mm: sparsemem: use page table lock to protect kernel pmd operations

The init_mm.page_table_lock is used to protect kernel page tables, we
can use it to serialize splitting vmemmap PMD mappings instead of mmap
write lock, which can increase the concurrency of vmemmap_remap_free().

Actually, It increase the concurrency between allocations of HugeTLB
pages.  But it is not the only benefit.  There are a lot of users of
mmap read lock of init_mm.  The mmap write lock is holding through
vmemmap_remap_free(), removing mmap write lock usage to make it does not
affect other users of mmap read lock.  It is not making anything worse
and always a win to move.

Now the kernel page table walker does not hold the page_table_lock when
walking pmd entries.  There may be consistency issue of a pmd entry,
because pmd entry might change from a huge pmd entry to a PTE page
table.  There is only one user of kernel page table walker, namely
ptdump.  The ptdump already considers the consistency, which use a local
variable to cache the value of pmd entry.  But we also need to update
->action to ACTION_CONTINUE to make sure the walker does not walk every
pte entry again when concurrent thread has split the huge pmd.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Muchun Song <[email protected]>
Cc: Barry Song <[email protected]>
Cc: Bodeddula Balasubramaniam <[email protected]>
Cc: Chen Huang <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Fam Zheng <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Qi Zheng <[email protected]>
Cc: Xiongchun Duan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Muchun Song

mm/ptdump.c

@@ -40,8 +40,10 @@ static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
 	if (st->effective_prot)
 		st->effective_prot(st, 0, pgd_val(val));
 
-	if (pgd_leaf(val))
+	if (pgd_leaf(val)) {
 		st->note_page(st, addr, 0, pgd_val(val));
+		walk->action = ACTION_CONTINUE;
+	}
 
 	return 0;
 }
@@ -61,8 +63,10 @@ static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
 	if (st->effective_prot)
 		st->effective_prot(st, 1, p4d_val(val));
 
-	if (p4d_leaf(val))
+	if (p4d_leaf(val)) {
 		st->note_page(st, addr, 1, p4d_val(val));
+		walk->action = ACTION_CONTINUE;
+	}
 
 	return 0;
 }
@@ -82,8 +86,10 @@ static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
 	if (st->effective_prot)
 		st->effective_prot(st, 2, pud_val(val));
 
-	if (pud_leaf(val))
+	if (pud_leaf(val)) {
 		st->note_page(st, addr, 2, pud_val(val));
+		walk->action = ACTION_CONTINUE;
+	}
 
 	return 0;
 }
@@ -101,8 +107,10 @@ static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
 
 	if (st->effective_prot)
 		st->effective_prot(st, 3, pmd_val(val));
-	if (pmd_leaf(val))
+	if (pmd_leaf(val)) {
 		st->note_page(st, addr, 3, pmd_val(val));
+		walk->action = ACTION_CONTINUE;
+	}
 
 	return 0;
 }

mm/sparse-vmemmap.c

@@ -53,8 +53,7 @@ struct vmemmap_remap_walk {
 	struct list_head *vmemmap_pages;
 };
 
-static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start,
-				  struct vmemmap_remap_walk *walk)
+static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 {
 	pmd_t __pmd;
 	int i;
@@ -76,15 +75,34 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start,
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
 
-	/* Make pte visible before pmd. See comment in pmd_install(). */
-	smp_wmb();
-	pmd_populate_kernel(&init_mm, pmd, pgtable);
-
-	flush_tlb_kernel_range(start, start + PMD_SIZE);
+	spin_lock(&init_mm.page_table_lock);
+	if (likely(pmd_leaf(*pmd))) {
+		/* Make pte visible before pmd. See comment in pmd_install(). */
+		smp_wmb();
+		pmd_populate_kernel(&init_mm, pmd, pgtable);
+		flush_tlb_kernel_range(start, start + PMD_SIZE);
+	} else {
+		pte_free_kernel(&init_mm, pgtable);
+	}
+	spin_unlock(&init_mm.page_table_lock);
 
 	return 0;
 }
 
+static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
+{
+	int leaf;
+
+	spin_lock(&init_mm.page_table_lock);
+	leaf = pmd_leaf(*pmd);
+	spin_unlock(&init_mm.page_table_lock);
+
+	if (!leaf)
+		return 0;
+
+	return __split_vmemmap_huge_pmd(pmd, start);
+}
+
 static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
 			      unsigned long end,
 			      struct vmemmap_remap_walk *walk)
@@ -121,13 +139,12 @@ static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
 
 	pmd = pmd_offset(pud, addr);
 	do {
-		if (pmd_leaf(*pmd)) {
-			int ret;
+		int ret;
+
+		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK);
+		if (ret)
+			return ret;
 
-			ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk);
-			if (ret)
-				return ret;
-		}
 		next = pmd_addr_end(addr, end);
 		vmemmap_pte_range(pmd, addr, next, walk);
 	} while (pmd++, addr = next, addr != end);
@@ -321,10 +338,8 @@ int vmemmap_remap_free(unsigned long start, unsigned long end,
 	 */
 	BUG_ON(start - reuse != PAGE_SIZE);
 
-	mmap_write_lock(&init_mm);
+	mmap_read_lock(&init_mm);
 	ret = vmemmap_remap_range(reuse, end, &walk);
-	mmap_write_downgrade(&init_mm);
-
 	if (ret && walk.nr_walked) {
 		end = reuse + walk.nr_walked * PAGE_SIZE;
 		/*