On 29.01.21 07:40, Oscar Salvador wrote:
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@xxxxxxxxxx/
https://lore.kernel.org/linux-mm/20200722094558.9828-10-david@xxxxxxxxxx/
Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>
---
v1 -> v2:
- Rename PAGE_INUSE to PAGE_UNUSED as it better describes what we do
---
arch/x86/mm/init_64.c | 91 +++++++++++++++++++++++++++++++++++++------
1 file changed, 79 insertions(+), 12 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b5a3fa4033d3..dbb76160ed52 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -871,7 +871,72 @@ int arch_add_memory(int nid, u64 start, u64 size,
return add_pages(nid, start_pfn, nr_pages, params);
}
-#define PAGE_INUSE 0xFD
+#define PAGE_UNUSED 0xFD
+
+/*
+ * The unused vmemmap range, which was not yet memset(PAGE_UNUSED) 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_UNUSED,
+ 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_UNUSED, end - addr);
+
+ return !memchr_inv((void *)start, PAGE_UNUSED, 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_UNUSED,
+ 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)
{
@@ -1008,10 +1073,10 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
* with 0xFD, and remove the page when it is wholly
* filled with 0xFD.
*/
- memset((void *)addr, PAGE_INUSE, next - addr);
+ memset((void *)addr, PAGE_UNUSED, next - addr);
page_addr = page_address(pte_page(*pte));
- if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
+ if (!memchr_inv(page_addr, PAGE_UNUSED, PAGE_SIZE)) {
free_pagetable(pte_page(*pte), 0);
I remember already raising this, in the context of other cleanups, but
let's start anew:
How could we ever even end up in "!PAGE_ALIGNED(addr) &&
PAGE_ALIGNED(next)"? As the comment correctly indicates, it would only
make sense for "freeing vmemmap pages".
This would mean we are removing parts of a vmemmap page (4k), calling
vmemmap_free()->remove_pagetable() on sub-page granularity.
Even sub-sections (2MB - 512 pages) have a memmap size with base pages:
- 56 bytes: 7 pages
- 64 bytes: 8 pages
- 72 bytes: 9 pages
sizeof(struct page) is always multiples of 8 bytes, so that will hold.
E.g., in __populate_section_memmap(), we already enforce proper
subsection alignment.
IMHO, we should rip out that code here and enforce page alignment in
vmemmap_populate()/vmemmap_free().
Am I missing something?
--
Thanks,
David / dhildenb
