mm/vmalloc: Enter lazy mmu mode while manipulating vmalloc ptes

Wrap vmalloc's pte table manipulation loops with
arch_enter_lazy_mmu_mode() / arch_leave_lazy_mmu_mode(). This provides
the arch code with the opportunity to optimize the pte manipulations.

Note that vmap_pfn() already uses lazy mmu mode since it delegates to
apply_to_page_range() which enters lazy mmu mode for both user and
kernel mappings.

These hooks will shortly be used by arm64 to improve vmalloc
performance.

Reviewed-by: Uladzislau Rezki (Sony) <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Reviewed-by: Anshuman Khandual <[email protected]>
Signed-off-by: Ryan Roberts <[email protected]>
Tested-by: Luiz Capitulino <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Ryan Roberts

mm/vmalloc.c

@@ -104,6 +104,9 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte = pte_alloc_kernel_track(pmd, addr, mask);
 	if (!pte)
 		return -ENOMEM;
+
+	arch_enter_lazy_mmu_mode();
+
 	do {
 		if (unlikely(!pte_none(ptep_get(pte)))) {
 			if (pfn_valid(pfn)) {
@@ -127,6 +130,8 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
 		pfn++;
 	} while (pte += PFN_DOWN(size), addr += size, addr != end);
+
+	arch_leave_lazy_mmu_mode();
 	*mask |= PGTBL_PTE_MODIFIED;
 	return 0;
 }
@@ -354,6 +359,8 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	unsigned long size = PAGE_SIZE;
 
 	pte = pte_offset_kernel(pmd, addr);
+	arch_enter_lazy_mmu_mode();
+
 	do {
 #ifdef CONFIG_HUGETLB_PAGE
 		size = arch_vmap_pte_range_unmap_size(addr, pte);
@@ -370,6 +377,8 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			ptent = ptep_get_and_clear(&init_mm, addr, pte);
 		WARN_ON(!pte_none(ptent) && !pte_present(ptent));
 	} while (pte += (size >> PAGE_SHIFT), addr += size, addr != end);
+
+	arch_leave_lazy_mmu_mode();
 	*mask |= PGTBL_PTE_MODIFIED;
 }
 
@@ -515,6 +524,9 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	pte = pte_alloc_kernel_track(pmd, addr, mask);
 	if (!pte)
 		return -ENOMEM;
+
+	arch_enter_lazy_mmu_mode();
+
 	do {
 		struct page *page = pages[*nr];
 
@@ -528,6 +540,8 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
 		(*nr)++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	arch_leave_lazy_mmu_mode();
 	*mask |= PGTBL_PTE_MODIFIED;
 	return 0;
 }