On 2026/9/8 11:03, Muchun Song wrote:
HugeTLB vmemmap optimization now uses per-zone shared tail vmemmap pages.
Device DAX has not been switched to that mechanism yet.
Switch device DAX to vmemmap_shared_tail_page() as well. This aligns DAX
with HugeTLB by using the common per-zone shared tail vmemmap page.
The optimization is enabled only for DEV-DAX through pgmap->vmemmap_shift,
which is assigned when a DEV-DAX device is initialized. Unlike FS-DAX,
DEV-DAX does not modify tail struct pages, so sharing them is safe.
Since the shared tail page can now back ZONE_DEVICE vmemmap mappings,
initialize its entries with PG_reserved for device zones. Also skip
poisoning vmemmap-optimizable sections while their struct pages may be
shared.
Signed-off-by: Muchun Song <[email protected]>
---
v2:
- Explain why sharing tail vmemmap pages is safe for DEV-DAX
(suggested by Qi Zheng)
---
include/linux/mmzone.h | 10 +++++++++
mm/memory_hotplug.c | 5 +++--
mm/sparse-vmemmap.c | 47 ++++++++++++++----------------------------
3 files changed, 28 insertions(+), 34 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d3778ba976a5..03ed9232f186 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1686,11 +1686,21 @@ static inline bool zone_is_zone_device(const struct
zone *zone)
{
return zone_idx(zone) == ZONE_DEVICE;
}
+
+static inline struct zone *device_zone(int nid)
+{
+ return &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+}
#else
static inline bool zone_is_zone_device(const struct zone *zone)
{
return false;
}
+
+static inline struct zone *device_zone(int nid)
+{
+ return NULL;
+}
#endif
/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b428da66d279..0db0379826df 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -554,8 +554,9 @@ void remove_pfn_range_from_zone(struct zone *zone,
/* Select all remaining pages up to the next section boundary */
cur_nr_pages =
min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn);
- page_init_poison(pfn_to_page(pfn),
- sizeof(struct page) * cur_nr_pages);
+ if (!section_vmemmap_optimizable(__pfn_to_section(pfn)))
+ page_init_poison(pfn_to_page(pfn),
+ sizeof(struct page) * cur_nr_pages);
}
/*
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aed1e7429daa..0201877a7f80 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -193,6 +193,8 @@ struct page __ref *vmemmap_shared_tail_page(unsigned int
order, struct zone *zon
set_page_node(page, zone_to_nid(zone));
set_page_zone(page, zone_idx(zone));
prep_compound_tail(page, NULL, order);
+ if (zone_is_zone_device(zone))
+ __SetPageReserved(page);
Sashiko said: "
Could setting PG_reserved here cause a use-after-free
during device hot-remove?
When a DEV-DAX device is removed and vmemmap_free is called,
remove_pte_table calls free_vmemmap_pages. In free_vmemmap_pages,
the PG_reserved flag redirects execution:
arch/x86/mm/init_64.c:free_vmemmap_pages() {
...
else if (PageReserved(page))
free_reserved_pages(page, order);
}
Does this forcefully drop the refcount and free the shared
page to the buddy allocator, leaving a dangling pointer in
zone->vmemmap_tails[idx] that breaks other DAX devices
sharing this page?
"
It is a false positive.
The struct page marked reserved here is an entry stored
inside the shared vmemmap backing page; after mapping, it
represents a Device DAX tail page. It is not the struct
page describing the backing page itself.
remove_pte_table() passes pte_page(*pte) to free_vmemmap_pages(),
which is the latter. The runtime-allocated backing page is
not reserved, so removal takes the __free_pages() path. Each
reused PTE takes a reference via get_page(), and removal
drops one such reference, while the allocation reference
retained by zone->vmemmap_tails[] remains. Therefore removing
one DAX device does not free the shared backing page or leave
a dangling pointer.
}
page = virt_to_page(addr);
@@ -490,23 +492,6 @@ static bool __meminit reuse_compound_section(unsigned long
start_pfn,
return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION;
}
-static pte_t * __meminit compound_section_tail_page(unsigned long addr)
-{
- pte_t *pte;
-
- addr -= PAGE_SIZE;
-
- /*
- * Assuming sections are populated sequentially, the previous section's
- * page data can be reused.
- */
- pte = pte_offset_kernel(pmd_off_k(addr), addr);
- if (!pte)
- return NULL;
-
- return pte;
-}
-
static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
unsigned long start,
unsigned long end, int
node,
@@ -516,21 +501,18 @@ static int __meminit
vmemmap_populate_compound_pages(unsigned long start_pfn,
pte_t *pte;
int rc;
unsigned long flags = VMEMMAP_POPULATE_DAX;
+ struct page *page;
+ unsigned int order = pfn_to_section_order(start_pfn);
- if (reuse_compound_section(start_pfn, pgmap)) {
- pte = compound_section_tail_page(start);
- if (!pte)
- return -ENOMEM;
+ page = vmemmap_shared_tail_page(order, device_zone(node));
+ if (!page)
+ return -ENOMEM;
- /*
- * Reuse the page that was populated in the prior iteration
- * with just tail struct pages.
- */
+ if (reuse_compound_section(start_pfn, pgmap))
return vmemmap_populate_range(start, end, node, NULL,
- pte_pfn(ptep_get(pte)), flags);
- }
+ page_to_pfn(page), flags);
- size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
+ size = min(end - start, (1UL << order) * sizeof(struct page));
for (addr = start; addr < end; addr += size) {
unsigned long next, last = addr + size;
@@ -546,12 +528,12 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
return -ENOMEM;
/*
- * Reuse the previous page for the rest of tail pages
+ * Reuse the shared page for the rest of tail pages
* See layout diagram in Documentation/mm/vmemmap_dedup.rst
*/
next += PAGE_SIZE;
rc = vmemmap_populate_range(next, last, node, NULL,
- pte_pfn(ptep_get(pte)), flags);
+ page_to_pfn(page), flags);
Another report is like:
"
When this shared tail page is used to back the
DEV-DAX tail pages, could concurrent initialization
corrupt the compound_head pointer for the entire
node?
Looking at memmap_init_zone_device which calls
memmap_init_compound, the head page template is copied
unconditionally into the tail pages:
mm/mm_init.c:memmap_init_compound() {
for (pfn = head_pfn + 2; pfn < end_pfn; pfn++)
zone_device_page_init_from_template(pfn_to_page(pfn), pfn,
&template);
}
Since page_to_pfn(page) here points to a node-wide
shared physical page, would this template copy overwrite
the compound_head for all DEV-DAX tail pages on the node
to point to the latest initialized PMD's head page?
"
This is also a false positive.
memmap_init_compound() does not initialize the full
compound range when the section uses vmemmap optimization.
compound_nr_pages() limits it to:
2 * PAGE_SIZE / sizeof(struct page)
i.e. exactly the entries in the retained vmemmap page.
The shared mappings start at addr + PAGE_SIZE, so the
template-copy loop stops before reaching them.
Thanks
Muchun
if (rc)
return -ENOMEM;
}
@@ -883,13 +865,14 @@ int __meminit sparse_add_section(int nid, unsigned long
start_pfn,
if (IS_ERR(memmap))
return PTR_ERR(memmap);
+ ms = __nr_to_section(section_nr);
/*
* Poison uninitialized struct pages in order to catch invalid flags
* combinations.
*/
- page_init_poison(memmap, sizeof(struct page) * nr_pages);
+ if (!section_vmemmap_optimizable(ms))
+ page_init_poison(memmap, sizeof(struct page) * nr_pages);
- ms = __nr_to_section(section_nr);
__section_mark_present(ms, section_nr);
/* Align memmap to section boundary in the subsection case */
