mm: thp: kill __transhuge_page_enabled()

The page fault path checks THP eligibility with __transhuge_page_enabled()
which does the similar thing as hugepage_vma_check(), so use
hugepage_vma_check() instead.

However page fault allows DAX and !anon_vma cases, so added a new flag,
in_pf, to hugepage_vma_check() to make page fault work correctly.

The in_pf flag is also used to skip shmem and file THP for page fault
since shmem handles THP in its own shmem_fault() and file THP allocation
on fault is not supported yet.

Also remove hugepage_vma_enabled() since hugepage_vma_check() is the only
caller now, it is not necessary to have a helper function.

Link: https://lkml.kernel.org/r/20220616174840.1202070-6-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Zach O'Keefe <zokeefe@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 40 insertions, 11 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8cbd21aaf03e..4b90c7021e52 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -71,27 +71,53 @@ unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
 bool hugepage_vma_check(struct vm_area_struct *vma,
 			unsigned long vm_flags,
-			bool smaps)
+			bool smaps, bool in_pf)
 {
 	if (!vma->vm_mm)		/* vdso */
 		return false;
 
-	if (!transhuge_vma_enabled(vma, vm_flags))
+	/*
+	 * Explicitly disabled through madvise or prctl, or some
+	 * architectures may disable THP for some mappings, for
+	 * example, s390 kvm.
+	 * */
+	if ((vm_flags & VM_NOHUGEPAGE) ||
+	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 		return false;
-
-	if (vm_flags & VM_NO_KHUGEPAGED)
+	/*
+	 * If the hardware/firmware marked hugepage support disabled.
+	 */
+	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX))
 		return false;
 
-	/* Don't run khugepaged against DAX vma */
+	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
 	if (vma_is_dax(vma))
+		return in_pf;
+
+	/*
+	 * Special VMA and hugetlb VMA.
+	 * Must be checked after dax since some dax mappings may have
+	 * VM_MIXEDMAP set.
+	 */
+	if (vm_flags & VM_NO_KHUGEPAGED)
 		return false;
 
-	/* Check alignment for file vma and size for both file and anon vma */
-	if (!transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
+	/*
+	 * Check alignment for file vma and size for both file and anon vma.
+	 *
+	 * Skip the check for page fault. Huge fault does the check in fault
+	 * handlers. And this check is not suitable for huge PUD fault.
+	 */
+	if (!in_pf &&
+	    !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
 		return false;
 
-	/* Enabled via shmem mount options or sysfs settings. */
-	if (shmem_file(vma->vm_file))
+	/*
+	 * Enabled via shmem mount options or sysfs settings.
+	 * Must be done before hugepage flags check since shmem has its
+	 * own flags.
+	 */
+	if (!in_pf && shmem_file(vma->vm_file))
 		return shmem_huge_enabled(vma);
 
 	if (!khugepaged_enabled())
@@ -102,7 +128,7 @@ bool hugepage_vma_check(struct vm_area_struct *vma,
 		return false;
 
 	/* Only regular file is valid */
-	if (file_thp_enabled(vma))
+	if (!in_pf && file_thp_enabled(vma))
 		return true;
 
 	if (!vma_is_anonymous(vma))
@@ -114,9 +140,12 @@ bool hugepage_vma_check(struct vm_area_struct *vma,
 	/*
 	 * THPeligible bit of smaps should show 1 for proper VMAs even
 	 * though anon_vma is not initialized yet.
+	 *
+	 * Allow page fault since anon_vma may be not initialized until
+	 * the first page fault.
 	 */
 	if (!vma->anon_vma)
-		return smaps;
+		return (smaps || in_pf);
 
 	return true;
 }