x86/vmemmap: handle unpopulated sub-pmd ranges

When sizeof(struct page) is not a power of 2, 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_UNUSED, 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/

[osalvador@suse.de: go back to the ifdef version]
Link: https://lkml.kernel.org/r/YGy++mSft7K4u+88@localhost.localdomain
Link: https://lkml.kernel.org/r/20210309214050.4674-4-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index af217ff6da577bc8a1d259f1b9b0596736791f9a..fa7948042bff0a659700603908bedaca4146e3e5 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -826,6 +826,51 @@ void __init paging_init(void)
        zone_sizes_init();
 }
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#define PAGE_UNUSED 0xFD
+
+/* Returns true if the PMD is completely unused and thus it can be freed */
+static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
+{
+       unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+       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)
+{
+       /*
+        * As we expect to add in the same granularity as we remove, it's
+        * sufficient to mark only some piece used to block the memmap page from
+        * getting removed when removing some other adjacent memmap (just in
+        * case the first memmap never gets initialized e.g., because the memory
+        * block never gets onlined).
+        */
+       memset((void *)start, 0, sizeof(struct page));
+}
+
+static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+       /*
+        * Could be our memmap page is filled with PAGE_UNUSED already from a
+        * previous remove. Make sure to reset it.
+        */
+       vmemmap_use_sub_pmd(start);
+
+       /*
+        * Mark with PAGE_UNUSED 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));
+       if (!IS_ALIGNED(end, PMD_SIZE))
+               memset((void *)end, PAGE_UNUSED,
+                       ALIGN(end, PMD_SIZE) - end);
+}
+#endif
+
 /*
  * Memory hotplug specific functions
  */
@@ -871,8 +916,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
        return add_pages(nid, start_pfn, nr_pages, params);
 }
 
-#define PAGE_INUSE 0xFD
-
 static void __meminit free_pagetable(struct page *page, int order)
 {
        unsigned long magic;
@@ -1006,7 +1049,6 @@ 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++) {
@@ -1026,22 +1068,16 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
                                pmd_clear(pmd);
                                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)) {
+                       }
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+                       else if (vmemmap_pmd_is_unused(addr, next)) {
                                        free_hugepage_table(pmd_page(*pmd),
                                                            altmap);
-
                                        spin_lock(&init_mm.page_table_lock);
                                        pmd_clear(pmd);
                                        spin_unlock(&init_mm.page_table_lock);
-                               }
                        }
-
+#endif
                        continue;
                }
 
@@ -1492,11 +1528,17 @@ 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);
                        continue;
                }
                if (vmemmap_populate_basepages(addr, next, node, NULL))