[PATCH v4 3/7] mm/huge_memory: respect MADV_COLLAPSE with PR_THP_DISABLE_EXCEPT_ADVISED

[Usama Arif <usamaarif642@gmail.com>]

From: David Hildenbrand <david@redhat.com>

Let's allow for making MADV_COLLAPSE succeed on areas that neither have
VM_HUGEPAGE nor VM_NOHUGEPAGE when we have THP disabled
unless explicitly advised (PR_THP_DISABLE_EXCEPT_ADVISED).

MADV_COLLAPSE is a clear advice that we want to collapse.

Note that we still respect the VM_NOHUGEPAGE flag, just like
MADV_COLLAPSE always does. So consequently, MADV_COLLAPSE is now only
refused on VM_NOHUGEPAGE with PR_THP_DISABLE_EXCEPT_ADVISED,
including for shmem.

Co-developed-by: Usama Arif <usamaarif642@gmail.com>
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
 include/linux/huge_mm.h    | 8 +++++++-
 include/uapi/linux/prctl.h | 2 +-
 mm/huge_memory.c           | 5 +++--
 mm/memory.c                | 6 ++++--
 mm/shmem.c                 | 2 +-
 5 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 92ea0b9771fae..1ac0d06fb3c1d 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -329,7 +329,7 @@ struct thpsize {
  * through madvise or prctl.
  */
 static inline bool vma_thp_disabled(struct vm_area_struct *vma,
-		vm_flags_t vm_flags)
+		vm_flags_t vm_flags, bool forced_collapse)
 {
 	/* Are THPs disabled for this VMA? */
 	if (vm_flags & VM_NOHUGEPAGE)
@@ -343,6 +343,12 @@ static inline bool vma_thp_disabled(struct vm_area_struct *vma,
 	 */
 	if (vm_flags & VM_HUGEPAGE)
 		return false;
+	/*
+	 * Forcing a collapse (e.g., madv_collapse), is a clear advice to
+	 * use THPs.
+	 */
+	if (forced_collapse)
+		return false;
 	return mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, vma->vm_mm);
 }
 
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 150b6deebfb1e..51c4e8c82b1e9 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -185,7 +185,7 @@ struct prctl_mm_map {
 #define PR_SET_THP_DISABLE	41
 /*
  * Don't disable THPs when explicitly advised (e.g., MADV_HUGEPAGE /
- * VM_HUGEPAGE).
+ * VM_HUGEPAGE, MADV_COLLAPSE).
  */
 # define PR_THP_DISABLE_EXCEPT_ADVISED	(1 << 1)
 #define PR_GET_THP_DISABLE	42
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9c716be949cbf..1eca2d543449c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -104,7 +104,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 {
 	const bool smaps = type == TVA_SMAPS;
 	const bool in_pf = type == TVA_PAGEFAULT;
-	const bool enforce_sysfs = type != TVA_FORCED_COLLAPSE;
+	const bool forced_collapse = type == TVA_FORCED_COLLAPSE;
+	const bool enforce_sysfs = !forced_collapse;
 	unsigned long supported_orders;
 
 	/* Check the intersection of requested and supported orders. */
@@ -122,7 +123,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 	if (!vma->vm_mm)		/* vdso */
 		return 0;
 
-	if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags))
+	if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags, forced_collapse))
 		return 0;
 
 	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
diff --git a/mm/memory.c b/mm/memory.c
index 7b1e8f137fa3f..e4f533655305a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5332,9 +5332,11 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *pa
 	 * It is too late to allocate a small folio, we already have a large
 	 * folio in the pagecache: especially s390 KVM cannot tolerate any
 	 * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any
-	 * PMD mappings if THPs are disabled.
+	 * PMD mappings if THPs are disabled. As we already have a THP ...
+	 * behave as if we are forcing a collapse.
 	 */
-	if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags))
+	if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags,
+						     /* forced_collapse=*/ true))
 		return ret;
 
 	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
diff --git a/mm/shmem.c b/mm/shmem.c
index e2c76a30802b6..d945de3a7f0e7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1817,7 +1817,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode,
 	vm_flags_t vm_flags = vma ? vma->vm_flags : 0;
 	unsigned int global_orders;
 
-	if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags)))
+	if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags, shmem_huge_force)))
 		return 0;
 
 	global_orders = shmem_huge_global_enabled(inode, index, write_end,
-- 
2.47.3