[PATCH v3 5/6] vdso/datastore: Allow prefaulting by mlockall()

[Thomas Weißschuh]

While mlockall() is meant to lock page *memory*, effectively it will
also create and lock the corresponding page table entries.
Latency-sensitive applications expect not to experience any pagefaults
after calling mlockall(). However mlockall() ignores VM_IO mappings,
which is used by the generic vDSO datastore.
While the fault handler itself is very fast, going through the full
pagefault exception handling is much slower, on the order of 20us in a
test machine.

Since the memory behind the datastore mappings is always present and
accessible it is not necessary to use VM_IO for them.

The data page mapping is now also aligned with the architecture-specific
code pages. Some architecture-specific data pages, like the x86 VCLOCK
pages, continue to use VM_IO as they are not always mappable. They will
require their own special handling later when the general aproach has
been agreed upon.

Regular mlock() would also work, but userspace does not know the boundaries
of the vDSO.

Reported-by: Nam Cao <namcao@xxxxxxxxxxxxx>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@xxxxxxxxxxxxx>
Tested-by: Nam Cao <namcao@xxxxxxxxxxxxx>
---
 lib/vdso/datastore.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
index 3381ccf9edb1..3f837cb6a886 100644
--- a/lib/vdso/datastore.c
+++ b/lib/vdso/datastore.c
@@ -125,7 +125,7 @@ const struct vm_special_mapping vdso_vvar_mapping = {
 struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr)
 {
 	return _install_special_mapping(mm, addr, VDSO_NR_PAGES * PAGE_SIZE,
-					VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP |
+					VM_READ | VM_MAYREAD | VM_DONTDUMP |
 					VM_MIXEDMAP | VM_SEALED_SYSMAP,
 					&vdso_vvar_mapping);
 }

-- 
2.53.0