mm: move mmu notifier call from change_protection to change_pmd_range

The NUMA scanning code can end up iterating over many gigabytes of
unpopulated memory, especially in the case of a freshly started KVM
guest with lots of memory.

This results in the mmu notifier code being called even when there are
no mapped pages in a virtual address range.  The amount of time wasted
can be enough to trigger soft lockup warnings with very large KVM
guests.

This patch moves the mmu notifier call to the pmd level, which
represents 1GB areas of memory on x86-64.  Furthermore, the mmu notifier
code is only called from the address in the PMD where present mappings
are first encountered.

The hugetlbfs code is left alone for now; hugetlb mappings are not
relocatable, and as such are left alone by the NUMA code, and should
never trigger this problem to begin with.

Signed-off-by: Rik van Riel <[email protected]>
Acked-by: David Rientjes <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Reported-by: Xing Gang <[email protected]>
Tested-by: Chegu Vinod <[email protected]>
Cc: Sasha Levin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/hugetlb.c

@@ -3186,6 +3186,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
+	mmu_notifier_invalidate_range_start(mm, start, end);
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;
@@ -3215,6 +3216,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 */
 	flush_tlb_range(vma, start, end);
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages << h->order;
 }

mm/mprotect.c

@@ -140,9 +140,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pmd_t *pmd;
+	struct mm_struct *mm = vma->vm_mm;
 	unsigned long next;
 	unsigned long pages = 0;
 	unsigned long nr_huge_updates = 0;
+	unsigned long mni_start = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -151,6 +153,13 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		next = pmd_addr_end(addr, end);
 		if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
 			continue;
+
+		/* invoke the mmu notifier if the pmd is populated */
+		if (!mni_start) {
+			mni_start = addr;
+			mmu_notifier_invalidate_range_start(mm, mni_start, end);
+		}
+
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
@@ -175,6 +184,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (mni_start)
+		mmu_notifier_invalidate_range_end(mm, mni_start, end);
+
 	if (nr_huge_updates)
 		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
@@ -234,15 +246,12 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
 		       int dirty_accountable, int prot_numa)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	unsigned long pages;
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
 		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
-	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages;
 }