mm: add mmap_action_simple_ioremap()

Currently drivers use vm_iomap_memory() as a simple helper function for
I/O remapping memory over a range starting at a specified physical address
over a specified length.

In order to utilise this from mmap_prepare, separate out the core logic
into __simple_ioremap_prep(), update vm_iomap_memory() to use it, and add
simple_ioremap_prepare() to do the same with a VMA descriptor object.

We also add MMAP_SIMPLE_IO_REMAP and relevant fields to the struct
mmap_action type to permit this operation also.

We use mmap_action_ioremap() to set up the actual I/O remap operation once
we have checked and figured out the parameters, which makes
simple_ioremap_prepare() easy to implement.

We then add mmap_action_simple_ioremap() to allow drivers to make use of
this mode.

We update the mmap_prepare documentation to describe this mode.  Finally,
we update the VMA tests to reflect this change.

Link: https://lkml.kernel.org/r/a08ef1c4542202684da63bb37f459d5dbbeddd91.1774045440.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>

Documentation/filesystems/mmap_prepare.rst

@@ -153,5 +153,8 @@ pointer. These are:
 * mmap_action_ioremap_full() - Same as mmap_action_ioremap(), only remaps
   the entire mapping from ``start_pfn`` onward.
 
+* mmap_action_simple_ioremap() - Sets up an I/O remap from a specified
+  physical address and over a specified length.
+
 **NOTE:** The ``action`` field should never normally be manipulated directly,
 rather you ought to use one of these helpers.

include/linux/mm.h

@@ -4326,6 +4326,28 @@ static inline void mmap_action_ioremap_full(struct vm_area_desc *desc,
 	mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc));
 }
 
+/**
+ * mmap_action_simple_ioremap - helper for mmap_prepare hook to specify that the
+ * physical range in [start_phys_addr, start_phys_addr + size) should be I/O
+ * remapped.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start_phys_addr: Start of the physical memory to be mapped.
+ * @size: Size of the area to map.
+ *
+ * NOTE: Some drivers might want to tweak desc->page_prot for purposes of
+ * write-combine or similar.
+ */
+static inline void mmap_action_simple_ioremap(struct vm_area_desc *desc,
+					      phys_addr_t start_phys_addr,
+					      unsigned long size)
+{
+	struct mmap_action *action = &desc->action;
+
+	action->simple_ioremap.start_phys_addr = start_phys_addr;
+	action->simple_ioremap.size = size;
+	action->type = MMAP_SIMPLE_IO_REMAP;
+}
+
 int mmap_action_prepare(struct vm_area_desc *desc);
 int mmap_action_complete(struct vm_area_struct *vma,
 			 struct mmap_action *action);

include/linux/mm_types.h

@@ -814,6 +814,7 @@ enum mmap_action_type {
 	MMAP_NOTHING,		/* Mapping is complete, no further action. */
 	MMAP_REMAP_PFN,		/* Remap PFN range. */
 	MMAP_IO_REMAP_PFN,	/* I/O remap PFN range. */
+	MMAP_SIMPLE_IO_REMAP,	/* I/O remap with guardrails. */
 };
 
 /*
@@ -822,13 +823,16 @@ enum mmap_action_type {
  */
 struct mmap_action {
 	union {
-		/* Remap range. */
 		struct {
 			unsigned long start;
 			unsigned long start_pfn;
 			unsigned long size;
 			pgprot_t pgprot;
 		} remap;
+		struct {
+			phys_addr_t start_phys_addr;
+			unsigned long size;
+		} simple_ioremap;
 	};
 	enum mmap_action_type type;
 

mm/internal.h

@@ -1842,6 +1842,7 @@ int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm);
 int remap_pfn_range_prepare(struct vm_area_desc *desc);
 int remap_pfn_range_complete(struct vm_area_struct *vma,
 			     struct mmap_action *action);
+int simple_ioremap_prepare(struct vm_area_desc *desc);
 
 static inline int io_remap_pfn_range_prepare(struct vm_area_desc *desc)
 {

mm/memory.c

@@ -3170,6 +3170,58 @@ int remap_pfn_range_complete(struct vm_area_struct *vma,
 	return do_remap_pfn_range(vma, start, pfn, size, prot);
 }
 
+static int __simple_ioremap_prep(unsigned long vm_len, pgoff_t vm_pgoff,
+				 phys_addr_t start_phys, unsigned long size,
+				 unsigned long *pfnp)
+{
+	unsigned long pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start_phys + size < start_phys)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	size += start_phys & ~PAGE_MASK;
+	pfn = start_phys >> PAGE_SHIFT;
+	pages = (size + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vm_pgoff;
+	pages -= vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	if ((vm_len >> PAGE_SHIFT) > pages)
+		return -EINVAL;
+
+	*pfnp = pfn;
+	return 0;
+}
+
+int simple_ioremap_prepare(struct vm_area_desc *desc)
+{
+	struct mmap_action *action = &desc->action;
+	const phys_addr_t start = action->simple_ioremap.start_phys_addr;
+	const unsigned long size = action->simple_ioremap.size;
+	unsigned long pfn;
+	int err;
+
+	err = __simple_ioremap_prep(vma_desc_size(desc), desc->pgoff,
+				    start, size, &pfn);
+	if (err)
+		return err;
+
+	/* The I/O remap logic does the heavy lifting. */
+	mmap_action_ioremap_full(desc, pfn);
+	return io_remap_pfn_range_prepare(desc);
+}
+
 /**
  * vm_iomap_memory - remap memory to userspace
  * @vma: user vma to map to
@@ -3187,32 +3239,15 @@ int remap_pfn_range_complete(struct vm_area_struct *vma,
  */
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
 {
-	unsigned long vm_len, pfn, pages;
+	const unsigned long vm_start = vma->vm_start;
+	const unsigned long vm_end = vma->vm_end;
+	const unsigned long vm_len = vm_end - vm_start;
+	unsigned long pfn;
+	int err;
 
-	/* Check that the physical memory area passed in looks valid */
-	if (start + len < start)
-		return -EINVAL;
-	/*
-	 * You *really* shouldn't map things that aren't page-aligned,
-	 * but we've historically allowed it because IO memory might
-	 * just have smaller alignment.
-	 */
-	len += start & ~PAGE_MASK;
-	pfn = start >> PAGE_SHIFT;
-	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
-	if (pfn + pages < pfn)
-		return -EINVAL;
-
-	/* We start the mapping 'vm_pgoff' pages into the area */
-	if (vma->vm_pgoff > pages)
-		return -EINVAL;
-	pfn += vma->vm_pgoff;
-	pages -= vma->vm_pgoff;
-
-	/* Can we fit all of the mapping? */
-	vm_len = vma->vm_end - vma->vm_start;
-	if (vm_len >> PAGE_SHIFT > pages)
-		return -EINVAL;
+	err = __simple_ioremap_prep(vm_len, vma->vm_pgoff, start, len, &pfn);
+	if (err)
+		return err;
 
 	/* Ok, let it rip */
 	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);

mm/util.c

@@ -1393,6 +1393,8 @@ int mmap_action_prepare(struct vm_area_desc *desc)
 		return remap_pfn_range_prepare(desc);
 	case MMAP_IO_REMAP_PFN:
 		return io_remap_pfn_range_prepare(desc);
+	case MMAP_SIMPLE_IO_REMAP:
+		return simple_ioremap_prepare(desc);
 	}
 
 	WARN_ON_ONCE(1);
@@ -1421,6 +1423,7 @@ int mmap_action_complete(struct vm_area_struct *vma,
 		err = remap_pfn_range_complete(vma, action);
 		break;
 	case MMAP_IO_REMAP_PFN:
+	case MMAP_SIMPLE_IO_REMAP:
 		/* Should have been delegated. */
 		WARN_ON_ONCE(1);
 		err = -EINVAL;
@@ -1438,6 +1441,7 @@ int mmap_action_prepare(struct vm_area_desc *desc)
 		break;
 	case MMAP_REMAP_PFN:
 	case MMAP_IO_REMAP_PFN:
+	case MMAP_SIMPLE_IO_REMAP:
 		WARN_ON_ONCE(1); /* nommu cannot handle these. */
 		break;
 	}
@@ -1456,6 +1460,7 @@ int mmap_action_complete(struct vm_area_struct *vma,
 		break;
 	case MMAP_REMAP_PFN:
 	case MMAP_IO_REMAP_PFN:
+	case MMAP_SIMPLE_IO_REMAP:
 		WARN_ON_ONCE(1); /* nommu cannot handle this. */
 
 		err = -EINVAL;

tools/testing/vma/include/dup.h

@@ -453,6 +453,7 @@ enum mmap_action_type {
 	MMAP_NOTHING,		/* Mapping is complete, no further action. */
 	MMAP_REMAP_PFN,		/* Remap PFN range. */
 	MMAP_IO_REMAP_PFN,	/* I/O remap PFN range. */
+	MMAP_SIMPLE_IO_REMAP,	/* I/O remap with guardrails. */
 };
 
 /*
@@ -461,13 +462,16 @@ enum mmap_action_type {
  */
 struct mmap_action {
 	union {
-		/* Remap range. */
 		struct {
 			unsigned long start;
 			unsigned long start_pfn;
 			unsigned long size;
 			pgprot_t pgprot;
 		} remap;
+		struct {
+			phys_addr_t start_phys_addr;
+			unsigned long size;
+		} simple_ioremap;
 	};
 	enum mmap_action_type type;