The x86 vvar mapping contains pages with differing cacheability
flags. This is currently only supported using (io_)remap_pfn_range,
but those functions can't be used inside page faults.
Add vm_insert_pfn_prot to support varying cacheability within the
same non-COW VMA in a more sane manner.
x86 needs this to avoid a CRIU-breaking and memory-wasting explosion
of VMAs when supporting userspace access to the HPET.
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
include/linux/mm.h | 2 ++
mm/memory.c | 25 +++++++++++++++++++++++--
2 files changed, 25 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 00bad7793788..87ef1d7730ba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2080,6 +2080,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
diff --git a/mm/memory.c b/mm/memory.c
index c387430f06c3..a29f0b90fc56 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1564,8 +1564,29 @@ out:
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
+ return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings. In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot)
+{
int ret;
- pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
@@ -1587,7 +1608,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
return ret;
}
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
--
2.5.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>