[PATCH 5.4.y 4/4] mm: add remap_pfn_range_notrack

[Harshvardhan Jha <harshvardhan.j.jha@oracle.com>]

From: Christoph Hellwig <hch@lst.de>

commit 74ffa5a3e68504dd289135b1cf0422c19ffb3f2e upstream.

Patch series "add remap_pfn_range_notrack instead of reinventing it in i915", v2.

i915 has some reason to want to avoid the track_pfn_remap overhead in
remap_pfn_range.  Add a function to the core VM to do just that rather
than reinventing the functionality poorly in the driver.

Note that the remap_io_sg path does get exercises when using Xorg on my
Thinkpad X1, so this should be considered lightly tested, I've not managed
to hit the remap_io_mapping path at all.

This patch (of 4):

Add a version of remap_pfn_range that does not call track_pfn_range.  This
will be used to fix horrible abuses of VM internals in the i915 driver.

Link: https://lkml.kernel.org/r/20210326055505.1424432-1-hch@lst.de
Link: https://lkml.kernel.org/r/20210326055505.1424432-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Harshvardhan Jha <harshvardhan.j.jha@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 69d4e1ce9087c8767f2fe9b9426fa2755c8e9072)
Signed-off-by: Harshvardhan Jha <harshvardhan.j.jha@oracle.com>
---
 include/linux/mm.h |  2 ++
 mm/memory.c        | 51 ++++++++++++++++++++++++++++------------------
 2 files changed, 33 insertions(+), 20 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d14aba548ff4e..4d3657b630dba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2566,6 +2566,8 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 struct vm_area_struct *find_extend_vma(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 vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
 				unsigned long num);
diff --git a/mm/memory.c b/mm/memory.c
index 1d009d3d87b34..fc7454cc138b6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1917,26 +1917,17 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 	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.
+/*
+ * 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(struct vm_area_struct *vma, unsigned long addr,
-		    unsigned long pfn, unsigned long size, pgprot_t prot)
+int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+		unsigned long pfn, unsigned long size, pgprot_t prot)
 {
 	pgd_t *pgd;
 	unsigned long next;
 	unsigned long end = addr + PAGE_ALIGN(size);
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long remap_pfn = pfn;
 	int err;
 
 	if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
@@ -1966,10 +1957,6 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		vma->vm_pgoff = pfn;
 	}
 
-	err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size));
-	if (err)
-		return -EINVAL;
-
 	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
 
 	BUG_ON(addr >= end);
@@ -1981,12 +1968,36 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		err = remap_p4d_range(mm, pgd, addr, next,
 				pfn + (addr >> PAGE_SHIFT), prot);
 		if (err)
-			break;
+			return err;
 	} while (pgd++, addr = next, addr != end);
 
+	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 = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
 	if (err)
-		untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size));
+		return -EINVAL;
 
+	err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
+	if (err)
+		untrack_pfn(vma, pfn, PAGE_ALIGN(size));
 	return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);
-- 
2.46.0