On 6/2/2021 5:46 PM, Hugh Dickins wrote
It's do_anonymous_page()'s business to map in the zero page on
read fault (see "my_zero_pfn(vmf->address)" in there), or fill
a freshly allocated page with zeroes on write fault - and now
you're sticking to MAP_PRIVATE, write faults in VM_WRITE areas
are okay for VM_NOSIGBUS.
Ideally you can simply call do_anonymous_page() from __do_fault()
in the VM_FAULT_SIGBUS on VM_NOSIGBUS case. That's what to start
from anyway: but look to see if there's state to be adjusted to
achieve that; and it won't be surprising if somewhere down in
do_anonymous_page() or something it calls, there's a BUG on it
being called when vma->vm_file is set, or something like that.
May need some tweaking.
do_anonymous_page() works nicely for read fault and write fault.
I didn't see any BUG() thing in my test.
But I'm still struggling with how to do "punch hole should remove the mapping of zero page".
Here is the hack I have now.
diff --git a/mm/memory.c b/mm/memory.c
index 46ecda5..6b5a897 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1241,7 +1241,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct page *page;
page = vm_normal_page(vma, addr, ptent);
- if (unlikely(details) && page) {
+ if (unlikely(details) && page && !(vma->vm_flags & VM_NOSIGBUS)) {
/*
* unmap_shared_mapping_pages() wants to
* invalidate cache without truncating:
And other parts of the patch is following,
----
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e9d67bc..af9e277 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -373,6 +373,8 @@ int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
# define VM_UFFD_MINOR VM_NONE
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+#define VM_NOSIGBUS VM_FLAGS_BIT(38) /* Do not SIGBUS on fault */
+
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ)
diff --git a/include/linux/mman.h b/include/linux/mman.h
index b2cbae9..c966b08 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -154,6 +154,7 @@ static inline bool arch_validate_flags(unsigned long flags)
_calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) |
_calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) |
_calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) |
+ _calc_vm_trans(flags, MAP_NOSIGBUS, VM_NOSIGBUS ) |
arch_calc_vm_flag_bits(flags);
}
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index f94f65d..a2a5333 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -29,6 +29,7 @@
#define MAP_HUGETLB 0x040000 /* create a huge page mapping */
#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */
#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */
+#define MAP_NOSIGBUS 0x200000 /* do not SIGBUS on fault */
#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be
* uninitialized */
diff --git a/mm/memory.c b/mm/memory.c
index eff2a47..46ecda5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3676,6 +3676,17 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
}
ret = vma->vm_ops->fault(vmf);
+ if (unlikely(ret & VM_FAULT_SIGBUS) && (vma->vm_flags & VM_NOSIGBUS)) {
+ /*
+ * For MAP_NOSIGBUS mapping, map in the zero page on read fault
+ * or fill a freshly allocated page with zeroes on write fault
+ */
+ ret = do_anonymous_page(vmf);
+ if (!ret)
+ ret = VM_FAULT_NOPAGE;
+ return ret;
+ }
+
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
VM_FAULT_DONE_COW)))
return ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 096bba4..74fb49a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1419,6 +1419,10 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
if (!len)
return -EINVAL;
+ /* Restrict MAP_NOSIGBUS to MAP_PRIVATE mapping */
+ if ((flags & MAP_NOSIGBUS) && !(flags & MAP_PRIVATE))
+ return -EINVAL;
+
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
*
