On Thu, Jun 16, 2022 at 09:30:33AM +0200, David Hildenbrand wrote:
> IIRC, that was used to skip these patches on the offlining path before
> we provided the ranges to offline_pages().
Yeah, it was designed for that purpose back then.
> I'd not mess with PG_reserved, and give them a clearer name, to not
> confuse them with other, ordinary, vmemmap pages that are not
> self-hosted (maybe in the future we might want to flag all vmemmap pages
> with a new type?).
Not sure whether a new type is really needed, or to put it another way, I
cannot see the benefit.
>
> I'd just try reusing the flag PG_owner_priv_1. And eventually, flag all
> (v)memmap pages with a type PG_memmap. However, the latter would be
> optional and might not be strictly required
>
>
> So what think could make sense is
>
> /* vmemmap pages that are self-hosted and cannot be optimized/freed. */
> PG_vmemmap_self_hosted = PG_owner_priv_1,
Sure, I just lightly tested the below, and seems to work, but not sure
whether that is what you are referring to.
@Munchun: thoughts?
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index e66f7aa3191d..a4556afd7bda 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -193,6 +193,11 @@ enum pageflags {
/* Only valid for buddy pages. Used to track pages that are reported */
PG_reported = PG_uptodate,
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+ /* For self-hosted memmap pages */
+ PG_vmemmap_self_hosted = PG_owner_priv_1,
+#endif
};
#define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1)
@@ -628,6 +633,10 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison)
*/
__PAGEFLAG(Reported, reported, PF_NO_COMPOUND)
+#ifdef CONFIG_MEMORY_HOTPLUG
+PAGEFLAG(Vmemmap_self_hosted, vmemmap_self_hosted, PF_ANY)
+#endif
+
/*
* On an anonymous page mapped into a user virtual memory area,
* page->mapping points to its anon_vma, not to a struct address_space;
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 1089ea8a9c98..e2de7ed27e9e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -101,6 +101,14 @@ void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
{
unsigned long vmemmap_addr = (unsigned long)head;
unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
+ struct mem_section *ms = __pfn_to_section(page_to_pfn(head));
+ struct page *memmap;
+
+ memmap = sparse_decode_mem_map(ms->section_mem_map,
+ pfn_to_section_nr(page_to_pfn(head)));
+
+ if (PageVmemmap_self_hosted(memmap))
+ return;
vmemmap_pages = hugetlb_optimize_vmemmap_pages(h);
if (!vmemmap_pages)
@@ -199,10 +207,10 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = {
static __init int hugetlb_vmemmap_sysctls_init(void)
{
/*
- * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
- * crosses page boundaries, the vmemmap pages cannot be optimized.
+ * If "struct page" crosses page boundaries, the vmemmap pages cannot
+ * be optimized.
*/
- if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
+ if (is_power_of_2(sizeof(struct page)))
register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
return 0;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1213d0c67a53..863966c2c6f1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -45,8 +45,6 @@
#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
static int memmap_on_memory_set(const char *val, const struct kernel_param *kp)
{
- if (hugetlb_optimize_vmemmap_enabled())
- return 0;
return param_set_bool(val, kp);
}
@@ -1032,6 +1030,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
{
unsigned long end_pfn = pfn + nr_pages;
int ret;
+ int i;
ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
if (ret)
@@ -1039,6 +1038,12 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE);
+ /*
+ * Let us flag self-hosted memmap
+ */
+ for (i = 0; i < nr_pages; i++)
+ SetPageVmemmap_self_hosted(pfn_to_page(pfn + i));
+
/*
* It might be that the vmemmap_pages fully span sections. If that is
* the case, mark those sections online here as otherwise they will be
--
Oscar Salvador
SUSE Labs
