mm: add mmap_action_map_kernel_pages[_full]()

A user can invoke mmap_action_map_kernel_pages() to specify that the
mapping should map kernel pages starting from desc->start of a specified
number of pages specified in an array.

In order to implement this, adjust mmap_action_prepare() to be able to
return an error code, as it makes sense to assert that the specified
parameters are valid as quickly as possible as well as updating the VMA
flags to include VMA_MIXEDMAP_BIT as necessary.

This provides an mmap_prepare equivalent of vm_insert_pages().  We
additionally update the existing vm_insert_pages() code to use
range_in_vma() and add a new range_in_vma_desc() helper function for the
mmap_prepare case, sharing the code between the two in range_is_subset().

We add both mmap_action_map_kernel_pages() and
mmap_action_map_kernel_pages_full() to allow for both partial and full VMA
mappings.

We update the documentation to reflect the new features.

Finally, we update the VMA tests accordingly to reflect the changes.

Link: https://lkml.kernel.org/r/926ac961690d856e67ec847bee2370ab3c6b9046.1774045440.git.ljs@kernel.org
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Bodo Stroesser <bostroesser@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Clemens Ladisch <clemens@ladisch.de>
Cc: David Hildenbrand <david@kernel.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Long Li <longli@microsoft.com>
Cc: Marc Dionne <marc.dionne@auristor.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Miquel Raynal <miquel.raynal@bootlin.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Richard Weinberger <richard@nod.at>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 100 insertions, 2 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 53b21de40f87..61dff7f03554 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2905,7 +2905,7 @@ static inline bool folio_maybe_mapped_shared(struct folio *folio)
  * The caller must add any reference (e.g., from folio_try_get()) it might be
  * holding itself to the result.
  *
- * Returns the expected folio refcount.
+ * Returns: the expected folio refcount.
  */
 static inline int folio_expected_ref_count(const struct folio *folio)
 {
@@ -4348,6 +4348,45 @@ static inline void mmap_action_simple_ioremap(struct vm_area_desc *desc,
 	action->type = MMAP_SIMPLE_IO_REMAP;
 }
 
+/**
+ * mmap_action_map_kernel_pages - helper for mmap_prepare hook to specify that
+ * @num kernel pages contained in the @pages array should be mapped to userland
+ * starting at virtual address @start.
+ * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped.
+ * @start: The virtual address from which to map them.
+ * @pages: An array of struct page pointers describing the memory to map.
+ * @nr_pages: The number of entries in the @pages aray.
+ */
+static inline void mmap_action_map_kernel_pages(struct vm_area_desc *desc,
+		unsigned long start, struct page **pages,
+		unsigned long nr_pages)
+{
+	struct mmap_action *action = &desc->action;
+
+	action->type = MMAP_MAP_KERNEL_PAGES;
+	action->map_kernel.start = start;
+	action->map_kernel.pages = pages;
+	action->map_kernel.nr_pages = nr_pages;
+	action->map_kernel.pgoff = desc->pgoff;
+}
+
+/**
+ * mmap_action_map_kernel_pages_full - helper for mmap_prepare hook to specify that
+ * kernel pages contained in the @pages array should be mapped to userland
+ * from @desc->start to @desc->end.
+ * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped.
+ * @pages: An array of struct page pointers describing the memory to map.
+ *
+ * The caller must ensure that @pages contains sufficient entries to cover the
+ * entire range described by @desc.
+ */
+static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc,
+		struct page **pages)
+{
+	mmap_action_map_kernel_pages(desc, desc->start, pages,
+				     vma_desc_pages(desc));
+}
+
 int mmap_action_prepare(struct vm_area_desc *desc);
 int mmap_action_complete(struct vm_area_struct *vma,
 			 struct mmap_action *action);
@@ -4364,10 +4403,59 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 	return vma;
 }
 
+/**
+ * range_is_subset - Is the specified inner range a subset of the outer range?
+ * @outer_start: The start of the outer range.
+ * @outer_end: The exclusive end of the outer range.
+ * @inner_start: The start of the inner range.
+ * @inner_end: The exclusive end of the inner range.
+ *
+ * Returns: %true if [inner_start, inner_end) is a subset of [outer_start,
+ * outer_end), otherwise %false.
+ */
+static inline bool range_is_subset(unsigned long outer_start,
+				   unsigned long outer_end,
+				   unsigned long inner_start,
+				   unsigned long inner_end)
+{
+	return outer_start <= inner_start && inner_end <= outer_end;
+}
+
+/**
+ * range_in_vma - is the specified [@start, @end) range a subset of the VMA?
+ * @vma: The VMA against which we want to check [@start, @end).
+ * @start: The start of the range we wish to check.
+ * @end: The exclusive end of the range we wish to check.
+ *
+ * Returns: %true if [@start, @end) is a subset of [@vma->vm_start,
+ * @vma->vm_end), %false otherwise.
+ */
 static inline bool range_in_vma(const struct vm_area_struct *vma,
 				unsigned long start, unsigned long end)
 {
-	return (vma && vma->vm_start <= start && end <= vma->vm_end);
+	if (!vma)
+		return false;
+
+	return range_is_subset(vma->vm_start, vma->vm_end, start, end);
+}
+
+/**
+ * range_in_vma_desc - is the specified [@start, @end) range a subset of the VMA
+ * described by @desc, a VMA descriptor?
+ * @desc: The VMA descriptor against which we want to check [@start, @end).
+ * @start: The start of the range we wish to check.
+ * @end: The exclusive end of the range we wish to check.
+ *
+ * Returns: %true if [@start, @end) is a subset of [@desc->start, @desc->end),
+ * %false otherwise.
+ */
+static inline bool range_in_vma_desc(const struct vm_area_desc *desc,
+				     unsigned long start, unsigned long end)
+{
+	if (!desc)
+		return false;
+
+	return range_is_subset(desc->start, desc->end, start, end);
 }
 
 #ifdef CONFIG_MMU
@@ -4411,6 +4499,9 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num);
+int map_kernel_pages_prepare(struct vm_area_desc *desc);
+int map_kernel_pages_complete(struct vm_area_struct *vma,
+			      struct mmap_action *action);
 int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
 				unsigned long num);
 int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b702c63bf0e0..a308e2c23b82 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -815,6 +815,7 @@ enum mmap_action_type {
 	MMAP_REMAP_PFN,		/* Remap PFN range. */
 	MMAP_IO_REMAP_PFN,	/* I/O remap PFN range. */
 	MMAP_SIMPLE_IO_REMAP,	/* I/O remap with guardrails. */
+	MMAP_MAP_KERNEL_PAGES,	/* Map kernel page range from array. */
 };
 
 /*
@@ -833,6 +834,12 @@ struct mmap_action {
 			phys_addr_t start_phys_addr;
 			unsigned long size;
 		} simple_ioremap;
+		struct {
+			unsigned long start;
+			struct page **pages;
+			unsigned long nr_pages;
+			pgoff_t pgoff;
+		} map_kernel;
 	};
 	enum mmap_action_type type;