From 4bbc16994e86b98bd8daa73afd27b77c7da42266 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Tue, 21 Jul 2026 13:14:52 +0100 Subject: [PATCH] x86/mm/pat: allocate split page tables as kernel page tables When splitting a large page in CPA in __split_large_page() we allocate a PTE directly without going through the standard page table allocation routines such as pte_alloc_one_kernel(). This means the page table constructor is never called nor is the page table marked as a kernel page table. The former results in the folio associated with the page table not being marked as a page table (__pagetable_ctor() is never called thus neither is __folio_set_pgtable()) nor are statistics updated to reflect it (lruvec_stat_add_folio() is never called). The latter issue of failing to mark the page table as a kernel page table (ptdesc_set_kernel() is never called) is far more problematic. Since commit 5ba2f0a15564 ("mm: introduce deferred freeing for kernel page tables") kernel page table freeing has been batched and since the subsequent commit e37d5a2d60a3 ("iommu/sva: invalidate stale IOTLB entries for kernel address space") IOTLB cache entries for kernel page tables have been invalidated upon being freed. Since split page tables are freed without this invalidation, the IOTLB can contain stale entries for them. Resolve the issue by using the ordinary PTE allocation API at split time. This results in these kernel page tables invoking a page table constructor, and thus requires a page table destructor. Since we cannot assume one is always present (early allocated direct map page tables are not marked as such), we conditionally call pagetable_dtor_free() if the PG_table folio flag for the ptdesc is set, otherwise we free the page table via pagetable_free(). Regardless of which path is taken page tables marked as kernel page tables, which now includes split page tables, take the correct route through pagetable_free_kernel(). There is a user-visible side effect in that split page tables will appear in nr_page_table_pages in /proc/vmstat (as do other kernel page tables allocated after early boot), however this is a positive change. This issue started being markedly problematic after commit 5ba2f0a15564 ("mm: introduce deferred freeing for kernel page tables") so choose this as the Fixes target. Link: https://lore.kernel.org/20260721-fix-cpa-kernel-pagetables-v2-1-2b255deed710@kernel.org Fixes: 5ba2f0a15564 ("mm: introduce deferred freeing for kernel page tables") Signed-off-by: Lorenzo Stoakes (ARM) Acked-by: Vishal Moola Cc: Andy Lutomirski Cc: Baolu Lu Cc: "Borislav Petkov (AMD)" Cc: Dave Hansen Cc: David Hildenbrand Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Kevin Tian Cc: Kiryl Shutsemau Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton --- arch/x86/mm/pat/set_memory.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 618f72096480..422ce7fba00c 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -440,7 +440,15 @@ static void __cpa_collapse_large_pages(struct cpa_data *cpa) list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) { list_del(&ptdesc->pt_list); - pagetable_free(ptdesc); + /* + * Only early alloc'd direct map should not be flagged PG_table + * here and those shouldn't be collapsed. However be abundantly + * cautious and handle the !PG_table case too. + */ + if (PageTable((ptdesc_page(ptdesc)))) + pagetable_dtor_free(ptdesc); + else + pagetable_free(ptdesc); } } @@ -1139,11 +1147,10 @@ set: static int __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, - struct ptdesc *ptdesc) + pte_t *pbase) { unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; - struct page *base = ptdesc_page(ptdesc); - pte_t *pbase = (pte_t *)page_address(base); + struct page *base = virt_to_page(pbase); unsigned int i, level; pgprot_t ref_prot; bool nx, rw; @@ -1247,22 +1254,22 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, static int split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address) { - struct ptdesc *ptdesc; + pte_t *pte; if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); if (cpa->init_mm_read_locked) mmap_read_unlock(&init_mm); - ptdesc = pagetable_alloc(GFP_KERNEL, 0); + pte = pte_alloc_one_kernel(&init_mm); if (cpa->init_mm_read_locked) mmap_read_lock(&init_mm); if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); - if (!ptdesc) + if (!pte) return -ENOMEM; - if (__split_large_page(cpa, kpte, address, ptdesc)) - pagetable_free(ptdesc); + if (__split_large_page(cpa, kpte, address, pte)) + pte_free_kernel(&init_mm, pte); return 0; }