We need all allocation and free sites to use the ptdesc APIs in order to allocate them separately from regular pages. Convert the pte allocation/free sites to use the generic page table apis, since those use ptdescs already. Pass through init_mm since these are kernel page tables, pte_alloc_one_kernel() effectively becomes a no-op otherwise. Signed-off-by: Vishal Moola (Oracle) --- arch/x86/mm/pat/set_memory.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 6c6eb486f7a6..d52010fd3023 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1408,7 +1408,7 @@ static bool try_to_free_pte_page(pte_t *pte) if (!pte_none(pte[i])) return false; - free_page((unsigned long)pte); + pte_free_kernel(&init_mm, pte); return true; } @@ -1539,7 +1539,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) static int alloc_pte_page(pmd_t *pmd) { - pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL); + pte_t *pte = pte_alloc_one_kernel(&init_mm); if (!pte) return -1; -- 2.53.0 We need all allocation and free sites to use the ptdesc APIs in order to allocate them separately from regular pages. Convert the pmd allocation/free sites to use the generic page table apis, since those use ptdescs already. Pass through init_mm since these are kernel page tables, pmd_alloc_one() needs it to identify kernel page tables. Also, the generic implementation doesn't use the second argument. Pass it a placeholder so we don't have to reimplement it or risk breaking other architectures. Signed-off-by: Vishal Moola (Oracle) --- arch/x86/mm/pat/set_memory.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index d52010fd3023..655bef618ea0 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1420,7 +1420,7 @@ static bool try_to_free_pmd_page(pmd_t *pmd) if (!pmd_none(pmd[i])) return false; - free_page((unsigned long)pmd); + pmd_free(&init_mm, pmd); return true; } @@ -1549,7 +1549,10 @@ static int alloc_pte_page(pmd_t *pmd) static int alloc_pmd_page(pud_t *pud) { - pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); + /* The generic implementation of pmd_alloc_one() doesn't use + * the second argument. Pass it 0 as a placeholder. + */ + pmd_t *pmd = pmd_alloc_one(&init_mm, 0); if (!pmd) return -1; -- 2.53.0 We need all allocation and free sites to use the ptdesc APIs in order to allocate them separately from regular pages. Convert the remaining get_zeroed_page() calls to the generic page table apis, since those use ptdescs already. Pass through init_mm since these are kernel page tables, both functions need it to identify kernel page tables. Also, the generic implementations don't use the second argument. Pass it a placeholder so we don't have to reimplement it or risk breaking other architectures. Its not obvious if these pages get freed. Regardless, the only other possible free paths have already been converted, and my frozen page table test kernel hasn't found any issues. Signed-off-by: Vishal Moola (Oracle) --- arch/x86/mm/pat/set_memory.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 655bef618ea0..8f74d4bfd591 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1746,7 +1746,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) pgd_entry = cpa->pgd + pgd_index(addr); if (pgd_none(*pgd_entry)) { - p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); + /* The generic implementation of p4d_alloc_one() + * doesn't use the second argument. Pass it 0 as + * a placeholder. + */ + p4d = p4d_alloc_one(&init_mm, 0); if (!p4d) return -1; @@ -1758,7 +1762,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) */ p4d = p4d_offset(pgd_entry, addr); if (p4d_none(*p4d)) { - pud = (pud_t *)get_zeroed_page(GFP_KERNEL); + /* The generic implementation of pud_alloc_one() + * doesn't use the second argument. Pass it 0 as + * a placeholder. + */ + pud = pud_alloc_one(&init_mm, 0); if (!pud) return -1; -- 2.53.0 In order to separately allocate ptdescs from pages, we need all allocation and free sites to use the appropriate functions. split_large_page() allocates a page to be used as a page table. This should be allocating a ptdesc, so convert it. Signed-off-by: Vishal Moola (Oracle) Acked-by: Mike Rapoport (Microsoft) --- arch/x86/mm/pat/set_memory.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 8f74d4bfd591..e26535f3b8bd 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1119,9 +1119,10 @@ static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn, static int __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, - struct page *base) + struct ptdesc *ptdesc) { unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; + struct page *base = ptdesc_page(ptdesc); pte_t *pbase = (pte_t *)page_address(base); unsigned int i, level; pgprot_t ref_prot; @@ -1226,18 +1227,18 @@ __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 page *base; + struct ptdesc *ptdesc; if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); - base = alloc_pages(GFP_KERNEL, 0); + ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); - if (!base) + if (!ptdesc) return -ENOMEM; - if (__split_large_page(cpa, kpte, address, base)) - __free_page(base); + if (__split_large_page(cpa, kpte, address, ptdesc)) + pagetable_free(ptdesc); return 0; } -- 2.53.0