[PATCH v10] mm, hugetlbfs: Allow for "high" userspace addresses

[Christophe Leroy]

This is a fix for commit f6795053dac8 ("mm: mmap: Allow for "high"
userspace addresses") for hugetlb.

This patch adds support for "high" userspace addresses that are
optionally supported on the system and have to be requested via a hint
mechanism ("high" addr parameter to mmap).

Architectures such as powerpc and x86 achieve this by making changes to
their architectural versions of hugetlb_get_unmapped_area() function.
However, arm64 uses the generic version of that function.

So take into account arch_get_mmap_base() and arch_get_mmap_end() in
hugetlb_get_unmapped_area(). To allow that, move those two macros
out of mm/mmap.c into include/linux/sched/mm.h

If these macros are not defined in architectural code then they default
to (TASK_SIZE) and (base) so should not introduce any behavioural
changes to architectures that do not define them.

For the time being, only ARM64 is affected by this change.

>From Catalin (ARM64):
  We should have fixed hugetlb_get_unmapped_area() as well when we
added support for 52-bit VA. The reason for commit f6795053dac8 was to
prevent normal mmap() from returning addresses above 48-bit by default
as some user-space had hard assumptions about this.

It's a slight ABI change if you do this for hugetlb_get_unmapped_area()
but I doubt anyone would notice. It's more likely that the current
behaviour would cause issues, so I'd rather have them consistent.

Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Steve Capper <steve.capper@xxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Fixes: f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses")
Cc: <stable@xxxxxxxxxxxxxxx> # 5.0.x
Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Acked-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Resending the patch as standalone so that is can be merged via mm tree in 5.18 and stable.

v10:
- Moved as first patch of the series so that it can be applied
separately as a flag and be easily applied back on stable.
- Added text from Catalin explaining why it is a fixup.
---
 fs/hugetlbfs/inode.c     | 9 +++++----
 include/linux/sched/mm.h | 8 ++++++++
 mm/mmap.c                | 8 --------
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 99c7477cee5c..dd3a088db11d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = current->mm->mmap_base;
-	info.high_limit = TASK_SIZE;
+	info.high_limit = arch_get_mmap_end(addr);
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	return vm_unmapped_area(&info);
@@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
 	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
-	info.high_limit = current->mm->mmap_base;
+	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
@@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
 		VM_BUG_ON(addr != -ENOMEM);
 		info.flags = 0;
 		info.low_limit = current->mm->mmap_base;
-		info.high_limit = TASK_SIZE;
+		info.high_limit = arch_get_mmap_end(addr);
 		addr = vm_unmapped_area(&info);
 	}
 
@@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct hstate *h = hstate_file(file);
+	const unsigned long mmap_end = arch_get_mmap_end(addr);
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
@@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (addr) {
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (mmap_end - len >= addr &&
 		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a80356e9dc69..1ad1f4bfa025 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 #endif /* CONFIG_MEMCG */
 
 #ifdef CONFIG_MMU
+#ifndef arch_get_mmap_end
+#define arch_get_mmap_end(addr)	(TASK_SIZE)
+#endif
+
+#ifndef arch_get_mmap_base
+#define arch_get_mmap_base(addr, base) (base)
+#endif
+
 extern void arch_pick_mmap_layout(struct mm_struct *mm,
 				  struct rlimit *rlim_stack);
 extern unsigned long
diff --git a/mm/mmap.c b/mm/mmap.c
index 3aa839f81e63..313b57d55a63 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
 	return addr;
 }
 
-#ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr)	(TASK_SIZE)
-#endif
-
-#ifndef arch_get_mmap_base
-#define arch_get_mmap_base(addr, base) (base)
-#endif
-
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
  *
-- 
2.35.1