Re: KVM Test result, kernel ff5bdac.., userspace eb2fd67.. -- One New Issue

[john cooper <john.cooper@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 600 bytes --]

Marcelo Tosatti wrote:
>
> This is a get_user_pages() with hugetlb-vma's bug, not KVM's problem,
> fixed by:
>
> commit 5b23dbe8173c212d6a326e35347b038705603d39
> Author: Adam Litke <agl@us.ibm.com>
> Date:   Wed Nov 14 16:59:33 2007 -0800
I'd say so. Just to close the loop here, attached is a trivial
patch gleaned from 2.6.25 which is relative to 2.6.23.9 fc8 where
I'd reproduced the issue. It dismisses the BIOS identify
problem and gets the guest through a full userland init (without
the earlier bandaid of mapping the first 2MB of physmem with 4KB
pages).

-john

-- 
john.cooper@redhat.com


[-- Attachment #2: kvm-1941302.diff --]
[-- Type: text/x-patch, Size: 2824 bytes --]

 include/linux/hugetlb.h |    4 ++--
 mm/hugetlb.c            |    7 ++++---
 mm/memory.c             |    2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)
=================================================================
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -19,7 +19,7 @@ static inline int is_vm_hugetlb_page(str
 int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
-int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
+int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int, int);
 void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
@@ -105,7 +105,7 @@ static inline unsigned long hugetlb_tota
 	return 0;
 }
 
-#define follow_hugetlb_page(m,v,p,vs,a,b,i)	({ BUG(); 0; })
+#define follow_hugetlb_page(m,v,p,vs,a,b,i,w)	({ BUG(); 0; })
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
=================================================================
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1039,7 +1039,7 @@ int get_user_pages(struct task_struct *t
 
 		if (is_vm_hugetlb_page(vma)) {
 			i = follow_hugetlb_page(mm, vma, pages, vmas,
-						&start, &len, i);
+						&start, &len, i, write);
 			continue;
 		}
 
=================================================================
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -621,7 +621,8 @@ int hugetlb_fault(struct mm_struct *mm, 
 
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			struct page **pages, struct vm_area_struct **vmas,
-			unsigned long *position, int *length, int i)
+			unsigned long *position, int *length, int i,
+			int write)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
@@ -639,11 +640,11 @@ int follow_hugetlb_page(struct mm_struct
 		 */
 		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-		if (!pte || pte_none(*pte)) {
+		if (!pte || pte_none(*pte) || (write && !pte_write(*pte))) {
 			int ret;
 
 			spin_unlock(&mm->page_table_lock);
-			ret = hugetlb_fault(mm, vma, vaddr, 0);
+			ret = hugetlb_fault(mm, vma, vaddr, write);
 			spin_lock(&mm->page_table_lock);
 			if (!(ret & VM_FAULT_ERROR))
 				continue;