mm/khugepaged: run khugepaged for all orders

If any order (m)THP is enabled we should allow running khugepaged to
attempt scanning and collapsing mTHPs.  In order for khugepaged to operate
when only mTHP sizes are specified in sysfs, we must modify the predicate
function that determines whether it ought to run to do so.

This function is currently called hugepage_pmd_enabled(), this patch
renames it to hugepage_enabled() and updates the logic to check to
determine whether any valid orders may exist which would justify
khugepaged running.

We must also update collapse_possible_orders() to check all orders if the
vma is anonymous and the collapse is khugepaged.

After this patch khugepaged mTHP collapse is fully enabled.

Link: https://lore.kernel.org/20260605161422.213817-14-npache@redhat.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Nico Pache <npache@redhat.com>
Reviewed-by: Lorenzo Stoakes <ljs@kernel.org>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Acked-by: Usama Arif <usama.arif@linux.dev>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gregory Price <gourry@gourry.net>
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: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rafael Aquini <raquini@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shivank Garg <shivankg@amd.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Takashi Iwai (SUSE) <tiwai@suse.de>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 5a2adbdbd0557771ed983833a3773ef3ee5e477b..6de1a148222a0f303e41c1b42738ad2a12d431ef 100644 (file)
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -503,23 +503,23 @@ static inline int collapse_test_exit_or_disable(struct mm_struct *mm)
                mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
 }
 
-static bool hugepage_pmd_enabled(void)
+static bool hugepage_enabled(void)
 {
        /*
         * We cover the anon, shmem and the file-backed case here; file-backed
         * hugepages, when configured in, are determined by the global control.
-        * Anon pmd-sized hugepages are determined by the pmd-size control.
+        * Anon hugepages are determined by its per-size mTHP control.
         * Shmem pmd-sized hugepages are also determined by its pmd-size control,
         * except when the global shmem_huge is set to SHMEM_HUGE_DENY.
         */
        if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
            hugepage_global_enabled())
                return true;
-       if (test_bit(PMD_ORDER, &huge_anon_orders_always))
+       if (READ_ONCE(huge_anon_orders_always))
                return true;
-       if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
+       if (READ_ONCE(huge_anon_orders_madvise))
                return true;
-       if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
+       if (READ_ONCE(huge_anon_orders_inherit) &&
            hugepage_global_enabled())
                return true;
        if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled())
@@ -566,7 +566,13 @@ void __khugepaged_enter(struct mm_struct *mm)
 static unsigned long collapse_possible_orders(struct vm_area_struct *vma,
                vm_flags_t vm_flags, enum tva_type tva_flags)
 {
-       const unsigned long orders = BIT(HPAGE_PMD_ORDER);
+       unsigned long orders;
+
+       /* If khugepaged is scanning an anonymous vma, allow mTHP collapse */
+       if ((tva_flags == TVA_KHUGEPAGED) && vma_is_anonymous(vma))
+               orders = THP_ORDERS_ALL_ANON;
+       else
+               orders = BIT(HPAGE_PMD_ORDER);
 
        return thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders);
 }
@@ -580,11 +586,9 @@ static bool collapse_possible(struct vm_area_struct *vma,
 void khugepaged_enter_vma(struct vm_area_struct *vma,
                          vm_flags_t vm_flags)
 {
-       if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
-           hugepage_pmd_enabled()) {
-               if (collapse_possible(vma, vm_flags, TVA_KHUGEPAGED))
-                       __khugepaged_enter(vma->vm_mm);
-       }
+       if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) && hugepage_enabled()
+           && collapse_possible(vma, vm_flags, TVA_KHUGEPAGED))
+               __khugepaged_enter(vma->vm_mm);
 }
 
 void __khugepaged_exit(struct mm_struct *mm)
@@ -2941,7 +2945,7 @@ breakouterloop_mmap_lock:
 
 static int khugepaged_has_work(void)
 {
-       return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
+       return !list_empty(&khugepaged_scan.mm_head) && hugepage_enabled();
 }
 
 static int khugepaged_wait_event(void)
@@ -3014,7 +3018,7 @@ static void khugepaged_wait_work(void)
                return;
        }
 
-       if (hugepage_pmd_enabled())
+       if (hugepage_enabled())
                wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
 }
 
@@ -3045,7 +3049,7 @@ void set_recommended_min_free_kbytes(void)
        int nr_zones = 0;
        unsigned long recommended_min;
 
-       if (!hugepage_pmd_enabled()) {
+       if (!hugepage_enabled()) {
                calculate_min_free_kbytes();
                goto update_wmarks;
        }
@@ -3095,7 +3099,7 @@ int start_stop_khugepaged(void)
        int err = 0;
 
        mutex_lock(&khugepaged_mutex);
-       if (hugepage_pmd_enabled()) {
+       if (hugepage_enabled()) {
                if (!khugepaged_thread)
                        khugepaged_thread = kthread_run(khugepaged, NULL,
                                                        "khugepaged");
@@ -3121,7 +3125,7 @@ fail:
 void khugepaged_min_free_kbytes_update(void)
 {
        mutex_lock(&khugepaged_mutex);
-       if (hugepage_pmd_enabled() && khugepaged_thread)
+       if (hugepage_enabled() && khugepaged_thread)
                set_recommended_min_free_kbytes();
        mutex_unlock(&khugepaged_mutex);
 }