Re: [PATCH v3 1/7] mm: khugepaged: extract vm flag setting outside of hugepage_madvise

[Usama Arif <usamaarif642@gmail.com>]

On 20/05/2025 15:57, Usama Arif wrote:
> 
> 
> On 20/05/2025 15:43, Lorenzo Stoakes wrote:
>> This commit message is really poor. You're also not mentioning that you're
>> changing s390 behaviour?
>>
>> On Mon, May 19, 2025 at 11:29:53PM +0100, Usama Arif wrote:
>>> This is so that flag setting can be resused later in other functions,
>>
>> Typo.
>>
>>> to reduce code duplication (including the s390 exception).
>>>
>>> No functional change intended with this patch.
>>
>> I'm pretty sure somebody reviewed that this should just be merged with whatever
>> uses this? I'm not sure this is all that valuable as you're not really changing
>> this structurally very much.
>>
> 

So I unfortunately never tested s390 build which the kernel bot is complaining.

So If I want to reuse hugepage_set_vmflags in patch 2 and 3 for the prctls,
the fix over here would be at the end.

If you don't like the approach of trying to abstract the flag setting away
and reusing it in prctl in this patch I can change it to the way in previous
revision and just do something like below. Happy with either approach and
can drop patch 1 if you prefer.


+       case PR_SET_THP_POLICY:
+               if (arg3 || arg4 || arg5)
+                       return -EINVAL;
+               if (mmap_write_lock_killable(me->mm))
+                       return -EINTR;
+               switch (arg2) {
+               case PR_DEFAULT_MADV_HUGEPAGE:
+                       if (!hugepage_global_enabled())
+                               error = -EPERM;
+#ifdef CONFIG_S390
+                       /*
+                       * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390
+                       * can't handle this properly after s390_enable_sie, so we simply
+                       * ignore the madvise to prevent qemu from causing a SIGSEGV.
+                       */
+                       else if (mm_has_pgste(vma->vm_mm))
+                               error = -EPERM;
+#endif
+                       else {
+                               me->mm->def_flags &= ~VM_NOHUGEPAGE;
+                               me->mm->def_flags |= VM_HUGEPAGE;
+                               process_default_madv_hugepage(me->mm, MADV_HUGEPAGE);
+                       }
+                       break;
+               default:
+                       error = -EINVAL;
+               }
+               mmap_write_unlock(me->mm);
+               break;




Thanks!

diff for fixing this patch:

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b24a2e0ae642..e5176afaaffe 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -432,7 +432,7 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
        }  while (0)
 
 void process_default_madv_hugepage(struct mm_struct *mm, int advice);
-int hugepage_set_vmflags(unsigned long *vm_flags, int advice);
+int hugepage_set_vmflags(struct mm_struct* mm, unsigned long *vm_flags, int advice);
 int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
                     int advice);
 int madvise_collapse(struct vm_area_struct *vma,
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index ab3427c87422..b6c9ed6bb442 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -346,7 +346,7 @@ struct attribute_group khugepaged_attr_group = {
 };
 #endif /* CONFIG_SYSFS */
 
-int hugepage_set_vmflags(unsigned long *vm_flags, int advice)
+int hugepage_set_vmflags(struct mm_struct * mm, unsigned long *vm_flags, int advice)
 {
        switch (advice) {
        case MADV_HUGEPAGE:
@@ -356,8 +356,8 @@ int hugepage_set_vmflags(unsigned long *vm_flags, int advice)
                 * can't handle this properly after s390_enable_sie, so we simply
                 * ignore the madvise to prevent qemu from causing a SIGSEGV.
                 */
-               if (mm_has_pgste(vma->vm_mm))
-                       return -EPERM;
+               if (mm_has_pgste(mm))
+                       return 0;
 #endif
                *vm_flags &= ~VM_NOHUGEPAGE;
                *vm_flags |= VM_HUGEPAGE;
@@ -373,13 +373,14 @@ int hugepage_set_vmflags(unsigned long *vm_flags, int advice)
                break;
        }
 
-       return 0;
+       return 1;
 }
 
 int hugepage_madvise(struct vm_area_struct *vma,
                     unsigned long *vm_flags, int advice)
 {
-       if (advice == MADV_HUGEPAGE && !hugepage_set_vmflags(vm_flags, advice)) {
+       if (hugepage_set_vmflags(vma->vm_mm, vm_flags, advice)
+           && advice == MADV_HUGEPAGE) {
                /*
                 * If the vma become good for khugepaged to scan,
                 * register it here without waiting a page fault that