[v2,12/16] mm: don't allow huge faults for files with pre content watches

Commit Message

Josef Bacik Aug. 8, 2024, 7:27 p.m. UTC

There's nothing stopping us from supporting this, we could simply pass
the order into the helper and emit the proper length.  However currently
there's no tests to validate this works properly, so disable it until
there's a desire to support this along with the appropriate tests.

Signed-off-by: Josef Bacik <[e-mail]>
---
 mm/memory.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

Comments

Christian Brauner Aug. 9, 2024, 12:13 p.m. UTC | #1

On Thu, Aug 08, 2024 at 03:27:14PM GMT, Josef Bacik wrote:
> There's nothing stopping us from supporting this, we could simply pass
> the order into the helper and emit the proper length.  However currently
> there's no tests to validate this works properly, so disable it until
> there's a desire to support this along with the appropriate tests.
> 
> Signed-off-by: Josef Bacik <[e-mail]>
> ---

Reviewed-by: Christian Brauner <[e-mail]>

Patch

diff --git a/mm/memory.c b/mm/memory.c
index d10e616d7389..3010bcc5e4f9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -78,6 +78,7 @@ 
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/sysctl.h>
+#include <linux/fsnotify.h>
 
 #include <trace/events/kmem.h>
 
@@ -5252,8 +5253,17 @@  static vm_fault_t do_numa_page(struct vm_fault *vmf)
 static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	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 (file && fsnotify_file_has_pre_content_watches(file))
+		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 	return VM_FAULT_FALLBACK;
@@ -5263,6 +5273,7 @@  static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	vm_fault_t ret;
 
@@ -5277,6 +5288,9 @@  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 (file && fsnotify_file_has_pre_content_watches(file))
+			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
@@ -5296,9 +5310,13 @@  static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
+	/* See comment in create_huge_pmd. */
+	if (file && fsnotify_file_has_pre_content_watches(file))
+		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -5310,12 +5328,16 @@  static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	vm_fault_t ret;
 
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		goto split;
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
+		/* See comment in create_huge_pmd. */
+		if (file && fsnotify_file_has_pre_content_watches(file))
+			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))