mm: sparsemem: use huge PMD mapping for vmemmap pages

The preparation of splitting huge PMD mapping of vmemmap pages is ready,
so switch the mapping from PTE to PMD.

Link: https://lkml.kernel.org/r/20210616094915.34432-3-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Chen Huang <chenhuang5@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 597572c..7a7da02 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1572,13 +1572,6 @@
                        enabled.
                        Allows heavy hugetlb users to free up some more
                        memory (6 * PAGE_SIZE for each 2MB hugetlb page).
-                       This feauture is not free though. Large page
-                       tables are not used to back vmemmap pages which
-                       can lead to a performance degradation for some
-                       workloads. Also there will be memory allocation
-                       required when hugetlb pages are freed from the
-                       pool which can lead to corner cases under heavy
-                       memory pressure.
                        Format: { on | off (default) }
 
                        on:  enable the feature

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9d9d18d..65ea585 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
-#include <linux/hugetlb.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1610,8 +1609,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
        VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
        VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
 
-       if ((is_hugetlb_free_vmemmap_enabled()  && !altmap) ||
-           end - start < PAGES_PER_SECTION * sizeof(struct page))
+       if (end - start < PAGES_PER_SECTION * sizeof(struct page))
                err = vmemmap_populate_basepages(start, end, node, NULL);
        else if (boot_cpu_has(X86_FEATURE_PSE))
                err = vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1639,8 +1637,6 @@ void register_page_bootmem_memmap(unsigned long section_nr,
        pmd_t *pmd;
        unsigned int nr_pmd_pages;
        struct page *page;
-       bool base_mapping = !boot_cpu_has(X86_FEATURE_PSE) ||
-                           is_hugetlb_free_vmemmap_enabled();
 
        for (; addr < end; addr = next) {
                pte_t *pte = NULL;
@@ -1666,7 +1662,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
                }
                get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-               if (base_mapping) {
+               if (!boot_cpu_has(X86_FEATURE_PSE)) {
                        next = (addr + PAGE_SIZE) & PAGE_MASK;
                        pmd = pmd_offset(pud, addr);
                        if (pmd_none(*pmd))

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cfde3be..f11ba70 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -895,20 +895,6 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-extern bool hugetlb_free_vmemmap_enabled;
-
-static inline bool is_hugetlb_free_vmemmap_enabled(void)
-{
-       return hugetlb_free_vmemmap_enabled;
-}
-#else
-static inline bool is_hugetlb_free_vmemmap_enabled(void)
-{
-       return false;
-}
-#endif
-
 #else  /* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
@@ -1063,13 +1049,14 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
                                        pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
-
-static inline bool is_hugetlb_free_vmemmap_enabled(void)
-{
-       return false;
-}
 #endif /* CONFIG_HUGETLB_PAGE */
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+extern bool hugetlb_free_vmemmap_enabled;
+#else
+#define hugetlb_free_vmemmap_enabled   false
+#endif
+
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
                                        struct mm_struct *mm, pte_t *pte)
 {

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 29d1d74..492560b 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1056,7 +1056,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
         *       populate a single PMD.
         */
        return memmap_on_memory &&
-              !is_hugetlb_free_vmemmap_enabled() &&
+              !hugetlb_free_vmemmap_enabled &&
               IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) &&
               size == memory_block_size_bytes() &&
               IS_ALIGNED(vmemmap_size, PMD_SIZE) &&