[PATCH RFC 3/4] mm: guest_memfd: Add option to remove guest private memory from direct map

[Elliot Berman <quic_eberman@quicinc.com>]

This patch was reworked from Patrick's patch:
https://lore.kernel.org/all/20240709132041.3625501-6-roypat@amazon.co.uk/

While guest_memfd is not available to be mapped by userspace, it is
still accessible through the kernel's direct map. This means that in
scenarios where guest-private memory is not hardware protected, it can
be speculatively read and its contents potentially leaked through
hardware side-channels. Removing guest-private memory from the direct
map, thus mitigates a large class of speculative execution issues
[1, Table 1].

Direct map removal do not reuse the `.prepare` machinery, since
`prepare` can be called multiple time, and it is the responsibility of
the preparation routine to not "prepare" the same folio twice [2]. Thus,
instead explicitly check if `filemap_grab_folio` allocated a new folio,
and remove the returned folio from the direct map only if this was the
case.

The patch uses release_folio instead of free_folio to reinsert pages
back into the direct map as by the time free_folio is called,
folio->mapping can already be NULL. This means that a call to
folio_inode inside free_folio might deference a NULL pointer, leaving no
way to access the inode which stores the flags that allow determining
whether the page was removed from the direct map in the first place.

[1]: https://download.vusec.net/papers/quarantine_raid23.pdf

Cc: Patrick Roy <roypat@amazon.co.uk>
Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
---
 include/linux/guest_memfd.h |  8 ++++++
 mm/guest_memfd.c            | 65 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 72 insertions(+), 1 deletion(-)

diff --git a/include/linux/guest_memfd.h b/include/linux/guest_memfd.h
index be56d9d53067..f9e4a27aed67 100644
--- a/include/linux/guest_memfd.h
+++ b/include/linux/guest_memfd.h
@@ -25,6 +25,14 @@ struct guest_memfd_operations {
 	int (*release)(struct inode *inode);
 };
 
+/**
+ * @GUEST_MEMFD_FLAG_NO_DIRECT_MAP: When making folios inaccessible by host, also
+ *                                  remove them from the kernel's direct map.
+ */
+enum {
+	GUEST_MEMFD_FLAG_NO_DIRECT_MAP		= BIT(0),
+};
+
 /**
  * @GUEST_MEMFD_GRAB_UPTODATE: Ensure pages are zeroed/up to date.
  *                             If trusted hyp will do it, can ommit this flag
diff --git a/mm/guest_memfd.c b/mm/guest_memfd.c
index 580138b0f9d4..e9d8cab72b28 100644
--- a/mm/guest_memfd.c
+++ b/mm/guest_memfd.c
@@ -7,9 +7,55 @@
 #include <linux/falloc.h>
 #include <linux/guest_memfd.h>
 #include <linux/pagemap.h>
+#include <linux/set_memory.h>
+
+static inline int guest_memfd_folio_private(struct folio *folio)
+{
+	unsigned long nr_pages = folio_nr_pages(folio);
+	unsigned long i;
+	int r;
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *page = folio_page(folio, i);
+
+		r = set_direct_map_invalid_noflush(page);
+		if (r < 0)
+			goto out_remap;
+	}
+
+	folio_set_private(folio);
+	return 0;
+out_remap:
+	for (; i > 0; i--) {
+		struct page *page = folio_page(folio, i - 1);
+
+		BUG_ON(set_direct_map_default_noflush(page));
+	}
+	return r;
+}
+
+static inline void guest_memfd_folio_clear_private(struct folio *folio)
+{
+	unsigned long start = (unsigned long)folio_address(folio);
+	unsigned long nr = folio_nr_pages(folio);
+	unsigned long i;
+
+	if (!folio_test_private(folio))
+		return;
+
+	for (i = 0; i < nr; i++) {
+		struct page *page = folio_page(folio, i);
+
+		BUG_ON(set_direct_map_default_noflush(page));
+	}
+	flush_tlb_kernel_range(start, start + folio_size(folio));
+
+	folio_clear_private(folio);
+}
 
 struct folio *guest_memfd_grab_folio(struct file *file, pgoff_t index, u32 flags)
 {
+	unsigned long gmem_flags = (unsigned long)file->private_data;
 	struct inode *inode = file_inode(file);
 	struct guest_memfd_operations *ops = inode->i_private;
 	struct folio *folio;
@@ -43,6 +89,12 @@ struct folio *guest_memfd_grab_folio(struct file *file, pgoff_t index, u32 flags
 			goto out_err;
 	}
 
+	if (gmem_flags & GUEST_MEMFD_FLAG_NO_DIRECT_MAP) {
+		r = guest_memfd_folio_private(folio);
+		if (r)
+			goto out_err;
+	}
+
 	/*
 	 * Ignore accessed, referenced, and dirty flags.  The memory is
 	 * unevictable and there is no storage to write back to.
@@ -213,14 +265,25 @@ static bool gmem_release_folio(struct folio *folio, gfp_t gfp)
 	if (ops->invalidate_end)
 		ops->invalidate_end(inode, offset, nr);
 
+	guest_memfd_folio_clear_private(folio);
+
 	return true;
 }
 
+static void gmem_invalidate_folio(struct folio *folio, size_t offset, size_t len)
+{
+	/* not yet supported */
+	BUG_ON(offset || len != folio_size(folio));
+
+	BUG_ON(!gmem_release_folio(folio, 0));
+}
+
 static const struct address_space_operations gmem_aops = {
 	.dirty_folio = noop_dirty_folio,
 	.migrate_folio = gmem_migrate_folio,
 	.error_remove_folio = gmem_error_folio,
 	.release_folio = gmem_release_folio,
+	.invalidate_folio = gmem_invalidate_folio,
 };
 
 static inline bool guest_memfd_check_ops(const struct guest_memfd_operations *ops)
@@ -241,7 +304,7 @@ struct file *guest_memfd_alloc(const char *name,
 	if (!guest_memfd_check_ops(ops))
 		return ERR_PTR(-EINVAL);
 
-	if (flags)
+	if (flags & ~GUEST_MEMFD_FLAG_NO_DIRECT_MAP)
 		return ERR_PTR(-EINVAL);
 
 	/*

-- 
2.34.1