[PATCH 15/19] fsnotify: generate pre-content permission event on page fault

[Jan Kara <jack@suse.cz>]

From: Josef Bacik <josef@toxicpanda.com>

FS_PRE_ACCESS will be generated on page fault depending on the faulting
method. This pre-content event is meant to be used by hierarchical storage
managers that want to fill in the file content on first read access.

Export a simple helper that file systems that have their own ->fault()
will use, and have a more complicated helper to be do fancy things in
filemap_fault.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/aa56c50ce81b1fd18d7f5d71dd2dfced5eba9687.1731684329.git.josef@toxicpanda.com
---
 include/linux/mm.h |  1 +
 mm/filemap.c       | 78 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         |  7 +++++
 3 files changed, 86 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2b0582..e9077ab16972 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3405,6 +3405,7 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf);
 extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
+extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf);
 
 extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
diff --git a/mm/filemap.c b/mm/filemap.c
index 98f15dccff89..0648bb568259 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -47,6 +47,7 @@
 #include <linux/splice.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched/mm.h>
+#include <linux/fsnotify.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -3287,6 +3288,52 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
 	return ret;
 }
 
+/**
+ * filemap_fsnotify_fault - maybe emit a pre-content event.
+ * @vmf:	struct vm_fault containing details of the fault.
+ * @folio:	the folio we're faulting in.
+ *
+ * If we have a pre-content watch on this file we will emit an event for this
+ * range.  If we return anything the fault caller should return immediately, we
+ * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the
+ * fault again and then the fault handler will run the second time through.
+ *
+ * This is meant to be called with the folio that we will be filling in to make
+ * sure the event is emitted for the correct range.
+ *
+ * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened.
+ */
+vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf)
+{
+	struct file *fpin = NULL;
+	int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS;
+	loff_t pos = vmf->pgoff >> PAGE_SHIFT;
+	size_t count = PAGE_SIZE;
+	vm_fault_t ret;
+
+	/*
+	 * We already did this and now we're retrying with everything locked,
+	 * don't emit the event and continue.
+	 */
+	if (vmf->flags & FAULT_FLAG_TRIED)
+		return 0;
+
+	/* No watches, we're done. */
+	if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode)))
+		return 0;
+
+	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
+	if (!fpin)
+		return VM_FAULT_SIGBUS;
+
+	ret = fsnotify_file_area_perm(fpin, mask, &pos, count);
+	fput(fpin);
+	if (ret)
+		return VM_FAULT_SIGBUS;
+	return VM_FAULT_RETRY;
+}
+EXPORT_SYMBOL_GPL(filemap_fsnotify_fault);
+
 /**
  * filemap_fault - read in file data for page fault handling
  * @vmf:	struct vm_fault containing details of the fault
@@ -3390,6 +3437,37 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * or because readahead was otherwise unable to retrieve it.
 	 */
 	if (unlikely(!folio_test_uptodate(folio))) {
+		/*
+		 * If this is a precontent file we have can now emit an event to
+		 * try and populate the folio.
+		 */
+		if (!(vmf->flags & FAULT_FLAG_TRIED) &&
+		    unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) {
+			loff_t pos = folio_pos(folio);
+			size_t count = folio_size(folio);
+
+			/* We're NOWAIT, we have to retry. */
+			if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) {
+				folio_unlock(folio);
+				goto out_retry;
+			}
+
+			if (mapping_locked)
+				filemap_invalidate_unlock_shared(mapping);
+			mapping_locked = false;
+
+			folio_unlock(folio);
+			fpin = maybe_unlock_mmap_for_io(vmf, fpin);
+			if (!fpin)
+				goto out_retry;
+
+			error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos,
+							count);
+			if (error)
+				ret = VM_FAULT_SIGBUS;
+			goto out_retry;
+		}
+
 		/*
 		 * If the invalidate lock is not held, the folio was in cache
 		 * and uptodate and now it is not. Strange but possible since we
diff --git a/mm/nommu.c b/mm/nommu.c
index 385b0c15add8..a8789faa49ee 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1614,6 +1614,13 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
+vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf)
+{
+	BUG();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(filemap_fsnotify_fault);
+
 vm_fault_t filemap_fault(struct vm_fault *vmf)
 {
 	BUG();
-- 
2.35.3