mm/huge_memory: refactor copy_huge_pmd() non-present logic

Right now we are inconsistent in our use of thp_migration_supported():

static inline bool thp_migration_supported(void)
{
	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
}

And simply having arbitrary and ugly #ifdef
CONFIG_ARCH_ENABLE_THP_MIGRATION blocks in code.

This is exhibited in copy_huge_pmd(), which inserts a large #ifdef
CONFIG_ARCH_ENABLE_THP_MIGRATION block and an if-branch which is difficult
to follow

It's difficult to follow the logic of such a large function and the
non-present PMD logic is clearly separate as it sits in a giant if-branch.

Therefore this patch both separates out the logic and utilises
thp_migration_supported().

No functional change intended.

Link: https://lkml.kernel.org/r/6eaadc23ed512d370ede65561e34e96241c54b9d.1762812360.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Chris Li <chrisl@kernel.org>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Wei Xu <weixugc@google.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b88b4b866cb3a7e64bf8742ee3674130a7e2f9e2..3bf8d2bf937459fa874bc6df6fafaceed8ff7b8f 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1699,6 +1699,62 @@ void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
                update_mmu_cache_pmd(vma, addr, pmd);
 }
 
+static void copy_huge_non_present_pmd(
+               struct mm_struct *dst_mm, struct mm_struct *src_mm,
+               pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+               struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+               pmd_t pmd, pgtable_t pgtable)
+{
+       swp_entry_t entry = pmd_to_swp_entry(pmd);
+       struct folio *src_folio;
+
+       VM_WARN_ON(!is_pmd_non_present_folio_entry(pmd));
+
+       if (is_writable_migration_entry(entry) ||
+           is_readable_exclusive_migration_entry(entry)) {
+               entry = make_readable_migration_entry(swp_offset(entry));
+               pmd = swp_entry_to_pmd(entry);
+               if (pmd_swp_soft_dirty(*src_pmd))
+                       pmd = pmd_swp_mksoft_dirty(pmd);
+               if (pmd_swp_uffd_wp(*src_pmd))
+                       pmd = pmd_swp_mkuffd_wp(pmd);
+               set_pmd_at(src_mm, addr, src_pmd, pmd);
+       } else if (is_device_private_entry(entry)) {
+               /*
+                * For device private entries, since there are no
+                * read exclusive entries, writable = !readable
+                */
+               if (is_writable_device_private_entry(entry)) {
+                       entry = make_readable_device_private_entry(swp_offset(entry));
+                       pmd = swp_entry_to_pmd(entry);
+
+                       if (pmd_swp_soft_dirty(*src_pmd))
+                               pmd = pmd_swp_mksoft_dirty(pmd);
+                       if (pmd_swp_uffd_wp(*src_pmd))
+                               pmd = pmd_swp_mkuffd_wp(pmd);
+                       set_pmd_at(src_mm, addr, src_pmd, pmd);
+               }
+
+               src_folio = pfn_swap_entry_folio(entry);
+               VM_WARN_ON(!folio_test_large(src_folio));
+
+               folio_get(src_folio);
+               /*
+                * folio_try_dup_anon_rmap_pmd does not fail for
+                * device private entries.
+                */
+               folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
+                                           dst_vma, src_vma);
+       }
+
+       add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+       mm_inc_nr_ptes(dst_mm);
+       pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
+       if (!userfaultfd_wp(dst_vma))
+               pmd = pmd_swp_clear_uffd_wp(pmd);
+       set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+}
+
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
                  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
@@ -1744,59 +1800,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        ret = -EAGAIN;
        pmd = *src_pmd;
 
-#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-       if (unlikely(is_swap_pmd(pmd))) {
-               swp_entry_t entry = pmd_to_swp_entry(pmd);
-
-               VM_WARN_ON(!is_pmd_non_present_folio_entry(pmd));
-
-               if (is_writable_migration_entry(entry) ||
-                   is_readable_exclusive_migration_entry(entry)) {
-                       entry = make_readable_migration_entry(swp_offset(entry));
-                       pmd = swp_entry_to_pmd(entry);
-                       if (pmd_swp_soft_dirty(*src_pmd))
-                               pmd = pmd_swp_mksoft_dirty(pmd);
-                       if (pmd_swp_uffd_wp(*src_pmd))
-                               pmd = pmd_swp_mkuffd_wp(pmd);
-                       set_pmd_at(src_mm, addr, src_pmd, pmd);
-               } else if (is_device_private_entry(entry)) {
-                       /*
-                        * For device private entries, since there are no
-                        * read exclusive entries, writable = !readable
-                        */
-                       if (is_writable_device_private_entry(entry)) {
-                               entry = make_readable_device_private_entry(swp_offset(entry));
-                               pmd = swp_entry_to_pmd(entry);
-
-                               if (pmd_swp_soft_dirty(*src_pmd))
-                                       pmd = pmd_swp_mksoft_dirty(pmd);
-                               if (pmd_swp_uffd_wp(*src_pmd))
-                                       pmd = pmd_swp_mkuffd_wp(pmd);
-                               set_pmd_at(src_mm, addr, src_pmd, pmd);
-                       }
-
-                       src_folio = pfn_swap_entry_folio(entry);
-                       VM_WARN_ON(!folio_test_large(src_folio));
-
-                       folio_get(src_folio);
-                       /*
-                        * folio_try_dup_anon_rmap_pmd does not fail for
-                        * device private entries.
-                        */
-                       folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
-                                                       dst_vma, src_vma);
-               }
-
-               add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
-               mm_inc_nr_ptes(dst_mm);
-               pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
-               if (!userfaultfd_wp(dst_vma))
-                       pmd = pmd_swp_clear_uffd_wp(pmd);
-               set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+       if (unlikely(thp_migration_supported() && is_swap_pmd(pmd))) {
+               copy_huge_non_present_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr,
+                                         dst_vma, src_vma, pmd, pgtable);
                ret = 0;
                goto out_unlock;
        }
-#endif
 
        if (unlikely(!pmd_trans_huge(pmd))) {
                pte_free(dst_mm, pgtable);