static void prep_and_add_allocated_folio
unsigned long flags;
struct folio *folio, *tmp_f;
+ /* Send list for bulk vmemmap optimization processing */
+ hugetlb_vmemmap_optimize_folios(h, folio_list);
+
/* Add all new pool pages to free lists in one lock cycle */
spin_lock_irqsave(&hugetlb_lock, flags);
list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
@@ -3326,6 +3329,35 @@ static void __init hugetlb_folio_init_vm
prep_compound_head((struct page *)folio, huge_page_order(h));
}
+static void __init prep_and_add_bootmem_folios(struct hstate *h,
+ struct list_head *folio_list)
+{
+ unsigned long flags;
+ struct folio *folio, *tmp_f;
+
+ /* Send list for bulk vmemmap optimization processing */
+ hugetlb_vmemmap_optimize_folios(h, folio_list);
+
+ /* Add all new pool pages to free lists in one lock cycle */
+ spin_lock_irqsave(&hugetlb_lock, flags);
+ list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
+ if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
+ /*
+ * If HVO fails, initialize all tail struct pages
+ * We do not worry about potential long lock hold
+ * time as this is early in boot and there should
+ * be no contention.
+ */
+ hugetlb_folio_init_tail_vmemmap(folio,
+ HUGETLB_VMEMMAP_RESERVE_PAGES,
+ pages_per_huge_page(h));
+ }
+ __prep_account_new_huge_page(h, folio_nid(folio));
+ enqueue_hugetlb_folio(h, folio);
+ }
+ spin_unlock_irqrestore(&hugetlb_lock, flags);
+}
+
/*
* Put bootmem huge pages into the standard lists after mem_map is up.
* Note: This only applies to gigantic (order > MAX_ORDER) pages.
@@ -3346,7 +3378,7 @@ static void __init gather_bootmem_preall
* in this list. If so, process each size separately.
*/
if (h != prev_h && prev_h != NULL)
- prep_and_add_allocated_folios(prev_h, &folio_list);
+ prep_and_add_bootmem_folios(prev_h, &folio_list);
prev_h = h;
VM_BUG_ON(!hstate_is_gigantic(h));
@@ -3354,12 +3386,7 @@ static void __init gather_bootmem_preall
hugetlb_folio_init_vmemmap(folio, h,
HUGETLB_VMEMMAP_RESERVE_PAGES);
- __prep_new_hugetlb_folio(h, folio);
- /* If HVO fails, initialize all tail struct pages */
- if (!HPageVmemmapOptimized(&folio->page))
- hugetlb_folio_init_tail_vmemmap(folio,
- HUGETLB_VMEMMAP_RESERVE_PAGES,
- pages_per_huge_page(h));
+ init_new_hugetlb_folio(h, folio);
list_add(&folio->lru, &folio_list);
/*
@@ -3371,7 +3398,7 @@ static void __init gather_bootmem_preall
cond_resched();
}
- prep_and_add_allocated_folios(h, &folio_list);
+ prep_and_add_bootmem_folios(h, &folio_list);
}
static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
--- a/mm/hugetlb_vmemmap.c~hugetlb-perform-vmemmap-optimization-on-a-list-of-pages
+++ a/mm/hugetlb_vmemmap.c
@@ -483,6 +483,9 @@ int hugetlb_vmemmap_restore(const struct
/* Return true iff a HugeTLB whose vmemmap should and can be optimized. */
static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head)
{
+ if (HPageVmemmapOptimized((struct page *)head))
+ return false;
+
if (!READ_ONCE(vmemmap_optimize_enabled))
return false;
@@ -572,6 +575,14 @@ void hugetlb_vmemmap_optimize(const stru
SetHPageVmemmapOptimized(head);
}
+void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+ struct folio *folio;
+
+ list_for_each_entry(folio, folio_list, lru)
+ hugetlb_vmemmap_optimize(h, &folio->page);
+}
+
static struct ctl_table hugetlb_vmemmap_sysctls[] = {
{
.procname = "hugetlb_optimize_vmemmap",
--- a/mm/hugetlb_vmemmap.h~hugetlb-perform-vmemmap-optimization-on-a-list-of-pages
+++ a/mm/hugetlb_vmemmap.h
@@ -20,6 +20,7 @@
#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head);
void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head);
+void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list);
static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h)
{
@@ -48,6 +49,10 @@ static inline void hugetlb_vmemmap_optim
{
}
+static inline void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+}
+
static inline unsigned int hugetlb_vmemmap_optimizable_size(const struct hstate *h)
{
return 0;
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-optimize-update_and_free_pages_bulk-to-avoid-lock-cycles.patch
hugetlb-restructure-pool-allocations.patch
hugetlb-perform-vmemmap-optimization-on-a-list-of-pages.patch
hugetlb-perform-vmemmap-restoration-on-a-list-of-pages.patch
hugetlb-batch-freeing-of-vmemmap-pages.patch
hugetlb-batch-tlb-flushes-when-restoring-vmemmap.patch
