1 files changed, 105 insertions, 2 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 33b60d448fca..b8ed647416e9 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"
@@ -1523,7 +1524,7 @@ void folio_end_read(struct folio *folio, bool success)
 	/* Must be in bottom byte for x86 to work */
 	BUILD_BUG_ON(PG_uptodate > 7);
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
-	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
+	VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio);
 
 	if (likely(success))
 		mask |= 1 << PG_uptodate;
@@ -2996,7 +2997,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas,
 		if (ops->is_partially_uptodate(folio, offset, bsz) ==
 							seek_data)
 			break;
-		start = (start + bsz) & ~(bsz - 1);
+		start = (start + bsz) & ~((u64)bsz - 1);
 		offset += bsz;
 	} while (offset < folio_size(folio));
 unlock:
@@ -3141,6 +3142,14 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	unsigned long vm_flags = vmf->vma->vm_flags;
 	unsigned int mmap_miss;
 
+	/*
+	 * If we have pre-content watches we need to disable readahead to make
+	 * sure that we don't populate our mapping with 0 filled pages that we
+	 * never emitted an event for.
+	 */
+	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
+		return fpin;
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
 	if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
@@ -3209,6 +3218,10 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
 	struct file *fpin = NULL;
 	unsigned int mmap_miss;
 
+	/* See comment in do_sync_mmap_readahead. */
+	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
+		return fpin;
+
 	/* If we don't want any read-ahead, don't bother */
 	if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
 		return fpin;
@@ -3268,6 +3281,48 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
 }
 
 /**
+ * filemap_fsnotify_fault - maybe emit a pre-content event.
+ * @vmf:	struct vm_fault containing details of the fault.
+ *
+ * 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.
+ *
+ * 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;
+	int err;
+
+	/*
+	 * 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;
+
+	err = fsnotify_file_area_perm(fpin, mask, &pos, count);
+	fput(fpin);
+	if (err)
+		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
  *
@@ -3371,6 +3426,37 @@ retry_find:
 	 */
 	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
 		 * didn't hold the page lock all the time. Let's drop
@@ -4376,6 +4462,20 @@ resched:
 }
 
 /*
+ * See mincore: reveal pagecache information only for files
+ * that the calling process has write access to, or could (if
+ * tried) open for writing.
+ */
+static inline bool can_do_cachestat(struct file *f)
+{
+	if (f->f_mode & FMODE_WRITE)
+		return true;
+	if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f)))
+		return true;
+	return file_permission(f, MAY_WRITE) == 0;
+}
+
+/*
  * The cachestat(2) system call.
  *
  * cachestat() returns the page cache statistics of a file in the
@@ -4430,6 +4530,9 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd,
 	if (is_file_hugepages(fd_file(f)))
 		return -EOPNOTSUPP;
 
+	if (!can_do_cachestat(fd_file(f)))
+		return -EPERM;
+
 	if (flags != 0)
 		return -EINVAL;