1 files changed, 29 insertions, 8 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 75c2dfd04f72..f8bebec145f5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -76,6 +76,7 @@
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/sysctl.h>
+#include <linux/fsnotify.h>
 
 #include <trace/events/kmem.h>
 
@@ -4733,12 +4734,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 			folio_throttle_swaprate(folio, gfp);
 			/*
 			 * When a folio is not zeroed during allocation
-			 * (__GFP_ZERO not used), folio_zero_user() is used
-			 * to make sure that the page corresponding to the
-			 * faulting address will be hot in the cache after
-			 * zeroing.
+			 * (__GFP_ZERO not used) or user folios require special
+			 * handling, folio_zero_user() is used to make sure
+			 * that the page corresponding to the faulting address
+			 * will be hot in the cache after zeroing.
 			 */
-			if (!alloc_zeroed())
+			if (user_alloc_needs_zeroing())
 				folio_zero_user(folio, vmf->address);
 			return folio;
 		}
@@ -5662,8 +5663,17 @@ out_map:
 static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(vmf);
+	/*
+	 * Currently we just emit PAGE_SIZE for our fault events, so don't allow
+	 * a huge fault if we have a pre content watch on this file.  This would
+	 * be trivial to support, but there would need to be tests to ensure
+	 * this works properly and those don't exist currently.
+	 */
+	if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
+		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 	return VM_FAULT_FALLBACK;
@@ -5687,6 +5697,9 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 	}
 
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+		/* See comment in create_huge_pmd. */
+		if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
+			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
@@ -5709,6 +5722,9 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
+	/* See comment in create_huge_pmd. */
+	if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
+		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -5726,6 +5742,9 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
 	if (vma_is_anonymous(vma))
 		goto split;
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+		/* See comment in create_huge_pmd. */
+		if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
+			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
@@ -6815,9 +6834,10 @@ static inline int process_huge_page(
 	return 0;
 }
 
-static void clear_gigantic_page(struct folio *folio, unsigned long addr,
+static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint,
 				unsigned int nr_pages)
 {
+	unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio));
 	int i;
 
 	might_sleep();
@@ -6851,13 +6871,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint)
 }
 
 static int copy_user_gigantic_page(struct folio *dst, struct folio *src,
-				   unsigned long addr,
+				   unsigned long addr_hint,
 				   struct vm_area_struct *vma,
 				   unsigned int nr_pages)
 {
-	int i;
+	unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst));
 	struct page *dst_page;
 	struct page *src_page;
+	int i;
 
 	for (i = 0; i < nr_pages; i++) {
 		dst_page = folio_page(dst, i);