mm: add remap_pfn_range_prepare(), remap_pfn_range_complete()

We need the ability to split PFN remap between updating the VMA and
performing the actual remap, in order to do away with the legacy f_op->mmap
hook.

To do so, update the PFN remap code to provide shared logic, and also make
remap_pfn_range_notrack() static, as its one user, io_mapping_map_user()
was removed in commit 9a4f90e246 ("mm: remove mm/io-mapping.c").

Then, introduce remap_pfn_range_prepare(), which accepts VMA descriptor
and PFN parameters, and remap_pfn_range_complete() which accepts the same
parameters as remap_pfn_rangte().

remap_pfn_range_prepare() will set the cow vma->vm_pgoff if necessary, so
it must be supplied with a correct PFN to do so.

While we're here, also clean up the duplicated #ifdef
__HAVE_PFNMAP_TRACKING check and put into a single #ifdef/#else block.

We keep these internal to mm as they should only be used by internal
helpers.

Link: https://lkml.kernel.org/r/75b55de63249b3aa0fd5b3b08ed1d3ff19255d0d.1760959442.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Pedro Falcato <pfalcato@suse.de>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chatre, Reinette <reinette.chatre@intel.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dave Martin <dave.martin@arm.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Morse <james.morse@arm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Robin Murohy <robin.murphy@arm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -489,6 +489,21 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/*
+ * Physically remapped pages are special. Tell the
+ * rest of the world about it:
+ *   VM_IO tells people not to look at these pages
+ *	(accesses can have side effects).
+ *   VM_PFNMAP tells the core MM that the base pages are just
+ *	raw PFN mappings, and do not have a "struct page" associated
+ *	with them.
+ *   VM_DONTEXPAND
+ *      Disable vma merging and expanding with mremap().
+ *   VM_DONTDUMP
+ *      Omit vma from core dump, even when VM_IO turned off.
+ */
+#define VM_REMAP_FLAGS (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP)
+
 /* This mask prevents VMA from being scanned with khugepaged */
 #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
 
@@ -3634,10 +3649,9 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 
 struct vm_area_struct *find_extend_vma_locked(struct mm_struct *,
 		unsigned long addr);
-int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
-			unsigned long pfn, unsigned long size, pgprot_t);
-int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
-		unsigned long pfn, unsigned long size, pgprot_t prot);
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		    unsigned long pfn, unsigned long size, pgprot_t pgprot);
+
 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);

mm/internal.h

@@ -1677,4 +1677,8 @@ static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
 void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm);
 int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm);
 
+void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn);
+int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t pgprot);
+
 #endif	/* __MM_INTERNAL_H */

mm/memory.c

@@ -2900,6 +2900,25 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 	return 0;
 }
 
+static int get_remap_pgoff(vm_flags_t vm_flags, unsigned long addr,
+		unsigned long end, unsigned long vm_start, unsigned long vm_end,
+		unsigned long pfn, pgoff_t *vm_pgoff_p)
+{
+	/*
+	 * There's a horrible special case to handle copy-on-write
+	 * behaviour that some programs depend on. We mark the "original"
+	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
+	 * See vm_normal_page() for details.
+	 */
+	if (is_cow_mapping(vm_flags)) {
+		if (addr != vm_start || end != vm_end)
+			return -EINVAL;
+		*vm_pgoff_p = pfn;
+	}
+
+	return 0;
+}
+
 static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr,
 		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
@@ -2912,31 +2931,7 @@ static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long ad
 	if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
 		return -EINVAL;
 
-	/*
-	 * Physically remapped pages are special. Tell the
-	 * rest of the world about it:
-	 *   VM_IO tells people not to look at these pages
-	 *	(accesses can have side effects).
-	 *   VM_PFNMAP tells the core MM that the base pages are just
-	 *	raw PFN mappings, and do not have a "struct page" associated
-	 *	with them.
-	 *   VM_DONTEXPAND
-	 *      Disable vma merging and expanding with mremap().
-	 *   VM_DONTDUMP
-	 *      Omit vma from core dump, even when VM_IO turned off.
-	 *
-	 * There's a horrible special case to handle copy-on-write
-	 * behaviour that some programs depend on. We mark the "original"
-	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
-	 * See vm_normal_page() for details.
-	 */
-	if (is_cow_mapping(vma->vm_flags)) {
-		if (addr != vma->vm_start || end != vma->vm_end)
-			return -EINVAL;
-		vma->vm_pgoff = pfn;
-	}
-
-	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+	VM_WARN_ON_ONCE((vma->vm_flags & VM_REMAP_FLAGS) != VM_REMAP_FLAGS);
 
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;
@@ -2957,7 +2952,7 @@ static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long ad
  * Variant of remap_pfn_range that does not call track_pfn_remap.  The caller
  * must have pre-validated the caching bits of the pgprot_t.
  */
-int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+static int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
 		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
 	int error = remap_pfn_range_internal(vma, addr, pfn, size, prot);
@@ -3002,23 +2997,9 @@ void pfnmap_track_ctx_release(struct kref *ref)
 	pfnmap_untrack(ctx->pfn, ctx->size);
 	kfree(ctx);
 }
-#endif /* __HAVE_PFNMAP_TRACKING */
 
-/**
- * remap_pfn_range - remap kernel memory to userspace
- * @vma: user vma to map to
- * @addr: target page aligned user address to start at
- * @pfn: page frame number of kernel physical memory address
- * @size: size of mapping area
- * @prot: page protection flags for this mapping
- *
- * Note: this is only safe if the mm semaphore is held when called.
- *
- * Return: %0 on success, negative error code otherwise.
- */
-#ifdef __HAVE_PFNMAP_TRACKING
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
-		    unsigned long pfn, unsigned long size, pgprot_t prot)
+static int remap_pfn_range_track(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
 	struct pfnmap_track_ctx *ctx = NULL;
 	int err;
@@ -3054,15 +3035,78 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	return err;
 }
 
+static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range_track(vma, addr, pfn, size, prot);
+}
 #else
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
-		    unsigned long pfn, unsigned long size, pgprot_t prot)
+static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
 	return remap_pfn_range_notrack(vma, addr, pfn, size, prot);
 }
 #endif
+
+void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn)
+{
+	/*
+	 * We set addr=VMA start, end=VMA end here, so this won't fail, but we
+	 * check it again on complete and will fail there if specified addr is
+	 * invalid.
+	 */
+	get_remap_pgoff(desc->vm_flags, desc->start, desc->end,
+			desc->start, desc->end, pfn, &desc->pgoff);
+	desc->vm_flags |= VM_REMAP_FLAGS;
+}
+
+static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size)
+{
+	unsigned long end = addr + PAGE_ALIGN(size);
+	int err;
+
+	err = get_remap_pgoff(vma->vm_flags, addr, end,
+			      vma->vm_start, vma->vm_end,
+			      pfn, &vma->vm_pgoff);
+	if (err)
+		return err;
+
+	vm_flags_set(vma, VM_REMAP_FLAGS);
+	return 0;
+}
+
+/**
+ * remap_pfn_range - remap kernel memory to userspace
+ * @vma: user vma to map to
+ * @addr: target page aligned user address to start at
+ * @pfn: page frame number of kernel physical memory address
+ * @size: size of mapping area
+ * @prot: page protection flags for this mapping
+ *
+ * Note: this is only safe if the mm semaphore is held when called.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		    unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	int err;
+
+	err = remap_pfn_range_prepare_vma(vma, addr, pfn, size);
+	if (err)
+		return err;
+
+	return do_remap_pfn_range(vma, addr, pfn, size, prot);
+}
 EXPORT_SYMBOL(remap_pfn_range);
 
+int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	return do_remap_pfn_range(vma, addr, pfn, size, prot);
+}
+
 /**
  * vm_iomap_memory - remap memory to userspace
  * @vma: user vma to map to