[PATCH] x86/vmemmap: Handle unpopulated sub-pmd ranges

[Oscar Salvador <osalvador@suse.de>]

When the size of a struct page is not multiple of 2MB, sections do
not span a PMD anymore and so when populating them some parts of the
PMD will remain unused.
Because of this, PMDs will be left behind when depopulating sections
since remove_pmd_table() thinks that those unused parts are still in
use.

Fix this by marking the unused parts with PAGE_INUSE, so memchr_inv() will
do the right thing and will let us free the PMD when the last user of it
is gone.

This patch is based on a similar patch by David Hildenbrand:

https://lore.kernel.org/linux-mm/20200722094558.9828-9-david@redhat.com/
https://lore.kernel.org/linux-mm/20200722094558.9828-10-david@redhat.com/

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c | 81 +++++++++++++++++++++++++++++++++++++++----
 1 file changed, 74 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b5a3fa4033d3..9b6d45ea353b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -873,6 +873,71 @@ int arch_add_memory(int nid, u64 start, u64 size,
 
 #define PAGE_INUSE 0xFD
 
+/*
+ * The unused vmemmap range, which was not yet memset(PAGE_INUSE) ranges
+ * from unused_pmd_start to next PMD_SIZE boundary.
+ */
+static unsigned long unused_pmd_start __meminitdata;
+
+static void __meminit vmemmap_flush_unused_pmd(void)
+{
+	if (!unused_pmd_start)
+		return;
+	/*
+	 * Clears (unused_pmd_start, PMD_END]
+	 */
+	memset((void *)unused_pmd_start, PAGE_INUSE,
+	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
+	unused_pmd_start = 0;
+}
+
+/* Returns true if the PMD is completely unused and thus it can be freed */
+static bool __meminit vmemmap_unuse_sub_pmd(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	vmemmap_flush_unused_pmd();
+	memset((void *)addr, PAGE_INUSE, end - addr);
+
+	return !memchr_inv((void *)start, PAGE_INUSE, PMD_SIZE);
+}
+
+static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * We only optimize if the new used range directly follows the
+	 * previously unused range (esp., when populating consecutive sections).
+	 */
+	if (unused_pmd_start == start) {
+		if (likely(IS_ALIGNED(end, PMD_SIZE)))
+			unused_pmd_start = 0;
+		else
+			unused_pmd_start = end;
+		return;
+	}
+
+	vmemmap_flush_unused_pmd();
+}
+
+static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+	vmemmap_flush_unused_pmd();
+
+	/*
+	 * Mark the unused parts of the new memmap range
+	 */
+	if (!IS_ALIGNED(start, PMD_SIZE))
+		memset((void *)start, PAGE_INUSE,
+		       start - ALIGN_DOWN(start, PMD_SIZE));
+	/*
+	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
+	 * consecutive sections. Remember for the last added PMD the last
+	 * unused range in the populated PMD.
+	 */
+	if (!IS_ALIGNED(end, PMD_SIZE))
+		unused_pmd_start = end;
+}
+
 static void __meminit free_pagetable(struct page *page, int order)
 {
 	unsigned long magic;
@@ -1034,7 +1099,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 	unsigned long next, pages = 0;
 	pte_t *pte_base;
 	pmd_t *pmd;
-	void *page_addr;
 
 	pmd = pmd_start + pmd_index(addr);
 	for (; addr < end; addr = next, pmd++) {
@@ -1055,12 +1119,10 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
 			} else {
-				/* If here, we are freeing vmemmap pages. */
-				memset((void *)addr, PAGE_INUSE, next - addr);
-
-				page_addr = page_address(pmd_page(*pmd));
-				if (!memchr_inv(page_addr, PAGE_INUSE,
-						PMD_SIZE)) {
+				/*
+				 * Free the PMD if the whole range is unused.
+				 */
+				if (vmemmap_unuse_sub_pmd(addr, next)) {
 					free_hugepage_table(pmd_page(*pmd),
 							    altmap);
 
@@ -1538,11 +1600,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 
 				addr_end = addr + PMD_SIZE;
 				p_end = p + PMD_SIZE;
+
+				if (!IS_ALIGNED(addr, PMD_SIZE) ||
+				    !IS_ALIGNED(next, PMD_SIZE))
+					vmemmap_use_new_sub_pmd(addr, next);
 				continue;
 			} else if (altmap)
 				return -ENOMEM; /* no fallback */
 		} else if (pmd_large(*pmd)) {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			vmemmap_use_sub_pmd(addr, next);
 			continue;
 		}
 		if (vmemmap_populate_basepages(addr, next, node, NULL))
-- 
2.26.2